## Why
Model and reasoning effort updates during a turn can leave request metadata and tool hooks reporting the turn's initial settings. Metadata should describe the step that issued the request or tool call.
## What changed
- Share captured execution metadata across Responses, MCP, and extension tool calls, including model, reasoning effort, and automatic review and Node REPL flags.
- Build Responses tool inventory metadata from the issuing step's finalized tool router. Attach the finalized inventory separately for remote compaction.
- Use captured step settings for pre- and post-tool hooks, and captured review settings for permission-request hooks.
## Testing
Add and extend regression tests for model and effort changes during a turn, MCP metadata, pre-tool hook model attribution, captured review flags, and tool inventory matching the issuing request.
GitOrigin-RevId: 9dee46a8b4839de8b434cdad4ed441cc0bb6ff9b
## What changed
Move the synchronous review loop, outcome mapping, deadline helpers, and session pool into `codex-guardian-reviewer`. Core supplies adapters for evidence capture, authorization checks, session creation, and event publication through the new host interfaces.
Have `guardian-v2` initialize the reviewer pool and host separately, with the pool managing prewarming, session reuse, concurrent forks, invalidation, and shutdown.
## Testing
Extend the app-server reviewer lifecycle test to cover interrupted concurrent reviews as well as completed reviews, including resuming a reviewer after parent shutdown. Adapt core reviewer tests to use the pool and factory interfaces.
GitOrigin-RevId: 2d69bd20c169b20534764b98cbdb63f38564a530
## Why
With reasoning effort overrides enabled, compaction used the selected effort even when sampling requests still used an earlier pinned effort. Successful compaction also left that old pin active in the new context window.
## What changed
- Use the pinned request effort for local and remote compaction when it matches the model.
- Resolve fallback models' effort without mutating the live pin, preserving it if compaction fails.
- Reset the pin after successful compaction so the next sampling request establishes the selected effort as its baseline without a redundant `configuration_update`.
## Testing
Add regression coverage for remote compaction success and failure, fallback model effort selection, pin preservation during fallback lookup, and compaction after resuming with overrides disabled.
GitOrigin-RevId: 35e666b0c8026553500715ddbe7bef02cd759f4a
## Why
Reasoning-effort changes should preserve the request baseline while trusted `configuration_update` items carry the selected effort.
## What changed
- Pin request-level reasoning effort for the current model when reasoning-effort overrides are available, including during WebSocket prewarm.
- Re-establish the selected effort after rollback, resume, or a model switch, refreshing the trusted override even when the selection is unchanged.
- Continue using the selected request effort when overrides are unavailable.
## Testing
Add regression coverage for WebSocket prewarm and reconnect, rollback, resume, and model switches. Update transition tests to assert that request-level effort stays pinned while configuration updates change.
GitOrigin-RevId: 89cfee6289543230347b0488d1388190b4da7216
## What changed
- Store the shared `GuardianReviewSessionManager` in thread extension data and let the Guardian extension spawn and fork reviewers through `ThreadManager`, independently of async scorer startup.
- Preserve reviewer reuse, concurrent forks, cancellation, inherited environments, and user instructions. Gate managed reviewer startup on parent registration and remove terminated reviewers from the manager.
- Retain the `guardian` subagent identity in saved conversations. Reject resume of live Guardian reviewers and reject client archive or delete of live owner-managed workers with JSON-RPC error `-32600`; allow normal access after the owner releases them.
- Keep standalone reviewer support for inline delegates and remove duplicated extension prompt and configuration code.
## Testing
Add app-server tests covering reviewer reuse and concurrent forks, inherited instructions and prompt cache keys, live resume and removal rejection, saved reviewer discovery and resume after parent shutdown, and strict Guardian assessment inside an inline review.
GitOrigin-RevId: 4f9893c1ade151eacb4c11ffeae3d9e9ec019187
## What changed
- Add the zero-based `window_number` to Responses turn metadata and include it in prewarm requests.
- Persist `forked_from_ordinal_exclusive` separately from the physical history base so fork lineage remains accurate after reverts and cold resumes.
- Report context-inheriting subagents through `parent_thread_id` without also emitting fork lineage.
- Reserve the new metadata keys while accepting and filtering previously valid configured values so Codex-owned values take precedence.
## Testing
- Cover window numbering across compaction, resume, and fork operations.
- Cover fork cutoff persistence across direct forks, legacy rollouts, reverts into inherited history, and cold resumes.
GitOrigin-RevId: 288f6cd632254814c1f166668b33828082d799a1
## What changed
- Add the opt-in `code_mode_prewarm` feature to establish the code-mode host session during startup, before the first turn.
- Make in-progress host initialization cancellable so a stalled prewarm does not block shutdown.
- Share a failed connection attempt with concurrent callers instead of immediately starting another attempt.
## Testing
- Verify app-server contacts the configured host before the first turn and can shut down while that connection is stalled.
- Exercise shared remote-host behavior with prewarming enabled.
GitOrigin-RevId: 3cfde5509be7b4aba80112c36c5616b9a9b632c6
## Why
Thread settings can change while a turn is running, and delegated review or
compaction steps can select a different model. Each request needs a consistent
set of settings resolved against the model that will execute it.
## What changed
- Capture immutable resolved settings for each model step, including model
metadata, reasoning options, service tier, approvals, and personality.
- Keep in-flight steps on their captured settings while applying thread updates
to subsequent work.
- Resolve inherited reasoning summaries and filter service tiers against the
selected model and feature configuration for review and compaction steps.
## Testing
Added coverage for settings updates during paused turns, model changes,
previous-model compaction, review-model defaults, and service-tier filtering.
GitOrigin-RevId: fca4b3b305379f1bf26a5cac75ee0dd1747ac1f6
## Why
Thread settings can change while a turn is still active, including between sampling requests. Those updates should apply to the next turn instead of changing the model configuration partway through the current turn.
## What changed
- Snapshot the model, reasoning settings, service tier, approval settings, and model-attributed telemetry in `StepContext`.
- Build prompts, model requests, world state, tracing, and startup prewarms from that step-scoped snapshot.
- Share immutable model metadata between turn and step contexts.
## Testing
Added an integration test that pauses an active turn, updates its thread settings, and verifies that all requests in the active turn retain the original settings while the next turn uses the updates.
GitOrigin-RevId: c51352218e463dcc9b7338566d16742292c49fbf
## Why
Persisted base instructions need to retain whether they were explicitly customized or generated from a model template. Without that distinction, forks and config-lock replays can treat model-generated instructions as custom and keep the wrong template after a model or personality change.
## What changed
- Record custom or model provenance with base instructions in rollouts and config locks.
- Preserve custom instructions across model changes, while allowing model-generated instructions to follow the selected model and personality.
- Keep legacy rollouts without provenance compatible and propagate provenance through forks and spawned agents.
## Testing
- Cover provenance serialization and legacy rollout decoding.
- Cover role personality changes, forked model changes, config-lock replay, and multi-agent configuration.
GitOrigin-RevId: 801c26559835f558027ce5112700c0cd31fcb21b
## Why
Interrupting a turn while MCP tools were still starting could abort before the
submitted user input was recorded in conversation history.
## What changed
- Build and retain the MCP tool list and tool router as part of each step
snapshot, using the turn cancellation token during tool discovery.
- Record turn hooks and submitted input when cancellation occurs during startup
prewarming, pre-sampling compaction, or first-step capture.
- Reuse the captured router for sampling, compaction, and prompt debugging so
advertised and executable tools share the same request-scoped view.
## Testing
Add coverage that interrupts each affected MCP startup phase and verifies that
the user prompt remains in history before the turn-aborted marker.
GitOrigin-RevId: 6e96c6814357a55545d69b580e28f35933cfadf7
## What changed
Instrument the spawned WebSocket startup prewarm task with a
`startup_prewarm` trace span. Set its OpenTelemetry name and attach the
session's `thread.id` so prewarm work can be associated with its session.
GitOrigin-RevId: f2d642d145686b883cd82be8a594bd2383470651
## Why
With deferred executors, a turn can begin before a remote environment
attaches. AGENTS.md discovery previously ran only during session setup,
so instructions from a later environment never reached the model or the
session instruction sources.
WorldState persistence has now landed, so this uses the durable
model-visible baseline directly instead of carrying a temporary
resume/fork compatibility path.
## What
- Add an `AgentsMdManager` in `SessionServices` to own host
instructions, loaded state, and refresh caching.
- When `DeferredExecutor` is enabled, refresh AGENTS.md when attached
environment selections change and freeze the result in the corresponding
`StepContext`.
- Represent AGENTS.md as a persisted WorldState section for every
session, with bounded initial, replacement, and removal updates.
- Remove duplicate AGENTS.md state and rendering from
`SessionConfiguration` and `TurnContext`.
- Build initial context, per-request updates, and compaction context
from the same step-scoped value.
- On resume and fork, compare current instructions with the restored
WorldState baseline and inject a replacement exactly once when they
differ.
Builds on #29833, #29835, and #29837.
## Tests
- Covers a remote environment becoming ready mid-turn, with AGENTS.md
appearing on the next request exactly once and updating canonical
instruction sources.
- Covers full, unchanged, replaced, and removed AGENTS.md WorldState
rendering.
- Covers changed instructions across cold resume and fork without
duplicate reinjection.
- Covers remote-v2 compaction retaining creation-time instructions in
the live session and cold resume appending one replacement when the
source changed.
- Ran focused `codex-core` AGENTS.md, WorldState, and context-update
test suites.
## Stack
This is PR 3 of the simplified HAI single-run-task stack:
- [#19047](https://github.com/openai/codex/pull/19047) Agent Identity
assertion and task-registration primitives, including the shared
run-task helper used by existing Agent Identity JWT auth.
- [#19049](https://github.com/openai/codex/pull/19049)
Disabled-by-default ChatGPT auth opt-in that provisions/reuses persisted
Agent Identity runtime auth and its single run task.
- [#19051](https://github.com/openai/codex/pull/19051) Run-scoped
provider auth that uses one backend-owned task id for first-party
inference and compaction requests.
[#19054](https://github.com/openai/codex/pull/19054) collapsed out of
the active stack because the simplified design no longer needs a
separate background/control-plane task helper.
## Summary
This PR moves Agent Identity usage into provider auth resolution. That
keeps `AgentAssertion` auth tied to first-party OpenAI provider requests
instead of applying a late session-wide override that could affect
local, custom, Bedrock, API-key, or external-bearer providers.
What changed:
- adds a small `ProviderAuthScope` struct carrying the run auth policy
and session source needed by provider-scoped auth resolution
- lets `Session` opt the existing `ModelClient` into `ChatGptAuth`
policy when `use_agent_identity` is enabled, without adding a second
model-client constructor
- resolves Agent Identity only for first-party OpenAI provider auth
paths
- uses the persisted run task id from the `AgentIdentityAuth` record to
build `AgentAssertion` auth for Responses requests
- routes shared request setup through scoped provider auth so unary
compact requests use the same run-task assertion path as inference turns
- keeps local/custom/Bedrock/env-key/external-bearer provider auth
unchanged
- lets missing run-task state surface through the existing model-request
error path instead of silently falling back to bearer auth
This PR intentionally does not create thread-scoped, target-scoped, or
background-scoped task identities. The run task is the only task Codex
registers in this POC shape.
## Testing
- `just test -p codex-model-provider`
- `just test -p codex-core client::tests::provider_auth_scope_uses`
- `just test -p codex-core remote_compact_uses_agent_identity_assertion`
## Why
With deferred executors, an environment can become ready between two
sampling requests in the same turn. The model-visible environment
update, advertised tools, and eventual tool execution must all describe
the same request-time view.
Otherwise, a request built while only environment B is ready can
advertise a tool without an `environment_id`; if higher-priority
environment A becomes ready before execution, that call could silently
run in A instead.
This PR is stacked on #29527.
## Design
`run_turn` captures one `Arc<StepContext>` at each sampling-request
boundary. That step owns the request's `TurnContext` and environment
snapshot.
- World-state environment updates and tool planning borrow that same
step.
- `ToolCallRuntime` retains the `Arc` while asynchronous tool calls
execute.
- `ToolInvocation` carries the step to handlers; its temporary `turn`
compatibility field is derived from the same object.
- `ToolRouter` does not retain `StepContext`; it only uses it while
constructing the request's tool set.
- With `DeferredExecutor` disabled, step capture keeps using the
environments frozen at turn start.
Simply: every sampling request gets one consistent picture of its
environments, from what the model sees through where its tool calls run.
## What changed
- Build environment-dependent tool specs from the current request's
`StepContext`.
- Use that same step for unified exec, legacy shell, `apply_patch`,
`view_image`, and `request_permissions` execution.
- Hide environment-backed tools, including `request_permissions`, while
no environment is attached.
- Resolve legacy shell paths and metadata from the selected step
environment instead of the stale turn-start environment.
- Capture explicit steps at non-turn-loop boundaries such as compaction,
prompt debug, and startup prewarm.
- Reconcile prompt-debug history from the same step used to build its
tools.
## Follow-up
- Bind yielded code-mode cells to the tool runtime that created them, so
nested calls made after yielding continue to use the originating
request's `StepContext`.
## Test plan
- `just test -p codex-core
deferred_executor_updates_context_and_tools_after_startup`
- `just test -p codex-core
environment_count_controls_environment_backed_tools`
- `just test -p codex-core
build_prompt_input_includes_context_and_user_message`
## Why
The first auto-review currently creates its Guardian child session on
demand, adding avoidable latency before the review can begin. Creating
the ordinary Guardian child during parent-session initialization lets
that child use the existing session startup WebSocket prewarm before the
first escalation. This does not introduce a Guardian-specific prewarm
mechanism.
## What changed
- initialize the existing Guardian review-session manager owned by
`Session` when a thread starts with auto-review enabled and an approval
policy that routes to Guardian
- use the standard Guardian child-session construction and the existing
session startup WebSocket prewarm
- preserve the existing reuse-key invalidation and lazy creation
fallback when startup initialization fails or the effective review
configuration changes
- add an integration test that verifies normal root-session startup
emits a Guardian `generate=false` prewarm request
## Benchmark
I compared release builds against main. Each prompt first ran a
non-escalated `sleep 3`, then requested an escalated marker command.
| binary | count | avg Guardian duration | median Guardian duration |
avg Guardian TTFT |
|---|---:|---:|---:|---:|
| origin-main | 10 | 4008.7 ms | 3949.5 ms | 3746.5 ms |
| session-fix | 10 | 2865.0 ms | 2594.0 ms | 2492.7 ms |
Guardian duration fell by 28.5% and Guardian TTFT fell by 33.5%. These
measurements cover Guardian review latency; they do not measure parent
thread-start latency.
## Why
Codex app-server latency traces do not granularly cover turn task
startup and inter-request handoffs. These spans help attribute time
across task execution, startup prewarm, in-flight tool completion, and
rollout persistence.
## What changed
- Add `session_task.run` spans around task execution and
`session_task.flush_rollout` around flushing pending conversation
transcript writes to durable storage
- Add `regular_task.prepare_run_turn` around regular-turn startup (Send
the `TurnStarted` event, reset turn-specific reasoning state, and
resolve any startup prewarm)
- Add `startup_prewarm.resolve` around waiting for background session
prewarming to finish, fail, time out, or be cancelled
- Add a function-level trace span around draining in-flight tool calls
(Wait for tool calls to complete, record tool result in conversation
history, and other bookkeeping)
## Verification
Trigger Codex rollout and observe new spans are included
## What
Introduce a `CodexResponsesMetadata` struct that defines all the core
metadata we send to Responses API. Example fields are `thread_id`,
`turn_id`, `window_id`, etc.
Going forward, `client_metadata["x-codex-turn-metadata"]` will be the
canonical way Codex sends metadata to Responses API across both HTTP and
websocket transports.
For now, we continue to emit the existing top-level HTTP headers and
top-level `client_metadata` fields from the same
`CodexResponsesMetadata` struct for compatibility reasons.
Also, app-server clients who specify additional
`responsesapi_client_metadata` via `turn/start` and `turn/steer` will
have those fields merged into
`client_metadata["x-codex-turn-metadata"]`, but cannot override the
reserved fields that core uses (i.e. the fields in
`CodexResponsesMetadata`).
## Why
Responses API request instrumentation is the source of truth for
downstream Codex analytics that join requests by Codex IDs such as
session, thread, turn, and context window. Before this change, those
values were assembled through several request-specific paths: HTTP
request bodies, websocket handshake headers, websocket `response.create`
payloads, compaction requests, and the rich `x-codex-turn-metadata`
envelope all had their own wiring.
That made metadata propagation easy to drift across API-key/direct
Responses API requests, ChatGPT-auth/proxied requests, websocket
requests, and compaction requests. It also made additions like
`window_id` error-prone because a field could be added to one transport
projection but missed in another.
## What changed
- Added `CodexResponsesMetadata` as the core-owned snapshot for Codex
metadata sent to ResponsesAPI.
- Render `client_metadata["x-codex-turn-metadata"]`, flat
`client_metadata` projections, and direct compatibility headers from
that same snapshot.
- Include the known Codex-owned fields in the turn metadata blob,
including installation/session/thread/turn/window IDs, request kind,
lineage, sandbox/workspace metadata, timing, and compaction details.
- Treat app-server `responsesapi_client_metadata` as enrichment for the
Codex turn metadata blob while preventing those extras from overriding
Codex-owned fields.
- Use the same metadata path for normal turns, websocket prewarm, local
compaction, remote v1 compaction, and remote v2 compaction.
- Keep websocket connection-only preconnect metadata separate so
handshakes carry compatibility identity headers without inventing a fake
turn metadata blob.
## Verification
- `cargo check -p codex-core`
- `just fix -p codex-core`
## Why
Compaction window identity is part of session history, not model-client
transport state. Persisting it with the compacted rollout item lets
resumed threads continue from the reconstructed window without keeping
mutable window state on `ModelClient`.
## What changed
- Added `window_id` to `CompactedItem` and stamp it when
`replace_compacted_history` installs compacted history.
- Moved auto-compact window id ownership into `AutoCompactWindow` /
`SessionState`; `ModelClient` now receives the request window id from
callers instead of storing it.
- Returned `window_id` from rollout reconstruction for resume.
Reconstruction uses the newest surviving compacted item's stored
`window_id` when present, and falls back to the legacy compacted-item
count when it is absent.
- Kept fork startup at the fresh default window id and updated direct
model-client tests to pass explicit test window ids.
## Validation
- `cargo check -p codex-core --tests`
## Summary
We originally addressed startup prewarming holding the read side of
`RwLock<McpConnectionManager>` by snapshotting tool-list state. Review
feedback identified the broader ownership problem: the outer
synchronization should only publish or retrieve the current manager,
while MCP operations rely on the manager's internal synchronization. A
follow-up preserved operation retirement with a separate gate, but
further review questioned whether that synchronization was actually
required and whether we could support latest-wins replacement instead.
This PR now stores the current MCP manager in `ArcSwap`. Each operation
uses `load_full()` to obtain an owned `Arc<McpConnectionManager>`, then
performs MCP I/O without retaining the publication mechanism. Refresh
cancels obsolete startup work, constructs a replacement, and atomically
publishes it. New operations see the latest manager, while operations
that already loaded the previous manager retain a valid handle. Refresh
happens at a turn boundary, so there should be no active user tool calls
to drain.
Git history supports dropping the outer `RwLock`. It was introduced in
`03ffe4d595` on November 17, 2025 for non-blocking MCP startup: the
session published an empty manager, startup initialized that same object
while holding the write lock, and readers waited for initialization.
`7cd2e84026` on February 19, 2026 removed that two-phase initialization
in favor of constructing a fresh manager and swapping it in, explicitly
noting that `Option` or `OnceCell` could replace the placeholder design.
Hot reload later reused the existing lock to publish a replacement, but
I found no indication that the lock was introduced to guarantee
in-flight tool calls finish before refresh or shutdown.
Terminal shutdown remains separate from refresh: it aborts startup
prewarming and active tasks before shutting down the current manager, so
tool calls may be interrupted and no model WebSocket work continues
after shutdown. Focused regression coverage exercises pending tool-list
cancellation, deferred refresh, and startup-prewarm shutdown.
## Summary
- accept non-empty model-defined reasoning effort values while
preserving built-in effort behavior
- propagate the non-Copy effort type through core, app-server, TUI,
telemetry, and persistence call sites
- preserve string wire encoding and expose an open-string schema for
clients
- update model selection and shortcut behavior for model-advertised
effort values
## Root cause
`ReasoningEffort` gained a string-backed custom variant, so it could no
longer implement `Copy` or rely on derived closed-enum serialization.
Existing consumers still moved effort values from shared references and
assumed a fixed built-in value set.
## Validation
- `just fmt`
- Local tests and compilation were not run per request; relying on CI.
## Summary
- skip startup websocket prewarm setup when the model client has
Responses-over-WebSocket disabled
- avoid making HTTP-only sessions build prewarm prompt/tool state that
cannot produce a reusable websocket session
## Why
Recent macOS timing flakes were timing out while waiting for first-turn
events in HTTP-only core tests. Startup prewarm is only useful for
websocket-capable providers, but it was scheduled for every session. For
HTTP-only test providers this added unnecessary async startup work
before the regular turn could reach the mocked response flow.
## Testing
- bazel test //codex-rs/core:core-all-test
--test_filter=suite::auto_review::remote_model_override_uses_catalog_model_for_strict_auto_review
--test_output=errors
- bazel test //codex-rs/core:core-all-test
--test_filter=suite::request_permissions_tool::approved_folder_write_request_permissions_unblocks_later_apply_patch
--test_output=errors
Stack split from #25708. Original PR intentionally left open. This third
PR resolves the effective per-thread multi-agent runtime from persisted
metadata, inherited runtime, and current model selection.
## Summary
- Add `request_kind` values for foreground turn, startup prewarm,
compaction, and detached memory model requests.
- Attach compaction dispatch metadata to local Responses, legacy
`/v1/responses/compact`, and remote v2 compact requests.
- Add the existing logical context-window identifier as `window_id` on
turn-owned model request metadata.
- Keep identity fields optional for detached memory requests, while
still emitting `request_kind="memory"` in non-git/no-sandbox workspaces.
## Root Cause
`x-codex-turn-metadata` has more than one producer. Foreground turns and
compaction requests own a real turn and should carry that turn identity.
Detached memory stage-one requests do not own a foreground turn, so
absent identity fields are valid rather than missing data. Startup
websocket prewarm is also a model request, but it has `generate=false`
and must not be counted as a foreground turn.
`thread_source` or session source identifies where a thread came from
(for example review, guardian, or another subagent). `request_kind`
identifies what the current outbound model request is doing (`turn`,
`prewarm`, `compaction`, or `memory`). A review or guardian thread can
issue either a normal turn request or a compaction request, so source
cannot replace request kind.
## Behavior / Impact
- Ordinary foreground requests send `request_kind="turn"`, their real
identity fields, and `window_id="<thread_id>:<window_generation>"`.
- Startup websocket warmup requests send `request_kind="prewarm"` so
they are not counted as foreground turns.
- Compaction requests send `request_kind="compaction"`, their real
owning turn identity, the existing `window_id`, and
`compaction.{trigger,reason,implementation,phase,strategy}`.
- Detached memory stage-one requests send `request_kind="memory"`
without `session_id`, `thread_id`, `turn_id`, or `window_id`; when no
workspace metadata exists, the kind-only header is still emitted.
- `session_id`, `thread_id`, `turn_id`, and `window_id` remain optional
in the header schema because detached memory requests do not own a
foreground turn or context window.
- `window_id` is not a new ID system: it is copied from the already-sent
`x-codex-window-id` / WS client metadata value at model-request dispatch
time.
- Existing `x-codex-window-id` HTTP/WS emission, value format,
generation advancement, resume behavior, and fork reset behavior are
unchanged.
- `request_kind`, `window_id`, and upstream turn-owned identity fields
remain schema-owned; input `responsesapi_client_metadata` cannot replace
their canonical values.
- No table, DAG, export, app-server API, or MCP `_meta` schema changes
are included.
A compaction attempt stopped by a pre-compact hook issues no model
request and therefore has no request header; its outcome remains in
analytics events. Status, error, duration, and token deltas also remain
analytics fields rather than request-header fields.
Future detached-memory attribution using a real initiating turn ID as
`trigger_turn_id` is intentionally not part of this PR.
## Sync With Main
- Final pushed head `716342e79` is rebased onto `origin/main@0d37db4b2`.
- The metadata conflict came from upstream `#24160`, which added
`forked_from_thread_id` on the same `turn_metadata` surface. Resolution
preserves that field and its protection from client metadata override
alongside this PR's request-kind, compaction, and window-id fields.
- While resolving the overlapping commits, I removed an accidental
recursive model-request overlay and a duplicate detached-memory header
builder before completing the rebase.
## Latency / User Experience Boundary
- Foreground turns perform no new filesystem, git, or network work. New
fields are inserted into metadata already serialized for outgoing
requests.
- Compaction issues the same model/HTTP requests with the same prompt,
model, service tier, and sampling settings; only metadata bytes change.
- Startup prewarm already sent metadata; it is now correctly classified
as `prewarm`.
- Non-git detached memory now sends a small kind-only metadata header
rather than no header.
- This client diff adds no user-visible latency mechanism beyond
negligible serialization and header bytes on already-existing requests.
## Validation
On conflict-resolved head `1d35c2cfb` based on `origin/main@487521733`:
- `just fmt` (passed)
- `just fix -p codex-core` (passed)
- `git diff --check origin/main...HEAD` (passed)
- `just test -p codex-core -E 'test(turn_metadata) |
test(websocket_first_turn_uses_startup_prewarm_and_create) |
test(responses_stream_includes_turn_metadata_header_for_git_workspace_e2e)
|
test(responses_websocket_forwards_turn_metadata_on_initial_and_incremental_create)
| test(remote_compact_v2_retries_failures_with_stream_retry_budget) |
test(window_id_advances_after_compact_persists_on_resume_and_resets_on_fork)'`
(`23 passed`; `bench-smoke` passed)
- `just test -p codex-app-server -E
'test(turn_start_forwards_client_metadata_to_responses_request_v2) |
test(turn_start_forwards_client_metadata_to_responses_websocket_request_body_v2)
| test(auto_compaction_remote_emits_started_and_completed_items)'` (`3
passed`; `bench-smoke` passed)
- `just test -p codex-memories-write` (`29 passed`; `bench-smoke`
passed)
## Why
While investigating `codex exec hi` startup latency, the useful
questions were not "is startup slow?" but "which durable bucket is slow
in production?"
The path we observed has a few distinct stages:
1. `thread/start` creates the session
2. startup prewarm builds the turn context, tools, and prompt
3. startup prewarm warms the websocket
4. the first real turn resolves the prewarm
5. the model produces the first token
Before this PR, production telemetry had some of the raw measurements
already:
- aggregate startup-prewarm duration / age-at-first-turn metrics
- TTFT as a metric
- websocket request telemetry
But there was no coherent production event stream for the startup
breakdown itself, and TTFT was metric-only. That made it hard to answer
the same latency questions from OpenTelemetry-backed logs without adding
one-off local instrumentation.
## What changed
Add durable production telemetry on the existing `SessionTelemetry`
path:
- new `codex.startup_phase` OTel log/trace events plus
`codex.startup.phase.duration_ms`
- new `codex.turn_ttft` OTel log/trace events while preserving the
existing TTFT metric
The startup phase event is emitted for the coarse buckets we actually
observed while running `exec hi`:
- `thread_start_create_thread`
- `startup_prewarm_total`
- `startup_prewarm_create_turn_context`
- `startup_prewarm_build_tools`
- `startup_prewarm_build_prompt`
- `startup_prewarm_websocket_warmup`
- `startup_prewarm_resolve`
These phases are intentionally low-cardinality so they remain safe as
production telemetry tags.
## Why this shape
This keeps the instrumentation on the same production path as the rest
of the session telemetry instead of adding a local debug-only trace
mode. It also avoids changing startup behavior:
- prewarm still runs
- no control flow changes
- no extra remote calls
- no user-visible behavior changes
One boundary is intentional: very early process bootstrap that happens
before a session exists is not included here, because this PR uses
session-scoped production telemetry. The expensive buckets we were
trying to understand after `thread/start` are now covered durably.
## Verification
- `cargo test -p codex-otel`
- `cargo test -p codex-core turn_timing`
- `cargo test -p codex-core
regular_turn_emits_turn_started_without_waiting_for_startup_prewarm`
- `cargo test -p codex-core
interrupting_regular_turn_waiting_on_startup_prewarm_emits_turn_aborted`
- `cargo test -p codex-app-server thread_start`
- `just fix -p codex-otel -p codex-core -p codex-app-server`
I also ran `cargo test -p codex-core`; it built successfully and then
hit an existing unrelated stack overflow in
`tools::handlers::multi_agents::tests::tool_handlers_cascade_close_and_resume_and_keep_explicitly_closed_subtrees_closed`.
## Summary
- reduce public module visibility across Rust crates, preferring private
or crate-private modules with explicit crate-root public exports
- update external call sites and tests to use the intended public crate
APIs instead of reaching through module trees
- add the module visibility guideline to AGENTS.md
## Validation
- `cargo check --workspace --all-targets --message-format=short` passed
before the final fix/format pass
- `just fix` completed successfully
- `just fmt` completed successfully
- `git diff --check` passed
Stacked on #16508.
This removes the temporary `codex-core` / `codex-login` re-export shims
from the ownership split and rewrites callsites to import directly from
`codex-model-provider-info`, `codex-models-manager`, `codex-api`,
`codex-protocol`, `codex-feedback`, and `codex-response-debug-context`.
No behavior change intended; this is the mechanical import cleanup layer
split out from the ownership move.
---------
Co-authored-by: Codex <noreply@openai.com>
## Description
This PR fixes a bad first-turn failure mode in app-server when the
startup websocket prewarm hangs. Before this change, `initialize ->
thread/start -> turn/start` could sit behind the prewarm for up to five
minutes, so the client would not see `turn/started`, and even
`turn/interrupt` would block because the turn had not actually started
yet.
Now, we:
- set a (configurable) timeout of 15s for websocket startup time,
exposed as `websocket_startup_timeout_ms` in config.toml
- `turn/started` is sent immediately on `turn/start` even if the
websocket is still connecting
- `turn/interrupt` can be used to cancel a turn that is still waiting on
the websocket warmup
- the turn task will wait for the full 15s websocket warming timeout
before falling back
## Why
The old behavior made app-server feel stuck at exactly the moment the
client expects turn lifecycle events to start flowing. That was
especially painful for external clients, because from their point of
view the server had accepted the request but then went silent for
minutes.
## Configuring the websocket startup timeout
Can set it in config.toml like this:
```
[model_providers.openai]
supports_websockets = true
websocket_connect_timeout_ms = 15000
```
Abhinav