## What changed
- Add `otel.tool_result.max_bytes`, defaulting to 2048 bytes, to control the
text included in `codex.tool_result` logs independently of model-visible
output limits.
- Apply truncation centrally when emitting telemetry, preserve UTF-8
boundaries, and report whether the logged output was truncated.
- Record typed tool names and namespaces, agent names, and process-local result
sequence numbers while keeping tool arguments and output out of trace events.
## Testing
- Cover configuration propagation, UTF-8-safe truncation, raw tool-output
logging, and log/trace event routing and fields.
GitOrigin-RevId: 89ca76e55f1a09b729e7770ce01f2e4d98f9a22d
## Why
Creating the telemetry shutdown thread during shutdown can fail under resource
pressure, including when the native thread guard page cannot be allocated.
## What changed
- Start and verify a dedicated shutdown worker when `OtelProvider` is created.
- Send the provider to the prepared worker for bounded shutdown, while preserving
timeout behavior and avoiding a potentially blocking destructor if worker
preparation failed.
- Rename the fallible provider constructor to `try_new`.
## Testing
Add Unix regression coverage that injects guard-page allocation failures, plus
coverage for worker preparation failure, successful shutdown, and timeouts.
GitOrigin-RevId: 3656298078a800a7fa392437c2ee4a68753092e3
## What changed
- Track app-server turn lifecycle events for OpenAI API-key sessions when OTLP telemetry export is enabled.
- Query the turn-cost endpoint after completed or aborted turns and emit `codex.turn_cost` with the estimated USD cost, interruption state, model, speed, and reasoning effort.
- Preserve provider organization and project headers, wait for all observed responses to be priced, and retry pending or transiently failed queries with bounded tracking.
- Re-probe availability after authentication changes and shut the worker down with other app-server background tasks.
## Testing
- Cover late API-key login, transient probe failures, telemetry after thread removal, and turns with multiple responses.
- Verify turn-cost requests use API-key authentication and provider scope headers and deserialize priced response data.
GitOrigin-RevId: a303162a54798b554fcb2e9e2b372e1cf9f49f39
## What changed
- Represent blocked network requests as approval actions so permission hooks,
automatic review, and user review use the common approval flow.
- Route network requests using the active turn's review settings, including for
background terminals started by an earlier turn.
- Record the final applied network decision in tool telemetry without exposing
the destination or assigning an approval source.
- Persist deny amendments and keep the blocked request denied.
## Testing
Added coverage for strict automatic review, cross-turn background network
requests, deny amendment persistence, and destination-safe telemetry.
GitOrigin-RevId: a2a9d106962f407ed93f4d198f40ced15f090b8e
## What changed
- Recognize validated create and edit marker commands from the trusted presentations, documents, spreadsheets, and PDF plugins.
- Emit a `codex_artifact_operation` analytics event plus started-count and expected-output-count metrics when a recognized marker starts through unified exec.
- Attribute remote executor commands only when their plugin cache path and script contents match a trusted local plugin, including primary-runtime plugins.
## Testing
- Cover supported marker combinations and reject mismatched plugins, paths, arguments, counts, and output formats.
- Cover local, relocated remote, and Windows-style plugin attribution, including rejection of modified remote scripts.
GitOrigin-RevId: 475cc1689aa7f371a24dec0a8bdb6f7fd5a2e922
## What changed
- Exclude conversation turn count, response-engine latency, and turn token usage metrics from the built-in Statsig exporter, alongside the existing API and tool-call exclusions.
- Apply the Statsig exclusion list consistently to counters, histograms, gauges, observable gauges, and duration histograms.
- Preserve all excluded metrics for custom OTLP exporters and extend the loopback coverage to verify they are exported.
GitOrigin-RevId: e49f9aa1433126a3de8dbed76a4d2688f2831af8
## What changed
Add the `codex.turn.unified_exec.running_processes` counter and increment it
by the number of background terminal processes remaining when a turn finishes.
GitOrigin-RevId: 82a33b89533960d86cef95360fa122836c8aa84d
## Why
An account change can select different OpenTelemetry collector settings. The
long-running app server needs to stop exporting telemetry with the previous
account's configuration.
## What changed
- Rebuild and install the log, trace, and metrics exporters when authentication
changes, and shut down the previous provider without blocking the app server.
- Make cached global metrics clients and the tracing layer follow the replacement
provider so existing callers continue exporting through the current account's
configuration.
- Clear the cached cloud configuration loader after login and logout so telemetry
reloads from the new account context.
## Testing
- Add an app-server integration test that switches accounts and verifies logs,
traces, and metrics reach the new collector while trace context is preserved.
- Add a metrics test covering cached clients after provider replacement.
GitOrigin-RevId: a74359777a35edbee5bbe0b2baccc155074cb172
## Why
A stalled telemetry exporter can block shutdown indefinitely when the interactive TUI exits.
## What changed
- Add `OtelProvider::shutdown_with_timeout` to run exporter shutdown on a detached thread and report completion, worker failure, or timeout.
- Give interactive TUI telemetry shutdown a 500 ms time budget and warn if cleanup does not finish successfully.
## Testing
- Cover successful shutdown on current-thread and multi-thread Tokio runtimes, worker creation failure, and timeout behavior.
- Verify that OTLP HTTP shutdown returns on time when a collector stalls.
GitOrigin-RevId: 5b5f31a841fbc5788715cb3065d522c6dafa994f
## What changed
- Treat `codex.api_request` and `codex.api_request.duration_ms` as runtime-only metrics for Statsig exporters, matching the existing tool-call metric behavior.
- Keep both metrics available through other OTLP exporters.
## Testing
- Extend the Statsig filtering test to cover both API request metrics.
- Verify the OTLP HTTP exporter still sends the API request count and duration.
GitOrigin-RevId: f0f800ade7979e4da72ae59641bf42aa8a3ebd5a
## What changed
- Treat `codex.tool.call` and `codex.tool.call.duration_ms` as runtime-only metrics when using the built-in Statsig exporter.
- Continue exporting both metrics through explicitly configured OTLP exporters.
## Testing
- Verify the Statsig configuration omits the tool-call metrics while retaining unrelated metrics.
- Extend the OTLP HTTP loopback test to cover the tool-call counter and duration histogram.
GitOrigin-RevId: 46dd2642063b34e9a4c69b67d58b45721609fcf2
## What changed
- Guard `OtelProvider::shutdown` so exporters shut down at most once, including when an explicit shutdown is followed by `Drop`.
- Let tracer provider shutdown handle flushing without a separate `force_flush` call.
- Add regression tests for explicit shutdown and drop-only shutdown.
GitOrigin-RevId: f3c8769146ee57102477eb9ee7fd948f688efb79
## What changed
- Add an optional `ExtensionMetrics` capability to thread, turn-input, and world-state contributors, backed by session telemetry in the host.
- Record skill counts, omissions, and truncated description characters for extension-rendered catalogs, tagged by the catalog surface.
- Preserve host session attribution on extension metrics, including the effective model for each turn, and prevent extension tags from overriding host metadata.
- Avoid duplicate host-catalog samples by recording world-state metrics only when the section is published or changes.
## Testing
- Cover metric values and surface tags, session metadata preservation, turn-level model changes, and host world-state publication behavior.
GitOrigin-RevId: 9059e521943a8f81df25a38b03692eddbc1d990d
## Why
Requests longer than 10 seconds were grouped into the overflow bucket, limiting visibility into long-running request latency.
## What changed
Add second-based duration histogram boundaries at 12, 15, 20, 30, 60, and 120 seconds.
## Testing
Extend the duration histogram test to cover every new boundary and a 121-second overflow value.
GitOrigin-RevId: 063a5d397dbd37d3b3940c7a1632b7b479e874a4
## What changed
- Parse `cache_write_tokens` from response input token details and carry it through token usage aggregation.
- Expose `cache_write_input_tokens` in protocol, app-server, exec, and TypeScript SDK usage events, defaulting it to zero for compatibility with older payloads.
- Report cache-write usage in analytics, metrics, traces, and rollout data alongside existing cache-read usage.
## Testing
- Add coverage for response parsing, usage event output, aggregation, analytics, metrics, and telemetry fields.
GitOrigin-RevId: 634e4fbe3086a8923c0ee13b622573e7d9d221bd
## What changed
Add finer-grained buckets from 1 to 10 seconds and extend millisecond duration histograms with buckets up to 120 seconds.
GitOrigin-RevId: dee492de08db058444926d22281ef7bc4ba1cdeb
## What changed
- Emit `responsesapi.websocket_timing` payloads as opt-in trace events with request context, while excluding them from diagnostic uploads and persisted logs by default.
- Preserve fractional-millisecond TBT values in telemetry histograms and runtime summaries, rounding only when formatting the TUI label.
## Testing
- Cover timing-log filtering, fractional TBT collection and display, and existing whole-millisecond duration behavior.
GitOrigin-RevId: 5f0a1c60c237abed17cc8b2d569ca77fbbc6ec41
## Summary
When enabled for the OpenAI provider, Codex sends
`stream_options.reasoning_summary_delivery = "sequential_cutoff"` on
HTTP and
WebSocket requests, including prewarm, and renders completed summary
sections
from `reasoning_summary_text.done`. Flag-off and non-OpenAI behavior is
unchanged.
## Expected rollout
```text
reasoning 0 added
summary 0 done
summary 1 done
summary 2 starts
summary 2 cancelled / incomplete
reasoning 0 done <-- cancel summary 2 work and mark it incomplete
message 1 added
message 1 text streams
message 1 completed
```
Depends on
[openai/openai#1096660](https://github.com/openai/openai/pull/1096660).
## Why
Codex telemetry pipeline needs a per-request TTFT value. The existing
`codex.turn_ttft` is recorded once per turn, so it cannot represent
later inference requests in the same turn and can miss the beginning of
hidden reasoning.
This restores the low-volume per-request signal proposed in
https://github.com/bk-nvidia/codex/pull/3 without bringing back
per-WebSocket-event TRACE logging.
## What changed
- start a timer when each mapped Responses stream begins
- latch the timer on the first `response.output_item.added`, including
an empty hidden-reasoning item
- attach `ttft_ms` to the existing `codex.sse_event` /
`response.completed` telemetry record
- cover the new completion field with an integration test
## Semantics
The value is per inference request, not per turn. It measures
mapped-stream-to-first-output-item latency, matching the
customer-proposed metric. For HTTP, the stream is already established
before timing begins, so request setup and response-header latency are
excluded.
`response.output_item.added` is a client-visible proxy for the start of
hidden reasoning; this does not claim access to the server's internal
first raw-token timestamp.
## Validation
- `just test -p codex-otel` (47 passed)
- `just test -p codex-core process_sse_emits_completed_telemetry` (1
passed after the final timer-placement change)
- attempted `just test -p codex-core`: 2,855 passed and 53 failed
because of unrelated local-environment failures (missing
`test_stdio_server` fixture binary, shell startup noise, and
timing-sensitive tests); the focused telemetry test passed in that run
as well
Fixes distributed trace continuity across exec-server JSON-RPC HTTP
egress by adding an executor client span and injecting its W3C context
through a reusable `codex-otel` helper.
This preserves the caller trace across core/tool → executor →
provider/MCP instead of dropping parentage at raw reqwest.
Note that this doesn't include the websocket path, which is needed to
really get the full story but at least we cover the basic http path with
this change.
## Summary
- Record bounded connection, request, and process lifecycle metrics.
- Report active gauges from callbacks on every collection, including
delta exports.
- Serialize active-count updates so concurrent starts and finishes
cannot publish stale values.
- Serialize process exit, explicit termination, and shutdown through the
process registry so exactly one completion result wins.
- Keep the implementation small with single-owner RAII guards and one
real OTLP/HTTP integration test using the existing `wiremock`
dependency.
## Root cause
Process exit and session shutdown previously used cloned completion
state. That avoided duplicate emission, but it duplicated lifecycle
ownership and made the ordering harder to reason about. The process
registry mutex already defines the lifecycle ordering, so the final
implementation stores the metric guard and termination flag directly on
the process entry. Whichever path claims the entry first owns the
completion result.
Production metric export uses delta temporality. Event-only synchronous
gauge recordings disappear after the next collection when no count
changes, so active counts now use observable callbacks that report
current state on every collection.
The cleanup also removes the constant `result="accepted"` connection
tag, redundant route and response assertions, a custom HTTP collector,
and fallback initialization machinery that did not add behavior.
## Stack
Review and land this stack in order:
1. #27466 — trace exec-server JSON-RPC requests
2. #27467 — record bounded connection, request, and process lifecycle
metrics **(this PR)**
3. #27470 — observe remote registration and Noise rendezvous lifecycle
## Validation
- `just test -p codex-exec-server --lib` (158 passed)
- `just test -p codex-cli --test exec_server` (3 passed)
- `just test -p codex-otel
observable_gauge_is_collected_on_every_delta_snapshot` (1 passed)
- `CARGO_BUILD_JOBS=1 just fix -p codex-otel -p codex-exec-server`
- `just fmt`
- `git diff --check`
## 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
Authentication mode is a domain concept used by login, model selection,
telemetry, and transports. Keeping the canonical type in app-server
protocol forces those lower-level crates to depend on an unrelated wire
API.
## What changed
- Added canonical `codex_protocol::auth::AuthMode` domain values.
- Kept the app-server wire DTO unchanged and added an explicit app-side
conversion.
- Removed production app-server-protocol dependencies from login,
model-provider-info, models-manager, and otel call paths.
## Stack
This is PR 2 of 6, stacked on [PR
#29714](https://github.com/openai/codex/pull/29714). Review only the
delta from `codex/split-json-rpc-protocols`. Next: [PR
#29722](https://github.com/openai/codex/pull/29722).
## Validation
- Auth and login coverage passed in the focused protocol/domain test
run.
- App-server account and auth conversion coverage passed.
When using Responses Lite, we should all use `additional_tools` and a
developer item instead of the top level tools array & instructions
field. This keeps things 1-to-1.
Forced namespacing for _all_ tools will land in a following PR after
some coordination & fixes in Responses API (around collisions & return
items).
The goal is to eventually expand the scope of this to _all_ requests
from codex, but that will require larger coordination across providers &
slower rollout.
## Summary
NVIDIA asked to measure Fast mode usage and reasoning effort from Codex
CLI OTEL logs. Add the finalized `service_tier` and
`model_reasoning_effort` to the existing `codex.sse_event`
`response.completed` record.
This intentionally reuses the existing completion event and leaves
transport APIs and shared telemetry plumbing unchanged.
## Testing
- `cargo build -p codex-cli --bin codex`
- `just test -p codex-core responses_api_emits_api_request_event`
- End-to-end with the built CLI and a local OTLP/HTTP collector:
- Fast/high emitted `service_tier=priority` and
`model_reasoning_effort=high` with token usage.
- Standard/low omitted `service_tier` and emitted
`model_reasoning_effort=low` with token usage.
## Why
Every successful Responses WebSocket event currently produces three
local log records: the full payload at TRACE, an OpenTelemetry log
event, and an OpenTelemetry trace event.
On busy threads these records fill the 1,000-row log partition in
seconds and cause continuous SQLite insert-and-prune churn.
Related to
https://openai.slack.com/archives/C095U48JNL9/p1782128972644209
## What changed
- Stop logging each successful Responses WebSocket payload at TRACE.
- Stop emitting `codex.websocket_event` as OpenTelemetry log and trace
events.
- Keep WebSocket event counters, duration metrics, response timing
metrics, parsing, and error handling.
Responses API safety buffering metadata currently stops at the transport
boundary, so app-server clients cannot render the in-progress safety
review state.
This change:
- decodes and deduplicates `safety_buffering` metadata from Responses
API SSE and WebSocket events without suppressing the original response
event
- emits a typed core event containing the requested model plus backend
use cases and reasons
- forwards that event as `turn/safetyBuffering/updated` through
app-server v2 and updates generated protocol schemas
- keeps the side-channel event out of persisted rollouts and turn timing
This supports the Codex Apps buffering UX and depends on the Responses
API backend work in https://github.com/openai/openai/pull/1044569 and
https://github.com/openai/openai/pull/1044571.
Validation:
- focused `codex-core` safety-buffering integration test passes
- `cargo check -p codex-core -p codex-app-server -p
codex-app-server-protocol`
- `just fix -p codex-api -p codex-protocol -p codex-core -p
codex-app-server-protocol -p codex-app-server -p codex-rollout -p
codex-rollout-trace -p codex-otel`
- `just fmt`
- broad package test run: 4,430/4,492 passed; 62 unrelated
local-environment/concurrency failures involved unavailable test
binaries, MCP subprocess setup, and app-server timeouts
The workspace denies `clippy::expect_used` in production. Although
`clippy.toml` allows `expect` in tests, Bazel Clippy compiles
integration-test helper code in a way that does not receive that
exemption, which encouraged verbose `unwrap_or_else(... panic!(...))`
and equivalent `match`/`let else` forms.
This allows `clippy::expect_used` once at each integration-test crate
root (including aggregated suites and test-support libraries), then
replaces manual panic-based Result and Option unwraps with
`expect`/`expect_err`. Standalone `tests/*.rs` files remain their own
crate roots. Intentional assertion and unexpected-variant panics remain
unchanged, and the production `expect_used = "deny"` lint remains in
place.
The cleanup is mechanical and net-negative in line count.
## Why
Exec-server request and connection latencies need fractional-second
histograms. The existing duration API records integer milliseconds and
uses millisecond-scale buckets.
## What changed
- Adds a described duration API that records `Duration` values as
fractional seconds.
- Uses second-scale explicit histogram boundaries.
- Caches duration histograms by name, unit, and description, matching
the existing instrument caching model.
- Covers exact boundaries, representative bucket placement, fractional
sums, and exported metadata.
This PR only adds the duration primitive. It does not add exec-server
adoption.
## Stack
1. #26091: counter descriptions
2. #27057: gauge instruments
3. **#27058: second-based duration histograms**
4. #25019: initialize exec-server OpenTelemetry at startup
Related independent coverage: #27059 tests OTLP HTTP log and trace event
export.
## Validation
- `just test -p codex-otel`
## Description
This PR adds an optional `metadata` field to `ResponseItem` for
Responses API calls. Only mechanical plumbing, no actual values
populated and sent yet. Turns out just adding a new field to
`ResponseItem` has quite a large blast radius already.
This change is backwards compatible because `metadata` is optional and
omitted when absent, so existing response items and rollout history
without it still deserialize and requests that do not set it keep the
same wire shape. For provider compatibility, we strip out `metadata`
before non-OpenAI Responses requests so Azure and AWS Bedrock never see
this field.
My followup PR here will actually make use of it to start storing and
passing along `turn_id`: https://github.com/openai/codex/pull/28360
## What changed
- Added `ResponseItemMetadata` with optional `turn_id`, plus optional
`metadata` on Responses API item variants and inter-agent communication.
- Preserved item metadata through response-item rewrites such as
truncation, missing tool-output synthesis, compaction history
rebuilding, visible-history conversion, rollout/resume, and generated
app-server schemas/types.
- Strip item metadata from non-OpenAI Responses requests while
preserving it for OpenAI-shaped requests.
- Updated the mechanical fixture/test construction churn required by the
new optional field.
## Why
The generic OTLP HTTP paths for log events and trace events need
end-to-end coverage before exec-server relies on them.
## What changed
- Adds loopback coverage for exporting `codex_otel.log_only` events to
`/v1/logs`.
- Verifies `codex_otel.trace_safe` events are present in the exported
trace payload.
This is a test-only PR. It does not change OTEL runtime behavior or
metric APIs.
## Related work
- #26091: counter descriptions
- #27057: gauge instruments
- #27058: second-based duration histograms
This PR is independent and can land directly on `main`.
## Validation
- `just test -p codex-otel`
- `just fix -p codex-otel`
- `just fmt`
## Why
Codex needs to manage Amazon Bedrock API key credentials through the
existing auth lifecycle instead of introducing a separate auth manager
or provider-specific credential file. Treating Bedrock API key login as
a primary auth mode gives it the same persistence, keyring, reload, and
logout behavior as the existing OpenAI API key and ChatGPT modes.
The credential is valid only for the `amazon-bedrock` model provider.
OpenAI-compatible providers must reject this auth mode rather than
treating the Bedrock key as an OpenAI bearer token.
## What changed
- Added `bedrockApiKey` as an app-server `AuthMode` and
`CodexAuth::BedrockApiKey` as a primary `AuthManager` mode.
- Added `BedrockApiKeyAuth`, containing the API key and AWS region, to
the existing `AuthDotJson` payload stored in `$CODEX_HOME/auth.json` or
the configured keyring backend.
- Added `login_with_bedrock_api_key(...)`, parallel to
`login_with_api_key(...)`, which replaces the current stored login with
Bedrock credentials.
- Reused generic auth reload and logout behavior instead of adding a
Bedrock-specific auth manager or logout path.
- Updated login restrictions, status reporting, diagnostics, telemetry
classification, generated app-server schemas, and auth fixtures for the
new mode.
- Added explicit errors when Bedrock API key auth is selected with an
OpenAI-compatible model provider.
This PR establishes managed storage and auth-mode behavior. Routing the
managed key and region into Amazon Bedrock requests will be in follow-up
PRs.
## Why
Exec-server observability needs current-value measurements in addition
to counters. The reusable OTEL client should expose that primitive
without coupling it to exec-server runtime behavior.
## What changed
- Adds integer gauge instruments, with optional descriptions.
- Caches gauges by name and description so instrument metadata remains
part of the declaration identity.
- Covers gauge values, descriptions, merged attributes, and OTLP HTTP
export.
This PR only adds the gauge primitive. It does not add second-based
duration histograms or exec-server adoption.
## Stack
1. #26091: counter descriptions
2. **#27057: gauge instruments**
3. #27058: second-based duration histograms
Related independent coverage: #27059 tests OTLP HTTP log and trace event
export.
## Validation
- `just test -p codex-otel`
- `just fix -p codex-otel`
- `just fmt`
## Why
Metric descriptions should be declared with reusable OTEL instruments
instead of being coupled to individual consumers. Counter descriptions
are the smallest API primitive needed by the exec-server observability
work.
## What changed
- Adds `counter_with_description` while preserving the existing counter
API.
- Caches counters by name and description so instrument metadata remains
part of the declaration identity.
- Covers the exported description together with the existing value and
attribute contract.
This PR only adds counter descriptions. It does not add gauges,
second-based durations, or exec-server adoption.
## Stack
1. **#26091: counter descriptions**
2. #27057: gauge instruments
3. #27058: second-based duration histograms
Related independent coverage: #27059 tests OTLP HTTP log and trace event
export.
The `codex-exec-server` bounded service tag now stays with the
exec-server adoption change instead of this reusable infrastructure
stack.
## Validation
- `just test -p codex-otel`
- `just fix -p codex-otel`
- `just fmt`
## Summary
- add v2 personal access token support for `codex login
--with-access-token` and `CODEX_ACCESS_TOKEN`
- classify opaque `at-` tokens separately from legacy Agent Identity
JWTs
- hydrate required ChatGPT account metadata through AuthAPI
`/v1/user-auth-credential/whoami`
- use PATs directly as bearer tokens while preserving existing ChatGPT
account surfaces
- expose PAT-backed auth as the explicit `personalAccessToken`
app-server auth mode
## Implementation
PAT auth is intentionally small and stateless. Loading a PAT performs
one AuthAPI metadata request, stores the hydrated metadata in the
in-memory auth object, and redacts the secret from debug output. Legacy
Agent Identity JWT handling remains unchanged. The shared access-token
classifier lives in a private neutral module because it dispatches
between both credential types.
PAT hydration fails closed when AuthAPI omits any required metadata,
including email. Hydrated metadata is intentionally not persisted:
startup performs a live `whoami` preflight so revoked tokens or changed
account metadata are not accepted from a stale cache.
## Workspace restriction scope
This change intentionally does **not** apply
`forced_chatgpt_workspace_id` to PAT authentication. The setting is a
client-side config guardrail, not an authorization boundary, and PAT
does not currently require workspace-ID parity. The PAT login and
`CODEX_ACCESS_TOKEN` paths therefore validate through AuthAPI without
threading workspace-restriction state through access-token loading.
Existing workspace checks for non-PAT auth remain on their established
paths.
## App-server compatibility
The public app-server `AuthMode` is shared across v1 and v2, and
PAT-backed auth reports `personalAccessToken` through both APIs.
Following human review, this intentionally removes the temporary v1
compatibility mapping that reported PATs as `chatgpt`; the deprecated v1
API is kept in parity with v2 rather than maintaining a separate closed
enum. Clients with exhaustive auth-mode handling in either API version
must add the new case and should generally treat it as ChatGPT-backed
unless they need PAT-specific behavior.
The v1 auth-status response still omits the raw PAT when `includeToken`
is requested because that response cannot carry the account metadata
needed to reuse the credential safely. Persisted PAT auth also omits the
new enum value so older Codex builds can deserialize `auth.json` and
infer PAT auth from the credential field after a rollback.
## Validation
Latest review-fix validation:
- `CARGO_INCREMENTAL=0 just test -p codex-login` (126 passed)
- `CARGO_INCREMENTAL=0 just test -p codex-cli` (263 passed)
- `CARGO_INCREMENTAL=0 just test -p codex-cli
stored_auth_validation_handles_personal_access_token`
- `CARGO_INCREMENTAL=0 just test -p codex-app-server-protocol` (226
passed)
- `CARGO_INCREMENTAL=0 just test -p codex-models-manager
refresh_available_models_uses_remote_only_catalog_for_chatgpt_auth`
- `CARGO_INCREMENTAL=0 just test -p codex-tui
existing_non_oauth_chatgpt_login_counts_as_signed_in`
- `CARGO_INCREMENTAL=0 just fix -p codex-login -p
codex-app-server-protocol -p codex-models-manager -p codex-tui -p
codex-cli`
- `just fmt`
- `git diff --check`
The broader `codex-tui` suite previously compiled and ran 2,834 tests.
Three unrelated environment-sensitive guardian/IDE-socket tests failed
after retries; the PAT-relevant TUI coverage passed.
## Why
First-party backends can supply turn-scoped moderation metadata that
app-server clients need for client-side presentation. Exposing this as
an experimental typed notification lets opted-in clients consume it
without interpreting raw Responses API events.
## What changed
- forward `response.metadata.openai_chatgpt_moderation_metadata` from
Responses API SSE and WebSocket streams as turn-scoped moderation
metadata
- emit the experimental app-server v2 `turn/moderationMetadata`
notification with `{ threadId, turnId, metadata }`
- add app-server integration coverage for the typed moderation metadata
notification
## Testing
- `just test -p codex-core
build_ws_client_metadata_includes_window_lineage_and_turn_metadata`
- `just test -p codex-core` (fails locally: 46 failures and 1 timeout,
primarily missing `test_stdio_server` and shell snapshot timeouts)
- `just test -p codex-app-server-protocol`
- `just test -p codex-app-server
turn_moderation_metadata_emits_typed_notification_v2`
- `just test -p codex-app-server` (fails locally: 792 passed, 10 failed,
and 5 timed out; failures are in existing environment-sensitive tests,
primarily because nested macOS `sandbox-exec` is not permitted)
- `just write-app-server-schema --experimental --schema-root
/tmp/codex-app-server-schema-experimental`
## Why
Multi-agent v2 currently routes agent instructions through normal tool
arguments and inter-agent context. That means the parent model can emit
plaintext task text, Codex can persist it in history/rollouts, and the
recipient can receive it as ordinary assistant-message JSON.
This changes the v2 path so agent instructions stay encrypted between
model calls: Responses encrypts the `message` argument returned by the
model, Codex forwards only that ciphertext, and Responses decrypts it
internally for the recipient model.
## What changed
- Mark the v2 `message` parameter as encrypted for `spawn_agent`,
`send_message`, and `followup_task`.
- Treat multi-agent v2 tool `message` values as ciphertext
unconditionally.
- Store v2 inter-agent task text in
`InterAgentCommunication.encrypted_content` with empty plaintext
`content`.
- Convert encrypted inter-agent communications into the Responses
`agent_message` input item before sending the child request.
- Preserve `agent_message` items across history, rollout, compaction,
telemetry, and app-server schema paths.
- Leave multi-agent v1 unchanged.
## Message shape
The model still calls the v2 tools with a `message` argument, but that
value is now ciphertext:
```json
{
"name": "spawn_agent",
"arguments": {
"task_name": "worker",
"message": "<ciphertext>"
}
}
```
Codex stores the task as encrypted inter-agent communication:
```json
{
"author": "/root",
"recipient": "/root/worker",
"content": "",
"encrypted_content": "<ciphertext>",
"trigger_turn": true
}
```
When Codex builds the recipient request, it forwards the ciphertext
using the new Responses input item:
```json
{
"type": "agent_message",
"author": "/root",
"recipient": "/root/worker",
"content": [
{
"type": "encrypted_content",
"encrypted_content": "<ciphertext>"
}
]
}
```
Responses decrypts that item internally for the recipient model.
## Context impact
- Parent context no longer carries plaintext v2 agent task instructions
from these tool arguments.
- Codex rollout/history stores ciphertext for v2 agent instructions.
- Recipient requests receive an `agent_message` item instead of
assistant commentary JSON for encrypted task delivery.
- Plaintext completion/status notifications are still plaintext because
they are Codex-generated status messages, not encrypted model tool
arguments.
## Validation
- `just test -p codex-tools`
- `just test -p codex-protocol`
- `just test -p codex-rollout`
- `just test -p codex-rollout-trace`
- `just test -p codex-otel`
- `just write-app-server-schema`
## Summary
Adds a dedicated `codex.sandbox_outcome` telemetry event so we can query
sandbox edge outcomes without threading sandbox metadata through
tool-result output types.
This is meant to make sandbox failures and approved escalation retries
visible in OTEL while keeping the existing `codex.tool_result` event
shape focused on tool completion data.
## What changed
- Adds `SessionTelemetry::sandbox_outcome(...)`, which emits
`codex.sandbox_outcome` as both a log and trace event.
- Records the tool name, call id, sandbox outcome, initial attempt
duration, and escalated attempt duration when a retry runs.
- Emits `denied` when the sandbox blocks execution and no retry is run.
- Emits `timed_out` and `signal` when those sandbox errors surface from
tool execution.
- Emits `escalated` when the initial sandboxed attempt fails and the
approved unsandboxed retry succeeds.
- Adds OTEL coverage for the new event payload, including timing fields.
## Validation
- `RUST_MIN_STACK=8388608 just test -p codex-core
sandbox_outcome_event_records_outcome
handle_sandbox_error_user_approves_retry_records_tool_decision`
- `just test -p codex-otel
otel_export_routing_policy_routes_tool_result_log_and_trace_events
runtime_metrics_summary_collects_tool_api_and_streaming_metrics`
- `just fix -p codex-core`
- `just fix -p codex-otel`
## 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.
## Why
Guardian reviews already emit analytics events, but we do not expose
aggregate OpenTelemetry metrics for review volume, latency, token usage,
or terminal outcomes. That makes it harder to monitor Guardian behavior
during rollouts and to compare review outcomes by source, action type,
session kind, model, and failure mode.
## What Changed
- Added Guardian review metric names for count, total duration, time to
first token, and token usage in `codex-rs/otel`.
- Added `core/src/guardian/metrics.rs` to convert
`GuardianReviewAnalyticsResult` into sanitized metric tags covering
decision, terminal status, failure reason, approval request source,
reviewed action, session kind, risk/outcome, model, reasoning effort,
and context/truncation state.
- Emitted the new metrics from `track_guardian_review` for each terminal
Guardian review result.
## Testing
- Added
`guardian_review_metrics_record_counts_durations_and_token_usage`, which
verifies the emitted count, duration, TTFT, token usage histograms, and
tag set through the in-memory metrics exporter.
## Summary
- drop the dead legacy profile usage metric and active-profile
conversation-start fields
- update role comments so they describe provider and service-tier
preservation without legacy config-profile wording
- pair the code cleanup with the file-backed profile docs update in
openai/developers-website#1476
## Testing
- `just fmt`
- `cargo test -p codex-otel`
- `cargo test -p codex-core` *(fails: existing stack overflow in
`mcp_tool_call::tests::guardian_mode_mcp_denial_returns_rationale_message`)*
- `cargo test -p codex-core --lib
mcp_tool_call::tests::guardian_mode_mcp_denial_returns_rationale_message`
*(fails with the same stack overflow)*
## Summary
- Add `list_available_plugins_to_install` as the inventory step for
plugin and connector install suggestions.
- Slim `request_plugin_install` so it only handles the actual
elicitation, instead of carrying the full discoverable list in its
prompt.
- Emit send-time telemetry when an install elicitation is dispatched,
including requested tool identity in the event payload.
- Emit install-result telemetry through `SessionTelemetry`, including
tool type, user response action, and completion status.
- Update registration and tests to cover the new two-step flow while
keeping the existing `tool_suggest` feature gate unchanged.
## Testing
- `just fmt`
- `cargo test -p codex-tools`
- `cargo test -p codex-core request_plugin_install`
- `cargo test -p codex-core list_available_plugins_to_install`
- `cargo test -p codex-core
install_suggestion_tools_can_be_registered_without_search_tool`
- `cargo test -p codex-otel
manager_records_plugin_install_suggestion_metric`
- `cargo test -p codex-otel
manager_records_plugin_install_elicitation_sent_metric`
- `just fix -p codex-core`
- `just fix -p codex-tools`
- `just fix -p codex-otel`
- `cargo check -p codex-core`
Addresses #22833, #22245, #23067
## Why
`/goal` can keep synthesizing turns even when the next turn cannot make
meaningful progress. Hard usage exhaustion can replay failing turns, and
repeated permission or external-resource blockers can keep burning
tokens while waiting for user or system intervention.
## What changed
- Add resumable `blocked` and `usageLimited` goal states. As with
`paused`, goal continuation stops with these states.
- Move to `usageLimited` after usage-limit failures.
- Allow the built-in `update_goal` tool to set `blocked` only under
explicit repeated-impasse guidance. Updated goal continuation prompt to
specify that agent should use `blocked` only when it has made at least
three attempts to get past an impasse.
Most of the files touched by this PR are because of the small app server
protocol update.
## Validation
I manually reproduced a number of situations where an agent can run into
a true impasse and verified that it properly enters `blocked` state. I
then resumed and verified that it once again entered `blocked` state
several turns later if the impasse still exists.
I also manually reproduced the usage-limit condition by creating a
simulated responses API endpoint that returns 429 errors with the
appropriate error message. Verified that the goal runtime properly moves
the goal into `usageLimited` state and TUI UI updates appropriately.
Verified that `/goal resume` resumes (and immediately goes back into
`ussageLImited` state if appropriate).
## Follow-up PRs
Small changes will be needed to the GUI clients to properly handle the
two new states.
## Summary
- Add optional image detail to user image inputs across core, app-server
v2, thread history/event mapping, and the generated app-server
schemas/types.
- Preserve requested detail when serializing Responses image inputs:
omitted detail stays on the existing `high` default, while explicit
`original` keeps local images on the original-resolution path.
- Support `high`/`original` consistently for tool image outputs,
including MCP `codex/imageDetail`, code-mode image helpers, and
`view_image`.
## Why
Remote compaction v2 was still using `context_compaction` as both the
request trigger and the compacted output shape. The Responses API now
has the landed contract for this flow: Codex sends a dedicated `{
"type": "compaction_trigger" }` input item, and the backend returns the
standard `compaction` output item with encrypted content.
This aligns the v2 path with that wire contract while preserving the
existing local compacted-history post-processing behavior.
## What changed
- Add `ResponseItem::CompactionTrigger` and regenerate the app-server
protocol schema fixtures.
- Send `compaction_trigger` from `remote_compaction_v2` instead of a
payload-less `context_compaction`.
- Collect exactly one backend `compaction` output item, then reuse the
existing compacted-history rebuilding path.
- Treat the trigger item as a transient request marker rather than model
output or persisted rollout/memory content.
## Verification
- `cargo test -p codex-protocol compaction_trigger`
- `cargo test -p codex-core remote_compact_v2`
- `cargo test -p codex-core compact_remote_v2`
- `cargo test -p codex-core
responses_websocket_sends_response_processed_after_remote_compaction_v2`
- `just write-app-server-schema`
- `cargo test -p codex-app-server-protocol schema_fixtures`
## Why
The MCP tool path had accumulated a few core-owned special cases: a
dedicated payload variant, resolver plumbing, a legacy `AfterToolUse`
translation path, and a side channel for parallel-call metadata. That
made `ToolRegistry` and the spec builder know more about MCP than they
needed to.
This change moves MCP-specific execution details back onto `ToolInfo`
and `McpHandler` so `codex-core` can treat MCP calls like normal
function calls while still preserving MCP-specific dispatch and
telemetry behavior where it belongs.
## What changed
- removed `resolve_mcp_tool_info`, `ToolPayload::Mcp`, `ToolKind`, and
the remaining registry-side MCP resolver path
- stored MCP routing metadata directly on `McpHandler` and `ToolInfo`,
including `supports_parallel_tool_calls`
- deleted the legacy `AfterToolUse` consumer in `core`, which removes
the need for handler-specific `after_tool_use_payload` implementations
- switched tool-result telemetry to handler-provided tags and kept
MCP-specific dispatch payload construction inside the handler
- simplified tool spec planning/building by passing `ToolInfo` directly
and dropping the direct/deferred MCP wrapper structs and the
parallel-server side table
## Testing
- `cargo check -p codex-core -p codex-mcp -p codex-otel`
- `cargo test -p codex-core
mcp_parallel_support_uses_exact_payload_server`
- `cargo test -p codex-core
direct_mcp_tools_register_namespaced_handlers`
- `cargo test -p codex-core
search_tool_description_lists_each_mcp_source_once`
- `cargo test -p codex-mcp
list_all_tools_uses_startup_snapshot_while_client_is_pending`
- `just fix -p codex-core -p codex-mcp -p codex-otel`
## 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
- add SQLite init, backfill-gate, and fallback telemetry without
introducing a cross-cutting state-db access wrapper
- install one process-scoped telemetry sink after OTEL startup and let
low-level state/rollout paths emit through it directly
- add process-start metrics for the process owners that initialize
SQLite
---------
Co-authored-by: Owen Lin <owen@openai.com>
