## Why
Interrupted automatic goal continuations reset the empty-response counter, allowing repeated interruptions without activity to keep a goal running indefinitely.
## What changed
Count interrupted automatic continuations without activity toward the existing three-turn limit that marks a goal as `blocked`. Defer evaluation until the thread is idle and serialize it with turn-start accounting. Activity and user turns still reset the counter.
## Testing
Extend accounting tests to cover interrupted and mixed empty continuations, including resets after tool activity or user turns. Add an app-server regression case where a `PreCompact` hook repeatedly interrupts automatic continuations and verify the `thread/goal/updated` notification reports `blocked`.
GitOrigin-RevId: 4c34e3ed1ae612e97cf067c2aa76836b10c50ef5
## What changed
- Move the SQLite schema, database filename, and shared pool registry into `local/pool.rs`.
- Share channel insertion between runtime writes and template setup, using typed board IDs and channel descriptions.
GitOrigin-RevId: c57a79c49fe9003b3c73f38010ce9293275a714c
## What changed
Expose `LocalBoardSetup` and `configure_local_board` to load initial channels and optional descriptions before agents start. Add a `configure_board` example and setup documentation.
Save version 1 templates and channels atomically in SQLite. Identical templates are safe to retry; conflicting templates, previously used boards without a pinned template, and deleted boards are rejected. Setup accepts an optional creation timestamp and leaves agent access unchanged. Remove the pinned template when deleting a board.
## Testing
Add an integration test covering channel metadata after reopen, identical retries, conflicting template rejection, retries after adding a channel, and rejection after board deletion.
GitOrigin-RevId: 0b5c5439ab127fb5c275f024962a373a56635ad0
## Why
Remote boards can allow replies while denying new threads. Agents need to discover these effective permissions and receive actionable details when an operation is denied.
## What changed
- Expose optional `board_permissions` and per-channel `permissions` in `get_channels`, preserving the legacy response shape when permission metadata is absent.
- Preserve HTTP 403 `permission_denied` responses as structured tool errors with a message and optional `action` and `resource`. Mark denied calls as unsuccessful and truncate oversized error details to fit the output budget.
- Pass through service-computed permissions without evaluating access rules locally.
## Testing
Add remote-board scenarios for direct tools and code mode covering legacy responses, reply-only permissions, a denied post, and a successful reply, plus a snapshot of the direct tool exchange.
GitOrigin-RevId: 76594bbc0a1283ff3c3c8682bd7615baa5ade428
## What changed
- Remove `ContentItemMetadata`, provenance and namespace types, and the `content_item_metadata` protocol field while retaining `content_item_kinds` classifications.
- Simplify context fragments, extension contributions, and hook output to carry content without source attribution. Return MCP tool results directly without an attribution wrapper.
- Render context-window hints together in a single text fragment.
## Testing
Update Responses and Responses Lite request assertions to expect content-kind classifications without per-content attribution, and adapt context, hook, and extension tests to the simplified types.
GitOrigin-RevId: 201894cd4c93c6d4b4c41c845e7a9af1dd3c95ca
Remove the repeated `selected_capability_roots` initializers from the two
`TurnEnvironmentSelection` fixtures in
`mcp_context_preserves_selected_executor_order_and_unavailability` so the
test can compile.
GitOrigin-RevId: 6e773cdcba84b95220eb024d51619fea67780617
## 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
## What changed
- Add `tui.keymap.global.leader`, defaulting to `ctrl-x`, and symbolic bindings such as `leader c` that follow the configured prefix. The default prefix yields to existing custom shortcuts and chord prefixes.
- Keep leader shortcut hints open until completion or cancellation, while ordinary chords retain their one-second timeout. Pressing `esc` or repeating the leader cancels the pending shortcut.
- Add leader configuration and a `Use leader...` capture option to `/keymap`, with resolved shortcut labels and conflict validation.
- Cancel pending chords when input targets change, on paste or focus loss, and on mouse actions other than movement.
- Move the default voice mute shortcut from `ctrl-x` to `f9` and update its tests and displayed hints.
GitOrigin-RevId: 35b964cccd2812c73200f0c26b0f19506821df92
## What changed
- Reformat Markdown tables and lists, login pages, inline visualization HTML, and sample JavaScript scripts.
- Escape union-type pipes in Python SDK API tables so they render within their cells.
- Keep the formatting-recipe test focused on the working directory and formatter commands by removing assertions on comment text.
GitOrigin-RevId: ae46d5b40fd013553de8b5ccf2c41d76be65aba8
## What changed
Add the disabled-by-default `guardian_trust_orchestrator_connectors` feature flag. When enabled, Guardian V2 accepts connectors with nonblank IDs from the host-owned plugin service orchestrator as a trusted source without requiring a matching user configuration declaration.
Distinguish orchestrator provenance from user configuration in trusted-tool context. Trust remains scoped to the exact server or connector identity and source; descriptions, outputs, other tools, and other connectors remain untrusted.
## Testing
Add coverage for host-owned connector context, rejection of extension-owned Apps lookalikes and blank connector IDs, source-specific trust metadata, and context token limits. Snapshot the connector approval request history.
GitOrigin-RevId: fbd87dd71110ca7b2b92d50eef02e1e739a74a02
## Why
Tools that do not opt into parallel execution acquire an exclusive scheduler lock, serializing independent reads.
## What changed
Allow skill listing and reading, memory listing, reading and searching, conversation history search and reading, plugin listing, agent listing, current time, remaining context, and `get_goal` to run in parallel. Keep goal creation and updates serialized.
## Testing
Add `cloud_skill_reads_run_in_parallel`, which uses a barrier to require two cloud skill reads to overlap and verifies that each returns the expected resource contents.
GitOrigin-RevId: 97b5634f1f84be2ba092be89e6e9c634ca75c07b
## What changed
Support `plugins._default.enabled` with explicit per-plugin `enabled` overrides. Omission preserves existing source and account enablement; configuration cannot activate a plugin disabled at its source. Plugin settings such as remembered tool approvals inherit the default unless `enabled` is explicitly set.
Apply the policy to plugin skills, MCP servers, Apps, and hooks, including selected executor roots and runtime configuration refreshes. Preserve the latest plugin policy when adding MCP dependencies and rebuild hooks when concurrent configuration updates replace their inputs.
Report effective enablement in `plugin/list`, `plugin/installed`, `plugin/read`, and `plugin/share/list`. Remote installation still installs disabled packages, but skips MCP and Apps authentication setup without writing an enablement override.
## Testing
Add regression coverage for default inheritance and explicit overrides, source-disabled plugins, policy refreshes during active turns, disabled or malformed selected plugin roots, and remote installation authentication behavior.
GitOrigin-RevId: 83b70c5b47fc95474fec292f248683f1f887221e
## What changed
- Add `ContentItemMetadata` to distinguish user input, developer instructions, `AGENTS.md`, skills, harness context, and tool-supplied context independently of message role and content classification.
- Keep attribution attached to content through prompt assembly, history processing, and hook-output spilling. Distinguish command hooks from MCP hooks and retain tool namespaces when known.
- Treat missing historical attribution as unknown and send per-content metadata only to Responses Lite.
## Testing
Update request and history assertions to cover attribution persistence and Responses Lite metadata handling.
GitOrigin-RevId: 24e56005f5bdb98bf82f2b3943f29c4c81f3d587
## What changed
- Accept an optional `description` in `create_channel` and return it in channel summaries so agents can describe a channel's purpose.
- Enforce a limit of 512 UTF-8 bytes and account for JSON escaping in the output budget before creating the channel.
- Store descriptions in both board backends and migrate existing SQLite databases, leaving older channels without descriptions.
## Testing
Add coverage for UTF-8 byte limits, serialization, output budgets, legacy database migration, and persistence after reopening. Update the model-context scenario to create and list a described channel before posting and reading a message.
GitOrigin-RevId: cf6f395944da23e238e078eefa5de201c8b9c197
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
A conversation classifier waiting for preparation or full response completion can block newer classifications. Concurrent reviews also need to prevent a later action's evidence or low-risk score from being reused for an earlier action.
## What changed
- Run conversation classifications independently, forking the latest compatible completed history from an earlier action. Only a valid completion with a newer action index can replace retained history.
- Keep admission and observation ordering atomic, and hold capacity permits through full response completion.
- Reject cached low-risk scores from later actions for tool-linked approvals, including initial approval checks.
- Track originating tool-call IDs separately from approval display IDs, preserving stdin write provenance and excluding synthetic MCP elicitation IDs from tool ordering.
## Testing
Add regression coverage for delayed preparation, capacity admission, out-of-order completion, cancellation, invalid retained output, and history snapshots. Exercise pending approval ordering in both `snapshot` and `conversation` modes, and verify linked and unlinked MCP elicitation provenance.
GitOrigin-RevId: 097476ccb3b8718369a69f55c3c39132f7f1a4c1
Remove repeated `selected_capability_roots` initializers from two
`TurnEnvironmentSelection` fixtures so the registry test can compile.
GitOrigin-RevId: bef3fba18dd786b80610703a37d6d3243cf33401
## Why
Tokio runtime tracing can cause SQLite log writes to enqueue more writes and exporter activity to generate further OTLP exports.
## What changed
- Exclude `tokio` and `runtime` spans from OTLP export alongside `h2` spans.
- Limit `tokio::` and `runtime::` targets to `INFO` in the default log filter, and reject their `TRACE` events directly in the SQLite sink even without an outer filter.
- Box and pin the session-loop future before spawning it.
- Reorder tracing and Tokio test attributes, restrict the skills concurrency test's subscriber to the catalog-refresh span, and use the default log filter in the SQLite formatter comparison test.
GitOrigin-RevId: f545013a2469088d7f9890c1f46bb93eb5446d2d
## What changed
Consume enabled tool definitions and borrow their metadata when installing `tools` and `ALL_TOOLS`, avoiding copies of the tool catalog. Retain only tool names and kinds in runtime callback state, preserving each cell's original callback indices for its lifetime.
GitOrigin-RevId: 62eaf62abce6de1a0cd5cdb3332fbed754a23993
## 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
## Why
Retained assistant context changes as the conversation grows. Keeping it separate from retained user instructions lets independent Guardian snapshots preserve a reusable instruction and transcript prefix.
## What changed
Move retained user instructions before the transcript and place assistant originals and their omission notice in a separate `RETAINED ASSISTANT CONTEXT` section afterward. Preserve evidence, delivery roles, source metadata, and deduplication across both retained sections. Clear omission delivery metadata when a split assistant notice cannot be attributed to a single section.
## Testing
Add regression coverage for prefix stability as assistant context and previous reviews change, evidence preservation, repeated preparation, and deduplication. Update approval-routing and scorer tests to check the new section order and retention of assistant text outside a smaller transcript budget.
GitOrigin-RevId: 15cda59d24bee0106f6a66c067f6a790fa91df69
## Why
Executor config reads omitted the startup `features.prefer_mxc` override, so clients could not see the CLI sandbox preference.
## What changed
- Include the explicit CLI `features.prefer_mxc` value in `environmentConfig/read` as a `session-flags` layer, above project config and below legacy managed file and MDM config.
- Retain only this preference from startup overrides.
- Expose `windows_mxc_allowed_by_config` to share MXC eligibility checks after callers resolve the active permission profile.
## Testing
Add CLI and remote executor coverage for preference propagation and filtering, plus a unit test verifying that both legacy managed config sources retain precedence.
GitOrigin-RevId: 5ac6f5257f1e807c2f197dcf5dcb2385cedca0ea
## Why
MCP contributors need the complete executor selection to distinguish an unavailable primary executor from a ready secondary. Ready capability roots alone do not preserve pending or failed selections.
## What changed
Add `with_selected_environments` and `selected_environments` to `McpServerContributionContext`, and pass the captured selections during thread MCP resolution and model-step plugin selection. Preserve priority order and pending or failed entries. Use `None` for threadless discovery and `Some(&[])` for an explicitly empty selection.
## Testing
Add regression coverage for executor ordering with pending and failed selections, environment context in model-step plugin selection, and the distinction between absent and explicitly empty selections.
GitOrigin-RevId: 2c1222fae72c7e2c75b2f40abfad3b2048cf9316
## Why
Capability discovery needs the roots captured with each environment snapshot. Threads sharing an executor can select different roots, and changing environment order must preserve executor skill aliases.
## What changed
- Attach the receiving thread's capability roots when constructing `TurnEnvironmentSelection` at startup and settings updates, including roots loaded from saved history.
- Resolve capability roots from environment snapshots while preserving their original order. Retain startup roots so deselecting and reselecting an environment restores its capabilities.
- Match inherited configuration by environment and workspace so differences in capability root metadata do not interrupt configuration propagation.
## Testing
Add regression coverage for root ordering across environment states and configuration changes, independent root selections on a shared executor, reselection with startup or saved roots, active turn updates, and pending configuration failures reaching child and grandchild threads.
GitOrigin-RevId: 4f2e4bb414d27195a6752406117a6050718a1198
## Why
Skill selection and disabled-path matching need to recognize equivalent Windows paths across case and separator differences while preserving literal spaces, `%`, and `#` in native filenames.
## What changed
- Carry `PathUri` through skill metadata, discovery mappings, filesystem lookups, disabled-path sets, and invocation analytics.
- Match linked skill mentions and TUI selections by parsed path identity.
- Use `LegacyAppPathString` for app-server skill paths and regenerate schemas and SDK types, preserving native path strings on the wire.
- Preserve native catalog display paths and ordering. Keep host filesystem probes and configuration writes restricted to host-compatible paths.
## Testing
Add regression tests for Windows path identity and disabled-skill matching, literal filename characters, catalog resource reads, native path ordering, and foreign-path analytics normalization.
GitOrigin-RevId: c212916dc9fef0e7616542726e107f0d6a313267
## What changed
Introduce `TranscriptRecord` and `PreparedTranscript` to retain attributed transcript text through preparation and composition. Cache rendered content, byte counts, and token estimates, refreshing them when text or framing changes.
Keep JSON records structured during budget recovery so truncation replaces only `text`, preserving metadata, field order, and framing without reparsing serialized JSON. Preserve whole-entry truncation for line transcripts and update synchronous and asynchronous consumers to use the preparation API.
## Testing
Expand coverage for cached estimates and delivery with escaped text, Unicode, and large payloads; metadata and framing preservation during recovery; and stable asynchronous history prefixes in both line and JSON formats.
GitOrigin-RevId: 8b3b5231ca4a6ee47d17dcc788ea68c56dd1a9bc
## Why
Transcript content can contain forged role headers, transcript boundaries, or claims of user approval. Guardian needs to distinguish that content from host-assigned authorship metadata.
## What changed
- Add `features.guardianv2.transcript_mode` with `line` (the default) and `json` options for synchronous review and asynchronous scoring.
- Render JSON transcript entries with host-assigned metadata and escaped `text`, and prepend matching provenance instructions to reviewer and classifier prompts.
- Preserve JSON metadata when budget recovery shortens historical text, and keep provenance instructions outside the configured classifier prompt limit.
## Testing
Add coverage for forged roles and approvals remaining within their original entries, JSON metadata surviving budget recovery, and provenance instructions surviving prompt limits. Extend review and scoring integration tests to verify JSON evidence and matching instructions.
GitOrigin-RevId: 81a3580390d3c4d1a664e554976cda5f1adc9a2c
## 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 low-risk score for a later action could release an earlier pending Guardian review when the thread's score lag reached zero, bypassing that action's synchronous review result.
## What changed
Track the accepted score's source action and allow it to release a pending review only when it comes from that action or an earlier one. Keep cached-score approval available before synchronous review starts, but prevent the initial computer-use allowance from releasing an already pending review.
## Testing
Add an app-server regression test with two pending reviews: a later low-risk score approves its own action while the earlier action remains pending and honors its synchronous denial.
GitOrigin-RevId: ed8b9c4793b2538f634edfc5699797a6983358cc
## 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
## Why
Serial connection opens let a stalled handshake delay healthy sockets. Waiting until the idle pool is empty to refill also leaves classification bursts using HTTP fallback.
## What changed
- Open up to four WebSockets concurrently and start replenishing when the idle pool falls to half capacity. Preserve successful in-flight opens when another open fails or times out.
- Make explicit prewarming wait for an existing refill before checking readiness.
- Add `ResponsesWebsocketClient::connect_with_connector` and reuse one connector per sampler, initializing TLS configuration on a blocking task while retaining per-connection authentication and destination policy checks.
- Record connection lease durations for admission, setup, and total time, tagged by transport.
## Testing
Add regression tests for a stalled handshake alongside a healthy socket and replenishment before the last idle socket is leased. Update cooldown, authentication, and transport retry tests to account for concurrent handshake completion.
GitOrigin-RevId: f4a8258977c1f2a58e00c6badc7b599280ef22ad
## 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
Partial answers contain answer fragments while a turn is still in progress. Treating them as final answers defers mailbox delivery and can count empty fragments as empty final responses; filtering them from forked histories and guardian transcripts loses answer content.
## What changed
- Allow mailbox preemption after `partial_answer` messages and keep mailbox delivery open.
- Preserve partial answers in forked agent histories and include them as protected assistant entries in guardian transcripts.
- Exclude empty partial answers from empty-final-response accounting for goals.
## Testing
Add regression coverage for partial-answer phases in live events, sampling continuations, follow-up requests, and forked child requests, plus mailbox preemption, goal accounting, and guardian transcript inclusion.
GitOrigin-RevId: 208c8933e211b42b6c2d0bec6952527b8c9c120e
## What changed
- Accept per-environment `skills.required` lists through `environment/add` and `environments.toml`.
- Before inference, require each named skill to be enabled and supplied by the selected environment. Missing skills fail the turn before a model request, including when environment setup fails.
- Stop applying an environment's requirements after it is deselected. Exempt isolated Guardian reviewers, which have no skill catalog.
## Testing
Add tests for available, missing, disabled, and wrong-environment skills, failed environment setup, recovery after deselection, and propagation of TOML requirements to the correct environment.
GitOrigin-RevId: 302ced4774697d2f414f745fe0535e71f747eda2
## What changed
Move base instructions from the top-level `instructions` field into a prefixed `developer` message in `input` for standard Responses requests, matching Responses Lite. Remove the field from HTTP and WebSocket request types and assign instruction messages stable IDs derived from the thread and instruction text.
## Testing
Extend standard and Responses Lite tests to cover instruction message serialization, stable IDs, and resume consistency. Update WebSocket tests to verify that changed instructions trigger a full request without `previous_response_id`.
GitOrigin-RevId: e2de4b8e30a9339377fac133ceda981abd1a112b
## 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
Use `OPENAI_API_KEY` for the Guardian Decisions sampler when `CODEX_GUARDIAN_DECISIONS_API_KEY` is absent, the provider is `openai`, and no custom base URL is configured. Preserve dedicated-key precedence, including empty values, and do not fall back for other providers or custom base URLs.
## Testing
Add a credential-selection test covering fallback, dedicated-key precedence, empty dedicated keys, and provider and base URL restrictions.
GitOrigin-RevId: a2a62c28789597f013544b51e142b21f9e214080
## Why
Manual, pre-turn, and post-turn compaction previously deferred rebuilding initial context until the next turn. Their saved replacement history could omit refreshed instructions and skill catalogs.
## What changed
- Install initial context during local and remote compaction, before the last real user message or summary, keeping the compaction summary last.
- Persist matching full world-state and turn-context baselines with every replacement instead of retaining only partial extension metadata.
- Build replacement context and recompute token usage for the current model even when the previous model performs compaction. Reuse that captured context for eligible current-model retries.
- Capture manual compaction context centrally and propagate preparation errors to the task runner.
## Testing
Update assertions and snapshots for context ordering, refreshed instructions, resume and fork history, current-model checkpoint baselines, and cloud skill catalog retention across compaction and resume.
GitOrigin-RevId: 8572a76c31c6884a3c580b3bbb350d49af876bd1
## Why
The Decisions adapter rejected developer messages, including host-annotated trusted-tool context. Requests containing that context could not be classified.
## What changed
Append developer text annotated with `TrustedTool::KIND` to the classification rubric, preserving its authority while keeping user evidence in the input messages. Accept only a single text part with a single matching annotation; continue rejecting other developer messages and unsupported evidence.
## Testing
Add a regression test covering trusted-tool context alongside untrusted user text, plus rejection of incorrect roles, missing or mismatched annotations, multiple annotations or content parts, and image content.
GitOrigin-RevId: 65b6301b2ee1ac54d67275978ccb5e37dcac7c16
## What changed
Measure `responses_duration` directly around `sampler.sample()` in the snapshot classification path. Leave it unset for conversation classification instead of timing submission and waiting for the score.
GitOrigin-RevId: 4cfac9db6f19f3c8513d7bf839ea9631d41bf3ac
## What changed
Record `agree`, `disagree`, or `unavailable` comparisons between Decisions risk classifications and accepted Responses scores. Emit paired latency histograms only when both backends succeed, and include request preparation and queue time in Decisions duration. Report unavailable comparisons when the comparison feature is enabled but the Decisions sampler is not initialized.
## Testing
Extend lifecycle coverage for an uninitialized Decisions sampler, checking skipped outcome and unavailable comparison metrics while preserving the baseline score.
GitOrigin-RevId: f11789ab5d5fd6957b7913d849bbb2ae7006d3ed
## What changed
Add the disabled-by-default `guardianv2_decisions_comparison` feature to run Decisions alongside Guardian V2 snapshot classification using the same policy and evidence. Initialize the comparison sampler with `CODEX_GUARDIAN_DECISIONS_API_KEY`.
Publish the baseline score before awaiting comparison results, and keep comparison results and failures from changing approvals. Apply Guardian's input token budget, skip conversation evidence, and cancel comparison work when the baseline classification is superseded. Record success, failure, and skip outcomes with bounded diagnostic reasons, including setup failures.
## Testing
Add lifecycle tests covering disabled comparison, disagreeing classifications, backend failures, unchanged published scores, matching policy and evidence, and rejection of over-budget requests before either backend sends them.
GitOrigin-RevId: 743d34c8ee440362da94f001058366027b39bd11
## What changed
Add a Decisions sampler under `#[cfg(test)]` for Guardian's optional comparison classifier, without wiring a runtime caller.
- Encode text and inline image evidence as a `guardian_risk` choice request using `gpt-6-luna`, accepting only `low` or `high` responses. Reject the complete request when evidence cannot be represented.
- Bound concurrency to 16 requests, cancel the oldest unfinished request at capacity, and abort unfinished work when its owning task is dropped.
- Enforce a six-second HTTP deadline, an 8 MiB inline image data limit, and a 16 KiB response limit. Keep credentials and wire bodies out of errors.
## Testing
Add tests for the HTTP contract, unsupported evidence, inline image preservation and size limits, response validation, oldest-request cancellation, and capacity release when a caller is dropped while awaiting completion.
GitOrigin-RevId: e7209ca49a04505acf10ff1aeaca941514589e13
## Why
Environment changes and overlapping catalog refreshes can cause a step to use another step's selected plugins or executor skills. Model context and skill tools need to agree on the capabilities captured for that step.
## What changed
- Resolve selected plugins from each step's ready capability roots, honoring disabled plugins, and retain the snapshot with the step's extension data.
- Use that snapshot for skill attribution in World State and the first step's active-plugin telemetry.
- Return executor skill catalogs directly from refresh so overlapping requests render their own results while retaining thread caches.
## Testing
Add regression coverage for overlapping executor catalogs and environment changes during step preparation. Verify that `skills.list` retains the original step's skills, the next step advertises the new skills, and disabled executor and plugin skills remain absent from model context.
GitOrigin-RevId: 37d3cbe8c7e062fd06290aa985ada4d3b3462d43
## Why
The rolling retained-context window can change as assistant messages are added or evicted. Placing it before the transcript invalidates the reusable history prefix.
## What changed
Move retained user instructions and context after the transcript and action-specific attestations, immediately before the planned action in asynchronous Guardian requests. Keep synchronous section ordering unchanged.
## Testing
Extend the cache-prefix regression test to cover retained assistant message growth and eviction alongside changing attestations. Update app-server and async scorer assertions to verify the new request ordering.
GitOrigin-RevId: 59953d582d4b174ce3e083606626c7532ce0776d
## Why
Executor skill reads need to use the environments and permissions captured for the current step, including newly approved grants. Cached continuation pages must remain bound to the filesystem and permissions that produced them.
## What changed
- Supply borrowed `EnvironmentAccess` to turn-input contributors and extension tools, with session and originating-turn grants already applied.
- Require executor skill reads to use filesystem access from an environment available to the callback, and replace separate optional read contexts with `SkillReadContext`.
- Bind skill pagination snapshots to `EnvironmentAccessKey`, which identifies the source filesystem and callback permissions.
- Route image-generation filesystem operations through the same accessor.
## Testing
Extend skill-read integration coverage to verify that a denied reference becomes readable after a turn-scoped grant is captured by the next model step. Update Windows coverage to verify that restricted reads fail when the executor cannot enforce a sandbox, and add a test requiring turn environment selection before exposing capability roots.
GitOrigin-RevId: 825b49302319965835d61c77fc5bcdb951e10543
## What changed
Return snapshots and model-visible fragments together from world-state rendering, and use those snapshots for history baselines, step updates, compaction, and new context windows.
Update `WorldStateSectionContribution` so its renderer returns an optional replacement snapshot and an optional fragment. A missing snapshot preserves stored section state, even when retained history requires a fresh render; a null snapshot removes the section. Derive step patches from the history baseline rather than a separately captured live world state.
Adapt skills and Git attribution contributors to the new contract.
## Testing
Add coverage for skipped snapshot updates, explicit section removal, changed-state patch replay, unchanged-state deduplication, and matching live and persisted checkpoints when starting a new context window.
GitOrigin-RevId: af71606a278358ae937853cb76e8a019a501408e
Eric Traut