codex

fix unified_exec::tests::unified_exec_timeouts to use a more unique match value (#9414 )

Fix unified_exec_timeouts to use a unique variable value rather than
"codex" which was causing false positives when running tests locally
(presumably from my bash prompts). Discovered while running tests to
validate another change.

Fixes https://github.com/openai/codex/issues/9413

Test Plan:

Ran test locally on my fedora 43 x86_64 machine with:
```
cd codex/cargo-rs
cargo nextest run --all-features --no-fail-fast unified_exec::tests::unified_exec_timeouts
```

Before, unified_exec_timeouts fails:
```
    Finished `test` profile [unoptimized + debuginfo] target(s) in 0.38s
────────────
 Nextest run ID fa2b4949-a66c-408c-8002-32c52c70ec4f with nextest profile: default
    Starting 1 test across 107 binaries (3211 tests skipped)
        FAIL [   5.667s] codex-core unified_exec::tests::unified_exec_timeouts
  stdout ───

    running 1 test
    test unified_exec::tests::unified_exec_timeouts ... FAILED

    failures:

    failures:
        unified_exec::tests::unified_exec_timeouts

    test result: FAILED. 0 passed; 1 failed; 0 ignored; 0 measured; 774 filtered out; finished in 5.66s

  stderr ───

    thread 'unified_exec::tests::unified_exec_timeouts' (459601) panicked at core/src/unified_exec/mod.rs:381:9:
    timeout too short should yield incomplete output
    note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace

────────────
     Summary [   5.677s] 1 test run: 0 passed, 1 failed, 3211 skipped
        FAIL [   5.667s] codex-core unified_exec::tests::unified_exec_timeouts
error: test run failed

```

After, works:
```
    Finished `test` profile [unoptimized + debuginfo] target(s) in 0.34s
────────────
 Nextest run ID f49e9004-e30b-4049-b0ff-283b543a1cd7 with nextest profile: default
    Starting 1 test across 107 binaries (3211 tests skipped)
        SLOW [> 15.000s] codex-core unified_exec::tests::unified_exec_timeouts
        PASS [  17.666s] codex-core unified_exec::tests::unified_exec_timeouts
────────────
     Summary [  17.676s] 1 test run: 1 passed (1 slow), 3211 skipped
```

Alex Hornby · 2026-01-17 09:05:53 -08:00

b877a2041e

fix(tui) Defer backtrack trim until rollback confirms (#9401 )

Document the backtrack/rollback state machine and invariants between the
transcript overlay, in-flight “live tail”, and core thread state (tui + tui2).

Also adjust behavior for correctness:
- Track a single pending rollback and block additional rollbacks until core responds.
- Defer trimming transcript cells until ThreadRolledBack for the active session.
- Clear the guard on ThreadRollbackFailed so the user can retry.
- After a confirmed trim, schedule a one-shot scrollback refresh on the next draw.
- Clear stale pending rollback state when switching sessions.

---------

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

Ahmed Ibrahim · 2026-01-17 06:29:41 +00:00

764f3c7d03

fix(codex-api): treat invalid_prompt as non-retryable (#9400 )

**Goal**: Prevent response.failed events with `invalid_prompt` from
being treated as retryable errors so the UI shows the actual error
message instead of continually retrying.

**Before**: Codex would continue to retry despite the prompt being
marked as disallowed
**After**: Codex will stop retrying once prompt is marked disallowed

Fouad Matin · 2026-01-16 22:22:08 -08:00

93a5e0fe1c

Add collaboration_mode override to turns (#9408 )

Ahmed Ibrahim · 2026-01-16 21:51:25 -08:00

146d54cede

Support enable/disable skill via config/api. (#9328 )

In config.toml:
```
[[skills.config]]
path = "/Users/xl/.codex/skills/my_skill/SKILL.md"
enabled = false
```

API:
skills/list, skills/config/write

xl-openai · 2026-01-16 20:22:05 -08:00

ad8bf59cbf

Introduce collaboration modes (#9340 )

- Merge `model` and `reasoning_effort` under collaboration modes.
- Add additional instructions for custom collaboration mode
- Default to Custom to not change behavior

Ahmed Ibrahim · 2026-01-17 00:28:22 +00:00

246f506551

feat: show forked from session id in /status (#9330 )

Summary:
- Add forked_from to SessionMeta/SessionConfiguredEvent and persist it
for forked sessions.
- Surface forked_from in /status for tui + tui2 and add snapshots.

Anton Panasenko · 2026-01-16 13:41:46 -08:00

c26fe64539

feat(app-server, core): return threads by created_at or updated_at (#9247 )

Add support for returning threads by either `created_at` OR `updated_at`
descending. Previously core always returned threads ordered by
`created_at`.

This PR:
- updates core to be able to list threads by `updated_at` OR
`created_at` descending based on what the caller wants
- also update `thread/list` in app-server to expose this (default to
`created_at` if not specified)

All existing codepaths (app-server, TUI) still default to `created_at`,
so no behavior change is expected with this PR.

**Implementation**
To sort by `updated_at` is a bit nontrivial (whereas `created_at` is
easy due to the way we structure the folders and filenames on disk,
which are all based on `created_at`).

The most naive way to do this without introducing a cache file or sqlite
DB (which we have to implement/maintain) is to scan files in reverse
`created_at` order on disk, and look at the file's mtime (last modified
timestamp according to the filesystem) until we reach `MAX_SCAN_FILES`
(currently set to 10,000). Then, we can return the most recent N
threads.

Based on some quick and dirty benchmarking on my machine with ~1000
rollout files, calling `thread/list` with limit 50, the `updated_at`
path is slower as expected due to all the I/O:
- updated-at: average 103.10 ms
- created-at: average 41.10 ms

Those absolute numbers aren't a big deal IMO, but we can certainly
optimize this in a followup if needed by introducing more state stored
on disk.

**Caveat**
There's also a limitation in that any files older than `MAX_SCAN_FILES`
will be excluded, which means if a user continues a REALLY old thread,
it's possible to not be included. In practice that should not be too big
of an issue.

If a user makes...
- 1000 rollouts/day → threads older than 10 days won't show up
- 100 rollouts/day → ~100 days

If this becomes a problem for some reason, even more motivation to
implement an updated_at cache.

Owen Lin · 2026-01-16 20:58:55 +00:00

f1653dd4d3

feat: /fork the current session instead of opening session picker (#9385 )

Implemented /fork to fork the current session directly (no picker),
handling it via a new ForkCurrentSession app event in both tui and tui2.
Updated slash command descriptions/tooltips and adjusted the fork tests
accordingly. Removed the unused in-session fork picker event.

Anton Panasenko · 2026-01-16 11:28:52 -08:00

e893e83eb9

chore: upgrade to Rust 1.92.0 (#8860 )

**Summary**
- Upgrade Rust toolchain used by CI to 1.92.0.
- Address new clippy `derivable_impls` warnings by deriving `Default`
for enums across protocol, core, backend openapi models, and
windows-sandbox setup.
- Tidy up related test/config behavior (originator header handling, env
override cleanup) and remove a now-unused assignment in TUI/TUI2 render
layout.

**Testing**
- `just fmt`
- `just fix -p codex-tui`
- `just fix -p codex-tui2`
- `just fix -p codex-windows-sandbox`
- `cargo test -p codex-tui`
- `cargo test -p codex-tui2`
- `cargo test -p codex-windows-sandbox`
- `cargo test -p codex-core --test all`
- `cargo test -p codex-app-server --test all`
- `cargo test -p codex-mcp-server --test all`
- `cargo test --all-features`

viyatb-oai · 2026-01-16 11:12:52 -08:00

f89a40a849

feat: tool call duration metric (#9364 )

jif-oai · 2026-01-16 18:33:14 +01:00

e650d4b02c

Turn-state sticky routing per turn (#9332 )

- capture the header from SSE/WS handshakes, store it per
ModelClientSession using `Oncelock`, echo it on turn-scoped requests,
and add SSE+WS integration tests for within-turn persistence +
cross-turn reset.

- keep `x-codex-turn-state` sticky within a user turn to maintain
routing continuity for retries/tool follow-ups.

Ahmed Ibrahim · 2026-01-16 09:30:11 -08:00

ebdd8795e9

add codex cloud list (#9324 )

for listing cloud tasks.

Jeremy Rose · 2026-01-16 08:56:38 -08:00

4125c825f9

Made codex exec resume --last consistent with codex resume --last (#9352 )

PR #9245 made `codex resume --last` honor cwd, but I forgot to make the
same change for `codex exec resume --last`. This PR fixes the
inconsistency.

This addresses #8700

Eric Traut · 2026-01-16 08:53:47 -08:00

9147df0e60

[device-auth] Add device code auth as a standalone option when headless environment is detected. (#9333 )

Matthew Zeng · 2026-01-16 08:35:03 -08:00

131590066e

fix: flaky tests (#9373 )

jif-oai · 2026-01-16 17:24:41 +01:00

2691e1ce21

chore: close pipe on non-pty processes (#9369 )

Closing the STDIN of piped process when starting them to avoid commands
like `rg` to wait for content on STDIN and hangs for ever

jif-oai · 2026-01-16 15:54:32 +01:00

1668ca726f

prompt collab (#9367 )

jif-oai · 2026-01-16 15:12:41 +01:00

7905e99d03

feat: CODEX_CI (#9366 )

jif-oai · 2026-01-16 13:52:16 +00:00

7fc49697dd

feat: collab wait multiple IDs (#9294 )

jif-oai · 2026-01-16 12:05:04 +01:00

c576756c81

feat: run user commands under user snapshot (#9357 )

The initial goal is for user snapshots to have access to aliases etc

jif-oai · 2026-01-16 11:49:28 +01:00

c1ac5223e1

feat: propagate approval request of unsubscribed threads (#9232 )

A thread can now be spawned by another thread. In order to process the
approval requests of such sub-threads, we need to detect those event and
show them in the TUI.

This is a temporary solution while the UX is being figured out. This PR
should be reverted once done

jif-oai · 2026-01-16 11:23:01 +01:00

f5b3e738fb

rename model turn to sampling request (#9336 )

We have two type of turns now: model and user turns. It's always
confusing to refer to either. Model turn is basically a sampling
request.

Ahmed Ibrahim · 2026-01-16 10:06:24 +01:00

0cce6ebd83

Fix token estimate during compaction (#9337 )

This addresses #9287

Eric Traut · 2026-01-15 19:48:11 -08:00

1fc72c647f

fix(mcp): include threadId in both content and structuredContent in CallToolResult (#9338 )

Michael Bolin · 2026-01-15 18:33:11 -08:00

99f47d6e9a

fix(tui): only show 'Worked for' separator when actual work was performed (#8958 )

Fixes #7919.

This PR addresses a TUI display bug where the "Worked for" separator
would appear prematurely during the planning stage.

**Changes:**
- Added `had_work_activity` flag to `ChatWidget` to track if actual work
(exec commands, MCP tool calls, patches) was performed in the current
turn.
- Updated `handle_streaming_delta` to only display the
`FinalMessageSeparator` if both `needs_final_message_separator` AND
`had_work_activity` are true.
- Updated `handle_exec_end_now`, `handle_patch_apply_end_now`, and
`handle_mcp_end_now` to set `had_work_activity = true`.

**Verification:**
- Ran `cargo test -p codex-tui` to ensure no regressions.
- Manual verification confirms the separator now only appears after
actual work is completed.

---------

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

Thanh Nguyen · 2026-01-16 01:41:43 +00:00

a6324ab34b

chore(windows) Enable Powershell UTF8 feature (#9195 )

## Summary
We've received a lot of positive feedback about this feature, so we're
going to enable it by default.

Dylan Hurd · 2026-01-16 01:29:12 +00:00

3cabb24210

Add text element metadata to protocol, app server, and core (#9331 )

The second part of breaking up PR
https://github.com/openai/codex/pull/9116

Summary:

- Add `TextElement` / `ByteRange` to protocol user inputs and user
message events with defaults.
- Thread `text_elements` through app-server v1/v2 request handling and
history rebuild.
- Preserve UI metadata only in user input/events (not `ContentItem`)
while keeping local image attachments in user events for rehydration.

Details:

- Protocol: `UserInput::Text` carries `text_elements`;
`UserMessageEvent` carries `text_elements` + `local_images`.
Serialization includes empty vectors for backward compatibility.
- app-server-protocol: v1 defines `V1TextElement` / `V1ByteRange` in
camelCase with conversions; v2 uses its own camelCase wrapper.
- app-server: v1/v2 input mapping includes `text_elements`; thread
history rebuilds include them.
- Core: user event emission preserves UI metadata while model history
stays clean; history replay round-trips the metadata.

charley-oai · 2026-01-15 17:26:41 -08:00

1fa8350ae7

fix: send non-null content on elicitation Accept (#9196 )

## Summary

- When a user accepts an MCP elicitation request, send `content:
Some(json!({}))` instead of `None`
- MCP servers that use elicitation expect content to be present when
action is Accept
- This matches the expected behavior shown in tests at
`exec-server/tests/common/lib.rs:171`

## Root Cause

In `codex-rs/core/src/codex.rs`, the `resolve_elicitation` function
always sent `content: None`:

```rust
let response = ElicitationResponse {
    action,
    content: None,  // Always None, even for Accept
};
```

## Fix

Send an empty object when accepting:

```rust
let content = match action {
    ElicitationAction::Accept => Some(serde_json::json!({})),
    ElicitationAction::Decline | ElicitationAction::Cancel => None,
};
```

## Test plan

- [x] Code compiles with `cargo check -p codex-core`
- [x] Formatted with `just fmt`
- [ ] Integration test `accept_elicitation_for_prompt_rule` (requires
MCP server binary)

Fixes #9053

Yuvraj Angad Singh · 2026-01-15 14:20:57 -08:00

004a74940a

Revert empty paste image handling (#9318 )

Revert #9049 behavior so empty paste events no longer trigger a
clipboard image read.

Ahmed Ibrahim · 2026-01-15 14:16:09 -08:00

749b58366c

remove needs_follow_up error log (#9272 )

pap-openai · 2026-01-15 21:20:54 +00:00

d886a8646c

[search] allow explicitly disabling web search (#9249 )

moving `web_search` rollout serverside, so need a way to explicitly
disable search + signal eligibility from the client.

- Add `x‑oai‑web‑search‑eligible` header that signifies whether the
request can have web search.
- Only attach the `web_search` tool when the resolved `WebSearchMode` is
`Live` or `Cached`.

sayan-oai · 2026-01-15 11:28:57 -08:00

169201b1b5

Support SKILL.toml file. (#9125 )

We’re introducing a new SKILL.toml to hold skill metadata so Codex can
deliver a richer Skills experience.

Initial focus is the interface block:
```
[interface]
display_name = "Optional user-facing name"
short_description = "Optional user-facing description"
icon_small = "./assets/small-400px.png"
icon_large = "./assets/large-logo.svg"
brand_color = "#3B82F6"
default_prompt = "Optional surrounding prompt to use the skill with"
```

All fields are exposed via the app server API.
display_name and short_description are consumed by the TUI.

xl-openai · 2026-01-15 11:20:04 -08:00

42fa4c237f

Revert recent styling change for input prompt placeholder text (#9307 )

A recent change in commit ccba737d26 modified the styling of the
placeholder text (e.g. "Implement {feature}") in the input box of the
CLI, changing it from non-italic to italic. I think this was likely
unintentional. It results in a bad display appearance on some terminal
emulators, and several users have complained about it.

This change switches back to non-italic styling, restoring the older
behavior.

It addresses #9262

Eric Traut · 2026-01-15 10:58:12 -08:00

5f10548772

nit: clean unified exec background processes (#9304 )

To fix the occurences where the End event is received after the listener
stopped listenning

jif-oai · 2026-01-15 18:34:33 +00:00

da44569fef

chore: better orchestrator prompt (#9301 )

jif-oai · 2026-01-15 18:11:43 +00:00

393a5a0311

revert: remove pre-Landlock bind mounts apply (#9300 )

**Description**

This removes the pre‑Landlock read‑only bind‑mount step from the Linux
sandbox so filesystem restrictions rely solely on Landlock again.
`mounts.rs` is kept in place but left unused. The linux‑sandbox README
is updated to match the new behavior and manual test expectations.

viyatb-oai · 2026-01-15 09:47:57 -08:00

55bda1a0f2

fix(exec): improve stdin prompt decoding (#9151 )

Fixes #8733.

- Read prompt from stdin as raw bytes and decode more helpfully.
- Strip UTF-8 BOM; decode UTF-16LE/UTF-16BE when a BOM is present.
- For other non-UTF8 input, fail with an actionable message (offset +
iconv hint).

Tests: `cargo test -p codex-exec`.

李琼羽 · 2026-01-15 09:29:05 -08:00

b4d240c3ae

Propagate MCP disabled reason (#9207 )

Indicate why MCP servers are disabled when they are disabled by
requirements:

```
➜  codex git:(main) ✗ just codex mcp list
cargo run --bin codex -- "$@"
    Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.27s
     Running `target/debug/codex mcp list`
Name         Command          Args  Env  Cwd  Status                                                                  Auth
docs         docs-mcp         -     -    -    disabled: requirements (MDM com.openai.codex:requirements_toml_base64)  Unsupported
hello_world  hello-world-mcp  -     -    -    disabled: requirements (MDM com.openai.codex:requirements_toml_base64)  Unsupported

➜  codex git:(main) ✗ just c
cargo run --bin codex -- "$@"
    Finished `dev` profile [unoptimized + debuginfo] target(s) in 0.90s
     Running `target/debug/codex`
╭─────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.0.0)                    │
│                                             │
│ model:     gpt-5.2 xhigh   /model to change │
│ directory: ~/code/codex/codex-rs            │
╰─────────────────────────────────────────────╯

/mcp

🔌  MCP Tools

  • No MCP tools available.

  • docs (disabled)
    • Reason: requirements (MDM com.openai.codex:requirements_toml_base64)

  • hello_world (disabled)
    • Reason: requirements (MDM com.openai.codex:requirements_toml_base64)
```

gt-oai · 2026-01-15 17:24:00 +00:00

f6df1596eb

Changed codex resume --last to honor the current cwd (#9245 )

This PR changes `codex resume --last` to work consistently with `codex
resume`. Namely, it filters based on the cwd when selecting the last
session. It also supports the `--all` modifier as an override.

This addresses #8700

Eric Traut · 2026-01-15 17:05:08 +00:00

ae96a15312

feat: basic tui for event emission (#9209 )

jif-oai · 2026-01-15 15:53:02 +00:00

3fc487e0e0

feat: add interrupt capabilities to send_input (#9276 )

jif-oai · 2026-01-15 14:59:07 +00:00

faeb08c1e1

feat: add agent roles to collab tools (#9275 )

Add `agent_type` parameter to the collab tool `spawn_agent` that
contains a preset to apply on the config when spawning this agent

jif-oai · 2026-01-15 13:33:52 +00:00

05b960671d

feat: collab tools app-server event mapping (#9213 )

jif-oai · 2026-01-15 09:03:26 +00:00

bad4c12b9d

fix: fallback to Landlock-only when user namespaces unavailable and set PR_SET_NO_NEW_PRIVS early (#9250 )

fixes https://github.com/openai/codex/issues/9236

### Motivation
- Prevent sandbox setup from failing when unprivileged user namespaces
are denied so Landlock-only protections can still be applied.
- Ensure `PR_SET_NO_NEW_PRIVS` is set before installing seccomp and
Landlock restrictions to avoid kernel `EPERM`/`LandlockRestrict`
ordering issues.

### Description
- Add `is_permission_denied` helper that detects `EPERM` /
`PermissionDenied` from `CodexErr` to drive fallback logic.
- In `apply_read_only_mounts` skip read-only bind-mount setup and return
`Ok(())` when `unshare_user_and_mount_namespaces()` fails with
permission-denied so Landlock rules can still be installed.
- Add `set_no_new_privs()` and call it from
`apply_sandbox_policy_to_current_thread` before installing seccomp
filters and Landlock rules when disk or network access is restricted.

viyatb-oai · 2026-01-14 22:24:34 -08:00

2259031d64

Add migration_markdown in model_info (#9219 )

Next step would be to clean Model Upgrade in model presets

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: aibrahim-oai <219906144+aibrahim-oai@users.noreply.github.com>

Ahmed Ibrahim · 2026-01-15 01:55:22 +00:00

a09711332a

Add text element metadata to types (#9235 )

Initial type tweaking PR to make the diff of
https://github.com/openai/codex/pull/9116 smaller

This should not change any behavior, just adds some fields to types

charley-oai · 2026-01-14 16:41:50 -08:00

4a9c2bcc5a

fix: increase timeout for release builds from 30 to 60 minutes (#9242 )

Windows builds have been tripping the 30 minute timeout. For sure, we
need to improve this, but as a quick fix, let's just increase the
timeout.

Perhaps we should switch to `lto = "thin"` for release builds, at least
for Windows:


https://github.com/openai/codex/blob/3728db11b87cb8490bcf6bf2cdf0e13dcfb0c28b/codex-rs/Cargo.toml#L288

See https://doc.rust-lang.org/cargo/reference/profiles.html#lto for
details.

Michael Bolin · 2026-01-15 00:38:25 +00:00

2a68b74b9b

fix: eliminate unnecessary clone() for each SSE event (#9238 )

Given how many SSE events we get, seems worth fixing.

Michael Bolin · 2026-01-15 00:06:09 +00:00

3728db11b8

fix: correct linux sandbox uid/gid mapping after unshare (#9234 )

fixes https://github.com/openai/codex/issues/9233
## Summary
- capture effective uid/gid before unshare for user namespace maps
- pass captured ids into uid/gid map writer

## Testing
- just fmt
- just fix -p codex-linux-sandbox
- cargo test -p codex-linux-sandbox

viyatb-oai · 2026-01-14 15:35:53 -08:00

e59e7d163d

2895 Commits