codex

change collaboration mode to struct (#9793 )

Shouldn't cause behavioral change

Ahmed Ibrahim · 2026-01-23 17:00:23 -08:00

69cfc73dc6

Load untrusted rules (#9791 )

gt-oai · 2026-01-23 21:52:27 +00:00

b9deb57689

still load skills (#9700 )

gt-oai · 2026-01-23 20:35:50 +00:00

c6ded0afd8

Fix resume picker when user event appears after head (#9512 )

Fixes #9501

Contributing guide:
https://github.com/openai/codex/blob/main/docs/contributing.md

## Summary
The resume picker requires a session_meta line and at least one
user_message event within the initial head scan. Some rollout files
contain multiple session_meta entries before the first user_message, so
the user event can fall outside the default head window and the session
is omitted from the picker even though it is resumable by ID.

This PR keeps the head summary bounded but extends scanning for a
user_message once a session_meta has been observed. The summary still
caps stored head entries, but we allow a small, bounded extra scan to
find the first user event so valid sessions are not filtered out.

## Changes
- Continue scanning past the head limit (bounded) when session_meta is
present but no user_message has been seen yet.
- Mark session_meta as seen even if the head summary buffer is already
full.
- Add a regression test with multiple session_meta lines before the
first user_message.

## Why This Is Safe
- The head summary remains bounded to avoid unbounded memory usage.
- The extra scan is capped (USER_EVENT_SCAN_LIMIT) and only triggers
after a session_meta is seen.
- Behavior is unchanged for typical files where the user_message appears
early.

## Testing
- cargo test -p codex-core --lib
test_list_threads_scans_past_head_for_user_event

JUAN DAVID SALAS CAMARGO · 2026-01-23 12:21:27 -08:00

e0ae219f36

Select default model from filtered presets (#9782 )

Pick the first available preset after auth filtering for default
selection.

Ahmed Ibrahim · 2026-01-23 12:18:36 -08:00

45fe58159e

Print warning if we skip config loading (#9611 )

https://github.com/openai/codex/pull/9533 silently ignored config if
untrusted. Instead, we still load it but disable it. Maybe we shouldn't
try to parse it either...

<img width="939" height="515" alt="Screenshot 2026-01-21 at 14 56 38"
src="https://github.com/user-attachments/assets/e753cc22-dd99-4242-8ffe-7589e85bef66"
/>

gt-oai · 2026-01-23 20:06:37 +00:00

7938c170d9

prompt (#9777 )

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.

Include a link to a bug report or enhancement request.

Ahmed Ibrahim · 2026-01-23 19:24:48 +00:00

f353d3d695

nit: exclude PWD for rc sourcing (#9753 )

jif-oai · 2026-01-23 13:35:48 +01:00

afa08570f2

chore: use some raw strings to reduce quoting (#9745 )

Small follow-ups for https://github.com/openai/codex/pull/9565. Mainly
`r#`, but also added some whitespace for early returns.

Michael Bolin · 2026-01-22 22:38:10 -08:00

86a1e41f2e

Fix execpolicy parsing for multiline quoted args (#9565 )

## What
Fix bash command parsing to accept double-quoted strings that contain
literal newlines so execpolicy can match allow rules.

## Why
Allow rules like [git, commit] should still match when commit messages
include a newline in a quoted argument; the parser currently rejects
these strings and falls back to the outer shell invocation.

## How
- Validate double-quoted strings by ensuring all named children are
string_content and then stripping the outer quotes from the raw node
text so embedded newlines are preserved.
- Reuse the helper for concatenated arguments.
- Ensure large SI suffix formatting uses the caller-provided locale
formatter for grouping.
- Add coverage for newline-containing quoted arguments.

Fixes #9541.

## Tests
- cargo test -p codex-core
- just fix -p codex-core
- cargo test -p codex-protocol
- just fix -p codex-protocol
- cargo test --all-features

JUAN DAVID SALAS CAMARGO · 2026-01-22 22:16:53 -08:00

f815fa14ea

Change the prompt for planning and reasoning effort (#9733 )

Change the prompt for planning and reasoning effort preset for better
experience

Ahmed Ibrahim · 2026-01-22 18:22:12 -08:00

d86bd20411

feat(app-server) Expose personality (#9674 )

### Motivation
Exposes a per-thread / per-turn `personality` override in the v2
app-server API so clients can influence model communication style at
thread/turn start. Ensures the override is passed into the session
configuration resolution so it becomes effective for subsequent turns
and headless runners.

### Testing
- [x] Add an integration-style test
`turn_start_accepts_personality_override_v2` in
`codex-rs/app-server/tests/suite/v2/turn_start.rs` that verifies a
`/personality` override results in a developer update message containing
`<personality_spec>` in the outbound model request.

------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_6971d646b1c08322a689a54d2649f3fe)

Dylan Hurd · 2026-01-22 18:00:20 -08:00

2b1ee24e11

[connectors] Support connectors part 1 - App server & MCP (#9667 )

In order to make Codex work with connectors, we add a built-in gateway
MCP that acts as a transparent proxy between the client and the
connectors. The gateway MCP collects actions that are accessible to the
user and sends them down to the user, when a connector action is chosen
to be called, the client invokes the action through the gateway MCP as
well.

 - [x] Add the system built-in gateway MCP to list and run connectors.
 - [x] Add the app server methods and protocol

Matthew Zeng · 2026-01-22 16:48:43 -08:00

a2c829a808

Update models.json (#9726 )

Automated update of models.json.

---------

Co-authored-by: aibrahim-oai <219906144+aibrahim-oai@users.noreply.github.com>
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>

github-actions[bot] · 2026-01-23 00:44:47 +00:00

d9e041e0a6

feat: support proxy for ws connection (#9719 )

reapply websocket changes without changing tls lib.

Anton Panasenko · 2026-01-22 15:23:15 -08:00

e117a3ff33

Fix typo in experimental_prompt.md (#9716 )

Simple typo fix in the first sentence of the experimental_prompt.md
instructions file.

iudi · 2026-01-22 14:07:14 -08:00

afd63e8bae

feat(app-server): support archived threads in thread/list (#9571 )

Owen Lin · 2026-01-22 12:22:36 -08:00

733cb68496

feat(core) update Personality on turn (#9644 )

## Summary
Support updating Personality mid-Thread via UserTurn/OverwriteTurn. This
is explicitly unused by the clients so far, to simplify PRs - app-server
and tui implementations will be follow-ups.

## Testing
- [x] added integration tests

Dylan Hurd · 2026-01-22 12:04:23 -08:00

8b3521ee77

Support end_turn flag (#9698 )

Experimental flag that signals the end of the turn.

pakrym-oai · 2026-01-22 17:27:48 +00:00

b511c38ddb

Revert "feat: support proxy for ws connection" (#9693 )

Reverts openai/codex#9409

pakrym-oai · 2026-01-22 15:57:18 +00:00

4d48d4e0c2

Fix: Lower log level for closed-channel send (#9653 )

## What?
- Downgrade the closed-channel send error log to debug in
`codex-rs/core/src/codex.rs`.

## Why?
- `async_channel::Sender::send` only fails when the channel is closed,
so the current error-level log is noisy during normal shutdown. See
issue #9652.

## How?
- Replace the error log with a debug log on send failure.

## Tests
- `just fmt`
- `just fix -p codex-core`
- `cargo test -p codex-core`

Kbediako · 2026-01-21 22:09:58 -08:00

079fd2adb9

Add tui.experimental_mode setting (#9656 )

To simplify testing

pakrym-oai · 2026-01-22 05:27:57 +00:00

836f0343a3

Add UI for skill enable/disable. (#9627 )

"/skill" will now allow you to enable/disable skills:
<img width="658" height="199" alt="image"
src="https://github.com/user-attachments/assets/bf8994c8-d6c1-462f-8bbb-f1ee9241caa4"
/>

xl-openai · 2026-01-21 18:21:12 -08:00

577ba3a4ca

feat(core) ModelInfo.model_instructions_template (#9597 )

## Summary
#9555 is the start of a rename, so I'm starting to standardize here.
Sets up `model_instructions` templating with a strongly-typed object for
injecting a personality block into the model instructions.

## Testing
- [x] Added tests
- [x] Ran locally

Dylan Hurd · 2026-01-21 18:11:18 -08:00

96a72828be

feat(tui): retire the tui2 experiment (#9640 )

## Summary
- Retire the experimental TUI2 implementation and its feature flag.
- Remove TUI2-only config/schema/docs so the CLI stays on the
terminal-native path.
- Keep docs aligned with the legacy TUI while we focus on redraw-based
improvements.

## Customer impact
- Retires the TUI2 experiment and keeps Codex on the proven
terminal-native UI while we invest in redraw-based improvements to the
existing experience.

## Migration / compatibility
- If you previously set tui2-related options in config.toml, they are
now ignored and Codex continues using the existing terminal-native TUI
(no action required).

## Context
- What worked: a transcript-owned viewport delivered excellent resize
rewrap and high-fidelity copy (especially for code).
- Why stop: making that experience feel fully native across the
environment matrix (terminal emulator, OS, input modality, multiplexer,
font/theme, alt-screen behavior) creates a combinatorial explosion of
edge cases.
- What next: we are focusing on redraw-based improvements to the
existing terminal-native TUI so scrolling, selection, and copy remain
native while resize/redraw correctness improves.

## Testing
- just write-config-schema
- just fmt
- cargo clippy --fix --all-features --tests --allow-dirty --allow-no-vcs
-p codex-core
- cargo clippy --fix --all-features --tests --allow-dirty --allow-no-vcs
-p codex-cli
- cargo check
- cargo test -p codex-core
- cargo test -p codex-cli

Josh McKinney · 2026-01-22 01:02:29 +00:00

a489b64cb5

Reduce burst testing flake (#9549 )

## Summary

- make paste-burst tests deterministic by injecting explicit timestamps
instead of relying on wall clock timing
- add time-aware helpers for input/submission paths so tests can drive
the burst heuristic precisely
- update burst-related tests to flush using computed timeouts while
preserving behavior assertions
- increase timeout slack in
shell_tools_start_before_response_completed_when_stream_delayed to
reduce flakiness

charley-oai · 2026-01-21 16:42:31 -08:00

41e38856f6

feat: publish config schema on release (#9572 )

Follow up to #8956; publish schema on new release to stable URL.

Also canonicalize schema (sort keys) when writing. This avoids reliance
on default `schema_rs` behavior and makes the schema easier to read.

sayan-oai · 2026-01-21 16:24:14 -08:00

c285b88980

Add layered config.toml support to app server (#9510 )

This PR adds support for chained (layered) config.toml file merging for
clients that use the app server interface. This feature already exists
for the TUI, but it does not work for GUI clients.

It does the following:
* Changes code paths for new thread, resume thread, and fork thread to
use the effective config based on the cwd.
* Updates the `config/read` API to accept an optional `cwd` parameter.
If specified, the API returns the effective config based on that cwd
path. Also optionally includes all layers including project config
files. If cwd is not specified, the API falls back on its older behavior
where it considers only the global (non-project) config files when
computing the effective config.

The changes in codex_message_processor.rs look deceptively large. They
mostly just involve moving existing blocks of code to a later point in
some functions so it can use the cwd to calculate the config.

This PR builds upon #9509 and should be reviewed and merged after that
PR.

Tested:
* Verified change with (dependent, as-yet-uncommitted) changes to IDE
Extension and confirmed correct behavior

The full fix requires additional changes in the IDE Extension code base,
but they depend on this PR.

Eric Traut · 2026-01-21 14:21:48 -08:00

2ca9a56528

Add collaboration_mode to TurnContextItem (#9583 )

## Summary
- add optional `collaboration_mode` to `TurnContextItem` in rollouts
- persist the current collaboration mode when recording turn context
(sampling + compaction)

## Rationale
We already persist turn context data for resume logic. Capturing
collaboration mode in the rollout gives us the mode context for each
turn, enabling follow‑up work to diff mode instructions correctly on
resume.

## Changes
- protocol: add optional `collaboration_mode` field to `TurnContextItem`
- core: persist collaboration mode alongside other turn context settings
in rollouts

charley-oai · 2026-01-21 14:14:21 -08:00

fe641f759f

Chore: update plan mode output in prompt (#9592 )

### Summary
* Update plan prompt output
* Update requestUserInput response to be a single key value pair
`answer: String`.

Shijie Rao · 2026-01-21 14:12:18 -08:00

3fcb40245e

chore: defensive shell snapshot (#9609 )

This PR adds 2 defensive mechanisms for shell snapshotting:
* Filter out invalid env variables (containing `-` for example) without
dropping the whole snapshot
* Validate the snapshot before considering it as valid by running a mock
command with a shell snapshot

jif-oai · 2026-01-21 18:41:58 +00:00

3355adad1d

feat: async shell snapshot (#9600 )

jif-oai · 2026-01-21 10:41:13 +00:00

b75024c465

Added "codex." prefix to "conversation.turn.count" metric name (#9594 )

All other metrics names start with "codex.", so I presume this was an
unintended omission.

Eric Traut · 2026-01-21 10:00:47 +00:00

16b9380e99

feat: display raw command on user shell (#9598 )

jif-oai · 2026-01-21 09:44:38 +00:00

a22a61e678

feat: max threads config (#9483 )

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.

Include a link to a bug report or enhancement request.

jif-oai · 2026-01-21 09:39:11 +00:00

f1c961d5f7

Feature to auto-enable websockets transport (#9578 )

pakrym-oai · 2026-01-20 20:32:06 -08:00

527b7b4c02

feat: add skill injected counter metric (#9575 )

alexsong-oai · 2026-01-20 19:05:37 -08:00

fabc2bcc32

Reject ask user question tool in Execute and Custom (#9560 )

## Summary
- Keep `request_user_input` in the tool list but reject it at runtime in
Execute/Custom modes with a clear model-facing error.
- Add a session accessor for current collaboration mode and enforce the
gate in the request_user_input handler.
- Update core/app-server tests to use Plan mode for success and add
Execute/Custom rejection coverage.

charley-oai · 2026-01-20 18:32:17 -08:00

0523a259c8

feat: rename experimental_instructions_file to model_instructions_file (#9555 )

A user who has `experimental_instructions_file` set will now see this:

<img width="888" height="660" alt="image"
src="https://github.com/user-attachments/assets/51c98312-eb9b-4881-81f1-bea6677e158d"
/>

And a `codex exec` would include this warning:

<img width="888" height="660" alt="image"
src="https://github.com/user-attachments/assets/a89f62be-1edf-4593-a75e-e0b4a762ed7d"
/>

Michael Bolin · 2026-01-21 02:25:08 +00:00

f4d55319d1

[codex-tui] exit when terminal is dumb (#9293 )

Using terminal with TERM=dumb specifically mean that TUIs and the like
don't work. Ensure that codex doesn't run in these environments and exit
with odd errors like crossterm's "Error: The cursor position could not
be read within a normal duration"

---------

Co-authored-by: Josh McKinney <joshka@openai.com>

Jeff Mickey · 2026-01-20 16:17:38 -08:00

c14e6813fb

fix(core): require approval for force delete on Windows (#8590 )

### What
Implemented detection for dangerous "force delete" commands on Windows
to trigger the user approval prompt when `--ask-for-approval on-request`
is set. This aligns Windows behavior with the existing safety checks for
`rm -rf` on Linux.

### Why
Fixes #8567 - a critical safety gap where destructive Windows commands
could bypass the approval prompt. This prevents accidental data loss by
ensuring the user explicitly confirms operations that would otherwise
suppress the OS's native confirmation prompts.

### How
Updated the Windows command safety module to identify and flag the
following patterns as dangerous:
*   **PowerShell**:
* Detects `Remove-Item` (and aliases `rm`, `ri`, `del`, `erase`, `rd`,
`rmdir`) when used with the `-Force` flag.
* Uses token-based analysis to robustly detect these patterns even
inside script blocks (`{...}`), sub-expression `(...)`, or
semicolon-chained sequences.
*   **CMD**:
    *   Detects `del /f` (force delete files).
    *   Detects `rd /s /q` (recursive delete quiet).
* **Command Chaining**: Added support for analyzing chained commands
(using `&`, `&&`, `|`, `||`) to separate and check individual commands
(e.g., catching `del /f` hidden in `echo log & del /f data`).

### Testing
Added comprehensive unit tests covering:
* **PowerShell**: `Remove-Item -Path 'test' -Recurse -Force` (Exact
reproduction case).
* **Complex Syntax**: Verified detection inside blocks (e.g., `if
($true) { rm -Force }`) and with trailing punctuation.
*   **CMD**:
    *   `del /f` (Flagged).
    *   `rd /s /q` (Flagged).
    *   Chained commands: `echo hi & del /f file` (Flagged).
*   **False Positives**:
    *   `rd /s` (Not flagged - relies on native prompt).
    *   Standard deletions without force flags.

Verified with `cargo test` and `cargo clippy`.

---------

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

HDCode · 2026-01-20 15:25:27 -08:00

80f80181c2

Enable remote models (#9554 )

Ahmed Ibrahim · 2026-01-20 23:17:22 +00:00

de4980d2ac

Add total (non-partial) TextElement placeholder accessors (#9545 )

## Summary
- Make `TextElement` placeholders private and add a text-backed accessor
to avoid assuming `Some`.
- Since they are optional in the protocol, we want to make sure any
accessors properly handle the None case (getting the placeholder using
the byte range in the text)
- Preserve placeholders during protocol/app-server conversions using the
accessor fallback.
- Update TUI composer/remap logic and tests to use the new
constructor/accessor.

charley-oai · 2026-01-20 14:04:11 -08:00

be9e55c5fc

merge remote models (#9547 )

We have `models.json` and `/models` response
Behavior:
1. New models from models endpoint gets added
2. Shared models get replaced by remote ones
3. Existing models in `models.json` but not `/models` are kept
4. Mark highest priority as default

Ahmed Ibrahim · 2026-01-20 14:02:07 -08:00

56fe5e7bea

fix(core): don't update the file's mtime on resume (#9553 )

Remove `FileTimes::new().set_modified(SystemTime::now())` when resuming
a thread.

Context: It's awkward in UI built on top of app-server that resuming a
thread bumps the `updated_at` timestamp, even if no message is sent. So
if you open a thread (perhaps to just view its contents), it
automatically reorders it to the top which is almost certainly not what
you want.

Owen Lin · 2026-01-20 21:39:31 +00:00

b0049ab644

fix: prevent repeating interrupted turns (#9043 )

## What
Record a model-visible `<turn_aborted>` marker in history when a turn is
interrupted, and treat it as a session prefix.

## Why
When a turn is interrupted, Codex emits `TurnAborted` but previously did
not persist anything model-visible in the conversation history. On the
next user turn, the model can’t tell the previous work was aborted and
may resume/repeat earlier actions (including duplicated side effects
like re-opening PRs).

Fixes: https://github.com/openai/codex/issues/9042

## How
On `TurnAbortReason::Interrupted`, append a hidden user message
containing a `<turn_aborted>…</turn_aborted>` marker and flush.
Treat `<turn_aborted>` like `<environment_context>` for session-prefix
filtering.
Add a regression test to ensure follow-up turns don’t repeat side
effects from an aborted turn.

## Testing
`just fmt`
`just fix -p codex-core`
`cargo test -p codex-core -- --test-threads=1`
`cargo test --all-features -- --test-threads=1`

---------

Co-authored-by: Skylar Graika <sgraika127@gmail.com>
Co-authored-by: jif-oai <jif@openai.com>
Co-authored-by: Eric Traut <etraut@openai.com>

Skylar Graika · 2026-01-20 13:07:28 -08:00

b236f1c95d

Fixed config merging issue with profiles (#9509 )

This PR fixes a small issue with chained (layered) config.toml file
merging. The old logic didn't properly handle profiles.

In particular, if a lower-layer config overrides a profile defined in a
higher-layer config, the override did not take effect. This prevents
users from having project-specific profile overrides and contradicts the
(soon-to-be) documented behavior of config merging.

The change adds a unit test for this case. It also exposes a function
from the config crate that is needed by the app server code paths to
implement support for layered configs.

Eric Traut · 2026-01-20 12:18:00 -08:00

79c5bf9835

fix: memory leak issue (#9543 )

Co-authored-by: Josh McKinney <joshka@openai.com>

jif-oai · 2026-01-20 20:14:14 +00:00

0b3c802a54

feat(personality) introduce model_personality config (#9459 )

## Summary
Introduces the concept of a config model_personality. I would consider
this an MVP for testing out the feature. There are a number of
follow-ups to this PR:

- More sophisticated templating with validation
- In-product experience to manage this

## Testing
- [x] Testing locally

Dylan Hurd · 2026-01-20 11:06:14 -08:00

714151eb4e

Fix typo in feature name from 'Mult-agents' to 'Multi-agents' (#9542 )

Fixes a typo in a feature description.

Simon Willison · 2026-01-20 10:55:36 -08:00

46a4a03083

1304 Commits