codex

Updated the AI labeler rules to match the most recent issue tracker labels (#6347 )

This PR updates the AI prompt used for the workflow that adds automated
labels to incoming issues. I've been updating and refining the list of
labels as I work through the issue backlog, and the old prompt was
becoming somewhat outdated.

Eric Traut · 2025-11-06 16:02:12 -08:00

039a4b070e

Remove shell tool when unified exec is enabled (#6345 )

Also drop streameable shell that's just an alias for unified exec.

pakrym-oai · 2025-11-06 15:46:24 -08:00

c368c6aeea

Don't retry "insufficient_quota" errors (#6340 )

This PR makes an "insufficient quota" error fatal so we don't attempt to
retry it multiple times in the agent loop.

We have multiple bug reports from users about intermittent retry
behaviors, and this could explain some of them. With this change, we'll
eliminate the retries and surface a clear error message.

The PR is a nearly identical copy of [this
PR](https://github.com/openai/codex/pull/4837) contributed by
@abimaelmartell. The original PR has gone stale. Rather than wait for
the contributor to resolve merge conflicts, I wanted to get this change
in.

Eric Traut · 2025-11-06 15:12:01 -08:00

0c647bc566

feat: Enable CTRL-n and CTRL-p for navigating slash commands, files, history (#1994 )

Adds CTRL-n and CTRL-p navigation for slash commands, files, and
history.
Closes #1992

Co-authored-by: Eric Traut <etraut@openai.com>

Ejaz Ahmed · 2025-11-06 14:58:18 -08:00

e30f65118d

tui: fix backtracking past /status (#6335 )

Fixes https://github.com/openai/codex/issues/4722

Supersedes https://github.com/openai/codex/pull/5058

Ideally we'd have a clearer way of separating history per-session than
by detecting a specific history cell type, but this is a fairly minimal
fix for now.

Jeremy Rose · 2025-11-06 14:50:07 -08:00

1bd2d7a659

Make generate_ts prettier output warn-only (#6342 )

Before, every file would be outputted with the time prettier spent
formatting it. This made downstream scripts way too noisy.

Gabriel Peal · 2025-11-06 17:45:51 -05:00

65d53fd4b1

Freeform unified exec output formatting (#6233 )

pakrym-oai · 2025-11-06 22:14:27 +00:00

b5349202e9

[App Server] Add more session metadata to listConversations (#6337 )

This unlocks a few new product experience for app server consumers

Gabriel Peal · 2025-11-06 17:13:24 -05:00

1b8cc8b625

core: widen sandbox to allow certificate ops when network is enabled (#5980 )

This allows `gh api` to work in the workspace-write sandbox w/ network
enabled. Without this we see e.g.

```
$ codex debug seatbelt --full-auto gh api repos/openai/codex/pulls --paginate -X GET -F state=all
Get "https://api.github.com/repos/openai/codex/pulls?per_page=100&state=all": tls: failed to verify certificate: x509: OSStatus -26276
```

Jeremy Rose · 2025-11-06 12:47:20 -08:00

8501b0b768

Updated contributing guidelines and PR template to request link to bug report in PR notes (#6332 )

Some PRs are being submitted without reference to existing bug reports
or feature requests. This updates the PR template and contributing
guidelines to request that all PRs from the community contain such a
link. This provides additional context and helps prioritize, track, and
assess PRs.

Eric Traut · 2025-11-06 12:02:39 -08:00

fe7eb18104

feat: clarify that gpt-5-codex should not amend commits unless requested (#6333 )

Thibault Sottiaux · 2025-11-06 11:42:47 -08:00

8c75ed39d5

chore: move relevant tests to app-server/tests/suite/v2 (#6289 )

These are technically app-server v2 APIs, so move them to the same
directory as the others.

Owen Lin · 2025-11-06 10:53:17 -08:00

fdb9fa301e

Windows Sandbox: Show Everyone-writable directory warning (#6283 )

Show a warning when Auto Sandbox mode becomes enabled, if we detect
Everyone-writable directories, since they cannot be protected by the
current implementation of the Sandbox.

This PR also includes changes to how we detect Everyone-writable to be
*much* faster

iceweasel-oai · 2025-11-06 10:44:42 -08:00

871d442b8e

chore: fix grammar mistakes (#6326 )

Ahmed Ibrahim · 2025-11-06 09:48:59 -08:00

dbad5eeec6

docs: Fix code fence and typo in advanced guide (#6295 )

- add `bash` to code fence
- fix spelling of `JavaScript`

vladislav doster · 2025-11-06 09:00:28 -08:00

4b4252210b

[app-server] feat: v2 Turn APIs (#6216 )

Implements:
```
turn/start
turn/interrupt
```

along with their integration tests. These are relatively light wrappers
around the existing core logic, and changes to core logic are minimal.

However, an improvement made for developer ergonomics:
- `turn/start` replaces both `SendUserMessage` (no turn overrides) and
`SendUserTurn` (can override model, approval policy, etc.)

Owen Lin · 2025-11-06 16:36:36 +00:00

6582554926

chore: rename for clarity (#6319 )

Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>

Thibault Sottiaux · 2025-11-06 08:32:57 -08:00

649ce520c4

feat: support models with single reasoning effort (#6300 )

Thibault Sottiaux · 2025-11-05 23:06:45 -08:00

667e841d3e

feat: add model nudge for queries (#6286 )

Ahmed Ibrahim · 2025-11-06 03:42:59 +00:00

63e1ef25af

[App-server] Add account/login/cancel v2 endpoint (#6288 )

Add `account/login/cancel` v2 endpoint for auth. this is similar
implementation to `cancelLoginChatgpt` v1 endpoint.

Celia Chen · 2025-11-06 01:13:55 +00:00

229d18f4d2

fix: ToC so it doesn’t include itself or duplicate the end marker (#4388 )

turns out the ToC was including itself when generating, which messed up
comparisons and sometimes made the file rewrite endlessly.

also fixed the slice so `<!-- End ToC -->` doesn’t get duplicated when
we insert the new ToC.

should behave nicely now - no extra rewrites, no doubled markers.

Co-authored-by: Eric Traut <etraut@openai.com>

wizard · 2025-11-05 14:52:51 -08:00

4a1a7f9685

Prevent dismissal of login menu in TUI (#6285 )

We currently allow the user to dismiss the login menu via Ctrl+C. This
leaves them in a bad state where they're not auth'ed but have an input
prompt. In the extension, this isn't a problem because we don't allow
the user to dismiss the login screen.

Testing: I confirmed that Ctrl+C no longer dismisses the login menu.

This is an alternative (simpler) fix for a [community
PR](https://github.com/openai/codex/pull/3234).

Eric Traut · 2025-11-05 14:25:58 -08:00

86c149ae8e

[App-server] Implement v2 for account/login/start and account/login/completed (#6183 )

This PR implements `account/login/start` and `account/login/completed`.
Instead of having separate endpoints for login with chatgpt and api, we
have a single enum handling different login methods. For sync auth
methods like sign in with api key, we still send a `completed`
notification back to be compatible with the async login flow.

Celia Chen · 2025-11-05 13:52:50 -08:00

05f0b4f590

stop capturing r when environment selection modal is open (#6249 )

This fixes an issue where you can't select environments with an r in them when the selection modal is open

easong-openai · 2025-11-05 13:23:46 -08:00

d4eda9d10b

Fixes intermittent test failures in CI (#6282 )

I'm seeing two tests fail intermittently in CI. This PR attempts to
address (or at least mitigate) the flakiness.

* summarize_context_three_requests_and_instructions - The test snapshots
server.received_requests() immediately after observing TaskComplete.
Because the OpenAI /v1/responses call is streamed, the HTTP request can
still be draining when that event fires, so wiremock occasionally
reports only two captured requests. Fix is to wait for async activity to
complete.
* archive_conversation_moves_rollout_into_archived_directory - times out
on a slow CI run. Mitigation is to increase timeout value from 10s to
20s.

Eric Traut · 2025-11-05 13:12:25 -08:00

d7953aed74

[app-server] feat: v2 Thread APIs (#6214 )

Implements:
```
thread/list
thread/start
thread/resume
thread/archive
```

along with their integration tests. These are relatively light wrappers
around the existing core logic, and changes to core logic are minimal.

However, an improvement made for developer ergonomics:
- `thread/start` and `thread/resume` automatically attaches a
conversation listener internally, so clients don't have to make a
separate `AddConversationListener` call like they do today.

For consistency, also updated `model/list` and `feedback/upload` (naming
conventions, list API params).

Owen Lin · 2025-11-05 20:28:43 +00:00

2ab1650d4d

Update rmcp to 0.8.5 (#6261 )

Picks up https://github.com/modelcontextprotocol/rust-sdk/pull/511 which
should fix todoist and some other MCP server oauth and may further
resolve issues in https://github.com/openai/codex/issues/5045

Gabriel Peal · 2025-11-05 14:20:30 -05:00

79aa83ee39

Improved token refresh handling to address "Re-connecting" behavior (#6231 )

Currently, when the access token expires, we attempt to use the refresh
token to acquire a new access token. This works most of the time.
However, there are situations where the refresh token is expired,
exhausted (already used to perform a refresh), or revoked. In those
cases, the current logic treats the error as transient and attempts to
retry it repeatedly.

This PR changes the token refresh logic to differentiate between
permanent and transient errors. It also changes callers to treat the
permanent errors as fatal rather than retrying them. And it provides
better error messages to users so they understand how to address the
problem. These error messages should also help us further understand why
we're seeing examples of refresh token exhaustion.

Here is the error message in the CLI. The same text appears within the
extension.

<img width="863" height="38" alt="image"
src="https://github.com/user-attachments/assets/7ffc0d08-ebf0-4900-b9a9-265064202f4f"
/>

I also correct the spelling of "Re-connecting", which shouldn't have a
hyphen in it.

Testing: I manually tested these code paths by adding temporary code to
programmatically cause my refresh token to be exhausted (by calling the
token refresh endpoint in a tight loop more than 50 times). I then
simulated an access token expiration, which caused the token refresh
logic to be invoked. I confirmed that the updated logic properly handled
the error condition.

Note: We earlier discussed the idea of forcefully logging out the user
at the point where token refresh failed. I made several attempts to do
this, and all of them resulted in a bad UX. It's important to surface
this error to users in a way that explains the problem and tells them
that they need to log in again. We also previously discussed deleting
the auth.json file when this condition is detected. That also creates
problems because it effectively changes the auth status from logged in
to logged out, and this causes odd failures and inconsistent UX. I think
it's therefore better not to delete auth.json in this case. If the user
closes the CLI or VSCE and starts it again, we properly detect that the
access token is expired and the refresh token is "dead", and we force
the user to go through the login flow at that time.

This should address aspects of #6191, #5679, and #5505

Eric Traut · 2025-11-05 10:51:57 -08:00

c4ebe4b078

refactor Conversation history file into its own directory (#6229 )

This is just a refactor of `conversation_history` file by breaking it up
into multiple smaller ones with helper. This refactor will help us move
more functionality related to context management here. in a clean way.

Ahmed Ibrahim · 2025-11-05 10:49:35 -08:00

1a89f70015

tui: refactor ChatWidget and BottomPane to use Renderables (#5565 )

- introduce RenderableItem to support both owned and borrowed children
in composite Renderables
- refactor some of our gnarlier manual layouts, BottomPane and
ChatWidget, to use ColumnRenderable
- Renderable and friends now handle cursor_pos()

Jeremy Rose · 2025-11-05 09:50:40 -08:00

62474a30e8

Add modelReasoningEffort option to TypeScript SDK (#6237 )

## Summary
- Adds `ModelReasoningEffort` type to TypeScript SDK with values:
`minimal`, `low`, `medium`, `high`
- Adds `modelReasoningEffort` option to `ThreadOptions`
- Forwards the option to the codex CLI via `--config
model_reasoning_effort="<value>"`
- Includes test coverage for the new option

## Changes
- `sdk/typescript/src/threadOptions.ts`: Define `ModelReasoningEffort`
type and add to `ThreadOptions`
- `sdk/typescript/src/index.ts`: Export `ModelReasoningEffort` type
- `sdk/typescript/src/exec.ts`: Forward `modelReasoningEffort` to CLI as
config flag
- `sdk/typescript/src/thread.ts`: Pass option through to exec (+ debug
logging)
- `sdk/typescript/tests/run.test.ts`: Add test for
`modelReasoningEffort` flag forwarding

---------

Co-authored-by: Eric Traut <etraut@openai.com>

Dan Hernandez · 2025-11-05 08:51:03 -08:00

9a10e80ab7

Upgrade rmcp to 0.8.4 (#6234 )

Picks up https://github.com/modelcontextprotocol/rust-sdk/pull/509 which
fixes https://github.com/openai/codex/issues/6164

Gabriel Peal · 2025-11-05 00:23:24 -05:00

9b538a8672

allow codex to be run from pid 1 (#4200 )

Previously it was not possible for codex to run commands as the init
process (pid 1) in linux. Commands run in containers tend to see their
own pid as 1. See https://github.com/openai/codex/issues/4198

This pr implements the solution mentioned in that issue.

Co-authored-by: Eric Traut <etraut@openai.com>

Andrew Dirksen · 2025-11-04 17:54:46 -08:00

95af417923

fix(core): load custom prompts from symlinked Markdown files (#3643 )

- Discover prompts via fs::metadata to follow symlinks

- Add Unix-only symlink test in custom_prompts.rs

- Update docs/prompts.md to mention symlinks

Fixes #3637

---------

Signed-off-by: Soroush Yousefpour <h.yusefpour@gmail.com>
Co-authored-by: dedrisian-oai <dedrisian@openai.com>
Co-authored-by: Eric Traut <etraut@openai.com>

Soroush Yousefpour · 2025-11-04 17:44:02 -08:00

fff576cf98

Fix nix build (#6230 )

Previously, the `nix build .#default` command fails due to a missing
output hash in the `./codex-rs/default.nix` for `crossterm-0.28.1`:

```
error: No hash was found while vendoring the git dependency crossterm-0.28.1. You can add
a hash through the `outputHashes` argument of `importCargoLock`:

outputHashes = {
 "crossterm-0.28.1" = "<hash>";
};

If you use `buildRustPackage`, you can add this attribute to the `cargoLock`
attribute set.
```

This PR adds the missing hash:

```diff
cargoLock.outputHashes = {
  "ratatui-0.29.0" = "sha256-HBvT5c8GsiCxMffNjJGLmHnvG77A6cqEL+1ARurBXho=";
+ "crossterm-0.28.1" = "sha256-6qCtfSMuXACKFb9ATID39XyFDIEMFDmbx6SSmNe+728=";
};
```

With this change, `nix build .#default` succeeds:

```
> nix build .#default --max-jobs 1 --cores 2

warning: Git tree '/home/lukas/r/github.com/lukasl-dev/codex' is dirty
[1/0/1 built] building codex-rs-0.1.0 (buildPhase)[1/0/1 built] building codex-rs-0.1.0 (buildP[1/0/1 built] building codex-rs-0.1.0 (buildPhase):    [1/0/1 built] building codex-rs-0.1.0 (b[1/0/1 built] building codex-rs-0.1.0 (buildPhase):    Compi[1/0/1 built] building codex-rs-0.1

> ./result/bin/codex
  You are running Codex in /home/lukas/r/github.com/lukasl-dev/codex

  Since this folder is version controlled, you may wish to allow Codex to work in this folder without asking for approval.
  ...
```

Lukas · 2025-11-04 17:07:37 -08:00

1575f0504c

[app-server] feat: export.rs supports a v2 namespace, initial v2 notifications (#6212 )

**Typescript and JSON schema exports**
While working on Thread/Turn/Items type definitions, I realize we will
run into name conflicts between v1 and v2 APIs (e.g. `RateLimitWindow`
which won't be reusable since v1 uses `RateLimitWindow` from `protocol/`
which uses snake_case, but we want to expose camelCase everywhere, so
we'll define a V2 version of that struct that serializes as camelCase).

To set us up for a clean and isolated v2 API, generate types into a
`v2/` namespace for both typescript and JSON schema.
- TypeScript: v2 types emit under `out_dir/v2/*.ts`, and root index.ts
now re-exports them via `export * as v2 from "./v2"`;.
- JSON Schemas: v2 definitions bundle under `#/definitions/v2/*` rather
than the root.

The location for the original types (v1 and types pulled from
`protocol/` and other core crates) haven't changed and are still at the
root. This is for backwards compatibility: no breaking changes to
existing usages of v1 APIs and types.

**Notifications**
While working on export.rs, I:
- refactored server/client notifications with macros (like we already do
for methods) so they also get exported (I noticed they weren't being
exported at all).
- removed the hardcoded list of types to export as JSON schema by
leveraging the existing macros instead
- and took a stab at API V2 notifications. These aren't wired up yet,
and I expect to iterate on these this week.

Owen Lin · 2025-11-05 01:02:39 +00:00

edf4c3f627

fix: Update the deprecation message to link to the docs (#6211 )

The deprecation message is currently a bit confusing. Users may not
understand what is `[features].x`. I updated the docs and the
deprecation message for more guidance.

---------

Co-authored-by: Gabriel Peal <gpeal@users.noreply.github.com>

Ahmed Ibrahim · 2025-11-04 21:02:27 +00:00

d40a6b7f73

Revert "fix: pin musl 1.2.5 for DNS fixes" (#6222 )

Reverts openai/codex#6189

Dylan Hurd · 2025-11-04 11:56:40 -08:00

3a22018edd

ignore deltas in codex_delegate (#6208 )

ignore legacy deltas in codex-delegate to avoid this
[issue](https://github.com/openai/codex/pull/6202).

Ahmed Ibrahim · 2025-11-04 19:21:35 +00:00

fe54c216a3

fix: pin musl 1.2.5 for DNS fixes (#6189 )

## Summary
musl 1.2.5 includes [several fixes to DNS over
TCP](https://www.openwall.com/lists/musl/2024/03/01/2), which appears to
be the root cause of #6116.

This approach is a bit janky, but according to codex:
> On the Ubuntu 24.04 runners we use, apt-cache policy musl-tools shows
only the distro build (1.2.4-2ubuntu2)"

We should build with this version and confirm.

## Testing
- [ ] TODO: test and see if this fixes Azure issues

Dylan Hurd · 2025-11-04 09:17:16 -08:00

cb6584de46

fix: ignore reasoning deltas because we send it with turn item (#6202 )

should fix this:

<img width="2418" height="242" alt="image"
src="https://github.com/user-attachments/assets/f818d00b-ed3a-479b-94a7-e4bc5db6326e"
/>

Ahmed Ibrahim · 2025-11-04 08:27:16 -08:00

7e068e1094

[App-server] v2 for account/updated and account/logout (#6175 )

V2 for `account/updated` and `account/logout` for app server. correspond
to old `authStatusChange` and `LogoutChatGpt` respectively. Followup PRs
will make other v2 endpoints call `account/updated` instead of
`authStatusChange` too.

Celia Chen · 2025-11-03 22:01:33 -08:00

d3187dbc17

Fix is_api_message to correctly exclude reasoning messages (#6156 )

## Problem

The `is_api_message` function in `conversation_history.rs` had a
misalignment between its documentation and implementation:

- **Comment stated**: "Anything that is not a system message or
'reasoning' message is considered an API message"
- **Code behavior**: Was returning `true` for `ResponseItem::Reasoning`,
meaning reasoning messages were incorrectly treated as API messages

This inconsistency could lead to reasoning messages being persisted in
conversation history when they should be filtered out.

## Root Cause

Investigation revealed that reasoning messages are explicitly excluded
throughout the codebase:

1. **Chat completions API** (lines 267-272 in `chat_completions.rs`)
omits reasoning from conversation history:
   ```rust
   ResponseItem::Reasoning { .. } | ResponseItem::Other => {
       // Omit these items from the conversation history.
       continue;
   }
   ```

2. **Existing tests** like `drops_reasoning_when_last_role_is_user` and
`ignores_reasoning_before_last_user` validate that reasoning should be
excluded from API payloads

## Solution

Fixed the `is_api_message` function to align with its documentation and
the rest of the codebase:

```rust
// Before: Reasoning was incorrectly returning true
ResponseItem::Reasoning { .. } | ResponseItem::WebSearchCall { .. } => true,

// After: Reasoning correctly returns false  
ResponseItem::WebSearchCall { .. } => true,
ResponseItem::Reasoning { .. } | ResponseItem::Other => false,
```

## Testing

- Enhanced existing test to verify reasoning messages are properly
filtered out
- All 264 core tests pass, including 8 chat completions tests that
validate reasoning behavior
- No regressions introduced

This ensures reasoning messages are consistently excluded from API
message processing across the entire codebase.

Robby He · 2025-11-03 20:55:41 -08:00

dc2f26f7b5

Follow symlinks during file search (#4453 )

I have read the CLA Document and I hereby sign the CLA

Closes #4452

This fixes a usability issue where users with symlinked folders in their
working directory couldn't search those files using the `@` file search
feature.

## Rationale

The "bug" was in the file search implementation in
`codex-rs/file-search/src/lib.rs`. The `WalkBuilder` was using default
settings which don't follow symlinks, causing two related issues:

1. Partial search results: The `@` search would find symlinked
directories but couldn't find files inside them
2. Inconsistent behavior: Users expect symlinked folders to behave like
regular folders in search results.

## Root cause

The `ignore` crate's `WalkBuilder` defaults to `.follow_links(false)`
[[source](https://github.com/BurntSushi/ripgrep/blob/9802945e6342ec284633924cb7d8d3ce67204995/crates/ignore/src/walk.rs#L532)],
so when traversing the file system, it would:

- Detect symlinked directories as directory entries
- But not traverse into them to index their contents
- The `get_file_path` function would then filter out actual directories,
leaving only the symlinked folder itself as a result

Fix: Added `.follow_links(true)` to the `WalkBuilder` configuration,
making the file search follow symlinks and index their contents just
like regular directories.

This change maintains backward compatibility since symlink following is
generally expected behavior for file search tools, and it aligns with
how users expect the `@` search feature to work.

Co-authored-by: Eric Traut <etraut@openai.com>

Ricardo Ander-Egg · 2025-11-03 20:28:33 -08:00

553db8def1

docs: add example config.toml (#5175 )

I was missing an example config.toml, and following docs/config.md alone
was slower. I had GPT-5 scan the codebase for every accepted config key,
check the defaults, and generate a single example config.toml with
annotations. It lists all keys Codex reads from TOML, sets each to its
effective default where it exists, leaves optional ones commented, and
adds short comments on purpose and valid values. This should make
onboarding faster and reduce configuration errors. I can rename it to
config.example.toml or move it under docs/ if you prefer.

Lucas Freire Sangoi · 2025-11-03 18:19:26 -08:00

ab63a47173

fix: --search shouldn't show deprecation message (#6180 )

Use the new feature flags instead of the old config.

Ahmed Ibrahim · 2025-11-04 00:11:50 +00:00

e658c6c73b

Fixed notify handler so it passes correct input_messages details (#6143 )

This fixes bug #6121. 

The `input_messages` field passed to the notify handler is currently
empty because the logic is incorrectly including the OutputText rather
than InputText. I've fixed that and added proper filtering to remove
messages associated with AGENTS.md and other context injected by the
harness.

Testing: I wrote a notify handler and verified that the user prompt is
correctly passed through to the handler.

Eric Traut · 2025-11-03 14:23:04 -08:00

1e0e553304

log sandbox commands to $CODEX_HOME instead of cwd (#6171 )

Logging commands in the Windows Sandbox is temporary, but while we are
doing it, let's always write to CODEX_HOME instead of dirtying the cwd.

iceweasel-oai · 2025-11-03 13:12:33 -08:00

07b7d28937

feat: add the time after aborting (#5996 )

Tell the model how much time passed after the user aborted the call.

Ahmed Ibrahim · 2025-11-03 11:44:06 -08:00

6ee7fbcfff

tui: refine text area word separator handling (#5541 )

## Summary
- replace the word part enum with a simple `is_word_separator` helper
- keep word-boundary logic aligned with the helper and punctuation-aware
behavior
- extend forward/backward deletion tests to cover whitespace around
separators

## Testing
- just fix -p codex-tui
- cargo test -p codex-tui


------
https://chatgpt.com/codex/tasks/task_i_68f91c71d838832ca2a3c4f0ec1b55d4

Jeremy Rose · 2025-11-03 11:33:34 -08:00

5f3a0473f1

4710 Commits