Use the existing model_info::with_config_overrides path for alias-specific context window and auto-compact overrides instead of mutating those fields inline in ModelsManager.
The custom alias path now folds alias-level override values into a temporary config and reuses the centralized override helper, which keeps the precedence behavior unchanged while removing duplicated override logic.
List custom model aliases before bundled models in the picker while keeping default-model selection anchored to the bundled priority order when bundled presets exist.
Also add a regression test covering the new ordering.
Accept custom model aliases from [[custom_models]] entries so user config matches the documented TOML shape.
Also add explicit alias names plus duplicate-alias validation and refresh the generated schema/docs to match.
This adds config.toml-defined model aliases that map to provider model slugs while applying alias-specific context settings for the active session.
- added custom_models config entries plus schema and docs coverage
- taught ModelsManager to resolve aliases to a provider-facing request_model while preserving the user-facing alias slug
- applied alias-specific context_window and model_auto_compact_token_limit overrides during model info resolution
- updated session/test plumbing and added regression coverage for alias resolution with local and remote model catalogs
Model selection and per-session context overrides already flow through ModelsManager and Config. Resolving aliases there keeps the provider slug separate from the user-facing alias while reusing the existing override plumbing.
- just write-config-schema
- just fmt
- cargo test -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server
- cargo test -p codex-tui
- cargo test -p codex-protocol -p codex-core (same two existing seatbelt failures remained in this environment: create_seatbelt_args_with_read_only_git_pointer_file and create_seatbelt_args_with_read_only_git_and_codex_subpaths)
- just fix -p codex-core -p codex-protocol -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server -p codex-tui
## Summary
Clarify the `js_repl` prompt guidance around persistent bindings and
redeclaration recovery.
This updates the generated `js_repl` instructions in
`core/src/project_doc.rs` to prefer this order when a name is already
bound:
1. Reuse the existing binding
2. Reassign a previously declared `let`
3. Pick a new descriptive name
4. Use `{ ... }` only for short-lived scratch scope
5. Reset the kernel only when a clean state is actually needed
The prompt now also explicitly warns against wrapping an entire cell in
block scope when the goal is to reuse names across later cells.
## Why
The previous wording still left too much room for low-value workarounds
like whole-cell block wrapping. In downstream browser rollouts, that
pattern was adding tokens and preventing useful state reuse across
`js_repl` cells.
This change makes the preferred behavior more explicit without changing
runtime semantics.
## Scope
- Prompt/documentation change only
- No runtime behavior changes
- Updates the matching string-backed `project_doc` tests
Enhance pty utils:
* Support closing stdin
* Separate stderr and stdout streams to allow consumers differentiate them
* Provide compatibility helper to merge both streams back into combined one
* Support specifying terminal size for pty, including on-demand resizes while process is already running
* Support terminating the process while still consuming its outputs
## Problem
Browser login failures historically leave support with an incomplete
picture. HARs can show that the browser completed OAuth and reached the
localhost callback, but they do not explain why the native client failed
on the final `/oauth/token` exchange. Direct `codex login` also relied
mostly on terminal stderr and the browser error page, so even when the
login crate emitted better sign-in diagnostics through TUI or app-server
flows, the one-shot CLI path still did not leave behind an easy artifact
to collect.
## Mental model
This implementation treats the browser page, the returned `io::Error`,
and the normal structured log as separate surfaces with different safety
requirements. The browser page and returned error preserve the detail
that operators need to diagnose failures. The structured log stays
narrower: it records reviewed lifecycle events, parsed safe fields, and
redacted transport errors without becoming a sink for secrets or
arbitrary backend bodies.
Direct `codex login` now adds a fourth support surface: a small
file-backed log at `codex-login.log` under the configured `log_dir`.
That artifact carries the same login-target events as the other
entrypoints without changing the existing stderr/browser UX.
## Non-goals
This does not add auth logging to normal runtime requests, and it does
not try to infer precise transport root causes from brittle string
matching. The scope remains the browser-login callback flow in the
`login` crate plus a direct-CLI wrapper that persists those events to
disk.
This also does not try to reuse the TUI logging stack wholesale. The TUI
path initializes feedback, OpenTelemetry, and other session-oriented
layers that are useful for an interactive app but unnecessary for a
one-shot login command.
## Tradeoffs
The implementation favors fidelity for caller-visible errors and
restraint for persistent logs. Parsed JSON token-endpoint errors are
logged safely by field. Non-JSON token-endpoint bodies remain available
to the returned error so CLI and browser surfaces still show backend
detail. Transport errors keep their real `reqwest` message, but attached
URLs are surgically redacted. Custom issuer URLs are sanitized before
logging.
On the CLI side, the code intentionally duplicates a narrow slice of the
TUI file-logging setup instead of sharing the full initializer. That
keeps `codex login` easy to reason about and avoids coupling it to
interactive-session layers that the command does not need.
## Architecture
The core auth behavior lives in `codex-rs/login/src/server.rs`. The
callback path now logs callback receipt, callback validation,
token-exchange start, token-exchange success, token-endpoint non-2xx
responses, and transport failures. App-server consumers still use this
same login-server path via `run_login_server(...)`, so the same
instrumentation benefits TUI, Electron, and VS Code extension flows.
The direct CLI path in `codex-rs/cli/src/login.rs` now installs a small
file-backed tracing layer for login commands only. That writes
`codex-login.log` under `log_dir` with login-specific targets such as
`codex_cli::login` and `codex_login::server`.
## Observability
The main signals come from the `login` crate target and are
intentionally scoped to sign-in. Structured logs include redacted issuer
URLs, redacted transport errors, HTTP status, and parsed token-endpoint
fields when available. The callback-layer log intentionally avoids
`%err` on token-endpoint failures so arbitrary backend bodies do not get
copied into the normal log file.
Direct `codex login` now leaves a durable artifact for both failure and
success cases. Example output from the new file-backed CLI path:
Failing callback:
```text
2026-03-06T22:08:54.143612Z INFO codex_cli::login: starting browser login flow
2026-03-06T22:09:03.431699Z INFO codex_login::server: received login callback path=/auth/callback has_code=false has_state=true has_error=true state_valid=true
2026-03-06T22:09:03.431745Z WARN codex_login::server: oauth callback returned error error_code="access_denied" has_error_description=true
```
Succeeded callback and token exchange:
```text
2026-03-06T22:09:14.065559Z INFO codex_cli::login: starting browser login flow
2026-03-06T22:09:36.431678Z INFO codex_login::server: received login callback path=/auth/callback has_code=true has_state=true has_error=false state_valid=true
2026-03-06T22:09:36.436977Z INFO codex_login::server: starting oauth token exchange issuer=https://auth.openai.com/ redirect_uri=http://localhost:1455/auth/callback
2026-03-06T22:09:36.685438Z INFO codex_login::server: oauth token exchange succeeded status=200 OK
```
## Tests
- `cargo test -p codex-login`
- `cargo clippy -p codex-login --tests -- -D warnings`
- `cargo test -p codex-cli`
- `just bazel-lock-update`
- `just bazel-lock-check`
- manual direct `codex login` smoke tests for both a failing callback
and a successful browser login
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
This is a structural cleanup of `codex-otel` to make the ownership
boundaries a lot clearer.
For example, previously it was quite confusing that `OtelManager` which
emits log + trace event telemetry lived under
`codex-rs/otel/src/traces/`. Also, there were two places that defined
methods on OtelManager via `impl OtelManager` (`lib.rs` and
`otel_manager.rs`).
What changed:
- move the `OtelProvider` implementation into `src/provider.rs`
- move `OtelManager` and session-scoped event emission into
`src/events/otel_manager.rs`
- collapse the shared log/trace event helpers into
`src/events/shared.rs`
- pull target classification into `src/targets.rs`
- move `traceparent_context_from_env()` into `src/trace_context.rs`
- keep `src/otel_provider.rs` as a compatibility shim for existing
imports
- update the `codex-otel` README to reflect the new layout
## Why
`lib.rs` and `otel_provider.rs` were doing too many different jobs at
once: provider setup, export routing, trace-context helpers, and session
event emission all lived together.
This refactor separates those concerns without trying to change the
behavior of the crate. The goal is to make future OTEL work easier to
reason about and easier to review.
## Notes
- no intended behavior change
- `OtelManager` remains the session-scoped event emitter in this PR
- the `otel_provider` shim keeps downstream churn low while the
internals move around
## Validation
- `just fmt`
- `cargo test -p codex-otel`
- `just fix -p codex-otel`
Restore the branch-local root/subagent prompt injection in codex-core and update the rollback snapshot to match. This keeps the watchdog branch aligned with its own role-prompt behavior instead of silently adopting main.s prompt layout.
Stop prepending root and subagent prompt files into session developer instructions during startup. Main no longer does this, and keeping the branch-local wrapping caused compaction and rollback snapshot drift in core tests.\n\nKeep the watchdog-specific prompt loader for watchdog check-ins, but leave ordinary session developer instructions sourced directly from config like upstream.
Align the branch ambient role spawn behavior with upstream by making spawn the default when neither the tool call nor the role config specifies a spawn mode.
This keeps the branch delta smaller while letting local config carry role-specific fork defaults where needed.
Stop hardcoding model and spawn-mode defaults for the built-in explorer, fast-worker, and awaiter roles.
That behavior can be expressed through local config instead, which keeps the branch feature focused on per-role override support rather than policy.
Set the built-in role to use , matching the existing lightweight worker-style roles.
This keeps long-running helper agents on the cheaper/faster model path by default while preserving per-role model override support in config.
Allow subagent spawning at the configured max depth by only disabling the agents feature when child depth exceeds the limit.
Update the affected codex-core tests to match the current role spec output and context-free spawn config behavior, and keep the depth-boundary spawn test on the plain spawn path while asserting that the spawned thread is actually registered.
Adjust the watchdog compaction regression test to match the new duplicate-blocking behavior instead of pre-seeding the in-progress set.
Also relax the MCP codex-tool assertion so it checks for developer instructions by substring, which keeps the test valid when branch-added root/subagent prompt text is coalesced into the same developer message.
Rename the branch-local collab inbox payload, constants, helper names,
and prompt text to agent inbox terminology without touching upstream
collaboration mode surfaces.
This keeps the watchdog/runtime behavior intact while removing the
branch-added collab naming that leaked into the stack.
Use the existing model_info::with_config_overrides path for alias-specific context window and auto-compact overrides instead of mutating those fields inline in ModelsManager.
The custom alias path now folds alias-level override values into a temporary config and reuses the centralized override helper, which keeps the precedence behavior unchanged while removing duplicated override logic.
List custom model aliases before bundled models in the picker while keeping default-model selection anchored to the bundled priority order when bundled presets exist.
Also add a regression test covering the new ordering.
Accept custom model aliases from [[custom_models]] entries so user config matches the documented TOML shape.
Also add explicit alias names plus duplicate-alias validation and refresh the generated schema/docs to match.
Preserve internal subagent handoffs as injected response items instead of degrading them into synthetic user messages.
When the destination root thread is idle, prepend an empty user message before the function-call/function-call-output pair so injection starts a valid turn. Keep active-turn behavior and subagent routing unchanged, and retain the regression coverage for the idle-root path.
This adds config.toml-defined model aliases that map to provider model slugs while applying alias-specific context settings for the active session.
- added custom_models config entries plus schema and docs coverage
- taught ModelsManager to resolve aliases to a provider-facing request_model while preserving the user-facing alias slug
- applied alias-specific context_window and model_auto_compact_token_limit overrides during model info resolution
- updated session/test plumbing and added regression coverage for alias resolution with local and remote model catalogs
Model selection and per-session context overrides already flow through ModelsManager and Config. Resolving aliases there keeps the provider slug separate from the user-facing alias while reusing the existing override plumbing.
- just write-config-schema
- just fmt
- cargo test -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server
- cargo test -p codex-tui
- cargo test -p codex-protocol -p codex-core (same two existing seatbelt failures remained in this environment: create_seatbelt_args_with_read_only_git_pointer_file and create_seatbelt_args_with_read_only_git_and_codex_subpaths)
- just fix -p codex-core -p codex-protocol -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server -p codex-tui
Reconcile the combined branch after merging the tracked feature branches.
- restore branch-owned config surface that was dropped during merge resolution
- handle ForkReference rollout items in codex-state metadata extraction
- materialize fork-reference history before building SessionConfigured so forked sessions keep parent lineage and startup scrollback
- cover the fork startup contract with a focused core regression test
## Summary
- reject the global `*` domain pattern in proxy allow/deny lists and
managed constraints introduced for testing earlier
- keep exact hosts plus scoped wildcards like `*.example.com` and
`**.example.com`
- update docs and regression tests for the new invalid-config behavior
Reject stale or corrupt archived rollout candidates before moving files
back into sessions. The unarchive path now requires the candidate to
live under archived_sessions and to have a rollout filename whose UUID
matches the requested thread id.
Add a regression test covering a stale archived DB rollout_path so an
unrelated active-session file is never renamed during lookup.
Restore archived rollout files back into sessions when resolving a thread by id. This lets resume, fork, and resume_agent paths that rely on find_thread_path_by_id_str recover archived sessions automatically instead of reporting them missing.
Also adds a regression test covering archived->sessions restoration and lookup behavior.
(cherry picked from commit fe31d1a911)
At over 7,000 lines, `codex-rs/core/src/config/mod.rs` was getting a bit
unwieldy.
This PR does the same type of move as
https://github.com/openai/codex/pull/12957 to put unit tests in their
own file, though I decided `config_tests.rs` is a more intuitive name
than `mod_tests.rs`.
Ultimately, I'll codemod the rest of the codebase to follow suit, but I
want to do it in stages to reduce merge conflicts for people.
## Summary
- reduce the SQLite-backed log retention window from 90 days to 10 days
## Testing
- just fmt
- cargo test -p codex-state
Co-authored-by: Codex <noreply@openai.com>
#### What
Add structured `@plugin` parsing and TUI support for plugin mentions.
- Core: switch from plain-text `@display_name` parsing to structured
`plugin://...` mentions via `UserInput::Mention` and
`[$...](plugin://...)` links in text, same pattern as apps/skills.
- TUI: add plugin mention popup, autocomplete, and chips when typing
`$`. Load plugin capability summaries and feed them into the composer;
plugin mentions appear alongside skills and apps.
- Generalize mention parsing to a sigil parameter, still defaults to `$`
<img width="797" height="119" alt="image"
src="https://github.com/user-attachments/assets/f0fe2658-d908-4927-9139-73f850805ceb"
/>
Builds on #13510. Currently clients have to build their own `id` via
`plugin@marketplace` and filter plugins to show by `enabled`, but we
will add `id` and `available` as fields returned from `plugin/list`
soon.
####Tests
Added tests, verified locally.
This branch:
* Avoid flushing DB when not necessary
* Filter events for which we perfom an `upsert` into the DB
* Add a dedicated update function of the `thread:updated_at` that is
lighter
This should significantly reduce the DB lock contention. If it is not
sufficient, we can de-sync the flush of the DB for `updated_at`
## Summary
- move sqlite log reads and writes onto a dedicated `logs_1.sqlite`
database to reduce lock contention with the main state DB
- add a dedicated logs migrator and route `codex-state-logs` to the new
database path
- leave the old `logs` table in the existing state DB untouched for now
## Testing
- just fmt
- cargo test -p codex-state
---------
Co-authored-by: Codex <noreply@openai.com>
### Summary
This adds turn-level latency metrics for the first model output and the
first completed agent message.
- `codex.turn.ttft.duration_ms` starts at turn start and records on the
first output signal we see from the model. That includes normal
assistant text, reasoning deltas, and non-text outputs like tool-call
items.
- `codex.turn.ttfm.duration_ms` also starts at turn start, but it
records when the first agent message finishes streaming rather than when
its first delta arrives.
### Implementation notes
The timing is tracked in codex-core, not app-server, so the definition
stays consistent across CLI, TUI, and app-server clients.
I reused the existing turn lifecycle boundary that already drives
`codex.turn.e2e_duration_ms`, stored the turn start timestamp in turn
state, and record each metric once per turn.
I also wired the new metric names into the OTEL runtime metrics summary
so they show up in the same in-memory/debug snapshot path as the
existing timing metrics.
Use the existing model_info::with_config_overrides path for alias-specific context window and auto-compact overrides instead of mutating those fields inline in ModelsManager.
The custom alias path now folds alias-level override values into a temporary config and reuses the centralized override helper, which keeps the precedence behavior unchanged while removing duplicated override logic.
This fixes a flaky `turn_start_shell_zsh_fork_executes_command_v2` test.
The interrupt path can race with the follow-up `/responses` request that
reports the aborted tool call, so the test now allows that extra no-op
response instead of assuming there will only ever be one request. The
assertions still stay focused on the behavior the test actually cares
about: starting the zsh-forked command correctly.
Testing:
- `just fmt`
- `cargo test -p codex-app-server --test all
suite::v2::turn_start_zsh_fork::turn_start_shell_zsh_fork_executes_command_v2
-- --exact --nocapture`
## Summary
Today `SandboxPermissions::requires_additional_permissions()` does not
actually mean "is `WithAdditionalPermissions`". It returns `true` for
any non-default sandbox override, including `RequireEscalated`. That
broad behavior is relied on in multiple `main` callsites.
The naming is security-sensitive because `SandboxPermissions` is used on
shell-like tool calls to tell the executor how a single command should
relate to the turn sandbox:
- `UseDefault`: run with the turn sandbox unchanged
- `RequireEscalated`: request execution outside the sandbox
- `WithAdditionalPermissions`: stay sandboxed but widen permissions for
that command only
## Problem
The old helper name reads as if it only applies to the
`WithAdditionalPermissions` variant. In practice it means "this command
requested any explicit sandbox override."
That ambiguity made it easy to read production checks incorrectly and
made the guardian change look like a standalone `main` fix when it is
not.
On `main` today:
- `shell` and `unified_exec` intentionally reject any explicit
`sandbox_permissions` request unless approval policy is `OnRequest`
- `exec_policy` intentionally treats any explicit sandbox override as
prompt-worthy in restricted sandboxes
- tests intentionally serialize both `RequireEscalated` and
`WithAdditionalPermissions` as explicit sandbox override requests
So changing those callsites from the broad helper to a narrow
`WithAdditionalPermissions` check would be a behavior change, not a pure
cleanup.
## What This PR Does
- documents `SandboxPermissions` as a per-command sandbox override, not
a generic permissions bag
- adds `requests_sandbox_override()` for the broad meaning: anything
except `UseDefault`
- adds `uses_additional_permissions()` for the narrow meaning: only
`WithAdditionalPermissions`
- keeps `requires_additional_permissions()` as a compatibility alias to
the broad meaning for now
- updates the current broad callsites to use the accurately named broad
helper
- adds unit coverage that locks in the semantics of all three helpers
## What This PR Does Not Do
This PR does not change runtime behavior. That is intentional.
---------
Co-authored-by: Codex <noreply@openai.com>
List custom model aliases before bundled models in the picker while keeping default-model selection anchored to the bundled priority order when bundled presets exist.
Also add a regression test covering the new ordering.
Accept custom model aliases from [[custom_models]] entries so user config matches the documented TOML shape.
Also add explicit alias names plus duplicate-alias validation and refresh the generated schema/docs to match.
## Summary
- add one-time session recovery in `RmcpClient` for streamable HTTP MCP
`404` session expiry
- rebuild the transport and retry the failed operation once after
reinitializing the client state
- extend the test server and integration coverage for `404`, `401`,
single-retry, and non-session failure scenarios
## Testing
- just fmt
- cargo test -p codex-rmcp-client (the post-rebase run lost its final
summary in the terminal; the suite had passed earlier before the rebase)
- just fix -p codex-rmcp-client
`/feedback` uploads can include `codex-logs.log` from the in-memory
feedback logger path. That logger was emitting level + message without a
timestamp, which made some uploaded logs much harder to inspect. This
change makes the feedback logger use an explicit timer so
feedback-captured log lines include timestamps consistently.
This is not Windows-specific code. The bug showed up in Windows reports
because those uploads were hitting the feedback-buffer path more often,
while Linux/macOS reports were typically coming from the SQLite feedback
export, which already prefixes timestamps.
Here's an example of a log that is missing the timestamps:
```
TRACE app-server request: getAuthStatus
TRACE app-server request: model/list
INFO models cache: evaluating cache eligibility
INFO models cache: attempting load_fresh
INFO models cache: loaded cache file
INFO models cache: cache version mismatch
INFO models cache: no usable cache entry
DEBUG
INFO models cache: cache miss, fetching remote models
TRACE windows::current_platform is called
TRACE Returning Info { os_type: Windows, version: Semantic(10, 0, 26200), edition: Some("Windows 11 Professional"), codename: None, bitness: X64, architecture: Some("x86_64") }
```
Restore the branch-local root/subagent prompt injection in codex-core and update the rollback snapshot to match. This keeps the watchdog branch aligned with its own role-prompt behavior instead of silently adopting main.s prompt layout.
Stop prepending root and subagent prompt files into session developer instructions during startup. Main no longer does this, and keeping the branch-local wrapping caused compaction and rollback snapshot drift in core tests.\n\nKeep the watchdog-specific prompt loader for watchdog check-ins, but leave ordinary session developer instructions sourced directly from config like upstream.
# 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.
#### What
on `plugin/install`, check if installed apps are already authed on
chatgpt, and return list of all apps that are not. clients can use this
list to trigger auth workflows as needed.
checks are best effort based on `codex_apps` loading, much like
`app/list`.
#### Tests
Added integration tests, tested locally.
- Replay thread rollback from the persisted rollout history instead of
truncating in-memory state.\n- Add rollback coverage, including
rollback-behind-compaction snapshot coverage.
## Summary
Simplify the trusted directory flow. This logic was originally designed
several months ago, to determine if codex should start in read-only or
workspace-write mode. However, that's no longer the purpose of directory
trust - and therefore we should get rid of this logic.
## Testing
- [x] Unit tests pass
We do this for codex-command-runner.exe as well for the same reason.
Windows sandbox users cannot execute binaries in the WindowsApp/
installed directory for the Codex App. This causes apply-patch to fail
because it tries to execute codex.exe as the sandbox user.
## Summary
- delete the network proxy admin server and its runtime listener/task
plumbing
- remove the admin endpoint config, runtime, requirement, protocol,
schema, and debug-surface fields
- update proxy docs to reflect the remaining HTTP and SOCKS listeners
only
## Summary
This PR:
1. fixes a deserialization mismatch for macOS automation permissions in
approval payloads by making core parsing accept both supported wire
shapes for bundle IDs.
2. added `#[serde(default)]` to `MacOsSeatbeltProfileExtensions` so
omitted fields deserialize to secure defaults.
## Why this change is needed
`MacOsAutomationPermission` uses `#[serde(try_from =
"MacOsAutomationPermissionDe")]`, so deserialization is controlled by
`MacOsAutomationPermissionDe`. After we aligned v2
`additionalPermissions.macos.automations` to the core shape, approval
payloads started including `{ "bundle_ids": [...] }` in some paths.
`MacOsAutomationPermissionDe` previously accepted only `"none" | "all"`
or a plain array, so object-shaped bundle IDs failed with `data did not
match any variant of untagged enum MacOsAutomationPermissionDe`. This
change restores compatibility by accepting both forms while preserving
existing normalization behavior (trim values and map empty bundle lists
to `None`).
## Validation
saw this error went away when running
```
cargo run -p codex-app-server-test-client -- \
--codex-bin ./target/debug/codex \
-c 'approval_policy="on-request"' \
-c 'features.shell_zsh_fork=true' \
-c 'zsh_path="/tmp/codex-zsh-fork/package/vendor/aarch64-apple-darwin/zsh/macos-15/zsh"' \
send-message-v2 --experimental-api \
'Use $apple-notes and run scripts/notes_info now.'
```
:
```
Error: failed to deserialize ServerRequest from JSONRPCRequest
Caused by:
data did not match any variant of untagged enum MacOsAutomationPermissionDe
```
Align the branch ambient role spawn behavior with upstream by making spawn the default when neither the tool call nor the role config specifies a spawn mode.
This keeps the branch delta smaller while letting local config carry role-specific fork defaults where needed.
## Summary
This PR removes legacy macOS permission model types from
`codex-rs/protocol/src/models.rs`:
- `MacOsPermissions`
- `MacOsPreferencesValue`
- `MacOsAutomationValue`
The protocol now relies on the current `MacOsSeatbeltProfileExtensions`
model for macOS permission data.
Stop hardcoding model and spawn-mode defaults for the built-in explorer, fast-worker, and awaiter roles.
That behavior can be expressed through local config instead, which keeps the branch feature focused on per-role override support rather than policy.
Set the built-in role to use , matching the existing lightweight worker-style roles.
This keeps long-running helper agents on the cheaper/faster model path by default while preserving per-role model override support in config.
Allow subagent spawning at the configured max depth by only disabling the agents feature when child depth exceeds the limit.
Update the affected codex-core tests to match the current role spec output and context-free spawn config behavior, and keep the depth-boundary spawn test on the plain spawn path while asserting that the spawned thread is actually registered.
Adjust the watchdog compaction regression test to match the new duplicate-blocking behavior instead of pre-seeding the in-progress set.
Also relax the MCP codex-tool assertion so it checks for developer instructions by substring, which keeps the test valid when branch-added root/subagent prompt text is coalesced into the same developer message.
## Summary
- default the resume picker sort key to UpdatedAt instead of CreatedAt
- keep Tab sort toggling behavior and update the test expectation for
the new default
## Testing
- just fmt
- cargo test -p codex-tui
Co-authored-by: Codex <noreply@openai.com>
This adds config.toml-defined model aliases that map to provider model slugs while applying alias-specific context settings for the active session.
### What changed
- added custom_models config entries plus schema and docs coverage
- taught ModelsManager to resolve aliases to a provider-facing request_model while preserving the user-facing alias slug
- applied alias-specific context_window and model_auto_compact_token_limit overrides during model info resolution
- updated session/test plumbing and added regression coverage for alias resolution with local and remote model catalogs
### Why this approach
Model selection and per-session context overrides already flow through ModelsManager and Config. Resolving aliases there keeps the provider slug separate from the user-facing alias while reusing the existing override plumbing.
### Testing
- just write-config-schema
- just fmt
- cargo test -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server
- cargo test -p codex-tui
- cargo test -p codex-protocol -p codex-core (same two existing seatbelt failures remained in this environment: create_seatbelt_args_with_read_only_git_pointer_file and create_seatbelt_args_with_read_only_git_and_codex_subpaths)
- just fix -p codex-core -p codex-protocol -p codex-app-server -p codex-api -p codex-exec -p codex-mcp-server -p codex-tui
## Summary
- keep the SQLite schema unchanged (no migrations)
- add timestamps to SQLite-backed `/feedback` log exports
- keep the existing SQL-side byte cap behavior and newline handling
- document the remaining fidelity gap (span prefixes + structured
fields) with TODOs
## Details
- update `query_feedback_logs` to format each exported line as:
- `YYYY-MM-DDTHH:MM:SS.ffffffZ {level} {message}`
- continue scoping rows to requested-thread + same-process threadless
logs
- continue capping in SQL before returning rows
- keep the existing fallback behavior unchanged when SQLite returns no
rows
- update parity tests to normalize away the new timestamp prefix while
we still only store `message`
## Follow-up
- TODO already in code: persist enough span/event metadata in SQLite to
reproduce span prefixes and structured fields in `/feedback` exports
## Testing
- `cargo test -p codex-state`
- `just fmt`
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- render pending steer previews with a single `pending steer:` prefix
instead of repeating it for each source line
- reuse the same truncation path for pending steers and queued drafts so
multiline previews behave consistently
- add snapshot coverage for the multiline pending steer case
Before
<img width="969" height="219" alt="Screenshot 2026-03-05 at 3 55 11 PM"
src="https://github.com/user-attachments/assets/b062c9c8-43d3-4a52-98e0-3c7643d1697b"
/>
After
<img width="965" height="203" alt="Screenshot 2026-03-05 at 3 56 08 PM"
src="https://github.com/user-attachments/assets/40935863-55b3-444f-9e14-1ac63126b2e1"
/>
## Codex author
`codex resume 019cc054-385e-79a3-bb85-ec9499623bd8`
Co-authored-by: Codex <noreply@openai.com>
- Replay thread rollback from the persisted rollout history instead of
truncating in-memory state.\n- Add rollback coverage, including
rollback-behind-compaction snapshot coverage.
Hydrate fork-reference chains before truncating forked histories and
before building forked spawn histories, then use the hydrated items
for forked-session startup replay while still persisting only the
compact fork-reference suffix.
This fixes fork-of-fork boundary calculations, preserves inherited
context on forked startup, and updates the regression tests to compare
logical materialized history instead of raw compact storage bytes.
## Summary
- group recent work by git repo when available, otherwise by directory
- render recent work as bounded user asks with per-thread cwd context
- exclude hidden files and directories from workspace trees
### Motivation
Today config.toml has three different OTEL knobs under `[otel]`:
- `exporter` controls where OTEL logs go
- `trace_exporter` controls where OTEL traces go
- `metrics_exporter` controls where metrics go
Those often (pretty much always?) serve different purposes.
For example, for OpenAI internal usage, the **log exporter** is already
being used for IT/security telemetry, and that use case is intentionally
content-rich: tool calls, arguments, outputs, MCP payloads, and in some
cases user content are all useful there. `log_user_prompt` is a good
example of that distinction. When it’s enabled, we include raw prompt
text in OTEL logs, which is acceptable for the security use case.
The **trace exporter** is a different story. The goal there is to give
OpenAI engineers visibility into latency and request behavior when they
run Codex locally, without sending sensitive prompt or tool data as
trace event data. In other words, traces should help answer “what was
slow?” or “where did time go?”, not “what did the user say?” or “what
did the tool return?”
The complication is that Rust’s `tracing` crate does not make a hard
distinction between “logs” and “trace events.” It gives us one
instrumentation API for logs and trace events (via `tracing::event!`),
and subscribers decide what gets treated as logs, trace events, or both.
Before this change, our OTEL trace layer was effectively attached to the
general tracing stream, which meant turning on `trace_exporter` could
pick up content-rich events that were originally written with logging
(and the `log_exporter`) in mind. That made it too easy for sensitive
data to end up in exported traces by accident.
### Concrete example
In `otel_manager.rs`, this `tracing::event!` call would be exported in
both logs AND traces (as a trace event).
```
pub fn user_prompt(&self, items: &[UserInput]) {
let prompt = items
.iter()
.flat_map(|item| match item {
UserInput::Text { text, .. } => Some(text.as_str()),
_ => None,
})
.collect::<String>();
let prompt_to_log = if self.metadata.log_user_prompts {
prompt.as_str()
} else {
"[REDACTED]"
};
tracing::event!(
tracing::Level::INFO,
event.name = "codex.user_prompt",
event.timestamp = %timestamp(),
// ...
prompt = %prompt_to_log,
);
}
```
Instead of `tracing::event!`, we should now be using `log_event!` and
`trace_event!` instead to more clearly indicate which sink (logs vs.
traces) that event should be exported to.
### What changed
This PR makes the log and trace export distinct instead of treating them
as two sinks for the same data.
On the provider side, OTEL logs and traces now have separate
routing/filtering policy. The log exporter keeps receiving the existing
`codex_otel` events, while trace export is limited to spans and trace
events.
On the event side, `OtelManager` now emits two flavors of telemetry
where needed:
- a log-only event with the current rich payloads
- a tracing-safe event with summaries only
It also has a convenience `log_and_trace_event!` macro for emitting to
both logs and traces when it's safe to do so, as well as log- and
trace-specific fields.
That means prompts, tool args, tool output, account email, MCP metadata,
and similar content stay in the log lane, while traces get the pieces
that are actually useful for performance work: durations, counts, sizes,
status, token counts, tool origin, and normalized error classes.
This preserves current IT/security logging behavior while making it safe
to turn on trace export for employees.
### Full list of things removed from trace export
- raw user prompt text from `codex.user_prompt`
- raw tool arguments and output from `codex.tool_result`
- MCP server metadata from `codex.tool_result` (mcp_server,
mcp_server_origin)
- account identity fields like `user.email` and `user.account_id` from
trace-safe OTEL events
- `host.name` from trace resources
- generic `codex.tool_decision` events from traces
- generic `codex.sse_event` events from traces
- the full ToolCall debug payload from the `handle_tool_call` span
What traces now keep instead is mostly:
- spans
- trace-safe OTEL events
- counts, lengths, durations, status, token counts, and tool origin
summaries
Mark the subagent panel helpers that are only exercised by the later behavior branch as dead-code-tolerant in the standalone foundation branch so codex-tui tests stay warning-free.
- Update `models.json` to surface the new model entry.
- Refresh the TUI model picker snapshot to match the updated catalog
ordering.
---------
Co-authored-by: aibrahim-oai <219906144+aibrahim-oai@users.noreply.github.com>
## Note-- added plugin mentions via @, but that conflicts with file
mentions
depends and builds upon #13433.
- introduces explicit `@plugin` mentions. this injects the plugin's mcp
servers, app names, and skill name format into turn context as a dev
message.
- we do not yet have UI for these mentions, so we currently parse raw
text (as opposed to skills and apps which have UI chips, autocomplete,
etc.) this depends on a `plugins/list` app-server endpoint we can feed
the UI with, which is upcoming
- also annotate mcp and app tool descriptions with the plugin(s) they
come from. this gives the model a first class way of understanding what
tools come from which plugins, which will help implicit invocation.
### Tests
Added and updated tests, unit and integration. Also confirmed locally a
raw `@plugin` injects the dev message, and the model knows about its
apps, mcps, and skills.
## Summary
This updates the `js_repl` prompt and docs to make the image guidance
less confusing.
## What changed
- Clarified that `codex.emitImage(...)` adds one image per call and can
be called multiple times to emit multiple images.
- Reworded the image-encoding guidance to be general `js_repl` advice
instead of `ImageDetailOriginal`-specific behavior.
- Updated the guidance to recommend JPEG at about quality 85 when lossy
compression is acceptable, and PNG when transparency or lossless detail
matters.
- Mirrored the same wording in the public `js_repl` docs.
Rename the branch-local collab inbox payload, constants, helper names,
and prompt text to agent inbox terminology without touching upstream
collaboration mode surfaces.
This keeps the watchdog/runtime behavior intact while removing the
branch-added collab naming that leaked into the stack.
This improves macOS Seatbelt handling for sandboxed tool processes.
## Changes
- Allow dual-stack local binding in proxy-managed sessions, while still
keeping traffic limited to loopback and configured proxy endpoints.
- Replace the old generic unix-socket path rule with explicit AF_UNIX
permissions for socket creation, bind, and outbound connect.
- Keep explicitly approved wrapper sockets connect-only.
Local helper servers are less likely to fail when binding on macOS.
Tools using local unix-socket IPC should work more reliably under the
sandbox.
Full-network sessions, proxy fail-closed behavior, and proxy lifecycle
are unchanged.
Rename the branch-added collab inbox payload, constants, helpers, snapshot, and spawn-mode type to agent terminology while leaving upstream-established collaboration surfaces unchanged.
Regenerate the app-server schema outputs and update the TUI replay snapshot to match the renamed AgentSpawnMode and agent inbox compatibility coverage.
Introduce the base TUI plumbing needed to render collaboration events and subagent state.
Add the foundational app events, history cells, chatwidget handling, and text formatting used by collaboration surfaces, and keep the replay dedupe coverage that prevents duplicate collab inbox rows when compatibility encodings are replayed from snapshots.
Keep forked sessions compact by recording fork references instead of duplicating full parent history.
Repair stale parent rollout paths by resolving the referenced thread id back to the current active or archived rollout location during replay, and materialize fork references before app-server derives thread summaries. Retain the core and app-server regressions that cover archive/unarchive and thread-read behavior.
Preserve internal subagent handoffs as injected response items instead of degrading them into synthetic user messages.
When the destination root thread is idle, prepend an empty user message before the function-call/function-call-output pair so injection starts a valid turn. Keep active-turn behavior and subagent routing unchanged, and retain the regression coverage for the idle-root path.
## Summary
- always pass `--unshare-user` in the Linux bubblewrap argv builders
- stop relying on bubblewrap's auto-userns behavior, which is skipped
for `uid 0`
- update argv expectations in tests and document the explicit user
namespace behavior
The installed Codex binary reproduced the same issue with:
- `codex -c features.use_linux_sandbox_bwrap=true sandbox linux -- true`
- `bwrap: Creating new namespace failed: Operation not permitted`
This happens because Codex asked bubblewrap for mount/pid/network
namespaces without explicitly asking for a user namespace. In a
root-inside-container environment without ambient `CAP_SYS_ADMIN`, that
fails. Adding `--unshare-user` makes bubblewrap create the user
namespace first and then the remaining namespaces succeed.
### Motivation
- Ensure the multitool `codex` wrapper enforces the same `ExecCli`
validation rules as the standalone `codex-exec` binary so `codex exec
--fork <id> resume` is rejected consistently and the related unit test
no longer fails.
### Description
- Call `ExecCli::validate()` in the multitool dispatch path before
forwarding to `codex_exec::run_main` and handle validation errors by
exiting appropriately; change located in `codex-rs/cli/src/main.rs`.
- Update the unit test `exec_fork_conflicts_with_resume_subcommand` to
parse the CLI and assert that `exec.validate()` returns an error (parse
succeeds but validation fails) to reflect where the conflict is
enforced.
### Testing
- Ran formatting with `just fmt` in the workspace and it completed
successfully.
- Executed the failing unit case with:
`PKG_CONFIG_PATH=/tmp/libcap-shim/lib/pkgconfig
NO_PROXY=127.0.0.1,localhost cargo test -p codex-cli
tests::exec_fork_conflicts_with_resume_subcommand`, and the test passed.
- Ran the `codex-exec` and `codex-cli` test suites with the same
environment shim (`PKG_CONFIG_PATH=/tmp/libcap-shim/lib/pkgconfig
NO_PROXY=127.0.0.1,localhost`) and they completed successfully.
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_69a9e5053e448323965a3c030a90e154)
This PR adds a durable trace linkage for each turn by storing the active
trace ID on the rollout TurnContext record stored in session rollout
files.
Before this change, we propagated trace context at runtime but didn’t
persist a stable per-turn trace key in rollout history. That made
after-the-fact debugging harder (for example, mapping a historical turn
to the corresponding trace in datadog). This sets us up for much easier
debugging in the future.
### What changed
- Added an optional `trace_id` to TurnContextItem (rollout schema).
- Added a small OTEL helper to read the current span trace ID.
- Captured `trace_id` when creating `TurnContext` and included it in
`to_turn_context_item()`.
- Updated tests and fixtures that construct TurnContextItem so
older/no-trace cases still work.
### Why this approach
TurnContext is already the canonical durable per-turn metadata in
rollout. This keeps ownership clean: trace linkage lives with other
persisted turn metadata.
### Motivation
- Prevent untrusted js_repl code from supplying arbitrary external URLs
that the host would forward into model input and cause external fetches
/ data exfiltration. This change narrows the emitImage contract to safe,
self-contained data URLs.
### Description
- Kernel: added `normalizeEmitImageUrl` and enforce that string-valued
`codex.emitImage(...)` inputs and `input_image`/content-item paths only
accept non-empty `data:` URLs; byte-based paths still produce data URLs
as before (`kernel.js`).
- Host: added `validate_emitted_image_url` and check `EmitImage`
requests before creating `FunctionCallOutputContentItem::InputImage`,
returning an error to the kernel if the URL is not a `data:` URL
(`mod.rs`).
- Tests/docs: added a runtime test
`js_repl_emit_image_rejects_non_data_url` to assert rejection of
non-data URLs and updated user-facing docs/instruction text to state
`data URL` support instead of generic direct image URLs (`mod.rs`,
`docs/js_repl.md`, `project_doc.rs`).
### Testing
- Ran `just fmt` in `codex-rs`; it completed successfully.
- Added a runtime test (`cargo test -p codex-core
js_repl_emit_image_rejects_non_data_url`) but executing the test in this
environment failed due to a missing system dependency required by
`codex-linux-sandbox` (the vendored `bubblewrap` build requires
`libcap.pc` via `pkg-config`), so the test could not be run here.
- Attempted a focused `cargo test` invocation with and without default
features; both compile/test attempts were blocked by the same missing
system `libcap` dependency in this environment.
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_69a7837bce98832d91db92d5f76d6cbe)
## Summary
This changes the Unix shell escalation path for skill-matched
executables to apply a skill's `PermissionProfile` as additive
permissions on top of the existing turn/request sandbox policy.
Previously, skill-matched executables compiled the skill permission
profile into a standalone sandbox policy and executed against that
replacement policy. Now they go through the same
`additional_permissions` merge path used elsewhere in shell sandbox
preparation.
## What Changed
- Changed `skill_escalation_execution()` to return
`EscalationPermissions::PermissionProfile(...)` for non-empty skill
permission profiles.
- Kept empty or missing skill permission profiles on the `TurnDefault`
path.
- Added tests covering the new additive skill-permission behavior.
- Added inline comments in `prepare_escalated_exec()` clarifying the
difference between additive permission merging and fully specified
replacement sandbox policies.
- Removed the now-unused skill permission compiler module after
switching this path away from standalone compiled skill sandbox
policies.
## Testing
- Ran `just fmt` in `codex-rs`
- Ran `cargo test -p codex-core`
`cargo test -p codex-core` still hits an unrelated existing failure:
`shell_snapshot::tests::snapshot_shell_does_not_inherit_stdin`
## Follow-up
This change intentionally does not merge skill-specific macOS seatbelt
profile extensions through the `additional_permissions` path yet.
Filesystem and network permissions now follow the additive merge path,
but seatbelt extension permissions still need separate handling in a
follow-up PR.
### Motivation
- A recent `--fork` addition used `conflicts_with = "command"` in the
`clap` attribute which references a non-existent id and caused a runtime
panic (`Argument or group 'command' ... does not exist`) during command
construction, breaking CI and tooling that invokes `codex exec`.
- The intent was to disallow `--fork` together with any subcommand; this
must be enforced without using an invalid clap conflict target.
### Description
- Removed the invalid `conflicts_with = "command"` attribute from the
`--fork` flag in `codex-rs/exec/src/cli.rs` and instead added an
explicit `Cli::validate()` method that returns a `clap::Error` with
`ErrorKind::ArgumentConflict` when `fork_session_id` and a subcommand
are both present.
- Wired `Cli::validate()` into the binary entrypoint in
`codex-rs/exec/src/main.rs` so the parsed CLI is validated before
execution and the standard clap error handling is used (`err.exit()` on
validation failure).
- Updated the existing unit test to call `Cli::validate()` after parse
so the test still asserts the intended conflict behavior.
- Ran formatting (`just fmt`) after changes.
### Testing
- Ran `just fmt` in `codex-rs` successfully.
- Ran unit/integration tests for the modified crate with environment
stubs: `PKG_CONFIG_PATH=/tmp/libcap-stub/lib/pkgconfig
NO_PROXY=127.0.0.1,localhost no_proxy=127.0.0.1,localhost cargo test -p
codex-exec` and `cargo test -p codex-exec --test all` which completed
with the `codex-exec` tests passing locally.
- Verified a targeted failing originator test after the change and it
passed when run with the same env overrides.
- Attempted to run `sdk/typescript` tests but the `pnpm`/`corepack`
install failed due to network/proxy download errors (403 from proxy)
when fetching `pnpm`, which is environmental and unrelated to this
change.
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_69a9d1a216ec8323a648cfa001def5ae)
## Summary
- Change `js_repl` failed-cell persistence so later cells keep prior
bindings plus only the current-cell bindings whose initialization
definitely completed before the throw.
- Preserve initialized lexical bindings across failed cells via
module-namespace readability, including top-level destructuring that
partially succeeds before a later throw.
- Preserve hoisted `var` and `function` bindings only when execution
clearly reached their declaration site, and preserve direct top-level
pre-declaration `var` writes and updates through explicit write-site
markers.
- Preserve top-level `for...in` / `for...of` `var` bindings when the
loop body executes at least once, using a first-iteration guard to avoid
per-iteration bookkeeping overhead.
- Keep prior module state intact across link-time failures and
evaluation failures before the prelude runs, while still allowing failed
cells that already recreated prior bindings to persist updates to those
existing bindings.
- Hide internal commit hooks from user `js_repl` code after the prelude
aliases them, so snippets cannot spoof committed bindings by calling the
raw `import.meta` hooks directly.
- Add focused regression coverage for the supported failed-cell
behaviors and the intentionally unsupported boundaries.
- Update `js_repl` docs and generated instructions to describe the new,
narrower failed-cell persistence model.
## Motivation
We saw `js_repl` drop bindings that had already been initialized
successfully when a later statement in the same cell threw, for example:
const { context: liveContext, session } =
await initializeGoogleSheetsLiveForTab(tab);
// later statement throws
That was surprising in practice because successful earlier work
disappeared from the next cell.
This change makes failed-cell persistence more useful without trying to
model every possible partially executed JavaScript edge case. The
resulting behavior is narrower and easier to reason about:
- prior bindings are always preserved
- lexical bindings persist when their initialization completed before
the throw
- hoisted `var` / `function` bindings persist only when execution
clearly reached their declaration or a supported top-level `var` write
site
- failed cells that already recreated prior bindings can persist writes
to those existing bindings even if they introduce no new bindings
The detailed edge-case matrix stays in `docs/js_repl.md`. The
model-facing `project_doc` guidance is intentionally shorter and focused
on generation-relevant behavior.
## Supported Failed-Cell Behavior
- Prior bindings remain available after a failed cell.
- Initialized lexical bindings remain available after a failed cell.
- Top-level destructuring like `const { a, b } = ...` preserves names
whose initialization completed before a later throw.
- Hoisted `function` bindings persist when execution reached the
declaration statement before the throw.
- Direct top-level pre-declaration `var` writes and updates persist, for
example:
- `x = 1`
- `x += 1`
- `x++`
- short-circuiting logical assignments only persist when the write
branch actually runs
- Non-empty top-level `for...in` / `for...of` `var` loops persist their
loop bindings.
- Failed cells can persist updates to existing carried bindings after
the prelude has run, even when the cell commits no new bindings.
- Link failures and eval failures before the prelude do not poison
`@prev`.
## Intentionally Unsupported Failed-Cell Cases
- Hoisted function reads before the declaration, such as `foo(); ...;
function foo() {}`
- Aliasing or inference-based recovery from reads before declaration
- Nested writes inside already-instrumented assignment RHS expressions
- Destructuring-assignment recovery for hoisted `var`
- Partial `var` destructuring recovery
- Pre-declaration `undefined` reads for hoisted `var`
- Empty top-level `for...in` / `for...of` loop vars
- Nested or scope-sensitive pre-declaration `var` writes outside direct
top-level expression statements
This adds a first-class server request for MCP server elicitations:
`mcpServer/elicitation/request`.
Until now, MCP elicitation requests only showed up as a raw
`codex/event/elicitation_request` event from core. That made it hard for
v2 clients to handle elicitations using the same request/response flow
as other server-driven interactions (like shell and `apply_patch`
tools).
This also updates the underlying MCP elicitation request handling in
core to pass through the full MCP request (including URL and form data)
so we can expose it properly in app-server.
### Why not `item/mcpToolCall/elicitationRequest`?
This is because MCP elicitations are related to MCP servers first, and
only optionally to a specific MCP tool call.
In the MCP protocol, elicitation is a server-to-client capability: the
server sends `elicitation/create`, and the client replies with an
elicitation result. RMCP models it that way as well.
In practice an elicitation is often triggered by an MCP tool call, but
not always.
### What changed
- add `mcpServer/elicitation/request` to the v2 app-server API
- translate core `codex/event/elicitation_request` events into the new
v2 server request
- map client responses back into `Op::ResolveElicitation` so the MCP
server can continue
- update app-server docs and generated protocol schema
- add an end-to-end app-server test that covers the full round trip
through a real RMCP elicitation flow
- The new test exercises a realistic case where an MCP tool call
triggers an elicitation, the app-server emits
mcpServer/elicitation/request, the client accepts it, and the tool call
resumes and completes successfully.
### app-server API flow
- Client starts a thread with `thread/start`.
- Client starts a turn with `turn/start`.
- App-server sends `item/started` for the `mcpToolCall`.
- While that tool call is in progress, app-server sends
`mcpServer/elicitation/request`.
- Client responds to that request with `{ action: "accept" | "decline" |
"cancel" }`.
- App-server sends `serverRequest/resolved`.
- App-server sends `item/completed` for the mcpToolCall.
- App-server sends `turn/completed`.
- If the turn is interrupted while the elicitation is pending,
app-server still sends `serverRequest/resolved` before the turn
finishes.
## Why
`shell_zsh_fork` already provides stronger guarantees around which
executables receive elevated permissions. To reuse that machinery from
unified exec without pushing Unix-specific escalation details through
generic runtime code, the escalation bootstrap and session lifetime
handling need a cleaner boundary.
That boundary also needs to be safe for long-lived sessions: when an
intercepted shell session is closed or pruned, any in-flight approval
workers and any already-approved escalated child they spawned must be
torn down with the session, and the inherited escalation socket must not
leak into unrelated subprocesses.
## What Changed
- Extracted a reusable `EscalationSession` and
`EscalateServer::start_session(...)` in `shell-escalation` so callers
can get the wrapper/socket env overlay and keep the escalation server
alive without immediately running a one-shot command.
- Documented that `EscalationSession::env()` and
`ShellCommandExecutor::run(...)` exchange only that env overlay, which
callers must merge into their own base shell environment.
- Clarified the prepared-exec helper boundary in `core` by naming the
new helper APIs around `ExecRequest`, while keeping the legacy
`execute_env(...)` entrypoints as thin compatibility wrappers for
existing callers that still use the older naming.
- Added a small post-spawn hook on the prepared execution path so the
parent copy of the inheritable escalation socket is closed immediately
after both the existing one-shot shell-command spawn and the
unified-exec spawn.
- Made session teardown explicit with session-scoped cancellation:
dropping an `EscalationSession` or canceling its parent request now
stops intercept workers, and the server-spawned escalated child uses
`kill_on_drop(true)` so teardown cannot orphan an already-approved
child.
- Added `UnifiedExecBackendConfig` plumbing through `ToolsConfig`, a
`shell::zsh_fork_backend` facade, and an opaque unified-exec
spawn-lifecycle hook so unified exec can prepare a wrapped `zsh -c/-lc`
request without storing `EscalationSession` directly in generic
process/runtime code.
- Kept the existing `shell_command` zsh-fork behavior intact on top of
the new bootstrap path. Tool selection is unchanged in this PR: when
`shell_zsh_fork` is enabled, `ShellCommand` still wins over
`exec_command`.
## Verification
- `cargo test -p codex-shell-escalation`
- includes coverage for `start_session_exposes_wrapper_env_overlay`
- includes coverage for `exec_closes_parent_socket_after_shell_spawn`
- includes coverage for
`dropping_session_aborts_intercept_workers_and_kills_spawned_child`
- `cargo test -p codex-core
shell_zsh_fork_prefers_shell_command_over_unified_exec`
- `cargo test -p codex-core --test all
shell_zsh_fork_prompts_for_skill_script_execution`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/13392).
* #13432
* __->__ #13392
- add a speed row to the startup/session header under the model row
- render the speed row with the same styling pattern as the model row,
using /fast to change
- show only Fast or Standard to users and update the affected snapshots
---------
Co-authored-by: Codex <noreply@openai.com>
add `web_search_tool_type` on model_info that can be populated from
backend. will be used to filter which models can use `web_search` with
images and which cant.
added small unit test.
- lower `submission_dispatch` span logging to debug for realtime audio
submissions only
- keep other submission spans at info and add a targeted test for the
level selection
---------
Co-authored-by: Codex <noreply@openai.com>
## Summary
- add `js_repl` support for dynamic imports of relative and absolute
local ESM `.js` / `.mjs` files
- keep bare package imports on the native Node path and resolved from
REPL-global search roots (`CODEX_JS_REPL_NODE_MODULE_DIRS`, then `cwd`),
even when they originate from imported local files
- restrict static imports inside imported local files to other local
relative/absolute `.js` / `.mjs` files, and surface a clear error for
unsupported top-level static imports in the REPL cell
- run imported local files inside the REPL VM context so they can access
`codex.tmpDir`, `codex.tool`, captured `console`, and Node-like
`import.meta` helpers
- reload local files between execs so later `await import("./file.js")`
calls pick up edits and fixed failures, while preserving package/builtin
caching and persistent top-level REPL bindings
- make `import.meta.resolve()` self-consistent by allowing the returned
`file://...` URLs to round-trip through `await import(...)`
- update both public and injected `js_repl` docs to clarify the narrowed
contract, including global bare-import resolution behavior for local
absolute files
## Testing
- `cargo test -p codex-core js_repl_`
- built codex binary and verified behavior
---------
Co-authored-by: Codex <noreply@openai.com>
### Motivation
- Fix a type mismatch that caused `codex-exec` to fail compiling when
resolving a fork/resume target path because underlying `std::io::Error`
results were returned from helpers while the caller expected
`anyhow::Error`.
### Description
- Update `resolve_thread_path_by_id_or_name` in
`codex-rs/exec/src/lib.rs` to convert the `std::io::Error` returned by
`find_thread_path_by_id_str` and `find_thread_path_by_name_str` into
`anyhow::Error` using `.map_err(anyhow::Error::from)`, so the function
returns `anyhow::Result<Option<PathBuf>>` consistently.
### Testing
- Ran `just fmt` in `codex-rs`, which completed successfully.
- Attempted `cargo test -p codex-exec`, but the build could not complete
in this environment because `codex-linux-sandbox` requires the system
`libcap` library (pkg-config could not find `libcap.pc`), so the test
suite did not finish.
------
[Codex
Task](https://chatgpt.com/codex/tasks/task_i_69a92230d0c08323b0417fbae810e6e0)
- rotate the paid-plan startup promo slot 50/50 between the existing
Codex App promo and a new Fast mode promo
- keep the Fast mode call to action platform-neutral so Windows can show
the same tip
- add a focused unit test to ensure the paid promo pool actually rotates
---------
Co-authored-by: Codex <noreply@openai.com>
### first half of changes, followed by #13510
Track plugin capabilities as derived summaries on `PluginLoadOutcome`
for enabled plugins with at least one skill/app/mcp.
Also add `Plugins` section to `user_instructions` injected on session
start. These introduce the plugins concept and list enabled plugins, but
do NOT currently include paths to enabled plugins or details on what
apps/mcps the plugins contain (current plan is to inject this on
@-mention). that can be adjusted in a follow up and based on evals.
### tests
Added/updated tests, confirmed locally that new `Plugins` section +
currently enabled plugins show up in `user_instructions`.
## Summary
- ensure `thread.resume` reuses the stored `gitInfo` instead of
rebuilding it from the live working tree
- persist and apply thread git metadata through the resume flow and add
a regression test covering branch mismatch cases
## Testing
- Not run (not requested)
Bumps [serde_with](https://github.com/jonasbb/serde_with) from 3.16.1 to
3.17.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/jonasbb/serde_with/releases">serde_with's
releases</a>.</em></p>
<blockquote>
<h2>serde_with v3.17.0</h2>
<h3>Added</h3>
<ul>
<li>Support <code>OneOrMany</code> with <code>smallvec</code> v1 (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/920">#920</a>,
<a
href="https://redirect.github.com/jonasbb/serde_with/issues/922">#922</a>)</li>
</ul>
<h3>Changed</h3>
<ul>
<li>Switch to <code>yaml_serde</code> for a maintained yaml dependency
by <a href="https://github.com/kazan417"><code>@kazan417</code></a> (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/921">#921</a>)</li>
<li>Bump MSRV to 1.82, since that is required for
<code>yaml_serde</code> dev-dependency.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="4031878a4c"><code>4031878</code></a>
Bump version to v3.17.0 (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/924">#924</a>)</li>
<li><a
href="204ae56f8b"><code>204ae56</code></a>
Bump version to v3.17.0</li>
<li><a
href="7812b5a006"><code>7812b5a</code></a>
serde_yaml 0.9 to yaml_serde 0.10 (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/921">#921</a>)</li>
<li><a
href="614bd8950b"><code>614bd89</code></a>
Bump MSRV to 1.82 as required by yaml_serde</li>
<li><a
href="518d0ed787"><code>518d0ed</code></a>
Suppress RUSTSEC-2026-0009 since we don't have untrusted time input in
tests ...</li>
<li><a
href="a6579a8984"><code>a6579a8</code></a>
Suppress RUSTSEC-2026-0009 since we don't have untrusted time input in
tests</li>
<li><a
href="9d4d0696e6"><code>9d4d069</code></a>
Implement OneOrMany for smallvec_1::SmallVec (<a
href="https://redirect.github.com/jonasbb/serde_with/issues/922">#922</a>)</li>
<li><a
href="fc78243e8c"><code>fc78243</code></a>
Add changelog</li>
<li><a
href="2b8c30bf67"><code>2b8c30b</code></a>
Implement OneOrMany for smallvec_1::SmallVec</li>
<li><a
href="2d9b9a1815"><code>2d9b9a1</code></a>
Carg.lock update</li>
<li>Additional commits viewable in <a
href="https://github.com/jonasbb/serde_with/compare/v3.16.1...v3.17.0">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Eric Traut <etraut@openai.com>
Bumps [strum_macros](https://github.com/Peternator7/strum) from 0.27.2
to 0.28.0.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/Peternator7/strum/blob/master/CHANGELOG.md">strum_macros's
changelog</a>.</em></p>
<blockquote>
<h2>0.28.0</h2>
<ul>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/461">#461</a>:
Allow any kind of passthrough attributes on
<code>EnumDiscriminants</code>.</p>
<ul>
<li>Previously only list-style attributes (e.g.
<code>#[strum_discriminants(derive(...))]</code>) were supported. Now
path-only
(e.g. <code>#[strum_discriminants(non_exhaustive)]</code>) and
name/value (e.g. <code>#[strum_discriminants(doc =
"foo")]</code>)
attributes are also supported.</li>
</ul>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/462">#462</a>:
Add missing <code>#[automatically_derived]</code> to generated impls not
covered by <a
href="https://redirect.github.com/Peternator7/strum/pull/444">#444</a>.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/466">#466</a>:
Bump MSRV to 1.71, required to keep up with updated <code>syn</code> and
<code>windows-sys</code> dependencies. This is a breaking change if
you're on an old version of rust.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/469">#469</a>:
Use absolute paths in generated proc macro code to avoid
potential name conflicts.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/465">#465</a>:
Upgrade <code>phf</code> dependency to v0.13.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/473">#473</a>:
Fix <code>cargo fmt</code> / <code>clippy</code> issues and add GitHub
Actions CI.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/477">#477</a>:
<code>strum::ParseError</code> now implements
<code>core::fmt::Display</code> instead
<code>std::fmt::Display</code> to make it <code>#[no_std]</code>
compatible. Note the <code>Error</code> trait wasn't available in core
until <code>1.81</code>
so <code>strum::ParseError</code> still only implements that in std.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/476">#476</a>:
<strong>Breaking Change</strong> - <code>EnumString</code> now
implements <code>From<&str></code>
(infallible) instead of <code>TryFrom<&str></code> when the
enum has a <code>#[strum(default)]</code> variant. This more accurately
reflects that parsing cannot fail in that case. If you need the old
<code>TryFrom</code> behavior, you can opt back in using
<code>parse_error_ty</code> and <code>parse_error_fn</code>:</p>
<pre lang="rust"><code>#[derive(EnumString)]
#[strum(parse_error_ty = strum::ParseError, parse_error_fn =
make_error)]
pub enum Color {
Red,
#[strum(default)]
Other(String),
}
<p>fn make_error(x: &str) -> strum::ParseError {
strum::ParseError::VariantNotFound
}
</code></pre></p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/431">#431</a>:
Fix bug where <code>EnumString</code> ignored the
<code>parse_err_ty</code>
attribute when the enum had a <code>#[strum(default)]</code>
variant.</p>
</li>
<li>
<p><a
href="https://redirect.github.com/Peternator7/strum/pull/474">#474</a>:
EnumDiscriminants will now copy <code>default</code> over from the
original enum to the Discriminant enum.</p>
<pre lang="rust"><code>#[derive(Debug, Default, EnumDiscriminants)]
#[strum_discriminants(derive(Default))] // <- Remove this in 0.28.
enum MyEnum {
#[default] // <- Will be the #[default] on the MyEnumDiscriminant
#[strum_discriminants(default)] // <- Remove this in 0.28
Variant0,
Variant1 { a: NonDefault },
}
</code></pre>
</li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="7376771128"><code>7376771</code></a>
Peternator7/0.28 (<a
href="https://redirect.github.com/Peternator7/strum/issues/475">#475</a>)</li>
<li><a
href="26e63cd964"><code>26e63cd</code></a>
Display exists in core (<a
href="https://redirect.github.com/Peternator7/strum/issues/477">#477</a>)</li>
<li><a
href="9334c728ee"><code>9334c72</code></a>
Make TryFrom and FromStr infallible if there's a default (<a
href="https://redirect.github.com/Peternator7/strum/issues/476">#476</a>)</li>
<li><a
href="0ccbbf823c"><code>0ccbbf8</code></a>
Honor parse_err_ty attribute when the enum has a default variant (<a
href="https://redirect.github.com/Peternator7/strum/issues/431">#431</a>)</li>
<li><a
href="2c9e5a9259"><code>2c9e5a9</code></a>
Automatically add Default implementation to EnumDiscriminant if it
exists on ...</li>
<li><a
href="e241243e48"><code>e241243</code></a>
Fix existing cargo fmt + clippy issues and add GH actions (<a
href="https://redirect.github.com/Peternator7/strum/issues/473">#473</a>)</li>
<li><a
href="639b67fefd"><code>639b67f</code></a>
feat: allow any kind of passthrough attributes on
<code>EnumDiscriminants</code> (<a
href="https://redirect.github.com/Peternator7/strum/issues/461">#461</a>)</li>
<li><a
href="0ea1e2d0fd"><code>0ea1e2d</code></a>
docs: Fix typo (<a
href="https://redirect.github.com/Peternator7/strum/issues/463">#463</a>)</li>
<li><a
href="36c051b910"><code>36c051b</code></a>
Upgrade <code>phf</code> to v0.13 (<a
href="https://redirect.github.com/Peternator7/strum/issues/465">#465</a>)</li>
<li><a
href="9328b38617"><code>9328b38</code></a>
Use absolute paths in proc macro (<a
href="https://redirect.github.com/Peternator7/strum/issues/469">#469</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/Peternator7/strum/compare/v0.27.2...v0.28.0">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Eric Traut <etraut@openai.com>
Bumps
[actions/download-artifact](https://github.com/actions/download-artifact)
from 7 to 8.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/actions/download-artifact/releases">actions/download-artifact's
releases</a>.</em></p>
<blockquote>
<h2>v8.0.0</h2>
<h2>v8 - What's new</h2>
<h3>Direct downloads</h3>
<p>To support direct uploads in <code>actions/upload-artifact</code>,
the action will no longer attempt to unzip all downloaded files.
Instead, the action checks the <code>Content-Type</code> header ahead of
unzipping and skips non-zipped files. Callers wishing to download a
zipped file as-is can also set the new <code>skip-decompress</code>
parameter to <code>false</code>.</p>
<h3>Enforced checks (breaking)</h3>
<p>A previous release introduced digest checks on the download. If a
download hash didn't match the expected hash from the server, the action
would log a warning. Callers can now configure the behavior on mismatch
with the <code>digest-mismatch</code> parameter. To be secure by
default, we are now defaulting the behavior to <code>error</code> which
will fail the workflow run.</p>
<h3>ESM</h3>
<p>To support new versions of the @actions/* packages, we've upgraded
the package to ESM.</p>
<h2>What's Changed</h2>
<ul>
<li>Don't attempt to un-zip non-zipped downloads by <a
href="https://github.com/danwkennedy"><code>@danwkennedy</code></a> in
<a
href="https://redirect.github.com/actions/download-artifact/pull/460">actions/download-artifact#460</a></li>
<li>Add a setting to specify what to do on hash mismatch and default it
to <code>error</code> by <a
href="https://github.com/danwkennedy"><code>@danwkennedy</code></a> in
<a
href="https://redirect.github.com/actions/download-artifact/pull/461">actions/download-artifact#461</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/download-artifact/compare/v7...v8.0.0">https://github.com/actions/download-artifact/compare/v7...v8.0.0</a></p>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="70fc10c6e5"><code>70fc10c</code></a>
Merge pull request <a
href="https://redirect.github.com/actions/download-artifact/issues/461">#461</a>
from actions/danwkennedy/digest-mismatch-behavior</li>
<li><a
href="f258da9a50"><code>f258da9</code></a>
Add change docs</li>
<li><a
href="ccc058e5fb"><code>ccc058e</code></a>
Fix linting issues</li>
<li><a
href="bd7976ba57"><code>bd7976b</code></a>
Add a setting to specify what to do on hash mismatch and default it to
<code>error</code></li>
<li><a
href="ac21fcf45e"><code>ac21fcf</code></a>
Merge pull request <a
href="https://redirect.github.com/actions/download-artifact/issues/460">#460</a>
from actions/danwkennedy/download-no-unzip</li>
<li><a
href="15999bff51"><code>15999bf</code></a>
Add note about package bumps</li>
<li><a
href="974686ed50"><code>974686e</code></a>
Bump the version to <code>v8</code> and add release notes</li>
<li><a
href="fbe48b1d27"><code>fbe48b1</code></a>
Update test names to make it clearer what they do</li>
<li><a
href="96bf374a61"><code>96bf374</code></a>
One more test fix</li>
<li><a
href="b8c4819ef5"><code>b8c4819</code></a>
Fix skip decompress test</li>
<li>Additional commits viewable in <a
href="https://github.com/actions/download-artifact/compare/v7...v8">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Improve observability of realtime conversation event handling by logging
non-audio events with payload details in the event loop, while skipping
audio-out events to reduce noise.
Support marketplace.json that points to a local file, with
```
"source":
{
"source": "local",
"path": "./plugin-1"
},
```
Add a new plugin/install endpoint which add the plugin to the cache folder and enable it in config.toml.
Addresses #13478
Summary
- Add two new scopes for `tui.notifications` config: `plan-mode-prompt`
and `user-input-requested`.
- Add Plan Mode prompt and user-input-requested notifications to the TUI
so these events surface consistently outside of plan mode
- Add helpers and tests to ensure the new notification types publish the
right titles, summaries, and type tags for filtering
- Add prioritization mechanism to fix an existing bug where one
notification event could arbitrarily overwrite others
Testing
- Manually tested plan mode to ensure that notification appeared
### Overview
This PR:
- Updates `app-server-test-client` to load OTEL settings from
`$CODEX_HOME/config.toml` and initializes its own OTEL provider.
- Add real client root spans to app-server test client traces.
This updates `codex-app-server-test-client` so its Datadog traces
reflect the full client-driven flow instead of a set of server spans
stitched together under a synthetic parent.
Before this change, the test client generated a fake `traceparent` once
and reused it for every JSON-RPC request. That kept the requests in one
trace, but there was no real client span at the top, so Datadog ended up
showing the sequence in a slightly misleading way, where all RPCs were
anchored under `initialize`.
Now the test client:
- loads OTEL settings from the normal Codex config path, including
`$CODEX_HOME/config.toml` and existing --config overrides
- initializes tracing the same way other Codex binaries do when trace
export is enabled
- creates a real client root span for each scripted command
- creates per-request client spans for JSON-RPC methods like
`initialize`, `thread/start`, and `turn/start`
- injects W3C trace context from the current client span into
request.trace instead of reusing a fabricated carrier
This gives us a cleaner trace shape in Datadog:
- one trace URL for the whole scripted flow
- a visible client root span
- proper client/server parent-child relationships for each app-server
request
## Problem
The `ansi`, `base16`, and `base16-256` syntax themes are designed to
emit ANSI palette colors so that highlighted code respects the user's
terminal color scheme. Syntect encodes this intent in the alpha channel
of its `Color` struct — a convention shared with `bat` — but
`convert_style` was ignoring it entirely, treating every foreground
color as raw RGB. This caused ANSI-family themes to produce hard-coded
RGB values (e.g. `Rgb(0x02, 0, 0)` instead of `Green`), defeating their
purpose and rendering them as near-invisible dark colors on most
terminals.
Reported in #12890.
## Mental model
Syntect themes use a compact encoding in their `Color` struct:
| `alpha` | Meaning of `r` | Mapped to |
|---------|----------------|-----------|
| `0x00` | ANSI palette index (0–255) | `RtColor::Black`…`Gray` for 0–7,
`Indexed(n)` for 8–255 |
| `0x01` | Unused (sentinel) | `None` — inherit terminal default fg/bg |
| `0xFF` | True RGB red channel | `RtColor::Rgb(r, g, b)` |
| other | Unexpected | `RtColor::Rgb(r, g, b)` (silent fallback) |
This encoding is a bat convention that three bundled themes rely on. The
new `convert_syntect_color` function decodes it; `ansi_palette_color`
maps indices 0–7 to ratatui's named ANSI variants.
| macOS - Dark | macOS - Light | Windows - ansi | Windows - base16 |
|---|---|---|---|
| <img width="1064" height="1205" alt="macos-dark"
src="https://github.com/user-attachments/assets/f03d92fb-b44b-4939-b2b9-503fde133811"
/> | <img width="1073" height="1227" alt="macos-light"
src="https://github.com/user-attachments/assets/2ecb2089-73b5-4676-bed8-e4e6794250b4"
/> |
|
|
## Non-goals
- Background color decoding — we intentionally skip backgrounds to
preserve the terminal's own background. The decoder supports it, but
`convert_style` does not apply it.
- Italic/underline changes — those remain suppressed as before.
- Custom `.tmTheme` support for ANSI encoding — only the bundled themes
use this convention.
## Tradeoffs
- The alpha-channel encoding is an undocumented bat/syntect convention,
not a formal spec. We match bat's behavior exactly, trading formality
for ecosystem compatibility.
- Indices 0–7 are mapped to ratatui's named variants (`Black`, `Red`, …,
`Gray`) rather than `Indexed(0)`…`Indexed(7)`. This lets terminals apply
bold/bright semantics to named colors, which is the expected behavior
for ANSI themes, but means the two representations are not perfectly
round-trippable.
## Architecture
All changes are in `codex-rs/tui/src/render/highlight.rs`, within the
style-conversion layer between syntect and ratatui:
```
syntect::highlighting::Color
└─ convert_syntect_color(color) [NEW — alpha-dispatch]
├─ a=0x00 → ansi_palette_color() [NEW — index→named/indexed]
├─ a=0x01 → None (terminal default)
├─ a=0xFF → Rgb(r,g,b) (standard opaque path)
└─ other → Rgb(r,g,b) (silent fallback)
```
`convert_style` delegates foreground mapping to `convert_syntect_color`
instead of inlining the `Rgb(r,g,b)` conversion. The core highlighter is
refactored into `highlight_to_line_spans_with_theme` (accepts an
explicit theme reference) so tests can highlight against specific themes
without mutating process-global state.
### ANSI-family theme contract
The ANSI-family themes (`ansi`, `base16`, `base16-256`) rely on upstream
alpha-channel encoding from two_face/syntect. We intentionally do
**not** validate this contract at runtime — if the upstream format
changes, the `ansi_themes_use_only_ansi_palette_colors` test catches it
at build time, long before it reaches users. A runtime warning would be
unactionable noise.
### Warning copy cleanup
User-facing warning messages were rewritten for clarity:
- Removed internal jargon ("alpha-encoded ANSI color markers", "RGB
fallback semantics", "persisted override config")
- Dropped "syntax" prefix from "syntax theme" — users just think "theme"
- Downgraded developer-only diagnostics (duplicate override, resolve
fallback) from `warn` to `debug`
## Observability
- The `ansi_themes_use_only_ansi_palette_colors` test enforces the
ANSI-family contract at build time.
- The snapshot test provides a regression tripwire for palette color
output.
- User-facing warnings are limited to actionable issues: unknown theme
names and invalid custom `.tmTheme` files.
## Tests
- **Unit tests for each alpha branch:** `alpha=0x00` with low index
(named color), `alpha=0x00` with high index (`Indexed`), `alpha=0x01`
(terminal default), unexpected alpha (falls back to RGB), ANSI white →
Gray mapping.
- **Integration test:**
`ansi_family_themes_use_terminal_palette_colors_not_rgb` — highlights a
Rust snippet with each ANSI-family theme and asserts zero `Rgb`
foreground colors appear.
- **Snapshot test:** `ansi_family_foreground_palette_snapshot` — records
the exact set of unique foreground colors each ANSI-family theme
produces, guarding against regressions.
- **Warning validation tests:** verify user-facing warnings for missing
custom themes, invalid `.tmTheme` files, and bundled theme resolution.
## Test plan
- [ ] `cargo test -p codex-tui` passes all new and existing tests
- [ ] Select `ansi`, `base16`, or `base16-256` theme and verify code
blocks render with terminal palette colors (not near-black RGB)
- [ ] Select a standard RGB theme (e.g. `dracula`) and verify no
regression in color output
## Summary
- update the /fast slash command description to mention fastest
inference
- mention the 3X plan usage tradeoff in the help copy
## Testing
- cargo test -p codex-tui slash_command (currently blocked by an
unrelated latest-main codex-tui compile error in chatwidget.rs:
refresh_queued_user_messages missing)
---------
Co-authored-by: Codex <noreply@openai.com>
This is PR 3 of the app-server tracing rollout.
PRs https://github.com/openai/codex/pull/13285 and
https://github.com/openai/codex/pull/13368 gave us inbound request spans
in app-server and propagated trace context through Submission. This
change finishes the next piece in core: when a request actually starts a
turn, we now create a core-owned long-lived span that stays open for the
real lifetime of the turn.
What changed:
- `Session::spawn_task` can now optionally create a long-lived turn span
and run the spawned task inside it
- `turn/start` uses that path, so normal turn execution stays under a
single core-owned span after the async handoff
- `review/start` uses the same pattern
- added a unit test that verifies the spawned turn task inherits the
submission dispatch trace ancestry
**Why**
The app-server request span is intentionally short-lived. Once work
crosses into core, we still want one span that covers the actual
execution window until completion or interruption. This keeps that
ownership where it belongs: in the layer that owns the runtime
lifecycle.
The electron app doesn't start up the app-server in a particular
workspace directory.
So sandbox setup happens in the app-installed directory instead of the
project workspace.
This allows the app do specify the workspace cwd so that the sandbox
setup actually sets up the ACLs instead of exiting fast and then having
the first shell command be slow.
Validated login + refresh flows. Removing scopes from the refresh
request until we have upgrade flow in place. Confirmed that tokens
refresh with existing scopes.
Follow-up to [#13388](https://github.com/openai/codex/pull/13388). This
uses the same general fix pattern as
[#12421](https://github.com/openai/codex/pull/12421), but in the
`codex-core` compact/resume/fork path.
## Why
`compact_resume_after_second_compaction_preserves_history` started
overflowing the stack on Windows CI after `#13388`.
The important part is that this was not a compaction-recursion bug. The
test exercises a path with several thin `async fn` wrappers around much
larger thread-spawn, resume, and fork futures. When one `async fn`
awaits another inline, the outer future stores the callee future as part
of its own state machine. In a long wrapper chain, that means a caller
can accidentally inline a lot more state than the source code suggests.
That is exactly what was happening here:
- `ThreadManager` convenience methods such as `start_thread`,
`resume_thread_from_rollout`, and `fork_thread` were inlining the larger
spawn/resume futures beneath them.
- `core_test_support::test_codex` added another wrapper layer on top of
those same paths.
- `compact_resume_fork` adds a few more helpers, and this particular
test drives the resume/fork path multiple times.
On Windows, that was enough to push both the libtest thread and Tokio
worker threads over the edge. The previous 8 MiB test-thread workaround
proved the failure was stack-related, but it did not address the
underlying future size.
## How This Was Debugged
The useful debugging pattern here was to turn the CI-only failure into a
local low-stack repro.
1. First, remove the explicit large-stack harness so the test runs on
the normal `#[tokio::test]` path.
2. Build the test binary normally.
3. Re-run the already-built `tests/all` binary directly with
progressively smaller `RUST_MIN_STACK` values.
Running the built binary directly matters: it keeps the reduced stack
size focused on the test process instead of also applying it to `cargo`
and `rustc`.
That made it possible to answer two questions quickly:
- Does the failure still reproduce without the workaround? Yes.
- Does boxing the wrapper futures actually buy back stack headroom? Also
yes.
After this change, the built test binary passes with
`RUST_MIN_STACK=917504` and still overflows at `786432`, which is enough
evidence to justify removing the explicit 8 MiB override while keeping a
deterministic low-stack repro for future debugging.
If we hit a similar issue again, the first places to inspect are thin
`async fn` wrappers that mostly forward into a much larger async
implementation.
## `Box::pin()` Primer
`async fn` compiles into a state machine. If a wrapper does this:
```rust
async fn wrapper() {
inner().await;
}
```
then `wrapper()` stores the full `inner()` future inline as part of its
own state.
If the wrapper instead does this:
```rust
async fn wrapper() {
Box::pin(inner()).await;
}
```
then the child future lives on the heap, and the outer future only
stores a pinned pointer to it. That usually trades one allocation for a
substantially smaller outer future, which is exactly the tradeoff we
want when the problem is stack pressure rather than raw CPU time.
Useful references:
-
[`Box::pin`](https://doc.rust-lang.org/std/boxed/struct.Box.html#method.pin)
- [Async book:
Pinning](https://rust-lang.github.io/async-book/04_pinning/01_chapter.html)
## What Changed
- Boxed the wrapper futures in `core/src/thread_manager.rs` around
`start_thread`, `resume_thread_from_rollout`, `fork_thread`, and the
corresponding `ThreadManagerState` spawn helpers so callers no longer
inline the full spawn/resume state machine through multiple layers.
- Boxed the matching test-only wrapper futures in
`core/tests/common/test_codex.rs` and
`core/tests/suite/compact_resume_fork.rs`, which sit directly on top of
the same path.
- Restored `compact_resume_after_second_compaction_preserves_history` in
`core/tests/suite/compact_resume_fork.rs` to a normal `#[tokio::test]`
and removed the explicit `TEST_STACK_SIZE_BYTES` thread/runtime sizing.
- Simplified a tiny helper in `compact_resume_fork` by making
`fetch_conversation_path()` synchronous, which removes one more
unnecessary future layer from the test path.
## Verification
- `cargo test -p codex-core --test all
suite::compact_resume_fork::compact_resume_after_second_compaction_preserves_history
-- --exact --nocapture`
- `cargo test -p codex-core --test all suite::compact_resume_fork --
--nocapture`
- Re-ran the built `codex-core` `tests/all` binary directly with reduced
stack sizes:
- `RUST_MIN_STACK=917504` passes
- `RUST_MIN_STACK=786432` still overflows
- `cargo test -p codex-core`
- Still fails locally in unrelated existing integration areas that
expect the `codex` / `test_stdio_server` binaries or hit the existing
`search_tool` wiremock mismatches.
## Summary
Changes the permission profile shape from a bare network boolean to a
nested object.
Before:
```yaml
permissions:
network: true
```
After:
```yaml
permissions:
network:
enabled: true
```
This also updates the shared Rust and app-server protocol types so
`PermissionProfile.network` is no longer `Option<bool>`, but
`Option<NetworkPermissions>` with `enabled: Option<bool>`.
## What Changed
- Updated `PermissionProfile` in `codex-rs/protocol/src/models.rs`:
- `pub network: Option<bool>` -> `pub network:
Option<NetworkPermissions>`
- Added `NetworkPermissions` with:
- `pub enabled: Option<bool>`
- Changed emptiness semantics so `network` is only considered empty when
`enabled` is `None`
- Updated skill metadata parsing to accept `permissions.network.enabled`
- Updated core permission consumers to read
`network.enabled.unwrap_or(false)` where a concrete boolean is needed
- Updated app-server v2 protocol types and regenerated schema/TypeScript
outputs
- Updated docs to mention `additionalPermissions.network.enabled`
## Why
Enterprises can already constrain approvals, sandboxing, and web search
through `requirements.toml` and MDM, but feature flags were still only
configurable as managed defaults. That meant an enterprise could suggest
feature values, but it could not actually pin them.
This change closes that gap and makes enterprise feature requirements
behave like the other constrained settings. The effective feature set
now stays consistent with enterprise requirements during config load,
when config writes are validated, and when runtime code mutates feature
flags later in the session.
It also tightens the runtime API for managed features. `ManagedFeatures`
now follows the same constraint-oriented shape as `Constrained<T>`
instead of exposing panic-prone mutation helpers, and production code
can no longer construct it through an unconstrained `From<Features>`
path.
The PR also hardens the `compact_resume_fork` integration coverage on
Windows. After the feature-management changes,
`compact_resume_after_second_compaction_preserves_history` was
overflowing the libtest/Tokio thread stacks on Windows, so the test now
uses an explicit larger-stack harness as a pragmatic mitigation. That
may not be the ideal root-cause fix, and it merits a parallel
investigation into whether part of the async future chain should be
boxed to reduce stack pressure instead.
## What Changed
Enterprises can now pin feature values in `requirements.toml` with the
requirements-side `features` table:
```toml
[features]
personality = true
unified_exec = false
```
Only canonical feature keys are allowed in the requirements `features`
table; omitted keys remain unconstrained.
- Added a requirements-side pinned feature map to
`ConfigRequirementsToml`, threaded it through source-preserving
requirements merge and normalization in `codex-config`, and made the
TOML surface use `[features]` (while still accepting legacy
`[feature_requirements]` for compatibility).
- Exposed `featureRequirements` from `configRequirements/read`,
regenerated the JSON/TypeScript schema artifacts, and updated the
app-server README.
- Wrapped the effective feature set in `ManagedFeatures`, backed by
`ConstrainedWithSource<Features>`, and changed its API to mirror
`Constrained<T>`: `can_set(...)`, `set(...) -> ConstraintResult<()>`,
and result-returning `enable` / `disable` / `set_enabled` helpers.
- Removed the legacy-usage and bulk-map passthroughs from
`ManagedFeatures`; callers that need those behaviors now mutate a plain
`Features` value and reapply it through `set(...)`, so the constrained
wrapper remains the enforcement boundary.
- Removed the production loophole for constructing unconstrained
`ManagedFeatures`. Non-test code now creates it through the configured
feature-loading path, and `impl From<Features> for ManagedFeatures` is
restricted to `#[cfg(test)]`.
- Rejected legacy feature aliases in enterprise feature requirements,
and return a load error when a pinned combination cannot survive
dependency normalization.
- Validated config writes against enterprise feature requirements before
persisting changes, including explicit conflicting writes and
profile-specific feature states that normalize into invalid
combinations.
- Updated runtime and TUI feature-toggle paths to use the constrained
setter API and to persist or apply the effective post-constraint value
rather than the requested value.
- Updated the `core_test_support` Bazel target to include the bundled
core model-catalog fixtures in its runtime data, so helper code that
resolves `core/models.json` through runfiles works in remote Bazel test
environments.
- Renamed the core config test coverage to emphasize that effective
feature values are normalized at runtime, while conflicting persisted
config writes are rejected.
- Ran `compact_resume_after_second_compaction_preserves_history` inside
an explicit 8 MiB test thread and Tokio runtime worker stack, following
the existing larger-stack integration-test pattern, to keep the Windows
`compact_resume_fork` test slice from aborting while a parallel
investigation continues into whether some of the underlying async
futures should be boxed.
## Verification
- `cargo test -p codex-config`
- `cargo test -p codex-core feature_requirements_ -- --nocapture`
- `cargo test -p codex-core
load_requirements_toml_produces_expected_constraints -- --nocapture`
- `cargo test -p codex-core
compact_resume_after_second_compaction_preserves_history -- --nocapture`
- `cargo test -p codex-core compact_resume_fork -- --nocapture`
- Re-ran the built `codex-core` `tests/all` binary with
`RUST_MIN_STACK=262144` for
`compact_resume_after_second_compaction_preserves_history` to confirm
the explicit-stack harness fixes the deterministic low-stack repro.
- `cargo test -p codex-core`
- This still fails locally in unrelated integration areas that expect
the `codex` / `test_stdio_server` binaries or hit existing `search_tool`
wiremock mismatches.
## Docs
`developers.openai.com/codex` should document the requirements-side
`[features]` table for enterprise and MDM-managed configuration,
including that it only accepts canonical feature keys and that
conflicting config writes are rejected.
## Summary
`PermissionProfile.network` could not be preserved when additional or
compiled permissions resolved to
`SandboxPolicy::ReadOnly`, because `ReadOnly` had no network_access
field. This change makes read-only + network
enabled representable directly and threads that through the protocol,
app-server v2 mirror, and permission-
merging logic.
## What changed
- Added `network_access: bool` to `SandboxPolicy::ReadOnly` in the core
protocol and app-server v2 protocol.
- Kept backward compatibility by defaulting the new field to false, so
legacy read-only payloads still
deserialize unchanged.
- Updated `has_full_network_access()` and sandbox summaries to respect
read-only network access.
- Preserved PermissionProfile.network when:
- compiling skill permission profiles into sandbox policies
- normalizing additional permissions
- merging additional permissions into existing sandbox policies
- Updated the approval overlay to show network in the rendered
permission rule when requested.
- Regenerated app-server schema fixtures for the new v2 wire shape.
# 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.
• Keep Windows sandbox runner launches working from packaged installs by
running the helper from a user-owned runtime location.
On some Windows installs, the packaged helper location is difficult to
use reliably for sandboxed runner launches even though the binaries are
present. This change works around that by copying codex-
command-runner.exe into CODEX_HOME/.sandbox-bin/, reusing that copy
across launches, and falling back to the existing packaged-path lookup
if anything goes wrong.
The runtime copy lives in a dedicated directory with tighter ACLs than
.sandbox: sandbox users can read and execute the runner there, but they
cannot modify it. This keeps the workaround focused on the
command runner, leaves the setup helper on its trusted packaged path,
and adds logging so it is clear which runner path was selected at
launch.
### Summary
Propagate trace context originating at app-server RPC method handlers ->
codex core submission loop (so this includes spans such as `run_turn`!).
This implements PR 2 of the app-server tracing rollout.
This also removes the old lower-level env-based reparenting in core so
explicit request/submission ancestry wins instead of being overridden by
ambient `TRACEPARENT` state.
### What changed
- Added `trace: Option<W3cTraceContext>` to codex_protocol::Submission
- Taught `Codex::submit()` / `submit_with_id()` to automatically capture
the current span context when constructing or forwarding a submission
- Wrapped the core submission loop in a submission_dispatch span
parented from Submission.trace
- Warn on invalid submission trace carriers and ignore them cleanly
- Removed the old env-based downstream reparenting path in core task
execution
- Stopped OTEL provider init from implicitly attaching env trace context
process-wide
- Updated mcp-server Submission call sites for the new field
Added focused unit tests for:
- capturing trace context into Submission
- preferring `Submission.trace` when building the core dispatch span
### Why
PR 1 gave us consistent inbound request spans in app-server, but that
only covered the transport boundary. For long-running work like turns
and reviews, the important missing piece was preserving ancestry after
the request handler returns and core continues work on a different async
path.
This change makes that handoff explicit and keeps the parentage rules
simple:
- app-server request span sets the current context
- `Submission.trace` snapshots that context
- core restores it once, at the submission boundary
- deeper core spans inherit naturally
That also lets us stop relying on env-based reparenting for this path,
which was too ambient and could override explicit ancestry.
This adds a first-class app-server v2 `skills/changed` notification for
the existing skills live-reload signal.
Before this change, clients only had the legacy raw
`codex/event/skills_update_available` event. With this PR, v2 clients
can listen for a typed JSON-RPC notification instead of depending on the
legacy `codex/event/*` stream, which we want to remove soon.
load plugin-apps from `.app.json`.
make apps runtime-mentionable iff `codex_apps` MCP actually exposes
tools for that `connector_id`.
if the app isn't available, it's filtered out of runtime connector set,
so no tools are added and no app-mentions resolve.
right now we don't have a clean cli-side error for an app not being
installed. can look at this after.
### Tests
Added tests, tested locally that using a plugin that bundles an app
picks up the app.
## Summary
Instead of always adding inner function call outputs to the model
context, let js code decide which ones to return.
- Stop auto-hoisting nested tool outputs from `codex.tool(...)` into the
outer `js_repl` function output.
- Keep `codex.tool(...)` return values unchanged as structured JS
objects.
- Add `codex.emitImage(...)` as the explicit path for attaching an image
to the outer `js_repl` function output.
- Support emitting from a direct image URL, a single `input_image` item,
an explicit `{ bytes, mimeType }` object, or a raw tool response object
containing exactly one image.
- Preserve existing `view_image` original-resolution behavior when JS
emits the raw `view_image` tool result.
- Suppress the special `ViewImageToolCall` event for `js_repl`-sourced
`view_image` calls so nested inspection stays side-effect free until JS
explicitly emits.
- Update the `js_repl` docs and generated project instructions with both
recommended patterns:
- `await codex.emitImage(codex.tool("view_image", { path }))`
- `await codex.emitImage({ bytes: await page.screenshot({ type: "jpeg",
quality: 85 }), mimeType: "image/jpeg" })`
#### [git stack](https://github.com/magus/git-stack-cli)
- ✅ `1` https://github.com/openai/codex/pull/13050
- 👉 `2` https://github.com/openai/codex/pull/13331
- ⏳ `3` https://github.com/openai/codex/pull/13049
## Summary
Add original-resolution support for `view_image` behind the
under-development `view_image_original_resolution` feature flag.
When the flag is enabled and the target model is `gpt-5.3-codex` or
newer, `view_image` now preserves original PNG/JPEG/WebP bytes and sends
`detail: "original"` to the Responses API instead of using the legacy
resize/compress path.
## What changed
- Added `view_image_original_resolution` as an under-development feature
flag.
- Added `ImageDetail` to the protocol models and support for serializing
`detail: "original"` on tool-returned images.
- Added `PromptImageMode::Original` to `codex-utils-image`.
- Preserves original PNG/JPEG/WebP bytes.
- Keeps legacy behavior for the resize path.
- Updated `view_image` to:
- use the shared `local_image_content_items_with_label_number(...)`
helper in both code paths
- select original-resolution mode only when:
- the feature flag is enabled, and
- the model slug parses as `gpt-5.3-codex` or newer
- Kept local user image attachments on the existing resize path; this
change is specific to `view_image`.
- Updated history/image accounting so only `detail: "original"` images
use the docs-based GPT-5 image cost calculation; legacy images still use
the old fixed estimate.
- Added JS REPL guidance, gated on the same feature flag, to prefer JPEG
at 85% quality unless lossless is required, while still allowing other
formats when explicitly requested.
- Updated tests and helper code that construct
`FunctionCallOutputContentItem::InputImage` to carry the new `detail`
field.
## Behavior
### Feature off
- `view_image` keeps the existing resize/re-encode behavior.
- History estimation keeps the existing fixed-cost heuristic.
### Feature on + `gpt-5.3-codex+`
- `view_image` sends original-resolution images with `detail:
"original"`.
- PNG/JPEG/WebP source bytes are preserved when possible.
- History estimation uses the GPT-5 docs-based image-cost calculation
for those `detail: "original"` images.
#### [git stack](https://github.com/magus/git-stack-cli)
- 👉 `1` https://github.com/openai/codex/pull/13050
- ⏳ `2` https://github.com/openai/codex/pull/13331
- ⏳ `3` https://github.com/openai/codex/pull/13049
## Summary
- add the v2 `thread/metadata/update` API, including
protocol/schema/TypeScript exports and app-server docs
- patch stored thread `gitInfo` in sqlite without resuming the thread,
with validation plus support for explicit `null` clears
- repair missing sqlite thread rows from rollout data before patching,
and make those repairs safe by inserting only when absent and updating
only git columns so newer metadata is not clobbered
- keep sqlite authoritative for mutable thread git metadata by
preserving existing sqlite git fields during reconcile/backfill and only
using rollout `SessionMeta` git fields to fill gaps
- add regression coverage for the endpoint, repair paths, concurrent
sqlite writes, clearing git fields, and rollout/backfill reconciliation
- fix the login server shutdown race so cancelling before the waiter
starts still terminates `block_until_done()` correctly
## Testing
- `cargo test -p codex-state
apply_rollout_items_preserves_existing_git_branch_and_fills_missing_git_fields`
- `cargo test -p codex-state
update_thread_git_info_preserves_newer_non_git_metadata`
- `cargo test -p codex-core
backfill_sessions_preserves_existing_git_branch_and_fills_missing_git_fields`
- `cargo test -p codex-app-server thread_metadata_update`
- `cargo test`
- currently fails in existing `codex-core` grep-files tests with
`unsupported call: grep_files`:
- `suite::grep_files::grep_files_tool_collects_matches`
- `suite::grep_files::grep_files_tool_reports_empty_results`
## Summary
- submit `Enter` steers immediately while a turn is already running
instead of routing them through `queued_user_messages`
- keep those submitted steers visible in the footer as `pending_steers`
until core records them as a user message or aborts the turn
- reconcile pending steers on `ItemCompleted(UserMessage)`, not
`RawResponseItem`
- emit user-message item lifecycle for leftover pending input at task
finish, then remove the TUI `TurnComplete` fallback
- keep `queued_user_messages` for actual queued drafts, rendered below
pending steers
## Problem
While the assistant was generating, pressing `Enter` could send the
input into `queued_user_messages`. That queue only drains after the turn
ends, so ordinary steers behaved like queued drafts instead of landing
at the next core sampling boundary.
The first version of this fix also used `RawResponseItem` to decide when
a steer had landed. Review feedback was that this is the wrong
abstraction for client behavior.
There was also a late edge case in core: if pending steer input was
accepted after the final sampling decision but before `TurnComplete`,
core would record that user message into history at task finish without
emitting `ItemStarted(UserMessage)` / `ItemCompleted(UserMessage)`. TUI
had a fallback to paper over that gap locally.
## Approach
- `Enter` during an active turn now submits a normal `Op::UserTurn`
immediately
- TUI keeps a local pending-steer preview instead of rendering that user
message into history immediately
- when core records the steer as `ItemCompleted(UserMessage)`, TUI
matches and removes the corresponding pending preview, then renders the
committed user message
- core now emits the same user-message lifecycle when
`on_task_finished(...)` drains leftover pending user input, before
`TurnComplete`
- with that lifecycle gap closed in core, TUI no longer needs to flush
pending steers into history on `TurnComplete`
- if the turn is interrupted, pending steers and queued drafts are both
restored into the composer, with pending steers first
## Notes
- `Tab` still uses the real queued-message path
- `queued_user_messages` and `pending_steers` are separate state with
separate semantics
- the pending-steer matching key is built directly from `UserInput`
- this removes the new TUI dependency on `RawResponseItem`
## Validation
- `just fmt`
- `cargo test -p codex-core
task_finish_emits_turn_item_lifecycle_for_leftover_pending_user_input --
--nocapture`
- `cargo test -p codex-tui`
Update config.toml plugin entries to use
<plugin_name>@<marketplace_name> as the key.
Plugin now stays in
[plugins/cache/marketplace-name/plugin-name/$version/]
Clean up the plugin code structure.
Add plugin install functionality (not used yet).
## Summary
- Route delegated realtime handoff turns from all handoff message texts,
preserving order
- Fallback to input_transcript only when no messages are present
- Add regression coverage for multi-message handoff requests
Realized EventMsg generated types were unintentionally removed as part
of this PR: https://github.com/openai/codex/pull/13375
Turns out our TypeScript export pipeline relied on transitively reaching
`EventMsg`. We should still export `EventMsg` explicitly since we're
still emitting `codex/event/*` events (for now, but getting dropped soon
as well).
## Summary
This removes the old app-server v1 methods and notifications we no
longer need, while keeping the small set the main codex app client still
depends on for now.
The remaining legacy surface is:
- `initialize`
- `getConversationSummary`
- `getAuthStatus`
- `gitDiffToRemote`
- `fuzzyFileSearch`
- `fuzzyFileSearch/sessionStart`
- `fuzzyFileSearch/sessionUpdate`
- `fuzzyFileSearch/sessionStop`
And the raw `codex/event/*` notifications emitted from core. These
notifications will be removed in a followup PR.
## What changed
- removed deprecated v1 request variants from the protocol and
app-server dispatcher
- removed deprecated typed notifications: `authStatusChange`,
`loginChatGptComplete`, and `sessionConfigured`
- updated the app-server test client to use v2 flows instead of deleted
v1 flows
- deleted legacy-only app-server test suites and added focused coverage
for `getConversationSummary`
- regenerated app-server schema fixtures and updated the MCP interface
docs to match the remaining compatibility surface
## Testing
- `just write-app-server-schema`
- `cargo test -p codex-app-server-protocol`
- `cargo test -p codex-app-server`
# 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.
## Summary
- collapse parsed command output to a single `Unknown` whenever the
normal parse includes any unknown entry
- preserve the existing parsing flow and existing `cd` handling,
including the current `cd && ...` collapse behavior
- trim redundant tests and add focused coverage for collapse-on-unknown
cases
## Testing
- `cargo test -p codex-shell-command`
## Summary
- write app-server SQLite logs at TRACE level when SQLite is enabled
- source app-server `/feedback` log attachments from SQLite for the
requested thread when available
- flush buffered SQLite log writes before `/feedback` queries them so
newly emitted events are not lost behind the async inserter
- include same-process threadless SQLite rows in those `/feedback` logs
so the attachment matches the process-wide feedback buffer more closely
- keep the existing in-memory ring buffer fallback unchanged, including
when the SQLite query returns no rows
## Details
- add a byte-bounded `query_feedback_logs` helper in `codex-state` so
`/feedback` does not fetch all rows before truncating
- scope SQLite feedback logs to the requested thread plus threadless
rows from the same `process_uuid`
- format exported SQLite feedback lines with the log level prefix to
better match the in-memory feedback formatter
- add an explicit `LogDbLayer::flush()` control path and await it in
app-server before querying SQLite for feedback logs
- pass optional SQLite log bytes through `codex-feedback` as the
`codex-logs.log` attachment override
- leave TUI behavior unchanged apart from the updated `upload_feedback`
call signature
- add regression coverage for:
- newest-within-budget ordering
- excluding oversized newest rows
- including same-process threadless rows
- keeping the newest suffix across mixed thread and threadless rows
- matching the feedback formatter shape aside from span prefixes
- falling back to the in-memory snapshot when SQLite returns no logs
- flushing buffered SQLite rows before querying
## Follow-up
- SQLite feedback exports still do not reproduce span prefixes like
`feedback-thread{thread_id=...}:`; there is a `TODO(ccunningham)` in
`codex-rs/state/src/log_db.rs` for that follow-up.
## Testing
- `cd codex-rs && cargo test -p codex-state`
- `cd codex-rs && cargo test -p codex-app-server`
- `cd codex-rs && just fmt`
## Summary
- add an `--experimental` flag to the export binary and thread the
option through TypeScript and JSON schema generation
- flatten the v2 schema bundle into a datamodel-code-generator-friendly
`codex_app_server_protocol.v2.schemas.json` export
- retarget shared helper refs to namespaced v2 definitions, add coverage
for the new export behavior, and vendor the generated schema fixtures
## Validation
- `cargo test -p codex-app-server-protocol` (71 unit tests and bin
targets passed locally; the final schema fixture integration target was
revalidated via fresh schema regeneration and a tree diff)
- `./target/debug/write_schema_fixtures --schema-root <tmpdir>`
- `diff -rq app-server-protocol/schema <tmpdir>`
## Tickets
- None
# 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.
## Summary
- add a direct install script for Windows at
`scripts/install/install.ps1`
- extend release staging so `install.ps1` is published alongside
`install.sh`
- install the Windows runtime payload (`codex.exe`, `rg.exe`, and helper
binaries) from the existing platform npm package
## Dependencies
- Depends on https://github.com/openai/codex/pull/12740
## Testing
- Smoke-tested with powershell
followup to https://github.com/openai/codex/pull/13212 to expose fast
tier controls to app server
(majority of this PR is generated schema jsons - actual code is +69 /
-35 and +24 tests )
- add service tier fields to the app-server protocol surfaces used by
thread lifecycle, turn start, config, and session configured events
- thread service tier through the app-server message processor and core
thread config snapshots
- allow runtime config overrides to carry service tier for app-server
callers
cleanup:
- Removing useless "legacy" code supporting "standard" - we moved to
None | "fast", so "standard" is not needed.
Closes#3493
## Problem
When a user's home directory (or any ancestor) contains a broad
`.gitignore` (e.g. `*` + `!.gitignore`), the `@` file mention picker in
Codex silently hides valid repository files like `package.json`. The
picker returns `no matches` for searches that should succeed. This is
surprising because manually typed paths still work, making the failure
hard to diagnose.
## Mental model
Git itself never walks above the repository root to assemble its ignore
list. Its `.gitignore` resolution is strictly scoped: it reads
`.gitignore` files from the repo root downward, the per-repo
`.git/info/exclude`, and the user's global excludes file (via
`core.excludesFile`). A `.gitignore` sitting in a parent directory above
the repo root has no effect on `git status`, `git ls-files`, or any
other git operation. Our file search should replicate this contract
exactly.
The `ignore` crate's `WalkBuilder` has a `require_git` flag that
controls whether it follows this contract:
- `require_git(false)` (the previous setting): the walker reads
`.gitignore` files from _all_ ancestor directories, even those above or
outside the repository root. This is a deliberate divergence from git's
behavior in the `ignore` crate, intended for non-git use cases. It means
a `~/.gitignore` with `*` will suppress every file in the walk—something
git itself would never do.
- `require_git(true)` (this fix): the walker only applies `.gitignore`
semantics when it detects a `.git` directory, scoping ignore resolution
to the repository boundary. This matches git's own behavior: parent
`.gitignore` files above the repo root have no effect.
The fix is a one-line change: `require_git(false)` becomes
`require_git(true)`.
## How `require_git(false)` got here
The setting was introduced in af338cc (#2981, "Improve @ file search:
include specific hidden dirs such as .github, .gitlab"). That PR's goal
was to make hidden directories like `.github` and `.vscode` discoverable
by setting `.hidden(false)` on the walker. The `require_git(false)` was
added alongside it with the comment _"Don't require git to be present to
apply git-related ignore rules"_—the author likely intended gitignore
rules to still filter results even when no `.git` directory exists (e.g.
searching an extracted tarball that has a `.gitignore` but no `.git`).
The unintended consequence: with `require_git(false)`, the `ignore`
crate walks _above_ the search root to find `.gitignore` files in
ancestor directories. This is a side effect the original author almost
certainly didn't anticipate. The PR message says "Preserve `.gitignore`
semantics," but `require_git(false)` actually _breaks_ git's semantics
by applying ancestor ignore files that git itself would never read.
In short: the intent was "apply gitignore even without `.git`" but the
effect was "apply gitignore from every ancestor directory." This fix
restores git-correct scoping.
## Non-goals
- This PR does not change behavior when `respect_gitignore` is `false`
(that path already disables all git-related ignore rules).
- The first test
(`parent_gitignore_outside_repo_does_not_hide_repo_files`) intentionally
omits `git init`. The `ignore` crate's `require_git(true)` causes it to
skip gitignore processing entirely when no `.git` exists, which is the
desired behavior for that scenario. A second test
(`git_repo_still_respects_local_gitignore_when_enabled`) covers the
complementary case with a real git repo.
## Tradeoffs
**Behavioral shift**: With `require_git(true)`, directories that contain
`.gitignore` files but are _not_ inside a git repository will no longer
have those ignore rules applied during `@` search. This is a correctness
improvement for the primary use case (searching inside repos), but
changes behavior for the edge case of searching non-repo directories
that happen to have `.gitignore` files. In practice, Codex is
overwhelmingly used inside git repositories, so this tradeoff strongly
favors the fix.
**Two test strategies**: The first test omits `git init` to verify
parent ignore leakage is blocked; the second runs `git init` to verify
the repo's own `.gitignore` is still honored. Together they cover both
sides of the `require_git(true)` contract.
## Architecture
The change is in `walker_worker()` within
`codex-rs/file-search/src/lib.rs`, which configures the
`ignore::WalkBuilder` used by the file search walker thread. The walker
feeds discovered file paths into `nucleo` for fuzzy matching. The
`require_git` flag controls whether the walker consults `.gitignore`
files at all—it sits upstream of all ignore processing.
```
walker_worker
└─ WalkBuilder::new(root)
├─ .hidden(false) — include dotfiles
├─ .follow_links(true) — follow symlinks
├─ .require_git(true) — ← THE FIX: only apply gitignore in git repos
└─ (conditional) git_ignore(false), git_global(false), etc.
└─ applied when respect_gitignore == false
```
## Tests
- `parent_gitignore_outside_repo_does_not_hide_repo_files`: creates a
temp directory tree with a parent `.gitignore` containing `*`, a child
"repo" directory with `package.json` and `.vscode/settings.json`, and
asserts that both files are discoverable via `run()` with
`respect_gitignore: true`.
- `git_repo_still_respects_local_gitignore_when_enabled`: the
complementary test—runs `git init` inside the child directory and
verifies that the repo's own `.gitignore` exclusions still work (e.g.
`.vscode/extensions.json` is excluded while `.vscode/settings.json` is
whitelisted). Confirms that `require_git(true)` does not disable
gitignore processing inside actual git repositories.
- add a local Fast mode setting in codex-core (similar to how model id
is currently stored on disk locally)
- send `service_tier=priority` on requests when Fast is enabled
- add `/fast` in the TUI and persist it locally
- feature flag
## Problem
Before this change, composer paths that cleared the textarea after
submit or slash-command dispatch
also cleared the textarea kill buffer. That meant a user could `Ctrl+K`
part of a draft, trigger a
composer action that cleared the visible draft, and then lose the
ability to `Ctrl+Y` the killed
text back.
This was especially awkward for workflows where the user wants to
temporarily remove text, run a
composer action such as changing reasoning level or dispatching a slash
command, and then restore
the killed text into the now-empty draft.
## Mental model
This change separates visible draft state from editing-history state.
The visible draft includes the current textarea contents and text
elements that should be cleared
when the composer submits or dispatches a command. The kill buffer is
different: it represents the
most recent killed text and should survive those composer-driven clears
so the user can still yank
it back afterward.
After this change, submit and slash-command dispatch still clear the
visible textarea contents, but
they no longer erase the most recent kill.
## Non-goals
This does not implement a multi-entry kill ring or change the semantics
of `Ctrl+K` and `Ctrl+Y`
beyond preserving the existing yank target across these clears.
It also does not change how submit, slash-command parsing, prompt
expansion, or attachment handling
work, except that those flows no longer discard the textarea kill buffer
as a side effect of
clearing the draft.
## Tradeoffs
The main tradeoff is that clearing the visible textarea is no longer
equivalent to fully resetting
all editing state. That is intentional here, because submit and
slash-command dispatch are composer
actions, not requests to forget the user's most recent kill.
The benefit is better editing continuity. The cost is that callers must
understand that full-buffer
replacement resets visible draft state but not the kill buffer.
## Architecture
The behavioral change is in `TextArea`: full-buffer replacement now
rebuilds text and elements
without clearing `kill_buffer`.
`ChatComposer` already clears the textarea after successful submit and
slash-command dispatch by
calling into those textarea replacement paths. With this change, those
existing composer flows
inherit the new behavior automatically: the visible draft is cleared,
but the last killed text
remains available for `Ctrl+Y`.
The tests cover both layers:
- `TextArea` verifies that the kill buffer survives full-buffer
replacement.
- `ChatComposer` verifies that it survives submit.
- `ChatComposer` also verifies that it survives slash-command dispatch.
## Observability
There is no dedicated logging for kill-buffer preservation. The most
direct way to reason about the
behavior is to inspect textarea-wide replacement paths and confirm
whether they treat the kill
buffer as visible-buffer state or as editing-history state.
If this regresses in the future, the likely failure mode is simple and
user-visible: `Ctrl+Y` stops
restoring text after submit or slash-command clears even though ordinary
kill/yank still works
within a single uninterrupted draft.
## Tests
Added focused regression coverage for the new contract:
- `kill_buffer_persists_across_set_text`
- `kill_buffer_persists_after_submit`
- `kill_buffer_persists_after_slash_command_dispatch`
Local verification:
- `just fmt`
- `cargo test -p codex-tui`
---------
Co-authored-by: Josh McKinney <joshka@openai.com>
## Summary
This change removes the compiled permissions field from skill metadata
and keeps permission_profile as the single source of truth.
Skill loading no longer compiles skill permissions eagerly. Instead, the
zsh-fork skill escalation path compiles `skill.permission_profile` when
it needs to determine the sandbox to apply for a skill script.
## Behavior change
For skills that declare:
```
permissions: {}
```
we now treat that the same as having no skill permissions override,
instead of creating and using a default readonly sandbox. This change
makes the behavior more intuitive:
- only non-empty skill permission profiles affect sandboxing
- omitting permissions and writing permissions: {} now mean the same
thing
- skill metadata keeps a single permissions representation instead of
storing derived state too
Overall, this makes skill sandbox behavior easier to understand and more
predictable.
Currently we emit `thread/status/changed` with `Idle` status right
before sending `thread/started` event (which also has `Idle` status in
it).
It feels that there is no point in that as client has no way to know
prior state of the thread as it didn't exist yet, so silence these kinds
of notifications.
This is a follow-up for https://github.com/openai/codex/pull/13047
## Why
We had a race where `turn/started` could be observed before the thread
had actually transitioned to `Active`. This was because we eagerly
emitted `turn/started` in the request handler for `turn/start` (and
`review/start`).
That was showing up as flaky `thread/resume` tests, but the real issue
was broader: a client could see `turn/started` and still get back an
idle thread immediately afterward.
The first idea was to eagerly call
`thread_watch_manager.note_turn_started(...)` from the `turn/start`
request path. That turns out to be unsafe, because
`submit(Op::UserInput)` only queues work. If a turn starts and completes
quickly, request-path bookkeeping can race with the real lifecycle
events and leave stale running state behind.
**The real fix** is to move `turn/started` to emit only after the turn
_actually_ starts, so we do that by waiting for the
`EventMsg::TurnStarted` notification emitted by codex core. We do this
for both `turn/start` and `review/start`.
I also verified this change is safe for our first-party codex apps -
they don't have any assumptions that `turn/started` is emitted before
the RPC response to `turn/start` (which is correct anyway).
I also removed `single_client_mode` since it isn't really necessary now.
## Testing
- `cargo test -p codex-app-server thread_resume -- --nocapture`
- `cargo test -p codex-app-server
'suite::v2::turn_start::turn_start_emits_notifications_and_accepts_model_override'
-- --exact --nocapture`
- `cargo test -p codex-app-server`
- migrate the realtime websocket transport to the new session and
handoff flow
- make the realtime model configurable in config.toml and use API-key
auth for the websocket
---------
Co-authored-by: Codex <noreply@openai.com>
### Overview
This PR adds the first piece of tracing for app-server JSON-RPC
requests.
There are two main changes:
- JSON-RPC requests can now take an optional W3C trace context at the
top level via a `trace` field (`traceparent` / `tracestate`).
- app-server now creates a dedicated request span for every inbound
JSON-RPC request in `MessageProcessor`, and uses the request-level trace
context as the parent when present.
For compatibility with existing flows, app-server still falls back to
the TRACEPARENT env var when there is no request-level traceparent.
This PR is intentionally scoped to the app-server boundary. In a
followup, we'll actually propagate trace context through the async
handoff into core execution spans like run_turn, which will make
app-server traces much more useful.
### Spans
A few details on the app-server span shape:
- each inbound request gets its own server span
- span/resource names are based on the JSON-RPC method (`initialize`,
`thread/start`, `turn/start`, etc.)
- spans record transport (stdio vs websocket), request id, connection
id, and client name/version when available
- `initialize` stores client metadata in session state so later requests
on the same connection can reuse it
Currently `thread/name/set` does only work for loaded threads.
Expand the scope to also support persisted but not-yet-loaded ones for a
more predictable API surface.
This will make it possible to rename threads discovered via
`thread/list` and similar operations.
## Summary
- increase `DEFAULT_READ_TIMEOUT` in `codex_message_processor_flow` from
20s to 45s
- keep test behavior the same while avoiding platform timing flakes
## Why
Windows ARM64 CI showed these tests taking about 24s before
`task_complete`, which could fail early and produce wiremock
request-count mismatches.
## Testing
- just fmt
- cargo test -p codex-app-server codex_message_processor_flow --
--nocapture
## Summary
Codex discovered this one - shell_snapshot tests were breaking on my
machine because I had a multiline env var. We should handle these!
## Testing
- [x] existing tests pass
- [x] Updated unit tests
## Summary
- restore `Tab to queue` when a draft is present and the agent is
running
- keep draft-idle footers passive by showing the normal footer or status
line instead of `? for shortcuts`
- align footer snapshot coverage with the updated draft footer behavior
## Codex author
`codex resume 019c7f1c-43aa-73e0-97c7-40f457396bb0`
---------
Co-authored-by: Codex <noreply@openai.com>
Fixes#13076
This PR fixes a bug that causes command-line config overrides for MCP
subtables to not be merged correctly.
Summary
- make project trust loading go through the dedicated struct so CLI
overrides can update trusted project-local MCP transports
---------
Co-authored-by: jif-oai <jif@openai.com>
Historically, we cloned the Bash repo from
https://github.com/bminor/bash, but for whatever reason, it was removed
at some point.
I had a local clone of it, so I pushed it to
https://github.com/bolinfest/bash so that we could continue running our
CI job. I did this in https://github.com/openai/codex/pull/9563, and as
you can see, I did not tamper with the commit hash we used as the basis
of this build.
Using a personal fork is not great, so this PR changes the CI job to use
what appears to be considered the source of truth for Bash, which is
https://git.savannah.gnu.org/git/bash.git.
Though in testing this out, it appears this Git server does not support
the combination of `git clone --depth 1
https://git.savannah.gnu.org/git/bash` and `git fetch --depth 1 origin
a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b`, as it fails with the
following error:
```
error: Server does not allow request for unadvertised object a8a1c2fac029404d3f42cd39f5a20f24b6e4fe4b
```
so unfortunately this means that we have to do a full clone instead of a
shallow clone in our CI jobs, which will be a bit slower.
Also updated `codex-rs/shell-escalation/README.md` to reflect this
change.
## Summary
- reuse the parent shell snapshot when spawning/forking/resuming
`SessionSource::SubAgent(SubAgentSource::ThreadSpawn { .. })` sessions
- plumb inherited snapshot through `AgentControl -> ThreadManager ->
Codex::spawn -> SessionConfiguration`
- skip shell snapshot refresh on cwd updates for thread-spawn subagents
so inherited snapshots are not replaced
## Why
- avoids per-subagent shell snapshot creation and cleanup work
- keeps thread-spawn subagents on the parent snapshot path, matching the
intended parent/child snapshot model
## Validation
- `just fmt` (in `codex-rs`)
- `cargo test -p codex-core --no-run`
- `cargo test -p codex-core spawn_agent -- --nocapture`
- `cargo test -p codex-core --test all
suite::agent_jobs::spawn_agents_on_csv_runs_and_exports`
## Notes
- full `cargo test -p codex-core --test all` was left running separately
for broader verification
Co-authored-by: Codex <noreply@openai.com>
## Summary
- raise contrast for subagent transcript labels and fallback states
- remove low-contrast dim styling from role tags and error details
- make the closed-agent picker dot readable in dark theme
## Validation
- just fmt
- just fix -p codex-tui
- cargo test -p codex-tui
Co-authored-by: Codex <noreply@openai.com>
Fixes#13203
Summary
- split the duplicate-finding workflow into two jobs so we gather all
issues first
- add an open-issue fallback job that runs only when the full scan finds
nothing
- centralize final selection so `comment-on-issue` always sees the best
dedupe output
## Summary
- record a realtime close developer message when a new realtime session
replaces an active one
- assert the replacement marker through the mocked responses request
path
---------
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Charles Cunningham <ccunningham@openai.com>
This change fixes a Codex app account-state sync bug where clients could
know the user was signed in but still miss the ChatGPT subscription
tier, which could lead to incorrect upgrade messaging for paid users.
The root cause was that `account/updated` only carried `authMode` while
plan information was available separately via `account/read` and
rate-limit snapshots, so this update adds `planType` to
`account/updated`, populates it consistently across login and refresh
paths.
…with launchservicesd
Add mach lookup for `launchservicesd` when extending the sandbox for
`MacOSAutomationPermission::BundleIDs`. This is necessary so that the
target application can be launched for automation.
This omission was due to a spec error in a document, which has been
fixed.
Support loading plugins.
Plugins can now be enabled via [plugins.<name>] in config.toml. They are
loaded as first-class entities through PluginsManager, and their default
skills/ and .mcp.json contributions are integrated into the existing
skills and MCP flows.
## Why
[#12964](https://github.com/openai/codex/pull/12964) added
`host_executable()` support to `codex-execpolicy`, and
[#13046](https://github.com/openai/codex/pull/13046) adopted it in the
zsh-fork interception path.
The remaining gap was the preflight execpolicy check in
`core/src/exec_policy.rs`. That path derives approval requirements
before execution for `shell`, `shell_command`, and `unified_exec`, but
it was still using the default exact-token matcher.
As a result, a command that already included an absolute executable
path, such as `/usr/bin/git status`, could still miss a basename rule
like `prefix_rule(pattern = ["git"], ...)` during preflight even when
the policy also defined a matching `host_executable(name = "git", ...)`
entry.
This PR brings the same opt-in `host_executable()` resolution to the
preflight approval path when an absolute program path is already present
in the parsed command.
## What Changed
- updated
`ExecPolicyManager::create_exec_approval_requirement_for_command()` in
`core/src/exec_policy.rs` to use `check_multiple_with_options(...)` with
`MatchOptions { resolve_host_executables: true }`
- kept the existing shell parsing flow for approval derivation, but now
allow basename rules to match absolute executable paths during preflight
when `host_executable()` permits it
- updated requested-prefix amendment evaluation to use the same
host-executable-aware matching mode, so suggested `prefix_rule()`
amendments are checked consistently for absolute-path commands
- added preflight coverage for:
- absolute-path commands that should match basename rules through
`host_executable()`
- absolute-path commands whose paths are not in the allowed
`host_executable()` mapping
- requested prefix-rule amendments for absolute-path commands
## Verification
- `just fix -p codex-core`
- `cargo test -p codex-core --lib exec_policy::tests::`
## Summary
- skip online model refresh for subagent sessions
- avoid rollout flushes during subagent startup
- keep /models refresh for non-subagent sessions
## Testing
- cargo test -p codex-core --test all
suite::models_etag_responses::refresh_models_on_models_etag_mismatch_and_avoid_duplicate_models_fetch
- cargo test -p codex-core --test all
suite::remote_models::remote_models_long_model_slug_is_sent_with_high_reasoning
- cargo test -p codex-core --test all
suite::model_switching::model_switch_to_smaller_model_updates_token_context_window
- cargo test -p codex-core --test all
suite::compact::pre_sampling_compact_runs_on_switch_to_smaller_context_model
- cargo test -p codex-core --test all
suite::compact::pre_sampling_compact_runs_after_resume_and_switch_to_smaller_model
- cargo test -p codex-core --test all
suite::personality::remote_model_friendly_personality_instructions_with_feature
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
- tighten Codex memory-read behavior around stale facts and conflicting
memory
- encode the risk-of-drift vs verification-effort decision rule directly
in the read-path prompt
- make partial stale-detail updates explicit so correcting only the
answer is not treated as sufficient
## What changed
- update `codex-rs/core/templates/memories/read_path.md`
- add guidance for when to verify cheap local facts vs when to answer
from older memory with visible provenance
- strengthen same-turn `MEMORY.md` updates when stored concrete details
are stale
## Notes
- this is based on some staleness eval work
Addresses #12913
`codex exec` was not correctly defaulting to Otel metrics to enabled
`codex mcp-server` completely lacked an Otel collector
Summary:
- default to enabling analytics when `codex exec` initializes
OpenTelemetry so the CLI actually reports metrics again
- add a regression test that proves the flag remains enabled by default
- added Otel collector to `codex mcp-server`
Addresses #12967
About a month ago, I updated the Github bug report templates to
accommodate the (at the time) new Codex app. The `/feedback` code path
in the CLI was referencing one of the old templates, and I didn't
realize it at the time. This PR updates the link so users don't get an
empty bug template when using `/feedback`.
#### what
adds a `codex debug clear-memories` command to help with clearing all
memories state from disk, sqlite db, and marking threads as
`memory_mode=disabled` so they don't get resummarized when the
`memories` feature is re-enabled.
#### tests
add tests
## Why
[#12964](https://github.com/openai/codex/pull/12964) added
`host_executable()` support to `codex-execpolicy`, but the zsh-fork
interception path in `unix_escalation.rs` was still evaluating commands
with the default exact-token matcher.
That meant an intercepted absolute executable such as `/usr/bin/git
status` could still miss basename rules like `prefix_rule(pattern =
["git", "status"])`, even when the policy also defined a matching
`host_executable(name = "git", ...)` entry.
This PR adopts the new matching behavior in the zsh-fork runtime only.
That keeps the rollout intentionally narrow: zsh-fork already requires
explicit user opt-in, so it is a safer first caller to exercise the new
`host_executable()` scheme before expanding it to other execpolicy call
sites.
It also brings zsh-fork back in line with the current `prefix_rule()`
execution model. Until prefix rules can carry their own permission
profiles, a matched `prefix_rule()` is expected to rerun the intercepted
command unsandboxed on `allow`, or after the user accepts `prompt`,
instead of merely continuing inside the inherited shell sandbox.
## What Changed
- added `evaluate_intercepted_exec_policy()` in
`core/src/tools/runtimes/shell/unix_escalation.rs` to centralize
execpolicy evaluation for intercepted commands
- switched intercepted direct execs in the zsh-fork path to
`check_multiple_with_options(...)` with `MatchOptions {
resolve_host_executables: true }`
- added `commands_for_intercepted_exec_policy()` so zsh-fork policy
evaluation works from intercepted `(program, argv)` data instead of
reconstructing a synthetic command before matching
- left shell-wrapper parsing intentionally disabled by default behind
`ENABLE_INTERCEPTED_EXEC_POLICY_SHELL_WRAPPER_PARSING`, so
path-sensitive matching relies on later direct exec interception rather
than shell-script parsing
- made matched `prefix_rule()` decisions rerun intercepted commands with
`EscalationExecution::Unsandboxed`, while unmatched-command fallback
keeps the existing sandbox-preserving behavior
- extracted the zsh-fork test harness into
`core/tests/common/zsh_fork.rs` so both the skill-focused and
approval-focused integration suites can exercise the same runtime setup
- limited this change to the intercepted zsh-fork path rather than
changing every execpolicy caller at once
- added runtime coverage in
`core/src/tools/runtimes/shell/unix_escalation_tests.rs` for allowed and
disallowed `host_executable()` mappings and the wrapper-parsing modes
- added integration coverage in `core/tests/suite/approvals.rs` to
verify a saved `prefix_rule(pattern=["touch"], decision="allow")` reruns
under zsh-fork outside a restrictive `WorkspaceWrite` sandbox
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/13046).
* #13065
* __->__ #13046
Stop `thread/start` from blocking other app-server requests.
Before this change, `thread/start ran` inline on the request loop, so
slow startup paths like MCP auth checks could hold up unrelated requests
on the same connection, including `thread/loaded/list`. This moves
`thread/start` into a background task.
While doing so, it revealed an issue where we were doing nested locking
(and there were some race conditions possible that could introduce a
"phantom listener"). This PR also refactors the listener/subscription
bookkeeping - listener/subscription state is now centralized in
`ThreadStateManager` instead of being split across multiple lock
domains. That makes late auto-attach on `thread/start` race-safe and
avoids reintroducing disconnected clients as phantom subscribers.
Addresses #12566
Summary
- stop printing the final assistant message on stdout when the process
is running in a terminal so interactive users only see it once
- add a helper that gates the stdout emission and cover it with unit
tests
- override startup tooltips with model availability NUX and persist
per-model show counts in config
- stop showing each model after four exposures and fall back to normal
tooltips
Addresses https://github.com/openai/codex/issues/13007 and
https://github.com/openai/codex/issues/12170
There are situations where the ChatGPT auth backend might return a JWT
that contains no plan information. Most code paths already handle this
case well, but the internal implementation of the "account/read" app
server call was failing in this case (returning an error rather than
properly returning None for the plan).
This resulted in a situation where users needed to log in every time the
extension or app started even if they successfully logged in the last
time.
Summary
- allow ChatGPT-authenticated accounts to fall back to
`AccountPlanType::Unknown` when the token omits the plan claim
- add regression coverage in `app-server/tests/suite/v2/account.rs` to
confirm `account/read` returns `plan_type: Unknown` when the claim is
absent
- ensure the Rust auth helpers and fixtures treat missing plan claims as
Optional and default to `Unknown`
Addresses https://github.com/openai/codex/issues/13040
Fixes a regression in 0.106.0 introduced in
https://github.com/openai/codex/pull/9393
Summary
- replace only the active completion range so unrelated text elements
(e.g., large-paste placeholders) stay atomic and can still expand
- add a regression test verifying large paste placeholders persist
through completions and submit
- could not fetch issue details via GitHub API because network access is
disabled in this sandboxed environment
## Problem
The TUI diff renderer uses hardcoded background palettes for
insert/delete lines that don't respect the user's chosen syntax theme.
When a theme defines `markup.inserted` / `markup.deleted` scope
backgrounds (the convention used by GitHub, Solarized, Monokai, and most
VS Code themes), those colors are ignored — the diff always renders with
the same green/red tints regardless of theme selection.
Separately, ANSI-16 terminals (and Windows Terminal sessions misreported
as ANSI-16) rendered diff backgrounds as full-saturation blocks that
obliterated syntax token colors, making highlighted diffs unreadable.
## Mental model
Diff backgrounds are resolved in three layers:
1. **Color level detection** — `diff_color_level_for_terminal()` maps
the raw `supports-color` probe + Windows Terminal heuristics to a
`DiffColorLevel` (TrueColor / Ansi256 / Ansi16). Windows Terminal gets
promoted from Ansi16 to TrueColor when `WT_SESSION` is present.
2. **Background resolution** — `resolve_diff_backgrounds()` queries the
active syntax theme for `markup.inserted`/`markup.deleted` (falling back
to `diff.inserted`/`diff.deleted`), then overlays those on top of the
hardcoded palette. For ANSI-256, theme RGB values are quantized to the
nearest xterm-256 index. For ANSI-16, backgrounds are `None`
(foreground-only).
3. **Style composition** — The resolved `ResolvedDiffBackgrounds` is
threaded through every call to `style_add`, `style_del`, `style_sign_*`,
and `style_line_bg_for`, which decide how to compose
foreground+background for each line kind and theme variant.
A new `RichDiffColorLevel` type (a subset of `DiffColorLevel` without
Ansi16) encodes the invariant "we have enough depth for tinted
backgrounds" at the type level, so background-producing functions have
exhaustive matches without unreachable arms.
## Non-goals
- No change to gutter (line number column) styling — gutter backgrounds
still use the hardcoded palette.
- No per-token scope background resolution — this is line-level
background only; syntax token colors come from the existing
`highlight_code_to_styled_spans` path.
- No dark/light theme auto-switching from scope backgrounds —
`DiffTheme` is still determined by querying the terminal's background
color.
## Tradeoffs
- **Theme trust vs. visual safety:** When a theme defines scope
backgrounds, we trust them unconditionally for rich color levels. A
badly authored theme could produce illegible combinations. The fallback
for `None` backgrounds (foreground-only) is intentionally conservative.
- **Quantization quality:** ANSI-256 quantization uses perceptual
distance across indices 16–255, skipping system colors. The result is
approximate — a subtle theme tint may land on a noticeably different
xterm index.
- **Single-query caching:** `resolve_diff_backgrounds` is called once
per `render_change` invocation (i.e., once per file in a diff). If the
theme changes mid-render (live preview), the next file picks up the new
backgrounds.
## Architecture
Files changed:
| File | Role |
|---|---|
| `tui/src/render/highlight.rs` | New: `DiffScopeBackgroundRgbs`,
`diff_scope_background_rgbs()`, scope extraction helpers |
| `tui/src/diff_render.rs` | New: `RichDiffColorLevel`,
`ResolvedDiffBackgrounds`, `resolve_diff_backgrounds*`,
`quantize_rgb_to_ansi256`, Windows Terminal promotion; modified: all
style helpers to accept/thread `ResolvedDiffBackgrounds` |
The scope-extraction code lives in `highlight.rs` because it uses
`syntect::highlighting::Highlighter` and the theme singleton. The
resolution and quantization logic lives in `diff_render.rs` because it
depends on diff-specific types (`DiffTheme`, `DiffColorLevel`, ratatui
`Color`).
## Observability
No runtime logging was added. The most useful debugging aid is the
`diff_color_level_for_terminal` function, which is pure and fully
unit-tested — to diagnose a color-depth mismatch, log its four inputs
(`StdoutColorLevel`, `TerminalName`, `WT_SESSION` presence,
`FORCE_COLOR` presence).
Scope resolution can be tested by loading a custom `.tmTheme` with known
`markup.inserted` / `markup.deleted` backgrounds and checking the diff
output in a truecolor terminal.
## Tests
- **Windows Terminal promotion:** 7 unit tests cover every branch of
`diff_color_level_for_terminal` (ANSI-16 promotion, `WT_SESSION`
unconditional promotion, `FORCE_COLOR` suppression, conservative
`Unknown` level).
- **ANSI-16 foreground-only:** Tests verify that `style_add`,
`style_del`, `style_sign_*`, `style_line_bg_for`, and `style_gutter_for`
all return `None` backgrounds on ANSI-16.
- **Scope resolution:** Tests verify `markup.*` preference over
`diff.*`, `None` when no scope matches, bundled theme resolution, and
custom `.tmTheme` round-trip.
- **Quantization:** Test verifies ANSI-256 quantization of a known RGB
triple.
- **Insta snapshots:** 2 new snapshot tests
(`ansi16_insert_delete_no_background`,
`theme_scope_background_resolution`) lock visual output.
## Summary
Implements Linux bubblewrap support for restricted `ReadOnlyAccess`
(introduced in #11387) by honoring `readable_roots` and
`include_platform_defaults` instead of failing closed.
## What changed
- Added a Linux platform-default read allowlist for common
system/runtime paths (e.g. /usr, /etc, /lib*, Nix store roots).
- Updated the bwrap filesystem mount builder to support restricted read
access:
- Full-read policies still use `--ro-bind / /`
- Restricted-read policies now start from` --tmpfs `/ and add scoped
`--ro-bind` mounts
- Preserved existing writable-root and protected-subpath behavior
(`.git`, `.codex`, etc.).
`ReadOnlyAccess::Restricted` was already modeled in protocol, but Linux
bwrap still returned `UnsupportedOperation` for restricted read access.
This closes that gap for the active Linux filesystem backend.
## Notes
Legacy Linux Landlock fallback still fail-closes for restricted read
access (unchanged).
Stablize app list updated event so that we only send 2 updates: 1 when
installed apps become available, one when all directory apps are
available. Previously it also updates when directory apps become
available before installed apps, which cuts off installed apps.
## Summary
This PR unifies rollout history reconstruction and resume/fork metadata
hydration under a single `Session::reconstruct_history_from_rollout`
implementation.
The key change from main is that replay metadata now comes from the same
reconstruction pass that rebuilds model-visible history, instead of
doing a second bespoke rollout scan to recover `previous_model` /
`reference_context_item`.
## What Changed
### Unified reconstruction output
`reconstruct_history_from_rollout` now returns a single
`RolloutReconstruction` bundle containing:
- rebuilt `history`
- `previous_model`
- `reference_context_item`
Resume and fork both consume that shared output directly.
### Reverse replay core
The reconstruction logic moved into
`codex-rs/core/src/codex/rollout_reconstruction.rs` and now scans
rollout items newest-to-oldest.
That reverse pass:
- derives `previous_model`
- derives whether `reference_context_item` is preserved or cleared
- stops early once it has both resume metadata and a surviving
`replacement_history` checkpoint
History materialization is still bridged eagerly for now by replaying
only the surviving suffix forward, which keeps the history result stable
while moving the control flow toward the future lazy reverse loader
design.
### Removed bespoke context lookup
This deletes `last_rollout_regular_turn_context_lookup` and its separate
compaction-aware scan.
The previous model / baseline metadata is now computed from the same
replay state that rebuilds history, so resume/fork cannot drift from the
reconstructed transcript view.
### `TurnContextItem` persistence contract
`TurnContextItem` is now treated as the replay source of truth for
durable model-visible baselines.
This PR keeps the following contract explicit:
- persist `TurnContextItem` for the first real user turn so resume can
recover `previous_model`
- persist it for later turns that emit model-visible context updates
- if mid-turn compaction reinjects full initial context into replacement
history, persist a fresh `TurnContextItem` after `Compacted` so
resume/fork can re-establish the baseline from the rewritten history
- do not treat manual compaction or pre-sampling compaction as creating
a new durable baseline on their own
## Behavior Preserved
- rollback replay stays aligned with `drop_last_n_user_turns`
- rollback skips only user turns
- incomplete active user turns are dropped before older finalized turns
when rollback applies
- unmatched aborts do not consume the current active turn
- missing abort IDs still conservatively clear stale compaction state
- compaction clears `reference_context_item` until a later
`TurnContextItem` re-establishes it
- `previous_model` still comes from the newest surviving user turn that
established one
## Tests
Targeted validation run for the current branch shape:
- `cd codex-rs && cargo test -p codex-core --lib
codex::rollout_reconstruction_tests -- --nocapture`
- `cd codex-rs && just fmt`
The branch also extracts the rollout reconstruction tests into
`codex-rs/core/src/codex/rollout_reconstruction_tests.rs` so this logic
has a dedicated home instead of living inline in `codex.rs`.
This updates the on-request permissions instructions so likely
sandbox-related network failures during dependency installation are
treated as escalation candidates.
Repro:
- Run `codex -a on-request -s workspace-write` in a fresh temp dir.
- Prompt: `Build a new rust app with one dependency, anyhow, and try
installing the dependency`.
- Before this change, DNS/registry failures like `Could not resolve
host: index.crates.io` could be treated like ordinary transient failures
and not escalate.
Fix:
- Clarify that likely sandbox-related network errors such as DNS/host
resolution, registry/index access, and dependency download failures
should trigger escalation.
Validation:
- Rebuild the CLI and rerun the same repro. The same instructions should
now be more likely to trigger escalation instead of silently stopping.
Related Slack canvas:
- https://openai.enterprise.slack.com/docs/T0BQTNSUF/F0ACVNJAV09
2026-02-27 13:48:52 -08:00
694 changed files with 90188 additions and 18121 deletions
@@ -51,6 +51,7 @@ You can enable notifications by configuring a script that is run whenever the ag
### `codex exec` to run Codex programmatically/non-interactively
To run Codex non-interactively, run `codex exec PROMPT` (you can also pass the prompt via `stdin`) and Codex will work on your task until it decides that it is done and exits. Output is printed to the terminal directly. You can set the `RUST_LOG` environment variable to see more about what's going on.
Use `codex exec --fork <SESSION_ID> PROMPT` to fork an existing session without launching the interactive picker/UI.
Use `codex exec --ephemeral ...` to run without persisting session rollout files to disk.
"description":"Patch the stored Git metadata for this thread. Omit a field to leave it unchanged, set it to `null` to clear it, or provide a string to replace the stored value."
},
"threadId":{
"type":"string"
}
},
"required":[
"threadId"
],
"type":"object"
},
"ThreadReadParams":{
"properties":{
"includeTurns":{
@@ -2155,6 +2314,23 @@
}
]
},
"serviceTier":{
"anyOf":[
{
"anyOf":[
{
"$ref":"#/definitions/ServiceTier"
},
{
"type":"null"
}
]
},
{
"type":"null"
}
]
},
"threadId":{
"type":"string"
}
@@ -2299,6 +2475,23 @@
"string",
"null"
]
},
"serviceTier":{
"anyOf":[
{
"anyOf":[
{
"$ref":"#/definitions/ServiceTier"
},
{
"type":"null"
}
]
},
{
"type":"null"
}
]
}
},
"type":"object"
@@ -2409,6 +2602,24 @@
],
"description":"Override the sandbox policy for this turn and subsequent turns."
},
"serviceTier":{
"anyOf":[
{
"anyOf":[
{
"$ref":"#/definitions/ServiceTier"
},
{
"type":"null"
}
]
},
{
"type":"null"
}
],
"description":"Override the service tier for this turn and subsequent turns."
"description":"Read access granted while running under this policy."
},
"network_access":{
"description":"When set to `true`, outbound network access is allowed. `false` by default.",
"type":"boolean"
},
"type":{
"enum":[
"read-only"
@@ -5350,11 +5632,15 @@
}
]
},
"ServiceTier":{
"enum":[
"fast",
"flex"
],
"type":"string"
},
"SessionNetworkProxyRuntime":{
"properties":{
"admin_addr":{
"type":"string"
},
"http_addr":{
"type":"string"
},
@@ -5363,7 +5649,6 @@
}
},
"required":[
"admin_addr",
"http_addr",
"socks_addr"
],
@@ -5852,6 +6137,46 @@
"title":"WebSearchTurnItem",
"type":"object"
},
{
"properties":{
"id":{
"type":"string"
},
"result":{
"type":"string"
},
"revised_prompt":{
"type":[
"string",
"null"
]
},
"saved_path":{
"type":[
"string",
"null"
]
},
"status":{
"type":"string"
},
"type":{
"enum":[
"ImageGeneration"
],
"title":"ImageGenerationTurnItemType",
"type":"string"
}
},
"required":[
"id",
"result",
"status",
"type"
],
"title":"ImageGenerationTurnItem",
"type":"object"
},
{
"properties":{
"id":{
@@ -5973,7 +6298,7 @@
"type":"object"
},
{
"description":"Explicit mention selected by the user (name + app://connectorid).",
"description":"Explicit structured mention selected by the user.\n\n`path` identifies the exact mention target, for example `app://<connector-id>` or `plugin://<plugin-name>@<marketplace-name>`.",
"properties":{
"name":{
"type":"string"
@@ -6694,6 +7019,16 @@
],
"description":"How to sandbox commands executed in the system"
},
"service_tier":{
"anyOf":[
{
"$ref":"#/definitions/ServiceTier"
},
{
"type":"null"
}
]
},
"session_id":{
"$ref":"#/definitions/ThreadId"
},
@@ -6933,6 +7268,66 @@
"title":"WebSearchEndEventMsg",
"type":"object"
},
{
"properties":{
"call_id":{
"type":"string"
},
"type":{
"enum":[
"image_generation_begin"
],
"title":"ImageGenerationBeginEventMsgType",
"type":"string"
}
},
"required":[
"call_id",
"type"
],
"title":"ImageGenerationBeginEventMsg",
"type":"object"
},
{
"properties":{
"call_id":{
"type":"string"
},
"result":{
"type":"string"
},
"revised_prompt":{
"type":[
"string",
"null"
]
},
"saved_path":{
"type":[
"string",
"null"
]
},
"status":{
"type":"string"
},
"type":{
"enum":[
"image_generation_end"
],
"title":"ImageGenerationEndEventMsgType",
"type":"string"
}
},
"required":[
"call_id",
"result",
"status",
"type"
],
"title":"ImageGenerationEndEventMsg",
"type":"object"
},
{
"description":"Notification that the server is about to execute a command.",
"properties":{
@@ -7455,12 +7850,19 @@
"id":{
"$ref":"#/definitions/RequestId"
},
"message":{
"type":"string"
"request":{
"$ref":"#/definitions/ElicitationRequest"
},
"server_name":{
"type":"string"
},
"turn_id":{
"description":"Turn ID that this elicitation belongs to, when known.",
"description":"Typed form schema for MCP `elicitation/create` requests.\n\nThis matches the `requestedSchema` shape from the MCP 2025-11-25 `ElicitRequestFormParams` schema.",
"description":"Active Codex turn when this elicitation was observed, if app-server could correlate one.\n\nThis is nullable because MCP models elicitation as a standalone server-to-client request identified by the MCP server request id. It may be triggered during a turn, but turn context is app-server correlation rather than part of the protocol identity of the elicitation itself.",
"description":"Optional client metadata for form-mode action handling."
},
"action":{
"$ref":"#/definitions/McpServerElicitationAction"
},
"content":{
"description":"Structured user input for accepted elicitations, mirroring RMCP `CreateElicitationResult`.\n\nThis is nullable because decline/cancel responses have no content."
"description":"Notification emitted when watched local skill files change.\n\nTreat this as an invalidation signal and re-run `skills/list` with the client's current parameters when refreshed skill metadata is needed.",
"type":"object"
},
"SubAgentSource":{
"oneOf":[
{
@@ -1655,6 +1676,10 @@
"description":"Working directory captured for the thread.",
"type":"string"
},
"ephemeral":{
"description":"Whether the thread is ephemeral and should not be materialized on disk.",
"description":"Typed form schema for MCP `elicitation/create` requests.\n\nThis matches the `requestedSchema` shape from the MCP 2025-11-25 `ElicitRequestFormParams` schema.",
"description":"Active Codex turn when this elicitation was observed, if app-server could correlate one.\n\nThis is nullable because MCP models elicitation as a standalone server-to-client request identified by the MCP server request id. It may be triggered during a turn, but turn context is app-server correlation rather than part of the protocol identity of the elicitation itself.",
"type":[
"string",
"null"
]
}
},
"required":[
"serverName",
"threadId"
],
"type":"object"
},
"NetworkApprovalContext":{
"properties":{
"host":{
@@ -966,6 +1584,31 @@
"title":"Item/tool/requestUserInputRequest",
"type":"object"
},
{
"description":"Request input for an MCP server elicitation.",
"description":"A path that is guaranteed to be absolute and normalized (though it is not guaranteed to be canonicalized or exist on the filesystem).\n\nIMPORTANT: When deserializing an `AbsolutePathBuf`, a base path must be set using [AbsolutePathBufGuard::new]. If no base path is set, the deserialization will fail unless the path being deserialized is already absolute.",
"description":"A path that is guaranteed to be absolute and normalized (though it is not guaranteed to be canonicalized or exist on the filesystem).\n\nIMPORTANT: When deserializing an `AbsolutePathBuf`, a base path must be set using [AbsolutePathBufGuard::new]. If no base path is set, the deserialization will fail unless the path being deserialized is already absolute.",
"type":"string"
}
},
"properties":{
"cwds":{
"description":"Optional working directories used to discover repo marketplaces. When omitted, only home-scoped marketplaces are considered.",
"description":"Notification emitted when watched local skill files change.\n\nTreat this as an invalidation signal and re-run `skills/list` with the client's current parameters when refreshed skill metadata is needed.",
"description":"There are two ways to fork a thread: 1. By thread_id: load the thread from disk by thread_id and fork it into a new thread. 2. By path: load the thread from disk by path and fork it into a new thread.\n\nIf using path, the thread_id param will be ignored.\n\nPrefer using thread_id whenever possible.",
"description":"Patch the stored Git metadata for this thread. Omit a field to leave it unchanged, set it to `null` to clear it, or provide a string to replace the stored value."
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
