## Why
The model list needs to carry display-ready service tier metadata so
clients can render tier choices with stable IDs, names, and
descriptions. A raw speed-tier string list is not enough for richer UI
copy or future tier labels.
## What changed
- Added `ModelServiceTier` to shared model metadata with string `id`,
`name`, and `description` fields.
- Added `service_tiers` to `ModelInfo` and `ModelPreset`, preserving
empty defaults for older cached model payloads.
- Exposed `serviceTiers` on app-server v2 `Model` responses and threaded
it through TUI app-server model conversion.
- Marked legacy `additional_speed_tiers` / `additionalSpeedTiers`
metadata as deprecated in source and generated schema output.
- Regenerated app-server protocol JSON schema and TypeScript fixtures,
including `ModelServiceTier.ts`.
## Verification
- Ran `just write-app-server-schema`.
- Did not run local tests per repo instruction; relying on PR CI.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
Large hook outputs can enter model-visible context through hook-specific
paths such as `additionalContext` and `Stop` continuation prompts.
Without a dedicated cap, one hook can inject a large blob directly into
conversation history instead of leaving a bounded preview for the model
and preserving the full text elsewhere.
## What
- spill hook text once it exceeds a fixed `2_500`-token budget,
preserving the full output on disk and leaving a head/tail preview plus
saved path in context
- add shared hook-output spilling under
`CODEX_HOME/hook_outputs/<thread_id>/<uuid>.txt`
- apply the cap to both `additionalContext`, `feedback_message`, and
`Stop` continuation fragments
Migrate token usage replay, rollback responses, and detached review
setup (a special case of forking) to be served from ThreadStore reads
rather direct rollout files.
- replay restored token usage from already-loaded `RolloutItem` history
instead of reopening `Thread.path`
- rebuild rollback responses from loaded `ThreadStore` snapshots and
history
- start detached reviews from store-backed parent history and stored
review-thread metadata
- remove obsolete app-server rollout-summary helper code that became
dead after the store-backed migration
- preserve response/notification ordering for resume, fork, rollback,
and detached review flows
- add integration test coverage for the affected paths
- Route `thread/metadata/update` through
`ThreadStore::update_thread_metadata`.
- Add `LocalThreadStore` git metadata patch support for set, partial
update, and clear semantics.
- Add some unit tests for the new thread store code
- Remove a lot of dead code/tests!
## Why
Tool families already disagree on what their existing `duration` fields
mean, so lifecycle latency should live on the shared item envelope
instead of being inferred from per-tool execution fields. Carrying that
envelope through app-server notifications gives downstream consumers one
reusable timing signal without pretending every tool has the same
execution semantics.
## What changed
- Adds `started_at_ms` to core `ItemStartedEvent` values and
`completed_at_ms` to core `ItemCompletedEvent` values.
- Populates those timestamps in the shared session lifecycle emitters,
so protocol-native items get timing without each producer tracking its
own clock state.
- Exposes `startedAtMs` on app-server `item/started` notifications and
`completedAtMs` on `item/completed` notifications.
- Maps the lifecycle timestamps through the app-server boundary while
leaving legacy-converted notifications nullable when no lifecycle
timestamp exists.
- Regenerates the app-server JSON schema and TypeScript fixtures for the
notification-envelope change and updates downstream fixtures that
construct those notifications directly.
- Extends the existing web-search and image-generation integration flows
to assert the new lifecycle timestamps on the native item events.
## Verification
- `cargo check -p codex-protocol -p codex-core -p
codex-app-server-protocol -p codex-app-server -p codex-tui -p codex-exec
-p codex-app-server-client`
- `cargo test -p codex-core --test all web_search_item_is_emitted`
- `cargo test -p codex-core --test all
image_generation_call_event_is_emitted`
- `cargo test -p codex-app-server-protocol`
---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/20514).
* #18748
* #18747
* #17090
* #17089
* __->__ #20514
## Summary
Moves the WebRTC realtime sideband websocket join out of the voice start
critical path. Call creation still posts the SDP offer and session
config synchronously so the client gets the SDP answer, but the sideband
websocket now connects in the input task async and doesn't block
conversation state installation.
This lets the normal realtime input channels buffer text, handoff
output, and audio while the WebRTC sideband websocket is connecting. If
the sideband join fails while the conversation is still active, the task
sends a RealtimeEvent::Error through the existing events_tx / fanout
path.
To rephrase this:
* No longer blocked on sideband: the client can receive the SDP answer
earlier, set up the WebRTC peer connection, and let the media leg
progress while the sideband websocket joins.
* Still blocked on sideband: queued text, handoff output, and sideband
server events cannot flow until connect_webrtc_sideband(...).await
finishes and then run_realtime_input_task(...) starts
## Validation
- `env CODEX_SKIP_VENDORED_BWRAP=1 cargo test --manifest-path
codex-rs/Cargo.toml -p codex-core --test all
conversation_webrtc_start_posts_generated_session`
`CODEX_SKIP_VENDORED_BWRAP=1` is needed in this local environment
because `libcap.pc` is not installed for the vendored bubblewrap build.
## Testing
I tested this locally by running `cargo run -p codex-cli --bin codex --
--enable realtime_conversation` and invoking `/realtime`. Then, we get
logs emitted in `~/.codex/log/codex-tui.log`.
### Before the Change
Logging commit
(c0299e6edf)
```
2026-05-04T16:06:09.251956Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: starting realtime conversation
2026-05-04T16:06:09.251980Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: creating realtime call transport="webrtc"
2026-05-04T16:06:10.365722Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: realtime call created; sdp answer ready transport="webrtc" call_id=rtc_u0_Dbq65nhak5eLjQZ73yhAy elapsed_ms=1113 total_elapsed_ms=1113
2026-05-04T16:06:10.365843Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: connecting realtime sideband websocket call_id=rtc_u0_Dbq65nhak5eLjQZ73yhAy
2026-05-04T16:06:10.784528Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: connected realtime sideband websocket call_id=rtc_u0_Dbq65nhak5eLjQZ73yhAy elapsed_ms=418 total_elapsed_ms=1532
2026-05-04T16:06:10.784665Z INFO session_loop{thread_id=019df3b9-e3d8-7271-b13a-b880119aa4c2}:submission_dispatch{otel.name="op.dispatch.realtime_conversation_start" submission.id="019df3bd-65df-7ee2-8125-1d6701fe39d2" codex.op="realtime_conversation_start"}: codex_core::realtime_conversation: realtime conversation started
```
### After the Change
Logging commit
(c8b00ac21a)
```
2026-05-04T15:41:24.080363Z INFO ... codex_core::realtime_conversation: starting realtime conversation
2026-05-04T15:41:24.080434Z INFO ... codex_core::realtime_conversation: creating realtime call transport="webrtc"
2026-05-04T15:41:25.106906Z INFO ... codex_core::realtime_conversation: realtime call created; sdp answer ready transport="webrtc" call_id=rtc_u0_Dbpi8nhak5eLjQZ73yhAy elapsed_ms=1026 total_elapsed_ms=1026
2026-05-04T15:41:25.107067Z INFO ... codex_core::realtime_conversation: spawned realtime sideband connection task transport="webrtc" total_elapsed_ms=1026
2026-05-04T15:41:25.107160Z INFO ... codex_core::realtime_conversation: realtime conversation started
2026-05-04T15:41:25.107185Z INFO codex_core::realtime_conversation: connecting realtime sideband websocket call_id=rtc_u0_Dbpi8nhak5eLjQZ73yhAy
2026-05-04T15:41:25.107352Z INFO ... codex_core::realtime_conversation: sent realtime sdp answer to client
2026-05-04T15:41:26.076685Z INFO codex_core::realtime_conversation: connected realtime sideband websocket call_id=rtc_u0_Dbpi8nhak5eLjQZ73yhAy elapsed_ms=969 total_elapsed_ms=1996
2026-05-04T15:41:26.573893Z INFO codex_core::realtime_conversation: realtime session updated realtime_session_id=sess_u0_Dbpi8nhak5eLjQZ73yhAy
2026-05-04T15:41:26.573970Z INFO codex_core::realtime_conversation: received realtime conversation event event=SessionUpdated { ... }
```
### Conclusion
Here we see that we saved about a half a second in conversation startup
(1532ms -> 969ms). This also checks out with my sanity tests; I was
seeing at most a second of saving.
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
The Bazel test coverage change exposed
`approved_folder_write_request_permissions_unblocks_later_apply_patch`,
and `rust-ci-full.yml` showed the same test failing on `main` on macOS.
There were two separate classes of problems here.
### Clean CI failure
The test emits an `apply_patch` tool call, but its config did not enable
the `apply_patch` tool, so the mocked response completed without an
`apply-patch-call` output. After enabling the tool, the same path also
needs the aggregate `codex-core` test binary to dispatch
`--codex-run-as-fs-helper`; sandboxed `apply_patch` uses that helper
under macOS Seatbelt.
The test now also canonicalizes the temporary patch target before
building the patch payload so the path matches normalized grants on
macOS, where `/var` paths often normalize to `/private/var`.
### Local/enterprise config isolation
The core test harness now builds its default test config with managed
config disabled, so host-managed enterprise config cannot alter these
tests. The request-permissions turns in this test also explicitly use
the user reviewer path, keeping the assertions focused on
`request_permissions` behavior rather than reviewer defaults from the
host.
## What Changed
- Enable `apply_patch` in
`approved_folder_write_request_permissions_unblocks_later_apply_patch`.
- Teach the core integration test binary to dispatch
`CODEX_FS_HELPER_ARG1`, matching the existing apply-patch and
linux-sandbox dispatch paths.
- Canonicalize the tempdir-backed patch target before creating the
patch.
- Ignore managed config in default core test configs and explicitly pin
this test to `ApprovalsReviewer::User`.
## Verification
Run outside the Codex app sandbox because these macOS tests
intentionally spawn Seatbelt:
- `cargo test -p codex-core
approved_folder_write_request_permissions_unblocks_later_apply_patch`
- `cargo test -p codex-core
approved_folder_write_request_permissions_unblocks_later_exec_without_sandbox_args`
## Why
Feedback reports do not currently surface a direct pointer to the last
model call, so investigations may require searching through many
requests in a session to find the bad response. Preserve the last
model-side IDs at response-stream time so immediate feedback reports
carry that breadcrumb.
## What changed
- Record `last_model_request_id` when a Responses stream exposes an
upstream request ID.
- Record `last_model_response_id` when the model response completes.
- Add unit coverage for the emitted feedback tags.
## Verification
- `cargo test -p codex-core
client::tests::response_stream_records_last_model_feedback_ids`
## Why
MCP servers can provide `instructions` that explain what their tools are
for. Directly exposed MCP namespaces already use those instructions when
a connector description is not available, but deferred `tool_search`
results did not preserve that fallback. The direct path falls back from
connector metadata to server instructions, while the deferred path only
carried `connector_description` and otherwise fell back to generic
namespace text.
That meant a plain MCP server could provide useful model-facing guidance
and still appear as `Tools in the X namespace.` whenever it was
discovered lazily through `tool_search`.
## What changed
- Store one model-facing `namespace_description` on `ToolInfo`, using
connector descriptions for connector-backed tools and server
instructions for plain MCP servers.
- Thread that namespace description through the `tool_search` source
list, search indexing, and returned namespace metadata.
- Add an end-to-end regression test for deferred non-app MCP search
results exposing server instructions as the namespace description.
## Verification
- `cargo test -p codex-tools
search_tool_description_lists_each_mcp_source_once --lib`
- `cargo test -p codex-core --test all
tool_search_uses_non_app_mcp_server_instructions_as_namespace_description`
## Summary
- normalize terminal-emitted C0 control characters through configurable
editor keymaps, covering raw control-key fallbacks like
Shift+Enter-as-LF in terminals from #20555 and #20898, plus part of the
modified-Enter behavior in #20580
- add default-unbound keymap actions for toggling Fast mode and killing
the current composer line, giving #20698 users a configurable zsh-style
Ctrl+U option without changing the existing default Ctrl+U behavior
- wire the new actions through gated /keymap picker entries, schema
generation, and snapshot coverage
Fixes#20555.
Fixes#20898.
## Testing
- just write-config-schema
- just fmt
- cargo test -p codex-config
- cargo test -p codex-tui keymap::tests
- cargo test -p codex-tui bottom_pane::textarea::tests
- cargo test -p codex-tui keymap_setup::tests
- cargo insta pending-snapshots
- just fix -p codex-tui
- git diff --check
- just argument-comment-lint
## Why
SQLite state was still being opened from consumer paths, including lazy
`OnceCell`-backed thread-store call sites. That let one process
construct multiple state DB connections for the same Codex home, which
makes SQLite lock contention and `database is locked` failures much
easier to hit.
State DB lifetime should be chosen by main-like entrypoints and tests,
then passed through explicitly. Consumers should use the supplied
`Option<StateDbHandle>` or `StateDbHandle` and keep their existing
filesystem fallback or error behavior when no handle is available.
The startup path also needs to keep the rollout crate in charge of
SQLite state initialization. Opening `codex_state::StateRuntime`
directly bypasses rollout metadata backfill, so entrypoints should
initialize through `codex_rollout::state_db` and receive a handle only
after required rollout backfills have completed.
## What Changed
- Initialize the state DB in main-like entrypoints for CLI, TUI,
app-server, exec, MCP server, and the thread-manager sample.
- Pass `Option<StateDbHandle>` through `ThreadManager`,
`LocalThreadStore`, app-server processors, TUI app wiring, rollout
listing/recording, personality migration, shell snapshot cleanup,
session-name lookup, and memory/device-key consumers.
- Remove the lazy local state DB wrapper from the thread store so
non-test consumers use only the supplied handle or their existing
fallback path.
- Make `codex_rollout::state_db::init` the local state startup path: it
opens/migrates SQLite, runs rollout metadata backfill when needed, waits
for concurrent backfill workers up to a bounded timeout, verifies
completion, and then returns the initialized handle.
- Keep optional/non-owning SQLite helpers, such as remote TUI local
reads, as open-only paths that do not run startup backfill.
- Switch app-server startup from direct
`codex_state::StateRuntime::init` to the rollout state initializer so
app-server cannot skip rollout backfill.
- Collapse split rollout lookup/list APIs so callers use the normal
methods with an optional state handle instead of `_with_state_db`
variants.
- Restore `getConversationSummary(ThreadId)` to delegate through
`ThreadStore::read_thread` instead of a LocalThreadStore-specific
rollout path special case.
- Keep DB-backed rollout path lookup keyed on the DB row and file
existence, without imposing the filesystem filename convention on
existing DB rows.
- Verify readable DB-backed rollout paths against `session_meta.id`
before returning them, so a stale SQLite row that points at another
thread's JSONL falls back to filesystem search and read-repairs the DB
row.
- Keep `debug prompt-input` filesystem-only so a one-off debug command
does not initialize or backfill SQLite state just to print prompt input.
- Keep goal-session test Codex homes alive only in the goal-specific
helper, rather than leaking tempdirs from the shared session test
helper.
- Update tests and call sites to pass explicit state handles where DB
behavior is expected and explicit `None` where filesystem-only behavior
is intended.
## Validation
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo check -p
codex-rollout -p codex-thread-store -p codex-app-server -p codex-core -p
codex-tui -p codex-exec -p codex-cli --tests`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout state_db_`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout find_thread_path`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout find_thread_path -- --nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout try_init_ -- --nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-rollout`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo clippy -p
codex-rollout --lib -- -D warnings`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-thread-store
read_thread_falls_back_when_sqlite_path_points_to_another_thread --
--nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-thread-store`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
shell_snapshot`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all personality_migration`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all rollout_list_find`
- `RUST_MIN_STACK=8388608 CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all rollout_list_find::find_prefers_sqlite_path_by_id --
--nocapture`
- `RUST_MIN_STACK=8388608 CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
--test all rollout_list_find -- --nocapture`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p codex-core
interrupt_accounts_active_goal_before_pausing`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-app-server get_auth_status -- --test-threads=1`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo test -p
codex-app-server --lib`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db cargo check -p codex-rollout
-p codex-app-server --tests`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p codex-rollout
-p codex-thread-store -p codex-core -p codex-app-server -p codex-tui -p
codex-exec -p codex-cli`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p codex-rollout -p
codex-app-server`
- `CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p
codex-rollout`
- `CODEX_SKIP_VENDORED_BWRAP=1
CARGO_TARGET_DIR=/tmp/codex-target-state-db just fix -p codex-core`
- `just argument-comment-lint -p codex-core`
- `just argument-comment-lint -p codex-rollout`
Focused coverage added in `codex-rollout`:
- `recorder::tests::state_db_init_backfills_before_returning` verifies
the rollout metadata row exists before startup init returns.
- `state_db::tests::try_init_waits_for_concurrent_startup_backfill`
verifies startup waits for another worker to finish backfill instead of
disabling the handle for the process.
-
`state_db::tests::try_init_times_out_waiting_for_stuck_startup_backfill`
verifies startup does not hang indefinitely on a stuck backfill lease.
-
`tests::find_thread_path_accepts_existing_state_db_path_without_canonical_filename`
verifies DB-backed lookup accepts valid existing rollout paths even when
the filename does not include the thread UUID.
-
`tests::find_thread_path_falls_back_when_db_path_points_to_another_thread`
verifies DB-backed lookup ignores a stale row whose existing path
belongs to another thread and read-repairs the row after filesystem
fallback.
Focused coverage updated in `codex-core`:
- `rollout_list_find::find_prefers_sqlite_path_by_id` now uses a
DB-preferred rollout file with matching `session_meta.id`, so it still
verifies that valid SQLite paths win without depending on stale/empty
rollout contents.
`cargo test -p codex-app-server thread_list_respects_search_term_filter
-- --test-threads=1 --nocapture` was attempted locally but timed out
waiting for the app-server test harness `initialize` response before
reaching the changed thread-list code path.
`bazel test //codex-rs/thread-store:thread-store-unit-tests
--test_output=errors` was attempted locally after the thread-store fix,
but this container failed before target analysis while fetching `v8+`
through BuildBuddy/direct GitHub. The equivalent local crate coverage,
including `cargo test -p codex-thread-store`, passes.
A plain local `cargo check -p codex-rollout -p codex-app-server --tests`
also requires system `libcap.pc` for `codex-linux-sandbox`; the
follow-up app-server check above used `CODEX_SKIP_VENDORED_BWRAP=1` in
this container.
## Why
This is a prep PR in the multi-environment process-tool stack. It
separates ownership/config cleanup from the behavior change that teaches
process tools to route by selected environment, so the follow-up PR can
focus on model-facing `environment_id` behavior.
## Stack
1. https://github.com/openai/codex/pull/20646 - `EnvironmentContext`
rendering for selected environments
2. https://github.com/openai/codex/pull/20669 - selected-environment
ownership and tool config prep (this PR)
3. https://github.com/openai/codex/pull/20647 - process-tool
`environment_id` routing
## What Changed
- keep the resolved turn environment list wrapped in
`ResolvedTurnEnvironments` through `TurnContext` instead of unwrapping
it back to a raw `Vec`
- add `TurnContext::resolve_path_against` so cwd-relative path
resolution has one shared helper
- replace the old tool config boolean with `ToolEnvironmentMode::{None,
Single, Multiple}`
## Testing
- Tests not run locally; this prep refactor is covered by GitHub CI for
the stack.
Co-authored-by: Codex <noreply@openai.com>
## Summary
- Treat `approval_mode = "approve"` as skip-review across all permission
modes.
- Remove the mode-specific split in the MCP auto-approval gate so
approved tools bypass review consistently.
- Expand regression coverage in the shared MCP helper and the core
tool-call flow.
## Testing
- `just fmt`
- `cargo test -p codex-mcp`
- `cargo test -p codex-core
approve_mode_skips_arc_and_guardian_in_every_permission_mode`
- `git diff --check`
- Full `cargo test -p codex-core` was also attempted, but the suite hit
an unrelated pre-existing stack overflow in an existing multi-agent test
## Why
`ModelClientSession` and `compact_conversation_history()` were still
rebuilding the same `ResponsesApiRequest` fields separately. That
duplication makes it easy for normal `/responses` turns and compact
requests to drift when request-shape changes land later, which is
exactly the kind of cache-affecting divergence we want to avoid.
This follow-up keeps the scope small by extracting the shared
request-construction logic into one helper and using it from both paths.
## What changed
- move `ResponsesApiRequest` construction into a shared
`ModelClient::build_responses_request(...)` helper in
`core/src/client.rs`
- update the normal `/responses` streaming path to call that helper
instead of the old `ModelClientSession`-local implementation
- update `compact_conversation_history()` to derive its compact payload
from the same helper so `model`, `instructions`, `input`, `tools`,
`parallel_tool_calls`, `reasoning`, and `text` stay aligned with normal
request building
- add a unit test covering the shared helper's prompt cache key,
installation metadata, and `service_tier` behavior
## Verification
- `cargo test -p codex-core
build_responses_request_sets_shared_cache_and_metadata_fields`
- `cargo test -p codex-core --test all
remote_compact_v2_reuses_context_compaction_for_followups`
## Docs
No docs update needed.
## Summary
Early adopters of the `/goal` feature have provided feedback that they
expect a goal they explicitly paused to remain paused when they resume a
thread. Previously, resuming a thread would reactivate a paused goal.
This PR keeps persisted goal status unchanged during thread resume. This
honors the user feedback while also simplifying the core goal logic.
Rather than have the core logic automatically resume a paused goal, that
responsibility is transferred to the client. The TUI now detects a
resumed thread with a paused goal and asks the user whether to `Resume
goal` or `Leave paused`. The prompt appears only for quiet resume flows,
so users who resume with an immediate prompt are not interrupted.
<img width="544" height="111" alt="image"
src="https://github.com/user-attachments/assets/0ac9de1c-6ee6-47ba-b223-c03c8eb4c192"
/>
## Why
This adds the `remote_compaction_v2` client path so remote compaction
can run through the normal Responses stream and install a
`context_compaction` item that trigger a compaction.
The goal is to migrate some of the compaction logic on the client side
We keeps the v2 transport behind a feature flag while letting follow-up
requests reuse the compacted context instead of falling back to the
legacy compaction item shape.
## What changed
- add `ResponseItem::ContextCompaction` and refresh the generated
app-server / schema / TypeScript fixtures that expose response items on
the wire
- add `core/src/compact_remote_v2.rs` to send compaction through the
standard streamed Responses client, require exactly one
`context_compaction` output item, and install that item into compacted
history
- route manual compact and auto-compaction through the v2 path when
`remote_compaction_v2` is enabled, while keeping the existing remote
compaction path as the fallback
- preserve the new item type across history retention, follow-up request
construction, telemetry, rollout persistence, and rollout-trace
normalization
- add targeted coverage for the feature flag, `context_compaction`
serialization, rollout-trace normalization, and remote-compaction
follow-up behavior
## Verification
- added protocol tests for `context_compaction`
serialization/deserialization in `protocol/src/models.rs`
- added rollout-trace coverage for `context_compaction` normalization in
`rollout-trace/src/reducer/conversation_tests.rs`
- added remote compaction integration coverage for v2 follow-up reuse
and mixed compaction output streams in
`core/tests/suite/compact_remote.rs`
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
`multi_agent_v2` usage hints sometimes need to reference resolved config
values such as the effective thread limit. Those values only exist after
config layering, defaulting, and feature materialization, so the raw
TOML alone was not enough to render them.
## What changed
- allow
`features.multi_agent_v2.{usage_hint_text,root_agent_usage_hint_text,subagent_usage_hint_text}`
to use `{{ ... }}` placeholders backed by the materialized effective
config
- fail config loading with a targeted error when a referenced
placeholder does not exist or does not resolve to a scalar value
- move resolved-config materialization into a shared helper so config
interpolation and config-lock export/replay both serialize the same
resolved feature, memory, and agent settings
## Example
```
[features.multi_agent_v2]
enabled = true
usage_hint_text = "lorem {{ features.multi_agent_v2.max_concurrent_threads_per_session }} ipsum"
```
gets rendered as
```
"description": String("... \lorem 4 ipsum"),
```
## Why
`McpToolCall` was still an app-server item synthesized from deprecated
legacy begin/end events. Recent item migrations moved this ownership
into core `TurnItem`s, so MCP tool calls now follow the same canonical
lifecycle and leave legacy events as compatibility fanout.
Keeping the core item close to the v2 `ThreadItem::McpToolCall` shape
also avoids spreading MCP result semantics across app-server conversion
code. Core now owns whether a completed call is `completed` or `failed`,
and whether the payload is a tool result or an error.
## What changed
- Added core `TurnItem::McpToolCall` with flattened `server`, `tool`,
`arguments`, `status`, `result`, and `error` fields.
- Updated MCP tool call emitters, including MCP resource tools, to emit
`ItemStarted`/`ItemCompleted` around directly constructed core MCP
items.
- Updated app-server v2 conversion to project the core MCP item into
`ThreadItem::McpToolCall` without deriving status or splitting `Result`
locally.
- Ignored live deprecated MCP legacy fanout in app-server v2 to avoid
duplicate item notifications, while keeping thread history replay on the
legacy event path.
## Verification
- `cargo test -p codex-protocol`
- `cargo test -p codex-app-server-protocol`
- `cargo test -p codex-core --lib mcp_tool_call`
- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server
mcp_tool_call_completion_notification_contains_truncated_large_result`
Tool suggest still misfires when model needs tool_search, updating the
prompts to further disambiguate it:
- [x] rename it from `tool_suggest` to `request_plugin_install`
- [x] rephrase "suggestion" to "install" in the tool descriptions.
- [x] disambiguate "the tool" vs "the plugin/connector".
Tested with the Codex App and verified it still works.
## Why
The model needs a way to see which environments are available during a
multi-environment turn without changing the legacy single-environment
prompt surface or pulling replay/persistence changes into the same
review.
## Stack
1. https://github.com/openai/codex/pull/20646 - `EnvironmentContext`
rendering for selected environments (this PR)
2. https://github.com/openai/codex/pull/20669 - selected-environment
ownership and tool config prep
3. https://github.com/openai/codex/pull/20647 - process-tool
`environment_id` routing
## What Changed
- extend `environment_context` so multi-environment turns render an
`<environments>` block with the selected environment ids and cwd values
- keep zero- and single-environment turns on the existing cwd-only
render path
- keep replay and persistence paths on the legacy surface for now so
this PR stays scoped to live prompt rendering
- add focused coverage in
`codex-rs/core/src/context/environment_context_tests.rs`
## Testing
- CI
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
Image-view results should be represented as a core-produced turn item
instead of being reconstructed by app-server. At the same time, existing
rollout/history paths still understand the legacy `ViewImageToolCall`
event, so this keeps that event as compatibility output generated from
the new item lifecycle.
## What changed
- Added `TurnItem::ImageView` to `codex-protocol`.
- Emitted image-view item start/completion directly from the core
`view_image` handler.
- Kept `ViewImageToolCall` as a legacy event and generate it from
completed `TurnItem::ImageView` items.
- Kept `thread_history.rs` on the legacy `ViewImageToolCall` replay
path, with `ImageView` item lifecycle events ignored there.
- Updated app-server protocol conversion, rollout persistence, and
affected exhaustive event matches for the new item plus legacy fan-out
shape.
## Verification
- `cargo test -p codex-protocol -p codex-app-server-protocol -p
codex-rollout -p codex-rollout-trace -p codex-mcp-server -p
codex-app-server --lib`
- `cargo test -p codex-core --test all
view_image_tool_attaches_local_image`
- `just fix -p codex-protocol -p codex-core -p codex-app-server-protocol
-p codex-app-server -p codex-rollout -p codex-rollout-trace -p
codex-mcp-server`
- `git diff --check`
## Why
`ConfigBuilder::build` performs a large amount of async config loading.
Leaving that entire future on the caller stack makes config startup more
fragile on small runtime worker stacks.
## What changed
- keep `ConfigBuilder::build` as a thin wrapper that boxes the
config-loading future before awaiting it
- move the existing implementation into a private `build_inner` method
so the large async state machine lives on the heap instead of the
runtime thread stack
## Testing
- Not run locally
## Summary
- make selected turn environments the source of truth for session
runtime cwd and MCP runtime environment selection
- keep local/no-selection fallback behavior intact
- add coverage for duplicate selected environments, cwd resolution, and
MCP runtime environment selection
## Validation
- git diff --check
- rustfmt was run on touched Rust files during the implementation
workflow
CI should provide the full Bazel/test signal.
---------
Co-authored-by: Codex <noreply@openai.com>
# Why
`notify` is the remaining compatibility surface from the legacy hook
implementation. The newer lifecycle hook engine now owns the active hook
system, so we should start steering users away from adding new `notify`
configs before removing the old path entirely. This also adds a
lightweight watchpoint for the deprecation so we can see how much legacy
usage remains before the clean drop.
# What
- emit a startup deprecation notice when a non-empty `notify` command is
configured
- emit `codex.notify.configured` when a session starts with legacy
`notify` configured
- emit `codex.notify.run` when the legacy notify path fires after a
completed turn
- mark `notify` as deprecated in the config schema and repo docs
- remove the orphaned `codex-rs/hooks/src/user_notification.rs` file
that is no longer compiled
- add regression coverage for the new deprecation notice
# Next steps
A follow-up PR can remove the legacy notify path entirely once we are
ready for the clean drop. Before then, we can watch
`codex.notify.configured` and `codex.notify.run` to understand the
deprecation impact and remaining active usage. The cleanup PR should
then delete the `notify` config field, the `legacy_notify`
implementation, the old compatibility dispatch types and callsites that
only exist for the legacy path, and the remaining compatibility
docs/tests.
# Testing
- `cargo test -p codex-hooks`
- `cargo test -p codex-config`
- `cargo test -p codex-core emits_deprecation_notice_for_notify`
## Why
`/goal` is supposed to keep Codex working until the goal is actually
done. The previous continuation logic had two ways to stop early: the
continuation prompt told the model to wait for new input when it felt
blocked, and the runtime suppressed another continuation turn after a
continuation finished without any tool calls.
That made goals stop short even when the agent could still keep making
progress (I received a few reports of this from users). It also relied
on a brittle heuristic that treated "no registry tool calls" as
equivalent to "should stop."
## What changed
- removed the continuation prompt sentence that told the model to stop
and wait for new input when it could not continue productively
- removed the goal runtime suppression heuristic that stopped
auto-continuation after a no-tool continuation turn
- deleted the continuation-activity bookkeeping and left `tool_calls` as
telemetry only
- added focused regressions for the two intended behaviors: completed
no-tool continuation turns still continue, while `request_user_input`
keeps the existing turn open instead of spawning a new continuation
## Why
Apply-patch file changes are now part of the core turn item stream, so
v2 clients can consume the same first-class item lifecycle path used by
other turn items instead of relying on app-server-specific remapping
from legacy patch events.
## What changed
- Added a core `TurnItem::FileChange` carrying apply-patch changes and
completion metadata.
- Updated the apply-patch tool emitter to send `ItemStarted` /
`ItemCompleted` with the new `FileChange` item while preserving legacy
`PatchApplyBegin` / `PatchApplyEnd` fan-out.
- Updated app-server v2 conversion to render the new core item directly
and stopped `event_mapping` from remapping old patch begin/end events
into item notifications.
- Kept thread history reconstruction based on the existing old
apply-patch events for rollout compatibility.
## Verification
- `cargo test -p codex-protocol -p codex-app-server-protocol`
- `cargo test -p codex-core --test all
apply_patch_tool_executes_and_emits_patch_events`
- `cargo test -p codex-app-server bespoke_event_handling`
## Why
For reproducibility. A hand-written `config.toml` is not enough to
recreate what a Codex session actually ran with because layered config,
CLI overrides, defaults, feature aliases, resolved feature config,
prompt setup, and model-catalog/session values can all affect the final
runtime behavior.
This PR adds an effective config lockfile path: one run can export the
resolved session config, and a later run can replay that lockfile and
fail early if the regenerated effective config drifts.
## What Changed
- Add a dedicated `ConfigLockfileToml` wrapper with top-level lockfile
metadata plus the replayable config:
```toml
version = 1
codex_version = "..."
[config]
# effective ConfigToml fields
```
- Keep lockfile metadata out of regular `ConfigToml`; replay loads
`ConfigLockfileToml` and then uses its nested `config` as the
authoritative config layer.
- Add `debug.config_lockfile.export_dir` to write
`<thread_id>.config.lock.toml` when a root session starts.
- Add `debug.config_lockfile.load_path` to replay a saved lockfile and
validate the regenerated session lockfile against it.
- Add `debug.config_lockfile.allow_codex_version_mismatch` to optionally
tolerate Codex binary version drift while still comparing the rest of
the lockfile.
- Add `debug.config_lockfile.save_fields_resolved_from_model_catalog` so
lock creation can either save model-catalog/session-resolved fields or
intentionally leave those fields dynamic.
- Build lockfiles from the effective config plus resolved runtime values
such as model selection, reasoning settings, prompts, service tier, web
search mode, feature states/config, memories config, skill instructions,
and agent limits.
- Materialize feature aliases and custom feature config into the
lockfile so replay compares canonical resolved behavior instead of
user-authored alias shape.
- Strip profile/debug/file-include/environment-specific inputs from
generated lockfiles so they contain replayable values rather than the
inputs that produced those values.
- Surface JSON-RPC server error code/data in app-server client and TUI
bootstrap errors so config-lock replay failures include the actual TOML
diff.
- Regenerate the config schema for the new debug config keys.
## Review Notes
The main flow is split across these files:
- `config/src/config_toml.rs`: lockfile/debug TOML shapes.
- `core/src/config/mod.rs`: loading `debug.config_lockfile.*`, replaying
a lockfile as a config layer, and preserving the expected lockfile for
validation.
- `core/src/session/config_lock.rs`: exporting the current session
lockfile and materializing resolved session/config values.
- `core/src/config_lock.rs`: lockfile parsing, metadata/version checks,
replay comparison, and diff formatting.
## Usage
Export a lockfile from a normal session:
```sh
codex -c 'debug.config_lockfile.export_dir="/tmp/codex-locks"'
```
Export a lockfile without saving model-catalog/session-resolved fields:
```sh
codex -c 'debug.config_lockfile.export_dir="/tmp/codex-locks"' \
-c 'debug.config_lockfile.save_fields_resolved_from_model_catalog=false'
```
Replay a saved lockfile in a later session:
```sh
codex -c 'debug.config_lockfile.load_path="/tmp/codex-locks/<thread_id>.config.lock.toml"'
```
If replay resolves to a different effective config, startup fails with a
TOML diff.
To tolerate Codex binary version drift during replay:
```sh
codex -c 'debug.config_lockfile.load_path="/tmp/codex-locks/<thread_id>.config.lock.toml"' \
-c 'debug.config_lockfile.allow_codex_version_mismatch=true'
```
## Limitations
This does not support custom rules/network policies.
## Verification
- `cargo test -p codex-core config_lock`
- `cargo test -p codex-config`
- `cargo test -p codex-thread-manager-sample`
## Why
Users have shared that the TUI can feel too visually flat because themes
mostly show up in code syntax highlighting. The configurable statusline
is a natural place to make the active theme more visible, while still
letting users keep the existing monotone statusline if they prefer it.
## What Changed
- Added a statusline styling helper that builds the rendered statusline
from `(StatusLineItem, text)` segments, preserving item identity while
keeping the plain text output unchanged.
- Derived foreground accent colors from the active syntax theme by
looking up TextMate scopes through the existing syntax highlighter, with
conservative ANSI fallbacks when a scope does not provide a foreground.
- Tuned theme-derived colors to keep the accents visible without making
the statusline feel overly bright.
- Added `[tui].status_line_use_colors`, defaulting to `true`, plus a
separated `/statusline` toggle so users can enable or disable
theme-derived statusline colors from the setup UI.
- Updated the live statusline and `/statusline` preview to use the same
styled builder, while keeping terminal-title preview text plain.
- Kept statusline separators and active-agent add-ons subdued while
removing blanket dimming from the whole passive statusline.
## Verification
- `cargo test -p codex-tui status_line`
- `cargo test -p codex-tui theme_picker`
- `cargo test -p codex-tui foreground_style_for_scopes`
- `cargo test -p codex-tui`
- `cargo test -p codex-config`
- `cargo test -p codex-core status_line_use_colors`
- `cargo insta pending-snapshots --manifest-path tui/Cargo.toml`
## Visual
<img width="369" height="23" alt="Screenshot 2026-04-30 at 6 16 08 PM"
src="https://github.com/user-attachments/assets/11d03efb-8e4f-4450-8f4d-00a9659ef4cd"
/>
<img width="385" height="23" alt="Screenshot 2026-04-30 at 6 16 02 PM"
src="https://github.com/user-attachments/assets/a3d89f36-bdc1-42e8-8e84-61350e3999e2"
/>
- Build one app-server process ThreadStore from startup config and share
it with ThreadManager and CodexMessageProcessor.
- Remove per-thread/fork store reconstruction so effective thread config
cannot switch the persistence backend.
- Add params to ThreadStore create/resume for specifying thread
metadata, since otherwise the metadata from store creation would be used
(incorrectly).
## Why
Several legacy `EventMsg` variants were still emitted or mapped even
though clients either ignored them or had moved to item/lifecycle
events. `Op::Undo` had also degraded to an unavailable shim, so this
removes that dead task path instead of preserving a command that cannot
do useful work.
`McpStartupComplete`, `WebSearchBegin`, and `ImageGenerationBegin` are
intentionally kept because useful consumers still depend on them: MCP
startup completion drives readiness behavior, and the begin events let
app-server/core consumers surface in-progress web-search and
image-generation items before the final payload arrives.
## What Changed
- Removed weak legacy event variants and payloads from `codex-protocol`,
including legacy agent deltas, background events, and undo lifecycle
events.
- Kept/restored `EventMsg::McpStartupComplete`,
`EventMsg::WebSearchBegin`, and `EventMsg::ImageGenerationBegin` with
serializer and emission coverage.
- Updated core, rollout, MCP server, app-server thread history,
review/delegate filtering, and tests to rely on the useful replacement
events that remain.
- Removed `Op::Undo`, `UndoTask`, the undo test module, and stale TUI
slash-command comments.
- Stopped agent job/background progress and compaction retry notices
from emitting `BackgroundEvent` payloads.
## Verification
- `cargo check -p codex-protocol -p codex-app-server-protocol -p
codex-core -p codex-rollout -p codex-rollout-trace -p codex-mcp-server`
- `cargo test -p codex-protocol -p codex-app-server-protocol -p
codex-rollout -p codex-rollout-trace -p codex-mcp-server`
- `cargo test -p codex-core --test all suite::items`
- `just fix -p codex-protocol -p codex-app-server-protocol -p codex-core
-p codex-rollout -p codex-rollout-trace -p codex-mcp-server`
- Earlier coverage on this PR also included `codex-mcp`, `codex-tui`,
core library tests, MCP/plugin/delegate/review/agent job tests, and MCP
startup TUI tests.
## Summary
Fixes a regression introduced in #10941 so that heredocs do not permit
file redirects to be approved by rules, and adds scenario tests to cover
this behavior.
Previously, heredoc command parsing would allow redirects and
environment variables:
```bash
# commands_for_exec_policy() would parse this via parse_shell_lc_single_command_prefix
PATH=/tmp/bad:$PATH cat <<'EOF' > /tmp/bad/hello.txt
hello
EOF
```
This conflicts with the Codex Rules documentation; heredoc parsing logic
should abide by the same strictness of parsing.
## Tests
- [x] Updated unit tests accordingly
- [x] Added scenario tests for these cases
---------
Co-authored-by: Codex <noreply@openai.com>
## Why
On Windows, Codex runs shell commands through a top-level
`powershell.exe -NoProfile -Command ...` wrapper. `execpolicy` was
matching that wrapper instead of the inner command, so prefix rules like
`["git", "push"]` did not fire for PowerShell-wrapped commands even
though the same normalization already happens for `bash -lc` on Unix.
This change makes the Windows shell wrapper transparent to rule matching
while preserving the existing Windows unmatched-command safelist and
dangerous-command heuristics.
## What changed
- add `parse_powershell_command_plain_commands()` in
`shell-command/src/powershell.rs` to unwrap the top-level PowerShell
`-Command` body with `extract_powershell_command()` and parse it with
the existing PowerShell AST parser
- update `core/src/exec_policy.rs` so `commands_for_exec_policy()`
treats top-level PowerShell wrappers like `bash -lc` and evaluates rules
against the parsed inner commands
- carry a small `ExecPolicyCommandOrigin` through unmatched-command
evaluation and expose `is_safe_powershell_words()` /
`is_dangerous_powershell_words()` so Windows safelist and
dangerous-command checks still work after unwrap
- add Windows-focused tests for wrapped PowerShell prompt/allow matches,
wrapper parsing, and unmatched safe/dangerous inner commands, and
re-enable the end-to-end `execpolicy_blocks_shell_invocation` test on
Windows
## Testing
- `cargo test -p codex-shell-command`
# Why
The hooks feature flag should use the concise canonical name `hooks`,
while existing configs that still use `codex_hooks` continue to work
during the rename.
# What
- change the canonical `Feature::CodexHooks` key from `codex_hooks` to
`hooks`
- register `codex_hooks` through the existing legacy-alias path
- update the config schema and canonical config fixtures to prefer
`hooks`
- add regression coverage that both `hooks` and `codex_hooks` resolve to
`Feature::CodexHooks`
# Verification
- `cargo test -p codex-features`
- `cargo test -p codex-core config::schema_tests`
- `cargo test -p codex-core
pre_tool_use_blocks_shell_when_defined_in_config_toml`
- `cargo test -p codex-app-server
hooks_list_uses_each_cwds_effective_feature_enablement`
## Why
Codex now has configurable TUI keymaps, but the composer still behaves
like a plain text field. Users who prefer modal editing need a way to
keep Vim muscle memory while drafting prompts, and the keymap picker
needs to expose Vim-specific actions if those bindings are configurable
instead of hardcoded.
## What Changed
- Adds composer Vim mode with insert/normal state, common normal-mode
movement and editing commands, `d`/`y` operator-pending flows, and
mode-aware footer and cursor indicators.
- Adds `/vim`, an optional global `toggle_vim_mode` binding, and
`tui.vim_mode_default` so Vim mode can be toggled per session or enabled
as the default composer state.
- Extends runtime and config keymaps with `vim_normal` and
`vim_operator` contexts, exposes those contexts in `/keymap`, refreshes
the config schema, and validates Vim bindings separately.
- Integrates Vim normal mode with existing composer behavior: `/` opens
slash command entry, `!` enters shell mode, `j`/`k` navigate history at
history boundaries, successful submissions reset back to normal mode,
and paste burst handling remains insert-mode only.
- Teaches the TUI render path to apply and restore cursor style so Vim
insert mode can use a bar cursor without leaving the terminal in that
state after exit.
## Validation
- `cargo test -p codex-tui keymap -- --nocapture` on the keymap/Vim
coverage
- `cargo insta pending-snapshots`
## Docs
This introduces user-facing `/vim`, `tui.vim_mode_default`, and Vim
keymap contexts under `tui.keymap`, so the public CLI configuration and
slash-command docs should be updated before the feature ships.
## Why
When an MCP or app tool is configured with approval mode `approve`
(always allow), users expect that decision to be authoritative. In
guardian auto-review mode, ARC could still return `ask-user`, which then
routed the approval question into guardian with the ARC reason as
context. That meant a tool explicitly configured as always allowed still
went through both safety monitors before running.
This change keeps the existing ARC behavior for non-auto-review
sessions, but avoids the ARC-to-guardian sequence when
`approvals_reviewer = auto_review` and the tool approval mode is
`approve`.
## What changed
- Short-circuit MCP tool approval handling when `approval_mode ==
approve` and `approvals_reviewer == auto_review`.
- Updated the MCP approval regression test so the auto-review case
asserts neither ARC nor guardian is called.
- Preserved existing tests that verify ARC can still block always-allow
MCP tools outside guardian auto-review mode.
## Verification
- `cargo test -p codex-core --lib mcp_tool_call`
## Description
Ignore these top-level config keys when loading project-scoped
config.toml files:
```
"openai_base_url",
"chatgpt_base_url",
"model_provider",
"model_providers",
"profile",
"profiles",
"experimental_realtime_ws_base_url",
```
## What changed
- Add a project-local config denylist for credential-routing fields such
as `openai_base_url`, `chatgpt_base_url`, `model_provider`,
`model_providers`, `profile`, `profiles`, and
`experimental_realtime_ws_base_url`.
- Strip those fields from project config layers before they participate
in effective config merging, while leaving safe project-local settings
intact.
- Track ignored project-local keys on config layers and surface a
startup warning telling users to move those settings to user-level
`config.toml` if they intentionally need them.
- Update profile behavior coverage so project-local `profile` /
`profiles` entries are ignored instead of overriding user-level profile
selection.
## Verification
- `cargo test -p codex-config`
- `cargo test -p codex-core
project_layer_ignores_unsupported_config_keys`
- `cargo test -p codex-core project_profiles_are_ignored`
- `cargo test -p codex-core config::config_loader_tests`
- migrate `thread/turns/list` to ThreadStore. Uses ThreadStore for most
data now but merges in the in-memory state from thread manager
- keep v2 `thread/list` pathless-store friendly by converting
`StoredThread` directly to API `Thread`
- add regression coverage for pathless store history/listing
## Summary
- Adds a separate feature control for external-browser Browser Use
integrations.
- Registers `browser_use_external` as a stable, default-enabled
requirements-owned feature key.
- Updates feature registry tests and regenerates the config schema.
Codex validation:
- `cargo fmt -- --config imports_granularity=Item`
- `cargo run -p codex-core --bin codex-write-config-schema`
- `cargo test -p codex-features`
## Addendum
This gives enterprise policy a coarse control for Browser Use outside
the Codex-managed in-app browser. The existing `browser_use` feature is
the Browser Use control, while `browser_use_external` can gate
extension/native integrations for external browsers as that surface
grows
## Why
`item/fileChange/outputDelta` text output was only the tool's summary or
error text and not used by client surfaces.
We keep `item/fileChange/outputDelta` in the app-server protocol as a
deprecated compatibility entry, but the server no longer emits it.
## What changed
- stop the `apply_patch` runtime from emitting `ExecCommandOutputDelta`
events
- simplify `item_event_to_server_notification` so command output deltas
always map to `item/commandExecution/outputDelta`
- remove the app-server bookkeeping that tried to detect whether an
output delta belonged to a file change
- mark `item/fileChange/outputDelta` as a deprecated legacy protocol
entry in the v2 types, schema, and README
- simplify the file-change approval tests so they only wait for
completion instead of expecting output-delta notifications
## Testing
- `cargo test -p codex-app-server-protocol`
- `cargo test -p codex-thread-manager-sample`
- `cargo test -p codex-app-server-protocol
protocol::event_mapping::tests::exec_command_output_delta_maps_to_command_execution_output_delta
-- --exact`
- `cargo test -p codex-app-server
turn_start_file_change_approval_accept_for_session_persists_v2 --
--exact` *(failed before the test assertions because the wiremock
`/responses` mock received 0 requests in setup)*
## Why
Large MCP tool call outputs can make rollout JSONL files enormous. In
the session that motivated this change, the biggest JSONL records were:
- `event_msg/mcp_tool_call_end`
- `response_item/function_call_output`
both containing the same unbounded MCP payloads - just 3 MCP tool calls
that each were multi-hundred MBs 😱
This PR truncates both of those JSONL records.
## How
#### For `response_item/function_call_output`
Unified exec already bounds tool output before it is injected into
model-facing history, which also keeps the corresponding rollout
`response_item/function_call_output` records small.
MCP should follow the same pattern: truncate the model-facing tool
output at the tool-output boundary, while leaving code-mode/raw hook
consumers alone.
#### For `event_msg/mcp_tool_call_end`
`McpToolCallEnd` also needs its own bounded event copy because it is the
app-server/replay/UI event shape that backs `ThreadItem::McpToolCall`.
Unfortunately this is _not_ downstream of the `ToolOutput` trait.
## Model behavior
Model behavior is actually unchanged as a result of this PR.
Before this PR, MCP output was:
1. Converted to `FunctionCallOutput`.
2. Recorded into in-memory history.
3. Truncated by `ContextManager::record_items()` before later model
turns saw it.
After this branch, MCP output is truncated earlier, in
`McpToolOutput::response_payload()`, using the same helper. Then
`ContextManager::record_items()` sees an already-truncated output and
effectively has little/no additional work to do.
So the model should still see the same kind of truncated function-call
output. The practical difference is where truncation happens: earlier,
before rollout persistence/app-server emission can see the giant
payload.
## Verification
- `cargo test -p codex-core mcp_tool_output`
- `cargo test -p codex-core
mcp_tool_call::tests::truncate_mcp_tool_result_for_event`
- `cargo test -p codex-core
mcp_post_tool_use_payload_uses_model_tool_name_args_and_result`
- `just fmt`
- `just fix -p codex-core`
- `git diff --check`
