Users of Azure endpoints are reporting that when they use `/review`,
they sometimes see an error "Invalid 'input[3].id". I suspect this is
specific to the Azure implementation of the `responses` API. The Azure
team generally copies the OpenAI code for this endpoint, but they do
have minor differences and sometimes lag in rolling out bug fixes or
updates.
The error appears to be triggered because the `/review` implementation
is using a user ID with a colon in it.
Addresses #9360
We already support reading from `config.toml` through a symlink, but the
code was not properly handling updates to a symlinked config file. This
PR generalizes safe symlink-chain resolution and atomic writes into
path_utils, updating all config write paths to use the shared logic
(including set_default_oss_provider, which previously didn't use the
common path), and adds tests for symlink chains and cycles.
This resolves#6646.
Notes:
* Symlink cycles or resolution failures replace the top-level symlink
with a real file.
* Shared config write path now handles symlinks consistently across
edits, defaults, and empty-user-layer creation.
This PR was inspired by https://github.com/openai/codex/pull/9437, which
was contributed by @ryoppippi
# External (non-OpenAI) Pull Request Requirements
Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md
If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
Include a link to a bug report or enhancement request.
### Description
- Remove the now-unused `instructions` field from the session metadata
to simplify SessionMeta and stop propagating transient instruction text
through the rollout recorder API. This was only saving
user_instructions, and was never being read.
- Stop passing user instructions into the rollout writer at session
creation so the rollout header only contains canonical session metadata.
### Testing
- Ran `just fmt` which completed successfully.
- Ran `just fix -p codex-protocol`, `just fix -p codex-core`, `just fix
-p codex-app-server`, `just fix -p codex-tui`, and `just fix -p
codex-tui2` which completed (Clippy fixes applied) as part of
verification.
- Ran `cargo test -p codex-protocol` which passed (28 tests).
- Ran `cargo test -p codex-core` which showed failures in a small set of
tests (not caused by the protocol type change directly):
`default_client::tests::test_create_client_sets_default_headers`,
several `models_manager::manager::tests::refresh_available_models_*`,
and `shell_snapshot::tests::linux_sh_snapshot_includes_sections` (these
tests failed in this CI run).
- Ran `cargo test -p codex-app-server` which reported several failing
integration tests (including
`suite::codex_message_processor_flow::test_codex_jsonrpc_conversation_flow`,
`suite::output_schema::send_user_turn_*`, and
`suite::user_agent::get_user_agent_returns_current_codex_user_agent`).
- `cargo test -p codex-tui` and `cargo test -p codex-tui2` were
attempted but aborted due to disk space exhaustion (`No space left on
device`).
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_696bd8ce632483228d298cf07c7eb41c)
## Summary
We have a variety of things we refer to as instructions in the code
base: our current canonical terms are:
- base instructions (raw string)
- developer instructions (has a type in protocol)
- user instructions
We also have `instructions` floating around in various places. We should
standardize on the above, and start using types to prevent them from
ending up in the wrong place. There will be additional PRs, but I'm
going to keep these small so we can easily follow them!
## Testing
- [x] Tests pass, this is purely a file move
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
```
**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
- Merge `model` and `reasoning_effort` under collaboration modes.
- Add additional instructions for custom collaboration mode
- Default to Custom to not change behavior
Summary:
- Add forked_from to SessionMeta/SessionConfiguredEvent and persist it
for forked sessions.
- Surface forked_from in /status for tui + tui2 and add snapshots.
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.
- 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.
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.
## 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
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`.
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.
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
### What
Add `WebSearchMode` enum (disabled, cached live, defaults to cached) to
config + V2 protocol. This enum takes precedence over legacy flags:
`web_search_cached`, `web_search_request`, and `tools.web_search`.
Keep `--search` as live.
### Tests
Added tests
A simple `s/mcp_server_requirements/mcp_servers/g` for an unreleased
feature. @bolinfest correctly pointed out, it's already in
`requirements.toml` so the `_requirements` is redundant.
Adding a prompt for collab tools. This is only for internal use and the
prompt won't be gated for now as it is not stable yet.
The goal of this PR is to provide the tool required to iterate on the
prompt
Emit the following events around the collab tools. On the `app-server`
this will be under `item/started` and `item/completed`
```
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabAgentSpawnBeginEvent {
/// Identifier for the collab tool call.
pub call_id: String,
/// Thread ID of the sender.
pub sender_thread_id: ThreadId,
/// Initial prompt sent to the agent. Can be empty to prevent CoT leaking at the
/// beginning.
pub prompt: String,
}
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabAgentSpawnEndEvent {
/// Identifier for the collab tool call.
pub call_id: String,
/// Thread ID of the sender.
pub sender_thread_id: ThreadId,
/// Thread ID of the newly spawned agent, if it was created.
pub new_thread_id: Option<ThreadId>,
/// Initial prompt sent to the agent. Can be empty to prevent CoT leaking at the
/// beginning.
pub prompt: String,
/// Last known status of the new agent reported to the sender agent.
pub status: AgentStatus,
}
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabAgentInteractionBeginEvent {
/// Identifier for the collab tool call.
pub call_id: String,
/// Thread ID of the sender.
pub sender_thread_id: ThreadId,
/// Thread ID of the receiver.
pub receiver_thread_id: ThreadId,
/// Prompt sent from the sender to the receiver. Can be empty to prevent CoT
/// leaking at the beginning.
pub prompt: String,
}
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabAgentInteractionEndEvent {
/// Identifier for the collab tool call.
pub call_id: String,
/// Thread ID of the sender.
pub sender_thread_id: ThreadId,
/// Thread ID of the receiver.
pub receiver_thread_id: ThreadId,
/// Prompt sent from the sender to the receiver. Can be empty to prevent CoT
/// leaking at the beginning.
pub prompt: String,
/// Last known status of the receiver agent reported to the sender agent.
pub status: AgentStatus,
}
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabWaitingBeginEvent {
/// Thread ID of the sender.
pub sender_thread_id: ThreadId,
/// Thread ID of the receiver.
pub receiver_thread_id: ThreadId,
/// ID of the waiting call.
pub call_id: String,
}
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabWaitingEndEvent {
/// Thread ID of the sender.
pub sender_thread_id: ThreadId,
/// Thread ID of the receiver.
pub receiver_thread_id: ThreadId,
/// ID of the waiting call.
pub call_id: String,
/// Last known status of the receiver agent reported to the sender agent.
pub status: AgentStatus,
}
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabCloseBeginEvent {
/// Identifier for the collab tool call.
pub call_id: String,
/// Thread ID of the sender.
pub sender_thread_id: ThreadId,
/// Thread ID of the receiver.
pub receiver_thread_id: ThreadId,
}
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq, JsonSchema, TS)]
pub struct CollabCloseEndEvent {
/// Identifier for the collab tool call.
pub call_id: String,
/// Thread ID of the sender.
pub sender_thread_id: ThreadId,
/// Thread ID of the receiver.
pub receiver_thread_id: ThreadId,
/// Last known status of the receiver agent reported to the sender agent before
/// the close.
pub status: AgentStatus,
}
```
## Problem
Codex’s TUI quit behavior has historically been easy to trigger
accidentally and hard to reason
about.
- `Ctrl+C`/`Ctrl+D` could terminate the UI immediately, which is a
common key to press while trying
to dismiss a modal, cancel a command, or recover from a stuck state.
- “Quit” and “shutdown” were not consistently separated, so some exit
paths could bypass the
shutdown/cleanup work that should run before the process terminates.
This PR makes quitting both safer (harder to do by accident) and more
uniform across quit
gestures, while keeping the shutdown-first semantics explicit.
## Mental model
After this change, the system treats quitting as a UI request that is
coordinated by the app
layer.
- The UI requests exit via `AppEvent::Exit(ExitMode)`.
- `ExitMode::ShutdownFirst` is the normal user path: the app triggers
`Op::Shutdown`, continues
rendering while shutdown runs, and only ends the UI loop once shutdown
has completed.
- `ExitMode::Immediate` exists as an escape hatch (and as the
post-shutdown “now actually exit”
signal); it bypasses cleanup and should not be the default for
user-triggered quits.
User-facing quit gestures are intentionally “two-step” for safety:
- `Ctrl+C` and `Ctrl+D` no longer exit immediately.
- The first press arms a 1-second window and shows a footer hint (“ctrl
+ <key> again to quit”).
- Pressing the same key again within the window requests a
shutdown-first quit; otherwise the
hint expires and the next press starts a fresh window.
Key routing remains modal-first:
- A modal/popup gets first chance to consume `Ctrl+C`.
- If a modal handles `Ctrl+C`, any armed quit shortcut is cleared so
dismissing a modal cannot
prime a subsequent `Ctrl+C` to quit.
- `Ctrl+D` only participates in quitting when the composer is empty and
no modal/popup is active.
The design doc `docs/exit-confirmation-prompt-design.md` captures the
intended routing and the
invariants the UI should maintain.
## Non-goals
- This does not attempt to redesign modal UX or make modals uniformly
dismissible via `Ctrl+C`.
It only ensures modals get priority and that quit arming does not leak
across modal handling.
- This does not introduce a persistent confirmation prompt/menu for
quitting; the goal is to keep
the exit gesture lightweight and consistent.
- This does not change the semantics of core shutdown itself; it changes
how the UI requests and
sequences it.
## Tradeoffs
- Quitting via `Ctrl+C`/`Ctrl+D` now requires a deliberate second
keypress, which adds friction for
users who relied on the old “instant quit” behavior.
- The UI now maintains a small time-bounded state machine for the armed
shortcut, which increases
complexity and introduces timing-dependent behavior.
This design was chosen over alternatives (a modal confirmation prompt or
a long-lived “are you
sure” state) because it provides an explicit safety barrier while
keeping the flow fast and
keyboard-native.
## Architecture
- `ChatWidget` owns the quit-shortcut state machine and decides when a
quit gesture is allowed
(idle vs cancellable work, composer state, etc.).
- `BottomPane` owns rendering and local input routing for modals/popups.
It is responsible for
consuming cancellation keys when a view is active and for
showing/expiring the footer hint.
- `App` owns shutdown sequencing: translating
`AppEvent::Exit(ShutdownFirst)` into `Op::Shutdown`
and only terminating the UI loop when exit is safe.
This keeps “what should happen” decisions (quit vs interrupt vs ignore)
in the chat/widget layer,
while keeping “how it looks and which view gets the key” in the
bottom-pane layer.
## Observability
You can tell this is working by running the TUIs and exercising the quit
gestures:
- While idle: pressing `Ctrl+C` (or `Ctrl+D` with an empty composer and
no modal) shows a footer
hint for ~1 second; pressing again within that window exits via
shutdown-first.
- While streaming/tools/review are active: `Ctrl+C` interrupts work
rather than quitting.
- With a modal/popup open: `Ctrl+C` dismisses/handles the modal (if it
chooses to) and does not
arm a quit shortcut; a subsequent quick `Ctrl+C` should not quit unless
the user re-arms it.
Failure modes are visible as:
- Quits that happen immediately (no hint window) from `Ctrl+C`/`Ctrl+D`.
- Quits that occur while a modal is open and consuming `Ctrl+C`.
- UI termination before shutdown completes (cleanup skipped).
## Tests
- Updated/added unit and snapshot coverage in `codex-tui` and
`codex-tui2` to validate:
- The quit hint appears and expires on the expected key.
- Double-press within the window triggers a shutdown-first quit request.
- Modal-first routing prevents quit bypass and clears any armed shortcut
when a modal consumes
`Ctrl+C`.
These tests focus on the UI-level invariants and rendered output; they
do not attempt to validate
real terminal key-repeat timing or end-to-end process shutdown behavior.
---
Screenshot:
<img width="912" height="740" alt="Screenshot 2026-01-13 at 1 05 28 PM"
src="https://github.com/user-attachments/assets/18f3d22e-2557-47f2-a369-ae7a9531f29f"
/>
Instead of having a hard-coded default review model, use the current
model for running `/review` unless one is specified in the config.
Also inherit current reasoning effort
### Motivation
- Landlock alone cannot prevent writes to sensitive in-repo files like
`.git/` when the repo root is writable, so explicit mount restrictions
are required for those paths.
- The sandbox must set up any mounts before calling Landlock so Landlock
can still be applied afterwards and the two mechanisms compose
correctly.
### Description
- Add a new `linux-sandbox` helper `apply_read_only_mounts` in
`linux-sandbox/src/mounts.rs` that: unshares namespaces, maps uids/gids
when required, makes mounts private, bind-mounts targets, and remounts
them read-only.
- Wire the mount step into the sandbox flow by calling
`apply_read_only_mounts(...)` before network/seccomp and before applying
Landlock rules in `linux-sandbox/src/landlock.rs`.
This PR is in the scope of multi-agent work.
An agent (=thread) can now spawn other agents. Those other agents are
not attached to any clients. We need a way to make sure that the clients
are aware of the new threads to look at (for approval for example). This
PR adds a channel to the `ThreadManager` that pushes the ID of those
newly created agents such that the client (here the app-server) can also
subscribe to those ones.
Shijie RaoandGitHub
jif-oaiandGitHub
Eric TrautandGitHub
Ahmed IbrahimandGitHub
Dylan HurdandGitHub
Alex HornbyandGitHub
Fouad MatinandGitHub
xl-openaiandGitHub
Anton PanasenkoandGitHub
Owen LinandGitHub
viyatb-oaiandGitHub
charley-oaiandGitHub
Yuvraj Angad SinghandGitHub
pap-openaiandGitHub
sayan-oaiandGitHub
gt-oaiandGitHub
pakrym-oaiandGitHub