## Why
Paginated MCP server status requests previously discovered all configured servers before selecting the response page, causing unnecessary connections to servers outside that page.
## What changed
Select and deduplicate server identities before discovery, then collect status only for servers on the requested page. Include thread runtime statuses when selecting pages and preserve separate entries for same-named servers in different environments. Empty pages skip discovery.
## Testing
Add coverage that counts MCP initialization requests across successive pages and an empty final page. Extend environment inventory coverage to verify that pagination preserves each registration's identity, authentication status, and tools.
GitOrigin-RevId: 0c9c9ca6c8016147eb9a12b53ffe533ac3334444
## Why
Relative attachment paths in queued submissions should refer to files in the thread's working directory, even when the app server runs from a different directory.
## What changed
Resolve relative `LocalImage` and `LocalAudio` paths against the loaded thread's current working directory or the stored working directory for an unloaded thread when adding or updating queued submissions. Preserve absolute paths and reject relative paths that cannot be resolved to an absolute path.
## Testing
Add a regression test for queue add and update with different images sharing the same filename in the thread and server working directories. Verify that the relative path selects the thread's image and that explicit absolute paths retain their meaning.
GitOrigin-RevId: 3c1a48693c031f1c650650a9b3a7059fb962ba5c
## What changed
Allow `thread/inject_items` to accept wrapped items with `retention: "default"` or `retention: "always"`, while preserving support for raw response items. Persist explicit policies separately from legacy client-authored metadata.
Carry explicitly retained items through local and remote compaction, context-window changes, and child-agent creation, subject to retention budgets. Preserve history order and keep retained tool exchanges together; require matching calls and outputs to be adjacent in the injection request and both marked `always`.
Update Quinn dependencies and record exceptions for additional Hickory DNSSEC advisories where DNSSEC is disabled.
## Testing
Update injection tests for explicit retention metadata and extend the compaction scenario to cover a retained tool exchange across repeated compaction and restart.
GitOrigin-RevId: 1195a4ed62dc162a62e58bc2ad733262fbabea27
## Why
An unset voice preference should use the call destination's default. Changed or cleared preferences should also take effect on the next V3 call, even when the thread retains an older setting.
## What changed
- Use `gpt-live-1.1-codex` as the default V3 realtime model.
- Preserve an unset voice until request serialization, defaulting V3 API calls to `marin` and ChatGPT calls to `cove`, while honoring explicit voice selections.
- Reload current voice settings when starting a new V3 call through the app server, including cleared preferences.
- Populate the TUI voice picker from the V3 catalog, add `marin` to that catalog, and remove voice-catalog lookups from call startup and preference saving.
## Testing
Add regression coverage for API and ChatGPT voice defaults, explicit overrides, changed and cleared settings, and TUI call requests and voice selection.
GitOrigin-RevId: d0dd4dcd4bcad9ab869d7bf524e7095a88ffcfaa
## Why
MCP servers registered under the same name in different environments need distinct inventory, routing, and status reporting.
## What changed
- Keep MCP inventory and runtime status keyed by registration scope so same-named servers remain separate.
- Add optional `environmentId` selectors for status lookup, tool calls, resource reads, and OAuth login. Omitting the selector preserves existing name-only routing.
- Carry environment identity through startup notifications, elicitation requests, and tool-call history, and display it in the TUI.
- Support `/mcp login <name> --environment <id>` and update generated protocol schemas and SDK types.
## Testing
Add integration coverage for two environments with identically named MCP servers, tools, and resource URIs. Verify separate inventory, explicit environment routing, legacy routing when the selector is omitted, and errors for unknown environments. Update protocol and TUI tests for environment identity.
GitOrigin-RevId: 074a3db10549438cb6aff33eb7bed10791adae4d
## What changed
- Replace individual JSON payload files with numbered Zstandard shards in trace schema v3. Add `PayloadReader` to resolve payload references, cache decoded shards, and validate payloads during replay.
- Capture exact outgoing HTTP bodies and WebSocket messages alongside prepared prompts. Preserve full formatted context for continuations from unrecorded WebSocket warmups while retaining the actual incremental request.
- Flush payload records before publishing references and seal the final shard before recording completion. Replace `recording_complete` with `recording_status` to distinguish unclosed recordings, closed recordings with partial payloads, and complete recordings.
Reduce trace bundles with the binary that recorded them.
## Testing
Add coverage for shard rotation, oversized records, live reads, cache eviction, and malformed or corrupt payloads. Extend HTTP and WebSocket integration assertions to verify captured requests and prepared prompts, including warmup continuations.
GitOrigin-RevId: 40ce3c11383f48e08f52e7120b706c61a449df9c
## What changed
Capture `codex_app_used_dictation` as per-input metadata, with patches taking precedence over replacements, and remove the key from metadata forwarded to Responses. Record attribution when user-origin input is accepted into turn history.
Add `used_dictation` to turn analytics: report `true` if any accepted input used dictation, `false` only when every accepted input has known non-dictation attribution, and omit the field otherwise.
## Testing
Add coverage for per-input extraction, patch precedence, and turn-level aggregation. Extend the app-server steering test to verify that dictation attribution reaches analytics while the metadata key is excluded from Responses requests.
GitOrigin-RevId: 0a55687a7dd61f00e9b188f89810e52bd941490b
## Why
Plan items used a single ID derived from the turn ID, so multiple completed plans within one turn shared an ID across retries or tool continuations.
## What changed
Generate UUIDv7 plan item IDs and carry an unfinished plan's ID across model requests within a turn. Once a plan completes, assign a fresh ID to the next plan.
## Testing
Add unit and integration coverage for unfinished retries, retries after plan completion, and tool continuations, including matching streamed events to saved completions. Update the app-server test to check plan IDs against the start notification.
GitOrigin-RevId: 87b4b3e6bd74224ea96f4308f739bcd2efb62299
## Why
Listing threads by ascending `recency_at` can omit `next_cursor` when rollout files have not yet been indexed in SQLite, preventing clients from fetching the remaining threads.
## What changed
Scan and index one extra rollout for ascending recency listings when SQLite is available, so the database can detect another page. Trim filesystem results to the requested page size for this sort order.
## Testing
Add a regression test that creates two unindexed rollouts after startup backfill and lists them with a provider filter and a page size of one. Verify both threads are returned in order, with a cursor only on the first page.
GitOrigin-RevId: 09354055b6e60666a493d9411ed3eb9778b73c0a
## What changed
Route direct reviews through the reusable Guardian session so sequential `thread/guardianReview` calls on the same loaded thread can share review history with live approvals. Keep the reviewer conversation separate from the actor and follow the parent thread's persistence settings. Retries reassess the final call under the current policy.
## Testing
Extend app-server coverage to verify history reuse within a parent thread and isolation between parents. Extend the core scenario and snapshot to cover sequential direct reviews without executing the recorded commands.
GitOrigin-RevId: 5f10a04aec43a9351e38575265cb6b5ff06530a5
## What changed
Consolidate cache refresh entry points around an explicit refresh mode, derive plugin keys from the configured sources, and share request matching and batch outcome handling. Clarify pending refresh state and extract the worker notification callback helper.
## Testing
Add an app-server regression test verifying that the first full plugin list installs a newly published plugin version while preserving cached contents for a plugin whose version is unchanged.
GitOrigin-RevId: 85d91ec7675e98f7430a8bd9c699118c7feb06c4
## Why
Normalizing whitespace before matching prevents thread search from producing snippets for queries containing repeated spaces, newlines, or tabs.
## What changed
Match against the original conversation text and select the surrounding excerpt before normalizing whitespace for display.
## Testing
Extend `thread_search_matches_json_escaped_content` to cover repeated spaces, newlines, and tabs alongside quotes and backslashes, and assert that the returned snippet has normalized whitespace.
GitOrigin-RevId: fffdcc8d246e7603a52c32bb5239b9873f8179fc
## Why
Lowercasing alone misses caseless matches such as Greek sigma variants and `ss` matching `ß` in `thread/searchOccurrences`.
## What changed
Use Unicode default case folding after lowercasing both search terms and text. Map folded matches back to source character boundaries so snippets highlight the original text correctly, including characters that expand during folding.
## Testing
Extend the app-server search integration test to cover sigma variants, `ss` matching `ß`, newer Unicode case mappings, and UTF-16 match ranges in text containing an emoji.
GitOrigin-RevId: 6c4937d475daf51d3cd7784b48f5f4a8ce5fa82a
## What changed
Carry `ContextWindowId` through session metadata, compaction checkpoints, rollout recording, and thread creation instead of converting IDs to strings. Add deserialization and JSON schema support while preserving the serialized string format and legacy numeric compaction IDs.
Validate deserialized IDs as UUIDv7 values before restoring context windows, preserving the existing handling of unsupported IDs.
GitOrigin-RevId: fda329d0654f438171a955c9f75550817c32c047
## What changed
Add the disabled-by-default `daybreak_program_propagation` feature to capture a parent's saved Daybreak choice when spawning native helpers. Retain the choice and account identity for helper turns and nested spawns, while preserving explicit `cyber_access_program` overrides. A helper's own saved preference takes precedence on later turns.
Read pending metadata before persisted metadata so preferences survive thread materialization, with stored choices taking precedence. Share this resolution logic with `thread/read` and support refreshing the feature through user configuration.
## Testing
Add coverage for saved and pending preferences, unset choices, explicit overrides, failed metadata reads, nested spawns, parent unloading, feature withdrawal, and preference changes between helper turns.
GitOrigin-RevId: b3b349da8cb3d48154cddf058890587385efcda2
## Why
Converting message content to tool output previously reduced file-backed audio to a text file ID, losing its audio type.
## What changed
- Allow `input_audio` tool output items to carry either `audio_url` or `file_id`, preserving both forms during content conversion.
- Account for file-backed tool audio in history estimates and output truncation, and prepare only inline audio data.
- Reject uploaded audio in raw function and custom tool output injection, extending the existing requirement to submit uploaded audio through typed turn input.
- Regenerate app-server schemas and TypeScript/Python types while preserving the Python inline audio class name.
## Testing
Add coverage for tool audio wire-format round trips, repeated file audio sharing text and audio output budgets, and rejection of raw uploaded audio injection across messages and tool outputs. Extend Python SDK coverage for the inline tool audio shape.
GitOrigin-RevId: f4704466e6151662d2c8b8dc3f5ca2ab2f5710a2
## Why
Background plugin cache refreshes fetched recommendations even when plugin recommendations were disabled.
## What changed
Pass the effective recommendation feature state into `PluginsConfigInput` and skip recommendation cache warming unless apps, plugins, and either `tool_suggest` or `recommended_plugins` are enabled. Installed-plugin cache refreshes continue independently.
Disable `tool_suggest` and `recommended_plugins` by default in core and app-server test helpers, with explicit overrides for recommendation tests.
## Testing
Update cache-warming and external-login recommendation tests to opt in explicitly. Update config RPC assertions to verify the test helpers' session flag overrides.
GitOrigin-RevId: dc04e2847c94e2b15842fcd95cc0cf1f104e1fac
## Why
An aborted turn could remain active, and a late abort for an unknown turn could interrupt a different turn with an explicit ID.
## What changed
Finalize the active turn after applying an abort. Only fall back to the active turn when the abort lacks a turn ID or the active turn has a generated ID.
## Testing
Extend regression coverage to verify that a late abort preserves a review turn's ID and completed status, and that repeating `turn/interrupt` returns `no active turn to interrupt`.
GitOrigin-RevId: 73072dda7879bd50b1013f4a0bbf1b68546f2619
## What changed
Add experimental `environments` fields to `turn/settings/update` and `thread/settings/update`. Turn updates apply to later steps of the running turn; thread updates apply to future turns. Omission or `null` preserves the selection, while `[]` clears it. Providing `cwd` in a thread update without an environment list selects the defaults for that directory.
Include the ordered environment selection in `thread/settings/updated`. Wait for Core to accept thread settings updates before returning success, and return rejections as request errors.
## Testing
Add integration coverage for attaching, replacing, preserving, and clearing environments; rejected updates; and the distinction between later steps and future turns.
GitOrigin-RevId: bfebeda57c676be94427aeb0c567c0b94fd9c387
## Why
`thread/sample` previously required the source's latest turn to finish before it could be sampled.
## What changed
Add `allowInProgressTurn`, defaulting to `false`, to sample a snapshot of the latest turn while the source continues running. The requested turn must still be the latest, but source history changes during sampling no longer invalidate the result when this option is enabled.
For an in-progress snapshot, include a context note explaining that the source was not stopped and pending tool calls may appear as `aborted` in the copy. Suppress the copy's default interruption message.
## Testing
Add coverage for sampling running turns in legacy and paginated history modes, including pending tool calls and mid-turn compaction. Verify that the source continues independently and that finished-turn samples retain their existing context.
GitOrigin-RevId: 771b979bf677e4ff0686476bfaf21aff92f7e7ac
## Why
Title and content searches exclude attached threads, preventing clients from finding their saved conversations alongside ordinary threads.
## What changed
- Add `includeAttachedThreads` to `thread/list` and `thread/search`. For `thread/list`, require a non-empty `searchTerm` and preserve the usual provider and source filters.
- Expose `attachedToThreadId` on thread responses to identify the owning parent independently of fork and subagent lineage.
- Support inclusive searches through SQLite and filesystem fallback, repairing missing database entries with saved thread names during title searches.
## Testing
Add regression coverage for opt-in title and content searches, attached-parent metadata after restart, default search filters, filesystem searches without SQLite, and discovery and repair of unindexed title matches.
GitOrigin-RevId: ac12ec3c730ad7f1722bdf8e21600d17f12017f0
## Why
Reference-backed forks can lack a local opening user message, causing them to disappear from thread listings or lose their inherited preview when a new turn is written. Compaction can also remove the opening message from the model context used to prepare a fork.
## What changed
- Persist inherited previews and preserve them when recording new turns and merging thread-list metadata.
- Include reference-backed forks with inherited history in thread listings before their first local message.
- Recover opening previews from transcript history within the requested fork boundary when compaction omits them from model context.
- Use the shared `user_message_preview` helper when deriving previews from rollout items.
## Testing
Extend thread-fork integration tests to check previews in listings before and after a new turn, after reopening, and when forking at a boundary after compaction.
GitOrigin-RevId: 5962cf71ea7104f07c9013cc77259b105e4c60d7
## What changed
Use eligible installed marketplaces as Git clone references to avoid fetching objects already available locally. Limit fetch negotiation to the recorded installation commit so local branch revisions are not advertised, and use `--dissociate` to keep the upgraded checkout self-contained.
Enable reuse only with Git 2.20 or newer and a recognized release version. Fall back to a fresh clone if reference cloning fails, and retain existing ref and sparse-checkout behavior.
## Testing
Add coverage for installation-commit negotiation, exclusion of local branch revisions, self-contained object stores, fallback with older or unknown Git versions and shallow references, and Git release parsing.
GitOrigin-RevId: 8d0f6a4bed7e7e2a3136e3912ba2f92150be9354
## What changed
Return first-party provider models in catalog order while retaining priority-based default selection and existing filtering. Apply this ordering only to provider-origin catalogs for the OpenAI provider using Codex backend routes or `model_catalog_url`. Bundled, configured, and third-party catalogs retain priority ordering.
## Testing
Add coverage showing that catalog display order can differ from priority order while the recommended model remains the default. Update custom-provider coverage to verify priority ordering with a reversed catalog response.
GitOrigin-RevId: 9c2361e070ba424c092a282ca7f1cf9952d270b3
## What changed
Move `ThreadMetadataBuilder` into its own module, make its fields private, and replace direct field assignments with fluent `with_*` methods. Initialize `updated_at` and `recency_at` from the creation time and default the approval mode to `OnRequest`.
Update `apply_rollout_items` to accept a boxed `ThreadMetadata` seed, keeping callers' async frames small while preserving existing database fields except for the seed rollout path. Add `build_thread_metadata` to use the state runtime's configured provider, and use `thread_id_from_rollout_path` directly for the doctor's filename fallback.
GitOrigin-RevId: a27e4c6b22832e902922dbdd60d7f5c11b4a1a83
## Why
Forked and recovered sessions can restore a tool call before its output has been recorded. Missing outputs for these calls should be treated as interrupted work rather than an error.
## What changed
Track the restored history's sequence cutoff so custom tool and local shell calls in that history can receive synthetic `aborted` outputs without reporting a missing-output error. Keep the existing checks for newly recorded calls and clamp the cutoff when history is replaced.
## Testing
Extend the active-turn fork test with a pending `apply_patch` call and verify that the fork's model input includes its `aborted` output.
GitOrigin-RevId: d989fa0991db72f0f8fa8a6d5de403fb307c40c7
## Why
An explicit denial from a workspace inference hook should stop the request, including retries and compaction model fallback.
## What changed
Recognize `inference_hook_denied` provider errors and preserve the provider's message, with a fallback when none is supplied. Expose the distinct `inferenceHookDenied` error through the app-server protocol and generated schemas and SDK types. Treat the denial as non-retryable during turns, compaction, and guardian review.
## Testing
Add coverage for terminal denials over HTTP, SSE, and WebSocket, error serialization and persistence in `thread/read`, and compaction failures that preserve token usage and history without retrying or falling back to another model.
GitOrigin-RevId: 2ebd480f01e52f4e6bd3db8a0f92d5814d18ccb1
## Why
MCP requests need to retain inbound W3C trace context even when no OpenTelemetry tracing layer is installed.
## What changed
- Carry validated request trace context through app-server MCP tasks, connection startup, and resource listing tasks, while preferring active span context.
- Forward fallback `traceparent` and `tracestate` headers for MCP HTTP requests, including discovery and initialization.
- Use HTTP trace headers as a fallback for exec-server RPC calls when active span context is unavailable.
## Testing
Add an app-server integration test that disables trace exporting and verifies that `mcpServer/resource/read` forwards the inbound `traceparent` and `tracestate` to the MCP server.
GitOrigin-RevId: c886a55ce0a3992f1b2e04614efec80a20cb4b49
## What changed
Mark `untrusted_as_tool_output` as stable and enable it by default. Untrusted additional context, such as browser information and goal objectives, now reaches the model as `function_call_output` items in the `agent` namespace instead of user messages. Setting `features.untrusted_as_tool_output = false` preserves the message format.
## Testing
Update core, app-server, TUI, and Python SDK test expectations for the default output format. Cover context persistence, deduplication, goal continuation, and explicit opt-out behavior.
GitOrigin-RevId: 30828351e2ed584928f6055b6dcf276d8288c0fb
## What changed
- Advertise `supportsDeviceAuth` in `account/gatewayOAuth/read` and accept `deviceAuth: true` in `account/gatewayOAuth/login`.
- Return a device prompt with `verificationUrl`, `userCode`, and `loginId` before approval, then notify the initiating connection of success or failure with the matching `loginId`.
- Reuse or refresh saved credentials when possible, returning `prompt: null` without another device authorization. Update protocol schemas, generated bindings, and documentation.
## Testing
Add an integration test covering the device prompt, correlated completion notification, capability reporting, and token refresh without another device grant.
GitOrigin-RevId: 6ecc38c9baadcfda3272654ed71e4aaa431421bf
## Why
Failure to open the diagnostic logs database should not disable thread storage or database-only history listing. Thread deletion must still preserve saved conversations when diagnostic log cleanup cannot complete.
## What changed
- Allow state initialization to continue after non-corruption errors opening the logs database, while preserving corruption recovery.
- Report the original diagnostic database error after tracing is installed in the TUI and app server, and return it from log operations.
- Reject thread deletion before destructive cleanup when diagnostic storage failed to initialize.
- Continue periodic cleanup of legacy logs when the current logs database is unavailable.
## Testing
Extend coverage for unavailable log directories, database-only history listing, startup diagnostics, deletion preserving saved conversations, corrupt log headers, and periodic legacy log cleanup during a diagnostic storage outage.
GitOrigin-RevId: a5184580ae6c39ed0c4eefa8cb48ee7731a991c3
## Why
Custom providers with gateway OAuth and an explicit model catalog should be able to discover models without an API key or API key model discovery enabled.
## What changed
- Enable catalog refreshes for custom gateway providers when `model_catalog_url` and `base_url` have the same origin.
- Reuse gateway credentials without starting an interactive login during catalog refreshes.
- Keep an unrelated saved API key from making gateway catalog discovery depend on the API key discovery setting.
## Testing
Add an app-server test for discovering a gateway catalog after OAuth login with no API key. Update coverage for catalog invalidation after gateway credentials require login, including across manager restarts, with API key discovery disabled.
GitOrigin-RevId: b133c428cb45a9037e4b2ef13ff2f9473ed96636
## What changed
Add experimental `deferOutput.mcpToolCall` support to `thread/items/list` requests scoped to a `turnId`. Successful, completed MCP calls with nonempty, unannotated plain-text results can return empty `result.content` with `outputDeferred: true`. Clients can retrieve the saved output through `thread/items/read`; connector identity remains on the listed item.
Keep rich results, JSON or fenced text, app UI results, and built-in `codex_app` results inline. Preserve plain-text output when creating bounded previews of oversized MCP results so those previews remain eligible for deferral. Reads return the saved preview when output exceeds the 64 KiB history limit.
## Testing
Extend thread history integration coverage for independent and combined command/MCP deferral, experimental capability gating, excluded result types, connector identity, oversized previews, and retrieval of deferred items.
GitOrigin-RevId: 5c160b30a4eac2a9b70e3fa65b6dbd83e935338b
## What changed
- Pass goal objectives as untrusted `goal_objective` context instead of embedding them in continuation instructions. Direct the model to use `get_goal` if the objective is missing or truncated.
- Inject newly created objectives into their originating active turn without dropping unrelated client context. Render them as tool outputs when `UntrustedAsToolOutput` is enabled.
- Queue additional context together with automatic turn input so both reach the first model request.
## Testing
Extend app-server coverage to verify that model-written objectives appear as tool outputs at creation and continuation, without duplicating them in user messages. Update steering and Python SDK tests to check objective preservation and delivery alongside continuation instructions.
GitOrigin-RevId: 6f44f6d6c895bb4dc378c9cf84d6470ccc885c67
## Why
Custom-provider sign-in previously required a saved gateway configuration and stopped at an error when none existed.
## What changed
- Add “Create a custom provider or gateway” to the sign-in picker, reusing the settings form and provider-write handling.
- Return to the picker after saving, highlight the new provider, and require explicit selection before setting it as the default and completing sign-in.
- Preserve entered fields after validation failures and keep the focused field or Save action visible in short terminals.
- Use consistent custom-provider and gateway wording across sign-in, settings, and validation messages.
## Testing
Add onboarding tests and snapshots for an empty picker, creation, validation retries, short-terminal rendering, and explicit default selection. Extend app-server coverage for rejecting the reserved `ollama-chat` provider ID.
GitOrigin-RevId: 339ac5807c5eecdae08df4dbd89874ea7c764d35
## Why
Security reminder requests need to use app-server's active authentication and HTTP runtime, with results bound to the login that fetched them.
## What changed
- Add `account/securitySetup/read`, returning an optional notice with account and user IDs, plus generated protocol schemas and bindings.
- Fetch reminders in app-server only for a matching saved ChatGPT login. Return `notice: null` for ineligible, unavailable, or timed-out reads, and discard results when the login changes during the request.
- Route TUI reminder reads through the new method while retaining notice validation and identity checks. Unsupported servers produce no reminder.
## Testing
Add coverage for shared runtime use across restarts, ineligible authentication modes, and login changes during a fetch. Update TUI coverage for unavailable, unsupported, and mismatched notices.
GitOrigin-RevId: 426fee7ce98df17970957c06876881bc5b005196
## Why
Remote-control enrollment, refresh, and client-management requests used ChatGPT bearer authentication without resolving the configured runtime authentication mode.
## What changed
Pass the app server's runtime auth slot and mode into remote control, and resolve authentication and HTTP client policy for each request. Supported OpenAI destinations use fresh runtime assertions in `dual_header` or `assertion_only` mode, while custom destinations retain bearer authentication.
Wait for runtime authentication to initialize and reject unsupported OpenAI origins or mismatched registered accounts. Pairing continues to use its server token.
## Testing
Add transport and app-server integration coverage for both runtime auth modes, fresh assertions, shared runtime registration, network policy enforcement, account validation, redirect credential handling, and pairing token preservation.
GitOrigin-RevId: 5401cf565630ab84eaba71ff6040ac27f7b92461
## Why
Regular chats start MCP servers eagerly even when cached tool definitions are available and the servers go unused. Allow those chats to use the cached catalog and defer eligible stdio servers until first use.
## What changed
- Add the disabled-by-default `mcp_lazy_stdio_startup` feature and expose it through experimental feature configuration.
- Defer cached stdio servers in regular chats when enabled, while keeping servers that require a live startup connection eager. Required servers with `startup_readiness = "catalog"` may defer; explicit reconnects remain eager.
- Announce the full eager startup batch before terminal statuses and exclude dormant servers from the initial startup summary. Update TUI tracking so deferred servers can report startup independently in later rounds.
## Testing
Add scenario coverage for a cached server staying dormant during unrelated work, starting on first use, and refreshing tool definitions and visibility. Cover required live startup, eager event ordering, experimental feature configuration, and TUI status handling.
GitOrigin-RevId: 74075fcd4f26c8c79b5901b6a8cb03fdb9e35a7f
## Why
A cached MCP tool can remain advertised after its server fails to start. Calling it previously returned a generic unavailable-tool error, hiding the startup failure from the model.
## What changed
Propagate preparation errors through MCP tool calls and recorded approval preparation, preserving the error chain and adding the server name to startup failures. Keep the unavailable-tool error for tools that are missing, filtered, or no longer visible to the model.
## Testing
Update the executor capability downgrade test to require the credential resolution startup error in the model's tool output and assert that the host token is absent.
GitOrigin-RevId: 434074eb748165b2fe19de3a40046835f26992df
## Why
Git-attribution settings requests need to honor runtime authentication for their destination. Repeated authorization failures after a credential refresh must also let world-state contribution finish.
## What changed
- Use the thread's `ProviderAuthContext` credentials and runtime authentication when available.
- Bind the settings client's network policy to the authenticated account and select authentication through the runtime-aware backend client.
- Stop policy resolution after an unsuccessful settings lookup or timeout instead of restarting it when credentials changed during recovery.
## Testing
Add app-server coverage for `dual_header` and `assertion_only` authentication with default and custom destinations, including attribution instructions in model input. Add a regression test verifying that repeated `401` responses trigger only one credential refresh and omit attribution instructions.
GitOrigin-RevId: 4824bde7d9ec11c241f1caebc754d203dbb0480c
## What changed
Allow `requirements.toml` to pin `features.runtime_agent_instances.mode` to `dual_header` or `assertion_only`. Apply the required mode when no explicit mode is configured and reject conflicting explicit settings, while preserving legacy boolean requirements.
Document experimental runtime authentication configuration, credential lifecycle, and bootstrap authentication behavior.
## Testing
Add coverage for managed mode defaults and conflicts, runtime reuse and rotation across account requests and restarts, fresh assertions on Realtime and MCP reconnects, and Realtime destination and environment restrictions.
GitOrigin-RevId: bcf9502178f477c1e8232386f1f3e360bf23d667
## What changed
Add a nullable `userId` to `GetAccountResponse`, populated from the same authenticated account snapshot as the rest of the response. ChatGPT and personal access token sessions return the canonical ChatGPT user ID when available; API-only and signed-out sessions return `null`.
Update the cloud client, generated schemas, TypeScript and Python types, and account identity documentation. Default missing IDs to `None` when deserializing responses from older app servers.
## Testing
Extend account response tests to check ChatGPT and personal access token user IDs, null IDs for other providers and signed-out sessions, and ID changes when switching providers with saved ChatGPT credentials.
GitOrigin-RevId: 7ad3da3cfc835c4d08d03c8e91b06cd7e007d874
## Why
Realtime connections bypassed runtime authentication and reused captured authentication headers for sideband handshakes. They need to honor the selected credential source and its transport policy across call creation, retries, and reconnects.
## What changed
- Use runtime authentication for realtime WebSocket connections, WebRTC call creation, and sideband attachment when enabled for supported OpenAI destinations.
- Resolve authentication on every WebSocket handshake, preserving credential ownership and request scope while generating fresh assertions. Reject authentication failures without falling back to bearer authentication.
- Keep call creation and sideband attachment bound to the selected credentials and account network policy, including when inference uses a different provider.
- Avoid runtime initialization for local marketplace and MCP operations, plugin commands that do not use the remote catalog, and model debugging with a configured catalog.
## Testing
Add coverage for fresh handshake credentials on retries and reconnects, credential and account changes, runtime authentication modes, destination validation, and registration failures.
GitOrigin-RevId: 57e53122912fa78a524427b0f51013f76f9f7681
## What changed
Refocus `openai-docs` on Codex and ChatGPT Work behavior and first-time API integrations. Skip API questions about existing integrations, action requests, and tasks fully answered by supplied text or data. Retain model migration guidance when users explicitly invoke `$openai-docs`.
Replace the broad routing workflow with guidance to check available tools and settings, consult documentation for the relevant product surface, and verify recent changes through the changelog and linked client changes or tests.
Update the skill's display metadata and affected skill catalog snapshots to match.
GitOrigin-RevId: 0a0e9abbee9975ebd30917b7477f475096f2c86b
## Why
Switching away from a model that requires automatic review should restore the user's requested approval reviewer instead of retaining the model's enforced reviewer.
## What changed
Recompute the reviewer from the requested preference and model requirements when the model changes without an explicit reviewer update, unless the session uses a trusted guardian reviewer. Preserve an explicit automatic-review preference across subsequent model switches.
## Testing
Extend the app-server settings regression test to cover restoring user review after leaving a protected model and retaining an explicit automatic-review choice across repeated model switches.
GitOrigin-RevId: a5672d1ebe94c2fac201ad460b4789d11df03b1a
## What changed
Read `final_answer_moderation` metadata and attach `moderation: { moderated: boolean }` to the completed final-answer message only when its item ID matches. Apply this in both normal and plan modes, and reset the pending decision when a new response starts.
Preserve the answer's native item ID and moderation flag through legacy events and history reconstruction. Combine text parts into one legacy event when a moderation decision is present.
Expose nullable moderation data on app-server agent messages and update the JSON schemas, TypeScript types, and Python models.
## Testing
Add an integration test for moderation on completed answers and their legacy events. Extend protocol conversion tests to cover populated moderation data and serialization as `null` when absent.
GitOrigin-RevId: f286b67731a84b3daf5d10b7644f2e31b62f0e53
## Why
Queued inputs previously stored and dispatched without the submitting client's Responses API metadata, losing attribution such as `client_type` when the queued turn started.
## What changed
- Accept `responsesapiClientMetadata` when adding or updating queued submissions and expose it on returned queue items.
- Persist metadata with the input and forward it when starting a selected item or dispatching an idle queue, including after restoration.
- Preserve existing metadata when an update omits it or supplies an empty map; replace it when a non-empty map is supplied.
- Keep stored inputs readable by older queue workers and update generated protocol artifacts.
## Testing
Extend queue service and app-server tests to cover metadata round trips, preservation and replacement on edits, compatibility with older readers, and forwarding during selected, idle, and restored dispatch.
GitOrigin-RevId: 508043b1d3d0298c9af2be8e05b6999de46596a1
## Why
Runtime authentication must use the credential selected by the model provider. Explicit API keys and command credentials need independent ownership so cached connections and in-flight work cannot cross credential sources.
## What changed
- Register and reuse runtimes per credential source, supporting explicit provider keys and command credentials without falling back to saved login credentials.
- Track `AuthOwner` by credential manager and owner generation across WebSocket state, compaction, and scoring.
- Preserve cached identity and runtime registration state during credential-source outages or failed storage reloads. Require a successful auth reload before logout revokes credentials.
- Reject requests whose production or staging environment differs from runtime registration, including model catalog requests.
## Testing
Add regression coverage for credential selection and runtime reuse, owner isolation, source outages, failed reloads and logout recovery, and environment mismatches.
GitOrigin-RevId: 7bab55e0ea502593393df10046309fd8502edbd0
## Why
Gateway OAuth reads and logins previously used only the current provider, preventing clients from authorizing another configured provider without changing the default.
## What changed
- Add optional `modelProvider` params to `account/gatewayOAuth/read` and `account/gatewayOAuth/login`, preserving current-provider behavior for omitted or null params and selectors.
- Validate explicit providers against current managed policy without changing the default or any thread's provider.
- Retain readiness state across providers and send `account/gatewayOAuth/changed` notifications for every configured provider sharing the changed credential.
- Update protocol schemas, TypeScript types, Python models, and documentation.
## Testing
Add coverage for non-default provider login, retained readiness when alternating providers, notifications for shared credentials without starting login, and legacy TypeScript request compatibility.
GitOrigin-RevId: cfd472c322b821fe36b8c133a8de774f4ba48534
## What changed
Allow `model_providers.<id>.gateway_oauth.credential_export` to supply a gateway access token instead of browser OAuth. Run the configured command on first use, cache its token in memory, and deliver it through the configured header or cookie. Export failures surface directly, and command-backed providers do not require an OAuth session.
Require mutually exclusive OAuth and exporter settings, same-origin model catalog access, and rejection of HTTP redirects for command-backed gateway credentials. Share the bounded, timeout-controlled command runner with AWS credential export.
## Testing
Add tests for inference and model listing without OAuth, token caching and recovery after invalid output, preservation of primary authentication, and rejection of mixed OAuth/exporter configuration.
GitOrigin-RevId: e3dbfd8823b1992045f1c1efd56ec98ee17e07a5
Charlie Marsh