`TranscriptState` has no `had_work_activity` field. Remove the assignment
from computer tool call completion handling to fix the resulting compile
error.
GitOrigin-RevId: 2adb15a213992e40a58dc6f217d7ae8d64c48154
## What changed
- Add feature-gated `/voice`, `/voice mute`, and `/voice stop` commands with local WebRTC audio and app-server signaling.
- Show live transcripts, conversation status, and microphone and speaker levels. Preserve captions and undelivered answers across thread switches.
- Speak final answers from voice handoffs while keeping delegated reasoning and commentary hidden and typed answers unspoken.
- Retry eligible startup failures once and clean up voice sessions on thread switches and disconnects.
- Stop voice and block late handoffs after a misalignment policy violation. Remove realtime event payloads and spoken text from receipt and debug logs.
## Testing
Add coverage for voice command mapping, rejected starts, disconnect cleanup, delegated final-answer speech, late handoff rejection, and transcript and footer rendering.
GitOrigin-RevId: 11def1f86b0e023b21d0d92072d6636ccad89815
## What changed
Render adjacent `cua_repl` calls as a compact “Using computer” or “Used computer” group with action and failure counts. Show the current action while running, and prioritize failures and screenshots in completed previews while preserving their chronological order.
Keep full call arguments and output in the expanded transcript, with a `ctrl+t` hint for hidden actions. End groups at other history items and turn boundaries, preserve completed results when pending actions are interrupted, and use the same grouping for live events and history replay.
## Testing
Add unit and snapshot coverage for live/replay parity, grouping boundaries, out-of-order completion, interruption, failure and screenshot previews, full transcript details, and narrow-terminal and Unicode rendering.
GitOrigin-RevId: 8e61ccf4c9f6d1a4d56d674a6d41ca5160d42c82
## Why
Managed app-server shutdowns use a fixed 60-second grace period. Allow users to adjust how long shutdown waits before forcing the process to exit.
## What changed
- Add `shutdownGraceSeconds` to daemon settings, accepting integers from 0 through 300 and defaulting to 60. Zero requests graceful shutdown and then forces termination immediately.
- Apply the setting to managed app-server stops and restarts, including updater-triggered restarts, and extend the lifecycle lock timeout to accommodate the maximum grace period.
- Keep `stop` usable with unreadable or invalid settings by falling back to the default grace period.
## Testing
Add tests for setting defaults and bounds, invalid-value fallback, preservation when saving remote-control settings, graceful process exit, and forced termination with zero or finite grace periods.
GitOrigin-RevId: 8627b391323cf27b40df96935a82e66aa715f572
## What changed
- Store the shared `GuardianReviewSessionManager` in thread extension data and let the Guardian extension spawn and fork reviewers through `ThreadManager`, independently of async scorer startup.
- Preserve reviewer reuse, concurrent forks, cancellation, inherited environments, and user instructions. Gate managed reviewer startup on parent registration and remove terminated reviewers from the manager.
- Retain the `guardian` subagent identity in saved conversations. Reject resume of live Guardian reviewers and reject client archive or delete of live owner-managed workers with JSON-RPC error `-32600`; allow normal access after the owner releases them.
- Keep standalone reviewer support for inline delegates and remove duplicated extension prompt and configuration code.
## Testing
Add app-server tests covering reviewer reuse and concurrent forks, inherited instructions and prompt cache keys, live resume and removal rejection, saved reviewer discovery and resume after parent shutdown, and strict Guardian assessment inside an inline review.
GitOrigin-RevId: 4f9893c1ade151eacb4c11ffeae3d9e9ec019187
## Why
The existing `userVerification/*` handlers always returned unavailability, leaving local clients unable to use the native verification provider.
## What changed
- Dispatch status, enrollment, deletion, and challenge signing through an account-scoped provider. Enrollment creates or reuses a local key; it does not register credentials with a server.
- Restrict enrollment, deletion, and signing to stdio and in-process connections, rejecting WebSocket and remote-control callers before parameter validation.
- Bound native work to one operation per service with a 120-second timeout, and propagate in-process caller cancellation. Recheck connection, cancellation, and authentication state before delivering results, including after waiting for response queue capacity.
- Add device-gated verification capability wiring for the experimental in-process `codex-tui` client, with automatic activation still disabled by default.
## Testing
Add tests for local key reuse and deletion, decoded challenge signing, cancellation, authentication changes during verification and response queuing, concurrent worker rejection, and stdio/WebSocket RPC behavior.
GitOrigin-RevId: 7eac15a5ffb049d27bf8fedcfbae19a49a3f6a3d
## What changed
Add `codex app-server daemon update` to check the latest stable release once, even when automatic updates are disabled. The command requires an installer-owned latest-channel standalone installation and reports `updated`, `noUpdate`, or `unsupported` as JSON, including installed and running versions.
Route manual requests through the updater so scheduled and manual installs share one owner and accepted updates continue if the CLI exits. Restart a running managed daemon when its binary or version differs from the selected installation; this may interrupt active or queued work. Return installer failures as command errors and retry requests across updater replacement.
## Testing
Add coverage for manual updates with automatic updates disabled, queued requests, same-version binary replacement, updater handoff retries, and unsupported installations or unmanaged servers.
GitOrigin-RevId: 240b63c79bae3a64a80768131a30da70900a4d62
## What changed
Replace horizontal turn separators with dim completion metadata after the final answer, including plain conversational answers. Show local completion times such as `done 2:32 PM`, adding the date for other days and the year for other years. Retain `Worked for` durations above sixty seconds and runtime metrics, and wrap metadata on narrow terminals.
Restore saved completion metadata when resuming conversations or loading older history. Keep each footer after its turn's items and deduplicate it across repeated notifications and overlapping pages. Only live completions fall back to the current time when a saved timestamp is unavailable. Failed, interrupted, and in-progress turns do not receive success footers.
Avoid submitting queued input or emitting completion notifications while replaying history.
## Testing
Add unit and snapshot coverage for timestamp formatting, duration thresholds, muted styling, narrow layouts, live and replayed completions, missing metadata, and pagination boundaries with overlapping pages.
GitOrigin-RevId: 308c35c6720720da43c9a391aa5a68c1b231c9a5
## Why
An installer can retarget the selected executable symlink or junction while an app server is running. Recording the launch-time identity preserves which binary was started after that path changes.
## What changed
- Resolve the executable path before launching on all platforms and store an optional executable identity in app-server PID records. Continue accepting older records without this field and expose the identity only for an active process.
- Use BLAKE3 for executable identity digests and make `ExecutableIdentity` serializable.
- Schedule updater checks with an explicit deadline in `tokio::select!`, preserving persisted update intervals, settings-error retries, and termination handling.
## Testing
Add a Unix test that verifies the recorded identity matches the resolved launch binary, differs from a retargeted symlink's binary, and remains optional when reading legacy PID records.
GitOrigin-RevId: 4821130b9a5e75b417a8e39c583b30427a872ff8
## What changed
- Introduce `codex-user-verification` with a provider interface for credential status, creation, deletion, and challenge signing. Include typed errors, shared cancellation guards, and hashed account-user key namespaces.
- Add P-256 public-key encoding as unpadded base64url SPKI DER, derive credential IDs from its SHA-256 digest, and redact proof fields in debug output.
- Add app-server helpers to validate challenge and display-text bounds and map provider errors to typed RPC errors without exposing provider diagnostics.
The platform implementation reports verification as unsupported. App-server requests still return typed unavailability, with the message updated to mention build or account availability.
## Testing
Add tests for credential encoding and signature verification, invalid curve points, cancellation across guard clones, stable and distinct account namespaces, and invalid challenge or display values. Update the app-server unavailability test for the revised message.
GitOrigin-RevId: fe4a4eb37c68d7fdc547704e76aa257abf3e9c81
## Why
A fork cutoff can exclude the `TurnContext` that records the source's multi-agent runtime version. Recovering that version should not require loading the source's full model context.
## What changed
- Preserve `multi_agent_version` in fork session metadata before applying the cutoff. If absent, scan backward for the newest version-bearing `TurnContext`, respecting inherited segment boundaries and stopping once resolved.
- Load the latest model context for paginated forks only when approval or permission settings need to be restored.
## Testing
Add regression tests covering stored-version precedence, early termination without reading older segments, and version recovery within inherited segment cutoffs.
GitOrigin-RevId: 00e66bcce6f4092805e273cde99bd50f304fb39e
## Why
The managed daemon's updater used a fixed hourly cadence with no saved preference to disable automatic updates.
## What changed
- Read `updater.autoUpdateEnabled` and `updater.updateIntervalMinutes` from `CODEX_HOME/app-server-daemon/settings.json`, defaulting to enabled with a 60-minute interval. Keep the initial five-minute delay and require a positive interval.
- Apply the enabled preference during daemon lifecycle operations and re-read settings before updates and recurring waits. Preserve updater preferences and unknown fields when saving remote-control settings, using atomic file replacement.
- Signal the updater's process group on Unix so stopping it also terminates installer children. Allow daemon shutdown even when settings are malformed.
- Document updater configuration and remote-control preference behavior. Manual `codex update` remains unaffected.
## Testing
Add tests for settings preservation, interval validation, recurring waits, enabling and disabling updates across restart and bootstrap, Unix installer termination, and shutdown with malformed settings.
GitOrigin-RevId: 5dbb72c5939e9ced2390b3760a7265608c8b61a0
## Why
A fork cutoff can remove the only `TurnContext` recording the source thread's selected multi-agent version. Forking before the first turn must preserve that version, including when the child is resumed before its first turn.
## What changed
Recover the version from the untrimmed source history or loaded parent, independently of permission overrides, and carry it into the fork's session metadata for `last_turn_id` and `before_turn_id` cutoffs.
## Testing
Add regression coverage for forks before the first turn across legacy and paginated history modes, with loaded and unloaded parents and explicit permission overrides. Verify that the child persists `MultiAgentVersion::V2` and still uses the `collaboration` tools after restarting and resuming.
GitOrigin-RevId: d7e30cf8bfdeb4f755fefab3d1d0884964d7c977
## What changed
Represent denied read paths and globs with `PermissionContext` and render them through a sync-only section in `codex-guardian-context`. Keep policy resolution in the host and preserve the existing permission warning in Guardian review prompts.
## Testing
Extend registry tests to verify permission sections appear only for synchronous reviews. Extend the session reuse test to check that resolved denied paths and globs appear in both the initial review request and the next review's delta.
GitOrigin-RevId: a966a14b367f1eedb5a577f7ed74a869559ae646
## What changed
- Replace `ComposedContext` with ordered `ContextSection` values that retain section identities through transcript selection and rendering.
- Add a shared `PlannedAction` section and renderer for core synchronous approval prompts and the Guardian V2 asynchronous scorer, preserving full, delta, terminal-input, and network-request framing.
- Keep action JSON and retry reasons out of `PlannedAction` debug output.
## Testing
Update registry and transcript tests to assert section identities and source roles. Extend registry coverage to verify planned-action collection for both consumers and omission of action JSON and reasons from debug output.
GitOrigin-RevId: 675b841a2cad06afce03f414615b4d7aa0553b13
The musl CLI allocator needs declared native tools and consistent header
flags. Configure `tikv-jemalloc-sys` to use Bazel's Make toolchain and LLVM's
`llvm-nm` and `llvm-ranlib`, and patch its build script to honor `MAKE`.
Preserve `CFLAGS` and `CXXFLAGS` when generating jemalloc header dependencies
so dependency generation uses the same compiler flags as compilation.
GitOrigin-RevId: 4022b587ce0c8bce9331c541adbdf29c1d245558
## Why
Starting a latest-channel standalone daemon required a separate `bootstrap` to enable automatic updates. A missing updater could also leave a running server without automatic updates until `bootstrap` was run again.
## What changed
- Ensure a single supported updater after managed `start`, `restart`, and restarts caused by remote-control changes. Repeated starts recover a missing updater while reusing the running server.
- Report updater failures as warnings so successful server starts and restarts still succeed.
- Preserve an existing updater while the latest-channel marker and managed binary may be temporarily inconsistent during installation. Stop it when the latest-channel marker is removed.
- Document automatic updater startup and the limitations of detecting out-of-band binary replacements.
## Testing
Add Unix tests for updater reuse and recovery, invalid updater records, marker mismatches and release pinning, unmanaged servers, and bootstrap status for managed local builds.
GitOrigin-RevId: 44148a8d65709f68def2072f542494620d7e574b
## Why
A code-mode `exec` wrapper and its nested tool calls each advance Guardian's score lag. Counting the unscored wrapper against its own nested approval can trigger a synchronous review sooner than needed.
## What changed
Track originating response items and approval tool-call IDs so cached approvals discount their own wrapper when it is newer than the latest score. Preserve wrapper identity across yields and waits, and retain the full lag when provenance is missing or evicted. Other wrappers and scoring failures still count.
Use the current `write_stdin` call's identity for approval freshness, and omit tool-call identity for `execve` intercepts that only retain the launch ID.
## Testing
Add coverage for wrapper-specific discounts, already-scored wrappers, missing and evicted provenance, identity across code-mode resumes, and approval identities for stdin writes and `execve` intercepts.
GitOrigin-RevId: 4002a06d64c4e1e0a13c072303503d6ddfacad09
## Why
Configured MCP servers must not be able to request user verification, even when they reuse the hosted apps server name. Local verification identity selection also needs to distinguish a user's workspace memberships.
## What changed
- Advertise `userVerification` only to the host-owned apps MCP server and cancel verification requests from other servers before prompting the client.
- Add `CodexAuth::get_chatgpt_account_user_id()` to read the access token's opaque `chatgpt_account_user_id` only when its workspace matches the selected account. Missing or malformed claims return no identity, without falling back to another user ID or breaking ordinary authentication.
## Testing
Add coverage for capability filtering, rejection of configured servers including those using the hosted apps name, and account-user identity selection with malformed or mismatched claims. Add an MCP round-trip test showing that verification waits for a client response even in full access mode, returns the supplied proof, and discards response metadata.
GitOrigin-RevId: 156e83d5a0302c013b85e564b46b4bfe858cbdb0
## Why
Bootstrapping the app-server daemon should preserve an explicitly selected release, even when that version is currently `latest`. Older managed binaries should also be able to serve app-server without supporting the updater command.
## What changed
- Record `latest` selections in `auto-update-version` in both standalone installers and clear the marker for explicit releases.
- Start the daemon updater only for a marked stable release whose binary supports `pid-update-loop`. Existing installs without a marker require a new `latest` installation to enable automatic updates.
- Recheck the selected release under the install lock so an in-flight update cannot overwrite a new pin, including installer calls from older updaters. Recheck selection before restarting app-server or replacing the updater.
- Cancel Unix installer process groups and clean up their owned fallback locks when the updater stops.
## Testing
Add coverage for channel markers, explicit pins of the current latest version, older updater guards, updater command support, and Unix installer cancellation with child-process and lock cleanup.
GitOrigin-RevId: 4d275237bd77d896bf64dc1b85a5bca3608142c7
## Why
Executor compatibility checks need a build identity that distinguishes commits
and compiler targets independently of the package release version.
## What changed
- Add optional `providerId` to exec-server environment metadata, cached at startup
and returned by initialization and `environment/info`.
- Derive the ID as SHA-256 of `git:<lowercase commit>:<target>`. It identifies a
standard build configuration, not exact executable bytes, and is omitted when
the commit stamp or target is unavailable or invalid.
- Embed the compiler target in `BuildInfo`, preserve compatibility with historical
metadata without a target, and stamp Cargo release builds with `STABLE_GIT_COMMIT`.
- Group Bazel build-script argument files under one `--arg-file` flag to reduce
Windows command-line length while preserving file order.
## Testing
Add deterministic build-ID vectors across targets, commit normalization and invalid
input coverage, and historical metadata compatibility tests. Extend exec-server
coverage for metadata caching and ensure runtime environment overrides cannot
replace the executor's build identity.
GitOrigin-RevId: 125a18c23de7ad006571940ba305836376c983f4
## Why
Unreaped zombies still pass `kill(pid, 0)` and retain their start time, so exited app-server and updater processes can appear active.
## What changed
Read process state alongside start time with `ps` and treat zombies as inactive. When the start time matches the PID record, attempt to reap the process with nonblocking `waitpid`.
## Testing
Add a Unix regression test verifying that an exited, unreaped updater is reported inactive and reaped.
GitOrigin-RevId: 55f1cd26dbb31b5835bea76591023817f1bc10b5
## What changed
Add `ThreadManager::fork_internal_session` to start an internal session from caller-selected committed history without reading an in-flight parent turn or appending an interruption marker. Preserve parent authentication and budget sharing, and propagate fork lineage. Keep `spawn_internal_session` starting with fresh history.
## Testing
Add a regression test verifying that the fork contains only the selected history, retains its parent association and authentication manager, and stays outside the public thread registry.
GitOrigin-RevId: df4260ed3adfa0abe7a07c2b6d8b8c6ef6ba3d16
## Why
Archiving threads reads metadata from every active rollout, including unrelated compressed files.
## What changed
Add `RolloutReferenceIndex::scan_unarchived_threads` and use it when archiving. Filter canonical filenames by the requested thread IDs before reading contents, while retaining metadata-based ownership checks.
## Testing
Add tests covering reverted rollouts, requested descendants, compressed rollouts, exclusion of archived and unrelated files, and candidate ownership checks.
GitOrigin-RevId: a64f7fa25e5493ed20312f1d8216422752272bae
## Why
After a cold resume and compaction, the subagent roster omitted children whose threads had not been loaded.
## What changed
Build the multi-agent v2 roster from registered direct children and render their full agent paths. Prioritize loaded children, sort alphabetically within each group, and cap the rendered roster at eight agents and 1,024 bytes. Preserve the existing behavior for other multi-agent versions.
## Testing
Extend the cold-resume integration test to check that post-compaction context includes unloaded children, excludes grandchildren, and lists a loaded child before an alphabetically earlier unloaded sibling.
GitOrigin-RevId: 745c1622133b9c01e61f4702e4b2ef6255417f39
## What changed
Add a public `codex_core::guardian_review` module exposing `GuardianAssessment`, the assessment parser and output schema, and the review session configuration builder for reuse by the Guardian extension.
Extract assessment handling and reviewer configuration into dedicated modules, preserving the existing parsing defaults, policy prompt, and read-only reviewer settings.
## Testing
Move the existing embedded-JSON, bare allow/deny, and output-schema tests alongside the assessment implementation.
GitOrigin-RevId: cb2aba3ccdb597e2876015e718e923d4f8f36802
## Why
A standalone root forked from a worker needs its inherited user instructions for Guardian review, including after compaction. Parent input counters belong to a different thread, and omitted parent answers may have restricted an inherited authorization.
## What changed
- Adopt inherited user instructions into thread-owned retained context for standalone roots, recovering surviving checkpoint messages when needed.
- Keep inherited instructions before local evidence without sharing local acceptance counters, and preserve that distinction during reconciliation and rollback.
- Mark parent verified answers as incomplete and treat recovered checkpoint instructions as incomplete excerpts.
## Testing
Add coverage for standalone forks from copied history and truncated checkpoints, retention through compaction and resume, inherited/local ordering collisions, and rollback scope.
GitOrigin-RevId: bf716e224a1d29d6c528ef0dd7cdb118a413a08c
## Why
Incomplete retained checkpoints can omit root user instructions that still survive in live history. Queued input can also reach model history after a later-accepted answer, so recording order cannot reliably order grants and restrictions for subagent authorization reviews.
## What changed
- Reconcile retained evidence with surviving local user messages using source identity and persisted acceptance order, including answers present only in the checkpoint.
- Preserve checkpoint gaps and mark evidence incomplete when recovered instructions lack an order or conflict with an existing order.
- Restore the input-order counter from surviving local metadata so new instructions sort after recovered evidence, even without a retained checkpoint.
## Testing
Add unit coverage for source matching, acceptance ordering, persistent gaps, conflicting orders, and counter restoration. Extend subagent authorization tests to cover checkpoint resume, queued approvals, missing sources, and a subsequent revocation.
GitOrigin-RevId: 8bfbfd2c797d725796187e5cecf7f3f11a5f3380
## What changed
- Remove the `fast_decision` and `full_review` extension hooks and `ApprovalAssessment`, leaving `ApprovalReviewContributor::decide` as the approval decision interface.
- Remove the duplicate Guardian V2 fast-approval implementation and `StrictReviewReason` state.
- Require an explicit `GuardianReviewReason` for synchronous reviews.
## Testing
Migrate Guardian reviewer tests to the production `decide_approval` path and cached-score tests to the registry's decision interface.
GitOrigin-RevId: 1f9092c0ff5bb1eed0c63fa557fb3807e2e71564
## What changed
Resolve `GuardianContextMode` once at session construction and share it across history retention, replay, evidence capture, compaction, and review consumers.
Extract synchronous reviewer context policy and consolidate Guardian V2 parent checkpoint selection so sampling and fast approval use the same eligibility checks. Preserve legacy checkpoint omission and strict compatibility requirements for thread-owned context.
## Testing
Adapt existing review and history tests to the explicit context mode. Move checkpoint tests alongside the extracted selector, retaining coverage for latest-item identity, unusable checkpoints, and complete-item size limits.
GitOrigin-RevId: c73fb6fea556921acfffe758a5f709d7494019dd
## Why
`TurnComplete` arrives before the active turn is cleared, so submitting a
rollback immediately can race with turn cleanup.
## What changed
Wait for the thread-idle callback with a 10-second timeout before rolling back
in the first-turn model-change and generated-image tests. Fail immediately on
an error event while waiting for `ThreadRolledBack`.
GitOrigin-RevId: c17b35d709b2c74361dd7933506ae192464ea4e8
## Why
Shell snapshot failures were grouped under `capture_failed`, making failure causes and retry attempts indistinguishable in metrics.
## What changed
- Add `purpose` (`execution` or `prewarm`), `attempt`, `shell`, and `sandbox` labels to capture counters and durations.
- Report bounded failure reasons such as `spawn_failed`, `timeout`, and `nonzero_exit` while preserving the original RPC errors.
- Include `failure_reason` on duration metrics as well as counters.
## Testing
Update the bounded retry and single-flight test to assert per-attempt metric labels for execution and prewarm captures, including failure reasons on both counters and durations.
GitOrigin-RevId: 907dc98736c5b8f91006909dacc43278efb43abf
## What changed
- Use `decide_approval` for MCP elicitations, carrying the effective approval policy, reviewer, and synchronous-review requirement into the decision.
- Preserve unsupported form and URL elicitations for user review.
- Use `computer_use_review_required()` for review evidence, session policy, and turn metadata so model policy takes precedence over the legacy flag.
- Derive strict-review notifications from each assessment's review reason.
## Testing
Add coverage for model policy precedence, user and full-access modes, sensitive elicitations, independent code-mode and nested-tool policies, cached score reuse, and user review of unsupported elicitations.
GitOrigin-RevId: d0a9c40572dca7b3dbf876230d2162b72728084d
## Why
Artifact checksums alone do not authenticate the downloaded checksum manifest. V8 downloads need a trusted digest recorded in the repository, and published releases should not have their assets overwritten.
## What changed
- Pin the V8 `150.4.0` release manifest digests and verify manifests before downloading archives or bindings in packaging and `setup-rusty-v8`, preserving CRLF support.
- Refuse to replace published V8 releases, remove unfinished drafts on retry, and use `gh release create` to upload assets before publication.
- Install Windows `sccache` through a pinned `taiki-e/install-action` in the release and canary workflows.
- Document independent manifest verification and digest recording for version updates.
## Testing
Add five packaging tests covering successful downloads, CRLF manifests, tampered manifests, missing pins, and missing pin files. Rejection tests verify that artifacts are not downloaded.
GitOrigin-RevId: 5c771cdcff376388e124faa4826bf81135d84b50
## Why
Concurrent parent compaction can remove evidence between Guardian checkpoint selection and prompt construction. New user instructions or answers received during a review can also invalidate an approval based on earlier authorization.
## What changed
- With `GuardianThreadContext` enabled, use the same parent history snapshot for checkpoint selection and prompt evidence.
- Cancel completed allow decisions if the owning session's user-message revision or root authorization version changed during the review, even without cacheable review evidence.
## Testing
Add regression coverage for evidence preservation during concurrent compaction and aborted approvals after new user instructions or verified answers. Extend reviewer context rollover coverage to exercise `GuardianThreadContext`.
GitOrigin-RevId: 1c2c82197a27c0d3d45b6fe08d200a835d80cc30
## What changed
- Let approval extensions choose between cached approval, synchronous review, and a user prompt for tool and permission requests, while core enforces mandatory Guardian and fresh-review requirements.
- Carry an optional `review_reason` on Guardian assessment events and use it to trigger strict-review notifications, retaining the fallback for older events.
- Require synchronous review when cached evidence has an unusable encrypted parent compaction.
## Testing
Add regression coverage for manual prompts and cached approvals with non-UTF-8 working directories. Update approval contributors in existing tests to use the decision API.
GitOrigin-RevId: a4e66416070bdaa881daa41429c49021629f44c1
## What changed
Advertise the experimental `codex/auth-change` capability for stdio MCP connections with an auth manager. When the server opts in, send `notifications/codex/authChanged` after initialization and on subsequent auth changes, with credential and owner generation counters and no credentials.
Track owner changes separately from credential refreshes so consumers can detect login, logout, or user, workspace, and auth-mode changes even when notifications coalesce. Treat credential changes with incomplete owner identity as owner changes as well.
Tie the notification watcher to the managed client's lifetime, limit each send to five seconds, and close the connection if a subsequent notification fails.
## Testing
Add tests for credential refreshes versus owner changes, coalesced logout and account switches, capability opt-in, notification payloads, and watcher cleanup.
GitOrigin-RevId: 35a99f5252bd48ca60a71fbdd1f708a8158e812c
Route `gpt-5.6-luna` POST requests through `luna_response` using the shared
classifier state in the guardian compaction and rollback test. This gives
HTTP classifier requests the configured mock score instead of treating them
as guardian review or parent requests.
GitOrigin-RevId: 3841705c7ed1ec564662c33f71e1c78e9b960c68
## What changed
Delete `codex-rs/app-server/README.md` and remove references to it from `AGENTS.md`, while retaining the requirement to update app-server docs and examples when API behavior changes.
GitOrigin-RevId: 664f38c4939a9784b1241225e5101b97ec4ae9e6
Set `SessionTarget::cwd` to `None` in the remote resume permission-override
and CLI fork startup tests to match the struct's required fields.
GitOrigin-RevId: d1e7a2e6b7ae3dda17ef062984917861c12fdeff
## Why
When no healthy pooled WebSocket is available, classification waits for a new connection to open and can stall on its handshake.
## What changed
- Use HTTP streaming when no healthy idle WebSocket is ready, and replenish the pool in the background with a five-minute cooldown after connection timeouts.
- Share concurrency limits and the sampling retry budget across both transports, and bound the wait for HTTP response headers.
- Cancel superseded requests while awaiting response headers and stop SSE polling when the consumer closes.
## Testing
Add coverage for HTTP fallback and recovery after cooldown, shared transport capacity, stalled response headers, and cancellation before headers or during body draining. Update sampler and extension tests to cover fallback after socket expiry, authentication changes, and transient failures.
GitOrigin-RevId: 0b23ccc1bfb2dfdbc8d2791d097706cd4dd44f39
## Why
Session transitions need stack headroom for embedded-server initialization and configuration loading. Running them inside event dispatch risks exhausting the TUI thread's stack.
## What changed
- Queue `/resume` and valid `/cd` requests for processing after event dispatch returns.
- Reject additional `/cd` requests while one is pending, and recheck the source session, working directory, idle state, and remote-environment restrictions before applying it.
## Testing
Add a Unix PTY regression test that exercises `/resume`, worktree conversation forks, `/cd`, and new worktree conversations through the real TUI event loop. Update the directory-change test to verify that dispatch queues the request without immediately changing configuration.
GitOrigin-RevId: 4950921931dfaba9e55e6bb04f98f7ba64b72122
## What changed
- Carry the working directory from `thread/list` and `thread/read` in session selections, and use app-server metadata to resolve resume and fork directories.
- Use the model reported by thread reads and thread-started notifications when restoring session state.
- Remove TUI helpers that read session IDs, working directories, and models directly from rollout files or the state database. Picker selection now requires a thread ID in the selected row.
## Testing
Extend picker coverage to verify that selections preserve the working directory, and add a snapshot asserting that switching to a read thread displays the server-reported model.
GitOrigin-RevId: c9d13e1e56ea2139d3e96344d72ca9ee2de73396
## Why
The TUI's local provider configuration can differ from the active thread's provider, causing `/status` to show misleading provider details.
## What changed
- Use the server-provided model provider ID in `/status` and update it when attaching to a thread.
- Omit the provider row until a thread is configured, and display IDs such as `openai` instead of provider names and base URLs.
- Remove runtime provider URL resolution from TUI startup and the associated widget state.
## Testing
Add regression coverage for provider display before session configuration, thread switching, and server settings updates. Update status snapshots to show server provider IDs while preserving usage-link behavior based on the server's authentication requirement.
GitOrigin-RevId: 87214b4fd971f63835e382557969e4fc3b602745
## Why
Client defaults can override the fork destination's model and reasoning effort or trigger a migration prompt for a stale model.
## What changed
- Omit implicit model and reasoning effort overrides during CLI fork startup, while preserving explicit launch settings.
- Skip the model migration prompt and service tier inference when the fork's model is left for the server to resolve.
- Initialize unspecified reasoning effort from the forked session's response.
## Testing
Add a startup regression test that changes server defaults after bootstrap and verifies that `thread/fork` proceeds without a migration prompt, model or reasoning effort overrides, an inferred service tier, or a `config/read` request.
GitOrigin-RevId: 858f0fe3c72b90bdcaf31b400144d37af5bc6ed7
## Why
Device-authenticated verification needs an app response outside automated approval and review. Previously, MCP user-verification requests were always cancelled.
## What changed
- Add typed `openai/userVerification` elicitations carrying a title, description, and challenge through core and app-server.
- Route verification to one connection enabled by trusted host activation. Restrict responses to that owner, exclude requests from replay, and cancel on disconnect or authentication changes, including account switches away and back.
- Return proofs in `content`, discard response metadata, and cancel malformed acceptances. Suppress verification response logging and analytics, and send only a generic verification notice to realtime.
- Keep the mode experimental and exclude it from stable schema exports. Capability advertisement remains disabled, and the TUI cancels verification requests.
## Testing
Add coverage for owner isolation, disconnect and authentication races, proof response handling, automated-review bypass, inactive-host cancellation, stable schema filtering, and realtime payload exclusion. Update the MCP integration test to verify that an activated request holds the tool until the client responds.
GitOrigin-RevId: c8c7b6691a3f7756682bbcca9def1df0d1feb906
## Why
The permissions picker displayed profiles from the connected app server but disabled selection of remote custom profiles.
## What changed
- Enable named profile selection through `thread/settings/update` and track pending selections until server confirmation.
- Use pending or confirmed server permissions for subsequent turns, preserve profiles across forks and prompt edits, and reconcile pending selections on reconnect.
- Block conflicting permission changes and forks while selection is pending. Preserve input when selection fails and report unsupported app servers.
- Reject working directory changes while a remote named profile is active.
## Testing
Add regression coverage for profile selection, turn permissions, pending-selection guards, prompt-edit profile preservation, reconnect reconciliation, and profile inheritance in forks and side conversations.
GitOrigin-RevId: 76e9bb7b4d631b1066974da013d9915a89dc54a7
## Why
Local permission settings could overwrite a remote task's saved server settings when resuming or forking, including its named permission profile.
## What changed
- Omit permission overrides from remote resume requests and remote fork requests that inherit saved settings.
- Reject explicit permission overrides when resuming or forking remote tasks, including overrides from session flags and selected configuration profiles.
- Refresh restored runtime permission and approval overrides after a remote resume so settings from the previous task do not persist.
- Carry the selected fork permission mode through retries after unarchiving.
## Testing
Add regression coverage for restoring saved server permission profiles, approval policies, and approval reviewers across resume and fork; rejecting explicit remote resume overrides; and clearing stale restored runtime overrides.
GitOrigin-RevId: 465c0444df380553e50ddbeeceff9dc64e5bf9c1
