## Why
A Guardian review restarting from the parent checkpoint must bypass cached reviewer sessions and snapshots, even when another review is using the cached session.
## What changed
- Add `ReviewerRequest::requires_fresh_session` and enable it for parent-checkpoint recovery.
- Replace an idle cached session with a fresh reusable session, or start a fresh ephemeral session when the cached session is busy. Neither recovery path inherits a cached snapshot.
- Reserve the review permit before validating a cached session and before exposing a newly spawned session to concurrent requests.
## Testing
Add tests covering recovery with idle and busy cached sessions, verifying that recovery receives no cached snapshot and that subsequent reviews reuse the appropriate session.
GitOrigin-RevId: 894f685736da54312336932aa2037e74a20629d9
## Why
Reviewer compaction can invalidate previously admitted transcript evidence. When a parent checkpoint is available, restarting from that checkpoint preserves the captured parent context instead of relying on a lossy reviewer summary.
## What changed
- Restart an invalidated reviewer once from the action-time parent checkpoint, within the original review deadline.
- Preserve fresh checkpoints during startup and fit review input using the existing budget selection.
- Select transcript evidence from the checkpoint actually loaded by the reviewer. Track the transcript source so cursors remain valid across legacy-history eviction and reset when the source changes.
- Resume transcript deltas after successful recovery, including authorization added after the parent checkpoint.
## Testing
Add regression coverage for checkpoint recovery, post-checkpoint authorization, resumed deltas, and stopping after one restart. Extend history tests to cover both legacy retention and parent-checkpoint reuse, and update the checkpoint-migration snapshot.
GitOrigin-RevId: bc20fb9489afaad963303beff1c79f62fa5023f7
## What changed
Use `OPENAI_API_KEY` for the Guardian Decisions sampler when `CODEX_GUARDIAN_DECISIONS_API_KEY` is absent, the provider is `openai`, and no custom base URL is configured. Preserve dedicated-key precedence, including empty values, and do not fall back for other providers or custom base URLs.
## Testing
Add a credential-selection test covering fallback, dedicated-key precedence, empty dedicated keys, and provider and base URL restrictions.
GitOrigin-RevId: a2a62c28789597f013544b51e142b21f9e214080
## What changed
Expose two JavaScript globals for consuming results as inputs settle:
- `as_settled(promises)` returns an async iterator of fulfilled and rejected records in settlement order, preserving queued results while the consumer is busy.
- `stream_settled(promises, emit)` delivers those records to a callback, awaiting each invocation and propagating callback errors.
Records include an `index`, a `status`, and either a `value` or a `reason`. Iterable inputs use positional indices; `Map` inputs retain their keys. Both helpers accept promises, thenables, and plain values.
## Testing
Add runtime coverage for ordering, input types, object identity, callback behavior, early iteration exit, and termination. Add stdio and gRPC host tests for partial results across waits, plus a scenario snapshot verifying fulfilled and rejected records reach the model.
GitOrigin-RevId: cddc9f3679ae04f2421e154caa0417afb15f550d
## Why
Incremental namespace declarations contain only changed or added tools. Their descriptions need to make clear that previously declared tools remain available unless explicitly marked unavailable, and that redefinitions replace earlier definitions.
## What changed
Append this guidance to updates of existing namespaces, preserving any namespace description. Leave initial declarations and catalog hashes unchanged.
## Testing
Extend unit and request-history coverage for the namespace hint, unchanged turns that append no tool definitions, and MCP tool removals that append a standalone notice without rewriting history or repeating the notice on the next turn.
GitOrigin-RevId: e32f3c9948efb44a1253868fe67967f117cc21e8
## Why
Manual, pre-turn, and post-turn compaction previously deferred rebuilding initial context until the next turn. Their saved replacement history could omit refreshed instructions and skill catalogs.
## What changed
- Install initial context during local and remote compaction, before the last real user message or summary, keeping the compaction summary last.
- Persist matching full world-state and turn-context baselines with every replacement instead of retaining only partial extension metadata.
- Build replacement context and recompute token usage for the current model even when the previous model performs compaction. Reuse that captured context for eligible current-model retries.
- Capture manual compaction context centrally and propagate preparation errors to the task runner.
## Testing
Update assertions and snapshots for context ordering, refreshed instructions, resume and fork history, current-model checkpoint baselines, and cloud skill catalog retention across compaction and resume.
GitOrigin-RevId: 8572a76c31c6884a3c580b3bbb350d49af876bd1
## Why
The Decisions adapter rejected developer messages, including host-annotated trusted-tool context. Requests containing that context could not be classified.
## What changed
Append developer text annotated with `TrustedTool::KIND` to the classification rubric, preserving its authority while keeping user evidence in the input messages. Accept only a single text part with a single matching annotation; continue rejecting other developer messages and unsupported evidence.
## Testing
Add a regression test covering trusted-tool context alongside untrusted user text, plus rejection of incorrect roles, missing or mismatched annotations, multiple annotations or content parts, and image content.
GitOrigin-RevId: 65b6301b2ee1ac54d67275978ccb5e37dcac7c16
## Why
MCP elicitation reviews used turn-start context, which could omit remote environments that became ready before the tool invocation and use stale environment permissions.
## What changed
Capture the issuing step's Guardian review context with each live MCP invocation and reuse it for elicitation reviews. Fall back to turn context when no matching live invocation is available, and preserve the captured context for in-flight actions.
## Testing
Extend the deferred-executor regression test to cover MCP elicitations, checking that Guardian receives the newly ready remote environment and its denied paths, excludes stale local denied paths, and returns the denial to the parent model.
GitOrigin-RevId: 0cc58b8f30543a9af87d53e1a90f574a8e6a2f84
## What changed
Measure `responses_duration` directly around `sampler.sample()` in the snapshot classification path. Leave it unset for conversation classification instead of timing submission and waiting for the score.
GitOrigin-RevId: 4cfac9db6f19f3c8513d7bf839ea9631d41bf3ac
## Why
Aborting a refresh task cannot retract a response already queued for delivery. The test helper could consume that stale response and return before the replacement refresh completed.
## What changed
Make `finish_overview_refresh` skip responses whose request ID does not match the active refresh. Extend the lifecycle test to queue an invalidated response before removing a task, exercising the wait for the replacement refresh.
GitOrigin-RevId: 97341681682e8dce9a9512fbcc1d5c0351b084f5
## Why
An already-cancelled delegate spawn can report a runtime admission or startup error instead of `TurnAborted`, including when runtime shutdown has been requested.
## What changed
Check the cancellation token before runtime admission and session startup so prior cancellation returns `TurnAborted` immediately after approval-policy validation.
## Testing
Extend the pre-cancelled spawn test to cover both normal operation and requested runtime shutdown, asserting `TurnAborted` within a one-second timeout.
GitOrigin-RevId: 5a25a211acdd5c246a3c638243ccc8b7240fd051
## Why
Snapshot classifier requests can arrive out of order, so continuation tests need to keep the next tool blocked until the current tool's classifier request has been captured and checked.
## What changed
Gate every mock Guardian review in high-risk review continuation scenarios. Release each review after checking the corresponding classifier request, preserving the ordering needed by the existing assertions.
GitOrigin-RevId: 9e52acd2bb1ce2fb71100fe0e1b92304d29e9634
## Why
The warning assertions need tracing callsite interest to remain independent of untraced parallel tests, even when the test runner already owns the global subscriber.
## What changed
Run the test on a current-thread Tokio runtime and capture warnings with a thread-local subscriber and an explicit buffer. Keep a `NoSubscriber` dispatch alive to stabilize callsite interest, and assert the deferral warning and `client_echo` directly against the captured logs.
GitOrigin-RevId: 5bf22b2cbfefcf8f65016d2cc1444112d9f6a6c7
## What changed
Add `tools_change_count` to turn profiles and turn analytics events. Compare the full model-visible tool list before each sampling request, retaining the previous list across turns and connection resets. The first list establishes a baseline; subsequent changes increment the current turn's count.
## Testing
Add coverage for schema changes, tool additions, ordering changes, empty lists, and tracking across sessions and transport fallback. Extend the turn event serialization test to include `tools_change_count`.
GitOrigin-RevId: 44a15c42dc7d0b35c166666faeb9627b718b33dd
## What changed
Add the default-off `stable_environment_tools` feature flag. When enabled, advertise environment-backed tools before an executor is ready, keep environment selectors stable as readiness changes, and include the `shell` and `login` parameters. Execution still requires a usable environment and its policy.
When disabled, expose environment-backed tools only when a usable environment exists, derive selectors from usable environments, and condition shell parameters on the execution configuration. Restore tool-specific unavailable-environment errors and skip the environment readiness check for `write_stdin`.
## Testing
Parameterize the empty-environment tool availability test for both flag states, check that commands require a ready transport by default, and explicitly opt tests that rely on stable tool exposure into the feature.
GitOrigin-RevId: 68c6240fb3adf85d7f9b407804d4823c515abfdc
## Why
Malformed `deny_read_acl_state.json` previously caused deny-read ACL reconciliation to fail. Recovery must restore bookkeeping without removing unknown existing restrictions or modifying a linked file's contents.
## What changed
- Retry malformed reads for up to two seconds, then rebuild bookkeeping only after excluding active writers and successfully applying current deny-read ACLs. Preserve unknown historical denies and continue propagating I/O errors.
- Validate the opened state file before reading or writing, rejecting reparse points and files with multiple hard links.
- Write state in place without truncating before validation, preserving file identity and permissions. Retry sharing violations during writes while preventing replacement through delete access.
## Testing
Add Windows tests for corrupt-state recovery, linked-file rejection, concurrent writer and delete-handle behavior, file identity and ACL preservation, and subsequent permission-profile changes. Extend the elevated sandbox integration test to verify that denied reads remain blocked after recovery while allowed writes and deletes succeed.
GitOrigin-RevId: 4aca32df00d015df3763fdc447ffdfbe3fd6cec0
## Why
Fresh starts connected to an app server can bootstrap with stale client model settings before reading the server configuration. An empty model catalog can also prevent startup even when managed new-thread defaults provide a model.
## What changed
- Read server configuration before model bootstrap for fresh starts using a local daemon or remote server without an explicit profile.
- Preserve explicit model and reasoning-effort overrides, clear implicit client settings when `config/read` is unsupported, and allow managed new-thread defaults to supply a model when the catalog is empty.
- Use the launch directory for local daemon configuration reads and the server directory for remote reads.
## Testing
Update startup-default tests to cover managed model selection with an empty catalog. Strengthen the reconnect test with a stale client model and an assertion that `config/read` uses the server directory.
GitOrigin-RevId: 8fe1485c6e66c8d46560b34d904ce1724458993a
## Why
New embedded TUI threads forced reasoning summaries off when no summary was explicitly configured, overriding the model's default. Client settings could also override the destination server's reasoning summary configuration.
## What changed
Use the same launch override handling for embedded and remote thread starts so server configuration and model defaults determine reasoning summaries. Forward explicit profile and command-line choices for `model_reasoning_summary` and `features.concurrent_reasoning_summaries`, preserving both enabled and disabled values.
## Testing
Extend coverage for model defaults reaching Responses requests, concurrent summary delivery, direct startup, and replacement sessions with profile and command-line overrides.
GitOrigin-RevId: c60e33d077298d7a89d6b95f94b1292c175d6c77
## What changed
- Remove redundant snapshot fixtures and selected rendering test cases across the TUI.
- Replace several full-output snapshots with direct assertions on messages, popup state, status indicators, and rendered content.
- Consolidate slash-command aliases, command-prefix selection, category titles, and hook events into shared test loops.
- Use shared snapshots for the setup import prompt and paginated transcript overlay across platforms.
GitOrigin-RevId: 461e30ebaf70ba930d91a135d2fc598ee4f04f27
## Why
A review can fail before the UI receives the event that enters review mode. Failed-turn completion also needs to preserve the running indicator when a queued `/review` has already been submitted and is awaiting startup.
## What changed
- Emit the review-entry lifecycle before starting the review task, after aborting existing tasks and clearing connector selection.
- When a live failed-turn completion repeats an already handled error, refresh task state only if no user turn is pending startup, and continue processing queued input.
## Testing
Add regression tests for lifecycle ordering on a server-overload response and for preserving the running indicator while a queued review awaits startup after a failed turn.
GitOrigin-RevId: 0f91d3d1a1a983542c54c2686630de9c232321b1
## What changed
Make plain `codex remote-control` start or reuse the managed daemon and enable remote control when daemon auto-start is enabled and the environment is eligible. Fall back to the foreground server when no managed backend is available or Windows restricts detached launch.
Add `codex remote-control --no-daemon` to explicitly run the foreground server, and honor the top-level `--no-daemon` flag. Reject this flag with `start`, `stop`, or `pair`. Keep `--json` and launches with configuration overrides or unsupported environments on the foreground path.
GitOrigin-RevId: cb28ae3f6074993b748660972c3cb7cbf6612c2f
## Why
Some Windows policies deny in-process reparse-point mutation while allowing the system junction creator, preventing managed daemon release selection.
## What changed
Fall back to `cmd.exe` with `mklink /J` when native junction creation or retargeting returns `PermissionDenied`. Pass quoted paths through environment variables and disable delayed expansion to handle shell metacharacters.
Create the replacement junction before moving the existing `current` junction aside, and attempt to restore the previous junction if installation fails. Preserve it for recovery if restoration also fails.
## Testing
Extend the Windows junction test to cover fallback creation, native retargeting, and fallback replacement under a path containing spaces, `&`, `%`, and `!`, while verifying that no standalone CLI installation is created.
GitOrigin-RevId: 039ee850f8c788f44f08116614ca3927e3e9952f
## Why
Pressing `/` in Vim Normal mode starts a composer search, even when the draft is empty. Allow this key to open slash commands directly on an empty draft.
## What changed
When slash commands are enabled, a standalone `/` on an empty draft switches to Insert mode, inserts `/`, and opens command completion. Preserve Vim search behavior for nonempty drafts, `?`, and pending operators.
## Testing
Add a snapshot test for the Insert mode transition and command picker. Exercise Vim slash-command entry in the transcript overlay test across terminal sizes, and extend command sparkle coverage to Vim mode.
GitOrigin-RevId: 806c2f6b841190ccdc1a258f88dfa590773ba33a
## Why
Command Center previously reset to project grouping on startup, losing the user's selected grouping.
## What changed
Save grouping changes to `tui.agents_overview_grouping` in the client’s user configuration and restore the saved choice at startup. Support `project`, `status`, and `model`, with `project` as the default. Report save failures in Command Center while keeping the selected grouping active.
## Testing
Add tests for cycling through and persisting all grouping modes, preserving unrelated settings in a custom configuration file, displaying save errors, and restoring saved grouping during startup.
GitOrigin-RevId: fd56dfecb4b79cfa8439f54420ce58cc0ed66ec7
## Why
Executable scanners can briefly hold newly staged files without delete sharing, causing the rename that publishes a managed daemon release to fail on Windows.
## What changed
Retry publication on permission-denied or sharing-violation errors at 50 ms intervals, up to 100 retries. Report the staging and release paths if publication fails.
## Testing
Add a Windows test that holds the staging directory open without delete sharing, releases the handle after a delay, and verifies that publication succeeds with the payload intact.
GitOrigin-RevId: 4fbd50934ec8937d3b440d38203a2cb7356a316d
## Why
MCP startup notifications from unrelated threads could create TUI event channels, allowing subsequent approval requests from those threads to appear in the current session.
## What changed
Check the parent of an untracked subagent before accepting its MCP startup notifications. Read thread metadata with bounded retries for threads that are not yet found or loaded, and ignore notifications unless the parent belongs to the TUI.
Share thread ownership checks across notification and approval routing, including side threads.
## Testing
Extend approval-routing coverage to verify that owned subagent approvals are preserved both before thread-start notifications and after MCP startup notifications, while unrelated threads do not create event channels or display approval prompts.
GitOrigin-RevId: 6f78f237f7441aadf10b491ed191357df75c3a6a
## Why
`/archive` was disabled during a running turn, preventing users from archiving the current session until the turn ended.
## What changed
Enable `/archive` during a running turn and warn in the confirmation dialog that archiving will stop the current turn. Cancelling the dialog leaves the turn running.
## Testing
Extend confirmation tests to cover both idle and running sessions, add a snapshot of the running-turn warning, and verify that cancellation leaves the task running without emitting archive events or operations.
GitOrigin-RevId: c7c530aa671b5f04e5dc2a637e3d27a81d98d8bf
## Why
Side conversations hide unavailable slash commands, leaving users without an explanation when searching for a known command.
## What changed
- Show matching unavailable commands as disabled rows with the reason `not available in a side conversation`. For example, `/arch` now shows a disabled `/archive` entry. Keep these commands hidden from the unfiltered `/` menu.
- Rank available matches first and skip disabled rows during keyboard selection and completion.
- Prevent `Tab` from queuing input when only disabled matches are visible, and insert `/` normally when no selectable command is present.
## Testing
Add a rendering snapshot and regression tests for unavailable command discovery, navigation, available command completion and queuing, blocked queuing of unavailable matches, and slash insertion.
GitOrigin-RevId: 7160b308ca57a24a5dcb6e2686b5248a8eb4b6a7
## Why
Environment readiness previously changed which tools and command parameters were advertised to the model, even when the selected environments stayed the same.
## What changed
- Keep enabled command, patch, image, and permission tools exposed when environments are absent, starting, or failed.
- Return a consistent message asking the model to wait when no usable execution environment is available, while preserving distinct errors for unknown environment IDs.
- Derive environment selectors from all selected environments rather than only ready ones.
- Always advertise `exec_command`'s `shell` and `login` parameters while continuing to enforce login policy at execution time.
## Testing
Expand integration coverage for empty, pending, failed, ready, and recovered environments, including stable command parameters and login-policy rejection. Update subagent and skill-catalog snapshots, with separate Windows expectations.
GitOrigin-RevId: bb08084066896a9f14b3b568c081c3eaac981db7
## What changed
- Display reasoning effort alongside the model in the agents overview, using `Unknown` when unavailable.
- Place model, reasoning, project, and usage information before attention details, activity, and the last message.
- Truncate long model and reasoning values with an ellipsis to keep each on one line.
## Testing
Update overview snapshots for the new layout and extend fixtures to cover a known model and long model and custom reasoning values.
GitOrigin-RevId: 1f36e5e1e0ccf09a851f8982bbbe4fbc7d9c7461
## Why
Windows Terminal's `sendInput` mapping delivers `ESC[13;2u` as individual console key events. Decode it as `Shift+Enter` so the mapping inserts a newline in the composer.
## What changed
- Wrap the Windows event stream with a decoder for the complete Escape-prefixed sequence, including interleaved key releases.
- Use a fixed 50 ms deadline for partial sequences and replay incomplete or mismatched input unchanged. Preserve literal text, paste events, and native key events.
- Update the `crossterm` revision and dependency lockfiles.
## Testing
Add tests for repeated and fragmented mappings, deadline handling, unchanged input, error and end-of-stream replay, and composer newline rendering with a snapshot.
GitOrigin-RevId: 95ab39960510d71322824c63817710633a2fda23
## Why
Foreground remote control on Windows should let the transport create its socket parent with a protected DACL instead of inheriting the broader ACL from a temporary directory.
## What changed
Use `codex-remote-control/rc-<pid>.sock` under `std::env::temp_dir()` on Windows, leaving parent directory creation to the transport. Keep the existing temporary socket directory behavior on other platforms.
GitOrigin-RevId: 6482ed0fc4ebc6b0e5de4e1d0e13adc93afa56d1
## Why
Path-like link labels were collapsed into their destinations, discarding the author's label text and formatting.
## What changed
Preserve nonblank local link labels alongside the formatted destination as `label (target)`, including in tables. Empty or whitespace-only labels show only the destination. Keep destination formatting and fall back to the original destination when a local file URL cannot be parsed.
Render file citations without a label so they continue to display only the formatted destination.
## Testing
Update rendering and transcript-copy tests and snapshots to cover preserved path labels, styled labels, empty labels, malformed file URLs, tables, and Markdown escaping.
GitOrigin-RevId: 2810b70f1ecdc59d7f90fa1b254b1e9069c8fc29
## Why
Third-party exposure settings can eagerly expose tool schemas or exclude tools from `exec`. Keeping eligible tools deferred lets MCP catalogs change between turns without changing the model's eager tool prefix.
## What changed
Add the disabled-by-default `code_mode_only_strict_3p_tools` feature, applied only when the effective model tool mode is Code Mode Only.
- Defer eligible MCP, app, and client-supplied dynamic tools while keeping them discoverable and callable through `exec`.
- Override `deferLoading`, MCP/app `omit_tools_from`, and direct-only or excluded namespace settings. Log conflicts without adding prompt warnings.
- Preserve disabled, app-only, policy-denied, and over-budget tool restrictions. Keep built-in tool exposure unchanged, including when a dynamic tool has the same name.
## Testing
Add unit and integration coverage for exposure overrides, effective model modes, tool eligibility, and app discovery and dispatch. Add an MCP refresh scenario that verifies the eager tool prefix stays unchanged as tools are added, replaced, and removed while `exec` tracks the current catalog.
GitOrigin-RevId: a6a8e401214119bb02ea4711473c8fa3ec85c81a
## Why
The plan confirmation prompt allowed transcript scrolling but blocked selecting and copying the visible plan text.
## What changed
Allow mouse selection and copying in the visible transcript while a bottom modal is open, preserving drags across redraws. Keep other keyboard input with the modal and suppress transcript link activation, disclosure toggles, and follow-control clicks during modal mouse handling.
## Testing
Extend the plan prompt test to cover selection, `Ctrl+Insert` copying, selection highlighting, and popup bounds. Add coverage confirming that ordinary and Control-clicks do not open links in selection-only mouse handling.
GitOrigin-RevId: 9e1fdfcb4bc18215e62a714f173bc8cb372b090a
## Why
Tool availability can change between calls. Conditioning discovery guidance on whether deferred tools are currently present changes the `exec` description when the catalog changes.
## What changed
Always include the configured discovery guidance in the Code Mode `exec` description, even when no deferred tools are present. The default guidance explains how to find tools in `ALL_TOOLS` and notes that availability can change between calls. Custom guidance and explicit empty overrides remain supported.
## Testing
Add regression coverage for stable guidance with empty and populated deferred tool catalogs in both Code Mode configurations, including custom and empty overrides. Update tool-description assertions and request snapshots.
GitOrigin-RevId: 086ea19a48e3c51ec8c429a619676a936d658721
## Why
Releases can contain different resources while shipping identical executable bytes. The daemon must recognize those release changes, while a stale updater should be able to hand off without restarting an already-current daemon.
## What changed
- Include a digest of the resolved executable path in `ExecutableIdentity` to distinguish release generations with identical binaries.
- Keep content-only comparisons for package preparation and manual update reporting.
- Check the running daemon's identity and version before restarting during updater adoption, manual updates, and production restoration. Preserve scheduled retries when the daemon is not ready.
## Testing
Add coverage for path-sensitive identity, scheduled no-op updates that preserve the daemon, and resource-only release updates that restart it despite identical executable bytes.
GitOrigin-RevId: bbea06cf502abb2251e70d4ba4b422cae867116c
## Why
`AbsolutePathBuf::relative_to_current_dir` previously read the current directory even for absolute paths, causing resolution to fail if the current directory had been deleted.
## What changed
Route absolute inputs through `from_absolute_path` without querying the current directory. Relative inputs continue to resolve against the current directory.
## Testing
Extend the Unix regression test to verify that `relative_to_current_dir` succeeds with a deleted current directory and produces the same normalized path as `from_absolute_path`.
GitOrigin-RevId: 6bc6cb43d9f4d57359639708c4d30524d89cfa92
## Why
The managed daemon writes an executable and Unix-style state beneath `CODEX_HOME`. Windows-mounted WSL filesystems (DrvFS/9p) do not reliably support the required permission semantics, which can cause startup to fail before the TUI opens.
## What changed
Detect WSL homes on 9p filesystems, checking an existing ancestor when `CODEX_HOME` does not yet exist. Keep the TUI in embedded mode instead of automatically starting the shared background server, and show a startup warning explaining the exclusion.
## Testing
Extend the daemon exclusion warning snapshot to cover the Windows-mounted WSL message.
GitOrigin-RevId: 995e6236d79d8190b0ab1e6b4761eeef3c068467
## Why
In `CodeModeOnly`, MCP resource helper definitions changed when the first server was added or the last server was removed.
## What changed
Always register `list_mcp_resources`, `list_mcp_resource_templates`, and `read_mcp_resource` in `CodeModeOnly`, even without configured MCP servers. This keeps their definitions stable across server configuration changes.
## Testing
Add a regression scenario that calls all three helpers before adding a server, with a server registered, and after removing it. Assert identical tool definitions across requests, empty resource and template lists, and the expected error when reading from an unknown server.
GitOrigin-RevId: c5777efac250b83dd4bb1c9100a6b6169470556f
## What changed
When `IncrementalTools` is enabled for Responses Lite, track tool definitions in world state and conversation history. Send the initial catalog once, then append only added or changed definitions while preserving earlier request history. Emit developer notices for removed tools and namespace instruction changes.
Use history-supplied definitions for normal requests and remote compaction, and omit empty `additional_tools` prefixes. Keep the existing tool delivery behavior for the Responses API and when the feature is disabled.
## Testing
Add unit and snapshot coverage for catalog and namespace transitions, empty catalogs, and stable hashing across JSON object key order. Add a request-history scenario covering unchanged tools, a model switch that changes one definition, persisted catalog hashes, and Responses API behavior.
GitOrigin-RevId: 76bde175973b81f8ad23873919da3c8ddcdf6065
## Why
Changing a deferred tool's output schema could add or remove the shared MCP type preamble from the `exec` description.
## What changed
Include the default or configured MCP TypeScript preamble whenever `code_mode_only` is enabled, regardless of the available tools' output schemas. Preserve an empty preamble override as a way to omit the section.
## Testing
Add a regression test that checks description stability when a deferred tool gains an MCP output schema, covering default, custom, and empty preambles. Update description expectations, request snapshots, and two Guardian context-budget test thresholds for the added preamble.
GitOrigin-RevId: 725035d6159e9da3c4beff5482c426c082e768b4
## Why
When `flush_transcript_tail_on_session_end` is enabled, remaining speech must be available in thread history as soon as realtime closure is reported, even while a model response is still running. Saving that transcript should not trigger another model request.
## What changed
Record the transcript tail directly in model and client history, attaching it to the active turn or creating a completed history turn when idle. Flush persistence before emitting `RealtimeConversationClosed`, and keep realtime context active until recording finishes so the return to text instructions follow the transcript.
## Testing
Extend core and app-server tests to cover immediate history visibility in paginated and legacy modes, idle and active turns, closure without extra inference, transcript reuse in subsequent text turns, and interruption after closure.
GitOrigin-RevId: ae323b711f22aa88db1432e24ad4bb3eb3f08f6b
## Why
Flattened notification settings prevent `serde_ignored` from detecting unknown keys in `[tui]`, allowing them to pass `--strict-config` validation.
## What changed
Detect unknown TUI keys by comparing configured keys with a serialized `Tui`, keeping accepted keys derived from the configuration type. Apply this check to config files and `-c`/`--config` overrides so keys such as `tui.bogus_key_xyz` produce an unknown-field error while valid notification settings remain accepted.
## Testing
Add regression coverage for unknown TUI keys, diagnostic source ranges, valid notification settings, and generic validation behavior. Extend CLI tests to cover TUI overrides and config validation before terminal checks.
GitOrigin-RevId: b04467523442183e7a54415d82c3f632f97ef319
## What changed
Add a scenario test and snapshot covering the request before remote `/compact`, the compaction request, the persisted replacement history, and the first subsequent user turn.
Capture the replacement history before the next turn can update its context, and assert that the compaction request contains one `compaction_trigger` and the next request includes the returned encrypted checkpoint.
GitOrigin-RevId: e22e12f16bdb11b1296e81a2e0ffd5f70e560ff6
## What changed
After successful Amazon Bedrock setup, check whether the configuration uses AWS GovCloud. If detected, show application configuration and security guidance with a terminal hyperlink and require an explicit Enter press to continue. Allow scrolling in short panes while keeping the acknowledgment visible.
Continue onboarding without the warning for non-GovCloud configurations, failed checks, or checks that exceed the 15-second timeout.
## Testing
Add snapshots and tests for the checking and warning screens, explicit acknowledgment, guidance hyperlinks, and scrolling in short panes, including a one-row content viewport.
GitOrigin-RevId: d5d0352af0a50b58e8b8feab5daf75fde428ece7
## What changed
Persist the service's last reported lifecycle reason and numeric HRESULT in the existing service registry key. Distinguish requested stops, shutdown, owner removal, startup failure, broker failure, and interrupted registration, and reset the record on startup. Recording is best-effort and does not affect the service lifecycle.
Emit `codex.windows_sandbox.service_stopped` when a provisioning client observes a stopped service, including the recorded reason, HRESULT, and Windows service exit codes. Recheck the service status and registry record before emitting to avoid pairing inconsistent evidence during a concurrent restart. The metric counts observations, not unique outages; the recorded reason is advisory.
Update the cached service status only after `SetServiceStatus` succeeds. Extract diagnostic error codes from typed errors without collecting error text or user data.
## Testing
Add a test covering Win32-to-HRESULT conversion, preservation of Windows HRESULTs through error context, and a zero fallback for untyped error text.
GitOrigin-RevId: d0d39d091410e2b5499a0803475804d12235f836
## Why
Archiving or deleting the selected task could make Command Center selection jump to the current task instead of a neighboring task in the displayed list.
## What changed
Choose the next surviving task in displayed order before removing tasks, falling back to the previous task when needed. Apply this selection behavior to archive, delete, and hide actions, respecting filtering and grouping.
Preserve the pending selection across view rebuilds, batched removals, and duplicate server notifications. Allow selection to fall back when a rename target disappears while retaining the existing notice about its unsubmitted title.
## Testing
Add regression tests and snapshots for archive/delete selection across project, status, and model grouping, with and without filtering. Cover removal of the attached task, external removal notifications, removal of a pending successor, repeated repaints, and an empty task list. Update the disappeared-rename-target snapshot to verify that the remaining selection is preserved.
GitOrigin-RevId: ca93d664fadbc602993fbdae316c7a375b449345
## What changed
Render confirmation dialogs as centered overlays while preserving the composer or parent picker behind them. Share dialog sizing and cursor placement across stacked views and full transcript rendering, with input still routed exclusively to the active dialog.
Use the shared confirmation preset for prompts including full access, session archive/delete, goal changes, and log upload consent.
## Testing
Add coverage for backdrop retention and cursor routing at multiple terminal sizes, and for preserving the compact viewport and composer draft after dismissing a confirmation without replaying history. Update confirmation snapshots to show the retained backdrop.
GitOrigin-RevId: 026af89904ec345e2b330317b8cc844512125d0e
## Why
Accepting a Find result must not let a held `Enter` submit the composer draft, including when terminals report repeated keys as fresh presses.
## What changed
- Make `Enter` accept the displayed result for reading, while `Ctrl+P` and `Ctrl+N` navigate older and newer matches.
- Make `Escape` cancel query editing and restore the pre-search presentation; after acceptance, it returns to the latest transcript content.
- Consume unmodified `Enter` while reading a result, but let modified `Enter` reach configured composer bindings.
- Update footer hints to show acceptance, cancellation, and the active Find state.
## Testing
Extend input-routing coverage for repeated `Enter` presses and modified composer bindings. Update search tests and footer snapshots for acceptance, cancellation, and result navigation.
GitOrigin-RevId: 2a2b7c389240ffa941e3623d7fb7d877455fa9a5
felixxia-oai