### Summary
After #7022, we no longer need this warning. We should also clean up the
schema for the notification, but this is a quick fix to just stop the
behavior in the VSCE
## Testing
- [x] Ran locally
Previously, we were running into an issue where we would run the `shell`
tool call with a timeout of 10s, but it fired an elicitation asking for
user approval, the time the user took to respond to the elicitation was
counted agains the 10s timeout, so the `shell` tool call would fail with
a timeout error unless the user is very fast!
This PR addresses this issue by introducing a "stopwatch" abstraction
that is used to manage the timeout. The idea is:
- `Stopwatch::new()` is called with the _real_ timeout of the `shell`
tool call.
- `process_exec_tool_call()` is called with the `Cancellation` variant
of `ExecExpiration` because it should not manage its own timeout in this
case
- the `Stopwatch` expiration is wired up to the `cancel_rx` passed to
`process_exec_tool_call()`
- when an elicitation for the `shell` tool call is received, the
`Stopwatch` pauses
- because it is possible for multiple elicitations to arrive
concurrently, it keeps track of the number of "active pauses" and does
not resume until that counter goes down to zero
I verified that I can test the MCP server using
`@modelcontextprotocol/inspector` and specify `git status` as the
`command` with a timeout of 500ms and that the elicitation pops up and I
have all the time in the world to respond whereas previous to this PR,
that would not have been possible.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/6973).
* #7005
* __->__ #6973
* #6972
This updates `ExecParams` so that instead of taking `timeout_ms:
Option<u64>`, it now takes a more general cancellation mechanism,
`ExecExpiration`, which is an enum that includes a
`Cancellation(tokio_util::sync::CancellationToken)` variant.
If the cancellation token is fired, then `process_exec_tool_call()`
returns in the same way as if a timeout was exceeded.
This is necessary so that in #6973, we can manage the timeout logic
external to the `process_exec_tool_call()` because we want to "suspend"
the timeout when an elicitation from a human user is pending.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/6972).
* #7005
* #6973
* __->__ #6972
- Use /bin/sh instead of /bin/bash on FreeBSD/OpenBSD in the process
group timeout test to avoid command-not-found failures.
- Accept /usr/local/bin/bash as a valid SHELL path to match common
FreeBSD installations.
- Switch the shell serialization duration test to /bin/sh for improved
portability across Unix platforms.
With this change, `cargo test -p codex-core --lib` runs and passes on
FreeBSD.
Our Restricted Token contains 3 SIDs (Logon, Everyone, {WorkspaceWrite
Capability || ReadOnly Capability})
because it must include Everyone, that left us vulnerable to directories
that allow writes to Everyone. Even though those directories do not have
ACEs that enable our capability SIDs to write to them, they could still
be written to even in ReadOnly mode, or even in WorkspaceWrite mode if
they are outside of a writable root.
A solution to this is to explicitly add *Deny* ACEs to these
directories, always for the ReadOnly Capability SID, and for the
WorkspaceWrite SID if the directory is outside of a workspace root.
Under a restricted token, Windows always checks Deny ACEs before Allow
ACEs so even though our restricted token would allow a write to these
directories due to the Everyone SID, it fails first because of the Deny
ACE on the capability SID
second attempt to fix this test after
https://github.com/openai/codex/pull/6884. I think this flakiness is
happening because yield_time is too small for a 10,000 step loop in
python.
adding execpolicycheck tool onto codex cli
this is useful for validating policies (can be multiple) against
commands.
it will also surface errors in policy syntax:
<img width="1150" height="281" alt="Screenshot 2025-11-19 at 12 46
21 PM"
src="https://github.com/user-attachments/assets/8f99b403-564c-4172-acc9-6574a8d13dc3"
/>
this PR also changes output format when there's no match in the CLI.
instead of returning the raw string `noMatch`, we return
`{"noMatch":{}}`
this PR is a rewrite of: https://github.com/openai/codex/pull/6932 (due
to the numerous merge conflicts present in the original PR)
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
setting user shell timeout to an unreasonably high value since there
isn't an easy way to have a command run without timeouts
currently, user shell commands timeout is 10 seconds
## Summary
- TUI feedback note now only links to the bug-report template when the
category is bug/bad result.
- Good result/other feedback shows a thank-you+thread ID instead of
funneling people to file a bug.
- Added a helper + unit test so future changes keep the behavior
consistent.
## Testing
- just fmt
- just fix -p codex-tui
- cargo test -p codex-tui
Fixes#6839
### Description
- codex exec --json resume --last "<prompt>" bailed out because clap
treated the prompt as SESSION_ID. I removed the conflicts_with flag and
reinterpret that positional as a prompt when
--last is set, so the flow now keeps working in JSON mode.
(codex-rs/exec/src/cli.rs:84-104, codex-rs/exec/src/lib.rs:75-130)
- Added a regression test that exercises resume --last in JSON mode to
ensure the prompt is accepted and the rollout file is updated.
(codex-rs/exec/tests/suite/resume.rs:126-178)
### Testing
- just fmt
- cargo test -p codex-exec
- just fix -p codex-exec
- cargo test -p codex-exec
#6717
Signed-off-by: Dmitri Khokhlov <dkhokhlov@cribl.io>
## Summary
- add an explicit `override_usage` string to `AddArgs` so clap prints
`<NAME>` before the command/url choice, matching the actual parser and
docs
### Before
Usage: codex mcp add [OPTIONS] <COMMAND|--url <URL>> <NAME>
### After
Usage: codex mcp add [OPTIONS] <NAME> [--url <URL> | -- <COMMAND>...]
---------
Signed-off-by: kyuheon-kr <kyuheon.kr@gmail.com>
## 🐛 Problem
Users running commands with non-ASCII characters (like Russian text
"пример") in Windows/WSL environments experience garbled text in
VSCode's shell preview window, with Unicode replacement characters (�)
appearing instead of the actual text.
**Issue**: https://github.com/openai/codex/issues/6178
## 🔧 Root Cause
The issue was in `StreamOutput<Vec<u8>>::from_utf8_lossy()` method in
`codex-rs/core/src/exec.rs`, which used `String::from_utf8_lossy()` to
convert shell output bytes to strings. This function immediately
replaces any invalid UTF-8 byte sequences with replacement characters,
without attempting to decode using other common encodings.
In Windows/WSL environments, shell output often uses encodings like:
- Windows-1252 (common Windows encoding)
- Latin-1/ISO-8859-1 (extended ASCII)
## 🛠️ Solution
Replaced the simple `String::from_utf8_lossy()` call with intelligent
encoding detection via a new `bytes_to_string_smart()` function that
tries multiple encoding strategies:
1. **UTF-8** (fast path for valid UTF-8)
2. **Windows-1252** (handles Windows-specific characters in 0x80-0x9F
range)
3. **Latin-1** (fallback for extended ASCII)
4. **Lossy UTF-8** (final fallback, same as before)
## 📁 Changes
### New Files
- `codex-rs/core/src/text_encoding.rs` - Smart encoding detection module
- `codex-rs/core/tests/suite/text_encoding_fix.rs` - Integration tests
### Modified Files
- `codex-rs/core/src/lib.rs` - Added text_encoding module
- `codex-rs/core/src/exec.rs` - Updated StreamOutput::from_utf8_lossy()
- `codex-rs/core/tests/suite/mod.rs` - Registered new test module
## ✅ Testing
- **5 unit tests** covering UTF-8, Windows-1252, Latin-1, and fallback
scenarios
- **2 integration tests** simulating the exact Issue #6178 scenario
- **Demonstrates improvement** over the previous
`String::from_utf8_lossy()` approach
All tests pass:
```bash
cargo test -p codex-core text_encoding
cargo test -p codex-core test_shell_output_encoding_issue_6178
```
## 🎯 Impact
- ✅ **Eliminates garbled text** in VSCode shell preview for non-ASCII
content
- ✅ **Supports Windows/WSL environments** with proper encoding detection
- ✅ **Zero performance impact** for UTF-8 text (fast path)
- ✅ **Backward compatible** - UTF-8 content works exactly as before
- ✅ **Handles edge cases** with robust fallback mechanism
## 🧪 Test Scenarios
The fix has been tested with:
- Russian text ("пример")
- Windows-1252 quotation marks (""test")
- Latin-1 accented characters ("café")
- Mixed encoding content
- Invalid byte sequences (graceful fallback)
## 📋 Checklist
- [X] Addresses the reported issue
- [X] Includes comprehensive tests
- [X] Maintains backward compatibility
- [X] Follows project coding conventions
- [X] No breaking changes
---------
Co-authored-by: Josh McKinney <joshka@openai.com>
This PR adds support for a new feature flag `tui.animations`. By
default, the TUI uses animations in its welcome screen, "working"
spinners, and "shimmer" effects. This animations can interfere with
screen readers, so it's good to provide a way to disable them.
This change is inspired by [a
PR](https://github.com/openai/codex/pull/4014) contributed by @Orinks.
That PR has faltered a bit, but I think the core idea is sound. This
version incorporates feedback from @aibrahim-oai. In particular:
1. It uses a feature flag (`tui.animations`) rather than the unqualified
CLI key `no-animations`. Feature flags are the preferred way to expose
boolean switches. They are also exposed via CLI command switches.
2. It includes more complete documentation.
3. It disables a few animations that the other PR omitted.
Thread through an `exit_notify` tokio `Notify` through to the
`UnifiedExecSession` so that we can return early if the command
terminates before `yield_time_ms`.
As Codex review correctly pointed out below 🙌 we also need a
`exit_signaled` flag so that commands which finish before we start
waiting can also exit early.
Since the default `yield_time_ms` is now 10s, this means that we don't
have to wait 10s for trivial commands like ls, sed, etc (which are the
majority of agent commands 😅)
---------
Co-authored-by: jif-oai <jif@openai.com>
This PR adds the API V2 version of the apply_patch approval flow, which
centers around `ThreadItem::FileChange`.
This PR wires the new RPC (`item/fileChange/requestApproval`, V2 only)
and related events (`item/started`, `item/completed` for
`ThreadItem::FileChange`, which are emitted in both V1 and V2) through
the app-server
protocol. The new approval RPC is only sent when the user initiates a
turn with the new `turn/start` API so we don't break backwards
compatibility with VSCE.
Similar to https://github.com/openai/codex/pull/6758, the approach I
took was to make as few changes to the Codex core as possible,
leveraging existing `EventMsg` core events, and translating those in
app-server. I did have to add a few additional fields to
`EventMsg::PatchApplyBegin` and `EventMsg::PatchApplyEnd`, but those
were fairly lightweight.
However, the `EventMsg`s emitted by core are the following:
```
1) Auto-approved (no request for approval)
- EventMsg::PatchApplyBegin
- EventMsg::PatchApplyEnd
2) Approved by user
- EventMsg::ApplyPatchApprovalRequest
- EventMsg::PatchApplyBegin
- EventMsg::PatchApplyEnd
3) Declined by user
- EventMsg::ApplyPatchApprovalRequest
- EventMsg::PatchApplyBegin
- EventMsg::PatchApplyEnd
```
For a request triggering an approval, this would result in:
```
item/fileChange/requestApproval
item/started
item/completed
```
which is different from the `ThreadItem::CommandExecution` flow
introduced in https://github.com/openai/codex/pull/6758, which does the
below and is preferable:
```
item/started
item/commandExecution/requestApproval
item/completed
```
To fix this, we leverage `TurnSummaryStore` on codex_message_processor
to store a little bit of state, allowing us to fire `item/started` and
`item/fileChange/requestApproval` whenever we receive the underlying
`EventMsg::ApplyPatchApprovalRequest`, and no-oping when we receive the
`EventMsg::PatchApplyBegin` later.
This is much less invasive than modifying the order of EventMsg within
core (I tried).
The resulting payloads:
```
{
"method": "item/started",
"params": {
"item": {
"changes": [
{
"diff": "Hello from Codex!\n",
"kind": "add",
"path": "/Users/owen/repos/codex/codex-rs/APPROVAL_DEMO.txt"
}
],
"id": "call_Nxnwj7B3YXigfV6Mwh03d686",
"status": "inProgress",
"type": "fileChange"
}
}
}
```
```
{
"id": 0,
"method": "item/fileChange/requestApproval",
"params": {
"grantRoot": null,
"itemId": "call_Nxnwj7B3YXigfV6Mwh03d686",
"reason": null,
"threadId": "019a9e11-8295-7883-a283-779e06502c6f",
"turnId": "1"
}
}
```
```
{
"id": 0,
"result": {
"decision": "accept"
}
}
```
```
{
"method": "item/completed",
"params": {
"item": {
"changes": [
{
"diff": "Hello from Codex!\n",
"kind": "add",
"path": "/Users/owen/repos/codex/codex-rs/APPROVAL_DEMO.txt"
}
],
"id": "call_Nxnwj7B3YXigfV6Mwh03d686",
"status": "completed",
"type": "fileChange"
}
}
}
```
This reverts commit c2ec477d93.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
Include a link to a bug report or enhancement request.
This PR threads execpolicy2 into codex-core.
activated via feature flag: exec_policy (on by default)
reads and parses all .codexpolicy files in `codex_home/codex`
refactored tool runtime API to integrate execpolicy logic
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
This PR reorganizes things slightly so that:
- Instead of a single multitool executable, `codex-exec-server`, we now
have two executables:
- `codex-exec-mcp-server` to launch the MCP server
- `codex-execve-wrapper` is the `execve(2)` wrapper to use with the
`BASH_EXEC_WRAPPER` environment variable
- `BASH_EXEC_WRAPPER` must be a single executable: it cannot be a
command string composed of an executable with args (i.e., it no longer
adds the `escalate` subcommand, as before)
- `codex-exec-mcp-server` takes `--bash` and `--execve` as options.
Though if `--execve` is not specified, the MCP server will check the
directory containing `std::env::current_exe()` and attempt to use the
file named `codex-execve-wrapper` within it. In development, this works
out since these executables are side-by-side in the `target/debug`
folder.
With respect to testing, this also fixes an important bug in
`dummy_exec_policy()`, as I was using `ends_with()` as if it applied to
a `String`, but in this case, it is used with a `&Path`, so the
semantics are slightly different.
Putting this all together, I was able to test this by running the
following:
```
~/code/codex/codex-rs$ npx @modelcontextprotocol/inspector \
./target/debug/codex-exec-mcp-server --bash ~/code/bash/bash
```
If I try to run `git status` in `/Users/mbolin/code/codex` via the
`shell` tool from the MCP server:
<img width="1589" height="1335" alt="image"
src="https://github.com/user-attachments/assets/9db6aea8-7fbc-4675-8b1f-ec446685d6c4"
/>
then I get prompted with the following elicitation, as expected:
<img width="1589" height="1335" alt="image"
src="https://github.com/user-attachments/assets/21b68fe0-494d-4562-9bad-0ddc55fc846d"
/>
Though a current limitation is that the `shell` tool defaults to a
timeout of 10s, which means I only have 10s to respond to the
elicitation. Ideally, the time spent waiting for a response from a human
should not count against the timeout for the command execution. I will
address this in a subsequent PR.
---
Note `~/code/bash/bash` was created by doing:
```
cd ~/code
git clone https://github.com/bminor/bash
cd bash
git checkout a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
<apply the patch below>
./configure
make
```
The patch:
```
diff --git a/execute_cmd.c b/execute_cmd.c
index 070f5119..d20ad2b9 100644
--- a/execute_cmd.c
+++ b/execute_cmd.c
@@ -6129,6 +6129,19 @@ shell_execve (char *command, char **args, char **env)
char sample[HASH_BANG_BUFSIZ];
size_t larray;
+ char* exec_wrapper = getenv("BASH_EXEC_WRAPPER");
+ if (exec_wrapper && *exec_wrapper && !whitespace (*exec_wrapper))
+ {
+ char *orig_command = command;
+
+ larray = strvec_len (args);
+
+ memmove (args + 2, args, (++larray) * sizeof (char *));
+ args[0] = exec_wrapper;
+ args[1] = orig_command;
+ command = exec_wrapper;
+ }
+
```
This closes#6748 by implementing fallback to
`model_family.default_reasoning_effort` in `reasoning_effort` display of
`/status` when no `model_reasoning_effort` is set in the configuration.
## common/src/config_summary.rs
- `create_config_summary_entries` now fills the "reasoning effort" entry
with the explicit `config.model_reasoning_effort` when present and falls
back to `config.model_family.default_reasoning_effort` when it is
`None`, instead of emitting the literal string `none`.
- This ensures downstream consumers such as `tui/src/status/helpers.rs`
continue to work unchanged while automatically picking up model-family
defaults when the user has not selected a reasoning effort.
## tui/src/status/helpers.rs / core/src/model_family.rs
`ModelFamily::default_reasoning_effort` metadata is set to `medium` for
both `gpt-5*-codex` and `gpt-5` models following the default behaviour
of the API and recommendation of the codebase:
- per https://platform.openai.com/docs/api-reference/responses/create
`gpt-5` defaults to `medium` reasoning when no preset is passed
- there is no mention of the preset for `gpt-5.1-codex` in the API docs
but `medium` is the default setting for `gpt-5.1-codex` as per
`codex-rs/tui/src/chatwidget/snapshots/codex_tui__chatwidget__tests__model_reasoning_selection_popup.snap`
---------
Signed-off-by: lionelchg <lionel.cheng@hotmail.fr>
Co-authored-by: Eric Traut <etraut@openai.com>
## Summary
- show live review token usage while `/review` runs and restore the main
session indicator afterward
- add regression coverage for the footer behavior
## Testing
- just fmt
- cargo test -p codex-tui
Fixes#5604
---------
Signed-off-by: Fahad <fahad@2doapp.com>
Fix world-writable audit false positives by expanding generic
permissions with MapGenericMask and then checking only concrete write
bits. The earlier check looked for FILE_GENERIC_WRITE/generic masks
directly, which shares bits with read permissions and could flag an
Everyone read ACE as writable.
This PR introduces an extra layer of abstraction to prepare us for the
migration to execpolicy2:
- introduces a new trait, `EscalationPolicy`, whose `determine_action()`
method is responsible for producing the `EscalateAction`
- the existing `ExecPolicy` typedef is changed to return an intermediate
`ExecPolicyOutcome` instead of `EscalateAction`
- the default implementation of `EscalationPolicy`,
`McpEscalationPolicy`, composes `ExecPolicy`
- the `ExecPolicyOutcome` includes `codex_execpolicy2::Decision`, which
has a `Prompt` variant
- when `McpEscalationPolicy` gets `Decision::Prompt` back from
`ExecPolicy`, it prompts the user via an MCP elicitation and maps the
result into an `ElicitationAction`
- now that the end user can reply to an elicitation with `Decline` or
`Cancel`, we introduce a new variant, `EscalateAction::Deny`, which the
client handles by returning exit code `1` without running anything
Note the way the elicitation is created is still not quite right, but I
will fix that once we have things running end-to-end for real in a
follow-up PR.
Expand the rate-limit cache/TUI: store credit snapshots alongside
primary and secondary windows, render “Credits” when the backend reports
they exist (unlimited vs rounded integer balances)
This PR allows clients to render historical messages when resuming a
thread via `thread/resume` by reading from the list of `EventMsg`
payloads loaded from the rollout, and then transforming them into Turns
and ThreadItems to be returned on the `Thread` object.
This is implemented by leveraging `SessionConfiguredNotification` which
returns this list of `EventMsg` objects when resuming a conversation,
and then applying a stateful `ThreadHistoryBuilder` that parses from
this EventMsg log and transforms it into Turns and ThreadItems.
Note that we only persist a subset of `EventMsg`s in a rollout as
defined in `policy.rs`, so we lose fidelity whenever we resume a thread
compared to when we streamed the thread's turns originally. However,
this behavior is at parity with the legacy API.
## Summary
Setting `/approvals` before the start of a conversation was not updating
the environment_context for a conversation. Not sure exactly when this
problem was introduced, but this should reduce model confusion
dramatically.
## Testing
- [x] Added unit test to reproduce bug, confirmed fix with update
- [x] Tested locally
## Summary
On app-server startup, detect whether the experimental sandbox is
enabled, and send a notification .
**Note**
New conversations will not respect the feature because we [ignore cli
overrides in
NewConversation](a75321a64c/codex-rs/app-server/src/codex_message_processor.rs (L1237-L1252)).
However, this should be okay, since we don't actually use config for
this, we use a [global
variable](87cce88f48/codex-rs/core/src/safety.rs (L105-L110)).
We should carefully unwind this setup at some point.
## Testing
- [ ] In progress: testing locally
---------
Co-authored-by: jif-oai <jif@openai.com>
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
Include a link to a bug report or enhancement request.
Instead of returning structured out and then re-formatting it into
freeform, return the freeform output from shell_command tool.
Keep `shell` as the default tool for GPT-5.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
Include a link to a bug report or enhancement request.
New strings:
1. Approval mode picker just says "Select Approval Mode"
1. Updated "Auto" to "Agent"
1. When you select "Agent", you get "Agent mode on Windows uses an
experimental sandbox to limit network and filesystem access. [Learn
more]"
1. Updated world-writable warning to "The Windows sandbox cannot protect
writes to folders that are writable by Everyone. Consider removing write
access for Everyone from the following folders: {folders}"
---------
Co-authored-by: iceweasel-oai <iceweasel@openai.com>
This adds the following fields to `ThreadStartResponse` and
`ThreadResumeResponse`:
```rust
pub model: String,
pub model_provider: String,
pub cwd: PathBuf,
pub approval_policy: AskForApproval,
pub sandbox: SandboxPolicy,
pub reasoning_effort: Option<ReasoningEffort>,
```
This is important because these fields are optional in
`ThreadStartParams` and `ThreadResumeParams`, so the caller needs to be
able to determine what values were ultimately used to start/resume the
conversation. (Though note that any of these could be changed later
between turns in the conversation.)
Though to get this information reliably, it must be read from the
internal `SessionConfiguredEvent` that is created in response to the
start of a conversation. Because `SessionConfiguredEvent` (as defined in
`codex-rs/protocol/src/protocol.rs`) did not have all of these fields, a
number of them had to be added as part of this PR.
Because `SessionConfiguredEvent` is referenced in many tests, test
instances of `SessionConfiguredEvent` had to be updated, as well, which
is why this PR touches so many files.
similar to logic in
`codex/codex-rs/exec/src/event_processor_with_jsonl_output.rs`.
translation of v1 -> v2 events:
`codex/event/task_complete` -> `turn/completed`
`codex/event/turn_aborted` -> `turn/completed` with `interrupted` status
`codex/event/error` -> `turn/completed` with `error` status
this PR also makes `items` field in `Turn` optional. For now, we only
populate it when we resume a thread, and leave it as None for all other
places until we properly rewrite core to keep track of items.
tested using the codex app server client. example new event:
```
< {
< "method": "turn/completed",
< "params": {
< "turn": {
< "id": "0",
< "items": [],
< "status": "interrupted"
< }
< }
< }
```
By default, show only sessions that shared a cwd with the current cwd.
`--all` shows all sessions in all cwds. Also, show the branch name from
the rollout metadata.
<img width="1091" height="638" alt="Screenshot 2025-11-04 at 3 30 47 PM"
src="https://github.com/user-attachments/assets/aae90308-6115-455f-aff7-22da5f1d9681"
/>
This PR fixes the `release_event_does_not_change_selection` test so it
doesn't cause an extra `config.toml` to be emitted in the sources when
running the tests locally. Prior to this fix, I needed to delete this
file every time I ran the tests to prevent it from showing up as an
uncommitted source file.
The `generated_ts_has_no_optional_nullable_fields` test was occasionally
failing on slow CI nodes because of a timeout. This change reduces the
work done by the test. It adds some "options" for the `generate_ts`
function so it can skip work that's not needed for the test.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
Include a link to a bug report or enhancement request.
- This PR is to make it on path for truncating by tokens. This path will
be initially used by unified exec and context manager (responsible for
MCP calls mainly).
- We are exposing new config `calls_output_max_tokens`
- Use `tokens` as the main budget unit but truncate based on the model
family by Introducing `TruncationPolicy`.
- Introduce `truncate_text` as a router for truncation based on the
mode.
In next PRs:
- remove truncate_with_line_bytes_budget
- Add the ability to the model to override the token budget.
- Local-shell tool responses were always tagged as
`ExecCommandSource::UserShell` because handler would call
`run_exec_like` with `is_user_shell_cmd` set to true.
- Treat `ToolPayload::LocalShell` the same as other model generated
shell tool calls by deleting `is_user_shell_cmd` from `run_exec_like`
(since actual user shell commands follow a separate code path)
## Summary
Enables shell_command for windows users, and starts adding some basic
command parsing here, to at least remove powershell prefixes. We'll
follow this up with command parsing but I wanted to land this change
separately with some basic UX.
**NOTE**: This implementation parses bash and powershell on both
platforms. In theory this is possible, since you can use git bash on
windows or powershell on linux. In practice, this may not be worth the
complexity of supporting, so I don't feel strongly about the current
approach vs. platform-specific branching.
## Testing
- [x] Added a bunch of tests
- [x] Ran on both windows and os x
## Summary
Similar to #6545, this PR updates the shell_serialization test suite to
cover the various `shell` tool invocations we have. Note that this does
not cover unified_exec, which has its own suite of tests. This should
provide some test coverage for when we eventually consolidate
serialization logic.
## Testing
- [x] These are tests
## Summary
- update documentation, example configs, and automation defaults to
reference gpt-5.1 / gpt-5.1-codex
- bump the CLI and core configuration defaults, model presets, and error
messaging to the new models while keeping the model-family/tool coverage
for legacy slugs
- refresh tests, fixtures, and TUI snapshots so they expect the upgraded
defaults
## Testing
- `cargo test -p codex-core
config::tests::test_precedence_fixture_with_gpt5_profile`
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_6916c5b3c2b08321ace04ee38604fc6b)
- enabling execpolicy2 parser to parse multiple policy files to build a
combined `Policy` (useful if codex detects many `.codexpolicy` files)
- adding functionality to `Policy` to allow evaluation of multiple cmds
at once (useful when we have chained commands)
This PR adds the API V2 version of the command‑execution approval flow
for the shell tool.
This PR wires the new RPC (`item/commandExecution/requestApproval`, V2
only) and related events (`item/started`, `item/completed`, and
`item/commandExecution/delta`, which are emitted in both V1 and V2)
through the app-server
protocol. The new approval RPC is only sent when the user initiates a
turn with the new `turn/start` API so we don't break backwards
compatibility with VSCE.
The approach I took was to make as few changes to the Codex core as
possible, leveraging existing `EventMsg` core events, and translating
those in app-server. I did have to add additional fields to
`EventMsg::ExecCommandEndEvent` to capture the command's input so that
app-server can statelessly transform these events to a
`ThreadItem::CommandExecution` item for the `item/completed` event.
Once we stabilize the API and it's complete enough for our partners, we
can work on migrating the core to be aware of command execution items as
a first-class concept.
**Note**: We'll need followup work to make sure these APIs work for the
unified exec tool, but will wait til that's stable and landed before
doing a pass on app-server.
Example payloads below:
```
{
"method": "item/started",
"params": {
"item": {
"aggregatedOutput": null,
"command": "/bin/zsh -lc 'touch /tmp/should-trigger-approval'",
"cwd": "/Users/owen/repos/codex/codex-rs",
"durationMs": null,
"exitCode": null,
"id": "call_lNWWsbXl1e47qNaYjFRs0dyU",
"parsedCmd": [
{
"cmd": "touch /tmp/should-trigger-approval",
"type": "unknown"
}
],
"status": "inProgress",
"type": "commandExecution"
}
}
}
```
```
{
"id": 0,
"method": "item/commandExecution/requestApproval",
"params": {
"itemId": "call_lNWWsbXl1e47qNaYjFRs0dyU",
"parsedCmd": [
{
"cmd": "touch /tmp/should-trigger-approval",
"type": "unknown"
}
],
"reason": "Need to create file in /tmp which is outside workspace sandbox",
"risk": null,
"threadId": "019a93e8-0a52-7fe3-9808-b6bc40c0989a",
"turnId": "1"
}
}
```
```
{
"id": 0,
"result": {
"acceptSettings": {
"forSession": false
},
"decision": "accept"
}
}
```
```
{
"params": {
"item": {
"aggregatedOutput": null,
"command": "/bin/zsh -lc 'touch /tmp/should-trigger-approval'",
"cwd": "/Users/owen/repos/codex/codex-rs",
"durationMs": 224,
"exitCode": 0,
"id": "call_lNWWsbXl1e47qNaYjFRs0dyU",
"parsedCmd": [
{
"cmd": "touch /tmp/should-trigger-approval",
"type": "unknown"
}
],
"status": "completed",
"type": "commandExecution"
}
}
}
```
The `cap_sid` file contains the IDs of the two custom SIDs that the
Windows sandbox creates/manages to implement read-only and
workspace-write sandbox policies.
It previously lived in `<cwd>/.codex` which means that the sandbox could
write to it, which could degrade the efficacy of the sandbox. This
change moves it to `~/.codex/` (or wherever `CODEX_HOME` points to) so
that it is outside the workspace.
This PR fixes keyboard handling for the Right Alt (aka "Alt-Gr") key on
Windows. This key appears on keyboards in Central and Eastern Europe.
Codex has effectively never worked for Windows users in these regions
because the code didn't properly handle this key, which is used for
typing common symbols like `\` and `@`.
A few days ago, I merged a [community-authored
PR](https://github.com/openai/codex/pull/6720) that supplied a partial
fix for this issue. Upon closer inspect, that PR was 1) too broad (not
scoped to Windows only) and 2) incomplete (didn't fix all relevant code
paths, so paste was still broken).
This improvement is based on another [community-provided
PR](https://github.com/openai/codex/pull/3241) by @marektomas-cz. He
submitted it back in September and later closed it because it didn't
receive any attention.
This fix addresses the following bugs: #5922, #3046, #3092, #3519,
#5684, #5843.
`--disable shell_tool` disables the built-in shell tool. This is useful
for MCP-only operation.
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
## Overview
Adds LM Studio OSS support. Closes#1883
### Changes
This PR enhances the behavior of `--oss` flag to support LM Studio as a
provider. Additionally, it introduces a new flag`--local-provider` which
can take in `lmstudio` or `ollama` as values if the user wants to
explicitly choose which one to use.
If no provider is specified `codex --oss` will auto-select the provider
based on whichever is running.
#### Additional enhancements
The default can be set using `oss-provider` in config like:
```
oss_provider = "lmstudio"
```
For non-interactive users, they will need to either provide the provider
as an arg or have it in their `config.toml`
### Notes
For best performance, [set the default context
length](https://lmstudio.ai/docs/app/advanced/per-model) for gpt-oss to
the maximum your machine can support
---------
Co-authored-by: Matt Clayton <matt@lmstudio.ai>
Co-authored-by: Eric Traut <etraut@openai.com>
We're running into quite a bit of drag maintaining this test, since
every time we add fields to an EventMsg that happened to be dumped into
the `binary-size-log.jsonl` fixture, this test starts to fail. The fix
is usually to either manually update the `binary-size-log.jsonl` fixture
file, or update the `upgrade_event_payload_for_tests` function to map
the data in that file into something workable.
Eason says it's fine to delete this test, so let's just delete it
## Summary
- Introduces the `codex-execpolicy2` crate.
- This PR covers only the prefix-rule subset of the planned execpolicy
v2 language; a richer language will follow.
## Policy
- Policy language centers on `prefix_rule(pattern=[...], decision?,
match?, not_match?)`, where `pattern` is an ordered list of tokens; any
element may be a list to denote alternatives. `decision` defaults to
`allow`; valid values are `allow`, `prompt`, and `forbidden`. `match` /
`not_match` hold example commands that are tokenized and validated at
load time (think of these as unit tests).
## Policy shapes
- Prefix rules use Starlark syntax:
```starlark
prefix_rule(
pattern = ["cmd", ["alt1", "alt2"]], # ordered tokens; list entries denote alternatives
decision = "prompt", # allow | prompt | forbidden; defaults to allow
match = [["cmd", "alt1"]], # examples that must match this rule (enforced at compile time)
not_match = [["cmd", "oops"]], # examples that must not match this rule (enforced at compile time)
)
```
## Response shapes
- Match:
```json
{
"match": {
"decision": "allow|prompt|forbidden",
"matchedRules": [
{
"prefixRuleMatch": {
"matchedPrefix": ["<token>", "..."],
"decision": "allow|prompt|forbidden"
}
}
]
}
}
```
- No match:
```json
"noMatch"
```
- `matchedRules` lists every rule whose prefix matched the command;
`matchedPrefix` is the exact prefix that matched.
- The effective `decision` is the strictest severity across all matches
(`forbidden` > `prompt` > `allow`).
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
## Summary
Builds on FreeBSD and OpenBSD were failing due to globally enabled
Linux-specific keyring features and hardening code paths not gated by
OS. This PR scopes keyring native backends to the
appropriate targets, disables default features at the workspace root,
and adds a BSD-specific hardening function. Linux/macOS/Windows behavior
remains unchanged, while FreeBSD/OpenBSD
now build and run with a supported backend.
## Key Changes
- Keyring features:
- Disable keyring default features at the workspace root to avoid
pulling Linux backends on non-Linux.
- Move native backend features into target-specific sections in the
affected crates:
- Linux: linux-native-async-persistent
- macOS: apple-native
- Windows: windows-native
- FreeBSD/OpenBSD: sync-secret-service
- Process hardening:
- Add pre_main_hardening_bsd() for FreeBSD/OpenBSD, applying:
- Set RLIMIT_CORE to 0
- Clear LD_* environment variables
- Simplify process-hardening Cargo deps to unconditional libc (avoid
conflicting OS fragments).
- No changes to CODEX_SANDBOX_* behavior.
## Rationale
- Previously, enabling keyring native backends globally pulled
Linux-only features on BSD, causing build errors.
- Hardening logic was tailored for Linux/macOS; BSD builds lacked a
gated path with equivalent safeguards.
- Target-scoped features and BSD hardening make the crates portable
across these OSes without affecting existing behavior elsewhere.
## Impact by Platform
- Linux: No functional change; backends now selected via target cfg.
- macOS: No functional change; explicit apple-native mapping.
- Windows: No functional change; explicit windows-native mapping.
- FreeBSD/OpenBSD: Builds succeed using sync-secret-service; BSD
hardening applied during startup.
## Testing
- Verified compilation across affected crates with target-specific
features.
- Smoke-checked that Linux/macOS/Windows feature sets remain identical
functionally after scoping.
- On BSD, confirmed keyring resolves to sync-secret-service and
hardening compiles.
## Risks / Compatibility
- Minimal risk: only feature scoping and OS-gated additions.
- No public API changes in the crates; runtime behavior on non-BSD
platforms is preserved.
- On BSD, the new hardening clears LD_*; this is consistent with
security posture on other Unix platforms.
## Reviewer Notes
- Pay attention to target-specific sections for keyring in the affected
Cargo.toml files.
- Confirm pre_main_hardening_bsd() mirrors the safe subset of
Linux/macOS hardening without introducing Linux-only calls.
- Confirm no references to CODEX_SANDBOX_ENV_VAR or
CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR were added/modified.
## Checklist
- Disable keyring default features at workspace root.
- Target-specific keyring features mapped per OS
(Linux/macOS/Windows/BSD).
- Add BSD hardening (RLIMIT_CORE=0, clear LD_*).
- Simplify process-hardening dependencies to unconditional libc.
- No changes to sandbox env var code.
- Formatting and linting: just fmt + just fix -p for changed crates.
- Project tests pass for changed crates; broader suite unchanged.
---------
Co-authored-by: celia-oai <celia@openai.com>
## Summary
Fixes streaming issue where Claude models return only 1-4 characters
instead of full responses when used through certain API
providers/proxies.
## Environment
- **OS**: Windows
- **Models affected**: Claude models (e.g., claude-haiku-4-5-20251001)
- **API Provider**: AAAI API proxy (https://api.aaai.vip/v1)
- **Working models**: GLM, Google models work correctly
## Problem
When using Claude models in both TUI and exec modes, only 1-4 characters
are displayed despite the backend receiving the full response. Debug
logs revealed that some API providers send SSE chunks with an empty
string finish_reason during active streaming, rather than null or
omitting the field entirely.
The current code treats any non-null finish_reason as a termination
signal, causing the stream to exit prematurely after the first chunk.
The problematic chunks contain finish_reason with an empty string
instead of null.
## Solution
Fix empty finish_reason handling in chat_completions.rs by adding a
check to only process non-empty finish_reason values. This ensures empty
strings are ignored and streaming continues normally.
## Testing
- Tested on Windows with Claude Haiku model via AAAI API proxy
- Full responses now received and displayed correctly in both TUI and
exec modes
- Other models (GLM, Google) continue to work as expected
- No regression in existing functionality
## Impact
- Improves compatibility with API providers that send empty
finish_reason during streaming
- Enables Claude models to work correctly in Windows environment
- No breaking changes to existing functionality
## Related Issues
This fix resolves the issue where Claude models appeared to return
incomplete responses. The root cause was identified as a compatibility
issue in parsing SSE responses from certain API providers/proxies,
rather than a model-specific problem. This change improves overall
robustness when working with various API endpoints.
---------
Co-authored-by: Eric Traut <etraut@openai.com>
### Summary
- Treat AltGr chords (Ctrl+Alt) as literal character input in the Codex
TUI textarea so Windows terminals that report
backslash and other characters via AltGr insert correctly.
- Add regression test altgr_ctrl_alt_char_inserts_literal to ensure
Ctrl+Alt char events append the character and
advance the cursor.
### Motivation
On US/UK keyboard layouts, backslash is produced by a plain key, so
Ctrl+Alt handling is never exercised and the
bug isn’t visible. On many non‑US layouts (e.g., German), backslash and
other symbols require AltGr, which terminals
report as Ctrl+Alt+<char>. Our textarea previously filtered these chords
like navigation bindings, so AltGr input was
dropped on affected layouts. This change treats AltGr chords as literal
input so backslash and similar symbols work on
Windows terminals.
This fixes multiple reported Issues where the \ symbol got cut off.
Like:
C:\Users\Admin
became
C:UsersAdmin
Co-authored-by: Eric Traut <etraut@openai.com>
## What?
Fixes MCP server initialization failures on Windows when using
script-based tools like `npx`, `pnpm`, and `yarn` that rely on
`.cmd`/`.bat` files rather than `.exe` binaries.
Fixes#2945
## Why?
Windows users encounter "program not found" errors when configuring MCP
servers with commands like `npx` in their `~/.codex/config.toml`. This
happens because:
- Tools like `npx` are batch scripts (`npx.cmd`) on Windows, not
executable binaries
- Rust's `std::process::Command` bypasses the shell and cannot execute
these scripts directly
- The Windows shell normally handles this by checking `PATHEXT` for
executable extensions
Without this fix, Windows users must specify full paths or add `.cmd`
extensions manually, which breaks cross-platform compatibility.
## How?
Added platform-specific program resolution using the `which` crate to
find the correct executable path:
- **Windows**: Resolves programs through PATH/PATHEXT to find
`.cmd`/`.bat` scripts
- **Unix**: Returns the program unchanged (no-op, as Unix handles
scripts natively)
### Changes
- Added `which = "6"` dependency to `mcp-client/Cargo.toml`
- Implemented `program_resolver` module in `mcp_client.rs` with
platform-specific resolution
- Added comprehensive tests for both Windows and Unix behavior
### Testing
Added platform-specific tests to verify:
- Unix systems execute scripts without extensions
- Windows fails without proper extensions
- Windows succeeds with explicit extensions
- Cross-platform resolution enables successful execution
**Tested on:**
- Windows 11 (NT 10.0.26100.0 x64)
- PowerShell 5.1 & 7+, CMD, Git Bash
- MCP servers: playwright, context7, supabase
- WSL (verified no regression)
**Local checks passed:**
```bash
cargo test && cargo clippy --tests && cargo fmt -- --config imports_granularity=Item
```
### Results
**Before:**
```
🖐 MCP client for `playwright` failed to start: program not found
```
**After:**
```
🖐 MCP client for `playwright` failed to start: request timed out
```
Windows users can now use simple commands like `npx` in their config
without specifying full paths or extensions. The timeout issue is a
separate concern that will be addressed in a follow-up PR.
---------
Co-authored-by: Eric Traut <etraut@openai.com>
The Custom Prompts documentation (docs/prompts.md) was incomplete for
named arguments:
1. **Documentation for custom prompts was incomplete** - named argument
usage was mentioned briefly but lacked comprehensive canonical examples
showing proper syntax and behavior.
2. **Fixed by adding canonical, tested syntax and examples:**
- Example 1: Basic named arguments with TICKET_ID and TICKET_TITLE
- Example 2: Mixed positional and named arguments with FILE and FOCUS
- Example 3: Using positional arguments
- Example 4: Updated draftpr example to use proper $FEATURE_NAME syntax
- Added clear usage examples showing KEY=value syntax
- Added expanded prompt examples showing the result
- Documented error handling and validation requirements
3. **Added Implementation Reference section** that references the
relevant feature implementation from the codebase (PRs #4470 and #4474
for initial implementation, #5332 and #5403 for clarifications).
This addresses issue #5039 by providing complete, accurate documentation
for named argument usage in custom prompts.
---------
Co-authored-by: Eric Traut <etraut@openai.com>
This PR does the following:
- Add compact prefix to the summary
- Change the compaction prompt
- Allow multiple compaction for long running tasks
- Filter out summary messages on the following compaction
Considerations:
- Filtering out the summary message isn't the most clean
- Theoretically, we can end up in infinite compaction loop if the user
messages > compaction limit . However, that's not possible in today's
code because we have hard cap on user messages.
- We need to address having multiple user messages because it confuses
the model.
Testing:
- Making sure that after compact we always end up with one user message
(task) and one summary, even on multiple compaction.
Fixes#4940Fixes#4892
When selecting "No, ask me to approve edits and commands" during
onboarding, the code wasn't applying the correct approval policy,
causing Codex to block all write operations instead of requesting
approval.
This PR fixes the issue by persisting the "DontTrust" decision in
config.toml as `trust_level = "untrusted"` and handling it in the
sandbox and approval policy logic, so Codex correctly asks for approval
before making changes.
## Before (bug)
<img width="709" height="500" alt="bef"
src="https://github.com/user-attachments/assets/5aced26d-d810-4754-879a-89d9e4e0073b"
/>
## After (fixed)
<img width="713" height="359" alt="aft"
src="https://github.com/user-attachments/assets/9887bbcb-a9a5-4e54-8e76-9125a782226b"
/>
---------
Co-authored-by: Eric Traut <etraut@openai.com>
For better caching performance all output items should be rendered in
the order they were produced before all new input items (for example,
all function_call before all function_call_output).
For app-server development it's been helpful to be able to trigger some
test flows end-to-end and print the JSON-RPC messages sent between
client and server.
## Summary
- add an `env` option for the TypeScript Codex client and plumb it into
`CodexExec` so the CLI can run without inheriting `process.env`
- extend the test spy to capture spawn environments, add coverage for
the new option, and document how to use it
## Testing
- `pnpm test` *(fails: corepack cannot download pnpm because outbound
network access is blocked in the sandbox)*
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_6916b2d7c7548322a72d61d91a2dac85)
## Summary
- default the `tui.notifications` setting to enabled so desktop
notifications work out of the box
- update configuration tests and documentation to reflect the new
default
## Testing
- `cargo test -p codex-core` *(fails:
`exec::tests::kill_child_process_group_kills_grandchildren_on_timeout`
is flaky in this sandbox because the spawned grandchild process stays
alive)*
- `cargo test -p codex-core
exec::tests::kill_child_process_group_kills_grandchildren_on_timeout`
*(fails: same sandbox limitation as above)*
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_69166f811144832c9e8aaf8ee2642373)
## Summary
- add `TestCodex::submit_turn_with_policies` and extend the response
helpers with reusable tool-call utilities
- update the grep_files, read_file, list_dir, shell_serialization, and
tools suites to rely on the shared helpers instead of local copies
- make the list_dir helper return `anyhow::Result` so clippy no longer
warns about `expect`
## Testing
- `just fix -p codex-core`
- `cargo test -p codex-core --test all
suite::grep_files::grep_files_tool_collects_matches`
- `cargo test -p codex-core
suite::grep_files::grep_files_tool_collects_matches -- --ignored`
(filter requests ignored tests so nothing runs, but the build stays
clean)
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_69112d53abac83219813cab4d7cb6446)
## Summary
- replace the bespoke network check in the chat completion payload and
SSE tests with the existing `skip_if_no_network!` helper so they follow
the same gating convention as the rest of the suite
## Testing
- `just fmt`
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_69112d4cb9f08321ba773e8ccf39778e)
A partner is consuming our generated JSON schema bundle for app-server
and identified a few issues:
- not all polymorphic / one-of types have a type descriminator
- `"$ref": "#/definitions/v2/SandboxPolicy"` is missing
- "Option<>" is an invalid schema name, and also unnecessary
This PR:
- adds the type descriminator to the various types that are missing it
except for `SessionSource` and `SubAgentSource` because they are
serialized to disk (adding this would break backwards compat for
resume), and they should not be necessary to consume for an integration
with app-server.
- removes the special handling in `export.rs` of various types like
SandboxPolicy, which turned out to be unnecessary and incorrect
- filters out `Option<>` which was auto-generated for request params
that don't need a body
For context, we currently pull in wayyy more types than we need through
the `EventMsg` god object which we are **not** planning to expose in API
v2 (this is how I suspect `SessionSource` and `SubAgentSource` are being
pulled in). But until we have all the necessary v2 notifications in
place that will allow us to remove `EventMsg`, we will keep exporting it
for now.
core event to app server event mapping:
1. `codex/event/reasoning_content_delta` ->
`item/reasoning/summaryTextDelta`.
2. `codex/event/reasoning_raw_content_delta` ->
`item/reasoning/textDelta`
3. `codex/event/agent_message_content_delta` →
`item/agentMessage/delta`.
4. `codex/event/agent_reasoning_section_break` ->
`item/reasoning/summaryPartAdded`.
Also added a change in core to pass down content index, summary index
and item id from events.
Tested with the `git checkout owen/app_server_test_client && cargo run
-p codex-app-server-test-client -- send-message-v2 "hello"` and verified
that new events are emitted correctly.
## Summary
Consolidates our apply_patch tests into one suite, and ensures each test
case tests the various ways the harness supports apply_patch:
1. Freeform custom tool call
2. JSON function tool
3. Simple shell call
4. Heredoc shell call
There are a few test cases that are specific to a particular variant,
I've left those alone.
## Testing
- [x] This adds a significant number of tests
## Summary
Adds support for specifying additional directories in the TypeScript SDK
through a new `additionalDirectories` option in `ThreadOptions`.
## Changes
- Added `additionalDirectories` parameter to `ThreadOptions` interface
- Updated `CodexExec` to accept and pass through additional directories
via the `--config` flag for `sandbox_workspace_write.writable_roots`
- Added comprehensive test coverage for the new functionality
## Test plan
- Added test case that verifies `additionalDirectories` is correctly
passed as repeated flags
- Existing tests continue to pass
---------
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
Adds AbortSignal support to the TypeScript SDK for canceling thread
execution using AbortController.
## Changes
- Add `signal?: AbortSignal` property to `TurnOptions` type
- Pass signal through Thread class methods to exec layer
- Add signal parameter to `CodexExecArgs`
- Leverage Node.js native `spawn()` signal support for automatic
cancellation
- Add comprehensive test coverage (6 tests covering all abort scenarios)
## Implementation
The implementation uses Node.js's built-in AbortSignal support in
`spawn()` (available since Node v15, SDK requires >=18), which
automatically handles:
- Checking if already aborted before starting
- Killing the child process when abort is triggered
- Emitting appropriate error events
- All cleanup operations
This is a one-line change to the core implementation (`signal:
args.signal` passed to spawn), making it simple, reliable, and
maintainable.
## Usage Example
```typescript
import { Codex } from '@openai/codex-sdk';
const codex = new Codex({ apiKey: 'your-api-key' });
const thread = codex.startThread();
// Create AbortController
const controller = new AbortController();
// Run with abort signal
const resultPromise = thread.run("Your prompt here", {
signal: controller.signal
});
// Cancel anytime
controller.abort('User requested cancellation');
```
## Testing
All tests pass (23 total across SDK):
- ✅ Aborts when signal is already aborted (both run and runStreamed)
- ✅ Aborts during execution/iteration
- ✅ Completes normally when not aborted
- ✅ Backward compatible (signal is optional)
Tests verified to fail correctly when signal support is removed (no
false positives).
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: pakrym-oai <pakrym@openai.com>
Previously the popup measured rows using the full content width while
the renderer drew them with 2 columns of padding, so at certain widths
the layout allocated too little vertical space and hid the third option.
Now both desired_height and render call a shared helper that subtracts
the padding before measuring, so the height we reserve always matches
what we draw and the menu doesn't drops entries.
https://github.com/user-attachments/assets/59058fd9-1e34-4325-b5fe-fc888dfcb6bc
We've received many reports of codex hanging when calling certain tools.
[Here](https://github.com/openai/codex/issues/3204) is one example. This
is likely a major cause. The problem occurs when
`consume_truncated_output` waits for `stdout` and `stderr` to be closed
once the child process terminates. This normally works fine, but it
doesn't handle the case where the child has spawned grandchild processes
that inherits `stdout` and `stderr`.
The fix was originally written by @md-oai in [this
PR](https://github.com/openai/codex/pull/1852), which has gone stale.
I've copied the original fix (which looks sound to me) and added an
integration test to prevent future regressions.
- Introducing a screen to inform users of model changes.
- Config name is being passed to be able to reuse this component in the
future for future models
This updates `thread/resume` to be at parity with v1's
`ResumeConversationParams`. Turns out history is useful for codex cloud
and path is useful for the VSCode extension. And config overrides are
always useful.
This PR addresses https://github.com/openai/codex/issues/6360. The root
problem is that the TUI was directly loading the `auth.json` file to
access the auth information. It should instead be using the AuthManager,
which records the current auth information. The `auth.json` file can be
overwritten at any time by other instances of the CLI or extension, so
its information can be out of sync with the current instance. The
`/status` command should always report the auth information associated
with the current instance.
An alternative fix for this bug was submitted by @chojs23 in [this
PR](https://github.com/openai/codex/pull/6495). That approach was only a
partial fix.
This is important to ensure that this:
```
codex --enable unified_exec
```
and this:
```
codex --config features.unified_exec=true
```
are equivalent. Also that when it is passed programmatically:
807e2c27f0/codex-rs/app-server-protocol/src/protocol/v1.rs (L55)
then this should work for `config`:
```json
{"features": {"shell_command_tool": true}}
```
though I believe also this:
```json
{"features.shell_command_tool": true}
```
This adds support for a new variant of the shell tool behind a flag. To
test, run `codex` with `--enable shell_command_tool`, which will
register the tool with Codex under the name `shell_command` that accepts
the following shape:
```python
{
command: str
workdir: str | None,
timeout_ms: int | None,
with_escalated_permissions: bool | None,
justification: str | None,
}
```
This is comparable to the existing tool registered under
`shell`/`container.exec`. The primary difference is that it accepts
`command` as a `str` instead of a `str[]`. The `shell_command` tool
executes by running `execvp(["bash", "-lc", command])`, though the exact
arguments to `execvp(3)` depend on the user's default shell.
The hypothesis is that this will simplify things for the model. For
example, on Windows, instead of generating:
```json
{"command": ["pwsh.exe", "-NoLogo", "-Command", "ls -Name"]}
```
The model could simply generate:
```json
{"command": "ls -Name"}
```
As part of this change, I extracted some logic out of `user_shell.rs` as
`Shell::derive_exec_args()` so that it can be reused in
`codex-rs/core/src/tools/handlers/shell.rs`. Note the original code
generated exec arg lists like:
```javascript
["bash", "-lc", command]
["zsh", "-lc", command]
["pwsh.exe", "-NoProfile", "-Command", command]
```
Using `-l` for Bash and Zsh, but then specifying `-NoProfile` for
PowerShell seemed inconsistent to me, so I changed this in the new
implementation while also adding a `use_login_shell: bool` option to
make this explicit. If we decide to add a `login: bool` to
`ShellCommandToolCallParams` like we have for unified exec:
807e2c27f0/codex-rs/core/src/tools/handlers/unified_exec.rs (L33-L34)
Then this should make it straightforward to support.
This PR fixes#6522 by correcting the comment for `full-auto` in both
`codex-rs/exec/src/cli.rs` and `codex-rs/tui/src/cli.rs` from `-a
on-failure` to `-a on-request` to make it coherent with
`codex-rs/tui/src/lib.rs:97-105`:
```rust
pub async fn run_main(
mut cli: Cli,
codex_linux_sandbox_exe: Option<PathBuf>,
) -> std::io::Result<AppExitInfo> {
let (sandbox_mode, approval_policy) = if cli.full_auto {
(
Some(SandboxMode::WorkspaceWrite),
Some(AskForApproval::OnRequest),
)
```
Running `just codex --help` or `just codex exec --help` should now yield
the correct description of `full-auto` CLI argument.
Signed-off-by: lionelchg <lionel.cheng@hotmail.fr>
This one should be quite straightforward, as it's just a translation of
TurnItem events we already emit to ThreadItem that app-server exposes to
customers.
To test, cp my change to owen/app_server_test_client and do the
following:
```
cargo build -p codex-cli
RUST_LOG=codex_app_server=info CODEX_BIN=target/debug/codex cargo run -p codex-app-server-test-client -- send-message-v2 "hello"
```
example event before (still kept there for backward compatibility):
```
{
< "method": "codex/event/item_completed",
< "params": {
< "conversationId": "019a74cc-fad9-7ab3-83a3-f42827b7b074",
< "id": "0",
< "msg": {
< "item": {
< "Reasoning": {
< "id": "rs_03d183492e07e20a016913a936eb8c81a1a7671a103fee8afc",
< "raw_content": [],
< "summary_text": [
< "Hey! What would you like to work on? I can explore the repo, run specific tests, or implement a change. Let's keep it short and straightforward. There's no need for a lengthy introduction or elaborate planning, just a friendly greeting and an open offer to help. I want to make sure the user feels welcomed and understood right from the start. It's all about keeping the tone friendly and concise!"
< ]
< }
< },
< "thread_id": "019a74cc-fad9-7ab3-83a3-f42827b7b074",
< "turn_id": "0",
< "type": "item_completed"
< }
< }
< }
```
after (v2):
```
< {
< "method": "item/completed",
< "params": {
< "item": {
< "id": "rs_03d183492e07e20a016913a936eb8c81a1a7671a103fee8afc",
< "text": "Hey! What would you like to work on? I can explore the repo, run specific tests, or implement a change. Let's keep it short and straightforward. There's no need for a lengthy introduction or elaborate planning, just a friendly greeting and an open offer to help. I want to make sure the user feels welcomed and understood right from the start. It's all about keeping the tone friendly and concise!",
< "type": "reasoning"
< }
< }
< }
```
Unified exec isn't working on Linux because we don't provide the correct
arg0.
The library we use for pty management doesn't allow setting arg0
separately from executable. Use the same aliasing strategy we use for
`apply_patch` for `codex-linux-sandbox`.
Use `#[ctor]` hack to dispatch codex-linux-sandbox calls.
Addresses https://github.com/openai/codex/issues/6450
This PR is to unlock future WinGet installation. WinGet struggles to
create command aliases when installing from nested ZIPs on some clients,
so adding raw Windows x64/Arm64 executables lets the manifest use
InstallerType: portable with direct EXEs, which reliably registers the
codex alias. This makes “winget install → codex” work out of the box
without PATH changes.
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
We already do this for notification definitions and it's really nice.
Verified there are no changes to actual exported files by diff'ing
before and after this change.
- Moved the unix-only suspend/resume logic into a dedicated job_control
module housing SuspendContext, replacing scattered cfg-gated fields and
helpers in tui.rs.
- Tui now holds a single suspend_context (Arc-backed) instead of
multiple atomics, and the event stream uses it directly for Ctrl-Z
handling.
- Added detailed docs around the suspend/resume flow, cursor tracking,
and the Arc/atomic ownership model for the 'static event stream.
- Renamed the process-level SIGTSTP helper to suspend_process and the
cursor tracker to set_cursor_y to better reflect their roles.
This adds a debugging tool for analyzing why certain commands fail to
execute under the sandbox.
Example output:
```
$ codex debug seatbelt --log-denials bash -lc "(echo foo > ~/foo.txt)"
bash: /Users/nornagon/foo.txt: Operation not permitted
=== Sandbox denials ===
(bash) file-write-data /dev/tty
(bash) file-write-data /dev/ttys001
(bash) sysctl-read kern.ngroups
(bash) file-write-create /Users/nornagon/foo.txt
```
It operates by:
1. spawning `log stream` to watch system logs, and
2. tracking all descendant PIDs using kqueue + proc_listchildpids.
this is a "best-effort" technique, as `log stream` may drop logs(?), and
kqueue + proc_listchildpids isn't atomic and can end up missing very
short-lived processes. But it works well enough in my testing to be
useful :)
## Summary
- log and surface clipboard failures instead of silently ignoring them
when `Ctrl+V` pastes an image (`paste_image_to_temp_png()` now feeds an
error history cell)
- enable `arboard`’s `wayland-data-control` feature so native Wayland
sessions can deliver image data without XWayland
- keep the success path unchanged: valid images still attach and show
the `[image …]` placeholder as before
Fixes#4818
---------
Co-authored-by: Eric Traut <etraut@openai.com>
Co-authored-by: Jeremy Rose <172423086+nornagon-openai@users.noreply.github.com>
## Summary
- add a `hide_rate_limit_model_nudge` notice flag plus config edit
plumbing so the rate limit reminder preference is persisted and
documented
- extend the chat widget prompt with a "never show again" option, and
wire new app events so selecting it hides future nudges immediately and
writes the config
- add unit coverage and refresh the snapshot for the three-option prompt
## Testing
- `just fmt`
- `just fix -p codex-tui`
- `just fix -p codex-core`
- `cargo test -p codex-tui`
- `cargo test -p codex-core` *(fails at
`exec::tests::kill_child_process_group_kills_grandchildren_on_timeout`:
grandchild process still alive)*
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_6910d7f407748321b2661fc355416994)
Add a `codex generate-json-schema` command for generating a JSON schema
bundle of app-server types, analogous to the existing `codex
generate-ts` command for Typescript.
The CLA action is designed to automatically lock a PR when it is closed.
This preserves the CLA agreement statements, preventing the contributor
from deleting them after the fact. However, this action is currently
locking PRs that are closed without merging. I'd like to keep such PRs
open so the contributor can respond with additional comments. I'm
currently manually unlocking PRs that I close, but I'd like to eliminate
this manual step.
I recently fixed a bug in [this
PR](https://github.com/openai/codex/pull/6285) that prevented Ctrl+C
from dismissing the login menu in the TUI and leaving the user unauthed.
A [user pointed out](https://github.com/openai/codex/issues/6418) that
this makes Ctrl+C can no longer be used to exit the app. This PR changes
the behavior so we exit the app rather than ignoring the Ctrl+C.
Update `codex generate-ts` to use the TS export code from
`app-server-protocol/src/export.rs`.
I realized there were two duplicate implementations of Typescript export
code:
- `app-server-protocol/src/export.rs`
- the `codex-protocol-ts` crate
The `codex-protocol-ts` crate that `codex generate-ts` uses is out of
date now since it doesn't handle the V2 namespace from:
https://github.com/openai/codex/pull/6212.
This is a simplified version of [a
PR](https://github.com/openai/codex/pull/6134) supplied by a community
member.
It updates the docs to reflect a recent config deprecation.
The CLI help text and inline comments incorrectly stated that -c
key=value flag parses values as JSON, when the implementation actually
uses TOML parsing via parse_toml_value(). This caused confusion when
users attempted to configure MCP servers using JSON syntax based on the
documentation.
Changes:
- Updated help text to correctly state TOML parsing instead of JSON
Fixes#4531
Bumps [zeroize](https://github.com/RustCrypto/utils) from 1.8.1 to
1.8.2.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="c100874101"><code>c100874</code></a>
zeroize v1.8.2 (<a
href="https://redirect.github.com/RustCrypto/utils/issues/1229">#1229</a>)</li>
<li><a
href="3940ccbebd"><code>3940ccb</code></a>
Switch from <code>doc_auto_cfg</code> to <code>doc_cfg</code> (<a
href="https://redirect.github.com/RustCrypto/utils/issues/1228">#1228</a>)</li>
<li><a
href="c68a5204b2"><code>c68a520</code></a>
Fix Nightly warnings (<a
href="https://redirect.github.com/RustCrypto/utils/issues/1080">#1080</a>)</li>
<li><a
href="b15cc6c1cd"><code>b15cc6c</code></a>
cargo: point <code>repository</code> metadata to clonable URLs (<a
href="https://redirect.github.com/RustCrypto/utils/issues/1079">#1079</a>)</li>
<li><a
href="3db6690f7b"><code>3db6690</code></a>
zeroize: fix <code>homepage</code>/<code>repository</code> in Cargo.toml
(<a
href="https://redirect.github.com/RustCrypto/utils/issues/1076">#1076</a>)</li>
<li>See full diff in <a
href="https://github.com/RustCrypto/utils/compare/zeroize-v1.8.1...zeroize-v1.8.2">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps
[taiki-e/install-action](https://github.com/taiki-e/install-action) from
2.60.0 to 2.62.49.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/taiki-e/install-action/releases">taiki-e/install-action's
releases</a>.</em></p>
<blockquote>
<h2>2.62.49</h2>
<ul>
<li>
<p>Update <code>cargo-binstall@latest</code> to 1.15.11.</p>
</li>
<li>
<p>Update <code>cargo-auditable@latest</code> to 0.7.2.</p>
</li>
<li>
<p>Update <code>vacuum@latest</code> to 0.20.2.</p>
</li>
</ul>
<h2>2.62.48</h2>
<ul>
<li>
<p>Update <code>mise@latest</code> to 2025.11.3.</p>
</li>
<li>
<p>Update <code>cargo-audit@latest</code> to 0.22.0.</p>
</li>
<li>
<p>Update <code>vacuum@latest</code> to 0.20.1.</p>
</li>
<li>
<p>Update <code>uv@latest</code> to 0.9.8.</p>
</li>
<li>
<p>Update <code>cargo-udeps@latest</code> to 0.1.60.</p>
</li>
<li>
<p>Update <code>zizmor@latest</code> to 1.16.3.</p>
</li>
</ul>
<h2>2.62.47</h2>
<ul>
<li>
<p>Update <code>vacuum@latest</code> to 0.20.0.</p>
</li>
<li>
<p>Update <code>cargo-nextest@latest</code> to 0.9.111.</p>
</li>
<li>
<p>Update <code>cargo-shear@latest</code> to 1.6.2.</p>
</li>
</ul>
<h2>2.62.46</h2>
<ul>
<li>
<p>Update <code>vacuum@latest</code> to 0.19.5.</p>
</li>
<li>
<p>Update <code>syft@latest</code> to 1.37.0.</p>
</li>
<li>
<p>Update <code>mise@latest</code> to 2025.11.2.</p>
</li>
<li>
<p>Update <code>knope@latest</code> to 0.21.5.</p>
</li>
</ul>
<h2>2.62.45</h2>
<ul>
<li>
<p>Update <code>zizmor@latest</code> to 1.16.2.</p>
</li>
<li>
<p>Update <code>cargo-binstall@latest</code> to 1.15.10.</p>
</li>
<li>
<p>Update <code>ubi@latest</code> to 0.8.4.</p>
</li>
<li>
<p>Update <code>mise@latest</code> to 2025.11.1.</p>
</li>
<li>
<p>Update <code>cargo-semver-checks@latest</code> to 0.45.0.</p>
</li>
</ul>
<h2>2.62.44</h2>
<ul>
<li>Update <code>mise@latest</code> to 2025.11.0.</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/taiki-e/install-action/blob/main/CHANGELOG.md">taiki-e/install-action's
changelog</a>.</em></p>
<blockquote>
<h1>Changelog</h1>
<p>All notable changes to this project will be documented in this
file.</p>
<p>This project adheres to <a href="https://semver.org">Semantic
Versioning</a>.</p>
<!-- raw HTML omitted -->
<h2>[Unreleased]</h2>
<h2>[2.62.49] - 2025-11-09</h2>
<ul>
<li>
<p>Update <code>cargo-binstall@latest</code> to 1.15.11.</p>
</li>
<li>
<p>Update <code>cargo-auditable@latest</code> to 0.7.2.</p>
</li>
<li>
<p>Update <code>vacuum@latest</code> to 0.20.2.</p>
</li>
</ul>
<h2>[2.62.48] - 2025-11-08</h2>
<ul>
<li>
<p>Update <code>mise@latest</code> to 2025.11.3.</p>
</li>
<li>
<p>Update <code>cargo-audit@latest</code> to 0.22.0.</p>
</li>
<li>
<p>Update <code>vacuum@latest</code> to 0.20.1.</p>
</li>
<li>
<p>Update <code>uv@latest</code> to 0.9.8.</p>
</li>
<li>
<p>Update <code>cargo-udeps@latest</code> to 0.1.60.</p>
</li>
<li>
<p>Update <code>zizmor@latest</code> to 1.16.3.</p>
</li>
</ul>
<h2>[2.62.47] - 2025-11-05</h2>
<ul>
<li>
<p>Update <code>vacuum@latest</code> to 0.20.0.</p>
</li>
<li>
<p>Update <code>cargo-nextest@latest</code> to 0.9.111.</p>
</li>
<li>
<p>Update <code>cargo-shear@latest</code> to 1.6.2.</p>
</li>
</ul>
<h2>[2.62.46] - 2025-11-04</h2>
<ul>
<li>
<p>Update <code>vacuum@latest</code> to 0.19.5.</p>
</li>
<li>
<p>Update <code>syft@latest</code> to 1.37.0.</p>
</li>
<li>
<p>Update <code>mise@latest</code> to 2025.11.2.</p>
</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="44c6d64aa6"><code>44c6d64</code></a>
Release 2.62.49</li>
<li><a
href="3a701df4c2"><code>3a701df</code></a>
Update <code>cargo-binstall@latest</code> to 1.15.11</li>
<li><a
href="4242e04eb8"><code>4242e04</code></a>
Update <code>cargo-auditable@latest</code> to 0.7.2</li>
<li><a
href="3df5533ef8"><code>3df5533</code></a>
Update <code>vacuum@latest</code> to 0.20.2</li>
<li><a
href="e797ba6a25"><code>e797ba6</code></a>
Release 2.62.48</li>
<li><a
href="bcf91e02ac"><code>bcf91e0</code></a>
Update <code>mise@latest</code> to 2025.11.3</li>
<li><a
href="e78113b60c"><code>e78113b</code></a>
Update <code>cargo-audit@latest</code> to 0.22.0</li>
<li><a
href="0ef486444e"><code>0ef4864</code></a>
Update <code>vacuum@latest</code> to 0.20.1</li>
<li><a
href="5eda7b1985"><code>5eda7b1</code></a>
Update <code>uv@latest</code> to 0.9.8</li>
<li><a
href="3853a413e6"><code>3853a41</code></a>
Update <code>cargo-udeps@latest</code> to 0.1.60</li>
<li>Additional commits viewable in <a
href="0c5db7f7f8...44c6d64aa6">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
On Windows, `npm` by itself does not resolve under std::process::Command
which does not consider PATHEXT to resolve it to `npm.cmd` in the PATH.
By running the npm upgrade command via cmd.exe we get proper path
semantics so it actually works.
## Problem
`codex cloud` always instantiated `AuthManager` with `File` mode,
ignoring the user's actual `cli_auth_credentials_store` setting. This
caused users with `cli_auth_credentials_store = "keyring"` (or `"auto"`)
to see "Not signed in" errors even when they had valid credentials
stored in the system keyring.
## Root cause
The code called `Config::load_from_base_config_with_overrides()` with an
empty `ConfigToml::default()`, which always returned `File` as the
default store mode instead of loading the actual user configuration.
## Solution
- **Added `util::load_cli_auth_manager()` helper**
Properly loads user config via
`load_config_as_toml_with_cli_overrides()` and extracts the
`cli_auth_credentials_store` setting before creating `AuthManager`.
- **Updated callers**
- `init_backend()` - used when starting cloud tasks UI
- `build_chatgpt_headers()` - used for API requests
## Testing
- ✅ `just fmt`
- ✅ `just fix -p codex-cloud-tasks`
- ✅ `cargo test -p codex-cloud-tasks`
## Files changed
- `codex-rs/cloud-tasks/src/lib.rs`
- `codex-rs/cloud-tasks/src/util.rs`
## Verification
Users with keyring-based auth can now run `codex cloud` successfully
without "Not signed in" errors.
---------
Co-authored-by: Eric Traut <etraut@openai.com>
Co-authored-by: celia-oai <celia@openai.com>
The TypeScript SDK's README incorrectly claimed that runStreamed() emits
"file diffs". However, the FileChangeItem type only contains metadata
(path, kind, status) without actual diff content.
Updated line 36 to accurately describe the SDK as providing "file change
notifications" instead of "file diffs" to match the actual
implementation in items.ts.
Fixes#5850
3 improvements:
1. show up to 3 actual paths that are world-writable
2. do the scan/warning for Read-Only mode too, because it also applies
there
3. remove the "Cancel" option since it doesn't always apply (like on
startup)
Shows single-key shortcuts (y, a, n) next to approval options to make
them more discoverable. Previously these shortcuts worked but were
hidden, making the feature hard to discover.
Changes:
- "Yes, proceed" now shows "y" shortcut
- "Yes, and don't ask again" now shows "a" shortcut
- "No, and tell Codex..." continues to show "esc" shortcut
This improves UX by surfacing the quick keyboard shortcuts that were
already functional but undiscoverable in the UI.
---
Update:
added parentheses for better visual clarity
<img width="1540" height="486" alt="CleanShot 2025-11-05 at 11 47 07@2x"
src="https://github.com/user-attachments/assets/f951c34a-9ec8-4b81-b151-7b2ccba94658"
/>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Eric Traut <etraut@openai.com>
1. scan many more directories since it's much faster than the original
implementation
2. limit overall scan time to 2s
3. skip some directories that are noisy - ApplicationData, Installer,
etc.
## Summary
- launch shell tool processes in their own process group so Codex owns
the full tree
- on timeout or ctrl-c, send SIGKILL to the process group before
terminating the tracked child
- document that the default shell/unified_exec timeout remains 1000 ms
## Original Bug
Long-lived shell tool commands hang indefinitely because the timeout
handler only terminated the direct child process; any grandchildren it
spawned kept running and held the PTY open, preventing Codex from
regaining control.
## Repro Original Bug
Install next.js and run `next dev` (which is a long-running shell
process with children). On openai:main, it will cause the agent to
permanently get stuck here until human intervention. On this branch,
this command will be terminated successfully after timeout_ms which will
unblock the agent. This is a critical fix for unmonitored / lightly
monitored agents that don't have immediate human observation to unblock
them.
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
Co-authored-by: Michael Bolin <bolinfest@gmail.com>
### Motivation
When Codex is launched from a region where Cloudflare blocks access (for
example, Russia), the CLI currently dumps Cloudflare’s entire HTML error
page. This isn’t actionable and makes it hard for users to understand
what happened. We want to detect the Cloudflare block and show a
concise, user-friendly explanation instead.
### What Changed
- Added CLOUDFLARE_BLOCKED_MESSAGE and a friendly_message() helper to
UnexpectedResponseError. Whenever we see a 403 whose body contains the
Cloudflare block notice, we now emit a single-line message (Access
blocked by Cloudflare…) while preserving the HTTP status and request id.
All other responses keep the original behaviour.
- Added two focused unit tests:
- unexpected_status_cloudflare_html_is_simplified ensures the Cloudflare
HTML case yields the friendly message.
- unexpected_status_non_html_is_unchanged confirms plain-text 403s still
return the raw body.
### Testing
- cargo build -p codex-cli
- cargo test -p codex-core
- just fix -p codex-core
- cargo test --all-features
---------
Co-authored-by: Eric Traut <etraut@openai.com>
Removes flush logic that was leftover to test against ratatui's flush
Cleaned up the flush logic so it's a bit more intent revealing.
DrawCommand now owns the Cells that it draws as this works around a
borrow checker problem.
When running under WSL, the update command could receive Windows-style
absolute paths (e.g., `C:\...`) and pass them to Linux processes
unchanged, which fails because WSL expects those paths in
`/mnt/<drive>/...` form.
This patch adds a tiny helper in the CLI (`cli/src/wsl_paths.rs`) that:
- Detects WSL (`WSL_DISTRO_NAME` or `"microsoft"` in `/proc/version`)
- Converts `X:\...` → `/mnt/x/...`
`run_update_action` now normalizes the package-manager command and
arguments under WSL before spawning.
Non-WSL platforms are unaffected.
Includes small unit tests for the converter.
**Fixes:** #6086, #6084
Co-authored-by: Eric Traut <etraut@openai.com>
## Summary
This PR adds two new optional boolean fields to `ThreadOptions` in the
TypeScript SDK:
- **`networkAccess`**: Enables network access in the sandbox by setting
`sandbox_workspace_write.network_access` config
- **`webSearch`**: Enables the web search tool by setting
`tools.web_search` config
These options map to existing Codex configuration options and are
properly threaded through the SDK layers:
1. `ThreadOptions` (threadOptions.ts) - User-facing API
2. `CodexExecArgs` (exec.ts) - Internal execution args
3. CLI flags via `--config` in the `codex exec` command
## Changes
- `sdk/typescript/src/threadOptions.ts`: Added `networkAccess` and
`webSearch` fields to `ThreadOptions` type
- `sdk/typescript/src/exec.ts`: Added fields to `CodexExecArgs` and CLI
flag generation
- `sdk/typescript/src/thread.ts`: Pass options through to exec layer
## Test Plan
- [x] Build succeeds (`pnpm build`)
- [x] Linter passes (`pnpm lint`)
- [x] Type definitions are properly exported
- [ ] Manual testing with sample code (to be done by reviewer)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Historically, running `create_github_release --publish-release` would
always publish a new release from latest `main`, which isn't always the
best idea. We should really publish an alpha, let it bake, and then
promote it.
This PR introduces a new flag, `--promote-alpha`, which does exactly
that. It also works with `--dry-run`, so you can sanity check the commit
it will use as the base commit for the new release before running it for
real.
```shell
$ ./codex-rs/scripts/create_github_release --dry-run --promote-alpha 0.56.0-alpha.2
Publishing version 0.56.0
Running gh api GET /repos/openai/codex/git/refs/tags/rust-v0.56.0-alpha.2
Running gh api GET /repos/openai/codex/git/tags/7d4ef77bc35b011aa0c76c5cbe6cd7d3e53f1dfe
Running gh api GET /repos/openai/codex/compare/main...8b49211e67d3c863df5ecc13fc5f88516a20fa69
Would publish version 0.56.0 using base commit 62474a30e8 derived from rust-v0.56.0-alpha.2.
```
Add the following fields to Thread:
```
pub preview: String,
pub model_provider: String,
pub created_at: i64,
```
Will prob need another PR once this lands:
https://github.com/openai/codex/pull/6337
This PR does two things:
1. add a new function in core that maps the core-internal plan type to
the external plan type;
2. implement account/read that get account status (v2 of
`getAuthStatus`).
Fixes https://github.com/openai/codex/issues/5485.
Fixed rename hunks so `apply_patch` resolves the destination path using
the verifier’s effective cwd, ensuring patches that run under `cd
<worktree> && apply_patch` stay inside the worktree.
Added a regression test
(`test_apply_patch_resolves_move_path_with_effective_cwd`) that
reproduced the old behavior (dest path resolved in the main repo) and
now passes.
Related to https://github.com/openai/codex/issues/5483.
Co-authored-by: Eric Traut <etraut@openai.com>
This PR updates the AI prompt used for the workflow that adds automated
labels to incoming issues. I've been updating and refining the list of
labels as I work through the issue backlog, and the old prompt was
becoming somewhat outdated.
This PR makes an "insufficient quota" error fatal so we don't attempt to
retry it multiple times in the agent loop.
We have multiple bug reports from users about intermittent retry
behaviors, and this could explain some of them. With this change, we'll
eliminate the retries and surface a clear error message.
The PR is a nearly identical copy of [this
PR](https://github.com/openai/codex/pull/4837) contributed by
@abimaelmartell. The original PR has gone stale. Rather than wait for
the contributor to resolve merge conflicts, I wanted to get this change
in.
This allows `gh api` to work in the workspace-write sandbox w/ network
enabled. Without this we see e.g.
```
$ codex debug seatbelt --full-auto gh api repos/openai/codex/pulls --paginate -X GET -F state=all
Get "https://api.github.com/repos/openai/codex/pulls?per_page=100&state=all": tls: failed to verify certificate: x509: OSStatus -26276
```
Some PRs are being submitted without reference to existing bug reports
or feature requests. This updates the PR template and contributing
guidelines to request that all PRs from the community contain such a
link. This provides additional context and helps prioritize, track, and
assess PRs.
Show a warning when Auto Sandbox mode becomes enabled, if we detect
Everyone-writable directories, since they cannot be protected by the
current implementation of the Sandbox.
This PR also includes changes to how we detect Everyone-writable to be
*much* faster
Implements:
```
turn/start
turn/interrupt
```
along with their integration tests. These are relatively light wrappers
around the existing core logic, and changes to core logic are minimal.
However, an improvement made for developer ergonomics:
- `turn/start` replaces both `SendUserMessage` (no turn overrides) and
`SendUserTurn` (can override model, approval policy, etc.)
turns out the ToC was including itself when generating, which messed up
comparisons and sometimes made the file rewrite endlessly.
also fixed the slice so `<!-- End ToC -->` doesn’t get duplicated when
we insert the new ToC.
should behave nicely now - no extra rewrites, no doubled markers.
Co-authored-by: Eric Traut <etraut@openai.com>
We currently allow the user to dismiss the login menu via Ctrl+C. This
leaves them in a bad state where they're not auth'ed but have an input
prompt. In the extension, this isn't a problem because we don't allow
the user to dismiss the login screen.
Testing: I confirmed that Ctrl+C no longer dismisses the login menu.
This is an alternative (simpler) fix for a [community
PR](https://github.com/openai/codex/pull/3234).
This PR implements `account/login/start` and `account/login/completed`.
Instead of having separate endpoints for login with chatgpt and api, we
have a single enum handling different login methods. For sync auth
methods like sign in with api key, we still send a `completed`
notification back to be compatible with the async login flow.
I'm seeing two tests fail intermittently in CI. This PR attempts to
address (or at least mitigate) the flakiness.
* summarize_context_three_requests_and_instructions - The test snapshots
server.received_requests() immediately after observing TaskComplete.
Because the OpenAI /v1/responses call is streamed, the HTTP request can
still be draining when that event fires, so wiremock occasionally
reports only two captured requests. Fix is to wait for async activity to
complete.
* archive_conversation_moves_rollout_into_archived_directory - times out
on a slow CI run. Mitigation is to increase timeout value from 10s to
20s.
Implements:
```
thread/list
thread/start
thread/resume
thread/archive
```
along with their integration tests. These are relatively light wrappers
around the existing core logic, and changes to core logic are minimal.
However, an improvement made for developer ergonomics:
- `thread/start` and `thread/resume` automatically attaches a
conversation listener internally, so clients don't have to make a
separate `AddConversationListener` call like they do today.
For consistency, also updated `model/list` and `feedback/upload` (naming
conventions, list API params).
Currently, when the access token expires, we attempt to use the refresh
token to acquire a new access token. This works most of the time.
However, there are situations where the refresh token is expired,
exhausted (already used to perform a refresh), or revoked. In those
cases, the current logic treats the error as transient and attempts to
retry it repeatedly.
This PR changes the token refresh logic to differentiate between
permanent and transient errors. It also changes callers to treat the
permanent errors as fatal rather than retrying them. And it provides
better error messages to users so they understand how to address the
problem. These error messages should also help us further understand why
we're seeing examples of refresh token exhaustion.
Here is the error message in the CLI. The same text appears within the
extension.
<img width="863" height="38" alt="image"
src="https://github.com/user-attachments/assets/7ffc0d08-ebf0-4900-b9a9-265064202f4f"
/>
I also correct the spelling of "Re-connecting", which shouldn't have a
hyphen in it.
Testing: I manually tested these code paths by adding temporary code to
programmatically cause my refresh token to be exhausted (by calling the
token refresh endpoint in a tight loop more than 50 times). I then
simulated an access token expiration, which caused the token refresh
logic to be invoked. I confirmed that the updated logic properly handled
the error condition.
Note: We earlier discussed the idea of forcefully logging out the user
at the point where token refresh failed. I made several attempts to do
this, and all of them resulted in a bad UX. It's important to surface
this error to users in a way that explains the problem and tells them
that they need to log in again. We also previously discussed deleting
the auth.json file when this condition is detected. That also creates
problems because it effectively changes the auth status from logged in
to logged out, and this causes odd failures and inconsistent UX. I think
it's therefore better not to delete auth.json in this case. If the user
closes the CLI or VSCE and starts it again, we properly detect that the
access token is expired and the refresh token is "dead", and we force
the user to go through the login flow at that time.
This should address aspects of #6191, #5679, and #5505
This is just a refactor of `conversation_history` file by breaking it up
into multiple smaller ones with helper. This refactor will help us move
more functionality related to context management here. in a clean way.
- introduce RenderableItem to support both owned and borrowed children
in composite Renderables
- refactor some of our gnarlier manual layouts, BottomPane and
ChatWidget, to use ColumnRenderable
- Renderable and friends now handle cursor_pos()
## Summary
- Adds `ModelReasoningEffort` type to TypeScript SDK with values:
`minimal`, `low`, `medium`, `high`
- Adds `modelReasoningEffort` option to `ThreadOptions`
- Forwards the option to the codex CLI via `--config
model_reasoning_effort="<value>"`
- Includes test coverage for the new option
## Changes
- `sdk/typescript/src/threadOptions.ts`: Define `ModelReasoningEffort`
type and add to `ThreadOptions`
- `sdk/typescript/src/index.ts`: Export `ModelReasoningEffort` type
- `sdk/typescript/src/exec.ts`: Forward `modelReasoningEffort` to CLI as
config flag
- `sdk/typescript/src/thread.ts`: Pass option through to exec (+ debug
logging)
- `sdk/typescript/tests/run.test.ts`: Add test for
`modelReasoningEffort` flag forwarding
---------
Co-authored-by: Eric Traut <etraut@openai.com>
Previously it was not possible for codex to run commands as the init
process (pid 1) in linux. Commands run in containers tend to see their
own pid as 1. See https://github.com/openai/codex/issues/4198
This pr implements the solution mentioned in that issue.
Co-authored-by: Eric Traut <etraut@openai.com>
Previously, the `nix build .#default` command fails due to a missing
output hash in the `./codex-rs/default.nix` for `crossterm-0.28.1`:
```
error: No hash was found while vendoring the git dependency crossterm-0.28.1. You can add
a hash through the `outputHashes` argument of `importCargoLock`:
outputHashes = {
"crossterm-0.28.1" = "<hash>";
};
If you use `buildRustPackage`, you can add this attribute to the `cargoLock`
attribute set.
```
This PR adds the missing hash:
```diff
cargoLock.outputHashes = {
"ratatui-0.29.0" = "sha256-HBvT5c8GsiCxMffNjJGLmHnvG77A6cqEL+1ARurBXho=";
+ "crossterm-0.28.1" = "sha256-6qCtfSMuXACKFb9ATID39XyFDIEMFDmbx6SSmNe+728=";
};
```
With this change, `nix build .#default` succeeds:
```
> nix build .#default --max-jobs 1 --cores 2
warning: Git tree '/home/lukas/r/github.com/lukasl-dev/codex' is dirty
[1/0/1 built] building codex-rs-0.1.0 (buildPhase)[1/0/1 built] building codex-rs-0.1.0 (buildP[1/0/1 built] building codex-rs-0.1.0 (buildPhase): [1/0/1 built] building codex-rs-0.1.0 (b[1/0/1 built] building codex-rs-0.1.0 (buildPhase): Compi[1/0/1 built] building codex-rs-0.1
> ./result/bin/codex
You are running Codex in /home/lukas/r/github.com/lukasl-dev/codex
Since this folder is version controlled, you may wish to allow Codex to work in this folder without asking for approval.
...
```
**Typescript and JSON schema exports**
While working on Thread/Turn/Items type definitions, I realize we will
run into name conflicts between v1 and v2 APIs (e.g. `RateLimitWindow`
which won't be reusable since v1 uses `RateLimitWindow` from `protocol/`
which uses snake_case, but we want to expose camelCase everywhere, so
we'll define a V2 version of that struct that serializes as camelCase).
To set us up for a clean and isolated v2 API, generate types into a
`v2/` namespace for both typescript and JSON schema.
- TypeScript: v2 types emit under `out_dir/v2/*.ts`, and root index.ts
now re-exports them via `export * as v2 from "./v2"`;.
- JSON Schemas: v2 definitions bundle under `#/definitions/v2/*` rather
than the root.
The location for the original types (v1 and types pulled from
`protocol/` and other core crates) haven't changed and are still at the
root. This is for backwards compatibility: no breaking changes to
existing usages of v1 APIs and types.
**Notifications**
While working on export.rs, I:
- refactored server/client notifications with macros (like we already do
for methods) so they also get exported (I noticed they weren't being
exported at all).
- removed the hardcoded list of types to export as JSON schema by
leveraging the existing macros instead
- and took a stab at API V2 notifications. These aren't wired up yet,
and I expect to iterate on these this week.
The deprecation message is currently a bit confusing. Users may not
understand what is `[features].x`. I updated the docs and the
deprecation message for more guidance.
---------
Co-authored-by: Gabriel Peal <gpeal@users.noreply.github.com>
## Summary
musl 1.2.5 includes [several fixes to DNS over
TCP](https://www.openwall.com/lists/musl/2024/03/01/2), which appears to
be the root cause of #6116.
This approach is a bit janky, but according to codex:
> On the Ubuntu 24.04 runners we use, apt-cache policy musl-tools shows
only the distro build (1.2.4-2ubuntu2)"
We should build with this version and confirm.
## Testing
- [ ] TODO: test and see if this fixes Azure issues
V2 for `account/updated` and `account/logout` for app server. correspond
to old `authStatusChange` and `LogoutChatGpt` respectively. Followup PRs
will make other v2 endpoints call `account/updated` instead of
`authStatusChange` too.
## Problem
The `is_api_message` function in `conversation_history.rs` had a
misalignment between its documentation and implementation:
- **Comment stated**: "Anything that is not a system message or
'reasoning' message is considered an API message"
- **Code behavior**: Was returning `true` for `ResponseItem::Reasoning`,
meaning reasoning messages were incorrectly treated as API messages
This inconsistency could lead to reasoning messages being persisted in
conversation history when they should be filtered out.
## Root Cause
Investigation revealed that reasoning messages are explicitly excluded
throughout the codebase:
1. **Chat completions API** (lines 267-272 in `chat_completions.rs`)
omits reasoning from conversation history:
```rust
ResponseItem::Reasoning { .. } | ResponseItem::Other => {
// Omit these items from the conversation history.
continue;
}
```
2. **Existing tests** like `drops_reasoning_when_last_role_is_user` and
`ignores_reasoning_before_last_user` validate that reasoning should be
excluded from API payloads
## Solution
Fixed the `is_api_message` function to align with its documentation and
the rest of the codebase:
```rust
// Before: Reasoning was incorrectly returning true
ResponseItem::Reasoning { .. } | ResponseItem::WebSearchCall { .. } => true,
// After: Reasoning correctly returns false
ResponseItem::WebSearchCall { .. } => true,
ResponseItem::Reasoning { .. } | ResponseItem::Other => false,
```
## Testing
- Enhanced existing test to verify reasoning messages are properly
filtered out
- All 264 core tests pass, including 8 chat completions tests that
validate reasoning behavior
- No regressions introduced
This ensures reasoning messages are consistently excluded from API
message processing across the entire codebase.
I have read the CLA Document and I hereby sign the CLA
Closes#4452
This fixes a usability issue where users with symlinked folders in their
working directory couldn't search those files using the `@` file search
feature.
## Rationale
The "bug" was in the file search implementation in
`codex-rs/file-search/src/lib.rs`. The `WalkBuilder` was using default
settings which don't follow symlinks, causing two related issues:
1. Partial search results: The `@` search would find symlinked
directories but couldn't find files inside them
2. Inconsistent behavior: Users expect symlinked folders to behave like
regular folders in search results.
## Root cause
The `ignore` crate's `WalkBuilder` defaults to `.follow_links(false)`
[[source](9802945e63/crates/ignore/src/walk.rs (L532))],
so when traversing the file system, it would:
- Detect symlinked directories as directory entries
- But not traverse into them to index their contents
- The `get_file_path` function would then filter out actual directories,
leaving only the symlinked folder itself as a result
Fix: Added `.follow_links(true)` to the `WalkBuilder` configuration,
making the file search follow symlinks and index their contents just
like regular directories.
This change maintains backward compatibility since symlink following is
generally expected behavior for file search tools, and it aligns with
how users expect the `@` search feature to work.
Co-authored-by: Eric Traut <etraut@openai.com>
I was missing an example config.toml, and following docs/config.md alone
was slower. I had GPT-5 scan the codebase for every accepted config key,
check the defaults, and generate a single example config.toml with
annotations. It lists all keys Codex reads from TOML, sets each to its
effective default where it exists, leaves optional ones commented, and
adds short comments on purpose and valid values. This should make
onboarding faster and reduce configuration errors. I can rename it to
config.example.toml or move it under docs/ if you prefer.
This fixes bug #6121.
The `input_messages` field passed to the notify handler is currently
empty because the logic is incorrectly including the OutputText rather
than InputText. I've fixed that and added proper filtering to remove
messages associated with AGENTS.md and other context injected by the
harness.
Testing: I wrote a notify handler and verified that the user prompt is
correctly passed through to the handler.
## Summary
- replace the word part enum with a simple `is_word_separator` helper
- keep word-boundary logic aligned with the helper and punctuation-aware
behavior
- extend forward/backward deletion tests to cover whitespace around
separators
## Testing
- just fix -p codex-tui
- cargo test -p codex-tui
------
https://chatgpt.com/codex/tasks/task_i_68f91c71d838832ca2a3c4f0ec1b55d4
This value is used to determine whether mid-turn compaction is required.
Reasoning items are only excluded between turns (and soon will start to
be preserved even across turns) so it's incorrect to subtract
reasoning_output_tokens mid term.
This will result in higher values reported between turns but we are also
looking into preserving reasoning items for the entire conversation to
improve performance and caching.
Error message for attempting to OAuth with a remote RCP is incorrect and
misleading. The correct config is
```
[features]
rmcp_client = true
```
Co-authored-by: Eric Traut <etraut@openai.com>
This pull request adds a new documentation section to explain the
available slash commands in Codex. The update introduces a clear
overview and a reference table for built-in commands, making it easier
for users to understand and utilize these features.
Documentation updates:
* Added a new section to `docs/slash_commands.md` describing what slash
commands are and listing all built-in commands with their purposes in a
formatted table.
Hi OpenAI Codex team, currently "Visit chatgpt.com/codex/settings/usage
for up-to-date information on rate limits and credits" message in status
card and error messages. For now, without the "https://" prefix, the
link cannot be clicked directly from most terminals or chat interfaces.
<img width="636" height="127" alt="Screenshot 2025-11-02 at 22 47 06"
src="https://github.com/user-attachments/assets/5ea11e8b-fb74-451c-85dc-f4d492b2678b"
/>
---
The fix is intent to improve this issue:
- It makes the link clickable in terminals that support it, hence better
accessibility
- It follows standard URL formatting practices
- It maintains consistency with other links in the application (like the
existing "https://openai.com/chatgpt/pricing" links)
Thank you!
Addresses issue https://github.com/openai/codex/issues/3582 where an
"archive conversation" command in the extension fails on Windows.
The problem is that the `archive_conversation` api server call is not
canonicalizing the path to the rollout path when performing its check to
verify that the rollout path is in the sessions directory. This causes
it to fail 100% of the time on Windows.
Testing: I was able to repro the error on Windows 100% prior to this
change. After the change, I'm no longer able to repro.
When I enable `experimental_sandbox_command_assessment`, I get an
incorrect deprecation warning: "experimental_sandbox_command_assessment
is deprecated. Use experimental_sandbox_command_assessment instead."
This PR fixes this error.
* Removed sandbox risk categories; feedback indicates that these are not
that useful and "less is more"
* Tweaked the assessment prompt to generate terser answers
* Fixed bug in orchestrator that prevents this feature from being
exposed in the extension
Fixes#4161
Currently Codex uses a regex to parse the "Please try again in 1.898s"
OpenAI-style rate limit message, so that it can wait the correct
duration before retrying. Azure OpenAI returns a different error that
looks like "Rate limit exceeded. Try again in 35 seconds."
This PR extends the regex and parsing code to match in a more fuzzy
manner, handling anything matching the pattern "try again in
\<duration>\<unit>".
## Summary
This PR fixes a broken self-referencing link in the contributing
documentation.
## Changes
- Removed the phrase 'Following the [development
setup](#development-workflow) instructions above' from the Development
workflow section
- The link referenced a non-existent section and the phrase didn't make
logical sense in context
## Before
The text referenced 'development setup instructions above' but:
1. No section called 'development setup' exists
2. There were no instructions 'above' that point
3. The link pointed to the same section it was in
## After
Simplified to: 'Ensure your change is free of lint warnings and test
failures.'
## Type
Documentation fix
I have read the CLA Document and I hereby sign the CLA
Co-authored-by: Ritesh Chauhan <sagar.chauhn11@gmail.com>
## Summary
Can never have enough tests on this code path - checking that json
inside a shell call is deserialized correctly.
## Tests
- [x] These are tests 😎
I finished reading “Getting Started,” but couldn’t find the
“Configuration” section in the README. After following the link, I
realized “Configuration” is in a separate file, so I updated the README
accordingly.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
Co-authored-by: Eric Traut <etraut@openai.com>
Bumps [indexmap](https://github.com/indexmap-rs/indexmap) from 2.10.0 to
2.11.4.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/indexmap-rs/indexmap/blob/main/RELEASES.md">indexmap's
changelog</a>.</em></p>
<blockquote>
<h2>2.11.4 (2025-09-18)</h2>
<ul>
<li>Updated the <code>hashbrown</code> dependency to a range allowing
0.15 or 0.16.</li>
</ul>
<h2>2.11.3 (2025-09-15)</h2>
<ul>
<li>Make the minimum <code>serde</code> version only apply when
"serde" is enabled.</li>
</ul>
<h2>2.11.2 (2025-09-15)</h2>
<ul>
<li>Switched the "serde" feature to depend on
<code>serde_core</code>, improving build
parallelism in cases where other dependents have enabled
"serde/derive".</li>
</ul>
<h2>2.11.1 (2025-09-08)</h2>
<ul>
<li>Added a <code>get_key_value_mut</code> method to
<code>IndexMap</code>.</li>
<li>Removed the unnecessary <code>Ord</code> bound on
<code>insert_sorted_by</code> methods.</li>
</ul>
<h2>2.11.0 (2025-08-22)</h2>
<ul>
<li>Added <code>insert_sorted_by</code> and
<code>insert_sorted_by_key</code> methods to <code>IndexMap</code>,
<code>IndexSet</code>, and <code>VacantEntry</code>, like customizable
versions of <code>insert_sorted</code>.</li>
<li>Added <code>is_sorted</code>, <code>is_sorted_by</code>, and
<code>is_sorted_by_key</code> methods to
<code>IndexMap</code> and <code>IndexSet</code>, as well as their
<code>Slice</code> counterparts.</li>
<li>Added <code>sort_by_key</code> and <code>sort_unstable_by_key</code>
methods to <code>IndexMap</code> and
<code>IndexSet</code>, as well as parallel counterparts.</li>
<li>Added <code>replace_index</code> methods to <code>IndexMap</code>,
<code>IndexSet</code>, and <code>VacantEntry</code>
to replace the key (or set value) at a given index.</li>
<li>Added optional <code>sval</code> serialization support.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="03f9e58626"><code>03f9e58</code></a>
Merge pull request <a
href="https://redirect.github.com/indexmap-rs/indexmap/issues/418">#418</a>
from a1phyr/hashbrown_0.16</li>
<li><a
href="ee6080d480"><code>ee6080d</code></a>
Release 2.11.4</li>
<li><a
href="a7da8f181e"><code>a7da8f1</code></a>
Use a range for hashbrown</li>
<li><a
href="0cd5aefb44"><code>0cd5aef</code></a>
Update <code>hashbrown</code> to 0.16</li>
<li><a
href="fd5c819daf"><code>fd5c819</code></a>
Merge pull request <a
href="https://redirect.github.com/indexmap-rs/indexmap/issues/417">#417</a>
from cuviper/release-2.11.3</li>
<li><a
href="9321145e1f"><code>9321145</code></a>
Release 2.11.3</li>
<li><a
href="7b485688c2"><code>7b48568</code></a>
Merge pull request <a
href="https://redirect.github.com/indexmap-rs/indexmap/issues/416">#416</a>
from cuviper/release-2.11.2</li>
<li><a
href="49ce7fa471"><code>49ce7fa</code></a>
Release 2.11.2</li>
<li><a
href="58fd834804"><code>58fd834</code></a>
Merge pull request <a
href="https://redirect.github.com/indexmap-rs/indexmap/issues/414">#414</a>
from DaniPopes/serde_core</li>
<li><a
href="5dc1d6ab31"><code>5dc1d6a</code></a>
Depend on <code>serde_core</code> instead of <code>serde</code></li>
<li>Additional commits viewable in <a
href="https://github.com/indexmap-rs/indexmap/compare/2.10.0...2.11.4">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Eric Traut <etraut@openai.com>
Bumps [anyhow](https://github.com/dtolnay/anyhow) from 1.0.99 to
1.0.100.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/dtolnay/anyhow/releases">anyhow's
releases</a>.</em></p>
<blockquote>
<h2>1.0.100</h2>
<ul>
<li>Teach clippy to lint formatting arguments in <code>bail!</code>,
<code>ensure!</code>, <code>anyhow!</code> (<a
href="https://redirect.github.com/dtolnay/anyhow/issues/426">#426</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="18c2598afa"><code>18c2598</code></a>
Release 1.0.100</li>
<li><a
href="f2719888cb"><code>f271988</code></a>
Merge pull request <a
href="https://redirect.github.com/dtolnay/anyhow/issues/426">#426</a>
from dtolnay/clippyfmt</li>
<li><a
href="52f2115a1f"><code>52f2115</code></a>
Mark macros with clippy::format_args</li>
<li><a
href="da5fd9d5a3"><code>da5fd9d</code></a>
Raise minimum tested compiler to rust 1.76</li>
<li><a
href="211e4092b7"><code>211e409</code></a>
Opt in to generate-macro-expansion when building on docs.rs</li>
<li><a
href="b48fc02c32"><code>b48fc02</code></a>
Enforce trybuild >= 1.0.108</li>
<li><a
href="d5f59fbd45"><code>d5f59fb</code></a>
Update ui test suite to nightly-2025-09-07</li>
<li><a
href="238415d25b"><code>238415d</code></a>
Update ui test suite to nightly-2025-08-24</li>
<li><a
href="3bab0709a3"><code>3bab070</code></a>
Update actions/checkout@v4 -> v5</li>
<li><a
href="42492546e3"><code>4249254</code></a>
Order cap-lints flag in the same order as thiserror build script</li>
<li>See full diff in <a
href="https://github.com/dtolnay/anyhow/compare/1.0.99...1.0.100">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Eric Traut <etraut@openai.com>
Bumps [thiserror](https://github.com/dtolnay/thiserror) from 2.0.16 to
2.0.17.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/dtolnay/thiserror/releases">thiserror's
releases</a>.</em></p>
<blockquote>
<h2>2.0.17</h2>
<ul>
<li>Use differently named __private module per patch release (<a
href="https://redirect.github.com/dtolnay/thiserror/issues/434">#434</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="72ae716e6d"><code>72ae716</code></a>
Release 2.0.17</li>
<li><a
href="599fdce83a"><code>599fdce</code></a>
Merge pull request <a
href="https://redirect.github.com/dtolnay/thiserror/issues/434">#434</a>
from dtolnay/private</li>
<li><a
href="9ec05f6b38"><code>9ec05f6</code></a>
Use differently named __private module per patch release</li>
<li><a
href="d2c492b549"><code>d2c492b</code></a>
Raise minimum tested compiler to rust 1.76</li>
<li><a
href="fc3ab9501d"><code>fc3ab95</code></a>
Opt in to generate-macro-expansion when building on docs.rs</li>
<li><a
href="819fe29dbb"><code>819fe29</code></a>
Update ui test suite to nightly-2025-09-12</li>
<li><a
href="259f48c549"><code>259f48c</code></a>
Enforce trybuild >= 1.0.108</li>
<li><a
href="470e6a681c"><code>470e6a6</code></a>
Update ui test suite to nightly-2025-08-24</li>
<li><a
href="544e191e6e"><code>544e191</code></a>
Update actions/checkout@v4 -> v5</li>
<li><a
href="cbc1ebad3e"><code>cbc1eba</code></a>
Delete duplicate cap-lints flag from build script</li>
<li>See full diff in <a
href="https://github.com/dtolnay/thiserror/compare/2.0.16...2.0.17">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
You can trigger a rebase of this PR by commenting `@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
> **Note**
> Automatic rebases have been disabled on this pull request as it has
been open for over 30 days.
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Eric Traut <etraut@openai.com>
## What?
Fixed error handling in `insert_history_lines_to_writer` where all
terminal operations were silently ignoring errors via `.ok()`.
## Why?
Silent I/O failures could leave the terminal in an inconsistent state
(e.g., scroll region not reset) with no way to debug. This violates Rust
error handling best practices.
## How?
- Changed function signature to return `io::Result<()>`
- Replaced all `.ok()` calls with `?` operator to propagate errors
- Added `tracing::warn!` in wrapper function for backward compatibility
- Updated 15 test call sites to handle Result with `.expect()`
## Testing
- ✅ Pass all tests
## Type of Change
- [x] Bug fix (non-breaking change)
---------
Signed-off-by: Huaiwu Li <lhwzds@gmail.com>
Co-authored-by: Eric Traut <etraut@openai.com>
we are seeing [reports](https://github.com/openai/codex/issues/6004) of
users having verbosity in their config.toml and facing issues.
gpt-5-codex doesn't accept other values rather than medium for
verbosity.
Fixes a Markdown parsing issue where a list item used `*` without a
following space (`*Line ranges ...`). Per CommonMark, a space after the
list marker is required. Updated to `* Line ranges ...` so the guideline
renders as a standalone bullet. This change improves readability and
prevents mis-parsing in renderers.
Co-authored-by: Eric Traut <etraut@openai.com>
## Summary
- add the `/exit` slash command alongside `/quit` and reuse shared exit
handling
- refactor the chat widget to funnel quit, exit, logout, and shutdown
flows through a common `request_exit` helper
- add focused unit tests that confirm both `/quit` and `/exit` send an
`ExitRequest`
## Testing
- `just fmt`
- `just fix -p codex-tui`
- `cargo test -p codex-tui`
------
https://chatgpt.com/codex/tasks/task_i_6903d5a8f47c8321bf180f031f2fa330
- Added the new codex-windows-sandbox crate that builds both a library
entry point (run_windows_sandbox_capture) and a CLI executable to launch
commands inside a Windows restricted-token sandbox, including ACL
management, capability SID provisioning, network lockdown, and output
capture
(windows-sandbox-rs/src/lib.rs:167, windows-sandbox-rs/src/main.rs:54).
- Introduced the experimental WindowsSandbox feature flag and wiring so
Windows builds can opt into the sandbox:
SandboxType::WindowsRestrictedToken, the in-process execution path, and
platform sandbox selection now honor the flag (core/src/features.rs:47,
core/src/config.rs:1224, core/src/safety.rs:19,
core/src/sandboxing/mod.rs:69, core/src/exec.rs:79,
core/src/exec.rs:172).
- Updated workspace metadata to include the new crate and its
Windows-specific dependencies so the core crate can link against it
(codex-rs/
Cargo.toml:91, core/Cargo.toml:86).
- Added a PowerShell bootstrap script that installs the Windows
toolchain, required CLI utilities, and builds the workspace to ease
development
on the platform (scripts/setup-windows.ps1:1).
- Landed a Python smoke-test suite that exercises
read-only/workspace-write policies, ACL behavior, and network denial for
the Windows sandbox
binary (windows-sandbox-rs/sandbox_smoketests.py:1).
# Summary
This PR is related to the Issue #3978 and contains a fix to the seatbelt
profile for macOS that allows to run java/jdk tooling from the sandbox.
I have found that the included change is the minimum change to make it
run on my machine.
There is a unit test added by codex when making this fix. I wonder if it
is useful since you need java installed on the target machine for it to
be relevant. I can remove it it is better.
Fixes#3978
There's still some debate about whether we want to expose
`tools.view_image` or `feature.view_image` so those are left unchanged
for now, but this old `include_view_image_tool` config is good-to-go.
Also updated the doc to reflect that `view_image` tool is now by default
true.
Pull request template, minimal:
---
### **What?**
Minor change (low-hanging fruit).
### **Why?**
To improve code quality or documentation with minimal risk and effort.
### **How?**
Edited directly via VSCode Editor.
---
**Checklist (pre-PR):**
* [x] I have read the CLA Document and hereby sign the CLA.
* [x] I reviewed the “Contributing” markdown file for this project.
*This template meets standard external (non-OpenAI) PR requirements and
signals compliance for maintainers.*
Co-authored-by: Eric Traut <etraut@openai.com>
We had this annotation everywhere in app-server APIs which made it so
that fields get serialized as `field?: T`, meaning if the field as
`None` we would omit the field in the payload. Removing this annotation
changes it so that we return `field: T | null` instead, which makes
codex app-server's API more aligned with the convention of public OpenAI
APIs like Responses.
Separately, remove the `#[ts(optional_fields = nullable)]` annotations
that were recently added which made all the TS types become `field?: T |
null` which is not great since clients need to handle undefined and
null.
I think generally it'll be best to have optional types be either:
- `field: T | null` (preferred, aligned with public OpenAI APIs)
- `field?: T` where we have to, such as types generated from the MCP
schema:
https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2025-06-18/schema.ts
(see changes to `mcp-types/`)
I updated @etraut-openai's unit test to check that all generated TS
types are one or the other, not both (so will error if we have a type
that has `field?: T | null`). I don't think there's currently a good use
case for that - but we can always revisit.
## Summary
Duplicates the tests in `apply_patch_cli.rs`, but tests the freeform
apply_patch tool as opposed to the function call path. The good news is
that all the tests pass with zero logical tests, with the exception of
the heredoc, which doesn't really make sense in the freeform tool
context anyway.
@jif-oai since you wrote the original tests in #5557, I'd love your
opinion on the right way to DRY these test cases between the two. Happy
to set up a more sophisticated harness, but didn't want to go down the
rabbit hole until we agreed on the right pattern
## Testing
- [x] These are tests
## Summary
- add a debug-only `/rollout` slash command that prints the rollout file
path or reports when none is known
- surface the new command in the slash command metadata and cover it
with unit tests
<img width="539" height="99" alt="image"
src="https://github.com/user-attachments/assets/688e1334-8a06-4576-abb8-ada33b458661"
/>
## Summary
- re-enable the TypeScript SDK test that verifies local images are
forwarded to `codex exec`
## Testing
- `pnpm test` *(fails: unable to download pnpm 10.8.1 because external
network access is blocked in the sandbox)*
------
https://chatgpt.com/codex/tasks/task_i_690289cb861083209fd006867e2adfb1
Adds AgentMessageContentDelta, ReasoningContentDelta,
ReasoningRawContentDelta item streaming events while maintaining
compatibility for old events.
---------
Co-authored-by: Owen Lin <owen@openai.com>
In this PR, I am exploring migrating task kind to an invocation of
Codex. The main reason would be getting rid off multiple
`ConversationHistory` state and streamlining our context/history
management.
This approach depends on opening a channel between the sub-codex and
codex. This channel is responsible for forwarding `interactive`
(`approvals`) and `non-interactive` events. The `task` is responsible
for handling those events.
This opens the door for implementing `codex as a tool`, replacing
`compact` and `review`, and potentially subagents.
One consideration is this code is very similar to `app-server` specially
in the approval part. If in the future we wanted an interactive
`sub-codex` we should consider using `codex-mcp`
The goal is to have a single place where we actually write files
In a follow-up PR, will move everything config related in a dedicated
module and move the helpers in a dedicated file
We currently have nested enums when sending raw response items in the
app-server protocol. This makes downstream schemas confusing because we
need to embed `type`-discriminated enums within each other.
This PR adds a small wrapper around the response item so we can keep the
schemas separate
This PR addresses a current hole in the TypeScript code generation for
the API server protocol. Fields that are marked as "Optional<>" in the
Rust code are serialized such that the value is omitted when it is
deserialized — appearing as `undefined`, but the TS type indicates
(incorrectly) that it is always defined but possibly `null`. This can
lead to subtle errors that the TypeScript compiler doesn't catch. The
fix is to include the `#[ts(optional_fields = nullable)]` macro for all
protocol structs that contain one or more `Optional<>` fields.
This PR also includes a new test that validates that all TS protocol
code containing "| null" in its type is marked optional ("?") to catch
cases where `#[ts(optional_fields = nullable)]` is omitted.
feature: Add "!cmd" user shell execution
This change lets users run local shell commands directly from the TUI by
prefixing their input with ! (e.g. !ls). Output is truncated to keep the
exec cell usable, and Ctrl-C cleanly
interrupts long-running commands (e.g. !sleep 10000).
**Summary of changes**
- Route Op::RunUserShellCommand through a dedicated UserShellCommandTask
(core/src/tasks/user_shell.rs), keeping the task logic out of codex.rs.
- Reuse the existing tool router: the task constructs a ToolCall for the
local_shell tool and relies on ShellHandler, so no manual MCP tool
lookup is required.
- Emit exec lifecycle events (ExecCommandBegin/ExecCommandEnd) so the
TUI can show command metadata, live output, and exit status.
**End-to-end flow**
**TUI handling**
1. ChatWidget::submit_user_message (TUI) intercepts messages starting
with !.
2. Non-empty commands dispatch Op::RunUserShellCommand { command };
empty commands surface a help hint.
3. No UserInput items are created, so nothing is enqueued for the model.
**Core submission loop**
4. The submission loop routes the op to handlers::run_user_shell_command
(core/src/codex.rs).
5. A fresh TurnContext is created and Session::spawn_user_shell_command
enqueues UserShellCommandTask.
**Task execution**
6. UserShellCommandTask::run emits TaskStartedEvent, formats the
command, and prepares a ToolCall targeting local_shell.
7. ToolCallRuntime::handle_tool_call dispatches to ShellHandler.
**Shell tool runtime**
8. ShellHandler::run_exec_like launches the process via the unified exec
runtime, honoring sandbox and shell policies, and emits
ExecCommandBegin/End.
9. Stdout/stderr are captured for the UI, but the task does not turn the
resulting ToolOutput into a model response.
**Completion**
10. After ExecCommandEnd, the task finishes without an assistant
message; the session marks it complete and the exec cell displays the
final output.
**Conversation context**
- The command and its output never enter the conversation history or the
model prompt; the flow is local-only.
- Only exec/task events are emitted for UI rendering.
**Demo video**
https://github.com/user-attachments/assets/fcd114b0-4304-4448-a367-a04c43e0b996
Found that the VS Code Codex extension throws “Error starting
conversation” when initializing a conversation with Git for Windows’
bash on PATH.
Debugging showed the bash-detection logic did not return as expected;
this change makes it reliable in that scenario.
Possibly related to issue #2841.
# Preserve PATH precedence & fix Windows MCP env propagation
## Problem & intent
Preserve user PATH precedence and reduce Windows setup friction for MCP
servers by avoiding PATH reordering and ensuring Windows child processes
receive essential env vars.
- Addresses: #4180#5225#2945#3245#3385#2892#3310#3457#4370
- Supersedes: #4182, #3866, #3828 (overlapping/inferior once this
merges)
- Notes: #2626 / #2646 are the original PATH-mutation sources being
corrected.
---
## Before / After
**Before**
- PATH was **prepended** with an `apply_patch` helper dir (Rust + Node
wrapper), reordering tools and breaking virtualenvs/shims on
macOS/Linux.
- On Windows, MCP servers missed core env vars and often failed to start
without explicit per-server env blocks.
**After**
- Helper dir is **appended** to PATH (preserves user/tool precedence).
- Windows MCP child env now includes common core variables and mirrors
`PATH` → `Path`, so typical CLIs/plugins work **without** per-server env
blocks.
---
## Scope of change
### `codex-rs/arg0/src/lib.rs`
- Append temp/helper dir to `PATH` instead of prepending.
### `codex-cli/bin/codex.js`
- Mirror the same append behavior for the Node wrapper.
### `codex-rs/rmcp-client/src/utils.rs`
- Expand Windows `DEFAULT_ENV_VARS` (e.g., `COMSPEC`, `SYSTEMROOT`,
`PROGRAMFILES*`, `APPDATA`, etc.).
- Mirror `PATH` → `Path` for Windows child processes.
- Small unit test; conditional `mut` + `clippy` cleanup.
---
## Security effects
No broadened privileges. Only environment propagation for well-known
Windows keys on stdio MCP child processes. No sandbox policy changes and
no network additions.
---
## Testing evidence
**Static**
- `cargo fmt`
- `cargo clippy -p codex-arg0 -D warnings` → **clean**
- `cargo clippy -p codex-rmcp-client -D warnings` → **clean**
- `cargo test -p codex-rmcp-client` → **13 passed**
**Manual**
- Local verification on Windows PowerShell 5/7 and WSL (no `unused_mut`
warnings on non-Windows targets).
---
## Checklist
- [x] Append (not prepend) helper dir to PATH in Rust and Node wrappers
- [x] Windows MCP child inherits core env vars; `PATH` mirrored to
`Path`
- [x] `cargo fmt` / `clippy` clean across touched crates
- [x] Unit tests updated/passing where applicable
- [x] Cross-platform behavior preserved (macOS/Linux PATH precedence
intact)
This PR adds an option to app server to allow conversation summaries to
be fetched from just the conversation id rather than rollout path for
convenience at the cost of some latency to discover the rollout path.
This convenience is non-trivial as it allows app servers to simply
maintain conversation ids rather than rollout paths and the associated
platform (Windows) handling associated with storing and encoding them
correctly.
Follow-up to https://github.com/openai/codex/pull/5063
Refined the app-server export pipeline so JSON Schema variants and
discriminator fields are annotated with descriptive, stable titles
before writing the bundle. This eliminates anonymous enum names in the
generated Pydantic models (goodbye Type7) while keeping downstream
tooling simple. Added shared helpers to derive titles and literals, and
reused them across the traversal logic for clarity. Running just fix -p
codex-app-server-protocol, just fmt, and cargo test -p
codex-app-server-protocol validates the change.
solves: https://github.com/openai/codex/issues/5675
Block non-image uploads in the view_image workflow. We now confirm the
file’s MIME is image/* before building the data URL; otherwise we emit a
“unsupported MIME type” error to the model. This stops the agent from
sending application/json blobs that the Responses API rejects with 400s.
<img width="409" height="556" alt="Screenshot 2025-10-28 at 1 15 10 PM"
src="https://github.com/user-attachments/assets/a92199e8-2769-4b1d-8e33-92d9238c90fe"
/>
Addresses https://github.com/openai/codex/issues/5773
Testing: I tested that images work (regardless of order that they are
associated with the task prompt) in both the CLI and Extension. Also
verified that conversations in CLI and extension with images can be
resumed.
This fixes an issue where messages sent during the final response stream
would seem to disappear, because the "queued messages" UI wasn't shown
during streaming.
There's a lot of visual noise in app-server's integration tests due to
the number of `.expect("<some_msg>")` lines which are largely redundant
/ not very useful. Clean them up by using `anyhow::Result` + `?`
consistently.
Replaces the existing pattern of:
```
let codex_home = TempDir::new().expect("create temp dir");
create_config_toml(codex_home.path()).expect("write config.toml");
let mut mcp = McpProcess::new(codex_home.path())
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("initialize timeout")
.expect("initialize request");
```
With:
```
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path())?;
let mut mcp = McpProcess::new(codex_home.path()).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
```
This PR is a follow-up to #5591. It allows users to choose which auth
storage mode they want by using the new
`cli_auth_credentials_store_mode` config.
## Summary
- Coerce Windows `workspace-write` configs back to read-only, surface
the forced downgrade in the approvals popup,
and funnel users toward WSL or Full Access.
- Add WSL installation instructions to the Auto preset on Windows while
keeping the preset available for other
platforms.
- Skip the trust-on-first-run prompt on native Windows so new folders
remain read-only without additional
confirmation.
- Expose a structured sandbox policy resolution from config to flag
Windows downgrades and adjust tests (core,
exec, TUI) to reflect the new behavior; provide a Windows-only approvals
snapshot.
## Testing
- cargo fmt
- cargo test -p codex-core
config::tests::add_dir_override_extends_workspace_writable_roots
- cargo test -p codex-exec
suite::resume::exec_resume_preserves_cli_configuration_overrides
- cargo test -p codex-tui
chatwidget::tests::approvals_selection_popup_snapshot
- cargo test -p codex-tui
approvals_popup_includes_wsl_note_for_auto_mode
- cargo test -p codex-tui windows_skips_trust_prompt
- just fix -p codex-core
- just fix -p codex-tui
fixing drag/drop photos bug in codex
state of the world before:
sometimes, when you drag screenshots into codex, the image does not
properly render into context. instead, the file name is shown in
quotation marks.
https://github.com/user-attachments/assets/3c0e540a-505c-4ec0-b634-e9add6a73119
the screenshot is not actually included in agent context. the agent
needs to manually call the view_image tool to see the screenshot. this
can be unreliable especially if the image is part of a longer prompt and
is dependent on the agent going out of its way to view the image.
state of the world after:
https://github.com/user-attachments/assets/5f2b7bf7-8a3f-4708-85f3-d68a017bfd97
now, images will always be directly embedded into chat context
## Technical Details
- MacOS sends screenshot paths with a narrow no‑break space right before
the “AM/PM” suffix, which used to trigger our non‑ASCII fallback in the
paste burst detector.
- That fallback flushed the partially buffered paste immediately, so the
path arrived in two separate `handle_paste` calls (quoted prefix +
`PM.png'`). The split string could not be normalized to a real path, so
we showed the quoted filename instead of embedding the image.
- We now append non‑ASCII characters into the burst buffer when a burst
is already active. Finder’s payload stays intact, the path normalizes,
and the image attaches automatically.
- When no burst is active (e.g. during IME typing), non‑ASCII characters
still bypass the buffer so text entry remains responsive.
It's pretty amazing we have gotten here without the ability for the
model to see image content from MCP tool calls.
This PR builds off of 4391 and fixes#4819. I would like @KKcorps to get
adequete credit here but I also want to get this fix in ASAP so I gave
him a week to update it and haven't gotten a response so I'm going to
take it across the finish line.
This test highlights how absured the current situation is. I asked the
model to read this image using the Chrome MCP
<img width="2378" height="674" alt="image"
src="https://github.com/user-attachments/assets/9ef52608-72a2-4423-9f5e-7ae36b2b56e0"
/>
After this change, it correctly outputs:
> Captured the page: image dhows a dark terminal-style UI labeled
`OpenAI Codex (v0.0.0)` with prompt `model: gpt-5-codex medium` and
working directory `/codex/codex-rs`
(and more)
Before this change, it said:
> Took the full-page screenshot you asked for. It shows a long,
horizontally repeating pattern of stylized people in orange, light-blue,
and mustard clothing, holding hands in alternating poses against a white
background. No text or other graphics-just rows of flat illustration
stretching off to the right.
Without this change, the Figma, Playwright, Chrome, and other visual MCP
servers are pretty much entirely useless.
I tested this change with the openai respones api as well as a third
party completions api
Makes sense to move this struct to `app-server-protocol/` since we want
to serialize as camelCase, but we don't for structs defined in
`protocol/`
It was:
```
export type Account = { "type": "ApiKey", api_key: string, } | { "type": "chatgpt", email: string | null, plan_type: PlanType, };
```
But we want:
```
export type Account = { "type": "apiKey", apiKey: string, } | { "type": "chatgpt", email: string | null, planType: PlanType, };
```
move the truncation logic to conversation history to use on any tool
output. This will help us in avoiding edge cases while truncating the
tool calls and mcp calls.
Follow-up PR to #5569. Add Keyring Support for Auth Storage in Codex CLI
as well as a hybrid mode (default to persisting in keychain but fall
back to file when unavailable.)
It also refactors out the keyringstore implementation from rmcp-client
[here](https://github.com/openai/codex/blob/main/codex-rs/rmcp-client/src/oauth.rs)
to a new keyring-store crate.
There will be a follow-up that picks the right credential mode depending
on the config, instead of hardcoding `AuthCredentialsStoreMode::File`.
This PR introduces a new `Auth Storage` abstraction layer that takes
care of read, write, and load of auth tokens based on the
AuthCredentialsStoreMode. It is similar to how we handle MCP client
oauth
[here](https://github.com/openai/codex/blob/main/codex-rs/rmcp-client/src/oauth.rs).
Instead of reading and writing directly from disk for auth tokens, Codex
CLI workflows now should instead use this auth storage using the public
helper functions.
This PR is just a refactor of the current code so the behavior stays the
same. We will add support for keyring and hybrid mode in follow-up PRs.
I have read the CLA Document and I hereby sign the CLA
This PR does the following:
1. Changes `try_refresh_token` to handle the case where the endpoint
returns a response without an `id_token`. The OpenID spec indicates that
this field is optional and clients should not assume it's present.
2. Changes the `attempt_stream_responses` to propagate token refresh
errors rather than silently ignoring them.
3. Fixes a typo in a couple of error messages (unrelated to the above,
but something I noticed in passing) - "reconnect" should be spelled
without a hyphen.
This PR does not implement the additional suggestion from @pakrym-oai
that we should sign out when receiving `refresh_token_expired` from the
refresh endpoint. Leaving this as a follow-on because I'm undecided on
whether this should be implemented in `try_refresh_token` or its
callers.
This adds an RPC to the app server to the the `ConversationSummary` via
a rollout path. Now that the VS Code extension supports showing the
Codex UI in an editor panel where the URI of the panel maps to the
rollout file, we need to be able to get the `ConversationSummary` from
the rollout file directly.
An AppServer client should be able to use any (`model_provider`, `model`) in the user's config. `NewConversationParams` already supported specifying the `model`, but this PR expands it to support `model_provider`, as well.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/5793).
* #5803
* __->__ #5793
Because conversations that use the Responses API can have encrypted
reasoning messages, trying to resume a conversation with a different
provider could lead to confusing "failed to decrypt" errors. (This is
reproducible by starting a conversation using ChatGPT login and resuming
it as a conversation that uses OpenAI models via Azure.)
This changes `ListConversationsParams` to take a `model_providers:
Option<Vec<String>>` and adds `model_provider` on each
`ConversationSummary` it returns so these cases can be disambiguated.
Note this ended up making changes to
`codex-rs/core/src/rollout/tests.rs` because it had a number of cases
where it expected `Some` for the value of `next_cursor`, but the list of
rollouts was complete, so according to this docstring:
bcd64c7e72/codex-rs/app-server-protocol/src/protocol.rs (L334-L337)
If there are no more items to return, then `next_cursor` should be
`None`. This PR updates that logic.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/5658).
* #5803
* #5793
* __->__ #5658
Revert #5642 because this generates:
```
// GENERATED CODE! DO NOT MODIFY BY HAND!
// This file was generated by [ts-rs](https://github.com/Aleph-Alpha/ts-rs). Do not edit this file manually.
export type GetAccountResponse = Account | null;
```
But `Account` is unknown.
The unique use of `#[ts(export)]` on `GetAccountResponse` is also
suspicious as are the changes to
`codex-rs/app-server-protocol/src/export.rs` since the existing system
has worked fine for quite some time.
Though a pure backout of #5642 puts things in a state where, as the PR
noted, the following does not work:
```
cargo run -p codex-app-server-protocol --bin export -- --out DIR
```
So in addition to the backout, this PR adds:
```rust
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
pub struct GetAccountResponse {
pub account: Account,
}
```
and changes `GetAccount.response` as follows:
```diff
- response: Option<Account>,
+ response: GetAccountResponse,
```
making it consistent with other types.
With this change, I verified that both of the following work:
```
just codex generate-ts --out /tmp/somewhere
cargo run -p codex-app-server-protocol --bin export -- --out /tmp/somewhere-else
```
The generated TypeScript is as follows:
```typescript
// GetAccountResponse.ts
import type { Account } from "./Account";
export type GetAccountResponse = { account: Account, };
```
and
```typescript
// Account.ts
import type { PlanType } from "./PlanType";
export type Account = { "type": "ApiKey", api_key: string, } | { "type": "chatgpt", email: string | null, plan_type: PlanType, };
```
Though while the inconsistency between `"type": "ApiKey"` and `"type":
"chatgpt"` is quite concerning, I'm not sure if that format is ever
written to disk in any case, but @owenlin0, I would recommend looking
into that.
Also, it appears that the types in `codex-rs/protocol/src/account.rs`
are used exclusively by the `app-server-protocol` crate, so perhaps they
should just be moved there?
Currently, `approval_policy` is supported in profiles, but
`sandbox_mode` is not. This PR adds support for `sandbox_mode`.
Note: a fix for this was submitted in [this
PR](https://github.com/openai/codex/pull/2397), but the underlying code
has changed significantly since then.
This addresses issue #3034
This PR fixes a test that is sporadically failing in CI.
The problem is that two unit tests (the older `login_and_cancel_chatgpt`
and a recently added
`login_chatgpt_includes_forced_workspace_query_param`) exercise code
paths that start the login server. The server binds to a hard-coded
localhost port number, so attempts to start more than one server at the
same time will fail. If these two tests happen to run concurrently, one
of them will fail.
To fix this, I've added a simple mutex. We can use this same mutex for
future tests that use the same pattern.
This PR adds support for a model-based summary and risk assessment for
commands that violate the sandbox policy and require user approval. This
aids the user in evaluating whether the command should be approved.
The feature works by taking a failed command and passing it back to the
model and asking it to summarize the command, give it a risk level (low,
medium, high) and a risk category (e.g. "data deletion" or "data
exfiltration"). It uses a new conversation thread so the context in the
existing thread doesn't influence the answer. If the call to the model
fails or takes longer than 5 seconds, it falls back to the current
behavior.
For now, this is an experimental feature and is gated by a config key
`experimental_sandbox_command_assessment`.
Here is a screen shot of the approval prompt showing the risk assessment
and summary.
<img width="723" height="282" alt="image"
src="https://github.com/user-attachments/assets/4597dd7c-d5a0-4e9f-9d13-414bd082fd6b"
/>
The API schema export is currently broken:
```
> cargo run -p codex-app-server-protocol --bin export -- --out DIR
Error: this type cannot be exported
```
This PR fixes the error message so we get more info:
```
> cargo run -p codex-app-server-protocol --bin export -- --out DIR
Error: failed to export client responses: dependency core::option::Option<codex_protocol::account::Account> cannot be exported
```
And fixes the root cause which is the `account/read` response.
## Summary
- wrap the default reqwest::Client inside a new
CodexHttpClient/CodexRequestBuilder pair and log the HTTP method, URL,
and status for each request
- update the auth/model/provider plumbing to use the new builder helpers
so headers and bearer auth continue to be applied consistently
- add the shared `http` dependency that backs the header conversion
helpers
## Testing
- `CODEX_SANDBOX=seatbelt CODEX_SANDBOX_NETWORK_DISABLED=1 cargo test -p
codex-core`
- `CODEX_SANDBOX=seatbelt CODEX_SANDBOX_NETWORK_DISABLED=1 cargo test -p
codex-chatgpt`
- `CODEX_SANDBOX=seatbelt CODEX_SANDBOX_NETWORK_DISABLED=1 cargo test -p
codex-tui`
------
https://chatgpt.com/codex/tasks/task_i_68fa5038c17483208b1148661c5873be
1. I have seen too many reports of people hitting startup timeout errors
and thinking Codex is broken. Hopefully this will help people
self-serve. We may also want to consider raising the timeout to ~15s.
2. Make it more clear what PAT is (personal access token) in the GitHub
error
<img width="2378" height="674" alt="CleanShot 2025-10-23 at 22 05 06"
src="https://github.com/user-attachments/assets/d148ce1d-ade3-4511-84a4-c164aefdb5c5"
/>
I want to centralize input processing and management to
`ConversationHistory`. This would need `ConversationHistory` to have
access to `token_info` (i.e. preventing adding a big input to the
history). Besides, it makes more sense to have it on
`ConversationHistory` than `state`.
Walk the sessions tree instead of using file_search so gitignored
CODEX_HOME directories can resume sessions. Add a regression test that
covers a .gitignore'd sessions directory.
Fixes#5247Fixes#5412
---------
Co-authored-by: Owen Lin <owen@openai.com>
Currently we collect all all turn items in a vector, then we add it to
the history on success. This result in losing those items on errors
including aborting `ctrl+c`.
This PR:
- Adds the ability for the tool call to handle cancellation
- bubble the turn items up to where we are recording this info
Admittedly, this logic is an ad-hoc logic that doesn't handle a lot of
error edge cases. The right thing to do is recording to the history on
the spot as `items`/`tool calls output` come. However, this isn't
possible because of having different `task_kind` that has different
`conversation_histories`. The `try_run_turn` has no idea what thread are
we using. We cannot also pass an `arc` to the `conversation_histories`
because it's a private element of `state`.
That's said, `abort` is the most common case and we should cover it
until we remove `task kind`
This shows the aggregated (stdout + stderr) buffer regardless of exit
code.
Many commands output useful / relevant info on stdout when returning a
non-zero exit code, or the same on stderr when returning an exit code of
0. Often, useful info is present on both stdout AND stderr. Also, the
model sees both. So it is confusing to see commands listed as "(no
output)" that in fact do have output, just on the stream that doesn't
match the exit status, or to see some sort of trivial output like "Tests
failed" but lacking any information about the actual failure.
As such, always display the aggregated output in the display. Transcript
mode remains unchanged as it was already displaying the text that the
model sees, which seems correct for transcript mode.
These are the schema definitions for the new JSON-RPC APIs associated
with accounts. These are not wired up to business logic yet and will
currently throw an internal error indicating these are unimplemented.
- ensure paste burst flush preserves ASCII characters before IME commits
- add regression test covering digit followed by Japanese text
submission
Fixesopenai/codex#4356
Co-authored-by: Josh McKinney <joshka@openai.com>
Codex will now send an `account/rateLimits/updated` notification
whenever the user's rate limits are updated.
This is implemented by just transforming the existing TokenCount event.
We are doing some ad-hoc logic while dealing with conversation history.
Ideally, we shouldn't mutate `vec[responseitem]` manually at all and
should depend on `ConversationHistory` for those changes.
Those changes are:
- Adding input to the history
- Removing items from the history
- Correcting history
I am also adding some `error` logs for cases we shouldn't ideally face.
For example, we shouldn't be missing `toolcalls` or `outputs`. We
shouldn't hit `ContextWindowExceeded` while performing `compact`
This refactor will give us granular control over our context management.
I haven't heard of any issues with the studio rmcp client so let's
remove the legacy one and default to the new one.
Any code changes are moving code from the adapter inline but there
should be no meaningful functionality changes.
1. Adds AgentMessage, Reasoning, WebSearch items.
2. Switches the ResponseItem parsing to use new items and then also emit
3. Removes user-item kind and filters out "special" (environment) user
items when returning to clients.
## What
- Add the `--cask` flag to the Homebrew update command for Codex.
## Why
- `brew upgrade codex` alone does not update the cask, so users were not
getting the right upgrade instructions.
## How
- Update `UpdateAction::BrewUpgrade` in `codex-rs/tui/src/updates.rs` to
use `upgrade --cask codex`.
## Testing
- [x] cargo test -p codex-tui
Co-authored-by: Thibault Sottiaux <tibo@openai.com>
While we do not want to encourage users to hardcode secrets in their
`config.toml` file, it should be possible to pass an API key
programmatically. For example, when using `codex app-server`, it is
possible to pass a "bag of configuration" as part of the
`NewConversationParams`:
682d05512f/codex-rs/app-server-protocol/src/protocol.rs (L248-L251)
When using `codex app-server`, it's not practical to change env vars of
the `codex app-server` process on the fly (which is how we usually read
API key values), so this helps with that.
## Summary
- make the plan tool available by default by removing the feature flag
and always registering the handler
- drop plan-tool CLI and API toggles across the exec, TUI, MCP server,
and app server code paths
- update tests and configs to reflect the always-on plan tool and guard
workspace restriction tests against env leakage
## Testing
Manually tested the extension.
------
https://chatgpt.com/codex/tasks/task_i_68f67a3ff2d083209562a773f814c1f9
This #[serial] approach is not ideal. I am tracking a separate issue to
create an injectable env var provider but I want to fix these tests
first.
Fixes#5447
Today `sub_id` is an ID of a single incoming Codex Op submition. We then
associate all events triggered by this operation using the same
`sub_id`.
At the same time we are also creating a TurnContext per submission and
we'd like to start associating some events (item added/item completed)
with an entire turn instead of just the operation that started it.
Using turn context when sending events give us flexibility to change
notification scheme.
Expose the session cwd in the notify payload and update docs so scripts
and extensions receive the real project path; users get accurate
project-aware notifications in CLI and VS Code.
Fixes#5387
Because the GitHub MCP is one of the most popular MCPs and it
confusingly doesn't support OAuth, we should make it more clear how to
make it work so people don't think Codex is broken.
Without proper `zsh -lc` parsing, we lose some things like proper
command parsing, turn diff tracking, safe command checks, and other
things we expect from raw or `bash -lc` commands.
Some MCP servers expose a lot of tools. In those cases, it is reasonable
to allow/denylist tools for Codex to use so it doesn't get overwhelmed
with too many tools.
The new configuration options available in the `mcp_server` toml table
are:
* `enabled_tools`
* `disabled_tools`
Fixes#4796
Adds a `GET account/rateLimits/read` API to app-server. This calls the
codex backend to fetch the user's current rate limits.
This would be helpful in checking rate limits without having to send a
message.
For calling the codex backend usage API, I generated the types and
manually copied the relevant ones into `codex-backend-openapi-types`.
It'll be nice to extend our internal openapi generator to support Rust
so we don't have to run these manual steps.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
We don't instruct the model to use citations, so it never emits them.
Further, ratatui [doesn't currently support rendering links into the
terminal with OSC 8](https://github.com/ratatui/ratatui/issues/1028), so
even if we did parse citations, we can't correctly render them.
So, remove all the code related to rendering them.
Adds a new ItemStarted event and delivers UserMessage as the first item
type (more to come).
Renames `InputItem` to `UserInput` considering we're using the `Item`
suffix for actual items.
The backend will be returning unix timestamps (seconds since epoch)
instead of RFC 3339 strings. This will make it more ergonomic for
developers to integrate against - no string parsing.
Add shared helper to format warnings when add-dir is incompatible with
the sandbox. Surface the warning in the TUI entrypoint and document the
limitation for add-dir.
Add annotations and an export script that let us generate app-server
protocol types as typescript and JSONSchema.
The script itself is a bit hacky because we need to manually label some
of the types. Unfortunately it seems that enum variants don't get good
names by default and end up with something like `EventMsg1`,
`EventMsg2`, etc. I'm not an expert in this by any means, but since this
is only run manually and we already need to enumerate the types required
to describe the protocol, it didn't seem that much worse. An ideal
solution here would be to have some kind of root that we could generate
schemas for in one go, but I'm not sure if that's compatible with how we
generate the protocol today.
Extends shell wrapper stripping in TUI to handle `zsh -lc` in addition
to `bash -lc`.
Currently, Linux users (and macOS users with zsh profiles) see cluttered
command headers like `• Ran zsh -lc "echo hello"` instead of `• Ran echo
hello`. This happens because `codex-rs/tui/src/exec_command.rs` only
checks for literal `"bash"`, ignoring `zsh` and absolute paths like
`/usr/bin/zsh`.
**Changes:**
- Added `is_login_shell_with_lc` helper that extracts shell basename and
matches against `bash` or `zsh`
- Updated pattern matching to use the helper instead of hardcoded check
- Added test coverage for zsh and absolute paths (`/usr/bin/zsh`,
`/bin/bash`)
**Testing:**
```bash
cd codex-rs
cargo test strip_bash_lc_and_escape -p codex-tui
```
All 4 test cases pass (bash, zsh, and absolute paths for both).
Closes#4201
Extend `run` and `runStreamed` input to be either a `string` or
structured input. A structured input is an array of text parts and/or
image paths, which will then be fed to the CLI through the `--image`
argument. Text parts are combined with double newlines. For instance:
```ts
const turn = await thread.run([
{ type: "text", text: "Describe these screenshots" },
{ type: "local_image", path: "./ui.png" },
{ type: "local_image", path: "./diagram.jpg" },
{ type: "text", text: "Thanks!" },
]);
```
Ends up launching the CLI with:
```
codex exec --image foo.png --image bar.png "Describe these screenshots\n\nThanks!"
```
The complete `Input` type for both function now is:
```ts
export type UserInput =
| {
type: "text";
text: string;
}
| {
type: "local_image";
path: string;
};
export type Input = string | UserInput[];
```
This brings the Codex SDK closer to feature parity with the CLI.
Adresses #5280 .
This should make it more clear that specific tools come from MCP
servers.
#4806 requested that we add the server name but we already do that.
Fixes#4806
Tightened the docs so the sandbox guide matches reality, noted the new
tools.view_image toggle next to web search, and linked the README to the
getting-started guide which now owns the familiar tips (backtrack, --cd,
--add-dir, etc.).
Updated the configuration guide so it matches the current CLI behavior.
Clarified the platform-specific default model, explained how custom
model-providers interact with bundled ones, refreshed the streamable
HTTP/MCP section with accurate guidance on the RMCP client and OAuth
flag, and removed stale keys from the reference table.
Update FAQ, improve general structure for config, add more links across
the sections in the documentation, remove out of date and duplicate
content and better explain certain concepts such as approvals and
sandboxing.
Add a `--add-dir` CLI flag so sessions can use extra writable roots in
addition to the ones specified in the config file. These are ephemerally
added during the session only.
Fixes#3303Fixes#2797
The goal of this change:
1. Unify user input and user turn implementation.
2. Have a single place where turn/session setting overrides are applied.
3. Have a single place where turn context is created.
4. Create TurnContext only for actual turn and have a separate structure
for current session settings (reuse ConfigureSession)
Expand the custom prompts documentation and link it from other guides. Show saved prompt metadata in the slash-command popup, with tests covering description fallbacks.
Exit when a requested resume session is missing after restoring the
terminal and print a helpful message instructing users how to resume
existing sessions.
Partially addresses #5247.
# What
Updates the install command in the changelog template (`cliff.toml`)
from
```
npm install -g codex@version
```
to
```
npm install -g @openai/codex@<version>
```
# Why
The current command is incorrect, it tries installs the old “codex”
static site generator rather than the OpenAI Codex CLI.
# How
Edited only the header string in `cliff.toml` to point to
@openai/codex@<version>. No changelog regeneration or other files
touched.
Fixes#2059
Co-authored-by: Thibault Sottiaux <tibo@openai.com>
Fixes#4870#4717#3260#4431#2718#4898#5036
- Fix the chat composer “phantom space” bug that appeared when
backspacing CJK (and other double-width) characters after the composer
got a uniform background in 43b63ccae89c….
- Pull diff_buffers’s clear-to-end logic forward to iterate by display
width, so wide graphemes are counted correctly when computing the
trailing column.
- Keep modifier-aware detection so styled cells are still flushed, and
add a regression test (diff_buffers_clear_to_end_starts_after_wide_char)
that covers the CJK deletion scenario.
---------
Co-authored-by: Josh McKinney <joshka@openai.com>
This change ensures that we store the absolute time instead of relative
offsets of when the primary and secondary rate limits will reset.
Previously these got recalculated relative to current time, which leads
to the displayed reset times to change over time, including after doing
a codex resume.
For previously changed sessions, this will cause the reset times to not
show due to this being a breaking change:
<img width="524" height="55" alt="Screenshot 2025-10-17 at 5 14 18 PM"
src="https://github.com/user-attachments/assets/53ebd43e-da25-4fef-9c47-94a529d40265"
/>
Fixes https://github.com/openai/codex/issues/4761
I dropped the build of the old cli from the flake, where the default.nix
already seemed to removed in a previous iterations. Then I updated
flake.nix and codex-rs expression to be able to build again (see
individual commits for details).
Tested by running the following builds:
```
$ nix build .#packages.x86_64-linux.codex-rs
$ nix build .#packages.aarch64-darwin.codex-cli
```
---------
Signed-off-by: Jörg Thalheim <joerg@thalheim.io>
`ParsedCommand::Read` has a `name` field that attempts to identify the
name of the file being read, but the file may not be in the `cwd` in
which the command is invoked as demonstrated by this existing unit test:
0139f6780c/codex-rs/core/src/parse_command.rs (L250-L260)
As you can see, `tui/Cargo.toml` is the relative path to the file being
read.
This PR introduces a new `path: PathBuf` field to `ParsedCommand::Read`
that attempts to capture this information. When possible, this is an
absolute path, though when relative, it should be resolved against the
`cwd` that will be used to run the command to derive the absolute path.
This should make it easier for clients to provide UI for a "read file"
event that corresponds to the command execution.
This makes stdio mcp servers more flexible by allowing users to specify
the cwd to run the server command from and adding additional environment
variables to be passed through to the server.
Example config using the test server in this repo:
```toml
[mcp_servers.test_stdio]
cwd = "/Users/<user>/code/codex/codex-rs"
command = "cargo"
args = ["run", "--bin", "test_stdio_server"]
env_vars = ["MCP_TEST_VALUE"]
```
@bolinfest I know you hate these env var tests but let's roll with this
for now. I may take a stab at the env guard + serial macro at some
point.
This adds two new config fields to streamable http mcp servers:
`http_headers`: a map of key to value
`env_http_headers` a map of key to env var which will be resolved at
request time
All headers will be passed to all MCP requests to that server just like
authorization headers.
There is a test ensuring that headers are not passed to other servers.
Fixes#5180
## Summary
When using the trusted state during tui startup, we created a new
WorkspaceWrite policy without checking the config.toml for a
`sandbox_workspace_write` field. This would result in us setting the
sandbox_mode as workspace-write, but ignoring the field if the user had
set `sandbox_workspace_write` without also setting `sandbox_mode` in the
config.toml. This PR adds support for respecting
`sandbox_workspace_write` setting in config.toml in the trusted
directory flow, and adds tests to cover this case.
## Testing
- [x] Added unit tests
Also: fixed the contents of the `APPLE_CERTIFICATE_P12` and
`APPLE_CERTIFICATE_PASSWORD` secrets, so the code-signing step will use
the right certificate now.
## Summary
- add a kill buffer to the text area and wire Ctrl+Y to yank it
- capture text from Ctrl+W, Ctrl+U, and Ctrl+K operations into the kill
buffer
- add regression coverage ensuring the last kill can be yanked back
Fixes#5017
------
https://chatgpt.com/codex/tasks/task_i_68e95bf06c48832cbf3d2ba8fa2035d2
This adds `parsed_cmd: Vec<ParsedCommand>` to `ExecApprovalRequestEvent`
in the core protocol (`protocol/src/protocol.rs`), which is also what
this field is named on `ExecCommandBeginEvent`. Honestly, I don't love
the name (it sounds like a single command, but it is actually a list of
them), but I don't want to get distracted by a naming discussion right
now.
This also adds `parsed_cmd` to `ExecCommandApprovalParams` in
`codex-rs/app-server-protocol/src/protocol.rs`, so it will be available
via `codex app-server`, as well.
For consistency, I also updated `ExecApprovalElicitRequestParams` in
`codex-rs/mcp-server/src/exec_approval.rs` to include this field under
the name `codex_parsed_cmd`, as that struct already has a number of
special `codex_*` fields. Note this is the code for when Codex is used
as an MCP _server_ and therefore has to conform to the official spec for
an MCP elicitation type.
Note these two types were identical, so it seems clear to standardize on the one in `codex_protocol` and eliminate the `Into` stuff.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/5218).
* #5222
* __->__ #5218
1. If Codex detects that a `codex mcp add -url …` server supports oauth,
it will auto-initiate the login flow.
2. If the TUI starts and a MCP server supports oauth but isn't logged
in, it will give the user an explicit warning telling them to log in.
Tightened the CLI integration tests to stop relying on wall-clock
sleeps—new fs watcher helper waits for session files instead of timing
out, and SSE mocks/fixtures make the flows deterministic.
keep a 1 cell margin at the right edge of the screen in the composer
(and in the user message in history).
this lets us print clear-to-EOL 1 char before the end of the line in
history, so that resizing the terminal will keep the background color
(at least in iterm/terminal.app). it also stops the cursor in the
textarea from floating off the right edge.
---------
Co-authored-by: joshka-oai <joshka@openai.com>
Add proper feature flag instead of having custom flags for everything.
This is just for experimental/wip part of the code
It can be used through CLI:
```bash
codex --enable unified_exec --disable view_image_tool
```
Or in the `config.toml`
```toml
# Global toggles applied to every profile unless overridden.
[features]
apply_patch_freeform = true
view_image_tool = false
```
Follow-up:
In a following PR, the goal is to have a default have `bundles` of
features that we can associate to a model
Refactor trust_directory to use ColumnRenderable & friends, thus
correcting wrapping behavior at small widths. Also introduce
RowRenderable with fixed-width rows.
- fixed wrapping in trust_directory
- changed selector cursor to match other list item selections
- allow y/n to work as well as 1/2
- fixed key_hint to be standard
before:
<img width="661" height="550" alt="Screenshot 2025-10-09 at 9 50 36 AM"
src="https://github.com/user-attachments/assets/e01627aa-bee4-4e25-8eca-5575c43f05bf"
/>
after:
<img width="661" height="550" alt="Screenshot 2025-10-09 at 9 51 31 AM"
src="https://github.com/user-attachments/assets/cb816cbd-7609-4c83-b62f-b4dba392d79a"
/>
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
This adds a queryable auth status for MCP servers which is useful:
1. To determine whether a streamable HTTP server supports auth or not
based on whether or not it supports RFC 8414-3.2
2. Allow us to build a better user experience on top of MCP status
Instead of querying all 256 terminal colors on startup, which was slow
in some terminals, hardcode the default xterm palette.
Additionally, tweak the shimmer so that it blends between default_fg and
default_bg, instead of "dark gray" (according to the terminal) and pure
white (regardless of terminal theme).
Clear the history cursor before checking for duplicate submissions so
sending the same message twice exits history mode. This prevents Up/Down
from staying stuck in history browsing after duplicate sends.
1. You can now add streamable http servers via the CLI
2. As part of this, I'm also changing the existing bearer_token plain
text config field with ane env var
```
mcp add github --url https://api.githubcopilot.com/mcp/ --bearer-token-env-var=GITHUB_PAT
```
This lets users/companies explicitly choose whether to force/disallow
the keyring/fallback file storage for mcp credentials.
People who develop with Codex will want to use this until we sign
binaries or else each ad-hoc debug builds will require keychain access
on every build. I don't love this and am open to other ideas for how to
handle that.
```toml
mcp_oauth_credentials_store = "auto"
mcp_oauth_credentials_store = "file"
mcp_oauth_credentials_store = "keyrung"
```
Defaults to `auto`
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
## Summary
- ensure the TypeScript SDK sets CODEX_INTERNAL_ORIGINATOR_OVERRIDE to
codex_sdk_ts when spawning the Codex CLI
- extend the responses proxy test helper to capture request headers for
assertions
- add coverage that verifies Codex threads launched from the TypeScript
SDK send the codex_sdk_ts originator header
## Testing
- Not Run (not requested)
------
https://chatgpt.com/codex/tasks/task_i_68e561b125248320a487f129093d16e7
We use to put the review prompt in the first user message as well to
bypass statsig overrides, but now that's been resolved and instructions
are being respected, so we're duplicating the review instructions.
this fixes an issue where text lines with long words would sometimes
overflow.
- the default penalties for the OptimalFit algorithm allow overflowing
in some cases. this seems insane to me, and i considered just banning
the OptimalFit algorithm by disabling the 'smawk' feature on textwrap,
but decided to keep it and just bump the overflow penalty to ~infinity
since optimal fit does sometimes produce nicer wrappings. it's not clear
this is worth it, though, and maybe we should just dump the optimal fit
algorithm completely.
- user history messages weren't rendering with the same wrap algorithm
as used in the composer, which sometimes resulted in wrapping messages
differently in the history vs. in the composer.
Before this change:
```
tamird@L03G26TD12 codex-rs % codex
zsh: do you wish to see all 3864 possibilities (1285 lines)?
```
After this change:
```
tamird@L03G26TD12 codex-rs % codex
app-server -- [experimental] Run the app server
apply a -- Apply the latest diff produced by Codex agent as a `git apply` to your local working tree
cloud -- [EXPERIMENTAL] Browse tasks from Codex Cloud and apply changes locally
completion -- Generate shell completion scripts
debug -- Internal debugging commands
exec e -- Run Codex non-interactively
generate-ts -- Internal: generate TypeScript protocol bindings
help -- Print this message or the help of the given subcommand(s)
login -- Manage login
logout -- Remove stored authentication credentials
mcp -- [experimental] Run Codex as an MCP server and manage MCP servers
mcp-server -- [experimental] Run the Codex MCP server (stdio transport)
responses-api-proxy -- Internal: run the responses API proxy
resume -- Resume a previous interactive session (picker by default; use --last to continue the most recent)
```
when exiting a session that was started with `codex resume`, the note
about how to resume again wasn't being printed.
thanks @aibrahim-oai for pointing out this issue!
`http_config.auth_header` automatically added `Bearer `. By adding it
ourselves, we were sending `Bearer Bearer <token>`.
I confirmed that the GitHub MCP initialization 400s before and works
now.
I also optimized the oauth flow to not check the keyring if you
explicitly pass in a bearer token.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
## Summary
- add a `codex sandbox` subcommand with macOS and Linux targets while
keeping the legacy `codex debug` aliases
- update documentation to highlight the new sandbox entrypoints and
point existing references to the new command
- clarify the core README about the linux sandbox helper alias
## Testing
- just fmt
- just fix -p codex-cli
- cargo test -p codex-cli
------
https://chatgpt.com/codex/tasks/task_i_68e2e00ca1e8832d8bff53aa0b50b49e
## Summary
- replace manual wiremock SSE mounts in the compact suite with the
shared response helpers
- simplify the exec auth_env integration test by using the
mount_sse_once_match helper
- rely on mount_sse_sequence plus server request collection to replace
the bespoke SeqResponder utility in tests
## Testing
- just fmt
------
https://chatgpt.com/codex/tasks/task_i_68e2e238f2a88320a337f0b9e4098093
## Summary
- expand the TypeScript SDK README with streaming, architecture, and API
docs
- refresh quick start examples and clarify thread management options
## Testing
- Not Run (docs only)
---------
Co-authored-by: pakrym-oai <pakrym@openai.com>
## Summary
- add a reusable `ev_response_created` helper that builds
`response.created` SSE events for integration tests
- update the exec and core integration suites to use the new helper
instead of repeating manual JSON literals
- keep the streaming fixtures consistent by relying on the shared helper
in every touched test
## Testing
- `just fmt`
------
https://chatgpt.com/codex/tasks/task_i_68e1fe885bb883208aafffb94218da61
`codex-responses-api-proxy` is designed so that there should be exactly
one copy of the API key in memory (that is `mlock`'d on UNIX), but in
practice, I was seeing two when I dumped the process data from
`/proc/$PID/mem`.
It appears that `std::io::stdin()` maintains an internal `BufReader`
that we cannot zero out, so this PR changes the implementation on UNIX
so that we use a low-level `read(2)` instead.
Even though it seems like it would be incredibly unlikely, we also make
this logic tolerant of short reads. Either `\n` or `EOF` must be sent to
signal the end of the key written to stdin.
## Summary
- replace manual event polling loops in several core test suites with
the shared wait_for_event helpers
- keep prior assertions intact by using closure captures for stateful
expectations, including plan updates, patch lifecycles, and review flow
checks
- rely on wait_for_event_with_timeout where longer waits are required,
simplifying timeout handling
## Testing
- just fmt
------
https://chatgpt.com/codex/tasks/task_i_68e1d58582d483208febadc5f90dd95e
## Summary
This PR is an alternative approach to #4711, but instead of changing our
storage, parses out shell calls in the client and reserializes them on
the fly before we send them out as part of the request.
What this changes:
1. Adds additional serialization logic when the
ApplyPatchToolType::Freeform is in use.
2. Adds a --custom-apply-patch flag to enable this setting on a
session-by-session basis.
This change is delicate, but is not meant to be permanent. It is meant
to be the first step in a migration:
1. (This PR) Add in-flight serialization with config
2. Update model_family default
3. Update serialization logic to store turn outputs in a structured
format, with logic to serialize based on model_family setting.
4. Remove this rewrite in-flight logic.
## Test Plan
- [x] Additional unit tests added
- [x] Integration tests added
- [x] Tested locally
In the past, we were treating `input exceeded context window` as a
streaming error and retrying on it. Retrying on it has no point because
it won't change the behavior. In this PR, we surface the error to the
client without retry and also send a token count event to indicate that
the context window is full.
<img width="650" height="125" alt="image"
src="https://github.com/user-attachments/assets/c26b1213-4c27-4bfc-90f4-51a270a3efd5"
/>
We truncate the output of exec commands to not blow the context window.
However, some cases we weren't doing that. This caused reports of people
with 76% context window left facing `input exceeded context window`
which is weird.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
The `experimental_use_rmcp_client` flag is still useful to:
1. Toggle between stdio clients
2. Enable oauth beacuse we want to land
https://github.com/modelcontextprotocol/rust-sdk/pull/469,
https://github.com/openai/codex/pull/4677, and binary signing before we
enable it by default
However, for no-auth http servers, there is only one option so we don't
need the flag and it seems to be working pretty well.
Codex isn’t great yet on Windows outside of WSL, and while we’ve merged
https://github.com/openai/codex/pull/4269 to reduce the repetitive
manual approvals on readonly commands, we’ve noticed that users seem to
have more issues with GPT-5-Codex than with GPT-5 on Windows.
This change makes GPT-5 the default for Windows users while we continue
to improve the CLI harness and model for GPT-5-Codex on Windows.
## Summary
- Factor `load_config_as_toml` into `core::config_loader` so config
loading is reusable across callers.
- Layer `~/.codex/config.toml`, optional `~/.codex/managed_config.toml`,
and macOS managed preferences (base64) with recursive table merging and
scoped threads per source.
## Config Flow
```
Managed prefs (macOS profile: com.openai.codex/config_toml_base64)
▲
│
~/.codex/managed_config.toml │ (optional file-based override)
▲
│
~/.codex/config.toml (user-defined settings)
```
- The loader searches under the resolved `CODEX_HOME` directory
(defaults to `~/.codex`).
- Managed configs let administrators ship fleet-wide overrides via
device profiles which is useful for enforcing certain settings like
sandbox or approval defaults.
- For nested hash tables: overlays merge recursively. Child tables are
merged key-by-key, while scalar or array values replace the prior layer
entirely. This lets admins add or tweak individual fields without
clobbering unrelated user settings.
Apparently we were not running our `pnpm run prettier` check in CI, so
many files that were covered by the existing Prettier check were not
well-formatted.
This updates CI and formats the files.
This PR adds oauth login support to streamable http servers when
`experimental_use_rmcp_client` is enabled.
This PR is large but represents the minimal amount of work required for
this to work. To keep this PR smaller, login can only be done with
`codex mcp login` and `codex mcp logout` but it doesn't appear in `/mcp`
or `codex mcp list` yet. Fingers crossed that this is the last large MCP
PR and that subsequent PRs can be smaller.
Under the hood, credentials are stored using platform credential
managers using the [keyring crate](https://crates.io/crates/keyring).
When the keyring isn't available, it falls back to storing credentials
in `CODEX_HOME/.credentials.json` which is consistent with how other
coding agents handle authentication.
I tested this on macOS, Windows, WSL (ubuntu), and Linux. I wasn't able
to test the dbus store on linux but did verify that the fallback works.
One quirk is that if you have credentials, during development, every
build will have its own ad-hoc binary so the keyring won't recognize the
reader as being the same as the write so it may ask for the user's
password. I may add an override to disable this or allow
users/enterprises to opt-out of the keyring storage if it causes issues.
<img width="5064" height="686" alt="CleanShot 2025-09-30 at 19 31 40"
src="https://github.com/user-attachments/assets/9573f9b4-07f1-4160-83b8-2920db287e2d"
/>
<img width="745" height="486" alt="image"
src="https://github.com/user-attachments/assets/9562649b-ea5f-4f22-ace2-d0cb438b143e"
/>
This issue was due to the fact that the timeout is not always sufficient
to have enough character for truncation + a race between synthetic
timeout and process kill
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
This updates `codex exec` so that, by default, most of the agent's
activity is written to stderr so that only the final agent message is
written to stdout. This makes it easier to pipe `codex exec` into
another tool without extra filtering.
I introduced `#![deny(clippy::print_stdout)]` to help enforce this
change and renamed the `ts_println!()` macro to `ts_msg()` because (1)
it no longer calls `println!()` and (2), `ts_eprintln!()` seemed too
long of a name.
While here, this also adds `-o` as an alias for `--output-last-message`.
Fixes https://github.com/openai/codex/issues/1670
# Tool System Refactor
- Centralizes tool definitions and execution in `core/src/tools/*`:
specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
registry/dispatch (`registry.rs`), and shared context (`context.rs`).
One registry now builds the model-visible tool list and binds handlers.
- Router converts model responses to tool calls; Registry dispatches
with consistent telemetry via `codex-rs/otel` and unified error
handling. Function, Local Shell, MCP, and experimental `unified_exec`
all flow through this path; legacy shell aliases still work.
- Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
make adding tools predictable and testable.
Example: `read_file`
- Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
registered by `build_specs`).
- Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
- E2E test: `core/tests/suite/read_file.rs` validates the tool returns
the requested lines.
## Next steps:
- Decompose `handle_container_exec_with_params`
- Add parallel tool calls
Previously, users could supply their API key directly via:
```shell
codex login --api-key KEY
```
but this has the drawback that `KEY` is more likely to end up in shell
history, can be read from `/proc`, etc.
This PR removes support for `--api-key` and replaces it with
`--with-api-key`, which reads the key from stdin, so either of these are
better options:
```
printenv OPENAI_API_KEY | codex login --with-api-key
codex login --with-api-key < my_key.txt
```
Other CLIs, such as `gh auth login --with-token`, follow the same
practice.
Before when you would enter `/di`, hit tab on `/diff`, and then hit
enter, it would execute `/diff`. But now it's just sending it as a text.
This fixes the issue.
### Summary
* Updated fuzzy search result to include the file name.
* This should not affect CLI usage and the UI there will be addressed in
a separate PR.
### Testing
Tested locally and with the extension.
### Screenshot
<img width="431" height="244" alt="Screenshot 2025-10-02 at 11 08 44 AM"
src="https://github.com/user-attachments/assets/ba2ca299-a81d-4453-9242-1750e945aea2"
/>
---------
Co-authored-by: shijie.rao <shijie.rao@squareup.com>
- prefix command approval reasons with "Reason:"
- show keyboard shortcuts for some ListSelectionItems
- remove "description" lines for approval options, and make the labels
more verbose
- add a spacer line in diff display after the path
and some other minor refactors that go along with the above.
<img width="859" height="508" alt="Screenshot 2025-10-02 at 1 24 50 PM"
src="https://github.com/user-attachments/assets/4fa7ecaf-3d3a-406a-bb4d-23e30ce3e5cf"
/>
Fixes#4176
Some common tools provide a schema (even if just an empty object schema)
as the value for `additionalProperties`. The parsing as it currently
stands fails when it encounters this. This PR updates the schema to
accept a schema object in addition to a boolean value, per the JSON
Schema spec.
We get spurrious reports that the model writes fenced code blocks
without an info tag which then causes auto-language detection in the
extension to incorrectly highlight the code and show the wrong language.
The model should really always include a tag when it can.
This PR fixes a bug that results in a hang in the oauth login flow if a
user logs in, then logs out, then logs in again without first closing
the browser window.
Root cause of problem: We use a local web server for the oauth flow, and
it's implemented using the `tiny_http` rust crate. During the first
login, a socket is created between the browser and the server. The
`tiny_http` library creates worker threads that persist for as long as
this socket remains open. Currently, there's no way to close the
connection on the server side — the library provides no API to do this.
The library also filters all "Connect: close" headers, which makes it
difficult to tell the client browser to close the connection. On the
second login attempt, the browser uses the existing connection rather
than creating a new one. Since that connection is associated with a
server instance that no longer exists, it is effectively ignored.
I considered switching from `tiny_http` to a different web server
library, but that would have been a big change with significant
regression risk. This PR includes a more surgical fix that works around
the limitation of `tiny_http` and sends a "Connect: close" header on the
last "success" page of the oauth flow.
Before this PR:
```typescript
export type RequestId = string | bigint;
```
After:
```typescript
export type RequestId = string | number;
```
`bigint` introduces headaches in TypeScript without providing any real
value.
I just had to use this like so:
```
./codex-rs/scripts/create_github_release --publish-alpha --emergency-version-override 0.43.0-alpha.10
```
because the build for `0.43.0-alpha.9` failed:
https://github.com/openai/codex/actions/runs/18167317356
## Summary
- show the remaining context window percentage in `/status` alongside
existing token usage details
- replace the composer shortcut prompt with the context window
percentage (or an unavailable message) while a task is running
- update TUI snapshots to reflect the new context window line
## Testing
- cargo test -p codex-tui
------
https://chatgpt.com/codex/tasks/task_i_68dc6e7397ac8321909d7daff25a396c
## Summary
- show a dim “(no output)” placeholder when an executed command produces
no stdout or stderr so empty runs are visible
- update TUI snapshots to include the new placeholder in history
renderings
## Testing
- cargo test -p codex-tui
------
https://chatgpt.com/codex/tasks/task_i_68dc056c1d5883218fe8d9929e9b1657
**Summary**
This PR fixes an issue in the device code login flow where trailing
slashes in the issuer URL could cause malformed URLs during codex token
exchange step
**Test**
Before the changes
`Error logging in with device code: device code exchange failed: error
decoding response body`
After the changes
`Successfully logged in`
Implement command safety for PowerShell commands on Windows
This change adds a new Windows-specific command-safety module under
`codex-rs/core/src/command_safety/windows_safe_commands.rs` to strictly
sanitise PowerShell invocations. Key points:
- Introduce `is_safe_command_windows()` to only allow explicitly
read-only PowerShell calls.
- Parse and split PowerShell invocations (including inline `-Command`
scripts and pipelines).
- Block unsafe switches (`-File`, `-EncodedCommand`, `-ExecutionPolicy`,
unknown flags, call operators, redirections, separators).
- Whitelist only read-only cmdlets (`Get-ChildItem`, `Get-Content`,
`Select-Object`, etc.), safe Git subcommands (`status`, `log`, `show`,
`diff`, `cat-file`), and ripgrep without unsafe options.
- Add comprehensive unit tests covering allowed and rejected command
patterns (nested calls, side effects, chaining, redirections).
This ensures Codex on Windows can safely execute discover-only
PowerShell workflows without risking destructive operations.
There was a bit of copypasta I put up with when were publishing two
packages to npm, but now that it's three, I created some more scripts to
consolidate things.
With this change, I ran:
```shell
./scripts/stage_npm_packages.py --release-version 0.43.0-alpha.8 --package codex --package codex-responses-api-proxy --package codex-sdk
```
Indeed when it finished, I ended up with:
```shell
$ tree dist
dist
└── npm
├── codex-npm-0.43.0-alpha.8.tgz
├── codex-responses-api-proxy-npm-0.43.0-alpha.8.tgz
└── codex-sdk-npm-0.43.0-alpha.8.tgz
$ tar tzvf dist/npm/codex-sdk-npm-0.43.0-alpha.8.tgz
-rwxr-xr-x 0 0 0 25476720 Oct 26 1985 package/vendor/aarch64-apple-darwin/codex/codex
-rwxr-xr-x 0 0 0 29871400 Oct 26 1985 package/vendor/aarch64-unknown-linux-musl/codex/codex
-rwxr-xr-x 0 0 0 28368096 Oct 26 1985 package/vendor/x86_64-apple-darwin/codex/codex
-rwxr-xr-x 0 0 0 36029472 Oct 26 1985 package/vendor/x86_64-unknown-linux-musl/codex/codex
-rw-r--r-- 0 0 0 10926 Oct 26 1985 package/LICENSE
-rw-r--r-- 0 0 0 30187520 Oct 26 1985 package/vendor/aarch64-pc-windows-msvc/codex/codex.exe
-rw-r--r-- 0 0 0 35277824 Oct 26 1985 package/vendor/x86_64-pc-windows-msvc/codex/codex.exe
-rw-r--r-- 0 0 0 4842 Oct 26 1985 package/dist/index.js
-rw-r--r-- 0 0 0 1347 Oct 26 1985 package/package.json
-rw-r--r-- 0 0 0 9867 Oct 26 1985 package/dist/index.js.map
-rw-r--r-- 0 0 0 12 Oct 26 1985 package/README.md
-rw-r--r-- 0 0 0 4287 Oct 26 1985 package/dist/index.d.ts
```
# Extract and Centralize Sandboxing
- Goal: Improve safety and clarity by centralizing sandbox planning and
execution.
- Approach:
- Add planner (ExecPlan) and backend registry (Direct/Seatbelt/Linux)
with run_with_plan.
- Refactor codex.rs to plan-then-execute; handle failures/escalation via
the plan.
- Delegate apply_patch to the codex binary and run it with an empty env
for determinism.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
We continue the separation between `codex app-server` and `codex
mcp-server`.
In particular, we introduce a new crate, `codex-app-server-protocol`,
and migrate `codex-rs/protocol/src/mcp_protocol.rs` into it, renaming it
`codex-rs/app-server-protocol/src/protocol.rs`.
Because `ConversationId` was defined in `mcp_protocol.rs`, we move it
into its own file, `codex-rs/protocol/src/conversation_id.rs`, and
because it is referenced in a ton of places, we have to touch a lot of
files as part of this PR.
We also decide to get away from proper JSON-RPC 2.0 semantics, so we
also introduce `codex-rs/app-server-protocol/src/jsonrpc_lite.rs`, which
is basically the same `JSONRPCMessage` type defined in `mcp-types`
except with all of the `"jsonrpc": "2.0"` removed.
Getting rid of `"jsonrpc": "2.0"` makes our serialization logic
considerably simpler, as we can lean heavier on serde to serialize
directly into the wire format that we use now.
Manually curating `protocol-ts/src/lib.rs` was error-prone, as expected.
I finally asked Codex to write some Rust macros so we can ensure that:
- For every variant of `ClientRequest` and `ServerRequest`, there is an
associated `params` and `response` type.
- All response types are included automatically in the output of `codex
generate-ts`.
I don't believe there is any upside in making process hardening opt-in
for Codex CLI releases. If you want to tinker with Codex CLI, then build
from source (or run as `root`)?
Fixes:
- Removed overdeclaration of types that were unnecessary because they
were already included by induction.
- Reordered list of response types to match the enum order, making it
easier to identify what was missing.
- Added `ExecArbitraryCommandResponse` because it was missing.
- Leveraged `use codex_protocol::mcp_protocol::*;` to make the file more
readable.
- Removed crate dependency on `mcp-types` now that we have separate the
app server from the MCP server:
https://github.com/openai/codex/pull/4471
My next move is to come up with some scheme that ensures request types
always have a response type and that the response type is automatically
included with the output of `codex generate-ts`.
This ensures changes the generated TypeScript type for `ClientRequest`
so that instead of this:
```typescript
/**
* Request from the client to the server.
*/
export type ClientRequest =
| { method: "initialize"; id: RequestId; params: InitializeParams }
| { method: "newConversation"; id: RequestId; params: NewConversationParams }
// ...
| { method: "getUserAgent"; id: RequestId }
| { method: "userInfo"; id: RequestId }
// ...
```
we have this:
```typescript
/**
* Request from the client to the server.
*/
export type ClientRequest =
| { method: "initialize"; id: RequestId; params: InitializeParams }
| { method: "newConversation"; id: RequestId; params: NewConversationParams }
// ...
| { method: "getUserAgent"; id: RequestId; params: undefined }
| { method: "userInfo"; id: RequestId; params: undefined }
// ...
```
which makes TypeScript happier when it comes to destructuring instances
of `ClientRequest` because it does not complain about `params` not being
guaranteed to exist anymore.
Update prompt to prevent codex to use Python script or fancy commands to
edit files.
## Testing:
3 scenarios have been considered:
1. Rename codex to meca_code. Proceed to the whole refactor file by
file. Don't ask for approval at each step
2. Add a description to every single function you can find in the repo
3. Rewrite codex.rs in a more idiomatic way. Make sure to touch ONLY
this file and that clippy does not complain at the end
Before this update, 22% (estimation as it's sometimes hard to find all
the creative way the model find to edit files) of the file editions
where made using something else than a raw `apply_patch`
After this update, not a single edition without `apply_patch` was found
[EDIT]
I managed to have a few `["bash", "-lc", "apply_path"]` when reaching <
10% context left
Here's the logic:
1. If text is empty and selector is open:
- Enter on a prompt without args should autosubmit the prompt
- Enter on a prompt with numeric args should add `/prompts:name ` to the
text input
- Enter on a prompt with named args should add `/prompts:name ARG1=""
ARG2=""` to the text input
2. If text is not empty but no args are passed:
- For prompts with numeric args -> we allow it to submit (params are
optional)
- For prompts with named args -> we throw an error (all params should
have values)
<img width="454" height="246" alt="Screenshot 2025-09-23 at 2 23 21 PM"
src="https://github.com/user-attachments/assets/fd180a1b-7d17-42ec-b231-8da48828b811"
/>
This is a very large PR with some non-backwards-compatible changes.
Historically, `codex mcp` (or `codex mcp serve`) started a JSON-RPC-ish
server that had two overlapping responsibilities:
- Running an MCP server, providing some basic tool calls.
- Running the app server used to power experiences such as the VS Code
extension.
This PR aims to separate these into distinct concepts:
- `codex mcp-server` for the MCP server
- `codex app-server` for the "application server"
Note `codex mcp` still exists because it already has its own subcommands
for MCP management (`list`, `add`, etc.)
The MCP logic continues to live in `codex-rs/mcp-server` whereas the
refactored app server logic is in the new `codex-rs/app-server` folder.
Note that most of the existing integration tests in
`codex-rs/mcp-server/tests/suite` were actually for the app server, so
all the tests have been moved with the exception of
`codex-rs/mcp-server/tests/suite/mod.rs`.
Because this is already a large diff, I tried not to change more than I
had to, so `codex-rs/app-server/tests/common/mcp_process.rs` still uses
the name `McpProcess` for now, but I will do some mechanical renamings
to things like `AppServer` in subsequent PRs.
While `mcp-server` and `app-server` share some overlapping functionality
(like reading streams of JSONL and dispatching based on message types)
and some differences (completely different message types), I ended up
doing a bit of copypasta between the two crates, as both have somewhat
similar `message_processor.rs` and `outgoing_message.rs` files for now,
though I expect them to diverge more in the near future.
One material change is that of the initialize handshake for `codex
app-server`, as we no longer use the MCP types for that handshake.
Instead, we update `codex-rs/protocol/src/mcp_protocol.rs` to add an
`Initialize` variant to `ClientRequest`, which takes the `ClientInfo`
object we need to update the `USER_AGENT_SUFFIX` in
`codex-rs/app-server/src/message_processor.rs`.
One other material change is in
`codex-rs/app-server/src/codex_message_processor.rs` where I eliminated
a use of the `send_event_as_notification()` method I am generally trying
to deprecate (because it blindly maps an `EventMsg` into a
`JSONNotification`) in favor of `send_server_notification()`, which
takes a `ServerNotification`, as that is intended to be a custom enum of
all notification types supported by the app server. So to make this
update, I had to introduce a new variant of `ServerNotification`,
`SessionConfigured`, which is a non-backwards compatible change with the
old `codex mcp`, and clients will have to be updated after the next
release that contains this PR. Note that
`codex-rs/app-server/tests/suite/list_resume.rs` also had to be update
to reflect this change.
I introduced `codex-rs/utils/json-to-toml/src/lib.rs` as a small utility
crate to avoid some of the copying between `mcp-server` and
`app-server`.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
# test
```
codex-rs % export CODEX_DEVICE_AUTH_BASE_URL=http://localhost:3007
codex-rs % cargo run --bin codex login --experimental_use-device-code
Compiling codex-login v0.0.0 (/Users/rakesh/code/codex/codex-rs/login)
Compiling codex-mcp-server v0.0.0 (/Users/rakesh/code/codex/codex-rs/mcp-server)
Compiling codex-tui v0.0.0 (/Users/rakesh/code/codex/codex-rs/tui)
Compiling codex-cli v0.0.0 (/Users/rakesh/code/codex/codex-rs/cli)
Finished `dev` profile [unoptimized + debuginfo] target(s) in 2.90s
Running `target/debug/codex login --experimental_use-device-code`
To authenticate, enter this code when prompted: 6Q27-KBVRF with interval 5
^C
```
The error in the last line is since the poll endpoint is not yet
implemented
Fixing the "? for shortcuts"
- Only show the hint when composer is empty
- Don't reset footer on new task updates
- Reorder the elements
- Align the "?" and "/" with overlay on and off
Based on #4364
### Title
## otel
Codex can emit [OpenTelemetry](https://opentelemetry.io/) **log events**
that
describe each run: outbound API requests, streamed responses, user
input,
tool-approval decisions, and the result of every tool invocation. Export
is
**disabled by default** so local runs remain self-contained. Opt in by
adding an
`[otel]` table and choosing an exporter.
```toml
[otel]
environment = "staging" # defaults to "dev"
exporter = "none" # defaults to "none"; set to otlp-http or otlp-grpc to send events
log_user_prompt = false # defaults to false; redact prompt text unless explicitly enabled
```
Codex tags every exported event with `service.name = "codex-cli"`, the
CLI
version, and an `env` attribute so downstream collectors can distinguish
dev/staging/prod traffic. Only telemetry produced inside the
`codex_otel`
crate—the events listed below—is forwarded to the exporter.
### Event catalog
Every event shares a common set of metadata fields: `event.timestamp`,
`conversation.id`, `app.version`, `auth_mode` (when available),
`user.account_id` (when available), `terminal.type`, `model`, and
`slug`.
With OTEL enabled Codex emits the following event types (in addition to
the
metadata above):
- `codex.api_request`
- `cf_ray` (optional)
- `attempt`
- `duration_ms`
- `http.response.status_code` (optional)
- `error.message` (failures)
- `codex.sse_event`
- `event.kind`
- `duration_ms`
- `error.message` (failures)
- `input_token_count` (completion only)
- `output_token_count` (completion only)
- `cached_token_count` (completion only, optional)
- `reasoning_token_count` (completion only, optional)
- `tool_token_count` (completion only)
- `codex.user_prompt`
- `prompt_length`
- `prompt` (redacted unless `log_user_prompt = true`)
- `codex.tool_decision`
- `tool_name`
- `call_id`
- `decision` (`approved`, `approved_for_session`, `denied`, or `abort`)
- `source` (`config` or `user`)
- `codex.tool_result`
- `tool_name`
- `call_id`
- `arguments`
- `duration_ms` (execution time for the tool)
- `success` (`"true"` or `"false"`)
- `output`
### Choosing an exporter
Set `otel.exporter` to control where events go:
- `none` – leaves instrumentation active but skips exporting. This is
the
default.
- `otlp-http` – posts OTLP log records to an OTLP/HTTP collector.
Specify the
endpoint, protocol, and headers your collector expects:
```toml
[otel]
exporter = { otlp-http = {
endpoint = "https://otel.example.com/v1/logs",
protocol = "binary",
headers = { "x-otlp-api-key" = "${OTLP_TOKEN}" }
}}
```
- `otlp-grpc` – streams OTLP log records over gRPC. Provide the endpoint
and any
metadata headers:
```toml
[otel]
exporter = { otlp-grpc = {
endpoint = "https://otel.example.com:4317",
headers = { "x-otlp-meta" = "abc123" }
}}
```
If the exporter is `none` nothing is written anywhere; otherwise you
must run or point to your
own collector. All exporters run on a background batch worker that is
flushed on
shutdown.
If you build Codex from source the OTEL crate is still behind an `otel`
feature
flag; the official prebuilt binaries ship with the feature enabled. When
the
feature is disabled the telemetry hooks become no-ops so the CLI
continues to
function without the extra dependencies.
---------
Co-authored-by: Anton Panasenko <apanasenko@openai.com>
This PR expands `.github/workflows/rust-release.yml` so that it also
builds and publishes the `npm` module for
`@openai/codex-responses-api-proxy` in addition to `@openai/codex`. Note
both `npm` modules are similar, in that they each contain a single `.js`
file that is a thin launcher around the appropriate native executable.
(Since we have a minimal dependency on Node.js, I also lowered the
minimum version from 20 to 16 and verified that works on my machine.)
As part of this change, we tighten up some of the docs around
`codex-responses-api-proxy` and ensure the details regarding protecting
the `OPENAI_API_KEY` in memory match the implementation.
To test the `npm` build process, I ran:
```
./codex-cli/scripts/build_npm_package.py --package codex-responses-api-proxy --version 0.43.0-alpha.3
```
which stages the `npm` module for `@openai/codex-responses-api-proxy` in
a temp directory, using the binary artifacts from
https://github.com/openai/codex/releases/tag/rust-v0.43.0-alpha.3.
This should make the `codex-responses-api-proxy` binaries available for
all platforms in a GitHub Release as well as a corresponding DotSlash
file.
Making `codex-responses-api-proxy` available as an `npm` module will be
done in a follow-up PR.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/4404).
* __->__ #4406
* #4404
* #4403
This removes the `codex responses-api-proxy` subcommand in favor of
running it as a standalone CLI.
As part of this change, we:
- remove the dependency on `tokio`/`async/await` as well as `codex_arg0`
- introduce the use of `pre_main_hardening()` so `CODEX_SECURE_MODE=1`
is not required
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/4404).
* #4406
* __->__ #4404
* #4403
This is likely the reason that I saw some conversations "freeze up" when
using the proxy.
Note the client in `core` does not specify a timeout when making
requests to the Responses API, so the proxy should not, either.
This PR adds support for streamable HTTP MCP servers when the
`experimental_use_rmcp_client` is enabled.
To set one up, simply add a new mcp server config with the url:
```
[mcp_servers.figma]
url = "http://127.0.0.1:3845/mcp"
```
It also supports an optional `bearer_token` which will be provided in an
authorization header. The full oauth flow is not supported yet.
The config parsing will throw if it detects that the user mixed and
matched config fields (like command + bearer token or url + env).
The best way to review it is to review `core/src` and then
`rmcp-client/src/rmcp_client.rs` first. The rest is tests and
propagating the `Transport` struct around the codebase.
Example with the Figma MCP:
<img width="5084" height="1614" alt="CleanShot 2025-09-26 at 13 35 40"
src="https://github.com/user-attachments/assets/eaf2771e-df3e-4300-816b-184d7dec5a28"
/>
- Render `send a message to load usage data` in the beginning of the
session
- Render `data not available yet` if received no rate limits
- nit case
- Deleted stall snapshots that were moved to
`codex-rs/tui/src/status/snapshots`
The [official Rust
SDK](57fc428c57)
has come a long way since we first started our mcp client implementation
5 months ago and, today, it is much more complete than our own
stdio-only implementation.
This PR introduces a new config flag `experimental_use_rmcp_client`
which will use a new mcp client powered by the sdk instead of our own.
To keep this PR simple, I've only implemented the same stdio MCP
functionality that we had but will expand on it with future PRs.
---------
Co-authored-by: pakrym-oai <pakrym@openai.com>
Adds a 1-per-turn todo-list item and item.updated event
```jsonl
{"type":"item.started","item":{"id":"item_6","item_type":"todo_list","items":[{"text":"Record initial two-step plan now","completed":false},{"text":"Update progress to next step","completed":false}]}}
{"type":"item.updated","item":{"id":"item_6","item_type":"todo_list","items":[{"text":"Record initial two-step plan now","completed":true},{"text":"Update progress to next step","completed":false}]}}
{"type":"item.completed","item":{"id":"item_6","item_type":"todo_list","items":[{"text":"Record initial two-step plan now","completed":true},{"text":"Update progress to next step","completed":false}]}}
```
Details are in `responses-api-proxy/README.md`, but the key contribution
of this PR is a new subcommand, `codex responses-api-proxy`, which reads
the auth token for use with the OpenAI Responses API from `stdin` at
startup and then proxies `POST` requests to `/v1/responses` over to
`https://api.openai.com/v1/responses`, injecting the auth token as part
of the `Authorization` header.
The expectation is that `codex responses-api-proxy` is launched by a
privileged user who has access to the auth token so that it can be used
by unprivileged users of the Codex CLI on the same host.
If the client only has one user account with `sudo`, one option is to:
- run `sudo codex responses-api-proxy --http-shutdown --server-info
/tmp/server-info.json` to start the server
- record the port written to `/tmp/server-info.json`
- relinquish their `sudo` privileges (which is irreversible!) like so:
```
sudo deluser $USER sudo || sudo gpasswd -d $USER sudo || true
```
- use `codex` with the proxy (see `README.md`)
- when done, make a `GET` request to the server using the `PORT` from
`server-info.json` to shut it down:
```shell
curl --fail --silent --show-error "http://127.0.0.1:$PORT/shutdown"
```
To protect the auth token, we:
- allocate a 1024 byte buffer on the stack and write `"Bearer "` into it
to start
- we then read from `stdin`, copying to the contents into the buffer
after the prefix
- after verifying the input looks good, we create a `String` from that
buffer (so the data is now on the heap)
- we zero out the stack-allocated buffer using
https://crates.io/crates/zeroize so it is not optimized away by the
compiler
- we invoke `.leak()` on the `String` so we can treat its contents as a
`&'static str`, as it will live for the rest of the processs
- on UNIX, we `mlock(2)` the memory backing the `&'static str`
- when using the `&'static str` when building an HTTP request, we use
`HeaderValue::from_static()` to avoid copying the `&str`
- we also invoke `.set_sensitive(true)` on the `HeaderValue`, which in
theory indicates to other parts of the HTTP stack that the header should
be treated with "special care" to avoid leakage:
439d1c50d7/src/header/value.rs (L346-L376)
- Refactor Exec Cell into its own module
- update exec command rendering to inline the first command line
- limit continuation lines
- always show trimmed output
Extracting tasks in a module and start abstraction behind a Trait (more
to come on this but each task will be tackled in a dedicated PR)
The goal was to drop the ActiveTask and to have a (potentially) set of
tasks during each turn
Certain shell commands are potentially dangerous, and we want to check
for them.
Unless the user has explicitly approved a command, we will *always* ask
them for approval
when one of these commands is encountered, regardless of whether they
are in a sandbox, or what their approval policy is.
The first (of probably many) such examples is `git reset --hard`. We
will be conservative and check for any `git reset`
This addresses bug #4092
Testing:
* Confirmed error occurs prior to fix if logging in using API key and no
`~/.codex` directory exists
* Confirmed after fix that `~/.codex` directory is properly created and
error doesn't occur
Adds a new `item.started` event to `codex exec` and implements it for
command_execution item type.
```jsonl
{"type":"session.created","session_id":"019982d1-75f0-7920-b051-e0d3731a5ed8"}
{"type":"item.completed","item":{"id":"item_0","item_type":"reasoning","text":"**Executing commands securely**\n\nI'm thinking about how the default harness typically uses \"bash -lc,\" while historically \"bash\" is what we've been using. The command should be executed as a string in our CLI, so using \"bash -lc 'echo hello'\" is optimal but calling \"echo hello\" directly feels safer. The sandbox makes sure environment variables like CODEX_SANDBOX_NETWORK_DISABLED=1 are set, so I won't ask for approval. I just need to run \"echo hello\" and correctly present the output."}}
{"type":"item.completed","item":{"id":"item_1","item_type":"reasoning","text":"**Preparing for tool calls**\n\nI realize that I need to include a preamble before making any tool calls. So, I'll first state the preamble in the commentary channel, then proceed with the tool call. After that, I need to present the final message along with the output. It's possible that the CLI will show the output inline, but I must ensure that I present the result clearly regardless. Let's move forward and get this organized!"}}
{"type":"item.completed","item":{"id":"item_2","item_type":"assistant_message","text":"Running `echo` to confirm shell access and print output."}}
{"type":"item.started","item":{"id":"item_3","item_type":"command_execution","command":"bash -lc echo hello","aggregated_output":"","exit_code":null,"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_3","item_type":"command_execution","command":"bash -lc echo hello","aggregated_output":"hello\n","exit_code":0,"status":"completed"}}
{"type":"item.completed","item":{"id":"item_4","item_type":"assistant_message","text":"hello"}}
```
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
This changes the reqwest client used in tests to be sandbox-friendly,
and skips a bunch of other tests that don't work inside the
sandbox/without network.
This pull request add a new experimental format of JSON output.
You can try it using `codex exec --experimental-json`.
Design takes a lot of inspiration from Responses API items and stream
format.
# Session and items
Each invocation of `codex exec` starts or resumes a session.
Session contains multiple high-level item types:
1. Assistant message
2. Assistant thinking
3. Command execution
4. File changes
5. To-do lists
6. etc.
# Events
Session and items are going through their life cycles which is
represented by events.
Session is `session.created` or `session.resumed`
Items are `item.added`, `item.updated`, `item.completed`,
`item.require_approval` (or other item types like `item.output_delta`
when we need streaming).
So a typical session can look like:
<details>
```
{
"type": "session.created",
"session_id": "01997dac-9581-7de3-b6a0-1df8256f2752"
}
{
"type": "item.completed",
"item": {
"id": "itm_0",
"item_type": "assistant_message",
"text": "I’ll locate the top-level README and remove its first line. Then I’ll show a quick summary of what changed."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_1",
"item_type": "command_execution",
"command": "bash -lc ls -la | sed -n '1,200p'",
"aggregated_output": "pyenv: cannot rehash: /Users/pakrym/.pyenv/shims isn't writable\ntotal 192\ndrwxr-xr-x@ 33 pakrym staff 1056 Sep 24 14:36 .\ndrwxr-xr-x 41 pakrym staff 1312 Sep 24 09:17 ..\n-rw-r--r--@ 1 pakrym staff 6 Jul 9 16:16 .codespellignore\n-rw-r--r--@ 1 pakrym staff 258 Aug 13 09:40 .codespellrc\ndrwxr-xr-x@ 5 pakrym staff 160 Jul 23 08:26 .devcontainer\n-rw-r--r--@ 1 pakrym staff 6148 Jul 22 10:03 .DS_Store\ndrwxr-xr-x@ 15 pakrym staff 480 Sep 24 14:38 .git\ndrwxr-xr-x@ 12 pakrym staff 384 Sep 2 16:00 .github\n-rw-r--r--@ 1 pakrym staff 778 Jul 9 16:16 .gitignore\ndrwxr-xr-x@ 3 pakrym staff 96 Aug 11 09:37 .husky\n-rw-r--r--@ 1 pakrym staff 104 Jul 9 16:16 .npmrc\n-rw-r--r--@ 1 pakrym staff 96 Sep 2 08:52 .prettierignore\n-rw-r--r--@ 1 pakrym staff 170 Jul 9 16:16 .prettierrc.toml\ndrwxr-xr-x@ 5 pakrym staff 160 Sep 14 17:43 .vscode\ndrwxr-xr-x@ 2 pakrym staff 64 Sep 11 11:37 2025-09-11\n-rw-r--r--@ 1 pakrym staff 5505 Sep 18 09:28 AGENTS.md\n-rw-r--r--@ 1 pakrym staff 92 Sep 2 08:52 CHANGELOG.md\n-rw-r--r--@ 1 pakrym staff 1145 Jul 9 16:16 cliff.toml\ndrwxr-xr-x@ 11 pakrym staff 352 Sep 24 13:03 codex-cli\ndrwxr-xr-x@ 38 pakrym staff 1216 Sep 24 14:38 codex-rs\ndrwxr-xr-x@ 18 pakrym staff 576 Sep 23 11:01 docs\n-rw-r--r--@ 1 pakrym staff 2038 Jul 9 16:16 flake.lock\n-rw-r--r--@ 1 pakrym staff 1434 Jul 9 16:16 flake.nix\n-rw-r--r--@ 1 pakrym staff 10926 Jul 9 16:16 LICENSE\ndrwxr-xr-x@ 465 pakrym staff 14880 Jul 15 07:36 node_modules\n-rw-r--r--@ 1 pakrym staff 242 Aug 5 08:25 NOTICE\n-rw-r--r--@ 1 pakrym staff 578 Aug 14 12:31 package.json\n-rw-r--r--@ 1 pakrym staff 498 Aug 11 09:37 pnpm-lock.yaml\n-rw-r--r--@ 1 pakrym staff 58 Aug 11 09:37 pnpm-workspace.yaml\n-rw-r--r--@ 1 pakrym staff 2402 Jul 9 16:16 PNPM.md\n-rw-r--r--@ 1 pakrym staff 4393 Sep 12 14:36 README.md\ndrwxr-xr-x@ 4 pakrym staff 128 Sep 18 09:28 scripts\ndrwxr-xr-x@ 2 pakrym staff 64 Sep 11 11:34 tmp\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_2",
"item_type": "reasoning",
"text": "**Reviewing README.md file**\n\nI've located the README.md file at the root, and it’s 4393 bytes. Now, I need to remove the first line, but first, I should check its content to make sure I’m patching it correctly. I’ll use sed to display the first 20 lines. By reviewing those lines, I can determine exactly what needs to be removed before I proceed with the editing. Let's do this carefully!"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_3",
"item_type": "command_execution",
"command": "bash -lc sed -n '1,40p' README.md",
"aggregated_output": "<h1 align=\"center\">OpenAI Codex CLI</h1>\n\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n```shell\nnpm install -g @openai/codex\n```\n\nAlternatively, if you use Homebrew:\n\n```shell\nbrew install codex\n```\n\nThen simply run `codex` to get started:\n\n```shell\ncodex\n```\n\n<details>\n<summary>You can also go to the <a href=\"https://github.com/openai/codex/releases/latest\">latest GitHub Release</a> and download the appropriate binary for your platform.</summary>\n\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_4",
"item_type": "reasoning",
"text": "**Updating README file**\n\nThe user wants to update the README by removing the first line, which is an HTML h1 tag. I'll proceed to delete that line while keeping the rest intact. To do this, I need to use the apply_patch tool and create a patch in the diff format. I’ll take care to include context lines around the change. After removing the header, I’m considering whether to delete the following blank line as well to keep it tidy."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_5",
"item_type": "reasoning",
"text": "**Crafting the patch**\n\nThe user has asked to remove just the first line, without mentioning the blank lines. Technically, leaving a blank line at the start is acceptable, but it's not ideal. Ideally, I'd prefer to remove the first line while maintaining the subsequent blank line. However, if I can also remove that blank line, it could tidy things up even more. Still, since the user's request is strictly to remove only the first line, I'll stick to that and craft the patch accordingly."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_6",
"item_type": "assistant_message",
"text": "Applying the change by removing the first line from `README.md`."
}
}
{
"type": "item.completed",
"item": {
"id": "itm_7",
"item_type": "file_change",
"changes": [
{
"path": "/Users/pakrym/code/codex/README.md",
"kind": "update"
}
],
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_8",
"item_type": "reasoning",
"text": "**Validating README Update**\n\nI updated the README.md and now I need to validate that the first line has been successfully removed. To do this, I'll check the first 10 lines of the document to ensure everything looks correct. It’s always good to double-check these kinds of changes, so I’m going to take that extra step to make sure the update was executed properly. Let's see what those initial lines say!"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_9",
"item_type": "command_execution",
"command": "bash -lc sed -n '1,20p' README.md",
"aggregated_output": "\n<p align=\"center\"><code>npm i -g @openai/codex</code><br />or <code>brew install codex</code></p>\n\n<p align=\"center\"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer.\n</br>\n</br>If you want Codex in your code editor (VS Code, Cursor, Windsurf), <a href=\"https://developers.openai.com/codex/ide\">install in your IDE</a>\n</br>If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href=\"https://chatgpt.com/codex\">chatgpt.com/codex</a></p>\n\n<p align=\"center\">\n <img src=\"./.github/codex-cli-splash.png\" alt=\"Codex CLI splash\" width=\"80%\" />\n </p>\n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with your preferred package manager. If you use npm:\n\n",
"exit_code": 0,
"status": "completed"
}
}
{
"type": "item.completed",
"item": {
"id": "itm_10",
"item_type": "assistant_message",
"text": "- Updated `README.md:1` by removing the opening H1 line.\n- The README now starts with the install instructions paragraph.\n\nWant me to also remove the leading blank line at the top?"
}
}
```
</details>
The idea is to give users fully formatted items they can use directly in
their rendering/application logic and avoid having them building up
items manually based on events (unless they want to for streaming).
This PR implements only the `item.completed` payload for some event
types, more event types and item types to come.
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
I would like to be able to swap in a different way to resolve model
sampling requests, so this refactoring consolidates things behind
`attempt_stream_responses()` to make that easier. Ideally, we would
support an in-memory backend that we can use in our integration tests,
for example.
Instead of overwriting the contents of the composer when pressing
<kbd>Esc</kbd> when there's a queued message, prepend the queued
message(s) to the composer draft.
Because the `codex` process could contain sensitive information in
memory, such as API keys, we add logic so that when
`CODEX_SECURE_MODE=1` is specified, we avail ourselves of whatever the
operating system provides to restrict observability/tampering, which
includes:
- disabling `ptrace(2)`, so it is not possible to attach to the process
with a debugger, such as `gdb`
- disabling core dumps
Admittedly, a user with root privileges can defeat these safeguards.
For now, we only add support for this in the `codex` multitool, but we
may ultimately want to support this in some of the smaller CLIs that are
buildable out of our Cargo workspace.
## Current State Observations
- `Session` currently holds many unrelated responsibilities (history,
approval queues, task handles, rollout recorder, shell discovery, token
tracking, etc.), making it hard to reason about ownership and lifetimes.
- The anonymous `State` struct inside `codex.rs` mixes session-long data
with turn-scoped queues and approval bookkeeping.
- Turn execution (`run_task`) relies on ad-hoc local variables that
should conceptually belong to a per-turn state object.
- External modules (`codex::compact`, tests) frequently poke the raw
`Session.state` mutex, which couples them to implementation details.
- Interrupts, approvals, and rollout persistence all have bespoke
cleanup paths, contributing to subtle bugs when a turn is aborted
mid-flight.
## Desired End State
- Keep a slim `Session` object that acts as the orchestrator and façade.
It should expose a focused API (submit, approvals, interrupts, event
emission) without storing unrelated fields directly.
- Introduce a `state` module that encapsulates all mutable data
structures:
- `SessionState`: session-persistent data (history, approved commands,
token/rate-limit info, maybe user preferences).
- `ActiveTurn`: metadata for the currently running turn (sub-id, task
kind, abort handle) and an `Arc<TurnState>`.
- `TurnState`: all turn-scoped pieces (pending inputs, approval waiters,
diff tracker, review history, auto-compact flags, last agent message,
outstanding tool call bookkeeping).
- Group long-lived helpers/managers into a dedicated `SessionServices`
struct so `Session` does not accumulate "random" fields.
- Provide clear, lock-safe APIs so other modules never touch raw
mutexes.
- Ensure every turn creates/drops a `TurnState` and that
interrupts/finishes delegate cleanup to it.
For the most part, we try to avoid environment variables in favor of
config options so the environment variables do not leak into child
processes. These environment variables are no longer honored, so let's
delete them to be clear.
Ultimately, I would also like to eliminate `CODEX_RS_SSE_FIXTURE` in
favor of something cleaner.
refactors command_safety files into its own package, so we can add
platform-specific ones
Also creates a windows-specific of `is_known_safe_command` that just
returns false always, since that is what happens today.
This eliminates a "bounce" at the end of streaming where we hide the
status indicator at the end of the turn and the composer moves up two
lines.
Also, simplify streaming further by removing the HistorySink and
inverting control, and collapsing a few single-element structures.
Bumps [chrono](https://github.com/chronotope/chrono) from 0.4.41 to
0.4.42.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/chronotope/chrono/releases">chrono's
releases</a>.</em></p>
<blockquote>
<h2>0.4.42</h2>
<h2>What's Changed</h2>
<ul>
<li>Add fuzzer for DateTime::parse_from_str by <a
href="https://github.com/tyler92"><code>@tyler92</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1700">chronotope/chrono#1700</a></li>
<li>Fix wrong amount of micro/milliseconds by <a
href="https://github.com/nmlt"><code>@nmlt</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1703">chronotope/chrono#1703</a></li>
<li>Add warning about MappedLocalTime and wasm by <a
href="https://github.com/lutzky"><code>@lutzky</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1702">chronotope/chrono#1702</a></li>
<li>Fix incorrect parsing of fixed-length second fractions by <a
href="https://github.com/chris-leach"><code>@chris-leach</code></a> in
<a
href="https://redirect.github.com/chronotope/chrono/pull/1705">chronotope/chrono#1705</a></li>
<li>Fix cfgs for <code>wasm32-linux</code> support by <a
href="https://github.com/arjunr2"><code>@arjunr2</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1707">chronotope/chrono#1707</a></li>
<li>Fix OpenHarmony's <code>tzdata</code> parsing by <a
href="https://github.com/ldm0"><code>@ldm0</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1679">chronotope/chrono#1679</a></li>
<li>Convert NaiveDate to/from days since unix epoch by <a
href="https://github.com/findepi"><code>@findepi</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1715">chronotope/chrono#1715</a></li>
<li>Add <code>?Sized</code> bound to related methods of
<code>DelayedFormat::write_to</code> by <a
href="https://github.com/Huliiiiii"><code>@Huliiiiii</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1721">chronotope/chrono#1721</a></li>
<li>Add <code>from_timestamp_secs</code> method to <code>DateTime</code>
by <a href="https://github.com/jasonaowen"><code>@jasonaowen</code></a>
in <a
href="https://redirect.github.com/chronotope/chrono/pull/1719">chronotope/chrono#1719</a></li>
<li>Migrate to core::error::Error by <a
href="https://github.com/benbrittain"><code>@benbrittain</code></a> in
<a
href="https://redirect.github.com/chronotope/chrono/pull/1704">chronotope/chrono#1704</a></li>
<li>Upgrade to windows-bindgen 0.63 by <a
href="https://github.com/djc"><code>@djc</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1730">chronotope/chrono#1730</a></li>
<li>strftime: simplify error handling by <a
href="https://github.com/djc"><code>@djc</code></a> in <a
href="https://redirect.github.com/chronotope/chrono/pull/1731">chronotope/chrono#1731</a></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="f3fd15f976"><code>f3fd15f</code></a>
Bump version to 0.4.42</li>
<li><a
href="5cf5603500"><code>5cf5603</code></a>
strftime: add regression test case</li>
<li><a
href="a6231701ee"><code>a623170</code></a>
strftime: simplify error handling</li>
<li><a
href="36fbfb1221"><code>36fbfb1</code></a>
strftime: move specifier handling out of match to reduce rightward
drift</li>
<li><a
href="7f413c363b"><code>7f413c3</code></a>
strftime: yield None early</li>
<li><a
href="9d5dfe1640"><code>9d5dfe1</code></a>
strftime: outline constants</li>
<li><a
href="e5f6be7db4"><code>e5f6be7</code></a>
strftime: move error() method below caller</li>
<li><a
href="d516c2764d"><code>d516c27</code></a>
strftime: merge impl blocks</li>
<li><a
href="0ee2172fb9"><code>0ee2172</code></a>
strftime: re-order items to keep impls together</li>
<li><a
href="757a8b0226"><code>757a8b0</code></a>
Upgrade to windows-bindgen 0.63</li>
<li>Additional commits viewable in <a
href="https://github.com/chronotope/chrono/compare/v0.4.41...v0.4.42">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
This commit removes the `once_cell` dependency from `Cargo.toml` files
in the `codex-rs` and `apply-patch` directories, replacing its usage
with `std::sync::LazyLock` and `std::sync::OnceLock` where applicable.
This change simplifies the dependency tree and utilizes standard library
features for lazy initialization.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
I am not sure what is going on, as
https://github.com/openai/codex/pull/3660 introduced this new logic and
I swear that CI was green before I merged that PR, but I am seeing
failures in this CI job this morning. This feels like a
non-backwards-compatible change in `gh`, but that feels unlikely...
Nevertheless, this is what I currently see on my laptop:
```
$ gh --version
gh version 2.76.2 (2025-07-30)
https://github.com/cli/cli/releases/tag/v2.76.2
$ gh run list --workflow .github/workflows/rust-release.yml --branch rust-v0.40.0 --json workflowName,url,headSha --jq 'first(.[])'
{
"headSha": "5268705a69713752adcbd8416ef9e84a683f7aa3",
"url": "https://github.com/openai/codex/actions/runs/17952349351",
"workflowName": ".github/workflows/rust-release.yml"
}
```
Looking at sample output from an old GitHub issue
(https://github.com/cli/cli/issues/6678), it appears that, at least at
one point in time, the `workflowName` was _not_ the path to the
workflow.
Bumps [tempfile](https://github.com/Stebalien/tempfile) from 3.20.0 to
3.22.0.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/Stebalien/tempfile/blob/master/CHANGELOG.md">tempfile's
changelog</a>.</em></p>
<blockquote>
<h2>3.22.0</h2>
<ul>
<li>Updated <code>windows-sys</code> requirement to allow version
0.61.x</li>
<li>Remove <code>unstable-windows-keep-open-tempfile</code>
feature.</li>
</ul>
<h2>3.21.0</h2>
<ul>
<li>Updated <code>windows-sys</code> requirement to allow version
0.60.x</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="f720dbe098"><code>f720dbe</code></a>
chore: release 3.22.0</li>
<li><a
href="55d742cb5d"><code>55d742c</code></a>
chore: remove deprecated unstable feature flag</li>
<li><a
href="bc41a0b586"><code>bc41a0b</code></a>
build(deps): update windows-sys requirement from >=0.52, <0.61 to
>=0.52, <0....</li>
<li><a
href="3c55387ede"><code>3c55387</code></a>
test: make sure we don't drop tempdirs early (<a
href="https://redirect.github.com/Stebalien/tempfile/issues/373">#373</a>)</li>
<li><a
href="17bf644406"><code>17bf644</code></a>
doc(builder): clarify permissions (<a
href="https://redirect.github.com/Stebalien/tempfile/issues/372">#372</a>)</li>
<li><a
href="c7423f1761"><code>c7423f1</code></a>
doc(env): document the alternative to setting the tempdir (<a
href="https://redirect.github.com/Stebalien/tempfile/issues/371">#371</a>)</li>
<li><a
href="5af60ca9e3"><code>5af60ca</code></a>
test(wasi): run a few tests that shouldn't have been disabled (<a
href="https://redirect.github.com/Stebalien/tempfile/issues/370">#370</a>)</li>
<li><a
href="6c0c56198a"><code>6c0c561</code></a>
fix(doc): temp_dir doesn't check if writable</li>
<li><a
href="48bff5f54c"><code>48bff5f</code></a>
test(tempdir): configure tempdir on wasi</li>
<li><a
href="704a1d2752"><code>704a1d2</code></a>
test(tempdir): cleanup tempdir tests and run more tests on wasi</li>
<li>Additional commits viewable in <a
href="https://github.com/Stebalien/tempfile/compare/v3.20.0...v3.22.0">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
[//]: # (dependabot-start)
⚠️ **Dependabot is rebasing this PR** ⚠️
Rebasing might not happen immediately, so don't worry if this takes some
time.
Note: if you make any changes to this PR yourself, they will take
precedence over the rebase.
---
[//]: # (dependabot-end)
Bumps [serde](https://github.com/serde-rs/serde) from 1.0.224 to
1.0.226.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/serde-rs/serde/releases">serde's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.226</h2>
<ul>
<li>Deduplicate variant matching logic inside generated Deserialize impl
for adjacently tagged enums (<a
href="https://redirect.github.com/serde-rs/serde/issues/2935">#2935</a>,
thanks <a
href="https://github.com/Mingun"><code>@Mingun</code></a>)</li>
</ul>
<h2>v1.0.225</h2>
<ul>
<li>Avoid triggering a deprecation warning in derived Serialize and
Deserialize impls for a data structure that contains its own
deprecations (<a
href="https://redirect.github.com/serde-rs/serde/issues/2879">#2879</a>,
thanks <a
href="https://github.com/rcrisanti"><code>@rcrisanti</code></a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="1799547846"><code>1799547</code></a>
Release 1.0.226</li>
<li><a
href="2dbeefb11b"><code>2dbeefb</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2935">#2935</a>
from Mingun/dedupe-adj-enums</li>
<li><a
href="8a3c29ff19"><code>8a3c29f</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2986">#2986</a>
from dtolnay/didnotwork</li>
<li><a
href="defc24d361"><code>defc24d</code></a>
Remove "did not work" comment from test suite</li>
<li><a
href="2316610760"><code>2316610</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2929">#2929</a>
from Mingun/flatten-enum-tests</li>
<li><a
href="c09e2bd690"><code>c09e2bd</code></a>
Add tests for flatten unit variant in adjacently tagged (tag + content)
enums</li>
<li><a
href="fe7dcc4cd8"><code>fe7dcc4</code></a>
Test all possible orders of map entries for enum-flatten-in-struct
representa...</li>
<li><a
href="a20e66e131"><code>a20e66e</code></a>
Check serialization in
flatten::enum_::internally_tagged::unit_enum_with_unkn...</li>
<li><a
href="1c1a5d95cd"><code>1c1a5d9</code></a>
Reorder struct_ and newtype tests of adjacently_tagged enums to match
order i...</li>
<li><a
href="ee3c2372fb"><code>ee3c237</code></a>
Opt in to generate-macro-expansion when building on docs.rs</li>
<li>Additional commits viewable in <a
href="https://github.com/serde-rs/serde/compare/v1.0.224...v1.0.226">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
This updates our release process so that when we build an alpha of the
Codex CLI (as determined by pushing a tag of the format
`rust-v<cli-version>-alpha.<alpha-version>`), we will now publish the
corresponding npm module publicly, but under the `alpha` tag. As you can
see, this PR adds `--tag alpha` to the `npm publish` command, as
appropriate.
We try to ensure ripgrep (`rg`) is provided with Codex.
- For `brew`, we declare it as a dependency of our formula:
08d82d8b00/Formula/c/codex.rb (L24)
- For `npm`, we declare `@vscode/ripgrep` as a dependency, which
installs the platform-specific binary as part of a `postinstall` script:
fdb8dadcae/codex-cli/package.json (L22)
- Users who download the CLI directly from GitHub Releases are on their
own.
In practice, I have seen `@vscode/ripgrep` fail on occasion. Here is a
trace from a GitHub workflow:
```
npm error code 1
npm error path /Users/runner/hostedtoolcache/node/20.19.5/arm64/lib/node_modules/@openai/codex/node_modules/@vscode/ripgrep
npm error command failed
npm error command sh -c node ./lib/postinstall.js
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Download attempt 1 failed, retrying in 2 seconds...
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Download attempt 2 failed, retrying in 4 seconds...
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Download attempt 3 failed, retrying in 8 seconds...
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Download attempt 4 failed, retrying in 16 seconds...
npm error Finding release for v13.0.0-13
npm error GET https://api.github.com/repos/microsoft/ripgrep-prebuilt/releases/tags/v13.0.0-13
npm error Deleting invalid download cache
npm error Error: Request failed: 403
```
To eliminate this error, this PR changes things so that we vendor the
`rg` binary into https://www.npmjs.com/package/@openai/codex so it is
guaranteed to be included when a user runs `npm i -g @openai/codex`.
The downside of this approach is the increase in package size: we
include the `rg` executable for six architectures (in addition to the
six copies of `codex` we already include). In a follow-up, I plan to add
support for "slices" of our npm module, so that soon users will be able
to do:
```
npm install -g @openai/codex@aarch64-apple-darwin
```
Admittedly, this is a sizable change and I tried to clean some things up
in the process:
- `install_native_deps.sh` has been replaced by `install_native_deps.py`
- `stage_release.sh` and `stage_rust_release.py` has been replaced by
`build_npm_package.py`
We now vendor in a DotSlash file for ripgrep (as a modest attempt to
facilitate local testing) and then build up the extension by:
- creating a temp directory and copying `package.json` over to it with
the target value for `"version"`
- finding the GitHub workflow that corresponds to the
`--release-version` and copying the various `codex` artifacts to
respective `vendor/TARGET_TRIPLE/codex` folder
- downloading the `rg` artifacts specified in the DotSlash file and
copying them over to the respective `vendor/TARGET_TRIPLE/path` folder
- if `--pack-output` is specified, runs `npm pack` on the temp directory
To test, I downloaded the artifact produced by this CI job:
https://github.com/openai/codex/actions/runs/17961595388/job/51085840022?pr=3660
and verified that `node ./bin/codex.js 'which -a rg'` worked as
intended.
### Summary
Sometimes in exec runs, we want to allow the model to use the
`update_plan` tool, but that's not easily configurable. This change adds
a feature flag for this, and formats the output so it's human-readable
## Test Plan
<img width="1280" height="354" alt="Screenshot 2025-09-11 at 12 39
44 AM"
src="https://github.com/user-attachments/assets/72e11070-fb98-47f5-a784-5123ca7333d9"
/>
- Only show the usage data section when signed in with ChatGPT. (Tested
with Chat auth and API auth.)
- Friendlier string change.
- Also removed `.dim()` on the string, since it was the only string in
`/status` that was dim.
## Summary
Introduces a “ghost commit” workflow that snapshots the tree without
touching refs.
1. git commit-tree writes an unreferenced commit object from the current
index, optionally pointing to the current HEAD as its parent.
2. We then stash that commit id and use git restore --source <ghost> to
roll the worktree (and index) back to the recorded snapshot later on.
## Details
- Ghost commits live only as loose objects—we never update branches or
tags—so the repo history stays untouched while still giving us a full
tree snapshot.
- Force-included paths let us stage otherwise ignored files before
capturing the tree.
- Restoration rehydrates both tracked and force-included files while
leaving untracked/ignored files alone.
## Summary
- refactor the stream retry integration tests to construct conversations
through `TestCodex`
- remove bespoke config and tempdir setup now handled by the shared
builder
## Testing
- cargo test -p codex-core --test all
stream_error_allows_next_turn::continue_after_stream_error
- cargo test -p codex-core --test all
stream_no_completed::retries_on_early_close
------
https://chatgpt.com/codex/tasks/task_i_68d2b94d83888320bc75a0bc3bd77b49
Adds a "View Stack" to the bottom pane to allow for pushing/popping
bottom panels.
`esc` will go back instead of dismissing.
Benefit: We retain the "selection state" of a parent panel (e.g. the
review panel).
Backtracking multiple times could drop earlier turns. We now derive the
active user-turn positions from the transcript on demand (keying off the
latest session header) instead of caching state. This keeps the replayed
context intact during repeated edits and adds a regression test.
The only file to watch is the cargo.toml
All the others come from just fix + a few manual small fix
The set of rules have been taken from the list of clippy rules
arbitrarily while trying to optimise the learning and style of the code
while limiting the loss of productivity
Adds the following options:
1. Review current changes
2. Review a specific commit
3. Review against a base branch (PR style)
4. Custom instructions
<img width="487" height="330" alt="Screenshot 2025-09-20 at 2 11 36 PM"
src="https://github.com/user-attachments/assets/edb0aaa5-5747-47fa-881f-cc4c4f7fe8bc"
/>
---
\+ Adds the following UI helpers:
1. Makes list selection searchable
2. Adds navigation to the bottom pane, so you could add a stack of
popups
3. Basic custom prompt view
We currently get information about rate limits in the response headers.
We want to forward them to the clients to have better transparency.
UI/UX plans have been discussed and this information is needed.
Currently, we change the tool description according to the sandbox
policy and approval policy. This breaks the cache when the user hits
`/approvals`. This PR does the following:
- Always use the shell with escalation parameter:
- removes `create_shell_tool_for_sandbox` and always uses unified tool
via `create_shell_tool`
- Reject the func call when the model uses escalation parameter when it
cannot.
### Why Use `tokio::sync::Mutex`
`std::sync::Mutex` are not _async-aware_. As a result, they will block
the entire thread instead of just yielding the task. Furthermore they
can be poisoned which is not the case of `tokio` Mutex.
This allows the Tokio runtime to continue running other tasks while
waiting for the lock, preventing deadlocks and performance bottlenecks.
In general, this is preferred in async environment
This change instructs the model to install any missing command. Else
tokens are wasted when it tries to run
commands that aren't available multiple times before installing them.
Often, `gh` infers `--repo` when it is run from a Git clone, but our
`publish-npm` step is designed to avoid the overhead of cloning the
repo, so add the `--repo` option explicitly to fix things.
The build for `v0.37.0-alpha.3` failed on the `Create GitHub Release`
step:
https://github.com/openai/codex/actions/runs/17786866086/job/50556513221
with:
```
⚠️ GitHub release failed with status: 403
{"message":"Resource not accessible by integration","documentation_url":"https://docs.github.com/rest/releases/releases#create-a-release","status":"403"}
Skip retry — your GitHub token/PAT does not have the required permission to create a release
```
I believe I should have not introduced a top-level `permissions` for the
workflow in https://github.com/openai/codex/pull/3431 because that
affected the `permissions` for each job in the workflow.
This PR introduces `publish-npm` as its own job, which allows us to:
- consolidate all the Node.js-related steps required for publishing
- limit the reach of the `id-token: write` permission
- skip it altogether if is an alpha build
With this PR, each of `release`, `publish-npm`, and `update-branch` has
an explicit `permissions` block.
Proposal: We want to record a dev message like so:
```
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "<user_action>
<context>User initiated a review task. Here's the full review output from reviewer model. User may select one or more comments to resolve.</context>
<action>review</action>
<results>
{findings_str}
</results>
</user_action>"
}
]
},
```
Without showing in the chat transcript.
Rough idea, but it fixes issue where the user finishes a review thread,
and asks the parent "fix the rest of the review issues" thinking that
the parent knows about it.
### Question: Why not a tool call?
Because the agent didn't make the call, it was a human. + we haven't
implemented sub-agents yet, and we'll need to think about the way we
represent these human-led tool calls for the agent.
1. Adds the environment prompt (including cwd) to review thread
2. Prepends the review prompt as a user message (temporary fix so the
instructions are not replaced on backend)
3. Sets reasoning to low
4. Sets default review model to `gpt-5-codex`
## Summary
SendUserTurn has not been correctly handling updates to policies. While
the tui protocol handles this in `Op::OverrideTurnContext`, the
SendUserTurn should be appending `EnvironmentContext` messages when the
sandbox settings change. MCP client behavior should match the cli
behavior, so we update `SendUserTurn` message to match.
## Testing
- [x] Added prompt caching tests
Bumps [wildmatch](https://github.com/becheran/wildmatch) from 2.4.0 to
2.5.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/becheran/wildmatch/releases">wildmatch's
releases</a>.</em></p>
<blockquote>
<h2>v2.5.0</h2>
<p><a
href="https://redirect.github.com/becheran/wildmatch/pull/27">becheran/wildmatch#27</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="b39902c120"><code>b39902c</code></a>
chore: Release wildmatch version 2.5.0</li>
<li><a
href="87a8cf4c80"><code>87a8cf4</code></a>
Merge pull request <a
href="https://redirect.github.com/becheran/wildmatch/issues/28">#28</a>
from smichaku/micha/fix-unicode-case-insensitive-matching</li>
<li><a
href="a3ab4903f5"><code>a3ab490</code></a>
fix: Fix unicode matching for non-ASCII characters</li>
<li>See full diff in <a
href="https://github.com/becheran/wildmatch/compare/v2.4.0...v2.5.0">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [serde](https://github.com/serde-rs/serde) from 1.0.219 to
1.0.223.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/serde-rs/serde/releases">serde's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.223</h2>
<ul>
<li>Fix serde_core documentation links (<a
href="https://redirect.github.com/serde-rs/serde/issues/2978">#2978</a>)</li>
</ul>
<h2>v1.0.222</h2>
<ul>
<li>Make <code>serialize_with</code> attribute produce code that works
if respanned to 2024 edition (<a
href="https://redirect.github.com/serde-rs/serde/issues/2950">#2950</a>,
thanks <a href="https://github.com/aytey"><code>@aytey</code></a>)</li>
</ul>
<h2>v1.0.221</h2>
<ul>
<li>Documentation improvements (<a
href="https://redirect.github.com/serde-rs/serde/issues/2973">#2973</a>)</li>
<li>Deprecate <code>serde_if_integer128!</code> macro (<a
href="https://redirect.github.com/serde-rs/serde/issues/2975">#2975</a>)</li>
</ul>
<h2>v1.0.220</h2>
<ul>
<li>Add a way for data formats to depend on serde traits without waiting
for serde_derive compilation: <a
href="https://docs.rs/serde_core">https://docs.rs/serde_core</a> (<a
href="https://redirect.github.com/serde-rs/serde/issues/2608">#2608</a>,
thanks <a
href="https://github.com/osiewicz"><code>@osiewicz</code></a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="6c316d7cb5"><code>6c316d7</code></a>
Release 1.0.223</li>
<li><a
href="a4ac0c2bc6"><code>a4ac0c2</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2978">#2978</a>
from dtolnay/htmlrooturl</li>
<li><a
href="ed76364f87"><code>ed76364</code></a>
Change serde_core's html_root_url to docs.rs/serde_core</li>
<li><a
href="57e21a1afa"><code>57e21a1</code></a>
Release 1.0.222</li>
<li><a
href="bb58726133"><code>bb58726</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2950">#2950</a>
from aytey/fix_lifetime_issue_2024</li>
<li><a
href="3f6925125b"><code>3f69251</code></a>
Delete unneeded field of MapDeserializer</li>
<li><a
href="fd4decf2fe"><code>fd4decf</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/serde/issues/2976">#2976</a>
from dtolnay/content</li>
<li><a
href="00b1b6b2b5"><code>00b1b6b</code></a>
Move Content's Deserialize impl from serde_core to serde</li>
<li><a
href="cf141aa8c7"><code>cf141aa</code></a>
Move Content's Clone impl from serde_core to serde</li>
<li><a
href="ff3aee490a"><code>ff3aee4</code></a>
Release 1.0.221</li>
<li>Additional commits viewable in <a
href="https://github.com/serde-rs/serde/compare/v1.0.219...v1.0.223">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [serde_json](https://github.com/serde-rs/json) from 1.0.143 to
1.0.145.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/serde-rs/json/releases">serde_json's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.145</h2>
<ul>
<li>Raise serde version requirement to >=1.0.220</li>
</ul>
<h2>v1.0.144</h2>
<ul>
<li>Switch serde dependency to serde_core (<a
href="https://redirect.github.com/serde-rs/json/issues/1285">#1285</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="efa66e3a1d"><code>efa66e3</code></a>
Release 1.0.145</li>
<li><a
href="23679e2b9d"><code>23679e2</code></a>
Add serde version constraint</li>
<li><a
href="fc27bafbf7"><code>fc27baf</code></a>
Release 1.0.144</li>
<li><a
href="caef3c6ea6"><code>caef3c6</code></a>
Ignore uninlined_format_args pedantic clippy lint</li>
<li><a
href="81ba3aaaff"><code>81ba3aa</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/json/issues/1285">#1285</a>
from dtolnay/serdecore</li>
<li><a
href="d21e8ce7a7"><code>d21e8ce</code></a>
Switch serde dependency to serde_core</li>
<li><a
href="6beb6cd596"><code>6beb6cd</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/json/issues/1286">#1286</a>
from dtolnay/up</li>
<li><a
href="1dbc803749"><code>1dbc803</code></a>
Raise required compiler to Rust 1.61</li>
<li><a
href="0bf5d87003"><code>0bf5d87</code></a>
Enforce trybuild >= 1.0.108</li>
<li><a
href="d12e943590"><code>d12e943</code></a>
Update actions/checkout@v4 -> v5</li>
<li>See full diff in <a
href="https://github.com/serde-rs/json/compare/v1.0.143...v1.0.145">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Reported height was `20` instead of `21`, so `area.height >=
MIN_ANIMATION_HEIGHT` was `false` and therefore `show_animation` was
`false`, so the animation never displayed.
Changes:
- skip the welcome animation when the terminal area is below 60x21
- skip the model upgrade animation when the terminal area is below 60x24
to avoid clipping
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
Bumps [tracing-subscriber](https://github.com/tokio-rs/tracing) from
0.3.19 to 0.3.20.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/tokio-rs/tracing/releases">tracing-subscriber's
releases</a>.</em></p>
<blockquote>
<h2>tracing-subscriber 0.3.20</h2>
<p><strong>Security Fix</strong>: ANSI Escape Sequence Injection
(CVE-TBD)</p>
<h2>Impact</h2>
<p>Previous versions of tracing-subscriber were vulnerable to ANSI
escape sequence injection attacks. Untrusted user input containing ANSI
escape sequences could be injected into terminal output when logged,
potentially allowing attackers to:</p>
<ul>
<li>Manipulate terminal title bars</li>
<li>Clear screens or modify terminal display</li>
<li>Potentially mislead users through terminal manipulation</li>
</ul>
<p>In isolation, impact is minimal, however security issues have been
found in terminal emulators that enabled an attacker to use ANSI escape
sequences via logs to exploit vulnerabilities in the terminal
emulator.</p>
<h2>Solution</h2>
<p>Version 0.3.20 fixes this vulnerability by escaping ANSI control
characters in when writing events to destinations that may be printed to
the terminal.</p>
<h2>Affected Versions</h2>
<p>All versions of tracing-subscriber prior to 0.3.20 are affected by
this vulnerability.</p>
<h2>Recommendations</h2>
<p>Immediate Action Required: We recommend upgrading to
tracing-subscriber 0.3.20 immediately, especially if your
application:</p>
<ul>
<li>Logs user-provided input (form data, HTTP headers, query parameters,
etc.)</li>
<li>Runs in environments where terminal output is displayed to
users</li>
</ul>
<h2>Migration</h2>
<p>This is a patch release with no breaking API changes. Simply update
your Cargo.toml:</p>
<pre lang="toml"><code>[dependencies]
tracing-subscriber = "0.3.20"
</code></pre>
<h2>Acknowledgments</h2>
<p>We would like to thank <a href="http://github.com/zefr0x">zefr0x</a>
who responsibly reported the issue at
<code>security@tokio.rs</code>.</p>
<p>If you believe you have found a security vulnerability in any
tokio-rs project, please email us at <code>security@tokio.rs</code>.</p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="4c52ca5266"><code>4c52ca5</code></a>
fmt: fix ANSI escape sequence injection vulnerability (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3368">#3368</a>)</li>
<li><a
href="f71cebe41e"><code>f71cebe</code></a>
subscriber: impl Clone for EnvFilter (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3360">#3360</a>)</li>
<li><a
href="3a1f571102"><code>3a1f571</code></a>
Fix CI (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3361">#3361</a>)</li>
<li><a
href="e63ef57f3d"><code>e63ef57</code></a>
chore: prepare tracing-attributes 0.1.30 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3316">#3316</a>)</li>
<li><a
href="6e59a13b1a"><code>6e59a13</code></a>
attributes: fix tracing::instrument regression around shadowing (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3311">#3311</a>)</li>
<li><a
href="e4df761275"><code>e4df761</code></a>
tracing: update core to 0.1.34 and attributes to 0.1.29 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3305">#3305</a>)</li>
<li><a
href="643f392ebb"><code>643f392</code></a>
chore: prepare tracing-attributes 0.1.29 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3304">#3304</a>)</li>
<li><a
href="d08e7a6eea"><code>d08e7a6</code></a>
chore: prepare tracing-core 0.1.34 (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3302">#3302</a>)</li>
<li><a
href="6e70c571d3"><code>6e70c57</code></a>
tracing-subscriber: count numbers of enters in <code>Timings</code> (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/2944">#2944</a>)</li>
<li><a
href="c01d4fd9de"><code>c01d4fd</code></a>
fix docs and enable CI on <code>main</code> branch (<a
href="https://redirect.github.com/tokio-rs/tracing/issues/3295">#3295</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/tokio-rs/tracing/compare/tracing-subscriber-0.3.19...tracing-subscriber-0.3.20">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [slab](https://github.com/tokio-rs/slab) from 0.4.10 to 0.4.11.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/tokio-rs/slab/releases">slab's
releases</a>.</em></p>
<blockquote>
<h2>v0.4.11</h2>
<ul>
<li>Fix <code>Slab::get_disjoint_mut</code> out of bounds (<a
href="https://redirect.github.com/tokio-rs/slab/issues/152">#152</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/tokio-rs/slab/blob/master/CHANGELOG.md">slab's
changelog</a>.</em></p>
<blockquote>
<h1>0.4.11 (August 8, 2025)</h1>
<ul>
<li>Fix <code>Slab::get_disjoint_mut</code> out of bounds (<a
href="https://redirect.github.com/tokio-rs/slab/issues/152">#152</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="2e5779f8eb"><code>2e5779f</code></a>
Release v0.4.11 (<a
href="https://redirect.github.com/tokio-rs/slab/issues/153">#153</a>)</li>
<li><a
href="2d65c514bc"><code>2d65c51</code></a>
Fix get_disjoint_mut error condition (<a
href="https://redirect.github.com/tokio-rs/slab/issues/152">#152</a>)</li>
<li>See full diff in <a
href="https://github.com/tokio-rs/slab/compare/v0.4.10...v0.4.11">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts page](https://github.com/openai/codex/network/alerts).
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Summary
- common: use exact equality for Swiftfox exclusion to avoid hiding
future slugs that merely contain the substring
- core: treat missing internal_storage.json as expected (debug), warn
only on real IO/parse errors
- tui: drop DEBUG_HIGH gate; always consider showing rollout prompt, but
suppress under ApiKey auth mode
When logging in using ChatGPT using the `codex login` command, a
successful login should write a new `auth.json` file with the ChatGPT
token information. The old code attempted to retain the API key and
merge the token information into the existing `auth.json` file. With the
new simplified login mechanism, `auth.json` should have auth information
for only ChatGPT or API Key, not both.
The `codex login --api-key <key>` code path was already doing the right
thing here, but the `codex login` command was incorrect. This PR fixes
the problem and adds test cases for both commands.
This PR addresses an edge-case bug that appears in the VS Code extension
in the following situation:
1. Log in using ChatGPT (using either the CLI or extension). This will
create an `auth.json` file.
2. Manually modify `config.toml` to specify a custom provider.
3. Start a fresh copy of the VS Code extension.
The profile menu in the VS Code extension will indicate that you are
logged in using ChatGPT even though you're not.
This is caused by the `get_auth_status` method returning an
`auth_method: 'chatgpt'` when a custom provider is configured and it
doesn't use OpenAI auth (i.e. `requires_openai_auth` is false). The
method should always return `auth_method: None` if
`requires_openai_auth` is false.
The same bug also causes the NUX (new user experience) screen to be
displayed in the VSCE in this situation.
## Summary
Resolves a merge conflict between #3597 and #3560, and adds tests to
double check our apply_patch configuration.
## Testing
- [x] Added unit tests
---------
Co-authored-by: dedrisian-oai <dedrisian@openai.com>
Adding the ability to resume conversations.
we have one verb `resume`.
Behavior:
`tui`:
`codex resume`: opens session picker
`codex resume --last`: continue last message
`codex resume <session id>`: continue conversation with `session id`
`exec`:
`codex resume --last`: continue last conversation
`codex resume <session id>`: continue conversation with `session id`
Implementation:
- I added a function to find the path in `~/.codex/sessions/` with a
`UUID`. This is helpful in resuming with session id.
- Added the above mentioned flags
- Added lots of testing
There are exactly 4 types of flaky tests in Windows x86 right now:
1. `review_input_isolated_from_parent_history` => Times out waiting for
closing events
2. `review_does_not_emit_agent_message_on_structured_output` => Times
out waiting for closing events
3. `auto_compact_runs_after_token_limit_hit` => Times out waiting for
closing events
4. `auto_compact_runs_after_token_limit_hit` => Also has a problem where
auto compact should add a third request, but receives 4 requests.
1, 2, and 3 seem to be solved with increasing threads on windows runner
from 2 -> 4.
Don't know yet why # 4 is happening, but probably also because of
WireMock issues on windows causing races.
We need to construct the history different when compact happens. For
this, we need to just consider the history after compact and convert
compact to a response item.
This needs to change and use `build_compact_history` when this #3446 is
merged.
No (intended) functional change.
This refactors the transcript view to hold a list of HistoryCells
instead of a list of Lines. This simplifies and makes much of the logic
more robust, as well as laying the groundwork for future changes, e.g.
live-updating history cells in the transcript.
Similar to #2879 in goal. Fixes#2755.
## 📝 Review Mode -- Core
This PR introduces the Core implementation for Review mode:
- New op `Op::Review { prompt: String }:` spawns a child review task
with isolated context, a review‑specific system prompt, and a
`Config.review_model`.
- `EnteredReviewMode`: emitted when the child review session starts.
Every event from this point onwards reflects the review session.
- `ExitedReviewMode(Option<ReviewOutputEvent>)`: emitted when the review
finishes or is interrupted, with optional structured findings:
```json
{
"findings": [
{
"title": "<≤ 80 chars, imperative>",
"body": "<valid Markdown explaining *why* this is a problem; cite files/lines/functions>",
"confidence_score": <float 0.0-1.0>,
"priority": <int 0-3>,
"code_location": {
"absolute_file_path": "<file path>",
"line_range": {"start": <int>, "end": <int>}
}
}
],
"overall_correctness": "patch is correct" | "patch is incorrect",
"overall_explanation": "<1-3 sentence explanation justifying the overall_correctness verdict>",
"overall_confidence_score": <float 0.0-1.0>
}
```
## Questions
### Why separate out its own message history?
We want the review thread to match the training of our review models as
much as possible -- that means using a custom prompt, removing user
instructions, and starting a clean chat history.
We also want to make sure the review thread doesn't leak into the parent
thread.
### Why do this as a mode, vs. sub-agents?
1. We want review to be a synchronous task, so it's fine for now to do a
bespoke implementation.
2. We're still unclear about the final structure for sub-agents. We'd
prefer to land this quickly and then refactor into sub-agents without
rushing that implementation.
this adds some more capabilities to the default sandbox which I feel are
safe. Most are in the
[renderer.sb](https://source.chromium.org/chromium/chromium/src/+/main:sandbox/policy/mac/renderer.sb)
sandbox for chrome renderers, which i feel is fair game for codex
commands.
Specific changes:
1. Allow processes in the sandbox to send signals to any other process
in the same sandbox (e.g. child processes or daemonized processes),
instead of just themselves.
2. Allow user-preference-read
3. Allow process-info* to anything in the same sandbox. This is a bit
wider than Chromium allows, but it seems OK to me to allow anything in
the sandbox to get details about other processes in the same sandbox.
Bazel uses these to e.g. wait for another process to exit.
4. Allow all CPU feature detection, this seems harmless to me. It's
wider than Chromium, but Chromium is concerned about fingerprinting, and
tightly controls what CPU features they actually care about, and we
don't have either that restriction or that advantage.
5. Allow new sysctl-reads:
```
(sysctl-name "vm.loadavg")
(sysctl-name-prefix "kern.proc.pgrp.")
(sysctl-name-prefix "kern.proc.pid.")
(sysctl-name-prefix "net.routetable.")
```
bazel needs these for waiting on child processes and for communicating
with its local build server, i believe. I wonder if we should just allow
all (sysctl-read), as reading any arbitrary info about the system seems
fine to me.
6. Allow iokit-open on RootDomainUserClient. This has to do with power
management I believe, and Chromium allows renderers to do this, so okay.
Bazel needs it to boot successfully, possibly for sleep/wake callbacks?
7. Mach lookup to `com.apple.system.opendirectoryd.libinfo`, which has
to do with user data, and which Chrome allows.
8. Mach lookup to `com.apple.PowerManagement.control`. Chromium allows
its GPU process to do this, but not its renderers. Bazel needs this to
boot, probably relatedly to sleep/wake stuff.
Azure Responses API doesn't work well with store:false and response
items.
If store = false and id is sent an error is thrown that ID is not found
If store = false and id is not sent an error is thrown that ID is
required
Add detection for Azure urls and add a workaround to preserve reasoning
item IDs and send store:true
sometimes the model forgets to actually invoke `apply_patch` and puts a
patch as the script body. trying to execute this as bash sometimes
creates files named `,` or `{` or does other unknown things, so catch
this situation and return an error to the model.
## Compact feature:
1. Stops the model when the context window become too large
2. Add a user turn, asking for the model to summarize
3. Build a bridge that contains all the previous user message + the
summary. Rendered from a template
4. Start sampling again from a clean conversation with only that bridge
It turns out that we want slightly different behavior for the
`SetDefaultModel` RPC because some models do not work with reasoning
(like GPT-4.1), so we should be able to explicitly clear this value.
Verified in `codex-rs/mcp-server/tests/suite/set_default_model.rs`.
## Summary
Standardizes the shell description across sandbox_types, since we cover
this in the prompt, and have moved necessary details (like
network_access and writeable workspace roots) to EnvironmentContext
messages.
## Test Plan
- [x] updated unit tests
This adds `SetDefaultModel`, which takes `model` and `reasoning_effort`
as optional fields. If set, the field will overwrite what is in the
user's `config.toml`.
This reuses logic that was added to support the `/model` command in the
TUI: https://github.com/openai/codex/pull/2799.
`ClientRequest::NewConversation` picks up the reasoning level from the user's defaults in `config.toml`, so it should be reported in `NewConversationResponse`.
Adds further information on how to get started with `codex mcp`:
- Tool details and parameter references
- Quickstart with example using MCP inspector.
## Summary
Handle timeouts the same way, regardless of approval mode. There's more
to do here, but this is simple and should be zero-regret
## Testing
- [x] existing tests pass
- [x] test locally and verify rollout
Created this PR by:
- adding `redundant_clone` to `[workspace.lints.clippy]` in
`cargo-rs/Cargol.toml`
- running `cargo clippy --tests --fix`
- running `just fmt`
Though I had to clean up one instance of the following that resulted:
```rust
let codex = codex;
```
Apparently `-F` is the correct thing to use. From the code sample on
https://docs.github.com/en/rest/git/refs?apiVersion=2022-11-28#update-a-reference
```shell
gh api \
--method PATCH \
-H "Accept: application/vnd.github+json" \
-H "X-GitHub-Api-Version: 2022-11-28" \
/repos/OWNER/REPO/git/refs/REF \
-f 'sha=aa218f56b14c9653891f9e74264a383fa43fefbd' -F "force=true"
```
Also, I ran the following locally and verified it worked:
```shell
export GITHUB_REPOSITORY=openai/codex
export GITHUB_SHA=305252b2fb2d57bb40a9e4bad269db9a761f7099
gh api \
repos/${GITHUB_REPOSITORY}/git/refs/heads/latest-alpha-cli \
-X PATCH \
-f sha="${GITHUB_SHA}" \
-F force=true
```
`$GITHUB_REPOSITORY` and `$GITHUB_SHA` should already be available as
environment variables for the `run` step without having to be redeclared
in the `env` section.
This PR does the following:
* Adds the ability to paste or type an API key.
* Removes the `preferred_auth_method` config option. The last login
method is always persisted in auth.json, so this isn't needed.
* If OPENAI_API_KEY env variable is defined, the value is used to
prepopulate the new UI. The env variable is otherwise ignored by the
CLI.
* Adds a new MCP server entry point "login_api_key" so we can implement
this same API key behavior for the VS Code extension.
<img width="473" height="140" alt="Screenshot 2025-09-04 at 3 51 04 PM"
src="https://github.com/user-attachments/assets/c11bbd5b-8a4d-4d71-90fd-34130460f9d9"
/>
<img width="726" height="254" alt="Screenshot 2025-09-04 at 3 51 32 PM"
src="https://github.com/user-attachments/assets/6cc76b34-309a-4387-acbc-15ee5c756db9"
/>
- Ensure replacements are applied in index order for determinism.
- Add tests for addition chunk followed by removal and worktree-aware
helper.
This fixes a panic I observed.
Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>
This updates `rust-release.yml` so that the last step of creating a
release entails updating the `latest-alpha-cli` branch to point to the
tag used to create the latest release. This will facilitate building
automation to identify the most recent alpha release of Codex CLI
(though note this branch could also point to an official release, as it
is implemented today).
This introduces a new job, `update-branch`, which depends on the
`release` job. I made it separate from the `release` job because
`update-branch` needs the `contents: write` permission, so this limits
the amount of work we do with that permission.
Note I also created a branch protection rule for `latest-alpha-cli`
that:
- specifies repository admins as the only members of the bypass list
- only those with bypass permissions can create, update, or delete this
branch
- this branch requires a linear history
- note that force pushes _are_ allowed
This is the first step in fixing
https://github.com/openai/codex/issues/3098.
As a follow-up to https://github.com/openai/codex/pull/3439, this adds a
CI job to ensure the codegen script has to be updated in order to change
`codex-rs/mcp-types/src/lib.rs`.
This PR changes get history op to get path. Then, forking will use a
path. This will help us have one unified codepath for resuming/forking
conversations. Will also help in having rollout history in order. It
also fixes a bug where you won't see the UI when resuming after forking.
## Unified PTY-Based Exec Tool
Note: this requires to have this flag in the config:
`use_experimental_unified_exec_tool=true`
- Adds a PTY-backed interactive exec feature (“unified_exec”) with
session reuse via
session_id, bounded output (128 KiB), and timeout clamping (≤ 60 s).
- Protocol: introduces ResponseItem::UnifiedExec { session_id,
arguments, timeout_ms }.
- Tools: exposes unified_exec as a function tool (Responses API);
excluded from Chat
Completions payload while still supported in tool lists.
- Path handling: resolves commands via PATH (or explicit paths), with
UTF‑8/newline‑aware
truncation (truncate_middle).
- Tests: cover command parsing, path resolution, session
persistence/cleanup, multi‑session
isolation, timeouts, and truncation behavior.
This adds a simple endpoint that provides the email address encoded in
`$CODEX_HOME/auth.json`.
As noted, for now, we do not hit the server to verify this is the user's
true email address.
https://github.com/openai/codex/pull/3395 updated `mcp-types/src/lib.rs`
by hand, but that file is generated code that is produced by
`mcp-types/generate_mcp_types.py`. Unfortunately, we do not have
anything in CI to verify this right now, but I will address that in a
subsequent PR.
#3395 ended up introducing a change that added a required field when
deserializing `InitializeResult`, breaking Codex when used as an MCP
client, so the quick fix in #3436 was to make the new field `Optional`
with `skip_serializing_if = "Option::is_none"`, but that did not address
the problem that `mcp-types/generate_mcp_types.py` and
`mcp-types/src/lib.rs` are out of sync.
This PR gets things back to where they are in sync. It removes the
custom `mcp_types::McpClientInfo` type that was added to
`mcp-types/src/lib.rs` and forces us to use the generated
`mcp_types::Implementation` type. Though this PR also updates
`generate_mcp_types.py` to generate the additional `user_agent:
Optional<String>` field on `Implementation` so that we can continue to
specify it when Codex operates as an MCP server.
However, this also requires us to specify `user_agent: None` when Codex
operates as an MCP client.
We may want to introduce our own `InitializeResult` type that is
specific to when we run as a server to avoid this in the future, but my
immediate goal is just to get things back in sync.
# External (non-OpenAI) Pull Request Requirements
Currently, mcp server fail to start with:
```
🖐 MCP client for `<CLIENT>` failed to start: missing field `user_agent`
````
It isn't clear to me yet why this is happening. My understanding is that
this struct is simply added as a new field to the response but this
should fix it until I figure out the full story here.
<img width="714" height="262" alt="CleanShot 2025-09-10 at 13 58 59"
src="https://github.com/user-attachments/assets/946b1313-5c1c-43d3-8ae8-ecc3de3406fc"
/>
Also, simplify the streaming behavior.
This fixes a number of display issues with streaming markdown, and paves
the way for better markdown features (e.g. customizable styles, syntax
highlighting, markdown-aware wrapping).
Not currently supported:
- footnotes
- tables
- reference-style links
This PR improves two existing auth-related tests. They were failing when
run in an environment where an `OPENAI_API_KEY` env variable was
defined. The change makes them more resilient.
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the "Contributing" section
of the README or your PR may be closed:
https://github.com/openai/codex#contributing
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
This PR adds an `images` field to the existing `UserMessageEvent` so we
can encode zero or more images associated with a user message. This
allows images to be restored when conversations are restored.
Model providers like Groq, Openrouter, AWS Bedrock, VertexAI and others
typically prefix the name of gpt-oss models with `openai`, e.g.
`openai/gpt-oss-120b`.
This PR is to match the model name slug using `contains` instead of
`starts_with` to ensure that the `apply_patch` tool is included in the
tools for models names like `openai/gpt-oss-120b`
Without this, the gpt-oss models will often try to call the
`apply_patch` tool directly instead of via the `shell` command, leading
to validation errors.
I have run all the local checks.
Note: The gpt-oss models from non-Ollama providers are typically run via
a profile with a different base_url (instead of with the `--oss` flag)
---------
Co-authored-by: Andrew Tan <andrewtan@Andrews-Mac.local>
The previous config approach had a few issues:
1. It is part of the config but not designed to be used externally
2. It had to be wired through many places (look at the +/- on this PR
3. It wasn't guaranteed to be set consistently everywhere because we
don't have a super well defined way that configs stack. For example, the
extension would configure during newConversation but anything that
happened outside of that (like login) wouldn't get it.
This env var approach is cleaner and also creates one less thing we have
to deal with when coming up with a better holistic story around configs.
One downside is that I removed the unit test testing for the override
because I don't want to deal with setting the global env or spawning
child processes and figuring out how to introspect their originator
header. The new code is sufficiently simple and I tested it e2e that I
feel as if this is still worth it.
It was hard for me to read the expected lines as a `["one", "two",
"three"]` array, maybe not so hard for the model but probably not having
to un-escape in its head would help it out :)
Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>
I verified that the output of `protocol-ts$ cargo run` is unchanged by
removing this line..
Added a comment on `ServerNotification` with justification to make this
clear.
This commit adds a re-export for InitialHistory from the internal
conversation_manager module in codex-core's lib.rs.
The `RolloutRecorder::get_rollout_history` method (exposed via `pub use
rollout::RolloutRecorder;`, already present in lib.rs) returns an
`InitialHistory` type, which is defined in the private
conversation_manager module. Without this re-export, consumers of the
public RolloutRecorder API would not be able to directly use the return
type, as they cannot access the private module. This would result in an
inconvenient experience where the method's return value cannot be
handled without additional, non-obvious imports.
By adding `pub use conversation_manager::InitialHistory;`, we make
InitialHistory available as `codex_core::InitialHistory`, improving API
ergonomics for users of the rollout functionality while keeping the
conversation_manager module internal.
No functional changes are made; this is a pure re-export for better
usability.
Signed-off-by: M4n5ter <m4n5terrr@gmail.com>
Adds support for `ArchiveConversation` in the JSON-RPC server that takes
a `(ConversationId, PathBuf)` pair and:
- verifies the `ConversationId` corresponds to the rollout id at the
`PathBuf`
- if so, invokes
`ConversationManager.remove_conversation(ConversationId)`
- if the `CodexConversation` was in memory, send `Shutdown` and wait for
`ShutdownComplete` with a timeout
- moves the `.jsonl` file to `$CODEX_HOME/archived_sessions`
---------
Co-authored-by: Gabriel Peal <gabriel@openai.com>
Adding the `rollout_path` to the `NewConversationResponse` makes it so a
client can perform subsequent operations on a `(ConversationId,
PathBuf)` pair. #3353 will introduce support for `ArchiveConversation`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/3352).
* #3353
* __->__ #3352
I started looking at https://nexte.st/ because I was interested in a
test harness that lets a test dynamically declare itself "skipped,"
which would be a nice alternative to this pattern:
4c46490e53/codex-rs/core/tests/suite/cli_stream.rs (L22-L27)
ChatGPT pointed me at https://nexte.st/, which also claims to be "up to
3x as fast as cargo test." Locally, in `codex-rs`, I see
- `cargo nextest run` finishes in 19s
- `cargo test` finishes in 37s
Though looking at CI, the wins are quite as big, presumably because my
laptop has more cores than our GitHub runners (which is a separate
issue...). Comparing the [CI jobs from this
PR](https://github.com/openai/codex/actions/runs/17561325162/job/49878216246?pr=3323)
with that of a [recent open
PR](https://github.com/openai/codex/actions/runs/17561066581/job/49877342753?pr=3321):
| | `cargo test` | `cargo nextest` |
| ----------------------------------------------- | ------------ |
--------------- |
| `macos-14 - aarch64-apple-darwin` | 2m16s | 1m51s |
| `macos-14 - aarch64-apple-darwin` | 5m04s | 3m44s |
| `ubuntu-24.04 - x86_64-unknown-linux-musl` | 2m02s | 1m56s |
| `ubuntu-24.04-arm - aarch64-unknown-linux-musl` | 2m01s | 1m35s |
| `windows-latest - x86_64-pc-windows-msvc` | 3m07s | 2m53s |
| `windows-11-arm - aarch64-pc-windows-msvc` | 3m10s | 2m45s |
I thought that, to start, we would only make this change in CI before
declaring it the "official" way for the team to run the test suite.
Though unfortunately, I do not believe that `cargo nextest` _actually_
supports a dynamic skip feature, so I guess I'll have to keep looking?
Some related discussions:
- https://internals.rust-lang.org/t/pre-rfc-skippable-tests/14611
- https://internals.rust-lang.org/t/skippable-tests/21260
## Session snapshot
For POSIX shell, the goal is to take a snapshot of the interactive shell
environment, store it in a session file located in `.codex/` and only
source this file for every command that is run.
As a result, if a snapshot files exist, `bash -lc <CALL>` get replaced
by `bash -c <CALL>`.
This also fixes the issue that `bash -lc` does not source `.bashrc`,
resulting in missing env variables and aliases in the codex session.
## POSIX unification
Unify `bash` and `zsh` shell into a POSIX shell. The rational is that
the tool will not use any `zsh` specific capabilities.
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
* Clarify how the shell's handling of quotes affects the interpretation
of TOML values in `--config`/`-c`
* Provide examples of the right way to pass complex TOML values
* The previous explanation incorrectly demonstrated how to pass TOML
values to `--config`/`-c` (misunderstanding how the shell’s handling of
quotes affects things) and would result in invalid invocations of
`codex`.
This PR does multiple things that are necessary for conversation resume
to work from the extension. I wanted to make sure everything worked so
these changes wound up in one PR:
1. Generate more ts types
2. Resume rollout history files rather than create a new one every time
it is resumed so you don't see a duplicate conversation in history for
every resume. Chatted with @aibrahim-oai to verify this
3. Return conversation_id in conversation summaries
4. [Cleanup] Use serde and strong types for a lot of the rollout file
parsing
- In the bottom line of the TUI, print the number of tokens to 3 sigfigs
with an SI suffix, e.g. "1.23K".
- Elsewhere where we print a number, I figure it's worthwhile to print
the exact number, because e.g. it's a summary of your session. Here we print
the numbers comma-separated.
#### Summary
- highlight proposed command previews with the shared bash syntax
highlighter
- keep the Proposed Command section consistent with other execution
renderings
Dependabot tried to automatically upgrade us to `actions/setup-node@v5`
in https://github.com/openai/codex/pull/3293, but it broke our CI. Note
this upgrade has breaking changes:
https://github.com/actions/setup-node/releases/tag/v5.0.0
I think the problem was that `v5` was correctly reading our
`packageManager` line here:
e2b3053b2b/package.json (L24)
and then tried to run `pnpm`, but couldn't because it wasn't available
yet. This PR:
- moves `pnpm/action-setup` before `actions/setup-node`
- drops `version` from our `pnpm/action-setup` step because it is not
necessary when it is specified in `package.json` (which it is in our
case), so leaving it here ran the risk of the two getting out of sync
- upgrades `actions/setup-node` from `v4` to `v5`
- deletes the two custom steps we had to enable Node.js caching since
`v5` claims to do this for us now
- adds `--frozen-lockfile` to our `pnpm install` invocation, which
seemed like something we should have always had there
• I have signed the CLA by commenting the required sentence and
triggered recheck.
• Local checks are all green (fmt / clippy / test).
• Could you please approve the pending GitHub Actions workflows
(first-time contributor), and when convenient, help with one approving
review so I can proceed? Thanks!
## Summary
- Catch and log task panics during server initialization instead of
propagating JoinError
- Handle tool listing failures gracefully, allowing partial server
initialization
- Improve error resilience on macOS where init timeouts are more common
## Test plan
- [x] Test MCP server initialization with timeout scenarios
- [x] Verify graceful handling of tool listing failures
- [x] Confirm improved error messages and logging
- [x] Test on macOS
## Fix issue #3196#2346#2555
### fix before:
<img width="851" height="363" alt="image"
src="https://github.com/user-attachments/assets/e1f9c749-71fd-4873-a04f-d3fc4cbe0ae6"
/>
<img width="775" height="108" alt="image"
src="https://github.com/user-attachments/assets/4e4748bd-9dd6-42b5-b38b-8bfe9341a441"
/>
### fix improved:
<img width="966" height="528" alt="image"
src="https://github.com/user-attachments/assets/418324f3-e37a-4a3c-8bdd-934f9ff21dfb"
/>
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
Bumps [image](https://github.com/image-rs/image) from 0.25.6 to 0.25.8.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/image-rs/image/blob/v0.25.8/CHANGES.md">image's
changelog</a>.</em></p>
<blockquote>
<h3>Version 0.25.8</h3>
<p>Re-release of <code>0.25.7</code></p>
<p>Fixes:</p>
<ul>
<li>Reverted a signature change to <code>load_from_memory</code> that
lead to large scale
type inference breakage despite being technically compatible.</li>
<li>Color conversion Luma to Rgb used incorrect coefficients instead of
broadcasting.</li>
</ul>
<h3>Version 0.25.7 (yanked)</h3>
<p>Features:</p>
<ul>
<li>Added an API for external image format implementations to register
themselves as decoders for a specific format in <code>image</code> (<a
href="https://redirect.github.com/image-rs/image/issues/2372">#2372</a>)</li>
<li>Added <a
href="https://www.color.org/iccmax/download/CICP_tag_and_type_amendment.pdf">CICP</a>
awarenes via <a href="https://crates.io/crates/moxcms">moxcms</a> to
support color spaces (<a
href="https://redirect.github.com/image-rs/image/issues/2531">#2531</a>).
The support for transforming is limited for now and will be gradually
expanded.</li>
<li>You can now embed Exif metadata when writing JPEG, PNG and WebP
images (<a
href="https://redirect.github.com/image-rs/image/issues/2537">#2537</a>,
<a
href="https://redirect.github.com/image-rs/image/issues/2539">#2539</a>)</li>
<li>Added functions to extract orientation from Exif metadata and
optionally clear it in the Exif chunk (<a
href="https://redirect.github.com/image-rs/image/issues/2484">#2484</a>)</li>
<li>Serde support for more types (<a
href="https://redirect.github.com/image-rs/image/issues/2445">#2445</a>)</li>
<li>PNM encoder now supports writing 16-bit images (<a
href="https://redirect.github.com/image-rs/image/issues/2431">#2431</a>)</li>
</ul>
<p>API improvements:</p>
<ul>
<li><code>save</code>, <code>save_with_format</code>,
<code>write_to</code> and <code>write_with_encoder</code> methods on
<code>DynamicImage</code> now automatically convert the pixel format
when necessary instead of returning an error (<a
href="https://redirect.github.com/image-rs/image/issues/2501">#2501</a>)</li>
<li>Added <code>DynamicImage::has_alpha()</code> convenience method</li>
<li>Implemented <code>TryFrom<ExtendedColorType></code> for
<code>ColorType</code> (<a
href="https://redirect.github.com/image-rs/image/issues/2444">#2444</a>)</li>
<li>Added <code>const HAS_ALPHA</code> to trait <code>Pixel</code></li>
<li>Unified the error for unsupported encoder colors (<a
href="https://redirect.github.com/image-rs/image/issues/2543">#2543</a>)</li>
<li>Added a <code>hooks</code> module to customize builtin behavior,
<code>register_format_detection_hook</code> and
<code>register_decoding_hook</code> for the determining format of a file
and selecting an <code>ImageDecoder</code> implementation respectively.
(<a
href="https://redirect.github.com/image-rs/image/issues/2372">#2372</a>)</li>
</ul>
<p>Performance improvements:</p>
<ul>
<li>Gaussian blur (<a
href="https://redirect.github.com/image-rs/image/issues/2496">#2496</a>)
and box blur (<a
href="https://redirect.github.com/image-rs/image/issues/2515">#2515</a>)
are now faster</li>
<li>Improve compilation times by avoiding unnecessary instantiation of
generic functions (<a
href="https://redirect.github.com/image-rs/image/issues/2468">#2468</a>,
<a
href="https://redirect.github.com/image-rs/image/issues/2470">#2470</a>)</li>
</ul>
<p>Bug fixes:</p>
<ul>
<li>Many improvements to image format decoding: TIFF, WebP, AVIF, PNG,
GIF, BMP, TGA</li>
<li>Fixed <code>GifEncoder::encode()</code> ignoring the speed parameter
and always using the slowest speed (<a
href="https://redirect.github.com/image-rs/image/issues/2504">#2504</a>)</li>
<li><code>.pnm</code> is now recognized as a file extension for the PNM
format (<a
href="https://redirect.github.com/image-rs/image/issues/2559">#2559</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="98b001da0d"><code>98b001d</code></a>
Merge pull request <a
href="https://redirect.github.com/image-rs/image/issues/2592">#2592</a>
from image-rs/release-0.25.8</li>
<li><a
href="f86232081c"><code>f862320</code></a>
Metadata and changelog for a 0.25.8</li>
<li><a
href="3b1c1db11d"><code>3b1c1db</code></a>
Merge pull request <a
href="https://redirect.github.com/image-rs/image/issues/2593">#2593</a>
from image-rs/luma-to-rgb-transform-is-broadcast</li>
<li><a
href="1f574d3d1e"><code>1f574d3</code></a>
Replace manual rounding code with f32::round</li>
<li><a
href="545cb3788b"><code>545cb37</code></a>
Color tests in the middle of dynamic range</li>
<li><a
href="9882fa9fe0"><code>9882fa9</code></a>
Remove coefficients from luma_expand</li>
<li><a
href="70b9aa3ef1"><code>70b9aa3</code></a>
Revert "Make load_from_memory generic"</li>
<li><a
href="b94c33379f"><code>b94c333</code></a>
Enable CI for backport branch</li>
<li><a
href="a24556bc87"><code>a24556b</code></a>
Merge pull request <a
href="https://redirect.github.com/image-rs/image/issues/2581">#2581</a>
from image-rs/release-0.25.7</li>
<li><a
href="9175dbc70e"><code>9175dbc</code></a>
Fix readme typo (<a
href="https://redirect.github.com/image-rs/image/issues/2580">#2580</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/image-rs/image/compare/v0.25.6...v0.25.8">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [clap](https://github.com/clap-rs/clap) from 4.5.45 to 4.5.47.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/clap-rs/clap/releases">clap's
releases</a>.</em></p>
<blockquote>
<h2>v4.5.47</h2>
<h2>[4.5.47] - 2025-09-02</h2>
<h3>Features</h3>
<ul>
<li>Added <code>impl FromArgMatches for ()</code></li>
<li>Added <code>impl Args for ()</code></li>
<li>Added <code>impl Subcommand for ()</code></li>
<li>Added <code>impl FromArgMatches for Infallible</code></li>
<li>Added <code>impl Subcommand for Infallible</code></li>
</ul>
<h3>Fixes</h3>
<ul>
<li><em>(derive)</em> Update runtime error text to match
<code>clap</code></li>
</ul>
<h2>v4.5.46</h2>
<h2>[4.5.46] - 2025-08-26</h2>
<h3>Features</h3>
<ul>
<li>Expose <code>StyledStr::push_str</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/clap-rs/clap/blob/master/CHANGELOG.md">clap's
changelog</a>.</em></p>
<blockquote>
<h2>[4.5.47] - 2025-09-02</h2>
<h3>Features</h3>
<ul>
<li>Added <code>impl FromArgMatches for ()</code></li>
<li>Added <code>impl Args for ()</code></li>
<li>Added <code>impl Subcommand for ()</code></li>
<li>Added <code>impl FromArgMatches for Infallible</code></li>
<li>Added <code>impl Subcommand for Infallible</code></li>
</ul>
<h3>Fixes</h3>
<ul>
<li><em>(derive)</em> Update runtime error text to match
<code>clap</code></li>
</ul>
<h2>[4.5.46] - 2025-08-26</h2>
<h3>Features</h3>
<ul>
<li>Expose <code>StyledStr::push_str</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="f046ca6a2b"><code>f046ca6</code></a>
chore: Release</li>
<li><a
href="436949dde1"><code>436949d</code></a>
docs: Update changelog</li>
<li><a
href="1ddab84c32"><code>1ddab84</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/5954">#5954</a>
from epage/tests</li>
<li><a
href="8a66dbf7c2"><code>8a66dbf</code></a>
test(complete): Add more native cases</li>
<li><a
href="76465cf223"><code>76465cf</code></a>
test(complete): Make things more consistent</li>
<li><a
href="232cedbe76"><code>232cedb</code></a>
test(complete): Remove redundant index</li>
<li><a
href="02244a69a3"><code>02244a6</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/5949">#5949</a>
from krobelus/option-name-completions-after-positionals</li>
<li><a
href="2e13847533"><code>2e13847</code></a>
fix(complete): Missing options in multi-val arg</li>
<li><a
href="74388d784b"><code>74388d7</code></a>
test(complete): Multi-valued, unbounded positional</li>
<li><a
href="5b3d45f72c"><code>5b3d45f</code></a>
refactor(complete): Extract function for options</li>
<li>Additional commits viewable in <a
href="https://github.com/clap-rs/clap/compare/clap_complete-v4.5.45...clap_complete-v4.5.47">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Seeing timeouts on certain, slow mcp server starting up when codex is
invoked. Before this change, the timeout was a hard-coded 10s. Need the
ability to define arbitrary timeouts on a per-server basis.
## Summary of changes
- Add startup_timeout_ms to McpServerConfig with 10s default when unset
- Use per-server timeout for initialize and tools/list
- Introduce ManagedClient to store client and timeout; rename
LIST_TOOLS_TIMEOUT to DEFAULT_STARTUP_TIMEOUT
- Update docs to document startup_timeout_ms with example and options
table
---------
Co-authored-by: Matthew Dolan <dolan-openai@users.noreply.github.com>
We're trying to migrate from `session_id: Uuid` to `conversation_id:
ConversationId`. Not only does this give us more type safety but it
unifies our terminology across Codex and with the implementation of
session resuming, a conversation (which can span multiple sessions) is
more appropriate.
I started this impl on https://github.com/openai/codex/pull/3219 as part
of getting resume working in the extension but it's big enough that it
should be broken out.
This updates the ctrl + c behavior to clear the current prompt if there
is text and you press ctrl + c.
I also updated the ctrl + c hint text to show `^c to interrupt` instead
of `^c to quit` if there is an active conversation.
Two things I don't love:
1. You can currently interrupt a conversation with escape or ctrl + c
(not related to this PR and maybe fine)
2. The bottom row hint text always says `^c to quit` but this PR doesn't
really make that worse.
https://github.com/user-attachments/assets/6eddadec-0d84-4fa7-abcb-d6f5a04e5748
Fixes https://github.com/openai/codex/issues/3126
No more picking out version numbers by hand! Now we let the script do
it:
```
$ ./codex-rs/scripts/create_github_release --dry-run --publish-alpha
Running gh api GET /repos/openai/codex/releases/latest
Running gh api GET /repos/openai/codex/releases?per_page=100
Publishing version 0.31.0-alpha.3
$ ./codex-rs/scripts/create_github_release --dry-run --publish-release
Running gh api GET /repos/openai/codex/releases/latest
Publishing version 0.31.0
```
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/3230).
* __->__ #3231
* #3230
* #3228
* #3226
What
- Show compact elapsed time in the TUI status indicator: Xs, MmSSs,
HhMMmSSs.
- Add private helper fmt_elapsed_compact with a unit test.
Why
- Seconds‑only becomes hard to read during longer runs; minutes/hours
improve clarity without extra noise.
How
- Implemented in codex-rs/tui/src/status_indicator_widget.rs only.
- The helper is used when rendering the existing “Working/Thinking”
timer.
- No changes to codex-common::elapsed::format_duration or other crates.
Scope/Impact
- TUI‑only; no public API changes; minimal risk.
- Snapshot tests should remain unchanged (most show “0s”).
Before/After
- Working (65s • Esc to interrupt) → Working (1m05s • Esc to interrupt)
- Working (3723s • …) → Working (1h02m03s • …)
Tests
- Unit: fmt_elapsed_compact_formats_seconds_minutes_hours.
- Local checks: cargo fmt --all, cargo clippy -p codex-tui -- -D
warnings, cargo test -p codex-tui.
Notes
- Open to adjusting the exact format or moving the helper if maintainers
prefer a shared location.
Signed-off-by: Enrique Moreno Tent <enriquemorenotent@gmail.com>
This PR addresses an issue that several users have reported. If the
local oauth login server in one codex instance is left running (e.g. the
user abandons the oauth flow), a subsequent codex instance will receive
an error when attempting to log in because the localhost port is already
in use by the dangling web server from the first instance.
This PR adds a cancelation mechanism that the second instance can use to
abort the first login attempt and free up the port.
When item ids are sent to Responses API it will load them from the
database ignoring the provided values. This adds extra latency.
Not having the mode to store requests also allows us to simplify the
code.
## Breaking change
The `disable_response_storage` configuration option is removed.
i'm not yet convinced i have the best heuristics for what to highlight,
but this feels like a useful step towards something a bit easier to
read, esp. when the model is producing large commands.
<img width="669" height="589" alt="Screenshot 2025-09-03 at 8 21 56 PM"
src="https://github.com/user-attachments/assets/b9cbcc43-80e8-4d41-93c8-daa74b84b331"
/>
also a fairly significant refactor of our line wrapping logic.
TuiEvent is supposed to be purely events that come from the "driver",
i.e. events from the terminal. Everything app-specific should be an
AppEvent. In this case, it didn't need to be an event at all.
This PR introduces introduces a new
`OutgoingMessage::AppServerNotification` variant that is designed to
wrap a `ServerNotification`, which makes the serialization more
straightforward compared to
`OutgoingMessage::Notification(OutgoingNotification)`. We still use the
latter for serializing an `Event` as a `JSONRPCMessage::Notification`,
but I will try to get away from that in the near future.
With this change, now the generated TypeScript type for
`ServerNotification` is:
```typescript
export type ServerNotification =
| { "method": "authStatusChange", "params": AuthStatusChangeNotification }
| { "method": "loginChatGptComplete", "params": LoginChatGptCompleteNotification };
```
whereas before it was:
```typescript
export type ServerNotification =
| { type: "auth_status_change"; data: AuthStatusChangeNotification }
| { type: "login_chat_gpt_complete"; data: LoginChatGptCompleteNotification };
```
Once the `Event`s are migrated to the `ServerNotification` enum in Rust,
it should be considerably easier to work with notifications on the
TypeScript side, as it will be possible to `switch (message.method)` and
check for exhaustiveness.
Though we will probably need to introduce:
```typescript
export type ServerMessage = ServerRequest | ServerNotification;
```
and then we still need to group all of the `ServerResponse` types
together, as well.
#### Summary
- Emit a “Proposed Command” history cell when an ExecApprovalRequest
arrives (parity with proposed patches).
- Simplify the approval dialog: show only the reason/instructions; move
the command preview into history.
- Make approval/abort decision history concise:
- Single line snippet; if multiline, show first line + " ...".
- Truncate to 80 graphemes with ellipsis for very long commands.
#### Details
- History
- Add `new_proposed_command` to render a header and indented command
preview.
- Use shared `prefix_lines` helper for first/subsequent line prefixes.
- Approval UI
- `UserApprovalWidget` no longer renders the command in the modal; shows
optional `reason` text only.
- Decision history renders an inline, dimmed snippet per rules above.
- Tests (snapshot-based)
- Proposed/decision flow for short command.
- Proposed multi-line + aborted decision snippet with “ ...”.
- Very long one-line command -> truncated snippet with “…”.
- Updated existing exec approval snapshots and test reasons.
<img width="1053" height="704" alt="Screenshot 2025-09-03 at 11 57
35 AM"
src="https://github.com/user-attachments/assets/9ed4c316-9daf-4ac1-80ff-7ae1f481dd10"
/>
after approving:
<img width="1053" height="704" alt="Screenshot 2025-09-03 at 11 58
18 AM"
src="https://github.com/user-attachments/assets/a44e243f-eb9d-42ea-87f4-171b3fb481e7"
/>
rejection:
<img width="1053" height="207" alt="Screenshot 2025-09-03 at 11 58
45 AM"
src="https://github.com/user-attachments/assets/a022664b-ae0e-4b70-a388-509208707934"
/>
big command:
https://github.com/user-attachments/assets/2dd976e5-799f-4af7-9682-a046e66cc494
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
We had multiple issues with context size calculation:
1. `initial_prompt_tokens` calculation based on cache size is not
reliable, cache misses might set it to much higher value. For now
hardcoded to a safer constant.
2. Input context size for GPT-5 is 272k (that's where 33% came from).
Fixes.
Bumps [uuid](https://github.com/uuid-rs/uuid) from 1.17.0 to 1.18.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/uuid-rs/uuid/releases">uuid's
releases</a>.</em></p>
<blockquote>
<h2>v1.18.0</h2>
<h2>What's Changed</h2>
<ul>
<li>Fix up mismatched_lifetime_syntaxes lint by <a
href="https://github.com/KodrAus"><code>@KodrAus</code></a> in <a
href="https://redirect.github.com/uuid-rs/uuid/pull/837">uuid-rs/uuid#837</a></li>
<li>Conversions between <code>Timestamp</code> and
<code>std::time::SystemTime</code> by <a
href="https://github.com/dcormier"><code>@dcormier</code></a> in <a
href="https://redirect.github.com/uuid-rs/uuid/pull/835">uuid-rs/uuid#835</a></li>
<li>Wrap the error type used in time conversions by <a
href="https://github.com/KodrAus"><code>@KodrAus</code></a> in <a
href="https://redirect.github.com/uuid-rs/uuid/pull/838">uuid-rs/uuid#838</a></li>
<li>Prepare for 1.18.0 release by <a
href="https://github.com/KodrAus"><code>@KodrAus</code></a> in <a
href="https://redirect.github.com/uuid-rs/uuid/pull/839">uuid-rs/uuid#839</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a href="https://github.com/dcormier"><code>@dcormier</code></a>
made their first contribution in <a
href="https://redirect.github.com/uuid-rs/uuid/pull/835">uuid-rs/uuid#835</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/uuid-rs/uuid/compare/v1.17.0...v1.18.0">https://github.com/uuid-rs/uuid/compare/v1.17.0...v1.18.0</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="60a49eb94f"><code>60a49eb</code></a>
Merge pull request <a
href="https://redirect.github.com/uuid-rs/uuid/issues/839">#839</a> from
uuid-rs/cargo/v1.18.0</li>
<li><a
href="eb8c697083"><code>eb8c697</code></a>
prepare for 1.18.0 release</li>
<li><a
href="281f26fcd9"><code>281f26f</code></a>
Merge pull request <a
href="https://redirect.github.com/uuid-rs/uuid/issues/838">#838</a> from
uuid-rs/chore/time-conversion</li>
<li><a
href="2d67ab2b5e"><code>2d67ab2</code></a>
don't use allocated values in errors</li>
<li><a
href="c284ed562f"><code>c284ed5</code></a>
wrap the error type used in time conversions</li>
<li><a
href="87a4359f25"><code>87a4359</code></a>
Merge pull request <a
href="https://redirect.github.com/uuid-rs/uuid/issues/835">#835</a> from
dcormier/main</li>
<li><a
href="8927396625"><code>8927396</code></a>
Merge pull request <a
href="https://redirect.github.com/uuid-rs/uuid/issues/837">#837</a> from
uuid-rs/fix/lifetime-syntaxes</li>
<li><a
href="6dfb4b135c"><code>6dfb4b1</code></a>
Conversions between <code>Timestamp</code> and
<code>std::time::SystemTime</code></li>
<li><a
href="b508383aff"><code>b508383</code></a>
fix up mismatched_lifetime_syntaxes lint</li>
<li>See full diff in <a
href="https://github.com/uuid-rs/uuid/compare/v1.17.0...v1.18.0">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
## Summary
Follow-up to #3056
This PR updates the mcp-server interface for reading the config settings
saved by the user. At risk of introducing _another_ Config struct, I
think it makes sense to avoid tying our protocol to ConfigToml, as its
become a bit unwieldy. GetConfigTomlResponse was a de-facto struct for
this already - better to make it explicit, in my opinion.
This is technically a breaking change of the mcp-server protocol, but
given the previous interface was introduced so recently in #2725, and we
have not yet even started to call it, I propose proceeding with the
breaking change - but am open to preserving the old endpoint.
## Testing
- [x] Added additional integration test coverage
Clarifies codex-rs testing approvals in AGENTS.md:
- Allow running project-specific or individual tests without asking.
- Require asking before running the complete test suite.
- Keep `just fmt` always allowed without approval.
Summary:
- pause the status timer while waiting on approval modals
- expose deterministic pause/resume helpers to avoid sleep-based tests
- simplify bottom pane timer handling now that the widget owns the clock
when the pager is scrolled to the bottom of the buffer, keep it there.
this should make transcript mode feel a bit more "alive". i've also seen
some confusion about what transcript mode does/doesn't show that i think
has been related to it not pinning scroll.
#### Summary
- render the edit queued message shortcut with the ⌥ modifier on macOS
builds
- add a helper for status indicator snapshot suffixes
- record macOS-specific snapshots for the status indicator widget
`rust-lang.rust-analyzer` is clearly something all contributors should
install.
`vadimcn.vscode-lldb` is maybe debatable, but I think this is often
better that print-debugging.
#### Summary
Avoid a potential panic when rendering the active execution cell when
the allocated area has zero height.
#### Changes
- Guard rendering with `active_cell_area.height > 0` and presence of
`active_exec_cell`.
- Use `saturating_add(1)` for the Y offset to avoid overflow.
- Render via `active_exec_cell.as_ref().unwrap().render_ref(...)` after
the explicit `is_some` check.
When serializing to JSON, the existing solution created an enormous
array of ints, which is far more bytes on the wire than a base64-encoded
string would be.
Last week, I thought I found the smoking gun in our flaky integration
tests where holding these locks could have led to potential deadlock:
- https://github.com/openai/codex/pull/2876
- https://github.com/openai/codex/pull/2878
Yet even after those PRs went in, we continued to see flakinees in our
integration tests! Though with the additional logging added as part of
debugging those tests, I now saw things like:
```
read message from stdout: Notification(JSONRPCNotification { jsonrpc: "2.0", method: "codex/event/exec_approval_request", params: Some(Object {"id": String("0"), "msg": Object {"type": String("exec_approval_request"), "call_id": String("call1"), "command": Array [String("python3"), String("-c"), String("print(42)")], "cwd": String("/tmp/.tmpFj2zwi/workdir")}, "conversationId": String("c67b32c5-9475-41bf-8680-f4b4834ebcc6")}) })
notification: Notification(JSONRPCNotification { jsonrpc: "2.0", method: "codex/event/exec_approval_request", params: Some(Object {"id": String("0"), "msg": Object {"type": String("exec_approval_request"), "call_id": String("call1"), "command": Array [String("python3"), String("-c"), String("print(42)")], "cwd": String("/tmp/.tmpFj2zwi/workdir")}, "conversationId": String("c67b32c5-9475-41bf-8680-f4b4834ebcc6")}) })
read message from stdout: Request(JSONRPCRequest { id: Integer(0), jsonrpc: "2.0", method: "execCommandApproval", params: Some(Object {"conversation_id": String("c67b32c5-9475-41bf-8680-f4b4834ebcc6"), "call_id": String("call1"), "command": Array [String("python3"), String("-c"), String("print(42)")], "cwd": String("/tmp/.tmpFj2zwi/workdir")}) })
writing message to stdin: Response(JSONRPCResponse { id: Integer(0), jsonrpc: "2.0", result: Object {"decision": String("approved")} })
in read_stream_until_notification_message(codex/event/task_complete)
[mcp stderr] 2025-09-04T00:00:59.738585Z INFO codex_mcp_server::message_processor: <- response: JSONRPCResponse { id: Integer(0), jsonrpc: "2.0", result: Object {"decision": String("approved")} }
[mcp stderr] 2025-09-04T00:00:59.738740Z DEBUG codex_core::codex: Submission sub=Submission { id: "1", op: ExecApproval { id: "0", decision: Approved } }
[mcp stderr] 2025-09-04T00:00:59.738832Z WARN codex_core::codex: No pending approval found for sub_id: 0
```
That is, a response was sent for a request, but no callback was in place
to handle the response!
This time, I think I may have found the underlying issue (though the
fixes for holding locks for too long may have also been part of it),
which is I found cases where we were sending the request:
234c0a0469/codex-rs/core/src/codex.rs (L597)
before inserting the `Sender` into the `pending_approvals` map (which
has to wait on acquiring a mutex):
234c0a0469/codex-rs/core/src/codex.rs (L598-L601)
so it is possible the request could go out and the client could respond
before `pending_approvals` was updated!
Note this was happening in both `request_command_approval()` and
`request_patch_approval()`, which maps to the sorts of errors we have
been seeing when these integration tests have been flaking on us.
While here, I am also adding some extra logging that prints if inserting
into `pending_approvals` overwrites an entry as opposed to purely
inserting one. Today, a conversation can have only one pending request
at a time, but as we are planning to support parallel tool calls, this
invariant may not continue to hold, in which case we need to revisit
this abstraction.
Adds a TUI resume flow with an interactive picker and quick resume.
- CLI:
- --resume / -r: open picker to resume a prior session
- --continue / -l: resume the most recent session (no picker)
- Behavior on resume: initial history is replayed, welcome banner
hidden, and the first redraw is suppressed to avoid flicker.
- Implementation:
- New tui/src/resume_picker.rs (paginated listing via
RolloutRecorder::list_conversations)
- App::run accepts ResumeSelection; resumes from disk when requested
- ChatWidget refactor with ChatWidgetInit and new_from_existing; replays
initial messages
- Tests: cover picker sorting/preview extraction and resumed-history
rendering.
- Docs: getting-started updated with flags and picker usage.
https://github.com/user-attachments/assets/1bb6469b-e5d1-42f6-bec6-b1ae6debda3b
Bumps [wiremock](https://github.com/LukeMathWalker/wiremock-rs) from
0.6.4 to 0.6.5.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="6b193047bf"><code>6b19304</code></a>
chore: Release wiremock version 0.6.5</li>
<li><a
href="ebaa70b024"><code>ebaa70b</code></a>
feat: Make method and MethodExactMatcher case in-sensitive (<a
href="https://redirect.github.com/LukeMathWalker/wiremock-rs/issues/165">#165</a>)</li>
<li><a
href="613b4f9135"><code>613b4f9</code></a>
Make <code>BodyPrintLimit</code> public (<a
href="https://redirect.github.com/LukeMathWalker/wiremock-rs/issues/167">#167</a>)</li>
<li><a
href="abfafd2227"><code>abfafd2</code></a>
chore: Upgrade all deps to their latest version (<a
href="https://redirect.github.com/LukeMathWalker/wiremock-rs/issues/170">#170</a>)</li>
<li><a
href="60688cfdde"><code>60688cf</code></a>
ci: Upgrade actions. Upgrade dependencies. (<a
href="https://redirect.github.com/LukeMathWalker/wiremock-rs/issues/169">#169</a>)</li>
<li>See full diff in <a
href="https://github.com/LukeMathWalker/wiremock-rs/compare/v0.6.4...v0.6.5">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
This PR does the following:
- divides user msgs into 3 categories: plain, user instructions, and
environment context
- Centralizes adding user instructions and environment context to a
degree
- Improve the integration testing
Building on top of #3123
Specifically this
[comment](https://github.com/openai/codex/pull/3123#discussion_r2319885089).
We need to send the user message while ignoring the User Instructions
and Environment Context we attach.
### Overview
This PR introduces the following changes:
1. Adds a unified mechanism to convert ResponseItem into EventMsg.
2. Ensures that when a session is initialized with initial history, a
vector of EventMsg is sent along with the session configuration. This
allows clients to re-render the UI accordingly.
3. Added integration testing
### Caveats
This implementation does not send every EventMsg that was previously
dispatched to clients. The excluded events fall into two categories:
• “Arguably” rolled-out events
Examples include tool calls and apply-patch calls. While these events
are conceptually rolled out, we currently only roll out ResponseItems.
These events are already being handled elsewhere and transformed into
EventMsg before being sent.
• Non-rolled-out events
Certain events such as TurnDiff, Error, and TokenCount are not rolled
out at all.
### Future Directions
At present, resuming a session involves maintaining two states:
• UI State
Clients can replay most of the important UI from the provided EventMsg
history.
• Model State
The model receives the complete session history to reconstruct its
internal state.
This design provides a solid foundation. If, in the future, more precise
UI reconstruction is needed, we have two potential paths:
1. Introduce a third data structure that allows us to derive both
ResponseItems and EventMsgs.
2. Clearly divide responsibilities: the core system ensures the
integrity of the model state, while clients are responsible for
reconstructing the UI.
In this test, the ChatGPT token path is used, and the auth layer tries
to refresh the token if it thinks the token is “old.” Your helper writes
a fixed last_refresh timestamp that has now aged past the 28‑day
threshold, so the code attempts a real refresh against auth.openai.com,
never reaches the mock, and you end up with
received_requests().await.unwrap() being empty.
## Summary
It appears that #2108 hit a merge conflict with #2355 - I failed to
notice the path difference when re-reviewing the former. This PR
rectifies that, and consolidates it into the protocol package, in line
with our philosophy of specifying types in one place.
## Testing
- [x] Adds config test for model_verbosity
**What?**
Auto-approve patches when `SandboxPolicy::DangerFullAccess` is enabled
on platforms without sandbox support.
Changes in `codex-rs/core/src/safety.rs`: return
`SafetyCheck::AutoApprove { sandbox_type: SandboxType::None }` when no
sandbox is available and DangerFullAccess is set.
**Why?**
On platforms lacking sandbox support, requiring explicit user approval
despite `DangerFullAccess` being explicitly enabled adds friction
without additional safety. This aligns behavior with the stated policy
intent.
**How?**
Extend `assess_patch_safety` match:
* If `get_platform_sandbox()` returns `Some`, keep `AutoApprove {
sandbox_type }`.
* If `None` **and** `SandboxPolicy::DangerFullAccess`, return
`AutoApprove { SandboxType::None }`.
* Otherwise, fall back to `AskUser`.
**Tests**
* Local checks:
```bash
cargo test && cargo clippy --tests && cargo fmt -- --config
imports_granularity=Item
```
(Additionally: `just fmt`, `just fix -p codex-core`, `cargo check -p
codex-core`.)
**Docs**
No user-facing CLI changes. No README/help updates needed.
**Risk/Impact**
Reduces prompts on non-sandboxed platforms when DangerFullAccess is
explicitly chosen; consistent with policy semantics.
---------
Co-authored-by: Michael Bolin <bolinfest@gmail.com>
# Improve @ file search: include specific hidden dirs
This should close#2980
## What
- Extend `@` fuzzy file search to include select top-level hidden
directories:
`.github`, `.gitlab`, `.circleci`, `.devcontainer`, `.azuredevops`,
`.vscode`, `.cursor`.
- Keep all other hidden directories excluded to avoid noise and heavy
traversals.
## Why
- Common project config lives under these dot-dirs (CI, editor,
devcontainer); users expect `@.github/...` and similar paths to resolve.
- Prior behavior hid all dot-dirs, making these files undiscoverable.
## How
- In `codex-file-search` walker:
- Enable hidden entries via `WalkBuilder.hidden(false)`.
- Add `filter_entry` to only allow those specific root dot-directories;
other hidden paths remain filtered out.
- Preserve `.gitignore` semantics and existing exclude handling.
## Local checks
- Ran formatting: `just fmt`
- Ran lint (scoped): `just fix -p codex-file-search`
- Ran tests:
- `cargo test -p codex-file-search`
- `cargo test -p codex-tui`
## Readiness
- Branch is up-to-date locally; tests pass; lint/format applied.
- No merge conflicts expected.
- Marking Ready for review.
---------
Signed-off-by: lionelchg <lionel.cheng@hotmail.fr>
Correct the `shell` tool description for sandboxed runs and add targeted
tests.
- Fix the WorkspaceWrite description to clearly state that writes
outside the writable roots require escalated permissions; reads are not
restricted. The previous wording/formatting could be read as restricting
reads outside the workspace.
- Render the writable roots list on its own lines under a newline after
"writable roots:" for clarity.
- Show the "Commands that require network access" note only in
WorkspaceWrite when network is disabled.
- Add focused tests that call `create_shell_tool_for_sandbox` directly
and assert the exact description text for WorkspaceWrite, ReadOnly, and
DangerFullAccess.
- Update AGENTS.md to note that `just fmt` can be run automatically
without asking.
- Move rollout persistence and listing into a dedicated module:
rollout/{recorder,list}.
- Expose lightweight conversation listing that returns file paths plus
the first 5 JSONL records for preview.
Bumps [thiserror](https://github.com/dtolnay/thiserror) from 2.0.12 to
2.0.16.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/dtolnay/thiserror/releases">thiserror's
releases</a>.</em></p>
<blockquote>
<h2>2.0.16</h2>
<ul>
<li>Add to "no-std" crates.io category (<a
href="https://redirect.github.com/dtolnay/thiserror/issues/429">#429</a>)</li>
</ul>
<h2>2.0.15</h2>
<ul>
<li>Prevent <code>Error::provide</code> API becoming unavailable from a
future new compiler lint (<a
href="https://redirect.github.com/dtolnay/thiserror/issues/427">#427</a>)</li>
</ul>
<h2>2.0.14</h2>
<ul>
<li>Allow build-script cleanup failure with NFSv3 output directory to be
non-fatal (<a
href="https://redirect.github.com/dtolnay/thiserror/issues/426">#426</a>)</li>
</ul>
<h2>2.0.13</h2>
<ul>
<li>Documentation improvements</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="40b58536cc"><code>40b5853</code></a>
Release 2.0.16</li>
<li><a
href="83dfb5f99b"><code>83dfb5f</code></a>
Merge pull request <a
href="https://redirect.github.com/dtolnay/thiserror/issues/429">#429</a>
from dtolnay/nostd</li>
<li><a
href="9b4a99fb90"><code>9b4a99f</code></a>
Add to "no-std" crates.io category</li>
<li><a
href="f6145ebe84"><code>f6145eb</code></a>
Release 2.0.15</li>
<li><a
href="2717177976"><code>2717177</code></a>
Merge pull request <a
href="https://redirect.github.com/dtolnay/thiserror/issues/427">#427</a>
from dtolnay/caplints</li>
<li><a
href="2cd13e6767"><code>2cd13e6</code></a>
Make error_generic_member_access compatible with -Dwarnings</li>
<li><a
href="eea6799e2d"><code>eea6799</code></a>
Release 2.0.14</li>
<li><a
href="a2aa6d7a57"><code>a2aa6d7</code></a>
Merge pull request <a
href="https://redirect.github.com/dtolnay/thiserror/issues/426">#426</a>
from dtolnay/enotempty</li>
<li><a
href="f00ebc57be"><code>f00ebc5</code></a>
Allow build-script cleanup failure with NFSv3 output directory to be
non-fatal</li>
<li><a
href="61f28da3df"><code>61f28da</code></a>
Release 2.0.13</li>
<li>Additional commits viewable in <a
href="https://github.com/dtolnay/thiserror/compare/2.0.12...2.0.16">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
## Summary
This PR implements advisory file locking for the message history using
Rust 1.89+ stabilized std::fs::File locking APIs, eliminating the need
for external dependencies.
## Key Changes
- **Stable API Usage**: Uses std::fs::File::try_lock() and
try_lock_shared() APIs stabilized in Rust 1.89
- **Cross-Platform Compatibility**:
- Unix systems use try_lock_shared() for advisory read locks
- Windows systems use try_lock() due to different lock semantics
- **Retry Logic**: Maintains existing retry behavior for concurrent
access scenarios
- **No External Dependencies**: Removes need for external file locking
crates
## Technical Details
The implementation provides advisory file locking to prevent corruption
when multiple Codex processes attempt to write to the message history
file simultaneously. The locking is platform-aware to handle differences
in Windows vs Unix file locking behavior.
## Testing
- ✅ Builds successfully on all platforms
- ✅ Existing message history tests pass
- ✅ File locking retry logic verified
Related to discussion in #2773 about using stabilized Rust APIs instead
of external dependencies.
---------
Co-authored-by: Michael Bolin <bolinfest@gmail.com>
## Summary
This PR enables Codex to build and run on Android/Termux environments by
conditionally gating the arboard clipboard dependency for Android
targets.
## Key Changes
- **Android Compatibility**: Gate arboard dependency for Android targets
where clipboard access may be restricted
- **Build Fixes**: Add missing tempfile::Builder import for image
clipboard operations
- **Code Cleanup**: Remove unnecessary parentheses to resolve formatting
warnings
## Technical Details
### Clipboard Dependency Gating
- Uses conditional compilation to exclude arboard on Android targets
- Maintains full clipboard functionality on other platforms
- Prevents build failures on Android/Termux where system clipboard
access is limited
### Import Fixes
- Adds missing tempfile::Builder import that was causing compilation
errors
- Ensures image clipboard operations work correctly when clipboard is
available
## Platform Support
- ✅ **Linux/macOS/Windows**: Full clipboard functionality maintained
- ✅ **Android/Termux**: Builds successfully without clipboard dependency
- ✅ **Other Unix platforms**: Unchanged behavior
## Testing
- ✅ Builds successfully on Android/Termux
- ✅ Maintains clipboard functionality on supported platforms
- ✅ No regression in existing functionality
This addresses the Android/Termux compatibility issues while keeping
clipboard functionality intact for platforms that support it.
- Summary:
- Updated the hardcoded hyperlink shown when no MCP servers are
configured to point at the canonical docs section:
- From: codex-rs/config.md#mcp_servers (moved/obsolete)
- To: docs/config.md#mcp_servers (correct GitHub path)
- Rationale:
- The TUI link was pointing to a file that only redirects; this makes
the link accurate and reduces user confusion.
- Validation:
- Verified that the target anchor exists at:
https://github.com/openai/codex/blob/main/docs/config.md#mcp_servers
- UI behavior unchanged otherwise (rendering of link text remains “MCP
docs”).
- Impact:
- One-line change in TUI display logic; no functional behavior change.
Co-authored-by: Michael Bolin <mbolin@openai.com>
The gpt-oss models require reasoning with subsequent Chat Completions
requests because otherwise the model forgets why the tools were called.
This change fixes that and also adds some additional missing
documentation around how to handle context windows in Ollama and how to
show the CoT if you desire to.
## Summary
Fixes an issue with the lark grammar definition for the apply_patch
freeform tool. This does NOT change the defaults, merely patches the
root cause of the issue we were seeing with empty lines, and an issue
with config flowing through correctly.
Specifically, the following requires that a line is non-empty:
```
add_line: "+" /(.+)/ LF -> line
```
but many changes _should_ involve creating/updating empty lines. The new
definition is:
```
add_line: "+" /(.*)/ LF -> line
```
## Testing
- [x] Tested locally, reproduced the issue without the update and
confirmed that the model will produce empty lines wiht the new lark
grammar
## Summary
- allow selection popups to specify their empty state message
- show a "loading..." placeholder in the file search popup while matches
are pending
- update other popup call sites to continue using a "no matches" message
## Testing
- just fmt
- just fix -p codex-tui
- cargo test -p codex-tui
------
https://chatgpt.com/codex/tasks/task_i_68b73e956e90832caf4d04a75fcc9c46
We have two ways of loading conversation with a previous history. Fork
conversation and the experimental resume that we had before. In this PR,
I am unifying their code path. The path is getting the history items and
recording them in a brand new conversation. This PR also constraint the
rollout recorder responsibilities to be only recording to the disk and
loading from the disk.
The PR also fixes a current bug when we have two forking in a row:
History 1:
<Environment Context>
UserMessage_1
UserMessage_2
UserMessage_3
**Fork with n = 1 (only remove one element)**
History 2:
<Environment Context>
UserMessage_1
UserMessage_2
<Environment Context>
**Fork with n = 1 (only remove one element)**
History 2:
<Environment Context>
UserMessage_1
UserMessage_2
**<Environment Context>**
This shouldn't happen but because we were appending the `<Environment
Context>` after each spawning and it's considered as _user message_.
Now, we don't add this message if restoring and old conversation.
https://github.com/openai/codex/pull/3062 added `windows-11-arm` to the
list of images used for building, but the job to build an alpha just
failed:
https://github.com/openai/codex/actions/runs/17415565601
with this error:
```
Creating archive: codex-aarch64-pc-windows-msvc.exe.zip
Add new data to archive: 1 file, 20484096 bytes (20 MiB)
Files read from disk: 1
Archive size: 7869619 bytes (7686 KiB)
Everything is Ok
C:\a\_temp\0e71926f-4d8a-42ae-a337-a9627acc9c57.sh: line 34: zstd: command not found
```
so allegedly this should fix it? I'm surprised this was not necessary
for the `windows-latest` image, though.
Fixes excessive blank lines appearing during agent message streaming.
- Only insert a separator blank line for new, non-streaming history
cells.
- Streaming continuations now append without adding a spacer,
eliminating extra gaps between chunks.
Affected area: TUI display of agent messages (tui/src/app.rs).
3 quick fixes to docs/config.md
- Fix the reference table so option lists render correctly
- Corrected the default `stream_max_retries` to 5 (Old: 10)
- Update example approval_policy to untrusted (Old: unless-allow-listed)
This is in support of https://github.com/openai/codex/issues/2979.
Once we have a release out, we can update the npm module and the VS Code
extension to take advantage of this.
Hide the “/init” suggestion in the new-session banner when an
`AGENTS.md` exists anywhere from the repo root down to the current
working directory.
Changes
- Conditional suggestion: use `discover_project_doc_paths(config)` to
suppress `/init` when agents docs are present.
- TUI style cleanup: switch banner construction to `Stylize` helpers
(`.bold()`, `.dim()`, `.into()`), avoiding `Span::styled`/`Span::raw`.
- Fixture update: remove `/init` line in
`tui/tests/fixtures/ideal-binary-response.txt` to match the new banner.
Validation
- Ran formatting and scoped lint fixes: `just fmt` and `just fix -p
codex-tui`.
- Tests: `cargo test -p codex-tui` passed (`176 passed, 0 failed`).
Notes
- No change to the `/init` command itself; only the welcome banner now
adapts based on presence of `AGENTS.md`.
we were checking every typed character to see if it was an image. this
involved going to disk, which was slow.
this was a bad interaction between image paste support and burst-paste
detection.
This PR fixes the link of contributing page in Pull Request template to
the right one following the migration of the section to a dedicated
file.
Signed-off-by: lionelchg <lionel.cheng@hotmail.fr>
## Summary
Pressing Enter with an empty composer was treated as a submission, which
queued a blank message while a task was running. This PR suppresses
submission when there is no text and no attachments.
## Root Cause
- ChatComposer returned Submitted even when the trimmed text was empty.
ChatWidget then queued it during a running task, leading to an empty
item appearing in the queued list and being popped later with no effect.
## Changes
- ChatComposer Enter handling: if trimmed text is empty and there are no
attached images, return None instead of Submitted.
- No changes to ChatWidget; behavior naturally stops queuing blanks at
the source.
## Code Paths
- Modified: `tui/src/bottom_pane/chat_composer.rs`
- Tests added:
- `tui/src/bottom_pane/chat_composer.rs`: `empty_enter_returns_none`
- `tui/src/chatwidget/tests.rs`:
`empty_enter_during_task_does_not_queue`
## Result
### Before
https://github.com/user-attachments/assets/a40e2f6d-42ba-4a82-928b-8f5458f5884d
### After
https://github.com/user-attachments/assets/958900b7-a566-44fc-b16c-b80380739c92
#2747 encouraged me to audit our codebase for similar issues, as now I
am particularly suspicious that our flaky tests are due to a racy
deadlock.
I asked Codex to audit our code, and one of its suggestions was this:
> **High-Risk Patterns**
>
> All `send_*` methods await on a bounded
`mpsc::Sender<OutgoingMessage>`. If the writer blocks, the channel fills
and the processor task blocks on send, stops draining incoming requests,
and stdin reader eventually blocks on its send. This creates a
backpressure deadlock cycle across the three tasks.
>
> **Recommendations**
> * Server outgoing path: break the backpressure cycle
> * Option A (minimal risk): Change `OutgoingMessageSender` to use an
unbounded channel to decouple producer from stdout. Add rate logging so
floods are visible.
> * Option B (bounded + drop policy): Change `send_*` to try_send and
drop messages (or coalesce) when the queue is full, logging a warning.
This prevents processor stalls at the cost of losing messages under
extreme backpressure.
> * Option C (two-stage buffer): Keep bounded channel, but have a
dedicated “egress” task that drains an unbounded internal queue, writing
to stdout with retries and a shutdown timeout. This centralizes
backpressure policy.
So this PR is Option A.
Indeed, we previously used a bounded channel with a capacity of `128`,
but as we discovered recently with #2776, there are certainly cases
where we can get flooded with events.
That said, `test_shell_command_approval_triggers_elicitation` just
failed one one build when I put up this PR, so clearly we are not out of
the woods yet...
**Update:** I think I found the true source of the deadlock! See
https://github.com/openai/codex/pull/2876
Today we had a breakage in the release build that went unnoticed by CI.
Here is what happened:
- https://github.com/openai/codex/pull/2242 originally added some logic
to do release builds to prevent this from happening
- https://github.com/openai/codex/pull/2276 undid that change to try to
speed things up by removing the step to build all the individual crates
in release mode, assuming the `cargo check` call was sufficient
coverage, which it would have been, had it specified `--profile`
This PR adds `--profile` to the `cargo check` step so we should get the
desired coverage from our build matrix.
Indeed, enabling this in our CI uncovered a warning that is only present
in release mode that was going unnoticed.
The default install command causes unexpected code to be executed:
```
npm install -g @openai/codex # Alternatively: `brew install codex`
```
The problem is some environment will treat # as literal string, not
start of comment. Therefore the user will execute this instead (because
it's in backtick)
```
brew install codex
```
And then the npm command will error (because it's trying to install
package #)
POC code
```rust
use tokio::sync::mpsc;
use std::time::Duration;
#[tokio::main]
async fn main() {
println!("=== Test 1: Simulating original MCP server pattern ===");
test_original_pattern().await;
}
async fn test_original_pattern() {
println!("Testing the original pattern from MCP server...");
// Create channel - this simulates the original incoming_tx/incoming_rx
let (tx, mut rx) = mpsc::channel::<String>(10);
// Task 1: Simulates stdin reader that will naturally terminate
let stdin_task = tokio::spawn({
let tx_clone = tx.clone();
async move {
println!(" stdin_task: Started, will send 3 messages then exit");
for i in 0..3 {
let msg = format!("Message {}", i);
if tx_clone.send(msg.clone()).await.is_err() {
println!(" stdin_task: Receiver dropped, exiting");
break;
}
println!(" stdin_task: Sent {}", msg);
tokio::time::sleep(Duration::from_millis(300)).await;
}
println!(" stdin_task: Finished (simulating EOF)");
// tx_clone is dropped here
}
});
// Task 2: Simulates message processor
let processor_task = tokio::spawn(async move {
println!(" processor_task: Started, waiting for messages");
while let Some(msg) = rx.recv().await {
println!(" processor_task: Processing {}", msg);
tokio::time::sleep(Duration::from_millis(100)).await;
}
println!(" processor_task: Finished (channel closed)");
});
// Task 3: Simulates stdout writer or other background task
let background_task = tokio::spawn(async move {
for i in 0..2 {
tokio::time::sleep(Duration::from_millis(500)).await;
println!(" background_task: Tick {}", i);
}
println!(" background_task: Finished");
});
println!(" main: Original tx is still alive here");
println!(" main: About to call tokio::join! - will this deadlock?");
// This is the pattern from the original code
let _ = tokio::join!(stdin_task, processor_task, background_task);
}
```
---------
Co-authored-by: Michael Bolin <bolinfest@gmail.com>
- Introduce websearch end to complement the begin
- Moves the logic of adding the sebsearch tool to
create_tools_json_for_responses_api
- Making it the client responsibility to toggle the tool on or off
- Other misc in #2371 post commit feedback
- Show the query:
<img width="1392" height="151" alt="image"
src="https://github.com/user-attachments/assets/8457f1a6-f851-44cf-bcca-0d4fe460ce89"
/>
Adds custom `/prompts` to `~/.codex/prompts/<command>.md`.
<img width="239" height="107" alt="Screenshot 2025-08-25 at 6 22 42 PM"
src="https://github.com/user-attachments/assets/fe6ebbaa-1bf6-49d3-95f9-fdc53b752679"
/>
---
Details:
1. Adds `Op::ListCustomPrompts` to core.
2. Returns `ListCustomPromptsResponse` with list of `CustomPrompt`
(name, content).
3. TUI calls the operation on load, and populates the custom prompts
(excluding prompts that collide with builtins).
4. Selecting the custom prompt automatically sends the prompt to the
agent.
## What
Make slash commands (/init, /status, /approvals, /model) bold and white
in the welcome message for better visibility.
<img width="990" height="286" alt="image"
src="https://github.com/user-attachments/assets/13f90e96-b84a-4659-aab4-576d84a31af7"
/>
## Why
The current welcome message displays all text in a dimmed style, making
the slash commands less prominent. Users need to quickly identify
available commands when starting Codex.
## How
Modified `tui/src/history_cell.rs` in the `new_session_info` function
to:
- Split each command line into separate spans
- Apply bold white styling to command text (`/init`, `/status`, etc.)
- Keep descriptions dimmed for visual contrast
- Maintain existing layout and spacing
## Test plan
- [ ] Run the TUI and verify commands appear bold in the welcome message
- [ ] Ensure descriptions remain dimmed for readability
- [ ] Confirm all existing tests pass
This PR fixes two edge cases in managing burst paste (mainly on power
shell).
Bugs:
- Needs an event key after paste to render the pasted items
> ChatComposer::flush_paste_burst_if_due() flushes on timeout. Called:
> - Pre-render in App on TuiEvent::Draw.
> - Via a delayed frame
>
BottomPane::request_redraw_in(ChatComposer::recommended_paste_flush_delay()).
- Parses two key events separately before starting parsing burst paste
> When threshold is crossed, pull preceding burst chars out of the
textarea and prepend to paste_burst_buffer, then keep buffering.
- Integrates with #2567 to bring image pasting to windows.
`test_shell_command_approval_triggers_elicitation()` is one of a number
of integration tests that we have observed to be flaky on GitHub CI, so
this PR tries to reduce the flakiness _and_ to provide us with more
information when it flakes. Specifically:
- Changed the command that we use to trigger the elicitation from `git
init` to `python3 -c 'import pathlib; pathlib.Path(r"{}").touch()'`
because running `git` seems more likely to invite variance.
- Increased the timeout to wait for the task response from 10s to 20s.
- Added more logging.
- added `uninlined_format_args` to `[workspace.lints.clippy]` in the
`Cargo.toml` for the workspace
- ran `cargo clippy --tests --fix`
- ran `just fmt`
This was supposed to be fixed by #2569, but I think the actual fix got
lost in the refactoring.
Intended behavior: pressing ^Z moves the cursor below the viewport
before suspending.
This was mostly written by codex under heavy guidance via test cases
drawn from logged session data and fuzzing. It also uncovered some bugs
in tui_markdown, which will in some cases split a list marker from the
list item content. We're not addressing those bugs for now.
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
This is a stopgap solution, but today, we are seeing the client get
flooded with events. Since we already truncate the output we send to the
model, it feels reasonable to limit how many deltas we send to the
client.
## Summary
Adds a GetConfig request to the MCP Protocol, so MCP clients can
evaluate the resolved config.toml settings which the harness is using.
## Testing
- [x] Added an end to end test of the endpoint
Prevented panics when deleting placeholders near multibyte characters by
clamping the cursor to a valid boundary and using get-based slicing
Added a regression test to ensure backspacing after multibyte text
leaves placeholders intact without crashing
---------
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
This fixes a bug where if you ran /diff while at turn was running,
transcript lines would be added to the end of the diff view. Also,
refactor to make this kind of issue less likely in future.
This pr addresses the fix for
https://github.com/openai/codex/issues/2713
### Changes:
- Added key handler for `Alt+Ctrl+H` → `delete_backward_word()`
- Added test coverage in `delete_backward_word_alt_keys()` that verifies
both:
- Standard `Alt+Backspace` binding continues to work
- New `Alt+Ctrl+H` binding works correctly for backward word deletion
### Testing:
The test ensures both key combinations produce identical behavior:
- Delete the previous word from "hello world" → "hello "
- Cursor positioned correctly after deletion
### Backward Compatibility:
This change is backward compatible - existing `Alt+Backspace`
functionality remains unchanged while adding support for the
terminal-specific `Alt+Ctrl+H` variant
Use emoji variation selector (VS16) for the keyboard icon so it
consistently renders as emoji (⌨️) rather than text (⌨) across
terminals.
Touches TUI command rendering for unknown parsed commands. No behavior
change beyond display.
### What this PR does
This PR introduces a new public method,
remove_conversation(conversation_id: Uuid), to the ConversationManager.
This allows consumers of the codex-core library to manually remove a
conversation from the manager's in-memory storage.
### Why this change is needed
I am currently adapting the Codex client to run as a long-lived server
application. In this server environment, ConversationManager instances
persist for extended periods, and new conversations are created for each
incoming user request.
The current implementation of ConversationManager stores all created
conversations in a HashMap indefinitely, with no mechanism for removal.
This leads to unbounded memory growth in a server context, as every new
conversation permanently occupies memory.
While an automatic TTL-based cleanup mechanism could be one solution, a
simpler, more direct remove_conversation method provides the necessary
control for my use case. It allows my server application to explicitly
manage the lifecycle of conversations, such as cleaning them up after a
request is fully processed or after a period of inactivity is detected
at the application level.
This change provides a minimal, non-intrusive way to address the memory
management issue for server-like applications built on top of
codex-core, giving developers the flexibility to implement their own
cleanup logic.
Signed-off-by: M4n5ter <m4n5terrr@gmail.com>
Co-authored-by: Michael Bolin <mbolin@openai.com>
There are some design issues with this action, so until we work them
out, we'll remove this code from the repository to avoid folks from
taking a dependency on it.
The CLI supports config settings `stream_max_retries` and
`request_max_retries` that allow users to override the default retry
counts (4 and 5, respectively). However, there's currently no cap placed
on these values. In theory, a user could configure an effectively
infinite retry count which could hammer the server. This PR adds a
reasonable cap (currently 100) to both of these values.
This PR improves the error message presented to the user when logged in
with ChatGPT and a rate-limit error occurs. In particular, it provides
the user with information about when the rate limit will be reset. It
removes older code that attempted to do the same but relied on parsing
of error messages that are not generated by the ChatGPT endpoint. The
new code uses newly-added error fields.
Esc and Ctrl+C while a task is running should do the same thing. There
were some cases where pressing Esc would leave a "stuck" widget in the
history; this fixes that and cleans up the logic so there's just one
path for interrupting the task. Also clean up some subtly mishandled key
events (e.g. Ctrl+D would quit the app while an approval modal was
showing if the textarea was empty).
---------
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
This PR fixes a bug in the token refresh logic. Token refresh is
performed in a retry loop so if we receive a 401 error, we refresh the
token, then we go around the loop again and reissue the fetch with a
fresh token. The bug is that we're not using the updated token on the
second and subsequent times through the loop. The result is that we'll
try to refresh the token a few more times until we hit the retry limit
(default of 4). The 401 error is then passed back up to the caller.
Subsequent calls will use the refreshed token, so the problem clears
itself up.
The fix is straightforward — make sure we use the updated auth
information each time through the retry loop.
In this PR:
- [x] Add support for dragging / copying image files into chat.
- [x] Don't remove image placeholders when submitting.
- [x] Add tests.
Works for:
- Image Files
- Dragging MacOS Screenshots (Terminal, iTerm)
Todos:
- [ ] In some terminals (VSCode, WIndows Powershell, and remote
SSH-ing), copy-pasting a file streams the escaped filepath as individual
key events rather than a single Paste event. We'll need to have a
function (in a separate PR) for detecting these paste events.
Esc should have other functionalities when it's not used in a
backtracking situation. i.e. to cancel pop up menu when selecting
model/approvals or to interrupt an active turn.
## Summary
These tests were getting a bit unwieldy, and they're starting to become
load-bearing. Let's clean them up, and get them working solidly so we
can easily expand this harness with new tests.
## Test Plan
- [x] Tests continue to pass
I noticed that when running `/status` on Windows, I saw something like:
```
Path: ~/src\codex
```
so now it should be:
```
Path: ~\src\codex
```
Admittedly, `~` is understood by PowerShell but not on Windows, in
general, but it's much less verbose than `%USERPROFILE%`.
**Context**
When running `/compact`, `drain_to_completed` would throw an error if
`token_usage` was `None` in `ResponseEvent::Completed`. This made the
command fail even though everything else had succeeded.
**What changed**
- Instead of erroring, we now just check `if let Some(token_usage)`
before sending the event.
- If it’s missing, we skip it and move on.
**Why**
This makes `AgentTask::compact()` behave in the same way as
`AgentTask::spawn()`, which also doesn’t error out when `token_usage`
isn’t available. Keeps things consistent and avoids unnecessary
failures.
**Fixes**
Closes#2417
---------
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
The `SessionManager` in `exec_command` owns a number of
`ExecCommandSession` objects where `ExecCommandSession` has a
non-trivial implementation of `Drop`, so we want to be able to drop an
individual `SessionManager` to help ensure things get cleaned up in a
timely fashion. To that end, we should have one `SessionManager` per
session rather than one global one for the lifetime of the CLI process.
`ToolsConfig::new()` taking a large number of boolean params was hard to
manage and it finally bit us (see
https://github.com/openai/codex/pull/2660). This changes
`ToolsConfig::new()` so that it takes a struct (and also reduces the
visibility of some members, where possible).
Fixes https://github.com/openai/codex/issues/2610
This PR sorts the tools in `get_openai_tools` by name to ensure a
consistent MCP tool order.
Currently, MCP servers are stored in a HashMap, which does not guarantee
ordering. As a result, the tool order changes across turns, effectively
breaking prompt caching in multi-turn sessions.
An alternative solution would be to replace the HashMap with an ordered
structure, but that would require a much larger code change. Given that
it is unrealistic to have so many MCP tools that sorting would cause
performance issues, this lightweight fix is chosen instead.
By ensuring deterministic tool order, this change should significantly
improve cache hit rates and prevent users from hitting usage limits too
quickly. (For reference, my own sessions last week reached the limit
unusually fast, with cache hit rates falling below 1%.)
## Result
After this fix, sessions with MCP servers now show caching behavior
almost identical to sessions without MCP servers.
Without MCP | With MCP
:-------------------------:|:-------------------------:
<img width="1368" height="1634" alt="image"
src="https://github.com/user-attachments/assets/26edab45-7be8-4d6a-b471-558016615fc8"
/> | <img width="1356" height="1632" alt="image"
src="https://github.com/user-attachments/assets/5f3634e0-3888-420b-9aaf-deefd9397b40"
/>
Bumps [whoami](https://github.com/ardaku/whoami) from 1.6.0 to 1.6.1.
<details>
<summary>Commits</summary>
<ul>
<li>See full diff in <a
href="https://github.com/ardaku/whoami/commits">compare view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Historically, Codex CLI has treated `apply_patch` (and its sometimes
misspelling, `applypatch`) as a "virtual CLI," intercepting it when it
appears as the first arg to `command` for the `"container.exec",
`"shell"`, or `"local_shell"` tools.
This approach has a known limitation where if, say, the model created a
Python script that runs `apply_patch` and then tried to run the Python
script, we have no insight as to what the model is trying to do and the
Python Script would fail because `apply_patch` was never really on the
`PATH`.
One way to solve this problem is to require users to install an
`apply_patch` executable alongside the `codex` executable (or at least
put it someplace where Codex can discover it). Though to keep Codex CLI
as a standalone executable, we exploit "the arg0 trick" where we create
a temporary directory with an entry named `apply_patch` and prepend that
directory to the `PATH` for the duration of the invocation of Codex.
- On UNIX, `apply_patch` is a symlink to `codex`, which now changes its
behavior to behave like `apply_patch` if arg0 is `apply_patch` (or
`applypatch`)
- On Windows, `apply_patch.bat` is a batch script that runs `codex
--codex-run-as-apply-patch %*`, as Codex also changes its behavior if
the first argument is `--codex-run-as-apply-patch`.
## Summary
We're seeing some issues in the freeform tool - let's disable by default
until it stabilizes.
## Testing
- [x] Ran locally, confirmed codex-cli could make edits
this dramatically improves time to run `cargo test -p codex-core` (~25x
speedup).
before:
```
cargo test -p codex-core 35.96s user 68.63s system 19% cpu 8:49.80 total
```
after:
```
cargo test -p codex-core 5.51s user 8.16s system 63% cpu 21.407 total
```
both tests measured "hot", i.e. on a 2nd run with no filesystem changes,
to exclude compile times.
approach inspired by [Delete Cargo Integration
Tests](https://matklad.github.io/2021/02/27/delete-cargo-integration-tests.html),
we move all test cases in tests/ into a single suite in order to have a
single binary, as there is significant overhead for each test binary
executed, and because test execution is only parallelized with a single
binary.
Adds web_search tool, enabling the model to use Responses API web_search
tool.
- Disabled by default, enabled by --search flag
- When --search is passed, exposes web_search_request function tool to
the model, which triggers user approval. When approved, the model can
use the web_search tool for the remainder of the turn
<img width="1033" height="294" alt="image"
src="https://github.com/user-attachments/assets/62ac6563-b946-465c-ba5d-9325af28b28f"
/>
---------
Co-authored-by: easong-openai <easong@openai.com>
We want to send an aggregated output of stderr and stdout so we don't
have to aggregate it stderr+stdout as we lose order sometimes.
---------
Co-authored-by: Gabriel Peal <gpeal@users.noreply.github.com>
This can be the underlying logic in order to start a conversation from a
previous message. will need some love in the UI.
Base for building this: #2588
## Summary
- read the shell exec approval request's actual id instead of assuming
it is always 0
- use that id when validating and responding in the test
## Testing
- `cargo test -p codex-mcp-server
test_shell_command_approval_triggers_elicitation`
------
https://chatgpt.com/codex/tasks/task_i_68a6ab9c732c832c81522cbf11812be0
Bumps [serde_json](https://github.com/serde-rs/json) from 1.0.142 to
1.0.143.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/serde-rs/json/releases">serde_json's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.143</h2>
<ul>
<li>Implement Clone and Debug for serde_json::Map iterators (<a
href="https://redirect.github.com/serde-rs/json/issues/1264">#1264</a>,
thanks <a
href="https://github.com/xlambein"><code>@xlambein</code></a>)</li>
<li>Implement Default for CompactFormatter (<a
href="https://redirect.github.com/serde-rs/json/issues/1268">#1268</a>,
thanks <a href="https://github.com/SOF3"><code>@SOF3</code></a>)</li>
<li>Implement FromStr for serde_json::Map (<a
href="https://redirect.github.com/serde-rs/json/issues/1271">#1271</a>,
thanks <a
href="https://github.com/mickvangelderen"><code>@mickvangelderen</code></a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="10102c49bf"><code>10102c4</code></a>
Release 1.0.143</li>
<li><a
href="2a5b85312c"><code>2a5b853</code></a>
Replace super::super with absolute path within crate</li>
<li><a
href="447170bd38"><code>447170b</code></a>
Merge pull request 1271 from
mickvangelderen/mick/impl-from-str-for-map</li>
<li><a
href="ec190d6dfd"><code>ec190d6</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/json/issues/1264">#1264</a>
from xlambein/master</li>
<li><a
href="8be664752f"><code>8be6647</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/json/issues/1268">#1268</a>
from SOF3/compact-default</li>
<li><a
href="ba5b3cccea"><code>ba5b3cc</code></a>
Revert "Pin nightly toolchain used for miri job"</li>
<li><a
href="fd35a02901"><code>fd35a02</code></a>
Implement FromStr for Map<String, Value></li>
<li><a
href="bea0fe6b3e"><code>bea0fe6</code></a>
Implement Default for CompactFormatter</li>
<li><a
href="0c0e9f6bfa"><code>0c0e9f6</code></a>
Add Clone and Debug impls to map iterators</li>
<li>See full diff in <a
href="https://github.com/serde-rs/json/compare/v1.0.142...v1.0.143">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Prior to this change, when we got a `CallToolResult` from an MCP server,
we JSON-serialized its `content` field as the `content` to send back to
the model as part of the function call output that we send back to the
model. This meant that we were dropping the `structuredContent` on the
floor.
Though reading
https://modelcontextprotocol.io/specification/2025-06-18/schema#tool, it
appears that if `outputSchema` is specified, then `structuredContent`
should be set, which seems to be a "higher-fidelity" response to the
function call. This PR updates our handling of `CallToolResult` to
prefer using the JSON-serialization of `structuredContent`, if present,
using `content` as a fallback.
Also, it appears that the sense of `success` was inverted prior to this
PR!
before:
```
$ time cargo test -p codex-tui -q
[...]
cargo test -p codex-tui -q 39.89s user 10.77s system 98% cpu 51.328 total
```
after:
```
$ time cargo test -p codex-tui -q
[...]
cargo test -p codex-tui -q 1.37s user 0.64s system 29% cpu 6.699 total
```
the major offenders were the textarea fuzz test and the custom_terminal
doctests. (i think the doctests were being recompiled every time which
made them extra slow?)
## Summary
When resolving our current directory as a project, we want to be a
little bit more clever:
1. If we're in a sub-directory of a git repo, resolve our project
against the root of the git repo
2. If we're in a git worktree, resolve the project against the root of
the git repo
## Testing
- [x] Added unit tests
- [x] Confirmed locally with a git worktree (the one i was using for
this feature)
## Summary
GPT-5 introduced the concept of [custom
tools](https://platform.openai.com/docs/guides/function-calling#custom-tools),
which allow the model to send a raw string result back, simplifying
json-escape issues. We are migrating gpt-5 to use this by default.
However, gpt-oss models do not support custom tools, only normal
functions. So we keep both tool definitions, and provide whichever one
the model family supports.
## Testing
- [x] Tested locally with various models
- [x] Unit tests pass
This PR adds a central `AuthManager` struct that manages the auth
information used across conversations and the MCP server. Prior to this,
each conversation and the MCP server got their own private snapshots of
the auth information, and changes to one (such as a logout or token
refresh) were not seen by others.
This is especially problematic when multiple instances of the CLI are
run. For example, consider the case where you start CLI 1 and log in to
ChatGPT account X and then start CLI 2 and log out and then log in to
ChatGPT account Y. The conversation in CLI 1 is still using account X,
but if you create a new conversation, it will suddenly (and
unexpectedly) switch to account Y.
With the `AuthManager`, auth information is read from disk at the time
the `ConversationManager` is constructed, and it is cached in memory.
All new conversations use this same auth information, as do any token
refreshes.
The `AuthManager` is also used by the MCP server's GetAuthStatus
command, which now returns the auth method currently used by the MCP
server.
This PR also includes an enhancement to the GetAuthStatus command. It
now accepts two new (optional) input parameters: `include_token` and
`refresh_token`. Callers can use this to request the in-use auth token
and can optionally request to refresh the token.
The PR also adds tests for the login and auth APIs that I recently added
to the MCP server.
Introduce a minimal paste-burst heuristic in the chat composer so Enter
is treated as a newline during paste-like bursts (plain chars arriving
in very short intervals), avoiding premature submit after the first line
on Windows consoles that lack bracketed paste.
- Detect tight sequences of plain Char events; open a short window where
Enter inserts a newline instead of submitting.
- Extend the window on newline to handle blank lines in pasted content.
- No behavior change for terminals that already emit Event::Paste; no
OS/env toggles added.
allow ctrl+v in TUI for images + @file that are images are appended as
raw files (and read by the model) rather than pasted as a path that
cannot be read by the model.
Re-used components and same interface we're using for copying pasted
content in
72504f1d9c.
@aibrahim-oai as you've implemented this, mind having a look at this
one?
https://github.com/user-attachments/assets/c6c1153b-6b32-4558-b9a2-f8c57d2be710
---------
Co-authored-by: easong-openai <easong@openai.com>
Co-authored-by: Daniel Edrisian <dedrisian@openai.com>
Co-authored-by: Michael Bolin <mbolin@openai.com>
This is a somewhat roundabout way to fix the issue that pressing ^Z
would put the shell prompt in the wrong place (overwriting some of the
status area below the composer). While I'm at it, clean up the suspend
logic and fix some suspend-while-in-alt-screen behavior too.
**Summary**
- Adds `model_verbosity` config (values: low, medium, high).
- Sends `text.verbosity` only for GPT‑5 family models via the Responses
API.
- Updates docs and adds serialization tests.
**Motivation**
- GPT‑5 introduces a verbosity control to steer output length/detail
without pro
mpt surgery.
- Exposing it as a config knob keeps prompts stable and makes behavior
explicit
and repeatable.
**Changes**
- Config:
- Added `Verbosity` enum (low|medium|high).
- Added optional `model_verbosity` to `ConfigToml`, `Config`, and
`ConfigProfi
le`.
- Request wiring:
- Extended `ResponsesApiRequest` with optional `text` object.
- Populates `text.verbosity` only when model family is `gpt-5`; omitted
otherw
ise.
- Tests:
- Verifies `text.verbosity` serializes when set and is omitted when not
set.
- Docs:
- Added “GPT‑5 Verbosity” section in `codex-rs/README.md`.
- Added `model_verbosity` section to `codex-rs/config.md`.
**Usage**
- In `~/.codex/config.toml`:
- `model = "gpt-5"`
- `model_verbosity = "low"` (or `"medium"` default, `"high"`)
- CLI override example:
- `codex -c model="gpt-5" -c model_verbosity="high"`
**API Impact**
- Requests to GPT‑5 via Responses API include: `text: { verbosity:
"low|medium|h
igh" }` when configured.
- For legacy models or Chat Completions providers, `text` is omitted.
**Backward Compatibility**
- Default behavior unchanged when `model_verbosity` is not set (server
default “
medium”).
**Testing**
- Added unit tests for serialization/omission of `text.verbosity`.
- Ran `cargo fmt` and `cargo test --all-features` (all green).
**Docs**
- `README.md`: new “GPT‑5 Verbosity” note under Config with example.
- `config.md`: new `model_verbosity` section.
**Out of Scope**
- No changes to temperature/top_p or other GPT‑5 parameters.
- No changes to Chat Completions wiring.
**Risks / Notes**
- If OpenAI changes the wire shape for verbosity, we may need to update
`Respons
esApiRequest`.
- Behavior gated to `gpt-5` model family to avoid unexpected effects
elsewhere.
**Checklist**
- [x] Code gated to GPT‑5 family only
- [x] Docs updated (`README.md`, `config.md`)
- [x] Tests added and passing
- [x] Formatting applied
Release note: Add `model_verbosity` config to control GPT‑5 output verbosity via the Responses API (low|medium|high).
## Summary
We've experienced a bit of drift in system prompting for `apply_patch`:
- As pointed out in #2030 , our prettier formatting started altering
prompt.md in a few ways
- We introduced a separate markdown file for apply_patch instructions in
#993, but currently duplicate them in the prompt.md file
- We added a first-class apply_patch tool in #2303, which has yet
another definition
This PR starts to consolidate our logic in a few ways:
- We now only use
`apply_patch_tool_instructions.md](https://github.com/openai/codex/compare/dh--apply-patch-tool-definition?expand=1#diff-d4fffee5f85cb1975d3f66143a379e6c329de40c83ed5bf03ffd3829df985bea)
for system instructions
- We no longer include apply_patch system instructions if the tool is
specified
I'm leaving the definition in openai_tools.rs as duplicated text for now
because we're going to be iterated on the first-class tool soon.
## Testing
- [x] Added integration tests to verify prompt stability
- [x] Tested locally with several different models (gpt-5, gpt-oss,
o4-mini)
## Summary
Small update to hopefully improve some shell edge cases, and make the
function clearer to the model what is going on. Keeping `timeout` as an
alias means that calls with the previous name will still work.
## Test Plan
- [x] Tested locally, model still works
moves TranscriptApp to be an "overlay", and continue to pump AppEvents
while the transcript is active, but forward all tui handling to the
transcript screen.
## Summary
Before we land #2243, let's start printing environment_context in our
preferred format. This struct will evolve over time with new
information, xml gives us a balance of human readable without too much
parsing, llm readable, and extensible.
Also moves us over to an Option-based struct, so we can easily provide
diffs to the model.
## Testing
- [x] Updated tests to reflect new format
This PR adds the following:
* A getAuthStatus method on the mcp server. This returns the auth method
currently in use (chatgpt or apikey) or none if the user is not
authenticated. It also returns the "preferred auth method" which
reflects the `preferred_auth_method` value in the config.
* A logout method on the mcp server. If called, it logs out the user and
deletes the `auth.json` file — the same behavior in the cli's `/logout`
command.
* An `authStatusChange` event notification that is sent when the auth
status changes due to successful login or logout operations.
* Logic to pass command-line config overrides to the mcp server at
startup time. This allows use cases like `codex mcp -c
preferred_auth_method=apikey`.
## What? Why? How?
- When running on Windows, codex often tries to invoke bash commands,
which commonly fail (unless WSL is installed)
- Fix: Detect if powershell is available and, if so, route commands to
it
- Also add a shell_name property to environmental context for codex to
default to powershell commands when running in that environment
## Testing
- Tested within WSL and powershell (e.g. get top 5 largest files within
a folder and validated that commands generated were powershell commands)
- Tested within Zsh
- Updated unit tests
---------
Co-authored-by: Eddy Escardo <eddy@openai.com>
This PR:
- fixes for internal employee because we currently want to prefer SIWC
for them.
- fixes retrying forever on unauthorized access. we need to break
eventually on max retries.
this is in preparation for adding more separate "modes" to the tui, in
particular, a "transcript mode" to view a full history once #2316 lands.
1. split apart "tui events" from "app events".
2. remove onboarding-related events from AppEvent.
3. move several general drawing tools out of App and into a new Tui
class
## Summary
Follow up to #2186 for #2072 - we added handling for `applypatch` in
default commands, but forgot to add detection to the heredocs logic.
## Testing
- [x] Added unit tests
- For selectable options, use sentences starting in lowercase and not
ending with periods. To be honest I don't love this style, but better to
be consistent for now.
- Tweak some other strings.
- Put in more compelling suggestions on launch. Excited to put `/mcp` in
there next.
ChatGPT token's live for only 1 hour. If the session is longer we don't
refresh the token. We should get the expiry timestamp and attempt to
refresh before it.
Codex created this PR from the following prompt:
> upgrade this entire repo to Rust 1.89. Note that this requires
updating codex-rs/rust-toolchain.toml as well as the workflows in
.github/. Make sure that things are "clippy clean" as this change will
likely uncover new Clippy errors. `just fmt` and `cargo clippy --tests`
are sufficient to check for correctness
Note this modifies a lot of lines because it folds nested `if`
statements using `&&`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2465).
* #2467
* __->__ #2465
The `ubuntu-24.04 - x86_64-unknown-linux-gnu` build is failing with `No
space left on device` on #2465, so let's get this in first, which should
help.
Note that `cargo check` should be faster and use less disk than `cargo
build` because it does not write out the object files.
## Summary
- just want to declutter the top level workspace section
## Testing
- `just fmt`
- `just fix` *(fails: error[E0658] let expressions in this position are
unstable in codex-protocol)*
- `cargo test -p codex-tui` *(fails: error[E0658] let expressions in
this position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_68a4a7311dbc832caf14f52e0fbaf9c2
Ensure Emacs-style Ctrl-b/Ctrl-f work when terminals send bare control
chars.
- Map ^B (U+0002) to move left when no CONTROL modifier is reported.
- Map ^F (U+0006) to move right when no CONTROL modifier is reported.
- Preserve existing Ctrl-b/Ctrl-f and Alt-b/Alt-f behavior.
- Add unit test covering the fallback path.
Background: Ghostty (and some tmux/terminal configs) can emit bare
control characters for Ctrl-b/Ctrl-f. Previously these could be treated
as literal input; with this change both styles behave identically.
## Summary
Adds a `/mcp` command to list active tools. We can extend this command
to allow configuration of MCP tools, but for now a simple list command
will help debug if your config.toml and your tools are working as
expected.
- Prevents the % left indicator from immediately decrementing to ~97%.
- Tested by prompting "hi" and noting it only decremented to 99%. And by
adding a bunch of debug logs and observing numbers.
Motivation: we have users who uses their API key although they want to
use ChatGPT account. We want to give them the chance to always login
with their account.
This PR displays login options when the user is not signed in with
ChatGPT. Even if you have set an OpenAI API key as an environment
variable, you will still be prompted to log in with ChatGPT.
We’ve also added a new flag, `always_use_api_key_signing` false by
default, which ensures you are never asked to log in with ChatGPT and
always defaults to using your API key.
https://github.com/user-attachments/assets/b61ebfa9-3c5e-4ab7-bf94-395c23a0e0af
After ChatGPT sign in:
https://github.com/user-attachments/assets/d58b366b-c46a-428f-a22f-2ac230f991c0
Updates the tokio task that monitors `shutdown_notify` and server
requests to ensure that `server.unblock()` is always called, which means
that `ShutdownHandle` only has to invoke `notify_waiters()`.
Now `LoginServer` no longer has to maintain a reference to `Server`. The
`Arc<Server>` only has two active references: the `thread::spawn()` for
reading server messages and the `tokio::task()` that consumes them (and
the shutdown message). Now when shutdown is called (or if login
completes successfully), the `server.unblock()` call ensures the thread
terminates cleanly, which in turn ensures `rx.recv()` in the
`tokio::spawn()` returns `Err`, causing the `tokio::task()` to exit
cleanly, as well.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2398).
* #2399
* __->__ #2398
* #2396
* #2395
* #2394
* #2393
* #2389
Folds the top-level `shutdown()` function into a method of
`ShutdownHandle` and then simply stores `ShutdownHandle` on
`LoginServer` since the two fields it contains were always being used
together, anyway.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2396).
* #2399
* #2398
* __->__ #2396
* #2395
* #2394
* #2393
* #2389
https://github.com/openai/codex/pull/2373 introduced
`ServerOptions.login_timeout` and `spawn_timeout_watcher()` to use an
extra thread to manage the timeout for the login server. Now that we
have asyncified the login stack, we can use `tokio::time::timeout()`
from "outside" the login library to manage the timeout rather than
having to a commit to a specific "timeout" concept from within.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2395).
* #2399
* #2398
* #2396
* __->__ #2395
* #2394
* #2393
* #2389
Prior to this PR, we had:
71cae06e66/codex-rs/login/src/server.rs (L141-L142)
which means that we could be blocked waiting for a new request in
`server_for_thread.recv()` and not notice that the state of
`shutdown_flag` had changed.
With this PR, we use `shutdown_flag: Notify` so that we can
`tokio::select!` on `shutdown_notify.notified()` and `rx.recv()` (which
is the "async stream" of requests read from `server_for_thread.recv()`)
and handle whichever one happens first.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2394).
* #2399
* #2398
* #2396
* #2395
* __->__ #2394
* #2393
* #2389
[//]: # (dependabot-start)
⚠️ **Dependabot is rebasing this PR** ⚠️
Rebasing might not happen immediately, so don't worry if this takes some
time.
Note: if you make any changes to this PR yourself, they will take
precedence over the rebase.
---
[//]: # (dependabot-end)
Bumps [clap](https://github.com/clap-rs/clap) from 4.5.43 to 4.5.45.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/clap-rs/clap/releases">clap's
releases</a>.</em></p>
<blockquote>
<h2>v4.5.45</h2>
<h2>[4.5.45] - 2025-08-12</h2>
<h3>Fixes</h3>
<ul>
<li><em>(unstable-v5)</em> <code>ValueEnum</code> variants now use the
full doc comment, not summary, for <code>PossibleValue::help</code></li>
</ul>
<h2>v4.5.44</h2>
<h2>[4.5.44] - 2025-08-11</h2>
<h3>Features</h3>
<ul>
<li>Add <code>Command::mut_subcommands</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/clap-rs/clap/blob/master/CHANGELOG.md">clap's
changelog</a>.</em></p>
<blockquote>
<h2>[4.5.45] - 2025-08-12</h2>
<h3>Fixes</h3>
<ul>
<li><em>(unstable-v5)</em> <code>ValueEnum</code> variants now use the
full doc comment, not summary, for <code>PossibleValue::help</code></li>
</ul>
<h2>[4.5.44] - 2025-08-11</h2>
<h3>Features</h3>
<ul>
<li>Add <code>Command::mut_subcommands</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="246d972a6c"><code>246d972</code></a>
chore: Release</li>
<li><a
href="a35a0761ae"><code>a35a076</code></a>
docs: Update changelog</li>
<li><a
href="9b985a3c17"><code>9b985a3</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/5912">#5912</a>
from epage/takes</li>
<li><a
href="389fbe87d2"><code>389fbe8</code></a>
feat(builder): Allow flags to take num_args=0..=1</li>
<li><a
href="c395d02703"><code>c395d02</code></a>
test(parser): Show flag behavior</li>
<li><a
href="32c119efa6"><code>32c119e</code></a>
refactor(assert): Be more specific than action.takes_values</li>
<li><a
href="80ea3e7c24"><code>80ea3e7</code></a>
fix(assert): Clean up num_args/action assert</li>
<li><a
href="2bc0f45fe5"><code>2bc0f45</code></a>
fix(builder): Make ValueRange display independent of usize::MAX</li>
<li><a
href="a0187c6f3b"><code>a0187c6</code></a>
test(assert): Verify num_args/action compat</li>
<li><a
href="a8f9885250"><code>a8f9885</code></a>
refactor(builder): Be more explicit in how takes_values is used</li>
<li>Additional commits viewable in <a
href="https://github.com/clap-rs/clap/compare/clap_complete-v4.5.43...clap_complete-v4.5.45">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [anyhow](https://github.com/dtolnay/anyhow) from 1.0.98 to 1.0.99.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/dtolnay/anyhow/releases">anyhow's
releases</a>.</em></p>
<blockquote>
<h2>1.0.99</h2>
<ul>
<li>Allow build-script cleanup failure with NFSv3 output directory to be
non-fatal (<a
href="https://redirect.github.com/dtolnay/anyhow/issues/420">#420</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="f2b963a759"><code>f2b963a</code></a>
Release 1.0.99</li>
<li><a
href="2c64c15e75"><code>2c64c15</code></a>
Merge pull request <a
href="https://redirect.github.com/dtolnay/anyhow/issues/420">#420</a>
from dtolnay/enotempty</li>
<li><a
href="8cf66f7936"><code>8cf66f7</code></a>
Allow build-script cleanup failure with NFSv3 output directory to be
non-fatal</li>
<li><a
href="f5e145c683"><code>f5e145c</code></a>
Revert "Pin nightly toolchain used for miri job"</li>
<li><a
href="1d7ef1db54"><code>1d7ef1d</code></a>
Update ui test suite to nightly-2025-06-30</li>
<li><a
href="69295727ce"><code>6929572</code></a>
Update ui test suite to nightly-2025-06-18</li>
<li><a
href="37224e3142"><code>37224e3</code></a>
Ignore mismatched_lifetime_syntaxes lint</li>
<li><a
href="11f0e81aaf"><code>11f0e81</code></a>
Pin nightly toolchain used for miri job</li>
<li><a
href="d04c999d63"><code>d04c999</code></a>
Raise required compiler for backtrace feature to rust 1.82</li>
<li><a
href="219d16330d"><code>219d163</code></a>
Update test suite to nightly-2025-05-01</li>
<li>See full diff in <a
href="https://github.com/dtolnay/anyhow/compare/1.0.98...1.0.99">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
This pull request resolves#2391. ctrl + h is not assigned to any other
operations at this moment, and this feature request sounds valid to me.
If we don't prefer having this, please feel free to close this.
The existing `wire_format.rs` should share more types with the
`codex-protocol` crate (like `AskForApproval` instead of maintaining a
parallel `CodexToolCallApprovalPolicy` enum), so this PR moves
`wire_format.rs` into `codex-protocol`, renaming it as
`mcp-protocol.rs`. We also de-dupe types, where appropriate.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2423).
* #2424
* __->__ #2423
Bumps
[@types/node](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/node)
from 24.2.1 to 24.3.0.
<details>
<summary>Commits</summary>
<ul>
<li>See full diff in <a
href="https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/node">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
New style guide:
# Headers, primary, and secondary text
- **Headers:** Use `bold`. For markdown with various header levels,
leave in the `#` signs.
- **Primary text:** Default.
- **Secondary text:** Use `dim`.
# Foreground colors
- **Default:** Most of the time, just use the default foreground color.
`reset` can help get it back.
- **Selection:** Use ANSI `blue`. (Ed & AE want to make this cyan too,
but we'll do that in a followup since it's riskier in different themes.)
- **User input tips and status indicators:** Use ANSI `cyan`.
- **Success and additions:** Use ANSI `green`.
- **Errors, failures and deletions:** Use ANSI `red`.
- **Codex:** Use ANSI `magenta`.
# Avoid
- Avoid custom colors because there's no guarantee that they'll contrast
well or look good on various terminal color themes.
- Avoid ANSI `black`, `white`, `yellow` as foreground colors because the
terminal theme will do a better job. (Use `reset` if you need to in
order to get those.) The exception is if you need contrast rendering
over a manually colored background.
(There are some rules to try to catch this in `clippy.toml`.)
# Testing
Tested in a variety of light and dark color themes in Terminal, iTerm2, and Ghostty.
Introduces `EventMsg::TurnAborted` that should be sent in response to
`Op::Interrupt`.
In the MCP server, updates the handling of a
`ClientRequest::InterruptConversation` request such that it sends the
`Op::Interrupt` but does not respond to the request until it sees an
`EventMsg::TurnAborted`.
This PR adds two new APIs for the MCP server: 1) loginChatGpt, and 2)
cancelLoginChatGpt. The first starts a login server and returns a local
URL that allows for browser-based authentication, and the second
provides a way to cancel the login attempt. If the login attempt
succeeds, a notification (in the form of an event) is sent to a
subscriber.
I also added a timeout mechanism for the existing login server. The
loginChatGpt code path uses a 10-minute timeout by default, so if the
user fails to complete the login flow in that timeframe, the login
server automatically shuts down. I tested the timeout code by manually
setting the timeout to a much lower number and confirming that it works
as expected when used e2e.
## Summary
- Show a temporary Working on diff state in the bottom pan
- Add `DiffResult` app event and dispatch git diff asynchronously
## Testing
- `just fmt`
- `just fix` *(fails: `let` expressions in this position are unstable)*
- `cargo test --all-features` *(fails: `let` expressions in this
position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_689a839f32b88321840a893551d5fbef
This pull request resolves#2296; I've confirmed if it works by:
1. Add settings to ~/.codex/config.toml:
```toml
model_reasoning_effort = "minimal"
```
2. Run the CLI:
```
cd codex-rs
cargo build && RUST_LOG=trace cargo run --bin codex
/status
tail -f ~/.codex/log/codex-tui.log
```
Co-authored-by: pakrym-oai <pakrym@openai.com>
This adds a new request type, `SendUserTurn`, that makes it possible to
submit a `Op::UserTurn` operation (introduced in #2329) to a
conversation. This PR also adds a new integration test that verifies
that changing from `AskForApproval::UnlessTrusted` to
`AskForApproval::Never` mid-conversation ensures that an elicitation is
no longer sent for running `python3 -c print(42)`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2345).
* __->__ #2345
* #2329
* #2343
* #2340
* #2338
This introduces `Op::UserTurn`, which makes it possible to override many
of the fields that were set when the `Session` was originally created
when creating a new conversation turn. This is one way we could support
changing things like `model` or `cwd` in the middle of the conversation,
though we may want to consider making each field optional, or
alternatively having a separate `Op` that mutates the `TurnContext`
associated with a `submission_loop()`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2329).
* #2345
* __->__ #2329
* #2343
* #2340
* #2338
This PR introduces `TurnContext`, which is designed to hold a set of
fields that should be constant for a turn of a conversation. Note that
the fields of `TurnContext` were previously governed by `Session`.
Ultimately, we want to enable users to change these values between turns
(changing model, approval policy, etc.), though in the current
implementation, the `TurnContext` is constant for the entire
conversation.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2345).
* #2345
* #2329
* __->__ #2343
* #2340
* #2338
I still see flakiness in
`test_shell_command_approval_triggers_elicitation()` on occasion where
`MockServer` claims it has not received all of its expected requests.
I recently introduced a similar type of test in #2264,
`test_codex_jsonrpc_conversation_flow()`, which I have not seen flake
(yet!), so this PR pulls over two things I did in that test:
- increased `worker_threads` from `2` to `4`
- added an assertion to make sure the `task_complete` notification is
received
Honestly, I'm still not sure why `MockServer` claims it sometimes does
not receive all its expected requests given that we assert that the
final `JSONRPCResponse` is read on the stream, but let's give this a
shot.
Assuming this fixes things, my hypothesis is that the increase in
`worker_threads` helps because perhaps there are async tasks in
`MockServer` that do not reliably complete fully when there are not
enough threads available? If that is correct, it seems like the test
would still be flaky, though perhaps with lower frequency?
I was looking at the implementation of `Session::get_writable_roots()`,
which did not seem right, as it was a copy of writable roots, which is
not guaranteed to be in sync with the `sandbox_policy` field.
I looked at who was calling `get_writable_roots()` and its only call
site was `apply_patch()` in `codex-rs/core/src/apply_patch.rs`, which
took the roots and forwarded them to `assess_patch_safety()` in
`safety.rs`. I updated `assess_patch_safety()` to take `sandbox_policy:
&SandboxPolicy` instead of `writable_roots: &[PathBuf]` (and replaced
`Session::get_writable_roots()` with `Session::get_sandbox_policy()`).
Within `safety.rs`, it was fairly easy to update
`is_write_patch_constrained_to_writable_paths()` to work with
`SandboxPolicy`, and in particular, it is far more accurate because, for
better or worse, `SandboxPolicy::get_writable_roots_with_cwd()` _returns
an empty vec_ for `SandboxPolicy::DangerFullAccess`, suggesting that
_nothing_ is writable when in reality _everything_ is writable. With
this PR, `is_write_patch_constrained_to_writable_paths()` now does the
right thing for each variant of `SandboxPolicy`.
I thought this would be the end of the story, but it turned out that
`test_writable_roots_constraint()` in `safety.rs` needed to be updated,
as well. In particular, the test was writing to
`std::env::current_dir()` instead of a `TempDir`, which I suspect was a
holdover from earlier when `SandboxPolicy::WorkspaceWrite` would always
make `TMPDIR` writable on macOS, which made it hard to write tests to
verify `SandboxPolicy` in `TMPDIR`. Fortunately, we now have
`exclude_tmpdir_env_var` as an option on
`SandboxPolicy::WorkspaceWrite`, so I was able to update the test to
preserve the existing behavior, but to no longer write to
`std::env::current_dir()`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2338).
* #2345
* #2329
* #2343
* #2340
* __->__ #2338
## Summary
We've been seeing a number of issues and reports with our synthetic
`apply_patch` tool, e.g. #802. Let's make this a real tool - in my
anecdotal testing, it's critical for GPT-OSS models, but I'd like to
make it the standard across GPT-5 and codex models as well.
## Testing
- [x] Tested locally
- [x] Integration test
Add env var to show the raw, unparsed command line under parsed
commands. When we have transcript mode we should show the full command
there, but this is useful for debugging.
This PR:
* Added the clippy.toml to configure allowable expect / unwrap usage in
tests
* Removed as many expect/allow lines as possible from tests
* moved a bunch of allows to expects where possible
Note: in integration tests, non `#[test]` helper functions are not
covered by this so we had to leave a few lingering `expect(expect_used`
checks around
It turns out that https://github.com/openai/codex/pull/2324 did not
quite work as intended. Chat's new idea is to have this catch-all "CI
results" job and update our branch protection rules to require this
instead.
When using codex-tui on a linux system I was unable to run `cargo
clippy` inside of codex due to:
```
[pid 3548377] socketpair(AF_UNIX, SOCK_SEQPACKET|SOCK_CLOEXEC, 0, <unfinished ...>
[pid 3548370] close(8 <unfinished ...>
[pid 3548377] <... socketpair resumed>0x7ffb97f4ed60) = -1 EPERM (Operation not permitted)
```
And
```
3611300 <... recvfrom resumed>0x708b8b5cffe0, 8, 0, NULL, NULL) = -1 EPERM (Operation not permitted)
```
This PR:
* Fixes a bug that disallowed AF_UNIX to allow it on `socket()`
* Adds recvfrom() to the syscall allow list, this should be fine since
we disable opening new sockets. But we should validate there is not a
open socket inheritance issue.
* Allow socketpair to be called for AF_UNIX
* Adds tests for AF_UNIX components
* All of which allows running `cargo clippy` within the sandbox on
linux, and possibly other tooling using a fork server model + AF_UNIX
comms.
we have a very unclear lifecycle for the chatwidget—this should only
have to be added in one place! but this fixes the "hanging commands"
issue where the active_exec_cell wasn't correctly cleared when commands
finished.
To repro w/o this PR:
1. prompt "run sleep 10"
2. once the command starts running, press <kbd>Esc</kbd>
3. prompt "run echo hi"
Expected:
```
✓ Completed
└ ⌨️ echo hi
codex
hi
```
Actual:
```
⚙︎ Working
└ ⌨️ echo hi
▌ Ask Codex to do anything
```
i.e. the "Working" never changes to "Completed".
The bug is fixed with this PR.
Our existing path filters for `rust-ci.yml`:
235987843c/.github/workflows/rust-ci.yml (L1-L11)
made it so that PRs that touch only `README.md` would not trigger those
builds, which is a problem because our branch protection rules are set
as follows:
<img width="1569" height="1883" alt="Screenshot 2025-08-14 at 4 45
59 PM"
src="https://github.com/user-attachments/assets/5a61f8cc-cdaf-4341-abda-7faa7b46dbd4"
/>
With the existing setup, a change to `README.md` would get stuck in
limbo because not all the CI jobs required to merge would get run. It
turns out that we need to "run" all the jobs, but make them no-ops when
the `codex-rs` and `.github` folders are untouched to get the best of
both worlds.
I asked chat how to fix this, as we want CI to be fast for
documentation-only changes. It had two suggestions:
- Use https://github.com/dorny/paths-filter or some other third-party
action.
- Write an inline Bash script to avoid a third-party dependency.
This PR takes the latter approach so that we are clear about what we're
running in CI.
The high-order bit on this PR is that it makes it so `sandbox.rs` tests
both Mac and Linux, as we introduce a general
`spawn_command_under_sandbox()` function with platform-specific
implementations for testing.
An important, and interesting, discovery in porting the test to Linux is
that (for reasons cited in the code comments), `/dev/shm` has to be
added to `writable_roots` on Linux in order for `multiprocessing.Lock`
to work there. Granting write access to `/dev/shm` comes with some
degree of risk, so we do not make this the default for Codex CLI.
Piggybacking on top of #2317, this moves the
`python_multiprocessing_lock_works` test yet again, moving
`codex-rs/core/tests/sandbox.rs` to `codex-rs/exec/tests/sandbox.rs`
because in `codex-rs/exec/tests` we can use `cargo_bin()` like so:
```
let codex_linux_sandbox_exe = assert_cmd::cargo::cargo_bin("codex-exec");
```
which is necessary so we can use `codex_linux_sandbox_exe` and therefore
`spawn_command_under_linux_sandbox` in an integration test.
This also moves `spawn_command_under_linux_sandbox()` out of `exec.rs`
and into `landlock.rs`, which makes things more consistent with
`seatbelt.rs` in `codex-core`.
For reference, https://github.com/openai/codex/pull/1808 is the PR that
made the change to Seatbelt to get this test to pass on Mac.
Previous to this PR, `codex-rs/core/tests/sandbox.rs` contained
integration tests that were specific to Seatbelt. This PR moves those
tests to `codex-rs/core/src/seatbelt.rs` and designates
`codex-rs/core/tests/sandbox.rs` to be used as the home for
cross-platform (well, Mac and Linux...) sandbox tests.
To start, this migrates
`python_multiprocessing_lock_works_under_seatbelt()` from #1823 to the
new `sandbox.rs` because this is the type of thing that should work on
both Mac _and_ Linux, though I still need to do some work to clean up
the test so it works on both platforms.
## Summary
- add a unit test to ensure the macOS seatbelt policy allows POSIX
semaphores
- add a macOS-only test that runs a Python multiprocessing Lock under
Seatbelt
## Testing
- `cargo test -p codex_core seatbelt_base_policy_allows_ipc_posix_sem
--no-fail-fast` (failed: failed to download from
`https://static.crates.io/crates/tokio-stream/0.1.17/download`)
- `cargo test -p codex_core seatbelt_base_policy_allows_ipc_posix_sem
--no-fail-fast --offline` (failed: attempting to make an HTTP request,
but --offline was specified)
- `cargo test --all-features --no-fail-fast --offline` (failed:
attempting to make an HTTP request, but --offline was specified)
- `just fmt` (failed: command not found: just)
- `just fix` (failed: command not found: just)
Ran tests locally to confirm it passes on master and failed before my
previous change
------
https://chatgpt.com/codex/tasks/task_i_6890f221e0a4833381cfb53e11499bcc
The "display format" of commands was sometimes producing incorrect
quoting like `echo foo '>' bar`, which is importantly different from the
actual command that was being run. This refactors ParsedCommand to have
a string in `cmd` instead of a vec, as a `vec` can't accurately capture
a full command.
instead of each shimmer needing to have its own animation thread, have
render_ref schedule a new frame if it wants one and coalesce to the
earliest next frame. this also makes the animations
frame-timing-independent, based on start time instead of frame count.
This improves handling of pasted content in the textarea. It's no longer
possible to partially delete a placeholder (e.g. by ^W or ^D), nor is it
possible to place the cursor inside a placeholder. Also, we now render
placeholders in a different color to make them more clearly
differentiated.
https://github.com/user-attachments/assets/2051b3c3-963d-4781-a610-3afee522ae29
#2291 made it so that `Session::new()` is on the critical path to
`Codex::spawn()`, which means it is on the hot path to CLI startup. This
refactors `Session::new()` to run a number of async tasks in parallel
that were previously run serially to try to reduce latency.
## Summary
Currently, we use request-time logic to determine the user_instructions
and environment_context messages. This means that neither of these
values can change over time as conversations go on. We want to add in
additional details here, so we're migrating these to save these messages
to the rollout file instead. This is simpler for the client, and allows
us to append additional environment_context messages to each turn if we
want
## Testing
- [x] Integration test coverage
- [x] Tested locally with a few turns, confirmed model could reference
environment context and cached token metrics were reasonably high
refactors HistoryCell to be a trait instead of an enum. Also collapse
the many "degenerate" HistoryCell enums which were just a store of lines
into a single PlainHistoryCell type.
The goal here is to allow more ways of rendering history cells (e.g.
expanded/collapsed/"live"), and I expect we will return to more varied
types of HistoryCell as we develop this area.
Historically, `Codex::spawn()` would create the instance of `Codex` and
enforce, by construction, that `Op::ConfigureSession` was the first `Op`
submitted via `submit()`. Then over in `submission_loop()`, it would
handle the case for taking the parameters of `Op::ConfigureSession` and
turning it into a `Session`.
This approach has two challenges from a state management perspective:
f968a1327a/codex-rs/core/src/codex.rs (L718)
- The local `sess` variable in `submission_loop()` has to be `mut` and
`Option<Arc<Session>>` because it is not invariant that a `Session` is
present for the lifetime of the loop, so there is a lot of logic to deal
with the case where `sess` is `None` (e.g., the `send_no_session_event`
function and all of its callsites).
- `submission_loop()` is written in such a way that
`Op::ConfigureSession` could be observed multiple times, but in
practice, it is only observed exactly once at the start of the loop.
In this PR, we try to simplify the state management by _removing_ the
`Op::ConfigureSession` enum variant and constructing the `Session` as
part of `Codex::spawn()` so that it can be passed to `submission_loop()`
as `Arc<Session>`. The original logic from the `Op::ConfigureSession`
has largely been moved to the new `Session::new()` constructor.
---
Incidentally, I also noticed that the handling of `Op::ConfigureSession`
can result in events being dispatched in addition to
`EventMsg::SessionConfigured`, as an `EventMsg::Error` is created for
every MCP initialization error, so it is important to preserve that
behavior:
f968a1327a/codex-rs/core/src/codex.rs (L901-L916)
Though admittedly, I believe this does not play nice with #2264, as
these error messages will likely be dispatched before the client has a
chance to call `addConversationListener`, so we likely need to make it
so `newConversation` automatically creates the subscription, but we must
also guarantee that the "ack" from `newConversation` is returned before
any other conversation-related notifications are sent so the client
knows what `conversation_id` to match on.
As `Session` needs a bit of work, it will make things easier to move
around if we can start by reducing the extent of its public API. This
makes all the fields private, though adds three `pub(crate)` getters.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2285).
* #2287
* #2286
* __->__ #2285
Sometimes COT is returns as text content instead of `ReasoningText`. We
should parse it but not serialize back on requests.
---------
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
This updates `CodexMessageProcessor` so that each notification it sends
for a `EventMsg` from a `CodexConversation` such that:
- The `params` always has an appropriate `conversationId` field.
- The `method` is now includes the name of the `EventMsg` type rather
than using `codex/event` as the `method` type for all notifications. (We
currently prefix the method name with `codex/event/`, but I think that
should go away once we formalize the notification schema in
`wire_format.rs`.)
As part of this, we update `test_codex_jsonrpc_conversation_flow()` to
verify that the `task_finished` notification has made it through the
system instead of sleeping for 5s and "hoping" the server finished
processing the task. Note we have seen some flakiness in some of our
other, similar integration tests, and I expect adding a similar check
would help in those cases, as well.
This introduces a new set of request types that our `codex mcp`
supports. Note that these do not conform to MCP tool calls so that
instead of having to send something like this:
```json
{
"jsonrpc": "2.0",
"method": "tools/call",
"id": 42,
"params": {
"name": "newConversation",
"arguments": {
"model": "gpt-5",
"approvalPolicy": "on-request"
}
}
}
```
we can send something like this:
```json
{
"jsonrpc": "2.0",
"method": "newConversation",
"id": 42,
"params": {
"model": "gpt-5",
"approvalPolicy": "on-request"
}
}
```
Admittedly, this new format is not a valid MCP tool call, but we are OK
with that right now. (That is, not everything we might want to request
of `codex mcp` is something that is appropriate for an autonomous agent
to do.)
To start, this introduces four request types:
- `newConversation`
- `sendUserMessage`
- `addConversationListener`
- `removeConversationListener`
The new `mcp-server/tests/codex_message_processor_flow.rs` shows how
these can be used.
The types are defined on the `CodexRequest` enum, so we introduce a new
`CodexMessageProcessor` that is responsible for dealing with requests
from this enum. The top-level `MessageProcessor` has been updated so
that when `process_request()` is called, it first checks whether the
request conforms to `CodexRequest` and dispatches it to
`CodexMessageProcessor` if so.
Note that I also decided to use `camelCase` for the on-the-wire format,
as that seems to be the convention for MCP.
For the moment, the new protocol is defined in `wire_format.rs` within
the `mcp-server` crate, but in a subsequent PR, I will probably move it
to its own crate to ensure the protocol has minimal dependencies and
that we can codegen a schema from it.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2264).
* #2278
* __->__ #2264
## Summary
- enable reasoning for any model slug starting with `codex-`
- provide default model info for `codex-*` slugs
- test that codex models are detected and support reasoning
## Testing
- `just fmt`
- `just fix` *(fails: E0658 `let` expressions in this position are
unstable)*
- `cargo test --all-features` *(fails: E0658 `let` expressions in this
position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_689d13f8705483208a6ed21c076868e1
I put this PR together because I noticed I have to wait quite a bit
longer on my PRs since we added
https://github.com/openai/codex/pull/2242 to catch more build issues.
I think we should think about reigning in our use of create features,
but this should be good enough to speed things up for now.
## Summary
Ripgrep is our preferred tool for file search. When users install via
`brew install codex`, it's automatically installed as a dependency. We
want to ensure that users running via an npm install also have this
tool! Microsoft has already solved this problem for VS Code - let's not
reinvent the wheel.
This approach of appending to the PATH directly might be a bit
heavy-handed, but feels reasonably robust to a variety of environment
concerns. Open to thoughts on better approaches here!
## Testing
- [x] confirmed this import approach works with `node -e "const { rgPath
} = require('@vscode/ripgrep'); require('child_process').spawn(rgPath,
['--version'], { stdio: 'inherit' })"`
- [x] Ran codex.js locally with `rg` uninstalled, asked it to run `which
rg`. Output below:
```
⚡ Ran command which rg; echo $?
⎿ /Users/dylan.hurd/code/dh--npm-rg/node_modules/@vscode/ripgrep/bin/rg
0
codex
Re-running to confirm the path and exit code.
- Path: `/Users/dylan.hurd/code/dh--npm-rg/node_modules/@vscode/ripgrep/bin/rg`
- Exit code: `0`
```
This PR does two things because after I got deep into the first one I
started pulling on the thread to the second:
- Makes `ConversationManager` the place where all in-memory
conversations are created and stored. Previously, `MessageProcessor` in
the `codex-mcp-server` crate was doing this via its `session_map`, but
this is something that should be done in `codex-core`.
- It unwinds the `ctrl_c: tokio::sync::Notify` that was threaded
throughout our code. I think this made sense at one time, but now that
we handle Ctrl-C within the TUI and have a proper `Op::Interrupt` event,
I don't think this was quite right, so I removed it. For `codex exec`
and `codex proto`, we now use `tokio::signal::ctrl_c()` directly, but we
no longer make `Notify` a field of `Codex` or `CodexConversation`.
Changes of note:
- Adds the files `conversation_manager.rs` and `codex_conversation.rs`
to `codex-core`.
- `Codex` and `CodexSpawnOk` are no longer exported from `codex-core`:
other crates must use `CodexConversation` instead (which is created via
`ConversationManager`).
- `core/src/codex_wrapper.rs` has been deleted in favor of
`ConversationManager`.
- `ConversationManager::new_conversation()` returns `NewConversation`,
which is in line with the `new_conversation` tool we want to add to the
MCP server. Note `NewConversation` includes `SessionConfiguredEvent`, so
we eliminate checks in cases like `codex-rs/core/tests/client.rs` to
verify `SessionConfiguredEvent` is the first event because that is now
internal to `ConversationManager`.
- Quite a bit of code was deleted from
`codex-rs/mcp-server/src/message_processor.rs` since it no longer has to
manage multiple conversations itself: it goes through
`ConversationManager` instead.
- `core/tests/live_agent.rs` has been deleted because I had to update a
bunch of tests and all the tests in here were ignored, and I don't think
anyone ever ran them, so this was just technical debt, at this point.
- Removed `notify_on_sigint()` from `util.rs` (and in a follow-up, I
hope to refactor the blandly-named `util.rs` into more descriptive
files).
- In general, I started replacing local variables named `codex` as
`conversation`, where appropriate, though admittedly I didn't do it
through all the integration tests because that would have added a lot of
noise to this PR.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2240).
* #2264
* #2263
* __->__ #2240
## Summary
- support Ctrl-b and Ctrl-f to move the cursor left and right in the
chat composer text area
- test Ctrl-b/Ctrl-f cursor movements
## Testing
- `just fmt`
- `just fix` *(fails: `let` expressions in this position are unstable)*
- `cargo test --all-features` *(fails: `let` expressions in this
position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_689cbd1d7968832e876fff169891e486
## Summary
- ensure CLI help uses `codex` as program name regardless of binary
filename
## Testing
- `just fmt`
- `just fix` *(fails: `let` expressions in this position are unstable)*
- `cargo test --all-features` *(fails: `let` expressions in this
position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_689bd5a731188320814dcbbc546ce22a
Wait for newlines, then render markdown on a line by line basis. Word wrap it for the current terminal size and then spit it out line by line into the UI. Also adds tests and fixes some UI regressions.
## Summary
- Display "Update plan" instead of "Update to do" when the plan is
updated in the TUI
## Testing
- `just fmt`
- `just fix` *(fails: E0658 `let` expressions in this position are
unstable)*
- `cargo test --all-features` *(fails: E0658 `let` expressions in this
position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_6897f78fc5908322be488f02db42a5b9
## Summary
In #1939 we overhauled a lot of our prompt. This was largely good, but
we're seeing some specific points of confusion from the model! This
prompt update attempts to address 3 of them:
- Enforcing the use of `ripgrep`, which is bundled as a dependency when
installed with homebrew. We should do the same on node (in progress)
- Explicit guidance on reading files in chunks.
- Slight adjustment to networking sandbox language. `enabled` /
`restricted` is anecdotally less confusing to the model and requires
less reasoning to escalate for approval.
We are going to continue iterating on shell usage and tools, but this
restores us to best practices for current model snapshots.
## Testing
- [x] evals
- [x] local testing
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [clap_complete](https://github.com/clap-rs/clap) from 4.5.55 to
4.5.56.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="9cec1007ac"><code>9cec100</code></a>
chore: Release</li>
<li><a
href="00e72e06f4"><code>00e72e0</code></a>
docs: Update changelog</li>
<li><a
href="c7848ff6fc"><code>c7848ff</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/6094">#6094</a>
from epage/home</li>
<li><a
href="60184fb76a"><code>60184fb</code></a>
feat(complete): Expand ~ in native completions</li>
<li><a
href="09969d3c1a"><code>09969d3</code></a>
chore(deps): Update Rust Stable to v1.89 (<a
href="https://redirect.github.com/clap-rs/clap/issues/6093">#6093</a>)</li>
<li><a
href="520beb5ec2"><code>520beb5</code></a>
chore: Release</li>
<li><a
href="2bd8ab3c00"><code>2bd8ab3</code></a>
docs: Update changelog</li>
<li><a
href="220875b585"><code>220875b</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/6091">#6091</a>
from epage/possible</li>
<li><a
href="e5eb6c9d84"><code>e5eb6c9</code></a>
fix(help): Integrate 'Possible Values:' into 'Arg::help'</li>
<li><a
href="594a771030"><code>594a771</code></a>
refactor(help): Make empty tracking more consistent</li>
<li>Additional commits viewable in <a
href="https://github.com/clap-rs/clap/compare/clap_complete-v4.5.55...clap_complete-v4.5.56">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
[//]: # (dependabot-start)
⚠️ **Dependabot is rebasing this PR** ⚠️
Rebasing might not happen immediately, so don't worry if this takes some
time.
Note: if you make any changes to this PR yourself, they will take
precedence over the rebase.
---
[//]: # (dependabot-end)
Bumps [clap](https://github.com/clap-rs/clap) from 4.5.41 to 4.5.43.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/clap-rs/clap/releases">clap's
releases</a>.</em></p>
<blockquote>
<h2>v4.5.43</h2>
<h2>[4.5.43] - 2025-08-06</h2>
<h3>Fixes</h3>
<ul>
<li><em>(help)</em> In long help, list Possible Values before defaults,
rather than after, for a more consistent look</li>
</ul>
<h2>v4.5.42</h2>
<h2>[4.5.42] - 2025-07-30</h2>
<h3>Fixes</h3>
<ul>
<li>Include subcommand visible long aliases in <code>--help</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/clap-rs/clap/blob/master/CHANGELOG.md">clap's
changelog</a>.</em></p>
<blockquote>
<h2>[4.5.43] - 2025-08-06</h2>
<h3>Fixes</h3>
<ul>
<li><em>(help)</em> In long help, list Possible Values before defaults,
rather than after, for a more consistent look</li>
</ul>
<h2>[4.5.42] - 2025-07-30</h2>
<h3>Fixes</h3>
<ul>
<li>Include subcommand visible long aliases in <code>--help</code></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="c4105bd90c"><code>c4105bd</code></a>
chore: Release</li>
<li><a
href="a029b20be6"><code>a029b20</code></a>
docs: Update changelog</li>
<li><a
href="cf15d48b59"><code>cf15d48</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/5893">#5893</a>
from 8LWXpg/patch-2</li>
<li><a
href="7e54542de9"><code>7e54542</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/5892">#5892</a>
from 8LWXpg/patch-1</li>
<li><a
href="6ffc88f8c9"><code>6ffc88f</code></a>
fix(complete): Check if help string is empty</li>
<li><a
href="7d8470ed9c"><code>7d8470e</code></a>
fix(complete): Fix single quote escaping in PowerShell</li>
<li><a
href="eadcc8f66c"><code>eadcc8f</code></a>
chore: Release</li>
<li><a
href="7ce0f7bea3"><code>7ce0f7b</code></a>
docs: Update changelog</li>
<li><a
href="fea7c5487b"><code>fea7c54</code></a>
Merge pull request <a
href="https://redirect.github.com/clap-rs/clap/issues/5888">#5888</a>
from epage/tut</li>
<li><a
href="c297ddd56e"><code>c297ddd</code></a>
docs(tutorial): Experiment with a flat layout</li>
<li>Additional commits viewable in <a
href="https://github.com/clap-rs/clap/compare/clap_complete-v4.5.41...clap_complete-v4.5.43">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [toml](https://github.com/toml-rs/toml) from 0.9.4 to 0.9.5.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="bd21148c49"><code>bd21148</code></a>
chore: Release</li>
<li><a
href="ff1cb9a263"><code>ff1cb9a</code></a>
docs: Update changelog</li>
<li><a
href="39dd8b6422"><code>39dd8b6</code></a>
fix(parser): Improve bad quote error messages (<a
href="https://redirect.github.com/toml-rs/toml/issues/1014">#1014</a>)</li>
<li><a
href="137338eb26"><code>137338e</code></a>
chore(deps): Update Rust crate serde_json to v1.0.142 (<a
href="https://redirect.github.com/toml-rs/toml/issues/1022">#1022</a>)</li>
<li><a
href="d5b8c8a94e"><code>d5b8c8a</code></a>
fix(parser): Improve missing-open-quote errors</li>
<li><a
href="ce91354fc7"><code>ce91354</code></a>
fix(parser): Don't treat trailing quotes as separate items</li>
<li><a
href="8f424edd08"><code>8f424ed</code></a>
fix(parser): Conjoin more values in unquoted string errors</li>
<li><a
href="2b9a81ae79"><code>2b9a81a</code></a>
fix(parser): Reduce float false positives</li>
<li><a
href="f6538413bb"><code>f653841</code></a>
fix(parser): Reduce float/bool false positives</li>
<li><a
href="f4864ef34b"><code>f4864ef</code></a>
test(parser): Add case for missing start quote</li>
<li>See full diff in <a
href="https://github.com/toml-rs/toml/compare/toml-v0.9.4...toml-v0.9.5">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Moves `use codex_core::protocol::EventMsg` inside the block annotated
with `#[cfg(debug_assertions)]` since that was the only place in the
file that was using it.
This eliminates the `warning: unused import:` when building with `cargo
build --release` in `cargo-rs/tui`.
Note this was not breaking CI because we do not build release builds on
CI since we're impatient :P
## Summary
Our current approach to prompt caching is fragile! The current approach
works, but we are planning to update to a more resilient system (storing
them in the rollout file). Let's start adding some integration tests to
ensure stability while we migrate it.
## Testing
- [x] These are the tests 😎
## Summary
GPT-OSS and `gpt-5-mini` have training artifacts that cause the models
to occasionally use `applypatch` instead of `apply_patch`. I think
long-term we'll want to provide `apply_patch` as a first class tool, but
for now let's silently handle this case to avoid hurting model
performance
## Testing
- [x] Added unit test
Right now, every time an exec ends, we emit it to history which makes it
immutable. In order to be able to update or merge successive tool calls
(which will be useful after https://github.com/openai/codex/pull/2095),
we need to retain it as the active cell.
This also changes the cell to contain the metadata necessary to render
it so it can be updated rather than baking in the final text lines when
the cell is created.
Part 1: https://github.com/openai/codex/pull/2095
Part 3: https://github.com/openai/codex/pull/2110
## Summary
#1865 added `AskForApproval::OnRequest`, but missed adding it to our
custom struct in `mcp-server`. This adds the missing configuration
## Testing
- [x] confirmed locally
# Note for reviewers
The bulk of this PR is in in the new file, `parse_command.rs`. This file
is designed to be written TDD and implemented with Codex. Do not worry
about reviewing the code, just review the unit tests (if you want). If
any cases are missing, we'll add more tests and have Codex fix them.
I think the best approach will be to land and iterate. I have some
follow-ups I want to do after this lands. The next PR after this will
let us merge (and dedupe) multiple sequential cells of the same such as
multiple read commands. The deduping will also be important because the
model often reads the same file multiple times in a row in chunks
===
This PR formats common commands like reading, formatting, testing, etc
more nicely:
It tries to extract things like file names, tests and falls back to the
cmd if it doesn't. It also only shows stdout/err if the command failed.
<img width="770" height="238" alt="CleanShot 2025-08-09 at 16 05 15"
src="https://github.com/user-attachments/assets/0ead179a-8910-486b-aa3d-7d26264d751e"
/>
<img width="348" height="158" alt="CleanShot 2025-08-09 at 16 05 32"
src="https://github.com/user-attachments/assets/4302681b-5e87-4ff3-85b4-0252c6c485a9"
/>
<img width="834" height="324" alt="CleanShot 2025-08-09 at 16 05 56 2"
src="https://github.com/user-attachments/assets/09fb3517-7bd6-40f6-a126-4172106b700f"
/>
Part 2: https://github.com/openai/codex/pull/2097
Part 3: https://github.com/openai/codex/pull/2110
This PR updates ChatWidget to ensure that when AgentMessage,
AgentReasoning, or AgentReasoningRawContent events arrive without any
streamed deltas, the final text from the event is rendered before the
stream is finalized. Previously, these handlers ignored the event text
in such cases, relying solely on prior deltas.
<img width="603" height="189" alt="image"
src="https://github.com/user-attachments/assets/868516f2-7963-4603-9af4-adb1b1eda61e"
/>
Bumps [tokio-util](https://github.com/tokio-rs/tokio) from 0.7.15 to
0.7.16.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="cf6b50a3fd"><code>cf6b50a</code></a>
chore: prepare tokio-util v0.7.16 (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7507">#7507</a>)</li>
<li><a
href="416e36b0df"><code>416e36b</code></a>
task: stabilise <code>JoinMap</code> (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7075">#7075</a>)</li>
<li><a
href="9741c90f9f"><code>9741c90</code></a>
sync: document cancel safety on <code>SetOnce::wait</code> (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7506">#7506</a>)</li>
<li><a
href="4e3f17bce3"><code>4e3f17b</code></a>
codec: also apply capacity to read buffer in
<code>Framed::with_capacity</code> (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7500">#7500</a>)</li>
<li><a
href="86cbf81e15"><code>86cbf81</code></a>
Merge 'tokio-1.47.1' into 'master'</li>
<li><a
href="be8ee45b3f"><code>be8ee45</code></a>
chore: prepare Tokio v1.47.1 (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7504">#7504</a>)</li>
<li><a
href="d9b19166cd"><code>d9b1916</code></a>
Merge 'tokio-1.43.2' into 'tokio-1.47.x' (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7503">#7503</a>)</li>
<li><a
href="db8edc620f"><code>db8edc6</code></a>
chore: prepare Tokio v1.43.2 (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7502">#7502</a>)</li>
<li><a
href="e47565b086"><code>e47565b</code></a>
blocking: clarify that spawn_blocking is aborted if not yet started (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7501">#7501</a>)</li>
<li><a
href="4730984d66"><code>4730984</code></a>
readme: add 1.47 as LTS release (<a
href="https://redirect.github.com/tokio-rs/tokio/issues/7497">#7497</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/tokio-rs/tokio/compare/tokio-util-0.7.15...tokio-util-0.7.16">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
- I had a recent conversation where the one-liner showed using 11M
tokens! But looking into it 10M were cached. So I looked into it and I
think we had a regression here. ->
- Use blended total tokens for chat composer usage display
- Compute remaining context using tokens_in_context_window helper
------
https://chatgpt.com/codex/tasks/task_i_68981a16c0a4832cbf416017390930e5
Users on "headless" machines, such as WSL users, are understandable
having trouble authenticating successfully. To date, I have been
providing one-off user support on issues such as
https://github.com/openai/codex/issues/2000, but we need a more detailed
explanation that we can link to so that users can self-serve. This PR
aims to provide detailed information that we can link to in response to
user issues going forward.
That said, it would also be helpful if we employed heuristics to detect
this issue at runtime, and/or we should just link to these docs as part
of the `codex login` flow.
This improves the release process by introducing
`scripts/publish_to_npm.py` to automate publishing to npm (modulo the
human 2fac step).
As part of this, it updates `.github/workflows/rust-release.yml` to
create the artifact for npm using `npm pack`.
And finally, while it is long overdue, this memorializes the release
process in `docs/release_management.md`.
## Summary
- allow Esc to interrupt the current session when a task is running
- document Esc as an interrupt key in status indicator
## Testing
- `just fmt`
- `just fix` *(fails: E0658 `let` expressions in this position are
unstable)*
- `cargo test --all-features` *(fails: E0658 `let` expressions in this
position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_689698cf605883208f57b0317ff6a303
## Summary
Allow tui conversations to resume after the client fails out of retries.
I tested this with exec / mocked api failures as well, and it appears to
be fine. But happy to add an exec integration test as well!
## Testing
- [x] Added integration test
- [x] Tested locally
## Summary
From codex-cli 😁
`-s/--sandbox` now correctly affects sandbox mode.
What changed
- In `codex-rs/exec/src/cli.rs`:
- Added `value_enum` to the `--sandbox` flag so Clap parses enum values
into `
SandboxModeCliArg`.
- This ensures values like `-s read-only`, `-s workspace-write`, and `-s
dange
r-full-access` are recognized and propagated.
Why this fixes it
- The enum already derives `ValueEnum`, but without `#[arg(value_enum)]`
Clap ma
y not map the string into the enum, leaving the option ineffective at
runtime. W
ith `value_enum`, `sandbox_mode` is parsed and then converted to
`SandboxMode` i
n `run_main`, which feeds into `ConfigOverrides` and ultimately into the
effecti
ve `sandbox_policy`.
This deletes the bulk of the `codex-cli` folder and eliminates the logic
that builds the TypeScript code and bundles it into the release.
Since this PR modifies `.github/workflows/rust-release.yml`, to test
changes to the release process, I locally commented out all of the "is
this commit on upstream `main`" checks in
`scripts/create_github_release.sh` and ran:
```
./codex-rs/scripts/create_github_release.sh 0.20.0-alpha.4
```
Which kicked off:
https://github.com/openai/codex/actions/runs/16842085113
And the release artifacts appear legit!
https://github.com/openai/codex/releases/tag/rust-v0.20.0-alpha.4
Historically, the release process for the npm module has been:
- I run `codex-rs/scripts/create_github_release.sh` to kick off a
release for the native artifacts.
- I wait until it is done.
- I run `codex-cli/scripts/stage_rust_release.py` to build the npm
release locally
- I run `npm publish` from my laptop
It has been a longstanding issue to move the npm build to CI. I may
still have to do the `npm publish` manually because it requires 2fac
with `npm`, though I assume we can work that out later.
Note I asked Codex to make these updates, and while they look pretty
good to me, I'm not 100% certain, but let's just merge this and I'll
kick off another alpha build and we'll see what happens?
To date, the build scripts in `codex-cli` still supported building the
old TypeScript version of the Codex CLI to give Windows users something
they can run, but we are just going to have them use the Rust version
like everyone else, so:
- updates `codex-cli/bin/codex.js` so that we run the native binary or
throw if the target platform/arch is not supported (no more conditional
usage based on `CODEX_RUST`, `use-native` file, etc.)
- drops the `--native` flag from `codex-cli/scripts/stage_release.sh`
and updates all the code paths to behave as if `--native` were passed
(i.e., it is the only way to run it now)
Tested this by running:
```
./codex-cli/scripts/stage_rust_release.py --release-version 0.20.0-alpha.2
```
Release builds are taking awhile and part of the reason that we are
building binaries that we are not really using. Adding Windows binaries
into releases (https://github.com/openai/codex/pull/2035) slows things
down, so we need to get some time back.
- `codex-exec` is basically a standalone `codex exec` that we were
offering because it's a bit smaller as it does not include all the bits
to power the TUI. We were using it in our experimental GitHub Action, so
this PR updates the Action to use `codex exec` instead.
- `codex-linux-sandbox` was a helper binary for the TypeScript version
of the CLI, but I am about to axe that, so we don't need this either.
If we decide to bring `codex-exec` back at some point, we should use a
separate instances so we can build it in parallel with `codex`. (I think
if we had beefier build machines, this wouldn't be so bad, but that's
not the case with the default runners from GitHub.)
We should stop shipping the old TypeScript CLI to Windows users. I did
some light testing of the Rust CLI on Windows in `cmd.exe` and it works
better than I expected!
This pull request implements a fix from #2000, as well as fixed an
additional problem with path lengths on windows that prevents the login
from displaying.
---------
Co-authored-by: Michael Bolin <bolinfest@gmail.com>
Co-authored-by: Michael Bolin <mbolin@openai.com>
## Summary
- fix typo in usage limit banner text
- update error message tests
## Testing
- `just fmt`
- `RUSTC_BOOTSTRAP=1 just fix` *(fails: `let` expressions in this
position are unstable)*
- `RUSTC_BOOTSTRAP=1 cargo test --all-features` *(fails: `let`
expressions in this position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_689610fc1fe4832081bdd1118779b60b
We wait until we have an entire newline, then format it with markdown and stream in to the UI. This reduces time to first token but is the right thing to do with our current rendering model IMO. Also lets us add word wrapping!
Uses this rough strategy for authentication:
```
if auth.json
if auth.json.API_KEY is NULL # new auth
CHAT
else # old auth
if plus or pro or team
CHAT
else
API_KEY
else OPENAI_API_KEY
```
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1970).
* __->__ #1971
* #1970
* #1966
* #1965
* #1962
There are two valid ways to create an instance of `CodexAuth`:
`from_api_key()` and `from_codex_home()`. Now both are static methods of
`CodexAuth` and are listed first in the implementation.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1966).
* #1971
* #1970
* __->__ #1966
* #1965
* #1962
`CodexAuth::new()` was the first method listed in `CodexAuth`, but it is
only meant to be used by tests. Rename it to
`create_dummy_chatgpt_auth_for_testing()` and move it to the end of the
implementation.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1962).
* #1971
* #1970
* #1966
* #1965
* __->__ #1962
## Summary
In collaboration with @gpeal: upgrade the onboarding flow, and persist
user settings.
---------
Co-authored-by: Gabriel Peal <gabriel@openai.com>
Trying to use `core` as the default has been "too clever." Users can
always take responsibility for controlling the env without this setting
at all by specifying the `env` they use when calling `codex` in the
first place.
See https://github.com/openai/codex/issues/1249.
## Summary
- add a pulsing dot loader before the shimmering `Working` label in the
status indicator widget and include a small test asserting the spinner
character is rendered
- also fix a small bug in the ran command header by adding a space
between the ⚡ and `Ran command`
https://github.com/user-attachments/assets/6768c9d2-e094-49cb-ad51-44bcac10aa6f
## Testing
- `just fmt`
- `just fix` *(failed: E0658 `let` expressions in core/src/client.rs)*
- `cargo test --all-features` *(failed: E0658 `let` expressions in
core/src/client.rs)*
------
https://chatgpt.com/codex/tasks/task_i_68941bffdb948322b0f4190bc9dbe7f6
---------
Co-authored-by: aibrahim-oai <aibrahim@openai.com>
- `/status` renders
```
signed in with chatgpt
login: example@example.com
plan: plus
```
- Setup for using this info in a few more places.
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
## Summary
- support `codex logout` via new subcommand and helper that removes the
stored `auth.json`
- expose a `logout` function in `codex-login` and test it
- add `/logout` slash command in the TUI; command list is filtered when
not logged in and the handler deletes `auth.json` then exits
## Testing
- `just fix` *(fails: failed to get `diffy` from crates.io)*
- `cargo test --all-features` *(fails: failed to get `diffy` from
crates.io)*
------
https://chatgpt.com/codex/tasks/task_i_68945c3facac832ca83d48499716fb51
- For absolute, use non-cached input + output.
- For estimating what % of the model's context window is used, we need
to account for reasoning output tokens from prior turns being dropped
from the context window. We approximate this here by subtracting
reasoning output tokens from the total. This will be off for the current
turn and pending function calls. We can improve it later.
This will make @ more discoverable (even though it is currently not
super useful, IMO it should be used to bring files into context from
outside CWD)
---------
Co-authored-by: Gabriel Peal <gpeal@users.noreply.github.com>
Replaces the `include_default_writable_roots` option on
`sandbox_workspace_write` (that defaulted to `true`, which was slightly
weird/annoying) with `exclude_tmpdir_env_var`, which defaults to
`false`.
Though perhaps more importantly `/tmp` is now enabled by default as part
of `sandbox_mode = "workspace-write"`, though `exclude_slash_tmp =
false` can be used to disable this.
Cursor wasn't moving when inserting a file, resulting in being not at
the end of the filename when inserting the file.
This fixes it by moving the cursor to the end of the file + one trailing
space.
Example screenshot after selecting a file when typing `@`
<img width="823" height="268" alt="image"
src="https://github.com/user-attachments/assets/ec6e3741-e1ba-4752-89d2-11f14a2bd69f"
/>
This sets up the scaffolding and basic flow for a TUI onboarding
experience. It covers sign in with ChatGPT, env auth, as well as some
safety guidance.
Next up:
1. Replace the git warning screen
2. Use this to configure default approval/sandbox modes
Note the shimmer flashes are from me slicing the video, not jank.
https://github.com/user-attachments/assets/0fbe3479-fdde-41f3-87fb-a7a83ab895b8
## Summary
We have been returning `exit code 0` from the apply patch command when
writes fail, which causes our `exec` harness to pass back confusing
messages to the model. Instead, we should loudly fail so that the
harness and the model can handle these errors appropriately.
Also adds a test to confirm this behavior.
## Testing
- `cargo test -p codex-apply-patch`
- Arguably a bugfix as previously CTRL-Z didn't do anything.
- Only in TUI mode for now. This may make sense in other modes... to be
researched.
- The TUI runs the terminal in raw mode and the signals arrive as key
events, so we handle CTRL-Z as a key event just like CTRL-C.
- Not adding UI for it as a composer redesign is coming, and we can just
add it then.
- We should follow with CTRL-Z a second time doing the native terminal
action.
- Updates the launch screen to:
```
>_ You are using OpenAI Codex in ~/code/codex/codex-rs
Try one of the following commands to get started:
1. /init - Create an AGENTS.md file with instructions for Codex
2. /status - Show current session configuration and token usage
3. /compact - Compact the chat history
4. /new - Start a new chat
```
- These aren't the perfect commands, but as more land soon we can
update.
- We should also add logic later to make /init only show when there's no
existing AGENTS.md.
- Majorly need to iterate on copy.
<img width="905" height="769" alt="image"
src="https://github.com/user-attachments/assets/5912939e-fb0e-4e76-94ff-785261e2d6ee"
/>
## Summary
- Prioritize provider-specific API keys over default Codex auth when
building requests
- Add test to ensure provider env var auth overrides default auth
## Testing
- `just fmt`
- `just fix` *(fails: `let` expressions in this position are unstable)*
- `cargo test --all-features` *(fails: `let` expressions in this
position are unstable)*
------
https://chatgpt.com/codex/tasks/task_i_68926a104f7483208f2c8fd36763e0e3
The docs and code do not match. It turns out the docs are "right" in
they are what we have been meaning to support, so this PR updates the
code:
ae88b69b09/README.md (L298-L302)
Support for `instructions.md` is a holdover from the TypeScript CLI, so
we are just going to drop support for it altogether rather than maintain
it in perpetuity.
## Summary
Forgot to remove this in #1869 last night! Too much of a performance hit
on the main thread. We can bring it back via an async thread on startup.
## Summary
Includes a new user message in the api payload which provides useful
environment context for the model, so it knows about things like the
current working directory and the sandbox.
## Testing
Updated unit tests
## Summary
Have seen these tests flaking over the course of today on different
boxes. `wiremock` seems to be generally written with tokio/threads in
mind but based on the weird panics from the tests, let's see if this
helps.
- Added a `/status` command, which will be useful when we update the
home screen to print less status.
- Moved `create_config_summary_entries` to common since it's used in a
few places.
- Noticed we inconsistently had periods in slash command descriptions
and just removed them everywhere.
- Noticed the diff description was overflowing so made it shorter.
This PR attempts to break `codex-rust-review.md` into sections so that
it is easier to consume.
It also adds a healthy new section on "Assertions in Tests" that has
been on my mind for awhile.
This script attempts to verify that:
- You have no local, uncommitted changes.
- You are on `main`
- The commit you are on exists on `main` also exists on the origin
`https://github.com/openai/codex`, i.e., it is not just a commit you
have pushed to your local version of `main`
As part of this, try to print better error message if/when these
conditions are violated.
Hardcoding to `prerelease: true` is a holdover from before we had
migrated to the Rust CLI for releases and decided on how we were doing
version numbers.
To date, I have had to change the release status from "prerelease" to
"actual release" manually through the GitHub Releases web page. This is
a semi-serious problem because I've discovered that it messes up
Homebrew's automation if the version number _looks_ like a real release
but turns out to be a prerelease. The release potentially gets skipped
from being published on Homebrew, so it's important to set the value
correctly from the start.
I verified that `steps.release_name.outputs.name` does not include the
`rust-v` prefix from the tag name.
https://github.com/openai/codex/pull/1868 is a related fix that was in
flight simultaenously, but after talking to @easong-openai, this:
- logs instead of renders for `BackgroundEvent`
- logs for `TurnDiff`
- renders for `PatchApplyEnd`
## Summary
A split-up PR of #1763 , stacked on top of a tools refactor #1858 to
make the change clearer. From the previous summary:
> Let's try something new: tell the model about the sandbox, and let it
decide when it will need to break the sandbox. Some local testing
suggests that it works pretty well with zero iteration on the prompt!
## Testing
- [x] Added unit tests
- [x] Tested locally and it appears to work smoothly!
## Summary
In an effort to make tools easier to work with and more configurable,
I'm introducing `ToolConfig` and updating `Prompt` to take in a general
list of Tools. I think this is simpler and better for a few reasons:
- We can easily assemble tools from various sources (our own harness,
mcp servers, etc.) and we can consolidate the logic for constructing the
logic in one place that is separate from serialization.
- client.rs no longer needs arbitrary config values, it just takes in a
list of tools to serialize
A hefty portion of the PR is now updating our conversion of
`mcp_types::Tool` to `OpenAITool`, but considering that @bolinfest
accurately called this out as a TODO long ago, I think it's time we
tackled it.
## Testing
- [x] Experimented locally, no changes, as expected
- [x] Added additional unit tests
- [x] Responded to rust-review
Previous to this PR, `ShutdownComplete` was not being handled correctly
in `codex exec`, so it always ended up printing the following to stderr:
```
ERROR codex_exec: Error receiving event: InternalAgentDied
```
Because we were not breaking out of the loop for `ShutdownComplete`,
inevitably `codex.next_event()` would get called again and
`rx_event.recv()` would fail and the error would get mapped to
`InternalAgentDied`:
ea7d3f27bd/codex-rs/core/src/codex.rs (L190-L197)
For reference, https://github.com/openai/codex/pull/1647 introduced the
`ShutdownComplete` variant.
## Summary
Escalating out of sandbox is (almost always) not going to fix
long-running commands timing out - therefore we should just pass the
failure back to the model instead of asking the user to re-run a command
that took a long time anyway.
## Testing
- [x] Ran locally with a timeout and confirmed this worked as expected
This PR started as an investigation with the goal of eliminating the use
of `unsafe { std::env::set_var() }` in `ollama/src/client.rs`, as
setting environment variables in a multithreaded context is indeed
unsafe and these tests were observed to be flaky, as a result.
Though as I dug deeper into the issue, I discovered that the logic for
instantiating `OllamaClient` under test scenarios was not quite right.
In this PR, I aimed to:
- share more code between the two creation codepaths,
`try_from_oss_provider()` and `try_from_provider_with_base_url()`
- use the values from `Config` when setting up Ollama, as we have
various mechanisms for overriding config values, so we should be sure
that we are always using the ultimate `Config` for things such as the
`ModelProviderInfo` associated with the `oss` id
Once this was in place,
`OllamaClient::try_from_provider_with_base_url()` could be used in unit
tests for `OllamaClient` so it was possible to create a properly
configured client without having to set environment variables.
I ended up force-pushing https://github.com/openai/codex/pull/1848
because CI jobs were not being triggered after updating the PR on
GitHub, so this spelling error sneaked through.
This adds support for easily running Codex backed by a local Ollama
instance running our new open source models. See
https://github.com/openai/gpt-oss for details.
If you pass in `--oss` you'll be prompted to install/launch ollama, and
it will automatically download the 20b model and attempt to use it.
We'll likely want to expand this with some options later to make the
experience smoother for users who can't run the 20b or want to run the
120b.
Co-authored-by: Michael Bolin <mbolin@openai.com>
https://github.com/openai/codex/pull/1835 has some messed up history.
This adds support for streaming chat completions, which is useful for ollama. We should probably take a very skeptical eye to the code introduced in this PR.
---------
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
To date, we have a number of hardcoded OpenAI model slug checks spread
throughout the codebase, which makes it hard to audit the various
special cases for each model. To mitigate this issue, this PR introduces
the idea of a `ModelFamily` that has fields to represent the existing
special cases, such as `supports_reasoning_summaries` and
`uses_local_shell_tool`.
There is a `find_family_for_model()` function that maps the raw model
slug to a `ModelFamily`. This function hardcodes all the knowledge about
the special attributes for each model. This PR then replaces the
hardcoded model name checks with checks against a `ModelFamily`.
Note `ModelFamily` is now available as `Config::model_family`. We should
ultimately remove `Config::model` in favor of
`Config::model_family::slug`.
Stream models thoughts and responses instead of waiting for the whole
thing to come through. Very rough right now, but I'm making the risk call to push through.
## Summary
Our recent change in #1737 can sometimes lead to the model confusing
AGENTS.md context as part of the message. But a little prompting and
formatting can help fix this!
## Testing
- Ran locally with a few different prompts to verify the model
behaves well.
- Updated unit tests
Previously, `codex exec` was printing `Warning: no file to write last
message to` as a warning to stderr even though `--output-last-message`
was not specified, which is wrong. This fixes the code and changes
`handle_last_message()` so that it is only called when
`last_message_path` is `Some`.
Bumps [serde_json](https://github.com/serde-rs/json) from 1.0.141 to
1.0.142.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/serde-rs/json/releases">serde_json's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.142</h2>
<ul>
<li>impl Default for &Value (<a
href="https://redirect.github.com/serde-rs/json/issues/1265">#1265</a>,
thanks <a
href="https://github.com/aatifsyed"><code>@aatifsyed</code></a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="1731167cd5"><code>1731167</code></a>
Release 1.0.142</li>
<li><a
href="e51c81450a"><code>e51c814</code></a>
Touch up PR 1265</li>
<li><a
href="84abbdb613"><code>84abbdb</code></a>
Merge pull request <a
href="https://redirect.github.com/serde-rs/json/issues/1265">#1265</a>
from aatifsyed/master</li>
<li><a
href="9206cc0150"><code>9206cc0</code></a>
feat: impl Default for &Value</li>
<li>See full diff in <a
href="https://github.com/serde-rs/json/compare/v1.0.141...v1.0.142">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [toml](https://github.com/toml-rs/toml) from 0.9.2 to 0.9.4.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="2126e6af51"><code>2126e6a</code></a>
chore: Release</li>
<li><a
href="fa2100a888"><code>fa2100a</code></a>
docs: Update changelog</li>
<li><a
href="0c75bbd6f7"><code>0c75bbd</code></a>
feat(toml): Expose DeInteger/DeFloat as_str/radix (<a
href="https://redirect.github.com/toml-rs/toml/issues/1021">#1021</a>)</li>
<li><a
href="e3d64dff47"><code>e3d64df</code></a>
feat(toml): Expose DeFloat::as_str</li>
<li><a
href="ffdd211033"><code>ffdd211</code></a>
feat(toml): Expose DeInteger::as_str/radix</li>
<li><a
href="9e7adcc7fa"><code>9e7adcc</code></a>
docs(readme): Fix links to crates (<a
href="https://redirect.github.com/toml-rs/toml/issues/1020">#1020</a>)</li>
<li><a
href="73d04e20b5"><code>73d04e2</code></a>
docs(readme): Fix links to crates</li>
<li><a
href="da667e8a7d"><code>da667e8</code></a>
chore: Release</li>
<li><a
href="b1327fbe7c"><code>b1327fb</code></a>
docs: Update changelog</li>
<li><a
href="fb5346827e"><code>fb53468</code></a>
fix(toml): Don't enable std in toml_writer (<a
href="https://redirect.github.com/toml-rs/toml/issues/1019">#1019</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/toml-rs/toml/compare/toml-v0.9.2...toml-v0.9.4">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Added:
* C-m for newline (not sure if this is actually treated differently to
Enter, but tui-textarea handles it and it doesn't hurt)
* C-d to delete one char forwards (same as Del)
* A-bksp to delete backwards one word
* A-arrows to navigate by word
The existing prompt is really bad. As a low-hanging fruit, let's correct
the apply_patch instructions - this helps smaller models successfully
apply patches.
Allows users to set their experimental_instructions_file in configs.
For example the below enables experimental instructions when running
`codex -p foo`.
```
[profiles.foo]
experimental_instructions_file = "/Users/foo/.codex/prompt.md"
```
# Testing
- ✅ Running against a profile with experimental_instructions_file works.
- ✅ Running against a profile without experimental_instructions_file
works.
- ✅ Running against no profile with experimental_instructions_file
works.
- ✅ Running against no profile without experimental_instructions_file
works.
This lets us show an accumulating diff across all patches in a turn.
Refer to the docs for TurnDiffTracker for implementation details.
There are multiple ways this could have been done and this felt like the
right tradeoff between reliability and completeness:
*Pros*
* It will pick up all changes to files that the model touched including
if they prettier or another command that updates them.
* It will not pick up changes made by the user or other agents to files
it didn't modify.
*Cons*
* It will pick up changes that the user made to a file that the model
also touched
* It will not pick up changes to codegen or files that were not modified
with apply_patch
## Summary
Users frequently complain about re-approving commands that have failed
for non-sandbox reasons. We can't diagnose with complete accuracy which
errors happened because of a sandbox failure, but we can start to
eliminate some common simple cases.
This PR captures the most common case I've seen, which is a `command not
found` error.
## Testing
- [x] Added unit tests
- [x] Ran a few cases locally
This replaces tui-textarea with a custom textarea component.
Key differences:
1. wrapped lines
2. better unicode handling
3. uses the native terminal cursor
This should perhaps be spun out into its own separate crate at some
point, but for now it's convenient to have it in-tree.
The following test script fails in the codex sandbox:
```
import multiprocessing
from multiprocessing import Lock, Process
def f(lock):
with lock:
print("Lock acquired in child process")
if __name__ == '__main__':
lock = Lock()
p = Process(target=f, args=(lock,))
p.start()
p.join()
```
with
```
Traceback (most recent call last):
File "/Users/david.hao/code/codex/codex-rs/cli/test.py", line 9, in <module>
lock = Lock()
^^^^^^
File "/Users/david.hao/.local/share/uv/python/cpython-3.12.9-macos-aarch64-none/lib/python3.12/multiprocessing/context.py", line 68, in Lock
return Lock(ctx=self.get_context())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/david.hao/.local/share/uv/python/cpython-3.12.9-macos-aarch64-none/lib/python3.12/multiprocessing/synchronize.py", line 169, in __init__
SemLock.__init__(self, SEMAPHORE, 1, 1, ctx=ctx)
File "/Users/david.hao/.local/share/uv/python/cpython-3.12.9-macos-aarch64-none/lib/python3.12/multiprocessing/synchronize.py", line 57, in __init__
sl = self._semlock = _multiprocessing.SemLock(
^^^^^^^^^^^^^^^^^^^^^^^^^
PermissionError: [Errno 1] Operation not permitted
```
After reading, adding this line to the sandbox configs fixes things -
MacOS multiprocessing appears to use sem_lock(), which opens an IPC
which is considered a disk write even though no file is created. I
interrogated ChatGPT about whether it's okay to loosen, and my
impression after reading is that it is, although would appreciate a
close look
Breadcrumb: You can run `cargo run -- debug seatbelt --full-auto <cmd>`
to test the sandbox
To make `--full-auto` safer, this PR updates the Seatbelt policy so that
a `SandboxPolicy` with a `writable_root` that contains a `.git/`
_directory_ will make `.git/` _read-only_ (though as a follow-up, we
should also consider the case where `.git` is a _file_ with a `gitdir:
/path/to/actual/repo/.git` entry that should also be protected).
The two major changes in this PR:
- Updating `SandboxPolicy::get_writable_roots_with_cwd()` to return a
`Vec<WritableRoot>` instead of a `Vec<PathBuf>` where a `WritableRoot`
can specify a list of read-only subpaths.
- Updating `create_seatbelt_command_args()` to honor the read-only
subpaths in `WritableRoot`.
The logic to update the policy is a fairly straightforward update to
`create_seatbelt_command_args()`, but perhaps the more interesting part
of this PR is the introduction of an integration test in
`tests/sandbox.rs`. Leveraging the new API in #1785, we test
`SandboxPolicy` under various conditions, including ones where `$TMPDIR`
is not readable, which is critical for verifying the new behavior.
To ensure that Codex can run its own tests, e.g.:
```
just codex debug seatbelt --full-auto -- cargo test if_git_repo_is_writable_root_then_dot_git_folder_is_read_only
```
I had to introduce the use of `CODEX_SANDBOX=sandbox`, which is
comparable to how `CODEX_SANDBOX_NETWORK_DISABLED=1` was already being
used.
Adding a comparable change for Landlock will be done in a subsequent PR.
Introduce conversation.create handler (handle_create_conversation) and
wire it in MessageProcessor.
Stack:
Top: #1783
Bottom: #1784
---------
Co-authored-by: Gabriel Peal <gpeal@users.noreply.github.com>
Without this change, it is challenging to create integration tests to
verify that the folders not included in `writable_roots` in
`SandboxPolicy::WorkspaceWrite` are read-only because, by default,
`get_writable_roots_with_cwd()` includes `TMPDIR`, which is where most
integrationt
tests do their work.
This introduces a `use_exact_writable_roots` option to disable the
default
includes returned by `get_writable_roots_with_cwd()`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1785).
* #1765
* __->__ #1785
## Summary
- stream command stdout as `ExecCommandStdout` events
- forward streamed stdout to clients and ignore in human output
processor
- adjust call sites for new streaming API
This fixes a bug in insert_history_lines where writing
`Line::From(vec!["A".bold(), "B".into()])` would write "B" as bold,
because "B" didn't explicitly subtract bold.
- MCP server: add send-user-message tool to send user input to a running
Codex session
- Added an integration tests for the happy and sad paths
Changes:
• Add tool definition and schema.
• Expose tool in capabilities.
• Route and handle tool requests with validation.
• Tests for success, bad UUID, and missing session.
follow‑ups
• Listen path not implemented yet; the tool is present but marked “don’t
use yet” in code comments.
• Session run flag reset: clear running_session_id_set appropriately
after turn completion/errors.
This is the third PR in a stack.
Stack:
Final: #1686
Intermediate: #1751
First: #1750
- Add operation to summarize the context so far.
- The operation runs a compact task that summarizes the context.
- The operation clear the previous context to free the context window
- The operation didn't use `run_task` to avoid corrupting the session
- Add /compact in the tui
https://github.com/user-attachments/assets/e06c24e5-dcfb-4806-934a-564d425a919c
- Expose mcp_protocol from mcp-server for reuse in tests and callers.
- In MessageProcessor, detect structured ToolCallRequestParams in
tools/call and forward to a new handler.
- Add handle_new_tool_calls scaffold (returns error for now).
- Test helper: add send_send_user_message_tool_call to McpProcess to
send ConversationSendMessage requests;
This is the second PR in a stack.
Stack:
Final: #1686
Intermediate: #1751
First: #1750
# Summary
- Align MCP server responses with mcp_types by emitting [CallToolResult,
RequestId] instead of an object.
Update send-message result to a tagged enum: Ok or Error { message }.
# Why
Protocol compliance with current MCP schema.
# Tests
- Updated assertions in mcp_protocol.rs for create/stream/send/list and
error cases.
This is the first PR in a stack.
Stack:
Final: #1686
Intermediate: #1751
First: #1750
This delays the call to insert_history_lines until a redraw is
happening. Crucially, the new lines are inserted _after the viewport is
resized_. This results in fewer stray blank lines below the viewport
when modals (e.g. user approval) are closed.
when we enabled KKP in https://github.com/openai/codex/pull/1743, we
started receiving keyup events, but didn't expect them anywhere in our
code. for now, just don't dispatch them at all.
At 550 lines, `exec.rs` was a bit large. In particular, I found it hard
to locate the Seatbelt-related code quickly without a file with
`seatbelt` in the name, so this refactors things so:
- `spawn_command_under_seatbelt()` and dependent code moves to a new
`seatbelt.rs` file
- `spawn_child_async()` and dependent code moves to a new `spawn.rs`
file
This is a follow-up to https://github.com/openai/codex/pull/1705, as
that PR inadvertently lost the logic where `PatchApplyBeginEvent` and
`PatchApplyEndEvent` events were sent when patches were auto-approved.
Though as part of this fix, I believe this also makes an important
safety fix to `assess_patch_safety()`, as there was a case that returned
`SandboxType::None`, which arguably is the thing we were trying to avoid
in #1705.
On a high level, we want there to be only one codepath where
`apply_patch` happens, which should be unified with the patch to run
`exec`, in general, so that sandboxing is applied consistently for both
cases.
Prior to this change, `apply_patch()` in `core` would either:
* exit early, delegating to `exec()` to shell out to `apply_patch` using
the appropriate sandbox
* proceed to run the logic for `apply_patch` in memory
549846b29a/codex-rs/core/src/apply_patch.rs (L61-L63)
In this implementation, only the latter would dispatch
`PatchApplyBeginEvent` and `PatchApplyEndEvent`, though the former would
dispatch `ExecCommandBeginEvent` and `ExecCommandEndEvent` for the
`apply_patch` call (or, more specifically, the `codex
--codex-run-as-apply-patch PATCH` call).
To unify things in this PR, we:
* Eliminate the back half of the `apply_patch()` function, and instead
have it also return with `DelegateToExec`, though we add an extra field
to the return value, `user_explicitly_approved_this_action`.
* In `codex.rs` where we process `DelegateToExec`, we use
`SandboxType::None` when `user_explicitly_approved_this_action` is
`true`. This means **we no longer run the apply_patch logic in memory**,
as we always `exec()`. (Note this is what allowed us to delete so much
code in `apply_patch.rs`.)
* In `codex.rs`, we further update `notify_exec_command_begin()` and
`notify_exec_command_end()` to take additional fields to determine what
type of notification to send: `ExecCommand` or `PatchApply`.
Admittedly, this PR also drops some of the functionality about giving
the user the opportunity to expand the set of writable roots as part of
approving the `apply_patch` command. I'm not sure how much that was
used, and we should probably rethink how that works as we are currently
tidying up the protocol to the TUI, in general.
this fixes a couple of panics that would happen when trying to render
something larger than the terminal, or insert history lines when the top
of the viewport is at y=0.
the git tests were failing on my local machine due to gpg signing config
in my ~/.gitconfig. tests should not be affected by ~/.gitconfig, so
configure them to ignore it.
Simplify and improve many UI elements.
* Remove all-around borders in most places. These interact badly with
terminal resizing and look heavy. Prefer left-side-only borders.
* Make the viewport adjust to the size of its contents.
* <kbd>/</kbd> and <kbd>@</kbd> autocomplete boxes appear below the
prompt, instead of above it.
* Restyle the keyboard shortcut hints & move them to the left.
* Restyle the approval dialog.
* Use synchronized rendering to avoid flashing during rerenders.
https://github.com/user-attachments/assets/96f044af-283b-411c-b7fc-5e6b8a433c20
<img width="1117" height="858" alt="Screenshot 2025-07-30 at 5 29 20 PM"
src="https://github.com/user-attachments/assets/0cc0af77-8396-429b-b6ee-9feaaccdbee7"
/>
The goal of this change is to try an experiment where we try to get AI
to take on more of the code review load. The idea is that once you
believe your PR is ready for review, please add the `codex-rust-review`
label (as opposed to the `codex-review` label).
Admittedly the corresponding prompt currently represents my personal
biases in terms of code review, but we should massage it over time to
represent the team's preferences.
Proof of concept for a resizable viewport.
The general approach here is to duplicate the `Terminal` struct from
ratatui, but with our own logic. This is a "light fork" in that we are
still using all the base ratatui functions (`Buffer`, `Widget` and so
on), but we're doing our own bookkeeping at the top level to determine
where to draw everything.
This approach could use improvement—e.g, when the window is resized to a
smaller size, if the UI wraps, we don't correctly clear out the
artifacts from wrapping. This is possible with a little work (i.e.
tracking what parts of our UI would have been wrapped), but this
behavior is at least at par with the existing behavior.
https://github.com/user-attachments/assets/4eb17689-09fd-4daa-8315-c7ebc654986d
cc @joshka who might have Thoughts™
Building on the work of https://github.com/openai/codex/pull/1702, this
changes how a shell call to `apply_patch` is handled.
Previously, a shell call to `apply_patch` was always handled in-process,
never leveraging a sandbox. To determine whether the `apply_patch`
operation could be auto-approved, the
`is_write_patch_constrained_to_writable_paths()` function would check if
all the paths listed in the paths were writable. If so, the agent would
apply the changes listed in the patch.
Unfortunately, this approach afforded a loophole: symlinks!
* For a soft link, we could fix this issue by tracing the link and
checking whether the target is in the set of writable paths, however...
* ...For a hard link, things are not as simple. We can run `stat FILE`
to see if the number of links is greater than 1, but then we would have
to do something potentially expensive like `find . -inum <inode_number>`
to find the other paths for `FILE`. Further, even if this worked, this
approach runs the risk of a
[TOCTOU](https://en.wikipedia.org/wiki/Time-of-check_to_time-of-use)
race condition, so it is not robust.
The solution, implemented in this PR, is to take the virtual execution
of the `apply_patch` CLI into an _actual_ execution using `codex
--codex-run-as-apply-patch PATCH`, which we can run under the sandbox
the user specified, just like any other `shell` call.
This, of course, assumes that the sandbox prevents writing through
symlinks as a mechanism to write to folders that are not in the writable
set configured by the sandbox. I verified this by testing the following
on both Mac and Linux:
```shell
#!/usr/bin/env bash
set -euo pipefail
# Can running a command in SANDBOX_DIR write a file in EXPLOIT_DIR?
# Codex is run in SANDBOX_DIR, so writes should be constrianed to this directory.
SANDBOX_DIR=$(mktemp -d -p "$HOME" sandboxtesttemp.XXXXXX)
# EXPLOIT_DIR is outside of SANDBOX_DIR, so let's see if we can write to it.
EXPLOIT_DIR=$(mktemp -d -p "$HOME" sandboxtesttemp.XXXXXX)
echo "SANDBOX_DIR: $SANDBOX_DIR"
echo "EXPLOIT_DIR: $EXPLOIT_DIR"
cleanup() {
# Only remove if it looks sane and still exists
[[ -n "${SANDBOX_DIR:-}" && -d "$SANDBOX_DIR" ]] && rm -rf -- "$SANDBOX_DIR"
[[ -n "${EXPLOIT_DIR:-}" && -d "$EXPLOIT_DIR" ]] && rm -rf -- "$EXPLOIT_DIR"
}
trap cleanup EXIT
echo "I am the original content" > "${EXPLOIT_DIR}/original.txt"
# Drop the -s to test hard links.
ln -s "${EXPLOIT_DIR}/original.txt" "${SANDBOX_DIR}/link-to-original.txt"
cat "${SANDBOX_DIR}/link-to-original.txt"
if [[ "$(uname)" == "Linux" ]]; then
SANDBOX_SUBCOMMAND=landlock
else
SANDBOX_SUBCOMMAND=seatbelt
fi
# Attempt the exploit
cd "${SANDBOX_DIR}"
codex debug "${SANDBOX_SUBCOMMAND}" bash -lc "echo pwned > ./link-to-original.txt" || true
cat "${EXPLOIT_DIR}/original.txt"
```
Admittedly, this change merits a proper integration test, but I think I
will have to do that in a follow-up PR.
Adds a `CodexAuth` type that encapsulates information about available
auth modes and logic for refreshing the token.
Changes `Responses` API to send requests to different endpoints based on
the auth type.
Updates login_with_chatgpt to support API-less mode and skip the key
exchange.
This adds a tool the model can call to update a plan. The tool doesn't
actually _do_ anything but it gives clients a chance to read and render
the structured plan. We will likely iterate on the prompt and tools
exposed for planning over time.
see
[discussion](https://github.com/rhysd/tui-textarea/issues/51#issuecomment-3021191712),
it's surprising that ^U behaves this way. IMO the undo/redo
functionality in tui-textarea isn't good enough to be worth preserving,
but if we do bring it back it should probably be on C-z / C-S-z / C-y.
Perhaps there was an intention to make the login screen prettier, but it
feels quite silly right now to just have a screen that says "press q",
so replace it with something that lets the user directly login without
having to quit the app.
<img width="1283" height="635" alt="Screenshot 2025-07-28 at 2 54 05 PM"
src="https://github.com/user-attachments/assets/f19e5595-6ef9-4a2d-b409-aa61b30d3628"
/>
## Summary
Per the [latest MCP
spec](https://modelcontextprotocol.io/specification/2025-06-18/basic#meta),
the `_meta` field is reserved for metadata. In the [Typescript
Schema](0695a497eb/schema/2025-06-18/schema.ts (L37-L40)),
`progressToken` is defined as a value to be attached to subsequent
notifications for that request.
The
[CallToolRequestParams](0695a497eb/schema/2025-06-18/schema.ts (L806-L817))
extends this definition but overwrites the params field. This ambiguity
makes our generated type definitions tricky, so I'm going to skip
`progressToken` field for now and just send back the `requestId`
instead.
In a future PR, we can clarify, update our `generate_mcp_types.py`
script, and update our progressToken logic accordingly.
## Testing
- [x] Added unit tests
- [x] Manually tested with mcp client
(Hopefully) temporary solution to the invisible approvals problem -
prints commands to history when they need approval and then also prints
the result of the approval. In the near future we should be able to do
some fancy stuff with updating commands before writing them to permanent
history.
Also, ctr-c while in the approval modal now acts as esc (aborts command)
and puts the TUI in the state where one additional ctr-c will exit.
This is a straight refactor, moving apply-patch-related code from
`codex.rs` and into the new `apply_patch.rs` file. The only "logical"
change is inlining `#[allow(clippy::unwrap_used)]` instead of declaring
`#![allow(clippy::unwrap_used)]` at the top of the file (which is
currently the case in `codex.rs`).
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1703).
* #1705
* __->__ #1703
* #1702
* #1698
* #1697
This introduces some special behavior to the CLIs that are using the
`codex-arg0` crate where if `arg1` is `--codex-run-as-apply-patch`, then
it will run as if `apply_patch arg2` were invoked. This is important
because it means we can do things like:
```
SANDBOX_TYPE=landlock # or seatbelt for macOS
codex debug "${SANDBOX_TYPE}" -- codex --codex-run-as-apply-patch PATCH
```
which gives us a way to run `apply_patch` while ensuring it adheres to
the sandbox the user specified.
While it would be nice to use the `arg0` trick like we are currently
doing for `codex-linux-sandbox`, there is no way to specify the `arg0`
for the underlying command when running under `/usr/bin/sandbox-exec`,
so it will not work for us in this case.
Admittedly, we could have also supported this via a custom environment
variable (e.g., `CODEX_ARG0`), but since environment variables are
inherited by child processes, that seemed like a potentially leakier
abstraction.
This change, as well as our existing reliance on checking `arg0`, place
additional requirements on those who include `codex-core`. Its
`README.md` has been updated to reflect this.
While we could have just added an `apply-patch` subcommand to the
`codex` multitool CLI, that would not be sufficient for the standalone
`codex-exec` CLI, which is something that we distribute as part of our
GitHub releases for those who know they will not be using the TUI and
therefore prefer to use a slightly smaller executable:
https://github.com/openai/codex/releases/tag/rust-v0.10.0
To that end, this PR adds an integration test to ensure that the
`--codex-run-as-apply-patch` option works with the standalone
`codex-exec` CLI.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1702).
* #1705
* #1703
* __->__ #1702
* #1698
* #1697
The overall idea here is: skip ratatui for writing into scrollback,
because its primitives are wrong. We want to render full lines of text,
that will be wrapped natively by the terminal, and which we never plan
to update using ratatui (so the `Buffer` struct is overhead and in fact
an inhibition).
Instead, we use ANSI scrolling regions (link reference doc to come).
Essentially, we:
1. Define a scrolling region that extends from the top of the prompt
area all the way to the top of scrollback
2. Scroll that region up by N < (screen_height - viewport_height) lines,
in this PR N=1
3. Put our cursor at the top of the newly empty region
4. Print out our new text like normal
The terminal interactions here (write_spans and its dependencies) are
mostly extracted from ratatui.
Most of the time, we expect the `String` returned by
`serde_json::to_string()` to have extra capacity, so `push('\n')` is
unlikely to allocate, which seems cheaper than an extra `write(2)` call,
on average?
This update replaces the previous ratatui history widget with an
append-only log so that the terminal can handle text selection and
scrolling. It also disables streaming responses, which we'll do our best
to bring back in a later PR. It also adds a small summary of token use
after the TUI exits.
Currently, codex on start shows the value for the approval policy as
name of
[AskForApproval](2437a8d17a/codex-rs/core/src/protocol.rs (L128))
enum, which differs from
[approval_policy](2437a8d17a/codex-rs/config.md (approval_policy))
config values.
E.g. "untrusted" becomes "UnlessTrusted", "on-failure" -> "OnFailure",
"never" -> "Never".
This PR changes render names of the approval policy to match with
configuration values.
This PR updates `is_known_safe_command()` to account for "safe
operators" to expand the set of commands that can be run without
approval. This concept existed in the TypeScript CLI, and we are
[finally!] porting it to the Rust one:
c9e2def494/codex-cli/src/approvals.ts (L531-L541)
The idea is that if we have `EXPR1 SAFE_OP EXPR2` and `EXPR1` and
`EXPR2` are considered safe independently, then `EXPR1 SAFE_OP EXPR2`
should be considered safe. Currently, `SAFE_OP` includes `&&`, `||`,
`;`, and `|`.
In the TypeScript implementation, we relied on
https://www.npmjs.com/package/shell-quote to parse the string of Bash,
as it could provide a "lightweight" parse tree, parsing `'beep || boop >
/byte'` as:
```
[ 'beep', { op: '||' }, 'boop', { op: '>' }, '/byte' ]
```
Though in this PR, we introduce the use of
https://crates.io/crates/tree-sitter-bash for parsing (which
incidentally we were already using in
[`codex-apply-patch`](c9e2def494/codex-rs/apply-patch/Cargo.toml (L18))),
which gives us a richer parse tree. (Incidentally, if you have never
played with tree-sitter, try the
[playground](https://tree-sitter.github.io/tree-sitter/7-playground.html)
and select **Bash** from the dropdown to see how it parses various
expressions.)
As a concrete example, prior to this change, our implementation of
`is_known_safe_command()` could verify things like:
```
["bash", "-lc", "grep -R \"Cargo.toml\" -n"]
```
but not:
```
["bash", "-lc", "grep -R \"Cargo.toml\" -n || true"]
```
With this change, the version with `|| true` is also accepted.
Admittedly, this PR does not expand the safety check to support
subshells, so it would reject, e.g. `bash -lc 'ls || (pwd && echo hi)'`,
but that can be addressed in a subsequent PR.
`nl` is a line-numbering tool that should be on the _trusted _ list, as
there is nothing concerning on https://gtfobins.github.io/gtfobins/nl/
that would merit exclusion.
`true` and `false` are also safe, though not particularly useful given
how `is_known_safe_command()` works today, but that will change with
https://github.com/openai/codex/pull/1668.
Because of a quirk of how implementation tests work in Rust, we had a
number of `#[allow(dead_code)]` annotations that were misleading because
the functions _were_ being used, just not by all integration tests in a
`tests/` folder, so when compiling the test that did not use the
function, clippy would complain that it was unused.
This fixes things by create a "test_support" crate under the `tests/`
folder that is imported as a dev dependency for the respective crate.
# Summary
- Writing effective evals for codex sessions requires context of the
overall repository state at the moment the session began
- This change adds this metadata (git repository, branch, commit hash)
to the top of the rollout of the session (if available - if not it
doesn't add anything)
- Currently, this is only effective on a clean working tree, as we can't
track uncommitted/untracked changes with the current metadata set.
Ideally in the future we may want to track unclean changes somehow, or
perhaps prompt the user to stash or commit them.
# Testing
- Added unit tests
- `cargo test && cargo clippy --tests && cargo fmt -- --config
imports_granularity=Item`
### Resulting Rollout
<img width="1243" height="127" alt="Screenshot 2025-07-17 at 1 50 00 PM"
src="https://github.com/user-attachments/assets/68108941-f015-45b2-985c-ea315ce05415"
/>
Bumps [toml](https://github.com/toml-rs/toml) from 0.9.1 to 0.9.2.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="c28f9ac30f"><code>c28f9ac</code></a>
chore: Release</li>
<li><a
href="f3a2299148"><code>f3a2299</code></a>
docs: Update changelog</li>
<li><a
href="69f09d3093"><code>69f09d3</code></a>
fix(lex): Don't loop over ')' for forever (<a
href="https://redirect.github.com/toml-rs/toml/issues/1003">#1003</a>)</li>
<li><a
href="cc68ae4f42"><code>cc68ae4</code></a>
fix(lex): Don't loop over ')' for forever</li>
<li>See full diff in <a
href="https://github.com/toml-rs/toml/compare/toml-v0.9.1...toml-v0.9.2">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [tree-sitter](https://github.com/tree-sitter/tree-sitter) from
0.25.6 to 0.25.8.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="f2f197b6b2"><code>f2f197b</code></a>
0.25.8</li>
<li><a
href="8bb33f7d8c"><code>8bb33f7</code></a>
perf: reorder conditional operands</li>
<li><a
href="6f944de32f"><code>6f944de</code></a>
fix(generate): propagate node types error</li>
<li><a
href="c15938532d"><code>c159385</code></a>
0.25.7</li>
<li><a
href="94b55bfcdc"><code>94b55bf</code></a>
perf: reorder expensive conditional operand</li>
<li><a
href="bcb30f7951"><code>bcb30f7</code></a>
fix(generate): use topological sort for subtype map</li>
<li><a
href="3bd8f7df8e"><code>3bd8f7d</code></a>
perf: More efficient computation of used symbols</li>
<li><a
href="d7529c3265"><code>d7529c3</code></a>
perf: reserve <code>Vec</code> capacities where appropriate</li>
<li><a
href="bf4217f0ff"><code>bf4217f</code></a>
fix(web): wasm export paths</li>
<li><a
href="bb7b339ae2"><code>bb7b339</code></a>
Fix 'extra' field generation for node-types.json</li>
<li>Additional commits viewable in <a
href="https://github.com/tree-sitter/tree-sitter/compare/v0.25.6...v0.25.8">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [rand](https://github.com/rust-random/rand) from 0.9.1 to 0.9.2.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/rust-random/rand/blob/master/CHANGELOG.md">rand's
changelog</a>.</em></p>
<blockquote>
<h2>[0.9.2 — 2025-07-20]</h2>
<h3>Deprecated</h3>
<ul>
<li>Deprecate <code>rand::rngs::mock</code> module and
<code>StepRng</code> generator (<a
href="https://redirect.github.com/rust-random/rand/issues/1634">#1634</a>)</li>
</ul>
<h3>Additions</h3>
<ul>
<li>Enable <code>WeightedIndex<usize></code> (de)serialization (<a
href="https://redirect.github.com/rust-random/rand/issues/1646">#1646</a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="d3dd415705"><code>d3dd415</code></a>
Prepare rand_core 0.9.2 (<a
href="https://redirect.github.com/rust-random/rand/issues/1605">#1605</a>)</li>
<li><a
href="99fabd20e9"><code>99fabd2</code></a>
Prepare rand_core 0.9.2</li>
<li><a
href="c7fe1c43b5"><code>c7fe1c4</code></a>
rand: re-export <code>rand_core</code> (<a
href="https://redirect.github.com/rust-random/rand/issues/1604">#1604</a>)</li>
<li><a
href="db2b1e0bb4"><code>db2b1e0</code></a>
rand: re-export <code>rand_core</code></li>
<li><a
href="ee1d96f9f5"><code>ee1d96f</code></a>
rand_core: implement reborrow for <code>UnwrapMut</code> (<a
href="https://redirect.github.com/rust-random/rand/issues/1595">#1595</a>)</li>
<li><a
href="e0eb2ee0fc"><code>e0eb2ee</code></a>
rand_core: implement reborrow for <code>UnwrapMut</code></li>
<li><a
href="975f602f5d"><code>975f602</code></a>
fixup clippy 1.85 warnings</li>
<li><a
href="775b05be1b"><code>775b05b</code></a>
Relax <code>Sized</code> requirements for blanket impls (<a
href="https://redirect.github.com/rust-random/rand/issues/1593">#1593</a>)</li>
<li>See full diff in <a
href="https://github.com/rust-random/rand/compare/rand_core-0.9.1...rand_core-0.9.2">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
1. Emit call_id to exec approval elicitations for mcp client convenience
2. Remove the `-retry` from the call id for the same reason as above but
upstream the reset behavior to the mcp client
Always store the entire conversation history.
Request encrypted COT when not storing Responses.
Send entire input context instead of sending previous_response_id
This PR adds a `load_dotenv()` helper function to the `codex-common`
crate that is available when the `cli` feature is enabled. The function
uses [`dotenvy`](https://crates.io/crates/dotenvy) to update the
environment from:
- `$CODEX_HOME/.env`
- `$(pwd)/.env`
To test:
- ran `printenv OPENAI_API_KEY` to verify the env var exists in my
environment
- ran `just codex exec hello` to verify the CLI uses my `OPENAI_API_KEY`
- ran `unset OPENAI_API_KEY`
- ran `just codex exec hello` again and got **ERROR: Missing environment
variable: `OPENAI_API_KEY`**, as expected
- created `~/.codex/.env` and added `OPENAI_API_KEY=sk-proj-...` (also
ran `chmod 400 ~/.codex/.env` for good measure)
- ran `just codex exec hello` again and it worked, verifying it picked
up `OPENAI_API_KEY` from `~/.codex/.env`
Note this functionality was available in the TypeScript CLI:
https://github.com/openai/codex/pull/122 and was recently requested over
on https://github.com/openai/codex/issues/1262#issuecomment-3093203551.
I noticed that releases have taken longer and longer to build.
Originally, I think I did `--all-targets` to be confident that
everything builds cleanly, but that's really the job of CI that runs on
`main`, so we're spending a lot of time in `rust-release.yml` for not
that much additional signal.
Some users have reported issues where child processes are not cleaned up
after Codex exits (e.g., https://github.com/openai/codex/issues/1570).
This is generally a tricky issue on operating systems: if a parent
process receives `SIGKILL`, then it terminates immediately and cannot
communicate with the child.
**It only helps on Linux**, but this PR introduces the use of `prctl(2)`
so that if the parent process dies, `SIGTERM` will be delivered to the
child process. Whereas previously, I believe that if Codex spawned a
long-running process (like `tsc --watch`) and the Codex process received
`SIGKILL`, the `tsc --watch` process would be reparented to the init
process and would never be killed. Now with the use of `prctl(2)`, the
`tsc --watch` process should receive `SIGTERM` in that scenario.
We still need to come up with a solution for macOS. I've started to look
at `launchd`, but I'm researching a number of options.
1. Added an elicitation for `approve-patch` which is very similar to
`approve-exec`.
2. Extracted both elicitations to their own files to prevent
`codex_tool_runner` from blowing up in size.
## Summary
Adds a new mcp tool call, `codex-reply`, so we can continue existing
sessions. This is a first draft and does not yet support sessions from
previous processes.
## Testing
- [x] tested with mcp client
This PR introduces a single integration test for `cargo mcp`, though it
also introduces a number of reusable components so that it should be
easier to introduce more integration tests going forward.
The new test is introduced in `codex-rs/mcp-server/tests/elicitation.rs`
and the reusable pieces are in `codex-rs/mcp-server/tests/common`.
The test itself verifies new functionality around elicitations
introduced in https://github.com/openai/codex/pull/1623 (and the fix
introduced in https://github.com/openai/codex/pull/1629) by doing the
following:
- starts a mock model provider with canned responses for
`/v1/chat/completions`
- starts the MCP server with a `config.toml` to use that model provider
(and `approval_policy = "untrusted"`)
- sends the `codex` tool call which causes the mock model provider to
request a shell call for `git init`
- the MCP server sends an elicitation to the client to approve the
request
- the client replies to the elicitation with `"approved"`
- the MCP server runs the command and re-samples the model, getting a
`"finish_reason": "stop"`
- in turn, the MCP server sends the final response to the original
`codex` tool call
- verifies that `git init` ran as expected
To test:
```
cargo test shell_command_approval_triggers_elicitation
```
In writing this test, I discovered that `ExecApprovalResponse` does not
conform to `ElicitResult`, so I added a TODO to fix that, since I think
that should be updated in a separate PR. As it stands, this PR does not
update any business logic, though it does make a number of members of
the `mcp-server` crate `pub` so they can be used in the test.
One additional learning from this PR is that
`std::process::Command::cargo_bin()` from the `assert_cmd` trait is only
available for `std::process::Command`, but we really want to use
`tokio::process::Command` so that everything is async and we can
leverage utilities like `tokio::time::timeout()`. The trick I came up
with was to use `cargo_bin()` to locate the program, and then to use
`std::process::Command::get_program()` when constructing the
`tokio::process::Command`.
This updates the MCP server so that if it receives an
`ExecApprovalRequest` from the `Codex` session, it in turn sends an [MCP
elicitation](https://modelcontextprotocol.io/specification/draft/client/elicitation)
to the client to ask for the approval decision. Upon getting a response,
it forwards the client's decision via `Op::ExecApproval`.
Admittedly, we should be doing the same thing for
`ApplyPatchApprovalRequest`, but this is our first time experimenting
with elicitations, so I'm inclined to defer wiring that code path up
until we feel good about how this one works.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1623).
* __->__ #1623
* #1622
* #1621
* #1620
Previous to this change, `MessageProcessor` had a
`tokio::sync::mpsc::Sender<JSONRPCMessage>` as an abstraction for server
code to send a message down to the MCP client. Because `Sender` is cheap
to `clone()`, it was straightforward to make it available to tasks
scheduled with `tokio::task::spawn()`.
This worked well when we were only sending notifications or responses
back down to the client, but we want to add support for sending
elicitations in #1623, which means that we need to be able to send
_requests_ to the client, and now we need a bit of centralization to
ensure all request ids are unique.
To that end, this PR introduces `OutgoingMessageSender`, which houses
the existing `Sender<OutgoingMessage>` as well as an `AtomicI64` to mint
out new, unique request ids. It has methods like `send_request()` and
`send_response()` so that callers do not have to deal with
`JSONRPCMessage` directly, as having to set the `jsonrpc` for each
message was a bit tedious (this cleans up `codex_tool_runner.rs` quite a
bit).
We do not have `OutgoingMessageSender` implement `Clone` because it is
important that the `AtomicI64` is shared across all users of
`OutgoingMessageSender`. As such, `Arc<OutgoingMessageSender>` must be
used instead, as it is frequently shared with new tokio tasks.
As part of this change, we update `message_processor.rs` to embrace
`await`, though we must be careful that no individual handler blocks the
main loop and prevents other messages from being handled.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1622).
* #1623
* __->__ #1622
* #1621
* #1620
This updates the schema in `generate_mcp_types.py` from `2025-03-26` to
`2025-06-18`, regenerates `mcp-types/src/lib.rs`, and then updates all
the code that uses `mcp-types` to honor the changes.
Ran
```
npx @modelcontextprotocol/inspector just codex mcp
```
and verified that I was able to invoke the `codex` tool, as expected.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1621).
* #1623
* #1622
* __->__ #1621
## Summary
- extend rollout format to store all session data in JSON
- add resume/write helpers for rollouts
- track session state after each conversation
- support `LoadSession` op to resume a previous rollout
- allow starting Codex with an existing session via
`experimental_resume` config variable
We need a way later for exploring the available sessions in a user
friendly way.
## Testing
- `cargo test --no-run` *(fails: `cargo: command not found`)*
------
https://chatgpt.com/codex/tasks/task_i_68792a29dd5c832190bf6930d3466fba
This video is outdated. you should use `-c experimental_resume:<full
path>` instead of `--resume <full path>`
https://github.com/user-attachments/assets/7a9975c7-aa04-4f4e-899a-9e87defd947a
## Summary
- add OpenAI retry and timeout fields to Config
- inject these settings in tests instead of mutating env vars
- plumb Config values through client and chat completions logic
- document new configuration options
## Testing
- `cargo test -p codex-core --no-run`
------
https://chatgpt.com/codex/tasks/task_i_68792c5b04cc832195c03050c8b6ea94
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
This is designed to facilitate programmatic use of Codex in a more
lightweight way than using `codex mcp`.
Passing `--json` to `codex exec` will print each event as a line of JSON
to stdout. Note that it does not print the individual tokens as they are
streamed, only full messages, as this is aimed at programmatic use
rather than to power UI.
<img width="1348" height="1307" alt="image"
src="https://github.com/user-attachments/assets/fc7908de-b78d-46e4-a6ff-c85de28415c7"
/>
I changed the existing `EventProcessor` into a trait and moved the
implementation to `EventProcessorWithHumanOutput`. Then I introduced an
alternative implementation, `EventProcessorWithJsonOutput`. The `--json`
flag determines which implementation to use.
Adds a default vscode config with generally applicable settings.
Adds more entrypoints to justfile both for environment setup and to help
agents better verify changes.
When Codex CLI is installed via `npm`, we use a `.js` wrapper script to
launch the Rust binary.
- Previously, we were not listening for signals to ensure that killing
the Node.js process would also kill the underlying Rust process.
- We also did not have a proper `exit` handler in place on the child
process to ensure we exited from the Node.js process.
This PR fixes these things and hopefully addresses
https://github.com/openai/codex/issues/1570.
This also adds logic so that Windows falls back to the TypeScript CLI
again, which should address https://github.com/openai/codex/issues/1573.
This PR implements server name validation for MCP (Model Context
Protocol) servers to ensure they conform to the required pattern
^[a-zA-Z0-9_-]+$. This addresses the TODO comment in
mcp_connection_manager.rs:82.
+ Added validation before spawning MCP client tasks
+ Invalid server names are added to errors map with descriptive messages
I have read the CLA Document and I hereby sign the CLA
---------
Co-authored-by: Michael Bolin <bolinfest@gmail.com>
- Added support for message and reasoning deltas
- Skipped adding the support in the cli and tui for later
- Commented a failing test (wrong merge) that needs fix in a separate
PR.
Side note: I think we need to disable merge when the CI don't pass.
While this does make it so that `ctrl-d` will not exit Codex when the
composer is not empty, `ctrl-d` will still exit Codex if it is in the
"working" state.
Fixes https://github.com/openai/codex/issues/1443.
It appears that `0.5.0` was built with `stage_release.sh` instead of
`stage_rust_release.py`, so add docs to clarify this and recommend
running `--version` on the release candidate to verify the right thing
was built.
## Summary
- add integration test for chat mode streaming via CLI using wiremock
- add integration test for Responses API streaming via fixture
- call `cargo run` to invoke the CLI during tests
## Testing
- `cargo test -p codex-core --test cli_stream -- --nocapture`
- `cargo clippy --all-targets --all-features -- -D warnings`
------
https://chatgpt.com/codex/tasks/task_i_68715980bbec8321999534fdd6a013c1
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
In order to to this, I created a new `chatgpt` crate where we can put
any code that interacts directly with ChatGPT as opposed to the OpenAI
API. I added a disclaimer to the README for it that it should primarily
be modified by OpenAI employees.
https://github.com/user-attachments/assets/bb978e33-d2c9-4d8e-af28-c8c25b1988e8
https://github.com/openai/codex/pull/1524 introduced the new `config`
field on `ModelClient`, so this does the post-PR cleanup to remove the
now-unnecessary `model` field.
As noted in the updated docs, this makes it so that you can set:
```toml
model_supports_reasoning_summaries = true
```
as a way of overriding the existing heuristic for when to set the
`reasoning` field on a sampling request:
341c091c5b/codex-rs/core/src/client_common.rs (L152-L166)
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps node from 22-slim to 24-slim.
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [toml](https://github.com/toml-rs/toml) from 0.9.0 to 0.9.1.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="8c8ef44ea1"><code>8c8ef44</code></a>
chore: Release</li>
<li><a
href="b60ac5bfe9"><code>b60ac5b</code></a>
fix(toml): Correct minimal version for indexmap (<a
href="https://redirect.github.com/toml-rs/toml/issues/998">#998</a>)</li>
<li><a
href="966bd40511"><code>966bd40</code></a>
fix(toml): Correct minimal version for indexmap</li>
<li><a
href="2ed2af6519"><code>2ed2af6</code></a>
docs(readme): Mention additional crates</li>
<li>See full diff in <a
href="https://github.com/toml-rs/toml/compare/toml-v0.9.0...toml-v0.9.1">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
## Summary
Add Android platform support to Codex CLI
## What?
- Added `android` to the list of supported platforms in
`codex-cli/bin/codex.js`
- Treats Android as Linux for binary compatibility
## Why?
- Fixes "Unsupported platform: android (arm64)" error on Termux
- Enables Codex CLI usage on Android devices via Termux
- Improves platform compatibility without affecting other platforms
## How?
- Modified the platform detection switch statement to include `case
"android":`
- Android falls through to the same logic as Linux, using appropriate
ARM64 binaries
- Minimal change with no breaking effects on existing functionality
## Testing
- Tested on Android/Termux environment
- Verified the fix resolves the platform detection error
- Confirmed no impact on other platforms
## Related Issues
Fixes the "Unsupported platform: android (arm64)" error reported by
Termux users
Current 0.4.0 release:
```
~/code/codex2/codex-rs$ codex completion | head
_codex-cli() {
local i cur prev opts cmd
COMPREPLY=()
if [[ "${BASH_VERSINFO[0]}" -ge 4 ]]; then
cur="$2"
else
cur="${COMP_WORDS[COMP_CWORD]}"
fi
prev="$3"
cmd=""
```
with this change:
```
~/code/codex2/codex-rs$ just codex completion | head
cargo run --bin codex -- "$@"
Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.82s
Running `target/debug/codex completion`
_codex() {
local i cur prev opts cmd
COMPREPLY=()
if [[ "${BASH_VERSINFO[0]}" -ge 4 ]]; then
cur="$2"
else
cur="${COMP_WORDS[COMP_CWORD]}"
fi
prev="$3"
cmd=""
```
Some users have proxies or other setups where they are ultimately
hitting OpenAI endpoints, but need a custom `base_url` rather than the
default value of `"https://api.openai.com/v1"`. This PR makes it
possible to override the `base_url` for the `openai` provider via the
`OPENAI_BASE_URL` environment variable.
This is a stopgap solution before migrating the build for the npm
release to GitHub Actions (which is ultimately what should be done to
ensure hermetic builds).
The idea is that instead of continuing to create PRs like
https://github.com/openai/codex/pull/1472 where I have to check in a
change to the `WORKFLOW_URL`, this script uses `gh run list` to get the
`WORKFLOW_URL` dynamically and then threads the value through to
`install_native_deps.sh`.
To create the 0.3.0 release on npm, I ran:
```shell
./codex-cli/scripts/stage_rust_release.py --release-version 0.3.0
```
and then did `npm publish --dry-run` followed by `npm publish` in the
temp directory created by `stage_rust_release.py`.
On a high-level, we try to design `config.toml` so that you don't have
to "comment out a lot of stuff" when testing different options.
Previously, defining a sandbox policy was somewhat at odds with this
principle because you would define the policy as attributes of
`[sandbox]` like so:
```toml
[sandbox]
mode = "workspace-write"
writable_roots = [ "/tmp" ]
```
but if you wanted to temporarily change to a read-only sandbox, you
might feel compelled to modify your file to be:
```toml
[sandbox]
mode = "read-only"
# mode = "workspace-write"
# writable_roots = [ "/tmp" ]
```
Technically, commenting out `writable_roots` would not be strictly
necessary, as `mode = "read-only"` would ignore `writable_roots`, but
it's still a reasonable thing to do to keep things tidy.
Currently, the various values for `mode` do not support that many
attributes, so this is not that hard to maintain, but one could imagine
this becoming more complex in the future.
In this PR, we change Codex CLI so that it no longer recognizes
`[sandbox]`. Instead, it introduces a top-level option, `sandbox_mode`,
and `[sandbox_workspace_write]` is used to further configure the sandbox
when when `sandbox_mode = "workspace-write"` is used:
```toml
sandbox_mode = "workspace-write"
[sandbox_workspace_write]
writable_roots = [ "/tmp" ]
```
This feels a bit more future-proof in that it is less tedious to
configure different sandboxes:
```toml
sandbox_mode = "workspace-write"
[sandbox_read_only]
# read-only options here...
[sandbox_workspace_write]
writable_roots = [ "/tmp" ]
[sandbox_danger_full_access]
# danger-full-access options here...
```
In this scheme, you never need to comment out the configuration for an
individual sandbox type: you only need to redefine `sandbox_mode`.
Relatedly, previous to this change, a user had to do `-c
sandbox.mode=read-only` to change the mode on the command line. With
this change, things are arguably a bit cleaner because the equivalent
option is `-c sandbox_mode=read-only` (and now `-c
sandbox_workspace_write=...` can be set separately).
Though more importantly, we introduce the `-s/--sandbox` option to the
CLI, which maps directly to `sandbox_mode` in `config.toml`, making
config override behavior easier to reason about. Moreover, as you can
see in the updates to the various Markdown files, it is much easier to
explain how to configure sandboxing when things like `--sandbox
read-only` can be used as an example.
Relatedly, this cleanup also made it straightforward to add support for
a `sandbox` option for Codex when used as an MCP server (see the changes
to `mcp-server/src/codex_tool_config.rs`).
Fixes https://github.com/openai/codex/issues/1248.
v0.2.0 of https://www.npmjs.com/package/@openai/codex now runs the Rust
CLI, so it makes sense to bring back the instructions to use `npm i -g
@openai/codex`.
In most places, I list `npm install` before `brew install` because I
believe `npm` is more readily available, though I in the more detailed
part of the documentation, I note that `brew install` will download
fewer bytes, and in that sense, is preferred.
This adds support for two new model provider config options:
- `http_headers` for hardcoded (key, value) pairs
- `env_http_headers` for headers whose values should be read from
environment variables
This also updates the built-in `openai` provider to use this feature to
set the following headers:
- `originator` => `codex_cli_rs`
- `version` => [CLI version]
- `OpenAI-Organization` => `OPENAI_ORGANIZATION` env var
- `OpenAI-Project` => `OPENAI_PROJECT` env var
for consistency with the TypeScript implementation:
bd5a9e8ba9/codex-cli/src/utils/agent/agent-loop.ts (L321-L329)
While here, this also consolidates some logic that was duplicated across
`client.rs` and `chat_completions.rs` by introducing
`ModelProviderInfo.create_request_builder()`.
Resolves https://github.com/openai/codex/discussions/1152
This introduces two changes to make a quick fix so we can deploy the
Rust CLI for `0.2.0` of `@openai/codex` on npm:
- Updates `WORKFLOW_URL` to point to
https://github.com/openai/codex/actions/runs/15981617627, which is the
GitHub workflow run used to create the binaries for the `0.2.0` release
we published to Homebrew.
- Adds a `--version` option to `stage_release.sh` to specify what the
`version` field in the `package.json` will be.
Locally, I ran the following:
```
./codex-cli/scripts/stage_release.sh --native --version 0.2.0
```
Previously, we only used the `--native` flag to publish to the `native`
tag of `@openai/codex` (e.g., `npm publish --tag native`), but we should
just publish this as the default tag for `0.2.0` to be consistent with
what is in Homebrew.
We can still publish one "final" version of the TypeScript CLI as 0.1.x
later.
Under the hood, this release will still contain `dist/cli.js`,
`bin/codex-linux-sandbox-x64`, and `bin/codex-x86_64-apple-darwin`,
which are not strictly necessary, but we'll fix that in `0.3.0`.
As promised on https://github.com/openai/codex/discussions/1405, we are
making the first official release of the Rust CLI as v0.2.0. As part of
this move, we are making it available in Homebrew:
https://github.com/Homebrew/homebrew-core/pull/228615
Ultimately, we also plan to continue to make the CLI available in npm,
as well, though brew is a bit nicer in that `brew install` will download
only the binary for your platform whereas an npm module is expected to
contain the binaries for _all_ supported platforms, so it is a bit more
heavyweight.
A big part of this change is updating the root `README.md` to document
the behavior of the Rust CLI, which differs in a number of ways from the
TypeScript CLI. The existing `README.md` is moved to
`codex-cli/README.md` as part of this PR, as it is still applicable to
that folder.
As this is still early days for the Rust CLI, I encourage folks to
provide feedback on the command line flags and configuration options.
As discovered in https://github.com/openai/codex/issues/1365, the Azure
provider needs to be able to specify `api-version` as a query param, so
this PR introduces a generic `query_params` option to the
`model_providers` config so that an Azure provider can be defined as
follows:
```toml
[model_providers.azure]
name = "Azure"
base_url = "https://YOUR_PROJECT_NAME.openai.azure.com/openai"
env_key = "AZURE_OPENAI_API_KEY"
query_params = { api-version = "2025-04-01-preview" }
```
This PR also updates the docs with this example.
While here, we also update `wire_api` to default to `"chat"`, as that is
likely the common case for someone defining an external provider.
Fixes https://github.com/openai/codex/issues/1365.
Looking at existing releases such as
https://github.com/openai/codex/releases/tag/codex-rs-b289c9207090b2e27494545d7b5404e063bd86f3-1-rust-v0.1.0-alpha.4,
the `.tar.gz` for the source code still seems to have `0.0.0` as the
`version` in `codex-rs/Cargo.toml` instead of what the tag seems to say
it should have:
b289c92070/codex-rs/Cargo.toml (L21)
ChatGPT claims:
> When GitHub generates the Source code (tar.gz) archive for a tag:
• It uses the commit the tag points to.
• But in some cases (e.g., shallow clones, GitHub CI, or local tools
that only clone the default branch), that commit may not be included,
and you might get an outdated view or nothing at all depending on how
it’s fetched.
Trying this recommended fix.
This is a small quality-of-life feature, the addition of
`--compute-indices` to the CLI, which, if enabled, will compute and set
the `indices` field for each `FileMatch` returned by `run()`. Note we
only bother to compute `indices` once we have the top N results because
there could be a lot of intermediate "top N" results during the search
that are ultimately discarded.
When set, the indices are included in the JSON output when `--json` is
specified and the matching indices are displayed in bold when `--json`
is not specified.
Introduces support for `@` to trigger a fuzzy-filename search in the
composer. Under the hood, this leverages
https://crates.io/crates/nucleo-matcher to do the fuzzy matching and
https://crates.io/crates/ignore to build up the list of file candidates
(so that it respects `.gitignore`).
For simplicity (at least for now), we do not do any caching between
searches like VS Code does for its file search:
1d89ed699b/src/vs/workbench/services/search/node/rawSearchService.ts (L212-L218)
Because we do not do any caching, I saw queries take up to three seconds
on large repositories with hundreds of thousands of files. To that end,
we do not perform searches synchronously on each keystroke, but instead
dispatch an event to do the search on a background thread that
asynchronously reports back to the UI when the results are available.
This is largely handled by the `FileSearchManager` introduced in this
PR, which also has logic for debouncing requests so there is at most one
search in flight at a time.
While we could potentially polish and tune this feature further, it may
already be overengineered for how it will be used, in practice, so we
can improve things going forward if it turns out that this is not "good
enough" in the wild.
Note this feature does not work like `@` in the TypeScript CLI, which
was more like directory-based tab completion. In the Rust CLI, `@`
triggers a full-repo fuzzy-filename search.
Fixes https://github.com/openai/codex/issues/1261.
Update `run()` to take `cancel_flag: Arc<AtomicBool>` that the worker
threads will periodically check to see if it is `true`, exiting early
(and returning empty results) if so.
As we are [close to releasing the Rust CLI
beta](https://github.com/openai/codex/discussions/1405), for the moment,
let's take a more neutral stance on what it takes to be a "built-in"
provider.
* For example, there seems to be a discrepancy around what the "right"
configuration for Gemini is: https://github.com/openai/codex/pull/881
* And while the current list of "built-in" providers are all arguably
"well-known" names, this raises a question of what to do about
potentially less familiar providers, such as
https://github.com/openai/codex/pull/1142. Do we just accept every pull
request like this, or is there some criteria a provider has to meet to
"qualify" to be bundled with Codex CLI?
I think that if we can establish clear ground rules for being a built-in
provider, then we can bring this back. But until then, I would rather
take a minimalist approach because if we decided to reverse our position
later, it would break folks who were depending on the presence of the
built-in providers.
Adds support for a `/diff` command comparable to the one available in
the TypeScript CLI.
<img width="1103" alt="Screenshot 2025-06-26 at 12 31 33 PM"
src="https://github.com/user-attachments/assets/5dc646ca-301f-41ff-92a7-595c68db64b6"
/>
While here, changed the `SlashCommand` enum so the declared variant
order is the order the commands appear in the popup menu. This way,
`/toggle-mouse-mode` is listed last, as it is the least likely to be
used.
Fixes https://github.com/openai/codex/issues/1253.
When using the OpenAI Responses API, we now record the `usage` field for
a `"response.completed"` event, which includes metrics about the number
of tokens consumed. We also introduce `openai_model_info.rs`, which
includes current data about the most common OpenAI models available via
the API (specifically `context_window` and `max_output_tokens`). If
Codex does not recognize the model, you can set `model_context_window`
and `model_max_output_tokens` explicitly in `config.toml`.
When then introduce a new event type to `protocol.rs`, `TokenCount`,
which includes the `TokenUsage` for the most recent turn.
Finally, we update the TUI to record the running sum of tokens used so
the percentage of available context window remaining can be reported via
the placeholder text for the composer:
We could certainly get much fancier with this (such as reporting the
estimated cost of the conversation), but for now, we are just trying to
achieve feature parity with the TypeScript CLI.
Though arguably this improves upon the TypeScript CLI, as the TypeScript
CLI uses heuristics to estimate the number of tokens used rather than
using the `usage` information directly:
296996d74e/codex-cli/src/utils/approximate-tokens-used.ts (L3-L16)
Fixes https://github.com/openai/codex/issues/1242
This PR reworks `assess_command_safety()` so that the combination of
`AskForApproval::Never` and `SandboxPolicy::DangerFullAccess` ensures
that commands are run without _any_ sandbox and the user should never be
prompted. In turn, it adds support for a new
`--dangerously-bypass-approvals-and-sandbox` flag (that cannot be used
with `--approval-policy` or `--full-auto`) that sets both of those
options.
Fixes https://github.com/openai/codex/issues/1254
For the `approval_policy` config option, renames `unless-allow-listed`
to `untrusted`. In general, when it comes to exec'ing commands, I think
"trusted" is a more accurate term than "safe."
Also drops the `AskForApproval::AutoEdit` variant, as we were not really
making use of it, anyway.
Fixes https://github.com/openai/codex/issues/1250.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1378).
* #1379
* __->__ #1378
Apparently `just` was added to `apt` in Ubuntu 24, so this required
updating the Ubuntu version in the `Dockerfile` to make it so we could
simply `apt install just`.
Though then that caused a conflict with the custom `dev` user we were
using, though the end result seems simpler since now we just use the
default `ubuntu` user provided by Ubuntu 24.
This is a major redesign of how sandbox configuration works and aims to
fix https://github.com/openai/codex/issues/1248. Specifically, it
replaces `sandbox_permissions` in `config.toml` (and the
`-s`/`--sandbox-permission` CLI flags) with a "table" with effectively
three variants:
```toml
# Safest option: full disk is read-only, but writes and network access are disallowed.
[sandbox]
mode = "read-only"
# The cwd of the Codex task is writable, as well as $TMPDIR on macOS.
# writable_roots can be used to specify additional writable folders.
[sandbox]
mode = "workspace-write"
writable_roots = [] # Optional, defaults to the empty list.
network_access = false # Optional, defaults to false.
# Disable sandboxing: use at your own risk!!!
[sandbox]
mode = "danger-full-access"
```
This should make sandboxing easier to reason about. While we have
dropped support for `-s`, the way it works now is:
- no flags => `read-only`
- `--full-auto` => `workspace-write`
- currently, there is no way to specify `danger-full-access` via a CLI
flag, but we will revisit that as part of
https://github.com/openai/codex/issues/1254
Outstanding issue:
- As noted in the `TODO` on `SandboxPolicy::is_unrestricted()`, we are
still conflating sandbox preferences with approval preferences in that
case, which needs to be cleaned up.
- Use Responses API for Azure provider endpoints
- Added a unit test to catch regression on the change from
`/chat/completions` to `/responses`
- Updated the default AOAI api version from `2025-03-01-preview` to
`2025-04-01-preview` to avoid user/400 errors due to missing summary
support in the March API version.
- Changes have been tested locally on AOAI endpoints
## Summary
This PR refactors the Codex CLI authentication flow so that
**non-OpenAI** providers (for example **azure**, or any future addition)
can supply their API key through a dedicated environment variable
without triggering the OpenAI login flow.
Key behaviours introduced:
* When `provider !== "openai"` the CLI consults `src/utils/providers.ts`
to locate the correct environment variable (`AZURE_OPENAI_API_KEY`,
`GEMINI_API_KEY`, and so on) before considering any interactive login.
* Credit redemption (`--free`) and PKCE login now run **only** when the
provider is OpenAI, eliminating unwanted browser prompts for Azure and
others.
* User-facing error messages are revamped to guide Azure users to
**[https://ai.azure.com/](https://ai.azure.com)** and show the exact
variable name they must set.
* All code paths still export `OPENAI_API_KEY` so legacy scripts
continue to operate unchanged.
---
## Example `config.json`
```jsonc
{
"model": "codex-mini",
"provider": "azure",
"providers": {
"azure": {
"name": "AzureOpenAI",
"baseURL": "https://ai-<project-name>.openai.azure.com/openai",
"envKey": "AZURE_OPENAI_API_KEY"
}
},
"history": {
"maxSize": 1000,
"saveHistory": true,
"sensitivePatterns": []
}
}
```
With this file in `~/.codex/config.json`, a single command line is
enough:
```bash
export AZURE_OPENAI_API_KEY="<your-key>"
codex "Hello from Azure"
```
No browser window opens, and the CLI works in entirely non-interactive
mode.
---
## Rationale
The new flow enables Codex to run **asynchronously** in sandboxed
environments such as GitHub Actions pipelines. By passing `--provider
azure` (or setting it in `config.json`) and exporting the correct key,
CI/CD jobs can invoke Codex without any ChatGPT-style login or PKCE
round-trip. This unlocks fully automated testing and deployment
scenarios.
---
## What’s changed
| File | Type | Description |
| ------------------------ | ------------------- |
-----------------------------------------------------------------------------------------------------------------------------
|
| `codex-cli/src/cli.tsx` | **feat / refactor** | +43 / -20 lines.
Imports `providers`, adds early provider-specific key lookup, gates
`--free` redemption, rewrites help text. |
| `src/utils/providers.ts` | **chore** | Now consumed by CLI for env-var
discovery. |
---
## How to test
```bash
# Azure example
export AZURE_OPENAI_API_KEY="<your-key>"
codex --provider azure "Automated run in CI"
# OpenAI example (unchanged behaviour)
codex --provider openai --login "Standard OpenAI flow"
```
Expected outcomes:
* Azure and other provider paths are non-interactive when provider flag
is passed.
* The CLI always sets `OPENAI_API_KEY` for backward compatibility.
---
## Checklist
* [x] Logic behind provider-specific env-var lookup added.
* [x] Redundant OpenAI login steps removed for other providers.
* [x] Unit tests cover new branches.
* [x] README and sample config updated.
* [x] CI passes on all supported Node versions.
---
**Related work**
* #92
* #769
* #1321
I have read the CLA Document and I hereby sign the CLA.
2025-06-22 17:56:36 -07:00
1635 changed files with 203407 additions and 59878 deletions
For MacOS and Linux: copy the output of `uname -mprs`
For Windows: copy the output of `"$([Environment]::OSVersion | ForEach-Object VersionString) $(if ([Environment]::Is64BitOperatingSystem) { "x64" } else { "x86" })"` in the PowerShell console
- type:textarea
id:actual
attributes:
label:What issue are you seeing?
description:Please include the full error messages and prompts with PII redacted. If possible, please provide text instead of a screenshot.
validations:
required:true
- type:textarea
id:steps
attributes:
label:What steps can reproduce the bug?
description:Explain the bug and provide a code snippet that can reproduce it.
description:Explain the bug and provide a code snippet that can reproduce it. Please include session id, token limit usage, context window usage if applicable.
validations:
required:true
- type:textarea
@@ -44,11 +59,6 @@ body:
attributes:
label:What is the expected behavior?
description:If possible, please provide text instead of a screenshot.
- type:textarea
id:actual
attributes:
label:What do you see instead?
description:If possible, please provide text instead of a screenshot.
Is Codex missing a feature that you'd like to see? Feel free to propose it here.
Before you submit a feature:
1. Search existing issues for similar features. If you find one, 👍 it rather than opening a new one.
2. The Codex team will try to balance the varying needs of the community when prioritizing or rejecting new features. Not all features will be accepted. See [Contributing](https://github.com/openai/codex#contributing) for more details.
- type:textarea
id:feature
attributes:
label:What feature would you like to see?
validations:
required:true
- type:textarea
id:notes
attributes:
label:Additional information
description:Is there anything else you think we should know?
description:Report an issue with the VS Code extension
labels:
- extension
- needs triage
body:
- type:markdown
attributes:
value:|
Before submitting a new issue, please search for existing issues to see if your issue has already been reported.
If it has, please add a 👍 reaction (no need to leave a comment) to the existing issue instead of creating a new one.
- type:input
id:version
attributes:
label:What version of the VS Code extension are you using?
validations:
required:true
- type:input
id:plan
attributes:
label:What subscription do you have?
validations:
required:true
- type:input
id:ide
attributes:
label:Which IDE are you using?
description:Like `VS Code`, `Cursor`, `Windsurf`, etc.
validations:
required:true
- type:input
id:platform
attributes:
label:What platform is your computer?
description:|
For MacOS and Linux: copy the output of `uname -mprs`
For Windows: copy the output of `"$([Environment]::OSVersion | ForEach-Object VersionString) $(if ([Environment]::Is64BitOperatingSystem) { "x64" } else { "x86" })"` in the PowerShell console
- type:textarea
id:actual
attributes:
label:What issue are you seeing?
description:Please include the full error messages and prompts with PII redacted. If possible, please provide text instead of a screenshot.
validations:
required:true
- type:textarea
id:steps
attributes:
label:What steps can reproduce the bug?
description:Explain the bug and provide a code snippet that can reproduce it. Please include session id, token limit usage, context window usage if applicable.
validations:
required:true
- type:textarea
id:expected
attributes:
label:What is the expected behavior?
description:If possible, please provide text instead of a screenshot.
- type:textarea
id:notes
attributes:
label:Additional information
description:Is there anything else you think we should know?
`openai/codex-action` is a GitHub Action that facilitates the use of [Codex](https://github.com/openai/codex) on GitHub issues and pull requests. Using the action, associate **labels** to run Codex with the appropriate prompt for the given context. Codex will respond by posting comments or creating PRs, whichever you specify!
Here is a sample workflow that uses `openai/codex-action`:
```yaml
name:Codex
on:
issues:
types:[opened, labeled]
pull_request:
branches:[main]
types:[labeled]
jobs:
codex:
if:...# optional, but can be effective in conserving CI resources
runs-on:ubuntu-latest
# TODO(mbolin): Need to verify if/when `write` is necessary.
permissions:
contents:write
issues:write
pull-requests:write
steps:
# By default, Codex runs network disabled using --full-auto, so perform
# any setup that requires network (such as installing dependencies)
See sample usage in [`codex.yml`](../../workflows/codex.yml).
## Triggering the Action
Using the sample workflow above, we have:
```yaml
on:
issues:
types:[opened, labeled]
pull_request:
branches:[main]
types:[labeled]
```
which means our workflow will be triggered when any of the following events occur:
- a label is added to an issue
- a label is added to a pull request against the `main` branch
### Label-Based Triggers
To define a GitHub label that should trigger Codex, create a file named `.github/codex/labels/LABEL-NAME.md` in your repository where `LABEL-NAME` is the name of the label. The content of the file is the prompt template to use when the label is added (see more on [Prompt Template Variables](#prompt-template-variables) below).
For example, if the file `.github/codex/labels/codex-review.md` exists, then:
- Adding the `codex-review` label will trigger the workflow containing the `openai/codex-action` GitHub Action.
- When `openai/codex-action` starts, it will replace the `codex-review` label with `codex-review-in-progress`.
- When `openai/codex-action` is finished, it will replace the `codex-review-in-progress` label with `codex-review-completed`.
If Codex sees that either `codex-review-in-progress` or `codex-review-completed` is already present, it will not perform the action.
As determined by the [default config](./src/default-label-config.ts), Codex will act on the following labels by default:
- Adding the `codex-review` label to a pull request will have Codex review the PR and add it to the PR as a comment.
- Adding the `codex-triage` label to an issue will have Codex investigate the issue and report its findings as a comment.
- Adding the `codex-issue-fix` label to an issue will have Codex attempt to fix the issue and create a PR wit the fix, if any.
## Action Inputs
The `openai/codex-action` GitHub Action takes the following inputs
### `openai_api_key` (required)
Set your `OPENAI_API_KEY` as a [repository secret](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions). See **Secrets and varaibles** then **Actions** in the settings for your GitHub repo.
Note that the secret name does not have to be `OPENAI_API_KEY`. For example, you might want to name it `CODEX_OPENAI_API_KEY` and then configure it on `openai/codex-action` as follows:
This is required so that Codex can post a comment or create a PR. Set this value on the action as follows:
```yaml
github_token:${{ secrets.GITHUB_TOKEN }}
```
### `codex_args`
A whitespace-delimited list of arguments to pass to Codex. Defaults to `--full-auto`, but if you want to override the default model to use `o3`:
```yaml
codex_args:"--full-auto --model o3"
```
For more complex configurations, use the `codex_home` input.
### `codex_home`
If set, the value to use for the `$CODEX_HOME` environment variable when running Codex. As explained [in the docs](https://github.com/openai/codex/tree/main/codex-rs#readme), this folder can contain the `config.toml` to configure Codex, custom instructions, and log files.
This should be a relative path within your repo.
## Prompt Template Variables
As shown above, `"prompt"` and `"promptPath"` are used to define prompt templates that will be populated and passed to Codex in response to certain events. All template variables are of the form `{CODEX_ACTION_...}` and the supported values are defined below.
### `CODEX_ACTION_ISSUE_TITLE`
If the action was triggered on a GitHub issue, this is the issue title.
Specifically it is read as the `.issue.title` from the `$GITHUB_EVENT_PATH`.
### `CODEX_ACTION_ISSUE_BODY`
If the action was triggered on a GitHub issue, this is the issue body.
Specifically it is read as the `.issue.body` from the `$GITHUB_EVENT_PATH`.
### `CODEX_ACTION_GITHUB_EVENT_PATH`
The value of the `$GITHUB_EVENT_PATH` environment variable, which is the path to the file that contains the JSON payload for the event that triggered the workflow. Codex can use `jq` to read only the fields of interest from this file.
### `CODEX_ACTION_PR_DIFF`
If the action was triggered on a pull request, this is the diff between the base and head commits of the PR. It is the output from `git diff`.
Note that the content of the diff could be quite large, so is generally safer to point Codex at `CODEX_ACTION_GITHUB_EVENT_PATH` and let it decide how it wants to explore the change.
description:"A reusable action that runs a Codex model."
inputs:
openai_api_key:
description:"The value to use as the OPENAI_API_KEY environment variable when running Codex."
required:true
trigger_phrase:
description:"Text to trigger Codex from a PR/issue body or comment."
required:false
default:""
github_token:
description:"Token so Codex can comment on the PR or issue."
required:true
codex_args:
description:"A whitespace-delimited list of arguments to pass to Codex. Due to limitations in YAML, arguments with spaces are not supported. For more complex configurations, use the `codex_home` input."
Provide a concise and respectful comment summarizing the findings.
### {CODEX_ACTION_ISSUE_TITLE}
{CODEX_ACTION_ISSUE_BODY}
`.trim(),
},
"codex-code-review":{
getPromptTemplate:()=>
`
Review this PR and respond with a very concise final message, formatted in Markdown.
There should be a summary of the changes (1-2 sentences) and a few bullet points if necessary.
Then provide the **review** (1-2 sentences plus bullet points, friendly tone).
{CODEX_ACTION_GITHUB_EVENT_PATH} contains the JSON that triggered this GitHub workflow. It contains the \`base\` and \`head\` refs that define this PR. Both refs are available locally.
`.trim(),
},
"codex-attempt-fix":{
getPromptTemplate:()=>
`
Attempt to solve the reported issue.
If a code change is required, create a new branch, commit the fix, and open a pull-request that resolves the problem.
Review this PR and respond with a very concise final message, formatted in Markdown.
There should be a summary of the changes (1-2 sentences) and a few bullet points if necessary.
Then provide the **review** (1-2 sentences plus bullet points, friendly tone).
Things to look out for when doing the review:
## General Principles
- **Make sure the pull request body explains the motivation behind the change.** If the author has failed to do this, call it out, and if you think you can deduce the motivation behind the change, propose copy.
- Ideally, the PR body also contains a small summary of the change. For small changes, the PR title may be sufficient.
- Each PR should ideally do one conceptual thing. For example, if a PR does a refactoring as well as introducing a new feature, push back and suggest the refactoring be done in a separate PR. This makes things easier for the reviewer, as refactoring changes can often be far-reaching, yet quick to review.
- When introducing new code, be on the lookout for code that duplicates existing code. When found, propose a way to refactor the existing code such that it should be reused.
## Code Organization
- Each create in the Cargo workspace in `codex-rs` has a specific purpose: make a note if you believe new code is not introduced in the correct crate.
- When possible, try to keep the `core` crate as small as possible. Non-core but shared logic is often a good candidate for `codex-rs/common`.
- Be wary of large files and offer suggestions for how to break things into more reasonably-sized files.
- Rust files should generally be organized such that the public parts of the API appear near the top of the file and helper functions go below. This is analagous to the "inverted pyramid" structure that is favored in journalism.
## Assertions in Tests
Assert the equality of the entire objects instead of doing "piecemeal comparisons," performing `assert_eq!()` on individual fields.
Note that unit tests also function as "executable documentation." As shown in the following example, "piecemeal comparisons" are often more verbose, provide less coverage, and are not as useful as executable documentation.
For example, suppose you have the following enum:
```rust
#[derive(Debug, PartialEq)]
enumMessage{
Request{
id: String,
method: String,
params: Option<serde_json::Value>,
},
Notification{
method: String,
params: Option<serde_json::Value>,
},
}
```
This is an example of a _piecemeal_ comparison:
```rust
// BAD: Piecemeal Comparison
#[test]
fntest_get_latest_messages(){
letmessages=get_latest_messages();
assert_eq!(messages.len(),2);
letm0=&messages[0];
matchm0{
Message::Request{id,method,params}=>{
assert_eq!(id,"123");
assert_eq!(method,"subscribe");
assert_eq!(
*params,
Some(json!({
"conversation_id": "x42z86"
}))
)
}
Message::Notification{..}=>{
panic!("expected Request");
}
}
letm1=&messages[1];
matchm1{
Message::Request{..}=>{
panic!("expected Notification");
}
Message::Notification{method,params}=>{
assert_eq!(method,"log");
assert_eq!(
*params,
Some(json!({
"level": "info",
"message": "subscribed"
}))
)
}
}
}
```
This is a _deep_ comparison:
```rust
// GOOD: Verify the entire structure with a single assert_eq!().
usepretty_assertions::assert_eq;
#[test]
fntest_get_latest_messages(){
letmessages=get_latest_messages();
assert_eq!(
vec![
Message::Request{
id: "123".to_string(),
method: "subscribe".to_string(),
params: Some(json!({
"conversation_id": "x42z86"
})),
},
Message::Notification{
method: "log".to_string(),
params: Some(json!({
"level": "info",
"message": "subscribed"
})),
},
],
messages,
);
}
```
## More Tactical Rust Things To Look Out For
- Do not use `unsafe` (unless you have a really, really good reason like using an operating system API directly and no safe wrapper exists). For example, there are cases where it is tempting to use `unsafe` in order to use `std::env::set_var()`, but this indeed `unsafe` and has led to race conditions on multiple occasions. (When this happens, find a mechanism other than environment variables to use for configuration.)
- Encourage the use of small enums or the newtype pattern in Rust if it helps readability without adding significant cognitive load or lines of code.
- If you see opportunities for the changes in a diff to use more idiomatic Rust, please make specific recommendations. For example, favor the use of expressions over `return`.
- When modifying a `Cargo.toml` file, make sure that dependency lists stay alphabetically sorted. Also consider whether a new dependency is added to the appropriate place (e.g., `[dependencies]` versus `[dev-dependencies]`)
## Pull Request Body
- If the nature of the change seems to have a visual component (which is often the case for changes to `codex-rs/tui`), recommend including a screenshot or video to demonstrate the change, if appropriate.
- References to existing GitHub issues and PRs are encouraged, where appropriate, though you likely do not have network access, so may not be able to help here.
# PR Information
{CODEX_ACTION_GITHUB_EVENT_PATH} contains the JSON that triggered this GitHub workflow. It contains the `base` and `head` refs that define this PR. Both refs are available locally.
You are an assistant that reviews GitHub issues for the repository.
Your job is to choose the most appropriate existing labels for the issue described later in this prompt.
Follow these rules:
- Only pick labels out of the list below.
- Prefer a small set of precise labels over many broad ones.
- If none of the labels fit, respond with an empty JSON array: []
- Output must be a JSON array of label names (strings) with no additional commentary.
Labels to apply:
1. bug — Reproducible defects in Codex products (CLI, VS Code extension, web, auth).
2. enhancement — Feature requests or usability improvements that ask for new capabilities, better ergonomics, or quality-of-life tweaks.
3. extension — VS Code (or other IDE) extension-specific issues.
4. windows-os — Bugs or friction specific to Windows environments (PowerShell behavior, path handling, copy/paste, OS-specific auth or tooling failures).
5. mcp — Topics involving Model Context Protocol servers/clients.
6. codex-web — Issues targeting the Codex web UI/Cloud experience.
8. azure — Problems or requests tied to Azure OpenAI deployments.
9. documentation — Updates or corrections needed in docs/README/config references (broken links, missing examples, outdated keys, clarification requests).
10. model-behavior — Undesirable LLM behavior: forgetting goals, refusing work, hallucinating environment details, quota misreports, or other reasoning/performance anomalies.
Issue information is available in environment variables:
core.info(`Author ${pr.user.login} has ${permission} access; skipping #${pr.number}`);
continue;
}
stalePrs.push(pr);
}
if (!stalePrs.length) {
core.info("No stale contributor pull requests found.");
return;
}
for (const pr of stalePrs) {
const issue_number = pr.number;
const closeComment = `Closing this pull request because it has had no updates for more than ${DAYS_INACTIVE} days. If you plan to continue working on it, feel free to reopen or open a new PR.`;
if (dryRun) {
core.info(`[dry-run] Would close contributor PR #${issue_number} from ${pr.user.login}`);
continue;
}
await github.rest.issues.createComment({
owner,
repo,
issue_number,
body: closeComment,
});
await github.rest.pulls.update({
owner,
repo,
pull_number: issue_number,
state: "closed",
});
core.info(`Closed contributor PR #${issue_number} from ${pr.user.login}`);
You are an assistant that triages new GitHub issues by identifying potential duplicates.
You will receive the following JSON files located in the current working directory:
- `codex-current-issue.json`: JSON object describing the newly created issue (fields: number, title, body).
- `codex-existing-issues.json`: JSON array of recent issues (each element includes number, title, body, createdAt).
Instructions:
- Compare the current issue against the existing issues to find up to five that appear to describe the same underlying problem or request.
- Focus on the underlying intent and context of each issue—such as reported symptoms, feature requests, reproduction steps, or error messages—rather than relying solely on string similarity or synthetic metrics.
- After your analysis, validate your results in 1-2 lines explaining your decision to return the selected matches.
You are an assistant that reviews GitHub issues for the repository.
Your job is to choose the most appropriate labels for the issue described later in this prompt.
Follow these rules:
- Add one (and only one) of the following three labels to distinguish the type of issue. Default to "bug" if unsure.
1. bug — Reproducible defects in Codex products (CLI, VS Code extension, web, auth).
2. enhancement — Feature requests or usability improvements that ask for new capabilities, better ergonomics, or quality-of-life tweaks.
3. documentation — Updates or corrections needed in docs/README/config references (broken links, missing examples, outdated keys, clarification requests).
- If applicable, add one of the following labels to specify which sub-product or product surface the issue relates to.
1. CLI — the Codex command line interface.
2. extension — VS Code (or other IDE) extension-specific issues.
3. codex-web — Issues targeting the Codex web UI/Cloud experience.
4. github-action — Issues with the Codex GitHub action.
5. iOS — Issues with the Codex iOS app.
- Additionally add zero or more of the following labels that are relevant to the issue content. Prefer a small set of precise labels over many broad ones.
1. windows-os — Bugs or friction specific to Windows environments (always when PowerShell is mentioned, path handling, copy/paste, OS-specific auth or tooling failures).
2. mcp — Topics involving Model Context Protocol servers/clients.
3. mcp-server — Problems related to the codex mcp-server command, where codex runs as an MCP server.
4. azure — Problems or requests tied to Azure OpenAI deployments.
5. model-behavior — Undesirable LLM behavior: forgetting goals, refusing work, hallucinating environment details, quota misreports, or other reasoning/performance anomalies.
6. code-review — Issues related to the code review feature or functionality.
7. auth - Problems related to authentication, login, or access tokens.
8. codex-exec - Problems related to the "codex exec" command or functionality.
9. context-management - Problems related to compaction, context windows, or available context reporting.
10. custom-model - Problems that involve using custom model providers, local models, or OSS models.
11. rate-limits - Problems related to token limits, rate limits, or token usage reporting.
12. sandbox - Issues related to local sandbox environments or tool call approvals to override sandbox restrictions.
13. tool-calls - Problems related to specific tool call invocations including unexpected errors, failures, or hangs.
14. TUI - Problems with the terminal user interface (TUI) including keyboard shortcuts, copy & pasting, menus, or screen update issues.
This file provides guidance to OpenAI Codex (openai.com/codex) when working with
code in this repository.
In the codex-rs folder where the rust code lives:
## Build, Lint & Test
- Crate names are prefixed with `codex-`. For example, the `core` folder's crate is named `codex-core`
- When using format! and you can inline variables into {}, always do that.
- Install any commands the repo relies on (for example `just`, `rg`, or `cargo-insta`) if they aren't already available before running instructions here.
- Never add or modify any code related to `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` or `CODEX_SANDBOX_ENV_VAR`.
- You operate in a sandbox where `CODEX_SANDBOX_NETWORK_DISABLED=1` will be set whenever you use the `shell` tool. Any existing code that uses `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` was authored with this fact in mind. It is often used to early exit out of tests that the author knew you would not be able to run given your sandbox limitations.
- Similarly, when you spawn a process using Seatbelt (`/usr/bin/sandbox-exec`), `CODEX_SANDBOX=seatbelt` will be set on the child process. Integration tests that want to run Seatbelt themselves cannot be run under Seatbelt, so checks for `CODEX_SANDBOX=seatbelt` are also often used to early exit out of tests, as appropriate.
- Always collapse if statements per https://rust-lang.github.io/rust-clippy/master/index.html#collapsible_if
- Always inline format! args when possible per https://rust-lang.github.io/rust-clippy/master/index.html#uninlined_format_args
- Use method references over closures when possible per https://rust-lang.github.io/rust-clippy/master/index.html#redundant_closure_for_method_calls
- Do not use unsigned integer even if the number cannot be negative.
- When writing tests, prefer comparing the equality of entire objects over fields one by one.
- When making a change that adds or changes an API, ensure that the documentation in the `docs/` folder is up to date if applicable.
### JavaScript/TypeScript
- Install dependencies: `pnpm install`
- Run all tests: `pnpm test`
- Run a single test: `pnpm test -- -t <pattern>` or `pnpm test -- path/to/file.spec.ts`
- Watch tests: `pnpm test:watch`
- Lint: `pnpm lint && pnpm lint:fix`
- Type-check: `pnpm typecheck`
- Format: `pnpm format:fix`
- Build: `pnpm build`
Run `just fmt` (in `codex-rs` directory) automatically after making Rust code changes; do not ask for approval to run it. Before finalizing a change to `codex-rs`, run `just fix -p <project>` (in `codex-rs` directory) to fix any linter issues in the code. Prefer scoping with `-p` to avoid slow workspace‑wide Clippy builds; only run `just fix` without `-p` if you changed shared crates. Additionally, run the tests:
### Rust (codex-rs workspace)
- Build: `cargo build --workspace --locked`
- Test all: `cargo test --workspace`
- Test crate: `cargo test -p <crate>`
- Single test: `cargo test -p <crate> -- <test_name>`
1. Run the test for the specific project that was changed. For example, if changes were made in `codex-rs/tui`, run `cargo test -p codex-tui`.
2. Once those pass, if any changes were made in common, core, or protocol, run the complete test suite with `cargo test --all-features`.
When running interactively, ask the user before running `just fix` to finalize. `just fmt` does not require approval. project-specific or individual tests can be run without asking the user, but do ask the user before running the complete test suite.
## Code Style Guidelines
## TUI style conventions
- JS/TS: ESLint + Prettier; group imports; camelCase vars & funcs; PascalCase types/components; catch specific errors
- Rust: rustfmt & Clippy (see `codex-rs/rustfmt.toml`); snake_case vars & funcs; PascalCase types; prefer early return; avoid `unwrap()` in prod
- General: Do not swallow exceptions; use DRY; generate/validate ASCII art programmatically
- Include any Cursor rules from `.cursor/rules/` or Copilot rules from `.github/copilot-instructions.md` if present
See `codex-rs/tui/styles.md`.
## TUI code conventions
- Use concise styling helpers from ratatui’s Stylize trait.
- Basic spans: use "text".into()
- Styled spans: use "text".red(), "text".green(), "text".magenta(), "text".dim(), etc.
- Prefer these over constructing styles with `Span::styled` and `Style` directly.
- Prefer Stylize helpers: use "text".dim(), .bold(), .cyan(), .italic(), .underlined() instead of manual Style where possible.
- Prefer simple conversions: use "text".into() for spans and vec![…].into() for lines; when inference is ambiguous (e.g., Paragraph::new/Cell::from), use Line::from(spans) or Span::from(text).
- Computed styles: if the Style is computed at runtime, using `Span::styled` is OK (`Span::from(text).set_style(style)` is also acceptable).
- Avoid hardcoded white: do not use `.white()`; prefer the default foreground (no color).
- Chaining: combine helpers by chaining for readability (e.g., url.cyan().underlined()).
- Single items: prefer "text".into(); use Line::from(text) or Span::from(text) only when the target type isn’t obvious from context, or when using .into() would require extra type annotations.
- Building lines: use vec![…].into() to construct a Line when the target type is obvious and no extra type annotations are needed; otherwise use Line::from(vec![…]).
- Avoid churn: don’t refactor between equivalent forms (Span::styled ↔ set_style, Line::from ↔ .into()) without a clear readability or functional gain; follow file‑local conventions and do not introduce type annotations solely to satisfy .into().
- Compactness: prefer the form that stays on one line after rustfmt; if only one of Line::from(vec![…]) or vec![…].into() avoids wrapping, choose that. If both wrap, pick the one with fewer wrapped lines.
### Text wrapping
- Always use textwrap::wrap to wrap plain strings.
- If you have a ratatui Line and you want to wrap it, use the helpers in tui/src/wrapping.rs, e.g. word_wrap_lines / word_wrap_line.
- If you need to indent wrapped lines, use the initial_indent / subsequent_indent options from RtOptions if you can, rather than writing custom logic.
- If you have a list of lines and you need to prefix them all with some prefix (optionally different on the first vs subsequent lines), use the `prefix_lines` helper from line_utils.
## Tests
### Snapshot tests
This repo uses snapshot tests (via `insta`), especially in `codex-rs/tui`, to validate rendered output. When UI or text output changes intentionally, update the snapshots as follows:
- Run tests to generate any updated snapshots:
-`cargo test -p codex-tui`
- Check what’s pending:
-`cargo insta pending-snapshots -p codex-tui`
- Review changes by reading the generated `*.snap.new` files directly in the repo, or preview a specific file:
-`cargo insta show -p codex-tui path/to/file.snap.new`
- Only if you intend to accept all new snapshots in this crate, run:
-`cargo insta accept -p codex-tui`
If you don’t have the tool:
-`cargo install cargo-insta`
### Test assertions
- Tests should use pretty_assertions::assert_eq for clearer diffs. Import this at the top of the test module if it isn't already.
### Integration tests (core)
- Prefer the utilities in `core_test_support::responses` when writing end-to-end Codex tests.
- All `mount_sse*` helpers return a `ResponseMock`; hold onto it so you can assert against outbound `/responses` POST bodies.
- Use `ResponseMock::single_request()` when a test should only issue one POST, or `ResponseMock::requests()` to inspect every captured `ResponsesRequest`.
-`ResponsesRequest` exposes helpers (`body_json`, `input`, `function_call_output`, `custom_tool_call_output`, `call_output`, `header`, `path`, `query_param`) so assertions can target structured payloads instead of manual JSON digging.
- Build SSE payloads with the provided `ev_*` constructors and the `sse(...)`.
- Prefer `wait_for_event` over `wait_for_event_with_timeout`.
- Prefer `mount_sse_once` over `mount_sse_once_match` or `mount_sse_sequence`
- Typical pattern:
```rust
let mock = responses::mount_sse_once(&server, responses::sse(vec
Codex CLI is an experimental project under active development. It is not yet stable, may contain bugs, incomplete features, or undergo breaking changes. We're building it in the open with the community and welcome:
- Bug reports
- Feature requests
- Pull requests
- Good vibes
Help us improve by filing issues or submitting PRs (see the section below for how to contribute)!
## Quickstart
Install globally:
### Installing and running Codex CLI
Install globally with your preferred package manager. If you use npm:
```shell
npm install -g @openai/codex
```
Next, set your OpenAI API key as an environment variable:
Alternatively, if you use Homebrew:
```shell
exportOPENAI_API_KEY="your-api-key-here"
brew install --cask codex
```
> **Note:** This command sets the key only for your current terminal session. You can add the `export` line to your shell's configuration file (e.g., `~/.zshrc`) but we recommend setting for the session. **Tip:** You can also place your API key into a `.env` file at the root of your project:
>
> ```env
> OPENAI_API_KEY=your-api-key-here
> ```
>
> The CLI will automatically load variables from `.env` (via `dotenv/config`).
<details>
<summary><strong>Use <code>--provider</code> to use other models</strong></summary>
> Codex also allows you to use other providers that support the OpenAI Chat Completions API. You can set the provider in the config file or use the `--provider` flag. The possible options for `--provider` are:
>
> - openai (default)
> - openrouter
> - azure
> - gemini
> - ollama
> - mistral
> - deepseek
> - xai
> - groq
> - arceeai
> - any other provider that is compatible with the OpenAI API
>
> If you use a provider other than OpenAI, you will need to set the API key for the provider in the config file or in the environment variable as:
>
> ```shell
> export <provider>_API_KEY="your-api-key-here"
> ```
>
> If you use a provider not listed above, you must also set the base URL for the provider:
Or, run with a prompt as input (and optionally in `Full Auto` mode):
If you're running into upgrade issues with Homebrew, see the [FAQ entry on brew upgrade codex](./docs/faq.md#brew-upgrade-codex-isnt-upgrading-me).
<details>
<summary>You can also go to the <a href="https://github.com/openai/codex/releases/latest">latest GitHub Release</a> and download the appropriate binary for your platform.</summary>
Each GitHub Release contains many executables, but in practice, you likely want one of these:
- macOS
- Apple Silicon/arm64: `codex-aarch64-apple-darwin.tar.gz`
- x86_64 (older Mac hardware): `codex-x86_64-apple-darwin.tar.gz`
Each archive contains a single entry with the platform baked into the name (e.g., `codex-x86_64-unknown-linux-musl`), so you likely want to rename it to `codex` after extracting it.
Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Team, Edu, or Enterprise plan. [Learn more about what's included in your ChatGPT plan](https://help.openai.com/en/articles/11369540-codex-in-chatgpt).
You can also use Codex with an API key, but this requires [additional setup](./docs/authentication.md#usage-based-billing-alternative-use-an-openai-api-key). If you previously used an API key for usage-based billing, see the [migration steps](./docs/authentication.md#migrating-from-usage-based-billing-api-key). If you're having trouble with login, please comment on [this issue](https://github.com/openai/codex/issues/1243).
### Model Context Protocol (MCP)
Codex can access MCP servers. To configure them, refer to the [config docs](./docs/config.md#mcp_servers).
### Configuration
Codex CLI supports a rich set of configuration options, with preferences stored in `~/.codex/config.toml`. For full configuration options, see [Configuration](./docs/config.md).
### Execpolicy Quickstart
Codex can enforce your own rules-based execution policy before it runs shell commands.
1. Create a policy directory: `mkdir -p ~/.codex/policy`.
2. Create one or more `.codexpolicy` files in that folder. Codex automatically loads every `.codexpolicy` file in there on startup.
3. Write `prefix_rule` entries to describe the commands you want to allow, prompt, or block:
```starlark
prefix_rule(
pattern = ["git", ["push", "fetch"]],
decision = "prompt", # allow | prompt | forbidden
match = [["git", "push", "origin", "main"]], # examples that must match
not_match = [["git", "status"]], # examples that must not match
)
```
-`pattern` is a list of shell tokens, evaluated from left to right; wrap tokens in a nested list to express alternatives (e.g., match both `push` and `fetch`).
-`decision` sets the severity; Codex picks the strictest decision when multiple rules match (forbidden > prompt > allow).
-`match` and `not_match` act as (optional) unit tests. Codex validates them when it loads your policy, so you get feedback if an example has unexpected behavior.
In this example rule, if Codex wants to run commands with the prefix `git push` or `git fetch`, it will first ask for user approval.
Use the `codex execpolicy check` subcommand to preview decisions before you save a rule (see the [`codex-execpolicy` README](./codex-rs/execpolicy/README.md) for syntax details):
```shell
codex "explain this codebase to me"
codex execpolicy check --policy ~/.codex/policy/default.codexpolicy git push origin main
```
```shell
codex --approval-mode full-auto "create the fanciest todo-list app"
```
That's it - Codex will scaffold a file, run it inside a sandbox, install any
missing dependencies, and show you the live result. Approve the changes and
they'll be committed to your working directory.
---
## Why Codex?
Codex CLI is built for developers who already **live in the terminal** and want
ChatGPT-level reasoning **plus** the power to actually run code, manipulate
files, and iterate - all under version control. In short, it's _chat-driven
development_ that understands and executes your repo.
-**Zero setup** - bring your OpenAI API key and it just works!
-**Full auto-approval, while safe + secure** by running network-disabled and directory-sandboxed
- **Multimodal** - pass in screenshots or diagrams to implement features ✨
And it's **fully open-source** so you can see and contribute to how it develops!
---
## Security model & permissions
Codex lets you decide _how much autonomy_ the agent receives and auto-approval policy via the
`--approval-mode` flag (or the interactive onboarding prompt):
| Mode | What the agent may do without asking | Still requires approval |
Key flags: `--model/-m`, `--approval-mode/-a`, `--quiet/-q`, and `--notify`.
---
## Memory & project docs
You can give Codex extra instructions and guidance using `AGENTS.md` files. Codex looks for `AGENTS.md` files in the following places, and merges them top-down:
1.`~/.codex/AGENTS.md` - personal global guidance
2.`AGENTS.md` at repo root - shared project notes
3.`AGENTS.md` in the current working directory - sub-folder/feature specifics
Disable loading of these files with `--no-project-doc` or the environment variable `CODEX_DISABLE_PROJECT_DOC=1`.
---
## Non-interactive / CI mode
Run Codex head-less in pipelines. Example GitHub Action step:
```yaml
- name:Update changelog via Codex
run:|
npm install -g @openai/codex
export OPENAI_API_KEY="${{ secrets.OPENAI_KEY }}"
codex -a auto-edit --quiet "update CHANGELOG for next release"
```
Set `CODEX_QUIET_MODE=1` to silence interactive UI noise.
## Tracing / verbose logging
Setting the environment variable `DEBUG=true` prints full API request and response details:
```shell
DEBUG=true codex
```
---
## Recipes
Below are a few bite-size examples you can copy-paste. Replace the text in quotes with your own task. See the [prompting guide](https://github.com/openai/codex/blob/main/codex-cli/examples/prompting_guide.md) for more tips and usage patterns.
<summary>OpenAI released a model called Codex in 2021 - is this related?</summary>
In 2021, OpenAI released Codex, an AI system designed to generate code from natural language prompts. That original Codex model was deprecated as of March 2023 and is separate from the CLI tool.
</details>
<details>
<summary>Which models are supported?</summary>
Any model available with [Responses API](https://platform.openai.com/docs/api-reference/responses). The default is `o4-mini`, but pass `--model gpt-4.1` or set `model: gpt-4.1` in your config file to override.
</details>
<details>
<summary>Why does <code>o3</code> or <code>o4-mini</code> not work for me?</summary>
It's possible that your [API account needs to be verified](https://help.openai.com/en/articles/10910291-api-organization-verification) in order to start streaming responses and seeing chain of thought summaries from the API. If you're still running into issues, please let us know!
</details>
<details>
<summary>How do I stop Codex from editing my files?</summary>
Codex runs model-generated commands in a sandbox. If a proposed command or file change doesn't look right, you can simply type **n** to deny the command or give the model feedback.
</details>
<details>
<summary>Does it work on Windows?</summary>
Not directly. It requires [Windows Subsystem for Linux (WSL2)](https://learn.microsoft.com/en-us/windows/wsl/install) - Codex has been tested on macOS and Linux with Node 22.
</details>
---
## Zero data retention (ZDR) usage
Codex CLI **does** support OpenAI organizations with [Zero Data Retention (ZDR)](https://platform.openai.com/docs/guides/your-data#zero-data-retention) enabled. If your OpenAI organization has Zero Data Retention enabled and you still encounter errors such as:
```
OpenAI rejected the request. Error details: Status: 400, Code: unsupported_parameter, Type: invalid_request_error, Message: 400 Previous response cannot be used for this organization due to Zero Data Retention.
```
You may need to upgrade to a more recent version with: `npm i -g @openai/codex@latest`
---
## Codex open source fund
We're excited to launch a **$1 million initiative** supporting open source projects that use Codex CLI and other OpenAI models.
- Grants are awarded up to **$25,000** API credits.
- Applications are reviewed **on a rolling basis**.
This project is under active development and the code will likely change pretty significantly. We'll update this message once that's complete!
More broadly we welcome contributions - whether you are opening your very first pull request or you're a seasoned maintainer. At the same time we care about reliability and long-term maintainability, so the bar for merging code is intentionally **high**. The guidelines below spell out what "high-quality" means in practice and should make the whole process transparent and friendly.
### Development workflow
- Create a _topic branch_ from `main` - e.g. `feat/interactive-prompt`.
- Keep your changes focused. Multiple unrelated fixes should be opened as separate PRs.
- Use `pnpm test:watch` during development for super-fast feedback.
- We use **Vitest** for unit tests, **ESLint** + **Prettier** for style, and **TypeScript** for type-checking.
- Before pushing, run the full test/type/lint suite:
### Git hooks with Husky
This project uses [Husky](https://typicode.github.io/husky/) to enforce code quality checks:
- **Pre-commit hook**: Automatically runs lint-staged to format and lint files before committing
- **Pre-push hook**: Runs tests and type checking before pushing to the remote
These hooks help maintain code quality and prevent pushing code with failing tests. For more details, see [HUSKY.md](./codex-cli/HUSKY.md).
```bash
pnpm test&& pnpm run lint && pnpm run typecheck
```
- If you have **not** yet signed the Contributor License Agreement (CLA), add a PR comment containing the exact text
```text
I have read the CLA Document and I hereby sign the CLA
```
The CLA-Assistant bot will turn the PR status green once all authors have signed.
```bash
# Watch mode (tests rerun on change)
pnpm test:watch
# Type-check without emitting files
pnpm typecheck
# Automatically fix lint + prettier issues
pnpm lint:fix
pnpm format:fix
```
### Debugging
To debug the CLI with a visual debugger, do the following in the `codex-cli` folder:
- Run `pnpm run build` to build the CLI, which will generate `cli.js.map` alongside `cli.js` in the `dist` folder.
- Run the CLI with `node --inspect-brk ./dist/cli.js` The program then waits until a debugger is attached before proceeding. Options:
- In VS Code, choose **Debug: Attach to Node Process** from the command palette and choose the option in the dropdown with debug port `9229` (likely the first option)
- Go to <chrome://inspect> in Chrome and find **localhost:9229** and click **trace**
### Writing high-impact code changes
1. **Start with an issue.** Open a new one or comment on an existing discussion so we can agree on the solution before code is written.
2. **Add or update tests.** Every new feature or bug-fix should come with test coverage that fails before your change and passes afterwards. 100% coverage is not required, but aim for meaningful assertions.
3. **Document behaviour.** If your change affects user-facing behaviour, update the README, inline help (`codex --help`), or relevant example projects.
4. **Keep commits atomic.** Each commit should compile and the tests should pass. This makes reviews and potential rollbacks easier.
### Opening a pull request
- Fill in the PR template (or include similar information) - **What? Why? How?**
- Run **all** checks locally (`npm test && npm run lint && npm run typecheck`). CI failures that could have been caught locally slow down the process.
- Make sure your branch is up-to-date with `main` and that you have resolved merge conflicts.
- Mark the PR as **Ready for review** only when you believe it is in a merge-able state.
### Review process
1. One maintainer will be assigned as a primary reviewer.
2. We may ask for changes - please do not take this personally. We value the work, we just also value consistency and long-term maintainability.
3. When there is consensus that the PR meets the bar, a maintainer will squash-and-merge.
### Community values
- **Be kind and inclusive.** Treat others with respect; we follow the [Contributor Covenant](https://www.contributor-covenant.org/).
- **Assume good intent.** Written communication is hard - err on the side of generosity.
- **Teach & learn.** If you spot something confusing, open an issue or PR with improvements.
### Getting help
If you run into problems setting up the project, would like feedback on an idea, or just want to say _hi_ - please open a Discussion or jump into the relevant issue. We are happy to help.
Together we can make Codex CLI an incredible tool. **Happy hacking!** :rocket:
### Contributor license agreement (CLA)
All contributors **must** accept the CLA. The process is lightweight:
1. Open your pull request.
2. Paste the following comment (or reply `recheck` if you've signed before):
```text
I have read the CLA Document and I hereby sign the CLA
```
3. The CLA-Assistant bot records your signature in the repo and marks the status check as passed.
No special Git commands, email attachments, or commit footers required.
Have you discovered a vulnerability or have concerns about model output? Please e-mail **security@openai.com** and we will respond promptly.
Pass multiple `--policy` flags to test how several files combine, and use `--pretty` for formatted JSON output. See the [`codex-rs/execpolicy` README](./codex-rs/execpolicy/README.md) for a more detailed walkthrough of the available syntax.
## Note: `execpolicy` commands are still in preview. The API may have breaking changes in the future.
- Load rollouts from `sessions/rollout-<UUID>.jsonl`.
- Printed resume command on exit: `codex session <UUID>`.
## codex-core enhancements
- Exposed core model types: `ContentItem`, `ReasoningItemReasoningSummary`, `ResponseItem`.
- Added `composer_max_rows` setting (with serde default) to TUI configuration.
## Dependency updates
- Added `uuid` crate to `codex-rs/cli` and `codex-rs/tui`.
## Pre-commit config changes
- Configured Rust build hook in `.pre-commit-config.yaml` to fail on warnings by setting `RUSTFLAGS="-D warnings"`.
## codex-rs/tui: Undo feedback decision with Esc key
- Pressing `Esc` in feedback-entry mode now cancels feedback entry and returns to the select menu, preserving the partially entered feedback text.
- Added a unit test for the ESC cancellation behavior in `tui/src/user_approval_widget.rs`.
## codex-rs/tui: restore inline mount DSL and slash-command dispatch
- Reintroduced logic in `ChatComposer` to dispatch `AppEvent::InlineMountAdd` and `AppEvent::InlineMountRemove` when `/mount-add` or `/mount-remove` is entered with inline arguments.
- Restored dispatch of `AppEvent::DispatchCommand` for slash commands selected via the command popup, including proper cleanup of the composer input.
- Added `markdown_compact` config flag under UI settings to collapse heading-content spacing when enabled.
- When enabled, headings render immediately adjacent to content with no blank line between them.
- Updated Markdown rendering in chat UI and logs to honor compact mode globally (diffs, docs, help messages).
- Added unit tests covering H1–H6 heading spacing for both compact and default modes.
## codex-rs: document MCP servers example in README
- Added an inline TOML snippet under “Model Context Protocol Support” in `codex-rs/README.md` showing how to configure external `mcp_servers` entries in `~/.codex/config.toml`.
- Documented `codex mcp` behavior: JSON-RPC over stdin/stdout, optional sandbox, no ephemeral container, default `codex` tool schema, and example ListTools/CallTool schema.
## Documentation tasks
## codex-rs/tui: interactive shell-command affordance via hotkey
- Bound `Ctrl+M` to open a ShellCommandView overlay for arbitrary container shell input.
- Toggled shell-command mode with `Ctrl+M` to enter or exit prompt, with styled border in shell mode.
- Executed commands asynchronously (`sh -c`) and recorded outputs inline in conversation history.
- Added unit tests for ShellCommandView event emission and shell-mode toggling behavior.
Tasks live under `agentydragon/tasks/` as individual Markdown files. Please update each task’s **Status** and **Implementation** sections in place rather than maintaining a static list here.
### Branch & Worktree Workflow
- **Branch convention**: work on each task in its own branch named `agentydragon-<task-id>-<task-slug>`, to avoid refname conflicts.
- **Worktree helper**: in `agentydragon/tasks/`, run:
-
- ```sh
- # Accept a full slug (NN-slug) or two-digit task ID (NN), optionally multiple; --tmux opens each in its own tmux pane and auto-commits each task as its Developer agent finishes:
- Without `--agent`, this creates or reuses a worktree at
-`agentydragon/tasks/.worktrees/<task-id>-<task-slug>` off the `agentydragon` branch.
- Internally, the helper uses CoW hydration instead of a normal checkout: it registers the worktree with `git worktree add --no-checkout`, then performs a filesystem-level reflink
- of all files (macOS: `cp -cRp`; Linux: `cp --reflink=auto`), falling back to `rsync` if reflinks aren’t supported. This makes new worktrees appear nearly instantly on supported filesystems while
- preserving untracked files.
- With `--agent`, after setting up a new worktree it runs presubmit pre-commit checks (aborting with a clear message on failure unless `--skip-presubmit` is passed), then launches the Developer Codex agent (using `prompts/developer.md` and the task file).
- After the Developer agent exits, if the task’s **Status** is set to `Done`, it automatically runs the Commit agent helper to stage fixes and commit the work.
**Commit agent helper**: in `agentydragon/tasks/`, run:
```sh
# Generate and apply commit(s) for completed task(s) in their worktrees:
After the Developer agent finishes and updates the task file, the Commit agent will write the commit message to a temporary file and then commit using that file (`git commit -F`). An external orchestrator can then stage files and run pre-commit hooks as usual. You do not need to run `git commit` manually.
---
*This README was autogenerated to summarize changes on the `agentydragon` branch.*
This document explains the multi-agent handoff pattern used for task development and commits
in the `agentydragon` workspace. It consolidates shared guidance so individual agent prompts
do not need to repeat these details.
## 1. Developer Agent
- **Scope**: Runs inside a sandboxed git worktree for a single task branch (`agentydragon-<ID>-<slug>`).
- **Actions**:
1. If the task’s **Status** is `Needs input`, stop immediately and await further instructions; do **not** implement code changes or run pre-commit hooks.
2. Update the task Markdown file’s **Status** to `Done` when implementation is complete.
3. Implement the code changes for the task.
4. Run `pre-commit run --files $(git diff --name-only)` to apply and stage any autofix changes.
5.**Do not** run `git commit`.
## 2. Commit Agent
- **Scope**: Runs in the sandbox (read-only `.git`) or equivalent environment.
- **Actions**:
1. Emit exactly one line to stdout: the commit message prefixed `agentydragon(tasks): `
summarizing the task’s **Implementation** section.
2. Stop immediately.
## 3. Orchestrator
- **Scope**: Outside the sandbox with full Git permissions.
- **Actions**:
1. Stage all changes: `git add -u`.
2. Run `pre-commit run --files $(git diff --name-only --cached)`.
3. Read the commit message and run `git commit -m "$MSG"`.
## 4. Status & Launch
- Use `agentydragon_task.py status` to view tasks (including those in `.done/`).
- Summaries:
- **Merged:** tasks with no branch/worktree.
- **Ready to merge:** tasks marked Done with branch commits ahead.
- **Unblocked:** tasks with no outstanding dependencies.
- The script also prints a `agentydragon/tools/create_task_worktree.py --agent --tmux <IDs>` command for all unblocked tasks.
This guide centralizes the handoff workflow for all agents.
Refer to `agentydragon/WORKFLOW.md` for the overall Developer→Commit→Orchestrator handoff workflow.
You are the **Commit** Codex agent for the `codex` repository. Your job is to stage and commit the changes made by the Developer agent.
Your sole responsibility is to generate the Git commit message on stdout.
Do **not** modify any files or run Git commands; this agent must remain sandbox-friendly.
When you run, **output exactly** the desired commit message (with no extra commentary) on stdout. The message must:
- Be prefixed with `agentydragon(tasks): `
- Concisely summarize the work performed as described in the task’s **Implementation** section.
Stop immediately after emitting the commit message. An external orchestrator will stage, run hooks, and commit using this message.
Below, you will get the task description the agent got. But still verify that the agent actually did what it was supposed to, and adjust the commit message according to what is actually implemented, DO NOT just copy what's in the task file.
Refer to `agentydragon/WORKFLOW.md` for the overall Developer→Commit→Orchestrator handoff workflow.
You are the **Developer** Codex agent for the `codex` repository. You are running inside a dedicated git worktree for a single task branch.
Use the task Markdown file under `agentydragon/tasks/` as your progress tracker: update its **Status** and **Implementation** sections to record your progress.
Before making any changes, read the task definition in `agentydragon/tasks/` and note that its **Status** and **Implementation** sections are placeholders.
After reviewing, update the task’s **Status** to "In progress" and fill in the **Implementation** section with your planned approach.
If the **Implementation** section is blank or does not describe your intended design and steps, populate it with a concise high‑level plan before proceeding.
Then proceed directly to implement the full functionality in the codebase as a single atomic unit—regardless of how many components are involved, do not split the work into separate sub-steps or pause to ask whether to decompose it.
Do not pause to seek user confirmation after editing the Markdown;
only ask clarifying questions if you encounter genuine ambiguities in the requirements.
At any point, you may set the task’s **Status** to any valid state (e.g. Not started, In progress, Needs input, Needs manual review, Done, Cancelled) as appropriate. Use **Needs input** to request further clarification or resources before proceeding.
When you have finished working on the task file:
- If the task’s **Status** is "Needs input", stop immediately and await further instructions; do **not** run pre-commit hooks or invoke the Commit agent.
- Otherwise, set the task’s **Status** to "Done".
- Run the repository’s pre-commit hooks on all changed files (e.g. `pre-commit run --files <changed-files>`), and stage any autofix changes.
- Do **not** stage or commit beyond hook-driven fixes. Instead, stop and await the Commit agent to record your updates.
You are the **Project Manager** Codex agent for the `codex` repository.
Refer to `agentydragon/WORKFLOW.md` for the standard Developer→Commit→Orchestrator handoff workflow.
Your responsibilities include:
- **Reading documentation**: Load and understand all relevant docs in this repo (especially those defining task, worktree, and branch conventions, as well as each task file and top‑level README files).
- **Task orchestration**: Maintain the list of tasks, statuses, and dependencies; plan waves of work; and generate commands to launch work in parallel using `agentydragon/tools/create_task_worktree.py` (or the legacy `agentydragon/tools/create-task-worktree.sh`) with `--agent` and `--tmux`.
- **Task creation**: When creating a new task stub, review the descriptions of all existing tasks; set the `dependencies` front-matter field to list the tasks that must be completed before work on this task can begin; and include a brief rationale as a Markdown comment (e.g., `<!-- rationale: depends on tasks X and Y because ... -->`) explaining why these dependencies are required and why other tasks are not.
- **Live coordination**: Continuously monitor and report progress, adjust the plan as tasks complete or new ones appear, and surface any blockers.
- **Worktree monitoring**: Check each task’s worktree for uncommitted changes or dirty state to detect agents still working or potential crashes, and report their status as in-progress or needing attention.
- When displaying the task-status table, highlight dirty worktrees in red and tasks marked Done or Merged in green; exclude tasks that are Merged with no branch and no worktree from the main table (they should instead be listed in a green “Done&merged:” summary at the bottom), and filter such merged tasks out of other tasks’ dependency lists.
- **Background polling**: On user request, enter a sleep‑and‑scan loop (e.g. 5min interval) to detect tasks marked “Done” in their Markdown; for each completed task, review its branch worktree, check for merge conflicts, propose merging cleanly mergeable branches, and suggest conflict‑resolution steps for any that aren’t cleanly mergeable.
- **Manager utilities**: Create and maintain utility scripts under `agentydragon/tools/manager_utils/` to support your work (e.g., branch scanning, conflict checking, merge proposals, polling loops). Include clear documentation (header comments or docstrings with usage examples) in each script, and invoke these scripts in your workflow.
- **Merge orchestration**: When proposing merges of completed task branches into the integration branch, consider both single-branch and octopus (multi-branch) merges. Detect and report conflicts between branches as well as with the integration branch, and recommend resolution steps or merge ordering to avoid or resolve conflicts.
### First Actions
1. For each task branch (named `agentydragon-<task-id>-<task-slug>`), **without changing the current working directory’s Git HEAD or modifying its status**, create or open a dedicated worktree for that branch (e.g. via `agentydragon/tools/create_task_worktree.py <task-slug>`) and read the task’s Markdown copy in that worktree to extract and list the task number, title, live **Status**, and dependencies. *(Always read the **Status** and dependencies from the copy of the task file in the branch’s worktree, never from master/HEAD.)*
2. Produce a one‑line tmux launch command to spin up only those tasks whose dependencies are satisfied and can actually run in parallel, following the conventions defined in repository documentation.
3. Describe the high‑level wave‑by‑wave plan and explain which tasks can run in parallel.
More functionality and refinements will be added later. Begin by executing these steps and await further instructions.
*If instructed, enter a background polling loop (sleep for a configured interval, e.g. 5minutes) to watch for tasks whose Markdown status is updated to “Done” and then prepare review/merge steps for only those branches.*
Once a task branch is merged cleanly into the integration branch, dispose of its worktree and delete its Git branch. To record that merge, use:
Use `python3 agentydragon/tools/manager_utils/agentydragon_task.py dispose <task-id>` to remove the worktree and branch without changing the status (e.g. for cancelled tasks).
read the description of all tasks in agentydragon/tasks/*.md and relevant context in codex-rs. for every task: disregard existing dependecy declarations in the frontmatter. think long about
why and how they might depend on each other and if there's any way they might conflict and whether the overall picturen of how they fit toether makes sense. for each, *REGENERATE* the
dependency list in frontmatter to the list of tasks the muast be done before each gvien taks becomes unblocked. no need to populate this for already merged tasks. also no need to list
You are the AI “Scaffolding Assistant” for the `codex` monorepo. Your mission is to generate, in separate commits, all of the initial scaffolding needed for the
tydragon-driven task workflow:
1.**Task stubs**
- Create `agentydragon/tasks/task-template.md`.
- Create numbered task stubs (`01-*.md`, `02-*.md`, …) for each planned feature (mounting, approval predicates, live‑reload, editor integration, etc.), filling in
e, “Status”, “Goal”, and sections for “Acceptance Criteria”, “Implementation”, and “Notes”.
-`--agent` mode to spin up a Codex agent in the worktree,
-`--tmux` to tile panes for multiple tasks in a single tmux session,
- two‑digit or slug ID resolution.
- Ensure usage, help text, and numeric/slug handling are correct.
3.**Helper scripts**
- Add `agentydragon/tasks/review-unmerged-task-branches.sh` to review and merge task branches.
- Add `agentydragon/tools/launch-project-manager.sh` to invoke the Project Manager agent prompt.
4.**Project‑manager prompts**
- Create `agentydragon/prompts/manager.md` containing the following Project Manager agent prompt:
```
# Project Manager Agent Prompt
You are the **Project Manager** Codex agent for the `codex` repository. Your responsibilities include:
- **Reading documentation**: Load and understand all relevant docs in this repo (especially those defining task, worktree, and branch conventions, as well as each task file and top‑level README files).
- **Task orchestration**: Maintain the list of tasks, statuses, and dependencies; plan waves of work; and generate shell commands to launch work on tasks in parallel using `create_task_worktree.py` with `--agent` and `--tmux`.
- **Live coordination**: Continuously monitor and report progress, adjust the plan as tasks complete or new ones appear, and surface any blockers.
- **Worktree monitoring**: Check each task’s worktree for uncommitted changes or dirty state to detect agents still working or potential crashes, and report their status as in-progress or needing attention.
- **Background polling**: On user request, enter a sleep‑and‑scan loop (e.g. 5min interval) to detect tasks marked “Done” in their Markdown; for each completed task, review its branch worktree, check for merge conflicts, propose merging cleanly mergeable branches, and suggest conflict‑resolution steps for any that aren’t cleanly mergeable.
- **Manager utilities**: Create and maintain utility scripts under `agentydragon/tools/manager_utils/` to support your work (e.g., branch scanning, conflict checking, merge proposals, polling loops). Include clear documentation (header comments or docstrings with usage examples) in each script, and invoke these scripts in your workflow.
- **Merge orchestration**: When proposing merges of completed task branches into the integration branch, consider both single-branch and octopus (multi-branch) merges. Detect and report conflicts between branches as well as with the integration branch, and recommend resolution steps or merge ordering to avoid or resolve conflicts.
### First Actions
1. For each task branch (named `agentydragon-<task-id>-<task-slug>`), **without changing the current working directory’s Git HEAD or modifying its status**, create or open a dedicated worktree for that branch (e.g. via `create_task_worktree.py <task-slug>`) and read the task’s Markdown copy under that worktree’s `agentydragon/tasks/` to extract and list the task number, title, live **Status**, and dependencies. *(Always read the **Status** and dependencies from the copy of the task file in the branch’s worktree, never from master/HEAD.)*
2. Produce a one‑line tmux launch command to spin up only those tasks whose dependencies are satisfied and can actually run in parallel, following the conventions defined in repository documentation.
3. Describe the high‑level wave‑by‑wave plan and explain which tasks can run in parallel.
More functionality and refinements will be added later. Begin by executing these steps and await further instructions.
```
5. **Wave‑by‑wave plan**
- Draft a human‑readable plan outlining task dependencies and four “waves” of work, indicating which tasks can run in parallel.
6. **Bootstrap commands**
- Provide concrete shell/`rg`/`tmux` oneliner examples to launch Wave1 (e.g. tasks06,03,08) in parallel.
- Provide a single tmux oneliner to spin up all unblocked tasks.
**Before you begin**, read the existing docs under `agentydragon/tasks/`, top‑level `README.md` and `oaipackaging/README.md` so you fully understand the context and
entions.
**Commit strategy**
- Commit each major component (tasks, script, helper scripts, prompts, plan) as its own Git commit.
- Follow our existing commit-message style: prefix with `agentydragon(tasks):`, `agentydragon:`, etc.
- Don’t batch everything into one huge commit; keep each logical piece isolated for easy review.
**Reporting**
After each commit, print a short status message (e.g. “✅ Task stubs created”, “✅ create_task_worktree.py implemented”, etc.) and await confirmation before continuing
the next step.
---
Begin now by listing the current task directory contents and generating `task-template.md`.
title = "Dynamic Mount-Add and Mount-Remove Commands"
status = "Merged"
dependencies = ""
last_updated = "2025-06-25T01:40:09.501150"
+++
# Task 01: Dynamic Mount-Add and Mount-Remove Commands
> *This task is specific to codex-rs.*
## Status
**General Status**: Merged
**Summary**: Implemented inline DSL and interactive dialogs for `/mount-add` and `/mount-remove`, with dynamic sandbox policy updates.
## Goal
Implement the `/mount-add` and `/mount-remove` slash commands in the TUI, supporting two modes:
1.**Inline DSL**: e.g. `/mount-add host=/path/to/host container=/path/in/agent mode=rw`
2.**Interactive dialog**: if the user just types `/mount-add` or `/mount-remove` without args, pop up a prompt to fill in `host`, `container`, and optional `mode` fields.
These commands should:
- Create or remove symlinks (or real directories) under the current working directory.
- Update the in-memory `SandboxPolicy` to grant or revoke read/write permission for the host path.
- Emit confirmation or error messages into the TUI log pane.
## Acceptance Criteria
- Users can type `/mount-add host=... container=... mode=...` and the mount is created immediately.
- Users can type `/mount-add` alone to open a small TUI form prompting for the three fields.
- Symmetrically for `/mount-remove` by container path.
- The `sandbox_policy` is updated so subsequent shell commands can read/write the newly mounted folder.
## Implementation
**How it was implemented**
- Added two new slash commands (`mount-add`, `mount-remove`) to the TUI’s `slash-command` popup.
- Inline DSL parsing: commands typed as `/mount-add host=... container=... mode=...` or `/mount-remove container=...` are detected and handled immediately by parsing key/value args, performing the mount/unmount, and updating the `Config.sandbox_policy` in memory.
- Interactive dialogs: selecting `/mount-add` or `/mount-remove` without args opens a bottom‑pane form (`MountAddView` or `MountRemoveView`) that prompts sequentially for the required fields and then triggers the same mount logic.
- Mount logic implemented in `do_mount_add`/`do_mount_remove`:
- Creates/removes a symlink under `cwd` pointing to the host path (`std::os::unix::fs::symlink` on Unix, platform equivalents on Windows).
- Uses new `SandboxPolicy` methods (`allow_disk_write_folder`/`revoke_disk_write_folder`) to grant or revoke `DiskWriteFolder` permissions for the host path.
- Emits success or error messages via `tracing::info!`/`tracing::error!`, which appear in the TUI log pane.
- The first-stage popup intercepts the mount-add command with args, dispatches `InlineMountAdd`, and the app parses the args and runs the mount logic immediately.
2. **Interactive dialog**
- User types `/mount-add` (or selects it via the popup) without args.
- A small form appears that prompts for `host`, `container`, then `mode`.
- Upon completion, the same mount logic runs.
3. **Unmount**
- `/mount-remove container=...` (inline) or `/mount-remove` (interactive) remove the symlink and revoke write permissions.
4. **Policy update**
- `allow_disk_write_folder` appends a `DiskWriteFolder` permission for new mounts.
- `revoke_disk_write_folder` removes the corresponding permission on unmount.
## Notes
- This builds on the static `[[sandbox.mounts]]` support introduced earlier.
title = "Live Config Reload and Prompt on Changes"
status = "Merged"
dependencies = "02,07,09,11,14,29"
last_updated = "2025-06-25T05:36:17.783726"
+++
# Task 03: Live Config Reload and Prompt on Changes
> *This task is specific to codex-rs.*
## Status
**General Status**: Done
**Summary**: Live config watcher, diff prompt, and reload integration implemented.
## Goal
Detect changes to the user `config.toml` file while a session is running and prompt the user to apply or ignore the updated settings.
## Acceptance Criteria
- A background file watcher watches `$CODEX_HOME/config.toml` (or active user config path).
- On any write event, compute a unified diff between the in-memory config and the on-disk file.
- Pause the agent, display the diff in the TUI bottom pane, and offer two actions: `Apply new config now` or `Continue with old config`.
- If the user applies, re-parse the config, merge overrides, and resume using the new settings. Otherwise, discard changes and resume.
## Implementation
**How it was implemented**
- Added `codex_tui::config_reload::generate_diff` to compute unified diffs via the `similar` crate (with a unit test).
- Spawned a `notify`-based filesystem watcher thread in `tui::run_main` that debounces write events on `$CODEX_HOME/config.toml`, generates diffs against the last-read contents, and posts `AppEvent::ConfigReloadRequest(diff)`.
- Introduced `AppEvent` variants (`ConfigReloadRequest`, `ConfigReloadApply`, `ConfigReloadIgnore`) and wired them in `App::run` to display a new `BottomPaneView` overlay.
- Created `BottomPaneView` implementation `ConfigReloadView` to render the diff and handle `<Enter>`/`<Esc>` for apply or ignore.
- On apply, reloaded `Config` via `Config::load_with_cli_overrides`, updated both `App.config` and `ChatWidget` (rebuilding its bottom pane with updated settings).
**How it works**
- The watcher thread detects on-disk changes and pushes a diff request into the UI event loop.
- Upon `ConfigReloadRequest`, the TUI bottom pane overlays the diff view and blocks normal input.
-`<Enter>` applies the new config (re-parses and updates runtime state); `<Esc>` dismisses the overlay and continues with the old settings.
## Notes
- Leverage a crate such as `notify` for FS events and `similar` or `diff` for unified diff generation.
title = "External Editor Integration for Prompt Entry"
status = "Merged"
dependencies = "02,07,09,11,14,29"
last_updated = "2025-06-25T02:40:09.505778"
+++
# Task 06: External Editor Integration for Prompt Entry
> *This task is specific to codex-rs.*
## Status
**General Status**: Done
**Summary**: External editor integration for prompt entry implemented.
## Goal
Allow users to spawn an external editor (e.g. Neovim) to compose or edit the chat prompt. The prompt box should update with the editor's contents when closed.
## Acceptance Criteria
- A slash command `/edit-prompt` (or `Ctrl+E`) launches the user's preferred editor on a temporary file pre-populated with the current draft.
- Upon editor exit, the draft is re-read into the composer widget.
- Configurable via `editor = "${VISUAL:-${EDITOR:-nvim}}"` setting in `config.toml`.
## Implementation
**How it was implemented**
- Added `editor` option to `[tui]` section in `config.toml`, defaulting to `${VISUAL:-${EDITOR:-nvim}}`.
- Exposed the `tui.editor` setting in the `codex-core` config model (`config_types.rs`) and wired it through to the TUI.
- Added a new slash-command variant `EditPrompt` in `tui/src/slash_command.rs` to trigger external-editor mode.
- Implemented `ChatComposer::open_external_editor()` in `tui/src/bottom_pane/chat_composer.rs`:
- Creates a temporary file pre-populated with the current draft prompt.
- Launches the configured editor (from `VISUAL`/`EDITOR` with `nvim` fallback) in a blocking subprocess.
- Reads the edited contents back into the `TextArea` on editor exit.
- Wired both `Ctrl+E` and the `/edit-prompt` slash command to invoke `open_external_editor()`.
- Updated `config.md` to document the new `editor` setting under `[tui]`.
**How it works**
- Pressing `Ctrl+E`, or typing `/edit-prompt` and hitting Enter, spawns the user's preferred editor on a temporary file containing the current draft.
- When the editor process exits, the plugin reads back the file and updates the chat composer with the edited text.
- The default editor is determined by `VISUAL`, then `EDITOR`, falling back to `nvim` if neither is set.
**Summary**: ESC key now cancels feedback entry and returns to the select menu, preserving any entered text; implementation and tests added.
## Goal
Enhance the user-approval dialog so that if the user opted to leave feedback (“No, enter feedback”) they can press `Esc` to cancel the feedback flow and return to the previous approval choice menu (e.g. “Yes, proceed” vs. “No, enter feedback”).
## Acceptance Criteria
- While the feedback-entry textarea is active, pressing `Esc` closes the feedback editor and reopens the yes/no confirmation dialog.
- The cancellation must restore the dialog state without losing any partially entered feedback text.
## Implementation
**How it was implemented**
- In `tui/src/user_approval_widget.rs`, updated `UserApprovalWidget::handle_input_key` so that pressing `Esc` in input mode switches `mode` back to `Select` (rather than sending a deny decision), and restores `selected_option` to the feedback entry item without clearing the input buffer.
- Added a unit test in the same module to verify that `Esc` cancels input mode, preserves the feedback text, and does not emit any decision event.
**How it works**
- When the widget is in `Mode::Input` (feedback-entry), receiving `KeyCode::Esc` resets `mode` to `Select` and sets `selected_option` to the index of the “Edit or give feedback” option.
- The `input` buffer remains intact, so any partially typed feedback is preserved for if/when the user re-enters feedback mode.
- No approval decision is sent on `Esc`, so the modal remains active and the user can still approve, deny, or re-enter feedback.
## Notes
- Changes in `tui/src/user_approval_widget.rs` to treat `Esc` in input mode as a cancel-feedback action and added corresponding tests.
title = "Set Shell Title to Reflect Session Status"
status = "Merged"
dependencies = "02,07,09,11,14,29"
last_updated = "2025-06-25T04:06:55.265790"
+++
# Task 08: Set Shell Title to Reflect Session Status
> *This task is specific to codex-rs.*
## Status
**General Status**: Done
**Summary**: Implemented session title persistence, `/set-title` slash command, and real-time ANSI updates in both TUI and exec clients.
## Goal
Allow the CLI to update the terminal title bar to reflect the current session status—executing, thinking (sampling), idle, or waiting for approval decision—and persist the title with the session. Users should also be able to explicitly set a custom title.
## Acceptance Criteria
- Implement a slash command or API (`/set-title <title>`) for users to explicitly set the session title.
- Persist the title in session metadata so that on resume the last title is restored.
- Dynamically update the shell/terminal title in real time based on session events:
- Executing: use a play symbol (e.g. ▶)
- Thinking/sampling: use an hourglass or brain symbol (e.g. ⏳)
- Idle: use a green dot or sleep symbol (e.g. 🟢)
- Waiting for approval decision: use an attention-grabbing symbol (e.g. ❗)
- Ensure title updates work across Linux, macOS, and Windows terminals via ANSI escape sequences.
## Implementation
**Note**: Populate this section with a concise high-level plan before beginning detailed implementation.
**Planned approach**
- Extend the session protocol schema (`SessionConfiguredEvent`) in `codex-rs/core` to include an optional `title` field and introduce a new `SessionUpdatedTitleEvent` type.
- Add a `SetTitle { title: String }` variant to the `Op` enum for custom titles and implement the `/set-title <text>` slash command in the TUI crates (`tui/src/slash_command.rs`, `tui/src/app_event.rs`, and `tui/src/app.rs`).
- Modify the core agent loop to handle `Op::SetTitle`: persist the new title in session metadata, emit a `SessionUpdatedTitleEvent`, and include the persisted title in `SessionConfiguredEvent` on startup/resume.
- Implement event listeners in both the interactive TUI (`tui/src/chatwidget.rs`) and non-interactive exec client (`exec/src/event_processor.rs`) that respond to session, title, and lifecycle events (session start, task begin/end, reasoning, idle, approval) by emitting ANSI escape sequences (`\x1b]0;<symbol> <title>\x07`) to update the terminal title bar.
- Choose consistent Unicode symbols for each session state—executing (▶), thinking (⏳), idle (🟢), awaiting approval (❗)—and apply these as status indicators prefixed to the title.
- On session startup or resume, restore the last persisted title or fall back to a default if none exists.
**How it works**
- Users type `/set-title MyTitle` to set a custom session title; the core persists it and broadcasts a `SessionUpdatedTitleEvent`.
- Clients print the appropriate ANSI escape code to update the terminal title before rendering UI or logs, reflecting real-time session state via the selected status symbol prefix.
## Notes
- Use ANSI escape code `\033]0;<title>\007` to set the terminal title.
- Extend the session JSON schema to include a `title` field.
- Select Unicode symbols that render consistently in common terminal fonts.
title = "Inspect Container State (Mounts, Permissions, Network)"
status = "Merged"
dependencies = ""
last_updated = "2025-06-25T04:07:56.197523"
+++
# Task 10: Inspect Container State (Mounts, Permissions, Network)
> *This task is specific to codex-rs.*
## Status
**General Status**: Completed
**Summary**: Implemented `codex inspect-env` subcommand, CLI output and TUI bindings, tested in sandbox and headless modes.
## Goal
Provide a runtime command that displays the current sandbox/container environment details—what is mounted where, permission scopes, network access status, and other relevant sandbox policies.
## Acceptance Criteria
- Implement a slash command or CLI subcommand (`/inspect-env` or `codex inspect-env`) that outputs:
- List of bind mounts (host path → container path, mode)
- File-system permission policies in effect
- Network sandbox status (restricted or allowed)
- Runtime TUI status‑bar indicators for key sandbox attributes (e.g. network enabled/disabled, mount count, read/write scopes)
- Any additional sandbox rules or policy settings applied
- Format the output in a human-readable table or tree view in the TUI and plaintext for logs.
- Ensure the command works in both interactive TUI sessions and non-interactive (headless) modes.
- Include a brief explanation header summarizing each section to help users understand what they are seeing.
## Implementation
**How it was implemented**
Implemented a new `inspect-env` subcommand in `codex-cli`, reusing `create_sandbox_policy` and `Config::load_with_cli_overrides` to derive the effective sandbox policy and working directory. The code computes read-only or read-write mount entries (root and writable roots), enumerates granted `SandboxPermission`s, and checks `has_full_network_access()`. It then prints a formatted table (via `println!`) and summary counts.
**How it works**
Running `codex inspect-env` loads user overrides, builds the sandbox policy, and:
- Lists mounts (path and mode) in a table.
- Prints each granted permission.
- Shows network status as `enabled`/`disabled`.
- Outputs summary counts for mounts and writable roots.
This command works both in CI/headless and inside the TUI (status-bar integration).
## Notes
- Leverage existing sandbox policy data structures used at startup.
- Reuse TUI table or tree components for formatting (e.g., tui-rs widgets).
- Include clear labels for network status (e.g., `NETWORK: disabled` or `NETWORK: enabled`).
Allow users to plug in an external executable that makes approval decisions for shell commands based on session context.
## Acceptance Criteria
- Support a new `[[approval_predicates]]` section in `config.toml` for Python-based predicates, each with a `python_predicate_binary = "..."` field (pointing to the predicate executable) and an implicit `never_expire = true` setting.
- Before prompting the user, invoke each configured predicate in order, passing the following (via CLI args or env vars):
- Session ID
- Container working directory (CWD)
- Host working directory (CWD)
- Candidate shell command string
- The predicate must print exactly one of `allow`, `deny`, or `ask` on stdout:
-`allow` → auto-approve and skip remaining predicates
-`deny` → auto-reject and skip remaining predicates
-`ask` → open the standard approval dialog and skip remaining predicates
- If a predicate exits non-zero or outputs anything else, treat it as `ask` and continue to the next predicate.
- Write unit and integration tests covering typical and edge-case predicate behavior.
- Document configuration syntax and behavior in the top-level config docs (`config.md`).
## Implementation
**How it was implemented**
- Added `approval_predicates` field to `ConfigToml` and `Config` in `codex_core::config`, supporting a `python_predicate_binary: PathBuf` and an implicit `never_expire = true`.
- Hooked into the command-approval code path in `codex_core::safety` to invoke each configured predicate executable before showing the approval prompt. Predicates are launched via `std::process::Command` with context passed in environment variables (`CODEX_SESSION_ID`, `CODEX_CONTAINER_CWD`, `CODEX_HOST_CWD`, `CODEX_COMMAND`).
- Parsed each predicate’s stdout for exactly `allow`, `deny`, or `ask`, short-circuiting on `allow` or `deny` (auto-approve/auto-reject) and treating failures or unexpected output as `ask` to continue to the next predicate.
- Wrote unit tests for configuration parsing and predicate-invocation behavior, covering exit-code and output edge cases, plus integration tests verifying end-to-end approval decisions.
- Updated `config.md` to document the `[[approval_predicates]]` table syntax, default semantics, and runtime behavior.
**How it works**
When a shell command requires approval, Codex iterates over each entry in `[[approval_predicates]]` in order. For each predicate:
- Launch the configured binary with session context in its environment.
- If it exits successfully and writes `allow`, Codex auto-approves and skips remaining predicates.
- If it writes `deny`, Codex auto-rejects and skips remaining predicates.
- Otherwise (writes `ask`, fails, or emits unexpected output), Codex moves to the next predicate or falls back to the manual approval dialog if none return `allow` or `deny`.
This mechanism lets users automate approval decisions via custom Python scripts while retaining manual control when predicates defer.
- Reuse invocation logic from the auto-approval predicates feature (Task02).
- **Motivating example**: auto-approve `pre-commit run --files <any number of space-separated files>`.
- **Motivating example**: auto-approve any `git` command (e.g. `git add`, `git commit`, `git push`, `git status`, etc.) provided its repository root is under `<directory>`, correctly handling common flags and safe invocation modes.
- **Motivating example**: auto-approve any shell pipeline composed out of `<these known-safe commands>` operating on `<known-safe files>` with `<known-safe params>`, using a general pipeline parser to ensure safety—a nontrivial example of predicate logic.
title = "Interactive Prompting and Commands While Executing"
status = "Merged"
dependencies = "02,07,09,11,14,29"
last_updated = "2025-06-25T01:40:09.509881"
+++
# Task 13: Interactive Prompting and Commands While Executing
> *This task is specific to codex-rs.*
## Status
**General Status**: Merged
**Summary**: Implemented interactive prompt overlay allowing user input during streaming without aborting runs.
## Goal
Allow users to interleave composing prompts and issuing slash-commands while the agent is actively executing (e.g. streaming completions), without aborting the current run.
## Acceptance Criteria
- While the LLM is streaming a response or executing a tool, the input box remains active for user edits and slash-commands.
- Sending a message or `/`-command does not implicitly cancel or abort the ongoing execution.
- Any tool invocation messages from the agent must still be immediately followed by their corresponding tool output messages (or the API will error).
- Ensure the TUI correctly preserves the stream and appends new user input at the bottom, scrolling as needed.
- No deadlocks or lost events if the agent finishes while the user is typing; buffer and render properly.
- Update tests to simulate concurrent user input during streaming and validate UI state.
## Implementation
**How it was implemented**
- Modified `BottomPane::handle_key_event` in `tui/src/bottom_pane/mod.rs` to special-case the `StatusIndicatorView` while `is_task_running`, forwarding key events to `ChatComposer` and preserving the overlay.
- Updated `BottomPane::render_ref` to always render the composer first and then overlay the active view, ensuring the input box remains visible and editable under the status indicator.
- Added unit tests in `tui/src/bottom_pane/mod.rs` to verify input is forwarded during task execution and that the status indicator overlay is removed upon task completion.
**How it works**
During LLM streaming or tool execution, the `StatusIndicatorView` remains active as an overlay. The modified event handler detects this overlay and forwards user key events to the underlying `ChatComposer` without dismissing the overlay. On task completion (`set_task_running(false)`), the overlay is automatically removed (via `should_hide_when_task_is_done`), returning to the normal input-only view.
## Notes
- Look at the ChatComposer and streaming loop in `tui/src/bottom_pane/chat_composer.rs` for input and stream handling.
- Ensure event loop in `app.rs` multiplexes between agent stream events and user input events without blocking.
- Consider locking or queuing tool-use messages to guarantee prompt tool-output pairing.
**Summary**: Enhanced the task scaffolding script to launch a Codex agent in a sandboxed worktree with writable worktree and TMPDIR, auto-approved file I/O and Git operations, and network disabled.
## Goal
Use `create-task-worktree.sh --agent` to wrap the agent invocation in a sandbox with these properties:
- The task worktree path and the system temporary directory (`$TMPDIR` or `/tmp`) are mounted read-write.
- All other paths on the host are treated as read-only.
- Git operations in the worktree (e.g. `git add`, `git commit`) succeed without additional confirmation.
- Any file read or write under the worktree root is automatically approved.
## Acceptance Criteria
The `create-task-worktree.sh --agent` invocation:
- launches the agent via `codex debug landlock` (or equivalent), passing flags to mount only the worktree and tempdir as writable.
- sets up Landlock permissions so that all other host paths are read-only.
- auto-approves any file system operation under the worktree directory.
- auto-approves Git commands in the worktree without prompting.
- still permits using system temp dir for ephemeral files.
- contains tests or manual verifications demonstrating blocked writes outside and allowed writes inside.
## Implementation
**How it was implemented**
- Extended `create-task-worktree.sh``--agent` mode to launch the Codex agent under a Landlock+seccomp sandbox by invoking `codex debug landlock --full-auto`, which grants write access only to the worktree (`cwd`) and the platform temp folder (`TMPDIR`), and disables network.
- Updated the `-a|--agent` help text to reflect the new sandbox behavior and tempdir whitelist.
- Added a test script demonstrating allowed writes inside the worktree and TMPDIR and blocked writes to directories outside those paths:
```bash
#!/usr/bin/env bash
# Test script for Task 15: verify sandbox restrictions and allowances
set -euo pipefail
worktree_root="$(cd "$(dirname "$0")"/.. && pwd)"
echo "Running sandbox tests in worktree: $worktree_root"
# Test write inside worktree
echo -n "Test: write inside worktree... "
if codex debug landlock --full-auto /usr/bin/env bash -c "touch '$worktree_root/inside_test'"; then
echo "PASS"
else
echo "FAIL" >&2
exit 1
fi
# Test write inside TMPDIR
tmpdir=${TMPDIR:-/tmp}
echo -n "Test: write inside TMPDIR ($tmpdir)... "
if codex debug landlock --full-auto /usr/bin/env bash -c "touch '$tmpdir/tmp_test'"; then
echo "PASS"
else
echo "FAIL" >&2
exit 1
fi
# Prepare external directory under HOME to test outside worktree/TMPDIR
The `--full-auto` flag configures Landlock to allow disk writes under the current directory and the system temp directory, disable network access, and automatically approve commands on success. As a result, any file I/O and Git operations in the worktree proceed without approval prompts, while writes outside the worktree and TMPDIR are blocked by the sandbox.
## Notes
- This feature depends on the underlying Landlock/Seatbelt sandbox APIs.
- Leverage the existing sandbox invocation (`codex debug landlock`) and approval predicates to auto-approve worktree and tmpdir I/O.
title: Chat UI Textarea Overlay and Border Styling Fix
status: Not started
summary: Fix overlay of waiting messages and streamline borders between chat window and input area to improve visibility and reclaim terminal space.
goal: |
Adjust the TUI chat interface so that waiting/status messages no longer overlay the first line of the input textarea (ensuring user drafts remain visible), and merge/remove borders as follows:
- Merge the bottom border of the chat history window with the top border of the input textarea.
- Remove the left, right, and bottom overall borders around the chat interface to reduce wasted space.
---
> *This task is specific to codex-rs.*
## Acceptance Criteria
- Waiting/status messages (e.g. "Thinking...", "Typing...", etc.) appear above the textarea rather than overlaying the first line of the input area.
- User draft text remains visible at all times, even when agent messages or status indicators are rendered.
- The bottom border of the chat history pane and the top border of the textarea are unified into a single border line.
- The left, right, and bottom borders around the entire chat UI are removed, reclaiming columns/rows in the terminal.
- Manual or automated visual verification steps demonstrate correct layout in a variety of terminal widths.
## Implementation
**How it was implemented**
* Merged the bottom border of the history pane and the top border of the input textarea into a single shared line by removing the textarea's top border and keeping only a bottom border on the textarea and both top/bottom borders on the history pane.*
* Removed left/right borders on both panes (history and textarea) and removed the textarea's bottom border from the overall UI to reclaim horizontal space.*
* Updated the status-indicator overlay to render in its own floating box immediately above the textarea instead of covering the first input line.*
**How it works**
At runtime the conversation history widget now draws only its top and bottom borders. The input textarea draws only its bottom border, carrying the help title there. These changes yield a single continuous border line separating history from input and eliminate the outer left, right, and bottom borders. Status messages ("Thinking...", etc.) render in a separate floating box positioned just above the textarea, leaving the user's draft text visible at all times.
## Notes
- This involves updating the rendering logic in the TUI modules (likely under `tui/src/` in `codex-rs`).
- Ensure layout changes do not break existing tests or rendering in unusual terminal sizes.
- Consider writing a simple snapshot test or manual demo script to validate border and overlay behavior.
title = "Bash Command Rendering Improvements for Less Verbosity"
status = "Merged"
dependencies = "02,07,09,11,14,29"
last_updated = "2025-06-25T05:36:32.641375"
+++
> *This task is specific to per-agent UI conventions and log readability.*
## Acceptance Criteria
- Shell commands render as plain text without `bash -lc` wrappers.
- Role labels and message content appear on the same line, separated by a space.
- Command-result annotations show a checkmark and duration for zero exit codes, or `exit code: N` and duration for nonzero codes, in the format `<icon or exit code> <duration>ms`.
- Collapse consecutive `BackgroundEvent` entries related to exec failures/retries into the standard active/completed exec-command cells.
- Update `new_active_exec_command` and `new_completed_exec_command` to use the new inline format (icon or exit code + duration, with `$ <command>` on the same block).
- Ensure role labels and plain-text messages render on a single line separated by a space.
- **Tests** (`codex-rs/tui/tests/`):
- Add or update test fixtures to verify:
- Commands appear without any `bash -lc` boilerplate.
- Completed commands show the correct checkmark or exit-code annotation with accurate duration formatting.
- Background debugging events no longer leak raw debug strings and are correctly collapsed into the exec-command flow.
## Notes
- Improves readability of interactive sessions and logs by reducing boilerplate.
- Ensure compatibility with both live TUI output and persisted log transcripts.
Provide an option to render Markdown without blank lines between headings and content for more vertical packing.
## Goal
Add a configuration flag to control Markdown rendering in the chat UI and logs so that headings render immediately adjacent to their content with no separating blank line.
## Acceptance Criteria
- Introduce a config flag `markdown_compact = true|false` under the UI settings.
- When enabled, the renderer omits the default blank line between headings (lines starting with `#`) and their subsequent content.
- The flag applies globally to all Markdown rendering (diffs, docs, help messages).
- Default behavior remains unchanged (blank lines preserved) when `markdown_compact` is false or unset.
- Add tests to verify both compact and default rendering modes across heading levels.
## Implementation
**How it was implemented**
- Extend the Markdown-to-TUI formatter to check `markdown_compact` and collapse heading/content spacing.
- Implement a post-processing step that removes blank lines immediately following heading tokens (`^#{1,6} `) when `markdown_compact` is true.
- Expose the new flag via the config parser and default it to `false`.
- Add unit tests covering H1–H6 headings, verifying absence of blank line in compact mode and presence in default mode.
## Notes
- This option improves vertical density for screens with limited height.
- Ensure compatibility with existing Markdown features like lists and code blocks; only target heading-content spacing.
title = "Interactive Container Command Affordance via Hotkey"
status = "Merged"
freeform_status = ""
dependencies = "01"
last_updated = "2025-06-25T12:10:10.584536"
+++
## Summary
Provide a keybinding to run arbitrary shell commands in the agent’s container and display output inline.
## Goal
Add a user-facing affordance (e.g. a hotkey) to invoke arbitrary shell commands within the agent's container during a session for on-demand inspection and debugging. The typed command should be captured as a chat turn, executed via the existing shell tool, and its output rendered inline in the chat UI.
## Acceptance Criteria
- Bind a hotkey (e.g. Ctrl+M) that opens a prompt for the user to type any shell command.
- When the user submits, capture the command as if entered in the chat input, and invoke the shell tool with the command in the agent’s container.
- Display the command invocation and its stdout/stderr output inline in the chat window, respecting formatting rules (e.g. compact rendering settings).
- Support chaining multiple commands in separate turns; history should show these command turns normally.
- Provide unit or integration tests simulating a user hotkey press, command input, and verifying the shell tool is called and output is displayed.
## Implementation
**How it was implemented**
- Added a new slash command `Shell` and updated dispatch logic in `app.rs` to push a shell-command view.
- Bound `Ctrl+M` in `ChatComposer` to dispatch `SlashCommand::Shell` for hotkey-driven shell prompt.
- Created `ShellCommandView` (bottom pane overlay) to capture arbitrary user input and emit `AppEvent::ShellCommand(cmd)`.
- Extended `AppEvent` with `ShellCommand(String)` and `ShellCommandResult { call_id, stdout, stderr, exit_code }` variants for round-trip messaging.
- Implemented `ChatWidget::handle_shell_command` to execute `sh -c <cmd>` asynchronously (tokio::spawn) and send back `ShellCommandResult`.
- Updated `ConversationHistoryWidget` to reuse existing exec-command cells to display shell commands and their output inline.
- Added tests:
- Unit test in `shell_command_view.rs` asserting correct event emission (skipping redraws).
- Integration test in `chat_composer.rs` asserting `Ctrl+M` opens the shell prompt view and allows input.
## Notes
- This feature aids debugging and inspection without leaving the agent workflow.
- Ensure that security policies (e.g. sandbox restrictions) still apply to these commands.
title = "Include Command Snippet in Session-Scoped Approval Label"
status = "Merged"
dependencies = "03,06,08,13,15,32,18,19,22,23"
last_updated = "2025-06-25T04:04:47.399379"
+++
## Summary
When asking for session-scoped approval of a command, embed a truncated snippet of the actual command in the approval label for clarity.
## Goal
Improve the session-scoped approval option label for commands by including a backtick-quoted snippet of the command itself (truncated to fit). This makes it clear exactly which command (including parameters) will be auto-approved for the session.
## Acceptance Criteria
- The session-scoped approval label changes from generic text to include a snippet of the current command, e.g.:
```text
Yes, always allow running `cat x | foo --bar > out` for this session (a)
```
- If the command is too long, truncate the middle (e.g. `long-part…end-part`) to fit a configurable max length.
- Implement the snippet templating in both Rust and JS UIs for consistency.
- Add unit tests to verify snippet extraction, truncation logic, and label rendering for various command lengths.
## Implementation
**Planned implementation**
- Add a `truncateMiddle` helper in both the Rust TUI and the JS/TS UI to ellipsize command snippets in the middle.
- Extract the first line of the command string (up to any newline), truncate to a default max length (e.g. 30 characters), inserting a single-character ellipsis `…` when needed.
- In the session-scoped approval option, replace the static label with a dynamic one:
`Yes, always allow running `<snippet>` for this session (a)`.
- Write unit tests for the helper and label generation covering commands shorter than, equal to, and longer than the max length.
## Notes
- This clarifies what parameters will be auto-approved and avoids ambiguity when multiple similar commands occur.
title = "Display Remaining Context Percentage in codex-rs TUI"
status = "Merged"
dependencies = "03,06,08,13,15,32,18,19,22,23"
last_updated = "2025-06-25T01:40:09.600000"
+++
## Summary
Show a live "x% context left" indicator in the TUI (Rust) to inform users of remaining model context buffer.
## Goal
Enhance the codex-rs TUI by adding a status indicator that displays the percentage of model context buffer remaining (e.g. "75% context left"). Update this indicator dynamically as the conversation progresses.
## Acceptance Criteria
- Compute current token usage and total context limit from the active session.
- Display "<N>% context left" in the status bar or header of the TUI, formatted compactly.
- Update the percentage after each message turn in real time.
- Ensure the indicator is visible but does not obstruct existing UI elements.
- Add unit or integration tests mocking token count updates and verifying correct percentage formatting (rounding behavior, boundary conditions).
## Implementation
**How it was implemented**
- Added a `history_items: Vec<ResponseItem>` field to `ChatWidget` to accumulate the raw sequence of messages and function calls.
- Created a new module `tui/src/context.rs` mirroring the JS heuristics:
-`approximate_tokens_used(&[ResponseItem])`: counts characters in text and function-call items, divides by 4 and rounds up.
-`max_tokens_for_model(&str)`: uses a registry of known model limits and heuristic fallbacks (32k, 16k, 8k, 4k, default 128k).
- Updated `ChatWidget::replay_items` and `ChatWidget::handle_codex_event` to push each incoming `ResponseItem` into `history_items`.
- Modified `ChatComposer::render_ref` to query `calculate_context_percent_remaining`, format and display "<N>% context left" after the input area, coloring it green/yellow/red per thresholds (>40%, 25–40%, ≤25%).
- Added unit tests in `tui/tests/context_percent.rs` covering token counting, model heuristics, percent rounding, and boundary conditions.
## Notes
- This feature helps users anticipate when they may need to truncate history or start a new session.
- Future enhancement: allow toggling this indicator on/off via config.
dependencies = "10" # Rationale: depends on Task 10 for container state inspection
last_updated = "2025-06-25T11:38:19Z"
+++
> *This task is specific to codex-rs.*
## Status
**General Status**: Done
**Summary**: Follow-up to Task10; add slash-command and TUI bindings for `inspect-env`.
## Goal
Add an `/inspect-env` slash-command in the TUI that invokes the existing `codex inspect-env` logic to display sandbox state inline.
## Acceptance Criteria
- Extend `SlashCommand` enum to include `InspectEnv`.
- Dispatch `AppEvent::InlineInspectEnv` when `/inspect-env` is entered.
- Handle `InlineInspectEnv` in `app.rs` to run `inspect-env` logic and stream its output to the TUI log pane.
- Render mounts, permissions, and network status in a formatted table or tree view in the bottom pane.
- Unit/integration tests simulating slash-command invocation and verifying rendered output.
## Implementation
**High-level approach**
- Extend `SlashCommand` enum with `InspectEnv` and provide user-visible description.
- Add `InlineInspectEnv` variant to `AppEvent` enum to represent inline slash-command invocation.
- Update dispatch logic in `App::run` to spawn a background thread on `InlineInspectEnv` that runs `codex inspect-env`, reads its stdout line-by-line, and sends each line as `AppEvent::LatestLog`, then triggers a redraw.
- Wire up `/inspect-env` to dispatch `InlineInspectEnv` in the slash-command handling.
- Add unit tests in the TUI crate to verify `built_in_slash_commands()` includes `inspect-env` mapping and description, and tests for the command-popup filter to ensure `InspectEnv` is listed when `/inspect-env` is entered.
**How it works**
When the user enters `/inspect-env`, the TUI parser recognizes the command and emits `AppEvent::InlineInspectEnv`. The main event loop handles this event by spawning a thread that invokes the external `codex inspect-env` command, captures its output line-by-line, and forwards each line into the TUI log pane via `AppEvent::LatestLog`. A redraw is scheduled once the inspection completes.
## Notes
- Reuse formatting code from `cli/src/inspect_env.rs` for consistency.
title = "Fix Approval Dialog Transparent Background"
status = "Done"
dependencies = ""
summary = "The approval dialog background is transparent, causing prompt text underneath to overlap and become unreadable."
last_updated = "2025-06-25T23:00:00.000000"
+++
> *UI bug:* When the approval dialog appears, its background is transparent and any partially entered prompt text shows through, overlapping and confusing the dialog.
## Status
**General Status**: Done
**Summary**: Identify and implement an opaque background for the approval dialog to prevent underlying text bleed-through.
## Goal
Ensure the approval dialog is drawn with a solid background color (matching the dialog border or theming) so that any underlying text does not bleed through.
## Acceptance Criteria
- Approval dialogs block underlying prompt text (solid background).
- Updated `render_ref` in `codex-rs/tui/src/user_approval_widget.rs` to fill the entire dialog area with a `DarkGray` background before drawing the border and content.
- Implemented nested loops over the dialog `Rect` calling `buf[(col, row)].set_bg(Color::DarkGray)` on each cell.
- Added unit test `render_approval_dialog_fills_background` in `tui/src/user_approval_widget.rs` to render the widget onto a buffer pre-filled with a red background and verify no cell in the dialog region remains transparent or retains the sentinel background.
Let users configure one or more scripts in `config.toml` that examine each proposed shell command and return exactly one of:
-`deny` => auto-reject (skip sandbox and do not run the command)
-`allow` => auto-approve and proceed under the sandbox
-`no-opinion` => no opinion (neither approve nor reject)
Multiple scripts cast votes: if any script returns `deny`, the command is denied; otherwise if any script returns `allow`, the command is allowed; otherwise (all scripts return `no-opinion` or exit non-zero), pause for manual approval (existing logic).
## Acceptance Criteria
- New `[[auto_allow]]` table in `config.toml` supporting one or more `script = "..."` entries.
- Before running any shell/subprocess, Codex invokes each configured script in order, passing the candidate command as an argument.
- If a script returns `deny` or `allow`, immediately take that vote and skip remaining scripts.
- After all scripts complete with only `no-opinion` results or errors, pause for manual approval (existing logic).
- Spawn each predicate script with the full command as its only argument.
- Parse stdout (case-insensitive) expecting `deny`, `allow`, or `no-opinion`, treating errors or unknown output as `NoOpinion`.
- Short-circuit on the first `Deny` or `Allow` vote.
- A `Deny` vote aborts execution.
- An `Allow` vote skips prompting and proceeds under sandbox.
- All `NoOpinion` votes fall back to existing approval logic.
## Implementation
-- Added `auto_allow: Vec<AutoAllowPredicate>` to `ConfigToml`, `ConfigProfile`, and `Config` to parse `[[auto_allow]]` entries from `config.toml`.
-- Defined `AutoAllowPredicate { script: String }` and `AutoAllowVote { Allow, Deny, NoOpinion }` in `core::safety`.
-- Implemented `evaluate_auto_allow_predicates` in `core::safety` to spawn each script with the candidate command, parse its stdout vote, and short-circuit on `Deny` or `Allow`.
-- Integrated `evaluate_auto_allow_predicates` into the shell execution path in `core::codex`, aborting on `Deny`, auto-approving on `Allow`, and falling back to manual or policy-based approval on `NoOpinion`.
-- Updated `config.md` to document the `[[auto_allow]]` table syntax and behavior.
-- Added comprehensive unit tests covering vote parsing, error propagation, short-circuit behavior, and end-to-end predicate functionality.
## Notes
- This pairs with the existing `approval_policy = "unless-allow-listed"` but adds custom logic before prompting.
dependencies = "11" # Rationale: depends on Task 11 for custom approval predicate infrastructure
last_updated = "2025-06-25T01:40:09.507043"
+++
# Task 09: File- and Directory-Level Approvals
> *This task is specific to codex-rs.*
## Status
**General Status**: Not started
**Summary**: Not started; missing Implementation details (How it was implemented and How it works).
## Goal
Enable fine-grained approval controls so users can whitelist edits scoped to specific files or directories at runtime, with optional time limits.
## Acceptance Criteria
- In the approval dialog, offer “Allow this file always” and “Allow this directory always” options alongside proceed/deny.
- Prompt for a time limit when granting a file/dir approval, with default presets (e.g. 5min, 1hr, 4hr, 24hr).
- Introduce runtime commands to inspect and manage granular approvals:
-`/approvals list` to view active approvals and remaining time
-`/approvals add [file|dir] <path> [--duration <preset>]` to grant approval
-`/approvals remove <id>` to revoke an approval
- Persist granular approvals in session metadata, keyed by working directory. On session resume in a different directory, warn the user and discard all file/dir approvals.
- Automatically expire and remove approvals when their time limits elapse.
- Reflect file/dir-approval state in the CLI shell prompt or title for quick visibility.
## Implementation
**How it was implemented**
*(Not implemented yet)*
**How it works**
*(Not implemented yet)*
## Notes
- Store approvals with {id, scope: file|dir, path, expires_at} in session JSON.
- Use a background timer or check-before-command to prune expired entries.
- Reuse existing command-parsing infrastructure to implement `/approvals` subcommands.
- Consider UI/UX for selecting presets in TUI dialogs.
**Summary**: Not started; missing Implementation details (How it was implemented and How it works).
## Goal
When a shell command is not auto-approved, the approval prompt should include 1–3 AI-generated approval predicates. Each suggestion is a time-limited Python predicate snippet plus an explanation of the full set of permissions it would grant. Users can pick one suggestion to append to the session’s approval policy as a broader-scope allow rule.
## Acceptance Criteria
- When a command is not auto-approved, show up to 3 suggested predicates inline in the TUI approval dialog.
- Each suggestion consists of:
- A Python code snippet defining a predicate function.
- An AI-generated explanation of exactly what permissions or scope that predicate grants.
- A TTL or expiration timestamp indicating how long it will remain active.
- Users can select one suggestion to append to the session’s list of approval predicates.
- Predicates are stored in session state (in-memory) for the duration of the session.
- Provide a slash/CLI command (`/inspect-approval-predicates`) to list current predicates, their code, explanations, and timeouts.
- Support headless and interactive modes equally.
## Implementation
**How it was implemented**
*(Not implemented yet)*
**How it works**
*(Not implemented yet)*
## Notes
- Reuse the existing AI reasoning engine to generate predicate suggestions.
- Represent predicates as Python functions returning a boolean.
- Ensure that expiration is enforced and stale predicates are ignored.
- Integrate the new `/inspect-approval-predicates` command into both the TUI and Exec CLI.
title = "Render Patch Content in Chat Display Window for Approve/Deny"
status = "Not started"
dependencies = "" # No prerequisites
last_updated = "2025-06-25T01:41:34.738344"
+++
> *This task is specific to the chat UI renderer.*
## Acceptance Criteria
- When displaying a patch for approve/deny, the full diff for the active patch is rendered inline in the chat window.
- Older or superseded patches collapse to show only up to N lines of context, with an indicator (e.g. "... 10 lines collapsed ...").
- File paths in diff headers are shown relative to the current working directory, unless the file resides outside the CWD.
- Event logs around patch application are simplified: drop structured event data and replace with a simple status note (e.g. "patch applied").
- Configurable parameter (e.g. `patch_context_lines`) controls the number of context lines for collapsed hunks.
- Preserve the user’s draft input when an approval dialog or patch diff appears; ensure the draft editor remains visible so users can continue editing while reviewing.
- Provide end-to-end integration tests that simulate drafting long messages, triggering approval dialogs and overlays, and verify that all UI elements (draft editor, diffs, logs) render correctly without overlap or content loss.
- Exhaustively test all dialog interaction flows (approve, deny, cancel) and overlay scenarios to confirm consistent behavior across combinations and prevent rendering artifacts.
## Implementation
**How it was implemented**
- Extend the chat renderer to detect patch approval prompts and render diffs using a custom formatter.
- Compute relative paths via `Path::strip_prefix`, falling back to full path if outside CWD.
- Track the current patch ID and render its full content; collapse previous patch bodies according to `patch_context_lines` setting.
- Preserve and render the current draft buffer alongside the active patch diff, ensuring live edits remain visible during approval steps.
- Add integration tests using the TUI test harness or end-to-end framework to simulate user input of long text, approval flows, overlay dialogs, and log output, asserting correct screen layout and content integrity.
- Design a parameterized test matrix covering all dialog interaction flows (approve/deny/cancel) and overlay transitions to ensure exhaustive coverage and UI sanity.
- Replace verbose event debug output with a single-line status message.
## Notes
- Users can override `patch_context_lines` in their config to see more or fewer collapsed lines.
- Ensure compatibility with both live TUI sessions and persisted transcript logs.
title = "Guard Against Missing Tool Output in JS Server Sequencing"
status = "Not started"
dependencies = "" # No prerequisites
last_updated = "2025-06-25T01:40:09.600000"
+++
## Summary
Prevent out-of-order chat messages and missing tool outputs when user input interrupts tool execution in the JS backend.
## Goal
Ensure the JS server never emits a user or model message before the corresponding tool output has been delivered. Add sequencing guards to the message dispatcher so that aborted rollouts or interleaved user messages cannot cause "No tool output found" errors.
## Acceptance Criteria
- When a tool invocation is interrupted or user sends a message mid-rollout, the JS server buffers subsequent messages until the tool output event arrives or the invocation is explicitly cancelled.
- The server must never log or emit an error like "No tool output found for local shell call" due to sequencing mismatch.
- Add automated tests simulating mid-rollout user interrupts in the JS test suite, verifying correct buffering and eventual message delivery or cancellation.
## Implementation
**How it was implemented**
- In the JS message dispatcher, track pending tool invocations by ID and delay processing of new chat messages until the pending invocation resolves (success, failure, or cancel).
- Add a guard in the `handleUserMessage` path to check for unresolved tool IDs before appending user content; if pending, queue the message.
- On receiving `toolOutput` or `toolError` for an invocation ID, flush any queued messages in order.
- Implement explicit cancellation paths so that if a tool invocation is abandoned, queued messages still flow after cancellation confirmation.
- Add unit and integration tests in the JS test harness to cover normal, aborted, and concurrent message scenarios.
## Notes
- This change prevents 400 Bad Request errors from tool retries where the model requests a tool before the output is streamed.
- Keep diagnostic logs around sequencing logic for troubleshooting but avoid spamming on normal race cases.
title = "Guard Against Missing Tool Output in Rust Server Sequencing"
status = "Needs input"
dependencies = "" # No prerequisites
last_updated = "2025-06-25T22:50:01.000000"
+++
## Summary
Prevent out-of-order chat messages and missing tool output errors when user input interrupts tool execution in the Rust backend.
## Goal
Ensure the Rust server implementation sequences tool output and chat messages correctly. Add synchronization logic so that an in-flight tool invocation either completes or is cancelled before new messages are processed, avoiding "No tool output found" invalid_request errors.
## Acceptance Criteria
- The Rust message broker must detect pending tool invocations and pause delivery of subsequent user or model messages until the tool result or cancellation is handled.
- No panic or 400 Bad Request errors should occur due to missing tool output in edge cases of interrupted rollouts or mid-stream user input.
- Add Rust integration tests simulating tool invocation interruption and user message interleaving, verifying correct ordering and delivery.
## Implementation
We will implement the following high-level plan:
- Locate where the ChatCompletion request messages array is built in Rust:
the `stream_chat_completions` function in `codex-rs/core/src/chat_completions.rs`.
- In that loop, track pending tool invocations by their call IDs when encountering `ResponseItem::FunctionCall` entries.
- Buffer any subsequent `ResponseItem::Message { role: "user" }` or new turn inputs until the matching `ResponseItem::FunctionCallOutput` (tool result) appears.
- Once the tool output is seen, flush buffered user messages in order immediately before continuing to build the next API call.
- Add tests under `codex-rs/core/tests/` (e.g. `guard_tool_output_sequencing.rs`) that exercise interleaved input sequences:
- A user message mid-rollout before tool output, ensuring it is delayed until after the tool result.
- Normal flow where no buffering is needed.
- Cancellation paths (no tool output) inserting a fake "Tool cancelled" tool message and flushing buffered messages.
- Front-end layers automatically render the "Tool cancelled" message as a tool output, satisfying UI requirements.
## Notes
```text
█
thinking █Deciding on file management █
───╮
I’m thinking that since file editing can be a hassle, it might be simpler to just remove the file. I could then ask the user to provide │any errors they’re facing. To do this, I'd create a patch to delete the specified file. Alternatively, I could consider reverting the │
changes with git, but applying the patch seems like a straightforward solution. So, I’ll go ahead and prepare to apply the patch to ──╯
delete the file.
proposed patch
D /Users/mpokorny/code/codex/agentydragon/tasks/.worktrees/23-interactive-container-command-affordance/codex-rs/.cargo/config.toml ny
ERROR: Turn interrupted
user
why did you try to delete that? s P
event
BackgroundEvent(BackgroundEventEvent { message: "stream error: unexpected status 400 Bad Request: {\n \"error\": {\n \"message\": \"No tool output found for local shell call call_PjdhYGAM7q52HL13WF8slGn9.\",\n \"type\": \"invalid_request_error\",\n \"param\":
\"input\",\n \"code\": null\n }\n}; retrying 1/10 in 201ms…" }) │
│
event │
BackgroundEvent(BackgroundEventEvent { message: "stream error: unexpected status 400 Bad Request: {\n \"error\": {\n \"message\": │
\"No tool output found for local shell call call_PjdhYGAM7q52HL13WF8slGn9.\",\n \"type\": \"invalid_request_error\",\n \"param\": │\"input\",\n \"code\": null\n }\n}; retrying 2/10 in 246ms…" }) │
│
event │BackgroundEvent(BackgroundEventEvent { message: "stream error: unexpected status 400 Bad Request: {\n \"error\": {\n \"message\": │
\"No tool output found for local shell call call_PjdhYGAM7q52HL13WF8slGn9.\",\n \"type\": \"invalid_request_error\",\n \"param\": █
\"input\",\n \"code\": null\n }\n}; retrying 3/10 in 371ms…" }) █
this is a lot of the problem still happening
```
## Next Steps / Debugging
The above change did not resolve the issue. We need to gather more debug information to understand why missing tool output errors still occur.
Suggested approaches:
- Enable detailed debug logging in the Rust message broker (e.g. set `RUST_LOG=debug` or add tracing spans around function calls).
- Dump the sequence of incoming and outgoing `ResponseItem` events to a log file for offline analysis.
- Instrument timing and ordering by recording timestamps when tool invocations start, complete, and when user input is received.
- Write a minimal reproduction harness that reliably triggers the missing output error under controlled conditions.
- Capture full request/response payloads to/from the OpenAI API to verify whether the function output is delivered but not processed.
Please expand this section with specific examples or helper scripts to collect the necessary data.
title = "Render Approval Requests in Separate Dialog from Draft Window"
status = "Not started"
dependencies = "09,23" # Rationale: depends on Tasks 09 and 23 for file-level approvals and interactive command affordance
last_updated = "2025-06-25T01:40:09.600000"
+++
## Summary
Display patch approval prompts in a distinct dialog or panel to avoid overlaying the draft editor.
## Goal
Change the chat UI so that approval requests (patch diffs for approve/deny) appear in a separate dialog element or panel, positioned adjacent to or below the chat window, rather than overlaying the draft input area.
This eliminates overlay conflicts and ensures the draft editor remains fully visible and interactive while reviewing patches.
## Acceptance Criteria
- Approval prompts with diffs open in a distinct UI element (e.g. side panel or bottom pane) that does not obscure the draft editor.
- The draft input area remains fully visible and editable whenever an approval dialog is active.
- The approval dialog is visually distinguished (border, background) and clearly labeled.
- The layout adjusts responsively for narrow/short terminal sizes, maintaining separation without clipping content.
- Add functional tests or integration tests verifying that the draft input remains accessible and that the approval dialog contents are rendered in the new panel.
## Implementation
**How it was implemented**
- Refactor the patch-approval renderer to spawn a separate TUI view (`ApprovalDialogView`) instead of the overlay popup.
- Allocate a consistent panel region (e.g. bottom X rows or right-hand column) for approval dialogs, reserving the draft editor region above or to the left.
- Update layout logic to recalculate positions on terminal resize, ensuring both panels remain visible.
- Style the new dialog with its own borders and title bar (e.g. "Approval Request").
- Add integration tests using the TUI test harness to simulate opening approval prompts and verifying that typing in the draft area still works and that the dialog appears in the correct panel.
## Notes
- This change fixes the long-standing overlay bug where approval diffs obstruct the draft.
- Future enhancements may allow toggling between inline overlay or separate panel modes.
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
