codex

nit: wording multi-agent (#11986 )

jif-oai · 2026-02-17 11:45:59 +00:00

56cd85cd4b

fix: race in js repl (#11922 )

js_repl_reset previously raced with in-flight/new js_repl executions
because reset() could clear exec_tool_calls without synchronizing with
execute(). In that window, a running exec could lose its per-exec
tool-call context, and subsequent kernel RunTool messages would fail
with js_repl exec context not found. The fix serializes reset and
execute on the same exec_lock, so reset cannot run concurrently with
exec setup/teardown. We also keep the timeout path safe by performing
reset steps inline while execute() already holds the lock, avoiding
re-entrant lock acquisition. A regression test now verifies that reset
waits for the exec lock and does not clear tool-call state early.

jif-oai · 2026-02-17 11:06:14 +00:00

77f74a5c17

fix: js_repl reset hang by clearing exec tool calls without waiting (#11932 )

Remove the waiting loop in `reset` so it no longer blocks on potentially
hanging exec tool calls + add `clear_all_exec_tool_calls_map` to drain
the map and notify waiters so `reset` completes immediately

jif-oai · 2026-02-17 08:40:54 +00:00

846464e869

fix(core) exec_policy parsing fixes (#11951 )

## Summary
Fixes a few things in our exec_policy handling of prefix_rules:
1. Correctly match redirects specifically for exec_policy parsing. i.e.
if you have `prefix_rule(["echo"], decision="allow")` then `echo hello >
output.txt` should match - this should fix #10321
2. If there already exists any rule that would match our prefix rule
(not just a prompt), then drop it, since it won't do anything.


## Testing
- [x] Updated unit tests, added approvals ScenarioSpecs

Dylan Hurd · 2026-02-16 23:11:59 -08:00

0fbe10a807

add(core): safety check downgrade warning (#11964 )

Add per-turn notice when a request is downgraded to a fallback model due
to cyber safety checks.

**Changes**

- codex-api: Emit a ServerModel event based on the openai-model response
header and/or response payload (SSE + WebSocket), including when the
model changes mid-stream.
- core: When the server-reported model differs from the requested model,
emit a single per-turn warning explaining the reroute to gpt-5.2 and
directing users to Trusted
    Access verification and the cyber safety explainer.
- app-server (v2): Surface these cyber model-routing warnings as
synthetic userMessage items with text prefixed by Warning: (and document
this behavior).

Fouad Matin · 2026-02-16 22:13:36 -08:00

02e9006547

chore(core) rm Feature::RequestRule (#11866 )

## Summary
This feature is now reasonably stable, let's remove it so we can
simplify our upcoming iterations here.

## Testing 
- [x] Existing tests pass

Dylan Hurd · 2026-02-16 22:30:23 +00:00

19afbc35c1

[apps] Fix app mention syntax. (#11894 )

- [x] Fix app mention syntax.

Matthew Zeng · 2026-02-16 22:01:49 +00:00

5b421bba34

Rename collab modules to multi agents (#11939 )

Summary
- rename the `collab` handlers and UI files to `multi_agents` to match
the new naming
- update module references and specs so the handlers and TUI widgets
consistently use the renamed files
- keep the existing functionality while aligning file and module names
with the multi-agent terminology

jif-oai · 2026-02-16 19:05:13 +00:00

beb5cb4f48

feat: drop MCP managing tools if no MCP servers (#11900 )

Drop MCP tools if no MCP servers to save context

For this https://github.com/openai/codex/issues/11049

jif-oai · 2026-02-16 18:40:45 +00:00

af434b4f71

feat: add customizable roles for multi-agents (#11917 )

The idea is to have 2 family of agents.

1. Built-in that we packaged directly with Codex
2. User defined that are defined using the `agents_config.toml` file. It
can reference config files that will override the agent config. This
looks like this:
```
version = 1

[agents.explorer]
description = """Use `explorer` for all codebase questions.
Explorers are fast and authoritative.
Always prefer them over manual search or file reading.
Rules:
- Ask explorers first and precisely.
- Do not re-read or re-search code they cover.
- Trust explorer results without verification.
- Run explorers in parallel when useful.
- Reuse existing explorers for related questions."""
config_file = "explorer.toml"
```

jif-oai · 2026-02-16 16:29:32 +00:00

e47045c806

nit: memory storage (#11924 )

jif-oai · 2026-02-16 16:18:53 +00:00

50aea4b0dc

chore: rename collab feature flag key to multi_agent (#11918 )

Summary
- rename the collab feature key to multi_agent while keeping the Feature
enum unchanged
- add legacy alias support so both "multi_agent" and "collab" map to the
same feature
- cover the alias behavior with a new unit test

jif-oai · 2026-02-16 15:28:31 +00:00

e41536944e

Allow hooks to error (#11615 )

Allow hooks to return errors. 

We should do this before introducing more hook types, or we'll have to
migrate them all.

gt-oai · 2026-02-16 14:11:05 +00:00

b3095679ed

feat: use shell policy in shell snapshot (#11759 )

Honor `shell_environment_policy.set` even after a shell snapshot

jif-oai · 2026-02-16 09:11:00 +00:00

825a4af42f

bazel: fix snapshot parity for tests/*.rs rust_test targets (#11893 )

## Summary
- make `rust_test` targets generated from `tests/*.rs` use Cargo-style
crate names (file stem) so snapshot names match Cargo (`all__...`
instead of Bazel-derived names)
- split lib vs `tests/*.rs` test env wiring in `codex_rust_crate` to
keep existing lib snapshot behavior while applying Bazel
runfiles-compatible workspace root for `tests/*.rs`
- compute the `tests/*.rs` snapshot workspace root from package depth so
`insta` resolves committed snapshots under Bazel `--noenable_runfiles`

## Validation
- `bazelisk test //codex-rs/core:core-all-test
--test_arg=suite::compact:: --cache_test_results=no`
- `bazelisk test //codex-rs/core:core-all-test
--test_arg=suite::compact_remote:: --cache_test_results=no`

Anton Panasenko · 2026-02-16 07:11:59 +00:00

1d95656149

fix: only emit unknown model warning on user turns (#11884 )

###### Context
unknown model warning added in #11690 has
[issues](https://github.com/openai/codex/actions/runs/22047424710/job/63700733887)
on ubuntu runners because we potentially emit it on all new turns,
including ones with intentionally fake models (i.e., `mock-model` in a
test).

###### Fix
change the warning to only emit on user turns/review turns.

###### Tests
CI now passes on ubuntu, still passes locally

sayan-oai · 2026-02-15 21:18:35 -08:00

bdea9974d9

feat: persist and restore codex app's tools after search (#11780 )

### What changed
1. Removed per-turn MCP selection reset in `core/src/tasks/mod.rs`.
2. Added `SessionState::set_mcp_tool_selection(Vec<String>)` in
`core/src/state/session.rs` for authoritative restore behavior (deduped,
order-preserving, empty clears).
3. Added rollout parsing in `core/src/codex.rs` to recover
`active_selected_tools` from prior `search_tool_bm25` outputs:
   - tracks matching `call_id`s
   - parses function output text JSON
   - extracts `active_selected_tools`
   - latest valid payload wins
   - malformed/non-matching payloads are ignored
4. Applied restore logic to resumed and forked startup paths in
`core/src/codex.rs`.
5. Updated instruction text to session/thread scope in
`core/templates/search_tool/tool_description.md`.
6. Expanded tests in `core/tests/suite/search_tool.rs`, plus unit
coverage in:
   - `core/src/codex.rs`
   - `core/src/state/session.rs`

### Behavior after change
1. Search activates matched tools.
2. Additional searches union into active selection.
3. Selection survives new turns in the same thread.
4. Resume/fork restores selection from rollout history.
5. Separate threads do not inherit selection unless forked.

Anton Panasenko · 2026-02-15 19:18:41 -08:00

02abd9a8ea

fix: show user warning when using default fallback metadata (#11690 )

### What
It's currently unclear when the harness falls back to the default,
generic `ModelInfo`. This happens when the `remote_models` feature is
disabled or the model is truly unknown, and can lead to bad performance
and issues in the harness.

Add a user-facing warning when this happens so they are aware when their
setup is broken.

### Tests
Added tests, tested locally.

sayan-oai · 2026-02-15 18:46:05 -08:00

060a320e7d

core: snapshot tests for compaction requests, post-compaction layout, some additional compaction tests (#11487 )

This PR keeps compaction context-layout test coverage separate from
runtime compaction behavior changes, so runtime logic review can stay
focused.

## Included
- Adds reusable context snapshot helpers in
`core/tests/common/context_snapshot.rs` for rendering model-visible
request/history shapes.
- Standardizes helper naming for readability:
  - `format_request_input_snapshot`
  - `format_response_items_snapshot`
  - `format_labeled_requests_snapshot`
  - `format_labeled_items_snapshot`
- Expands snapshot coverage for both local and remote compaction flows:
  - pre-turn auto-compaction
  - pre-turn failure/context-window-exceeded paths
  - mid-turn continuation compaction
  - manual `/compact` with and without prior user turns
- Captures both sides where relevant:
  - compaction request shape
  - post-compaction history layout shape
- Adds/uses shared request-inspection helpers so assertions target
structured request content instead of ad-hoc JSON string parsing.
- Aligns snapshots/assertions to current behavior and leaves explicit
`TODO(ccunningham)` notes where behavior is known and intentionally
deferred.

## Not Included
- No runtime compaction logic changes.
- No model-visible context/state behavior changes.

Charley Cunningham · 2026-02-14 19:57:10 -08:00

85034b189e

fix(core): add linux bubblewrap sandbox tag (#11767 )

## Summary
- add a distinct `linux_bubblewrap` sandbox tag when the Linux
bubblewrap pipeline feature is enabled
- thread the bubblewrap feature flag into sandbox tag generation for:
  - turn metadata header emission
  - tool telemetry metric tags and after-tool-use hooks
- add focused unit tests for `sandbox_tag` precedence and Linux
bubblewrap behavior

## Validation
- `just fmt`
- `cargo clippy -p codex-core --all-targets`
- `cargo test -p codex-core sandbox_tags::tests`
- started `cargo test -p codex-core` and stopped it per request

Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>

viyatb-oai · 2026-02-14 19:00:01 +00:00

db6aa80195

feat(core): add structured network approval plumbing and policy decision model (#11672 )

### Description
#### Summary
Introduces the core plumbing required for structured network approvals

#### What changed
- Added structured network policy decision modeling in core.
- Added approval payload/context types needed for network approval
semantics.
- Wired shell/unified-exec runtime plumbing to consume structured
decisions.
- Updated related core error/event surfaces for structured handling.
- Updated protocol plumbing used by core approval flow.
- Included small CLI debug sandbox compatibility updates needed by this
layer.

#### Why
establishes the minimal backend foundation for network approvals without
yet changing high-level orchestration or TUI behavior.

#### Notes
- Behavior remains constrained by existing requirements/config gating.
- Follow-up PRs in the stack handle orchestration, UX, and app-server
integration.

---------

Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>

viyatb-oai · 2026-02-14 04:18:12 +00:00

b527ee2890

Handle model-switch base instructions after compaction (#11659 )

Strip trailing <model_switch> during model-switch compaction request,
and append <model_switch> after model switch compaction

Charley Cunningham · 2026-02-13 19:02:53 -08:00

67e577da53

add perf metrics for connectors load (#11803 )

alexsong-oai · 2026-02-13 18:15:07 -08:00

8156c57234

feat(skills): add permission profiles from openai.yaml metadata (#11658 )

## Summary

This PR adds support for skill-level permissions in .codex/openai.yaml
and wires that through the skill loading pipeline.

  ## What’s included

1. Added a new permissions section for skills (network, filesystem, and
macOS-related access).
2. Implemented permission parsing/normalization and translation into
runtime permission profiles.
3. Threaded the new permission profile through SkillMetadata and loader
flow.

  ## Follow-up

A follow-up PR will connect these permission profiles to actual sandbox
enforcement and add user approval prompts for executing binaries/scripts
from skill directories.


 ## Example 
`openai.yaml` snippet:
```
  permissions:
    network: true
    fs_read:
      - "./data"
      - "./data"
    fs_write:
      - "./output"
    macos_preferences: "readwrite"
    macos_automation:
      - "com.apple.Notes"
    macos_accessibility: true
    macos_calendar: true
```

compiled skill permission profile metadata (macOS): 
```
SkillPermissionProfile {
      sandbox_policy: SandboxPolicy::WorkspaceWrite {
          writable_roots: vec![
              AbsolutePathBuf::try_from("/ABS/PATH/TO/SKILL/output").unwrap(),
          ],
          read_only_access: ReadOnlyAccess::Restricted {
              include_platform_defaults: true,
              readable_roots: vec![
                  AbsolutePathBuf::try_from("/ABS/PATH/TO/SKILL/data").unwrap(),
              ],
          },
          network_access: true,
          exclude_tmpdir_env_var: false,
          exclude_slash_tmp: false,
      },
      // Truncated for readability; actual generated profile is longer.
      macos_seatbelt_permission_file: r#"
  (allow user-preference-write)
  (allow appleevent-send
      (appleevent-destination "com.apple.Notes"))
  (allow mach-lookup (global-name "com.apple.axserver"))
  (allow mach-lookup (global-name "com.apple.CalendarAgent"))
  ...
  "#.to_string(),
```

Celia Chen · 2026-02-14 01:43:44 +00:00

5b6911cb1b

Fix js_repl in-flight tool-call waiter race (#11800 )

## Summary

This PR fixes a race in `js_repl` tool-call draining that could leave an
exec waiting indefinitely for in-flight tool calls to finish.

The fix is in:

-
`/Users/fjord/code/codex-jsrepl-seq/codex-rs/core/src/tools/js_repl/mod.rs`

## Problem

`js_repl` tracks in-flight tool calls per exec and waits for them to
drain on completion/timeout/cancel paths.
The previous wait logic used a check-then-wait pattern with `Notify`
that could miss a wakeup:

1. Observe `in_flight > 0`
2. Drop lock
3. Register wait (`notified().await`)

If `notify_waiters()` happened between (2) and (3), the waiter could
sleep until another notification that never comes.

## What changed

- Updated all exec-tool-call wait loops to create an owned notification
future while holding the lock:
- use `Arc<Notify>::notified_owned()` instead of cloning notify and
awaiting later.
- Applied this consistently to:
  - `wait_for_exec_tool_calls`
  - `wait_for_all_exec_tool_calls`
  - `wait_for_exec_tool_calls_map`

This preserves existing behavior while eliminating the lost-wakeup
window.

## Test coverage

Added a regression test:

- `wait_for_exec_tool_calls_map_drains_inflight_calls_without_hanging`

The test repeatedly races waiter/finisher tasks and asserts bounded
completion to catch hangs.

## Impact

- No API changes.
- No user-facing behavior changes intended.
- Improves reliability of exec lifecycle boundaries when tool calls are
still in flight.


#### [git stack](https://github.com/magus/git-stack-cli)
- ✅ `1` https://github.com/openai/codex/pull/11796
- 👉 `2` https://github.com/openai/codex/pull/11800
- ⏳ `3` https://github.com/openai/codex/pull/10673
- ⏳ `4` https://github.com/openai/codex/pull/10670

Curtis 'Fjord' Hawthorne · 2026-02-14 01:24:52 +00:00

0d76d029b7

Fix js_repl view_image test runtime panic (#11796 )

## Summary
Fixes a flaky/panicking `js_repl` image-path test by running it on a
multi-thread Tokio runtime and tightening assertions to focus on real
behavior.

## Problem
`js_repl_can_attach_image_via_view_image_tool` in  

`/Users/fjord/code/codex-jsrepl-seq/codex-rs/core/src/tools/js_repl/mod.rs`
can panic under single-thread test runtime with:

`can call blocking only when running on the multi-threaded runtime`

It also asserted a brittle user-facing text string.

## Changes
1. Updated the test runtime to:
   `#[tokio::test(flavor = "multi_thread", worker_threads = 2)]`
2. Removed the brittle `"attached local image path"` string assertion.
3. Kept the concrete side-effect assertions:
   - tool call succeeds
- image is actually injected into pending input (`InputImage` with
`data:image/png;base64,...`)

## Why this is safe
This is test-only behavior. No production runtime code paths are
changed.

## Validation
- Ran:
`cargo test -p codex-core
tools::js_repl::tests::js_repl_can_attach_image_via_view_image_tool --
--nocapture`
- Result: pass


#### [git stack](https://github.com/magus/git-stack-cli)
- 👉 `1` https://github.com/openai/codex/pull/11796
- ⏳ `2` https://github.com/openai/codex/pull/11800
- ⏳ `3` https://github.com/openai/codex/pull/10673
- ⏳ `4` https://github.com/openai/codex/pull/10670

Curtis 'Fjord' Hawthorne · 2026-02-14 01:11:13 +00:00

6cbb489e6e

turn metadata followups (#11782 )

some trivial simplifications from #11677

pash-openai · 2026-02-13 14:59:16 -08:00

a5e8e69d18

turn metadata: per-turn non-blocking (#11677 )

pash-openai · 2026-02-13 12:48:29 -08:00

6c0a924203

support app usage analytics (#11687 )

Emit app mentioned and app used events. Dedup by (turn_id, connector_id)

Example event params:
{
    "event_type": "codex_app_used",
    "connector_id": "asdk_app_xxx",
    "thread_id": "019c5527-36d4-xxx",
    "turn_id": "019c552c-cd17-xxx",
    "app_name": "Slack (OpenAI Internal)",
    "product_client_id": "codex_cli_rs",
    "invoke_type": "explicit",
    "model_slug": "gpt-5.3-codex"
}

alexsong-oai · 2026-02-13 12:00:16 -08:00

e71760fc64

Add js_repl kernel crash diagnostics (#11666 )

## Summary

This PR improves `js_repl` crash diagnostics so kernel failures are
debuggable without weakening timeout/reset guarantees.

## What Changed

- Added bounded kernel stderr capture and truncation logic (line + byte
caps).
- Added structured kernel snapshots (`pid`, exit status, stderr tail)
for failure paths.
- Enriched model-visible kernel-failure errors with a structured
diagnostics payload:
  - `js_repl diagnostics: {...}`
  - Included only for likely kernel-failure write/EOF cases.
- Improved logging around kernel write failures, unexpected exits, and
kill/wait paths.
- Added/updated unit tests for:
  - UTF-8-safe truncation
  - stderr tail bounds
  - structured diagnostics shape/truncation
  - conditional diagnostics emission
  - timeout kill behavior
  - forced kernel-failure diagnostics

## Why

Before this, failures like broken pipe / unexpected kernel exit often
surfaced as generic errors with little context. This change preserves
existing behavior but adds actionable diagnostics while keeping output
bounded.

## Scope

- Code changes are limited to:
-
`/Users/fjord/code/codex-jsrepl-seq/codex-rs/core/src/tools/js_repl/mod.rs`

## Validation

- `cargo clippy -p codex-core --all-targets -- -D warnings`
- Targeted `codex-core` js_repl unit tests (including new
diagnostics/timeout coverage)
- Tried starting a long running js_repl command (sleep for 10 minutes),
verified error output was as expected after killing the node process.

#### [git stack](https://github.com/magus/git-stack-cli)
- 👉 `1` https://github.com/openai/codex/pull/11666
- ⏳ `2` https://github.com/openai/codex/pull/10673
- ⏳ `3` https://github.com/openai/codex/pull/10670

Curtis 'Fjord' Hawthorne · 2026-02-13 11:57:11 -08:00

a02342c9e1

chore: mini (#11772 )

https://github.com/openai/codex/issues/11764

jif-oai · 2026-02-13 19:30:49 +00:00

c54a4ec078

Update read_path prompt (#11763 )

## Summary

- Created branch zuxin/read-path-update from main.
- Copied codex-rs/core/templates/memories/read_path.md from the current
branch.
- Committed the content change.

## Testing
Not run (content copy + commit only).

zuxin-oai · 2026-02-13 18:34:54 +00:00

b934ffcaaa

Report syntax errors in rules file (#11686 )

Currently, if there are syntax errors detected in the starlark rules
file, the entire policy is silently ignored by the CLI. The app server
correctly emits a message that can be displayed in a GUI.

This PR changes the CLI (both the TUI and non-interactive exec) to fail
when the rules file can't be parsed. It then prints out an error message
and exits with a non-zero exit code. This is consistent with the
handling of errors in the config file.

This addresses #11603

Eric Traut · 2026-02-13 10:33:40 -08:00

b98c810328

feat(tui): prevent macOS idle sleep while turns run (#11711 )

## Summary
- add a shared `codex-core` sleep inhibitor that uses native macOS IOKit
assertions (`IOPMAssertionCreateWithName` / `IOPMAssertionRelease`)
instead of spawning `caffeinate`
- wire sleep inhibition to turn lifecycle in `tui` (`TurnStarted`
enables; `TurnComplete` and abort/error finalization disable)
- gate this behavior behind a `/experimental` feature toggle
(`[features].prevent_idle_sleep`) instead of a dedicated `[tui]` config
flag
- expose the toggle in `/experimental` on macOS; keep it under
development on other platforms
- keep behavior no-op on non-macOS targets

<img width="1326" height="577" alt="image"
src="https://github.com/user-attachments/assets/73fac06b-97ae-46a2-800a-30f9516cf8a3"
/>

## Testing
- `cargo check -p codex-core -p codex-tui`
- `cargo test -p codex-core sleep_inhibitor::tests -- --nocapture`
- `cargo test -p codex-core
tui_config_missing_notifications_field_defaults_to_enabled --
--nocapture`
- `cargo test -p codex-core prevent_idle_sleep_is_ -- --nocapture`

## Semantics and API references
- This PR targets `caffeinate -i` semantics: prevent *idle system sleep*
while allowing display idle sleep.
- `caffeinate -i` mapping in Apple open source (`assertionMap`):
  - `kIdleAssertionFlag -> kIOPMAssertionTypePreventUserIdleSystemSleep`
- Source:
https://github.com/apple-oss-distributions/PowerManagement/blob/PowerManagement-1846.60.12/caffeinate/caffeinate.c#L52-L54
- Apple IOKit docs for assertion types and API:
-
https://developer.apple.com/documentation/iokit/iopmlib_h/iopmassertiontypes
-
https://developer.apple.com/documentation/iokit/1557092-iopmassertioncreatewithname
  - https://developer.apple.com/library/archive/qa/qa1340/_index.html

## Codex Electron vs this PR (full stack path)
- Codex Electron app requests sleep blocking with
`powerSaveBlocker.start("prevent-app-suspension")`:
-
https://github.com/openai/codex/blob/main/codex/codex-vscode/electron/src/electron-message-handler.ts
- Electron maps that string to Chromium wake lock type
`kPreventAppSuspension`:
-
https://github.com/electron/electron/blob/main/shell/browser/api/electron_api_power_save_blocker.cc
- Chromium macOS backend maps wake lock types to IOKit assertion
constants and calls IOKit:
  - `kPreventAppSuspension -> kIOPMAssertionTypeNoIdleSleep`
- `kPreventDisplaySleep / kPreventDisplaySleepAllowDimming ->
kIOPMAssertionTypeNoDisplaySleep`
-
https://github.com/chromium/chromium/blob/main/services/device/wake_lock/power_save_blocker/power_save_blocker_mac.cc

## Why this PR uses a different macOS constant name
- This PR uses `"PreventUserIdleSystemSleep"` directly, via
`IOPMAssertionCreateWithName`, in
`codex-rs/core/src/sleep_inhibitor.rs`.
- Apple’s IOKit header documents `kIOPMAssertionTypeNoIdleSleep` as
deprecated and recommends `kIOPMAssertPreventUserIdleSystemSleep` /
`kIOPMAssertionTypePreventUserIdleSystemSleep`:
-
https://github.com/apple-oss-distributions/IOKitUser/blob/IOKitUser-100222.60.2/pwr_mgt.subproj/IOPMLib.h#L1000-L1030
- So Chromium and this PR are using different constant names, but
semantically equivalent idle-system-sleep prevention behavior.

## Future platform support
The architecture is intentionally set up for multi-platform extensions:
- UI code (`tui`) only calls `SleepInhibitor::set_turn_running(...)` on
turn lifecycle boundaries.
- Platform-specific behavior is isolated in
`codex-rs/core/src/sleep_inhibitor.rs` behind `cfg(...)` blocks.
- Feature exposure is centralized in `core/src/features.rs` and surfaced
via `/experimental`.
- Adding new OS backends should not require additional TUI wiring; only
the backend internals and feature stage metadata need to change.

Potential follow-up implementations:
- Windows:
- Add a backend using Win32 power APIs
(`SetThreadExecutionState(ES_CONTINUOUS | ES_SYSTEM_REQUIRED)` as
baseline).
- Optionally move to `PowerCreateRequest` / `PowerSetRequest` /
`PowerClearRequest` for richer assertion semantics.
- Linux:
- Add a backend using logind inhibitors over D-Bus
(`org.freedesktop.login1.Manager.Inhibit` with `what="sleep"`).
  - Keep a no-op fallback where logind/D-Bus is unavailable.

This PR keeps the cross-platform API surface minimal so future PRs can
add Windows/Linux support incrementally with low churn.

---------

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

Yaroslav Volovich · 2026-02-13 10:31:39 -08:00

32da5eb358

fix: reduce flakiness of compact_resume_after_second_compaction_preserves_history (#11663 )

## Why
`compact_resume_after_second_compaction_preserves_history` has been
intermittently flaky in Windows CI.

The test had two one-shot request matchers in the second compact/resume
phase that could overlap, and it waited for the first `Warning` event
after compaction. In practice, that made the test sensitive to
platform/config-specific prompt shape and unrelated warning timing.

## What Changed
- Hardened the second compaction matcher in
`codex-rs/core/tests/suite/compact_resume_fork.rs` so it accepts
expected compact-request variants while explicitly excluding the
`AFTER_SECOND_RESUME` payload.
- Updated `compact_conversation()` to wait for the specific compaction
warning (`COMPACT_WARNING_MESSAGE`) rather than any `Warning` event.
- Added an inline comment explaining why the matcher is intentionally
broad but disjoint from the follow-up resume matcher.

## Test Plan
- `cargo test -p codex-core --test all
suite::compact_resume_fork::compact_resume_after_second_compaction_preserves_history
-- --exact`
- Repeated the same test in a loop (40 runs) to check for local
nondeterminism.

Michael Bolin · 2026-02-13 09:51:22 -08:00

2383978a2c

core: limit search_tool_bm25 to Apps and clarify discovery guidance (#11669 )

## Summary
- Limit `search_tool_bm25` indexing to `codex_apps` tools only, so
non-Apps MCP servers are no longer discoverable through this search
path.
- Move search-tool discovery guidance into the `search_tool_bm25` tool
description (via template include) instead of injecting it as a separate
developer message.
- Update Apps discovery guidance wording to clarify when to use
`search_tool_bm25` for Apps-backed systems (for example Slack, Google
Drive, Jira, Notion) and when to call tools directly.
- Remove dead `core` helper code (`filter_codex_apps_mcp_tools` and
`codex_apps_connector_id`) that is no longer used after the
tool-selection refactor.
- Update `core` search-tool tests to assert codex-apps-only behavior and
to validate guidance from the tool description.

## Validation
- ✅ `just fmt`
- ✅ `cargo test -p codex-core search_tool`
- ⚠️ `cargo test -p codex-core` was attempted, but the run repeatedly
stalled on
`tools::js_repl::tests::js_repl_can_attach_image_via_view_image_tool`.

## Tickets
- None

Anton Panasenko · 2026-02-13 09:32:46 -08:00

38c442ca7f

Fix memories output schema requirements (#11748 )

Summary
- make the phase1 memories schema require `rollout_slug` while still
allowing it to be `null`
- update the corresponding test to check the required fields and
nullable type list

Testing
- Not run (not requested)

jif-oai · 2026-02-13 16:17:21 +00:00

c0749c349f

chore: move explorer to spark (#11745 )

jif-oai · 2026-02-13 16:13:24 +00:00

561fc14045

feat: add slug in name (#11739 )

jif-oai · 2026-02-13 15:24:03 +00:00

db66d827be

feat: memories config (#11731 )

jif-oai · 2026-02-13 14:18:15 +00:00

e00080cea3

chore: streamline phase 2 (#11712 )

jif-oai · 2026-02-13 13:21:11 +00:00

36541876f4

Lower missing rollout log level (#11722 )

Fix this: https://github.com/openai/codex/issues/11634

jif-oai · 2026-02-13 12:59:17 +00:00

feae389942

feat: add token usage on memories (#11618 )

Add aggregated token usage metrics on phase 1 of memories

jif-oai · 2026-02-13 09:31:20 +00:00

e5e40e2d4b

chore(core) Restrict model-suggested rules (#11671 )

## Summary
If the model suggests a bad rule, don't show it to the user. This does
not impact the parsing of existing rules, just the ones we show.

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

Dylan Hurd · 2026-02-12 23:57:53 -08:00

e6e4c5fa3a

[apps] Fix app loading logic. (#11518 )

When `app/list` is called with `force_refetch=True`, we should seed the
results with what is already cached instead of starting from an empty
list. Otherwise when we send app/list/updated events, the client will
first see an empty list of accessible apps and then get the updated one.

Matthew Zeng · 2026-02-13 03:55:10 +00:00

f93037f55d

chore(approvals) More approvals scenarios (#11660 )

## Summary
Add some additional tests to approvals flow

## Testing
- [x] these are tests

Dylan Hurd · 2026-02-12 19:54:54 -08:00

35692e99c1

Added a test to verify that feature flags that are enabled by default are stable (#11275 )

We've had a few cases recently where someone enabled a feature flag for
a feature that's still under development or experimental. This test
should prevent this.

Eric Traut · 2026-02-12 17:53:15 -08:00

537102e657

Remove git commands from dangerous command checks (#11510 )

### Motivation

- Git subcommand matching was being classified as "dangerous" and caused
benign developer workflows (for example `git push --force-with-lease`)
to be blocked by the preflight policy.
- The change aligns behavior with the intent to reserve the dangerous
checklist for truly destructive shell ops (e.g. `rm -rf`) and avoid
surprising developer-facing blocks.

### Description

- Remove git-specific subcommand checks from
`is_dangerous_to_call_with_exec` in
`codex-rs/shell-command/src/command_safety/is_dangerous_command.rs`,
leaving only explicit `rm` and `sudo` passthrough checks.
- Deleted the git-specific helper logic that classified `reset`,
`branch`-delete, `push` (force/delete/refspec) and `clean --force` as
dangerous.
- Updated unit tests in the same file to assert that various `git
reset`/`git branch`/`git push`/`git clean` variants are no longer
classified as dangerous.
- Kept `find_git_subcommand` (used by safe-command classification)
intact so safe/unsafe parsing elsewhere remains functional.

### Testing

- Ran formatter with `just fmt` successfully.  
- Ran unit tests with `cargo test -p codex-shell-command` and all tests
passed (`144 passed; 0 failed`).

------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_698d19dedb4883299c3ceb5bbc6a0dcf)

Josh McKinney · 2026-02-13 01:33:02 +00:00

fc073c9c5b

Persist complete TurnContextItem state via canonical conversion (#11656 )

## Summary

This PR delivers the first small, shippable step toward model-visible
state diffing by making
`TurnContextItem` more complete and standardizing how it is built.

Specifically, it:
- Adds persisted network context to `TurnContextItem`.
- Introduces a single canonical `TurnContext -> TurnContextItem`
conversion path.
- Routes existing rollout write sites through that canonical conversion
helper.

No context injection/diff behavior changes are included in this PR.

## Why this change

The design goal is to make `TurnContextItem` the canonical source of
truth for context-diff
decisions.
Before this PR:
- `TurnContextItem` did not include all TurnContext-derived environment
inputs needed for v1
completeness.
- Construction was duplicated at multiple write sites.

This PR addresses both with a minimal, reviewable change.

## Changes

### 1) Extend `TurnContextItem` with network state
- Added `TurnContextNetworkItem { allowed_domains, denied_domains }`.
- Added `network: Option<TurnContextNetworkItem>` to `TurnContextItem`.
- Kept backward compatibility by making the new field optional and
skipped when absent.

Files:
- `codex-rs/protocol/src/protocol.rs`

### 2) Canonical conversion helper
- Added `TurnContext::to_turn_context_item(collaboration_mode)` in core.
- Added internal helper to derive network fields from
`config_layer_stack.requirements().network`.

Files:
- `codex-rs/core/src/codex.rs`

### 3) Use canonical conversion at rollout write sites
- Replaced ad hoc `TurnContextItem { ... }` construction with
`to_turn_context_item(...)` in:
  - sampling request path
  - compaction path

Files:
- `codex-rs/core/src/codex.rs`
- `codex-rs/core/src/compact.rs`

### 4) Update fixtures/tests for new optional field
- Updated existing `TurnContextItem` literals in tests to include
`network: None`.
- Added protocol tests for:
  - deserializing old payloads with no `network`
  - serializing when `network` is present

Files:
- `codex-rs/core/tests/suite/resume_warning.rs`
- No replay/diff logic changes.
- Persisted rollout `TurnContextItem` now carries additional network
context when available.
- Older rollout lines without `network` remain readable.

Charley Cunningham · 2026-02-12 17:22:44 -08:00

f24669d444

Add new apps_mcp_gateway (#11630 )

Adds a new apps_mcp_gateway flag to route Apps MCP calls through
https://api.openai.com/v1/connectors/mcp/ when enabled, while keeping
legacy MCP routing as default.

canvrno-oai · 2026-02-12 16:54:11 -08:00

46b2da35d5

1753 Commits