## What changed
Tag `codex.tools.incremental_updates` counters with the qualified tool name alongside the action. Continue excluding initial catalogs and namespace headers, while counting each removed namespace member.
Add `codex.tools.spec_description_bytes` to measure UTF-8 description bytes when an existing tool definition is replaced. Skip definitions without descriptions and use logarithmic histogram boundaries up to 1 MiB.
## Testing
Extend namespace transition tests to check per-tool counts and description sizes. Add scenario assertions for replacement metrics with incremental tool updates and their absence on the non-incremental request path.
GitOrigin-RevId: e20e6d81f21a867b285df1f0da005c2806dd03c6
## Why
With granular sandbox approvals disabled, `write_stdin` rejected input to terminals retaining additional permissions even when those permissions were still granted.
## What changed
Let input reach approval review when the terminal's retained permissions match active grants for its environment. Require identical filesystem grants, including entry order, and an active network grant when retained permissions enable network access. Each input still requires review.
Keep rejecting input when retained authority is no longer covered or the approval policy changes to `Never`.
## Testing
Add regression coverage for user and Guardian review, turn grant expiry, session grants, and switching to `Never`. Cover filesystem restrictions, protected metadata, symlinks, and ordered denials, and verify that rejected input never reaches the terminal.
GitOrigin-RevId: 9abf7da8d03b1526d26ca2a718e36349a255330b
## Why
Environment tool availability and selectors should remain stable as selected environments become ready.
## What changed
- Keep configured environment tools advertised even when no execution environment is ready, and derive `environment_id` selectors from all selected environments.
- Return guidance to wait when an environment is unavailable, while preserving errors for unknown environment IDs. Require a usable primary environment for `write_stdin`.
- Always include `shell` and `login` in the `exec_command` schema and mark `stable_environment_tools` as removed.
## Testing
Update integration tests to expect environment tools with empty or starting environments, and remove explicit feature opt-ins from affected scenarios.
GitOrigin-RevId: 1590c1b5be16a39e4a370663c552b881602545b5
## Why
Advancing the test clock expires the review, but command cancellation and output drainage still run asynchronously. The model can poll before the final timeout failure is available.
## What changed
Hold the initial tool result until the command emits `ExecCommandEnd`, with a bounded wait that also catches unexpected approval requests or turn completion. Only request a poll when the initial result reports a running process, and accept the timeout output from either `exec_command` or `write_stdin`.
Keep the assertions that the model receives the timeout explanation without a user approval prompt or a misleading user-rejection message.
GitOrigin-RevId: 219a1579dce35caf8f0d45b1d92a7343ec1a8935
## Why
Coordinated MCP OAuth refresh must stop retrying a definitively rejected refresh token, including after the runtime is rebuilt.
## What changed
Remove the rejected refresh token while preserving the access token and credential record. Compare stored credentials under the appropriate locks before writing so a replacement login is preserved, and update file entries using their existing keys.
Keep rejection handling alive through caller cancellation and prevent reuse within the runtime even if persistence fails. For ordinary direct-keyring credentials shared across `CODEX_HOME` directories, retire the token only in the current runtime because locking does not span those directories. Report persistence failures without exposing backend diagnostics.
## Testing
Add coverage for reauthentication after runtime rebuild, legacy file keys, cancellation with a concurrent credential replacement, keyring scope, and persistence failures with diagnostic redaction.
GitOrigin-RevId: a6e602ca2e2893ed711d853becc45142d9575fab
## Why
PowerShell safety checks can mistake a literal `start` argument for a URL-launch command, or combine a process launch with a URL from a separate command.
## What changed
Classify independently parsed literal PowerShell commands separately so commands such as `Write-Output start 'https://example.com'` do not trigger URL-launch checks. Retain conservative checks for pipelines, script state, executable strings, and shell or terminal wrappers, while continuing to detect actual URL launches and destructive commands.
## Testing
Add policy regression coverage for literal arguments, separate commands, URL launches, wrappers, and destructive commands, plus a Windows integration test covering execution and policy rejection.
GitOrigin-RevId: 2878aa86bc36b44c60230cc1de3430922b28b81a
## Why
Thread stores need a way to reuse history and writer state loaded while preparing a resume, rather than loading them again during session startup.
## What changed
- Add an opaque, single-use `ThreadStoreResumePreparation` and an optional preparation in `StartThreadOptions`.
- Pass preparation through session startup to `ThreadStore::resume_thread_with_preparation`, which defaults to an unsupported-operation error.
- Reject preparation for ephemeral threads or threads without resumed history. Continue using `resume_thread` when no preparation is supplied.
## Testing
Add a regression test verifying that supplied preparation selects the prepared store path and propagates its unsupported-operation error instead of falling back to ordinary resume.
GitOrigin-RevId: 26537d9b83443bd56341d6afc713f32b999dc67c
## Why
A remote primary environment could supply its working directory and workspace roots to host plugins and MCP processes, breaking relative MCP executable resolution and applying the wrong workspace permissions.
## What changed
- Build host configuration from the local environment, falling back to the session's host working directory and runtime workspace roots when no local environment is selected. Preserve explicitly empty local roots.
- Use the same host configuration for MCP startup and refresh, and refresh MCP state when runtime workspace roots change.
- Keep repository skill discovery paired with the primary executor's working directory and filesystem.
- Box skill warmup and turn context construction futures to reduce enclosing future sizes.
## Testing
Extend the MCP integration test to cover a remote primary with populated, empty, or absent local roots; relative executable resolution before and after refresh; workspace-root revocation; and remote repository skill discovery.
GitOrigin-RevId: 21a73c90507b55fd94261e7bf348695ff8466a24
## Why
Compaction could record partial output before the response completed, leaving failed summaries in conversation history and persisted rollouts.
## What changed
Buffer compaction output until `response.completed` so failed or incomplete attempts leave no partial output in history. Record successful output before the response completion notification, preserving its compaction metadata.
## Testing
Add regression coverage for preserving messages, tool results, and token usage after a disconnected compaction stream, including after restart. Verify incomplete compaction output is excluded from subsequent requests and successful output remains observable and persisted.
GitOrigin-RevId: 8651200b2aae616000c55c1ed63283f3e2c1b8d5
## Why
Standalone thread settings updates cleared the running turn's continuation lineage, preventing recovery after a daemon restart.
## What changed
Preserve continuation lineage while a task is registered. Continue invalidating pending continuations for idle, reserved, and finishing turns, and record started-turn lineage atomically with task registration.
## Testing
Extend settings invalidation coverage to idle, reserved, and finishing turns. Exercise an in-flight reasoning effort update before compaction, then verify cold resume preserves the turn's frozen settings and allows continuation. Wait for thread idle before testing idle continuation.
GitOrigin-RevId: d7c316af6a4c871790bb57f0af9892bb30871ac8
## Why
Incremental-tool windows recorded base instructions only at setup, so a catalog refresh for the same model could leave active instructions stale. Instruction changes need to reach the model without rewriting the existing history prefix.
## What changed
- Track model identity and instruction content independently, appending a `model_instructions` developer message when either changes. Explicitly mark replacement or removal of base instructions, and avoid repeating unchanged updates.
- Start new windows after compaction with the latest model instructions while preserving custom base instructions.
- Preserve the recorded window base during local compaction retries, including empty instructions, and rebuild current model instructions when reconstructing child context.
## Testing
Add integration tests and request snapshots for catalog refreshes, instruction removal, model switches, compaction, restart, and forks. Extend regression coverage for legacy snapshots and local compaction retries.
GitOrigin-RevId: eeca69067b4d9cd91c817732d79b4d5c1faa18b9
## Why
Message roles and content classifications do not identify who supplied each context part. Source attribution needs to survive prompt assembly and history truncation, including messages that combine text from different producers.
## What changed
- Add per-part `ContentItemMetadata` for user input, developer instructions, `AGENTS.md`, skills, harness context, command hooks, and tool context with optional callable namespaces.
- Carry attribution alongside content and classifications through contextual fragments, extension prompts, hook output, and agent messages. Keep tool-provided context-window hints separate from harness text.
- Preserve the source of retained text slices during compaction and attribute generated truncation notices to the harness. Default missing historical attribution to unknown.
- Attribute host MCP calls using cached tool namespaces only when catalog revisions remain stable, without starting servers or refreshing catalogs for attribution.
- Send the new metadata to Responses Lite and strip it from requests to endpoints that do not support it.
## Testing
Extend compaction tests to cover mixed sources, missing or extra metadata entries, and discarded media. Update Responses Lite request assertions to verify endpoint-specific attribution handling.
GitOrigin-RevId: b0ebc929b7c60f3ec49d1affbf897312d63edcc8
## What changed
- Launch background compaction at eligible pre-turn, mid-turn, and post-turn checkpoints when `AsyncCompaction` is enabled, capturing the current world state and client routing state.
- Adopt ready results at compaction checkpoints while preserving newer messages, tool outputs, and world-state updates. Continue normally if an optional result is rejected.
- Run one foreground compaction if an adopted result still exceeds the context limit.
- Prevent cancelled turns from launching new background work while preserving already-running work for later reuse.
## Testing
Add unit and scenario coverage for stale history and account changes, cancellation, pending-result reuse and fallback, retained tool outputs, compaction event pairing, and token usage accounting. Add a context snapshot covering a collaboration-mode change while compaction runs.
GitOrigin-RevId: 04ac028d9fe2e3ea64aacaaeb351c3c776cf3940
## Why
Assistant messages delivered during a pending Guardian review can change its evidence. Previously, these context changes aborted the review instead of triggering a fresh assessment.
## What changed
Treat changes to local or root review context as stale authorization so Guardian retries with updated evidence. Cancellation and history resets still abort the review.
## Testing
Extend local and worker delivery tests to cover refreshed allow and deny decisions, verify that the new review includes the delivered message, and ensure commands execute exactly once after approval and never on stale approval or denial.
GitOrigin-RevId: 019205bee6d3f4e8cf6b9268f72bbc5db6b3899e
## What changed
Add optional `voiceSessionId` to realtime start parameters and forward it as the `voice-session-id` header for WebSocket, WebRTC, and existing-call transports. Keep this client-generated voice session identifier distinct from `realtimeSessionId`, which uses `x-session-id`.
## Testing
Extend serialization tests and add coverage for distinct session ID headers, WebRTC request forwarding, and existing-call handshake forwarding.
GitOrigin-RevId: cb558dbb9d438f2d34e281199a7e81fe5d33b879
## What changed
- Return qualified skill names such as `team:deploy` and parsed `dependencies` and `policy` instead of a separate namespace and raw metadata file. Share `agents/openai.yaml` parsing and validation between skill loaders and executor discovery.
- Include each standalone skill's search-root ID and path in `discoveryRoot`, while accepting responses from older executors that omit it.
- Add plugin `displayName`, falling back to the manifest name or installation directory.
- Materialize inline MCP declarations in `mcpConfig` with the manifest as their source path, and report incomplete discovery when declared MCP or Apps configuration files have no returned contents.
## Testing
Add coverage for JSON round trips, omitted `discoveryRoot`, optional and invalid skill metadata, qualified names, display-name fallbacks, and inline MCP configuration. Verify standalone search roots survive cached discovery and sandboxed RPC responses.
GitOrigin-RevId: 4124972444ad7c2fb8c6418acbf9a589d797fad2
## What changed
When the remote global catalog is active, let a cached `visualize@openai-curated-remote` install supersede `visualize@openai-bundled`, matching the existing Sites behavior. A disabled remote install also suppresses the bundled plugin; a missing remote bundle preserves the bundled fallback.
## Testing
Extend the agent-turn compatibility tests to cover Visualize with enabled, disabled, and missing remote bundles, asserting which skills appear in the developer prompt.
GitOrigin-RevId: 7d0cc564189249e597d5bd29b5800353d89a9060
## What changed
- Add the disabled-by-default `executor_capability_discovery_v2` feature to acquire `capabilities/discoverV2` inventories from supporting remote executors using each selected environment's working directory and sandbox.
- Share snapshots with MCP and world-state contributors and skill providers without activating discovered plugins or publishing discovered skills to the model.
- Cache inventories by environment instance, executor session, working directory, and sandbox. Coalesce concurrent requests, refresh the cache at turn start, retry transient failures, and refresh MCP projections after recovery.
- Resolve the system skills root in the executor and pass it explicitly to capability location discovery.
## Testing
Add coverage for feature gating, unsupported executors, inert inventories, cache reuse and eviction, turn refreshes, failure recovery, executor replacement, and system skill locations.
GitOrigin-RevId: 1bdca28fa7f17622b27e2713ab3dcc0c13426889
## What changed
Use `conversation` when neither a local `async_classifier_mode` override nor a model default specifies a mode. Keep `snapshot` available as an explicit override and update the configuration documentation and schema to describe the new fallback.
## Testing
Expand configuration tests to cover all local override and model default combinations. Update app-server approval tests to exercise conversation mode without an explicit override, and explicitly select snapshot mode in tests that depend on it.
GitOrigin-RevId: a62479a3f6454bf28d589373a236d8b0ab5023b9
## What changed
- Default `features.api_key_cyber_access_programs` to `true` and allow `codex exec` to select Daybreak with an OpenAI API key. Select the advertised standard program when `daybreak=false`, while respecting explicit feature opt-outs.
- Resolve API-key eligibility for TUI background turns from the target thread's feature settings, including project opt-outs. Omit access-program overrides when the server cannot report those settings.
- Preserve automatic server treatment for unlisted models and missing or empty Cyber program metadata in exec and TUI. Continue rejecting Daybreak when a nonempty program list does not offer it.
## Testing
Update regression coverage for API-key Daybreak selection, the off override, explicit opt-outs, resumed sessions, target-thread settings, and missing model metadata.
GitOrigin-RevId: f3cf7bd95a2754d4b4281bc70b18c7da4b177552
## Why
MCP servers must forward sandbox policy unchanged to `codex sandbox --sandbox-state-json`, while interpreting launcher information to find the Codex CLI. Keep those contracts separate so consumers can preserve unknown policy fields.
## What changed
- Accept the experimental `codex/sandbox-state` capability alongside the deprecated `codex/sandbox-state-meta` capability, and send identical policy values under both `_meta` keys.
- Move `codexExecutable` out of the policy into `codex/sandbox-launcher`, supplied only when a verified CLI path is available for a local stdio server.
- Replace stale sandbox metadata while retaining unrelated entries, and remove stale launcher metadata when no launcher is available.
- Document the metadata contract and how servers should forward policy and retain authority for long-lived subprocesses.
## Testing
Update unit and integration coverage for policy serialization, identical state aliases, launcher availability across execution environments, and stale metadata replacement.
GitOrigin-RevId: e544c06e6e023953b1fc8069b7b1affa065262d1
## Why
Canceled classifier requests need bounded cleanup that preserves received token usage and returns only safe WebSocket connections to the pool.
## What changed
- Own classifier response streams and connection leases together, interrupting dropped responses with a one-second cleanup deadline.
- Require a matching interruption acknowledgement and response completion before reusing a canceled response's socket. Retire sockets on rejection, invalid acknowledgements, or timeout while preserving any received completion and token usage.
- Skip requests canceled before dispatch and return their unused sockets to the pool.
- Distinguish cancellation from ordinary steering, which continues draining without requiring an interruption acknowledgement.
## Testing
Add regression coverage for cancellation, acknowledgement ordering and failures, cleanup timeouts, socket reuse, and token accounting under backpressure. Extend steering tests to cover rejected and missing acknowledgements.
GitOrigin-RevId: c4e7aac49d36cea2c2d0e9f2ba5f6147f67471dd
## Why
Encrypted compaction payloads can include sampled-token replay caches that increase their size roughly threefold. Budgeting them as ordinary text can reject checkpoints that fit the model context budget.
## What changed
Use a shared estimate of one token per twelve ciphertext bytes, rounded up, for encrypted `Compaction` and `ContextCompaction` items in history and Guardian context budgeting. Guardian continues to count framing and metadata separately.
Check parent compactions against the configured token budget and a separate hard wire-size limit. Preserve the complete encrypted checkpoint when it fits. The token estimate remains a heuristic and can underestimate legacy checkpoints without replay caches.
## Testing
Add coverage for token-estimate rounding, parent compaction token and wire-size limits, and reviewer continuation with a cached compaction preserved intact.
GitOrigin-RevId: cc18ca29802491865167eef992830efcf93d97da
## Why
Prediction forks need to retain their parent's context even when it exceeds the automatic compaction threshold. Compaction or context resets can otherwise replace the history used for the prediction.
## What changed
- Apply a thread-local `AutoCompactionDisabled` policy to experimental prediction forks without changing model or skill budgets.
- Skip automatic compaction before, during, and after turns, including context-limit recovery, and suppress new token-budget reminders.
- Reject `new_context` requests for these threads and report context-limit failures without compacting their history.
## Testing
Add regression tests for legacy and paginated prediction forks across compaction thresholds, unchanged parent compaction and skill/tool inputs, context-limit failures, and rejected context resets. Add a request-history snapshot verifying inherited context and reminders survive without compaction or additional reminders after a tool call.
GitOrigin-RevId: 7df374287f4142f776981bb6c22e5caa564d74a5
## Why
A transient Apps MCP startup failure can remove cached tools that the model has already discovered, preventing a later Code Mode invocation from using them.
## What changed
Keep cached Apps tools in the model's tool catalog while startup recovery runs. Let invocation readiness start or join a shared retry before acquiring the tool execution lock, while tool discovery remains nonblocking. Keep recovery running if a waiting invocation is cancelled.
## Testing
Extend connection-manager tests to cover cached tool bindings and shared recovery. Add a Code Mode regression test that discovers a cached Calendar tool, invokes it after startup fails, and verifies that it succeeds after recovery while unrelated tools remain able to execute.
GitOrigin-RevId: e888501a1050884a50a473e71b893cf6672fe256
## Why
Terminal `response.incomplete` errors discard reported token usage. Counting that usage as a new context baseline can also double-count input and trigger unnecessary compaction on the next turn.
## What changed
- Carry the response ID and valid reported usage with incomplete-response errors.
- Record usage for sampling and foreground compaction in cumulative totals, rollout records, budgets, and token-usage contributors without replacing the context baseline. Preserve the original terminal error, including when accounting exhausts the budget or cancellation races the error.
- Charge incomplete background compaction requests to the rollout budget without publishing foreground token usage.
- Ignore missing or malformed usage rather than estimating it.
## Testing
Extend coverage for SSE and WebSocket incomplete responses, rollout usage records, compaction accounting, deferred token-count events, and token-usage contributors. Add regressions for unnecessary compaction on the next turn and background compaction publishing foreground usage.
GitOrigin-RevId: bf1ee6df3912052ab7c19e1c6af8ad3dc4b07675
## Why
Cancellation after initial input admission could leave a child registered even though the spawn caller had not received its result.
## What changed
Resolve the child's status and configuration before committing reservations and releasing provisional ownership. This keeps cancellation cleanup active through the final awaits and lets the spawn result return without yielding after commitment. Cancellation after the result returns does not retract the accepted child.
## Testing
Add a regression test that cancels spawn during the final status lookup after input admission and verifies that the child is unregistered, terminated, and unloaded, and that shutdown completes. Extend the provisional-child cancellation test to cover both native V1 and V2 callers.
GitOrigin-RevId: 028b873ad4c1fac2c4b5d1dc823b4561ff19e6bf
## Why
Non-parallel tool calls can acquire their lock in either order, making the shared board scenario's `last_message_id` snapshot nondeterministic.
## What changed
Send each `collaboration.post` call in a separate mocked response to order the writes before snapshotting. Update the `board_connections` snapshot and expected request count from 15 to 17 to reflect the additional responses.
GitOrigin-RevId: a290a01f5071a2081d4d0b1531b1b31bfbb8a6e6
## What changed
Emit `codex.guardian.review.truncation` counts and `codex.guardian.review.truncation.bytes` histograms after successful input finalization. Aggregate observations across reduction stages by component and disposition (`truncated` or `omitted`), recording original, retained, and omitted byte totals. Exclude feasibility checks and failed retries from loss telemetry.
Keep blocking command-hook cancellation fixtures in the local environment and use double quotes for the Python command.
## Testing
Add metric-export tests covering aggregation across multiple reductions, separate truncation and omission totals, no loss metrics for rejected inputs, and no duplicate reporting on repeated finalization.
GitOrigin-RevId: 69182fc7afe230be69dd2469caedb5ae4494947b
## Why
Remote process exit can arrive before the final output, and inherited pipes can keep the output stream open after exit. Removing the session at exit can lose output that should remain available to `write_stdin` polls.
## What changed
- Retain remote sessions with open or unread output after exit, including early exits and cancelled initial collection.
- Collect pending output when `write_stdin` races with exit, skipping stdin writes once remote exit is known.
- After initial collection finishes and the process exits, allow a five-second grace period before a final background read. Respect active polling deadlines and keep later polls available while that read recovers retained output.
- Let explicit termination stop output collection even when the process has already exited, and install the exit watcher before cancellable cleanup.
## Testing
Extend remote process event tests to cover output arriving after the initial yield, polling during a delayed final read, active polls exceeding the background grace period, resumable cancellation, and termination before the initial yield.
GitOrigin-RevId: b1671fad8b61a2cdecf7cf9fdf92e57c028c7af8
## What changed
Add `features.multi_agent_v2.disable_native_tools` to hide native multi-agent tools while keeping the V2 runtime and its instructions enabled for host-provided tools. The option defaults to `false`, preserving existing tool exposure.
## Testing
Extend configuration parsing tests for the new option and parameterize the multi-agent catalog scenario to cover both settings. Add a snapshot showing native tools are absent while the V2 runtime and instructions remain enabled.
GitOrigin-RevId: 21a53584d2395bb678813c876a8b7927bea61c90
## Why
Inputs arriving during turn finalization could be queued after the final batch had already been drained, or recorded ahead of that batch.
## What changed
Mark active turns as finishing before draining pending input. Reject injection into finishing turns and make late client responses and notifications wait until the final batch is recorded before appending to history. Continue accepting input into turns reserved but not yet started.
## Testing
Extend the task-completion test to block final recording, verify that input admission is closed, and confirm that a late notification is recorded after queued input while preserving the notification truncation budget. Strengthen the retained-tool-output scenario to assert tool output names and ordering.
GitOrigin-RevId: a57e44bd974e60e134183dab989795e2c3538596
## Why
Incomplete responses such as `max_output_tokens` were classified as stream errors, allowing retries and compaction model fallback after the response had hit its output limit.
## What changed
Introduce `ResponseIncomplete` errors that preserve the server-provided reason and stop stream processing immediately. Make these errors non-retryable and stop compaction without falling back to the selected model. Record incomplete responses separately in sampler failure metrics.
## Testing
Add regression tests that verify incomplete responses surface a terminal error without retries over SSE and WebSocket, and that compaction stops without retrying or switching models for both local and remote compaction.
GitOrigin-RevId: 6e107d441b9bf03fa47ea47b88eeb94b71a9f729
## Why
Local message boards were scoped to an agent tree. Independently created Codex runtimes need a way to share a board while receiving different access permissions.
## What changed
- Add `LocalBoard` and `LocalBoardConnection` so hosts can supply read-only or read-write access through `thread_extension_init`, including for isolated, ephemeral runtimes.
- Allow read-only connections to read and manage their own subscriptions; reject posting, replying, channel creation, and changes to another agent's subscriptions. Expose effective permissions in channel discovery.
- Use unique runtime paths and require matching board IDs and canonical database paths when resolving agents or delivering notifications.
- Document explicit extension installation and connection setup for new runtimes, cold resumes, and forks.
## Testing
Add a scenario and context snapshot covering an independent writer and isolated Guardian sharing a board through a symlink alias, read-only permission denials, subscription and explicit notifications, and rejection of notifications to an unconnected runtime before a post is written.
GitOrigin-RevId: f92410c3a5c6a46920c3e0e71849c85dc83d9c31
## Why
With `multi_agent_v2.disable_direct_message` enabled, an unavailable agent message board could cause tool router construction to reject the turn.
## What changed
Remove the requirement that the router expose the board's `post` tool. Unavailable board calls return an unsupported-call error to the model, allowing the turn to continue.
## Testing
Update scenario coverage for a disabled board feature, legacy agents, and ephemeral sessions. Assert that unavailable board calls return an error to the model, that `post`, `send_message`, and `followup_task` are not advertised, and that no board database is created.
GitOrigin-RevId: cb9571459c128d84c3c96f185e70c404e0463473
## What changed
Add a unified execution test where `exec_command` yields a session and a subsequent `write_stdin` poll completes after the remote process exits while its output stream remains open. Verify that the poll returns the delayed output and exit code, emits the command completion event, and removes the background session without issuing a `process/read` request.
GitOrigin-RevId: 3a316eb9f6b29682da81a2ecbdda52f659f4b792
## Why
A remote process can exit while its output stream remains open, leaving the exit watcher waiting and delaying `ExecCommandEnd` even after output collection finishes.
## What changed
Cancel the process output token after final collection or polling, on one-shot cancellation, and after confirmed termination. This releases the exit watcher while allowing delayed output to be collected before the final poll completes.
## Testing
Add remote process event tests for output streams that remain open at the collection deadline, during interruption, and during explicit termination. Assert that `ExecCommandEnd` preserves the exit code and aggregated output, background terminals are cleared, and interruption and termination require no extra `process/read` requests.
GitOrigin-RevId: 8346e5ce446280915b6e2ffa362fcfd79280bfff
## Why
Cold resume can replace saved unnamed permissions with current configuration defaults or recover an executor's permissions from turn context. A first-turn context can also predate an acknowledged settings update.
## What changed
- Restore eligible unnamed permission profiles from settings snapshots owned by the resumed thread, honoring explicit caller overrides and current managed requirements.
- Use owned snapshots as the authority for named permission profiles and reapply workspace permissions for the resumed workspace roots.
- Persist a thread-owned settings checkpoint after the first turn's context, serialized with settings updates so older checkpoints cannot supersede newer settings.
## Testing
Extend regression coverage for cold resume with changed defaults, managed permission restrictions, workspace-root overrides, foreign snapshots, and settings updates during first-turn processing.
GitOrigin-RevId: e411d9fd3d586a4162498c9c77c4184459071bd1
## Why
Client-supplied tool outputs can carry task instructions. Even when marked with `retain: true`, these instructions could be trimmed before compaction and disappear from the compacted history.
## What changed
Add the disabled-by-default `retain_client_tool_outputs` feature to honor retention for explicitly marked, named `function_call_output` items without a `call_id`.
- Preserve eligible outputs in remote compaction v2 and when starting a new context window, keeping their original role.
- Stop emergency tool-output trimming at a retained output.
- Share the existing 64,000-token retention budget, keeping outputs whole and dropping an oversized output and older items rather than partially truncating it.
- Place initial context before retained standalone outputs and account for their images in retained-image counts.
## Testing
Add a scenario covering enabled and disabled retention, emergency trimming, oversized-output handling, and preservation of the latest instruction after compaction and cold resume. Verify that retention annotations stay out of model requests.
GitOrigin-RevId: 449179670e4d2be2623928700738758e43b5dc1a
## What changed
- Add the disabled-by-default `output_token_replay` feature to request `output.encrypted_content` from OpenAI providers.
- Preserve encrypted message and tool-call output, message and function-call status, and output-text `annotations` and `logprobs` through history and replay. Update the generated protocol schemas and SDK types.
- Strip output ciphertext from requests to other providers while retaining it in stored history, including after replay is disabled. Remove encrypted content from memory extraction inputs.
## Testing
Add integration coverage for the feature/provider combinations, metadata replay across follow-up requests, and history preservation when resuming with replay disabled.
GitOrigin-RevId: 77729a021b6771933402aebe74ece8eb39c057e2
## What changed
Add `model_messages.tools.incremental_tools` overrides for the update hint, tool and namespace removal headers, and namespace instruction update and clearing messages. Missing, null, or over-512-byte values fall back to bundled wording; empty strings omit static text while retaining runtime names and instructions.
Substitute `{name}` in namespace message templates and append runtime instructions verbatim. Wording changes alone do not trigger tool catalog updates.
## Testing
Extend unit tests and MCP request-history snapshots to cover custom wording, empty notices, tool removal and restoration, and namespace instruction changes and clearing without repeating unchanged tools or notices.
GitOrigin-RevId: 22dea0a6fb4cfcd646f5e65346424834c8b7d5a2
## What changed
- Add `grpc+stdio://` as a host transport and the disabled-by-default `code_mode_host_grpc` feature flag to select it.
- Share a lazy HTTP/2 channel and host process across code-mode sessions while keeping session state isolated.
- Use HTTP/2 keepalives to detect unresponsive hosts, kill and reap disconnected children, and spawn a fresh host on reconnect. Exit the host when its stdio connection closes.
## Testing
Add coverage for shared-host session isolation, host exit on stdin EOF, and recovery after an unresponsive host is reaped. Exercise nested tool calls with both legacy stdio and gRPC stdio, asserting that the feature flag selects the expected transport.
GitOrigin-RevId: 31389d8540de236b8e0571d3c24e29e117b75c4a
## What changed
Pass the parent turn's `cyber_access_program` to Guardian reviewers and asynchronous classifiers. Use `daybreak_blue` for either Daybreak selection, preserve `standard`, and omit `access_programs` when no program is selected.
Capture the selection with the owning turn so asynchronous observations retain it across later turns. Resolve classifier programs using current authentication and the same provider and API-key feature policy as ordinary model requests.
## Testing
Add regression tests for program changes across reused reviewer sessions with API-key and ChatGPT authentication, snapshot and conversation classifiers at low and high risk, and enabled, disabled, and unsupported-provider API-key policies. Verify parent requests retain their selected program.
GitOrigin-RevId: 447f306df3a6bd6805464b819950690c751b04b4
## Why
JavaScript objects containing Serde's reserved JSON keys can be reinterpreted during deserialization, allowing nested `RawValue` markers to bypass the parser's normal recursion limit.
## What changed
Reject `$serde_json::private::RawValue` and `$serde_json::private::Number` object keys before passing V8's serialized JSON to `serde_json`. Report a `reserved JSON object key` serialization error while continuing to allow marker text in strings and longer keys.
## Testing
Add runtime regression coverage for nested and escaped marker keys, recursion limits, normal JSON conversion, and session recovery without overwriting stored values. Extend the host-backed integration test to verify that stored values remain available across turns after rejection.
GitOrigin-RevId: 27ddce08e1ffe98ec9dffe02473a815ceae2cc89
## Why
Resumed threads can retain stale capability root locations when the current environment supplies an explicit owner configuration. Matching roots from that configuration previously could not refresh persisted thread roots.
## What changed
Refresh persisted roots from the current attachment when both the root ID and environment ID match, including roots selected by owner-provided configuration. Preserve persisted locations when no matching root is supplied, and continue using the owner's selected roots rather than the executor's shared roots.
Apply the same merge behavior to capability root inspection and per-step resolution.
## Testing
Extend the remote environment regression test to cover owner-provided configurations with and without refreshed roots, including an executor root location that differs from the owner's selection.
GitOrigin-RevId: ad3a639924b348d6d5337ccc64dc8c08234276e3
## What changed
Move `ExecServerProcess` into `core_test_support::exec_server` and update the sandbox, plugin, access, and turn-input tests to use it. Preserve the fixture's startup timeout, temporary `CODEX_HOME`, WebSocket URL discovery, and child-process cleanup.
GitOrigin-RevId: 152de3a83f4ad39e2c1223e15438608dba452850
## What changed
Add `TurnInput::AnnotatedResponseItem` with a caller-supplied `retain` annotation. For function-call outputs, `retain: true` sets `client_authored` history metadata while keeping annotations out of model requests. Accept annotated items through the existing turn submission paths, including continuation.
## Testing
Add an integration test covering retention metadata during turn start, steering, idle submission, and rollout storage. Verify that ordinary outputs remain unmarked and model requests contain neither `retain` nor `client_authored`.
GitOrigin-RevId: 7285dde31149b17b0dcf31d4ea1c7cba66d9efe6
## Why
A credential bound to a host with MITM hooks could also be used at an alias without hooks, allowing the proxy to inject the real credential without enforcing hook policy.
## What changed
Reject requests to unhooked aliases when their selected brokered credentials are also bound to a hooked host. Check both HTTP forwarding and MITM requests before replacing dummy credentials, returning `403` with `blocked-by-mitm-hook` for denied requests.
Use the same destination and credential-selection rules for alias checks and injection, including configured URL prefixes, safe paths, equivalent credentials, merged Basic authentication fields, and environment scope.
## Testing
Add regression coverage for built-in and configured provider aliases, IPv6 destinations, credential selection, and unrelated credentials. Add an agent-started proxy test that verifies credential masking and alias denial.
GitOrigin-RevId: 12be41654761cedcf87b170f7661d6566f7a864e
## Why
A tool can return before its background watcher emits `ExecCommandEnd`. Waiting for that event first can discard an earlier `TurnComplete`, causing the shell snapshot test helper to time out.
## What changed
Update `run_tool_turn_on_harness` to track both the matching `ExecCommandEnd` and `TurnComplete` in a single event loop, returning only after both have arrived regardless of order.
GitOrigin-RevId: c9b749a46eda1244aa3e80fd88b663d110d67d1b
## Why
A local command can exit while a descendant keeps its inherited output pipes open, delaying `exec_command` completion and turn completion.
## What changed
Start the bounded output drain when a local exec-server process exits, whether exit is reported by an event or recovered through `process/read`. Remote execution continues waiting for output closure so buffered or delayed output is retained.
## Testing
Add regression coverage for local shell snapshot execution completing before a descendant releases stdout, preserving the foreground output and exit code. Add remote event-stream cases that retain output arriving after both reported and recovered process exit.
GitOrigin-RevId: d38bcd394be42cf48d2af02733e883b02d1dd62f
Alex Kira