## Why
Guardian transcripts omitted encrypted agent messages, leaving reviews without evidence such as encrypted parent replies.
## What changed
- Carry encrypted `agent_message` items through synchronous reviews and asynchronous scoring, preserving their order, author, recipient, and ciphertext.
- Account for native messages in context budgets and omit them whole with an explicit notice when limits require it.
- Support mixed text and native messages during review admission while retaining user-content annotations.
## Testing
Add coverage for transcript ordering and budget eviction in both reviewer profiles, plus a mocked scenario verifying that an encrypted parent reply appears exactly once in each of two incremental Guardian reviews.
GitOrigin-RevId: abc2f1ce5accd83beb06f799ef9ed9d7fa2cd90a
## Why
The transcript supplied to Guardian may omit earlier user instructions, restrictions, or revoked permissions. History retrieval lets the reviewer check relevant authorization before approving actions with side effects.
## What changed
- Add the disabled-by-default `guardian_conversation_history_tools` feature. With Apps enabled, expose `user_message.search_messages` and `user_message.read_messages` through the parent's live Apps connection and conversation identity.
- Recheck the parent's current app and tool policy on each call, rejecting disabled tools and calls requiring approval.
- Add retrieval instructions that distinguish user authorization from assistant context and account for later revocations and incomplete results. Allow overrides through `auto_review.experimental_conversation_history_prompt`.
- Limit history responses to an estimated 4,000 tokens by default, configurable through `auto_review.conversation_history_max_output_tokens`, while preserving stricter parent and reviewer limits.
- Allow explicit extension registries for isolated sessions and prevent those sessions from inheriting the implicit Apps connection.
## Testing
Add scenarios covering history tool exposure, parent connection and identity reuse, custom prompts, output truncation, stricter reviewer budgets, and live permission changes on a reused reviewer. Extend configuration coverage for blank prompt overrides.
GitOrigin-RevId: 055a69b113c8548bd58e7d5618ea026ba6d1ffb1
## Why
Message-board notifications delivered as ordinary injected input could cause an agent to sample again after its final answer.
## What changed
Route notifications through the current turn's mailbox as `InterAgentCommunication`, checking atomically that the turn is running and still accepts mailbox delivery. Skip notifications when delivery is closed. Accepted notifications may remain in conversation history for a later turn without reopening the finalized answer or starting a new turn.
Report pending inter-agent communications as mailbox activity, while preserving priority for steering input.
## Testing
Add regression scenarios for notifications arriving before and after finalization, asserting no extra sampling and the expected notification presence in the next turn. Extend input-queue coverage to recognize already-pending mailbox activity.
GitOrigin-RevId: 41d786041b4eccc5ccf926f2f190473676a3ac2f
## What changed
- Give tool fragment sizes and namespace counts logarithmic boundaries through 32,768.
- Give enabled and kept skill counts integer boundaries from 0 through 512, removed description characters logarithmic boundaries through 131,072, and skill truncation flags boundaries at 0 and 1.
- Record these metrics with explicit boundaries, separating zero values and retaining overflow buckets above each range.
## Testing
Extend tool and skill metric tests to assert explicit boundaries. Add an export test covering zero, one, the upper boundary, and overflow, including bucket counts, ordering, and sample totals.
GitOrigin-RevId: 9fbf3acbe352d7c74f3ad11f0b690148c083a6ef
## 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
Guardian reviews need to retain original evidence across parent compaction when checkpoint reuse is disabled, including after resume and rollback.
## What changed
- Make disabling `guardian_reuse_parent_compaction` select a bounded, independent review transcript while preserving thread-owned authorization.
- Keep synchronous reviews and asynchronous scoring independent of parent checkpoints, and allow reviewer sessions to continue using transcript deltas across parent compaction.
- Persist transcript entries with rollback provenance while remaining compatible with older checkpoint readers and metadata-free checkpoints.
- Exclude compaction output from the transcript and synthetic summaries from rollback turn boundaries. Use acceptance ordering to remove rolled-back evidence even when persistence order differs.
## Testing
Add regression coverage for reviewer continuity, evidence retention across compaction and resume, rollback after local and remote compaction, and checkpoint serialization compatibility.
GitOrigin-RevId: fea0852cc5537372854f4a34bacb6bfda6d13e88
## Why
Guardian needs the assistant's delivered question to interpret a user's reply. Messages sent through nested Code Mode tools must remain available as review context, and approvals based on earlier context must become stale when a new delivery is confirmed. Assistant messages do not themselves grant authorization.
## What changed
- Capture successful hosted User Messaging sends after input rewriting and before result callbacks or post-tool hooks.
- Retain bounded delivery text in acceptance order, persist it through cancellation and shutdown, and preserve it across compaction and resume with an older-client-compatible rollout encoding.
- Track assistant review context separately from user authorization, invalidating pending and cached approvals for both local and worker reviews when that context changes.
- Associate retained deliveries with the correct instruction or communication boundary during rollback.
## Testing
Add coverage for nested messaging review context, fast replies and communication ordering, shutdown persistence, stale local and worker approvals, rollout compatibility, and rollback retention.
GitOrigin-RevId: 1bc1ec9e8947560b99f4b39a42ddb9f2099f519b
## Why
Changes in executor availability can alter cloud skill catalog rendering under a shared budget and repeat an unchanged executor catalog when it reconnects.
## What changed
- Cap cloud skills at three quarters of the metadata budget initially, leaving the remaining budget and unused cloud allowance for filesystem skills. Reduce the cloud cap only when doing so allows all skill entries to fit; description truncation alone does not trigger rebalancing.
- Persist the allocation across disconnects, compaction, and thread resume. Recompute it when the cloud inventory or total budget changes.
- Emit a short availability update when an unchanged selected-environment catalog returns and its full text remains in history. Reinject the full catalog when that text is missing.
## Testing
Add coverage for allocation stability, catalog and budget changes, omission handling, and full catalog reinjection after compaction and resume. Extend the selected capability stack test to verify reconnection avoids repeating the catalog.
GitOrigin-RevId: 839fe98024e00c4082a46e6a40675e15fd2c16c6
## Why
Complete assistant messages with empty text can produce misleading omitted-context notices in Guardian reviews.
## What changed
- Skip complete, empty assistant messages when recording and rendering retained context, while preserving omission notices for incomplete messages.
- Separate retained instruction fragments with blank lines and keep blank lines free of role prefixes, while labeling every nonempty line with its original role.
- Update source-order guidance detection and empty-section deduplication for the added spacing.
## Testing
Extend retained-context tests to cover empty completed messages across resume, restored empty messages, incomplete-message notices, blank-line spacing, and role labeling. Update Guardian prompt snapshots.
GitOrigin-RevId: e945717b18689fa4538d9b617b89a644858ab1c8
## Why
Cached executor MCP declarations must not gain access to host environment credentials when reconnecting to an executor that lacks environment credential resolution.
## What changed
- Retain credential policy through MCP registration, catalog materialization, and runtime setup. Derive selected HTTP plugin policy from the plugin's source environment.
- Reject host bearer-token fallback and transports requiring host environment headers or helpers for executor-owned declarations. Preserve host-configured credential resolution.
- Include credential policy in connection and tool catalog cache identities, and avoid reading host environment values for executor-only identities.
## Testing
Add regression coverage for legacy executors, cached declarations after a capability downgrade, policy preservation through catalog rebuilds, and connection and tool cache isolation.
GitOrigin-RevId: 2d5b85e4e98668c637c538cbe528914c936bd831
## Why
Async Guardian requests include retained user instructions even when complete copies are already present in the same request's transcript.
## What changed
- Include retained source metadata and order labels in async user transcript entries.
- Omit retained instructions when the current transcript contains the same complete source revision. Keep ordering guidance in every async sample and never rely on previous samples for deduplication.
- Preserve retained originals when transcript copies are incomplete or lack source metadata.
## Testing
Extend retained-instruction tests to cover async deduplication, preservation of originals without complete source proof, and budget protection. Update async scorer expectations for source order labels and deduplicated instructions.
GitOrigin-RevId: 7029731b296d2342eea4ad74ffa9d3447578d83e
## Why
Synchronous Guardian reviews can include the same user instruction in both the retained instructions section and the conversation transcript. Avoid this duplication while preserving complete authorization evidence and its original acceptance order.
## What changed
- Carry retained source metadata into transcript rendering. Omit a retained instruction when the transcript delivers its complete matching source revision.
- Label qualifying transcript entries with retained source order and protect them from budget truncation. Keep separate retained instructions when source metadata is missing or incomplete.
- Track delivery of source-order guidance so it remains available even when all retained instructions are delivered through the transcript. Invalidate that delivery proof when messages are shortened.
## Testing
Add coverage for complete-source deduplication, missing or incomplete metadata, budget protection, guidance redelivery, and source metadata preservation across resume. Update Guardian review assertions and snapshots to verify instructions are delivered once.
GitOrigin-RevId: 20ad0304501fa49f1596c4cfaf3ef89d64815753
Derive `Serialize` and `Deserialize` for `CreateChannelRequest`,
`ReadPostRequest`, and `SubscriptionRequest`.
GitOrigin-RevId: 7da638c029f7d57b59e865a3a45ae80924780fba
## What changed
Return post metadata from the in-memory message board after updating board state when no notification recipients remain. This avoids constructing an unused notification preview, including when the author is the only requested recipient.
## Testing
Run the existing post-and-search model-context scenario against both disk and in-memory message boards, checking that post metadata and search results reach the model without self-notifications.
GitOrigin-RevId: dcf07a5fd55738fbcd6edd3dce3f6fb8fc910eaf
## 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
## Why
Editing recent conversation images failed when the selected images included a file reference from a message or tool output.
## What changed
Use `ImageReference` in `ImageEditRequest` to accept both `image_url` and `file_id` inputs. Pass file references from conversation history through to image edit requests while preserving image selection order.
## Testing
Update tests to cover file references from messages and tool outputs, and serialization of mixed inline and file references in image edit requests.
GitOrigin-RevId: 2764bf36a81a62ddd25cf9df27346a434a10c449
## Why
Dropping the last board handle releases its state but leaves a stale entry in
`InMemoryMessageBoards`, allowing registry entries to accumulate across sessions.
## What changed
Prune entries whose state has no remaining strong references whenever a board is
opened, while preserving shared state for live boards.
## Testing
Add a regression test that repeatedly opens and drops boards, checks that expired
entries are removed, and verifies that reopening a live board shares its state.
GitOrigin-RevId: c3f1c27b42ee17915f0ece01b85a22d0fdf632ce
## Why
Ephemeral sessions cannot use the SQLite-backed agent message board. An in-memory backend lets agents share discussions without creating durable board storage.
## What changed
- Add the opt-in `message_board_in_memory` setting to the multi-agent v2 configuration, allowing the board to run in ephemeral sessions when both required features are enabled.
- Share board state across agents in the same tree and release it when the last handle is dropped.
- Implement channels, posts, subscriptions, notifications, search, and paginated reads through the existing `AgentMessageBoard` interface, including request deduplication.
## Testing
Add coverage for shared handles, concurrent request deduplication, tree isolation, and state release. Run existing query and tool test cases against both backends, and extend the parent/child scenario to verify ephemeral board sharing without creating a board database.
GitOrigin-RevId: d0b2083f8ea5b1c5a3a70f258ef738b87ea74cef
## Why
Plugin identity and skill ownership need to be available independently of MCP data, including for plugins without servers or connectors. Hosted plugins have no executor root and should not own executor skills.
## What changed
- Add `McpServerContributor::selected_plugins` to declare executor plugin identities with deferred MCP data. Let the host assign server attribution and precedence across contributors.
- Represent hosted connectors with `HostedPluginConnectors` and make `SelectedPluginIdentity::selected_root_id` optional instead of assigning synthetic roots to hosted plugins.
- Resolve executor contributions before reading hosted connectors, and clear stale hosted state on account changes before executor loading can wait.
- Preserve connector declarations from disabled plugins so Apps can hide those connectors.
## Testing
Add coverage for account changes while executor loading is pending. Update tests to verify hosted identities have no executor root and disabled plugins hide their connectors even when plugin IDs differ from root IDs.
GitOrigin-RevId: e7f511264c5874c1b56d5f3e4a46820724046db0
## Why
Fixed schema budgets can strip parameter descriptions from large MCP tools or render their Code Mode input types as `unknown`. Allow larger budgets to preserve that guidance.
## What changed
- Add `mcp_servers.<name>.tool_input_schema_max_bytes` to configure the UTF-8 byte threshold for best-effort input schema compaction, retaining the 5,000-byte default.
- Add `features.code_mode.tool_input_schema_max_bytes` for rendered input types. Use the largest of the 16,000-byte default, the Code Mode setting, and the ordinary MCP server's explicit setting.
- Apply rendering budgets to prompt declarations and the runtime tool catalog, and avoid reusing cached declarations after the Code Mode budget changes.
## Testing
Add coverage for UTF-8 compaction thresholds, budget precedence, configuration round trips, and preservation of parameter guidance in both the Code Mode prompt and `ALL_TOOLS`.
GitOrigin-RevId: 0ef2823a614d4794e636f518b09c0b03a5239b45
## Why
Required MCP servers can block startup while establishing a live connection even when a usable tool catalog is already cached.
## What changed
- Add per-server `startup_readiness = "catalog"` to expose cached tools while the connection starts, retaining `"connection"` as the default.
- Allow an eligible cached catalog to satisfy required-server startup validation and model binding capture. Explicit server or plugin requirements still wait for a live connection, and tool execution still requires the current connection.
- Check tool filters and model visibility when accepting cached catalogs, and preserve cached catalog revisions for binding reuse.
- Serialize the new setting, expose it in the configuration schema, and trace startup readiness at validation and model binding gates.
GitOrigin-RevId: a1cbdf1757ebb5824cffe2cc56408be49711c422
## What changed
- Make `LocalThreadStore` default to paginated history while retaining explicit legacy mode.
- Explicitly use paginated history for Guardian review sessions and allow in-memory stores to create paginated threads.
- Rename full-history resume, fork, and subagent helpers to identify them as legacy APIs, and document the paginated alternatives.
- Reject `thread/revert` for ephemeral threads and prevent the TUI from replaying or attaching to ephemeral agent threads.
## Testing
Add coverage for preserving the default and explicitly selected history modes and conversation context across restart, and for retaining context after rejected ephemeral reverts. Extend Guardian checkpoint coverage across both history modes and verify that saved reviews use paginated history.
GitOrigin-RevId: 870239eb3757018159ee4f230a009c97d38ac5b7
## 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
## Why
History notes and image generation requests used default HTTP clients that did not carry the configured application network policy.
## What changed
Pass `Config::http_client_factory()` into both extension backends and create transports with `ClientRouteClass::Api`, so their requests honor application network restrictions and configured proxy behavior.
## Testing
Add regression coverage verifying that denied image requests never reach the server and that history notes context requests stop after the network policy becomes restrictive. Retain coverage for image file access restrictions.
GitOrigin-RevId: 7ba61fdc60fa1afe1842d869da9ccd744ab7d82f
## What changed
Remove the session-level capture mode and make thread-owned retained context the default throughout history management. Simplify input ordering, compaction identity preservation, fork handling, and approval freshness checks by removing legacy capture branches.
Keep checkpoint compatibility review separate: unknown or incompatible checkpoints can still use legacy review while retaining user evidence. Set the already-removed `guardianv2.thread_context` feature's default to false and remove redundant opt-out test variants.
## Testing
Update checkpoint tests to exercise legacy review through restored checkpoint data. Adapt existing compaction, resume, rollback, and fork tests to use unconditional context capture.
GitOrigin-RevId: ab23a0d7aca71d5a103458cff8b0c68137dd9708
## What changed
Always use `GuardianContextMode::ThreadOwned` for session capture and subagent history forks, regardless of `guardianv2.thread_context`. Continue selecting reviewer policy from saved checkpoints, preserving legacy review for incompatible checkpoints and removing the feature gate from reviewer compaction compatibility checks.
## Testing
Update coverage for unconditional retained context across compaction, resume, and subagent forks. Exercise legacy review with saved checkpoints, and verify that local and managed opt-outs do not disable sender context capture or checkpoint migration.
GitOrigin-RevId: cd74e2029c83f12bc655b6563242d06f29dd46af
## What changed
- Deprecate and ignore `features.guardianv2.thread_context`, including profile overrides, with a migration notice. Ignore managed requirements for the removed flag with a warning.
- Preserve surviving legacy root instructions across compaction and resume when retained instructions are incomplete. Include unmatched instructions in worker authorization context with an explicit unknown-ordering notice, without replacing newer retained facts or expanding the reviewer's model window.
- Use surviving source calls to roll back verified answers from older checkpoints that lack acceptance-order metadata.
## Testing
Add regression coverage for legacy instruction recovery, compaction and resume, source matching, and answer rollback around same-turn user input. Update configuration and Guardian review tests to verify that the deprecated opt-out still uses thread-owned context and rejects incompatible compaction evidence.
GitOrigin-RevId: a65936c9e0b912e7667d1385a2ec53df726565de
## What changed
Add `ModelRequestContributor` and `ModelResponseInterceptor` to the extension API. Contributors can add filtered `client_metadata` without overwriting existing or reserved fields and create interceptors for individual requests.
Wire contributors into HTTP and WebSocket requests, distinguishing generation from warmup. Apply response interceptors in registration order before tracing and response bookkeeping so transformed output is recorded consistently. Interceptors can inspect, buffer, or transform events, with stream ownership carrying request state and cancellation.
## Testing
Add tests for metadata protection, incremental event transformation, interceptor ordering, upstream cancellation, and consistency between delivered output, traces, and WebSocket bookkeeping. Integration tests cover output gating and interruption over HTTP and WebSocket, including a contributor that bypasses gating for warmup requests.
GitOrigin-RevId: d4bc1745d2cacf8636728dbc0a58ab9f250e9392
## Why
Channel tools use bundled descriptions even when the model catalog supplies tool messages. Let their descriptions follow the active model, including model changes within a turn.
## What changed
- Add channel tool entries to `MultiAgentToolMessages` and pass them to the message board extension for each step.
- Apply catalog descriptions while retaining bundled text for missing or null values and honoring empty strings. Ignore parameter overrides with a warning and keep bundled schemas.
- Clarify bundled descriptions for channel discovery, thread reading, posting, and subscription notifications.
## Testing
Add coverage for full and partial overrides in namespaced and Code Mode tools, preserving Code Mode declarations and parameter schemas. Extend the mid-turn model-change test to verify that the `post` description follows the active model.
GitOrigin-RevId: fca20bed1203d5214713f82cb16a91eeebb38f56
## Why
Tool lifecycle observers need visibility into calls rejected before execution starts and timing that remains available on cancellation, independently of tracing settings.
## What changed
- Add `on_tool_dispatch` and `on_tool_timing` callbacks to `ToolLifecycleContributor`, with thread, turn, and call IDs for correlation.
- Report direct calls before readiness, dispatch waiting, and hooks. Report handler duration when dispatch completes or is dropped, excluding readiness and gate waiting and returning zero if the call never passes the gate.
- Expose code-mode host durations as a separate `HostOperation` timing boundary. Exclude nested code-mode calls from dispatch and handler timing observations to avoid double counting.
## Testing
Add tests for callback ordering on completed and rejected calls, timing on cancellation, zero handler duration before gate admission without tracing, and code-mode host timing without nested dispatch or handler timing observations.
GitOrigin-RevId: 97998b5094564c13cb2cfad089bb0a9d6615eb5c
## Why
The Browser connector on `codex_apps` needs the computer-use policies and review handling already applied to `node_repl` and `cua_repl`.
## What changed
- Classify `connector_openai_browser` using registered tool metadata and preserve its computer-use scope through Guardian review.
- Extend confirmation-policy forwarding, review evidence capture, JavaScript execution tracking, and initial-call approval handling to the Browser connector.
- Correlate Browser elicitations with live invocations so nested actions retain their own review identity while assessments are attributed to the originating call. Require verified Browser identity for strict nested review.
- Include the Browser connector in computer-use policy prompts and bundled model messages.
## Testing
Add integration coverage for ordinary and strict Browser nested reviews, including policy injection and action attribution. Verify strict review declines requests with missing or unknown invocation correlation or a non-Browser registration.
GitOrigin-RevId: b04af6fb9db1bac2203dc4265913d210746df90b
## Why
HTTP retries used local backoff even when the server supplied `Retry-After`. Relative retry delays also failed to account for time spent propagating errors or reporting retries.
## What changed
- Parse `Retry-After` delay seconds and HTTP dates into a monotonic deadline captured when response headers arrive.
- Honor that deadline for HTTP retries, falling back to local backoff when valid advice is absent.
- Preserve deadlines through API and Bedrock error mapping, stream retries, and exhausted retry state. Expired advice remains a zero delay instead of triggering local backoff.
## Testing
Add coverage for header parsing, deadline countdown and expiry, error mapping after exhausted HTTP retries, and delayed stream retry notifications. Update Responses and remote compaction tests to verify that HTTP retries honor `Retry-After`.
GitOrigin-RevId: a2eff02946e5524f29e06f7ba1431e3d339261a4
## Why
Ordinary user replies can depend on preceding assistant messages. Losing those messages during compaction can leave Guardian without the context needed to interpret a reply's scope.
## What changed
- Retain original assistant messages, including commentary, with their recorded order across checkpoints and resume. Exclude compaction output from this evidence.
- Include assistant context in local and delegated reviews as untrusted context, with separate storage limits and lower budget priority than user instructions.
- Prefer assistant context preceding ordinary replies when selecting bounded root evidence, and report unavailable context without inferring what a reply refers to.
- Preserve inherited context scope and remove assistant evidence beyond rollback boundaries, including during rollout migration.
## Testing
Extend coverage for compaction and resume, checkpoint migration, queued-input ordering and rollback, role labeling, and evidence budgets that preserve user restrictions while dropping assistant context.
GitOrigin-RevId: 886189b0be29ffc3d324b56f5d0b673d6b8d84da
## What changed
Add the boolean `transparent_background` argument to `image_gen.imagegen` for generation and editing. Map `true` to `transparent` and `false` or omission to `opaque`, replacing the previous `auto` background setting.
Update tool guidance to request transparency for background removal and cutouts, and to preserve existing transparency during edits unless the user asks to change it.
## Testing
Add integration coverage for transparent, opaque, and omitted background arguments across generation, editing, and code-mode generation. Verify that `null`, string, and numeric values return a validation error without dispatching an image request.
GitOrigin-RevId: b10ac200a619c72cc1787da41b49d65d0cde05dd
## Why
Destination restrictions and policy revocation must remain effective during redirects, response body reads, and established WebSocket traffic. Policy denials must also survive error handling so callers do not retry them or report a revoked operation as successful.
## What changed
- Route managed HTTP clients through a shared `RequestBuilder` and policy-aware execution, checking each redirect destination before route resolution and retaining a network permit while consuming response bodies.
- Guard WebSocket connection setup, reads, and writes with revocable permits, including independent wakeups for split readers and writers.
- Preserve `TransportError::Policy` through HTTP, SSE, and realtime error handling, and treat policy denials as non-retryable.
- Keep the supplied network policy in plugin startup HTTP requests and propagate response body failures from backend and plugin requests.
## Testing
Add regression coverage for rejection before connecting, revocation during redirect routing and streamed body reads, split WebSocket revocation, realtime writer error propagation, and revoked plugin upload responses.
GitOrigin-RevId: fba36700444c98a8364c09b4dc5452c4d78a90fb
## Why
`invalid_prompt` responses were classified as generic invalid requests, losing the server's specific error classification.
## What changed
Add `InvalidPrompt` variants to the API and core error types and serialize the core protocol classification as `invalid_prompt`. Recognize the code in HTTP 400 responses, wrapped WebSocket errors, and SSE `response.failed` events while preserving server messages and keeping the error non-retryable. Map it to `other` in the app-server v2 protocol.
## Testing
Extend coverage for typed error mapping, missing and blank messages, protocol conversion, and guardian retry handling. Exercise HTTP and SSE failures in core integration tests, asserting the error message, serialized classification, and a single request without retry.
GitOrigin-RevId: 5d9a299a013b06158a4dc27a4054f3dbc5fd0f4d
## Why
Cloud skill discovery ran on every turn, even when the Apps resource generation and authentication scope were unchanged.
## What changed
- Reuse warning-free catalogs, including empty catalogs, while their authentication scope and Apps resource cache key remain current.
- Refresh after invalidation and retry failed or partial discovery on the next turn.
- Reject discovery results if the Apps resource cache key changes during discovery.
## Testing
Update lifecycle tests to verify cached turns avoid catalog listings and skill reads, while connection and authentication changes trigger refreshes. Update the referenced-resource test to verify partial discovery retries on the next turn without an explicit MCP refresh.
GitOrigin-RevId: ac47d5202d76703c4946afef3b1a48eaf05b54c2
## Why
Failed image requests discarded the `x-codex-imagegen-request-id` header, leaving failure analytics without the request ID.
## What changed
Carry the request ID through `ImageRequestError` and backend errors for image generation and editing. Preserve it on failed image generation items for HTTP errors, response decoding errors, and responses with no image data.
## Testing
Extend the app-server failure test to verify that a request ID returned with an HTTP 500 response reaches `codex_image_generation_event` analytics.
GitOrigin-RevId: 57cddacc0221e5b58877ac375d5eca0afb99d853
## What changed
Reject authorization endpoints with schemes other than `http` or `https` before client registration or authorization URL return. Document this constraint for `mcpServer/oauth/login`.
## Testing
Make existing asynchronous tests wait for cleanup: wait for `ThreadIdle` before injecting user input in the guardian cached-score test, and poll for queue consumption before asserting that dispatched items are gone.
GitOrigin-RevId: e5f6b4c5556234c3cc2aa56910486e892c011116
## What changed
Mark `guardianv2.thread_context` as stable and enable it by default for synchronous and asynchronous Guardian reviews. Keep it independent of the Guardian v2 `enabled` toggle and preserve explicit configuration and profile overrides. Update the configuration schema documentation to match.
## Testing
Update coverage for default configuration and sender user messages, review prompt snapshots, history retention across compaction, and checkpoint provenance. Assert that later user input invalidates an in-flight review's authorization. Keep legacy transcript budgeting coverage by explicitly disabling thread context in that test.
GitOrigin-RevId: 19afd34d7bfc0ee36bbf878089c68b732a21bc6a
## Why
Posting to a new channel subscribed its author to replies on that post, but not to new discussion roots in the channel. The creator could therefore miss notifications for subsequent discussions.
## What changed
Subscribe the author to the channel in the same transaction that creates the channel and its first post. Document this behavior in the API and the `new_channel_name` tool parameter.
## Testing
Update coverage to verify that channel creators receive notifications without explicit targeting and that posting to an existing channel preserves an explicit unsubscribe. Adjust thread-deletion test expectations for the additional persisted subscription.
GitOrigin-RevId: 5553ebc9f9b51456ab48886e9871733e93370a2b
## Why
Posting to a discussion automatically subscribed its author, undoing an explicit unsubscribe and restoring unwanted reply notifications.
## What changed
Persist explicit opt-outs so posting follows a discussion by default but leaves unsubscribed agents opted out until explicitly subscribed again. Keep active subscriptions in the existing table for compatibility with older readers, and remove opt-outs when deleting a board. Update the API and tool descriptions to explain the behavior.
## Testing
Extend the local board test to cover reopening an older database, preserving opt-outs across reopen and subsequent posts, legacy subscription queries, explicit notifications without resubscribing, explicit resubscription, and board cleanup.
GitOrigin-RevId: 8b8f7f50cea5041541b8d93067c52db18cdde85c
## Why
Channel and thread subscriptions, or explicit `agents_to_notify`, could cause agents to receive notifications for their own posts.
## What changed
Exclude the author from notification recipients, even when explicitly targeted. Preserve the author's subscriptions so replies from other agents still reach them, and document this requirement in the board API.
## Testing
Update board tests to cover explicit self-targeting, subscribed authors, and delivery of other agents' replies. Update the model-context scenario and snapshot to verify posts remain searchable without a `CHANNEL_POST` self-notification.
GitOrigin-RevId: 0b2558e7df79122a6da06ad592f9735ba260cce1
## Why
Standalone web search selected a proxy route only for the initial endpoint. Redirect destinations can require a different system proxy route.
## What changed
- Add `RouteAwareClientPool` support to `ReqwestTransport` for both buffered and streaming requests, and use it for standalone web search.
- Preserve default Codex headers and Cloudflare cookie handling across routes, while retaining the default client behavior when route-aware handling is disabled or Codex is sandboxed.
- Share request construction so URL authentication and header precedence follow `reqwest` semantics, applying them once before redirects and TLS retries.
- Map route-aware failures to transport errors and remove request URLs from those errors.
## Testing
Add regression coverage for redirects through distinct proxies, preservation of POST bodies and default headers, URL authentication and header precedence, and transport error classification without URL leakage.
GitOrigin-RevId: 19a10a62118846db09dd95265dc277e54aac09ef
## Why
Classifier requests need to preserve their owning thread's workspace routing and account binding, including when reusing pooled connections or retrying after authentication changes.
## What changed
- Share the thread's `WorkspaceRoutingContext` with Guardian v2 and resolve routing before leasing HTTP or pooled WebSocket connections.
- Reuse WebSockets only when their connection key and authentication state still match. Cache HTTP transports by URL and redirect policy, rejecting redirects when routing requires it.
- Stop classification requests and retries when the account owner changes while allowing token refreshes for the same user and workspace.
## Testing
Add regression coverage for routing failures with prewarmed sockets, shared thread routing state, account switches during HTTP and WebSocket requests, same-account token refreshes, and HTTP redirect-policy cache changes.
GitOrigin-RevId: 7b3efcadb4797b6a2de2e28e7506b297b0728d69
## Why
Standalone web search used a default HTTP client, bypassing the configured system proxy route when `respect_system_proxy` was enabled.
## What changed
Pass the configured `HttpClientFactory` to the web search tool and create its client asynchronously for the provider's search URL using the API route policy. Export and reuse `SEARCH_ENDPOINT` so route selection and search requests use the same endpoint.
## Testing
Add an isolated regression test with environment proxies removed and a mock system proxy. Verify that standalone web search reaches the proxy and returns its result in the follow-up model request.
GitOrigin-RevId: 3b64803a777b9d1eb0ccf694e06658b0fd562129
## Why
Extension calls omitted environments whose working directories could not be converted to host-native paths, preventing extensions from receiving those environments.
## What changed
Store `ToolEnvironment.cwd` as `PathUri` and pass all turn environments to extension tools without requiring host-native path conversion. Keep image generation's existing path requirements by selecting the first environment with a convertible working directory when reading referenced images or saving generated images.
GitOrigin-RevId: b4320c6e07d27ef59885cd0013e5d1c535f69659
felixxia-oai