## Why
Retained Guardian classifier conversations already contain previously delivered synchronous reviews. Appending those reviews again repeats evidence and consumes input budget.
## What changed
Track each review completion with a stable identity in host-only history metadata. Filter already delivered reviews before composing and budgeting continuation input, while preserving distinct completions even when their text is identical.
Fresh conversations receive the review evidence again, and shortened messages no longer count as complete delivery. Delivery metadata stays out of model requests.
## Testing
Add coverage for delivering retained reviews once, appending newly completed reviews, restoring evidence after failed streams, and retaining reviews when history lacks complete delivery metadata.
GitOrigin-RevId: b8d58ffdd7d9c484676af707c65fa50020aae73c
## What changed
- Add `features.guardianv2.async_classifier_mode` with `snapshot` and `conversation` modes. Local configuration overrides model defaults; snapshots remain the fallback.
- Retain completed classifier requests and responses in conversation mode, appending transcript deltas without repeating previously delivered user instructions.
- Rebuild retained history when authorization, classifier instructions, or parent compaction changes, after an incomplete response, or when the next request exceeds the configured token limit. Add `async_classifier_conversation_token_limit`, defaulting to 100,000 tokens, while preserving the model's input limit for fresh requests.
- Serialize conversation requests in observation order, bound outstanding work, and reject stale work after authorization changes or thread shutdown. Record retained and new input token costs.
## Testing
Add tests for configuration precedence, history reuse and resets, ordered admission, queue overflow, and stale or stopped requests. Exercise the approval matrix in both modes, including resume, fork, mandatory review, authorization changes, and stream failure after an early score.
GitOrigin-RevId: 35b9800104648cde4f467086e678dee12458c3e5
## What changed
Remove the repository-root `AGENTS.md` from `codex-rs/core` test data and from the root Bazel `exports_files` list.
GitOrigin-RevId: 644052d50f79b4c798baf40e53aab824f0fd73c3
## What changed
When the model catalog is provided in context and model overrides are exposed, tell V2 `spawn_agent` callers to inherit the current model unless the user explicitly asks for a different model. Include this guidance even when spawn metadata is hidden.
## Testing
Extend tool-description tests to cover hidden metadata with both inline and context catalogs, and update request-level assertions for V1 and V2 model override guidance.
GitOrigin-RevId: b70b0f09b0b5987a0eccba578196b8ef7cee4baf
## What changed
Register `browser_annotation_api` as a stable, default-enabled feature intended for requirements rather than user configuration. It controls websites opening and customizing annotation tools in desktop apps, independently of ordinary user-driven annotation.
Add the key to the configuration schema, extending the browser requirements support introduced in https://github.com/openai/codex/pull/18956.
## Testing
Extend `browser_feature_requirements_are_valid` to verify that enterprise requirements setting `browser_annotation_api = false` disable the feature.
GitOrigin-RevId: 8c7bb65932e08560040958b4472fe45f6d1c916f
## What changed
Capture each environment's effective Windows sandbox backend in the MCP runtime and include it as `useMxc` in sandbox state metadata for supporting servers. Use the server's captured environment selection, including local fallback, so the local MXC preference does not leak into attached environments. Default missing backend information to `false`.
## Testing
Extend tests to cover MXC metadata handoff, attachment isolation, local fallback without a selected local environment, and preservation of captured backend settings across runtime refreshes.
GitOrigin-RevId: f559bffeff383838334e5a475b1eab608d571fa1
## What changed
Allow API-key sessions using the OpenAI provider to forward explicit cyber access programs when `features.api_key_cyber_access_programs` is enabled, regardless of `features.api_key_model_discovery`.
## Testing
Expand the app-server test to cover all four combinations of the two feature flags, checking forwarded programs and failures when forwarding is disabled. Default the API-key test helper to model discovery disabled.
GitOrigin-RevId: f9cf1d2bd7c231645d50178cc6721b55a8d63268
## Why
An inaccessible user profile directory can prevent sandboxed PowerShell from preserving its working directory and resolving relative paths in a project beneath that profile.
## What changed
Pass `USERPROFILE` to elevated setup and refresh. When the command's working directory is beneath an absolute profile path, grant the sandbox group non-inheriting `FILE_READ_ATTRIBUTES` access to the profile directory.
Preserve existing permissions and deny ACEs during non-inheriting ACL updates without propagating changes to descendants. Expand generic deny masks when checking for conflicting permissions.
## Testing
Add a Windows regression test that checks PowerShell's working directory and reading `.\public.txt` beneath a protected profile. Add an ACL test that verifies a non-inheriting grant leaves an unprotected child's security descriptor unchanged.
GitOrigin-RevId: 7f142a7ffdee795c3255d4a6e79568fa9391c055
## What changed
Emit `codex.skill_invocation` logs for explicit skill injection and detected implicit use, including skill-tool reads. Include skill name, invocation type, conversation, turn, model, and client metadata, plus scope, plugin ID, and ChatGPT user and account IDs when available.
Exclude skill contents, resource paths, email addresses, prompts, and tool payloads. Use the existing OTEL log exporter without an additional opt-in; `otel.exporter = "none"` continues to export no logs.
Document the event fields, exporter configuration, and detection semantics in `codex-rs/otel/README.md`.
GitOrigin-RevId: 0f9c492c3f224455f3de3660be89692d776c1951
## What changed
- Start a turn-owned notification receiver using the same remote board client and session identity as the board tools. Deliver post previews as agent messages and cancel the receiver when the turn stops, aborts, or errors.
- Wait for the initial connection attempt before inference, then retry failed or disconnected streams without waking idle agents.
- Skip malformed notices, mismatched recipients or turns, and oversized previews. Reject delivery to stale or canceled turns and bound remote notices to a 1 KiB context budget.
## Testing
Extend remote board tests to cover interrupted setup, connection failures, reconnection, invalid and stale notices, preview delivery into model context, and receiver shutdown after turn completion.
GitOrigin-RevId: c7c8d977fe74b7a5cb3bd8216dc0146f3f297e44
## What changed
Register `in_app_voice` as a stable, default-enabled feature and add it to the configuration schema. The gate is intended for managed requirements to control permission for voice in desktop apps; permission does not establish voice availability or provider support.
## Testing
Add app-server coverage for reporting `in_app_voice = false` from `requirements.toml` in both requirements and feature-list responses. Extend the CLI feature-list test to verify that cloud-managed requirements disable the gate despite a user-configured `true` value, without rewriting the user configuration.
GitOrigin-RevId: 6ec3bc0176fdb3e1714b0136bf812bd56591f6a1
## Why
`windows.allowed_sandbox_implementations` permits MXC regardless of the listed implementations. Managed requirements need a separate way to block both explicit MXC configuration and automatic selection through `prefer_mxc`.
## What changed
Add the optional managed requirement `windows.allow_mxc`. Setting it to `false` disables automatic MXC selection and rejects explicit `windows.sandbox = "mxc"` configuration with an error identifying the requirement. Leaving it unset or setting it to `true` preserves existing behavior.
## Testing
Add coverage for the requirement alongside allowed sandbox implementations, preference resolution, and cloud-managed opt-out behavior for implicit, elevated, and explicit MXC configurations.
GitOrigin-RevId: a458a7b4c92cf17e687dbbad8208884d1c097da5
## Why
Resuming a thread rereads persisted history even when a preloaded snapshot is unchanged. Reusing that snapshot must still account for writes committed before writer ownership is acquired.
## What changed
- Carry optional, non-serialized revisions from stored history and model context through thread and agent resume paths.
- Validate the revision under writer ownership and reuse the shared snapshot when it matches. Reload stored history when the revision is missing or changed, while preserving explicit history overrides.
- Resolve the selected rollout before loading context, validate compressed snapshots before materialization, and enforce archived-thread restrictions on canonical paths.
## Testing
Extend coverage for snapshot reuse and late-write refresh in legacy and paginated histories, compressed rollout reuse, archived rollout symlinks, and cold child restoration that includes edits made after preloading history.
GitOrigin-RevId: e1fd7aee6ef2b30f41951e6b7e6b01c3e1420cab
## Why
A stored history snapshot can become stale before a resumed thread acquires writer ownership. Resume must include writes committed before that acquisition.
## What changed
Make `ThreadStore::resume_thread` return the replay context and use it for session restoration and metadata initialization. The local store refreshes stored snapshots while holding writer ownership, reads through the installed writer to honor explicit rollout paths, and releases the writer if loading context fails. Explicit histories without a canonical session header retain their override semantics.
## Testing
Extend resume tests to cover edits made after the initial snapshot in both legacy and paginated history modes, stale SQLite rollout paths, and preservation of explicitly supplied history.
GitOrigin-RevId: 2361f524d324c859f5dfcf2863320e2045736c2e
## Why
User goal edits and clears need to reach the model as user instructions, including when a thread is unloaded or history is being compacted. Automatic goal lifecycle updates must not supply user authorization.
## What changed
- Add optional `origin` values of `user` and `automatic` to `thread/goal/set` and `thread/goal/clear`, and mark TUI goal requests as user actions. Omitted origins do not supply user authorization.
- Persist explicit user objective, status, and clear instructions before changing goal state. Recording failures leave goal state unchanged.
- Coordinate goal edits with thread resume, reload stored history under writer ownership, and preserve edits accepted after the compaction input snapshot.
- Update generated protocol schemas and TypeScript and Python bindings.
## Testing
Add coverage for user edits and clears on loaded and unloaded threads, concurrent path-based resume, exclusion of automatic goals from user instructions, preservation of edits during compaction, and recording failures that leave goal state unchanged.
GitOrigin-RevId: d779d7c678a0c32a6ef76975dbe5b1400d1df245
## Why
Guardian and parent requests can arrive in either order after a command yields. A shared response sequence can let parent requests consume Guardian review decisions.
## What changed
Match Guardian responses separately and drive parent responses from the latest tool output in the strict automatic network review test. Poll running sessions with `write_stdin` until the process exits, and assert that the command and network request each receive Guardian review.
GitOrigin-RevId: 21300abd65a3b2d439e8c1ea04e4429d5bd528dd
## Why
Guardian does not consume skills, but host skill discovery can block its startup or turn creation when the primary executor is offline.
## What changed
Skip plugin and skill warmup during Guardian session initialization, and use an empty host skills snapshot when building Guardian turn contexts.
## Testing
Add a regression test that discovers skills for the parent session, disconnects its primary executor, and verifies that Guardian still reviews and denies a network permission request.
GitOrigin-RevId: 3c12129721c82cb78a3fa618d6b05faea631966a
## Why
Refreshing available model descriptions changes the `spawn_agent` tool schema. Keep model choices current while preserving tool definitions and earlier conversation input.
## What changed
- Add the disabled-by-default `model_catalog_in_context` feature for multi-agent V1 and V2. When enabled and model overrides are available, move model listings from tool descriptions into developer `<model_catalog>` messages.
- Include picker-visible, compatible models with descriptions, reasoning efforts, and service tiers in a listing bounded to 1,000 bytes. Point `spawn_agent` guidance to the latest catalog.
- Append updated listings only when their rendered content changes, restore missing listings, and invalidate retained catalogs when they no longer apply.
## Testing
Extend integration coverage for V1 and V2 with the feature enabled and disabled. Verify that catalog refreshes preserve tool definitions and prior input when enabled, append the updated listing once, and retain the existing tool-description behavior when disabled. Add a request-history snapshot for the V1 opt-in path.
GitOrigin-RevId: 67b11b4ad6c35f00d0e29edf6343bb0b4804d797
## What changed
- Fork the selected conversation and open the new session with `f`, configurable through `agents.fork` in the TUI keymap.
- Move the default search shortcuts to `F3` and `/`, preserving unshadowed defaults when custom bindings conflict.
- Keep queued input on the source conversation while attaching and forking, and require closing an open side conversation before forking another task.
- Expose the fork action in command-center help and the keymap picker.
## Testing
Add regression coverage for queued-input preservation, side-conversation protection, configurable fork shortcuts, metadata editing, disconnected actions, and search fallback bindings. Update help and keymap snapshots.
GitOrigin-RevId: b11ae21ef6a2053609b31ce97c646104f18806a3
## What changed
Add a debug-only analytics test that switches accounts after the first isolated event request. Assert that only the first request reaches the server and carries the original account's credentials, so subsequent batches do not send stale credentials after the switch.
Remove an unused `ToolCallSource` import.
GitOrigin-RevId: e66904c7a7176f1eaa37662b836132586328884a
## Why
`TurnAborted` could be emitted before extension abort callbacks finished, allowing consumers to observe a terminal event while lifecycle cleanup was still pending.
## What changed
Await `on_turn_abort` within task abort handling before emitting `TurnAborted`, retaining callback delivery for already-cancelled tasks. Document that `on_turn_stop` and `on_turn_abort` complete before their corresponding terminal events, if emitted.
## Testing
Add regression coverage for interrupt, conditional interrupt, and shutdown. Hold the abort callback open to verify that `TurnAborted` waits for completion, then verify that the callback runs exactly once with the expected turn ID and abort reason.
GitOrigin-RevId: f34d7e94d04c02544178dc445b85abc65a6ce499
## Why
Login shell startup can reset `PATH`, preventing commands and their children from finding bundled tools such as `rg` in executor-reported directories.
## What changed
When `login_shell_package_path` is enabled, prepend missing executor-reported directories to `PATH` inside the POSIX login shell before running the requested command. Preserve existing entries and the order of newly added directories, and export `PATH` for child commands.
Respect explicit `PATH` overrides and preserve the requested login mode when directories are unusable or `PATH` is read-only. Keep shell diagnostics and `$LINENO` aligned with the original script, including when directory names contain newlines. The feature remains disabled by default.
## Testing
Add shell tests for nested tool lookup, existing entries, quoting, line numbers, and read-only `PATH`. Extend remote execution tests to cover feature gating, explicit overrides, unusable directories, and preservation of the original command in execution events.
GitOrigin-RevId: 301aa34e72cc6292293693250e190c19903f390a
## Why
Responses overload and exhausted-request errors could terminate despite server retry advice, and WebSocket-to-HTTP fallback could issue a request before the advised deadline.
## What changed
- Allow `ServerOverloaded` and `RetryLimit` errors to retry when server advice is present, within the configured retry budgets.
- Preserve `Retry-After` headers from rejected WebSocket upgrades and wait for the server deadline before falling back to HTTP.
- Keep quota, usage-limit, and policy failures terminal even when they include retry advice.
## Testing
Add coverage for HTTP overload and rate-limit recovery, WebSocket upgrade rejection and fallback timing, retry deadline preservation through error mapping, and retry limits for sampling and manual and automatic compaction.
GitOrigin-RevId: 72d30a9f078652664754dfa971fd7dc7a78f20e8
## What changed
Update the replay assertion in the recorder refresh test to compare `executed_tool_call_metadata()` instead of entire response items. This keeps the assertion focused on preserving recorded tool call metadata across a configuration refresh.
GitOrigin-RevId: 763173a918f4e0bc79c3c04466453cafb9629775
## What changed
Forward explicit `cyberAccessProgram` selections for the built-in OpenAI provider when both `api_key_cyber_access_programs` and `api_key_model_discovery` are enabled. The new feature defaults to disabled and can be toggled through the app server's experimental feature enablement API.
Reject explicit selections in OpenAI API-key sessions when either feature is disabled, instead of silently omitting the program. Leave entitlement and model restrictions to the server, and preserve the requested program when a server rejection triggers transport retries.
## Testing
Add app-server coverage for both feature gates, forwarding all three program values, and server rejection without fallback. Update core coverage for API-key resumes with disabled features and custom-provider omission.
GitOrigin-RevId: aa639afb841aa651b28f6f3f61198299372baa2d
## What changed
Register `login_shell_package_path` as a disabled-by-default experimental feature and add it to the configuration schema. Expose it in `/experimental` as “Bundled tools in login shells,” with a description explaining its intended use when login shell startup resets `PATH`.
## Testing
Extend the experimental feature metadata snapshot test to cover the new feature's label, description, and unchecked default state.
GitOrigin-RevId: dc110486ccd8d2d76ac788ba5a413a1374699ff8
## Why
Persistence and aggregate metadata budgets can omit tool-call observations that are still relevant to the current request, including tool result metadata needed during compaction.
## What changed
- Retain live direct-call observations separately from bounded persisted outputs, keyed by response item ID so reused call IDs cannot mix results.
- Restore those observations for sampling and compaction, pruning them only when sampling confirms they have left the history window. Preserve observations across shortened compaction retries.
- Remove aggregate prompt metadata caps while retaining per-call argument limits and the outgoing message size limit. Invalidate cell completeness when argument normalization truncates a recorded call.
## Testing
Add regression coverage for exhausted persistence budgets, reused call IDs and reversed completion order, shortened compaction retries, and completeness after argument truncation. Extend integration coverage for large Code Mode metadata, provider metadata support, and fork/resume behavior.
GitOrigin-RevId: 004082b69bff9cc8b05f36d1052057f163c67f07
## What changed
- Instrument MCP OAuth loads, saves, deletes, fallback cleanup, and refresh persistence with credential-free storage metrics, distinguishing configured policy from operations on a pinned store.
- Retain the originating client across background tasks, blocking storage operations, and session recovery, including recovery after startup found no credentials.
- Preserve typed keyring and lock error categories for metrics and remove raw error details from storage warnings.
## Testing
Add tests for policy and pinned-store outcomes, best-effort cleanup failures, wrapped lock errors, and successful or failed refresh persistence without duplicate observations. Add recovery tests that verify client attribution after anonymous startup and across threads with different originators.
GitOrigin-RevId: 5ea4528bcdcf500c8ffdf1d9c7008ea52112c726
## Why
Elevated sandbox tests share machine-local Windows accounts. Concurrent setup can rotate account passwords between another test's setup and logon.
## What changed
- Add a shared file-lock guard for elevated sandbox tests in `codex-core`, `codex-exec-server`, and `codex-windows-sandbox`, held through sandbox commands and cleanup.
- Queue these tests in a single-threaded Nextest group before their timeouts start, while retaining the file lock to coordinate other test processes.
- Limit account locking to tests that use elevated accounts and remove the sandbox crate's blanket Bazel `exclusive-if-local` tag.
GitOrigin-RevId: 26d4606cb1fdcac65926d29835bed4eac04c19c0
## Why
Successful file fallback can hide a secure-store failure. Storage diagnostics need to distinguish that fallback from explicit file storage while keeping credential values out of error output.
## What changed
- Record credential load, save, delete, and fallback-file cleanup outcomes, including secure-store failures and fallback reasons.
- Preserve the initiating client's attribution across app-server requests, login tasks, sessions, turns, and blocking token persistence.
- Preserve storage error context and typed causes while redacting credential JSON data errors and payload-bearing keyring errors.
- Include sanitized fallback completion warnings in the default `codex login` file logs.
## Testing
Add coverage for storage policy and metric attribution, credential redaction, login diagnostics, concurrent app-server clients, device-code login, and token refresh during a turn.
GitOrigin-RevId: 6d5651c1718d184016fa77befa02aa528750b2ae
## What changed
- Carry the selected shell and login mode through unified exec using `ShellInvocation`. Use this metadata for shell snapshots and credential brokerage instead of inferring it from command arguments.
- Add `prependPathDirs` to exec-server environment metadata, populated from the executor's package PATH directory. Default to an empty list for older servers and omit empty lists from serialized output.
## Testing
Extend environment metadata round-trip coverage for `prependPathDirs` and the remote exec-server integration test to verify the packaged `codex-path` directory is reported.
GitOrigin-RevId: c571c068effcb305d196a701ad9a335ec7a3f5a2
## Why
Denied-read policies previously kept explicitly approved commands within their original filesystem restrictions, preventing operations that need broader write access, such as updating Git metadata.
## What changed
- Apply broader filesystem permissions after approval of explicit escalation while retaining the sandbox, denied reads, and network policy. Command allow rules alone do not widen filesystem access.
- Reject escalation when the required local sandbox is unavailable or a remote exec server lacks support for preserving the restrictions.
- Track escalated terminal access so subsequent `write_stdin` calls still require review when stdin approval is enabled.
## Testing
Add coverage for approved and denied escalation, allow rules, remote server compatibility, and stdin approval before input delivery. Add a Windows integration test verifying that an approved `git pull` updates Git metadata while exact-path and glob-based read denials remain enforced. Serialize Windows sandbox integration tests across processes to protect shared test account credentials.
GitOrigin-RevId: 5dce6d41487ee4d39bd795c8d086398ab9794d5b
## What changed
Preserve catalog `multi_agent_version` values instead of forcing V1, allowing models that declare V2 to use it by default. Retain Ultra in supported reasoning levels so it appears in the Astra advanced reasoning picker for Bedrock Mantle and Runtime.
## Testing
Add coverage for preserving configured multi-agent versions, selecting V2 and exposing `collaboration.spawn_agent` and `collaboration.followup_task` without the V2 feature flag, and displaying and selecting Ultra in both Bedrock reasoning pickers.
GitOrigin-RevId: 4fb1336c79b3f86ce12fa5ea81fe2237a300840d
Add `gpt-6.1-sol` to the bundled model catalog with its capabilities,
reasoning levels, and availability message. Give it the highest catalog
priority and update older Sol descriptions to reflect their generations.
Update startup, model picker, and tool catalog snapshots to reflect the
new default and catalog contents.
GitOrigin-RevId: 1092a0524c6d1813ddd600c31c4fd0e708294ae9
## Why
A subagent stopped by repeated Guardian denials remained interrupted without notifying its parent. The parent needs guidance to report the stop and wait for explicit user confirmation before continuing the blocked work.
## What changed
Forward `TooManyDenials` interruptions from `MultiAgentV2` children to their parents with Guardian-specific guidance to inform the user and avoid resuming or retrying until the user explicitly confirms. Preserve the child's `Interrupted` status and keep ordinary interruptions silent.
## Testing
Add integration coverage for parent notifications under `CircuitBreakAction::Strict`, silence under `CircuitBreakAction::Default`, and preservation of the child's interrupted status. Add a unit test ensuring long denial messages stay within the notification token limit while retaining the guidance.
GitOrigin-RevId: c9bb90827393068d9c92edaf0443a52e6ff57f9f
## Why
Guardian review and classification telemetry lacks the context mode needed to distinguish `legacy`, `independent`, and `thread_owned` reviews.
## What changed
- Add `guardian_context_mode` to review and classification analytics and `context_mode` to their metrics.
- Capture the mode from the conversation history snapshot before review preparation or classification setup so failure metrics retain it, including when review preparation or reviewer startup fails.
- Use `unknown` for review metric tags when no context mode is available.
## Testing
Update metric assertions to cover `thread_owned` classification tags and the `unknown` review fallback.
GitOrigin-RevId: 79f7d11b3e4ccfc53681890d75fbc7c54e1ce7de
## Why
Stale thread capability roots can reconnect executors that are not selected for the current turn and shadow selected roots with the same ID.
## What changed
Filter out roots whose environments are absent from the turn snapshot before deduplication and readiness resolution. Update app-server capability tests to explicitly select the executor environments used by each turn, including after resume.
## Testing
Add regression coverage for full-access and workspace-write permissions, verifying that stale roots never connect an unselected executor, selected roots with matching IDs remain available, and turns with no environments expose no roots.
GitOrigin-RevId: afe375047cc5e8aad06df83334149510460dcdcc
## Why
`TurnComplete` can arrive before the previous turn finishes teardown, making `start_turn_if_idle` race with cleanup in the encrypted parent reply scenario.
## What changed
Submit the reply through `Op::InterAgentCommunication` so it queues through the same mailbox path as real agent messages. The scenario continues to verify that the encrypted parent reply appears exactly once in each incremental Guardian review.
GitOrigin-RevId: 3d356c274442aa839324b9425490feafacd47313
## Why
Responses prewarm can reconnect and consume scripted WebSocket replies intended for realtime conversations when both share a test server.
## What changed
- Give realtime conversations a separate scripted server in tests for runtime replacement, prompts, and voice selection.
- Disable Responses WebSocket prewarm in the audio/text round-trip test while preserving coverage of the default realtime endpoint.
- Update connection counts and request assertions to address only realtime connections.
GitOrigin-RevId: 8e3b5ac86ee80777cf94063db468c80203966999
## Why
Reloads can reject a valid thread configuration when the host configuration references a missing model provider that thread overrides replace. Concurrent cloud refreshes can also leave older policy snapshots or staged cache writes eligible for publication.
## What changed
- Compose preserved session layers before materializing refreshed configuration, retaining source-aware validation errors.
- Carry cloud policy revision bindings through config loading and role overrides. Reject stale MCP refreshes and disable enterprise MCP authorization when the policy is suspended. Retire the old policy when replacing or clearing its loader.
- Stage cloud cache writes in temporary files and publish them atomically only while their policy revision remains current.
- Route file reloads through the shared runtime refresh path, resolve paths relative to each config file, and preserve session settings. Restore host defaults for `secret_auth_storage` and `mcp_oauth_refresh_coordination` when explicit overrides are removed.
## Testing
Add regressions for thread-provided model providers, managed plugin and feature requirement refreshes, stale and suspended policy snapshots, superseded and retired cache writes, and file reloads preserving runtime settings and restoring feature defaults.
GitOrigin-RevId: 3280a2445eeb7074a142f720690bb0e4f01d174b
## What changed
Add `features.multi_agent_v2.message_board_remote` with a board URL and a bearer token supplied directly or through an environment variable. When configured, use the remote board in preference to local or in-memory storage, including in ephemeral sessions, while preserving the existing board tools and session identity.
Ignore remote board settings in project-local configuration and use the runtime HTTP client and clock for remote requests.
## Testing
Add a mock-server integration test and snapshot covering an ephemeral session posting through the existing tool, with the expected bearer authentication, session identity, timestamp, and returned post.
GitOrigin-RevId: 263413d90a1ee4c0bdba8c1b08ba9f68bdd7a986
## Why
Steering and recovery requests can have different traces from the turn they join. Sampling can also finish while tools remain in flight. Tracing needs to preserve that correlation and distinguish sampling time from time spent waiting for tools.
## What changed
- Add `codex.turn_input` spans with `conversation.id` and the accepted `turn.id` for started, steered, and recovered turns.
- Add sampling, tool-blocking, and automatic and manual compaction spans with `codex.turn.phase` and conversation and turn IDs. End the sampling span before draining outstanding tools.
- Emit a `codex.mailbox_preemption` event when pending mailbox input preempts sampling.
## Testing
Add integration coverage for cross-trace steering and recovery, sampling and tool-blocking boundaries through a blocked dynamic tool, and completion or interruption. Extend mailbox preemption tests to check event emission with preemption enabled or deferred.
GitOrigin-RevId: 59893c2d463c02cbd05f5c332e5afc2351cc8b62
## Why
Configuration reloads must honor current managed restrictions without granting new enterprise MCP authority to existing sessions or overwriting newer configuration with stale snapshots.
## What changed
- Allow enterprise managed authentication only for configured MCP servers. Remove plugin `ema_auth` overlays from the schema and disable servers that still use them.
- Refresh ordinary MCP settings while preserving session settings and initially admitted enterprise registrations. Disable enterprise MCP when its registration changes, policy revokes access, or configuration loading or resolution fails; require a new session to restore enterprise authority.
- Publish refreshes only when their captured configuration is still current, with bounded retries in app-server reloads. Preserve updated managed restrictions even when a refresh is rejected.
- Finish processing other thread refreshes before `config/mcpServer/reload` reports a rejection, and document that an error can accompany partially applied changes.
## Testing
Add regression coverage for stale refreshes, bounded retries, managed-policy revocation, persistent enterprise disablement, ordinary MCP transport changes, and rejection of plugin enterprise authentication. Verify that denied enterprise servers receive no requests.
GitOrigin-RevId: 34429cd339c1ec152a2ee8697cb29f0cff5d9e5f
## Why
Background helpers launched from a detached Windows process can allocate console windows. Job Object launches and containment fallbacks need to preserve console suppression as well.
## What changed
- Add `codex_utils_process::background_command` to set `CREATE_NO_WINDOW` on Windows, and use it across background subprocess launches, including Git, plugins, authentication, diagnostics, and sandbox helpers.
- Centralize console suppression in Job Object launches. Keep `CREATE_NO_WINDOW` when retrying without containment, and clear `CREATE_SUSPENDED` so the fallback child can run.
- Preserve console inheritance for interactive shell launches and interactive AWS authentication refreshes.
## Testing
Add Windows regression tests covering console-free launches from detached parents through standard and Tokio commands, stdout/stderr capture, successful containment, Job Object creation and assignment failures, and sandbox setup refresh helpers.
GitOrigin-RevId: b2c238fa7d4f9fbd868e5adf7d4be9958ff01e6c
## Why
Turn error hooks receive only a `CodexErrorInfo` category, which omits backend metadata such as usage-limit reset times and rate-limit snapshots.
## What changed
Add borrowed `CodexErrorDetails` to `TurnErrorInput` and pass the original details through turn and compaction error notifications, alongside the existing error category.
## Testing
Add coverage for usage-limit metadata during sampling, manual compaction, and post-turn compaction, including preservation of completed answers and existing error events. Extend lifecycle tests to verify that an `InvalidImageRequest` retains its details when surfaced as `BadRequest`.
GitOrigin-RevId: 6f2058992126da0f69508ef51998e7581557deea
## Why
Providers with `model_catalog_url` could advertise bundled models absent from their catalog or reuse stale models after a failed refresh. Model metadata could also match by prefix or namespaced suffix instead of the provider's exact model ID.
## What changed
- Suppress bundled model fallback and merging for explicit provider catalogs, including when discovery is disabled.
- Require unique, non-empty catalog slugs and match metadata by exact model ID.
- Serialize explicit catalog refreshes and invalidate in-memory and persisted catalog entries after fetch failures, preventing stale cache reuse.
- Report a clear configuration error when startup has no available model, while allowing an explicitly configured `model`.
## Testing
Add regression coverage for exact model matching, hidden catalog entries, cache invalidation across restart and recovery, invalid slugs, and empty-catalog startup with and without an explicit model. Update app-server model-list expectations and verify the TUI configuration error.
GitOrigin-RevId: ac323a94178e3c48df8d4a159a86fdbac20b03a2
## What changed
Move content-filter guidance recording from the sampling loop into
`handle_response_stream_error`. Pass `StepContext` so the handler can resolve
model-specific guidance and record it before retry decisions for sampling
requests. Keep remote compaction excluded from guidance recording and update
callers and the existing retry-deadline test to use the new signature.
GitOrigin-RevId: 030bde1d4f1597fc4f3971ad837478e5304c5aa9
## Why
Skills available from both cloud and executor providers consume duplicate catalog space, leaving less room for descriptions of unique skills.
## What changed
- Prefer model-visible cloud skills over executor listings with the same `plugin:skill` name before allocating the metadata budget.
- Preserve aliases from the full visible executor inventory so filtering duplicates does not renumber remaining packages. Continue choosing full locators when they fit the budget better.
- Keep executor packages available through `skills.list` and `skills.read`, and retain executor listings when cloud skills are disabled.
## Testing
Add regression tests and a model-request snapshot covering description retention, stable aliases across turns, executor availability changes, package reads, and full-locator selection after deduplication.
GitOrigin-RevId: 477e4cf16b8968dbe61438dd5af1eca9cbfa78c8
## Why
Responses stopped by `content_filter` previously followed generic stream-error retry handling without guidance about the block. Retried requests need instructions to explain the limitation and offer a permitted alternative.
## What changed
- Recognize content-filter failures as a distinct error while preserving retryability and the existing public error representation.
- Append developer guidance to the conversation after each sampling block, retaining delivered output and using the existing retry handling.
- Support a model catalog override through `model_messages.content_filter_guidance`. Missing, null, blank, or values exceeding 512 UTF-8 bytes fall back to bundled guidance.
- The bundled guidance tells the model to avoid reproducing or working around blocked content, briefly explain the limitation, offer a permitted alternative, and continue unrelated authorized work.
## Testing
Add a scenario and request-history snapshot covering repeated blocks, catalog guidance on each retry, retained partial output, and eventual completion. Add error-mapping assertions for retryability, public error classification, and error text.
GitOrigin-RevId: ba0c201b3a5a3acf5cfa971332027240e0690225
Clarify in the `requires_openai_auth` field documentation and configuration schema that credentials use the backend selected by `cli_auth_credentials_store`, rather than always being stored in `auth.json`. Also clarify that `env_key` specifies the environment variable containing the API key.
GitOrigin-RevId: e65753a72258e43b24c4e40b51ff26830c5b3756
felixxia-oai