codex

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

fix(tui) turn timing incremental (#9599 )

## Summary
When we send multiple assistant messages, reset the timer so "Worked for
2m 36s" is the time since the last time we showed the message, rather
than an ever-increasing number.

We could instead change the copy so it's more clearly a running counter.

## Testing
- [x] ran locally

<img width="903" height="732" alt="Screenshot 2026-01-21 at 1 42 51 AM"
src="https://github.com/user-attachments/assets/bb4d827b-3a0e-48ba-bd6a-d8cd65d8e892"
/>

Dylan Hurd · 2026-01-21 15:59:56 -08:00

f1240ff4fe

feat: better sorting of shell commands (#9629 )

This PR changes the way we sort slash command by going in this order:
1. Exact match
2. Prefix
3. Fuzzy

As a result, we you type `/ps` the default command is not `/approvals`

jif-oai · 2026-01-21 23:03:01 +00:00

5dad1b956e

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

Add websockets logging (#9633 )

To help with debugging.

pakrym-oai · 2026-01-21 21:35:38 +00:00

f2e1ad59bc

forgot to add some windows sandbox nux events. (#9624 )

iceweasel-oai · 2026-01-21 13:24:09 -08:00

7a9c9b8636

[bazel] Upgrade llvm toolchain and enable remote repo cache (#9616 )

On bazel9 this lets us avoid performing some external repo downloads if
they've been previously uploaded to remote cache, downloads are deferred
until they are actually needed to execute an uncached action

zbarsky-openai · 2026-01-21 12:52:39 -08:00

ab8415dcf5

Update skills/list protocol readme (#9623 )

Updates readme example for `skills/list` to reflect latest response
spec.

Gav Verma · 2026-01-21 12:51:51 -08:00

2e06d61339

docs: fix outdated MCP subcommands documentation (#9622 )

Tien Nguyen · 2026-01-21 11:17:37 -08:00

68b8381723

define/emit some metrics for windows sandbox setup (#9573 )

This should give us visibility into how users are using the elevated
sandbox nux flow, and the timing of the elevated setup.

iceweasel-oai · 2026-01-21 11:07:26 -08:00

f81dd128a2

fix: Fix tilde expansion to avoid absolute-path escape (#9621 )

### Motivation
- Prevent inputs like `~//` or `~///etc` from expanding to arbitrary
absolute paths (e.g. `/`) because `Path::join` discards the left side
when the right side is absolute, which could allow config values to
escape `HOME` and broaden writable roots.

### Description
- In `codex-rs/utils/absolute-path/src/lib.rs` update
`maybe_expand_home_directory` to trim leading separators from the suffix
and return `home` when the remainder is empty so tilde expansion stays
rooted under `HOME`.
- Add a non-Windows unit test
`home_directory_double_slash_on_non_windows_is_expanded_in_deserialization`
that validates `"~//code"` expands to `home.join("code")`.

### Testing
- Ran `just fmt` successfully.
- Ran `just fix -p codex-utils-absolute-path` (Clippy autofix)
successfully.
- Ran `cargo test -p codex-utils-absolute-path` and all tests passed.

------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_697007481cac832dbeb1ee144d1e4cbe)

Tiffany Citra · 2026-01-21 10:43:10 -08:00

8179312ff5

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

nit: ui on interruption (#9606 )

jif-oai · 2026-01-21 14:09:15 +00:00

338f2d634b

[bazel] Upgrade to bazel9 (#9576 )

zbarsky-openai · 2026-01-21 13:25:36 +00:00

2338f99f58

nit: better collab tui (#9551 )

<img width="478" height="304" alt="Screenshot 2026-01-21 at 11 53 50"
src="https://github.com/user-attachments/assets/e2ef70de-2fff-44e0-a574-059177966ed2"
/>

jif-oai · 2026-01-21 11:53:58 +00:00

f1b6a43907

fix: nit tui on terminal interactions (#9602 )

jif-oai · 2026-01-21 11:30:34 +00:00

13358fa131

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

fix going up and down on questions after writing notes (#9596 )

Ahmed Ibrahim · 2026-01-21 09:37:37 +00:00

6e9a31def1

Add request-user-input overlay (#9585 )

- Add request-user-input overlay and routing in the TUI

Ahmed Ibrahim · 2026-01-21 00:19:35 -08:00

5f55ed666b

don't ask for approval for just fix (#9586 )

It blocks all my skills from executing because it asks to run just fmt.
It's quick command that doesn't need approval.


<img width="967" height="120" alt="image"
src="https://github.com/user-attachments/assets/f8e6ca76-a650-49e9-beb2-ce98ba48d310"
/>

Ahmed Ibrahim · 2026-01-21 04:56:11 +00:00

ebc88f29f8

fix CI by running pnpm (#9587 )

Ahmed Ibrahim · 2026-01-20 20:54:15 -08:00

465da00d02

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

Prompt Expansion: Preserve Text Elements (#9518 )

Summary
- Preserve `text_elements` through custom prompt argument parsing and
expansion (named and numeric placeholders).
- Translate text element ranges through Shlex parsing using sentinel
substitution, and rehydrate text + element ranges per arg.
- Drop image attachments when their placeholder does not survive prompt
expansion, keeping attachments consistent with rendered elements.
- Mirror changes in TUI2 and expand tests for prompt parsing/expansion
edge cases.

Tests
- placeholders with spaces as single tokens (positional + key=value,
quoted + unquoted),
  - prompt expansion with image placeholders,
  - large paste + image arg combinations,
  - unused image arg dropped after expansion.

charley-oai · 2026-01-20 18:30:20 -08:00

531748a080

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

Show session header before configuration (#9568 )

We were skipping if we know the model. We shouldn't

Ahmed Ibrahim · 2026-01-21 02:13:54 +00:00

3a0eeb8edf

fix: bminor/bash is no longer on GitHub so use bolinfest/bash instead (#9563 )

This should fix CI.

Michael Bolin · 2026-01-21 00:35:42 +00:00

ac2090caf2

feat(tui2): add /experimental menu (#9562 )

Adds an /experimental slash command and bottom-pane view to toggle beta
features.

Persists feature-flag updates to config.toml, matching tui behavior.

Josh McKinney · 2026-01-21 00:20:57 +00:00

0a26675155

[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

queue only when task is working (#9558 )

Ahmed Ibrahim · 2026-01-20 15:24:45 -08:00

fbd8afad81

Enable remote models (#9554 )

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

de4980d2ac

Improve UI spacing for queued messages (#9162 )

Despite good spacing between queued messages and assistant message text:
<img width="462" height="322" alt="Screenshot 2026-01-12 at 4 54 50 PM"
src="https://github.com/user-attachments/assets/e8b46252-0b33-40d2-b431-cb73b9a3bd2e"
/>

Codex has confusing spacing between queued messages and shimmering
status text (making the queued message seem like a sub-item of the
shimmering status text)
<img width="615" height="217" alt="Screenshot 2026-01-12 at 4 54 18 PM"
src="https://github.com/user-attachments/assets/ee5e6095-8fe9-4863-88d2-10472cab8bd6"
/>

This PR changes the spacing between the queued message(s) and shimmering
status text to make it less confusing:
<img width="440" height="240" alt="Screenshot 2026-01-13 at 11 20 36 AM"
src="https://github.com/user-attachments/assets/02dcc690-cbe9-4943-87de-c7300ef51120"
/>

While working on the status/queued spacing change, we noticed two
paste‑burst tests were timing‑sensitive and could fail
on slower CI. We added a small test‑only helper to keep the paste‑burst
state active and refreshed during these tests. This
removes dependence on tight timing and makes the tests deterministic
without affecting runtime behavior.

charley-oai · 2026-01-20 14:54:49 -08:00

64678f895a

fix(cli): add execute permission to bin/codex.js (#9532 )

## Summary
Fixes #9520

The `bin/codex.js` file was missing execute permissions (`644` instead
of `755`), causing the `codex` command to fail after npm global
installation.

## Changes
- Added execute permission (`+x`) to `codex-cli/bin/codex.js`

## Verification
After this fix, npm tarballs will include the correct file permissions:
```bash
# Before: -rw-r--r-- (644)
# After:  -rwxr-xr-x (755)
```

---
🤖 Generated with Claude Code

Co-authored-by: Claude <noreply@anthropic.com>

zerone0x · 2026-01-20 14:53:14 -08:00

ca23b0da5b

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(windows-sandbox): parse PATH list entries for audit roots (#9319 )

## Summary
- Use `std::env::split_paths` to parse PATH entries in audit candidate
collection
- Add a unit test covering multiple PATH entries (including spaces)

## Testing
- `cargo test -p codex-windows-sandbox` (Windows)

Fixes #9317

Max Kong · 2026-01-20 14:00:27 -08:00

c73a11d55e

fix(windows-sandbox): deny .git file entries under writable roots (#9314 )

## Summary
- Deny `.git` entries under writable roots even when `.git` is a file
(worktrees/submodules)
- Add a unit test for `.git` file handling

## Testing
- `cargo test -p codex-windows-sandbox` (Windows)

Fixes #9313

Max Kong · 2026-01-20 13:59:59 -08:00

f2de920185

lookup system SIDs instead of hardcoding English strings. (#9552 )

The elevated setup does not work on non-English windows installs where
Users/Administrators/etc are in different languages. This PR uses the
well-known SIDs instead, which do not vary based on locale

iceweasel-oai · 2026-01-20 13:55:37 -08:00

9ea8e3115e

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

2989 Commits