## What changed
Enable `instant_interrupt` by default so new user input can preempt responses and yield foreground code-mode observations. Keep the feature marked as under development and update feature-policy tests to allow this exception.
Explicitly disable instant interrupts in core, TUI, and Python SDK tests that depend on responses completing before steering or processing subsequent input.
GitOrigin-RevId: a8cab2d6c445bfdbd10b0b2abcf7893d32ee8595
## What changed
Add the `ultrafast` service tier to bundled catalogs for `openai.gpt-6.1-sol` on Bedrock Mantle and `global.openai.gpt-6.1-sol` and `us.openai.gpt-6.1-sol` on Bedrock Runtime. This exposes `/ultrafast` for these models while keeping tier selection opt-in.
## Testing
Extend catalog, app-server, core request, and TUI tests to cover GPT-6.1 Sol tier discovery and selection across all three model IDs, including toggling back to the default tier and honoring custom catalog commands.
GitOrigin-RevId: b5bbde8615b73a1d73eb16db7952b10d044b9fa6
## What changed
Move `SandboxOverride` into the shared protocol and carry the controller's selection through tool attempts, execution requests, and exec-server process and filesystem sandbox preparation. Include it as `sandboxOverride` in filesystem sandbox contexts for observation without granting broader permissions or altering sandbox commands.
Default missing values to `NoOverride` and omit that value when serializing to preserve compatibility with existing requests.
## Testing
Extend tests to cover override propagation, wire round-trips for all three variants, and deserialization of requests without `sandboxOverride`.
GitOrigin-RevId: 2f438cf4aef1134e3149959d14aa731682168ae5
## 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
Remove the duplicate tool metadata stored in `CachedMcpHandler` and compare incoming metadata directly with `McpHandler::tool_info()`.
Preserve complete agent plugin namespace descriptions in the handler, applying the existing 1,000-byte limit when building tool specs and search metadata. Truncation continues to respect UTF-8 character boundaries.
## Testing
Extend the agent plugin namespace description test to verify that the handler retains the full description while search output remains bounded.
GitOrigin-RevId: d0a9d5f6796143315235e658e77e059657e85f13
## Why
Guardian cannot capture sender instructions from another host when the sender thread is absent from the receiver's local runtime.
## What changed
Fall back to the authenticated thread store to reconstruct sender history without resuming the sender. Respect compaction and rollback, and label persisted evidence to indicate that newer unpersisted messages may be missing.
Limit storage reads to five seconds and capture sender context before acquiring the active-turn lock. Bind the captured evidence to the turn that accepts the delivery, allowing an existing turn to finish while the read is pending.
## Testing
Add cross-host scenarios for legacy and paginated history that verify sender evidence reaches only Guardian and excludes rolled-back permissions. Add a gated storage-read test that verifies turn completion remains unblocked and evidence is bound to the newly accepted turn.
GitOrigin-RevId: fe896f4e82fe3e32017fe4884846f3fa90a87949
## What changed
Apply `code_mode_tool_description_first` when preparing nested tool definitions for Code Mode execution and tool search. When enabled, place each tool's description before its namespace description; otherwise, preserve namespace-first ordering.
Reuse cached MCP definitions only when both the input schema budget and description-order setting match.
## Testing
Extend deferred app tool integration tests to cover both description orders with and without ranked search, including consistency between search results and `ALL_TOOLS`. Extend the MCP cache test to reject reuse when the description-order setting changes.
GitOrigin-RevId: 1e3f84d2d95c200aef21ad710d367274b2169b4b
## What changed
Register `code_mode_tool_description_first` as an under-development feature, disabled by default, for placing tool descriptions before namespace descriptions in Code Mode. Add the boolean option to the configuration schema.
GitOrigin-RevId: 5d7e2f7cef87a040f9d96b0d97c2697880c12c17
## 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
Elevated Windows sandbox tests share machine-wide accounts. Running them in the sharded core suite can consume test deadlines while shards wait for the account lock.
## What changed
Move the Windows sandbox tests into the Windows-only `windows_sandbox` integration-test binary. Update the nextest account-sharing group to select the entire binary instead of individual test names, so tests queue before their timeouts start. Keep the existing guard for coordination with other test binaries.
GitOrigin-RevId: 613925c9398b5acc8440fa34c658680f31f65c8b
## What changed
Increment `codex.agents_md.edit` for committed `apply_patch` changes to `AGENTS.md` and `AGENTS.override.md`, matching filenames case-insensitively and tagging the counter with the normalized filename.
Count additions, deletions, updates, and distinct move destinations, including changes committed before a later patch failure.
GitOrigin-RevId: bcbfa671acb37a2a24fe7e4effc9318981a22ec7
## 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
Published MCP elicitation requests could lose their response waiter without notifying the event consumer that the request was no longer answerable.
## What changed
- Add `ElicitationAbandoned` with the original server name and response token for requests published through unbounded event channels.
- Emit abandonment exactly once when a waiter is dropped, response delivery fails, or the MCP runtime shuts down.
- Close the elicitation router during shutdown, reject new requests on unbounded sources, and wait for terminal deliveries before shutdown completes. Preserve bounded sources' request-only behavior and backpressure.
## Testing
Add router tests for ordered, exactly-once abandonment, closed receivers, failed response delivery, shutdown coordination, and bounded-channel backpressure. Add a core integration scenario verifying that a pending form's abandonment precedes `ShutdownComplete`.
GitOrigin-RevId: 53fe9f4a8b32f7324be180288aa492f31f4d2057
## Why
Interrupting a turn or terminating a Code Mode cell can drop a pending dynamic tool handler before it publishes its completion. Cancellation needs to settle the call in live events and persisted history without allowing a late response into model context.
## What changed
- Let dynamic tool handlers observe cancellation and publish their terminal item before dispatch finishes. Calls cancelled while awaiting a response complete with a failed item and a cancellation error.
- Keep readiness, dispatch admission, registry lock waits, hooks, and output processing cancellable so cancellation can finish even when a hook is blocked.
- Report an aborted tool lifecycle outcome when cancellation interrupts dispatch, including before handler execution.
## Testing
Add regression tests for turn interruption with pending calls or blocked hooks, cell termination with persisted failure and late-response exclusion, cancellation before dispatch admission, and exactly one completion when a response races cancellation.
GitOrigin-RevId: 0112fc74c8652c91503ed5bbfb334ae2e26930ef
## What changed
Add `windows.allow_mxc` to configuration and its JSON schema. Setting it to `false` blocks automatic MXC selection even when `features.prefer_mxc` is enabled, and rejects explicit `windows.sandbox = "mxc"` configuration with a clear error. Omitting the setting preserves existing behavior.
## Testing
Extend configuration tests to cover disabling automatic MXC selection and rejecting explicit MXC configuration when `windows.allow_mxc = false`.
GitOrigin-RevId: bf7c0648cfcb3cc1d0dc41b9faffcb8078672780
## Why
A delayed detach or cleanup from an older realtime conversation must not close its replacement or end the replacement's history segment. Realtime start parameters can also contain credentials in text and transport endpoints, so diagnostics should avoid exposing them.
## What changed
- Add `RealtimeConversationAttach` to report the connection attempt's result through a reply channel, using the sequential start path.
- Add `RealtimeConversationDetach` to close only the matching `realtime_session_id` after earlier starts finish. Detaching an older session leaves the replacement connected.
- Emit the previous conversation's close event before starting its replacement, and prevent stale fanout cleanup from closing or clearing the replacement's context.
- Limit `ConversationStartParams` debug output to output modality, initial item count, and protocol version.
## Testing
Add coverage for attachment completion after the handshake, stale detaches, failed replacement and retry, natural-close ordering, handoff history after replacement, and debug redaction for existing-call and WebRTC transports.
GitOrigin-RevId: 23aee6f70522f0b17e6aa9349dbbcc2ea985f233
## 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
Attachment stores need to distinguish uploads from ephemeral threads, which intentionally skip durable persistence.
## What changed
Add `ephemeral` to `UploadRequest` and propagate the turn configuration through image preparation for messages, tool outputs, and history replay. Include the flag in debug output while keeping attachment bytes redacted.
## Testing
Extend the Guardian context-budget test to assert that a persistent Guardian uploads exactly one image with `ephemeral: false`. Update the attachment debug-output assertion to include the new field.
GitOrigin-RevId: 42814c514a571ed6798e4dcf79a22028ee4efc28
## Why
Agent tree shutdown previously returned a generic error without identifying which operation or thread failed, making cleanup failures difficult to diagnose.
## What changed
- Add `AgentTreeShutdown::wait_detailed()` and public report types while preserving the existing `wait()` result and error message.
- Record operation, optional thread ID, and either an abandoned teardown guard or a failed phase with a payload-free error category across session cleanup, child spawn cleanup, and resident eviction.
- Give each tree a correlation ID, log each failure, and retain up to 64 failures with a count of additional failures omitted. Record failures before releasing tree membership so all completed waiters observe the same report.
## Testing
Add unit coverage for aborted and completed teardown, cloned guard context, concurrent and repeated waiters, omitted failure counts, and report formatting without raw error payloads. Extend integration coverage for successful tree shutdown and persistence writer failures, including compatibility with `wait()`.
GitOrigin-RevId: 68784af28b63e875b00a55d78729f0cc5b01ac15
## Why
Windows temp grants could fall back to host `TEMP`/`TMP` values and bypass read-only or denied subpaths. Sandbox permissions must match the environment passed to the child process.
## What changed
- Resolve `:tmpdir` from absolute `TEMP`/`TMP` paths in the completed workload environment, preserving access modes and missing-path rules without falling back to host values.
- Deduplicate Windows environment keys case-insensitively in a deterministic order so permission resolution and the child environment select the same value.
- Use the resolved temp policy for elevated sandbox overrides across core execution, exec-server, and direct spawning.
- Launch direct-spawn sandbox wrappers with the supplied Codex executable, materializing an inner helper only when it is that executable.
## Testing
Add Windows regression coverage for temp-only writes, read-only and denied carveouts, mixed-case and duplicate environment keys, unavailable temp paths, and empty or missing write-root overrides. Exercise core execution and direct spawning, and extend exec-server RPC coverage to the elevated backend with temp values set through the environment policy.
GitOrigin-RevId: 16b8bd4702cc434fd743a08c75a3e4515780bff3
## 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
## What changed
- Use `p` to pin or unpin the selected task, with a configurable `agents.toggle_pin` binding.
- Display pinned tasks first in a `Pinned` group, preserving shared section order and applying search and status filters.
- Load pins from the shared thread section, including tasks outside the recent-task window, and refresh after pin changes. Disable pinning when the server does not support shared sections.
## Testing
Add coverage for shared pin/unpin state, paginated pin discovery and refreshing pins on reopen, shortcut dispatch and duplicate-action suppression, and pinned-group and custom-help snapshots.
GitOrigin-RevId: d1a2cab6642d059c3c8df8480b5c59a10c493936
## 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
## What changed
Remove `workspace_roots`, `current_date`, `timezone`, `network`, `personality`, and `multi_agent_mode` from `TurnContextItem` and stop recording them in rollouts. Update the precomputed protocol schema accordingly.
Make `summary` optional when reading turn context and write `"none"` as a compatibility placeholder for older readers, rather than persisting the active reasoning-summary setting.
## Testing
Update protocol tests to cover omitted `summary` fields and compatibility-placeholder serialization. Extend compaction tests to verify that model requests retain the updated reasoning-summary setting after compaction while the rollout checkpoint records the placeholder.
GitOrigin-RevId: d49eabaa1b340be1d79f7f09115281a307ea8a64
## 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
## Why
Changing the incremental tools setting on resume should not move tool declarations and base instructions within an existing context window.
## What changed
- Determine the current window's tool declaration mode from its history, and apply the incremental tools setting when building a new window after compaction or a context reset.
- Use that mode consistently for sampling, remote compaction, startup prewarm, prompt debugging, and Guardian input budgeting.
- Preserve tool declarations alongside their comparison baseline in full-history agent forks, including compacted histories; remove them together when rebuilding context.
## Testing
Add request snapshots covering legacy resume, migration after remote compaction or a context reset, disabling incremental tools, and tool updates after restart. Extend agent fork and WebSocket startup prewarm tests to cover retained declarations and incremental tools.
GitOrigin-RevId: 7c46849a1788027a8435082e4d1f7e7f48d2700c
## Why
Submission diagnostics need approval and turn metadata without logging user input, tool responses, commands, paths, or instruction payloads.
## What changed
- Log thread and submission IDs, operation kind, and parent/root turn IDs as explicit fields.
- Give `Op` and `ThreadSettingsOverrides` selective `Debug` output that retains identifiers, approval decisions, and policy categories while omitting payloads.
- Preserve Guardian review identifiers and status when logging approval of a denied-action retry.
## Testing
Add an app-server integration test that verifies command approval, Guardian review, and turn policy metadata reach SQLite-backed diagnostic logs with `RUST_LOG=off`.
GitOrigin-RevId: 308acb7b70e4849cf31514b11e4d9b46eaf6a09b
## 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 `model` and `reasoningEffort` to `subAgentActivity` items for multi-agent v2 spawns. Capture startup settings before the child begins its turn and resolve the reported effort against model metadata, including model defaults, while preserving the child's configured effort.
Carry these fields through live notifications, persisted activity, thread history, and legacy rollout migration. Update the JSON schemas and generated TypeScript and Python types. Older records and other activity kinds retain null values.
## Testing
Add coverage for resolved spawn settings matching the child's request across legacy and paginated history, preserving configured effort, forwarding metadata through events and history, and reading and migrating older records without the new fields.
GitOrigin-RevId: a9e4241ae21bb8db1ead293f78ffba8257cca0ae
Use `TurnEnvironmentRequests` and the executor environment's `request()` in the MCP turn metadata test to match `ThreadSettingsOverrides`. Allow additional fields when matching `TurnInputSubmission::Started` in the pending input test.
GitOrigin-RevId: 6f7f7c60511d999274079f715ba2a68163e69caf
## Why
WebSocket rate-limit and overload errors ignored `Retry-After` advice and ended turns even when the server supplied a retry delay.
## What changed
Extract retry advice from nested `error.headers`, falling back to top-level `headers` when nested advice is missing or invalid. Use the shared HTTP header validation and retry-delay parser, and preserve the delay when mapping WebSocket errors.
## Testing
Add coverage for nested-header precedence, malformed headers, HTTP header validation, and recovery after an advised rate limit. Verify that overloads retry only while advice is present, without falling back to HTTP, and that headerless rate limits, usage limits, and `flex_unavailable` errors remain terminal.
GitOrigin-RevId: 61add0c36197e10402d6d3c325332aac72a5a521
## Why
An interrupt or turn replacement can invalidate a pending-work wakeup while its turn context is being constructed. Task startup could then recreate a turn whose reservation was no longer active.
## What changed
- Recheck that the wakeup still owns the active turn reservation immediately before calling `start_task`, and return if it does not.
- Allow the remote-control re-enrollment test up to 45 seconds for the connection following reconnect backoff.
## Testing
Add a regression test that pauses wakeup context construction, processes an interrupt, and then resumes construction. It verifies that no additional turn starts and only the initial model request is sent.
GitOrigin-RevId: c857fdd9f0fac3790d35a95a1f21a6d41977bb29
## 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
## What changed
Add the turn's `root_turn_id` to `_codex_apps` request metadata for host-owned Apps MCP calls. Remove any tool-supplied value before populating it from turn metadata, and omit the field for user-configured or extension-owned Apps servers.
## Testing
Extend unit coverage to verify that host-owned Apps calls replace an untrusted `root_turn_id` and user-configured Apps calls omit it. Update integration assertions for default and explicitly supplied root turn IDs, including approval flows, and verify that extension-owned calls omit the field.
GitOrigin-RevId: 754a642c2fff36a866b8cffa9fb3e161f232de08
## Why
Queue-only agent mail can wake a sleeping session without starting a new task. The wake turn needs to retain the previous turn's attribution so delegated work reports completion to the initiating agent, including after a reload.
## What changed
Capture the previous turn's attribution while reserving the pending-work turn. Reuse its trigger, parent and root turn IDs, and initiating agent path for queue-only wakes. Mail that explicitly starts a new task continues to supply its own attribution.
## Testing
Extend regression coverage for live and reloaded sleep wakes, delegated and unknown attribution, settings changes while asleep, and subsequent task-triggering mail. Verify that a reloaded sleeping worker routes completion to the initiating turn.
GitOrigin-RevId: 28e38474028bdbf35a0538c1202165f056bb3dc3
## 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
Recovering an interrupted turn replaced its original trigger with `retry` and restored only its root lineage from model context. Turns suspended before that context was written could lose their attribution entirely.
## What changed
- Persist regular-turn attribution in `TurnStartedEvent` and compaction resume metadata, including the trigger, parent and root turn IDs, and initiating agent path.
- Restore matching attribution during recovery, keep unknown triggers absent, and retain the model-context root fallback for older records.
- Reconstruct attribution from surviving turns across rollback and late completion or abort events, and clear inherited attribution when spawning a forked agent.
## Testing
Add coverage for repeated cold recovery, suspension before context persistence, legacy rollouts, fresh attribution on subsequent turns, compaction checkpoints, rollback, and late terminal events.
GitOrigin-RevId: 85b5763e8fbd48a1ea2c07cfda8196e63c2cd33a
## 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
Spawn failures can share an error kind and message despite different causes, such as execution and residency capacity limits. Telemetry needs enough detail to distinguish these failures without using error messages or correlation IDs as metric labels.
## What changed
- Add `AgentErrorContext` annotations for capacity limits, registry rejections, runtime availability, and spawn stages. Preserve the first annotation so outer stages retain the more precise failure origin.
- Add bounded `detail` and `error_kind` labels to spawn failure metrics, using `unknown` when no context is available.
- Emit spawn failure trace events with these classifications and the call and turn IDs for both multi-agent versions.
## Testing
Add tests for distinct capacity and registry failure contexts, preservation of manager, fork, and shutdown errors, and metric aggregation across different error messages and correlation IDs. Verify that annotations preserve existing error kinds and user-visible messages.
GitOrigin-RevId: 5bbe3d32f6ce408622f38e559fddeab05b8ccb65
## What changed
Add `codex.shell_snapshot.command` and `codex.shell_snapshot.wait_ms` metrics for eligible command preparations in the unified exec runtime and exec server. Tag observations with snapshot version, availability state, and whether replay was selected (`used`) or normal shell startup was used (`fallback`). Exclude background prewarming from command observations; `used` measures replay selection, not successful restoration or command completion.
## Testing
Extend snapshot retry tests to verify command counts and wait observations across fallback and recovery, excluding prewarm captures. Extend credential-broker approval tests to verify one `protected` snapshot observation for login-shell commands.
GitOrigin-RevId: d3d9f370b6bbba6dfc930a44044ce09373841799
Refresh the ranked tool catalog and partial-answer fork snapshots to reflect instructions requiring `fork_turns: "none"` when overriding the model or reasoning effort. Update the affected collaboration tool and message hashes.
GitOrigin-RevId: 5c3cbdd734f57eaefee0b0412e555e3882b1472e
## What changed
Carry `multi_agent_version` from the turn context through resolved configuration facts into turn analytics events.
## Testing
Extend the turn event serialization test to assert that `MultiAgentVersion::V2` is emitted as `"v2"` in `multi_agent_version`.
GitOrigin-RevId: f3e8c98588926d41a18c3db9aa229677e68cf5c1
## What changed
Record elapsed time for completed `wait_agent` waits in `codex.multi_agent.wait.duration_ms`, with an `outcome` tag of `mailbox`, `steered`, or `timed_out`. Exclude dropped waits because they have no observed outcome.
GitOrigin-RevId: 6378b98bfadab69d47aa2e9c93fa9d720f9cd0ef
## What changed
Increment `codex.multi_agent.result_delivery` when sending a terminal child result to its parent, with `outcome=queued` for queue acceptance and `outcome=failed` for delivery errors.
GitOrigin-RevId: 7571f66c2c2d2baea1a54dce3741f6393e809b66
## What changed
- Limit multi-agent V2 `fork_turns` guidance to `all` and `none`. Accept legacy positive integer strings as full-history forks instead of truncating parent history.
- Remove partial-history fork handling and telemetry, and direct model override usage to `fork_turns: "none"`.
- Strip inherited `multi_agent.role_instructions` and `multi_agent.usage_hint` content by kind, including persisted hints whose wording predates the current bundled instructions.
## Testing
Update regression coverage for legacy `"1"` and `"3"` values inheriting full history, invalid and zero values being rejected, and stale parent hints being removed from compacted history with both marked and unmarked instructions.
GitOrigin-RevId: 8f6017dc66ad8deefd7745399ef76e1bb1435bb2
## Why
Messages with the `partial_answer` phase contain answer text without declaring a terminal answer. They should remain searchable and speakable without being treated as final messages.
## What changed
- Preserve explicit `partial_answer` phases in streamed and completed realtime handoffs, bypassing legacy channel-prefix parsing and routing them to the `speakable` channel.
- Treat partial answers as nonterminal in V1 handoffs and omit the final-message prefix.
- Include partial answers in thread occurrence searches and normalize them to the final conversation channel in rollout traces.
## Testing
Extend coverage for realtime phase routing, streamed and completed handoffs, partial-answer search results, and rollout normalization. Verify that turn summaries still exclude nonterminal messages.
GitOrigin-RevId: aa183da783f6e7e0b78ddd51073cba533297e121
## Why
Fast mode previously gated both Fast and Ultra Fast, preventing policies from allowing one while disabling the other.
## What changed
- Add the default-enabled `features.ultrafast_mode` flag and enforce it independently of `features.fast_mode` in service-tier selection, requests, and agent prewarming.
- Filter TUI service-tier commands and selections by the corresponding policy and model catalog support.
- Report `supportsIndependentSpeedModes: true` from `configRequirements/read` and update the protocol schemas and generated bindings. Retain the shared Fast gate when connecting to older servers that omit this capability.
- Preserve legacy cloud speed denials by translating `rbac-fast-mode` fragments with `fast_mode = false` into a denial of both modes, while retaining higher-priority enterprise overrides.
## Testing
Add coverage for all four Fast/Ultra Fast policy combinations in requirements responses and request routing, agent prewarm inheritance, TUI command visibility and saved selections, and legacy cloud denial normalization and override precedence.
GitOrigin-RevId: 147e08524c4b228ea9d46b25a9f8aa64c359e169
## 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
## Why
Assistant answer text may be followed by more output or tools. A distinct `partial_answer` phase lets callers represent this separately from commentary and a terminal `final_answer`.
## What changed
- Add `MessagePhase::PartialAnswer` and expose `partial_answer` in the app-server schemas and generated TypeScript and Python types.
- Keep the TUI working indicator visible after partial answers and exclude them from the thread history's final-answer summary field.
- Route partial answers to the speakable channel in realtime V3 BEM-tag mode.
## Testing
Add coverage for phase preservation through serialization, input-message conversion, and SSE item start/completion events. Extend TUI snapshot coverage to verify that partial answers keep the working indicator visible while final answers hide it.
GitOrigin-RevId: 1ae3ad9264b6e36ae1cbe6b93df3d345ab4460e6
pakrym-oai