## Why
PR #21460 reverted the earlier move of skills change watching from
`codex-core` into app-server. This reapplies that boundary change so
app-server owns client-facing `skills/changed` notifications and core no
longer carries the watcher.
## What
- Restore the app-server `SkillsWatcher` and register it from thread
listener setup.
- Remove the core-owned skills watcher and its core live-reload
integration surface.
- Restore app-server coverage for `skills/changed` notifications after a
watched skill file changes.
## Validation
- `cargo test -p codex-app-server --test all
suite::v2::skills_list::skills_changed_notification_is_emitted_after_skill_change
-- --exact --nocapture`
- `cargo test -p codex-core --lib --no-run`
## Summary
TL;DR: teaches `codex-rs` / app-server to request a desktop-provided
attestation token and attach it as `x-oai-attestation` on the scoped
ChatGPT Codex request paths.
## Details
This PR teaches the Codex app-server runtime how to request and attach
an attestation token. It does not generate DeviceCheck tokens directly;
instead, it relies on the connected desktop app to advertise that it can
generate attestation and then asks that app for a fresh header value
when needed.
The flow is:
1. The Codex desktop app connects to app-server.
2. During `initialize`, the app can advertise that it supports
`requestAttestation`.
3. Before app-server calls selected ChatGPT Codex endpoints, it sends
the internal server request `attestation/generate` to the app.
4. app-server receives a pre-encoded header value back.
5. app-server forwards that value as `x-oai-attestation` on the scoped
outbound requests.
The code in this repo is mostly protocol and runtime plumbing: it adds
the app-server request/response shape, introduces an attestation
provider in core, wires that provider into Responses / compaction /
realtime setup paths, and covers the intended scoping with tests. The
signed macOS DeviceCheck generation remains owned by the desktop app PR.
## Related PR
- Codex desktop app implementation:
https://github.com/openai/openai/pull/878649
## Validation
<details>
<summary>Tests run</summary>
```sh
cargo test -p codex-app-server-protocol
cargo test -p codex-core attestation --lib
cargo test -p codex-app-server --lib attestation
```
Also ran:
```sh
just fix -p codex-core
just fix -p codex-app-server
just fix -p codex-app-server-protocol
just fmt
just write-app-server-schema
```
</details>
<details>
<summary>E2E DeviceCheck validation</summary>
First validated the signed desktop app boundary directly: launched a
packaged signed `Codex.app`, sent `attestation/generate`, decoded the
returned `v1.` attestation header, and validated the extracted
DeviceCheck token with `personal/jm/verify_devicecheck_token.py` using
bundle ID `com.openai.codex`. Apple returned `status_code: 200` and
`is_ok: true`.
Then ran the fuller app + app-server flow. The packaged `Codex.app`
launched a current-branch app-server via `CODEX_CLI_PATH`, and a local
MITM proxy intercepted outbound `chatgpt.com` traffic. The app-server
requested `attestation/generate` from the real Electron app process, and
the intercepted `/backend-api/codex/responses` traffic included
`x-oai-attestation` on both routes:
```text
GET /backend-api/codex/responses Upgrade: websocket x-oai-attestation: present
POST /backend-api/codex/responses Upgrade: none x-oai-attestation: present
```
The captured header decoded to a DeviceCheck token that also validated
with Apple for `com.openai.codex` (`status_code: 200`, `is_ok: true`,
team `2DC432GLL2`).
</details>
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
Reverts #20689 to restore the previous optional state DB plumbing. The
conflict resolution keeps the newer installation ID and session/thread
identity changes that landed after #20689, while removing the mandatory
state DB and agent graph store dependency from ThreadManager
construction.
## What changed
- Restored `Option<StateDbHandle>` through app-server, MCP server,
prompt debug, and test entry points.
- Removed the `codex-core` dependency on `codex-agent-graph-store` and
reverted descendant lookup back to the existing state DB path when
available.
- Kept newer `installation_id` forwarding by passing it beside the
optional DB handle.
- Kept local thread-name updates working when the optional state DB
handle is absent.
## Validation
- `git diff --check`
- `cargo test -p codex-thread-store`
- `cargo test -p codex-state -p codex-rollout -p
codex-app-server-protocol`
- Attempted `env CARGO_INCREMENTAL=0 cargo test -p codex-core -p
codex-app-server -p codex-app-server-client -p codex-mcp-server -p
codex-thread-manager-sample -p codex-tui`; blocked locally by a rustc
ICE while compiling `v8 v146.4.0` with `rustc 1.93.0 (254b59607
2026-01-19)` on `aarch64-apple-darwin`.
## Why
Skills update notifications are app-server API behavior, but the watcher
lived in `codex-core` and surfaced through
`EventMsg::SkillsUpdateAvailable`. Moving the watcher out keeps core
focused on thread execution and lets app-server own both cache
invalidation and the `skills/changed` notification.
## What changed
- Added an app-server-owned skills watcher that watches local skill
roots, clears the shared skills cache, and emits `skills/changed`
directly.
- Registers skill watches from the common app-server thread listener
attach path, including direct starts, resumes, and app-server-observed
child or forked threads.
- Stores the `WatchRegistration` on `ThreadState`, so listener
replacement, thread teardown, idle unload, and app-server shutdown
deregister by dropping the RAII guard.
- Removed `EventMsg::SkillsUpdateAvailable`, the core watcher, and the
old core live-reload test.
- Extended the app-server skills change test to verify a cached skills
list is refreshed after a filesystem change without forcing reload.
## Validation
- `cargo check -p codex-core -p codex-app-server -p codex-mcp-server -p
codex-rollout -p codex-rollout-trace`
- `cargo test -p codex-app-server
skills_changed_notification_is_emitted_after_skill_change`
## Summary
- resolve or inject the installation ID before core startup and pass it
through `ThreadManager`, `CodexSpawnArgs`, and `Session` as a plain
`String`
- keep child sessions on the parent installation ID instead of
rediscovering it inside core
- propagate installation ID startup failures in `mcp-server` instead of
panicking
## Why
Core was still touching the filesystem on the session startup path to
discover `installation_id`. This moves that work to the outer host
boundary so core no longer depends on `codex_home` reads during session
construction.
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- make `thread_source` an explicit optional thread-level field on
`thread/start`, `thread/fork`, and returned thread payloads
- persist `thread_source` in rollout/session metadata so resumed live
threads retain the original value
- replace the old best-effort `session_source` -> `thread_source`
mapping with an explicit caller-supplied analytics classification
## Why
Before this change, analytics `thread_source` was populated by a
best-effort mapping from `session_source`. `session_source` describes
the runtime/client surface, not the actual thread-level origin, so that
projection was not accurate enough to distinguish cases such as `user`,
`subagent`, `memory_consolidation`, and future thread origins reliably.
Making `thread_source` explicit keeps one thread-level analytics field
while letting callers provide the real classification directly instead
of recovering it indirectly from `session_source`.
## Impact
For new analytics events, `thread_source` now reflects the explicit
thread-level classification supplied by the caller rather than an
inferred value derived from `session_source`. Existing protocol fields
remain optional; callers that omit `threadSource` now produce `null`
instead of a best-effort inferred value.
## Validation
- `just write-app-server-schema`
- `cargo test -p codex-analytics -p codex-core -p
codex-app-server-protocol --no-run`
- `cargo test -p codex-app-server-protocol
generated_ts_optional_nullable_fields_only_in_params`
- `cargo test -p codex-analytics
thread_initialized_event_serializes_expected_shape`
- `cargo test -p codex-core
resume_stopped_thread_from_rollout_preserves_thread_source`
## Why
Thread names are app-server metadata now, backed by the thread store and
sqlite state database. Keeping a core `SetThreadName` op plus a rollout
`thread_name_updated` event made rename persistence live in the wrong
layer and required historical replay support for an event that new
app-server flows should not write.
## What changed
- Removed `Op::SetThreadName` and `EventMsg::ThreadNameUpdated` from the
core protocol and deleted the core handler path that appended rename
events to rollouts.
- Updated app-server `thread/name/set` so both loaded and unloaded
threads write through thread-store metadata and app-server emits
`thread/name/updated` notifications.
- Updated local thread-store name metadata updates to write sqlite title
metadata and the legacy thread-name index without appending rollout
events.
- Removed state extraction and rollout handling for the deleted
thread-name event.
## Validation
- `cargo test -p codex-app-server thread_name_updated_broadcasts`
- `cargo test -p codex-app-server
thread_name_set_is_reflected_in_read_list_and_resume`
- `cargo test -p codex-thread-store
update_thread_metadata_sets_name_on_active_rollout_and_indexes_name`
- `cargo test -p codex-state`
- `cargo check -p codex-mcp-server -p codex-rollout-trace`
- `just fix -p codex-app-server -p codex-thread-store -p codex-state -p
codex-mcp-server -p codex-rollout-trace`
## Docs
No external documentation update is expected for this internal ownership
change.
## Why
We want the agent graph store to be passed down the stack as a real
dependency, the same way we already treat the thread store.
This will let us inject the agent graph store as a real dependency and
support implementations other than the local SQLite-backed one. Right
now most code instantiates a state DB and an agent graph store
just-in-time. Ideally, we would not depend on the state DB directly but
only read through the higher-level interfaces.
This change makes the dependency boundaries explicit and moves state DB
initialization to process bootstrap instead of hiding it inside local
store implementations.
## What changed
- `ThreadManager` now requires a `StateDbHandle` and an
`AgentGraphStore` at construction time instead of treating them as
optional internals.
- The local store constructors no longer lazily initialize SQLite.
Callers now initialize the state DB once per process and use that shared
handle to build:
- `LocalThreadStore`
- `LocalAgentGraphStore`
- App bootstraps (`app-server`, `mcp-server`, `prompt_debug`, and the
thread-manager sample) now initialize the state DB up front and inject
the resulting handle down the stack.
- `app-server` now consistently uses its process-scoped state DB handle
instead of reopening SQLite or trying to recover it from loaded threads.
- Device-key storage now reuses the shared state DB handle instead of
maintaining its own lazy opener.
- The thread archive / descendant traversal paths now use the injected
`AgentGraphStore` instead of reaching through local
thread-store-specific state.
## Verification
- `cargo check -p codex-core -p codex-thread-store -p codex-app-server
-p codex-mcp-server -p codex-thread-manager-sample --tests`
- `cargo test -p codex-thread-store`
- `cargo test -p codex-core
thread_manager_accepts_separate_agent_graph_store_and_thread_store --
--nocapture`
- `cargo test -p codex-app-server
thread_archive_archives_spawned_descendants -- --nocapture`
## Why
This is a prep PR in the multi-environment process-tool stack. It
separates ownership/config cleanup from the behavior change that teaches
process tools to route by selected environment, so the follow-up PR can
focus on model-facing `environment_id` behavior.
## Stack
1. https://github.com/openai/codex/pull/20646 - `EnvironmentContext`
rendering for selected environments
2. https://github.com/openai/codex/pull/20669 - selected-environment
ownership and tool config prep (this PR)
3. https://github.com/openai/codex/pull/20647 - process-tool
`environment_id` routing
## What Changed
- keep the resolved turn environment list wrapped in
`ResolvedTurnEnvironments` through `TurnContext` instead of unwrapping
it back to a raw `Vec`
- add `TurnContext::resolve_path_against` so cwd-relative path
resolution has one shared helper
- replace the old tool config boolean with `ToolEnvironmentMode::{None,
Single, Multiple}`
## Testing
- Tests not run locally; this prep refactor is covered by GitHub CI for
the stack.
Co-authored-by: Codex <noreply@openai.com>
## Summary
- make selected turn environments the source of truth for session
runtime cwd and MCP runtime environment selection
- keep local/no-selection fallback behavior intact
- add coverage for duplicate selected environments, cwd resolution, and
MCP runtime environment selection
## Validation
- git diff --check
- rustfmt was run on touched Rust files during the implementation
workflow
CI should provide the full Bazel/test signal.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
Several legacy `EventMsg` variants were still emitted or mapped even
though clients either ignored them or had moved to item/lifecycle
events. `Op::Undo` had also degraded to an unavailable shim, so this
removes that dead task path instead of preserving a command that cannot
do useful work.
`McpStartupComplete`, `WebSearchBegin`, and `ImageGenerationBegin` are
intentionally kept because useful consumers still depend on them: MCP
startup completion drives readiness behavior, and the begin events let
app-server/core consumers surface in-progress web-search and
image-generation items before the final payload arrives.
## What Changed
- Removed weak legacy event variants and payloads from `codex-protocol`,
including legacy agent deltas, background events, and undo lifecycle
events.
- Kept/restored `EventMsg::McpStartupComplete`,
`EventMsg::WebSearchBegin`, and `EventMsg::ImageGenerationBegin` with
serializer and emission coverage.
- Updated core, rollout, MCP server, app-server thread history,
review/delegate filtering, and tests to rely on the useful replacement
events that remain.
- Removed `Op::Undo`, `UndoTask`, the undo test module, and stale TUI
slash-command comments.
- Stopped agent job/background progress and compaction retry notices
from emitting `BackgroundEvent` payloads.
## Verification
- `cargo check -p codex-protocol -p codex-app-server-protocol -p
codex-core -p codex-rollout -p codex-rollout-trace -p codex-mcp-server`
- `cargo test -p codex-protocol -p codex-app-server-protocol -p
codex-rollout -p codex-rollout-trace -p codex-mcp-server`
- `cargo test -p codex-core --test all suite::items`
- `just fix -p codex-protocol -p codex-app-server-protocol -p codex-core
-p codex-rollout -p codex-rollout-trace -p codex-mcp-server`
- Earlier coverage on this PR also included `codex-mcp`, `codex-tui`,
core library tests, MCP/plugin/delegate/review/agent job tests, and MCP
startup TUI tests.
## Why
`codex-models-manager` had grown to own provider-specific concerns:
constructing OpenAI-compatible `/models` requests, resolving provider
auth, emitting request telemetry, and deciding how provider catalogs
should be sourced. That made the manager harder to reuse for providers
whose model catalog is not fetched from the OpenAI `/models` endpoint,
such as Amazon Bedrock.
This change moves provider-specific model discovery behind
provider-owned implementations, so the models manager can focus on
refresh policy, cache behavior, picker ordering, and model metadata
merging.
## What Changed
- Introduced a `ModelsManager` trait with separate `OpenAiModelsManager`
and `StaticModelsManager` implementations.
- Added `ModelsEndpointClient` so OpenAI-compatible HTTP fetching lives
outside `codex-models-manager`.
- Moved `/models` request construction, provider auth resolution,
timeout handling, and request telemetry into `codex-model-provider` via
`OpenAiModelsEndpoint`.
- Added provider-owned `models_manager(...)` construction so configured
OpenAI-compatible providers use `OpenAiModelsManager`, while
static/catalog-backed providers can return `StaticModelsManager`.
- Added an Amazon Bedrock static model catalog for the GPT OSS Bedrock
model IDs.
- Updated core/session/thread manager code and tests to depend on
`Arc<dyn ModelsManager>`.
- Moved offline model test helpers into
`codex_models_manager::test_support`.
## Metadata References
The Bedrock catalog metadata is based on the official Amazon Bedrock
OpenAI model documentation:
- [Amazon Bedrock OpenAI
models](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-openai.html)
lists the Bedrock model IDs, text input/output modalities, and `128,000`
token context window for `gpt-oss-20b` and `gpt-oss-120b`.
- [Amazon Bedrock `gpt-oss-120b` model
card](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html)
lists the `bedrock-runtime` model ID `openai.gpt-oss-120b-1:0`, the
`bedrock-mantle` model ID `openai.gpt-oss-120b`, text-only modalities,
and `128K` context window.
- [OpenAI `gpt-oss-120b` model
docs](https://developers.openai.com/api/docs/models/gpt-oss-120b)
document configurable reasoning effort with `low`, `medium`, and `high`,
plus text input/output modality.
The display names, default reasoning effort, and priority ordering are
Codex-local catalog choices.
## Test Plan
- Manually verified app-server model listing with an AWS profile:
```shell
CODEX_HOME="$(mktemp -d)" cargo run -p codex-app-server-test-client -- \
--codex-bin ./target/debug/codex \
-c 'model_provider="amazon-bedrock"' \
-c 'model_providers.amazon-bedrock.aws.profile="codex-bedrock"' \
-c 'model_providers.amazon-bedrock.aws.region="us-west-2"' \
model-list
```
The response returned the Bedrock catalog with `openai.gpt-oss-120b-1:0`
as the default model and `openai.gpt-oss-20b-1:0` as the second listed
model, both text-only and supporting low/medium/high reasoning effort.
## Summary
Adds the debug CLI entry point for reducing recorded rollout traces.
This gives developers a direct way to inspect whether the emitted trace
stream reduces into the expected conversation/runtime model.
## Stack
This is PR 5/5 in the rollout trace stack.
- [#18876](https://github.com/openai/codex/pull/18876): Add rollout
trace crate
- [#18877](https://github.com/openai/codex/pull/18877): Record core
session rollout traces
- [#18878](https://github.com/openai/codex/pull/18878): Trace tool and
code-mode boundaries
- [#18879](https://github.com/openai/codex/pull/18879): Trace sessions
and multi-agent edges
- [#18880](https://github.com/openai/codex/pull/18880): Add debug trace
reduction command
## Review Notes
This PR is intentionally last: it depends on the trace crate, core
recorder, runtime/tool events, and session/agent edge data all existing.
The command should remain a debug/developer tool and avoid adding new
runtime behavior.
The useful review question is whether the CLI exposes the reducer in the
smallest practical way for local inspection without turning the debug
command into a supported user-facing workflow.
Addresses #11267
## Summary
`/review` can be interrupted while it is still spawning the review
sub-agent. That spawn path lives in `codex-core` and did not observe the
task cancellation token until after `Codex::spawn` returned, so an
interrupted review could keep building a child session and leave the TUI
in a wedged state.
The TUI exit path also waited indefinitely for app-server
`thread/unsubscribe`, which made Ctrl+C look broken if the app-server
was already stuck. This makes interactive delegate startup
cancellation-aware and bounds the TUI shutdown-first unsubscribe wait
with a short UI escape-hatch timeout.
## Testing
I reproed the hang using the steps in the bug report. Confirmed hang no
longer exists after fix.
Begin migrating the thread write codepaths to ThreadStore.
This starts using ThreadStore inside of core session code, not only in
the app server code.
Rework the interfaces around thread recording/persistence. We're left
with the following:
* `ThreadManager`: owns the process-level registry of loaded threads and
handles cross-thread orchestration: start, resume, fork, lookup, remove,
and route ops to running CodexThreads.
* `CodexThread`: represents one loaded/running thread from the outside.
It is the handle app-server and callers use to submit ops, inspect
session metadata, and shut the thread down.
* `LiveThread`: session-owned persistence lifecycle handle for one
active thread. Core session code uses it to append rollout items,
materialize lazy persistence, flush, shutdown, discard init-failed
writers, and load that thread’s persisted history.
* `ThreadStore`: storage backend abstraction. It answers “how are
threads persisted, read, listed, updated, archived?” Local and remote
implementations live behind this trait.
* `LocalThreadStore`: local ThreadStore implementation. It owns the
file/sqlite-specific details and keeps RolloutRecorder as a local
implementation detail.
This is a few too many Thread abstractions for my liking, but they do
all represent different concepts / needs / layers.
Migration note: in places where the core code explicitly requires a
path, rather than a thread ID, throw an error if we're running with a
remote store.
Cover the new local live-writer lifecycle with focused tests and
preserve app-server thread-start behavior, including ephemeral pathless
sessions.
## Summary
Allow the user to approve a request_permissions_tool request with the
condition that all commands in the rest of the turn are reviewed by
guardian, regardless of sandbox status.
## Testing
- [x] Added unit tests
- [x] Ran locally
## Summary
Wires rollout trace recording into `codex-core` session and turn
execution. This records the core model request/response, compaction, and
session lifecycle boundaries needed for replay without yet tracing every
nested runtime/tool boundary.
## Stack
This is PR 2/5 in the rollout trace stack.
- [#18876](https://github.com/openai/codex/pull/18876): Add rollout
trace crate
- [#18877](https://github.com/openai/codex/pull/18877): Record core
session rollout traces
- [#18878](https://github.com/openai/codex/pull/18878): Trace tool and
code-mode boundaries
- [#18879](https://github.com/openai/codex/pull/18879): Trace sessions
and multi-agent edges
- [#18880](https://github.com/openai/codex/pull/18880): Add debug trace
reduction command
## Review Notes
This layer is the first live integration point. The important review
question is whether trace recording is isolated from normal session
behavior: trace failures should not become user-visible execution
failures, and recording should preserve the existing turn/session
lifecycle semantics.
The PR depends on the reducer/data model from the first stack entry and
only introduces the core recorder surface that later PRs use for richer
runtime and relationship events.
## Why
Guardian approvals now run as review sessions, but Codex analytics did
not have a terminal event for those reviews. That made it hard to
measure approval outcomes, failure modes, Guardian session reuse, model
metadata, token usage, and timing separately from the parent turn.
## What changed
Adds `codex_guardian_review` analytics emission for Guardian approval
reviews. The event is emitted from the Guardian review path with review
identity, target item id, approval request source, a PII-minimized
reviewed-action shape, terminal decision/status, failure reason,
Guardian assessment fields, Guardian session metadata, token usage, and
timing metadata.
The reviewed-action payload intentionally omits high-risk fields such as
shell commands, working directories, argv, file paths, network
targets/hosts, rationale, retry reason, and permission justifications.
It also classifies prompt-build failures separately from Guardian
session/runtime failures so fail-closed cases are distinguishable in
analytics.
## Verification
- Guardian review analytics tests cover terminal success,
timeout/cancel/fail-closed paths, session metadata, and token usage
plumbing.
- `cargo clippy -p codex-core --lib --tests -- -D warnings`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/17693).
* #17696
* #17695
* __->__ #17693
## Summary
- add experimental turn/start.environments params for per-turn
environment id + cwd selections
- pass selections through core protocol ops and resolve them with
EnvironmentManager before TurnContext creation
- treat omitted selections as default behavior, empty selections as no
environment, and non-empty selections as first environment/cwd as the
turn primary
## Testing
- ran `just fmt`
- ran `just write-app-server-schema`
- not run: unit tests for this stacked PR
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
Permission approval responses must not be able to grant more access than
the tool requested. Moving this flow to `PermissionProfile` means the
comparison must be profile-shaped instead of `SandboxPolicy`-shaped, and
cwd-relative special paths such as `:cwd` and `:project_roots` must stay
anchored to the turn that produced the request.
## What changed
This implements semantic `PermissionProfile` intersection in
`codex-sandboxing` for file-system and network permissions. The
intersection accepts narrower path grants, rejects broader grants,
preserves deny-read carve-outs and glob scan depth, and materializes
cwd-dependent special-path grants to absolute paths before they can be
recorded for reuse.
The request-permissions response paths now use that intersection
consistently. App-server captures the request turn cwd before waiting
for the client response, includes that cwd in the v2 approval params,
and core stores the requested profile plus cwd for direct TUI/client
responses and Guardian decisions before recording turn- or
session-scoped grants. The TUI app-server bridge now preserves the
app-server request cwd when converting permission approval params into
core events.
## Verification
- `cargo test -p codex-sandboxing intersect_permission_profiles --
--nocapture`
- `cargo test -p codex-app-server request_permissions_response --
--nocapture`
- `cargo test -p codex-core
request_permissions_response_materializes_session_cwd_grants_before_recording
-- --nocapture`
- `cargo check -p codex-tui --tests`
- `cargo check --tests`
- `cargo test -p codex-tui
app_server_request_permissions_preserves_file_system_permissions`
## Summary
When auto-review is enabled, it should handle request_permissions tool.
We'll need to clean up the UX but I'm planning to do that in a separate
pass
## Testing
- [x] Ran locally
<img width="893" height="396" alt="Screenshot 2026-04-17 at 1 16 13 PM"
src="https://github.com/user-attachments/assets/4c045c5f-1138-4c6c-ac6e-2cb6be4514d8"
/>
---------
Co-authored-by: Codex <noreply@openai.com>
### **Issue**
guardian_parallel_reviews_fork_from_last_committed_trunk_history was
failing on Windows/Bazel with a stack overflow:
`thread
'guardian::tests::guardian_parallel_reviews_fork_from_last_committed_trunk_history'
has overflowed its stack`
- This problem was a stack-headroom problem
### **Solution**
Reduced stack pressure in the guardian async path by boxing thin wrapper
futures, and run the affected test on a dedicated 2 MiB thread stack.
Concretely:
- added Box::pin(...) around thin async wrapper hops in the guardian
review/delegate path
- changed
guardian_parallel_reviews_fork_from_last_committed_trunk_history to run
inside an explicitly sized thread stack so it has enough headroom in
low-stack environments
## Summary
- Add `TimedOut` to Guardian/review carrier types:
- `ReviewDecision::TimedOut`
- `GuardianAssessmentStatus::TimedOut`
- app-server v2 `GuardianApprovalReviewStatus::TimedOut`
- Regenerate app-server JSON/TypeScript schemas for the new wire shape.
- Wire the new status through core/app-server/TUI mappings with
conservative fail-closed handling.
- Keep `TimedOut` non-user-selectable in the approval UI.
**Does not change runtime behavior yet; emitting `TimeOut` and
parent-model timeout messaging will come in followup PRs**
## Description
This PR introduces `review_id` as the stable identifier for guardian
reviews and exposes it in app-server `item/autoApprovalReview/started`
and `item/autoApprovalReview/completed` events.
Internally, guardian rejection state is now keyed by `review_id` instead
of the reviewed tool item ID. `target_item_id` is still included when a
review maps to a concrete thread item, but it is no longer overloaded as
the review lifecycle identifier.
## Motivation
We'd like to give users the ability to preempt a guardian review while
it's running (approve or decline).
However, we can't implement the API that allows the user to override a
running guardian review because we didn't have a unique `review_id` per
guardian review. Using `target_item_id` is not correct since:
- with execve reviews, there can be multiple execve calls (and therefore
guardian reviews) per shell command
- with network policy reviews, there is no target item ID
The PR that actually implements user overrides will use `review_id` as
the stable identifier.
## Summary
This PR adds the parent conversation/session id to the subagent-start
analytics event for Guardian subagents.
Previously, Guardian sessions were emitted as subagent
thread-initialized events, but their `parent_thread_id` was serialized
as `null`. After this change, the `codex_thread_initialized` analytics
event for a Guardian child session includes the parent user conversation
id.
## Summary
App-server v2 already receives turn-scoped `clientMetadata`, but the
Rust app-server was dropping it before the outbound Responses request.
This change keeps the fix lightweight by threading that metadata through
the existing turn-metadata path rather than inventing a new transport.
## What we're trying to do and why
We want turn-scoped metadata from the app-server protocol layer,
especially fields like Hermes/GAAS run IDs, to survive all the way to
the actual Responses API request so it is visible in downstream
websocket request logging and analytics.
The specific bug was:
- app-server protocol uses camelCase `clientMetadata`
- Responses transport already has an existing turn metadata carrier:
`x-codex-turn-metadata`
- websocket transport already rewrites that header into
`request.request_body.client_metadata["x-codex-turn-metadata"]`
- but the Rust app-server never parsed or stored `clientMetadata`, so
nothing from the app-server request was making it into that existing
path
This PR fixes that without adding a new header or a second metadata
channel.
## How we did it
### Protocol surface
- Add optional `clientMetadata` to v2 `TurnStartParams` and
`TurnSteerParams`
- Regenerate the JSON schema / TypeScript fixtures
- Update app-server docs to describe the field and its behavior
### Runtime plumbing
- Add a dedicated core op for app-server user input carrying turn-scoped
metadata: `Op::UserInputWithClientMetadata`
- Wire `turn/start` and `turn/steer` through that op / signature path
instead of dropping the metadata at the message-processor boundary
- Store the metadata in `TurnMetadataState`
### Transport behavior
- Reuse the existing serialized `x-codex-turn-metadata` payload
- Merge the new app-server `clientMetadata` into that JSON additively
- Do **not** replace built-in reserved fields already present in the
turn metadata payload
- Keep websocket behavior unchanged at the outer shape level: it still
sends only `client_metadata["x-codex-turn-metadata"]`, but that JSON
string now contains the merged fields
- Keep HTTP fallback behavior unchanged except that the existing
`x-codex-turn-metadata` header now includes the merged fields too
### Request shape before / after
Before, a websocket `response.create` looked like:
```json
{
"type": "response.create",
"client_metadata": {
"x-codex-turn-metadata": "{\"session_id\":\"...\",\"turn_id\":\"...\"}"
}
}
```
Even if the app-server caller supplied `clientMetadata`, it was not
represented there.
After, the same request shape is preserved, but the serialized payload
now includes the new turn-scoped fields:
```json
{
"type": "response.create",
"client_metadata": {
"x-codex-turn-metadata": "{\"session_id\":\"...\",\"turn_id\":\"...\",\"fiber_run_id\":\"fiber-start-123\",\"origin\":\"gaas\"}"
}
}
```
## Validation
### Targeted tests added / updated
- protocol round-trip coverage for `clientMetadata` on `turn/start` and
`turn/steer`
- protocol round-trip coverage for `Op::UserInputWithClientMetadata`
- `TurnMetadataState` merge test proving client metadata is added
without overwriting reserved built-in fields
- websocket request-shape test proving outbound `response.create`
contains merged metadata inside
`client_metadata["x-codex-turn-metadata"]`
- app-server integration tests proving:
- `turn/start` forwards `clientMetadata` into the outbound Responses
request path
- websocket warmup + real turn request both behave correctly
- `turn/steer` updates the follow-up request metadata
### Commands run
- `just write-app-server-schema`
- `cargo test -p codex-app-server-protocol`
- `cargo test -p codex-protocol`
- `cargo test -p codex-core
turn_metadata_state_merges_client_metadata_without_replacing_reserved_fields
--lib`
- `cargo test -p codex-core --test all
responses_websocket_preserves_custom_turn_metadata_fields`
- `cargo test -p codex-app-server --test all client_metadata`
- `cargo test -p codex-app-server --test all
turn_start_forwards_client_metadata_to_responses_websocket_request_body_v2
-- --nocapture`
- `just fmt`
- `just fix -p codex-core -p codex-protocol -p codex-app-server-protocol
-p codex-app-server`
- `just fix -p codex-exec -p codex-tui-app-server`
- `just argument-comment-lint`
### Full suite note
`cargo test` in `codex-rs` still fails in:
-
`suite::v2::turn_interrupt::turn_interrupt_resolves_pending_command_approval_request`
I verified that same failure on a clean detached `HEAD` worktree with an
isolated `CARGO_TARGET_DIR`, so it is not caused by this patch.
## Summary
- make `CODEX_EXEC_SERVER_URL=none` map to an explicit disabled
environment mode instead of inferring from a missing URL
- expose environment capabilities (`exec_enabled`, `filesystem_enabled`)
so tool building can gate behavior explicitly and future
multi-environment work has a clearer seam
- suppress env-backed tools when the relevant capability is unavailable,
including exec tools, `js_repl`, `apply_patch`, `list_dir`, and
`view_image`
- keep handler/runtime backstops so disabled environments still reject
execution if a tool path somehow bypasses registration
## Testing
- `just fmt`
- `cargo test -p codex-exec-server`
- `cargo test -p codex-tools
disabled_environment_omits_environment_backed_tools`
- `cargo test -p codex-tools
environment_capabilities_gate_exec_and_filesystem_tools_independently`
- remote devbox Bazel build via `codex-applied-devbox`:
`//codex-rs/cli:cli`
Stacked on #16508.
This removes the temporary `codex-core` / `codex-login` re-export shims
from the ownership split and rewrites callsites to import directly from
`codex-model-provider-info`, `codex-models-manager`, `codex-api`,
`codex-protocol`, `codex-feedback`, and `codex-response-debug-context`.
No behavior change intended; this is the mechanical import cleanup layer
split out from the ownership move.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
`codex-core` was re-exporting APIs owned by sibling `codex-*` crates,
which made downstream crates depend on `codex-core` as a proxy module
instead of the actual owner crate.
Removing those forwards makes crate boundaries explicit and lets leaf
crates drop unnecessary `codex-core` dependencies. In this PR, this
reduces the dependency on `codex-core` to `codex-login` in the following
files:
```
codex-rs/backend-client/Cargo.toml
codex-rs/mcp-server/tests/common/Cargo.toml
```
## What
- Remove `codex-rs/core/src/lib.rs` re-exports for symbols owned by
`codex-login`, `codex-mcp`, `codex-rollout`, `codex-analytics`,
`codex-protocol`, `codex-shell-command`, `codex-sandboxing`,
`codex-tools`, and `codex-utils-path`.
- Delete the `default_client` forwarding shim in `codex-rs/core`.
- Update in-crate and downstream callsites to import directly from the
owning `codex-*` crate.
- Add direct Cargo dependencies where callsites now target the owner
crate, and remove `codex-core` from `codex-rs/backend-client`.
## Description
Previously the `action` field on `EventMsg::GuardianAssessment`, which
describes what Guardian is reviewing, was typed as an arbitrary JSON
blob. This PR cleans it up and defines a sum type representing all the
various actions that Guardian can review.
This is a breaking change (on purpose), which is fine because:
- the Codex app / VSCE does not actually use `action` at the moment
- the TUI code that consumes `action` is updated in this PR as well
- rollout files that serialized old `EventMsg::GuardianAssessment` will
just silently drop these guardian events
- the contract is defined as unstable, so other clients have a fair
warning :)
This will make things much easier for followup Guardian work.
## Why
The old guardian review payloads worked, but they pushed too much shape
knowledge into downstream consumers. The TUI had custom JSON parsing
logic for commands, patches, network requests, and MCP calls, and the
app-server protocol was effectively just passing through an opaque blob.
Typing this at the protocol boundary makes the contract clearer.
## Why
This is effectively a follow-up to
[#15812](https://github.com/openai/codex/pull/15812). That change
removed the special skill-script exec path, but `skill_metadata` was
still being threaded through command-approval payloads even though the
approval flow no longer uses it to render prompts or resolve decisions.
Keeping it around added extra protocol, schema, and client surface area
without changing behavior.
Removing it keeps the command-approval contract smaller and avoids
carrying a dead field through app-server, TUI, and MCP boundaries.
## What changed
- removed `ExecApprovalRequestSkillMetadata` and the corresponding
`skillMetadata` field from core approval events and the v2 app-server
protocol
- removed the generated JSON and TypeScript schema output for that field
- updated app-server, MCP server, TUI, and TUI app-server approval
plumbing to stop forwarding the field
- cleaned up tests that previously constructed or asserted
`skillMetadata`
## Testing
- `cargo test -p codex-app-server-protocol`
- `cargo test -p codex-protocol`
- `cargo test -p codex-app-server-test-client`
- `cargo test -p codex-mcp-server`
- `just argument-comment-lint`
Add environment manager that is a singleton and is created early in
app-server (before skill manager, before config loading).
Use an environment variable to point to a running exec server.
Migrate `cwd` and related session/config state to `AbsolutePathBuf` so
downstream consumers consistently see absolute working directories.
Add test-only `.abs()` helpers for `Path`, `PathBuf`, and `TempDir`, and
update branch-local tests to use them instead of
`AbsolutePathBuf::try_from(...)`.
For the remaining TUI/app-server snapshot coverage that renders absolute
cwd values, keep the snapshots unchanged and skip the Windows-only cases
where the platform-specific absolute path layout differs.
### Summary
Make `FileWatcher` a reusable core component which can be built upon.
Extract skills-related logic into a separate `SkillWatcher`.
Introduce a composable `ThrottledWatchReceiver` to throttle filesystem
events, coalescing affected paths among them.
### Testing
Updated existing unit tests.
## Summary
If a subagent requests approval, and the user persists that approval to
the execpolicy, it should (by default) propagate. We'll need to rethink
this a bit in light of coming Permissions changes, though I think this
is closer to the end state that we'd want, which is that execpolicy
changes to one permissions profile should be synced across threads.
## Testing
- [x] Added integration test
---------
Co-authored-by: Codex <noreply@openai.com>
## What is flaky
The Windows shell-driven integration tests in `codex-rs/core` were
intermittently unstable, especially:
- `apply_patch_cli_can_use_shell_command_output_as_patch_input`
- `websocket_test_codex_shell_chain`
- `websocket_v2_test_codex_shell_chain`
## Why it was flaky
These tests were exercising real shell-tool flows through whichever
shell Codex selected on Windows, and the `apply_patch` test also nested
a PowerShell read inside `cmd /c`.
There were multiple independent sources of nondeterminism in that setup:
- The test harness depended on the model-selected Windows shell instead
of pinning the shell it actually meant to exercise.
- `cmd.exe /c powershell.exe -Command "..."` is quoting-sensitive; on CI
that could leave the read command wrapped as a literal string instead of
executing it.
- Even after getting the quoting right, PowerShell could emit CLIXML
progress records like module-initialization output onto stdout.
- The `apply_patch` test was building a patch directly from shell
stdout, so any quoting artifact or progress noise corrupted the patch
input.
So the failures were driven by shell startup and output-shape variance,
not by the `apply_patch` or websocket logic themselves.
## How this PR fixes it
- Add a test-only `user_shell_override` path so Windows integration
tests can pin `cmd.exe` explicitly.
- Use that override in the websocket shell-chain tests and in the
`apply_patch` harness.
- Change the nested Windows file read in
`apply_patch_cli_can_use_shell_command_output_as_patch_input` to a UTF-8
PowerShell `-EncodedCommand` script.
- Run that nested PowerShell process with `-NonInteractive`, set
`$ProgressPreference = 'SilentlyContinue'`, and read the file with
`[System.IO.File]::ReadAllText(...)`.
## Why this fix fixes the flakiness
The outer harness now runs under a deterministic shell, and the inner
PowerShell read no longer depends on fragile `cmd` quoting or on
progress output staying quiet by accident. The shell tool returns only
the file contents, so patch construction and websocket assertions depend
on stable test inputs instead of on runner-specific shell behavior.
---------
Co-authored-by: Ahmed Ibrahim <219906144+aibrahim-oai@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
## Why
Once the repo-local lint exists, `codex-rs` needs to follow the
checked-in convention and CI needs to keep it from drifting. This commit
applies the fallback `/*param*/` style consistently across existing
positional literal call sites without changing those APIs.
The longer-term preference is still to avoid APIs that require comments
by choosing clearer parameter types and call shapes. This PR is
intentionally the mechanical follow-through for the places where the
existing signatures stay in place.
After rebasing onto newer `main`, the rollout also had to cover newly
introduced `tui_app_server` call sites. That made it clear the first cut
of the CI job was too expensive for the common path: it was spending
almost as much time installing `cargo-dylint` and re-testing the lint
crate as a representative test job spends running product tests. The CI
update keeps the full workspace enforcement but trims that extra
overhead from ordinary `codex-rs` PRs.
## What changed
- keep a dedicated `argument_comment_lint` job in `rust-ci`
- mechanically annotate remaining opaque positional literals across
`codex-rs` with exact `/*param*/` comments, including the rebased
`tui_app_server` call sites that now fall under the lint
- keep the checked-in style aligned with the lint policy by using
`/*param*/` and leaving string and char literals uncommented
- cache `cargo-dylint`, `dylint-link`, and the relevant Cargo
registry/git metadata in the lint job
- split changed-path detection so the lint crate's own `cargo test` step
runs only when `tools/argument-comment-lint/*` or `rust-ci.yml` changes
- continue to run the repo wrapper over the `codex-rs` workspace, so
product-code enforcement is unchanged
Most of the code changes in this commit are intentionally mechanical
comment rewrites or insertions driven by the lint itself.
## Verification
- `./tools/argument-comment-lint/run.sh --workspace`
- `cargo test -p codex-tui-app-server -p codex-tui`
- parsed `.github/workflows/rust-ci.yml` locally with PyYAML
---
* -> #14652
* #14651
## Summary
- add `approvals_reviewer = "user" | "guardian_subagent"` as the runtime
control for who reviews approval requests
- route Smart Approvals guardian review through core for command
execution, file changes, managed-network approvals, MCP approvals, and
delegated/subagent approval flows
- expose guardian review in app-server with temporary unstable
`item/autoApprovalReview/{started,completed}` notifications carrying
`targetItemId`, `review`, and `action`
- update the TUI so Smart Approvals can be enabled from `/experimental`,
aligned with the matching `/approvals` mode, and surfaced clearly while
reviews are pending or resolved
## Runtime model
This PR does not introduce a new `approval_policy`.
Instead:
- `approval_policy` still controls when approval is needed
- `approvals_reviewer` controls who reviewable approval requests are
routed to:
- `user`
- `guardian_subagent`
`guardian_subagent` is a carefully prompted reviewer subagent that
gathers relevant context and applies a risk-based decision framework
before approving or denying the request.
The `smart_approvals` feature flag is a rollout/UI gate. Core runtime
behavior keys off `approvals_reviewer`.
When Smart Approvals is enabled from the TUI, it also switches the
current `/approvals` settings to the matching Smart Approvals mode so
users immediately see guardian review in the active thread:
- `approval_policy = on-request`
- `approvals_reviewer = guardian_subagent`
- `sandbox_mode = workspace-write`
Users can still change `/approvals` afterward.
Config-load behavior stays intentionally narrow:
- plain `smart_approvals = true` in `config.toml` remains just the
rollout/UI gate and does not auto-set `approvals_reviewer`
- the deprecated `guardian_approval = true` alias migration does
backfill `approvals_reviewer = "guardian_subagent"` in the same scope
when that reviewer is not already configured there, so old configs
preserve their original guardian-enabled behavior
ARC remains a separate safety check. For MCP tool approvals, ARC
escalations now flow into the configured reviewer instead of always
bypassing guardian and forcing manual review.
## Config stability
The runtime reviewer override is stable, but the config-backed
app-server protocol shape is still settling.
- `thread/start`, `thread/resume`, and `turn/start` keep stable
`approvalsReviewer` overrides
- the config-backed `approvals_reviewer` exposure returned via
`config/read` (including profile-level config) is now marked
`[UNSTABLE]` / experimental in the app-server protocol until we are more
confident in that config surface
## App-server surface
This PR intentionally keeps the guardian app-server shape narrow and
temporary.
It adds generic unstable lifecycle notifications:
- `item/autoApprovalReview/started`
- `item/autoApprovalReview/completed`
with payloads of the form:
- `{ threadId, turnId, targetItemId, review, action? }`
`review` is currently:
- `{ status, riskScore?, riskLevel?, rationale? }`
- where `status` is one of `inProgress`, `approved`, `denied`, or
`aborted`
`action` carries the guardian action summary payload from core when
available. This lets clients render temporary standalone pending-review
UI, including parallel reviews, even when the underlying tool item has
not been emitted yet.
These notifications are explicitly documented as `[UNSTABLE]` and
expected to change soon.
This PR does **not** persist guardian review state onto `thread/read`
tool items. The intended follow-up is to attach guardian review state to
the reviewed tool item lifecycle instead, which would improve
consistency with manual approvals and allow thread history / reconnect
flows to replay guardian review state directly.
## TUI behavior
- `/experimental` exposes the rollout gate as `Smart Approvals`
- enabling it in the TUI enables the feature and switches the current
session to the matching Smart Approvals `/approvals` mode
- disabling it in the TUI clears the persisted `approvals_reviewer`
override when appropriate and returns the session to default manual
review when the effective reviewer changes
- `/approvals` still exposes the reviewer choice directly
- the TUI renders:
- pending guardian review state in the live status footer, including
parallel review aggregation
- resolved approval/denial state in history
## Scope notes
This PR includes the supporting core/runtime work needed to make Smart
Approvals usable end-to-end:
- shell / unified-exec / apply_patch / managed-network / MCP guardian
review
- delegated/subagent approval routing into guardian review
- guardian review risk metadata and action summaries for app-server/TUI
- config/profile/TUI handling for `smart_approvals`, `guardian_approval`
alias migration, and `approvals_reviewer`
- a small internal cleanup of delegated approval forwarding to dedupe
fallback paths and simplify guardian-vs-parent approval waiting (no
intended behavior change)
Out of scope for this PR:
- redesigning the existing manual approval protocol shapes
- persisting guardian review state onto app-server `ThreadItem`s
- delegated MCP elicitation auto-review (the current delegated MCP
guardian shim only covers the legacy `RequestUserInput` path)
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
PR #13783 moved the `codex.rs` unit tests into `codex_tests.rs`. This
applies the same extraction pattern across the rest of `codex-rs/core`
so the production modules stay focused on runtime code instead of large
inline test blocks.
Keeping the tests in sibling files also makes follow-up edits easier to
review because product changes no longer have to share a file with
hundreds or thousands of lines of test scaffolding.
## What changed
- replaced each inline `mod tests { ... }` in `codex-rs/core/src/**`
with a path-based module declaration
- moved each extracted unit test module into a sibling `*_tests.rs`
file, using `mod_tests.rs` for `mod.rs` modules
- preserved the existing `cfg(...)` guards and module-local structure so
the refactor remains structural rather than behavioral
## Testing
- `cargo test -p codex-core --lib` (`1653 passed; 0 failed; 5 ignored`)
- `just fix -p codex-core`
- `cargo fmt --check`
- `cargo shear`
## Summary
This PR keeps app-server RPC request trace context alive for the full
lifetime of the work that request kicks off (e.g. for `thread/start`,
this is `app-server rpc handler -> tokio background task -> core op
submissions`). Previously we lose trace lineage once the request handler
returns or hands work off to background tasks.
This approach is especially relevant for `thread/start` and other RPC
handlers that run in a non-blocking way. In the near future we'll most
likely want to make all app-server handlers run in a non-blocking way by
default, and only queue operations that must operate in order (e.g.
thread RPCs per thread?), so we want to make sure tracing in app-server
just generally works.
Depends on https://github.com/openai/codex/pull/14300
**Before**
<img width="155" height="207" alt="image"
src="https://github.com/user-attachments/assets/c9487459-36f1-436c-beb7-fafeb40737af"
/>
**After**
<img width="299" height="337" alt="image"
src="https://github.com/user-attachments/assets/727392b2-d072-4427-9dc4-0502d8652dea"
/>
## What changed
- Keep request-scoped trace context around until we send the final
response or error, or the connection closes.
- Thread that trace context through detached `thread/start` work so
background startup stays attached to the originating request.
- Pass request trace context through to downstream core operations,
including:
- thread creation
- resume/fork flows
- turn submission
- review
- interrupt
- realtime conversation operations
- Add tracing tests that verify:
- remote W3C trace context is preserved for `thread/start`
- remote W3C trace context is preserved for `turn/start`
- downstream core spans stay under the originating request span
- request-scoped tracing state is cleaned up correctly
- Clean up shutdown behavior so detached background tasks and spawned
threads are drained before process exit.
