codex

Removed the "remote_compaction" feature flag (#10840 )

This feature is always on now

Eric Traut · 2026-02-05 23:54:57 -08:00

dd80e332c4

Personality setting is no longer available in experimental menu (#10852 )

This PR removes the inaccurate "Disable in /experimental." statement now
that the "personality" feature flag is no longer experimental.

This addresses #10850

Eric Traut · 2026-02-05 22:19:09 -08:00

f61226d32a

Log an event (info only) when we receive a file watcher event (#10843 )

Eric Traut · 2026-02-05 20:24:16 -08:00

e5c1a2d6fb

Gate app tooltips to macOS (#10784 )

- Gate app promo tips to macOS and use non-app copy elsewhere.

Ahmed Ibrahim · 2026-02-05 19:18:08 -08:00

048e0f3888

feat: expose detailed metrics to runtime metrics (#10699 )

Anton Panasenko · 2026-02-05 18:22:30 -08:00

4ee039744e

Print warning when config does not meet requirements (#10792 )

<img width="1019" height="284" alt="Screenshot 2026-02-05 at 23 34 08"
src="https://github.com/user-attachments/assets/19ec3ce1-3c3b-40f5-b251-a31d964bf3bb"
/>

Currently, if a config value is set that fails the requirements, we exit
Codex.

Now, instead of this, we print a warning and default to a
requirements-permitting value.

gt-oai · 2026-02-06 01:12:44 +00:00

d74fa8edd1

feat(app-server): turn/steer API (#10821 )

This PR adds a dedicated `turn/steer` API for appending user input to an
in-flight turn.

## Motivation
Currently, steering in the app is implemented by just calling
`turn/start` while a turn is running. This has some really weird quirks:
- Client gets back a new `turn.id`, even though streamed
events/approvals remained tied to the original active turn ID.
- All the various turn-level override params on `turn/start` do not
apply to the "steer", and would only apply to the next real turn.
- There can also be a race condition where the client thinks the turn is
active but the server has already completed it, so there might be bugs
if the client has baked in some client-specific behavior thinking it's a
steer when in fact the server kicked off a new turn. This is
particularly possible when running a client against a remote app-server.

Having a dedicated `turn/steer` API eliminates all those quirks.

`turn/steer` behavior:
- Requires an active turn on threadId. Returns a JSON-RPC error if there
is no active turn.
- If expectedTurnId is provided, it must match the active turn (more
useful when connecting to a remote app-server).
- Does not emit `turn/started`.
- Does not accept turn overrides (`cwd`, `model`, `sandbox`, etc.) or
`outputSchema` to accurately reflect that these are not applied when
steering.

Owen Lin · 2026-02-06 00:35:04 +00:00

0d8b2b74c4

Add stage field for experimental flags. (#10793 )

- [x] Add stage field for experimental flags.

Matthew Zeng · 2026-02-05 23:31:04 +00:00

729b016515

updates: use brew api for version check (#10809 )

## Problem

`codex` currently prompts you to update via `brew upgrade --cask codex`
but the brew api does not return the new version

> <img width="1500" height="822" alt="Screenshot 2026-02-05 at 12 36
09 PM"
src="https://github.com/user-attachments/assets/9e12929d-95e8-43f4-8fba-ab93f5f76e73"
/>

## Solution

`codex-rs/tui/src/updates.rs` was using the [latest cask in
github](https://github.com/Homebrew/homebrew-cask/blob/HEAD/Casks/c/codex.rb)
but this does not agree with the brew api, which leads to the issue
above. Instead we use the [brew api json
endpoint](https://github.com/Homebrew/homebrew-cask/blob/HEAD/Casks/c/codex.rb)
to ensure our version check agrees with the upgrade command.

Noah Jorgensen · 2026-02-05 15:12:27 -08:00

dcea972db8

Send beta header with websocket connects (#10727 )

pakrym-oai · 2026-02-05 15:05:02 -08:00

dbe47ea01a

go back to auto-enabling web_search for azure (#10820 )

###### What
Remove special-casing that prevented auto-enabling `web_search` for
Azure model provider users. Addresses #10071, #10257.

###### Why
Azure fixed their responsesapi implementation; `web_search` is now
supported on models it wasn't before (like `gpt-5.1-codex-max`).

This request now works:
```
curl "$AZURE_API_ENDPOINT" -H "Content-Type: application/json" -H "Authorization: Bearer $AZURE_API_KEY" -d '{
  "model": "gpt-5.1-codex-max",
  "tools": [
    { "type": "web_search" }
  ],
  "tool_choice": "auto",
  "input": "Find the sunrise time in Paris today and cite the source."
}'
```

###### Tests
Tested with above curl, removed Azure-specific tests.

sayan-oai · 2026-02-05 14:57:07 -08:00

378f1cabe8

Sync app-server requirements API with refreshed cloud loader (#10815 )

configRequirements/read now returns updated cloud requirements after
login.

xl-openai · 2026-02-05 14:43:31 -08:00

43a7290f11

other announcement (#10818 )

jif-oai · 2026-02-05 22:21:02 +00:00

e65f76947f

Add app-server transport layer with websocket support (#10693 )

- Adds --listen <URL> to codex app-server with two listen modes:
      - stdio:// (default, existing behavior)
      - ws://IP:PORT (new websocket transport)
  - Refactors message routing to be connection-aware:
- Tracks per-connection session state (initialize/experimental
capability)
      - Routes responses/errors to the originating connection
- Broadcasts server notifications/requests to initialized connections
- Updates initialization semantics to be per connection (not
process-global), and updates app-server docs accordingly.
- Adds websocket accept/read/write handling (JSON-RPC per text frame,
ping/pong handling, connection lifecycle events).

Testing

- Unit tests for transport URL parsing and targeted response/error
routing.
  - New websocket integration test validating:
      - per-connection initialization requirements
      - no cross-connection response leakage
      - same request IDs on different connections route independently.

Max Johnson · 2026-02-05 20:56:34 +00:00

8473096efb

feat: wait for backfill to be ready (#10790 )

jif-oai · 2026-02-05 20:45:16 +00:00

428a9f6035

Add analytics for /rename and /fork (#10655 )

pap-openai · 2026-02-05 20:18:29 +00:00

529b539564

chore: limit update to 0.98.0 NUX to < 0.98.0 ver (#10787 )

seems like footgun if we forget to remove before releasing 0.99.0,
limited announcement to versions < 0.98.0

sayan-oai · 2026-02-05 12:11:32 -08:00

5602edc1d0

[app-server] Add a method to list experimental features. (#10721 )

- [x] Add a method to list experimental features.

Matthew Zeng · 2026-02-05 20:04:01 +00:00

7e81f63698

fix: announcement in prio (#10783 )

jif-oai · 2026-02-05 19:57:57 +00:00

ddd09a9368

chore: rm web-search-eligible header (#10660 )

default-enablement of web_search is now client-side, no need to send
eligibility headers to backend.

Tested locally, headers no longer sent.

will wait for corresponding backend change to deploy before merging

sayan-oai · 2026-02-05 11:48:34 -08:00

5fdf6f5efa

add sandbox policy and sandbox name to codex.tool.call metrics (#10711 )

This will give visibility into the comparative success rate of the
Windows sandbox implementations compared to other platforms.

iceweasel-oai · 2026-02-05 11:42:12 -08:00

901d5b8fd6

nit: gpt-5.3-codex announcement 2 (#10782 )

jif-oai · 2026-02-05 19:22:24 +00:00

4df9f2020b

nit: gpt-5.3-codex announcement (#10775 )

jif-oai · 2026-02-05 19:17:04 +00:00

ddfb8bfd77

fix(auth): isolate chatgptAuthTokens concept to auth manager and app-server (#10423 )

So that the rest of the codebase (like TUI) don't need to be concerned
whether ChatGPT auth was handled by Codex itself or passed in via
app-server's external auth mode.

Owen Lin · 2026-02-05 10:46:06 -08:00

3582b74d01

fix(tui): fix resume_picker_orders_by_updated_at test (#10769 )

I think this was due to https://github.com/openai/codex/issues/10752
landing and not rebased on top of
9ee746afd6

Owen Lin · 2026-02-05 18:03:10 +00:00

5c0fd62ff1

feat(tui): add sortable resume picker with created/updated timestamp toggle (#10752 )

## Summary

- Add sorting support to the resume session picker with Tab key toggle
- Sessions can now be sorted by either creation time or last updated
time
- Display the current sort mode in the picker header
- Default to sorting by creation time (most recent first)

## Changes

- Add `sort_key` field to `PickerState` to track current sort order
- Pass sort key to `RolloutRecorder::list_threads()` for proper backend
sorting
- Add Tab key handler to toggle between `CreatedAt` and `UpdatedAt`
sorting
- Show current sort mode ("Created at" / "Updated at") in header
- Add "Tab to toggle sort" keyboard hint
- Intelligently hide secondary date column when terminal is narrow
- Reload session list when sort order changes

## Test plan

- [x] Unit tests for sort key toggle functionality
- [x] Snapshot tests updated for new header format
- [x] Test that Tab key triggers reload with new sort key
- [x] Test column visibility adapts to narrow terminals

Felipe Coury · 2026-02-05 09:08:31 -08:00

22545bf206

feat(tui): add /statusline command for interactive status line configuration (#10546 )

## Summary
- Adds a new `/statusline` command to configure TUI footer status line
- Introduces reusable `MultiSelectPicker` component with keyboard
navigation, optional ordering and toggle support
- Implement status line setup modal that persist configuration to
config.toml

  ## Status Line Items
  The following items can be displayed in the status line:
  - **Model**: Current model name (with optional reasoning level)
  - **Context**: Remaining/used context window percentage
  - **Rate Limits**: 5-day and weekly usage limits
  - **Git**: Current branch (with optimized lookups)
  - **Tokens**: Used tokens, input/output token counts
  - **Session**: Session ID (full or shortened prefix)
  - **Paths**: Current directory, project root
  - **Version**: Codex version

  ## Features
  - Live preview while configuring status line items
  - Fuzzy search filtering in the picker
  - Intelligent truncation when items don't fit
  - Items gracefully omit when data is unavailable
  - Configuration persists to `config.toml`
  - Validates and warns about invalid status line items

  ## Test plan
  - [x] Run `/statusline` and verify picker UI appears
  - [x] Toggle items on/off and verify live preview updates
  - [x] Confirm selection persists after restart
  - [x] Verify truncation behavior with many items selected
  - [x] Test git branch detection in and out of git repos

---------

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

Felipe Coury · 2026-02-05 08:50:21 -08:00

b0e5a6305b

Add hooks implementation and wire up to notify (#9691 )

This introduces a `Hooks` service. It registers hooks from config and
dispatches hook events at runtime.

N.B. The hook config is not wired up to this yet. But for legacy
reasons, we wire up `notify` from config and power it using hooks now.
Nothing about the `notify` interface has changed.

I'd start by reviewing `hooks/types.rs`

Some things to note:
  - hook names subject to change
  - no hook result yet
  - stopping semantics yet to be introduced
  - additional hooks yet to be introduced

gt-oai · 2026-02-05 16:49:35 +00:00

3b54fd7336

Leverage state DB metadata for thread summaries (#10621 )

Summary:
- read conversation summaries and cwd info from the state DB when
possible so we no longer rely on rollout files for metadata and avoid
extra I/O
- persist CLI version in thread metadata, surface it through summary
builders, and add the necessary DB migration hooks
- simplify thread listing by using enriched state DB data directly
rather than reading rollout heads

Testing:
- Not run (not requested)

jif-oai · 2026-02-05 16:39:11 +00:00

9ee746afd6

nit: add DB version is discrepancy recording (#10762 )

jif-oai · 2026-02-05 16:24:18 +00:00

68e82e5dc9

feat: repair DB in case of missing lines (#10751 )

jif-oai · 2026-02-05 16:21:49 +00:00

901215e310

feat: add memory tool (#10637 )

Add a tool for memory to retrieve a full memory based on the memory ID

jif-oai · 2026-02-05 16:16:31 +00:00

41f3b1ba0b

chore: handle shutdown correctly in tui (#10756 )

jif-oai · 2026-02-05 16:07:50 +00:00

fe1cbd0f38

feat: wire ephemeral in codex exec (#10758 )

jif-oai · 2026-02-05 15:49:57 +00:00

d337b51741

feat: resumable backfill (#10745 )

## Summary

This PR makes SQLite rollout backfill resumable and repeatable instead
of one-shot-on-db-create.

## What changed

- Added a persisted backfill state table:
  - state/migrations/0008_backfill_state.sql
- Tracks status (pending|running|complete), last_watermark, and
last_success_at.
- Added backfill state model/types in codex-state:
  - BackfillState, BackfillStatus (state/src/model/backfill_state.rs)
- Added runtime APIs to manage backfill lifecycle/progress:
  - get_backfill_state
  - mark_backfill_running
  - checkpoint_backfill
  - mark_backfill_complete
- Updated core startup behavior:
- Backfill now runs whenever state is not Complete (not only when DB
file is newly created).
- Reworked backfill execution:
- Collect rollout files, derive deterministic watermark per path, sort,
resume from last_watermark.
- Process in batches (BACKFILL_BATCH_SIZE = 200), checkpoint after each
batch.
  - Mark complete with last_success_at at the end.

## Why

Previous behavior could leave users permanently partially backfilled if
the process exited during initial async backfill. This change allows
safe continuation across restarts and avoids restarting from scratch.

jif-oai · 2026-02-05 14:34:34 +00:00

4033f905c6

Include real OS info in metrics. (#10425 )

calculated a hashed user ID from either auth user id or API key
Also correctly populates OS.

These will make our metrics more useful and powerful for analysis.

iceweasel-oai · 2026-02-05 06:30:31 -08:00

f2ffc4e5d0

Update explorer role default model (#10748 )

Summary
- switch the explorer role in core agent configuration to use
`gpt-5.1-codex-mini` as the default model override
- leave other role defaults untouched

Testing
- Not run (not requested)

jif-oai · 2026-02-05 13:51:53 +00:00

040ecee715

adding fork information (UI) when forking (#10246 )

- shows `/fork` command that ran in prev session
- shows `session forked from name (uuid) || uuid (if name is not set)` as an event in new session

pap-openai · 2026-02-05 13:24:55 +00:00

b2424cb635

nit: backfill stronger (#10738 )

jif-oai · 2026-02-05 12:30:16 +00:00

aa46b5cf99

Allow user shell commands to run alongside active turns (#10513 )

Summary
- refactor user shell command execution into a shared helper and add
modes for standalone vs active-turn execution
- run user shell commands asynchronously when a turn is already active
so they don’t replace or abort the current turn
- extend the tests to cover the new behavior and add the generated Codex
environment manifest

Testing
- Not run (not requested)

jif-oai · 2026-02-05 11:11:00 +00:00

97582ac52d

fix: flaky landlock (#10689 )

https://openai.slack.com/archives/C095U48JNL9/p1770243347893959

jif-oai · 2026-02-05 10:30:18 +00:00

c67120f4a0

fix(tui): flush input buffer on init to prevent early exit on Windows (#10729 )

Fixes #10661.

### Problem
On Windows, the sign-in menu can exit immediately if the OS-level input
buffer contains trailing characters (like the Enter key from running the
command).

### Solution
**Flush Input Buffer on Init**: Use FlushConsoleInputBuffer on Windows
(and cflush on Unix) in ui::init() to discard any input captured before
the TUI was ready.

Verified by @CodebyAmbrose in #10661.

Ashutosh Kumar Singh · 2026-02-05 00:59:32 -08:00

7b28b350e1

fix(core,app-server) resume with different model (#10719 )

## Summary
When resuming with a different model, we should also append a developer
message with the model instructions

## Testing
- [x] Added unit tests

Dylan Hurd · 2026-02-05 00:40:05 -08:00

fe8b474acd

Reload cloud requirements after user login (#10725 )

Reload cloud requirements after user login so it could take effect
immediately.

xl-openai · 2026-02-05 00:27:16 -08:00

1e1146cd29

Fix remote compaction estimator/payload instruction small mismatch (#10692 )

## Summary
This PR fixes a deterministic mismatch in remote compaction where
pre-trim estimation and the `/v1/responses/compact` payload could use
different base instructions.

Before this change:
- pre-trim estimation used model-derived instructions
(`model_info.get_model_instructions(...)`)
- compact payload used session base instructions
(`sess.get_base_instructions()`)

After this change:
- remote pre-trim estimation and compact payload both use the same
`BaseInstructions` instance from session state.

## Changes
- Added a shared estimator entry point in `ContextManager`:
- `estimate_token_count_with_base_instructions(&self, base_instructions:
&BaseInstructions) -> Option<i64>`
- Kept `estimate_token_count(&TurnContext)` as a thin wrapper that
resolves model/personality instructions and delegates to the new helper.
- Updated remote compaction flow to fetch base instructions once and
reuse it for both:
  - trim preflight estimation
  - compact request payload construction
- Added regression coverage for parity and behavior:
  - unit test verifying explicit-base estimator behavior
- integration test proving remote compaction uses session override
instructions and trims accordingly

## Why this matters
This removes a deterministic divergence source where pre-trim could
think the request fits while the actual compact request exceeded context
because its instructions were longer/different.

## Scope
In scope:
- estimator/payload base-instructions parity in remote compaction

Out of scope:
- retry-on-`context_length_exceeded`
- compaction threshold/headroom policy changes
- broader trimming policy changes

## Codex author:
`codex fork 019c2b24-c2df-7b31-a482-fb8cf7a28559`

Charley Cunningham · 2026-02-04 23:24:06 -08:00

dc7007beaa

Make steer stable by default (#10690 )

Promotes the Steer feature from Experimental to Stable and enables it by
default.

## What is Steer mode?

Steer mode changes how message submission works in the TUI:

- **With Steer enabled (new default)**: 
  - `Enter` submits messages immediately, even when a task is running
- `Tab` queues messages when a task is running (allows building up a
queue)
  
- **With Steer disabled (old behavior)**:
  - `Enter` queues messages when a task is running
  - This preserves the previous "queue while a task is running" behavior

## How Steer vs Queue work

The key difference is in the submission behavior:

1. **Steer mode** (`steer_enabled = true`):
- Enter → `InputResult::Submitted` → sends immediately via
`submit_user_message()`
- Tab → `InputResult::Queued` → queues via `queue_user_message()` if a
task is running
- This gives users direct control: Enter for immediate submission, Tab
for queuing

2. **Queue mode** (`steer_enabled = false`, previous default):
- Enter → `InputResult::Queued` → always queues when a task is running
   - Tab → `InputResult::Queued` → queues when a task is running
- This preserves the original behavior where Enter respects the running
task queue

## Implementation details

The behavior is controlled in
`ChatComposer::handle_key_event_without_popup()`:
- When `steer_enabled` is true, Enter calls `handle_submission(false)`
(submit immediately)
- When `steer_enabled` is false, Enter calls `handle_submission(true)`
(queue)

See `codex-rs/tui/src/bottom_pane/chat_composer.rs` for the
implementation.

## Documentation

For more details on the chat composer behavior, see:
- [TUI Chat Composer documentation](docs/tui-chat-composer.md)
- Feature flag definition: `codex-rs/core/src/features.rs`

Ahmed Ibrahim · 2026-02-04 23:12:59 -08:00

cd5f49a619

Sync collaboration mode naming across Default prompt, tools, and TUI (#10666 )

## Summary
- add shared `ModeKind` helpers for display names, TUI visibility, and
`request_user_input` availability
- derive TUI mode filtering/labels from shared `ModeKind` metadata
instead of local hardcoded matches
- derive `request_user_input` availability text and unavailable error
mode names from shared mode metadata
- replace hardcoded known mode names in the Default collaboration-mode
template with `{{KNOWN_MODE_NAMES}}` and fill it from
`TUI_VISIBLE_COLLABORATION_MODES`
- add regression tests for mode metadata sync and placeholder
replacement

## Notes
- `cargo test -p codex-core` integration target (`tests/all`) still
shows pre-existing env-specific failures in this environment due missing
`test_stdio_server` binary resolution; core unit tests are green.

## Codex author
`codex resume 019c26ff-dfe7-7173-bc04-c9e1fff1e447`

Charley Cunningham · 2026-02-04 23:03:28 -08:00

41b4962b0a

fix(core) switching model appends model instructions (#10651 )

## Summary
When switching models, we should append the instructions of the new
model to the conversation as a developer message.

## Test
- [x] Adds a unit test

Dylan Hurd · 2026-02-05 05:50:38 +00:00

e482978261

chore(config) Default Personality Pragmatic (#10705 )

## Summary
Switch back to Pragmatic personality

## Testing
- [x] Updated unit tests

Dylan Hurd · 2026-02-04 21:22:47 -08:00

a05aadfa1b

fix: ensure resume args precede image args (#10709 )

## Summary
Fixes argument ordering when `resumeThread()` is used with
`local_image`. The SDK previously emitted CLI args with `--image` before
`resume <threadId>`, which caused the Codex CLI to treat `resume`/UUID
as image paths and start a new session. This PR moves `resume
<threadId>` before any `--image` flags and adds a regression test.

## Bug Report / Links
- OpenAI issue: https://github.com/openai/codex/issues/10708
- Repro repo:
https://github.com/cryptonerdcn/codex-resume-local-image-repro
- Repro issue (repo):
https://github.com/cryptonerdcn/codex-resume-local-image-repro/issues/1

## Repro (pre-fix)
1. Build SDK from source
2. Run resume + local_image
3. Args order: `--image <path> resume <id>`
4. Result: new session created (thread id changes)

## Fix
Move `resume <threadId>` before `--image` in `CodexExec.run` and add a
regression test to assert ordering.

## Tests
- `cd sdk/typescript && npm test`
  - **Failed**: `codex-rs/target/debug/codex` missing (ENOENT)

## Notes
- I can rerun tests in an environment with `codex-rs` built and report
results.

cryptonerdcn · 2026-02-04 21:19:56 -08:00

1dc06b6ffc

3718 Commits