When trying to introduce an integration test for the `codex-shell-tool-mcp` in
https://github.com/openai/codex/pull/7617, macOS CI hit serde decode errors in
the escalation pipe when huge env vars inflated the `EscalateRequest` payload
past the stream frame, corrupting JSON. (I'm pretty sure `$GITHUB_EVENT` was the
offending env var.)
This PR updates `exec-server` to filter out oversized env entries and skip
reserved vars before serialization.
It also updates the code to avoid attaching empty `SCM_RIGHTS` control messages
so frames stay lean when no FDs are sent.
- Introduce `with_remote_overrides` and update
`refresh_available_models`
- Put `auth_manager` instead of `auth_mode` on `models_manager`
- Remove `ShellType` and `ReasoningLevel` to use already existing
structs
## Summary
This PR introduces an End to End test suite for apply-patch, so we can
easily validate behavior against other implementations as well.
## Testing
- [x] These are tests
The caller should decide whether wrapping the policy in `Arc<RwLock>` is
necessary. This should make https://github.com/openai/codex/pull/7609 a
bit smoother.
- `exec_policy_for()` -> `load_exec_policy_for_features()`
- introduce `load_exec_policy()` that does not take `Features` as an arg
- both return `Result<Policy, ExecPolicyError>` instead of
Result<Arc<RwLock<Policy>>, ExecPolicyError>`
This simplifies the tests as they have no need for `Arc<RwLock>`.
**Summary**
- Shortcut toggle using `?` in `handle_shortcut_overlay_key` fails to
trigger on some platforms (notably Windows). Current match requires
`KeyCode::Char('?')` with `KeyModifiers::NONE`. Some terminals set
`SHIFT` when producing `?` (since it is typically `Shift + /`), so the
strict `NONE` check prevents toggling.
**Impact**
- On Windows consoles/terminals, pressing `?` with an empty composer
often does nothing, leading to inconsistent UX compared to macOS/Linux.
**Root Cause**
- Crossterm/terminal backends report modifiers inconsistently across
platforms. Generating `?` may include `SHIFT`. The code enforces
`modifiers == NONE`, so valid `?` presses with `SHIFT` are ignored.
AltGr keyboards may also surface as `ALT`.
**Repro Steps**
- Open the TUI, ensure the composer is empty.
- Press `?`.
- Expected: Shortcut overlay toggles.
- Actual (Windows frequently): No toggle occurs.
**Fix Options**
- Option 1 (preferred): Accept `?` regardless of `SHIFT`, but reject
`CONTROL` and `ALT`.
- Rationale: Keeps behavior consistent across platforms with minimal
code change.
- Example change:
- Before: matching `KeyModifiers::NONE` only.
- After: allow `SHIFT`, disallow `CONTROL | ALT`.
- Suggested condition:
```rust
let toggles = matches!(key_event.code, KeyCode::Char('?'))
&& !key_event.modifiers.intersects(KeyModifiers::CONTROL |
KeyModifiers::ALT)
&& self.is_empty();
```
- Option 2: Platform-specific handling (Windows vs non-Windows).
- Implement two variants or conditional branches using `#[cfg(target_os
= "windows")]`.
- On Windows, accept `?` with `SHIFT`; on other platforms, retain
current behavior.
- Trade-off: Higher maintenance burden and code divergence for limited
benefit.
---
close#5495
VSCE renders `codex/event/stream_error` (automatically retried, e.g.
`"Reconnecting... 1/n"`) and `codex/event/error` (terminal errors)
differently, so add `will_retry` on ErrorNotification to indicate this.
- Inline response recording during streaming: `run_turn` now records
items as they arrive instead of building a `ProcessedResponseItem` list
and post‑processing via `process_items`.
- Simplify turn handling: `handle_output_item_done` returns the
follow‑up signal + optional tool future; `needs_follow_up` is set only
there, and in‑flight tool futures are drained once at the end (errors
logged, no extra state writes).
- Flattened stream loop: removed `process_items` indirection and the
extra output queue
- - Tests: relaxed `tool_parallelism::tool_results_grouped` to allow any
completion order while still requiring matching call/output IDs.
## Related issues:
- https://github.com/openai/codex/issues/3939
- https://github.com/openai/codex/issues/2292
- https://github.com/openai/codex/issues/7528 (After correction
https://github.com/openai/codex/pull/3990)
**Area:** `codex-cli` (image handling / clipboard & file uploads)
**Platforms affected:** WSL (Ubuntu on Windows 10/11). No behavior
change on native Linux/macOS/Windows.
## Summary
This PR fixes image pasting and file uploads when running `codex-cli`
inside WSL. Previously, image operations failed silently or with
permission errors because paths weren't properly mapped between Windows
and WSL filesystems.
## Visual Result
<img width="1118" height="798" alt="image"
src="https://github.com/user-attachments/assets/14e10bc4-6b71-4d1f-b2a6-52c0a67dd069"
/>
## Last Rust-Cli
<img width="1175" height="859" alt="image"
src="https://github.com/user-attachments/assets/7ef41e29-9118-42c9-903c-7116d21e1751"
/>
## Root cause
The CLI assumed native Linux/Windows environments and didn't handle the
WSL↔Windows boundary:
- Used Linux paths for files that lived on the Windows host
- Missing path normalization between Windows (`C:\...`) and WSL
(`/mnt/c/...`)
- Clipboard access failed under WSL
### Why `Ctrl+V` doesn't work in WSL terminals
Most WSL terminal emulators (Windows Terminal, ConEmu, etc.) intercept
`Ctrl+V` at the terminal level to paste text from the Windows clipboard.
This keypress never reaches the CLI application itself, so our clipboard
image handler never gets triggered. Users need `Ctrl+Alt+V`.
## Changes
### WSL detection & path mapping
- Detects WSL by checking `/proc/sys/kernel/osrelease` and the
`WSL_INTEROP` env var
- Maps Windows drive paths to WSL mount paths (`C:\...` → `/mnt/c/...`)
### Clipboard fallback for WSL
- When clipboard access fails under WSL, falls back to PowerShell to
extract images from the Windows clipboard
- Saves to a temp file and maps the path back to WSL
### UI improvements
- Shows `Ctrl+Alt+V` hint on WSL (many terminals intercept plain
`Ctrl+V`)
- Better error messages for unreadable images
## Performance
- Negligible overhead. The fallback adds a single FS copy to a temp file
only when needed.
- Direct streaming remains the default.
## Files changed
- `protocol/src/lib.rs` – Added platform detection module
- `protocol/src/models.rs` – Added WSL path mapping for local images
- `protocol/src/platform.rs` – New module with WSL detection utilities
- `tui/src/bottom_pane/chat_composer.rs` – Added base64 data URL support
and WSL path mapping
- `tui/src/bottom_pane/footer.rs` – WSL-aware keyboard shortcuts
- `tui/src/clipboard_paste.rs` – PowerShell clipboard fallback
## How to reproduce the original bug (pre-fix)
1. Run `codex-cli` inside WSL2 on Windows.
2. Paste an image from the Windows clipboard or drag an image from
`C:\...` into the terminal.
3. Observe that the image is not attached (silent failure) or an error
is logged; no artifact reaches the tool.
## How to verify the fix
1. Build this branch and run `codex-cli` inside WSL2.
2. Paste from clipboard and drag from both Windows and WSL paths.
3. Confirm that the image appears in the tool and the CLI shows a single
concise info line (no warning unless fallback was used).
I’m happy to adjust paths, naming, or split helpers into a separate
module if you prefer.
## How to try this branch
If you want to try this before it’s merged, you can use my Git branch:
Repository: https://github.com/Waxime64/codex.git
Branch: `wsl-image-2`
1. Start WSL on your Windows machine.
2. Clone the repository and switch to the branch:
```bash
git clone https://github.com/Waxime64/codex.git
cd codex
git checkout wsl-image-2
# then go into the Rust workspace root, e.g.:
cd codex-rs
3. Build the TUI binary:
cargo build -p codex-tui --bin codex-tui --release
4. Install the binary:
sudo install -m 0755 target/release/codex-tui /usr/local/bin/codex
5. From the project directory where you want to use Codex, start it
with:
cd /path/to/your/project
/usr/local/bin/codex
On WSL, use CTRL+ALT+V to paste an image from the Windows clipboard into
the chat.
**Change**: Seatbelt now allows file-ioctl on /dev/ttys[0-9]+ even
without the sandbox extension so pre-created PTYs remain interactive
(Python REPL, shells).
**Risk**: A seatbelted process that already holds a PTY fd (including
one it shouldn’t) could issue tty ioctls like TIOCSTI or termios changes
on that fd. This doesn’t allow opening new PTYs or reading/writing them;
it only broadens ioctl capability on existing fds.
**Why acceptable**: We already hand the child its PTY for interactive
use; restoring ioctls is required for isatty() and prompts to work. The
attack requires being given or inheriting a sensitive PTY fd; by design
we don’t hand untrusted processes other users’ PTYs (we don't hand them
any PTYs actually), so the practical exposure is limited to the PTY
intentionally allocated for the session.
**Validation**:
Running
```
start a python interpreter and keep it running
```
Followed by:
* `calculate 1+1 using it` -> works as expected
* `Use this Python session to run the command just fix in
/Users/jif/code/codex/codex-rs` -> does not work as expected
## Updating the `execpolicy` TUI flow
In the TUI, when going through the command approval flow, codex will now
ask the user if they would like to whitelist the FIRST unmatched command
among a chain of commands.
For example, let's say the agent wants to run `apple | pear` with an
empty `execpolicy`
Neither apple nor pear will match to an `execpolicy` rule. Thus, when
prompting the user, codex tui will ask the user if they would like to
whitelist `apple`.
If the agent wants to run `apple | pear` again, they would be prompted
again because pear is still unknown. when prompted, the user will now be
asked if they'd like to whitelist `pear`.
Here's a demo video of this flow:
https://github.com/user-attachments/assets/fd160717-f6cb-46b0-9f4a-f0a974d4e710
This PR also removed the `allow for this session` option from the TUI.
## Refactor of the `execpolicy` crate
To illustrate why we need this refactor, consider an agent attempting to
run `apple | rm -rf ./`. Suppose `apple` is allowed by `execpolicy`.
Before this PR, `execpolicy` would consider `apple` and `pear` and only
render one rule match: `Allow`. We would skip any heuristics checks on
`rm -rf ./` and immediately approve `apple | rm -rf ./` to run.
To fix this, we now thread a `fallback` evaluation function into
`execpolicy` that runs when no `execpolicy` rules match a given command.
In our example, we would run `fallback` on `rm -rf ./` and prevent
`apple | rm -rf ./` from being run without approval.
this PR enables TUI to approve commands and add their prefixes to an
allowlist:
<img width="708" height="605" alt="Screenshot 2025-11-21 at 4 18 07 PM"
src="https://github.com/user-attachments/assets/56a19893-4553-4770-a881-becf79eeda32"
/>
note: we only show the option to whitelist the command when
1) command is not multi-part (e.g `git add -A && git commit -m 'hello
world'`)
2) command is not already matched by an existing rule
## Summary
- render tooltip content through the markdown renderer and prepend a
bold Tip label
- wrap tooltips at the available width using the indent’s measured width
before adding the indent
## Testing
- `/root/.cargo/bin/just fmt`
- `RUSTFLAGS="--cfg tokio_unstable" TOKIO_UNSTABLE=1
/root/.cargo/bin/just fix -p codex-tui` *(fails: codex-tui tests
reference tokio::time::advance/start_paused gated behind the tokio
test-util feature)*
- `RUSTFLAGS="--cfg tokio_unstable" TOKIO_UNSTABLE=1 cargo test -p
codex-tui` *(fails: codex-tui tests reference
tokio::time::advance/start_paused gated behind the tokio test-util
feature)*
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_693081406050832c9772ae9fa5dd77ca)
When we are writing to config using `config/value/write` or
`config/batchWrite`, it always require a `config/read` before it right
now in order to get the correct file path to write to. make this
optional so we read from the default user config file if this is not
passed in.
This PR moves `ModelsFamily` to `openai_models`. It also propagates
`ModelsManager` to session services and use it to drive model family. We
also make `derive_default_model_family` private because it's a step
towards what we want: one place that gives model configuration.
This is a second step at having one source of truth for models
information and config: `ModelsManager`.
Next steps would be to remove `ModelsFamily` from config. That's massive
because it's being used in 41 occasions mostly pre launching `codex`.
Also, we need to make `find_family_for_model` private. It's also big
because it's being used in 21 occasions ~ all tests.
- This PR treats the `ModelsManager` like `AuthManager` and propagate it
into the tui, replacing the `builtin_model_presets`
- We are also decreasing the visibility of `builtin_model_presets`
based on https://github.com/openai/codex/pull/7552
What
-----
- Fix the Ctrl+T transcript overlay so that very long exec output lines
are soft‑wrapped to the viewport width instead of being rendered as a
single truncated row.
- Add a regression test to `TranscriptOverlay` to ensure long exec
outputs are rendered on multiple lines in the overlay.
Why
----
- Previously, the transcript overlay rendered extremely long single exec
lines as one on‑screen row and simply cut them off at the right edge,
with no horizontal scrolling.
- This made it impossible to inspect the full content of long tool/exec
outputs in the transcript view, even though the main TUI view already
wrapped those lines.
- Fixes#7454.
How
----
- Update `ExecCell::transcript_lines` to wrap exec output lines using
the existing `RtOptions`/`word_wrap_line` helpers so that transcript
rendering is width‑aware.
- Reuse the existing line utilities to expand the wrapped `Line` values
into the transcript overlay, preserving styling while respecting the
current viewport width.
- Add `transcript_overlay_wraps_long_exec_output_lines` test in
`pager_overlay.rs` that constructs a long single‑line exec output,
renders the transcript overlay into a small buffer, and asserts that the
long marker string spans multiple rendered lines.
I noticed that `features: Features` was defined on `struct
SessionConfiguration`, which is commonly owned by `SessionState`, which
is in turn owned by `Session`.
Though I do not believe that `Features` should be allowed to be modified
over the course of a session (if the feature state is not invariant, it
makes it harder to reason about), which argues that it should live on
`Session` rather than `SessionState` or `SessionConfiguration`.
This PR moves `Features` to `Session` and updates all call sites. It
appears the only place we were mutating `Features` was:
- in tests
- the sub-agent config for a review task:
3ef76ff29d/codex-rs/core/src/tasks/review.rs (L86-L89)
Note this change also means it is no longer an `async` call to check the
state of a feature, eliminating the possibility of a
[TOCTTOU](https://en.wikipedia.org/wiki/Time-of-check_to_time-of-use)
error between checking the state of a feature and acting on it:
3ef76ff29d/codex-rs/core/src/codex.rs (L1069-L1076)
- Treat Ctrl-P/N (and their C0 fallbacks) the same as Up/Down so cursor
movement matches popup/history behavior and control bytes never land in
the buffer
Fixes#7529
Signed-off-by: Aofei Sheng <aofei@aofeisheng.com>
What
- Limit the TUI "user shell" output panel by the number of visible
screen lines rather than by the number of logical lines.
- Apply middle truncation after wrapping, so a few extremely long lines
cannot expand into hundreds of visible lines.
- Add a regression test to guard this behavior.
Why
When the `ExecCommandSource::UserShell` tool returns a small number of
very long logical lines, the TUI wraps those lines into many visual
lines. The existing truncation logic applied
`USER_SHELL_TOOL_CALL_MAX_LINES` to the number of logical lines *before*
wrapping.
As a result, a command like:
- `Ran bash -lc "grep -R --line-number 'maskAssetId' ."`
or a synthetic command that prints a single ~50,000‑character line, can
produce hundreds of screen lines and effectively flood the viewport. The
intended middle truncation for user shell output does not take effect in
this scenario.
How
- In `codex-rs/tui/src/exec_cell/render.rs`, change the `ExecCell`
rendering path for `ExecCommandSource::UserShell` so that:
- Each logical line from `CommandOutput::aggregated_output` is first
wrapped via `word_wrap_line` into multiple screen lines using the
appropriate `RtOptions` and width from the `EXEC_DISPLAY_LAYOUT`
configuration.
- `truncate_lines_middle` is then applied to the wrapped screen lines,
with `USER_SHELL_TOOL_CALL_MAX_LINES` as the limit. This means the limit
is enforced on visible screen lines, not logical lines.
- The existing layout struct (`ExecDisplayLayout`) continues to provide
`output_max_lines`, so user shell output is subject to both
`USER_SHELL_TOOL_CALL_MAX_LINES` and the layout-specific
`output_max_lines` constraint.
- Keep using `USER_SHELL_TOOL_CALL_MAX_LINES` as the cap, but interpret
it as a per‑tool‑call limit on screen lines.
- Add a regression test `user_shell_output_is_limited_by_screen_lines`
in `codex-rs/tui/src/exec_cell/render.rs` that:
- Constructs two extremely long logical lines containing a short marker
(`"Z"`), so each wrapped screen line still contains the marker.
- Wraps them at a narrow width to generate many screen lines.
- Asserts that the unbounded wrapped output would exceed
`USER_SHELL_TOOL_CALL_MAX_LINES` screen lines.
- Renders an `ExecCell` for `ExecCommandSource::UserShell` at the same
width and counts rendered lines containing the marker.
- Asserts `output_screen_lines <= USER_SHELL_TOOL_CALL_MAX_LINES`,
guarding against regressions where truncation happens before wrapping.
This change keeps user shell output readable while ensuring it cannot
flood the TUI, even when the tool emits a few extremely long lines.
Tests
- `cargo test -p codex-tui`
Issue
- Fixes#7447
- Introduce `openai_models` in `/core`
- Move `PRESETS` under it
- Move `ModelPreset`, `ModelUpgrade`, `ReasoningEffortPreset`,
`ReasoningEffortPreset`, and `ReasoningEffortPreset` to `protocol`
- Introduce `Op::ListModels` and `EventMsg::AvailableModels`
Next steps:
- migrate `app-server` and `tui` to use the introduced Operation
No integration test for now because it would make them flaky. Tracking
it in my todos to add some once we have a clock based system for
integration tests
This item is sent as a turn notification instead: `turn/plan/updated`,
similar to Turn diffs (which is `turn/diff/updated`).
We treat these concepts as ephemeral compared to Items which are usually
persisted.
### Summary
Added `mcp/servers/list` which is equivalent to `/mcp` slash command in
CLI for response. This will be used in VSCE MCP settings to show log in
status, available tools etc.
If an image can't be read by the API, it will poison the entire history,
preventing any new turn on the conversation.
This detect such cases and replace the image by a placeholder
Closes#3404
## Summary
On windows, ctrl+v does not work for the same reason that cmd+v does not
work on macos. This PR adds alt/option+v detection, which allows windows
users to paste images from the clipboard using.
We could swap between just ctrl on mac and just alt on windows, but this
felt simpler - I don't feel strongly about it.
Note that this will NOT address image pasting in WSL environments, due
to issues with WSL <> Windows clipboards. I'm planning to address that
in a separate PR since it will likely warrant some discussion.
## Testing
- [x] Tested locally on a Mac and Windows laptop
# Unified Exec Shell Selection on Windows
## Problem
reference issue #7466
The `unified_exec` handler currently deserializes model-provided tool
calls into the `ExecCommandArgs` struct:
```rust
#[derive(Debug, Deserialize)]
struct ExecCommandArgs {
cmd: String,
#[serde(default)]
workdir: Option<String>,
#[serde(default = "default_shell")]
shell: String,
#[serde(default = "default_login")]
login: bool,
#[serde(default = "default_exec_yield_time_ms")]
yield_time_ms: u64,
#[serde(default)]
max_output_tokens: Option<usize>,
#[serde(default)]
with_escalated_permissions: Option<bool>,
#[serde(default)]
justification: Option<String>,
}
```
The `shell` field uses a hard-coded default:
```rust
fn default_shell() -> String {
"/bin/bash".to_string()
}
```
When the model returns a tool call JSON that only contains `cmd` (which
is the common case), Serde fills in `shell` with this default value.
Later, `get_command` uses that value as if it were a model-provided
shell path:
```rust
fn get_command(args: &ExecCommandArgs) -> Vec<String> {
let shell = get_shell_by_model_provided_path(&PathBuf::from(args.shell.clone()));
shell.derive_exec_args(&args.cmd, args.login)
}
```
On Unix, this usually resolves to `/bin/bash` and works as expected.
However, on Windows this behavior is problematic:
- The hard-coded `"/bin/bash"` is not a valid Windows path.
- `get_shell_by_model_provided_path` treats this as a model-specified
shell, and tries to resolve it (e.g. via `which::which("bash")`), which
may or may not exist and may not behave as intended.
- In practice, this leads to commands being executed under a non-default
or non-existent shell on Windows (for example, WSL bash), instead of the
expected Windows PowerShell or `cmd.exe`.
The core of the issue is that **"model did not specify `shell`" is
currently interpreted as "the model explicitly requested `/bin/bash`"**,
which is both Unix-specific and wrong on Windows.
## Proposed Solution
Instead of hard-coding `"/bin/bash"` into `ExecCommandArgs`, we should
distinguish between:
1. **The model explicitly specifying a shell**, e.g.:
```json
{
"cmd": "echo hello",
"shell": "pwsh"
}
```
In this case, we *do* want to respect the model’s choice and use
`get_shell_by_model_provided_path`.
2. **The model omitting the `shell` field entirely**, e.g.:
```json
{
"cmd": "echo hello"
}
```
In this case, we should *not* assume `/bin/bash`. Instead, we should use
`default_user_shell()` and let the platform decide.
To express this distinction, we can:
1. Change `shell` to be optional in `ExecCommandArgs`:
```rust
#[derive(Debug, Deserialize)]
struct ExecCommandArgs {
cmd: String,
#[serde(default)]
workdir: Option<String>,
#[serde(default)]
shell: Option<String>,
#[serde(default = "default_login")]
login: bool,
#[serde(default = "default_exec_yield_time_ms")]
yield_time_ms: u64,
#[serde(default)]
max_output_tokens: Option<usize>,
#[serde(default)]
with_escalated_permissions: Option<bool>,
#[serde(default)]
justification: Option<String>,
}
```
Here, the absence of `shell` in the JSON is represented as `shell:
None`, rather than a hard-coded string value.
When running `npx @openai/codex-shell-tool-mcp`, the old code derived
`__dirname` from `process.argv[1]`, which points to npx’s transient
wrapper script in
`~/.npm/_npx/134d0fb7e1a27652/node_modules/.bin/codex-shell-tool-mcp`.
That made `vendorRoot` resolve to `<npx cache>/vendor`, so the startup
checks failed with "Required binary missing" because it looked for
`codex-execve-wrapper` in the wrong place.
By relying on the real module `__dirname` and `path.resolve(__dirname,
"..", "vendor")`, the package now anchors to its installed location
under `node_modules/@openai/codex-shell-tool-mcp/`, so the bundled
binaries are found and npx launches correctly.
Fix issue #7430
Generate unique numbered placeholders for multiple large pastes of the
same length so deleting one no longer removes the others.
Signed-off-by: Joshua <joshua1s@protonmail.com>
I find it helpful to easily verify which version is running.
Tested:
```shell
~/code/codex3/codex-rs/exec-server$ cargo run --bin codex-exec-mcp-server -- --help
Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.19s
Running `/Users/mbolin/code/codex3/codex-rs/target/debug/codex-exec-mcp-server --help`
Usage: codex-exec-mcp-server [OPTIONS]
Options:
--execve <EXECVE_WRAPPER> Executable to delegate execve(2) calls to in Bash
--bash <BASH_PATH> Path to Bash that has been patched to support execve() wrapping
-h, --help Print help
-V, --version Print version
~/code/codex3/codex-rs/exec-server$ cargo run --bin codex-exec-mcp-server -- --version
Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.17s
Running `/Users/mbolin/code/codex3/codex-rs/target/debug/codex-exec-mcp-server --version`
codex-exec-server 0.0.0
```
Pull FrameRequester out of tui.rs into its own module and make a
FrameScheduler struct. This is effectively an Actor/Handler approach
(see https://ryhl.io/blog/actors-with-tokio/). Adds tests and docs.
Small refactor of pending_viewport_area logic.
I think this might help with https://github.com/openai/codex/pull/7033
because `create_approval_requirement_for_command()` will soon need
access to `Session.state`, which is a `tokio::sync::Mutex` that needs to
be accessed via `async`.
This PR honors the `history.max_bytes` configuration parameter by
trimming `history.jsonl` whenever it grows past the configured limit.
While appending new entries we retain the newest record, drop the oldest
lines to stay within the byte budget, and serialize the compacted file
back to disk under the same lock to keep writers safe.
The problem with using `serde(flatten)` on Turn status is that it
conditionally serializes the `error` field, which is not the pattern we
want in API v2 where all fields on an object should always be returned.
```
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(rename_all = "camelCase")]
#[ts(export_to = "v2/")]
pub struct Turn {
pub id: String,
/// Only populated on a `thread/resume` response.
/// For all other responses and notifications returning a Turn,
/// the items field will be an empty list.
pub items: Vec<ThreadItem>,
#[serde(flatten)]
pub status: TurnStatus,
}
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, JsonSchema, TS)]
#[serde(tag = "status", rename_all = "camelCase")]
#[ts(tag = "status", export_to = "v2/")]
pub enum TurnStatus {
Completed,
Interrupted,
Failed { error: TurnError },
InProgress,
}
```
serializes to:
```
{
"id": "turn-123",
"items": [],
"status": "completed"
}
{
"id": "turn-123",
"items": [],
"status": "failed",
"error": {
"message": "Tool timeout",
"codexErrorInfo": null
}
}
```
Instead we want:
```
{
"id": "turn-123",
"items": [],
"status": "completed",
"error": null
}
{
"id": "turn-123",
"items": [],
"status": "failed",
"error": {
"message": "Tool timeout",
"codexErrorInfo": null
}
}
```
this PR
- adds a helper function to amend `.codexpolicy` files with new prefix
rules
- adds a utility to `Policy` allowing prefix rules to be added to
existing `Policy` structs
both additions will be helpful as we thread codexpolicy into the TUI
workflow
# Ghost snapshot ignores
This PR should close#7067, #7395, #7405.
Prior to this change the ghost snapshot task ran `git status
--ignored=matching` so the report picked up literally every ignored
file. When a directory only contained entries matched by patterns such
as `dozens/*.txt`, `/test123/generated/*.html`, or `/wp-includes/*`, Git
still enumerated them and the large-untracked-dir detection treated the
parent directory as “large,” even though everything inside was
intentionally ignored.
By removing `--ignored=matching` we only capture true untracked paths
now, so those patterns stay out of the snapshot report and no longer
trigger the “large untracked directories” warning.
---------
Signed-off-by: lionelchg <lionel.cheng@hotmail.fr>
Co-authored-by: lionelchg <lionel.cheng@hotmail.fr>
Add a warning message as a user turn to the model if the model does not
behave as expected (here, for example, if the model opens too many
`unified_exec` sessions)
This change prototypes support for Skills with the CLI. This is an
**experimental** feature for internal testing.
---------
Co-authored-by: Gav Verma <gverma@openai.com>
Fixes#3939Fixes#2803
## Summary
- convert Windows clipboard file paths into their `/mnt/<drive>`
equivalents when running inside WSL so pasted images resolve correctly
- add WSL detection helpers and share them with unit tests to cover both
native Windows and WSL clipboard normalization cases
- improve the test suite by exercising Windows path handling plus a
dedicated WSL conversion scenario and keeping the code path guarded by
targeted cfgs
## Testing
- just fmt
- cargo test -p codex-tui
- cargo clippy -p codex-tui --tests
- just fix -p codex-tui
## Screenshots
_Codex TUI screenshot:_
<img width="1880" height="848" alt="describe this copied image"
src="https://github.com/user-attachments/assets/c620d43c-f45c-451e-8893-e56ae85a5eea"
/>
_GitHub docs directory screenshot:_
<img width="1064" height="478" alt="image-copied"
src="https://github.com/user-attachments/assets/eb5eef6c-eb43-45a0-8bfe-25c35bcae753"
/>
Co-authored-by: Eric Traut <etraut@openai.com>
- Add portable history log id helper to support inode-like tracking on
Unix and creation time on Windows
- Refactor history metadata and lookup to share code paths and allow
nonzero log ids across platforms
- Add coverage for lookup stability after appends
Fix the issue #7416 that the codex-cli produce an error "MCP startup
failure on missing 'type' field" in the startup.
- Cause: serde in `convert_to_rmcp`
(`codex-rs/rmcp-client/src/utils.rs`) failed because no `r#type` value
was provided
- Fix: set a default `r#type` value in the corresponding structs
## Summary
Adds the missing `xhigh` reasoning level everywhere it should have been
documented, and makes clear it only works with `gpt-5.1-codex-max`.
## Changes
* `docs/config.md`
* Add `xhigh` to the official list of reasoning levels with a note that
`xhigh` is exclusive to Codex Max.
* `docs/example-config.md`
* Update the example comment adding `xhigh` as a valid option but only
for Codex Max.
* `docs/faq.md`
* Update the model recommendation to `GPT-5.1 Codex Max`.
* Mention that users can choose `high` or the newly documented `xhigh`
level when using Codex Max.
Output hash for `rmcp-0.9.0` was missing from the nix package, (i.e.
`error: No hash was found while vendoring the git dependency
rmcp-0.9.0.`) blocking the build.
Fixes#7333
This is a small bug fix.
This PR fixes an inconsistency in `recent_commits` where `limit == 0`
still returns 1 commit due to the use of `limit.max(1)` when
constructing the `git log -n` argument.
Expected behavior: requesting 0 commits should return an empty list.
This PR:
- returns an empty `Vec` when `limit == 0`
- adds a test for `recent_commits(limit == 0)` that fails before the
change and passes afterwards
- maintains existing behavior for `limit > 0`
This aligns behavior with API expectations and avoids downstream
consumers misinterpreting the repository as having commit history when
`limit == 0` is used to explicitly request none.
Happy to adjust if the current behavior is intentional.
Bumps [serde_with](https://github.com/jonasbb/serde_with) from 3.14.0 to
3.16.1.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/jonasbb/serde_with/releases">serde_with's
releases</a>.</em></p>
<blockquote>
<h2>serde_with v3.16.1</h2>
<h3>Fixed</h3>
<ul>
<li>Fix <code>JsonSchemaAs</code> of <code>SetPreventDuplicates</code>
and <code>SetLastValueWins</code>. (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/906">#906</a>,
<a
href="https://redirect.github.com/jonasbb/serde_with/issues/907">#907</a>)</li>
</ul>
<h2>serde_with v3.16.0</h2>
<h3>Added</h3>
<ul>
<li>Added support for <code>smallvec</code> v1 under the
<code>smallvec_1</code> feature flag by <a
href="https://github.com/isharma228"><code>@isharma228</code></a> (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/895">#895</a>)</li>
<li>Add <code>JsonSchemaAs</code> implementation for
<code>json::JsonString</code> by <a
href="https://github.com/yogevm15"><code>@yogevm15</code></a> (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/901">#901</a>)</li>
</ul>
<h2>serde_with v3.15.1</h2>
<h3>Fixed</h3>
<ul>
<li>Fix building of the documentation by updating references to use
<code>serde_core</code>.</li>
</ul>
<h2>serde_with v3.15.0</h2>
<h3>Added</h3>
<ul>
<li>
<p>Added error inspection to <code>VecSkipError</code> and
<code>MapSkipError</code> by <a
href="https://github.com/michelhe"><code>@michelhe</code></a> (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/878">#878</a>)
This allows interacting with the previously hidden error, for example
for logging.
Checkout the newly added example to both types.</p>
</li>
<li>
<p>Allow documenting the types generated by <code>serde_conv!</code>.
The <code>serde_conv!</code> macro now acceps outer attributes before
the optional visibility modifier.
This allow adding doc comments in the shape of <code>#[doc =
"..."]</code> or any other attributes, such as lint
modifiers.</p>
<pre lang="rust"><code>serde_conv!(
#[doc = "Serialize bools as string"]
#[allow(dead_code)]
pub BoolAsString,
bool,
|x: &bool| ::std::string::ToString::to_string(x),
|x: ::std::string::String| x.parse()
);
</code></pre>
</li>
<li>
<p>Add support for <code>hashbrown</code> v0.16 (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/877">#877</a>)</p>
<p>This extends the existing support for <code>hashbrown</code> v0.14
and v0.15 to the newly released version.</p>
</li>
</ul>
<h3>Changed</h3>
<ul>
<li>Bump MSRV to 1.76, since that is required for <code>toml</code>
dev-dependency.</li>
</ul>
<h2>serde_with v3.14.1</h2>
<h3>Fixed</h3>
<ul>
<li>Show macro expansion in the docs.rs generated rustdoc.</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="8513323fda"><code>8513323</code></a>
Bump version to 3.16.1 (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/908">#908</a>)</li>
<li><a
href="5392bbe75e"><code>5392bbe</code></a>
Bump version to 3.16.1</li>
<li><a
href="1e54f1cd38"><code>1e54f1c</code></a>
Fix duplicate schema set definitions for schemars 0.8, 0.9, and 1.0 (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/907">#907</a>)</li>
<li><a
href="0650180645"><code>0650180</code></a>
Fix duplicate schema set definitions for schemars 0.8, 0.9, and 1.0</li>
<li><a
href="41d1033438"><code>41d1033</code></a>
Fix test conditions for schemars tests to include "hex"
feature</li>
<li><a
href="2eed58af05"><code>2eed58a</code></a>
Bump the github-actions group across 1 directory with 2 updates (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/905">#905</a>)</li>
<li><a
href="ed040f2330"><code>ed040f2</code></a>
Bump the github-actions group across 1 directory with 2 updates</li>
<li><a
href="fa2129b1b9"><code>fa2129b</code></a>
Bump ron from 0.11.0 to 0.12.0 (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/904">#904</a>)</li>
<li><a
href="b55cb99757"><code>b55cb99</code></a>
Bump ron from 0.11.0 to 0.12.0</li>
<li><a
href="066b9d4019"><code>066b9d4</code></a>
Bump version to 3.16.0 (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/903">#903</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/jonasbb/serde_with/compare/v3.14.0...v3.16.1">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>
Co-authored-by: Eric Traut <etraut@openai.com>
Bumps [arboard](https://github.com/1Password/arboard) from 3.6.0 to
3.6.1.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/1Password/arboard/releases">arboard's
releases</a>.</em></p>
<blockquote>
<h2>v3.6.1</h2>
<p>This release focuses on improving compatibility with data in the real
world and bug fixes. It also includes a new <code>Set</code> API for
working with file paths via drag-and-drop interfaces across Linux,
macOS, and Windows.</p>
<p>This release also marks the start of exclusively publishing
changelogs via GitHub Releases. The old <code>CHANGELOG.md</code> has
been removed due to maintenance overhead and duplication. <a
href="https://github.com/1Password/arboard/releases/tag/v3.6.0">v3.6.0</a>
is the last revision to include this file.</p>
<h3>Added</h3>
<ul>
<li>Add support for pasting lists of files via
<code>Set::file_list</code> interface by <a
href="https://github.com/Gae24"><code>@Gae24</code></a> in <a
href="https://redirect.github.com/1Password/arboard/pull/181">1Password/arboard#181</a></li>
<li>Support <code>windows-sys</code> 0.60 in <code>arboard</code>'s
allowed version range by <a
href="https://github.com/complexspaces"><code>@complexspaces</code></a>
in <a
href="https://redirect.github.com/1Password/arboard/pull/201">1Password/arboard#201</a></li>
</ul>
<h3>Changed</h3>
<ul>
<li>Fix grammar and typos by <a
href="https://github.com/complexspaces"><code>@complexspaces</code></a>
and <a href="https://github.com/gagath"><code>@gagath</code></a> in <a
href="https://redirect.github.com/1Password/arboard/pull/194">1Password/arboard#194</a>
and <a
href="https://redirect.github.com/1Password/arboard/pull/196">1Password/arboard#196</a></li>
<li>Prefer PNG when pasting images on Windows by <a
href="https://github.com/wcassels"><code>@wcassels</code></a> in <a
href="https://redirect.github.com/1Password/arboard/pull/198">1Password/arboard#198</a>
<ul>
<li>Note: This change greatly increases compatibility for
"complicated" images that contain alpha values and/or
transparent pixels. Support for transparency in <code>BITMAP</code>
formats is ill-defined and inconsistently implemented in the wild, but
is consistent in <code>PNG</code>. Most applications loading images onto
the clipboard include <code>PNG</code>-encoded data already.</li>
</ul>
</li>
<li>Bitmap images pasted on Windows now use the <code>image</code> crate
instead of a homegrown internal parser.
<ul>
<li>This <strong>should not</strong> regress any existing Bitmap use
cases and instead will provide more consistent and robust parsing. If
you notice something now broken, please open an issue!</li>
</ul>
</li>
</ul>
<h3>Fixed</h3>
<ul>
<li>Remove silent dropping of file paths when non-UTF8 was mixed in on
Linux by <a href="https://github.com/Gae24"><code>@Gae24</code></a> in
<a
href="https://redirect.github.com/1Password/arboard/pull/197">1Password/arboard#197</a></li>
<li>Fix parsing of 24-bit bitmaps on Windows by <a
href="https://github.com/wcassels"><code>@wcassels</code></a> in <a
href="https://redirect.github.com/1Password/arboard/pull/198">1Password/arboard#198</a>
<ul>
<li>Example: Images with transparency copied by Firefox are now handled
correctly, among others.</li>
</ul>
</li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a href="https://github.com/gagath"><code>@gagath</code></a> made
their first contribution in <a
href="https://redirect.github.com/1Password/arboard/pull/196">1Password/arboard#196</a></li>
<li><a href="https://github.com/wcassels"><code>@wcassels</code></a>
made their first contribution in <a
href="https://redirect.github.com/1Password/arboard/pull/198">1Password/arboard#198</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/1Password/arboard/compare/v3.6.0...v3.6.1">https://github.com/1Password/arboard/compare/v3.6.0...v3.6.1</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="a3750c79a5"><code>a3750c7</code></a>
Release 3.6.1</li>
<li><a
href="edcce2cd6b"><code>edcce2c</code></a>
Remove CHANGELOG.md in favor of GitHub releases</li>
<li><a
href="26a96a6199"><code>26a96a6</code></a>
Bump windows-sys semver range to support 0.60.x</li>
<li><a
href="7bdd1c1175"><code>7bdd1c1</code></a>
Update errno for windows-sys 0.60 flexibility</li>
<li><a
href="55c0b260c4"><code>55c0b26</code></a>
read/write_unaligned rather than using manual field offsets</li>
<li><a
href="ff15a093d6"><code>ff15a09</code></a>
Return conversionFailure instead of adhoc errors</li>
<li><a
href="16ef18113f"><code>16ef181</code></a>
Implement fetching PNG on Windows and prefer over DIB when
available</li>
<li><a
href="a3c64f9a93"><code>a3c64f9</code></a>
Add a couple of end-to-end DIBV5 tests</li>
<li><a
href="e6008eaa91"><code>e6008ea</code></a>
Use image for reading DIB and try to make it do the right thing for
32-bit BI...</li>
<li><a
href="17ef05ce13"><code>17ef05c</code></a>
add <code>file_list</code> to <code>Set</code> interface (<a
href="https://redirect.github.com/1Password/arboard/issues/181">#181</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/1Password/arboard/compare/v3.6.0...v3.6.1">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>
Title: Improve rollout session initialization error messages
Issue: https://github.com/openai/codex/issues/7283
What: add targeted mapping for rollout/session initialization errors so
users get actionable messages when Codex cannot access session files.
Why: session creation previously returned a generic internal error,
hiding permissions/FS issues and making support harder.
How:
- Added rollout::error::map_session_init_error to translate the more
common io::Error kinds into user-facing hints (permission, missing dir,
file blocking, corruption). Others are passed through directly with
`CodexErr::Fatal`.
- Reused the mapper in Codex session creation to preserve root causes
instead of returning InternalAgentDied.
This PR is a modified version of [a
PR](https://github.com/openai/codex/pull/7316) submitted by @yydrowz3.
* Removes a redundant `experimental_sandbox_command_assessment` flag
* Moves `mcp_oauth_credentials_store` from the `[features]` table, where
it doesn't belong
This PR is a documentation only one which:
- addresses the #7231 by adding a paragraph in `docs/getting-started.md`
in the tips category to encourage users to load everything needed in
their environment
- corrects link referencing in `docs/platform-sandboxing.md` so that the
page link opens at the right section
- removes the explicit heading IDs like {#my-id} in `docs/advanced.md`
which are not supported by GitHub and are **not** rendered in the UI:
<img width="1198" height="849" alt="Screenshot 2025-11-26 at 16 25 31"
src="https://github.com/user-attachments/assets/308d33c3-81d3-4785-a6c1-e9377e6d3ea6"
/>
This caused the following links in `README.md` to not work in `main` but
to work in this branch (you can test by going to
https://github.com/openai/codex/blob/docs/getting-started-enhancement/README.md)
- the MCP link goes straight to the correct section now:
```markdown
- [**Advanced**](./docs/advanced.md)
- [Tracing / verbose logging](./docs/advanced.md#tracing--verbose-logging)
- [Model Context Protocol (MCP)](./docs/advanced.md#model-context-protocol-mcp)
```
---------
Signed-off-by: lionel-oai <lionel@openai.com>
Signed-off-by: lionelchg <lionel.cheng@hotmail.fr>
Co-authored-by: lionelchg <lionel.cheng@hotmail.fr>
Recent model updates caused the experimental "sandbox tool assessment"
to time out most of the time leaving the user without any risk
assessment or tool summary. This change explicitly sets the reasoning
effort to medium and bumps the timeout.
This change has no effect if the user hasn't enabled the
`experimental_sandbox_command_assessment` feature flag.
the `/approvals` popup fails to recognize that the CLI is in
WorkspaceWrite mode if that policy has extra bits, like `writable_roots`
etc.
This change matches the policy, ignoring additional config aspects.
This is the V2 version of `EventMsg::TurnDiff`.
I decided to expose this as a `turn/*` notification as opposed to an
Item to make it more explicit that the diff is accumulated throughout a
turn (every `apply_patch` call updates the running diff). Also, I don't
think it's worth persisting this diff as an Item because it can always
be recomputed from the actual `FileChange` Items.
Add `thread_id` and `turn_id` to `item/started`, `item/completed`, and
`error` notifications. Otherwise the client will have a hard time
knowing which thread & turn (if multiple threads are running in
parallel) a new item/error is for.
Also add `thread_id` to `turn/started` and `turn/completed`.
Add a new endpoint that allows us to test multi-turn behavior.
Tested with running:
```
RUST_LOG=codex_app_server=debug CODEX_BIN=target/debug/codex \
cargo run -p codex-app-server-test-client -- \
send-follow-up-v2 "hello" "and now a follow-up question"
```
### **Summary of Changes**
**What?**
Fix for slash commands (e.g., /prompts:code-review) not being recognized
when large content (>3000 chars) is pasted.
[Bug Report](https://github.com/openai/codex/issues/7047)
**Why?**
With large pastes, slash commands were ignored, so custom prompts
weren't expanded and were submitted as literal text.
**How?**
Refactored the early return block in handle_key_event_without_popup
(lines 957-968).
Instead of returning early after replacing placeholders, the code now
replaces placeholders in the textarea and continues to the normal
submission flow.
This reuses the existing slash command detection and custom prompt
expansion logic (lines 981-1047), avoiding duplication.
**Changes:**
Modified codex-rs/tui/src/bottom_pane/chat_composer.rs: refactored early
return block to continue to normal flow instead of returning immediately
Added test: custom_prompt_with_large_paste_expands_correctly to verify
the fix
**Code Quality:**
No lint warnings
Code follows existing patterns and reuses existing logic
Atomic change focused on the bug fix
Bumps [webbrowser](https://github.com/amodm/webbrowser-rs) from 1.0.5 to
1.0.6.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/amodm/webbrowser-rs/releases">webbrowser's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.6</h2>
<h3>Fixed</h3>
<ul>
<li>Windows: fix browser opening when unicode characters exist in path.
See PR <a
href="https://redirect.github.com/amodm/webbrowser-rs/issues/108">#108</a></li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/amodm/webbrowser-rs/blob/main/CHANGELOG.md">webbrowser's
changelog</a>.</em></p>
<blockquote>
<h2>[1.0.6] - 2025-10-15 <!-- raw HTML omitted --><!-- raw HTML omitted
--></h2>
<h3>Fixed</h3>
<ul>
<li>Windows: fix browser opening when unicode characters exist in path.
See PR <a
href="https://redirect.github.com/amodm/webbrowser-rs/issues/108">#108</a></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="659622914a"><code>6596229</code></a>
Release v1.0.6 [skip ci]</li>
<li><a
href="44908ca5f3"><code>44908ca</code></a>
ios: fix lint for objc2 invocation #build-ios</li>
<li><a
href="b76a217a07"><code>b76a217</code></a>
Merge branch 'Nodeigi-fix/107'</li>
<li><a
href="ee2b1cdf2e"><code>ee2b1cd</code></a>
fix opening a browser that is located in a path that contains unicode
characters</li>
<li><a
href="061e65e6b8"><code>061e65e</code></a>
ios: fix lints</li>
<li><a
href="85dd4a37fc"><code>85dd4a3</code></a>
macos: fix lints</li>
<li>See full diff in <a
href="https://github.com/amodm/webbrowser-rs/compare/v1.0.5...v1.0.6">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 [toml_edit](https://github.com/toml-rs/toml) from 0.23.4 to
0.23.5.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="4695fb02fc"><code>4695fb0</code></a>
chore: Release</li>
<li><a
href="6a77ed71cf"><code>6a77ed7</code></a>
docs: Update changelog</li>
<li><a
href="c1e8197964"><code>c1e8197</code></a>
refactor: Switch serde dependency to serde_core (<a
href="https://redirect.github.com/toml-rs/toml/issues/1036">#1036</a>)</li>
<li><a
href="d85d6cd61c"><code>d85d6cd</code></a>
refactor: Switch serde dependency to serde_core</li>
<li>See full diff in <a
href="https://github.com/toml-rs/toml/compare/v0.23.4...v0.23.5">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>
Bumps [regex](https://github.com/rust-lang/regex) from 1.11.1 to 1.12.2.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/rust-lang/regex/blob/master/CHANGELOG.md">regex's
changelog</a>.</em></p>
<blockquote>
<h1>1.12.2 (2025-10-13)</h1>
<p>This release fixes a <code>cargo doc</code> breakage on nightly when
<code>--cfg docsrs</code> is
enabled. This caused documentation to fail to build on docs.rs.</p>
<p>Bug fixes:</p>
<ul>
<li>[BUG <a
href="https://redirect.github.com/rust-lang/regex/issues/1305">#1305</a>](<a
href="https://redirect.github.com/rust-lang/regex/issues/1305">rust-lang/regex#1305</a>):
Switches the <code>doc_auto_cfg</code> feature to <code>doc_cfg</code>
on nightly for docs.rs builds.</li>
</ul>
<h1>1.12.1 (2025-10-10)</h1>
<p>This release makes a bug fix in the new
<code>regex::Captures::get_match</code> API
introduced in <code>1.12.0</code>. There was an oversight with the
lifetime parameter
for the <code>Match</code> returned. This is technically a breaking
change, but given
that it was caught almost immediately and I've yanked the
<code>1.12.0</code> release,
I think this is fine.</p>
<h1>1.12.0 (2025-10-10)</h1>
<p>This release contains a smattering of bug fixes, a fix for excessive
memory
consumption in some cases and a new
<code>regex::Captures::get_match</code> API.</p>
<p>Improvements:</p>
<ul>
<li>[FEATURE <a
href="https://redirect.github.com/rust-lang/regex/issues/1146">#1146</a>](<a
href="https://redirect.github.com/rust-lang/regex/issues/1146">rust-lang/regex#1146</a>):
Add <code>Capture::get_match</code> for returning the overall match
without <code>unwrap()</code>.</li>
</ul>
<p>Bug fixes:</p>
<ul>
<li>[BUG <a
href="https://redirect.github.com/rust-lang/regex/issues/1083">#1083</a>](<a
href="https://redirect.github.com/rust-lang/regex/issues/1083">rust-lang/regex#1083</a>):
Fixes a panic in the lazy DFA (can only occur for especially large
regexes).</li>
<li>[BUG <a
href="https://redirect.github.com/rust-lang/regex/issues/1116">#1116</a>](<a
href="https://redirect.github.com/rust-lang/regex/issues/1116">rust-lang/regex#1116</a>):
Fixes a memory usage regression for large regexes (introduced in
<code>regex 1.9</code>).</li>
<li>[BUG <a
href="https://redirect.github.com/rust-lang/regex/issues/1195">#1195</a>](<a
href="https://redirect.github.com/rust-lang/regex/issues/1195">rust-lang/regex#1195</a>):
Fix universal start states in sparse DFA.</li>
<li>[BUG <a
href="https://redirect.github.com/rust-lang/regex/issues/1295">#1295</a>](<a
href="https://redirect.github.com/rust-lang/regex/pull/1295">rust-lang/regex#1295</a>):
Fixes a panic when deserializing a corrupted dense DFA.</li>
<li><a
href="8f5d9479d0">BUG
8f5d9479</a>:
Make <code>regex_automata::meta::Regex::find</code> consistently return
<code>None</code> when
<code>WhichCaptures::None</code> is used.</li>
</ul>
<h1>1.11.3 (2025-09-25)</h1>
<p>This is a small patch release with an improvement in memory usage in
some
cases.</p>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="5ea3eb1e95"><code>5ea3eb1</code></a>
1.12.2</li>
<li><a
href="ab0b07171b"><code>ab0b071</code></a>
regex-automata-0.4.13</li>
<li><a
href="691d51457d"><code>691d514</code></a>
regex-syntax-0.8.8</li>
<li><a
href="1dd9077779"><code>1dd9077</code></a>
docs: swap <code>doc_auto_cfg</code> with <code>doc_cfg</code></li>
<li><a
href="0089034cb3"><code>0089034</code></a>
regex-cli-0.2.3</li>
<li><a
href="140f8949da"><code>140f894</code></a>
regex-lite-0.1.8</li>
<li><a
href="27d6d65263"><code>27d6d65</code></a>
1.12.1</li>
<li><a
href="85398ad500"><code>85398ad</code></a>
changelog: 1.12.1</li>
<li><a
href="764efbd305"><code>764efbd</code></a>
api: tweak the lifetime of <code>Captures::get_match</code></li>
<li><a
href="ee6aa55e01"><code>ee6aa55</code></a>
rure-0.2.4</li>
<li>Additional commits viewable in <a
href="https://github.com/rust-lang/regex/compare/1.11.1...1.12.2">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>
clean up the code for scanning for world writable directories
One path (selecting a sandbox mode from /approvals) was using an
incorrect method that did not use the new method of creating deny aces
to prevent writing to those directories. Now all paths are the same.
- The total token used returned from the api doesn't account for the
reasoning items before the assistant message
- Account for those for auto compaction
- Add the encrypted reasoning effort in the common tests utils
- Add a test to make sure it works as expected
This introduces a new feature to Codex when it operates as an MCP
_client_ where if an MCP _server_ replies that it has an entry named
`"codex/sandbox-state"` in its _server capabilities_, then Codex will
send it an MCP notification with the following structure:
```json
{
"method": "codex/sandbox-state/update",
"params": {
"sandboxPolicy": {
"type": "workspace-write",
"network-access": false,
"exclude-tmpdir-env-var": false
"exclude-slash-tmp": false
},
"codexLinuxSandboxExe": null,
"sandboxCwd": "/Users/mbolin/code/codex2"
}
}
```
or with whatever values are appropriate for the initial `sandboxPolicy`.
**NOTE:** Codex _should_ continue to send the MCP server notifications
of the same format if these things change over the lifetime of the
thread, but that isn't wired up yet.
The result is that `shell-tool-mcp` can consume these values so that
when it calls `codex_core::exec::process_exec_tool_call()` in
`codex-rs/exec-server/src/posix/escalate_server.rs`, it is now sure to
call it with the correct values (whereas previously we relied on
hardcoded values).
While I would argue this is a supported use case within the MCP
protocol, the `rmcp` crate that we are using today does not support
custom notifications. As such, I had to patch it and I submitted it for
review, so hopefully it will be accepted in some form:
https://github.com/modelcontextprotocol/rust-sdk/pull/556
To test out this change from end-to-end:
- I ran `cargo build` in `~/code/codex2/codex-rs/exec-server`
- I built the fork of Bash in `~/code/bash/bash`
- I added the following to my `~/.codex/config.toml`:
```toml
# Use with `codex --disable shell_tool`.
[mcp_servers.execshell]
args = ["--bash", "/Users/mbolin/code/bash/bash"]
command = "/Users/mbolin/code/codex2/codex-rs/target/debug/codex-exec-mcp-server"
```
- From `~/code/codex2/codex-rs`, I ran `just codex --disable shell_tool`
- When the TUI started up, I verified that the sandbox mode is
`workspace-write`
- I ran `/mcp` to verify that the shell tool from the MCP is there:
<img width="1387" height="1400" alt="image"
src="https://github.com/user-attachments/assets/1a8addcc-5005-4e16-b59f-95cfd06fd4ab"
/>
- Then I asked it:
> what is the output of `gh issue list`
because this should be auto-approved with our existing dummy policy:
af63e6eccc/codex-rs/exec-server/src/posix.rs (L157-L164)
And it worked:
<img width="1387" height="1400" alt="image"
src="https://github.com/user-attachments/assets/7568d2f7-80da-4d68-86d0-c265a6f5e6c1"
/>
`process_exec_tool_call()` was taking `SandboxType` as a param, but in
practice, the only place it was constructed was in
`codex_message_processor.rs` where it was derived from the other
`sandbox_policy` param, so this PR inlines the logic that decides the
`SandboxType` into `process_exec_tool_call()`.
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/7122).
* #7112
* __->__ #7122
Piping to codex fails to do anything useful and locks up the process.
We currently check for stdout, but not stdin
```
❯ echo foo|just c
cargo run --bin codex -- "$@"
Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.21s
Running `target/debug/codex`
Error: stdin is not a terminal
error: Recipe `codex` failed on line 10 with exit code 1
```
The unified exec tool has a `login` option that defaults to `true`:
3bdcbc7292/codex-rs/core/src/tools/handlers/unified_exec.rs (L35-L36)
This updates the `ExecParams` for `shell-tool-mcp` to support the same
parameter. Note it is declared as `Option<bool>` to ensure it is marked
optional in the generated JSON schema.
## Summary
When incrementing the minor version, we should reset patch to 0, rather
than keeping it.
## Testing
- [x] tested locally with dry_run and `get_latest_release_version`
mocked out
---------
Co-authored-by: Michael Bolin <mbolin@openai.com>
https://github.com/openai/codex/pull/7005 introduced a new part of the
release process that added multiple files named `bash` in the `dist/`
folder used as the basis of the GitHub Release. I believe that all file
names in a GitHub Release have to be unique, which is why the recent
release build failed:
https://github.com/openai/codex/actions/runs/19577669780/job/56070183504
Based on the output of the **List** step, I believe these are the
appropriate artifacts to delete as a quick fix.
Add a `Declined` status for when we request an approval from the user
and the user declines. This allows us to distinguish from commands that
actually ran, but failed.
This behaves similarly to apply_patch / FileChange, which does the same
thing.
This adds a GitHub workflow for building a new npm module we are
experimenting with that contains an MCP server for running Bash
commands. The new workflow, `shell-tool-mcp`, is a dependency of the
general `release` workflow so that we continue to use one version number
for all artifacts across the project in one GitHub release.
`.github/workflows/shell-tool-mcp.yml` is the primary workflow
introduced by this PR, which does the following:
- builds the `codex-exec-mcp-server` and `codex-execve-wrapper`
executables for both arm64 and x64 versions of Mac and Linux (preferring
the MUSL version for Linux)
- builds Bash (dynamically linked) for a [comically] large number of
platforms (both x64 and arm64 for most) with a small patch specified by
`shell-tool-mcp/patches/bash-exec-wrapper.patch`:
- `debian-11`
- `debian-12`
- `ubuntu-20.04`
- `ubuntu-22.04`
- `ubuntu-24.04`
- `centos-9`
- `macos-13` (x64 only)
- `macos-14` (arm64 only)
- `macos-15` (arm64 only)
- builds the TypeScript for the [new] Node module declared in the
`shell-tool-mcp/` folder, which creates `bin/mcp-server.js`
- adds all of the native binaries to `shell-tool-mcp/vendor/` folder;
`bin/mcp-server.js` does a runtime check to determine which ones to
execute
- uses `npm pack` to create the `.tgz` for the module
- if `publish: true` is set, invokes the `npm publish` call with the
`.tgz`
The justification for building Bash for so many different operating
systems is because, since it is dynamically linked, we want to increase
our confidence that the version we build is compatible with the glibc
whatever OS we end up running on. (Note this is less of a concern with
`codex-exec-mcp-server` and `codex-execve-wrapper` on Linux, as they are
statically linked.)
This PR also introduces the code for the npm module in `shell-tool-mcp/`
(the proposed module name is `@openai/codex-shell-tool-mcp`). Initially,
I intended the module to be a single file of vanilla JavaScript (like
[`codex-cli/bin/codex.js`](ab5972d447/codex-cli/bin/codex.js)),
but some of the logic seemed a bit tricky, so I decided to port it to
TypeScript and add unit tests.
`shell-tool-mcp/src/index.ts` defines the `main()` function for the
module, which performs runtime checks to determine the clang triple to
find the path to the Rust executables within the `vendor/` folder
(`resolveTargetTriple()`). It uses a combination of `readOsRelease()`
and `resolveBashPath()` to determine the correct Bash executable to run
in the environment. Ultimately, it spawns a command like the following:
```
codex-exec-mcp-server \
--execve codex-execve-wrapper \
--bash custom-bash "$@"
```
Note `.github/workflows/shell-tool-mcp-ci.yml` defines a fairly standard
CI job for the module (`format`/`build`/`test`).
To test this PR, I pushed this branch to my personal fork of Codex and
ran the CI job there:
https://github.com/bolinfest/codex/actions/runs/19564311320
Admittedly, the graph looks a bit wild now:
<img width="5115" height="2969" alt="Screenshot 2025-11-20 at 11 44
58 PM"
src="https://github.com/user-attachments/assets/cc5ef306-efc1-4ed7-a137-5347e394f393"
/>
But when it finished, I was able to download `codex-shell-tool-mcp-npm`
from the **Artifacts** for the workflow in an empty temp directory,
unzip the `.zip` and then the `.tgz` inside it, followed by `xattr -rc
.` to remove the quarantine bits. Then I ran:
```shell
npx @modelcontextprotocol/inspector node /private/tmp/foobar4/package/bin/mcp-server.js
```
which launched the MCP Inspector and I was able to use it as expected!
This bodes well that this should work once the package is published to
npm:
```shell
npx @modelcontextprotocol/inspector npx @openai/codex-shell-tool-mcp
```
Also, to verify the package contains what I expect:
```shell
/tmp/foobar4/package$ tree
.
├── bin
│ └── mcp-server.js
├── package.json
├── README.md
└── vendor
├── aarch64-apple-darwin
│ ├── bash
│ │ ├── macos-14
│ │ │ └── bash
│ │ └── macos-15
│ │ └── bash
│ ├── codex-exec-mcp-server
│ └── codex-execve-wrapper
├── aarch64-unknown-linux-musl
│ ├── bash
│ │ ├── centos-9
│ │ │ └── bash
│ │ ├── debian-11
│ │ │ └── bash
│ │ ├── debian-12
│ │ │ └── bash
│ │ ├── ubuntu-20.04
│ │ │ └── bash
│ │ ├── ubuntu-22.04
│ │ │ └── bash
│ │ └── ubuntu-24.04
│ │ └── bash
│ ├── codex-exec-mcp-server
│ └── codex-execve-wrapper
├── x86_64-apple-darwin
│ ├── bash
│ │ └── macos-13
│ │ └── bash
│ ├── codex-exec-mcp-server
│ └── codex-execve-wrapper
└── x86_64-unknown-linux-musl
├── bash
│ ├── centos-9
│ │ └── bash
│ ├── debian-11
│ │ └── bash
│ ├── debian-12
│ │ └── bash
│ ├── ubuntu-20.04
│ │ └── bash
│ ├── ubuntu-22.04
│ │ └── bash
│ └── ubuntu-24.04
│ └── bash
├── codex-exec-mcp-server
└── codex-execve-wrapper
26 directories, 26 files
```
It stopped working (found zero duplicates) starting three days ago when
the model was switched from `gpt-5` to `gpt-5.1`. I'm not sure why it
stopped working. This is an attempt to get it working again by using the
default model for the codex action (which is presumably
`gpt-5.1-codex-max`).
### 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.
For MacOS and Linux: copy the output of `uname -mprs`
For Windows: copy the output of `"$([Environment]::OSVersion | ForEach-Object VersionString) $(if ([Environment]::Is64BitOperatingSystem) { "x64" } else { "x86" })"` in the PowerShell console
- type:textarea
id:actual
attributes:
label:What issue are you seeing?
description:Please include the full error messages and prompts with PII redacted. If possible, please provide text instead of a screenshot.
validations:
required:true
- type:textarea
id:steps
attributes:
label:What steps can reproduce the bug?
description:Explain the bug and provide a code snippet that can reproduce it.
description:Explain the bug and provide a code snippet that can reproduce it. Please include session id, token limit usage, context window usage if applicable.
validations:
required:true
- type:textarea
@@ -44,11 +59,6 @@ body:
attributes:
label:What is the expected behavior?
description:If possible, please provide text instead of a screenshot.
- type:textarea
id:actual
attributes:
label:What do you see instead?
description:If possible, please provide text instead of a screenshot.
label:What version of the VS Code extension are you using?
validations:
required:true
- type:input
id:plan
attributes:
label:What subscription do you have?
validations:
required:true
- type:input
id:ide
attributes:
label:Which IDE are you using?
description:Like `VS Code`, `Cursor`, `Windsurf`, etc.
validations:
required:true
- type:input
id:platform
attributes:
@@ -26,11 +36,18 @@ body:
description:|
For MacOS and Linux: copy the output of `uname -mprs`
For Windows: copy the output of `"$([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.
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
@@ -38,11 +55,6 @@ 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.
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.
@@ -8,11 +8,18 @@ In the codex-rs folder where the rust code lives:
- 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.
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:
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.
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.
- 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).
@@ -39,6 +47,7 @@ See `codex-rs/tui/styles.md`.
- 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.
@@ -60,8 +69,36 @@ This repo uses snapshot tests (via `insta`), especially in `codex-rs/tui`, to va
-`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.
<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>
@@ -62,29 +63,37 @@ You can also use Codex with an API key, but this requires [additional setup](./d
### Model Context Protocol (MCP)
Codex CLI supports [MCP servers](./docs/advanced.md#model-context-protocol-mcp). Enable by adding an `mcp_servers` section to your `~/.codex/config.toml`.
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
See the [Execpolicy quickstart](./docs/execpolicy.md) to set up rules that govern what commands Codex can execute.
You can also install via Homebrew (`brew install codex`) or download a platform-specific release directly from our [GitHub Releases](https://github.com/openai/codex/releases).
You can also install via Homebrew (`brew install --cask codex`) or download a platform-specific release directly from our [GitHub Releases](https://github.com/openai/codex/releases).
## Documentation quickstart
- First run with Codex? Follow the walkthrough in [`docs/getting-started.md`](../docs/getting-started.md) for prompts, keyboard shortcuts, and session management.
- Already shipping with Codex and want deeper control? Jump to [`docs/advanced.md`](../docs/advanced.md) and the configuration reference at [`docs/config.md`](../docs/config.md).
## What's new in the Rust CLI
@@ -23,9 +28,15 @@ Codex supports a rich set of configuration options. Note that the Rust CLI uses
### Model Context Protocol Support
Codex CLI functions as an MCP client that can connect to MCP servers on startup. See the [`mcp_servers`](../docs/config.md#mcp_servers) section in the configuration documentation for details.
#### MCP client
It is still experimental, but you can also launch Codex as an MCP _server_ by running `codex mcp-server`. Use the [`@modelcontextprotocol/inspector`](https://github.com/modelcontextprotocol/inspector) to try it out:
Codex CLI functions as an MCP client that allows the Codex CLI and IDE extension to connect to MCP servers on startup. See the [`configuration documentation`](../docs/config.md#mcp_servers) for details.
#### MCP server (experimental)
Codex can be launched as an MCP _server_ by running `codex mcp-server`. This allows _other_ MCP clients to use Codex as a tool for another agent.
Use the [`@modelcontextprotocol/inspector`](https://github.com/modelcontextprotocol/inspector) to try it out:
@@ -41,39 +52,22 @@ You can enable notifications by configuring a script that is run whenever the ag
To run Codex non-interactively, run `codex exec PROMPT` (you can also pass the prompt via `stdin`) and Codex will work on your task until it decides that it is done and exits. Output is printed to the terminal directly. You can set the `RUST_LOG` environment variable to see more about what's going on.
### Use `@` for file search
Typing `@` triggers a fuzzy-filename search over the workspace root. Use up/down to select among the results and Tab or Enter to replace the `@` with the selected path. You can use Esc to cancel the search.
### Esc–Esc to edit a previous message
When the chat composer is empty, press Esc to prime “backtrack” mode. Press Esc again to open a transcript preview highlighting the last user message; press Esc repeatedly to step to older user messages. Press Enter to confirm and Codex will fork the conversation from that point, trim the visible transcript accordingly, and pre‑fill the composer with the selected user message so you can edit and resubmit it.
In the transcript preview, the footer shows an `Esc edit prev` hint while editing is active.
### `--cd`/`-C` flag
Sometimes it is not convenient to `cd` to the directory you want Codex to use as the "working root" before running Codex. Fortunately, `codex` supports a `--cd` option so you can specify whatever folder you want. You can confirm that Codex is honoring `--cd` by double-checking the **workdir** it reports in the TUI at the start of a new session.
### Shell completions
Generate shell completion scripts via:
```shell
codex completion bash
codex completion zsh
codex completion fish
```
### Experimenting with the Codex Sandbox
To test to see what happens when a command is run under the sandbox provided by Codex, we provide the following subcommands in Codex CLI:
"Generated TypeScript still includes unions with `undefined` in {undefined_offenders:?}"
);
// If this assertion fails, it means a field was generated as
// "?: T | null" — i.e., both optional (undefined) and nullable (null).
// We only want either "?: T" or ": T | null".
assert!(
optional_nullable_offenders.is_empty(),
"Generated TypeScript has optional fields with nullable types (disallowed '?: T | null'), add #[ts(optional)] to fix:\n{optional_nullable_offenders:?}"
`codex app-server` is the interface Codex uses to power rich interfaces such as the [Codex VS Code extension](https://marketplace.visualstudio.com/items?itemName=openai.chatgpt).
## Table of Contents
- [Protocol](#protocol)
- [Message Schema](#message-schema)
- [Core Primitives](#core-primitives)
- [Lifecycle Overview](#lifecycle-overview)
- [Initialization](#initialization)
- [API Overview](#api-overview)
- [Events](#events)
- [Auth endpoints](#auth-endpoints)
## Protocol
Similar to [MCP](https://modelcontextprotocol.io/), `codex app-server` supports bidirectional communication, streaming JSONL over stdio. The protocol is JSON-RPC 2.0, though the `"jsonrpc":"2.0"` header is omitted.
## Message Schema
Currently, you can dump a TypeScript version of the schema using `codex app-server generate-ts`, or a JSON Schema bundle via `codex app-server generate-json-schema`. Each output is specific to the version of Codex you used to run the command, so the generated artifacts are guaranteed to match that version.
```
codex app-server generate-ts --out DIR
codex app-server generate-json-schema --out DIR
```
## Core Primitives
The API exposes three top level primitives representing an interaction between a user and Codex:
- **Thread**: A conversation between a user and the Codex agent. Each thread contains multiple turns.
- **Turn**: One turn of the conversation, typically starting with a user message and finishing with an agent message. Each turn contains multiple items.
- **Item**: Represents user inputs and agent outputs as part of the turn, persisted and used as the context for future conversations. Example items include user message, agent reasoning, agent message, shell command, file edit, etc.
Use the thread APIs to create, list, or archive conversations. Drive a conversation with turn APIs and stream progress via turn notifications.
## Lifecycle Overview
- Initialize once: Immediately after launching the codex app-server process, send an `initialize` request with your client metadata, then emit an `initialized` notification. Any other request before this handshake gets rejected.
- Start (or resume) a thread: Call `thread/start` to open a fresh conversation. The response returns the thread object and you’ll also get a `thread/started` notification. If you’re continuing an existing conversation, call `thread/resume` with its ID instead.
- Begin a turn: To send user input, call `turn/start` with the target `threadId` and the user's input. Optional fields let you override model, cwd, sandbox policy, etc. This immediately returns the new turn object and triggers a `turn/started` notification.
- Stream events: After `turn/start`, keep reading JSON-RPC notifications on stdout. You’ll see `item/started`, `item/completed`, deltas like `item/agentMessage/delta`, tool progress, etc. These represent streaming model output plus any side effects (commands, tool calls, reasoning notes).
- Finish the turn: When the model is done (or the turn is interrupted via making the `turn/interrupt` call), the server sends `turn/completed` with the final turn state and token usage.
## Initialization
Clients must send a single `initialize` request before invoking any other method, then acknowledge with an `initialized` notification. The server returns the user agent string it will present to upstream services; subsequent requests issued before initialization receive a `"Not initialized"` error, and repeated `initialize` calls receive an `"Already initialized"` error.
Applications building on top of `codex app-server` should identify themselves via the `clientInfo` parameter.
Example (from OpenAI's official VSCode extension):
```json
{"method":"initialize","id":0,"params":{
"clientInfo":{"name":"codex-vscode","title":"Codex VS Code Extension","version":"0.1.0"}
}}
```
## API Overview
-`thread/start` — create a new thread; emits `thread/started` and auto-subscribes you to turn/item events for that thread.
-`thread/resume` — reopen an existing thread by id so subsequent `turn/start` calls append to it.
-`thread/list` — page through stored rollouts; supports cursor-based pagination and optional `modelProviders` filtering.
-`thread/archive` — move a thread’s rollout file into the archived directory; returns `{}` on success.
-`turn/start` — add user input to a thread and begin Codex generation; responds with the initial `turn` object and streams `turn/started`, `item/*`, and `turn/completed` notifications.
-`turn/interrupt` — request cancellation of an in-flight turn by `(thread_id, turn_id)`; success is an empty `{}` response and the turn finishes with `status: "interrupted"`.
-`review/start` — kick off Codex’s automated reviewer for a thread; responds like `turn/start` and emits `item/started`/`item/completed` notifications with `enteredReviewMode` and `exitedReviewMode` items, plus a final assistant `agentMessage` containing the review.
-`command/exec` — run a single command under the server sandbox without starting a thread/turn (handy for utilities and validation).
-`model/list` — list available models (with reasoning effort options).
-`feedback/upload` — submit a feedback report (classification + optional reason/logs and conversation_id); returns the tracking thread id.
-`command/exec` — run a single command under the server sandbox without starting a thread/turn (handy for utilities and validation).
-`config/read` — fetch the effective config on disk after resolving config layering.
-`config/value/write` — write a single config key/value to the user's config.toml on disk.
-`config/batchWrite` — apply multiple config edits atomically to the user's config.toml on disk.
### Example: Start or resume a thread
Start a fresh thread when you need a new Codex conversation.
```json
{"method":"thread/start","id":10,"params":{
// Optionally set config settings. If not specified, will use the user's
To continue a stored session, call `thread/resume` with the `thread.id` you previously recorded. The response shape matches `thread/start`, and no additional notifications are emitted:
You can optionally specify config overrides on the new turn. If specified, these settings become the default for subsequent turns on the same thread.
```json
{"method":"turn/start","id":30,"params":{
"threadId":"thr_123",
"input":[{"type":"text","text":"Run tests"}],
// Below are optional config overrides
"cwd":"/Users/me/project",
"approvalPolicy":"unlessTrusted",
"sandboxPolicy":{
"mode":"workspaceWrite",
"writableRoots":["/Users/me/project"],
"networkAccess":true
},
"model":"gpt-5.1-codex",
"effort":"medium",
"summary":"concise"
}}
{"id":30,"result":{"turn":{
"id":"turn_456",
"status":"inProgress",
"items":[],
"error":null
}}}
```
### Example: Interrupt an active turn
You can cancel a running Turn with `turn/interrupt`.
```json
{"method":"turn/interrupt","id":31,"params":{
"threadId":"thr_123",
"turnId":"turn_456"
}}
{"id":31,"result":{}}
```
The server requests cancellations for running subprocesses, then emits a `turn/completed` event with `status: "interrupted"`. Rely on the `turn/completed` to know when Codex-side cleanup is done.
### Example: Request a code review
Use `review/start` to run Codex’s reviewer on the currently checked-out project. The request takes the thread id plus a `target` describing what should be reviewed:
-`{"type":"uncommittedChanges"}` — staged, unstaged, and untracked files.
-`{"type":"baseBranch","branch":"main"}` — diff against the provided branch’s upstream (see prompt for the exact `git merge-base`/`git diff` instructions Codex will run).
-`{"type":"commit","sha":"abc1234","title":"Optional subject"}` — review a specific commit.
-`{"type":"custom","instructions":"Free-form reviewer instructions"}` — fallback prompt equivalent to the legacy manual review request.
-`delivery` (`"inline"` or `"detached"`, default `"inline"`) — where the review runs:
-`"inline"`: run the review as a new turn on the existing thread. The response’s `reviewThreadId` equals the original `threadId`, and no new `thread/started` notification is emitted.
-`"detached"`: fork a new review thread from the parent conversation and run the review there. The response’s `reviewThreadId` is the id of this new review thread, and the server emits a `thread/started` notification for it before streaming review items.
For a detached review, use `"delivery": "detached"`. The response is the same shape, but `reviewThreadId` will be the id of the new review thread (different from the original `threadId`). The server also emits a `thread/started` notification for that new thread before streaming the review turn.
Codex streams the usual `turn/started` notification followed by an `item/started`
with an `enteredReviewMode` item so clients can show progress:
```json
{"method":"item/started","params":{"item":{
"type":"enteredReviewMode",
"id":"turn_900",
"review":"current changes"
}}}
```
When the reviewer finishes, the server emits `item/started` and `item/completed`
containing an `exitedReviewMode` item with the final review text:
The `review` string is plain text that already bundles the overall explanation plus a bullet list for each structured finding (matching `ThreadItem::ExitedReviewMode` in the generated schema). Use this notification to render the reviewer output in your client.
### Example: One-off command execution
Run a standalone command (argv vector) in the server’s sandbox without creating a thread or turn:
```json
{"method":"command/exec","id":32,"params":{
"command":["ls","-la"],
"cwd":"/Users/me/project",// optional; defaults to server cwd
"sandboxPolicy":{"type":"workspaceWrite"},// optional; defaults to user config
"timeoutMs":10000// optional; ms timeout; defaults to server timeout
-`sandboxPolicy` accepts the same shape used by `turn/start` (e.g., `dangerFullAccess`, `readOnly`, `workspaceWrite` with flags).
- When omitted, `timeoutMs` falls back to the server default.
## Events
Event notifications are the server-initiated event stream for thread lifecycles, turn lifecycles, and the items within them. After you start or resume a thread, keep reading stdout for `thread/started`, `turn/*`, and `item/*` notifications.
### Turn events
The app-server streams JSON-RPC notifications while a turn is running. Each turn starts with `turn/started` (initial `turn`) and ends with `turn/completed` (final `turn` status). Token usage events stream separately via `thread/tokenUsage/updated`. Clients subscribe to the events they care about, rendering each item incrementally as updates arrive. The per-item lifecycle is always: `item/started` → zero or more item-specific deltas → `item/completed`.
-`turn/started` — `{ turn }` with the turn id, empty `items`, and `status: "inProgress"`.
-`turn/completed` — `{ turn }` where `turn.status` is `completed`, `interrupted`, or `failed`; failures carry `{ error: { message, codexErrorInfo? } }`.
-`turn/diff/updated` — `{ threadId, turnId, diff }` represents the up-to-date snapshot of the turn-level unified diff, emitted after every FileChange item. `diff` is the latest aggregated unified diff across every file change in the turn. UIs can render this to show the full "what changed" view without stitching individual `fileChange` items.
-`turn/plan/updated` — `{ turnId, explanation?, plan }` whenever the agent shares or changes its plan; each `plan` entry is `{ step, status }` with `status` in `pending`, `inProgress`, or `completed`.
Today both notifications carry an empty `items` array even when item events were streamed; rely on `item/*` notifications for the canonical item list until this is fixed.
#### Items
`ThreadItem` is the tagged union carried in turn responses and `item/*` notifications. Currently we support events for the following items:
-`userMessage` — `{id, content}` where `content` is a list of user inputs (`text`, `image`, or `localImage`).
-`agentMessage` — `{id, text}` containing the accumulated agent reply.
-`reasoning` — `{id, summary, content}` where `summary` holds streamed reasoning summaries (applicable for most OpenAI models) and `content` holds raw reasoning blocks (applicable for e.g. open source models).
-`commandExecution` — `{id, command, cwd, status, commandActions, aggregatedOutput?, exitCode?, durationMs?}` for sandboxed commands; `status` is `inProgress`, `completed`, `failed`, or `declined`.
-`fileChange` — `{id, changes, status}` describing proposed edits; `changes` list `{path, kind, diff}` and `status` is `inProgress`, `completed`, `failed`, or `declined`.
-`mcpToolCall` — `{id, server, tool, status, arguments, result?, error?}` describing MCP calls; `status` is `inProgress`, `completed`, or `failed`.
-`webSearch` — `{id, query}` for a web search request issued by the agent.
-`imageView` — `{id, path}` emitted when the agent invokes the image viewer tool.
-`enteredReviewMode` — `{id, review}` sent when the reviewer starts; `review` is a short user-facing label such as `"current changes"` or the requested target description.
-`exitedReviewMode` — `{id, review}` emitted when the reviewer finishes; `review` is the full plain-text review (usually, overall notes plus bullet point findings).
-`compacted` - `{threadId, turnId}` when codex compacts the conversation history. This can happen automatically.
All items emit two shared lifecycle events:
-`item/started` — emits the full `item` when a new unit of work begins so the UI can render it immediately; the `item.id` in this payload matches the `itemId` used by deltas.
-`item/completed` — sends the final `item` once that work finishes (e.g., after a tool call or message completes); treat this as the authoritative state.
There are additional item-specific events:
#### agentMessage
-`item/agentMessage/delta` — appends streamed text for the agent message; concatenate `delta` values for the same `itemId` in order to reconstruct the full reply.
#### reasoning
-`item/reasoning/summaryTextDelta` — streams readable reasoning summaries; `summaryIndex` increments when a new summary section opens.
-`item/reasoning/summaryPartAdded` — marks the boundary between reasoning summary sections for an `itemId`; subsequent `summaryTextDelta` entries share the same `summaryIndex`.
-`item/reasoning/textDelta` — streams raw reasoning text (only applicable for e.g. open source models); use `contentIndex` to group deltas that belong together before showing them in the UI.
#### commandExecution
-`item/commandExecution/outputDelta` — streams stdout/stderr for the command; append deltas in order to render live output alongside `aggregatedOutput` in the final item.
Final `commandExecution` items include parsed `commandActions`, `status`, `exitCode`, and `durationMs` so the UI can summarize what ran and whether it succeeded.
#### fileChange
-`item/fileChange/outputDelta` - contains the tool call response of the underlying `apply_patch` tool call.
### Errors
`error` event is emitted whenever the server hits an error mid-turn (for example, upstream model errors or quota limits). Carries the same `{ error: { message, codexErrorInfo? } }` payload as `turn.status: "failed"` and may precede that terminal notification.
`codexErrorInfo` maps to the `CodexErrorInfo` enum. Common values:
-`ContextWindowExceeded`
-`UsageLimitExceeded`
-`HttpConnectionFailed { httpStatusCode? }`: upstream HTTP failures including 4xx/5xx
-`ResponseStreamConnectionFailed { httpStatusCode? }`: failure to connect to the response SSE stream
-`ResponseStreamDisconnected { httpStatusCode? }`: disconnect of the response SSE stream in the middle of a turn before completion
When an upstream HTTP status is available (for example, from the Responses API or a provider), it is forwarded in `httpStatusCode` on the relevant `codexErrorInfo` variant.
## Approvals
Certain actions (shell commands or modifying files) may require explicit user approval depending on the user's config. When `turn/start` is used, the app-server drives an approval flow by sending a server-initiated JSON-RPC request to the client. The client must respond to tell Codex whether to proceed. UIs should present these requests inline with the active turn so users can review the proposed command or diff before choosing.
- Requests include `threadId` and `turnId`—use them to scope UI state to the active conversation.
- Respond with a single `{ "decision": "accept" | "decline" }` payload (plus optional `acceptSettings` on command executions). The server resumes or declines the work and ends the item with `item/completed`.
### Command execution approvals
Order of messages:
1.`item/started` — shows the pending `commandExecution` item with `command`, `cwd`, and other fields so you can render the proposed action.
2.`item/commandExecution/requestApproval` (request) — carries the same `itemId`, `threadId`, `turnId`, optionally `reason` or `risk`, plus `parsedCmd` for friendly display.
4.`item/completed` — final `commandExecution` item with `status: "completed" | "failed" | "declined"` and execution output. Render this as the authoritative result.
### File change approvals
Order of messages:
1.`item/started` — emits a `fileChange` item with `changes` (diff chunk summaries) and `status: "inProgress"`. Show the proposed edits and paths to the user.
2.`item/fileChange/requestApproval` (request) — includes `itemId`, `threadId`, `turnId`, and an optional `reason`.
4.`item/completed` — returns the same `fileChange` item with `status` updated to `completed`, `failed`, or `declined` after the patch attempt. Rely on this to show success/failure and finalize the diff state in your UI.
UI guidance for IDEs: surface an approval dialog as soon as the request arrives. The turn will proceed after the server receives a response to the approval request. The terminal `item/completed` notification will be sent with the appropriate status.
## Auth endpoints
The JSON-RPC auth/account surface exposes request/response methods plus server-initiated notifications (no `id`). Use these to determine auth state, start or cancel logins, logout, and inspect ChatGPT rate limits.
### API Overview
-`account/read` — fetch current account info; optionally refresh tokens.
-`account/login/start` — begin login (`apiKey` or `chatgpt`).
-`account/login/completed` (notify) — emitted when a login attempt finishes (success or error).
-`account/login/cancel` — cancel a pending ChatGPT login by `loginId`.
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.
