## What changed
- Match final serving assessments to their response and output item, then retain them with tool invocations and code cells across waits.
- Use matching assessments instead of asynchronous scoring for adaptive review: low-risk actions can skip synchronous review, while elevated-risk actions require it.
- Revalidate captured authorization and policy before approval. Require fresh review for stale or incomplete authorization, preserve explicit review requirements, and discard assessments when hooks rewrite tool input.
- Keep asynchronous scoring as the fallback when an assessment is missing or does not match.
## Testing
Add integration coverage for direct and nested tool calls, hook rewrites, explicit escalation, interrupted responses, catalog-driven policy, incomplete authorization, and assessment retention across code-cell yields and waits.
GitOrigin-RevId: 4346a227204137f018c03c34b302d6f1e9592c96
## What changed
Add `ReviewInput` to bundle an approval request with its captured parent history and review context. Its `assess_isolated` method runs a fresh reviewer without publishing a live approval, honors deadlines and cancellation, and returns a `GuardianAssessment` or review error.
Share review parameter construction with the live review path and extract assessment parsing and error conversion into `GuardianReviewSessionOutcome::into_assessment`.
## Testing
Add a mock-backed test that verifies the isolated assessment is returned and the reviewer receives the captured history without instructions added after capture.
GitOrigin-RevId: 10dd5fddf5fc58bfab124f5962a6b7f45d435c83
## What changed
- Separate evidence collection from prompt preparation and pass reviewer history, model limits, and image preparation policy through shared `guardian-context` APIs.
- Detect captured images before composition and measure reviewer history tokens only when images and a valid context window require it.
- Share instruction and native-message delivery filtering across budget checks, including restoration of retained evidence after history changes.
GitOrigin-RevId: 65ef53cf0bc22e1bde9abfb7a9ffce65cfab6f1c
## Why
Guardian's `write_stdin` approval requests lacked the command used to launch the receiving terminal, leaving reviews without that context.
## What changed
- Carry `original_command` from the terminal's launch command into the approval request and Guardian action JSON. This describes the original launch, not the terminal's current state.
- Exclude `original_command` from the 8,000-byte stdin approval size check so launch context does not consume the budget for input, permission details, and the approval reason. Launch context remains subject to Guardian's normal request budget.
## Testing
Extend serialization coverage to check `original_command` and the strict stdin review integration test to verify that a launch command longer than 8,000 bytes reaches Guardian intact.
GitOrigin-RevId: cc765a6bf80d080baf94c959eafa6227b2889e1f
## What changed
Extract MCP approval elicitation parsing and review-decision response conversion from `core/src/session/mcp.rs` into `codex-guardian-reviewer`. Export the helpers and `GuardianElicitationReview` for the session code to use, while keeping session lookup, provenance checks, and approval enforcement in the host.
## Testing
Move the existing elicitation tests into the reviewer crate, retaining coverage for request construction, opt-in requirements, unsupported forms, decision mapping, and model-specific timeout instructions.
GitOrigin-RevId: fb745fa0e49a29f015bbda16c14b5fc2b12278b9
## What changed
Export `ReviewAction` and its conversion from `GuardianApprovalRequest` from
`codex-guardian-reviewer`. Keep host-specific approval preparation and environment
validation in core as standalone functions, and update callers accordingly.
## Testing
Move the `write_stdin` serialization and tool-call provenance test into the
reviewer crate, preserving coverage for input, Windows working directories, and
sandbox permission modes.
GitOrigin-RevId: 9a1caf9bbb67ba017e4950a2da9ef2543b013007
## What changed
Move review evidence storage, authorization snapshots, sender exchange selection,
and bounded Node REPL evidence into `codex-guardian-reviewer`. Update core to
call or re-export these APIs while retaining host-specific context rendering and
capture-mode selection.
Move the existing Node REPL evidence and text truncation tests alongside their
implementations in the reviewer crate.
GitOrigin-RevId: d851cd353cf9f31eb47ce13f43f6f935dc2f5d93
## What changed
Move `GuardianContextMode`, parent compaction checkpoint policy, and reviewer instruction assembly into `codex-guardian-reviewer`. Export the conversation-history prompt and follow-up reminder from the same crate, and update core to use these shared definitions.
Keep session-specific authorization version lookup in core while preserving existing context selection, checkpoint validation, and prompt behavior.
GitOrigin-RevId: a4cadb6c8ad95e756467316b7d8658e8cd527b24
## What changed
Move review state, fork history, checkpoint recovery bookkeeping, and Node REPL evidence admission into `codex-guardian-reviewer`. Expose helpers for session initialization and snapshot publication, and update core to delegate to them while preserving the existing review logic.
GitOrigin-RevId: 56d6a0124301a3c70908614d4bc3bfe970ac1c85
## What changed
Add `ReviewerPool::review_isolated` to run a review in a temporary session without reading or changing the reusable reviewer. Build the request context without a previous session and spawn without a cached snapshot.
## Testing
Add a test verifying that an isolated review receives no snapshot, uses a separate session, and preserves the prewarmed session for the next regular review.
GitOrigin-RevId: 6cceff0c399f30f3c3303b0bf5232c274c902e3a
## What changed
Keep original scheduled messages and heartbeat provenance during synchronous transcript collection. Add `prepare_sync_context` to compress repeated heartbeat instructions across the complete collected transcript before selecting the requested suffix, preserving reference numbering in full and delta prompts.
Route synchronous reviewer prompts through this preparation step and reject composition of unprepared scheduled messages. Move transcript profiles and REPL evidence rendering into the preparation module. Asynchronous heartbeat compression remains in collection.
## Testing
Extend heartbeat transcript coverage to compare prepared full and delta prompts with the existing rendering and verify that direct composition rejects unprepared scheduled messages.
GitOrigin-RevId: c9824b8862021301a1f537a74f83bc7eb20aa0ad
## What changed
Move planned-action construction from the core Guardian prompt builder into the exported `codex_guardian_reviewer::build_guardian_planned_action` helper. Keep the existing action kinds, MCP tool and connector descriptions, and reason selection unchanged.
GitOrigin-RevId: 119323523ed2e199c998c1139fb8e6255bc730d9
## What changed
Move approval-request assessment and analytics mappings, target item lookup, and turn ID selection into `codex-guardian-reviewer`. Export the helpers from the crate and re-export them in core, preserving existing behavior.
## Testing
Move the apply-patch serialization test into the reviewer crate. It checks that Windows paths are preserved and patch text is omitted from the assessment action.
GitOrigin-RevId: 3a011db0bc51c653bb0877c4b0cb52eb61c63244
## What changed
Move approval request serialization and model-visible action formatting from `codex-core` into `codex-guardian-reviewer`, expose both helpers publicly, and re-export them from core. Preserve the existing JSON shapes and formatting.
## Testing
Move the MCP tool-call and network-access trigger serialization tests into the reviewer crate, retaining coverage for omitted optional fields and Windows path rendering.
GitOrigin-RevId: c0093c023b2f4c1be16bac481f1173a5da6ac25c
## What changed
Export `GuardianPromptItems` and `compose_guardian_prompt` from `codex-guardian-reviewer`, and delegate prompt composition from core to the new helper. Core continues to collect context sections and choose the history version.
Preserve full and delta transcript selection, empty-transcript placeholders, cursor accounting, and Node REPL evidence sequencing.
GitOrigin-RevId: e3e2b2a87a42709ddb5441f47cbb7461b0130579
## What changed
Export `GuardianApprovalRequest`, `GuardianNetworkAccessTrigger`, and
`GuardianMcpAnnotations` from `codex-guardian-reviewer` and re-export them in
core. Move environment lookup and scope classification with the request type,
preserving existing classification and credential-safe debug output.
GitOrigin-RevId: 5253a5124d5e370a1230b46aa7dc48b24b1c902e
## What changed
Move Guardian session-source detection, the reviewer name constant, and parent-thread prompt cache key generation into `codex-guardian-reviewer`. Re-export them from core, preserving existing behavior.
## Testing
Move the existing prompt cache key test into the reviewer crate, retaining coverage for parent-thread scoping, key length, and missing or inapplicable inputs.
GitOrigin-RevId: c14b3c030ba93676a0799aba56b23a676dbbc56d
## What changed
Export `token_usage_delta` from `codex-guardian-reviewer` and use it in the core review session. Preserve the existing calculation, including clamping negative deltas to zero.
## Testing
Move the existing nonnegative token usage delta test alongside the helper in the reviewer crate.
GitOrigin-RevId: fcfce24b8d50a63dcd1122a4204939bc6750feda
## What changed
- Recognize `policy_capacity_unavailable` in HTTP and streaming API errors and expose it as `policyCapacityUnavailable` through the app-server protocol and generated bindings.
- Display “Policy-restricted capacity is unavailable. Please try again later.” while preserving overload retry behavior based on `Retry-After`.
- Handle the new error in TUI overload rendering, reviewer retries, and error telemetry.
## Testing
Add coverage for HTTP and streaming error classification, retry advice, WebSocket terminal error attribution, protocol serialization, and TUI rendering with and without an upstream message.
GitOrigin-RevId: 1b9536fba1e11cc891dcf689aee35410d82f5412
## What changed
- Add `CoreToolRuntime::requires_guardian_review` to review opted-in function calls before dispatch and stop execution when review rejects the call.
- Deliver proposed calls as native review evidence, preserving encrypted argument metadata. When hooks rewrite arguments, review the updated arguments and discard the original encrypted replay content.
- Deduplicate native call evidence against reviewer history and include paired evidence outputs in input budgets.
- Keep review accounting and metrics for native calls without emitting action-specific client assessment events, and omit approval payloads from debug output.
## Testing
Extend regression coverage for rewritten native calls across review retries, denied calls that never execute their handlers, oversized native evidence, and review metrics without client events.
GitOrigin-RevId: c3b22c0220344581c2b38f233001abaed49cba34
## Why
Provider errors with code `model_not_found` should end the turn immediately and preserve the provider's message instead of triggering retries.
## What changed
- Recognize `model_not_found` in HTTP 400, 403, and 404 responses and in streamed `error` and `response.failed` events.
- Preserve the provider message and any available HTTP status, and expose `modelNotFound` through the app-server protocol and generated schemas and SDK types.
## Testing
Add coverage for HTTP classification, statusless stream errors, and terminal failures without retries across HTTP, SSE, and WebSocket responses. Verify that `thread/read` preserves the error reported by the live notification.
GitOrigin-RevId: 88f824ac03c8c9669915b1e40c67b76c08326fbe
## What changed
Add `auto_review.timeout_ms` to configure the overall Guardian review budget, including setup and retries. Keep the default at 90,000 milliseconds; setting it to `0` disables the review deadline while preserving cancellation, retry attempt limits, and independent transport timeouts.
Carry the configured deadline through review execution and report the configured budget in review telemetry, using zero for unlimited reviews.
## Testing
Add coverage for shared setup budgets, configured timeouts, cancellation with unlimited reviews, and retry attempt limits without a deadline.
GitOrigin-RevId: 00404e0cb2f2cfaf6de183d6e27f5e4a371942a8
## Why
Guardian review metrics derived duration from wall-clock timestamps, while analytics measured elapsed time when tracking the result. Clock changes and delayed tracking could produce inconsistent latencies.
## What changed
Capture one monotonic duration at review completion and pass it to both metrics and analytics. Preserve wall-clock timestamps for event ordering, and saturate analytics latency conversion at `u64::MAX`.
## Testing
Add a regression test covering skewed wall-clock timestamps and delayed tracking, verifying that the duration metric uses the captured interval and completion timestamps are preserved.
GitOrigin-RevId: 19eafb8e1f1a3d13a751bdc72c218e4cafeae410
## What changed
Record `codex.guardian.turn.blocking_ms` when a turn completes or aborts, with an `outcome` label. Count overlapping approval waits once, exclude idle gaps, and split pending reviews across the active turns they span. Use each turn's telemetry so samples retain the servicing turn's model attribution.
## Testing
Add unit coverage for overlapping waits, idle gaps, late turn completion, and duplicate stops. Extend integration coverage to verify attribution across turns and model changes for yielded command reviews and MCP elicitation, including aborted turns.
GitOrigin-RevId: a3e6a0c32a06fe58ea93119ecd941076100fb82c
## Why
Cancelled or timed-out Guardian reviews can admit transcript evidence without completing a review. Reusing that session can leave subsequent reviews without the evidence they need.
## What changed
Mark interrupted reviews for rollback to the last completed review instead of reusing their live context. Preserve committed review history and replay pending evidence on the next review.
## Testing
Add cancellation and timeout regression coverage that verifies encrypted evidence appears exactly once in the next review, the last completed review survives rollback, and interrupted or denied commands do not execute. Update session disposition assertions and make the program-change session reuse test wait for review completion before releasing the classifier result.
GitOrigin-RevId: f39552b24db5309cffddd9eda97280256be3e97b
## What changed
- Record review attempt counts and final outcomes with a `retried` tag.
- Measure retry waits by failure reason and whether the wait ends in a retry, cancellation, or deadline; count retries only when another attempt will run.
- Count required synchronous reviews with the `required_sync` route.
- Use the originating turn's telemetry for Guardian reviews so metrics retain that turn's model attribution.
## Testing
Add metric assertions for attempt counts, retry outcomes, and waits interrupted by cancellation or deadlines. Extend the delayed cached-score integration test to verify route and retry-wait metrics use the originating turn's model after a model override.
GitOrigin-RevId: 681a719ad5dd9e4436cb37b6f5f972cb11a5c890
## What changed
- Add `ComposedContext::retain_new_images` and use it in Guardian review sessions and the async scorer. Compare host-prepared image references against admitted history, ignoring image detail, and skip scanning history when no images need checking.
- Restore `ConversationState` directly from a checkpoint, retaining committed history for rollback or transferring it with `take_history` for ephemeral forks.
## Testing
Extend tests for prepared-image matching across differing detail levels, image-free continuations that avoid scanning history, and checkpoint restoration and history transfer.
GitOrigin-RevId: bafeb6de9babc721182be43d0eb1a653955a0ebb
## Why
A failed Guardian inference can retain its input in a reusable session. Tracking transcript progress only after successful reviews can admit the same evidence again on retry.
## What changed
Advance transcript progress when a failed turn has retained its input and the session remains reusable, without counting it as a completed review or changing the committed fork checkpoint. Leave progress unchanged when failure occurs before input admission.
## Testing
Extend regression coverage for encrypted agent messages across review retries, pending evidence after compaction failures, and fork checkpoints after transcript admission without a completed review.
GitOrigin-RevId: 36239ec9d47f484bcfe68d65e7c8d8ab8660db0d
## What changed
- Preserve approval resolution sources through tool errors and tag cancelled MCP approvals with `error_type=approval`, `error_code=cancelled`, and `approval_source` (`guardian`, `user`, `hook`, or `unknown`). The source identifies the reviewer, not who caused cancellation.
- Record `context_changed` when validating a Guardian allow against changed authorization or review context, even when a concurrent stop or history reset determines the outcome. Retain the flag across retries and fresh-checkpoint recovery, and include it in the Guardian review counter.
GitOrigin-RevId: a19a986a7565f9a78a9bb2eaabdb5651834d28b8
## Why
An asynchronous approval currently waits for the redundant synchronous review to finish cancellation cleanup before returning a decision.
## What changed
Cancel the redundant review and let it drain under the parent's `ReviewerTasks` tracker so a current approval can return immediately. Revalidate the approval and check cancellation before approving the action. Hosts without a task tracker continue to wait for cleanup.
Keep the reviewer reservation held until cleanup completes, and let shutdown join the tracked attempt. Discard late results and evidence from the cancelled review.
## Testing
Add tests covering current, invalidated, and cancelled approvals while cleanup is blocked, suppression of late evidence, reviewer reservations during cleanup, and shutdown waiting for abandoned attempts.
GitOrigin-RevId: f227738e545243f99c19a6c557a78d330f9d2767
## Why
Stale authorization requires refreshing local evidence, so service retry backoff unnecessarily delays the next review attempt.
## What changed
Yield cooperatively before retrying `StaleAuthorization`, then check cancellation and the shared deadline. Keep retries within the existing attempt budget.
## Testing
Extend paused-time tests to cover recovery with fresh evidence and exhaustion of the shared attempt budget, asserting that retries incur no backoff and return the final attempt's evidence.
GitOrigin-RevId: fda7ddd040a761d08883740bb5e7aaecacfa6091
## What changed
Pass the parent turn's `cyber_access_program` to Guardian reviewers and asynchronous classifiers. Use `daybreak_blue` for either Daybreak selection, preserve `standard`, and omit `access_programs` when no program is selected.
Capture the selection with the owning turn so asynchronous observations retain it across later turns. Resolve classifier programs using current authentication and the same provider and API-key feature policy as ordinary model requests.
## Testing
Add regression tests for program changes across reused reviewer sessions with API-key and ChatGPT authentication, snapshot and conversation classifiers at low and high risk, and enabled, disabled, and unsupported-provider API-key policies. Verify parent requests retain their selected program.
GitOrigin-RevId: 447f306df3a6bd6805464b819950690c751b04b4
## What changed
- Add debug spans with review, thread, turn, and tool-call identifiers to correlate approval reviews and background scoring.
- Log review retry scheduling with failure details, attempt limits, backoff, and remaining deadline budget.
- Emit warnings for Guardian V2 background scoring failures with the failure reason, context mode, and duration, even when metrics are unavailable.
GitOrigin-RevId: 3e20d16836576f834998af473815bfb55e671de5
All callers already check that an assessment payload is present before parsing it. Change `parse_guardian_assessment` to accept `&str` instead of `Option<&str>` and remove its redundant missing-payload check.
Update the callers and existing parser tests to pass text directly.
GitOrigin-RevId: e4fb4bf7aca5b20f25f5b27300ce9a6f22c97939
## Why
Authorization updates during a pending Guardian approval can invalidate its decision. Retries need the updated guidance without inheriting the invalidated review or losing earlier valid context.
## What changed
- Validate authorization while the reviewer is reserved, before publishing its history checkpoint.
- Roll back stale attempts to the last committed review, preserving earlier valid reviews across repeated invalidations.
- Pin the issuing action's repository instruction snapshot for reviewers and retries, avoiding fresh instruction discovery through disconnected executors.
- Treat stale authorization as a request for a new review rather than a failed decision.
## Testing
Add regression coverage for repeated approval invalidation, retention of earlier valid context, exclusion of stale decisions, and execution of the pending action exactly once. Extend the disconnected-executor test to verify that retries retain repository instructions and use updated authorization.
GitOrigin-RevId: 0bff6cc551fee1f0905082eb97ccdecaa8628867
## Why
Failed Guardian review evidence was process-local, so restarting Codex lost the context needed for later diagnostic reports.
## What changed
- Persist failed-review records in SQLite before reviewer cleanup, retaining at most 64 records globally, eight per thread, and 8 MiB of evidence. Delete persisted evidence when its reviewed thread is deleted.
- Recover and deduplicate persisted and in-memory records for the reported task tree when uploading `auto-review-failures.jsonl`.
- Bound persistence attempts to 250 ms and retain an in-memory fallback when storage is unavailable. Keep capture gated by user opt-in and non-ephemeral sessions, and export evidence only when logs are included.
## Testing
Add coverage for persistence across reopen and process restart, retention limits, cascading deletion, busy-storage fallback, and report uploads with and without logs, including SQLite log failures.
GitOrigin-RevId: ea2da1818d4a5da3da29f211042ca45e834342bc
## What changed
Add `TurnEnvironmentRequests` to carry environment requests together with their fallback working directory. Update thread settings overrides and active turn settings to accept requests, constructing `TurnEnvironmentSelection` values in the receiving thread before validation and runtime use.
Adapt app-server callers, reviewer settings, and existing tests to supply requests or explicitly convert runtime selections back into requests.
GitOrigin-RevId: 8028f804bebe3fde553f57bb450f6dca3970cc4a
## Why
Clients starting delegated work need to attribute descendant turns to the original turn and retain that attribution through completion and history reads.
## What changed
- Accept optional `parentTurnId` and `rootTurnId` in `turn/start`, and expose `rootTurnId` on returned turns and lifecycle notifications.
- Default new turns to their own root when none is supplied. Preserve the active turn's root when steering, ignoring incoming lineage fields.
- Carry root IDs through completion, interruption, recovery, and fork boundaries, and persist them for paginated history reads. Leave unknown roots null in older history.
- Update protocol schemas and generated TypeScript and Python bindings.
## Testing
Extend coverage for default and explicit roots, steering without changing lineage, interrupted and recovered turns, history reads after restart in both history modes, nested fork pagination, and compatibility with older database writers.
GitOrigin-RevId: f1a570a12bd11742929fd2e8b017e5d35aa07dcb
## Why
A synchronous Guardian review could keep an action waiting even after an asynchronous score supplied valid low-risk evidence for approval.
## What changed
- In adaptive mode, race the synchronous review against score updates that satisfy the existing cached-approval checks, unless a fresh review is required.
- When asynchronous approval wins, cancel and drain the pending review, then revalidate the action and history lifetime and enforce cancellation and timeout limits before approving.
- Emit an approved review completion without a synchronous assessment or risk level, and use the cached-approval path for the final decision.
## Testing
Add an app-server regression case that holds the synchronous review pending, releases a low-risk score, and verifies approval completes without a risk level. Sequence existing scenarios to finish synchronous reviews before releasing classification results when they test synchronous evidence.
GitOrigin-RevId: 04f5ad6b960b819b565fccb1b85c8039ccbd0479
## What changed
Increment `codex.guardian.denial_limit_reached` when automatic approval review reaches a turn's denial limit, immediately before interrupting the turn. Record the counter once per turn, matching the denial warning's existing behavior.
GitOrigin-RevId: ec8eeeff6a681a261572496e59cf694e87e813ce
## What changed
Add `codex.guardian.decision.duration_ms` around the complete approval decision operation, including fast decisions, preparation, and cancellation alongside model review time.
GitOrigin-RevId: e5a8d5a3b9a0ff81e1b866be87b8f3a439ae6a1d
## Why
A Guardian review restarting from the parent checkpoint must bypass cached reviewer sessions and snapshots, even when another review is using the cached session.
## What changed
- Add `ReviewerRequest::requires_fresh_session` and enable it for parent-checkpoint recovery.
- Replace an idle cached session with a fresh reusable session, or start a fresh ephemeral session when the cached session is busy. Neither recovery path inherits a cached snapshot.
- Reserve the review permit before validating a cached session and before exposing a newly spawned session to concurrent requests.
## Testing
Add tests covering recovery with idle and busy cached sessions, verifying that recovery receives no cached snapshot and that subsequent reviews reuse the appropriate session.
GitOrigin-RevId: 894f685736da54312336932aa2037e74a20629d9
## What changed
- Add request preparation that preserves committed classifier history and appends transcript deltas, filtering instructions and images already delivered. Account for the complete input budget before transferring history; rejected requests leave the checkpoint and cursor intact.
- Add retained sampling that publishes the early score while collecting completed assistant output and encrypted reasoning for reuse. Preserve item IDs and input metadata, and discard unusable history without retracting an already published score.
- Keep the existing snapshot sampling path and share input preparation and execution with the new retained path. Retained sampling is not yet wired into the active backend.
## Testing
Add coverage for transcript and image deduplication, immutable history prefixes, budget boundaries, rejected preparation, WebSocket output retention, and retention failures that preserve the early score.
GitOrigin-RevId: 0fa33db8b8ea4483eb64d75e207690f1d349123b
## Why
Guardian review and classification telemetry lacks the context mode needed to distinguish `legacy`, `independent`, and `thread_owned` reviews.
## What changed
- Add `guardian_context_mode` to review and classification analytics and `context_mode` to their metrics.
- Capture the mode from the conversation history snapshot before review preparation or classification setup so failure metrics retain it, including when review preparation or reviewer startup fails.
- Use `unknown` for review metric tags when no context mode is available.
## Testing
Update metric assertions to cover `thread_owned` classification tags and the `unknown` review fallback.
GitOrigin-RevId: 79f7d11b3e4ccfc53681890d75fbc7c54e1ce7de
## Why
Guardian denial-limit interruptions lack a structured error identifying the cause. Make this opt-in because older clients may not recognize the new error in shared history.
## What changed
- Add `auto_review.circuit_break_action = "strict"` to attach `TooManyDenials` to the interrupted turn. The default leaves the error unset.
- Expose `turn.error.codexErrorInfo = "tooManyDenials"` in app-server notifications and saved history, and update protocol schemas and generated types.
- Preserve the warning, denial limit, and interrupted status without emitting a separate error notification.
## Testing
Add an integration test covering omitted, `default`, and `strict` settings, checking warnings, live turn errors, the absence of separate error notifications, and persisted turn errors after restart.
GitOrigin-RevId: cb5d379e64728d4d7b9daf834c13756e4a70db31
## Why
Reused Guardian sessions already contain previously delivered instructions. Follow-up reviews can avoid repeating that evidence, but must deliver it again if it changes or compaction removes it.
## What changed
- Track retained source identity, revision, and completeness in host-owned history metadata, preserving revisions during replay.
- Omit retained instructions from synchronous review inputs only when the same complete revision remains in reviewer history.
- Restore missing evidence after reviewer compaction, enforcing the request budget before persisting additions. Classify restored evidence as context rather than new user authorization.
- Keep source-order labels stable across eviction and retain full delivery for legacy records without reliable provenance.
## Testing
Add coverage for consecutive-review deduplication, changed revisions, missing or incomplete metadata, and restoring compacted evidence exactly once. Extend compaction and resume coverage to verify retained revisions.
GitOrigin-RevId: e90fca16cde0a0970da36dd873af2ca1dbaaf4d3
## What changed
- Recognize `flex_unavailable` in HTTP 429 responses and streamed `error` and `response.failed` events. End normal turns without retries and report `Flex capacity unavailable.`
- Expose `flexUnavailable` through the core and app-server protocols and generated schemas and SDK types.
- Keep Flex capacity failures eligible for Guardian review and sampler retries, with a distinct telemetry classification.
- Map unexpected HTTP responses to `HttpConnectionFailed`, preserving their status codes.
## Testing
Add regression coverage for terminal Flex failures over HTTP, SSE, and WebSocket, HTTP 504 status preservation after a stream retry, and protocol serialization. Update Guardian retry and sampler recovery tests to cover Flex failures.
GitOrigin-RevId: f2e03a6d2d36a6d9748c35952e40397f8670d121
## What changed
Add `otel.log_guardian_assessments`, disabled by default and requiring an OTLP HTTP or gRPC log exporter. Emit `codex.guardian_assessment` when a synchronous Guardian review finishes, including review identifiers, status, risk level, user authorization, and rationale. Include `allow` or `deny` outcomes only for completed model assessments, not review errors, timeouts, or cancellations.
Cap exported rationales at 64 KiB on a UTF-8 character boundary and record their original byte length and truncation status. Use the log-only route to exclude assessment payloads from trace export, local state logs, and bug-report log buffers. Cached V2 approvals are not included.
## Testing
Add coverage for configuration gating, enabled and disabled denial logging, terminal statuses and outcomes, UTF-8 rationale truncation, export routing, and bug-report log buffer exclusion.
GitOrigin-RevId: dcbb5b429c8726a5a5c80ff82f9d625e81796ede
## Why
Asynchronous Guardian scoring omitted the target environment's denied-read restrictions, and cached score authorization did not include that permission context. A score from one environment could therefore be reused for an action in another environment with different restrictions.
## What changed
- Share permission resolution between synchronous review and asynchronous scoring, including resolving `write_stdin` targets from the owning terminal session.
- Include environment identity and denied-read paths/globs in async scoring context and cached score authorization.
- Fall back to synchronous review when permission evidence cannot be resolved or exceeds the async limit of 3,000 bytes, rather than omitting restrictions.
## Testing
Add regression coverage for rejecting cached scores with different environments or denied paths, passing the target environment's restrictions to the classifier, and rejecting oversized async permission evidence.
GitOrigin-RevId: 14b6f3454bbea458be037560eb1da47d22874df1
## Why
New user input during a Guardian review invalidated an in-flight approval and aborted the pending action, even when the input was only a status inquiry. Review the action again against the latest authorization evidence so it can proceed or be denied based on the updated instructions.
## What changed
- Treat stale authorization as a retryable review error within the existing attempt budget and shared deadline.
- Refresh authorization evidence for each attempt while keeping the pending action fixed, and record evidence from the completed attempt.
- Preserve cancellation and history-reset aborts, and deny approval if stale authorization exhausts the retry budget.
## Testing
Add and update coverage for parent status updates, authorization revocation, repeated updates, cancellation, history resets, and retry deadlines. Verify that refreshed reviews see the latest input and that the pending action executes exactly once only after approval.
GitOrigin-RevId: c683e2efb6f07840b99d0d34acf0d38c9ddfe9bd
jif