Compare commits

..

39 Commits

Author SHA1 Message Date
pap-openai
c6b2c5c772 Merge branch 'main' into codex-concurrent-simple 2025-08-03 00:42:39 +01:00
pap
aed712286b adding best-of-n 2025-08-03 00:38:25 +01:00
pap
6fcedb46a9 adding automerge option 2025-08-02 23:41:04 +01:00
aibrahim-oai
81bb1c9e26 Fix compact (#1798)
We are not recording the summary in the history.
2025-08-02 12:05:06 -07:00
Jeremy Rose
7e0f506da2 check for updates (#1764)
1. Ping https://api.github.com/repos/openai/codex/releases/latest (at
most once every 20 hrs)
2. Store the result in ~/.codex/version.jsonl
3. If CARGO_PKG_VERSION < latest_version, print a message at boot.

---------

Co-authored-by: easong-openai <easong@openai.com>
2025-08-02 00:31:38 +00:00
pakrym-oai
929ba50adc Update succesfull login page look (#1789) 2025-08-01 23:30:15 +00:00
Michael Bolin
80555d4ff2 feat: make .git read-only within a writable root when using Seatbelt (#1765)
To make `--full-auto` safer, this PR updates the Seatbelt policy so that
a `SandboxPolicy` with a `writable_root` that contains a `.git/`
_directory_ will make `.git/` _read-only_ (though as a follow-up, we
should also consider the case where `.git` is a _file_ with a `gitdir:
/path/to/actual/repo/.git` entry that should also be protected).

The two major changes in this PR:

- Updating `SandboxPolicy::get_writable_roots_with_cwd()` to return a
`Vec<WritableRoot>` instead of a `Vec<PathBuf>` where a `WritableRoot`
can specify a list of read-only subpaths.
- Updating `create_seatbelt_command_args()` to honor the read-only
subpaths in `WritableRoot`.

The logic to update the policy is a fairly straightforward update to
`create_seatbelt_command_args()`, but perhaps the more interesting part
of this PR is the introduction of an integration test in
`tests/sandbox.rs`. Leveraging the new API in #1785, we test
`SandboxPolicy` under various conditions, including ones where `$TMPDIR`
is not readable, which is critical for verifying the new behavior.

To ensure that Codex can run its own tests, e.g.:

```
just codex debug seatbelt --full-auto -- cargo test if_git_repo_is_writable_root_then_dot_git_folder_is_read_only
```

I had to introduce the use of `CODEX_SANDBOX=sandbox`, which is
comparable to how `CODEX_SANDBOX_NETWORK_DISABLED=1` was already being
used.

Adding a comparable change for Landlock will be done in a subsequent PR.
2025-08-01 16:11:24 -07:00
aibrahim-oai
97ab8fb610 MCP: add conversation.create tool [Stack 2/2] (#1783)
Introduce conversation.create handler (handle_create_conversation) and
wire it in MessageProcessor.

Stack:
Top: #1783 
Bottom: #1784

---------

Co-authored-by: Gabriel Peal <gpeal@users.noreply.github.com>
2025-08-01 22:18:36 +00:00
aibrahim-oai
fe62f859a6 Add Error variant to ConversationCreateResult [Stack 1/2] (#1784)
Switch ConversationCreateResult from a struct to a tagged enum (Ok |
Error)

Stack:
Top: #1783 
Bottom: #1784
2025-08-01 15:13:53 -07:00
Michael Bolin
92f3566d78 chore: introduce SandboxPolicy::WorkspaceWrite::include_default_writable_roots (#1785)
Without this change, it is challenging to create integration tests to
verify that the folders not included in `writable_roots` in
`SandboxPolicy::WorkspaceWrite` are read-only because, by default,
`get_writable_roots_with_cwd()` includes `TMPDIR`, which is where most
integrationt
tests do their work.

This introduces a `use_exact_writable_roots` option to disable the
default
includes returned by `get_writable_roots_with_cwd()`.




---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/1785).
* #1765
* __->__ #1785
2025-08-01 14:15:55 -07:00
aibrahim-oai
f20de21cb6 collabse stdout and stderr delta events into one (#1787) 2025-08-01 14:00:19 -07:00
aibrahim-oai
bc7beddaa2 feat: stream exec stdout events (#1786)
## Summary
- stream command stdout as `ExecCommandStdout` events
- forward streamed stdout to clients and ignore in human output
processor
- adjust call sites for new streaming API
2025-08-01 13:04:34 -07:00
Jeremy Rose
8360c6a3ec fix insert_history modifier handling (#1774)
This fixes a bug in insert_history_lines where writing
`Line::From(vec!["A".bold(), "B".into()])` would write "B" as bold,
because "B" didn't explicitly subtract bold.
2025-08-01 10:37:43 -07:00
aibrahim-oai
f918198bbb Introduce a new function to just send user message [Stack 3/3] (#1686)
- MCP server: add send-user-message tool to send user input to a running
Codex session
- Added an integration tests for the happy and sad paths

Changes:
•	Add tool definition and schema.
•	Expose tool in capabilities.
•	Route and handle tool requests with validation.
•	Tests for success, bad UUID, and missing session.


follow‑ups
• Listen path not implemented yet; the tool is present but marked “don’t
use yet” in code comments.
• Session run flag reset: clear running_session_id_set appropriately
after turn completion/errors.

This is the third PR in a stack.
Stack:
Final: #1686
Intermediate: #1751
First: #1750
2025-08-01 17:04:12 +00:00
pakrym-oai
88ea215c80 Add a custom originator setting (#1781) 2025-08-01 09:55:23 -07:00
aibrahim-oai
b67c485d84 ci fix (#1782) 2025-08-01 09:17:13 -07:00
aibrahim-oai
e2c994e32a Add /compact (#1527)
- Add operation to summarize the context so far.
- The operation runs a compact task that summarizes the context.
- The operation clear the previous context to free the context window
- The operation didn't use `run_task` to avoid corrupting the session
- Add /compact in the tui



https://github.com/user-attachments/assets/e06c24e5-dcfb-4806-934a-564d425a919c
2025-07-31 21:34:32 -07:00
aibrahim-oai
ad0295b893 MCP server: route structured tool-call requests and expose mcp_protocol [Stack 2/3] (#1751)
- Expose mcp_protocol from mcp-server for reuse in tests and callers.
- In MessageProcessor, detect structured ToolCallRequestParams in
tools/call and forward to a new handler.
- Add handle_new_tool_calls scaffold (returns error for now).
- Test helper: add send_send_user_message_tool_call to McpProcess to
send ConversationSendMessage requests;

This is the second PR in a stack.
Stack:
Final: #1686
Intermediate: #1751
First: #1750
2025-08-01 02:46:04 +00:00
aibrahim-oai
d3aa5f46b7 MCP Protocol: Align tool-call response with CallToolResult [Stack 1/3] (#1750)
# Summary
- Align MCP server responses with mcp_types by emitting [CallToolResult,
RequestId] instead of an object.
Update send-message result to a tagged enum: Ok or Error { message }.

# Why
Protocol compliance with current MCP schema.

# Tests
- Updated assertions in mcp_protocol.rs for create/stream/send/list and
error cases.

This is the first PR in a stack.
Stack:
Final: #1686
Intermediate: #1751
First: #1750
2025-08-01 02:30:03 +00:00
easong-openai
575590e4c2 Detect kitty terminals (#1748)
We want to detect kitty terminals so we can preferentially upgrade their UX without degrading older terminals.
2025-08-01 00:30:44 +00:00
Jeremy Rose
4aca3e46c8 insert history lines with redraw (#1769)
This delays the call to insert_history_lines until a redraw is
happening. Crucially, the new lines are inserted _after the viewport is
resized_. This results in fewer stray blank lines below the viewport
when modals (e.g. user approval) are closed.
2025-07-31 17:15:26 -07:00
Jeremy Rose
d787434aa8 fix: always send KeyEvent, we now check kind in the handler (#1772)
https://github.com/openai/codex/pull/1754 and #1771 fixed the same thing
in colliding ways.
2025-08-01 00:13:36 +00:00
Jeremy Rose
ea69a1d72f lighter approval modal (#1768)
The yellow hazard stripes were too scary :)

This also has the added benefit of not rendering anything at the full
width of the terminal, so resizing is a little easier to handle.

<img width="860" height="390" alt="Screenshot 2025-07-31 at 4 03 29 PM"
src="https://github.com/user-attachments/assets/18476e1a-065d-4da9-92fe-e94978ab0fce"
/>

<img width="860" height="390" alt="Screenshot 2025-07-31 at 4 05 03 PM"
src="https://github.com/user-attachments/assets/337db0da-de40-48c6-ae71-0e40f24b87e7"
/>
2025-07-31 17:10:52 -07:00
Jeremy Rose
610addbc2e do not dispatch key releases (#1771)
when we enabled KKP in https://github.com/openai/codex/pull/1743, we
started receiving keyup events, but didn't expect them anywhere in our
code. for now, just don't dispatch them at all.
2025-07-31 17:00:48 -07:00
pakrym-oai
0935e6a875 Send account id when available (#1767)
For users with multiple accounts we need to specify the account to use.
2025-07-31 15:40:19 -07:00
easong-openai
6ce0a5875b Initial planning tool (#1753)
We need to optimize the prompt, but this causes the model to use the new
planning_tool.

<img width="765" height="110" alt="image"
src="https://github.com/user-attachments/assets/45633f7f-3c85-4e60-8b80-902f1b3b508d"
/>
2025-07-31 20:45:52 +00:00
Michael Bolin
5a0ad5ab8f chore: refactor exec.rs: create separate seatbelt.rs and spawn.rs files (#1762)
At 550 lines, `exec.rs` was a bit large. In particular, I found it hard
to locate the Seatbelt-related code quickly without a file with
`seatbelt` in the name, so this refactors things so:

- `spawn_command_under_seatbelt()` and dependent code moves to a new
`seatbelt.rs` file
- `spawn_child_async()` and dependent code moves to a new `spawn.rs`
file
2025-07-31 13:11:47 -07:00
easong-openai
9aa11269a5 Fix double-scrolling in approval model (#1754)
Previously, pressing up or down arrow in the new approval modal would be
the equivalent of two up or down presses.
2025-07-31 19:41:32 +00:00
Michael Bolin
06c786b2da fix: ensure PatchApplyBeginEvent and PatchApplyEndEvent are dispatched reliably (#1760)
This is a follow-up to https://github.com/openai/codex/pull/1705, as
that PR inadvertently lost the logic where `PatchApplyBeginEvent` and
`PatchApplyEndEvent` events were sent when patches were auto-approved.

Though as part of this fix, I believe this also makes an important
safety fix to `assess_patch_safety()`, as there was a case that returned
`SandboxType::None`, which arguably is the thing we were trying to avoid
in #1705.

On a high level, we want there to be only one codepath where
`apply_patch` happens, which should be unified with the patch to run
`exec`, in general, so that sandboxing is applied consistently for both
cases.

Prior to this change, `apply_patch()` in `core` would either:

* exit early, delegating to `exec()` to shell out to `apply_patch` using
the appropriate sandbox
* proceed to run the logic for `apply_patch` in memory


549846b29a/codex-rs/core/src/apply_patch.rs (L61-L63)

In this implementation, only the latter would dispatch
`PatchApplyBeginEvent` and `PatchApplyEndEvent`, though the former would
dispatch `ExecCommandBeginEvent` and `ExecCommandEndEvent` for the
`apply_patch` call (or, more specifically, the `codex
--codex-run-as-apply-patch PATCH` call).

To unify things in this PR, we:

* Eliminate the back half of the `apply_patch()` function, and instead
have it also return with `DelegateToExec`, though we add an extra field
to the return value, `user_explicitly_approved_this_action`.
* In `codex.rs` where we process `DelegateToExec`, we use
`SandboxType::None` when `user_explicitly_approved_this_action` is
`true`. This means **we no longer run the apply_patch logic in memory**,
as we always `exec()`. (Note this is what allowed us to delete so much
code in `apply_patch.rs`.)
* In `codex.rs`, we further update `notify_exec_command_begin()` and
`notify_exec_command_end()` to take additional fields to determine what
type of notification to send: `ExecCommand` or `PatchApply`.

Admittedly, this PR also drops some of the functionality about giving
the user the opportunity to expand the set of writable roots as part of
approving the `apply_patch` command. I'm not sure how much that was
used, and we should probably rethink how that works as we are currently
tidying up the protocol to the TUI, in general.
2025-07-31 11:13:57 -07:00
pakrym-oai
549846b29a Add codex login --api-key (#1759)
Allow setting the API key via `codex login --api-key`
2025-07-31 17:48:49 +00:00
Jeremy Rose
96654a5d52 clamp render area to terminal size (#1758)
this fixes a couple of panics that would happen when trying to render
something larger than the terminal, or insert history lines when the top
of the viewport is at y=0.
2025-07-31 09:59:36 -07:00
easong-openai
861ba86403 Show error message after panic (#1752)
Previously we were swallowing errors and silently exiting, which isn't
great for helping users help us.
2025-07-31 09:19:08 -07:00
Jeremy Rose
be0cd34300 fix git tests (#1747)
the git tests were failing on my local machine due to gpg signing config
in my ~/.gitconfig. tests should not be affected by ~/.gitconfig, so
configure them to ignore it.
2025-07-31 09:17:59 -07:00
Jeremy Rose
d86270696e streamline ui (#1733)
Simplify and improve many UI elements.
* Remove all-around borders in most places. These interact badly with
terminal resizing and look heavy. Prefer left-side-only borders.
* Make the viewport adjust to the size of its contents.
* <kbd>/</kbd> and <kbd>@</kbd> autocomplete boxes appear below the
prompt, instead of above it.
* Restyle the keyboard shortcut hints & move them to the left.
* Restyle the approval dialog.
* Use synchronized rendering to avoid flashing during rerenders.


https://github.com/user-attachments/assets/96f044af-283b-411c-b7fc-5e6b8a433c20

<img width="1117" height="858" alt="Screenshot 2025-07-30 at 5 29 20 PM"
src="https://github.com/user-attachments/assets/0cc0af77-8396-429b-b6ee-9feaaccdbee7"
/>
2025-07-31 00:43:21 -07:00
pap-openai
defeafb279 add keyboard enhancements to support shift_return (#1743)
For terminal that supports [keyboard
enhancements](https://docs.rs/libcrossterm/latest/crossterm/enum.KeyboardEnhancementFlags.html),
adds the enhancements (enabling [kitty keyboard
protocol](https://sw.kovidgoyal.net/kitty/keyboard-protocol/)) to
support shift+enter listener.

Those users (users with terminals listed on
[KPP](https://sw.kovidgoyal.net/kitty/keyboard-protocol/)) should be
able to press shift+return for new line

---------

Co-authored-by: easong-openai <easong@openai.com>
2025-07-31 03:23:56 +00:00
pakrym-oai
51b6bdefbe Auto format toml (#1745)
Add recommended extension and configure it to auto format prompt.
2025-07-30 18:37:00 -07:00
Michael Bolin
35010812c7 chore: add support for a new label, codex-rust-review (#1744)
The goal of this change is to try an experiment where we try to get AI
to take on more of the code review load. The idea is that once you
believe your PR is ready for review, please add the `codex-rust-review`
label (as opposed to the `codex-review` label).

Admittedly the corresponding prompt currently represents my personal
biases in terms of code review, but we should massage it over time to
represent the team's preferences.
2025-07-30 17:49:07 -07:00
Jeremy Rose
f2134f6633 resizable viewport (#1732)
Proof of concept for a resizable viewport.

The general approach here is to duplicate the `Terminal` struct from
ratatui, but with our own logic. This is a "light fork" in that we are
still using all the base ratatui functions (`Buffer`, `Widget` and so
on), but we're doing our own bookkeeping at the top level to determine
where to draw everything.

This approach could use improvement—e.g, when the window is resized to a
smaller size, if the UI wraps, we don't correctly clear out the
artifacts from wrapping. This is possible with a little work (i.e.
tracking what parts of our UI would have been wrapped), but this
behavior is at least at par with the existing behavior.


https://github.com/user-attachments/assets/4eb17689-09fd-4daa-8315-c7ebc654986d


cc @joshka who might have Thoughts™
2025-07-31 00:06:55 +00:00
Michael Bolin
221ebfcccc fix: run apply_patch calls through the sandbox (#1705)
Building on the work of https://github.com/openai/codex/pull/1702, this
changes how a shell call to `apply_patch` is handled.

Previously, a shell call to `apply_patch` was always handled in-process,
never leveraging a sandbox. To determine whether the `apply_patch`
operation could be auto-approved, the
`is_write_patch_constrained_to_writable_paths()` function would check if
all the paths listed in the paths were writable. If so, the agent would
apply the changes listed in the patch.

Unfortunately, this approach afforded a loophole: symlinks!

* For a soft link, we could fix this issue by tracing the link and
checking whether the target is in the set of writable paths, however...
* ...For a hard link, things are not as simple. We can run `stat FILE`
to see if the number of links is greater than 1, but then we would have
to do something potentially expensive like `find . -inum <inode_number>`
to find the other paths for `FILE`. Further, even if this worked, this
approach runs the risk of a
[TOCTOU](https://en.wikipedia.org/wiki/Time-of-check_to_time-of-use)
race condition, so it is not robust.

The solution, implemented in this PR, is to take the virtual execution
of the `apply_patch` CLI into an _actual_ execution using `codex
--codex-run-as-apply-patch PATCH`, which we can run under the sandbox
the user specified, just like any other `shell` call.

This, of course, assumes that the sandbox prevents writing through
symlinks as a mechanism to write to folders that are not in the writable
set configured by the sandbox. I verified this by testing the following
on both Mac and Linux:

```shell
#!/usr/bin/env bash
set -euo pipefail

# Can running a command in SANDBOX_DIR write a file in EXPLOIT_DIR?

# Codex is run in SANDBOX_DIR, so writes should be constrianed to this directory.
SANDBOX_DIR=$(mktemp -d -p "$HOME" sandboxtesttemp.XXXXXX)
# EXPLOIT_DIR is outside of SANDBOX_DIR, so let's see if we can write to it.
EXPLOIT_DIR=$(mktemp -d -p "$HOME" sandboxtesttemp.XXXXXX)

echo "SANDBOX_DIR: $SANDBOX_DIR"
echo "EXPLOIT_DIR: $EXPLOIT_DIR"

cleanup() {
  # Only remove if it looks sane and still exists
  [[ -n "${SANDBOX_DIR:-}" && -d "$SANDBOX_DIR" ]] && rm -rf -- "$SANDBOX_DIR"
  [[ -n "${EXPLOIT_DIR:-}" && -d "$EXPLOIT_DIR" ]] && rm -rf -- "$EXPLOIT_DIR"
}

trap cleanup EXIT

echo "I am the original content" > "${EXPLOIT_DIR}/original.txt"

# Drop the -s to test hard links.
ln -s "${EXPLOIT_DIR}/original.txt" "${SANDBOX_DIR}/link-to-original.txt"

cat "${SANDBOX_DIR}/link-to-original.txt"

if [[ "$(uname)" == "Linux" ]]; then
    SANDBOX_SUBCOMMAND=landlock
else
    SANDBOX_SUBCOMMAND=seatbelt
fi

# Attempt the exploit
cd "${SANDBOX_DIR}"

codex debug "${SANDBOX_SUBCOMMAND}" bash -lc "echo pwned > ./link-to-original.txt" || true

cat "${EXPLOIT_DIR}/original.txt"
```

Admittedly, this change merits a proper integration test, but I think I
will have to do that in a follow-up PR.
2025-07-30 16:45:08 -07:00
107 changed files with 5300 additions and 1437 deletions

View File

@@ -0,0 +1,23 @@
Review this PR and respond with a very concise final message, formatted in Markdown.
There should be a summary of the changes (1-2 sentences) and a few bullet points if necessary.
Then provide the **review** (1-2 sentences plus bullet points, friendly tone).
Things to look out for when doing the review:
- **Make sure the pull request body explains the motivation behind the change.** If the author has failed to do this, call it out, and if you think you can deduce the motivation behind the change, propose copy.
- Ideally, the PR body also contains a small summary of the change. For small changes, the PR title may be sufficient.
- Each PR should ideally do one conceptual thing. For example, if a PR does a refactoring as well as introducing a new feature, push back and suggest the refactoring be done in a separate PR. This makes things easier for the reviewer, as refactoring changes can often be far-reaching, yet quick to review.
- If the nature of the change seems to have a visual component (which is often the case for changes to `codex-rs/tui`), recommend including a screenshot or video to demonstrate the change, if appropriate.
- Rust files should generally be organized such that the public parts of the API appear near the top of the file and helper functions go below. This is analagous to the "inverted pyramid" structure that is favored in journalism.
- Encourage the use of small enums or the newtype pattern in Rust if it helps readability without adding significant cognitive load or lines of code.
- Be wary of large files and offer suggestions for how to break things into more reasonably-sized files.
- When modifying a `Cargo.toml` file, make sure that dependency lists stay alphabetically sorted. Also consider whether a new dependency is added to the appropriate place (e.g., `[dependencies]` versus `[dev-dependencies]`)
- If you see opportunities for the changes in a diff to use more idiomatic Rust, please make specific recommendations. For example, favor the use of expressions over `return`.
- When introducing new code, be on the lookout for code that duplicates existing code. When found, propose a way to refactor the existing code such that it should be reused.
- Each create in the Cargo workspace in `codex-rs` has a specific purpose: make a note if you believe new code is not introduced in the correct crate.
- When possible, try to keep the `core` crate as small as possible. Non-core but shared logic is often a good candidate for `codex-rs/common`.
- References to existing GitHub issues and PRs are encouraged, where appropriate, though you likely do not have network access, so may not be able to help here.
{CODEX_ACTION_GITHUB_EVENT_PATH} contains the JSON that triggered this GitHub workflow. It contains the `base` and `head` refs that define this PR. Both refs are available locally.

View File

@@ -20,7 +20,7 @@ jobs:
(github.event_name == 'issues' && (
(github.event.action == 'labeled' && (github.event.label.name == 'codex-attempt' || github.event.label.name == 'codex-triage'))
)) ||
(github.event_name == 'pull_request' && github.event.action == 'labeled' && github.event.label.name == 'codex-review')
(github.event_name == 'pull_request' && github.event.action == 'labeled' && (github.event.label.name == 'codex-review' || github.event.label.name == 'codex-rust-review'))
runs-on: ubuntu-latest
permissions:
contents: write # can push or create branches

5
.vscode/extensions.json vendored Normal file
View File

@@ -0,0 +1,5 @@
{
"recommendations": [
"tamasfe.even-better-toml",
]
}

View File

@@ -6,5 +6,11 @@
"[rust]": {
"editor.defaultFormatter": "rust-lang.rust-analyzer",
"editor.formatOnSave": true,
}
},
"[toml]": {
"editor.defaultFormatter": "tamasfe.even-better-toml",
"editor.formatOnSave": true,
},
"evenBetterToml.formatter.reorderArrays": true,
"evenBetterToml.formatter.reorderKeys": true,
}

View File

@@ -2,7 +2,9 @@
In the codex-rs folder where the rust code lives:
- Never add or modify any code related to `CODEX_SANDBOX_NETWORK_DISABLED_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.
- 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.
Before creating a pull request with changes to `codex-rs`, run `just fmt` (in `codex-rs` directory) to format the code and `just fix` (in `codex-rs` directory) to fix any linter issues in the code, ensure the test suite passes by running `cargo test --all-features` in the `codex-rs` directory.

4
NOTICE
View File

@@ -1,2 +1,6 @@
OpenAI Codex
Copyright 2025 OpenAI
This project includes code derived from [Ratatui](https://github.com/ratatui/ratatui), licensed under the MIT license.
Copyright (c) 2016-2022 Florian Dehau
Copyright (c) 2023-2025 The Ratatui Developers

21
SUMMARY.md Normal file
View File

@@ -0,0 +1,21 @@
You are a summarization assistant. A conversation follows between a user and a coding-focused AI (Codex). Your task is to generate a clear summary capturing:
• High-level objective or problem being solved
• Key instructions or design decisions given by the user
• Main code actions or behaviors from the AI
• Important variables, functions, modules, or outputs discussed
• Any unresolved questions or next steps
Produce the summary in a structured format like:
**Objective:**
**User instructions:** … (bulleted)
**AI actions / code behavior:** … (bulleted)
**Important entities:** … (e.g. function names, variables, files)
**Open issues / next steps:** … (if any)
**Summary (concise):** (one or two sentences)

View File

@@ -83,6 +83,7 @@ if (wantsNative && process.platform !== 'win32') {
const child = spawn(binaryPath, process.argv.slice(2), {
stdio: "inherit",
env: { ...process.env, CODEX_MANAGED_BY_NPM: "1" },
});
child.on("error", (err) => {

16
codex-rs/Cargo.lock generated
View File

@@ -695,6 +695,7 @@ dependencies = [
"reqwest",
"seccompiler",
"serde",
"serde_bytes",
"serde_json",
"sha1",
"shlex",
@@ -793,6 +794,7 @@ dependencies = [
"reqwest",
"serde",
"serde_json",
"tempfile",
"tokio",
]
@@ -841,6 +843,7 @@ version = "0.0.0"
dependencies = [
"anyhow",
"base64 0.22.1",
"chrono",
"clap",
"codex-ansi-escape",
"codex-arg0",
@@ -859,6 +862,8 @@ dependencies = [
"ratatui",
"ratatui-image",
"regex-lite",
"reqwest",
"serde",
"serde_json",
"shlex",
"strum 0.27.2",
@@ -2642,6 +2647,7 @@ version = "0.0.0"
dependencies = [
"anyhow",
"assert_cmd",
"codex-core",
"codex-mcp-server",
"mcp-types",
"pretty_assertions",
@@ -2649,6 +2655,7 @@ dependencies = [
"shlex",
"tempfile",
"tokio",
"uuid",
"wiremock",
]
@@ -3948,6 +3955,15 @@ dependencies = [
"serde_derive",
]
[[package]]
name = "serde_bytes"
version = "0.11.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8437fd221bde2d4ca316d61b90e337e9e702b3820b87d63caa9ba6c02bd06d96"
dependencies = [
"serde",
]
[[package]]
name = "serde_derive"
version = "1.0.219"

View File

@@ -1,5 +1,4 @@
[workspace]
resolver = "2"
members = [
"ansi-escape",
"apply-patch",
@@ -17,6 +16,7 @@ members = [
"mcp-types",
"tui",
]
resolver = "2"
[workspace.package]
version = "0.0.0"
@@ -45,4 +45,3 @@ codegen-units = 1
[patch.crates-io]
# ratatui = { path = "../../ratatui" }
ratatui = { git = "https://github.com/nornagon/ratatui", branch = "nornagon-v0.29.0-patch" }

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-ansi-escape"
version = { workspace = true }
edition = "2024"
[lib]
name = "codex_ansi_escape"
@@ -10,7 +10,7 @@ path = "src/lib.rs"
[dependencies]
ansi-to-tui = "7.0.0"
ratatui = { version = "0.29.0", features = [
"unstable-widget-ref",
"unstable-rendered-line-info",
"unstable-widget-ref",
] }
tracing = { version = "0.1.41", features = ["log"] }

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-apply-patch"
version = { workspace = true }
edition = "2024"
[lib]
name = "codex_apply_patch"

View File

@@ -58,16 +58,24 @@ impl PartialEq for IoError {
#[derive(Debug, PartialEq)]
pub enum MaybeApplyPatch {
Body(Vec<Hunk>),
Body(ApplyPatchArgs),
ShellParseError(ExtractHeredocError),
PatchParseError(ParseError),
NotApplyPatch,
}
/// Both the raw PATCH argument to `apply_patch` as well as the PATCH argument
/// parsed into hunks.
#[derive(Debug, PartialEq)]
pub struct ApplyPatchArgs {
pub patch: String,
pub hunks: Vec<Hunk>,
}
pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
match argv {
[cmd, body] if cmd == "apply_patch" => match parse_patch(body) {
Ok(hunks) => MaybeApplyPatch::Body(hunks),
Ok(source) => MaybeApplyPatch::Body(source),
Err(e) => MaybeApplyPatch::PatchParseError(e),
},
[bash, flag, script]
@@ -77,7 +85,7 @@ pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
{
match extract_heredoc_body_from_apply_patch_command(script) {
Ok(body) => match parse_patch(&body) {
Ok(hunks) => MaybeApplyPatch::Body(hunks),
Ok(source) => MaybeApplyPatch::Body(source),
Err(e) => MaybeApplyPatch::PatchParseError(e),
},
Err(e) => MaybeApplyPatch::ShellParseError(e),
@@ -116,11 +124,19 @@ pub enum MaybeApplyPatchVerified {
NotApplyPatch,
}
#[derive(Debug, PartialEq)]
/// ApplyPatchAction is the result of parsing an `apply_patch` command. By
/// construction, all paths should be absolute paths.
#[derive(Debug, PartialEq)]
pub struct ApplyPatchAction {
changes: HashMap<PathBuf, ApplyPatchFileChange>,
/// The raw patch argument that can be used with `apply_patch` as an exec
/// call. i.e., if the original arg was parsed in "lenient" mode with a
/// heredoc, this should be the value without the heredoc wrapper.
pub patch: String,
/// The working directory that was used to resolve relative paths in the patch.
pub cwd: PathBuf,
}
impl ApplyPatchAction {
@@ -140,8 +156,28 @@ impl ApplyPatchAction {
panic!("path must be absolute");
}
#[allow(clippy::expect_used)]
let filename = path
.file_name()
.expect("path should not be empty")
.to_string_lossy();
let patch = format!(
r#"*** Begin Patch
*** Update File: {filename}
@@
+ {content}
*** End Patch"#,
);
let changes = HashMap::from([(path.to_path_buf(), ApplyPatchFileChange::Add { content })]);
Self { changes }
#[allow(clippy::expect_used)]
Self {
changes,
cwd: path
.parent()
.expect("path should have parent")
.to_path_buf(),
patch,
}
}
}
@@ -149,7 +185,7 @@ impl ApplyPatchAction {
/// patch.
pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApplyPatchVerified {
match maybe_parse_apply_patch(argv) {
MaybeApplyPatch::Body(hunks) => {
MaybeApplyPatch::Body(ApplyPatchArgs { patch, hunks }) => {
let mut changes = HashMap::new();
for hunk in hunks {
let path = hunk.resolve_path(cwd);
@@ -183,7 +219,11 @@ pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApp
}
}
}
MaybeApplyPatchVerified::Body(ApplyPatchAction { changes })
MaybeApplyPatchVerified::Body(ApplyPatchAction {
changes,
patch,
cwd: cwd.to_path_buf(),
})
}
MaybeApplyPatch::ShellParseError(e) => MaybeApplyPatchVerified::ShellParseError(e),
MaybeApplyPatch::PatchParseError(e) => MaybeApplyPatchVerified::CorrectnessError(e.into()),
@@ -264,7 +304,7 @@ pub fn apply_patch(
stderr: &mut impl std::io::Write,
) -> Result<(), ApplyPatchError> {
let hunks = match parse_patch(patch) {
Ok(hunks) => hunks,
Ok(source) => source.hunks,
Err(e) => {
match &e {
InvalidPatchError(message) => {
@@ -652,7 +692,7 @@ mod tests {
]);
match maybe_parse_apply_patch(&args) {
MaybeApplyPatch::Body(hunks) => {
MaybeApplyPatch::Body(ApplyPatchArgs { hunks, patch: _ }) => {
assert_eq!(
hunks,
vec![Hunk::AddFile {
@@ -679,7 +719,7 @@ PATCH"#,
]);
match maybe_parse_apply_patch(&args) {
MaybeApplyPatch::Body(hunks) => {
MaybeApplyPatch::Body(ApplyPatchArgs { hunks, patch: _ }) => {
assert_eq!(
hunks,
vec![Hunk::AddFile {
@@ -954,7 +994,7 @@ PATCH"#,
));
let patch = parse_patch(&patch).unwrap();
let update_file_chunks = match patch.as_slice() {
let update_file_chunks = match patch.hunks.as_slice() {
[Hunk::UpdateFile { chunks, .. }] => chunks,
_ => panic!("Expected a single UpdateFile hunk"),
};
@@ -992,7 +1032,7 @@ PATCH"#,
));
let patch = parse_patch(&patch).unwrap();
let chunks = match patch.as_slice() {
let chunks = match patch.hunks.as_slice() {
[Hunk::UpdateFile { chunks, .. }] => chunks,
_ => panic!("Expected a single UpdateFile hunk"),
};
@@ -1029,7 +1069,7 @@ PATCH"#,
));
let patch = parse_patch(&patch).unwrap();
let chunks = match patch.as_slice() {
let chunks = match patch.hunks.as_slice() {
[Hunk::UpdateFile { chunks, .. }] => chunks,
_ => panic!("Expected a single UpdateFile hunk"),
};
@@ -1064,7 +1104,7 @@ PATCH"#,
));
let patch = parse_patch(&patch).unwrap();
let chunks = match patch.as_slice() {
let chunks = match patch.hunks.as_slice() {
[Hunk::UpdateFile { chunks, .. }] => chunks,
_ => panic!("Expected a single UpdateFile hunk"),
};
@@ -1110,7 +1150,7 @@ PATCH"#,
// Extract chunks then build the unified diff.
let parsed = parse_patch(&patch).unwrap();
let chunks = match parsed.as_slice() {
let chunks = match parsed.hunks.as_slice() {
[Hunk::UpdateFile { chunks, .. }] => chunks,
_ => panic!("Expected a single UpdateFile hunk"),
};
@@ -1193,6 +1233,8 @@ g
new_content: "updated session directory content\n".to_string(),
},
)]),
patch: argv[1].clone(),
cwd: session_dir.path().to_path_buf(),
})
);
}

View File

@@ -22,6 +22,7 @@
//!
//! The parser below is a little more lenient than the explicit spec and allows for
//! leading/trailing whitespace around patch markers.
use crate::ApplyPatchArgs;
use std::path::Path;
use std::path::PathBuf;
@@ -102,7 +103,7 @@ pub struct UpdateFileChunk {
pub is_end_of_file: bool,
}
pub fn parse_patch(patch: &str) -> Result<Vec<Hunk>, ParseError> {
pub fn parse_patch(patch: &str) -> Result<ApplyPatchArgs, ParseError> {
let mode = if PARSE_IN_STRICT_MODE {
ParseMode::Strict
} else {
@@ -150,7 +151,7 @@ enum ParseMode {
Lenient,
}
fn parse_patch_text(patch: &str, mode: ParseMode) -> Result<Vec<Hunk>, ParseError> {
fn parse_patch_text(patch: &str, mode: ParseMode) -> Result<ApplyPatchArgs, ParseError> {
let lines: Vec<&str> = patch.trim().lines().collect();
let lines: &[&str] = match check_patch_boundaries_strict(&lines) {
Ok(()) => &lines,
@@ -173,7 +174,8 @@ fn parse_patch_text(patch: &str, mode: ParseMode) -> Result<Vec<Hunk>, ParseErro
line_number += hunk_lines;
remaining_lines = &remaining_lines[hunk_lines..]
}
Ok(hunks)
let patch = lines.join("\n");
Ok(ApplyPatchArgs { hunks, patch })
}
/// Checks the start and end lines of the patch text for `apply_patch`,
@@ -425,6 +427,7 @@ fn parse_update_file_chunk(
}
#[test]
#[allow(clippy::unwrap_used)]
fn test_parse_patch() {
assert_eq!(
parse_patch_text("bad", ParseMode::Strict),
@@ -455,8 +458,10 @@ fn test_parse_patch() {
"*** Begin Patch\n\
*** End Patch",
ParseMode::Strict
),
Ok(Vec::new())
)
.unwrap()
.hunks,
Vec::new()
);
assert_eq!(
parse_patch_text(
@@ -472,8 +477,10 @@ fn test_parse_patch() {
+ return 123\n\
*** End Patch",
ParseMode::Strict
),
Ok(vec![
)
.unwrap()
.hunks,
vec![
AddFile {
path: PathBuf::from("path/add.py"),
contents: "abc\ndef\n".to_string()
@@ -491,7 +498,7 @@ fn test_parse_patch() {
is_end_of_file: false
}]
}
])
]
);
// Update hunk followed by another hunk (Add File).
assert_eq!(
@@ -504,8 +511,10 @@ fn test_parse_patch() {
+content\n\
*** End Patch",
ParseMode::Strict
),
Ok(vec![
)
.unwrap()
.hunks,
vec![
UpdateFile {
path: PathBuf::from("file.py"),
move_path: None,
@@ -520,7 +529,7 @@ fn test_parse_patch() {
path: PathBuf::from("other.py"),
contents: "content\n".to_string()
}
])
]
);
// Update hunk without an explicit @@ header for the first chunk should parse.
@@ -533,8 +542,10 @@ fn test_parse_patch() {
+bar
*** End Patch"#,
ParseMode::Strict
),
Ok(vec![UpdateFile {
)
.unwrap()
.hunks,
vec![UpdateFile {
path: PathBuf::from("file2.py"),
move_path: None,
chunks: vec![UpdateFileChunk {
@@ -543,7 +554,7 @@ fn test_parse_patch() {
new_lines: vec!["import foo".to_string(), "bar".to_string()],
is_end_of_file: false,
}],
}])
}]
);
}
@@ -574,7 +585,10 @@ fn test_parse_patch_lenient() {
);
assert_eq!(
parse_patch_text(&patch_text_in_heredoc, ParseMode::Lenient),
Ok(expected_patch.clone())
Ok(ApplyPatchArgs {
hunks: expected_patch.clone(),
patch: patch_text.to_string()
})
);
let patch_text_in_single_quoted_heredoc = format!("<<'EOF'\n{patch_text}\nEOF\n");
@@ -584,7 +598,10 @@ fn test_parse_patch_lenient() {
);
assert_eq!(
parse_patch_text(&patch_text_in_single_quoted_heredoc, ParseMode::Lenient),
Ok(expected_patch.clone())
Ok(ApplyPatchArgs {
hunks: expected_patch.clone(),
patch: patch_text.to_string()
})
);
let patch_text_in_double_quoted_heredoc = format!("<<\"EOF\"\n{patch_text}\nEOF\n");
@@ -594,7 +611,10 @@ fn test_parse_patch_lenient() {
);
assert_eq!(
parse_patch_text(&patch_text_in_double_quoted_heredoc, ParseMode::Lenient),
Ok(expected_patch.clone())
Ok(ApplyPatchArgs {
hunks: expected_patch.clone(),
patch: patch_text.to_string()
})
);
let patch_text_in_mismatched_quotes_heredoc = format!("<<\"EOF'\n{patch_text}\nEOF\n");

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-arg0"
version = { workspace = true }
edition = "2024"
[lib]
name = "codex_arg0"

View File

@@ -2,6 +2,8 @@ use std::future::Future;
use std::path::Path;
use std::path::PathBuf;
use codex_core::CODEX_APPLY_PATCH_ARG1;
/// While we want to deploy the Codex CLI as a single executable for simplicity,
/// we also want to expose some of its functionality as distinct CLIs, so we use
/// the "arg0 trick" to determine which CLI to dispatch. This effectively allows
@@ -43,7 +45,7 @@ where
}
let argv1 = args.next().unwrap_or_default();
if argv1 == "--codex-run-as-apply-patch" {
if argv1 == CODEX_APPLY_PATCH_ARG1 {
let patch_arg = args.next().and_then(|s| s.to_str().map(|s| s.to_owned()));
let exit_code = match patch_arg {
Some(patch_arg) => {
@@ -55,7 +57,7 @@ where
}
}
None => {
eprintln!("Error: --codex-run-as-apply-patch requires a UTF-8 PATCH argument.");
eprintln!("Error: {CODEX_APPLY_PATCH_ARG1} requires a UTF-8 PATCH argument.");
1
}
};

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-chatgpt"
version = { workspace = true }
edition = "2024"
[lints]
workspace = true
@@ -9,12 +9,12 @@ workspace = true
[dependencies]
anyhow = "1"
clap = { version = "4", features = ["derive"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
codex-common = { path = "../common", features = ["cli"] }
codex-core = { path = "../core" }
codex-login = { path = "../login" }
reqwest = { version = "0.12", features = ["json", "stream"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
tokio = { version = "1", features = ["full"] }
[dev-dependencies]

View File

@@ -18,7 +18,7 @@ pub fn set_chatgpt_token_data(value: TokenData) {
/// Initialize the ChatGPT token from auth.json file
pub async fn init_chatgpt_token_from_auth(codex_home: &Path) -> std::io::Result<()> {
let auth = codex_login::load_auth(codex_home)?;
let auth = codex_login::load_auth(codex_home, true)?;
if let Some(auth) = auth {
let token_data = auth.get_token_data().await?;
set_chatgpt_token_data(token_data);

View File

@@ -10,8 +10,13 @@ use tokio::process::Command;
async fn create_temp_git_repo() -> anyhow::Result<TempDir> {
let temp_dir = TempDir::new()?;
let repo_path = temp_dir.path();
let envs = vec![
("GIT_CONFIG_GLOBAL", "/dev/null"),
("GIT_CONFIG_NOSYSTEM", "1"),
];
let output = Command::new("git")
.envs(envs.clone())
.args(["init"])
.current_dir(repo_path)
.output()
@@ -25,12 +30,14 @@ async fn create_temp_git_repo() -> anyhow::Result<TempDir> {
}
Command::new("git")
.envs(envs.clone())
.args(["config", "user.email", "test@example.com"])
.current_dir(repo_path)
.output()
.await?;
Command::new("git")
.envs(envs.clone())
.args(["config", "user.name", "Test User"])
.current_dir(repo_path)
.output()
@@ -39,12 +46,14 @@ async fn create_temp_git_repo() -> anyhow::Result<TempDir> {
std::fs::write(repo_path.join("README.md"), "# Test Repo\n")?;
Command::new("git")
.envs(envs.clone())
.args(["add", "README.md"])
.current_dir(repo_path)
.output()
.await?;
let output = Command::new("git")
.envs(envs.clone())
.args(["commit", "-m", "Initial commit"])
.current_dir(repo_path)
.output()

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-cli"
version = { workspace = true }
edition = "2024"
[[bin]]
name = "codex"
@@ -20,8 +20,8 @@ clap = { version = "4", features = ["derive"] }
clap_complete = "4"
codex-arg0 = { path = "../arg0" }
codex-chatgpt = { path = "../chatgpt" }
codex-core = { path = "../core" }
codex-common = { path = "../common", features = ["cli"] }
codex-core = { path = "../core" }
codex-exec = { path = "../exec" }
codex-login = { path = "../login" }
codex-mcp-server = { path = "../mcp-server" }

View File

@@ -0,0 +1,584 @@
use std::fs::File;
use std::io::Write;
use std::path::Path;
use std::path::PathBuf;
use std::process::Command;
use std::process::Stdio;
use std::sync::OnceLock;
use tokio::process::Command as TokioCommand;
use tokio::sync::Semaphore;
use anyhow::Context;
use codex_common::CliConfigOverrides;
use codex_exec::Cli as ExecCli;
// Serialize git worktree add operations across tasks to avoid repository lock contention.
static GIT_WORKTREE_ADD_SEMAPHORE: OnceLock<Semaphore> = OnceLock::new();
#[derive(Debug, Clone)]
pub struct ConcurrentRunResult {
pub branch: String,
pub worktree_dir: PathBuf,
pub log_file: Option<PathBuf>,
pub exec_exit_code: Option<i32>,
pub _had_changes: bool,
pub _applied_changes: Option<usize>,
}
fn compute_codex_home() -> PathBuf {
if let Ok(val) = std::env::var("CODEX_HOME") {
if !val.is_empty() {
return PathBuf::from(val);
}
}
// Fallback to default (~/.codex) without requiring it to already exist.
codex_core::config::find_codex_home().unwrap_or_else(|_| {
let mut p = std::env::var_os("HOME")
.map(PathBuf::from)
.unwrap_or_default();
if p.as_os_str().is_empty() {
return PathBuf::from(".codex");
}
p.push(".codex");
p
})
}
fn slugify_prompt(prompt: &str, max_len: usize) -> String {
let mut out = String::with_capacity(prompt.len());
let mut prev_hyphen = false;
for ch in prompt.chars() {
let c = ch.to_ascii_lowercase();
let keep = matches!(c, 'a'..='z' | '0'..='9');
if keep {
out.push(c);
prev_hyphen = false;
} else if c.is_ascii_whitespace() || matches!(c, '-' | '_' | '+') {
if !prev_hyphen && !out.is_empty() {
out.push('-');
prev_hyphen = true;
}
} else {
// skip other punctuation/symbols
}
if out.len() >= max_len {
break;
}
}
// Trim trailing hyphens
while out.ends_with('-') {
out.pop();
}
if out.is_empty() {
"task".to_string()
} else {
out
}
}
fn git_output(repo_dir: &Path, args: &[&str]) -> anyhow::Result<String> {
let out = Command::new("git")
.args(args)
.current_dir(repo_dir)
.output()
.with_context(|| format!("running git {args:?}"))?;
if !out.status.success() {
anyhow::bail!(
"git {:?} failed with status {}: {}",
args,
out.status,
String::from_utf8_lossy(&out.stderr)
);
}
Ok(String::from_utf8_lossy(&out.stdout).trim().to_string())
}
fn git_capture_stdout(repo_dir: &Path, args: &[&str]) -> anyhow::Result<Vec<u8>> {
let out = Command::new("git")
.args(args)
.current_dir(repo_dir)
.output()
.with_context(|| format!("running git {args:?}"))?;
if !out.status.success() {
anyhow::bail!(
"git {:?} failed with status {}: {}",
args,
out.status,
String::from_utf8_lossy(&out.stderr)
);
}
Ok(out.stdout)
}
fn count_files_in_patch(diff: &[u8]) -> usize {
// Count occurrences of lines starting with "diff --git ", which mark file boundaries.
// This works for text and binary patches produced by `git diff --binary`.
let mut count = 0usize;
for line in diff.split(|&b| b == b'\n') {
if line.starts_with(b"diff --git ") {
count += 1;
}
}
count
}
pub async fn run_concurrent_flow(
prompt: String,
cli_config_overrides: CliConfigOverrides,
codex_linux_sandbox_exe: Option<PathBuf>,
automerge: bool,
quiet: bool,
) -> anyhow::Result<ConcurrentRunResult> {
let cwd = std::env::current_dir()?;
// Ensure we are in a git repo and find repo root.
let repo_root_str = git_output(&cwd, &["rev-parse", "--show-toplevel"]);
let repo_root = match repo_root_str {
Ok(p) => PathBuf::from(p),
Err(err) => {
eprintln!("Not inside a Git repo: {err}");
std::process::exit(1);
}
};
// Determine current branch and original head commit.
let current_branch = git_output(&repo_root, &["rev-parse", "--abbrev-ref", "HEAD"])
.unwrap_or_else(|_| "HEAD".to_string());
let original_head =
git_output(&repo_root, &["rev-parse", "HEAD"]).context("finding original HEAD commit")?;
// Build worktree target path under $CODEX_HOME/worktrees/<repo>/<branch>
let mut codex_home = compute_codex_home();
codex_home.push("worktrees");
// repo name = last component of repo_root
let repo_name = repo_root
.file_name()
.map(|s| s.to_string_lossy().to_string())
.unwrap_or_else(|| "repo".to_string());
codex_home.push(repo_name.clone());
// Prepare branch name: codex/<slug>, retrying with a numeric suffix to avoid races.
let slug = slugify_prompt(&prompt, 64);
let mut branch: String;
let worktree_dir: PathBuf;
let mut attempt: u32 = 1;
loop {
branch = if attempt == 1 {
format!("codex/{slug}")
} else {
format!("codex/{slug}-{attempt}")
};
let mut candidate_dir = codex_home.clone();
candidate_dir.push(&branch);
// Create parent directories for candidate path.
if let Some(parent) = candidate_dir.parent() {
std::fs::create_dir_all(parent)?;
}
if !quiet {
println!(
"Creating worktree at {} with branch {}",
candidate_dir.display(),
branch
);
}
// Try to add worktree with new branch from current HEAD
let worktree_path_str = candidate_dir.to_string_lossy().to_string();
let add_status = Command::new("git")
.arg("worktree")
.arg("add")
.arg("-b")
.arg(&branch)
.arg(&worktree_path_str)
.current_dir(&repo_root)
.status()?;
if add_status.success() {
worktree_dir = candidate_dir;
break;
}
attempt += 1;
if attempt > 50 {
anyhow::bail!("Failed to create git worktree after multiple attempts");
}
// Retry with a new branch name.
}
// Either run codex exec inline (verbose) or as a subprocess with logs redirected.
let mut log_file: Option<PathBuf> = None;
let mut exec_exit_code: Option<i32> = None;
if quiet {
let exe = std::env::current_exe()
.map_err(|e| anyhow::anyhow!("failed to locate current executable: {e}"))?;
// Prepare logs directory: $CODEX_HOME/logs/<repo_name>
let mut logs_dir = compute_codex_home();
logs_dir.push("logs");
logs_dir.push(&repo_name);
std::fs::create_dir_all(&logs_dir)?;
let sanitized_branch = branch.replace('/', "_");
let log_path = logs_dir.join(format!("{sanitized_branch}.log"));
let log_f = File::create(&log_path)?;
log_file = Some(log_path.clone());
let mut cmd = Command::new(exe);
cmd.arg("exec")
.arg("--full-auto")
.arg("--cd")
.arg(worktree_dir.as_os_str())
.stdout(Stdio::from(log_f.try_clone()?))
.stderr(Stdio::from(log_f));
// Forward any root-level config overrides.
for ov in cli_config_overrides.raw_overrides.iter() {
cmd.arg("-c").arg(ov);
}
// Append the prompt last (positional argument).
cmd.arg(&prompt);
let status = cmd.status()?;
exec_exit_code = status.code();
if !status.success() && !quiet {
eprintln!("codex exec failed with exit code {exec_exit_code:?}");
}
} else {
// Build an ExecCli to run in full-auto mode at the worktree directory.
let mut exec_cli = ExecCli {
images: vec![],
model: None,
sandbox_mode: None,
config_profile: None,
full_auto: true,
dangerously_bypass_approvals_and_sandbox: false,
cwd: Some(worktree_dir.clone()),
skip_git_repo_check: false,
config_overrides: CliConfigOverrides::default(),
color: Default::default(),
json: false,
last_message_file: None,
prompt: Some(prompt.clone()),
};
// Prepend any root-level config overrides.
super::prepend_config_flags(&mut exec_cli.config_overrides, cli_config_overrides);
// Run codex exec
if let Err(e) = codex_exec::run_main(exec_cli, codex_linux_sandbox_exe).await {
eprintln!("codex exec failed: {e}");
// Do not attempt to bring changes on failure; leave worktree for inspection.
return Err(e);
}
}
// Auto-commit changes in the worktree if any
let status_out = Command::new("git")
.args(["status", "--porcelain"])
.current_dir(&worktree_dir)
.output()?;
let status_text = String::from_utf8_lossy(&status_out.stdout);
let had_changes = !status_text.trim().is_empty();
if had_changes {
// Stage and commit
if !Command::new("git")
.args(["add", "-A"])
.current_dir(&worktree_dir)
.status()?
.success()
{
anyhow::bail!("git add failed in worktree");
}
let commit_message = format!("Codex concurrent: {prompt}");
if !Command::new("git")
.args(["commit", "-m", &commit_message])
.current_dir(&worktree_dir)
.status()?
.success()
{
if !quiet {
eprintln!("No commit created (maybe no changes)");
}
} else if !quiet {
println!("Committed changes in worktree branch {branch}");
}
} else if !quiet {
println!("No changes detected in worktree; skipping commit.");
}
if !automerge {
if !quiet {
println!(
"Auto-merge disabled; leaving changes in worktree {} on branch {}.",
worktree_dir.display(),
branch
);
println!(
"You can review and manually merge from that branch into {current_branch} when ready."
);
println!("Summary: Auto-merge disabled.");
}
return Ok(ConcurrentRunResult {
branch,
worktree_dir,
log_file,
exec_exit_code,
_had_changes: had_changes,
_applied_changes: None,
});
}
// Bring the changes into the main working tree as UNSTAGED modifications.
// We generate a patch from the original HEAD to the worktree branch tip, then apply with 3-way merge.
if !quiet {
println!("Applying changes from {branch} onto {current_branch} as unstaged modifications");
}
let range = format!("{original_head}..{branch}");
let mut diff_bytes =
git_capture_stdout(&repo_root, &["diff", "--binary", "--full-index", &range])?;
// Fallback: if there is nothing in the commit range (e.g., commit didn't happen),
// try to capture uncommitted changes from the worktree working tree.
if diff_bytes.is_empty() && had_changes {
// If we saw changes earlier but no commit diff was produced, fall back to working tree diff.
// This captures unstaged changes relative to HEAD in the worktree.
diff_bytes =
git_capture_stdout(&worktree_dir, &["diff", "--binary", "--full-index", "HEAD"])?;
}
if diff_bytes.is_empty() {
if !quiet {
println!("Summary: 0 changes detected.");
}
return Ok(ConcurrentRunResult {
branch,
worktree_dir,
log_file,
exec_exit_code,
_had_changes: had_changes,
_applied_changes: Some(0),
});
}
let changed_files = count_files_in_patch(&diff_bytes);
let mut child = Command::new("git")
.arg("apply")
.arg("-3")
.stdin(Stdio::piped())
.stdout(Stdio::inherit())
.stderr(Stdio::inherit())
.current_dir(&repo_root)
.spawn()
.context("spawning git apply")?;
if let Some(stdin) = child.stdin.as_mut() {
stdin
.write_all(&diff_bytes)
.context("writing patch to git apply stdin")?;
}
let status = child.wait().context("waiting for git apply")?;
if !status.success() {
if !quiet {
eprintln!(
"Applying changes failed. You can manually inspect {} and apply diffs.",
worktree_dir.display()
);
println!("Summary: Apply failed.");
}
} else {
if !quiet {
println!("Changes applied to working tree (unstaged).");
println!("Summary: Applied {changed_files} files changed.");
}
// Cleanup: remove the worktree and delete the temporary branch.
if !quiet {
println!(
"Cleaning up worktree {} and branch {}",
worktree_dir.display(),
branch
);
}
let worktree_path_str = worktree_dir.to_string_lossy().to_string();
let remove_status = Command::new("git")
.args(["worktree", "remove", &worktree_path_str])
.current_dir(&repo_root)
.status();
match remove_status {
Ok(s) if s.success() => {
// removed
}
_ => {
if !quiet {
eprintln!("git worktree remove failed; retrying with --force");
}
let _ = Command::new("git")
.args(["worktree", "remove", "--force", &worktree_path_str])
.current_dir(&repo_root)
.status();
}
}
let del_status = Command::new("git")
.args(["branch", "-D", &branch])
.current_dir(&repo_root)
.status();
if let Ok(s) = del_status {
if !s.success() && !quiet {
eprintln!("Failed to delete branch {branch}");
}
} else if !quiet {
eprintln!("Error running git branch -D {branch}");
}
}
Ok(ConcurrentRunResult {
branch,
worktree_dir,
log_file,
exec_exit_code,
_had_changes: had_changes,
_applied_changes: Some(changed_files),
})
}
/// A Send-friendly variant used for best-of-n: run quietly (logs redirected) and do not auto-merge.
/// This intentionally avoids referencing non-Send types from codex-exec.
pub async fn run_concurrent_flow_quiet_no_automerge(
prompt: String,
cli_config_overrides: CliConfigOverrides,
_codex_linux_sandbox_exe: Option<PathBuf>,
) -> anyhow::Result<ConcurrentRunResult> {
let cwd = std::env::current_dir()?;
let repo_root_str = git_output(&cwd, &["rev-parse", "--show-toplevel"]);
let repo_root = match repo_root_str {
Ok(p) => PathBuf::from(p),
Err(err) => {
eprintln!("Not inside a Git repo: {err}");
std::process::exit(1);
}
};
// Capture basic repo info (not used further in quiet/no-automerge flow).
let mut codex_home = compute_codex_home();
codex_home.push("worktrees");
let repo_name = repo_root
.file_name()
.map(|s| s.to_string_lossy().to_string())
.unwrap_or_else(|| "repo".to_string());
codex_home.push(repo_name.clone());
let slug = slugify_prompt(&prompt, 64);
let mut branch: String;
let worktree_dir: PathBuf;
// Serialize worktree creation to avoid git repo lock contention across tasks.
{
let semaphore = GIT_WORKTREE_ADD_SEMAPHORE.get_or_init(|| Semaphore::new(1));
let _permit = semaphore.acquire().await.expect("semaphore closed");
let mut attempt: u32 = 1;
loop {
branch = if attempt == 1 {
format!("codex/{slug}")
} else {
format!("codex/{slug}-{attempt}")
};
let mut candidate_dir = codex_home.clone();
candidate_dir.push(&branch);
if let Some(parent) = candidate_dir.parent() {
std::fs::create_dir_all(parent)?;
}
let worktree_path_str = candidate_dir.to_string_lossy().to_string();
let add_status = TokioCommand::new("git")
.arg("worktree")
.arg("add")
.arg("-b")
.arg(&branch)
.arg(&worktree_path_str)
.current_dir(&repo_root)
.status()
.await?;
if add_status.success() {
worktree_dir = candidate_dir;
break;
}
attempt += 1;
if attempt > 50 {
anyhow::bail!("Failed to create git worktree after multiple attempts");
}
}
}
// Run the CLI in quiet mode (logs redirected).
let exe = std::env::current_exe()
.map_err(|e| anyhow::anyhow!("failed to locate current executable: {e}"))?;
let mut logs_dir = compute_codex_home();
logs_dir.push("logs");
logs_dir.push(&repo_name);
std::fs::create_dir_all(&logs_dir)?;
let sanitized_branch = branch.replace('/', "_");
let log_path = logs_dir.join(format!("{sanitized_branch}.log"));
let log_f = File::create(&log_path)?;
let log_file = Some(log_path.clone());
let mut cmd = TokioCommand::new(exe);
cmd.arg("exec")
.arg("--full-auto")
.arg("--cd")
.arg(worktree_dir.as_os_str())
.stdout(Stdio::from(log_f.try_clone()?))
.stderr(Stdio::from(log_f));
for ov in cli_config_overrides.raw_overrides.iter() {
cmd.arg("-c").arg(ov);
}
cmd.arg(&prompt);
let status = cmd.status().await?;
let exec_exit_code = status.code();
// Auto-commit changes in the worktree if any
let status_out = TokioCommand::new("git")
.args(["status", "--porcelain"])
.current_dir(&worktree_dir)
.output()
.await?;
let status_text = String::from_utf8_lossy(&status_out.stdout);
let had_changes = !status_text.trim().is_empty();
if had_changes {
if !TokioCommand::new("git")
.args(["add", "-A"])
.current_dir(&worktree_dir)
.status()
.await?
.success()
{
anyhow::bail!("git add failed in worktree");
}
let commit_message = format!("Codex concurrent: {prompt}");
let _ = TokioCommand::new("git")
.args(["commit", "-m", &commit_message])
.current_dir(&worktree_dir)
.status()
.await?;
}
Ok(ConcurrentRunResult {
branch,
worktree_dir,
log_file,
exec_exit_code,
_had_changes: had_changes,
_applied_changes: None,
})
}

View File

@@ -4,10 +4,10 @@ use codex_common::CliConfigOverrides;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_core::config_types::SandboxMode;
use codex_core::exec::StdioPolicy;
use codex_core::exec::spawn_command_under_linux_sandbox;
use codex_core::exec::spawn_command_under_seatbelt;
use codex_core::exec_env::create_env;
use codex_core::seatbelt::spawn_command_under_seatbelt;
use codex_core::spawn::StdioPolicy;
use crate::LandlockCommand;
use crate::SeatbeltCommand;

View File

@@ -1,8 +1,12 @@
use std::env;
use codex_common::CliConfigOverrides;
use codex_core::config::Config;
use codex_core::config::ConfigOverrides;
use codex_login::AuthMode;
use codex_login::OPENAI_API_KEY_ENV_VAR;
use codex_login::load_auth;
use codex_login::login_with_api_key;
use codex_login::login_with_chatgpt;
pub async fn run_login_with_chatgpt(cli_config_overrides: CliConfigOverrides) -> ! {
@@ -21,14 +25,40 @@ pub async fn run_login_with_chatgpt(cli_config_overrides: CliConfigOverrides) ->
}
}
pub async fn run_login_with_api_key(
cli_config_overrides: CliConfigOverrides,
api_key: String,
) -> ! {
let config = load_config_or_exit(cli_config_overrides);
match login_with_api_key(&config.codex_home, &api_key) {
Ok(_) => {
eprintln!("Successfully logged in");
std::process::exit(0);
}
Err(e) => {
eprintln!("Error logging in: {e}");
std::process::exit(1);
}
}
}
pub async fn run_login_status(cli_config_overrides: CliConfigOverrides) -> ! {
let config = load_config_or_exit(cli_config_overrides);
match load_auth(&config.codex_home) {
match load_auth(&config.codex_home, true) {
Ok(Some(auth)) => match auth.mode {
AuthMode::ApiKey => {
if let Some(api_key) = auth.api_key.as_deref() {
eprintln!("Logged in using an API key - {}", safe_format_key(api_key));
if let Ok(env_api_key) = env::var(OPENAI_API_KEY_ENV_VAR) {
if env_api_key == api_key {
eprintln!(
" API loaded from OPENAI_API_KEY environment variable or .env file"
);
}
}
} else {
eprintln!("Logged in using an API key");
}

View File

@@ -8,6 +8,7 @@ use codex_chatgpt::apply_command::run_apply_command;
use codex_cli::LandlockCommand;
use codex_cli::SeatbeltCommand;
use codex_cli::login::run_login_status;
use codex_cli::login::run_login_with_api_key;
use codex_cli::login::run_login_with_chatgpt;
use codex_cli::proto;
use codex_common::CliConfigOverrides;
@@ -16,6 +17,7 @@ use codex_tui::Cli as TuiCli;
use std::path::PathBuf;
use crate::proto::ProtoCli;
mod concurrent;
/// Codex CLI
///
@@ -31,6 +33,22 @@ struct MultitoolCli {
#[clap(flatten)]
pub config_overrides: CliConfigOverrides,
/// Experimental:Launch a concurrent task in a separate Git worktree using the given prompt.
/// Creates worktree under $CODEX_HOME/worktrees/<repo>/codex/<slug> and runs `codex exec` in full-auto mode.
#[arg(long = "concurrent", value_name = "PROMPT")]
pub concurrent: Option<String>,
/// When using --concurrent, also attempt to auto-merge the resulting changes
/// back into the current working tree as unstaged modifications via
/// a 3-way git apply. Disable with --automerge=false.
#[arg(long = "automerge", default_value_t = true, action = clap::ArgAction::Set)]
pub automerge: bool,
/// Run the same --concurrent prompt N times in separate worktrees and keep them all.
/// Intended to generate multiple candidate solutions without auto-merging.
#[arg(long = "best-of-n", value_name = "N", default_value_t = 1)]
pub best_of_n: usize,
#[clap(flatten)]
interactive: TuiCli,
@@ -92,6 +110,9 @@ struct LoginCommand {
#[clap(skip)]
config_overrides: CliConfigOverrides,
#[arg(long = "api-key", value_name = "API_KEY")]
api_key: Option<String>,
#[command(subcommand)]
action: Option<LoginSubcommand>,
}
@@ -112,6 +133,87 @@ fn main() -> anyhow::Result<()> {
async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()> {
let cli = MultitoolCli::parse();
// Handle --concurrent at the root level.
if let Some(prompt) = cli.concurrent.clone() {
if cli.subcommand.is_some() {
eprintln!("--concurrent cannot be used together with a subcommand");
std::process::exit(2);
}
let runs = if cli.best_of_n == 0 { 1 } else { cli.best_of_n };
if runs > 1 {
println!(
"Running best-of-n with {runs} runs; auto-merge will be disabled and worktrees kept."
);
// Launch all runs concurrently and collect results as they finish.
let mut join_set = tokio::task::JoinSet::new();
for _ in 0..runs {
let prompt = prompt.clone();
let overrides = cli.config_overrides.clone();
let sandbox = codex_linux_sandbox_exe.clone();
join_set.spawn(async move {
concurrent::run_concurrent_flow_quiet_no_automerge(prompt, overrides, sandbox)
.await
});
}
let mut results: Vec<concurrent::ConcurrentRunResult> = Vec::with_capacity(runs);
while let Some(join_result) = join_set.join_next().await {
match join_result {
Ok(Ok(res)) => {
println!(
"task finished for branch: {}\n, directory: {}",
res.branch,
res.worktree_dir.display()
);
results.push(res);
}
Ok(Err(err)) => {
eprintln!("concurrent task failed: {err}");
}
Err(join_err) => {
eprintln!("failed to join concurrent task: {join_err}");
}
}
}
println!("\nBest-of-n summary:");
for r in &results {
let status = match r.exec_exit_code {
Some(0) => "OK",
Some(_code) => "FAIL",
None => "OK",
};
let log = r
.log_file
.as_ref()
.map(|p| p.to_string_lossy().to_string())
.unwrap_or_else(|| "<no log>".to_string());
println!(
"[{status}] branch={} worktree={} log={}",
r.branch,
r.worktree_dir.display(),
log
);
}
} else {
concurrent::run_concurrent_flow(
prompt,
cli.config_overrides,
codex_linux_sandbox_exe,
cli.automerge,
false,
)
.await?;
}
return Ok(());
}
if cli.best_of_n > 1 {
eprintln!("--best-of-n requires --concurrent <PROMPT>");
std::process::exit(2);
}
match cli.subcommand {
None => {
let mut tui_cli = cli.interactive;
@@ -133,7 +235,11 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
run_login_status(login_cli.config_overrides).await;
}
None => {
run_login_with_chatgpt(login_cli.config_overrides).await;
if let Some(api_key) = login_cli.api_key {
run_login_with_api_key(login_cli.config_overrides, api_key).await;
} else {
run_login_with_chatgpt(login_cli.config_overrides).await;
}
}
}
}

View File

@@ -36,7 +36,7 @@ pub async fn run_main(opts: ProtoCli) -> anyhow::Result<()> {
.map_err(anyhow::Error::msg)?;
let config = Config::load_with_cli_overrides(overrides_vec, ConfigOverrides::default())?;
let auth = load_auth(&config.codex_home)?;
let auth = load_auth(&config.codex_home, true)?;
let ctrl_c = notify_on_sigint();
let CodexSpawnOk { codex, .. } = Codex::spawn(config, auth, ctrl_c.clone()).await?;
let codex = Arc::new(codex);

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-common"
version = { workspace = true }
edition = "2024"
[lints]
workspace = true
@@ -9,11 +9,11 @@ workspace = true
[dependencies]
clap = { version = "4", features = ["derive", "wrap_help"], optional = true }
codex-core = { path = "../core" }
toml = { version = "0.9", optional = true }
serde = { version = "1", optional = true }
toml = { version = "0.9", optional = true }
[features]
# Separate feature so that `clap` is not a mandatory dependency.
cli = ["clap", "toml", "serde"]
cli = ["clap", "serde", "toml"]
elapsed = []
sandbox_summary = []

View File

@@ -7,6 +7,7 @@ pub fn summarize_sandbox_policy(sandbox_policy: &SandboxPolicy) -> String {
SandboxPolicy::WorkspaceWrite {
writable_roots,
network_access,
include_default_writable_roots,
} => {
let mut summary = "workspace-write".to_string();
if !writable_roots.is_empty() {
@@ -19,6 +20,9 @@ pub fn summarize_sandbox_policy(sandbox_policy: &SandboxPolicy) -> String {
.join(", ")
));
}
if !*include_default_writable_roots {
summary.push_str(" (exact writable roots)");
}
if *network_access {
summary.push_str(" (network access enabled)");
}

View File

@@ -259,6 +259,8 @@ disk, but attempts to write a file or access the network will be blocked.
A more relaxed policy is `workspace-write`. When specified, the current working directory for the Codex task will be writable (as well as `$TMPDIR` on macOS). Note that the CLI defaults to using the directory where it was spawned as `cwd`, though this can be overridden using `--cwd/-C`.
On macOS (and soon Linux), all writable roots (including `cwd`) that contain a `.git/` folder _as an immediate child_ will configure the `.git/` folder to be read-only while the rest of the Git repository will be writable. This means that commands like `git commit` will fail, by default (as it entails writing to `.git/`), and will require Codex to ask for permission.
```toml
# same as `--sandbox workspace-write`
sandbox_mode = "workspace-write"

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-core"
version = { workspace = true }
edition = "2024"
[lib]
name = "codex_core"
@@ -15,10 +15,10 @@ anyhow = "1"
async-channel = "2.3.1"
base64 = "0.22"
bytes = "1.10.1"
codex-apply-patch = { path = "../apply-patch" }
codex-mcp-client = { path = "../mcp-client" }
chrono = { version = "0.4", features = ["serde"] }
codex-apply-patch = { path = "../apply-patch" }
codex-login = { path = "../login" }
codex-mcp-client = { path = "../mcp-client" }
dirs = "6"
env-flags = "0.1.1"
eventsource-stream = "0.2.3"
@@ -31,6 +31,7 @@ rand = "0.9"
reqwest = { version = "0.12", features = ["json", "stream"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
serde_bytes = "0.11"
sha1 = "0.10.6"
shlex = "1.3.0"
strum_macros = "0.27.2"
@@ -49,8 +50,8 @@ tracing = { version = "0.1.41", features = ["log"] }
tree-sitter = "0.25.8"
tree-sitter-bash = "0.25.0"
uuid = { version = "1", features = ["serde", "v4"] }
wildmatch = "2.4.0"
whoami = "1.6.0"
wildmatch = "2.4.0"
[target.'cfg(target_os = "linux")'.dependencies]

View File

@@ -96,3 +96,12 @@ You can invoke apply_patch like:
```
shell {"command":["apply_patch","*** Begin Patch\n*** Add File: hello.txt\n+Hello, world!\n*** End Patch\n"]}
```
Plan updates
A tool named `update_plan` is available. Use it to keep an uptodate, stepbystep plan for the task so you can follow your progress. When making your plans, keep in mind that you are a deployed coding agent - `update_plan` calls should not involve doing anything that you aren't capable of doing. For example, `update_plan` calls should NEVER contain tasks to merge your own pull requests. Only stop to ask the user if you genuinely need their feedback on a change.
- At the start of the task, call `update_plan` with an initial plan: a short list of 1sentence steps with a `status` for each step (`pending`, `in_progress`, or `completed`). There should always be exactly one `in_progress` step until everything is done.
- Whenever you finish a step, call `update_plan` again, marking the finished step as `completed` and the next step as `in_progress`.
- If your plan needs to change, call `update_plan` with the revised steps and include an `explanation` describing the change.
- When all steps are complete, make a final `update_plan` call with all steps marked `completed`.

View File

@@ -1,277 +1,107 @@
use crate::codex::Session;
use crate::models::FunctionCallOutputPayload;
use crate::models::ResponseInputItem;
use crate::protocol::Event;
use crate::protocol::EventMsg;
use crate::protocol::FileChange;
use crate::protocol::PatchApplyBeginEvent;
use crate::protocol::PatchApplyEndEvent;
use crate::protocol::ReviewDecision;
use crate::safety::SafetyCheck;
use crate::safety::assess_patch_safety;
use anyhow::Context;
use codex_apply_patch::AffectedPaths;
use codex_apply_patch::ApplyPatchAction;
use codex_apply_patch::ApplyPatchFileChange;
use codex_apply_patch::print_summary;
use std::collections::HashMap;
use std::path::Path;
use std::path::PathBuf;
pub const CODEX_APPLY_PATCH_ARG1: &str = "--codex-run-as-apply-patch";
pub(crate) enum InternalApplyPatchInvocation {
/// The `apply_patch` call was handled programmatically, without any sort
/// of sandbox, because the user explicitly approved it. This is the
/// result to use with the `shell` function call that contained `apply_patch`.
Output(ResponseInputItem),
/// The `apply_patch` call was approved, either automatically because it
/// appears that it should be allowed based on the user's sandbox policy
/// *or* because the user explicitly approved it. In either case, we use
/// exec with [`CODEX_APPLY_PATCH_ARG1`] to realize the `apply_patch` call,
/// but [`ApplyPatchExec::auto_approved`] is used to determine the sandbox
/// used with the `exec()`.
DelegateToExec(ApplyPatchExec),
}
pub(crate) struct ApplyPatchExec {
pub(crate) action: ApplyPatchAction,
pub(crate) user_explicitly_approved_this_action: bool,
}
impl From<ResponseInputItem> for InternalApplyPatchInvocation {
fn from(item: ResponseInputItem) -> Self {
InternalApplyPatchInvocation::Output(item)
}
}
pub(crate) async fn apply_patch(
sess: &Session,
sub_id: String,
call_id: String,
sub_id: &str,
call_id: &str,
action: ApplyPatchAction,
) -> ResponseInputItem {
) -> InternalApplyPatchInvocation {
let writable_roots_snapshot = {
#[allow(clippy::unwrap_used)]
let guard = sess.writable_roots.lock().unwrap();
guard.clone()
};
let auto_approved = match assess_patch_safety(
match assess_patch_safety(
&action,
sess.approval_policy,
&writable_roots_snapshot,
&sess.cwd,
) {
SafetyCheck::AutoApprove { .. } => true,
SafetyCheck::AutoApprove { .. } => {
InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
action,
user_explicitly_approved_this_action: false,
})
}
SafetyCheck::AskUser => {
// Compute a readable summary of path changes to include in the
// approval request so the user can make an informed decision.
//
// Note that it might be worth expanding this approval request to
// give the user the option to expand the set of writable roots so
// that similar patches can be auto-approved in the future during
// this session.
let rx_approve = sess
.request_patch_approval(sub_id.clone(), call_id.clone(), &action, None, None)
.request_patch_approval(sub_id.to_owned(), call_id.to_owned(), &action, None, None)
.await;
match rx_approve.await.unwrap_or_default() {
ReviewDecision::Approved | ReviewDecision::ApprovedForSession => false,
ReviewDecision::Approved | ReviewDecision::ApprovedForSession => {
InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
action,
user_explicitly_approved_this_action: true,
})
}
ReviewDecision::Denied | ReviewDecision::Abort => {
return ResponseInputItem::FunctionCallOutput {
call_id,
ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: "patch rejected by user".to_string(),
success: Some(false),
},
};
}
.into()
}
}
}
SafetyCheck::Reject { reason } => {
return ResponseInputItem::FunctionCallOutput {
call_id,
output: FunctionCallOutputPayload {
content: format!("patch rejected: {reason}"),
success: Some(false),
},
};
}
};
// Verify write permissions before touching the filesystem.
let writable_snapshot = {
#[allow(clippy::unwrap_used)]
sess.writable_roots.lock().unwrap().clone()
};
if let Some(offending) = first_offending_path(&action, &writable_snapshot, &sess.cwd) {
let root = offending.parent().unwrap_or(&offending).to_path_buf();
let reason = Some(format!(
"grant write access to {} for this session",
root.display()
));
let rx = sess
.request_patch_approval(
sub_id.clone(),
call_id.clone(),
&action,
reason.clone(),
Some(root.clone()),
)
.await;
if !matches!(
rx.await.unwrap_or_default(),
ReviewDecision::Approved | ReviewDecision::ApprovedForSession
) {
return ResponseInputItem::FunctionCallOutput {
call_id,
output: FunctionCallOutputPayload {
content: "patch rejected by user".to_string(),
success: Some(false),
},
};
}
// user approved, extend writable roots for this session
#[allow(clippy::unwrap_used)]
sess.writable_roots.lock().unwrap().push(root);
}
let _ = sess
.tx_event
.send(Event {
id: sub_id.clone(),
msg: EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
call_id: call_id.clone(),
auto_approved,
changes: convert_apply_patch_to_protocol(&action),
}),
})
.await;
let mut stdout = Vec::new();
let mut stderr = Vec::new();
// Enforce writable roots. If a write is blocked, collect offending root
// and prompt the user to extend permissions.
let mut result = apply_changes_from_apply_patch_and_report(&action, &mut stdout, &mut stderr);
if let Err(err) = &result {
if err.kind() == std::io::ErrorKind::PermissionDenied {
// Determine first offending path.
let offending_opt = action
.changes()
.iter()
.flat_map(|(path, change)| match change {
ApplyPatchFileChange::Add { .. } => vec![path.as_ref()],
ApplyPatchFileChange::Delete => vec![path.as_ref()],
ApplyPatchFileChange::Update {
move_path: Some(move_path),
..
} => {
vec![path.as_ref(), move_path.as_ref()]
}
ApplyPatchFileChange::Update {
move_path: None, ..
} => vec![path.as_ref()],
})
.find_map(|path: &Path| {
// ApplyPatchAction promises to guarantee absolute paths.
if !path.is_absolute() {
panic!("apply_patch invariant failed: path is not absolute: {path:?}");
}
let writable = {
#[allow(clippy::unwrap_used)]
let roots = sess.writable_roots.lock().unwrap();
roots.iter().any(|root| path.starts_with(root))
};
if writable {
None
} else {
Some(path.to_path_buf())
}
});
if let Some(offending) = offending_opt {
let root = offending.parent().unwrap_or(&offending).to_path_buf();
let reason = Some(format!(
"grant write access to {} for this session",
root.display()
));
let rx = sess
.request_patch_approval(
sub_id.clone(),
call_id.clone(),
&action,
reason.clone(),
Some(root.clone()),
)
.await;
if matches!(
rx.await.unwrap_or_default(),
ReviewDecision::Approved | ReviewDecision::ApprovedForSession
) {
// Extend writable roots.
#[allow(clippy::unwrap_used)]
sess.writable_roots.lock().unwrap().push(root);
stdout.clear();
stderr.clear();
result = apply_changes_from_apply_patch_and_report(
&action,
&mut stdout,
&mut stderr,
);
}
}
}
}
// Emit PatchApplyEnd event.
let success_flag = result.is_ok();
let _ = sess
.tx_event
.send(Event {
id: sub_id.clone(),
msg: EventMsg::PatchApplyEnd(PatchApplyEndEvent {
call_id: call_id.clone(),
stdout: String::from_utf8_lossy(&stdout).to_string(),
stderr: String::from_utf8_lossy(&stderr).to_string(),
success: success_flag,
}),
})
.await;
match result {
Ok(_) => ResponseInputItem::FunctionCallOutput {
call_id,
SafetyCheck::Reject { reason } => ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_owned(),
output: FunctionCallOutputPayload {
content: String::from_utf8_lossy(&stdout).to_string(),
success: None,
},
},
Err(e) => ResponseInputItem::FunctionCallOutput {
call_id,
output: FunctionCallOutputPayload {
content: format!("error: {e:#}, stderr: {}", String::from_utf8_lossy(&stderr)),
content: format!("patch rejected: {reason}"),
success: Some(false),
},
},
}
}
/// Return the first path in `hunks` that is NOT under any of the
/// `writable_roots` (after normalising). If all paths are acceptable,
/// returns None.
fn first_offending_path(
action: &ApplyPatchAction,
writable_roots: &[PathBuf],
cwd: &Path,
) -> Option<PathBuf> {
let changes = action.changes();
for (path, change) in changes {
let candidate = match change {
ApplyPatchFileChange::Add { .. } => path,
ApplyPatchFileChange::Delete => path,
ApplyPatchFileChange::Update { move_path, .. } => move_path.as_ref().unwrap_or(path),
};
let abs = if candidate.is_absolute() {
candidate.clone()
} else {
cwd.join(candidate)
};
let mut allowed = false;
for root in writable_roots {
let root_abs = if root.is_absolute() {
root.clone()
} else {
cwd.join(root)
};
if abs.starts_with(&root_abs) {
allowed = true;
break;
}
}
if !allowed {
return Some(candidate.clone());
}
.into(),
}
None
}
pub(crate) fn convert_apply_patch_to_protocol(
@@ -299,85 +129,6 @@ pub(crate) fn convert_apply_patch_to_protocol(
result
}
fn apply_changes_from_apply_patch_and_report(
action: &ApplyPatchAction,
stdout: &mut impl std::io::Write,
stderr: &mut impl std::io::Write,
) -> std::io::Result<()> {
match apply_changes_from_apply_patch(action) {
Ok(affected_paths) => {
print_summary(&affected_paths, stdout)?;
}
Err(err) => {
writeln!(stderr, "{err:?}")?;
}
}
Ok(())
}
fn apply_changes_from_apply_patch(action: &ApplyPatchAction) -> anyhow::Result<AffectedPaths> {
let mut added: Vec<PathBuf> = Vec::new();
let mut modified: Vec<PathBuf> = Vec::new();
let mut deleted: Vec<PathBuf> = Vec::new();
let changes = action.changes();
for (path, change) in changes {
match change {
ApplyPatchFileChange::Add { content } => {
if let Some(parent) = path.parent() {
if !parent.as_os_str().is_empty() {
std::fs::create_dir_all(parent).with_context(|| {
format!("Failed to create parent directories for {}", path.display())
})?;
}
}
std::fs::write(path, content)
.with_context(|| format!("Failed to write file {}", path.display()))?;
added.push(path.clone());
}
ApplyPatchFileChange::Delete => {
std::fs::remove_file(path)
.with_context(|| format!("Failed to delete file {}", path.display()))?;
deleted.push(path.clone());
}
ApplyPatchFileChange::Update {
unified_diff: _unified_diff,
move_path,
new_content,
} => {
if let Some(move_path) = move_path {
if let Some(parent) = move_path.parent() {
if !parent.as_os_str().is_empty() {
std::fs::create_dir_all(parent).with_context(|| {
format!(
"Failed to create parent directories for {}",
move_path.display()
)
})?;
}
}
std::fs::rename(path, move_path)
.with_context(|| format!("Failed to rename file {}", path.display()))?;
std::fs::write(move_path, new_content)?;
modified.push(move_path.clone());
deleted.push(path.clone());
} else {
std::fs::write(path, new_content)?;
modified.push(path.clone());
}
}
}
}
Ok(AffectedPaths {
added,
modified,
deleted,
})
}
pub(crate) fn get_writable_roots(cwd: &Path) -> Vec<PathBuf> {
let mut writable_roots = Vec::new();
if cfg!(target_os = "macos") {

View File

@@ -192,7 +192,7 @@ impl ModelClient {
loop {
attempt += 1;
let req_builder = self
let mut req_builder = self
.client
.post(format!("{base_url}/responses"))
.header("OpenAI-Beta", "responses=experimental")
@@ -201,7 +201,20 @@ impl ModelClient {
.header(reqwest::header::ACCEPT, "text/event-stream")
.json(&payload);
let req_builder = self.provider.apply_http_headers(req_builder);
if auth.mode == AuthMode::ChatGPT {
if let Some(account_id) = auth.get_account_id().await {
req_builder = req_builder.header("chatgpt-account-id", account_id);
}
}
req_builder = self.provider.apply_http_headers(req_builder);
let originator = self
.config
.internal_originator
.as_deref()
.unwrap_or("codex_cli_rs");
req_builder = req_builder.header("originator", originator);
let res = req_builder.send().await;
if let Ok(resp) = &res {

View File

@@ -30,6 +30,9 @@ use tracing::trace;
use tracing::warn;
use uuid::Uuid;
use crate::apply_patch::ApplyPatchExec;
use crate::apply_patch::CODEX_APPLY_PATCH_ARG1;
use crate::apply_patch::InternalApplyPatchInvocation;
use crate::apply_patch::convert_apply_patch_to_protocol;
use crate::apply_patch::get_writable_roots;
use crate::apply_patch::{self};
@@ -45,6 +48,7 @@ use crate::error::SandboxErr;
use crate::exec::ExecParams;
use crate::exec::ExecToolCallOutput;
use crate::exec::SandboxType;
use crate::exec::StdoutStream;
use crate::exec::process_exec_tool_call;
use crate::exec_env::create_env;
use crate::mcp_connection_manager::McpConnectionManager;
@@ -71,8 +75,11 @@ use crate::protocol::EventMsg;
use crate::protocol::ExecApprovalRequestEvent;
use crate::protocol::ExecCommandBeginEvent;
use crate::protocol::ExecCommandEndEvent;
use crate::protocol::FileChange;
use crate::protocol::InputItem;
use crate::protocol::Op;
use crate::protocol::PatchApplyBeginEvent;
use crate::protocol::PatchApplyEndEvent;
use crate::protocol::ReviewDecision;
use crate::protocol::SandboxPolicy;
use crate::protocol::SessionConfiguredEvent;
@@ -81,6 +88,7 @@ use crate::protocol::TaskCompleteEvent;
use crate::rollout::RolloutRecorder;
use crate::safety::SafetyCheck;
use crate::safety::assess_command_safety;
use crate::safety::assess_safety_for_untrusted_command;
use crate::shell;
use crate::user_notification::UserNotification;
use crate::util::backoff;
@@ -354,14 +362,32 @@ impl Session {
}
}
async fn notify_exec_command_begin(&self, sub_id: &str, call_id: &str, params: &ExecParams) {
async fn notify_exec_command_begin(&self, exec_command_context: ExecCommandContext) {
let ExecCommandContext {
sub_id,
call_id,
command_for_display,
cwd,
apply_patch,
} = exec_command_context;
let msg = match apply_patch {
Some(ApplyPatchCommandContext {
user_explicitly_approved_this_action,
changes,
}) => EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
call_id,
auto_approved: !user_explicitly_approved_this_action,
changes,
}),
None => EventMsg::ExecCommandBegin(ExecCommandBeginEvent {
call_id,
command: command_for_display.clone(),
cwd,
}),
};
let event = Event {
id: sub_id.to_string(),
msg: EventMsg::ExecCommandBegin(ExecCommandBeginEvent {
call_id: call_id.to_string(),
command: params.command.clone(),
cwd: params.cwd.clone(),
}),
msg,
};
let _ = self.tx_event.send(event).await;
}
@@ -373,18 +399,33 @@ impl Session {
stdout: &str,
stderr: &str,
exit_code: i32,
is_apply_patch: bool,
) {
// Because stdout and stderr could each be up to 100 KiB, we send
// truncated versions.
const MAX_STREAM_OUTPUT: usize = 5 * 1024; // 5KiB
let stdout = stdout.chars().take(MAX_STREAM_OUTPUT).collect();
let stderr = stderr.chars().take(MAX_STREAM_OUTPUT).collect();
let msg = if is_apply_patch {
EventMsg::PatchApplyEnd(PatchApplyEndEvent {
call_id: call_id.to_string(),
stdout,
stderr,
success: exit_code == 0,
})
} else {
EventMsg::ExecCommandEnd(ExecCommandEndEvent {
call_id: call_id.to_string(),
stdout,
stderr,
exit_code,
})
};
let event = Event {
id: sub_id.to_string(),
// Because stdout and stderr could each be up to 100 KiB, we send
// truncated versions.
msg: EventMsg::ExecCommandEnd(ExecCommandEndEvent {
call_id: call_id.to_string(),
stdout: stdout.chars().take(MAX_STREAM_OUTPUT).collect(),
stderr: stderr.chars().take(MAX_STREAM_OUTPUT).collect(),
exit_code,
}),
msg,
};
let _ = self.tx_event.send(event).await;
}
@@ -402,6 +443,12 @@ impl Session {
let _ = self.tx_event.send(event).await;
}
/// Build the full turn input by concatenating the current conversation
/// history with additional items for this turn.
pub fn turn_input_with_history(&self, extra: Vec<ResponseItem>) -> Vec<ResponseItem> {
[self.state.lock().unwrap().history.contents(), extra].concat()
}
/// Returns the input if there was no task running to inject into
pub fn inject_input(&self, input: Vec<InputItem>) -> Result<(), Vec<InputItem>> {
let mut state = self.state.lock().unwrap();
@@ -492,6 +539,21 @@ impl State {
}
}
#[derive(Clone, Debug)]
pub(crate) struct ExecCommandContext {
pub(crate) sub_id: String,
pub(crate) call_id: String,
pub(crate) command_for_display: Vec<String>,
pub(crate) cwd: PathBuf,
pub(crate) apply_patch: Option<ApplyPatchCommandContext>,
}
#[derive(Clone, Debug)]
pub(crate) struct ApplyPatchCommandContext {
pub(crate) user_explicitly_approved_this_action: bool,
pub(crate) changes: HashMap<PathBuf, FileChange>,
}
/// A series of Turns in response to user input.
pub(crate) struct AgentTask {
sess: Arc<Session>,
@@ -509,6 +571,25 @@ impl AgentTask {
handle,
}
}
fn compact(
sess: Arc<Session>,
sub_id: String,
input: Vec<InputItem>,
compact_instructions: String,
) -> Self {
let handle = tokio::spawn(run_compact_task(
Arc::clone(&sess),
sub_id.clone(),
input,
compact_instructions,
))
.abort_handle();
Self {
sess,
sub_id,
handle,
}
}
fn abort(self) {
if !self.handle.is_finished() {
@@ -829,7 +910,7 @@ async fn submission_loop(
}
});
}
Op::SummarizeContext => {
Op::Compact => {
let sess = match sess.as_ref() {
Some(sess) => sess,
None => {
@@ -839,67 +920,19 @@ async fn submission_loop(
};
// Create a summarization request as user input
const SUMMARIZATION_PROMPT: &str = r#"
You are the component that compacts a long coding session log into a structured memory object.
This memory will become the ONLY reference for continuing the task.
All critical facts, user intentions, tool results, and file operations must be captured.
Omit filler talk and commentary. Do not invent information; use "none" if evidence is missing.
Output ONLY the XML object below. No extra text.
<project_memory>
<mission>
<!-- One concise line describing the users main goal. -->
</mission>
<essentials>
<!-- Bullet-like facts the agent must retain: commands, APIs, paths, configs, tickets, rules. -->
<!-- Example:
- Build cmd: `npm run build`
- Repo branch: `feature/auth-refactor`
- API version: v2
-->
</essentials>
<workspace>
<!-- Record file interactions and key observations. -->
<!-- Example:
- CREATED: `tests/login.test.ts` initial test
- MODIFIED: `src/auth.ts` swapped jwt library
- DELETED: none
-->
</workspace>
<activity_log>
<!-- Key actions and tool outputs in the recent session. -->
<!-- Example:
- Ran `npm test` 1 failure in `User.test.ts`
- Queried `grep 'oldAPI'` 2 matches
-->
</activity_log>
<next_steps>
<!-- Stepwise plan; mark status. -->
<!-- Example:
1. [DONE] Identify old API usage
2. [NEXT] Refactor `auth.ts` to new API
3. [TODO] Update tests
-->
</next_steps>
</project_memory>
"#;
let summarization_prompt = vec![InputItem::Text {
text: SUMMARIZATION_PROMPT.to_string(),
}];
const SUMMARIZATION_PROMPT: &str = include_str!("../../../SUMMARY.md");
// Attempt to inject input into current task
if let Err(items) = sess.inject_input(summarization_prompt) {
run_task(sess.clone(), sub.id, items).await;
// only keep the last input item and clear the rest
let mut pending_input = sess.state.lock().unwrap().pending_input.clone();
pending_input.truncate(1);
sess.state.lock().unwrap().pending_input = pending_input;
if let Err(items) = sess.inject_input(vec![InputItem::Text {
text: "Start Summarization".to_string(),
}]) {
let task = AgentTask::compact(
sess.clone(),
sub.id,
items,
SUMMARIZATION_PROMPT.to_string(),
);
sess.set_task(task);
}
}
Op::Shutdown => {
@@ -963,7 +996,7 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
return;
}
let initial_input_for_turn = ResponseInputItem::from(input);
let initial_input_for_turn: ResponseInputItem = ResponseInputItem::from(input);
sess.record_conversation_items(&[initial_input_for_turn.clone().into()])
.await;
@@ -984,8 +1017,7 @@ async fn run_task(sess: Arc<Session>, sub_id: String, input: Vec<InputItem>) {
// conversation history on each turn. The rollout file, however, should
// only record the new items that originated in this turn so that it
// represents an append-only log without duplicates.
let turn_input: Vec<ResponseItem> =
[sess.state.lock().unwrap().history.contents(), pending_input].concat();
let turn_input: Vec<ResponseItem> = sess.turn_input_with_history(pending_input);
let turn_input_messages: Vec<String> = turn_input
.iter()
@@ -1311,6 +1343,88 @@ async fn try_run_turn(
}
}
async fn run_compact_task(
sess: Arc<Session>,
sub_id: String,
input: Vec<InputItem>,
compact_instructions: String,
) {
let start_event = Event {
id: sub_id.clone(),
msg: EventMsg::TaskStarted,
};
if sess.tx_event.send(start_event).await.is_err() {
return;
}
let initial_input_for_turn: ResponseInputItem = ResponseInputItem::from(input);
let turn_input: Vec<ResponseItem> =
sess.turn_input_with_history(vec![initial_input_for_turn.clone().into()]);
let prompt = Prompt {
input: turn_input,
user_instructions: None,
store: !sess.disable_response_storage,
extra_tools: HashMap::new(),
base_instructions_override: Some(compact_instructions.clone()),
};
let max_retries = sess.client.get_provider().stream_max_retries();
let mut retries = 0;
loop {
let attempt_result = drain_to_completed(&sess, &sub_id, &prompt).await;
match attempt_result {
Ok(()) => break,
Err(CodexErr::Interrupted) => return,
Err(e) => {
if retries < max_retries {
retries += 1;
let delay = backoff(retries);
sess.notify_background_event(
&sub_id,
format!(
"stream error: {e}; retrying {retries}/{max_retries} in {delay:?}"
),
)
.await;
tokio::time::sleep(delay).await;
continue;
} else {
let event = Event {
id: sub_id.clone(),
msg: EventMsg::Error(ErrorEvent {
message: e.to_string(),
}),
};
sess.send_event(event).await;
return;
}
}
}
}
sess.remove_task(&sub_id);
let event = Event {
id: sub_id.clone(),
msg: EventMsg::AgentMessage(AgentMessageEvent {
message: "Compact task completed".to_string(),
}),
};
sess.send_event(event).await;
let event = Event {
id: sub_id.clone(),
msg: EventMsg::TaskComplete(TaskCompleteEvent {
last_agent_message: None,
}),
};
sess.send_event(event).await;
let mut state = sess.state.lock().unwrap();
state.history.keep_last_messages(1);
}
async fn handle_response_item(
sess: &Session,
sub_id: &str,
@@ -1493,9 +1607,14 @@ async fn handle_container_exec_with_params(
call_id: String,
) -> ResponseInputItem {
// check if this was a patch, and apply it if so
match maybe_parse_apply_patch_verified(&params.command, &params.cwd) {
let apply_patch_exec = match maybe_parse_apply_patch_verified(&params.command, &params.cwd) {
MaybeApplyPatchVerified::Body(changes) => {
return apply_patch::apply_patch(sess, sub_id, call_id, changes).await;
match apply_patch::apply_patch(sess, &sub_id, &call_id, changes).await {
InternalApplyPatchInvocation::Output(item) => return item,
InternalApplyPatchInvocation::DelegateToExec(apply_patch_exec) => {
Some(apply_patch_exec)
}
}
}
MaybeApplyPatchVerified::CorrectnessError(parse_error) => {
// It looks like an invocation of `apply_patch`, but we
@@ -1511,20 +1630,67 @@ async fn handle_container_exec_with_params(
}
MaybeApplyPatchVerified::ShellParseError(error) => {
trace!("Failed to parse shell command, {error:?}");
None
}
MaybeApplyPatchVerified::NotApplyPatch => (),
}
// safety checks
let safety = {
let state = sess.state.lock().unwrap();
assess_command_safety(
&params.command,
sess.approval_policy,
&sess.sandbox_policy,
&state.approved_commands,
)
MaybeApplyPatchVerified::NotApplyPatch => None,
};
let (params, safety, command_for_display) = match &apply_patch_exec {
Some(ApplyPatchExec {
action: ApplyPatchAction { patch, cwd, .. },
user_explicitly_approved_this_action,
}) => {
let path_to_codex = std::env::current_exe()
.ok()
.map(|p| p.to_string_lossy().to_string());
let Some(path_to_codex) = path_to_codex else {
return ResponseInputItem::FunctionCallOutput {
call_id,
output: FunctionCallOutputPayload {
content: "failed to determine path to codex executable".to_string(),
success: None,
},
};
};
let params = ExecParams {
command: vec![
path_to_codex,
CODEX_APPLY_PATCH_ARG1.to_string(),
patch.clone(),
],
cwd: cwd.clone(),
timeout_ms: params.timeout_ms,
env: HashMap::new(),
};
let safety = if *user_explicitly_approved_this_action {
SafetyCheck::AutoApprove {
sandbox_type: SandboxType::None,
}
} else {
assess_safety_for_untrusted_command(sess.approval_policy, &sess.sandbox_policy)
};
(
params,
safety,
vec!["apply_patch".to_string(), patch.clone()],
)
}
None => {
let safety = {
let state = sess.state.lock().unwrap();
assess_command_safety(
&params.command,
sess.approval_policy,
&sess.sandbox_policy,
&state.approved_commands,
)
};
let command_for_display = params.command.clone();
(params, safety, command_for_display)
}
};
let sandbox_type = match safety {
SafetyCheck::AutoApprove { sandbox_type } => sandbox_type,
SafetyCheck::AskUser => {
@@ -1569,7 +1735,22 @@ async fn handle_container_exec_with_params(
}
};
sess.notify_exec_command_begin(&sub_id, &call_id, &params)
let exec_command_context = ExecCommandContext {
sub_id: sub_id.clone(),
call_id: call_id.clone(),
command_for_display: command_for_display.clone(),
cwd: params.cwd.clone(),
apply_patch: apply_patch_exec.map(
|ApplyPatchExec {
action,
user_explicitly_approved_this_action,
}| ApplyPatchCommandContext {
user_explicitly_approved_this_action,
changes: convert_apply_patch_to_protocol(&action),
},
),
};
sess.notify_exec_command_begin(exec_command_context.clone())
.await;
let params = maybe_run_with_user_profile(params, sess);
@@ -1579,6 +1760,11 @@ async fn handle_container_exec_with_params(
sess.ctrl_c.clone(),
&sess.sandbox_policy,
&sess.codex_linux_sandbox_exe,
Some(StdoutStream {
sub_id: sub_id.clone(),
call_id: call_id.clone(),
tx_event: sess.tx_event.clone(),
}),
)
.await;
@@ -1591,8 +1777,15 @@ async fn handle_container_exec_with_params(
duration,
} = output;
sess.notify_exec_command_end(&sub_id, &call_id, &stdout, &stderr, exit_code)
.await;
sess.notify_exec_command_end(
&sub_id,
&call_id,
&stdout,
&stderr,
exit_code,
exec_command_context.apply_patch.is_some(),
)
.await;
let is_success = exit_code == 0;
let content = format_exec_output(
@@ -1610,7 +1803,7 @@ async fn handle_container_exec_with_params(
}
}
Err(CodexErr::Sandbox(error)) => {
handle_sandbox_error(error, sandbox_type, params, sess, sub_id, call_id).await
handle_sandbox_error(params, exec_command_context, error, sandbox_type, sess).await
}
Err(e) => {
// Handle non-sandbox errors
@@ -1626,13 +1819,17 @@ async fn handle_container_exec_with_params(
}
async fn handle_sandbox_error(
params: ExecParams,
exec_command_context: ExecCommandContext,
error: SandboxErr,
sandbox_type: SandboxType,
params: ExecParams,
sess: &Session,
sub_id: String,
call_id: String,
) -> ResponseInputItem {
let call_id = exec_command_context.call_id.clone();
let sub_id = exec_command_context.sub_id.clone();
let cwd = exec_command_context.cwd.clone();
let is_apply_patch = exec_command_context.apply_patch.is_some();
// Early out if the user never wants to be asked for approval; just return to the model immediately
if sess.approval_policy == AskForApproval::Never {
return ResponseInputItem::FunctionCallOutput {
@@ -1662,7 +1859,7 @@ async fn handle_sandbox_error(
sub_id.clone(),
call_id.clone(),
params.command.clone(),
params.cwd.clone(),
cwd.clone(),
Some("command failed; retry without sandbox?".to_string()),
)
.await;
@@ -1678,8 +1875,7 @@ async fn handle_sandbox_error(
sess.notify_background_event(&sub_id, "retrying command without sandbox")
.await;
sess.notify_exec_command_begin(&sub_id, &call_id, &params)
.await;
sess.notify_exec_command_begin(exec_command_context).await;
// This is an escalated retry; the policy will not be
// examined and the sandbox has been set to `None`.
@@ -1689,6 +1885,11 @@ async fn handle_sandbox_error(
sess.ctrl_c.clone(),
&sess.sandbox_policy,
&sess.codex_linux_sandbox_exe,
Some(StdoutStream {
sub_id: sub_id.clone(),
call_id: call_id.clone(),
tx_event: sess.tx_event.clone(),
}),
)
.await;
@@ -1701,8 +1902,15 @@ async fn handle_sandbox_error(
duration,
} = retry_output;
sess.notify_exec_command_end(&sub_id, &call_id, &stdout, &stderr, exit_code)
.await;
sess.notify_exec_command_end(
&sub_id,
&call_id,
&stdout,
&stderr,
exit_code,
is_apply_patch,
)
.await;
let is_success = exit_code == 0;
let content = format_exec_output(
@@ -1792,3 +2000,45 @@ fn get_last_assistant_message_from_turn(responses: &[ResponseItem]) -> Option<St
}
})
}
async fn drain_to_completed(sess: &Session, sub_id: &str, prompt: &Prompt) -> CodexResult<()> {
let mut stream = sess.client.clone().stream(prompt).await?;
loop {
let maybe_event = stream.next().await;
let Some(event) = maybe_event else {
return Err(CodexErr::Stream(
"stream closed before response.completed".into(),
));
};
match event {
Ok(ResponseEvent::OutputItemDone(item)) => {
// Record only to in-memory conversation history; avoid state snapshot.
let mut state = sess.state.lock().unwrap();
state.history.record_items(std::slice::from_ref(&item));
}
Ok(ResponseEvent::Completed {
response_id: _,
token_usage,
}) => {
let token_usage = match token_usage {
Some(usage) => usage,
None => {
return Err(CodexErr::Stream(
"token_usage was None in ResponseEvent::Completed".into(),
));
}
};
sess.tx_event
.send(Event {
id: sub_id.to_string(),
msg: EventMsg::TokenCount(token_usage),
})
.await
.ok();
return Ok(());
}
Ok(_) => continue,
Err(e) => return Err(e),
}
}
}

View File

@@ -26,7 +26,7 @@ pub struct CodexConversation {
/// that callers can surface the information to the UI.
pub async fn init_codex(config: Config) -> anyhow::Result<CodexConversation> {
let ctrl_c = notify_on_sigint();
let auth = load_auth(&config.codex_home)?;
let auth = load_auth(&config.codex_home, true)?;
let CodexSpawnOk {
codex,
init_id,

View File

@@ -146,6 +146,9 @@ pub struct Config {
/// Include an experimental plan tool that the model can use to update its current plan and status of each step.
pub include_plan_tool: bool,
/// The value for the `originator` header included with Responses API requests.
pub internal_originator: Option<String>,
}
impl Config {
@@ -336,6 +339,9 @@ pub struct ConfigToml {
/// Experimental path to a file whose contents replace the built-in BASE_INSTRUCTIONS.
pub experimental_instructions_file: Option<PathBuf>,
/// The value for the `originator` header included with Responses API requests.
pub internal_originator: Option<String>,
}
impl ConfigToml {
@@ -350,6 +356,7 @@ impl ConfigToml {
Some(s) => SandboxPolicy::WorkspaceWrite {
writable_roots: s.writable_roots.clone(),
network_access: s.network_access,
include_default_writable_roots: true,
},
None => SandboxPolicy::new_workspace_write_policy(),
},
@@ -529,6 +536,7 @@ impl Config {
experimental_resume,
include_plan_tool: include_plan_tool.unwrap_or(false),
internal_originator: cfg.internal_originator,
};
Ok(config)
}
@@ -720,6 +728,7 @@ writable_roots = [
SandboxPolicy::WorkspaceWrite {
writable_roots: vec![PathBuf::from("/tmp")],
network_access: false,
include_default_writable_roots: true,
},
sandbox_workspace_write_cfg.derive_sandbox_policy(sandbox_mode_override)
);
@@ -887,6 +896,7 @@ disable_response_storage = true
experimental_resume: None,
base_instructions: None,
include_plan_tool: false,
internal_originator: None,
},
o3_profile_config
);
@@ -936,6 +946,7 @@ disable_response_storage = true
experimental_resume: None,
base_instructions: None,
include_plan_tool: false,
internal_originator: None,
};
assert_eq!(expected_gpt3_profile_config, gpt3_profile_config);
@@ -1000,6 +1011,7 @@ disable_response_storage = true
experimental_resume: None,
base_instructions: None,
include_plan_tool: false,
internal_originator: None,
};
assert_eq!(expected_zdr_profile_config, zdr_profile_config);

View File

@@ -30,6 +30,34 @@ impl ConversationHistory {
}
}
}
pub(crate) fn keep_last_messages(&mut self, n: usize) {
if n == 0 {
self.items.clear();
return;
}
// Collect the last N message items (assistant/user), newest to oldest.
let mut kept: Vec<ResponseItem> = Vec::with_capacity(n);
for item in self.items.iter().rev() {
if let ResponseItem::Message { role, content, .. } = item {
kept.push(ResponseItem::Message {
// we need to remove the id or the model will complain that messages are sent without
// their reasonings
id: None,
role: role.clone(),
content: content.clone(),
});
if kept.len() == n {
break;
}
}
}
// Preserve chronological order (oldest to newest) within the kept slice.
kept.reverse();
self.items = kept;
}
}
/// Anything that is not a system message or "reasoning" message is considered

View File

@@ -6,23 +6,29 @@ use std::io;
use std::path::Path;
use std::path::PathBuf;
use std::process::ExitStatus;
use std::process::Stdio;
use std::sync::Arc;
use std::time::Duration;
use std::time::Instant;
use async_channel::Sender;
use tokio::io::AsyncRead;
use tokio::io::AsyncReadExt;
use tokio::io::BufReader;
use tokio::process::Child;
use tokio::process::Command;
use tokio::sync::Notify;
use tracing::trace;
use crate::error::CodexErr;
use crate::error::Result;
use crate::error::SandboxErr;
use crate::protocol::Event;
use crate::protocol::EventMsg;
use crate::protocol::ExecCommandOutputDeltaEvent;
use crate::protocol::ExecOutputStream;
use crate::protocol::SandboxPolicy;
use crate::seatbelt::spawn_command_under_seatbelt;
use crate::spawn::StdioPolicy;
use crate::spawn::spawn_child_async;
use serde_bytes::ByteBuf;
// Maximum we send for each stream, which is either:
// - 10KiB OR
@@ -37,24 +43,6 @@ const DEFAULT_TIMEOUT_MS: u64 = 10_000;
const SIGKILL_CODE: i32 = 9;
const TIMEOUT_CODE: i32 = 64;
const MACOS_SEATBELT_BASE_POLICY: &str = include_str!("seatbelt_base_policy.sbpl");
/// When working with `sandbox-exec`, only consider `sandbox-exec` in `/usr/bin`
/// to defend against an attacker trying to inject a malicious version on the
/// PATH. If /usr/bin/sandbox-exec has been tampered with, then the attacker
/// already has root access.
const MACOS_PATH_TO_SEATBELT_EXECUTABLE: &str = "/usr/bin/sandbox-exec";
/// Experimental environment variable that will be set to some non-empty value
/// if both of the following are true:
///
/// 1. The process was spawned by Codex as part of a shell tool call.
/// 2. SandboxPolicy.has_full_network_access() was false for the tool call.
///
/// We may try to have just one environment variable for all sandboxing
/// attributes, so this may change in the future.
pub const CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR: &str = "CODEX_SANDBOX_NETWORK_DISABLED";
#[derive(Debug, Clone)]
pub struct ExecParams {
pub command: Vec<String>,
@@ -74,18 +62,26 @@ pub enum SandboxType {
LinuxSeccomp,
}
#[derive(Clone)]
pub struct StdoutStream {
pub sub_id: String,
pub call_id: String,
pub tx_event: Sender<Event>,
}
pub async fn process_exec_tool_call(
params: ExecParams,
sandbox_type: SandboxType,
ctrl_c: Arc<Notify>,
sandbox_policy: &SandboxPolicy,
codex_linux_sandbox_exe: &Option<PathBuf>,
stdout_stream: Option<StdoutStream>,
) -> Result<ExecToolCallOutput> {
let start = Instant::now();
let raw_output_result: std::result::Result<RawExecToolCallOutput, CodexErr> = match sandbox_type
{
SandboxType::None => exec(params, sandbox_policy, ctrl_c).await,
SandboxType::None => exec(params, sandbox_policy, ctrl_c, stdout_stream.clone()).await,
SandboxType::MacosSeatbelt => {
let ExecParams {
command,
@@ -101,7 +97,7 @@ pub async fn process_exec_tool_call(
env,
)
.await?;
consume_truncated_output(child, ctrl_c, timeout_ms).await
consume_truncated_output(child, ctrl_c, timeout_ms, stdout_stream.clone()).await
}
SandboxType::LinuxSeccomp => {
let ExecParams {
@@ -124,7 +120,7 @@ pub async fn process_exec_tool_call(
)
.await?;
consume_truncated_output(child, ctrl_c, timeout_ms).await
consume_truncated_output(child, ctrl_c, timeout_ms, stdout_stream).await
}
};
let duration = start.elapsed();
@@ -168,27 +164,6 @@ pub async fn process_exec_tool_call(
}
}
pub async fn spawn_command_under_seatbelt(
command: Vec<String>,
sandbox_policy: &SandboxPolicy,
cwd: PathBuf,
stdio_policy: StdioPolicy,
env: HashMap<String, String>,
) -> std::io::Result<Child> {
let args = create_seatbelt_command_args(command, sandbox_policy, &cwd);
let arg0 = None;
spawn_child_async(
PathBuf::from(MACOS_PATH_TO_SEATBELT_EXECUTABLE),
args,
arg0,
cwd,
sandbox_policy,
stdio_policy,
env,
)
.await
}
/// Spawn a shell tool command under the Linux Landlock+seccomp sandbox helper
/// (codex-linux-sandbox).
///
@@ -248,65 +223,6 @@ fn create_linux_sandbox_command_args(
linux_cmd
}
fn create_seatbelt_command_args(
command: Vec<String>,
sandbox_policy: &SandboxPolicy,
cwd: &Path,
) -> Vec<String> {
let (file_write_policy, extra_cli_args) = {
if sandbox_policy.has_full_disk_write_access() {
// Allegedly, this is more permissive than `(allow file-write*)`.
(
r#"(allow file-write* (regex #"^/"))"#.to_string(),
Vec::<String>::new(),
)
} else {
let writable_roots = sandbox_policy.get_writable_roots_with_cwd(cwd);
let (writable_folder_policies, cli_args): (Vec<String>, Vec<String>) = writable_roots
.iter()
.enumerate()
.map(|(index, root)| {
let param_name = format!("WRITABLE_ROOT_{index}");
let policy: String = format!("(subpath (param \"{param_name}\"))");
let cli_arg = format!("-D{param_name}={}", root.to_string_lossy());
(policy, cli_arg)
})
.unzip();
if writable_folder_policies.is_empty() {
("".to_string(), Vec::<String>::new())
} else {
let file_write_policy = format!(
"(allow file-write*\n{}\n)",
writable_folder_policies.join(" ")
);
(file_write_policy, cli_args)
}
}
};
let file_read_policy = if sandbox_policy.has_full_disk_read_access() {
"; allow read-only file operations\n(allow file-read*)"
} else {
""
};
// TODO(mbolin): apply_patch calls must also honor the SandboxPolicy.
let network_policy = if sandbox_policy.has_full_network_access() {
"(allow network-outbound)\n(allow network-inbound)\n(allow system-socket)"
} else {
""
};
let full_policy = format!(
"{MACOS_SEATBELT_BASE_POLICY}\n{file_read_policy}\n{file_write_policy}\n{network_policy}"
);
let mut seatbelt_args: Vec<String> = vec!["-p".to_string(), full_policy];
seatbelt_args.extend(extra_cli_args);
seatbelt_args.push("--".to_string());
seatbelt_args.extend(command);
seatbelt_args
}
#[derive(Debug)]
pub struct RawExecToolCallOutput {
pub exit_status: ExitStatus,
@@ -331,6 +247,7 @@ async fn exec(
}: ExecParams,
sandbox_policy: &SandboxPolicy,
ctrl_c: Arc<Notify>,
stdout_stream: Option<StdoutStream>,
) -> Result<RawExecToolCallOutput> {
let (program, args) = command.split_first().ok_or_else(|| {
CodexErr::Io(io::Error::new(
@@ -349,91 +266,7 @@ async fn exec(
env,
)
.await?;
consume_truncated_output(child, ctrl_c, timeout_ms).await
}
#[derive(Debug, Clone, Copy)]
pub enum StdioPolicy {
RedirectForShellTool,
Inherit,
}
/// Spawns the appropriate child process for the ExecParams and SandboxPolicy,
/// ensuring the args and environment variables used to create the `Command`
/// (and `Child`) honor the configuration.
///
/// For now, we take `SandboxPolicy` as a parameter to spawn_child() because
/// we need to determine whether to set the
/// `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` environment variable.
async fn spawn_child_async(
program: PathBuf,
args: Vec<String>,
#[cfg_attr(not(unix), allow(unused_variables))] arg0: Option<&str>,
cwd: PathBuf,
sandbox_policy: &SandboxPolicy,
stdio_policy: StdioPolicy,
env: HashMap<String, String>,
) -> std::io::Result<Child> {
trace!(
"spawn_child_async: {program:?} {args:?} {arg0:?} {cwd:?} {sandbox_policy:?} {stdio_policy:?} {env:?}"
);
let mut cmd = Command::new(&program);
#[cfg(unix)]
cmd.arg0(arg0.map_or_else(|| program.to_string_lossy().to_string(), String::from));
cmd.args(args);
cmd.current_dir(cwd);
cmd.env_clear();
cmd.envs(env);
if !sandbox_policy.has_full_network_access() {
cmd.env(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR, "1");
}
// If this Codex process dies (including being killed via SIGKILL), we want
// any child processes that were spawned as part of a `"shell"` tool call
// to also be terminated.
// This relies on prctl(2), so it only works on Linux.
#[cfg(target_os = "linux")]
unsafe {
cmd.pre_exec(|| {
// This prctl call effectively requests, "deliver SIGTERM when my
// current parent dies."
if libc::prctl(libc::PR_SET_PDEATHSIG, libc::SIGTERM) == -1 {
return Err(io::Error::last_os_error());
}
// Though if there was a race condition and this pre_exec() block is
// run _after_ the parent (i.e., the Codex process) has already
// exited, then the parent is the _init_ process (which will never
// die), so we should just terminate the child process now.
if libc::getppid() == 1 {
libc::raise(libc::SIGTERM);
}
Ok(())
});
}
match stdio_policy {
StdioPolicy::RedirectForShellTool => {
// Do not create a file descriptor for stdin because otherwise some
// commands may hang forever waiting for input. For example, ripgrep has
// a heuristic where it may try to read from stdin as explained here:
// https://github.com/BurntSushi/ripgrep/blob/e2362d4d5185d02fa857bf381e7bd52e66fafc73/crates/core/flags/hiargs.rs#L1101-L1103
cmd.stdin(Stdio::null());
cmd.stdout(Stdio::piped()).stderr(Stdio::piped());
}
StdioPolicy::Inherit => {
// Inherit stdin, stdout, and stderr from the parent process.
cmd.stdin(Stdio::inherit())
.stdout(Stdio::inherit())
.stderr(Stdio::inherit());
}
}
cmd.kill_on_drop(true).spawn()
consume_truncated_output(child, ctrl_c, timeout_ms, stdout_stream).await
}
/// Consumes the output of a child process, truncating it so it is suitable for
@@ -442,6 +275,7 @@ pub(crate) async fn consume_truncated_output(
mut child: Child,
ctrl_c: Arc<Notify>,
timeout_ms: Option<u64>,
stdout_stream: Option<StdoutStream>,
) -> Result<RawExecToolCallOutput> {
// Both stdout and stderr were configured with `Stdio::piped()`
// above, therefore `take()` should normally return `Some`. If it doesn't
@@ -462,11 +296,15 @@ pub(crate) async fn consume_truncated_output(
BufReader::new(stdout_reader),
MAX_STREAM_OUTPUT,
MAX_STREAM_OUTPUT_LINES,
stdout_stream.clone(),
false,
));
let stderr_handle = tokio::spawn(read_capped(
BufReader::new(stderr_reader),
MAX_STREAM_OUTPUT,
MAX_STREAM_OUTPUT_LINES,
stdout_stream.clone(),
true,
));
let interrupted = ctrl_c.notified();
@@ -500,10 +338,12 @@ pub(crate) async fn consume_truncated_output(
})
}
async fn read_capped<R: AsyncRead + Unpin>(
async fn read_capped<R: AsyncRead + Unpin + Send + 'static>(
mut reader: R,
max_output: usize,
max_lines: usize,
stream: Option<StdoutStream>,
is_stderr: bool,
) -> io::Result<Vec<u8>> {
let mut buf = Vec::with_capacity(max_output.min(8 * 1024));
let mut tmp = [0u8; 8192];
@@ -517,6 +357,25 @@ async fn read_capped<R: AsyncRead + Unpin>(
break;
}
if let Some(stream) = &stream {
let chunk = tmp[..n].to_vec();
let msg = EventMsg::ExecCommandOutputDelta(ExecCommandOutputDeltaEvent {
call_id: stream.call_id.clone(),
stream: if is_stderr {
ExecOutputStream::Stderr
} else {
ExecOutputStream::Stdout
},
chunk: ByteBuf::from(chunk),
});
let event = Event {
id: stream.sub_id.clone(),
msg,
};
#[allow(clippy::let_unit_value)]
let _ = stream.tx_event.send(event).await;
}
// Copy into the buffer only while we still have byte and line budget.
if remaining_bytes > 0 && remaining_lines > 0 {
let mut copy_len = 0;

View File

@@ -111,9 +111,14 @@ mod tests {
// Helper function to create a test git repository
async fn create_test_git_repo(temp_dir: &TempDir) -> PathBuf {
let repo_path = temp_dir.path().to_path_buf();
let envs = vec![
("GIT_CONFIG_GLOBAL", "/dev/null"),
("GIT_CONFIG_NOSYSTEM", "1"),
];
// Initialize git repo
Command::new("git")
.envs(envs.clone())
.args(["init"])
.current_dir(&repo_path)
.output()
@@ -122,6 +127,7 @@ mod tests {
// Configure git user (required for commits)
Command::new("git")
.envs(envs.clone())
.args(["config", "user.name", "Test User"])
.current_dir(&repo_path)
.output()
@@ -129,6 +135,7 @@ mod tests {
.expect("Failed to set git user name");
Command::new("git")
.envs(envs.clone())
.args(["config", "user.email", "test@example.com"])
.current_dir(&repo_path)
.output()
@@ -140,6 +147,7 @@ mod tests {
fs::write(&test_file, "test content").expect("Failed to write test file");
Command::new("git")
.envs(envs.clone())
.args(["add", "."])
.current_dir(&repo_path)
.output()
@@ -147,6 +155,7 @@ mod tests {
.expect("Failed to add files");
Command::new("git")
.envs(envs.clone())
.args(["commit", "-m", "Initial commit"])
.current_dir(&repo_path)
.output()

View File

@@ -39,8 +39,11 @@ mod project_doc;
pub mod protocol;
mod rollout;
mod safety;
pub mod seatbelt;
pub mod shell;
pub mod spawn;
mod user_notification;
pub mod util;
pub use apply_patch::CODEX_APPLY_PATCH_ARG1;
pub use client_common::model_supports_reasoning_summaries;

View File

@@ -12,10 +12,6 @@ use std::env::VarError;
use std::time::Duration;
use crate::error::EnvVarError;
/// Value for the `OpenAI-Originator` header that is sent with requests to
/// OpenAI.
const OPENAI_ORIGINATOR_HEADER: &str = "codex_cli_rs";
const DEFAULT_STREAM_IDLE_TIMEOUT_MS: u64 = 300_000;
const DEFAULT_STREAM_MAX_RETRIES: u64 = 10;
const DEFAULT_REQUEST_MAX_RETRIES: u64 = 4;
@@ -229,15 +225,9 @@ pub fn built_in_model_providers() -> HashMap<String, ModelProviderInfo> {
wire_api: WireApi::Responses,
query_params: None,
http_headers: Some(
[
(
"originator".to_string(),
OPENAI_ORIGINATOR_HEADER.to_string(),
),
("version".to_string(), env!("CARGO_PKG_VERSION").to_string()),
]
.into_iter()
.collect(),
[("version".to_string(), env!("CARGO_PKG_VERSION").to_string())]
.into_iter()
.collect(),
),
env_http_headers: Some(
[

View File

@@ -13,6 +13,7 @@ use std::time::Duration;
use mcp_types::CallToolResult;
use serde::Deserialize;
use serde::Serialize;
use serde_bytes::ByteBuf;
use strum_macros::Display;
use uuid::Uuid;
@@ -124,7 +125,7 @@ pub enum Op {
/// Request the agent to summarize the current conversation context.
/// The agent will use its existing context (either conversation history or previous response id)
/// to generate a summary which will be returned as an AgentMessage event.
SummarizeContext,
Compact,
/// Request to shut down codex instance.
Shutdown,
}
@@ -179,9 +180,29 @@ pub enum SandboxPolicy {
/// default.
#[serde(default)]
network_access: bool,
/// When set to `true`, will include defaults like the current working
/// directory and TMPDIR (on macOS). When `false`, only `writable_roots`
/// are used. (Mainly used for testing.)
#[serde(default = "default_true")]
include_default_writable_roots: bool,
},
}
/// A writable root path accompanied by a list of subpaths that should remain
/// readonly even when the root is writable. This is primarily used to ensure
/// toplevel VCS metadata directories (e.g. `.git`) under a writable root are
/// not modified by the agent.
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct WritableRoot {
pub root: PathBuf,
pub read_only_subpaths: Vec<PathBuf>,
}
fn default_true() -> bool {
true
}
impl FromStr for SandboxPolicy {
type Err = serde_json::Error;
@@ -203,6 +224,7 @@ impl SandboxPolicy {
SandboxPolicy::WorkspaceWrite {
writable_roots: vec![],
network_access: false,
include_default_writable_roots: true,
}
}
@@ -228,27 +250,51 @@ impl SandboxPolicy {
}
}
/// Returns the list of writable roots that should be passed down to the
/// Landlock rules installer, tailored to the current working directory.
pub fn get_writable_roots_with_cwd(&self, cwd: &Path) -> Vec<PathBuf> {
/// Returns the list of writable roots (tailored to the current working
/// directory) together with subpaths that should remain readonly under
/// each writable root.
pub fn get_writable_roots_with_cwd(&self, cwd: &Path) -> Vec<WritableRoot> {
match self {
SandboxPolicy::DangerFullAccess => Vec::new(),
SandboxPolicy::ReadOnly => Vec::new(),
SandboxPolicy::WorkspaceWrite { writable_roots, .. } => {
let mut roots = writable_roots.clone();
roots.push(cwd.to_path_buf());
SandboxPolicy::WorkspaceWrite {
writable_roots,
include_default_writable_roots,
..
} => {
// Start from explicitly configured writable roots.
let mut roots: Vec<PathBuf> = writable_roots.clone();
// Also include the per-user tmp dir on macOS.
// Note this is added dynamically rather than storing it in
// writable_roots because writable_roots contains only static
// values deserialized from the config file.
if cfg!(target_os = "macos") {
if let Some(tmpdir) = std::env::var_os("TMPDIR") {
roots.push(PathBuf::from(tmpdir));
// Optionally include defaults (cwd and TMPDIR on macOS).
if *include_default_writable_roots {
roots.push(cwd.to_path_buf());
// Also include the per-user tmp dir on macOS.
// Note this is added dynamically rather than storing it in
// `writable_roots` because `writable_roots` contains only static
// values deserialized from the config file.
if cfg!(target_os = "macos") {
if let Some(tmpdir) = std::env::var_os("TMPDIR") {
roots.push(PathBuf::from(tmpdir));
}
}
}
// For each root, compute subpaths that should remain read-only.
roots
.into_iter()
.map(|writable_root| {
let mut subpaths = Vec::new();
let top_level_git = writable_root.join(".git");
if top_level_git.is_dir() {
subpaths.push(top_level_git);
}
WritableRoot {
root: writable_root,
read_only_subpaths: subpaths,
}
})
.collect()
}
}
}
@@ -323,6 +369,9 @@ pub enum EventMsg {
/// Notification that the server is about to execute a command.
ExecCommandBegin(ExecCommandBeginEvent),
/// Incremental chunk of output from a running command.
ExecCommandOutputDelta(ExecCommandOutputDeltaEvent),
ExecCommandEnd(ExecCommandEndEvent),
ExecApprovalRequest(ExecApprovalRequestEvent),
@@ -476,6 +525,24 @@ pub struct ExecCommandEndEvent {
pub exit_code: i32,
}
#[derive(Debug, Clone, Deserialize, Serialize)]
#[serde(rename_all = "snake_case")]
pub enum ExecOutputStream {
Stdout,
Stderr,
}
#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct ExecCommandOutputDeltaEvent {
/// Identifier for the ExecCommandBegin that produced this chunk.
pub call_id: String,
/// Which stream produced this chunk.
pub stream: ExecOutputStream,
/// Raw bytes from the stream (may not be valid UTF-8).
#[serde(with = "serde_bytes")]
pub chunk: ByteBuf,
}
#[derive(Debug, Clone, Deserialize, Serialize)]
pub struct ExecApprovalRequestEvent {
/// Identifier for the associated exec call, if available.

View File

@@ -41,11 +41,13 @@ pub fn assess_patch_safety(
}
}
if is_write_patch_constrained_to_writable_paths(action, writable_roots, cwd) {
SafetyCheck::AutoApprove {
sandbox_type: SandboxType::None,
}
} else if policy == AskForApproval::OnFailure {
// Even though the patch *appears* to be constrained to writable paths, it
// is possible that paths in the patch are hard links to files outside the
// writable roots, so we should still run `apply_patch` in a sandbox in that
// case.
if is_write_patch_constrained_to_writable_paths(action, writable_roots, cwd)
|| policy == AskForApproval::OnFailure
{
// Only autoapprove when we can actually enforce a sandbox. Otherwise
// fall back to asking the user because the patch may touch arbitrary
// paths outside the project.
@@ -75,9 +77,6 @@ pub fn assess_command_safety(
sandbox_policy: &SandboxPolicy,
approved: &HashSet<Vec<String>>,
) -> SafetyCheck {
use AskForApproval::*;
use SandboxPolicy::*;
// A command is "trusted" because either:
// - it belongs to a set of commands we consider "safe" by default, or
// - the user has explicitly approved the command for this session
@@ -97,6 +96,16 @@ pub fn assess_command_safety(
};
}
assess_safety_for_untrusted_command(approval_policy, sandbox_policy)
}
pub(crate) fn assess_safety_for_untrusted_command(
approval_policy: AskForApproval,
sandbox_policy: &SandboxPolicy,
) -> SafetyCheck {
use AskForApproval::*;
use SandboxPolicy::*;
match (approval_policy, sandbox_policy) {
(UnlessTrusted, _) => {
// Even though the user may have opted into DangerFullAccess,

View File

@@ -0,0 +1,312 @@
use std::collections::HashMap;
use std::path::Path;
use std::path::PathBuf;
use tokio::process::Child;
use crate::protocol::SandboxPolicy;
use crate::spawn::CODEX_SANDBOX_ENV_VAR;
use crate::spawn::StdioPolicy;
use crate::spawn::spawn_child_async;
const MACOS_SEATBELT_BASE_POLICY: &str = include_str!("seatbelt_base_policy.sbpl");
/// When working with `sandbox-exec`, only consider `sandbox-exec` in `/usr/bin`
/// to defend against an attacker trying to inject a malicious version on the
/// PATH. If /usr/bin/sandbox-exec has been tampered with, then the attacker
/// already has root access.
const MACOS_PATH_TO_SEATBELT_EXECUTABLE: &str = "/usr/bin/sandbox-exec";
pub async fn spawn_command_under_seatbelt(
command: Vec<String>,
sandbox_policy: &SandboxPolicy,
cwd: PathBuf,
stdio_policy: StdioPolicy,
mut env: HashMap<String, String>,
) -> std::io::Result<Child> {
let args = create_seatbelt_command_args(command, sandbox_policy, &cwd);
let arg0 = None;
env.insert(CODEX_SANDBOX_ENV_VAR.to_string(), "seatbelt".to_string());
spawn_child_async(
PathBuf::from(MACOS_PATH_TO_SEATBELT_EXECUTABLE),
args,
arg0,
cwd,
sandbox_policy,
stdio_policy,
env,
)
.await
}
fn create_seatbelt_command_args(
command: Vec<String>,
sandbox_policy: &SandboxPolicy,
cwd: &Path,
) -> Vec<String> {
let (file_write_policy, extra_cli_args) = {
if sandbox_policy.has_full_disk_write_access() {
// Allegedly, this is more permissive than `(allow file-write*)`.
(
r#"(allow file-write* (regex #"^/"))"#.to_string(),
Vec::<String>::new(),
)
} else {
let writable_roots = sandbox_policy.get_writable_roots_with_cwd(cwd);
let mut writable_folder_policies: Vec<String> = Vec::new();
let mut cli_args: Vec<String> = Vec::new();
for (index, wr) in writable_roots.iter().enumerate() {
// Canonicalize to avoid mismatches like /var vs /private/var on macOS.
let canonical_root = wr.root.canonicalize().unwrap_or_else(|_| wr.root.clone());
let root_param = format!("WRITABLE_ROOT_{index}");
cli_args.push(format!(
"-D{root_param}={}",
canonical_root.to_string_lossy()
));
if wr.read_only_subpaths.is_empty() {
writable_folder_policies.push(format!("(subpath (param \"{root_param}\"))"));
} else {
// Add parameters for each read-only subpath and generate
// the `(require-not ...)` clauses.
let mut require_parts: Vec<String> = Vec::new();
require_parts.push(format!("(subpath (param \"{root_param}\"))"));
for (subpath_index, ro) in wr.read_only_subpaths.iter().enumerate() {
let canonical_ro = ro.canonicalize().unwrap_or_else(|_| ro.clone());
let ro_param = format!("WRITABLE_ROOT_{index}_RO_{subpath_index}");
cli_args.push(format!("-D{ro_param}={}", canonical_ro.to_string_lossy()));
require_parts
.push(format!("(require-not (subpath (param \"{ro_param}\")))"));
}
let policy_component = format!("(require-all {} )", require_parts.join(" "));
writable_folder_policies.push(policy_component);
}
}
if writable_folder_policies.is_empty() {
("".to_string(), Vec::<String>::new())
} else {
let file_write_policy = format!(
"(allow file-write*\n{}\n)",
writable_folder_policies.join(" ")
);
(file_write_policy, cli_args)
}
}
};
let file_read_policy = if sandbox_policy.has_full_disk_read_access() {
"; allow read-only file operations\n(allow file-read*)"
} else {
""
};
// TODO(mbolin): apply_patch calls must also honor the SandboxPolicy.
let network_policy = if sandbox_policy.has_full_network_access() {
"(allow network-outbound)\n(allow network-inbound)\n(allow system-socket)"
} else {
""
};
let full_policy = format!(
"{MACOS_SEATBELT_BASE_POLICY}\n{file_read_policy}\n{file_write_policy}\n{network_policy}"
);
let mut seatbelt_args: Vec<String> = vec!["-p".to_string(), full_policy];
seatbelt_args.extend(extra_cli_args);
seatbelt_args.push("--".to_string());
seatbelt_args.extend(command);
seatbelt_args
}
#[cfg(test)]
mod tests {
#![expect(clippy::expect_used)]
use super::MACOS_SEATBELT_BASE_POLICY;
use super::create_seatbelt_command_args;
use crate::protocol::SandboxPolicy;
use pretty_assertions::assert_eq;
use std::fs;
use std::path::Path;
use std::path::PathBuf;
use tempfile::TempDir;
#[test]
fn create_seatbelt_args_with_read_only_git_subpath() {
// Create a temporary workspace with two writable roots: one containing
// a top-level .git directory and one without it.
let tmp = TempDir::new().expect("tempdir");
let PopulatedTmp {
root_with_git,
root_without_git,
root_with_git_canon,
root_with_git_git_canon,
root_without_git_canon,
} = populate_tmpdir(tmp.path());
// Build a policy that only includes the two test roots as writable and
// does not automatically include defaults like cwd or TMPDIR.
let policy = SandboxPolicy::WorkspaceWrite {
writable_roots: vec![root_with_git.clone(), root_without_git.clone()],
network_access: false,
include_default_writable_roots: false,
};
let args = create_seatbelt_command_args(
vec!["/bin/echo".to_string(), "hello".to_string()],
&policy,
tmp.path(),
);
// Build the expected policy text using a raw string for readability.
// Note that the policy includes:
// - the base policy,
// - read-only access to the filesystem,
// - write access to WRITABLE_ROOT_0 (but not its .git) and WRITABLE_ROOT_1.
let expected_policy = format!(
r#"{MACOS_SEATBELT_BASE_POLICY}
; allow read-only file operations
(allow file-read*)
(allow file-write*
(require-all (subpath (param "WRITABLE_ROOT_0")) (require-not (subpath (param "WRITABLE_ROOT_0_RO_0"))) ) (subpath (param "WRITABLE_ROOT_1"))
)
"#,
);
let expected_args = vec![
"-p".to_string(),
expected_policy,
format!(
"-DWRITABLE_ROOT_0={}",
root_with_git_canon.to_string_lossy()
),
format!(
"-DWRITABLE_ROOT_0_RO_0={}",
root_with_git_git_canon.to_string_lossy()
),
format!(
"-DWRITABLE_ROOT_1={}",
root_without_git_canon.to_string_lossy()
),
"--".to_string(),
"/bin/echo".to_string(),
"hello".to_string(),
];
assert_eq!(args, expected_args);
}
#[test]
fn create_seatbelt_args_for_cwd_as_git_repo() {
// Create a temporary workspace with two writable roots: one containing
// a top-level .git directory and one without it.
let tmp = TempDir::new().expect("tempdir");
let PopulatedTmp {
root_with_git,
root_with_git_canon,
root_with_git_git_canon,
..
} = populate_tmpdir(tmp.path());
// Build a policy that does not specify any writable_roots, but does
// use the default ones (cwd and TMPDIR) and verifies the `.git` check
// is done properly for cwd.
let policy = SandboxPolicy::WorkspaceWrite {
writable_roots: vec![],
network_access: false,
include_default_writable_roots: true,
};
let args = create_seatbelt_command_args(
vec!["/bin/echo".to_string(), "hello".to_string()],
&policy,
root_with_git.as_path(),
);
let tmpdir_env_var = if cfg!(target_os = "macos") {
std::env::var("TMPDIR")
.ok()
.map(PathBuf::from)
.and_then(|p| p.canonicalize().ok())
.map(|p| p.to_string_lossy().to_string())
} else {
None
};
let tempdir_policy_entry = if tmpdir_env_var.is_some() {
" (subpath (param \"WRITABLE_ROOT_1\"))"
} else {
""
};
// Build the expected policy text using a raw string for readability.
// Note that the policy includes:
// - the base policy,
// - read-only access to the filesystem,
// - write access to WRITABLE_ROOT_0 (but not its .git) and WRITABLE_ROOT_1.
let expected_policy = format!(
r#"{MACOS_SEATBELT_BASE_POLICY}
; allow read-only file operations
(allow file-read*)
(allow file-write*
(require-all (subpath (param "WRITABLE_ROOT_0")) (require-not (subpath (param "WRITABLE_ROOT_0_RO_0"))) ){tempdir_policy_entry}
)
"#,
);
let mut expected_args = vec![
"-p".to_string(),
expected_policy,
format!(
"-DWRITABLE_ROOT_0={}",
root_with_git_canon.to_string_lossy()
),
format!(
"-DWRITABLE_ROOT_0_RO_0={}",
root_with_git_git_canon.to_string_lossy()
),
];
if let Some(p) = tmpdir_env_var {
expected_args.push(format!("-DWRITABLE_ROOT_1={p}"));
}
expected_args.extend(vec![
"--".to_string(),
"/bin/echo".to_string(),
"hello".to_string(),
]);
assert_eq!(args, expected_args);
}
struct PopulatedTmp {
root_with_git: PathBuf,
root_without_git: PathBuf,
root_with_git_canon: PathBuf,
root_with_git_git_canon: PathBuf,
root_without_git_canon: PathBuf,
}
fn populate_tmpdir(tmp: &Path) -> PopulatedTmp {
let root_with_git = tmp.join("with_git");
let root_without_git = tmp.join("no_git");
fs::create_dir_all(&root_with_git).expect("create with_git");
fs::create_dir_all(&root_without_git).expect("create no_git");
fs::create_dir_all(root_with_git.join(".git")).expect("create .git");
// Ensure we have canonical paths for -D parameter matching.
let root_with_git_canon = root_with_git.canonicalize().expect("canonicalize with_git");
let root_with_git_git_canon = root_with_git_canon.join(".git");
let root_without_git_canon = root_without_git
.canonicalize()
.expect("canonicalize no_git");
PopulatedTmp {
root_with_git,
root_without_git,
root_with_git_canon,
root_with_git_git_canon,
root_without_git_canon,
}
}
}

View File

@@ -220,6 +220,7 @@ mod tests {
Arc::new(Notify::new()),
&SandboxPolicy::DangerFullAccess,
&None,
None,
)
.await
.unwrap();

107
codex-rs/core/src/spawn.rs Normal file
View File

@@ -0,0 +1,107 @@
use std::collections::HashMap;
use std::path::PathBuf;
use std::process::Stdio;
use tokio::process::Child;
use tokio::process::Command;
use tracing::trace;
use crate::protocol::SandboxPolicy;
/// Experimental environment variable that will be set to some non-empty value
/// if both of the following are true:
///
/// 1. The process was spawned by Codex as part of a shell tool call.
/// 2. SandboxPolicy.has_full_network_access() was false for the tool call.
///
/// We may try to have just one environment variable for all sandboxing
/// attributes, so this may change in the future.
pub const CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR: &str = "CODEX_SANDBOX_NETWORK_DISABLED";
/// Should be set when the process is spawned under a sandbox. Currently, the
/// value is "seatbelt" for macOS, but it may change in the future to
/// accommodate sandboxing configuration and other sandboxing mechanisms.
pub const CODEX_SANDBOX_ENV_VAR: &str = "CODEX_SANDBOX";
#[derive(Debug, Clone, Copy)]
pub enum StdioPolicy {
RedirectForShellTool,
Inherit,
}
/// Spawns the appropriate child process for the ExecParams and SandboxPolicy,
/// ensuring the args and environment variables used to create the `Command`
/// (and `Child`) honor the configuration.
///
/// For now, we take `SandboxPolicy` as a parameter to spawn_child() because
/// we need to determine whether to set the
/// `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` environment variable.
pub(crate) async fn spawn_child_async(
program: PathBuf,
args: Vec<String>,
#[cfg_attr(not(unix), allow(unused_variables))] arg0: Option<&str>,
cwd: PathBuf,
sandbox_policy: &SandboxPolicy,
stdio_policy: StdioPolicy,
env: HashMap<String, String>,
) -> std::io::Result<Child> {
trace!(
"spawn_child_async: {program:?} {args:?} {arg0:?} {cwd:?} {sandbox_policy:?} {stdio_policy:?} {env:?}"
);
let mut cmd = Command::new(&program);
#[cfg(unix)]
cmd.arg0(arg0.map_or_else(|| program.to_string_lossy().to_string(), String::from));
cmd.args(args);
cmd.current_dir(cwd);
cmd.env_clear();
cmd.envs(env);
if !sandbox_policy.has_full_network_access() {
cmd.env(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR, "1");
}
// If this Codex process dies (including being killed via SIGKILL), we want
// any child processes that were spawned as part of a `"shell"` tool call
// to also be terminated.
// This relies on prctl(2), so it only works on Linux.
#[cfg(target_os = "linux")]
unsafe {
cmd.pre_exec(|| {
// This prctl call effectively requests, "deliver SIGTERM when my
// current parent dies."
if libc::prctl(libc::PR_SET_PDEATHSIG, libc::SIGTERM) == -1 {
return Err(std::io::Error::last_os_error());
}
// Though if there was a race condition and this pre_exec() block is
// run _after_ the parent (i.e., the Codex process) has already
// exited, then the parent is the _init_ process (which will never
// die), so we should just terminate the child process now.
if libc::getppid() == 1 {
libc::raise(libc::SIGTERM);
}
Ok(())
});
}
match stdio_policy {
StdioPolicy::RedirectForShellTool => {
// Do not create a file descriptor for stdin because otherwise some
// commands may hang forever waiting for input. For example, ripgrep has
// a heuristic where it may try to read from stdin as explained here:
// https://github.com/BurntSushi/ripgrep/blob/e2362d4d5185d02fa857bf381e7bd52e66fafc73/crates/core/flags/hiargs.rs#L1101-L1103
cmd.stdin(Stdio::null());
cmd.stdout(Stdio::piped()).stderr(Stdio::piped());
}
StdioPolicy::Inherit => {
// Inherit stdin, stdout, and stderr from the parent process.
cmd.stdin(Stdio::inherit())
.stdout(Stdio::inherit())
.stderr(Stdio::inherit());
}
}
cmd.kill_on_drop(true).spawn()
}

View File

@@ -1,7 +1,7 @@
#![expect(clippy::unwrap_used)]
use assert_cmd::Command as AssertCommand;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use std::time::Duration;
use std::time::Instant;
use tempfile::TempDir;
@@ -460,9 +460,14 @@ async fn integration_git_info_unit_test() {
// 1. Create temp directory for git repo
let temp_dir = TempDir::new().unwrap();
let git_repo = temp_dir.path().to_path_buf();
let envs = vec![
("GIT_CONFIG_GLOBAL", "/dev/null"),
("GIT_CONFIG_NOSYSTEM", "1"),
];
// 2. Initialize a git repository with some content
let init_output = std::process::Command::new("git")
.envs(envs.clone())
.args(["init"])
.current_dir(&git_repo)
.output()
@@ -471,12 +476,14 @@ async fn integration_git_info_unit_test() {
// Configure git user (required for commits)
std::process::Command::new("git")
.envs(envs.clone())
.args(["config", "user.name", "Integration Test"])
.current_dir(&git_repo)
.output()
.unwrap();
std::process::Command::new("git")
.envs(envs.clone())
.args(["config", "user.email", "test@example.com"])
.current_dir(&git_repo)
.output()
@@ -487,12 +494,14 @@ async fn integration_git_info_unit_test() {
std::fs::write(&test_file, "integration test content").unwrap();
std::process::Command::new("git")
.envs(envs.clone())
.args(["add", "."])
.current_dir(&git_repo)
.output()
.unwrap();
let commit_output = std::process::Command::new("git")
.envs(envs.clone())
.args(["commit", "-m", "Integration test commit"])
.current_dir(&git_repo)
.output()
@@ -501,6 +510,7 @@ async fn integration_git_info_unit_test() {
// Create a branch to test branch detection
std::process::Command::new("git")
.envs(envs.clone())
.args(["checkout", "-b", "integration-test-branch"])
.current_dir(&git_repo)
.output()
@@ -508,6 +518,7 @@ async fn integration_git_info_unit_test() {
// Add a remote to test repository URL detection
std::process::Command::new("git")
.envs(envs.clone())
.args([
"remote",
"add",

View File

@@ -5,11 +5,11 @@ use codex_core::Codex;
use codex_core::CodexSpawnOk;
use codex_core::ModelProviderInfo;
use codex_core::built_in_model_providers;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::protocol::EventMsg;
use codex_core::protocol::InputItem;
use codex_core::protocol::Op;
use codex_core::protocol::SessionConfiguredEvent;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_login::AuthDotJson;
use codex_login::AuthMode;
use codex_login::CodexAuth;
@@ -95,8 +95,8 @@ async fn includes_session_id_and_model_headers_in_request() {
// get request from the server
let request = &server.received_requests().await.unwrap()[0];
let request_session_id = request.headers.get("session_id").unwrap();
let request_originator = request.headers.get("originator").unwrap();
let request_authorization = request.headers.get("authorization").unwrap();
let request_originator = request.headers.get("originator").unwrap();
assert!(current_session_id.is_some());
assert_eq!(
@@ -170,6 +170,59 @@ async fn includes_base_instructions_override_in_request() {
);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn originator_config_override_is_used() {
#![allow(clippy::unwrap_used)]
// Mock server
let server = MockServer::start().await;
let first = ResponseTemplate::new(200)
.insert_header("content-type", "text/event-stream")
.set_body_raw(sse_completed("resp1"), "text/event-stream");
Mock::given(method("POST"))
.and(path("/v1/responses"))
.respond_with(first)
.expect(1)
.mount(&server)
.await;
let model_provider = ModelProviderInfo {
base_url: Some(format!("{}/v1", server.uri())),
..built_in_model_providers()["openai"].clone()
};
let codex_home = TempDir::new().unwrap();
let mut config = load_default_config_for_test(&codex_home);
config.model_provider = model_provider;
config.internal_originator = Some("my_override".to_string());
let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
let CodexSpawnOk { codex, .. } = Codex::spawn(
config,
Some(CodexAuth::from_api_key("Test API Key".to_string())),
ctrl_c.clone(),
)
.await
.unwrap();
codex
.submit(Op::UserInput {
items: vec![InputItem::Text {
text: "hello".into(),
}],
})
.await
.unwrap();
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
let request = &server.received_requests().await.unwrap()[0];
let request_originator = request.headers.get("originator").unwrap();
assert_eq!(request_originator.to_str().unwrap(), "my_override");
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn chatgpt_auth_sends_correct_request() {
#![allow(clippy::unwrap_used)]
@@ -235,8 +288,9 @@ async fn chatgpt_auth_sends_correct_request() {
// get request from the server
let request = &server.received_requests().await.unwrap()[0];
let request_session_id = request.headers.get("session_id").unwrap();
let request_originator = request.headers.get("originator").unwrap();
let request_authorization = request.headers.get("authorization").unwrap();
let request_originator = request.headers.get("originator").unwrap();
let request_chatgpt_account_id = request.headers.get("chatgpt-account-id").unwrap();
let request_body = request.body_json::<serde_json::Value>().unwrap();
assert!(current_session_id.is_some());
@@ -249,6 +303,7 @@ async fn chatgpt_auth_sends_correct_request() {
request_authorization.to_str().unwrap(),
"Bearer Access Token"
);
assert_eq!(request_chatgpt_account_id.to_str().unwrap(), "account_id");
assert!(!request_body["store"].as_bool().unwrap());
assert!(request_body["stream"].as_bool().unwrap());
assert_eq!(
@@ -327,14 +382,14 @@ fn auth_from_token(id_token: String) -> CodexAuth {
AuthMode::ChatGPT,
PathBuf::new(),
Some(AuthDotJson {
tokens: TokenData {
openai_api_key: None,
tokens: Some(TokenData {
id_token,
access_token: "Access Token".to_string(),
refresh_token: "test".to_string(),
account_id: None,
},
last_refresh: Utc::now(),
openai_api_key: None,
account_id: Some("account_id".to_string()),
}),
last_refresh: Some(Utc::now()),
}),
)
}

View File

@@ -0,0 +1,254 @@
#![expect(clippy::unwrap_used)]
use codex_core::Codex;
use codex_core::CodexSpawnOk;
use codex_core::ModelProviderInfo;
use codex_core::built_in_model_providers;
use codex_core::protocol::EventMsg;
use codex_core::protocol::InputItem;
use codex_core::protocol::Op;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_login::CodexAuth;
use core_test_support::load_default_config_for_test;
use core_test_support::wait_for_event;
use serde_json::Value;
use tempfile::TempDir;
use wiremock::Mock;
use wiremock::MockServer;
use wiremock::ResponseTemplate;
use wiremock::matchers::method;
use wiremock::matchers::path;
use pretty_assertions::assert_eq;
// --- Test helpers -----------------------------------------------------------
/// Build an SSE stream body from a list of JSON events.
fn sse(events: Vec<Value>) -> String {
use std::fmt::Write as _;
let mut out = String::new();
for ev in events {
let kind = ev.get("type").and_then(|v| v.as_str()).unwrap();
writeln!(&mut out, "event: {kind}").unwrap();
if !ev.as_object().map(|o| o.len() == 1).unwrap_or(false) {
write!(&mut out, "data: {ev}\n\n").unwrap();
} else {
out.push('\n');
}
}
out
}
/// Convenience: SSE event for a completed response with a specific id.
fn ev_completed(id: &str) -> Value {
serde_json::json!({
"type": "response.completed",
"response": {
"id": id,
"usage": {"input_tokens":0,"input_tokens_details":null,"output_tokens":0,"output_tokens_details":null,"total_tokens":0}
}
})
}
/// Convenience: SSE event for a single assistant message output item.
fn ev_assistant_message(id: &str, text: &str) -> Value {
serde_json::json!({
"type": "response.output_item.done",
"item": {
"type": "message",
"role": "assistant",
"id": id,
"content": [{"type": "output_text", "text": text}]
}
})
}
fn sse_response(body: String) -> ResponseTemplate {
ResponseTemplate::new(200)
.insert_header("content-type", "text/event-stream")
.set_body_raw(body, "text/event-stream")
}
async fn mount_sse_once<M>(server: &MockServer, matcher: M, body: String)
where
M: wiremock::Match + Send + Sync + 'static,
{
Mock::given(method("POST"))
.and(path("/v1/responses"))
.and(matcher)
.respond_with(sse_response(body))
.expect(1)
.mount(server)
.await;
}
const FIRST_REPLY: &str = "FIRST_REPLY";
const SUMMARY_TEXT: &str = "SUMMARY_ONLY_CONTEXT";
const SUMMARIZE_TRIGGER: &str = "Start Summarization";
const THIRD_USER_MSG: &str = "next turn";
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn summarize_context_three_requests_and_instructions() {
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
println!(
"Skipping test because it cannot execute when network is disabled in a Codex sandbox."
);
return;
}
// Set up a mock server that we can inspect after the run.
let server = MockServer::start().await;
// SSE 1: assistant replies normally so it is recorded in history.
let sse1 = sse(vec![
ev_assistant_message("m1", FIRST_REPLY),
ev_completed("r1"),
]);
// SSE 2: summarizer returns a summary message.
let sse2 = sse(vec![
ev_assistant_message("m2", SUMMARY_TEXT),
ev_completed("r2"),
]);
// SSE 3: minimal completed; we only need to capture the request body.
let sse3 = sse(vec![ev_completed("r3")]);
// Mount three expectations, one per request, matched by body content.
let first_matcher = |req: &wiremock::Request| {
let body = std::str::from_utf8(&req.body).unwrap_or("");
body.contains("\"text\":\"hello world\"")
&& !body.contains(&format!("\"text\":\"{SUMMARIZE_TRIGGER}\""))
};
mount_sse_once(&server, first_matcher, sse1).await;
let second_matcher = |req: &wiremock::Request| {
let body = std::str::from_utf8(&req.body).unwrap_or("");
body.contains(&format!("\"text\":\"{SUMMARIZE_TRIGGER}\""))
};
mount_sse_once(&server, second_matcher, sse2).await;
let third_matcher = |req: &wiremock::Request| {
let body = std::str::from_utf8(&req.body).unwrap_or("");
body.contains(&format!("\"text\":\"{THIRD_USER_MSG}\""))
};
mount_sse_once(&server, third_matcher, sse3).await;
// Build config pointing to the mock server and spawn Codex.
let model_provider = ModelProviderInfo {
base_url: Some(format!("{}/v1", server.uri())),
..built_in_model_providers()["openai"].clone()
};
let home = TempDir::new().unwrap();
let mut config = load_default_config_for_test(&home);
config.model_provider = model_provider;
let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
let CodexSpawnOk { codex, .. } = Codex::spawn(
config,
Some(CodexAuth::from_api_key("dummy".to_string())),
ctrl_c.clone(),
)
.await
.unwrap();
// 1) Normal user input should hit server once.
codex
.submit(Op::UserInput {
items: vec![InputItem::Text {
text: "hello world".into(),
}],
})
.await
.unwrap();
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
// 2) Summarize second hit with summarization instructions.
codex.submit(Op::Compact).await.unwrap();
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
// 3) Next user input third hit; history should include only the summary.
codex
.submit(Op::UserInput {
items: vec![InputItem::Text {
text: THIRD_USER_MSG.into(),
}],
})
.await
.unwrap();
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
// Inspect the three captured requests.
let requests = server.received_requests().await.unwrap();
assert_eq!(requests.len(), 3, "expected exactly three requests");
let req1 = &requests[0];
let req2 = &requests[1];
let req3 = &requests[2];
let body1 = req1.body_json::<serde_json::Value>().unwrap();
let body2 = req2.body_json::<serde_json::Value>().unwrap();
let body3 = req3.body_json::<serde_json::Value>().unwrap();
// System instructions should change for the summarization turn.
let instr1 = body1.get("instructions").and_then(|v| v.as_str()).unwrap();
let instr2 = body2.get("instructions").and_then(|v| v.as_str()).unwrap();
assert_ne!(
instr1, instr2,
"summarization should override base instructions"
);
assert!(
instr2.contains("You are a summarization assistant"),
"summarization instructions not applied"
);
// The summarization request should include the injected user input marker.
let input2 = body2.get("input").and_then(|v| v.as_array()).unwrap();
// The last item is the user message created from the injected input.
let last2 = input2.last().unwrap();
assert_eq!(last2.get("type").unwrap().as_str().unwrap(), "message");
assert_eq!(last2.get("role").unwrap().as_str().unwrap(), "user");
let text2 = last2["content"][0]["text"].as_str().unwrap();
assert!(text2.contains(SUMMARIZE_TRIGGER));
// Third request must contain only the summary from step 2 as prior history plus new user msg.
let input3 = body3.get("input").and_then(|v| v.as_array()).unwrap();
println!("third request body: {body3}");
assert!(
input3.len() >= 2,
"expected summary + new user message in third request"
);
// Collect all (role, text) message tuples.
let mut messages: Vec<(String, String)> = Vec::new();
for item in input3 {
if item["type"].as_str() == Some("message") {
let role = item["role"].as_str().unwrap_or_default().to_string();
let text = item["content"][0]["text"]
.as_str()
.unwrap_or_default()
.to_string();
messages.push((role, text));
}
}
// Exactly one assistant message should remain after compaction and the new user message is present.
let assistant_count = messages.iter().filter(|(r, _)| r == "assistant").count();
assert_eq!(
assistant_count, 1,
"exactly one assistant message should remain after compaction"
);
assert!(
messages
.iter()
.any(|(r, t)| r == "user" && t == THIRD_USER_MSG),
"third request should include the new user message"
);
assert!(
!messages.iter().any(|(_, t)| t.contains("hello world")),
"third request should not include the original user input"
);
assert!(
!messages.iter().any(|(_, t)| t.contains(SUMMARIZE_TRIGGER)),
"third request should not include the summarize trigger"
);
}

View File

@@ -0,0 +1,143 @@
#![cfg(unix)]
use std::collections::HashMap;
use std::path::PathBuf;
use std::sync::Arc;
use async_channel::Receiver;
use codex_core::exec::ExecParams;
use codex_core::exec::SandboxType;
use codex_core::exec::StdoutStream;
use codex_core::exec::process_exec_tool_call;
use codex_core::protocol::Event;
use codex_core::protocol::EventMsg;
use codex_core::protocol::ExecCommandOutputDeltaEvent;
use codex_core::protocol::ExecOutputStream;
use codex_core::protocol::SandboxPolicy;
use tokio::sync::Notify;
fn collect_stdout_events(rx: Receiver<Event>) -> Vec<u8> {
let mut out = Vec::new();
while let Ok(ev) = rx.try_recv() {
if let EventMsg::ExecCommandOutputDelta(ExecCommandOutputDeltaEvent {
stream: ExecOutputStream::Stdout,
chunk,
..
}) = ev.msg
{
out.extend_from_slice(&chunk);
}
}
out
}
#[tokio::test]
async fn test_exec_stdout_stream_events_echo() {
let (tx, rx) = async_channel::unbounded::<Event>();
let stdout_stream = StdoutStream {
sub_id: "test-sub".to_string(),
call_id: "call-1".to_string(),
tx_event: tx,
};
let cmd = vec![
"/bin/sh".to_string(),
"-c".to_string(),
// Use printf for predictable behavior across shells
"printf 'hello-world\n'".to_string(),
];
let params = ExecParams {
command: cmd,
cwd: std::env::current_dir().unwrap_or_else(|_| PathBuf::from(".")),
timeout_ms: Some(5_000),
env: HashMap::new(),
};
let ctrl_c = Arc::new(Notify::new());
let policy = SandboxPolicy::new_read_only_policy();
let result = process_exec_tool_call(
params,
SandboxType::None,
ctrl_c,
&policy,
&None,
Some(stdout_stream),
)
.await;
let result = match result {
Ok(r) => r,
Err(e) => panic!("process_exec_tool_call failed: {e}"),
};
assert_eq!(result.exit_code, 0);
assert_eq!(result.stdout, "hello-world\n");
let streamed = collect_stdout_events(rx);
// We should have received at least the same contents (possibly in one chunk)
assert_eq!(String::from_utf8_lossy(&streamed), "hello-world\n");
}
#[tokio::test]
async fn test_exec_stderr_stream_events_echo() {
let (tx, rx) = async_channel::unbounded::<Event>();
let stdout_stream = StdoutStream {
sub_id: "test-sub".to_string(),
call_id: "call-2".to_string(),
tx_event: tx,
};
let cmd = vec![
"/bin/sh".to_string(),
"-c".to_string(),
// Write to stderr explicitly
"printf 'oops\n' 1>&2".to_string(),
];
let params = ExecParams {
command: cmd,
cwd: std::env::current_dir().unwrap_or_else(|_| PathBuf::from(".")),
timeout_ms: Some(5_000),
env: HashMap::new(),
};
let ctrl_c = Arc::new(Notify::new());
let policy = SandboxPolicy::new_read_only_policy();
let result = process_exec_tool_call(
params,
SandboxType::None,
ctrl_c,
&policy,
&None,
Some(stdout_stream),
)
.await;
let result = match result {
Ok(r) => r,
Err(e) => panic!("process_exec_tool_call failed: {e}"),
};
assert_eq!(result.exit_code, 0);
assert_eq!(result.stdout, "");
assert_eq!(result.stderr, "oops\n");
// Collect only stderr delta events
let mut err = Vec::new();
while let Ok(ev) = rx.try_recv() {
if let EventMsg::ExecCommandOutputDelta(ExecCommandOutputDeltaEvent {
stream: ExecOutputStream::Stderr,
chunk,
..
}) = ev.msg
{
err.extend_from_slice(&chunk);
}
}
assert_eq!(String::from_utf8_lossy(&err), "oops\n");
}

View File

@@ -0,0 +1,195 @@
#![cfg(target_os = "macos")]
#![expect(clippy::expect_used)]
use std::collections::HashMap;
use std::path::Path;
use std::path::PathBuf;
use codex_core::protocol::SandboxPolicy;
use codex_core::seatbelt::spawn_command_under_seatbelt;
use codex_core::spawn::CODEX_SANDBOX_ENV_VAR;
use codex_core::spawn::StdioPolicy;
use tempfile::TempDir;
struct TestScenario {
repo_parent: PathBuf,
file_outside_repo: PathBuf,
repo_root: PathBuf,
file_in_repo_root: PathBuf,
file_in_dot_git_dir: PathBuf,
}
struct TestExpectations {
file_outside_repo_is_writable: bool,
file_in_repo_root_is_writable: bool,
file_in_dot_git_dir_is_writable: bool,
}
impl TestScenario {
async fn run_test(&self, policy: &SandboxPolicy, expectations: TestExpectations) {
if std::env::var(CODEX_SANDBOX_ENV_VAR) == Ok("seatbelt".to_string()) {
eprintln!("{CODEX_SANDBOX_ENV_VAR} is set to 'seatbelt', skipping test.");
return;
}
assert_eq!(
touch(&self.file_outside_repo, policy).await,
expectations.file_outside_repo_is_writable
);
assert_eq!(
self.file_outside_repo.exists(),
expectations.file_outside_repo_is_writable
);
assert_eq!(
touch(&self.file_in_repo_root, policy).await,
expectations.file_in_repo_root_is_writable
);
assert_eq!(
self.file_in_repo_root.exists(),
expectations.file_in_repo_root_is_writable
);
assert_eq!(
touch(&self.file_in_dot_git_dir, policy).await,
expectations.file_in_dot_git_dir_is_writable
);
assert_eq!(
self.file_in_dot_git_dir.exists(),
expectations.file_in_dot_git_dir_is_writable
);
}
}
/// If the user has added a workspace root that is not a Git repo root, then
/// the user has to specify `--skip-git-repo-check` or go through some
/// interstitial that indicates they are taking on some risk because Git
/// cannot be used to backup their work before the agent begins.
///
/// Because the user has agreed to this risk, we do not try find all .git
/// folders in the workspace and block them (though we could change our
/// position on this in the future).
#[tokio::test]
async fn if_parent_of_repo_is_writable_then_dot_git_folder_is_writable() {
let tmp = TempDir::new().expect("should be able to create temp dir");
let test_scenario = create_test_scenario(&tmp);
let policy = SandboxPolicy::WorkspaceWrite {
writable_roots: vec![test_scenario.repo_parent.clone()],
network_access: false,
include_default_writable_roots: false,
};
test_scenario
.run_test(
&policy,
TestExpectations {
file_outside_repo_is_writable: true,
file_in_repo_root_is_writable: true,
file_in_dot_git_dir_is_writable: true,
},
)
.await;
}
/// When the writable root is the root of a Git repository (as evidenced by the
/// presence of a .git folder), then the .git folder should be read-only if
/// the policy is `WorkspaceWrite`.
#[tokio::test]
async fn if_git_repo_is_writable_root_then_dot_git_folder_is_read_only() {
let tmp = TempDir::new().expect("should be able to create temp dir");
let test_scenario = create_test_scenario(&tmp);
let policy = SandboxPolicy::WorkspaceWrite {
writable_roots: vec![test_scenario.repo_root.clone()],
network_access: false,
include_default_writable_roots: false,
};
test_scenario
.run_test(
&policy,
TestExpectations {
file_outside_repo_is_writable: false,
file_in_repo_root_is_writable: true,
file_in_dot_git_dir_is_writable: false,
},
)
.await;
}
/// Under DangerFullAccess, all writes should be permitted anywhere on disk,
/// including inside the .git folder.
#[tokio::test]
async fn danger_full_access_allows_all_writes() {
let tmp = TempDir::new().expect("should be able to create temp dir");
let test_scenario = create_test_scenario(&tmp);
let policy = SandboxPolicy::DangerFullAccess;
test_scenario
.run_test(
&policy,
TestExpectations {
file_outside_repo_is_writable: true,
file_in_repo_root_is_writable: true,
file_in_dot_git_dir_is_writable: true,
},
)
.await;
}
/// Under ReadOnly, writes should not be permitted anywhere on disk.
#[tokio::test]
async fn read_only_forbids_all_writes() {
let tmp = TempDir::new().expect("should be able to create temp dir");
let test_scenario = create_test_scenario(&tmp);
let policy = SandboxPolicy::ReadOnly;
test_scenario
.run_test(
&policy,
TestExpectations {
file_outside_repo_is_writable: false,
file_in_repo_root_is_writable: false,
file_in_dot_git_dir_is_writable: false,
},
)
.await;
}
fn create_test_scenario(tmp: &TempDir) -> TestScenario {
let repo_parent = tmp.path().to_path_buf();
let repo_root = repo_parent.join("repo");
let dot_git_dir = repo_root.join(".git");
std::fs::create_dir(&repo_root).expect("should be able to create repo root");
std::fs::create_dir(&dot_git_dir).expect("should be able to create .git dir");
TestScenario {
file_outside_repo: repo_parent.join("outside.txt"),
repo_parent,
file_in_repo_root: repo_root.join("repo_file.txt"),
repo_root,
file_in_dot_git_dir: dot_git_dir.join("dot_git_file.txt"),
}
}
/// Note that `path` must be absolute.
async fn touch(path: &Path, policy: &SandboxPolicy) -> bool {
assert!(path.is_absolute(), "Path must be absolute: {path:?}");
let mut child = spawn_command_under_seatbelt(
vec![
"/usr/bin/touch".to_string(),
path.to_string_lossy().to_string(),
],
policy,
std::env::current_dir().expect("should be able to get current dir"),
StdioPolicy::RedirectForShellTool,
HashMap::new(),
)
.await
.expect("should be able to spawn command under seatbelt");
child
.wait()
.await
.expect("should be able to wait for child process")
.success()
}

View File

@@ -6,10 +6,10 @@ use std::time::Duration;
use codex_core::Codex;
use codex_core::CodexSpawnOk;
use codex_core::ModelProviderInfo;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::protocol::EventMsg;
use codex_core::protocol::InputItem;
use codex_core::protocol::Op;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_login::CodexAuth;
use core_test_support::load_default_config_for_test;
use core_test_support::load_sse_fixture;

View File

@@ -1,41 +0,0 @@
#![expect(clippy::unwrap_used, clippy::expect_used)]
//! Tests for the `Op::SummarizeContext` operation added to verify that
//! summarization requests are properly handled and injected as user input.
use std::time::Duration;
use codex_core::Codex;
use codex_core::protocol::EventMsg;
use codex_core::protocol::Op;
use core_test_support::load_default_config_for_test;
use tempfile::TempDir;
use tokio::time::timeout;
/// Helper function to set up a codex session and wait for it to be configured
async fn setup_configured_codex_session() -> Codex {
let codex_home = TempDir::new().unwrap();
let config = load_default_config_for_test(&codex_home);
let codex_conversation = codex_core::codex_wrapper::init_codex(config).await.unwrap();
codex_conversation.codex
}
#[tokio::test]
async fn test_summarize_context_spawns_new_agent_task() {
// Test the specific behavior: when there's no current task,
// SummarizeContext should spawn a new AgentTask with the summarization prompt
let codex = setup_configured_codex_session().await;
// At this point, there should be no current task running
let _sub_id = codex.submit(Op::SummarizeContext).await.unwrap();
let event = timeout(Duration::from_secs(5), codex.next_event())
.await
.expect("timeout waiting for task started event")
.expect("codex closed");
assert!(
matches!(event.msg, EventMsg::TaskStarted),
"Expected TaskStarted when no current task exists - should spawn new AgentTask"
);
}

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-exec"
version = { workspace = true }
edition = "2024"
[[bin]]
name = "codex-exec"
@@ -19,12 +19,12 @@ anyhow = "1"
chrono = "0.4.40"
clap = { version = "4", features = ["derive"] }
codex-arg0 = { path = "../arg0" }
codex-core = { path = "../core" }
codex-common = { path = "../common", features = [
"cli",
"elapsed",
"sandbox_summary",
] }
codex-core = { path = "../core" }
owo-colors = "4.2.0"
serde_json = "1"
shlex = "1.3.0"

View File

@@ -239,6 +239,7 @@ impl EventProcessor for EventProcessorWithHumanOutput {
cwd.to_string_lossy(),
);
}
EventMsg::ExecCommandOutputDelta(_) => {}
EventMsg::ExecCommandEnd(ExecCommandEndEvent {
call_id,
stdout,

View File

@@ -1,5 +1,6 @@
use anyhow::Context;
use assert_cmd::prelude::*;
use codex_core::CODEX_APPLY_PATCH_ARG1;
use std::fs;
use std::process::Command;
use tempfile::tempdir;
@@ -16,7 +17,7 @@ fn test_standalone_exec_cli_can_use_apply_patch() -> anyhow::Result<()> {
Command::cargo_bin("codex-exec")
.context("should find binary for codex-exec")?
.arg("--codex-run-as-apply-patch")
.arg(CODEX_APPLY_PATCH_ARG1)
.arg(
r#"*** Begin Patch
*** Update File: source.txt

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-file-search"
version = { workspace = true }
edition = "2024"
[[bin]]
name = "codex-file-search"

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-linux-sandbox"
version = { workspace = true }
edition = "2024"
[[bin]]
name = "codex-linux-sandbox"
@@ -19,8 +19,8 @@ anyhow = "1"
clap = { version = "4", features = ["derive"] }
codex-common = { path = "../common", features = ["cli"] }
codex-core = { path = "../core" }
libc = "0.2.172"
landlock = "0.4.1"
libc = "0.2.172"
seccompiler = "0.5.0"
[target.'cfg(target_os = "linux")'.dev-dependencies]

View File

@@ -36,7 +36,11 @@ pub(crate) fn apply_sandbox_policy_to_current_thread(
}
if !sandbox_policy.has_full_disk_write_access() {
let writable_roots = sandbox_policy.get_writable_roots_with_cwd(cwd);
let writable_roots = sandbox_policy
.get_writable_roots_with_cwd(cwd)
.into_iter()
.map(|writable_root| writable_root.root)
.collect();
install_filesystem_landlock_rules_on_current_thread(writable_roots)?;
}

View File

@@ -49,6 +49,7 @@ async fn run_cmd(cmd: &[&str], writable_roots: &[PathBuf], timeout_ms: u64) {
let sandbox_policy = SandboxPolicy::WorkspaceWrite {
writable_roots: writable_roots.to_vec(),
network_access: false,
include_default_writable_roots: true,
};
let sandbox_program = env!("CARGO_BIN_EXE_codex-linux-sandbox");
let codex_linux_sandbox_exe = Some(PathBuf::from(sandbox_program));
@@ -59,6 +60,7 @@ async fn run_cmd(cmd: &[&str], writable_roots: &[PathBuf], timeout_ms: u64) {
ctrl_c,
&sandbox_policy,
&codex_linux_sandbox_exe,
None,
)
.await
.unwrap();
@@ -149,6 +151,7 @@ async fn assert_network_blocked(cmd: &[&str]) {
ctrl_c,
&sandbox_policy,
&codex_linux_sandbox_exe,
None,
)
.await;

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-login"
version = { workspace = true }
edition = "2024"
[lints]
workspace = true
@@ -18,3 +18,6 @@ tokio = { version = "1", features = [
"rt-multi-thread",
"signal",
] }
[dev-dependencies]
tempfile = "3"

View File

@@ -20,7 +20,7 @@ use tokio::process::Command;
const SOURCE_FOR_PYTHON_SERVER: &str = include_str!("./login_with_chatgpt.py");
const CLIENT_ID: &str = "app_EMoamEEZ73f0CkXaXp7hrann";
const OPENAI_API_KEY_ENV_VAR: &str = "OPENAI_API_KEY";
pub const OPENAI_API_KEY_ENV_VAR: &str = "OPENAI_API_KEY";
#[derive(Clone, Debug, PartialEq)]
pub enum AuthMode {
@@ -70,13 +70,16 @@ impl CodexAuth {
pub async fn get_token_data(&self) -> Result<TokenData, std::io::Error> {
#[expect(clippy::unwrap_used)]
let auth_dot_json = self.auth_dot_json.lock().unwrap().clone();
match auth_dot_json {
Some(auth_dot_json) => {
if auth_dot_json.last_refresh < Utc::now() - chrono::Duration::days(28) {
Some(AuthDotJson {
tokens: Some(mut tokens),
last_refresh: Some(last_refresh),
..
}) => {
if last_refresh < Utc::now() - chrono::Duration::days(28) {
let refresh_response = tokio::time::timeout(
Duration::from_secs(60),
try_refresh_token(auth_dot_json.tokens.refresh_token.clone()),
try_refresh_token(tokens.refresh_token.clone()),
)
.await
.map_err(|_| {
@@ -92,13 +95,21 @@ impl CodexAuth {
)
.await?;
tokens = updated_auth_dot_json
.tokens
.clone()
.ok_or(std::io::Error::other(
"Token data is not available after refresh.",
))?;
#[expect(clippy::unwrap_used)]
let mut auth_dot_json = self.auth_dot_json.lock().unwrap();
*auth_dot_json = Some(updated_auth_dot_json);
let mut auth_lock = self.auth_dot_json.lock().unwrap();
*auth_lock = Some(updated_auth_dot_json);
}
Ok(auth_dot_json.tokens.clone())
Ok(tokens)
}
None => Err(std::io::Error::other("Token data is not available.")),
_ => Err(std::io::Error::other("Token data is not available.")),
}
}
@@ -112,11 +123,22 @@ impl CodexAuth {
}
}
}
pub async fn get_account_id(&self) -> Option<String> {
match self.mode {
AuthMode::ApiKey => None,
AuthMode::ChatGPT => {
let token_data = self.get_token_data().await.ok()?;
token_data.account_id.clone()
}
}
}
}
// Loads the available auth information from the auth.json or OPENAI_API_KEY environment variable.
pub fn load_auth(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
let auth_file = codex_home.join("auth.json");
pub fn load_auth(codex_home: &Path, include_env_var: bool) -> std::io::Result<Option<CodexAuth>> {
let auth_file = get_auth_file(codex_home);
let auth_dot_json = try_read_auth_json(&auth_file).ok();
@@ -125,12 +147,21 @@ pub fn load_auth(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
.and_then(|a| a.openai_api_key.clone())
.filter(|s| !s.is_empty());
let openai_api_key = env::var(OPENAI_API_KEY_ENV_VAR)
.ok()
.filter(|s| !s.is_empty())
.or(auth_json_api_key);
let openai_api_key = if include_env_var {
env::var(OPENAI_API_KEY_ENV_VAR)
.ok()
.filter(|s| !s.is_empty())
.or(auth_json_api_key)
} else {
auth_json_api_key
};
if openai_api_key.is_none() && auth_dot_json.is_none() {
let has_tokens = auth_dot_json
.as_ref()
.and_then(|a| a.tokens.as_ref())
.is_some();
if openai_api_key.is_none() && !has_tokens {
return Ok(None);
}
@@ -148,6 +179,10 @@ pub fn load_auth(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
}))
}
fn get_auth_file(codex_home: &Path) -> PathBuf {
codex_home.join("auth.json")
}
/// Run `python3 -c {{SOURCE_FOR_PYTHON_SERVER}}` with the CODEX_HOME
/// environment variable set to the provided `codex_home` path. If the
/// subprocess exits 0, read the OPENAI_API_KEY property out of
@@ -187,6 +222,15 @@ pub async fn login_with_chatgpt(codex_home: &Path, capture_output: bool) -> std:
}
}
pub fn login_with_api_key(codex_home: &Path, api_key: &str) -> std::io::Result<()> {
let auth_dot_json = AuthDotJson {
openai_api_key: Some(api_key.to_string()),
tokens: None,
last_refresh: None,
};
write_auth_json(&get_auth_file(codex_home), &auth_dot_json)
}
/// Attempt to read and refresh the `auth.json` file in the given `CODEX_HOME` directory.
/// Returns the full AuthDotJson structure after refreshing if necessary.
pub fn try_read_auth_json(auth_file: &Path) -> std::io::Result<AuthDotJson> {
@@ -198,35 +242,38 @@ pub fn try_read_auth_json(auth_file: &Path) -> std::io::Result<AuthDotJson> {
Ok(auth_dot_json)
}
async fn update_tokens(
auth_file: &Path,
id_token: String,
access_token: Option<String>,
refresh_token: Option<String>,
) -> std::io::Result<AuthDotJson> {
fn write_auth_json(auth_file: &Path, auth_dot_json: &AuthDotJson) -> std::io::Result<()> {
let json_data = serde_json::to_string_pretty(auth_dot_json)?;
let mut options = OpenOptions::new();
options.truncate(true).write(true).create(true);
#[cfg(unix)]
{
options.mode(0o600);
}
let mut file = options.open(auth_file)?;
file.write_all(json_data.as_bytes())?;
file.flush()?;
Ok(())
}
async fn update_tokens(
auth_file: &Path,
id_token: String,
access_token: Option<String>,
refresh_token: Option<String>,
) -> std::io::Result<AuthDotJson> {
let mut auth_dot_json = try_read_auth_json(auth_file)?;
auth_dot_json.tokens.id_token = id_token.to_string();
let tokens = auth_dot_json.tokens.get_or_insert_with(TokenData::default);
tokens.id_token = id_token.to_string();
if let Some(access_token) = access_token {
auth_dot_json.tokens.access_token = access_token.to_string();
tokens.access_token = access_token.to_string();
}
if let Some(refresh_token) = refresh_token {
auth_dot_json.tokens.refresh_token = refresh_token.to_string();
}
auth_dot_json.last_refresh = Utc::now();
let json_data = serde_json::to_string_pretty(&auth_dot_json)?;
{
let mut file = options.open(auth_file)?;
file.write_all(json_data.as_bytes())?;
file.flush()?;
tokens.refresh_token = refresh_token.to_string();
}
auth_dot_json.last_refresh = Some(Utc::now());
write_auth_json(auth_file, &auth_dot_json)?;
Ok(auth_dot_json)
}
@@ -282,12 +329,14 @@ pub struct AuthDotJson {
#[serde(rename = "OPENAI_API_KEY")]
pub openai_api_key: Option<String>,
pub tokens: TokenData,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub tokens: Option<TokenData>,
pub last_refresh: DateTime<Utc>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub last_refresh: Option<DateTime<Utc>>,
}
#[derive(Deserialize, Serialize, Clone, Debug, PartialEq)]
#[derive(Deserialize, Serialize, Clone, Debug, PartialEq, Default)]
pub struct TokenData {
/// This is a JWT.
pub id_token: String,
@@ -299,3 +348,95 @@ pub struct TokenData {
pub account_id: Option<String>,
}
#[cfg(test)]
mod tests {
use super::*;
use tempfile::tempdir;
#[test]
#[expect(clippy::unwrap_used)]
fn writes_api_key_and_loads_auth() {
let dir = tempdir().unwrap();
login_with_api_key(dir.path(), "sk-test-key").unwrap();
let auth = load_auth(dir.path(), false).unwrap().unwrap();
assert_eq!(auth.mode, AuthMode::ApiKey);
assert_eq!(auth.api_key.as_deref(), Some("sk-test-key"));
}
#[test]
#[expect(clippy::unwrap_used)]
fn loads_from_env_var_if_env_var_exists() {
let dir = tempdir().unwrap();
let env_var = std::env::var(OPENAI_API_KEY_ENV_VAR);
if let Ok(env_var) = env_var {
let auth = load_auth(dir.path(), true).unwrap().unwrap();
assert_eq!(auth.mode, AuthMode::ApiKey);
assert_eq!(auth.api_key, Some(env_var));
}
}
#[tokio::test]
#[expect(clippy::unwrap_used)]
async fn loads_token_data_from_auth_json() {
let dir = tempdir().unwrap();
let auth_file = dir.path().join("auth.json");
std::fs::write(
auth_file,
format!(
r#"
{{
"OPENAI_API_KEY": null,
"tokens": {{
"id_token": "test-id-token",
"access_token": "test-access-token",
"refresh_token": "test-refresh-token"
}},
"last_refresh": "{}"
}}
"#,
Utc::now().to_rfc3339()
),
)
.unwrap();
let auth = load_auth(dir.path(), false).unwrap().unwrap();
assert_eq!(auth.mode, AuthMode::ChatGPT);
assert_eq!(auth.api_key, None);
assert_eq!(
auth.get_token_data().await.unwrap(),
TokenData {
id_token: "test-id-token".to_string(),
access_token: "test-access-token".to_string(),
refresh_token: "test-refresh-token".to_string(),
account_id: None,
}
);
}
#[tokio::test]
#[expect(clippy::unwrap_used)]
async fn loads_api_key_from_auth_json() {
let dir = tempdir().unwrap();
let auth_file = dir.path().join("auth.json");
std::fs::write(
auth_file,
r#"
{
"OPENAI_API_KEY": "sk-test-key",
"tokens": null,
"last_refresh": null
}
"#,
)
.unwrap();
let auth = load_auth(dir.path(), false).unwrap().unwrap();
assert_eq!(auth.mode, AuthMode::ApiKey);
assert_eq!(auth.api_key, Some("sk-test-key".to_string()));
assert!(auth.get_token_data().await.is_err());
}
}

View File

@@ -686,6 +686,7 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
justify-content: center;
position: relative;
background: white;
font-family: system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
}
.inner-container {
@@ -703,6 +704,7 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
align-items: center;
gap: 20px;
display: flex;
margin-top: 15vh;
}
.svg-wrapper {
position: relative;
@@ -710,9 +712,9 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
.title {
text-align: center;
color: var(--text-primary, #0D0D0D);
font-size: 28px;
font-size: 32px;
font-weight: 400;
line-height: 36.40px;
line-height: 40px;
word-wrap: break-word;
}
.setup-box {
@@ -785,16 +787,26 @@ LOGIN_SUCCESS_HTML = """<!DOCTYPE html>
word-wrap: break-word;
text-decoration: none;
}
.logo {
display: flex;
align-items: center;
justify-content: center;
width: 4rem;
height: 4rem;
border-radius: 16px;
border: .5px solid rgba(0, 0, 0, 0.1);
box-shadow: rgba(0, 0, 0, 0.1) 0px 4px 16px 0px;
box-sizing: border-box;
background-color: rgb(255, 255, 255);
}
</style>
</head>
<body>
<div class="container">
<div class="inner-container">
<div class="content">
<div data-svg-wrapper class="svg-wrapper">
<svg width="56" height="56" viewBox="0 0 56 56" fill="none" xmlns="http://www.w3.org/2000/svg">
<path d="M4.6665 28.0003C4.6665 15.1137 15.1132 4.66699 27.9998 4.66699C40.8865 4.66699 51.3332 15.1137 51.3332 28.0003C51.3332 40.887 40.8865 51.3337 27.9998 51.3337C15.1132 51.3337 4.6665 40.887 4.6665 28.0003ZM37.5093 18.5088C36.4554 17.7672 34.9999 18.0203 34.2583 19.0742L24.8508 32.4427L20.9764 28.1808C20.1095 27.2272 18.6338 27.1569 17.6803 28.0238C16.7267 28.8906 16.6565 30.3664 17.5233 31.3199L23.3566 37.7366C23.833 38.2606 24.5216 38.5399 25.2284 38.4958C25.9353 38.4517 26.5838 38.089 26.9914 37.5098L38.0747 21.7598C38.8163 20.7059 38.5632 19.2504 37.5093 18.5088Z" fill="var(--green-400, #04B84C)"/>
</svg>
<div class="logo">
<svg xmlns="http://www.w3.org/2000/svg" width="32" height="32" fill="none" viewBox="0 0 32 32"><path stroke="#000" stroke-linecap="round" stroke-width="2.484" d="M22.356 19.797H17.17M9.662 12.29l1.979 3.576a.511.511 0 0 1-.005.504l-1.974 3.409M30.758 16c0 8.15-6.607 14.758-14.758 14.758-8.15 0-14.758-6.607-14.758-14.758C1.242 7.85 7.85 1.242 16 1.242c8.15 0 14.758 6.608 14.758 14.758Z"></path></svg>
</div>
<div class="title">Signed in to Codex CLI</div>
</div>

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-mcp-server"
version = { workspace = true }
edition = "2024"
[[bin]]
name = "codex-mcp-server"
@@ -23,9 +23,7 @@ schemars = "0.8.22"
serde = { version = "1", features = ["derive"] }
serde_json = "1"
shlex = "1.3.0"
toml = "0.9"
tracing = { version = "0.1.41", features = ["log"] }
tracing-subscriber = { version = "0.3", features = ["fmt", "env-filter"] }
strum_macros = "0.27.2"
tokio = { version = "1", features = [
"io-std",
"macros",
@@ -33,8 +31,10 @@ tokio = { version = "1", features = [
"rt-multi-thread",
"signal",
] }
toml = "0.9"
tracing = { version = "0.1.41", features = ["log"] }
tracing-subscriber = { version = "0.3", features = ["env-filter", "fmt"] }
uuid = { version = "1", features = ["serde", "v4"] }
strum_macros = "0.27.2"
[dev-dependencies]
assert_cmd = "2"

View File

@@ -258,6 +258,7 @@ async fn run_codex_tool_session_inner(
| EventMsg::McpToolCallBegin(_)
| EventMsg::McpToolCallEnd(_)
| EventMsg::ExecCommandBegin(_)
| EventMsg::ExecCommandOutputDelta(_)
| EventMsg::ExecCommandEnd(_)
| EventMsg::BackgroundEvent(_)
| EventMsg::PatchApplyBegin(_)

View File

@@ -0,0 +1,121 @@
use std::sync::Arc;
use crate::exec_approval::handle_exec_approval_request;
use crate::outgoing_message::OutgoingMessageSender;
use crate::outgoing_message::OutgoingNotificationMeta;
use crate::patch_approval::handle_patch_approval_request;
use codex_core::Codex;
use codex_core::protocol::AgentMessageEvent;
use codex_core::protocol::ApplyPatchApprovalRequestEvent;
use codex_core::protocol::EventMsg;
use codex_core::protocol::ExecApprovalRequestEvent;
use mcp_types::RequestId;
use tracing::error;
pub async fn run_conversation_loop(
codex: Arc<Codex>,
outgoing: Arc<OutgoingMessageSender>,
request_id: RequestId,
) {
let request_id_str = match &request_id {
RequestId::String(s) => s.clone(),
RequestId::Integer(n) => n.to_string(),
};
// Stream events until the task needs to pause for user interaction or
// completes.
loop {
match codex.next_event().await {
Ok(event) => {
outgoing
.send_event_as_notification(
&event,
Some(OutgoingNotificationMeta::new(Some(request_id.clone()))),
)
.await;
match event.msg {
EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
command,
cwd,
call_id,
reason: _,
}) => {
handle_exec_approval_request(
command,
cwd,
outgoing.clone(),
codex.clone(),
request_id.clone(),
request_id_str.clone(),
event.id.clone(),
call_id,
)
.await;
continue;
}
EventMsg::Error(_) => {
error!("Codex runtime error");
}
EventMsg::ApplyPatchApprovalRequest(ApplyPatchApprovalRequestEvent {
call_id,
reason,
grant_root,
changes,
}) => {
handle_patch_approval_request(
call_id,
reason,
grant_root,
changes,
outgoing.clone(),
codex.clone(),
request_id.clone(),
request_id_str.clone(),
event.id.clone(),
)
.await;
continue;
}
EventMsg::TaskComplete(_) => {}
EventMsg::SessionConfigured(_) => {
tracing::error!("unexpected SessionConfigured event");
}
EventMsg::AgentMessageDelta(_) => {
// TODO: think how we want to support this in the MCP
}
EventMsg::AgentReasoningDelta(_) => {
// TODO: think how we want to support this in the MCP
}
EventMsg::AgentMessage(AgentMessageEvent { .. }) => {
// TODO: think how we want to support this in the MCP
}
EventMsg::TaskStarted
| EventMsg::TokenCount(_)
| EventMsg::AgentReasoning(_)
| EventMsg::McpToolCallBegin(_)
| EventMsg::McpToolCallEnd(_)
| EventMsg::ExecCommandBegin(_)
| EventMsg::ExecCommandEnd(_)
| EventMsg::BackgroundEvent(_)
| EventMsg::ExecCommandOutputDelta(_)
| EventMsg::PatchApplyBegin(_)
| EventMsg::PatchApplyEnd(_)
| EventMsg::GetHistoryEntryResponse(_)
| EventMsg::PlanUpdate(_)
| EventMsg::ShutdownComplete => {
// For now, we do not do anything extra for these
// events. Note that
// send(codex_event_to_notification(&event)) above has
// already dispatched these events as notifications,
// though we may want to do give different treatment to
// individual events in the future.
}
}
}
Err(e) => {
error!("Codex runtime error: {e}");
}
}
}
}

View File

@@ -17,12 +17,14 @@ use tracing_subscriber::EnvFilter;
mod codex_tool_config;
mod codex_tool_runner;
mod conversation_loop;
mod exec_approval;
mod json_to_toml;
mod mcp_protocol;
mod message_processor;
pub mod mcp_protocol;
pub(crate) mod message_processor;
mod outgoing_message;
mod patch_approval;
pub(crate) mod tool_handlers;
use crate::message_processor::MessageProcessor;
use crate::outgoing_message::OutgoingMessage;

View File

@@ -7,7 +7,10 @@ use serde::Serialize;
use strum_macros::Display;
use uuid::Uuid;
use mcp_types::CallToolResult;
use mcp_types::ContentBlock;
use mcp_types::RequestId;
use mcp_types::TextContent;
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[serde(transparent)]
@@ -118,10 +121,47 @@ pub struct ToolCallResponse {
pub request_id: RequestId,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub is_error: Option<bool>,
#[serde(default, skip_serializing_if = "Option::is_none")]
#[serde(default, skip_serializing_if = "Option::is_none", flatten)]
pub result: Option<ToolCallResponseResult>,
}
impl From<ToolCallResponse> for CallToolResult {
fn from(val: ToolCallResponse) -> Self {
let ToolCallResponse {
request_id: _request_id,
is_error,
result,
} = val;
match result {
Some(res) => match serde_json::to_value(&res) {
Ok(v) => CallToolResult {
content: vec![ContentBlock::TextContent(TextContent {
r#type: "text".to_string(),
text: v.to_string(),
annotations: None,
})],
is_error,
structured_content: Some(v),
},
Err(e) => CallToolResult {
content: vec![ContentBlock::TextContent(TextContent {
r#type: "text".to_string(),
text: format!("Failed to serialize tool result: {e}"),
annotations: None,
})],
is_error: Some(true),
structured_content: None,
},
},
None => CallToolResult {
content: vec![],
is_error,
structured_content: None,
},
}
}
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
#[serde(untagged)]
pub enum ToolCallResponseResult {
@@ -132,17 +172,26 @@ pub enum ToolCallResponseResult {
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
pub struct ConversationCreateResult {
pub conversation_id: ConversationId,
pub model: String,
#[serde(untagged)]
pub enum ConversationCreateResult {
Ok {
conversation_id: ConversationId,
model: String,
},
Error {
message: String,
},
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
pub struct ConversationStreamResult {}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
pub struct ConversationSendMessageResult {
pub success: bool,
// TODO: remove this status because we have is_error field in the response.
#[serde(tag = "status", rename_all = "camelCase")]
pub enum ConversationSendMessageResult {
Ok,
Error { message: String },
}
#[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
@@ -449,16 +498,19 @@ mod tests {
request_id: RequestId::Integer(1),
is_error: None,
result: Some(ToolCallResponseResult::ConversationCreate(
ConversationCreateResult {
ConversationCreateResult::Ok {
conversation_id: ConversationId(uuid!("d0f6ecbe-84a2-41c1-b23d-b20473b25eab")),
model: "o3".into(),
},
)),
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 1,
"result": {
"content": [
{ "type": "text", "text": "{\"conversation_id\":\"d0f6ecbe-84a2-41c1-b23d-b20473b25eab\",\"model\":\"o3\"}" }
],
"structuredContent": {
"conversation_id": "d0f6ecbe-84a2-41c1-b23d-b20473b25eab",
"model": "o3"
}
@@ -467,6 +519,36 @@ mod tests {
observed, expected,
"response (ConversationCreate) must match"
);
assert_eq!(req_id, RequestId::Integer(1));
}
#[test]
fn response_error_conversation_create_full_schema() {
let env = ToolCallResponse {
request_id: RequestId::Integer(2),
is_error: Some(true),
result: Some(ToolCallResponseResult::ConversationCreate(
ConversationCreateResult::Error {
message: "Failed to initialize session".into(),
},
)),
};
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"content": [
{ "type": "text", "text": "{\"message\":\"Failed to initialize session\"}" }
],
"isError": true,
"structuredContent": {
"message": "Failed to initialize session"
}
});
assert_eq!(
observed, expected,
"error response (ConversationCreate) must match"
);
assert_eq!(req_id, RequestId::Integer(2));
}
#[test]
@@ -478,15 +560,17 @@ mod tests {
ConversationStreamResult {},
)),
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 2,
"result": {}
"content": [ { "type": "text", "text": "{}" } ],
"structuredContent": {}
});
assert_eq!(
observed, expected,
"response (ConversationStream) must have empty object result"
);
assert_eq!(req_id, RequestId::Integer(2));
}
#[test]
@@ -495,18 +579,20 @@ mod tests {
request_id: RequestId::Integer(3),
is_error: None,
result: Some(ToolCallResponseResult::ConversationSendMessage(
ConversationSendMessageResult { success: true },
ConversationSendMessageResult::Ok,
)),
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 3,
"result": { "success": true }
"content": [ { "type": "text", "text": "{\"status\":\"ok\"}" } ],
"structuredContent": { "status": "ok" }
});
assert_eq!(
observed, expected,
"response (ConversationSendMessageAccepted) must match"
);
assert_eq!(req_id, RequestId::Integer(3));
}
#[test]
@@ -526,10 +612,13 @@ mod tests {
},
)),
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 4,
"result": {
"content": [
{ "type": "text", "text": "{\"conversations\":[{\"conversation_id\":\"67e55044-10b1-426f-9247-bb680e5fe0c8\",\"title\":\"Refactor config loader\"}],\"next_cursor\":\"next123\"}" }
],
"structuredContent": {
"conversations": [
{
"conversation_id": "67e55044-10b1-426f-9247-bb680e5fe0c8",
@@ -543,6 +632,7 @@ mod tests {
observed, expected,
"response (ConversationsList with cursor) must match"
);
assert_eq!(req_id, RequestId::Integer(4));
}
#[test]
@@ -552,15 +642,17 @@ mod tests {
is_error: Some(true),
result: None,
};
let observed = to_val(&env);
let req_id = env.request_id.clone();
let observed = to_val(&CallToolResult::from(env));
let expected = json!({
"requestId": 4,
"content": [],
"isError": true
});
assert_eq!(
observed, expected,
"error response must omit `result` and include `isError`"
);
assert_eq!(req_id, RequestId::Integer(4));
}
// ----- Notifications -----

View File

@@ -1,4 +1,5 @@
use std::collections::HashMap;
use std::collections::HashSet;
use std::path::PathBuf;
use std::sync::Arc;
@@ -6,11 +7,17 @@ use crate::codex_tool_config::CodexToolCallParam;
use crate::codex_tool_config::CodexToolCallReplyParam;
use crate::codex_tool_config::create_tool_for_codex_tool_call_param;
use crate::codex_tool_config::create_tool_for_codex_tool_call_reply_param;
use crate::mcp_protocol::ToolCallRequestParams;
use crate::mcp_protocol::ToolCallResponse;
use crate::mcp_protocol::ToolCallResponseResult;
use crate::outgoing_message::OutgoingMessageSender;
use crate::tool_handlers::create_conversation::handle_create_conversation;
use crate::tool_handlers::send_message::handle_send_message;
use codex_core::Codex;
use codex_core::config::Config as CodexConfig;
use codex_core::protocol::Submission;
use mcp_types::CallToolRequest;
use mcp_types::CallToolRequestParams;
use mcp_types::CallToolResult;
use mcp_types::ClientRequest;
@@ -37,6 +44,7 @@ pub(crate) struct MessageProcessor {
codex_linux_sandbox_exe: Option<PathBuf>,
session_map: Arc<Mutex<HashMap<Uuid, Arc<Codex>>>>,
running_requests_id_to_codex_uuid: Arc<Mutex<HashMap<RequestId, Uuid>>>,
running_session_ids: Arc<Mutex<HashSet<Uuid>>>,
}
impl MessageProcessor {
@@ -52,9 +60,22 @@ impl MessageProcessor {
codex_linux_sandbox_exe,
session_map: Arc::new(Mutex::new(HashMap::new())),
running_requests_id_to_codex_uuid: Arc::new(Mutex::new(HashMap::new())),
running_session_ids: Arc::new(Mutex::new(HashSet::new())),
}
}
pub(crate) fn session_map(&self) -> Arc<Mutex<HashMap<Uuid, Arc<Codex>>>> {
self.session_map.clone()
}
pub(crate) fn outgoing(&self) -> Arc<OutgoingMessageSender> {
self.outgoing.clone()
}
pub(crate) fn running_session_ids(&self) -> Arc<Mutex<HashSet<Uuid>>> {
self.running_session_ids.clone()
}
pub(crate) async fn process_request(&mut self, request: JSONRPCRequest) {
// Hold on to the ID so we can respond.
let request_id = request.id.clone();
@@ -300,6 +321,14 @@ impl MessageProcessor {
params: <mcp_types::CallToolRequest as mcp_types::ModelContextProtocolRequest>::Params,
) {
tracing::info!("tools/call -> params: {:?}", params);
// Serialize params into JSON and try to parse as new type
if let Ok(new_params) =
serde_json::to_value(&params).and_then(serde_json::from_value::<ToolCallRequestParams>)
{
// New tool call matched → forward
self.handle_new_tool_calls(id, new_params).await;
return;
}
let CallToolRequestParams { name, arguments } = params;
match name.as_str() {
@@ -323,6 +352,29 @@ impl MessageProcessor {
}
}
}
async fn handle_new_tool_calls(&self, request_id: RequestId, params: ToolCallRequestParams) {
match params {
ToolCallRequestParams::ConversationCreate(args) => {
handle_create_conversation(self, request_id, args).await;
}
ToolCallRequestParams::ConversationSendMessage(args) => {
handle_send_message(self, request_id, args).await;
}
_ => {
let result = CallToolResult {
content: vec![ContentBlock::TextContent(TextContent {
r#type: "text".to_string(),
text: "Unknown tool".to_string(),
annotations: None,
})],
is_error: Some(true),
structured_content: None,
};
self.send_response::<CallToolRequest>(request_id, result)
.await;
}
}
}
async fn handle_tool_call_codex(&self, id: RequestId, arguments: Option<serde_json::Value>) {
let (initial_prompt, config): (String, CodexConfig) = match arguments {
@@ -631,4 +683,20 @@ impl MessageProcessor {
) {
tracing::info!("notifications/message -> params: {:?}", params);
}
pub(crate) async fn send_response_with_optional_error(
&self,
id: RequestId,
message: Option<ToolCallResponseResult>,
error: Option<bool>,
) {
let response = ToolCallResponse {
request_id: id.clone(),
is_error: error,
result: message,
};
let result: CallToolResult = response.into();
self.send_response::<mcp_types::CallToolRequest>(id.clone(), result)
.await;
}
}

View File

@@ -0,0 +1,160 @@
use std::collections::HashMap;
use std::path::PathBuf;
use std::sync::Arc;
use codex_core::Codex;
use codex_core::codex_wrapper::init_codex;
use codex_core::config::Config as CodexConfig;
use codex_core::config::ConfigOverrides;
use codex_core::protocol::EventMsg;
use codex_core::protocol::SessionConfiguredEvent;
use mcp_types::RequestId;
use tokio::sync::Mutex;
use uuid::Uuid;
use crate::conversation_loop::run_conversation_loop;
use crate::json_to_toml::json_to_toml;
use crate::mcp_protocol::ConversationCreateArgs;
use crate::mcp_protocol::ConversationCreateResult;
use crate::mcp_protocol::ConversationId;
use crate::mcp_protocol::ToolCallResponseResult;
use crate::message_processor::MessageProcessor;
pub(crate) async fn handle_create_conversation(
message_processor: &MessageProcessor,
id: RequestId,
args: ConversationCreateArgs,
) {
// Build ConfigOverrides from args
let ConversationCreateArgs {
prompt: _, // not used here; creation only establishes the session
model,
cwd,
approval_policy,
sandbox,
config,
profile,
base_instructions,
} = args;
// Convert config overrides JSON into CLI-style TOML overrides
let cli_overrides: Vec<(String, toml::Value)> = match config {
Some(v) => match v.as_object() {
Some(map) => map
.into_iter()
.map(|(k, v)| (k.clone(), json_to_toml(v.clone())))
.collect(),
None => Vec::new(),
},
None => Vec::new(),
};
let overrides = ConfigOverrides {
model: Some(model.clone()),
cwd: Some(PathBuf::from(cwd)),
approval_policy,
sandbox_mode: sandbox,
model_provider: None,
config_profile: profile,
codex_linux_sandbox_exe: None,
base_instructions,
include_plan_tool: None,
};
let cfg: CodexConfig = match CodexConfig::load_with_cli_overrides(cli_overrides, overrides) {
Ok(cfg) => cfg,
Err(e) => {
message_processor
.send_response_with_optional_error(
id,
Some(ToolCallResponseResult::ConversationCreate(
ConversationCreateResult::Error {
message: format!("Failed to load config: {e}"),
},
)),
Some(true),
)
.await;
return;
}
};
// Initialize Codex session
let codex_conversation = match init_codex(cfg).await {
Ok(conv) => conv,
Err(e) => {
message_processor
.send_response_with_optional_error(
id,
Some(ToolCallResponseResult::ConversationCreate(
ConversationCreateResult::Error {
message: format!("Failed to initialize session: {e}"),
},
)),
Some(true),
)
.await;
return;
}
};
// Expect SessionConfigured; if not, return error.
let EventMsg::SessionConfigured(SessionConfiguredEvent { model, .. }) =
&codex_conversation.session_configured.msg
else {
message_processor
.send_response_with_optional_error(
id,
Some(ToolCallResponseResult::ConversationCreate(
ConversationCreateResult::Error {
message: "Expected SessionConfigured event".to_string(),
},
)),
Some(true),
)
.await;
return;
};
let effective_model = model.clone();
let session_id = codex_conversation.session_id;
let codex_arc = Arc::new(codex_conversation.codex);
// Store session for future calls
insert_session(
session_id,
codex_arc.clone(),
message_processor.session_map(),
)
.await;
// Run the conversation loop in the background so this request can return immediately.
let outgoing = message_processor.outgoing();
let spawn_id = id.clone();
tokio::spawn(async move {
run_conversation_loop(codex_arc.clone(), outgoing, spawn_id).await;
});
// Reply with the new conversation id and effective model
message_processor
.send_response_with_optional_error(
id,
Some(ToolCallResponseResult::ConversationCreate(
ConversationCreateResult::Ok {
conversation_id: ConversationId(session_id),
model: effective_model,
},
)),
Some(false),
)
.await;
}
async fn insert_session(
session_id: Uuid,
codex: Arc<Codex>,
session_map: Arc<Mutex<HashMap<Uuid, Arc<Codex>>>>,
) {
let mut guard = session_map.lock().await;
guard.insert(session_id, codex);
}

View File

@@ -0,0 +1,2 @@
pub(crate) mod create_conversation;
pub(crate) mod send_message;

View File

@@ -0,0 +1,124 @@
use std::collections::HashMap;
use std::sync::Arc;
use codex_core::Codex;
use codex_core::protocol::Op;
use codex_core::protocol::Submission;
use mcp_types::RequestId;
use tokio::sync::Mutex;
use uuid::Uuid;
use crate::mcp_protocol::ConversationSendMessageArgs;
use crate::mcp_protocol::ConversationSendMessageResult;
use crate::mcp_protocol::ToolCallResponseResult;
use crate::message_processor::MessageProcessor;
pub(crate) async fn handle_send_message(
message_processor: &MessageProcessor,
id: RequestId,
arguments: ConversationSendMessageArgs,
) {
let ConversationSendMessageArgs {
conversation_id,
content: items,
parent_message_id: _,
conversation_overrides: _,
} = arguments;
if items.is_empty() {
message_processor
.send_response_with_optional_error(
id,
Some(ToolCallResponseResult::ConversationSendMessage(
ConversationSendMessageResult::Error {
message: "No content items provided".to_string(),
},
)),
Some(true),
)
.await;
return;
}
let session_id = conversation_id.0;
let Some(codex) = get_session(session_id, message_processor.session_map()).await else {
message_processor
.send_response_with_optional_error(
id,
Some(ToolCallResponseResult::ConversationSendMessage(
ConversationSendMessageResult::Error {
message: "Session does not exist".to_string(),
},
)),
Some(true),
)
.await;
return;
};
let running = {
let running_sessions = message_processor.running_session_ids();
let mut running_sessions = running_sessions.lock().await;
!running_sessions.insert(session_id)
};
if running {
message_processor
.send_response_with_optional_error(
id,
Some(ToolCallResponseResult::ConversationSendMessage(
ConversationSendMessageResult::Error {
message: "Session is already running".to_string(),
},
)),
Some(true),
)
.await;
return;
}
let request_id_string = match &id {
RequestId::String(s) => s.clone(),
RequestId::Integer(i) => i.to_string(),
};
let submit_res = codex
.submit_with_id(Submission {
id: request_id_string,
op: Op::UserInput { items },
})
.await;
if let Err(e) = submit_res {
message_processor
.send_response_with_optional_error(
id,
Some(ToolCallResponseResult::ConversationSendMessage(
ConversationSendMessageResult::Error {
message: format!("Failed to submit user input: {e}"),
},
)),
Some(true),
)
.await;
return;
}
message_processor
.send_response_with_optional_error(
id,
Some(ToolCallResponseResult::ConversationSendMessage(
ConversationSendMessageResult::Ok,
)),
Some(false),
)
.await;
}
pub(crate) async fn get_session(
session_id: Uuid,
session_map: Arc<Mutex<HashMap<Uuid, Arc<Codex>>>>,
) -> Option<Arc<Codex>> {
let guard = session_map.lock().await;
guard.get(&session_id).cloned()
}

View File

@@ -3,9 +3,9 @@ use std::env;
use std::path::Path;
use std::path::PathBuf;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::protocol::FileChange;
use codex_core::protocol::ReviewDecision;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_mcp_server::CodexToolCallParam;
use codex_mcp_server::ExecApprovalElicitRequestParams;
use codex_mcp_server::ExecApprovalResponse;

View File

@@ -10,6 +10,7 @@ path = "lib.rs"
anyhow = "1"
assert_cmd = "2"
codex-mcp-server = { path = "../.." }
codex-core = { path = "../../../core" }
mcp-types = { path = "../../../mcp-types" }
pretty_assertions = "1.4.1"
serde_json = "1"
@@ -22,3 +23,4 @@ tokio = { version = "1", features = [
"rt-multi-thread",
] }
wiremock = "0.6"
uuid = { version = "1", features = ["serde", "v4"] }

View File

@@ -11,8 +11,14 @@ use tokio::process::ChildStdout;
use anyhow::Context;
use assert_cmd::prelude::*;
use codex_core::protocol::InputItem;
use codex_mcp_server::CodexToolCallParam;
use codex_mcp_server::CodexToolCallReplyParam;
use codex_mcp_server::mcp_protocol::ConversationCreateArgs;
use codex_mcp_server::mcp_protocol::ConversationId;
use codex_mcp_server::mcp_protocol::ConversationSendMessageArgs;
use codex_mcp_server::mcp_protocol::ToolCallRequestParams;
use mcp_types::CallToolRequestParams;
use mcp_types::ClientCapabilities;
use mcp_types::Implementation;
@@ -29,6 +35,7 @@ use pretty_assertions::assert_eq;
use serde_json::json;
use std::process::Command as StdCommand;
use tokio::process::Command;
use uuid::Uuid;
pub struct McpProcess {
next_request_id: AtomicI64,
@@ -174,6 +181,61 @@ impl McpProcess {
.await
}
pub async fn send_user_message_tool_call(
&mut self,
message: &str,
session_id: &str,
) -> anyhow::Result<i64> {
let params = ToolCallRequestParams::ConversationSendMessage(ConversationSendMessageArgs {
conversation_id: ConversationId(Uuid::parse_str(session_id)?),
content: vec![InputItem::Text {
text: message.to_string(),
}],
parent_message_id: None,
conversation_overrides: None,
});
self.send_request(
mcp_types::CallToolRequest::METHOD,
Some(serde_json::to_value(params)?),
)
.await
}
pub async fn send_conversation_create_tool_call(
&mut self,
prompt: &str,
model: &str,
cwd: &str,
) -> anyhow::Result<i64> {
let params = ToolCallRequestParams::ConversationCreate(ConversationCreateArgs {
prompt: prompt.to_string(),
model: model.to_string(),
cwd: cwd.to_string(),
approval_policy: None,
sandbox: None,
config: None,
profile: None,
base_instructions: None,
});
self.send_request(
mcp_types::CallToolRequest::METHOD,
Some(serde_json::to_value(params)?),
)
.await
}
pub async fn send_conversation_create_with_args(
&mut self,
args: ConversationCreateArgs,
) -> anyhow::Result<i64> {
let params = ToolCallRequestParams::ConversationCreate(args);
self.send_request(
mcp_types::CallToolRequest::METHOD,
Some(serde_json::to_value(params)?),
)
.await
}
async fn send_request(
&mut self,
method: &str,

View File

@@ -0,0 +1,128 @@
#![allow(clippy::expect_used, clippy::unwrap_used)]
use std::path::Path;
use mcp_test_support::McpProcess;
use mcp_test_support::create_final_assistant_message_sse_response;
use mcp_test_support::create_mock_chat_completions_server;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use pretty_assertions::assert_eq;
use serde_json::json;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn test_conversation_create_and_send_message_ok() {
// Mock server we won't strictly rely on it, but provide one to satisfy any model wiring.
let responses = vec![
create_final_assistant_message_sse_response("Done").expect("build mock assistant message"),
];
let server = create_mock_chat_completions_server(responses).await;
// Temporary Codex home with config pointing at the mock server.
let codex_home = TempDir::new().expect("create temp dir");
create_config_toml(codex_home.path(), &server.uri()).expect("write config.toml");
// Start MCP server process and initialize.
let mut mcp = McpProcess::new(codex_home.path())
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("init timeout")
.expect("init failed");
// Create a conversation via the new tool.
let req_id = mcp
.send_conversation_create_tool_call("", "o3", "/repo")
.await
.expect("send conversationCreate");
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
)
.await
.expect("create response timeout")
.expect("create response error");
// Structured content must include status=ok, a UUID conversation_id and the model we passed.
let sc = &resp.result["structuredContent"];
let conv_id = sc["conversation_id"].as_str().expect("uuid string");
assert!(!conv_id.is_empty());
assert_eq!(sc["model"], json!("o3"));
// Now send a message to the created conversation and expect an OK result.
let send_id = mcp
.send_user_message_tool_call("Hello", conv_id)
.await
.expect("send message");
let send_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(send_id)),
)
.await
.expect("send response timeout")
.expect("send response error");
assert_eq!(
send_resp.result["structuredContent"],
json!({ "status": "ok" })
);
// avoid race condition by waiting for the mock server to receive the chat.completions request
let deadline = std::time::Instant::now() + DEFAULT_READ_TIMEOUT;
loop {
let requests = server.received_requests().await.unwrap_or_default();
if !requests.is_empty() {
break;
}
if std::time::Instant::now() >= deadline {
panic!("mock server did not receive the chat.completions request in time");
}
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
}
// Verify the outbound request body matches expectations for Chat Completions.
let request = &server.received_requests().await.unwrap()[0];
let body = request
.body_json::<serde_json::Value>()
.expect("parse request body as JSON");
assert_eq!(body["model"], json!("o3"));
assert!(body["stream"].as_bool().unwrap_or(false));
let messages = body["messages"]
.as_array()
.expect("messages should be array");
let last = messages.last().expect("at least one message");
assert_eq!(last["role"], json!("user"));
assert_eq!(last["content"], json!("Hello"));
drop(server);
}
// Helper to create a config.toml pointing at the mock model server.
fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
format!(
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "danger-full-access"
model_provider = "mock_provider"
[model_providers.mock_provider]
name = "Mock provider for test"
base_url = "{server_uri}/v1"
wire_api = "chat"
request_max_retries = 0
stream_max_retries = 0
"#
),
)
}

View File

@@ -3,7 +3,7 @@
use std::path::Path;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_mcp_server::CodexToolCallParam;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;

View File

@@ -0,0 +1,163 @@
#![allow(clippy::expect_used)]
use std::path::Path;
use std::thread::sleep;
use std::time::Duration;
use codex_mcp_server::CodexToolCallParam;
use mcp_test_support::McpProcess;
use mcp_test_support::create_final_assistant_message_sse_response;
use mcp_test_support::create_mock_chat_completions_server;
use mcp_types::JSONRPC_VERSION;
use mcp_types::JSONRPCResponse;
use mcp_types::RequestId;
use pretty_assertions::assert_eq;
use serde_json::json;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn test_send_message_success() {
// Spin up a mock completions server that immediately ends the Codex turn.
// Two Codex turns hit the mock model (session start + send-user-message). Provide two SSE responses.
let responses = vec![
create_final_assistant_message_sse_response("Done").expect("build mock assistant message"),
create_final_assistant_message_sse_response("Done").expect("build mock assistant message"),
];
let server = create_mock_chat_completions_server(responses).await;
// Create a temporary Codex home with config pointing at the mock server.
let codex_home = TempDir::new().expect("create temp dir");
create_config_toml(codex_home.path(), &server.uri()).expect("write config.toml");
// Start MCP server process and initialize.
let mut mcp_process = McpProcess::new(codex_home.path())
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp_process.initialize())
.await
.expect("init timed out")
.expect("init failed");
// Kick off a Codex session so we have a valid session_id.
let codex_request_id = mcp_process
.send_codex_tool_call(CodexToolCallParam {
prompt: "Start a session".to_string(),
..Default::default()
})
.await
.expect("send codex tool call");
// Wait for the session_configured event to get the session_id.
let session_id = mcp_process
.read_stream_until_configured_response_message()
.await
.expect("read session_configured");
// The original codex call will finish quickly given our mock; consume its response.
timeout(
DEFAULT_READ_TIMEOUT,
mcp_process.read_stream_until_response_message(RequestId::Integer(codex_request_id)),
)
.await
.expect("codex response timeout")
.expect("codex response error");
// Now exercise the send-user-message tool.
let send_msg_request_id = mcp_process
.send_user_message_tool_call("Hello again", &session_id)
.await
.expect("send send-message tool call");
let response: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp_process.read_stream_until_response_message(RequestId::Integer(send_msg_request_id)),
)
.await
.expect("send-user-message response timeout")
.expect("send-user-message response error");
assert_eq!(
JSONRPCResponse {
jsonrpc: JSONRPC_VERSION.into(),
id: RequestId::Integer(send_msg_request_id),
result: json!({
"content": [
{
"text": "{\"status\":\"ok\"}",
"type": "text",
}
],
"isError": false,
"structuredContent": {
"status": "ok"
}
}),
},
response
);
// wait for the server to hear the user message
sleep(Duration::from_secs(1));
// Ensure the server and tempdir live until end of test
drop(server);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn test_send_message_session_not_found() {
// Start MCP without creating a Codex session
let codex_home = TempDir::new().expect("tempdir");
let mut mcp = McpProcess::new(codex_home.path()).await.expect("spawn");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("timeout")
.expect("init");
let unknown = uuid::Uuid::new_v4().to_string();
let req_id = mcp
.send_user_message_tool_call("ping", &unknown)
.await
.expect("send tool");
let resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
)
.await
.expect("timeout")
.expect("resp");
let result = resp.result.clone();
let content = result["content"][0]["text"].as_str().unwrap_or("");
assert!(content.contains("Session does not exist"));
assert_eq!(result["isError"], json!(true));
}
// ---------------------------------------------------------------------------
// Helpers
// ---------------------------------------------------------------------------
fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
let config_toml = codex_home.join("config.toml");
std::fs::write(
config_toml,
format!(
r#"
model = "mock-model"
approval_policy = "never"
sandbox_mode = "danger-full-access"
model_provider = "mock_provider"
[model_providers.mock_provider]
name = "Mock provider for test"
base_url = "{server_uri}/v1"
wire_api = "chat"
request_max_retries = 0
stream_max_retries = 0
"#
),
)
}

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "mcp-types"
version = { workspace = true }
edition = "2024"
[lints]
workspace = true

View File

@@ -1,7 +1,7 @@
[package]
edition = "2024"
name = "codex-tui"
version = { workspace = true }
edition = "2024"
[[bin]]
name = "codex-tui"
@@ -17,15 +17,16 @@ workspace = true
[dependencies]
anyhow = "1"
base64 = "0.22.1"
chrono = { version = "0.4", features = ["serde"] }
clap = { version = "4", features = ["derive"] }
codex-ansi-escape = { path = "../ansi-escape" }
codex-arg0 = { path = "../arg0" }
codex-core = { path = "../core" }
codex-common = { path = "../common", features = [
"cli",
"elapsed",
"sandbox_summary",
] }
codex-core = { path = "../core" }
codex-file-search = { path = "../file-search" }
codex-login = { path = "../login" }
color-eyre = "0.6.3"
@@ -41,6 +42,8 @@ ratatui = { version = "0.29.0", features = [
] }
ratatui-image = "8.0.0"
regex-lite = "0.1"
reqwest = { version = "0.12", features = ["json"] }
serde = { version = "1", features = ["derive"] }
serde_json = { version = "1", features = ["preserve_order"] }
shlex = "1.3.0"
strum = "0.27.2"
@@ -62,6 +65,8 @@ unicode-segmentation = "1.12.0"
unicode-width = "0.1"
uuid = "1"
[dev-dependencies]
insta = "1.43.1"
pretty_assertions = "1"

View File

@@ -12,8 +12,14 @@ use codex_core::protocol::Event;
use codex_core::protocol::EventMsg;
use codex_core::protocol::Op;
use color_eyre::eyre::Result;
use crossterm::SynchronizedUpdate;
use crossterm::event::KeyCode;
use crossterm::event::KeyEvent;
use crossterm::event::KeyEventKind;
use crossterm::terminal::supports_keyboard_enhancement;
use ratatui::layout::Offset;
use ratatui::prelude::Backend;
use ratatui::text::Line;
use std::path::PathBuf;
use std::sync::Arc;
use std::sync::atomic::AtomicBool;
@@ -52,12 +58,23 @@ pub(crate) struct App<'a> {
/// True when a redraw has been scheduled but not yet executed.
pending_redraw: Arc<AtomicBool>,
pending_history_lines: Vec<Line<'static>>,
/// Stored parameters needed to instantiate the ChatWidget later, e.g.,
/// after dismissing the Git-repo warning.
chat_args: Option<ChatWidgetArgs>,
/// Tracks pending summarization requests for the compact feature.
pending_summarization: Option<PendingSummarization>,
enhanced_keys_supported: bool,
}
/// Aggregate parameters needed to create a `ChatWidget`, as creation may be
/// deferred until after the Git warning screen is dismissed.
#[derive(Clone)]
struct ChatWidgetArgs {
config: Config,
initial_prompt: Option<String>,
initial_images: Vec<PathBuf>,
enhanced_keys_supported: bool,
}
impl App<'_> {
@@ -71,6 +88,8 @@ impl App<'_> {
let app_event_tx = AppEventSender::new(app_event_tx);
let pending_redraw = Arc::new(AtomicBool::new(false));
let enhanced_keys_supported = supports_keyboard_enhancement().unwrap_or(false);
// Spawn a dedicated thread for reading the crossterm event loop and
// re-publishing the events as AppEvents, as appropriate.
{
@@ -123,6 +142,7 @@ impl App<'_> {
config: config.clone(),
initial_prompt,
initial_images,
enhanced_keys_supported,
}),
)
} else {
@@ -131,6 +151,7 @@ impl App<'_> {
app_event_tx.clone(),
initial_prompt,
initial_images,
enhanced_keys_supported,
);
(
AppState::Chat {
@@ -143,13 +164,14 @@ impl App<'_> {
let file_search = FileSearchManager::new(config.cwd.clone(), app_event_tx.clone());
Self {
app_event_tx,
pending_history_lines: Vec::new(),
app_event_rx,
app_state,
config,
file_search,
pending_redraw,
chat_args,
pending_summarization: None,
enhanced_keys_supported,
}
}
@@ -189,20 +211,21 @@ impl App<'_> {
while let Ok(event) = self.app_event_rx.recv() {
match event {
AppEvent::InsertHistory(lines) => {
crate::insert_history::insert_history_lines(terminal, lines);
self.pending_history_lines.extend(lines);
self.app_event_tx.send(AppEvent::RequestRedraw);
}
AppEvent::RequestRedraw => {
self.schedule_redraw();
}
AppEvent::Redraw => {
self.draw_next_frame(terminal)?;
std::io::stdout().sync_update(|_| self.draw_next_frame(terminal))??;
}
AppEvent::KeyEvent(key_event) => {
match key_event {
KeyEvent {
code: KeyCode::Char('c'),
modifiers: crossterm::event::KeyModifiers::CONTROL,
kind: KeyEventKind::Press,
..
} => {
match &mut self.app_state {
@@ -217,6 +240,7 @@ impl App<'_> {
KeyEvent {
code: KeyCode::Char('d'),
modifiers: crossterm::event::KeyModifiers::CONTROL,
kind: KeyEventKind::Press,
..
} => {
match &mut self.app_state {
@@ -235,9 +259,15 @@ impl App<'_> {
}
}
}
_ => {
KeyEvent {
kind: KeyEventKind::Press | KeyEventKind::Repeat,
..
} => {
self.dispatch_key_event(key_event);
}
_ => {
// Ignore Release key events for now.
}
};
}
AppEvent::Paste(text) => {
@@ -264,20 +294,15 @@ impl App<'_> {
self.app_event_tx.clone(),
None,
Vec::new(),
self.enhanced_keys_supported,
));
self.app_state = AppState::Chat { widget: new_widget };
self.app_event_tx.send(AppEvent::RequestRedraw);
}
SlashCommand::Compact => {
if let AppState::Chat { widget } = &mut self.app_state {
// Submit the summarization request to the current widget
widget.submit_op(Op::SummarizeContext);
// Set up tracking for the summary response
self.pending_summarization = Some(PendingSummarization {
summary_buffer: String::new(),
started_receiving: false,
});
widget.clear_token_usage();
self.app_event_tx.send(AppEvent::CodexOp(Op::Compact));
}
}
SlashCommand::Quit => {
@@ -304,6 +329,45 @@ impl App<'_> {
widget.add_diff_output(text);
}
}
#[cfg(debug_assertions)]
SlashCommand::TestApproval => {
use std::collections::HashMap;
use codex_core::protocol::ApplyPatchApprovalRequestEvent;
use codex_core::protocol::FileChange;
self.app_event_tx.send(AppEvent::CodexEvent(Event {
id: "1".to_string(),
// msg: EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
// call_id: "1".to_string(),
// command: vec!["git".into(), "apply".into()],
// cwd: self.config.cwd.clone(),
// reason: Some("test".to_string()),
// }),
msg: EventMsg::ApplyPatchApprovalRequest(
ApplyPatchApprovalRequestEvent {
call_id: "1".to_string(),
changes: HashMap::from([
(
PathBuf::from("/tmp/test.txt"),
FileChange::Add {
content: "test".to_string(),
},
),
(
PathBuf::from("/tmp/test2.txt"),
FileChange::Update {
unified_diff: "+test\n-test2".to_string(),
move_path: None,
},
),
]),
reason: None,
grant_root: Some(PathBuf::from("/tmp")),
},
),
}));
}
},
AppEvent::StartFileSearch(query) => {
self.file_search.on_user_query(query);
@@ -328,8 +392,52 @@ impl App<'_> {
}
fn draw_next_frame(&mut self, terminal: &mut tui::Tui) -> Result<()> {
// TODO: add a throttle to avoid redrawing too often
let screen_size = terminal.size()?;
let last_known_screen_size = terminal.last_known_screen_size;
if screen_size != last_known_screen_size {
let cursor_pos = terminal.get_cursor_position()?;
let last_known_cursor_pos = terminal.last_known_cursor_pos;
if cursor_pos.y != last_known_cursor_pos.y {
// The terminal was resized. The only point of reference we have for where our viewport
// was moved is the cursor position.
// NB this assumes that the cursor was not wrapped as part of the resize.
let cursor_delta = cursor_pos.y as i32 - last_known_cursor_pos.y as i32;
let new_viewport_area = terminal.viewport_area.offset(Offset {
x: 0,
y: cursor_delta,
});
terminal.set_viewport_area(new_viewport_area);
terminal.clear()?;
}
}
let size = terminal.size()?;
let desired_height = match &self.app_state {
AppState::Chat { widget } => widget.desired_height(size.width),
AppState::GitWarning { .. } => 10,
};
let mut area = terminal.viewport_area;
area.height = desired_height.min(size.height);
area.width = size.width;
if area.bottom() > size.height {
terminal
.backend_mut()
.scroll_region_up(0..area.top(), area.bottom() - size.height)?;
area.y = size.height - area.height;
}
if area != terminal.viewport_area {
terminal.clear()?;
terminal.set_viewport_area(area);
}
if !self.pending_history_lines.is_empty() {
crate::insert_history::insert_history_lines(
terminal,
self.pending_history_lines.clone(),
);
self.pending_history_lines.clear();
}
match &mut self.app_state {
AppState::Chat { widget } => {
terminal.draw(|frame| frame.render_widget_ref(&**widget, frame.area()))?;
@@ -361,6 +469,7 @@ impl App<'_> {
self.app_event_tx.clone(),
args.initial_prompt,
args.initial_images,
args.enhanced_keys_supported,
));
self.app_state = AppState::Chat { widget };
self.app_event_tx.send(AppEvent::RequestRedraw);
@@ -383,113 +492,9 @@ impl App<'_> {
}
fn dispatch_codex_event(&mut self, event: Event) {
// First check if we're waiting for a summarization response
if self.pending_summarization.is_some() {
self.handle_summarization_response(event);
return;
}
// Otherwise dispatch to the current app state
match &mut self.app_state {
AppState::Chat { widget } => widget.handle_codex_event(event),
AppState::GitWarning { .. } => {}
}
}
/// Handles responses during a summarization request.
fn handle_summarization_response(&mut self, event: Event) {
match &event.msg {
EventMsg::AgentMessage(msg) => {
// Only collect messages once we've started receiving the summarization
if let Some(ref mut pending) = self.pending_summarization {
// Start collecting once we see a message that looks like a summary
if !pending.started_receiving && msg.message.contains("summarize") {
pending.started_receiving = true;
}
if pending.started_receiving {
pending.summary_buffer.push_str(&msg.message);
pending.summary_buffer.push('\n');
}
}
}
EventMsg::TaskComplete(_) => {
// Task is complete, now create a new widget with the summary
if let Some(pending) = self.pending_summarization.take() {
let summary = create_compact_summary_prompt(&pending.summary_buffer);
// Create new widget with summary as initial prompt
let new_widget = Box::new(ChatWidget::new(
self.config.clone(),
self.app_event_tx.clone(),
Some(summary),
Vec::new(),
));
self.app_state = AppState::Chat { widget: new_widget };
self.app_event_tx.send(AppEvent::Redraw);
}
}
_ => {}
}
}
}
/// State for tracking a pending summarization request.
struct PendingSummarization {
/// Buffer to collect the summary response.
summary_buffer: String,
/// Whether we've received the first message of the summarization response.
started_receiving: bool,
}
/// Aggregate parameters needed to create a `ChatWidget`, as creation may be
/// deferred until after the Git warning screen is dismissed.
#[derive(Clone)]
struct ChatWidgetArgs {
config: Config,
initial_prompt: Option<String>,
initial_images: Vec<PathBuf>,
}
/// Creates the initial prompt for a compacted conversation.
fn create_compact_summary_prompt(summary_text: &str) -> String {
if summary_text.trim().is_empty() {
"Previous conversation has been summarized.".to_string()
} else {
format!(
r#"This chat is a continuation of a previous conversation. After providing the summary, acknowledge that /compact command has been applied. Here is the summary of the previous conversation:
{}"#,
summary_text.trim()
)
}
}
#[cfg(test)]
mod tests {
#![allow(clippy::unwrap_used)]
use super::*;
#[test]
fn test_summary_buffer_accumulation() {
let mut buffer = String::new();
// Simulate the way we accumulate messages in pending_summarization
buffer.push_str("First message part");
buffer.push('\n');
buffer.push_str("Second message part");
buffer.push('\n');
buffer.push_str("Final message part");
let prompt = create_compact_summary_prompt(&buffer);
// Should contain all parts
assert!(prompt.contains("First message part"));
assert!(prompt.contains("Second message part"));
assert!(prompt.contains("Final message part"));
// Should preserve newlines in the content
let trimmed_buffer = buffer.trim();
assert!(prompt.contains(trimmed_buffer));
}
}

View File

@@ -6,7 +6,7 @@ use ratatui::text::Line;
use crate::slash_command::SlashCommand;
#[allow(clippy::large_enum_variant)]
pub enum AppEvent {
pub(crate) enum AppEvent {
CodexEvent(Event),
/// Request a redraw which will be debounced by the [`App`].

View File

@@ -3,18 +3,18 @@ use std::sync::mpsc::Sender;
use crate::app_event::AppEvent;
#[derive(Clone, Debug)]
pub struct AppEventSender {
pub(crate) struct AppEventSender {
app_event_tx: Sender<AppEvent>,
}
impl AppEventSender {
pub fn new(app_event_tx: Sender<AppEvent>) -> Self {
pub(crate) fn new(app_event_tx: Sender<AppEvent>) -> Self {
Self { app_event_tx }
}
/// Send an event to the app event channel. If it fails, we swallow the
/// error and log it.
pub fn send(&self, event: AppEvent) {
pub(crate) fn send(&self, event: AppEvent) {
if let Err(e) = self.app_event_tx.send(event) {
tracing::error!("failed to send event: {e}");
}

View File

@@ -57,6 +57,10 @@ impl<'a> BottomPaneView<'a> for ApprovalModalView<'a> {
self.current.is_complete() && self.queue.is_empty()
}
fn desired_height(&self, width: u16) -> u16 {
self.current.desired_height(width)
}
fn render(&self, area: Rect, buf: &mut Buffer) {
(&self.current).render_ref(area, buf);
}
@@ -95,6 +99,7 @@ mod tests {
let mut pane = BottomPane::new(super::super::BottomPaneParams {
app_event_tx: AppEventSender::new(tx_raw2),
has_input_focus: true,
enhanced_keys_supported: false,
});
assert_eq!(CancellationEvent::Handled, view.on_ctrl_c(&mut pane));
assert!(view.queue.is_empty());

View File

@@ -28,6 +28,9 @@ pub(crate) trait BottomPaneView<'a> {
CancellationEvent::Ignored
}
/// Return the desired height of the view.
fn desired_height(&self, width: u16) -> u16;
/// Render the view: this will be displayed in place of the composer.
fn render(&self, area: Rect, buf: &mut Buffer);

View File

@@ -1,11 +1,13 @@
use codex_core::protocol::TokenUsage;
use crossterm::event::KeyEvent;
use ratatui::buffer::Buffer;
use ratatui::layout::Alignment;
use ratatui::layout::Rect;
use ratatui::style::Color;
use ratatui::style::Style;
use ratatui::style::Styled;
use ratatui::style::Stylize;
use ratatui::text::Line;
use ratatui::text::Span;
use ratatui::widgets::BorderType;
use ratatui::widgets::Borders;
use ratatui::widgets::Widget;
@@ -22,7 +24,7 @@ use crate::app_event::AppEvent;
use crate::app_event_sender::AppEventSender;
use codex_file_search::FileMatch;
const BASE_PLACEHOLDER_TEXT: &str = "send a message";
const BASE_PLACEHOLDER_TEXT: &str = "...";
/// If the pasted content exceeds this number of characters, replace it with a
/// placeholder in the UI.
const LARGE_PASTE_CHAR_THRESHOLD: usize = 1000;
@@ -33,12 +35,13 @@ pub enum InputResult {
None,
}
pub struct ChatComposer<'a> {
pub(crate) struct ChatComposer<'a> {
textarea: TextArea<'a>,
active_popup: ActivePopup,
app_event_tx: AppEventSender,
history: ChatComposerHistory,
ctrl_c_quit_hint: bool,
use_shift_enter_hint: bool,
dismissed_file_popup_token: Option<String>,
current_file_query: Option<String>,
pending_pastes: Vec<(String, String)>,
@@ -52,17 +55,24 @@ enum ActivePopup {
}
impl ChatComposer<'_> {
pub fn new(has_input_focus: bool, app_event_tx: AppEventSender) -> Self {
pub fn new(
has_input_focus: bool,
app_event_tx: AppEventSender,
enhanced_keys_supported: bool,
) -> Self {
let mut textarea = TextArea::default();
textarea.set_placeholder_text(BASE_PLACEHOLDER_TEXT);
textarea.set_cursor_line_style(ratatui::style::Style::default());
let use_shift_enter_hint = enhanced_keys_supported;
let mut this = Self {
textarea,
active_popup: ActivePopup::None,
app_event_tx,
history: ChatComposerHistory::new(),
ctrl_c_quit_hint: false,
use_shift_enter_hint,
dismissed_file_popup_token: None,
current_file_query: None,
pending_pastes: Vec::new(),
@@ -71,6 +81,15 @@ impl ChatComposer<'_> {
this
}
pub fn desired_height(&self) -> u16 {
self.textarea.lines().len().max(1) as u16
+ match &self.active_popup {
ActivePopup::None => 1u16,
ActivePopup::Command(c) => c.calculate_required_height(),
ActivePopup::File(c) => c.calculate_required_height(),
}
}
/// Returns true if the composer currently contains no user input.
pub(crate) fn is_empty(&self) -> bool {
self.textarea.is_empty()
@@ -460,6 +479,20 @@ impl ChatComposer<'_> {
self.textarea.insert_newline();
(InputResult::None, true)
}
Input {
key: Key::Char('d'),
ctrl: true,
alt: false,
shift: false,
} => {
self.textarea.input(Input {
key: Key::Delete,
ctrl: false,
alt: false,
shift: false,
});
(InputResult::None, true)
}
input => self.handle_input_basic(input),
}
}
@@ -612,37 +645,17 @@ impl ChatComposer<'_> {
}
fn update_border(&mut self, has_focus: bool) {
struct BlockState {
right_title: Line<'static>,
border_style: Style,
}
let bs = if has_focus {
if self.ctrl_c_quit_hint {
BlockState {
right_title: Line::from("Ctrl+C to quit").alignment(Alignment::Right),
border_style: Style::default(),
}
} else {
BlockState {
right_title: Line::from("Enter to send | Ctrl+D to quit | Ctrl+J for newline")
.alignment(Alignment::Right),
border_style: Style::default(),
}
}
let border_style = if has_focus {
Style::default().fg(Color::Cyan)
} else {
BlockState {
right_title: Line::from(""),
border_style: Style::default().dim(),
}
Style::default().dim()
};
self.textarea.set_block(
ratatui::widgets::Block::default()
.title_bottom(bs.right_title)
.borders(Borders::ALL)
.border_type(BorderType::Rounded)
.border_style(bs.border_style),
.borders(Borders::LEFT)
.border_type(BorderType::QuadrantOutside)
.border_style(border_style),
);
}
}
@@ -651,49 +664,80 @@ impl WidgetRef for &ChatComposer<'_> {
fn render_ref(&self, area: Rect, buf: &mut Buffer) {
match &self.active_popup {
ActivePopup::Command(popup) => {
let popup_height = popup.calculate_required_height(&area);
let popup_height = popup.calculate_required_height();
// Split the provided rect so that the popup is rendered at the
// *top* and the textarea occupies the remaining space below.
let popup_rect = Rect {
// **bottom** and the textarea occupies the remaining space above.
let popup_height = popup_height.min(area.height);
let textarea_rect = Rect {
x: area.x,
y: area.y,
width: area.width,
height: popup_height.min(area.height),
height: area.height.saturating_sub(popup_height),
};
let textarea_rect = Rect {
let popup_rect = Rect {
x: area.x,
y: area.y + popup_rect.height,
y: area.y + textarea_rect.height,
width: area.width,
height: area.height.saturating_sub(popup_rect.height),
height: popup_height,
};
popup.render(popup_rect, buf);
self.textarea.render(textarea_rect, buf);
}
ActivePopup::File(popup) => {
let popup_height = popup.calculate_required_height(&area);
let popup_height = popup.calculate_required_height();
let popup_rect = Rect {
let popup_height = popup_height.min(area.height);
let textarea_rect = Rect {
x: area.x,
y: area.y,
width: area.width,
height: popup_height.min(area.height),
};
let textarea_rect = Rect {
x: area.x,
y: area.y + popup_rect.height,
width: area.width,
height: area.height.saturating_sub(popup_height),
};
let popup_rect = Rect {
x: area.x,
y: area.y + textarea_rect.height,
width: area.width,
height: popup_height,
};
popup.render(popup_rect, buf);
self.textarea.render(textarea_rect, buf);
}
ActivePopup::None => {
self.textarea.render(area, buf);
let mut textarea_rect = area;
textarea_rect.height = textarea_rect.height.saturating_sub(1);
self.textarea.render(textarea_rect, buf);
let mut bottom_line_rect = area;
bottom_line_rect.y += textarea_rect.height;
bottom_line_rect.height = 1;
let key_hint_style = Style::default().fg(Color::Cyan);
let hint = if self.ctrl_c_quit_hint {
vec![
Span::from(" "),
"Ctrl+C again".set_style(key_hint_style),
Span::from(" to quit"),
]
} else {
let newline_hint_key = if self.use_shift_enter_hint {
"Shift+⏎"
} else {
"Ctrl+J"
};
vec![
Span::from(" "),
"".set_style(key_hint_style),
Span::from(" send "),
newline_hint_key.set_style(key_hint_style),
Span::from(" newline "),
"Ctrl+C".set_style(key_hint_style),
Span::from(" quit"),
]
};
Line::from(hint)
.style(Style::default().dim())
.render_ref(bottom_line_rect, buf);
}
}
}
@@ -859,7 +903,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
let needs_redraw = composer.handle_paste("hello".to_string());
assert!(needs_redraw);
@@ -882,7 +926,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
let large = "x".repeat(LARGE_PASTE_CHAR_THRESHOLD + 10);
let needs_redraw = composer.handle_paste(large.clone());
@@ -911,7 +955,7 @@ mod tests {
let large = "y".repeat(LARGE_PASTE_CHAR_THRESHOLD + 1);
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
composer.handle_paste(large);
assert_eq!(composer.pending_pastes.len(), 1);
@@ -947,7 +991,7 @@ mod tests {
for (name, input) in test_cases {
// Create a fresh composer for each test case
let mut composer = ChatComposer::new(true, sender.clone());
let mut composer = ChatComposer::new(true, sender.clone(), false);
if let Some(text) = input {
composer.handle_paste(text);
@@ -984,7 +1028,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
// Define test cases: (paste content, is_large)
let test_cases = [
@@ -1057,7 +1101,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
// Define test cases: (content, is_large)
let test_cases = [
@@ -1130,7 +1174,7 @@ mod tests {
let (tx, _rx) = std::sync::mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut composer = ChatComposer::new(true, sender, false);
// Define test cases: (cursor_position_from_end, expected_pending_count)
let test_cases = [

View File

@@ -3,9 +3,9 @@ use ratatui::layout::Rect;
use ratatui::style::Color;
use ratatui::style::Style;
use ratatui::style::Stylize;
use ratatui::widgets::Block;
use ratatui::widgets::BorderType;
use ratatui::widgets::Borders;
use ratatui::symbols::border::QUADRANT_LEFT_HALF;
use ratatui::text::Line;
use ratatui::text::Span;
use ratatui::widgets::Cell;
use ratatui::widgets::Row;
use ratatui::widgets::Table;
@@ -71,12 +71,8 @@ impl CommandPopup {
/// Determine the preferred height of the popup. This is the number of
/// rows required to show **at most** `MAX_POPUP_ROWS` commands plus the
/// table/border overhead (one line at the top and one at the bottom).
pub(crate) fn calculate_required_height(&self, _area: &Rect) -> u16 {
let matches = self.filtered_commands();
let row_count = matches.len().clamp(1, MAX_POPUP_ROWS) as u16;
// Account for the border added by the Block that wraps the table.
// 2 = one line at the top, one at the bottom.
row_count + 2
pub(crate) fn calculate_required_height(&self) -> u16 {
self.filtered_commands().len().clamp(1, MAX_POPUP_ROWS) as u16
}
/// Return the list of commands that match the current filter. Matching is
@@ -158,18 +154,19 @@ impl WidgetRef for CommandPopup {
let default_style = Style::default();
let command_style = Style::default().fg(Color::LightBlue);
for (idx, cmd) in visible_matches.iter().enumerate() {
let (cmd_style, desc_style) = if Some(idx) == self.selected_idx {
(
command_style.bg(Color::DarkGray),
default_style.bg(Color::DarkGray),
)
} else {
(command_style, default_style)
};
rows.push(Row::new(vec![
Cell::from(format!("/{}", cmd.command())).style(cmd_style),
Cell::from(cmd.description().to_string()).style(desc_style),
Cell::from(Line::from(vec![
if Some(idx) == self.selected_idx {
Span::styled(
"",
Style::default().bg(Color::DarkGray).fg(Color::LightCyan),
)
} else {
Span::styled(QUADRANT_LEFT_HALF, Style::default().fg(Color::DarkGray))
},
Span::styled(format!("/{}", cmd.command()), command_style),
])),
Cell::from(cmd.description().to_string()).style(default_style),
]));
}
}
@@ -180,12 +177,13 @@ impl WidgetRef for CommandPopup {
rows,
[Constraint::Length(FIRST_COLUMN_WIDTH), Constraint::Min(10)],
)
.column_spacing(0)
.block(
Block::default()
.borders(Borders::ALL)
.border_type(BorderType::Rounded),
);
.column_spacing(0);
// .block(
// Block::default()
// .borders(Borders::LEFT)
// .border_type(BorderType::QuadrantOutside)
// .border_style(Style::default().fg(Color::DarkGray)),
// );
table.render(area, buf);
}

View File

@@ -109,18 +109,14 @@ impl FileSearchPopup {
}
/// Preferred height (rows) including border.
pub(crate) fn calculate_required_height(&self, _area: &Rect) -> u16 {
pub(crate) fn calculate_required_height(&self) -> u16 {
// Row count depends on whether we already have matches. If no matches
// yet (e.g. initial search or query with no results) reserve a single
// row so the popup is still visible. When matches are present we show
// up to MAX_RESULTS regardless of the waiting flag so the list
// remains stable while a newer search is in-flight.
let rows = if self.matches.is_empty() {
1
} else {
self.matches.len().clamp(1, MAX_RESULTS)
} as u16;
rows + 2 // border
self.matches.len().clamp(1, MAX_RESULTS) as u16
}
}
@@ -128,7 +124,14 @@ impl WidgetRef for &FileSearchPopup {
fn render_ref(&self, area: Rect, buf: &mut Buffer) {
// Prepare rows.
let rows: Vec<Row> = if self.matches.is_empty() {
vec![Row::new(vec![Cell::from(" no matches ")])]
vec![Row::new(vec![
Cell::from(if self.waiting {
"(searching …)"
} else {
"no matches"
})
.style(Style::new().add_modifier(Modifier::ITALIC | Modifier::DIM)),
])]
} else {
self.matches
.iter()
@@ -169,17 +172,12 @@ impl WidgetRef for &FileSearchPopup {
.collect()
};
let mut title = format!(" @{} ", self.pending_query);
if self.waiting {
title.push_str(" (searching …)");
}
let table = Table::new(rows, vec![Constraint::Percentage(100)])
.block(
Block::default()
.borders(Borders::ALL)
.border_type(BorderType::Rounded)
.title(title),
.borders(Borders::LEFT)
.border_type(BorderType::QuadrantOutside)
.border_style(Style::default().fg(Color::DarkGray)),
)
.widths([Constraint::Percentage(100)]);

View File

@@ -14,7 +14,7 @@ use ratatui::widgets::WidgetRef;
mod approval_modal_view;
mod bottom_pane_view;
pub mod chat_composer;
mod chat_composer;
mod chat_composer_history;
mod command_popup;
mod file_search_popup;
@@ -50,12 +50,18 @@ pub(crate) struct BottomPane<'a> {
pub(crate) struct BottomPaneParams {
pub(crate) app_event_tx: AppEventSender,
pub(crate) has_input_focus: bool,
pub(crate) enhanced_keys_supported: bool,
}
impl BottomPane<'_> {
pub fn new(params: BottomPaneParams) -> Self {
let enhanced_keys_supported = params.enhanced_keys_supported;
Self {
composer: ChatComposer::new(params.has_input_focus, params.app_event_tx.clone()),
composer: ChatComposer::new(
params.has_input_focus,
params.app_event_tx.clone(),
enhanced_keys_supported,
),
active_view: None,
app_event_tx: params.app_event_tx,
has_input_focus: params.has_input_focus,
@@ -64,6 +70,13 @@ impl BottomPane<'_> {
}
}
pub fn desired_height(&self, width: u16) -> u16 {
self.active_view
.as_ref()
.map(|v| v.desired_height(width))
.unwrap_or(self.composer.desired_height())
}
/// Forward a key event to the active view or the composer.
pub fn handle_key_event(&mut self, key_event: KeyEvent) -> InputResult {
if let Some(mut view) = self.active_view.take() {
@@ -291,6 +304,7 @@ mod tests {
let mut pane = BottomPane::new(BottomPaneParams {
app_event_tx: tx,
has_input_focus: true,
enhanced_keys_supported: false,
});
pane.push_approval_request(exec_request());
assert_eq!(CancellationEvent::Handled, pane.on_ctrl_c());

View File

@@ -2,13 +2,13 @@
source: tui/src/bottom_pane/chat_composer.rs
expression: terminal.backend()
---
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮"
"│[Pasted Content 1002 chars][Pasted Content 1004 chars] │"
" "
" "
" "
" "
" "
" "
" "
"╰───────────────────────────────────────────────Enter to send | Ctrl+D to quit | Ctrl+J for newline╯"
"▌[Pasted Content 1002 chars][Pasted Content 1004 chars] "
""
" "
" "
" "
" "
" "
" "
" "
" send Ctrl+J newline Ctrl+C quit "

View File

@@ -2,13 +2,13 @@
source: tui/src/bottom_pane/chat_composer.rs
expression: terminal.backend()
---
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮"
"│ send a message "
" "
" "
" "
" "
" "
" "
" "
"╰───────────────────────────────────────────────Enter to send | Ctrl+D to quit | Ctrl+J for newline╯"
"▌ ... "
" "
" "
" "
" "
" "
" "
" "
" "
" send Ctrl+J newline Ctrl+C quit "

View File

@@ -2,13 +2,13 @@
source: tui/src/bottom_pane/chat_composer.rs
expression: terminal.backend()
---
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮"
"│[Pasted Content 1005 chars] "
" "
" "
" "
" "
" "
" "
" "
"╰───────────────────────────────────────────────Enter to send | Ctrl+D to quit | Ctrl+J for newline╯"
"▌[Pasted Content 1005 chars] "
" "
" "
" "
" "
" "
" "
" "
" "
" send Ctrl+J newline Ctrl+C quit "

View File

@@ -2,13 +2,13 @@
source: tui/src/bottom_pane/chat_composer.rs
expression: terminal.backend()
---
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮"
"│[Pasted Content 1003 chars][Pasted Content 1007 chars] another short paste │"
" "
" "
" "
" "
" "
" "
" "
"╰───────────────────────────────────────────────Enter to send | Ctrl+D to quit | Ctrl+J for newline╯"
"▌[Pasted Content 1003 chars][Pasted Content 1007 chars] another short paste "
""
" "
" "
" "
" "
" "
" "
" "
" send Ctrl+J newline Ctrl+C quit "

View File

@@ -2,13 +2,13 @@
source: tui/src/bottom_pane/chat_composer.rs
expression: terminal.backend()
---
"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮"
"│short "
" "
" "
" "
" "
" "
" "
" "
"╰───────────────────────────────────────────────Enter to send | Ctrl+D to quit | Ctrl+J for newline╯"
"▌short "
" "
" "
" "
" "
" "
" "
" "
" "
" send Ctrl+J newline Ctrl+C quit "

View File

@@ -33,6 +33,10 @@ impl BottomPaneView<'_> for StatusIndicatorView {
true
}
fn desired_height(&self, width: u16) -> u16 {
self.view.desired_height(width)
}
fn render(&self, area: ratatui::layout::Rect, buf: &mut Buffer) {
self.view.render_ref(area, buf);
}

View File

@@ -1,3 +1,4 @@
use std::collections::HashMap;
use std::path::PathBuf;
use std::sync::Arc;
use std::time::Duration;
@@ -24,6 +25,7 @@ use codex_core::protocol::PatchApplyBeginEvent;
use codex_core::protocol::TaskCompleteEvent;
use codex_core::protocol::TokenUsage;
use crossterm::event::KeyEvent;
use crossterm::event::KeyEventKind;
use ratatui::buffer::Buffer;
use ratatui::layout::Rect;
use ratatui::widgets::Widget;
@@ -44,6 +46,12 @@ use crate::history_cell::PatchEventType;
use crate::user_approval_widget::ApprovalRequest;
use codex_file_search::FileMatch;
struct RunningCommand {
command: Vec<String>,
#[allow(dead_code)]
cwd: PathBuf,
}
pub(crate) struct ChatWidget<'a> {
app_event_tx: AppEventSender,
codex_op_tx: UnboundedSender<Op>,
@@ -56,6 +64,7 @@ pub(crate) struct ChatWidget<'a> {
// We wait for the final AgentMessage event and then emit the full text
// at once into scrollback so the history contains a single message.
answer_buffer: String,
running_commands: HashMap<String, RunningCommand>,
}
struct UserMessage {
@@ -86,6 +95,7 @@ impl ChatWidget<'_> {
app_event_tx: AppEventSender,
initial_prompt: Option<String>,
initial_images: Vec<PathBuf>,
enhanced_keys_supported: bool,
) -> Self {
let (codex_op_tx, mut codex_op_rx) = unbounded_channel::<Op>();
@@ -131,6 +141,7 @@ impl ChatWidget<'_> {
bottom_pane: BottomPane::new(BottomPaneParams {
app_event_tx,
has_input_focus: true,
enhanced_keys_supported,
}),
config,
initial_user_message: create_initial_user_message(
@@ -140,11 +151,18 @@ impl ChatWidget<'_> {
token_usage: TokenUsage::default(),
reasoning_buffer: String::new(),
answer_buffer: String::new(),
running_commands: HashMap::new(),
}
}
pub fn desired_height(&self, width: u16) -> u16 {
self.bottom_pane.desired_height(width)
}
pub(crate) fn handle_key_event(&mut self, key_event: KeyEvent) {
self.bottom_pane.clear_ctrl_c_quit_hint();
if key_event.kind == KeyEventKind::Press {
self.bottom_pane.clear_ctrl_c_quit_hint();
}
match self.bottom_pane.handle_key_event(key_event) {
InputResult::Submitted(text) => {
@@ -158,7 +176,7 @@ impl ChatWidget<'_> {
self.bottom_pane.handle_paste(text);
}
pub(crate) fn add_to_history(&mut self, cell: HistoryCell) {
fn add_to_history(&mut self, cell: HistoryCell) {
self.app_event_tx
.send(AppEvent::InsertHistory(cell.plain_lines()));
}
@@ -280,6 +298,10 @@ impl ChatWidget<'_> {
self.add_to_history(HistoryCell::new_error_event(message.clone()));
self.bottom_pane.set_task_running(false);
}
EventMsg::PlanUpdate(update) => {
self.add_to_history(HistoryCell::new_plan_update(update));
self.request_redraw();
}
EventMsg::ExecApprovalRequest(ExecApprovalRequestEvent {
call_id: _,
command,
@@ -339,13 +361,20 @@ impl ChatWidget<'_> {
self.request_redraw();
}
EventMsg::ExecCommandBegin(ExecCommandBeginEvent {
call_id: _,
call_id,
command,
cwd: _,
cwd,
}) => {
self.running_commands.insert(
call_id,
RunningCommand {
command: command.clone(),
cwd: cwd.clone(),
},
);
self.add_to_history(HistoryCell::new_active_exec_command(command));
self.request_redraw();
}
EventMsg::ExecCommandOutputDelta(_) => {}
EventMsg::PatchApplyBegin(PatchApplyBeginEvent {
call_id: _,
auto_approved,
@@ -357,7 +386,6 @@ impl ChatWidget<'_> {
PatchEventType::ApplyBegin { auto_approved },
changes,
));
self.request_redraw();
}
EventMsg::ExecCommandEnd(ExecCommandEndEvent {
call_id,
@@ -365,8 +393,9 @@ impl ChatWidget<'_> {
stdout,
stderr,
}) => {
let cmd = self.running_commands.remove(&call_id);
self.add_to_history(HistoryCell::new_completed_exec_command(
call_id,
cmd.map(|cmd| cmd.command).unwrap_or_else(|| vec![call_id]),
CommandOutput {
exit_code,
stdout,
@@ -380,7 +409,6 @@ impl ChatWidget<'_> {
invocation,
}) => {
self.add_to_history(HistoryCell::new_active_mcp_tool_call(invocation));
self.request_redraw();
}
EventMsg::McpToolCallEnd(McpToolCallEndEvent {
call_id: _,
@@ -415,7 +443,6 @@ impl ChatWidget<'_> {
}
event => {
self.add_to_history(HistoryCell::new_background_event(format!("{event:?}")));
self.request_redraw();
}
}
}
@@ -432,7 +459,6 @@ impl ChatWidget<'_> {
pub(crate) fn add_diff_output(&mut self, diff_output: String) {
self.add_to_history(HistoryCell::new_diff_output(diff_output.clone()));
self.request_redraw();
}
/// Forward file-search results to the bottom pane.
@@ -477,6 +503,12 @@ impl ChatWidget<'_> {
pub(crate) fn token_usage(&self) -> &TokenUsage {
&self.token_usage
}
pub(crate) fn clear_token_usage(&mut self) {
self.token_usage = TokenUsage::default();
self.bottom_pane
.set_token_usage(self.token_usage.clone(), self.config.model_context_window);
}
}
impl WidgetRef for &ChatWidget<'_> {

View File

@@ -0,0 +1,588 @@
// This is derived from `ratatui::Terminal`, which is licensed under the following terms:
//
// The MIT License (MIT)
// Copyright (c) 2016-2022 Florian Dehau
// Copyright (c) 2023-2025 The Ratatui Developers
//
// Permission is hereby granted, free of charge, to any person obtaining a copy
// of this software and associated documentation files (the "Software"), to deal
// in the Software without restriction, including without limitation the rights
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
// copies of the Software, and to permit persons to whom the Software is
// furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included in all
// copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
// SOFTWARE.
use std::io;
use ratatui::backend::Backend;
use ratatui::backend::ClearType;
use ratatui::buffer::Buffer;
use ratatui::layout::Position;
use ratatui::layout::Rect;
use ratatui::layout::Size;
use ratatui::widgets::StatefulWidget;
use ratatui::widgets::StatefulWidgetRef;
use ratatui::widgets::Widget;
use ratatui::widgets::WidgetRef;
#[derive(Debug, Hash)]
pub struct Frame<'a> {
/// Where should the cursor be after drawing this frame?
///
/// If `None`, the cursor is hidden and its position is controlled by the backend. If `Some((x,
/// y))`, the cursor is shown and placed at `(x, y)` after the call to `Terminal::draw()`.
pub(crate) cursor_position: Option<Position>,
/// The area of the viewport
pub(crate) viewport_area: Rect,
/// The buffer that is used to draw the current frame
pub(crate) buffer: &'a mut Buffer,
/// The frame count indicating the sequence number of this frame.
pub(crate) count: usize,
}
#[allow(dead_code)]
impl Frame<'_> {
/// The area of the current frame
///
/// This is guaranteed not to change during rendering, so may be called multiple times.
///
/// If your app listens for a resize event from the backend, it should ignore the values from
/// the event for any calculations that are used to render the current frame and use this value
/// instead as this is the area of the buffer that is used to render the current frame.
pub const fn area(&self) -> Rect {
self.viewport_area
}
/// Render a [`Widget`] to the current buffer using [`Widget::render`].
///
/// Usually the area argument is the size of the current frame or a sub-area of the current
/// frame (which can be obtained using [`Layout`] to split the total area).
///
/// # Example
///
/// ```rust
/// # use ratatui::{backend::TestBackend, Terminal};
/// # let backend = TestBackend::new(5, 5);
/// # let mut terminal = Terminal::new(backend).unwrap();
/// # let mut frame = terminal.get_frame();
/// use ratatui::{layout::Rect, widgets::Block};
///
/// let block = Block::new();
/// let area = Rect::new(0, 0, 5, 5);
/// frame.render_widget(block, area);
/// ```
///
/// [`Layout`]: crate::layout::Layout
pub fn render_widget<W: Widget>(&mut self, widget: W, area: Rect) {
widget.render(area, self.buffer);
}
/// Render a [`WidgetRef`] to the current buffer using [`WidgetRef::render_ref`].
///
/// Usually the area argument is the size of the current frame or a sub-area of the current
/// frame (which can be obtained using [`Layout`] to split the total area).
///
/// # Example
///
/// ```rust
/// # #[cfg(feature = "unstable-widget-ref")] {
/// # use ratatui::{backend::TestBackend, Terminal};
/// # let backend = TestBackend::new(5, 5);
/// # let mut terminal = Terminal::new(backend).unwrap();
/// # let mut frame = terminal.get_frame();
/// use ratatui::{layout::Rect, widgets::Block};
///
/// let block = Block::new();
/// let area = Rect::new(0, 0, 5, 5);
/// frame.render_widget_ref(block, area);
/// # }
/// ```
#[allow(clippy::needless_pass_by_value)]
pub fn render_widget_ref<W: WidgetRef>(&mut self, widget: W, area: Rect) {
widget.render_ref(area, self.buffer);
}
/// Render a [`StatefulWidget`] to the current buffer using [`StatefulWidget::render`].
///
/// Usually the area argument is the size of the current frame or a sub-area of the current
/// frame (which can be obtained using [`Layout`] to split the total area).
///
/// The last argument should be an instance of the [`StatefulWidget::State`] associated to the
/// given [`StatefulWidget`].
///
/// # Example
///
/// ```rust
/// # use ratatui::{backend::TestBackend, Terminal};
/// # let backend = TestBackend::new(5, 5);
/// # let mut terminal = Terminal::new(backend).unwrap();
/// # let mut frame = terminal.get_frame();
/// use ratatui::{
/// layout::Rect,
/// widgets::{List, ListItem, ListState},
/// };
///
/// let mut state = ListState::default().with_selected(Some(1));
/// let list = List::new(vec![ListItem::new("Item 1"), ListItem::new("Item 2")]);
/// let area = Rect::new(0, 0, 5, 5);
/// frame.render_stateful_widget(list, area, &mut state);
/// ```
///
/// [`Layout`]: crate::layout::Layout
pub fn render_stateful_widget<W>(&mut self, widget: W, area: Rect, state: &mut W::State)
where
W: StatefulWidget,
{
widget.render(area, self.buffer, state);
}
/// Render a [`StatefulWidgetRef`] to the current buffer using
/// [`StatefulWidgetRef::render_ref`].
///
/// Usually the area argument is the size of the current frame or a sub-area of the current
/// frame (which can be obtained using [`Layout`] to split the total area).
///
/// The last argument should be an instance of the [`StatefulWidgetRef::State`] associated to
/// the given [`StatefulWidgetRef`].
///
/// # Example
///
/// ```rust
/// # #[cfg(feature = "unstable-widget-ref")] {
/// # use ratatui::{backend::TestBackend, Terminal};
/// # let backend = TestBackend::new(5, 5);
/// # let mut terminal = Terminal::new(backend).unwrap();
/// # let mut frame = terminal.get_frame();
/// use ratatui::{
/// layout::Rect,
/// widgets::{List, ListItem, ListState},
/// };
///
/// let mut state = ListState::default().with_selected(Some(1));
/// let list = List::new(vec![ListItem::new("Item 1"), ListItem::new("Item 2")]);
/// let area = Rect::new(0, 0, 5, 5);
/// frame.render_stateful_widget_ref(list, area, &mut state);
/// # }
/// ```
#[allow(clippy::needless_pass_by_value)]
pub fn render_stateful_widget_ref<W>(&mut self, widget: W, area: Rect, state: &mut W::State)
where
W: StatefulWidgetRef,
{
widget.render_ref(area, self.buffer, state);
}
/// After drawing this frame, make the cursor visible and put it at the specified (x, y)
/// coordinates. If this method is not called, the cursor will be hidden.
///
/// Note that this will interfere with calls to [`Terminal::hide_cursor`],
/// [`Terminal::show_cursor`], and [`Terminal::set_cursor_position`]. Pick one of the APIs and
/// stick with it.
///
/// [`Terminal::hide_cursor`]: crate::Terminal::hide_cursor
/// [`Terminal::show_cursor`]: crate::Terminal::show_cursor
/// [`Terminal::set_cursor_position`]: crate::Terminal::set_cursor_position
pub fn set_cursor_position<P: Into<Position>>(&mut self, position: P) {
self.cursor_position = Some(position.into());
}
/// Gets the buffer that this `Frame` draws into as a mutable reference.
pub fn buffer_mut(&mut self) -> &mut Buffer {
self.buffer
}
/// Returns the current frame count.
///
/// This method provides access to the frame count, which is a sequence number indicating
/// how many frames have been rendered up to (but not including) this one. It can be used
/// for purposes such as animation, performance tracking, or debugging.
///
/// Each time a frame has been rendered, this count is incremented,
/// providing a consistent way to reference the order and number of frames processed by the
/// terminal. When count reaches its maximum value (`usize::MAX`), it wraps around to zero.
///
/// This count is particularly useful when dealing with dynamic content or animations where the
/// state of the display changes over time. By tracking the frame count, developers can
/// synchronize updates or changes to the content with the rendering process.
///
/// # Examples
///
/// ```rust
/// # use ratatui::{backend::TestBackend, Terminal};
/// # let backend = TestBackend::new(5, 5);
/// # let mut terminal = Terminal::new(backend).unwrap();
/// # let mut frame = terminal.get_frame();
/// let current_count = frame.count();
/// println!("Current frame count: {}", current_count);
/// ```
pub const fn count(&self) -> usize {
self.count
}
}
#[derive(Debug, Default, Clone, Eq, PartialEq, Hash)]
pub struct Terminal<B>
where
B: Backend,
{
/// The backend used to interface with the terminal
backend: B,
/// Holds the results of the current and previous draw calls. The two are compared at the end
/// of each draw pass to output the necessary updates to the terminal
buffers: [Buffer; 2],
/// Index of the current buffer in the previous array
current: usize,
/// Whether the cursor is currently hidden
hidden_cursor: bool,
/// Area of the viewport
pub viewport_area: Rect,
/// Last known size of the terminal. Used to detect if the internal buffers have to be resized.
pub last_known_screen_size: Size,
/// Last known position of the cursor. Used to find the new area when the viewport is inlined
/// and the terminal resized.
pub last_known_cursor_pos: Position,
/// Number of frames rendered up until current time.
frame_count: usize,
}
impl<B> Drop for Terminal<B>
where
B: Backend,
{
#[allow(clippy::print_stderr)]
fn drop(&mut self) {
// Attempt to restore the cursor state
if self.hidden_cursor {
if let Err(err) = self.show_cursor() {
eprintln!("Failed to show the cursor: {err}");
}
}
}
}
impl<B> Terminal<B>
where
B: Backend,
{
/// Creates a new [`Terminal`] with the given [`Backend`] and [`TerminalOptions`].
///
/// # Example
///
/// ```rust
/// use std::io::stdout;
///
/// use ratatui::{backend::CrosstermBackend, layout::Rect, Terminal, TerminalOptions, Viewport};
///
/// let backend = CrosstermBackend::new(stdout());
/// let viewport = Viewport::Fixed(Rect::new(0, 0, 10, 10));
/// let terminal = Terminal::with_options(backend, TerminalOptions { viewport })?;
/// # std::io::Result::Ok(())
/// ```
pub fn with_options(mut backend: B) -> io::Result<Self> {
let screen_size = backend.size()?;
let cursor_pos = backend.get_cursor_position()?;
Ok(Self {
backend,
buffers: [
Buffer::empty(Rect::new(0, 0, 0, 0)),
Buffer::empty(Rect::new(0, 0, 0, 0)),
],
current: 0,
hidden_cursor: false,
viewport_area: Rect::new(0, cursor_pos.y, 0, 0),
last_known_screen_size: screen_size,
last_known_cursor_pos: cursor_pos,
frame_count: 0,
})
}
/// Get a Frame object which provides a consistent view into the terminal state for rendering.
pub fn get_frame(&mut self) -> Frame {
let count = self.frame_count;
Frame {
cursor_position: None,
viewport_area: self.viewport_area,
buffer: self.current_buffer_mut(),
count,
}
}
/// Gets the current buffer as a mutable reference.
pub fn current_buffer_mut(&mut self) -> &mut Buffer {
&mut self.buffers[self.current]
}
/// Gets the backend
pub const fn backend(&self) -> &B {
&self.backend
}
/// Gets the backend as a mutable reference
pub fn backend_mut(&mut self) -> &mut B {
&mut self.backend
}
/// Obtains a difference between the previous and the current buffer and passes it to the
/// current backend for drawing.
pub fn flush(&mut self) -> io::Result<()> {
let previous_buffer = &self.buffers[1 - self.current];
let current_buffer = &self.buffers[self.current];
let updates = previous_buffer.diff(current_buffer);
if let Some((col, row, _)) = updates.last() {
self.last_known_cursor_pos = Position { x: *col, y: *row };
}
self.backend.draw(updates.into_iter())
}
/// Updates the Terminal so that internal buffers match the requested area.
///
/// Requested area will be saved to remain consistent when rendering. This leads to a full clear
/// of the screen.
pub fn resize(&mut self, screen_size: Size) -> io::Result<()> {
self.last_known_screen_size = screen_size;
Ok(())
}
/// Sets the viewport area.
pub fn set_viewport_area(&mut self, area: Rect) {
self.buffers[self.current].resize(area);
self.buffers[1 - self.current].resize(area);
self.viewport_area = area;
}
/// Queries the backend for size and resizes if it doesn't match the previous size.
pub fn autoresize(&mut self) -> io::Result<()> {
let screen_size = self.size()?;
if screen_size != self.last_known_screen_size {
self.resize(screen_size)?;
}
Ok(())
}
/// Draws a single frame to the terminal.
///
/// Returns a [`CompletedFrame`] if successful, otherwise a [`std::io::Error`].
///
/// If the render callback passed to this method can fail, use [`try_draw`] instead.
///
/// Applications should call `draw` or [`try_draw`] in a loop to continuously render the
/// terminal. These methods are the main entry points for drawing to the terminal.
///
/// [`try_draw`]: Terminal::try_draw
///
/// This method will:
///
/// - autoresize the terminal if necessary
/// - call the render callback, passing it a [`Frame`] reference to render to
/// - flush the current internal state by copying the current buffer to the backend
/// - move the cursor to the last known position if it was set during the rendering closure
///
/// The render callback should fully render the entire frame when called, including areas that
/// are unchanged from the previous frame. This is because each frame is compared to the
/// previous frame to determine what has changed, and only the changes are written to the
/// terminal. If the render callback does not fully render the frame, the terminal will not be
/// in a consistent state.
///
/// # Examples
///
/// ```
/// # let backend = ratatui::backend::TestBackend::new(10, 10);
/// # let mut terminal = ratatui::Terminal::new(backend)?;
/// use ratatui::{layout::Position, widgets::Paragraph};
///
/// // with a closure
/// terminal.draw(|frame| {
/// let area = frame.area();
/// frame.render_widget(Paragraph::new("Hello World!"), area);
/// frame.set_cursor_position(Position { x: 0, y: 0 });
/// })?;
///
/// // or with a function
/// terminal.draw(render)?;
///
/// fn render(frame: &mut ratatui::Frame) {
/// frame.render_widget(Paragraph::new("Hello World!"), frame.area());
/// }
/// # std::io::Result::Ok(())
/// ```
pub fn draw<F>(&mut self, render_callback: F) -> io::Result<()>
where
F: FnOnce(&mut Frame),
{
self.try_draw(|frame| {
render_callback(frame);
io::Result::Ok(())
})
}
/// Tries to draw a single frame to the terminal.
///
/// Returns [`Result::Ok`] containing a [`CompletedFrame`] if successful, otherwise
/// [`Result::Err`] containing the [`std::io::Error`] that caused the failure.
///
/// This is the equivalent of [`Terminal::draw`] but the render callback is a function or
/// closure that returns a `Result` instead of nothing.
///
/// Applications should call `try_draw` or [`draw`] in a loop to continuously render the
/// terminal. These methods are the main entry points for drawing to the terminal.
///
/// [`draw`]: Terminal::draw
///
/// This method will:
///
/// - autoresize the terminal if necessary
/// - call the render callback, passing it a [`Frame`] reference to render to
/// - flush the current internal state by copying the current buffer to the backend
/// - move the cursor to the last known position if it was set during the rendering closure
/// - return a [`CompletedFrame`] with the current buffer and the area of the terminal
///
/// The render callback passed to `try_draw` can return any [`Result`] with an error type that
/// can be converted into an [`std::io::Error`] using the [`Into`] trait. This makes it possible
/// to use the `?` operator to propagate errors that occur during rendering. If the render
/// callback returns an error, the error will be returned from `try_draw` as an
/// [`std::io::Error`] and the terminal will not be updated.
///
/// The [`CompletedFrame`] returned by this method can be useful for debugging or testing
/// purposes, but it is often not used in regular applicationss.
///
/// The render callback should fully render the entire frame when called, including areas that
/// are unchanged from the previous frame. This is because each frame is compared to the
/// previous frame to determine what has changed, and only the changes are written to the
/// terminal. If the render function does not fully render the frame, the terminal will not be
/// in a consistent state.
///
/// # Examples
///
/// ```should_panic
/// # use ratatui::layout::Position;;
/// # let backend = ratatui::backend::TestBackend::new(10, 10);
/// # let mut terminal = ratatui::Terminal::new(backend)?;
/// use std::io;
///
/// use ratatui::widgets::Paragraph;
///
/// // with a closure
/// terminal.try_draw(|frame| {
/// let value: u8 = "not a number".parse().map_err(io::Error::other)?;
/// let area = frame.area();
/// frame.render_widget(Paragraph::new("Hello World!"), area);
/// frame.set_cursor_position(Position { x: 0, y: 0 });
/// io::Result::Ok(())
/// })?;
///
/// // or with a function
/// terminal.try_draw(render)?;
///
/// fn render(frame: &mut ratatui::Frame) -> io::Result<()> {
/// let value: u8 = "not a number".parse().map_err(io::Error::other)?;
/// frame.render_widget(Paragraph::new("Hello World!"), frame.area());
/// Ok(())
/// }
/// # io::Result::Ok(())
/// ```
pub fn try_draw<F, E>(&mut self, render_callback: F) -> io::Result<()>
where
F: FnOnce(&mut Frame) -> Result<(), E>,
E: Into<io::Error>,
{
// Autoresize - otherwise we get glitches if shrinking or potential desync between widgets
// and the terminal (if growing), which may OOB.
self.autoresize()?;
let mut frame = self.get_frame();
render_callback(&mut frame).map_err(Into::into)?;
// We can't change the cursor position right away because we have to flush the frame to
// stdout first. But we also can't keep the frame around, since it holds a &mut to
// Buffer. Thus, we're taking the important data out of the Frame and dropping it.
let cursor_position = frame.cursor_position;
// Draw to stdout
self.flush()?;
match cursor_position {
None => self.hide_cursor()?,
Some(position) => {
self.show_cursor()?;
self.set_cursor_position(position)?;
}
}
self.swap_buffers();
// Flush
self.backend.flush()?;
// increment frame count before returning from draw
self.frame_count = self.frame_count.wrapping_add(1);
Ok(())
}
/// Hides the cursor.
pub fn hide_cursor(&mut self) -> io::Result<()> {
self.backend.hide_cursor()?;
self.hidden_cursor = true;
Ok(())
}
/// Shows the cursor.
pub fn show_cursor(&mut self) -> io::Result<()> {
self.backend.show_cursor()?;
self.hidden_cursor = false;
Ok(())
}
/// Gets the current cursor position.
///
/// This is the position of the cursor after the last draw call.
#[allow(dead_code)]
pub fn get_cursor_position(&mut self) -> io::Result<Position> {
self.backend.get_cursor_position()
}
/// Sets the cursor position.
pub fn set_cursor_position<P: Into<Position>>(&mut self, position: P) -> io::Result<()> {
let position = position.into();
self.backend.set_cursor_position(position)?;
self.last_known_cursor_pos = position;
Ok(())
}
/// Clear the terminal and force a full redraw on the next draw call.
pub fn clear(&mut self) -> io::Result<()> {
if self.viewport_area.is_empty() {
return Ok(());
}
self.backend
.set_cursor_position(self.viewport_area.as_position())?;
self.backend.clear_region(ClearType::AfterCursor)?;
// Reset the back buffer to make sure the next update will redraw everything.
self.buffers[1 - self.current].reset();
Ok(())
}
/// Clears the inactive buffer and swaps it with the current buffer
pub fn swap_buffers(&mut self) {
self.buffers[1 - self.current].reset();
self.current = 1 - self.current;
}
/// Queries the real size of the backend.
pub fn size(&self) -> io::Result<Size> {
self.backend.size()
}
}

View File

@@ -1,4 +1,4 @@
use crate::exec_command::escape_command;
use crate::exec_command::strip_bash_lc_and_escape;
use crate::markdown::append_markdown;
use crate::text_block::TextBlock;
use crate::text_formatting::format_and_truncate_tool_result;
@@ -9,6 +9,9 @@ use codex_common::summarize_sandbox_policy;
use codex_core::WireApi;
use codex_core::config::Config;
use codex_core::model_supports_reasoning_summaries;
use codex_core::plan_tool::PlanItemArg;
use codex_core::plan_tool::StepStatus;
use codex_core::plan_tool::UpdatePlanArgs;
use codex_core::protocol::FileChange;
use codex_core::protocol::McpInvocation;
use codex_core::protocol::SessionConfiguredEvent;
@@ -109,6 +112,10 @@ pub(crate) enum HistoryCell {
/// behaviour of `ActiveExecCommand` so the user sees *what* patch the
/// model wants to apply before being prompted to approve or deny it.
PendingPatch { view: TextBlock },
/// A humanfriendly rendering of the model's current plan and step
/// statuses provided via the `update_plan` tool.
PlanUpdate { view: TextBlock },
}
const TOOL_CALL_MAX_LINES: usize = 5;
@@ -130,6 +137,7 @@ impl HistoryCell {
| HistoryCell::CompletedExecCommand { view }
| HistoryCell::CompletedMcpToolCall { view }
| HistoryCell::PendingPatch { view }
| HistoryCell::PlanUpdate { view }
| HistoryCell::ActiveExecCommand { view, .. }
| HistoryCell::ActiveMcpToolCall { view, .. } => {
view.lines.iter().map(line_to_static).collect()
@@ -246,7 +254,7 @@ impl HistoryCell {
}
pub(crate) fn new_active_exec_command(command: Vec<String>) -> Self {
let command_escaped = escape_command(&command);
let command_escaped = strip_bash_lc_and_escape(&command);
let lines: Vec<Line<'static>> = vec![
Line::from(vec!["command".magenta(), " running...".dim()]),
@@ -259,7 +267,7 @@ impl HistoryCell {
}
}
pub(crate) fn new_completed_exec_command(command: String, output: CommandOutput) -> Self {
pub(crate) fn new_completed_exec_command(command: Vec<String>, output: CommandOutput) -> Self {
let CommandOutput {
exit_code,
stdout,
@@ -283,7 +291,8 @@ impl HistoryCell {
let src = if exit_code == 0 { stdout } else { stderr };
lines.push(Line::from(format!("$ {command}")));
let cmdline = strip_bash_lc_and_escape(&command);
lines.push(Line::from(format!("$ {cmdline}")));
let mut lines_iter = src.lines();
for raw in lines_iter.by_ref().take(TOOL_CALL_MAX_LINES) {
lines.push(ansi_escape_line(raw).dim());
@@ -476,6 +485,87 @@ impl HistoryCell {
}
}
/// Render a userfriendly plan update with colourful status icons and a
/// simple progress indicator so users can follow along.
pub(crate) fn new_plan_update(update: UpdatePlanArgs) -> Self {
let UpdatePlanArgs { explanation, plan } = update;
let mut lines: Vec<Line<'static>> = Vec::new();
// Title
lines.push(Line::from("plan".magenta().bold()));
if !plan.is_empty() {
// Progress bar show completed/total with a visual bar
let total = plan.len();
let completed = plan
.iter()
.filter(|p| matches!(p.status, StepStatus::Completed))
.count();
let width: usize = 20;
let filled = (completed * width + total / 2) / total;
let empty = width.saturating_sub(filled);
let mut bar_spans: Vec<Span> = Vec::new();
if filled > 0 {
bar_spans.push(Span::styled(
"".repeat(filled),
Style::default().fg(Color::Green),
));
}
if empty > 0 {
bar_spans.push(Span::styled(
"".repeat(empty),
Style::default().fg(Color::Gray),
));
}
let progress_prefix = Span::raw("progress [");
let progress_suffix = Span::raw("] ");
let fraction = Span::raw(format!("{completed}/{total}"));
let mut progress_line_spans = vec![progress_prefix];
progress_line_spans.extend(bar_spans);
progress_line_spans.push(progress_suffix);
progress_line_spans.push(fraction);
lines.push(Line::from(progress_line_spans));
}
// Optional explanation/note from the model
if let Some(expl) = explanation.and_then(|s| {
let t = s.trim().to_string();
if t.is_empty() { None } else { Some(t) }
}) {
lines.push(Line::from("note".gray().italic()));
for l in expl.lines() {
lines.push(Line::from(l.to_string()).gray());
}
}
// Steps (1based numbering) with fun, readable status icons
if plan.is_empty() {
lines.push(Line::from("(no steps provided)".gray().italic()));
} else {
for (idx, PlanItemArg { step, status }) in plan.into_iter().enumerate() {
let num = idx + 1;
let icon_span: Span = match status {
StepStatus::Completed => Span::from("").fg(Color::Green),
StepStatus::InProgress => Span::from("").fg(Color::Yellow).bold(),
StepStatus::Pending => Span::from("").fg(Color::Gray),
};
lines.push(Line::from(vec![
format!("{num:>2}. [").into(),
icon_span,
"] ".into(),
step.into(),
]));
}
}
lines.push(Line::from(""));
HistoryCell::PlanUpdate {
view: TextBlock::new(lines),
}
}
/// Create a new `PendingPatch` cell that lists the filelevel summary of
/// a proposed patch. The summary lines should already be formatted (e.g.
/// "A path/to/file.rs").

View File

@@ -4,6 +4,7 @@ use std::io::Write;
use crate::tui;
use crossterm::Command;
use crossterm::cursor::MoveTo;
use crossterm::queue;
use crossterm::style::Color as CColor;
use crossterm::style::Colors;
@@ -12,7 +13,6 @@ use crossterm::style::SetAttribute;
use crossterm::style::SetBackgroundColor;
use crossterm::style::SetColors;
use crossterm::style::SetForegroundColor;
use ratatui::layout::Position;
use ratatui::layout::Size;
use ratatui::prelude::Backend;
use ratatui::style::Color;
@@ -23,6 +23,7 @@ use ratatui::text::Span;
/// Insert `lines` above the viewport.
pub(crate) fn insert_history_lines(terminal: &mut tui::Tui, lines: Vec<Line>) {
let screen_size = terminal.backend().size().unwrap_or(Size::new(0, 0));
let cursor_pos = terminal.get_cursor_position().ok();
let mut area = terminal.get_frame().area();
@@ -35,12 +36,12 @@ pub(crate) fn insert_history_lines(terminal: &mut tui::Tui, lines: Vec<Line>) {
.backend_mut()
.scroll_region_down(area.top()..screen_size.height, scroll_amount)
.ok();
let cursor_top = area.top() - 1;
let cursor_top = area.top().saturating_sub(1);
area.y += scroll_amount;
terminal.set_viewport_area(area);
cursor_top
} else {
area.top() - 1
area.top().saturating_sub(1)
};
// Limit the scroll region to the lines from the top of the screen to the
@@ -60,9 +61,10 @@ pub(crate) fn insert_history_lines(terminal: &mut tui::Tui, lines: Vec<Line>) {
// └──────────────────────────────┘
queue!(std::io::stdout(), SetScrollRegion(1..area.top())).ok();
terminal
.set_cursor_position(Position::new(0, cursor_top))
.ok();
// NB: we are using MoveTo instead of set_cursor_position here to avoid messing with the
// terminal's last_known_cursor_position, which hopefully will still be accurate after we
// fetch/restore the cursor position. insert_history_lines should be cursor-position-neutral :)
queue!(std::io::stdout(), MoveTo(0, cursor_top)).ok();
for line in lines {
queue!(std::io::stdout(), Print("\r\n")).ok();
@@ -70,6 +72,11 @@ pub(crate) fn insert_history_lines(terminal: &mut tui::Tui, lines: Vec<Line>) {
}
queue!(std::io::stdout(), ResetScrollRegion).ok();
// Restore the cursor position to where it was before we started.
if let Some(cursor_pos) = cursor_pos {
queue!(std::io::stdout(), MoveTo(cursor_pos.x, cursor_pos.y)).ok();
}
}
fn wrapped_line_count(lines: &[Line], width: u16) -> u16 {
@@ -209,18 +216,18 @@ where
{
let mut fg = Color::Reset;
let mut bg = Color::Reset;
let mut modifier = Modifier::empty();
let mut last_modifier = Modifier::empty();
for span in content {
let mut next_modifier = modifier;
next_modifier.insert(span.style.add_modifier);
next_modifier.remove(span.style.sub_modifier);
if next_modifier != modifier {
let mut modifier = Modifier::empty();
modifier.insert(span.style.add_modifier);
modifier.remove(span.style.sub_modifier);
if modifier != last_modifier {
let diff = ModifierDiff {
from: modifier,
to: next_modifier,
from: last_modifier,
to: modifier,
};
diff.queue(&mut writer)?;
modifier = next_modifier;
last_modifier = modifier;
}
let next_fg = span.style.fg.unwrap_or(Color::Reset);
let next_bg = span.style.bg.unwrap_or(Color::Reset);
@@ -243,3 +250,37 @@ where
SetAttribute(crossterm::style::Attribute::Reset),
)
}
#[cfg(test)]
mod tests {
#![allow(clippy::unwrap_used)]
use super::*;
#[test]
fn writes_bold_then_regular_spans() {
use ratatui::style::Stylize;
let spans = ["A".bold(), "B".into()];
let mut actual: Vec<u8> = Vec::new();
write_spans(&mut actual, spans.iter()).unwrap();
let mut expected: Vec<u8> = Vec::new();
queue!(
expected,
SetAttribute(crossterm::style::Attribute::Bold),
Print("A"),
SetAttribute(crossterm::style::Attribute::NormalIntensity),
Print("B"),
SetForegroundColor(CColor::Reset),
SetBackgroundColor(CColor::Reset),
SetAttribute(crossterm::style::Attribute::Reset),
)
.unwrap();
assert_eq!(
String::from_utf8(actual).unwrap(),
String::from_utf8(expected).unwrap()
);
}
}

View File

@@ -25,6 +25,7 @@ mod bottom_pane;
mod chatwidget;
mod citation_regex;
mod cli;
mod custom_terminal;
mod exec_command;
mod file_search;
mod get_git_diff;
@@ -40,6 +41,11 @@ mod text_formatting;
mod tui;
mod user_approval_widget;
#[cfg(not(debug_assertions))]
mod updates;
#[cfg(not(debug_assertions))]
use color_eyre::owo_colors::OwoColorize;
pub use cli::Cli;
pub async fn run_main(
@@ -74,7 +80,7 @@ pub async fn run_main(
config_profile: cli.config_profile.clone(),
codex_linux_sandbox_exe,
base_instructions: None,
include_plan_tool: None,
include_plan_tool: Some(true),
};
// Parse `-c` overrides from the CLI.
let cli_kv_overrides = match cli.config_overrides.parse_overrides() {
@@ -138,6 +144,38 @@ pub async fn run_main(
.with(tui_layer)
.try_init();
#[allow(clippy::print_stderr)]
#[cfg(not(debug_assertions))]
if let Some(latest_version) = updates::get_upgrade_version(&config) {
let current_version = env!("CARGO_PKG_VERSION");
let exe = std::env::current_exe()?;
let managed_by_npm = std::env::var_os("CODEX_MANAGED_BY_NPM").is_some();
eprintln!(
"{} {current_version} -> {latest_version}.",
"✨⬆️ Update available!".bold().cyan()
);
if managed_by_npm {
let npm_cmd = "npm install -g @openai/codex@latest";
eprintln!("Run {} to update.", npm_cmd.cyan().on_black());
} else if cfg!(target_os = "macos")
&& (exe.starts_with("/opt/homebrew") || exe.starts_with("/usr/local"))
{
let brew_cmd = "brew upgrade codex";
eprintln!("Run {} to update.", brew_cmd.cyan().on_black());
} else {
eprintln!(
"See {} for the latest releases and installation options.",
"https://github.com/openai/codex/releases/latest"
.cyan()
.on_black()
);
}
eprintln!("");
}
let show_login_screen = should_show_login_screen(&config);
if show_login_screen {
std::io::stdout()
@@ -175,9 +213,13 @@ fn run_ratatui_app(
color_eyre::install()?;
// Forward panic reports through tracing so they appear in the UI status
// line instead of interleaving raw panic output with the interface.
std::panic::set_hook(Box::new(|info| {
// line, but do not swallow the default/color-eyre panic handler.
// Chain to the previous hook so users still get a rich panic report
// (including backtraces) after we restore the terminal.
let prev_hook = std::panic::take_hook();
std::panic::set_hook(Box::new(move |info| {
tracing::error!("panic: {info}");
prev_hook(info);
}));
let mut terminal = tui::init(&config)?;
terminal.clear()?;
@@ -221,7 +263,7 @@ fn should_show_login_screen(config: &Config) -> bool {
// Reading the OpenAI API key is an async operation because it may need
// to refresh the token. Block on it.
let codex_home = config.codex_home.clone();
match load_auth(&codex_home) {
match load_auth(&codex_home, true) {
Ok(Some(_)) => false,
Ok(None) => true,
Err(err) => {

View File

@@ -16,6 +16,8 @@ pub enum SlashCommand {
Compact,
Diff,
Quit,
#[cfg(debug_assertions)]
TestApproval,
}
impl SlashCommand {
@@ -23,13 +25,13 @@ impl SlashCommand {
pub fn description(self) -> &'static str {
match self {
SlashCommand::New => "Start a new chat.",
SlashCommand::Compact => {
"Summarize and compact the current conversation to free up context."
}
SlashCommand::Compact => "Compact the chat history.",
SlashCommand::Quit => "Exit the application.",
SlashCommand::Diff => {
"Show git diff of the working directory (including untracked files)"
}
#[cfg(debug_assertions)]
SlashCommand::TestApproval => "Test approval request",
}
}
@@ -44,58 +46,3 @@ impl SlashCommand {
pub fn built_in_slash_commands() -> Vec<(&'static str, SlashCommand)> {
SlashCommand::iter().map(|c| (c.command(), c)).collect()
}
#[cfg(test)]
mod tests {
use crate::app_event_sender::AppEventSender;
use crate::bottom_pane::chat_composer::ChatComposer;
use crossterm::event::KeyCode;
use insta::assert_snapshot;
use ratatui::Terminal;
use ratatui::backend::TestBackend;
use std::sync::mpsc;
#[test]
fn test_slash_commands() {
let (tx, _rx) = mpsc::channel();
let sender = AppEventSender::new(tx);
let mut composer = ChatComposer::new(true, sender);
let mut terminal = match Terminal::new(TestBackend::new(100, 10)) {
Ok(t) => t,
Err(e) => panic!("Failed to create terminal: {e}"),
};
// Initial empty state
if let Err(e) = terminal.draw(|f| f.render_widget_ref(&composer, f.area())) {
panic!("Failed to draw empty composer: {e}");
}
assert_snapshot!("empty_slash", terminal.backend());
// Type slash to show commands
let _ = composer.handle_key_event(crossterm::event::KeyEvent::new(
KeyCode::Char('/'),
crossterm::event::KeyModifiers::empty(),
));
if let Err(e) = terminal.draw(|f| f.render_widget_ref(&composer, f.area())) {
panic!("Failed to draw slash commands: {e}");
}
assert_snapshot!("slash_commands", terminal.backend());
// Type 'c' to filter to compact
let _ = composer.handle_key_event(crossterm::event::KeyEvent::new(
KeyCode::Char('c'),
crossterm::event::KeyModifiers::empty(),
));
if let Err(e) = terminal.draw(|f| f.render_widget_ref(&composer, f.area())) {
panic!("Failed to draw filtered commands: {e}");
}
assert_snapshot!("compact_filtered", terminal.backend());
// Select compact command - we don't check the final state since it's handled by the app layer
let _ = composer.handle_key_event(crossterm::event::KeyEvent::new(
KeyCode::Enter,
crossterm::event::KeyModifiers::empty(),
));
}
}

Some files were not shown because too many files have changed in this diff Show More