### Purpose
While trying to build out CLI-Tools for the agent to use under skills we
have found that those tools sometimes need to invoke a user elicitation.
These elicitations are handled out of band of the codex app-server but
need to indicate to the exec manager that the command running is not
going to progress on the usual timeout horizon.
### Example
Model calls universal exec:
`$ download-credit-card-history --start-date 2026-01-19 --end-date
2026-02-19 > credit_history.jsonl`
download-cred-card-history might hit a hosted/preauthenticated service
to fetch data. That service might decide that the request requires an
end user approval the access to the personal data. It should be able to
signal to the running thread that the command in question is blocked on
user elicitation. In that case we want the exec to continue, but the
timeout to not expire on the tool call, essentially freezing time until
the user approves or rejects the command at which point the tool would
signal the app-server to decrement the outstanding elicitation count.
Now timeouts would proceed as normal.
### What's Added
- New v2 RPC methods:
- thread/increment_elicitation
- thread/decrement_elicitation
- Protocol updates in:
- codex-rs/app-server-protocol/src/protocol/common.rs
- codex-rs/app-server-protocol/src/protocol/v2.rs
- App-server handlers wired in:
- codex-rs/app-server/src/codex_message_processor.rs
### Behavior
- Counter starts at 0 per thread.
- increment atomically increases the counter.
- decrement atomically decreases the counter; decrement at 0 returns
invalid request.
- Transition rules:
- 0 -> 1: broadcast pause state, pausing all active stopwatches
immediately.
- \>0 -> >0: remain paused.
- 1 -> 0: broadcast unpause state, resuming stopwatches.
- Core thread/session logic:
- codex-rs/core/src/codex_thread.rs
- codex-rs/core/src/codex.rs
- codex-rs/core/src/mcp_connection_manager.rs
### Exec-server stopwatch integration
- Added centralized stopwatch tracking/controller:
- codex-rs/exec-server/src/posix/stopwatch_controller.rs
- Hooked pause/unpause broadcast handling + stopwatch registration:
- codex-rs/exec-server/src/posix/mcp.rs
- codex-rs/exec-server/src/posix/stopwatch.rs
- codex-rs/exec-server/src/posix.rs
Summary
- relocate truncation logic for exec command output into the new
`ExecCommandToolOutput` response helper instead of centralized handler
code
- update all affected tools and unified exec handling to use the new
response item structure and eliminate `Function(FunctionToolOutput)`
responses
- adjust context, registry, and handler interfaces to align with the new
response semantics and error fields
Testing
- Not run (not requested)
**Summary**
- allow `code_mode` to pass enabled tools metadata to the runner and
expose them via `tools.js`
- import tools inside JavaScript rather than relying only on globals or
proxies for nested tool calls
- update specs, docs, and tests to exercise the new bridge and explain
the tooling changes
**Testing**
- Not run (not requested)
(Experimental)
This PR adds a first MVP for hooks, with SessionStart and Stop
The core design is:
- hooks live in a dedicated engine under codex-rs/hooks
- each hook type has its own event-specific file
- hook execution is synchronous and blocks normal turn progression while
running
- matching hooks run in parallel, then their results are aggregated into
a normalized HookRunSummary
On the AppServer side, hooks are exposed as operational metadata rather
than transcript-native items:
- new live notifications: hook/started, hook/completed
- persisted/replayed hook results live on Turn.hookRuns
- we intentionally did not add hook-specific ThreadItem variants
Hooks messages are not persisted, they remain ephemeral. The context
changes they add are (they get appended to the user's prompt)
#### What
###### Context + Problem
With the introduction of plugins, we now have one more type of
`$`-mentionable item in the TUI's popup menu on `$`. Apps, skills, and
plugins can all have the same user-facing name, and we attempt to
distinguish with a category tag suffix, like `[App]`. This has a few
problems:
- We decide to show tags by the text that will be inserted into the
conversation, not the actual user-visible text, so two visibly-identical
entries can have no clarifying category tag suffix
- The category tag is a suffix and commonly gets cut off by long
descriptions
- The skill category tag is currently only displayed on repo skills as
`[Repo]`, which is confusing to most users
- The plugin category tag is currently `[<marketplace-name>]`, which is
also confusing to most users
###### Solution
- **Always** show a **prefix** category tag that is `[Skill]`, `[App]`,
or `[Plugin]`. No conditional rendering or copy.
Before:
<img width="801" height="153" alt="image"
src="https://github.com/user-attachments/assets/448e06e7-2af8-4c14-9804-ed1ca17cf514"
/>
After:
<img width="800" height="118" alt="image"
src="https://github.com/user-attachments/assets/57895b41-06fe-4d92-887b-68704c5a15fd"
/>
I also feel this clarifies the results at-a-glance while you scroll:
https://github.com/user-attachments/assets/cbdd5840-53d9-4656-812c-6e816755e1fd
### Tests
Added + updated tests (including snapshots), tested locally
## Summary
- preserve unknown `:special_path` tokens, including nested entries, so
older Codex builds warn and ignore instead of failing config load
- fail closed with a startup warning when a permissions profile has
missing or empty filesystem entries instead of aborting profile
compilation
- normalize Windows verbatim paths like `\?\C:\...` before absolute-path
validation while keeping explicit errors for truly invalid paths
## Testing
- just fmt
- cargo test -p codex-core permissions_profiles_allow
- cargo test -p codex-core
normalize_absolute_path_for_platform_simplifies_windows_verbatim_paths
- cargo test -p codex-protocol
unknown_special_paths_are_ignored_by_legacy_bridge
- cargo clippy -p codex-core -p codex-protocol --all-targets -- -D
warnings
- cargo clean
## Summary
This is a fast follow to the initial `[permissions]` structure.
- keep the new split-policy carveout behavior for narrower non-write
entries under broader writable roots
- preserve legacy `WorkspaceWrite` semantics by using a cwd-aware bridge
that drops only redundant nested readable roots when projecting from
`SandboxPolicy`
- route the legacy macOS seatbelt adapter through that same legacy
bridge so redundant nested readable roots do not become read-only
carveouts on macOS
- derive the legacy bridge for `command_exec` using the sandbox root cwd
rather than the request cwd so policy derivation matches later sandbox
enforcement
- add regression coverage for the legacy macOS nested-readable-root case
## Examples
### Legacy `workspace-write` on macOS
A legacy `workspace-write` policy can redundantly list a nested readable
root under an already-writable workspace root.
For example, legacy config can effectively mean:
- workspace root (`.` / `cwd`) is writable
- `docs/` is also listed in `readable_roots`
The new shared split-policy helper intentionally treats a narrower
non-write entry under a broader writable root as a carveout for real
`[permissions]` configs. Without this fast follow, the unchanged macOS
seatbelt legacy adapter could project that legacy shape into a
`FileSystemSandboxPolicy` that treated `docs/` like a read-only carveout
under the writable workspace root. In practice, legacy callers on macOS
could unexpectedly lose write access inside `docs/`, even though that
path was writable before the `[permissions]` migration work.
This change fixes that by routing the legacy seatbelt path through the
cwd-aware legacy bridge, so:
- legacy `workspace-write` keeps `docs/` writable when `docs/` was only
a redundant readable root
- explicit `[permissions]` entries like `'.' = 'write'` and `'docs' =
'read'` still make `docs/` read-only, which is the new intended
split-policy behavior
### Legacy `command_exec` with a subdirectory cwd
`command_exec` can run a command from a request cwd that is narrower
than the sandbox root cwd.
For example:
- sandbox root cwd is `/repo`
- request cwd is `/repo/subdir`
- legacy policy is still `workspace-write` rooted at `/repo`
Before this fast follow, `command_exec` derived the legacy bridge using
the request cwd, but the sandbox was later built using the sandbox root
cwd. That mismatch could miss redundant legacy readable roots during
projection and accidentally reintroduce read-only carveouts for paths
that should still be writable under the legacy model.
This change fixes that by deriving the legacy bridge with the same
sandbox root cwd that sandbox enforcement later uses.
## Verification
- `just fmt`
- `cargo test -p codex-core
seatbelt_legacy_workspace_write_nested_readable_root_stays_writable`
- `cargo test -p codex-core test_sandbox_config_parsing`
- `cargo clippy -p codex-core -p codex-app-server --all-targets -- -D
warnings`
- `cargo clean`
## Summary
We need to support allowing request_permissions calls when using
`Reject` policy
<img width="1133" height="588" alt="Screenshot 2026-03-09 at 12 06
40 PM"
src="https://github.com/user-attachments/assets/a8df987f-c225-4866-b8ab-5590960daec5"
/>
Note that this is a backwards-incompatible change for Reject policy. I'm
not sure if we need to add a default based on our current use/setup
## Testing
- [x] Added tests
- [x] Tested locally
## Summary
The apply_patch tool should also respect AdditionalPermissions
## Testing
- [x] Added unit tests
---------
Co-authored-by: Codex <noreply@openai.com>
Healthcheck endpoints for the websocket server
- serve `GET /readyz` and `GET /healthz` from the same listener used for
`--listen ws://...`
- switch the websocket listener over to `axum` upgrade handling instead
of manual socket parsing
- add websocket transport coverage for the health endpoints and document
the new behavior
Testing
- integration tests
- built and tested e2e
```
> curl -i http://127.0.0.1:9234/readyz
HTTP/1.1 200 OK
content-length: 0
date: Fri, 06 Mar 2026 19:20:23 GMT
> curl -i http://127.0.0.1:9234/healthz
HTTP/1.1 200 OK
content-length: 0
date: Fri, 06 Mar 2026 19:20:24 GMT
```
This changes the web_search tool spec in codex-core to use dedicated
Responses-API payload structs instead of shared config types and custom
serializers.
Previously, `ToolSpec::WebSearch` stored `WebSearchFilters` and
`WebSearchUserLocation` directly and relied on hand-written serializers
to shape the outgoing JSON. This worked, but it mixed config/schema
types with the OpenAI Responses payload contract and created an easy
place for drift if those shared types changed later.
### Why
This keeps the boundary clearer:
- app-server/config/schema types stay focused on config
- Responses tool payload types stay focused on the OpenAI wire format
It also makes the serialization behavior obvious from the structs
themselves, instead of hiding it in custom serializer functions.
## Summary
request_permissions flows should support persisting results for the
session.
Open Question: Still deciding if we need within-turn approvals - this
adds complexity but I could see it being useful
## Testing
- [x] Updated unit tests
---------
Co-authored-by: Codex <noreply@openai.com>
## What changed
- TypeScript schema fixture generation now goes through in-memory tree
helpers rather than a heavier on-disk generation path.
- The comparison logic normalizes generated banner and path differences
that are not semantically relevant to the exported schema.
- TypeScript and JSON fixture coverage are split into separate tests,
and the expensive schema-export tests are serialized in `nextest`.
## Why this fixes the flake
- The original fixture coverage mixed several heavy codegen paths into
one monolithic test and then compared generated output that included
incidental banner/path differences.
- On Windows CI, that combination created both runtime pressure and
output variance unrelated to the schema shapes we actually care about.
- Splitting the coverage isolates failures by format, in-memory
generation reduces filesystem churn, normalization strips generator
noise, and serializing the heavy tests removes parallel resource
contention.
## Scope
- Production helper change plus test changes.
## What changed
- The RMCP streamable HTTP tests now wait for metadata and tool
readiness before issuing tool calls.
- OAuth state is isolated per test home.
- The helper server startup path now uses bounded bind retries so
transient `AddrInUse` collisions do not fail the test immediately.
## Why this fixes the flake
- The old tests could begin issuing tool requests before the helper
server had finished advertising its metadata and tools, so the first
request sometimes raced the server startup sequence.
- On top of that, shared OAuth state and occasional bind collisions on
CI runners introduced cross-test environmental noise unrelated to the
functionality under test.
- Readiness polling makes the client wait for an observable “server is
ready” signal, while isolated state and bounded bind retries remove
external contention that was causing intermittent failures.
## Scope
- Test-only change.
This cleans up a bunch of metric plumbing that had started to drift.
The main change is making `codex-otel` the canonical home for shared
metric definitions and metric tag helpers. I moved the `turn/thread`
metric names that were still duplicated into the OTEL metric registry,
added a shared `metrics::tags` module for common tag keys and session
tag construction, and updated `SessionTelemetry` to build its metadata
tags through that shared path.
On the codex-core side, TTFT/TTFM now use the shared metric-name
constants instead of local string definitions. I also switched the
obvious remaining turn/thread metric callsites over to the shared
constants, and added a small helper so TTFT/TTFM can attach an optional
sanitized client.name tag from TurnContext.
This should make follow-on telemetry work less ad hoc:
- one canonical place for metric names
- one canonical place for common metric tag keys/builders
- less duplication between `codex-core` and `codex-otel`
add `plugin/uninstall` app-server endpoint to fully rm plugin from
plugins cache dir and rm entry from user config file.
plugin-enablement is session-scoped, so uninstalls are only picked up in
new sessions (like installs).
added tests.
## Summary
Alternative to #14061 - we need to use a child process on windows to
correctly validate Powershell behavior.
## Testing
- [x] These are tests
## What changed
- add a bounded `resume_until_initial_messages` helper in
`core/tests/suite/resume.rs`
- retry the resume call until `initial_messages` contains the fully
persisted final turn shape before asserting
## Why this fixes flakiness
The old test resumed once immediately after `TurnComplete` and sometimes
read rollout state before the final turn had been persisted. That made
the assertion race persistence timing instead of checking the resumed
message shape. The new helper polls for up to two seconds in 10ms steps
and only asserts once the expected message sequence is actually present,
so the test waits for the real readiness condition instead of depending
on a lucky timing window.
## Scope
- test-only
- no production logic change
## Summary
- align the guardian permission test with the actual sandbox policy it
widens and use a slightly larger Windows-only timeout budget
- expose the additional-permissions normalization helper to the guardian
test module
- replace the guardian popup snapshot assertion with targeted string
assertions
## Why this fixes the flake
This group was carrying two separate sources of drift. The guardian core
test widened derived sandbox policies without updating the source
sandbox policy, and it used a Windows command/timeout combination that
was too tight on slower runners. Separately, the TUI test was
snapshotting the full popup even though unrelated feature text changes
were the only thing moving. The new assertions keep coverage on the
guardian entry itself while removing unrelated snapshot churn.
## Summary
- drain the active turn tasks before clearing pending approvals during
interruption
- keep the turn in hand long enough for interrupted tasks to observe
cancellation first
## Why this fixes the flake
Interrupted turns could clear pending approvals too early, which let an
in-flight approval wait surface as a model-visible rejection before the
turn emitted `TurnAborted`. Reordering the cleanup removes that race
without changing the steady-state task model.
## Summary
- replace the Python-based file creation command in the MCP shell
approval test with native platform commands
- build the expected command string from the exact argv that the test
sends
## Why this fixes the flake
The old test depended on Python startup and shell quoting details that
varied across runners. The new version still verifies the same approval
flow, but it uses `touch` on Unix and `New-Item` on Windows so the
assertion only depends on the MCP shell command that Codex actually
forwards.
Handle cloud requirements 401s with the same auth recovery flow as
normal requests, so permanent refresh failures surface the existing
user-facing auth message instead of a generic workspace-config load
error.
## What changed
- The realtime startup-context tests no longer assume the interesting
websocket payload is always `connection 1 / request 0`.
- Instead, they now wait for the first outbound websocket request that
actually carries `session.instructions`, regardless of which websocket
connection won the accept-order race on the runner.
- The env-key fallback test stays serialized because it mutates process
environment.
## Why this fixes the flake
- The old test synchronized on the mirrored `session.updated` client
event and then inspected a fixed websocket slot.
- On CI, the response websocket and the realtime websocket can race each
other during startup. When the response websocket wins that race, the
fixed slot can contain `response.create` instead of the
startup-context-bearing `session.update` request the test actually cares
about.
- That made the test fail nondeterministically by inspecting the wrong
request, or by timing out waiting on a secondary event even though the
real outbound request path was correct.
- Waiting directly on the first request whose payload includes
`session.instructions` removes both ordering assumptions and makes the
assertion line up with the actual contract under test.
- Separately, serializing the environment-mutating fallback case
prevents unrelated tests from seeing partially updated auth state.
## Scope
- Test-only change.
## What changed
- `snapshot_shell_does_not_inherit_stdin` now runs under its own serial
key.
- The change isolates it from other Unix shell-snapshot tests that also
interact with stdin.
## Why this fixes the flake
- The failure was not a shell-snapshot logic bug. It was shared-stdin
interference between concurrently executing tests.
- When multiple tests compete for inherited stdin at the same time, one
test can observe EOF or consumed input that actually belongs to a
different test.
- Running this specific test in a dedicated serial bucket guarantees
exclusive ownership of stdin, which makes the assertion deterministic
without weakening coverage.
## Scope
- Test-only change.
## What changed
- The thread-resume replay tests now use unchecked mock sequencing so
the replay flow can complete before the test asserts.
- They also poll outbound `/responses` request counts and fail
immediately if replay emits an unexpected extra request.
## Why this fixes the flake
- The previous version asserted while the replay machinery was still
mid-flight, so the test was sometimes checking an intermediate state
instead of the completed behavior.
- Strict mock sequencing made that problem worse by forcing the test to
care about exact sub-step timing rather than about the end result.
- Letting replay settle and then asserting on stabilized request counts
makes the test validate the real contract: the replay path finishes and
does not send extra model requests.
## Scope
- Test-only change.
## What changed
- `app-server` now sends initialize notifications to the specific
websocket connection before that connection is marked outbound-ready.
- `message_processor` now exposes the forwarding hook needed to target
that initialize delivery path.
## Why this fixes the flake
- This was a real websocket ordering bug.
- The old code allowed “connection is ready for outbound broadcasts” to
become true before the initialize notification had been routed to the
intended client.
- On CI this showed up as a race where tests would occasionally miss or
misorder initialize delivery depending on scheduler timing.
- Sending initialize to the exact connection first, then exposing it to
the general outbound path, removes that race instead of hiding it with
timing slack.
## Scope
- Production logic change.
## What changed
- run the two plan-mode app-server tests on a multi-thread Tokio runtime
instead of the default single-thread test runtime
- stop relying on wiremock teardown expectations for `/responses` and
explicitly wait for the expected request count after the turn completes
## Why this fixes the flake
- this failure was showing up on Windows ARM as a late wiremock panic
saying the mock server saw zero `/responses` calls, but the real issue
was that the test could stall around app-server startup and only fail
during teardown
- moving these tests to the same multi-thread runtime used by the other
collaboration-mode app-server tests removes that startup scheduling race
- asserting the `/responses` count directly makes the test
deterministic: we now wait for the real POST instead of depending on a
drop-time verification that can hide the underlying timing issue
## Scope
- test-only change; no production logic changes
## What changed
- The PTY Python REPL test now starts Python with a startup marker
already embedded in argv.
- The test waits for that marker in PTY output before making assertions.
## Why this fixes the flake
- The old version tried to probe the live REPL almost immediately after
spawn.
- That races PTY initialization, Python startup, and prompt buffering,
all of which vary across platforms and CI load.
- By having the child process emit a known marker as part of its own
startup path, the test gets a deterministic synchronization point that
comes from the process under test rather than from guessed timing.
## Scope
- Test-only change.
## What changed
- The pid-file cleanup test now keeps polling when the pid file exists
but is still empty.
- Assertions only proceed once the wrapper has actually written the
child pid.
## Why this fixes the flake
- File creation and pid writing are not atomic as one logical action
from the test’s point of view.
- The previous test sometimes won the race and read the file in the tiny
window after creation but before the pid bytes were flushed.
- Treating “empty file” as “not ready yet” synchronizes the test on the
real event we need: the wrapper has finished publishing the child pid.
## Scope
- Test-only change.
## What changed
- `turn_start_shell_zsh_fork_executes_command_v2` now keeps the shell
command alive with a file marker until the interrupt arrives instead of
using a command that can finish too quickly.
-
`turn_start_shell_zsh_fork_subcommand_decline_marks_parent_declined_v2`
now waits for `turn/completed` before sending a fallback interrupt and
accepts the real terminal outcomes observed across platforms.
## Why this fixes the flake
- The original tests assumed a narrow ordering window: the child command
would still be running when the interrupt happened, and completion would
always arrive in one specific order.
- In CI, especially across different shells and runner speeds, those
assumptions break. Sometimes the child finishes before the interrupt;
sometimes the protocol completes while the fallback path is still arming
itself.
- Holding the command open until the interrupt and waiting for the
explicit protocol completion event makes the tests synchronize on the
behavior under test instead of on wall-clock timing.
## Scope
- Test-only change.
## What changed
- The auth/account/fuzzy-file-search test configs disable unrelated
`shell_snapshot` setup.
- The fuzzy-file-search fixture set was reduced so the stop-updates test
does less incidental work before reaching the assertion.
## Why this fixes the flake
- These failures were caused by cumulative timeout pressure, not by a
missing product-level delay.
- The old tests were paying for shell snapshot initialization and extra
fixture volume that were not part of the behavior being validated.
- Removing that incidental work keeps the same coverage but shortens the
critical path enough that the tests finish comfortably inside the
existing timeout budget, which is the right fix versus simply extending
the timeout.
## Scope
- Test-only change.
## Summary
- remove the remaining model-visible guardian-specific `on-request`
prompt additions so enabling the feature does not change the main
approval-policy instructions
- neutralize user-facing guardian wording to talk about automatic
approval review / approval requests rather than a second reviewer or
only sandbox escalations
- tighten guardian retry-context handling so agent-authored
`justification` stays in the structured action JSON and is not also
injected as raw retry context
- simplify guardian review plumbing in core by deleting dead
prompt-append paths and trimming some request/transcript setup code
## Notable Changes
- delete the dead `permissions/approval_policy/guardian.md` append path
and stop threading `guardian_approval_enabled` through model-facing
developer-instruction builders
- rename the experimental feature copy to `Automatic approval review`
and update the `/experimental` snapshot text accordingly
- make approval-review status strings generic across shell, patch,
network, and MCP review types
- forward real sandbox/network retry reasons for shell and unified-exec
guardian review, but do not pass agent-authored justification as raw
retry context
- simplify `guardian.rs` by removing the one-field request wrapper,
deduping reasoning-effort selection, and cleaning up transcript entry
collection
## Testing
- `just fmt`
- full validation left to CI
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- make
`list_apps_waits_for_accessible_data_before_emitting_directory_updates`
accept the two valid notification paths the server can emit
- keep rejecting the real bug this test is meant to catch: a
directory-only `app/list/updated` notification before accessible app
data is available
## Why this fixes the flake
The old test used a fixed `150ms` silence window and assumed the first
notification after that window had to be the fully merged final update.
In CI, scheduling occasionally lets accessible app data arrive before
directory data, so the first valid notification can be an
accessible-only interim update. That made the test fail even though the
server behavior was correct.
This change makes the test deterministic by reading notifications until
the final merged payload arrives. Any interim update is only accepted if
it contains accessible apps only; if the server ever emits inaccessible
directory data before accessible data is ready, the test still fails
immediately.
## Change type
- test-only; no production app-list logic changes
Adds a built-in `request_permissions` tool and wires it through the
Codex core, protocol, and app-server layers so a running turn can ask
the client for additional permissions instead of relying on a static
session policy.
The new flow emits a `RequestPermissions` event from core, tracks the
pending request by call ID, forwards it through app-server v2 as an
`item/permissions/requestApproval` request, and resumes the tool call
once the client returns an approved subset of the requested permission
profile.
## Summary
- split the pending input preview into labeled pending-steer and queued
follow-up sections
- explain that pending steers submit after the next tool call and that
Esc can interrupt and send them immediately
- treat Esc as an interrupt-plus-resubmit path when pending steers
exist, with updated TUI snapshots and tests
Queues and steers:
<img width="1038" height="263" alt="Screenshot 2026-03-07 at 10 17
17 PM"
src="https://github.com/user-attachments/assets/4ef433ef-27a3-4b7c-ad69-2046f6eb89e6"
/>
After pressing Esc:
<img width="1046" height="320" alt="Screenshot 2026-03-07 at 10 17
21 PM"
src="https://github.com/user-attachments/assets/0f4d89e0-b6b9-486a-9f04-b6021f169ba7"
/>
## Codex author
`codex resume 019cc6f4-2cca-7803-b717-8264526dbd97`
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
This test was missing the turn completion event in the responses stream,
so it was hanging. This PR fixes the issue
## Testing
- [x] This does update the test
This is a subset of PR #13636. See that PR for a full overview of the
architectural change.
This PR implements the in-process app server and modifies the
non-interactive "exec" entry point to use the app server.
---------
Co-authored-by: Felipe Coury <felipe.coury@gmail.com>
