codex

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

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

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

jif-oai · 2026-02-05 20:45:16 +00:00

428a9f6035

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

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

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

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

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(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

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

chore(core) personality migration tests (#10650 )

## Summary
Adds additional tests for personality edge cases

## Testing
- [x] These are tests

Dylan Hurd · 2026-02-04 19:03:14 -08:00

73f32840c6

Cloud Requirements: increase timeout and retries (#10631 )

Add retries and an increased-length timeout for loading Cloud
Requirements.

Co-authored-by: alexsong-oai <alexsong@openai.com>

gt-oai · 2026-02-05 01:52:12 +00:00

1f47e08d66

feat(core): add configurable log_dir (#10678 )

Adds a top-level `log_dir` config key (defaults to `$CODEX_HOME/log`) so
one-off runs can redirect `codex-tui.log` via `-c`, e.g.:

  codex -c log_dir=./.codex-log

Also resolves relative paths in CLI `-c/--config` overrides for
`AbsolutePathBuf` values against the effective cwd (when available).

Tests:
- cargo test -p codex-core

Josh McKinney · 2026-02-05 01:23:30 +00:00

cddfd1e675

Session-level model client (#10664 )

Make ModelClient a session-scoped object.
Move state that is session level onto the client, and make state that is
per-turn explicit on corresponding methods.
Stop taking a huge Config object, instead only pass in values that are
actually needed.

---------

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

pakrym-oai · 2026-02-04 16:58:48 -08:00

0e8d359da9

feat(app-server, core): allow text + image content items for dynamic tool outputs (#10567 )

Took over the work that @aaronl-openai started here:
https://github.com/openai/codex/pull/10397

Now that app-server clients are able to set up custom tools (called
`dynamic_tools` in app-server), we should expose a way for clients to
pass in not just text, but also image outputs. This is something the
Responses API already supports for function call outputs, where you can
pass in either a string or an array of content outputs (text, image,
file):
https://platform.openai.com/docs/api-reference/responses/create#responses_create-input-input_item_list-item-function_tool_call_output-output-array-input_image

So let's just plumb it through in Codex (with the caveat that we only
support text and image for now). This is implemented end-to-end across
app-server v2 protocol types and core tool handling.

## Breaking API change
NOTE: This introduces a breaking change with dynamic tools, but I think
it's ok since this concept was only recently introduced
(https://github.com/openai/codex/pull/9539) and it's better to get the
API contract correct. I don't think there are any real consumers of this
yet (not even the Codex App).

Old shape:
`{ "output": "dynamic-ok", "success": true }`

New shape:
```
{
    "contentItems": [
      { "type": "inputText", "text": "dynamic-ok" },
      { "type": "inputImage", "imageUrl": "data:image/png;base64,AAA" }
    ]
  "success": true
}
```

Owen Lin · 2026-02-04 16:12:47 -08:00

5ea107a088

add none personality option (#10688 )

- add none personality enum value and empty placeholder behavior\n- add
docs/schema updates and e2e coverage

Ahmed Ibrahim · 2026-02-04 15:40:33 -08:00

f9c38f531c

Added support for live updates to skills (#10478 )

Add a centralized FileWatcher in codex-core (using notify) that watches
skill roots from the config layer stack (recursive)

Send `SkillsChanged` events when relevant file system changes are
detected

On `SkillsChanged`:
* Invalidate the skills cache immediately in ThreadManager
* Emit EventMsg::SkillsUpdateAvailable to active sessions
~~* Broadcast a new app-server notification:
SkillsListUpdatedNotification~~

This change does not inject new items into the event stream. That means
the agent will not know about new skills, so it won't be able to
implicitly invoke new skills. It also won't know about changes to
existing skills, so if it has already read the contents of a modified
skill, it will not honor the new behavior.

This change also does not detect modifications to AGENTS.md.

I plan to address these limitations in a follow-on PR modeled after
#9985. Injection of new skills and AGENTS was deemed to risky, hence the
need to split the feature into two stages. The changes in this PR were
designed to easily accommodate the second stage once we have some other
foundational changes in place.

Testing: In addition to automated tests, I did manual testing to confirm
that newly-created skills, deleted skills, and renamed skills are
reflected in the TUI skill picker menu. Also confirmed that
modifications to behaviors for explicitly-invoked skills are honored.

---------

Co-authored-by: Xin Lin <xl@openai.com>

Eric Traut · 2026-02-04 15:25:03 -08:00

7bcc552325

Add /debug-config slash command (#10642 )

<img width="409" height="175" alt="image"
src="https://github.com/user-attachments/assets/76efe9c5-8375-4af3-b6af-bd9e162c1bc3"
/>

gt-oai · 2026-02-04 22:26:17 +00:00

d452bb3ae5

[apps] Cache MCP actions from apps. (#10662 )

MCP actions take a long time to load for users with lots of apps
installed. Adding a cache for these actions with 1hr expiration, given
that they are almost always aren't going to change unless people install
another app, which means they also need to restart codex to pick it up.

Matthew Zeng · 2026-02-04 13:51:57 -08:00

acdbd8edc5

feat: add phase 1 mem db (#10634 )

- Schema: thread_id (PK, FK to threads.id with cascade delete),
trace_summary, memory_summary, updated_at.
- Migration: creates the table and an index on (updated_at DESC,
thread_id DESC) for efficient recent-first reads.
  - Runtime API (DB-only):
      - `get_thread_memory(thread_id)`: fetch one memory row.
- `upsert_thread_memory(thread_id, trace_summary, memory_summary)`:
insert/update by thread id and always advance updated_at.
- `get_last_n_thread_memories_for_cwd(cwd, n)`: join thread_memory with
threads and return newest n rows for an exact cwd match.
- Model layer: introduced ThreadMemory and row conversion types to keep
query decoding typed and consistent with existing state models.

jif-oai · 2026-02-04 21:38:39 +00:00

4922b3e571

Persist pending input user events (#10656 )

- Persist user-message events for mid-turn injected input by emitting
user message turn items when pending input is recorded.

Ahmed Ibrahim · 2026-02-04 11:47:10 -08:00

7a253076fe

feat(linux-sandbox): add bwrap support (#9938 )

## Summary
This PR introduces a gated Bubblewrap (bwrap) Linux sandbox path. The
curent Linux sandbox path relies on in-process restrictions (including
Landlock). Bubblewrap gives us a more uniform filesystem isolation
model, especially explicit writable roots with the option to make some
directories read-only and granular network controls.

This is behind a feature flag so we can validate behavior safely before
making it the default.

- Added temporary rollout flag:
  - `features.use_linux_sandbox_bwrap`
- Preserved existing default path when the flag is off.
- In Bubblewrap mode:
- Added internal retry without /proc when /proc mount is not permitted
by the host/container.

viyatb-oai · 2026-02-04 11:13:17 -08:00

ae4de43ccc

Cloud Requirements: take precedence over MDM (#10633 )

Cloud Requirements should be applied before MDM requirements.

gt-oai · 2026-02-04 18:40:56 +00:00

1b153a3d4a

feat: add phase 1 mem client (#10629 )

Adding a client on top of https://github.com/openai/openai/pull/672176

jif-oai · 2026-02-04 17:59:36 +00:00

e9335374b9

fix: flaky test (#10644 )

jif-oai · 2026-02-04 17:59:22 +00:00

71e63f8d10

Add option to approve and remember MCP/Apps tool usage (#10584 )

This PR adds a new approval option for app/MCP tool calls: “Allow and
remember” (session-scoped).
When selected, Codex stores a temporary approval and auto-approves
matching future calls for the rest of the session.

Added a session-scoped approval key (`server`, `connector_id`,
`tool_name`) and persisted it in `tool_approvals` as
`ApprovedForSession`.
On subsequent matching calls, approval is skipped and treated as
accepted.
- Updated the approval question options to conditionally include:
- Accept
- Allow and remember (conditional)
- Decline
- Cancel

The new “Allow and remember” option is only shown when all of these are
true:

1. The call is routed through the Codex Apps MCP server (codex_apps).
2. The tool requires approval based on annotations:
- read_only_hint == false, and
- destructive_hint == true or open_world_hint == true.
3. The tool includes a connector_id in metadata (used to build the
remembered approval key).

If no `connector_id` is present, the prompt still appears (when approval
is required), but only with the existing choices (Accept / Decline /
Cancel). Approval prompting in this path has an explicit early return
unless server == `codex_apps`.

canvrno-oai · 2026-02-04 09:38:41 -08:00

282f42c0ce

Stop client from being state carrier (#10595 )

I'd like to make client session wide. This requires shedding all random
state it has to carry.

pakrym-oai · 2026-02-04 09:05:37 -08:00

7f20357611

feat: land unified_exec (#10641 )

Land `unified_exec` for all non-windows OS

jif-oai · 2026-02-04 16:39:41 +00:00

49dd67a260

Update tests to stop using sse_completed fixture (#10638 )

Summary:
- replace the `sse_completed` fixture and related JSON template with
direct `responses::ev_completed` payload builders
- cascade the new SSE helpers through all affected core tests for
consistency and clarity
- remove legacy fixtures that were no longer needed once the helpers are
in place

Testing:
- Not run (not requested)

pakrym-oai · 2026-02-04 08:38:06 -08:00

0efd33f7f4

Migrate state DB path helpers to versioned filename (#10623 )

Summary
- add versioned state sqlite filename helpers and re-export them from
the state crate
- remove legacy state files when initializing the runtime and update
consumers/tests to use the new helpers
- tweak logs client description and database resolution to match the new
path

jif-oai · 2026-02-04 14:31:12 +00:00

583e5d4f41

Add a codex.rate_limits event for websockets (#10324 )

When communicating over websockets, we can't rely on headers to deliver
rate limit information. This PR adds a `codex.rate_limits` event that
the server can pass to the client to inform them about rate limit usage.
The client parses this data the same way we parse rate limit headers in
HTTP mode.

This PR also wires up the etag and reasoning headers for websockets

Rasmus Rygaard · 2026-02-04 06:01:47 -08:00

df000da917

fix: make sure file exist in find_thread_path_by_id_str_in_subdir (#10618 )

jif-oai · 2026-02-04 13:01:17 +00:00

61aecdde66

chore: simplify user message detection (#10611 )

We don't check anymore the response item with `user` role as they may be
instructions etc

jif-oai · 2026-02-04 11:14:53 +00:00

38f6c6b114

Requirements: add source to constrained requirement values (#10568 )

If we want to build `/debug-config`, we'll need to know the requirements
sources that supplied the values.

This PR adds those sources such that we can render them in the UI.

gt-oai · 2026-02-04 11:09:48 +00:00

1eb21e279e

Prefer state DB thread listings before filesystem (#10544 )

Summary
- add Cursor/ThreadsPage conversions so state DB listings can be mapped
back into the rollout list model
- make recorder list helpers query the state DB first (archived flag
included) and only fall back to file traversal if needed, along with
populating head bytes lazily
- add extensive tests to ensure the DB path is honored for active and
archived threads and that the fallback works

Testing
- Not run (not requested)

<img width="1196" height="693" alt="Screenshot 2026-02-03 at 20 42 33"
src="https://github.com/user-attachments/assets/826b3c7a-ef11-4b27-802a-3c343695794a"
/>

jif-oai · 2026-02-04 09:27:24 +00:00

100eb6e6f0

Move metadata calculation out of client (#10589 )

Model client shouldn't be responsible for this.

pakrym-oai · 2026-02-03 21:59:13 -08:00

56ebfff1a8

1727 Commits