2462 Commits
Author SHA1 Message Date
liame-oai 014489466a Add optional MCP disablement for prediction forks and samples (#55463)
## What changed

Add `experimentalDisablePredictionMcp` to `thread/fork` and `disableMcp` to `thread/sample`. Disable MCP servers when requested and the inherited history contains incremental tools on Responses Lite. The fork option requires `experimentalPredictionMode: true`.

Apply disablement through a thread-local policy that excludes configured MCP servers and runtime contributions, including after MCP refresh. Preserve the inherited history prefix and append tool-removal instructions without changing the parent's tools.

## Testing

Add coverage for prediction forks with legacy and paginated history, flag validation, conditional disablement, MCP refresh, and sample/fork request parity. Add a request-history snapshot covering preserved history, tool removal across child turns, and unchanged parent tools.

GitOrigin-RevId: e31d602480e6550ed130d8152f538b8668280fa0
2026-10-20 05:25:43 +00:00
liame-oai a4c9194247 Add cancellation for experimental thread samples (#55441)
## What changed

Add the experimental `thread/sample/cancel` request with a `requestId` identifying a `thread/sample` request on the same connection. Cancellation returns an empty response, stops the matching sample with `sample canceled`, and cleans up its ephemeral fork. Repeated cancellation and unknown request IDs are harmless no-ops; other request types are unaffected.

## Testing

Add coverage for connection and request ID isolation, request type filtering, and repeated cancellation. Extend the sample integration test to verify cancellation keeps the parent responsive and reclaims the child thread.

GitOrigin-RevId: 92d12e5c0190e1d3b06cb482543615a3ec77bdc8
2026-10-20 03:09:44 +00:00
cooper-oai 7827cd886d Track credential sources separately from auth owners (#55410)
## Why

A new OAuth login can belong to the same account as an earlier session, while token refreshes can change credentials within one session. Auth consumers need to distinguish these cases when deciding whether a runtime can be reused.

## What changed

- Add `source_generation` to `AuthChangeState` and expose `AuthManager::auth_change_state_for` to check whether selected credentials still match the manager's current source.
- Preserve source continuity across OAuth refreshes only when session, issuer, and identity claims match. Advance the source revision for new sessions, credential replacements, and logout.
- Keep agent identity persistence from replacing cached credentials with credentials read from disk; credential publication remains managed by `AuthManager`.

## Testing

Add tests for refresh continuity, new logins, identity and workspace changes, sessionless tokens, API key replacement, logout, and identity persistence followed by an explicit credential reload.

GitOrigin-RevId: 56eddb7edb9c5f8854b18fd50ce917c0b27e75d6
2026-10-20 00:13:01 +00:00
richardopenai 431185b78b Defer environment disconnect notifications until recovery fails (#55401)
## Why

A temporary exec-server transport loss could emit a thread environment disconnect notification while the session was still recovering.

## What changed

- Add `EnvironmentConnectionState::Recovering` for interrupted transports and pending session recovery.
- Suppress thread lifecycle notifications during recovery, emit a connected notification after successful recovery, and report disconnection when recovery fails.
- Ignore recovery callbacks from retired clients so they cannot overwrite the connection state during refresh.

## Testing

Add coverage for fast and near-deadline recovery, recovery timeout, rejected session resume, and retired-client callbacks. Extend app-server coverage to verify one lifecycle notification per selected thread and usable `environment/info` after recovery.

GitOrigin-RevId: d6dce5cc5264af29b6f993daa209b93102122e40
2026-10-19 22:55:42 +00:00
jif 896604a12d Record OAuth provenance and login identity for account tokens (#55397)
## Why

Token refresh needs the issuer and client ID used at login. Unverified token claims cannot establish that authority, and OAuth error bodies may echo credentials.

## What changed

- Save `oauth_provenance` and a new `login_owner_id` on browser and device-code login. Preserve the login identifier through token rotation.
- Refresh using the recorded issuer and client ID, retaining the existing endpoint override and fallback behavior for legacy records. Clear provenance when an override changes the endpoint or when a response without token rotation encounters a concurrently replaced refresh token.
- Keep both metadata fields optional for older records without inferring provenance from token claims.
- Remove backend token error details from structured logs and refresh error messages.
- Box large futures in token refresh, MCP initialization, and embedded app-server test startup to reduce surrounding async frame sizes.

## Testing

Add coverage for legacy record compatibility and metadata round trips, browser and device-code login persistence, refresh using recorded OAuth settings, metadata preservation through rotation, and provenance clearing for a superseded refresh token.

GitOrigin-RevId: b6b5d2fcbe2a284a171a242c1a17128af55f1024
2026-10-19 22:21:13 +00:00
jif affa861ddf Roll back interrupted Guardian reviews to preserve evidence (#55395)
## Why

Cancelled or timed-out Guardian reviews can admit transcript evidence without completing a review. Reusing that session can leave subsequent reviews without the evidence they need.

## What changed

Mark interrupted reviews for rollback to the last completed review instead of reusing their live context. Preserve committed review history and replay pending evidence on the next review.

## Testing

Add cancellation and timeout regression coverage that verifies encrypted evidence appears exactly once in the next review, the last completed review survives rollback, and interrupted or denied commands do not execute. Update session disposition assertions and make the program-change session reuse test wait for review completion before releasing the classifier result.

GitOrigin-RevId: f39552b24db5309cffddd9eda97280256be3e97b
2026-10-19 22:03:06 +00:00
jif 61fa059d49 Use thread connections for enterprise MCP status listings (#55394)
## Why

Enterprise-managed MCP authentication requires the thread's admitted connection. Bulk `mcpServerStatus/list` requests need to use that connection to report the enterprise server's catalog consistently with single-server requests.

## What changed

- Read enterprise server metadata from the thread runtime when listing all MCP servers, preserving ordinary server discovery.
- Check the expected server registration before discovery so edited or disabled registrations cannot reuse an old connection's catalog.

## Testing

Add coverage for bulk and single-server status consistency, catalog metadata, and registration changes. Extend enterprise authentication lifecycle tests to cover bearer renewal, grant replacement, and logout during a pending exchange. Add a scenario asserting that enterprise sign-in failure preserves ordinary MCP tool schemas, calls, and model history.

GitOrigin-RevId: 3bf3bd672511d0c753cd95ec777892f72bd6eb89
2026-10-19 22:02:44 +00:00
Eric Traut fea1d7f7d1 Add support for Academic Researchers plans (#55387)
## What changed

- Recognize `sci` and `sci_plus` in authentication, account responses, rate limits, and generated client schemas.
- Treat both plans as workspace accounts eligible for cloud configuration, and use business analytics routes.
- Display “Academic Researchers” and “Academic Researchers Plus” in the TUI and direct users to their admin when usage limits are reached.

## Testing

Add coverage for plan parsing, workspace classification, account and rate-limit responses, cloud configuration eligibility, analytics routing, TUI labels, and usage-limit guidance. Exercise installed-app refresh and listing with `sci_plus` authentication.

GitOrigin-RevId: b51c5df03029b8bc249d44f11b353a7755e7dd04
2026-10-19 21:43:19 +00:00
jif 1e4ba692b8 Preserve thread metadata before rollout files are materialized (#55380)
## Why

A live thread can have updated SQLite metadata before its rollout file exists.
Reading metadata from the missing file loses creation details such as fork and
parent relationships and triggers unnecessary filesystem discovery and retries.

## What changed

- Read deferred `SessionMeta` through the rollout writer, ordered with persistence.
  Return no in-memory metadata once the rollout is materialized or resumed.
- Combine that creation metadata with SQLite metadata for reads that exclude
  history, and use it to determine the canonical history mode during updates.
- Keep untouched threads without a stored record unavailable for fork and resume.

## Testing

Add coverage for metadata reads and updates before persistence in both legacy and
paginated history modes, including equality with metadata read after persistence.
Verify the recorder exposes creation metadata only while deferred, and expand
fork/resume rejection tests across history modes and resume turn inclusion.

GitOrigin-RevId: 8d293cc8f87156409f195130437d93858a4099b9
2026-10-19 21:02:19 +00:00
jgrodman-arch ee8b4ea181 Import only the continuation of backgrounded Claude sessions (#55365)
## Why

Backgrounding a Claude session creates a continuation that includes its history. Offering both sessions for import duplicates that history.

## What changed

Skip sessions containing a `continued-in` record with a nonblank `continuedInSessionId` during import detection, leaving the continuation available for import.

## Testing

Add detection and app-server regression tests covering continuation-only detection, importing the full history into one thread, and no remaining import candidates afterward.

GitOrigin-RevId: bf8383faadce984ae3c41a0b8e8b3072680fd4b2
2026-10-19 19:53:58 +00:00
liame-oai 8f8e7a6e09 Add experimental thread/sample requests to the app server (#55339)
## What changed

Add `thread/sample` to collect one model response on an ephemeral fork that inherits a loaded thread's context and configuration. Return the source turn ID, response ID, assistant text, and available token usage without modifying the source conversation.

Require an idle, persistent root thread and an `expectedTurnId` matching its latest completed turn. Reject results if the source history changes during sampling. Keep the parent responsive while sampling, hide sample forks from `thread/loaded/list`, and reclaim them after completion or timeout.

Intercept responses before tool execution or Stop hooks can run, returning null text for tool calls or responses without text. Apply optional reasoning-effort updates only when the provider and model support cache-preserving updates.

## Testing

Add integration coverage for inherited context and reasoning effort, source preservation, tool and Stop hook suppression, invalid requests, stream errors, parent responsiveness, and timeout cleanup.

GitOrigin-RevId: 08f4867e53ec7f6c8f4428d5542eeea4e6dadd0b
2026-10-19 18:25:07 +00:00
jif 1569abc5dc Enable enterprise-managed authorization for MCP connections (#55334)
## What changed

- Connect directly configured MCP servers using account-scoped enterprise grants stored in the keyring, with token exchange and authenticated HTTP requests.
- Retain authorization for the thread across MCP refreshes and revoke it when the account owner changes, cloud configuration becomes invalid, or an enterprise login replaces the grant.
- Negotiate the enterprise-managed authorization extension with the `2026-07-28` protocol, bypass shared tool catalog caching for enterprise servers, and report credential status with enterprise sign-in guidance.

GitOrigin-RevId: c0f96d37194212758a211ae6a4107205df96df26
2026-10-19 17:57:35 +00:00
acrognale-oai 1277bcfddc Add one-shot app-server startup configuration discovery (#55300)
## What changed

Add `codex app-server --print-startup-config` to validate local and cloud-backed configuration and emit the app-server version and configuration requirements as JSON without initializing environments, thread storage, or plugins. Configuration failures produce structured JSON errors and a nonzero exit status.

Support `--startup-sign-out` to remove account credentials and reload signed-out requirements, including recovery when cloud policy is unavailable. Reject sign-out for host-owned external authentication. Accept `--startup-client-info` to identify configuration and authentication requests.

Reuse configuration loading and account cleanup logic between startup discovery and the running app server.

## Testing

Add CLI integration coverage for configuration validation, project login restrictions, managed cloud requirements and failures, sign-out recovery, external authentication protection, and independence from locked or invalid history databases.

GitOrigin-RevId: 636ccb095b684b6136cf9e408f3f8613cb776e16
2026-10-19 15:13:44 +00:00
jif cca40e57a4 Track MCP enterprise auth cancellation across config reloads (#55287)
## Why

Configuration loading can finish before a pending startup is visible to the thread manager. Reloads need a cancellation scope that also covers these configuration snapshots.

## What changed

- Capture an enterprise managed authentication (EMA) cancellation token before loading configuration and carry it through config layers, role overrides, runtime refreshes, and `McpConfig`.
- Cancel the previous scope on MCP or user configuration reloads and cloud config loader changes, then create a fresh scope for subsequent loads.
- Cancel the session's token when enterprise MCP authentication is disabled or a refresh leaves it unavailable.

## Testing

Extend the MCP reload test to verify that existing thread and pending startup tokens are cancelled while a fresh startup receives an uncancelled token.

GitOrigin-RevId: 5fc0658b74c360e7dc9ab3488339fcf19bfe9fae
2026-10-19 14:07:10 +00:00
Charlie Marsh b1fd48c48e Avoid cloning events in the app-server thread listener (#55283)
Record whether an event is `ShutdownComplete` before moving it into
`apply_bespoke_event_handling`, preserving shutdown drain notification without
cloning the event.

GitOrigin-RevId: 9e4ca8c657d4d5b98056de8c7aba1391233994c1
2026-10-19 13:27:16 +00:00
jif d28be12577 Honor per-thread unload delays in app-server (#55270)
## Why

Thread unload timing used the server-wide delay, ignoring per-thread configuration overrides. Clients need to control how long individual idle, unsubscribed threads remain loaded.

## What changed

- Resolve unload timing from each loaded thread's `thread_unload_delay_secs` configuration. Setting it to `0` allows immediate unloading once the thread has no subscribers or activity.
- Allow this runtime retention override in `experimentalPredictionMode` forks while continuing to reject other configuration overrides. Reject negative values and delays too large to schedule.
- Replace the source-specific immediate-unload behavior with explicit configuration.

## Testing

Extend integration coverage for per-thread delays, unloading after active turns finish, fork overrides, and invalid prediction-fork delays. Verify that immediate unloading preserves persistent history and that cold resumes and ordinary nested forks use their default delay instead of retaining the previous runtime's override.

GitOrigin-RevId: fcb82bd73a101260c51e2a8476f94320c23ac929
2026-10-19 12:30:33 +00:00
jif 9032fc7683 Unload idle ephemeral composer prediction threads without delay (#55255)
## What changed

Set the app server's unload delay to zero for ephemeral threads whose `thread_source` is `composer_predictions`, excluding subagent sessions. These threads unload once they are idle and have no subscribers, while active turns continue to completion.

## Testing

Extend integration coverage to check immediate unloading after an active prediction turn finishes and after unsubscribing from a fork that inherits the prediction configuration. Verify that persistent threads and ephemeral threads without the prediction source retain the configured delay.

GitOrigin-RevId: 04a0e405b666c689ccf6f482055d24692b18ead0
2026-10-19 11:09:48 +00:00
Vivian Fang 70b3bb6d88 Add observation-only model request lifecycle hooks (#55144)
## What changed

- Add `PreModelRequest` and `PostModelRequest` hooks around model request attempts, including retries. Pass model, session, turn, and optional subagent context; report completion, failure, or cancellation with errors and token usage when available.
- Treat hook output as diagnostic data without allowing it to veto requests or alter model context. Wait for synchronous post-request hooks before dispatching tools, while asynchronous hooks allow streaming tool dispatch to continue.
- Apply memory-consolidation hook filtering and expose the new events through configuration, protocol schemas, generated clients, and the hooks browser.

## Testing

Add integration coverage for failures and retries, ignored control directives, cancellation, synchronous and asynchronous tool ordering, interrupted-turn resume and token accounting, and memory-consolidation filtering. Update hook schema fixtures and hooks browser snapshots.

GitOrigin-RevId: 6ed7b39fc8bb94cf467e350d07d97fcc729c21ce
2026-10-18 22:43:56 +00:00
thorvald-oai 7b44ac1661 Gate app-server WebSocket compression behind a feature flag (#54949)
## What changed

Add `features.app_server_websocket_compression`, disabled by default. TCP WebSocket and Unix-domain socket listeners now negotiate zstd compression only when the feature is enabled and the client offers the supported protocol. Otherwise, connections use plain text messages.

Include the feature in the configuration schema and allow its override during TUI daemon startup.

## Testing

Extend transport tests to cover enabled and disabled compression with supported, unsupported, and absent client offers on both transports. Add an app-server integration test that verifies startup configuration controls negotiation and the message format used for initialization responses.

GitOrigin-RevId: 6001d65f66f9c48f099b85380c2cad8ffee04de7
2026-10-17 23:34:04 +00:00
Adam Perry @ OpenAI 82d958597f Gate the file-copy extension behind multi_env_copy_file (#54741)
## What changed

Add the `multi_env_copy_file` feature flag, disabled by default and marked as under development, to the feature registry and configuration schema. Install the file-copy extension in app-server threads and CLI debug prompt construction when the flag is enabled.

GitOrigin-RevId: 6d8b4c7479974f4b70c39f52333491c13d60d2a2
2026-10-17 00:02:06 +00:00
victor-openai 0e67502123 Preserve MCP tool-list metadata in server status (#54686)
## Why

MCP tool discovery discarded response-level `_meta`, leaving server-status clients unable to inspect metadata associated with the tool catalog.

## What changed

- Preserve opaque `_meta` from the first `tools/list` page through catalog refreshes and caches.
- Expose it as `toolListMeta` in `McpServerStatus`, with `null` when unavailable, and update generated schemas and bindings.
- Scope cached Apps catalog metadata to discovery settings, including client capabilities and extensions, while retaining tools from older caches without metadata.
- Restrict server capabilities in status snapshots to the selected servers.

## Testing

Add regression coverage for listing legacy cached Apps tools during failed startup, and update protocol serialization expectations for nullable `toolListMeta`.

GitOrigin-RevId: 62335e2fd8c482067a7a78a7612b58c3eaa9fb55
2026-10-16 19:26:46 +00:00
vkg-oai a083a1e49e Distinguish MCP approval cancellation reasons (#54679)
## Why

MCP tool calls reported every aborted approval as "user cancelled MCP tool call", including interrupted requests and automatic cancellations in `exec` mode.

## What changed

Carry `user`, `interrupted`, or `non_interactive` cancellation reasons through MCP approval metadata and resolution. Mark explicit TUI cancellations as user actions, interrupted requests as interruptions, and automatic `exec` cancellations as non-interactive.

Use the reason to report when a call was cancelled before approval or because interactive approval is unavailable in `exec` mode. Preserve the existing cancellation message for clients that omit the reason.

## Testing

Update tests to verify that a closed approval response carries the interruption reason and that `exec` cancellation responses include the non-interactive reason.

GitOrigin-RevId: be2a5f7fef539b5db2add53b46aea27e2b8a66fc
2026-10-16 19:08:19 +00:00
Tom 96eb400d12 Distinguish retryable thread-store errors from unknown write outcomes (#54664)
## What changed

Add `ThreadStoreError::Retryable` for transient failures known to be safe to retry and `ThreadStoreError::OutcomeUnknown` for writes that may already have committed. Recovery remains the operation owner's responsibility; neither category automatically triggers retries.

Preserve existing app-server error mappings and fatal session startup behavior, and report the new categories in shutdown diagnostics without exposing raw error payloads.

## Testing

Add coverage for conservative SQLx error classification, mutation error mappings, session initialization categories, and shutdown diagnostics that omit raw error payloads.

GitOrigin-RevId: 259a9bfaa6ff3cbfa2ee61a01a1f1e744c90f118
2026-10-16 17:31:47 +00:00
jif 2bf2bdf82c Bind plugin hook approval to plugin contents (#54619)
## Why

A plugin's scripts can change without changing its hook declaration. Declaration-only approval therefore lets changed plugin code run under an existing hook approval.

## What changed

- Fingerprint plugin bundle contents and include the content hash in the approval value returned by `hooks/list`. Persist it as `trusted_content_hash`, keeping `trusted_hash` compatible with older clients.
- Verify contents before each command or MCP hook execution, within the hook's timeout, and require renewed approval when approved contents change.
- Migrate legacy declaration-only approvals to a shared, immutable content baseline per plugin and config home.
- Exclude generated Python bytecode, `.venv`, and `.egg-info` entries from fingerprints. Run app-server hook listing on blocking tasks.

## Testing

Extend integration coverage for plugin upgrades and rollbacks requiring approval, same-turn script changes preventing further hook execution, shared legacy approval baselines, and generated Python artifacts preserving trust.

GitOrigin-RevId: faaf7658210d8adb2534ddd614c72ec993920840
2026-10-16 14:38:19 +00:00
Eric Traut e90f49a269 Treat explicit connections to the verified default daemon as local (#54421)
## Why

Explicitly selecting the default daemon socket previously classified the TUI connection as remote, changing how local configuration and thread parameters were handled. A socket at that path may also be an SSH forward, so the path alone cannot establish that the daemon is local.

## What changed

- Verify the default daemon endpoint before classifying an explicit connection as local. On Unix, check the expected symlink target and the private socket directory's ownership and permissions, then connect to the protected endpoint directly.
- Preserve local workspace behavior and local thread parameters for verified attachments while keeping directly bound Unix sockets classified as remote.
- Report a missing explicitly requested socket, disable embedded fallback for explicit attachments, and restrict daemon auto-start to implicit connections.

## Testing

Extend tests to cover explicit and implicit local target selection, verified socket resolution, and rejection of a directly bound socket as a local daemon endpoint.

GitOrigin-RevId: ac2226ca1c5f60b26aad9571f945e3325d3bebfa
2026-10-15 21:35:40 +00:00
Matt Kaufer 592964c0cb Record local image inputs on completed image-generation items (#54420)
## What changed

Add optional `inputImages` metadata containing each referenced local image's path and SHA-256 hash of the bytes read before normalization. Compute the hash from the same bytes used to prepare the edit request.

Preserve this metadata through completion events, persisted thread history, resume, and legacy rollout migration. Update app-server schemas and generated TypeScript and Python types; older items continue to deserialize without the field.

## Testing

Add coverage for input ordering, changed contents at the same path, unreadable or invalid references, serialization, persisted history and resume, and legacy migration.

GitOrigin-RevId: 522be8ec1e39c9b2bbe5b9ccb37ea67d17f0e21a
2026-10-15 21:30:56 +00:00
Krish Chainani aabf13307a Store generated image items as attachment references (#54398)
## What changed

- Upload generated images to the attachment store and expose `fileId` in image-generation items when available, with inline `result` fallback on upload or decoding failure.
- Preserve file references through legacy events, persisted rollouts, thread history, and task output summaries. Keep model-facing image preparation separate.
- Add attachment request tags and mark generated-image uploads with `usage=image_gen`, preserving the thread's ephemeral setting.
- Update public schemas and SDK types to accept either image representation, retain the Python `ImageGenerationThreadItem` alias, and prefer `fileId` when reading records containing both fields.

## Testing

Add coverage for file-backed generation and rollout persistence, legacy history replay, inline and transitional serialization, task output visibility, and Python SDK alias compatibility.

GitOrigin-RevId: f7a2bb5707e2f277348a547a988bc33c8e96d891
2026-10-15 19:51:22 +00:00
jif 2a6ecbb93c Preserve recent speech when trimming realtime transcripts (#54257)
## Why

Trimming interleaved realtime transcripts by utterance order can discard the latest speech from an earlier utterance. Evicting after each delta can also drop one speaker before the other speaker's delta from the same frame arrives, losing recent instructions at handoff.

## What changed

Use raw frame recency to trim timed frameless bidirectional transcripts within the 8 KiB budget. Defer eviction until the frame advances or the transcript is consumed, and retain both speakers' suffixes when they share the newest frame. Preserve conversation order and fall back to FIFO eviction when timing is unavailable.

Track trimmed prefixes so final transcripts can extend retained speech without making delayed finals appear newer.

## Testing

Add regression coverage for frame recency, same-frame event ordering, UTF-8 truncation, delayed finals, and untimed fallback. Add an app-server handoff test verifying that both speakers' recent speech and the latest user instruction survive while live transcript notifications remain unchanged.

GitOrigin-RevId: b01b729d8bdd4acb26e0385442ce40819355deac
2026-10-15 10:46:59 +00:00
smurching-oai 7943713993 Reload the model catalog after account changes (#54169)
## Why

The app server retained its startup model provider for catalog requests, so signing in or out could leave `model/list` using stale provider settings or requiring a restart after managed provider requirements changed.

## What changed

- Invalidate the catalog after successful login and logout, then reload the effective configuration on the next model list or background refresh. Rebuild the models manager when the provider or catalog changes, while preserving existing threads' routes.
- Retain the original project context and the TUI's `--oss` provider selection across reloads. Retry configuration loading after falling back to defaults so temporary failures do not pin the fallback catalog.
- Keep provider policy checks for cached catalogs and apply runtime `api_key_model_discovery` toggles to the active catalog manager.

## Testing

Add and extend tests for provider selection and definition changes after login, catalog reloads after logout, OAuth gateway transitions, fallback recovery, project context, and runtime model discovery toggles.

GitOrigin-RevId: bce2e23ff567e1a52eac2b6ad736a6e63ff61e2b
2026-10-15 03:06:16 +00:00
duc-openai 9e7b2a577f Forward turn metadata to image generation and edit requests (#54058)
## Why

Native extensions need configured Responses metadata for request attribution, but extension calls used the MCP metadata template, which omits it. Image requests also did not forward the turn metadata to the backend.

## What changed

Use the Responses metadata template for native extension calls while continuing to exclude tool inventory. Forward the resulting metadata in the `x-codex-turn-metadata` header on image generation and edit requests.

## Testing

Extend metadata tests to cover configured values in extension calls and app-server tests to verify `display_name` and `turn_trigger` on image generation and edit requests, including a Unicode display name.

GitOrigin-RevId: a2ffaa4d15259c662917612391b8717ee34b9c6c
2026-10-14 18:01:54 +00:00
marksteinbrick-oai 2b21129c6b Add Responses API client metadata patches for turn start and steer (#54053)
## Why

Clients need a way to update individual turn metadata entries without replacing the existing client metadata map.

## What changed

Add the experimental `responsesapiClientMetadataPatch` field to `turn/start` and `turn/steer`. Patches add or overwrite entries while retaining other keys and apply after `responsesapiClientMetadata` when both are supplied. The existing field retains replacement semantics, including clearing unprotected entries with an empty map.

Continue protecting reserved metadata keys and preserving targeted `misalignment_override` continuations across updates.

## Testing

Extend the app-server metadata integration test to cover replacement and patch steering, patch precedence at turn start, preservation of unrelated entries during patches, and protection of targeted continuations.

GitOrigin-RevId: 8c4da3ba1b87329da20b5295846bdcf3a88126de
2026-10-14 17:39:43 +00:00
jif 76ed3b484d Fix session lookup and resume after rollout compression (#54008)
## Why

Compression replaces `.jsonl` rollout files with `.jsonl.zst` files, so checking only the original path can skip existing sessions. Compression can also replace a file between path lookup and canonicalization.

## What changed

- Resolve compressed rollout alternatives when selecting the latest local session.
- Retry rollout path resolution when files disappear during lookup or canonicalization.

## Testing

Extend coverage to verify latest-session filtering after startup compression and resuming a compressed rollout through its original relative `.jsonl` path with preserved turns.

GitOrigin-RevId: a4d5c399567ab4c7cd8aaa8b5f38821ee8b8d802
2026-10-14 15:22:02 +00:00
tongzhou wang 1b6e0d8145 Track content provenance through prompt assembly and compaction (#53831)
## Why

Message roles and content classifications do not identify who supplied each context part. Source attribution needs to survive prompt assembly and history truncation, including messages that combine text from different producers.

## What changed

- Add per-part `ContentItemMetadata` for user input, developer instructions, `AGENTS.md`, skills, harness context, command hooks, and tool context with optional callable namespaces.
- Carry attribution alongside content and classifications through contextual fragments, extension prompts, hook output, and agent messages. Keep tool-provided context-window hints separate from harness text.
- Preserve the source of retained text slices during compaction and attribute generated truncation notices to the harness. Default missing historical attribution to unknown.
- Attribute host MCP calls using cached tool namespaces only when catalog revisions remain stable, without starting servers or refreshing catalogs for attribution.
- Send the new metadata to Responses Lite and strip it from requests to endpoints that do not support it.

## Testing

Extend compaction tests to cover mixed sources, missing or extra metadata entries, and discarded media. Update Responses Lite request assertions to verify endpoint-specific attribution handling.

GitOrigin-RevId: b0ebc929b7c60f3ec49d1affbf897312d63edcc8
2026-10-14 02:01:49 +00:00
Eric Traut ca2b076fff Add safe diagnostics to workspace routing configuration errors (#53805)
## Why

Workspace routing reported generic requirements load and reload failures, hiding the cause. Raw configuration errors can contain secrets, so exposing their messages directly is unsafe.

## What changed

Include a safe reason in configuration load and reload errors: file locations or non-file line and column numbers, cloud error categories and HTTP status codes, known network policy denials, or OS error details. Exclude raw parser messages, configuration contents, and backend-supplied policy names and IDs.

## Testing

Add regression coverage for configuration locations, cloud failures, and network policy denials. Verify that malformed local and cloud configuration reports useful errors without exposing secret values or policy identifiers, and still prevents workspace routing from falling back to startup configuration.

GitOrigin-RevId: a71484c700d32662ced9e19041dbedda5d1da8a5
2026-10-13 23:59:56 +00:00
Chris Dong 6786dccbe7 Forward client voice session IDs in realtime requests (#53784)
## What changed

Add optional `voiceSessionId` to realtime start parameters and forward it as the `voice-session-id` header for WebSocket, WebRTC, and existing-call transports. Keep this client-generated voice session identifier distinct from `realtimeSessionId`, which uses `x-session-id`.

## Testing

Extend serialization tests and add coverage for distinct session ID headers, WebRTC request forwarding, and existing-call handshake forwarding.

GitOrigin-RevId: cb558dbb9d438f2d34e281199a7e81fe5d33b879
2026-10-13 22:21:31 +00:00
felixxia-oai 4d82d36ccf Default Guardian v2 async classification to conversation mode (#53733)
## What changed

Use `conversation` when neither a local `async_classifier_mode` override nor a model default specifies a mode. Keep `snapshot` available as an explicit override and update the configuration documentation and schema to describe the new fallback.

## Testing

Expand configuration tests to cover all local override and model default combinations. Update app-server approval tests to exercise conversation mode without an explicit override, and explicitly select snapshot mode in tests that depend on it.

GitOrigin-RevId: a62479a3f6454bf28d589373a236d8b0ab5023b9
2026-10-13 18:08:10 +00:00
jif cb7091b180 Preserve URLs and email addresses during external agent migration (#53706)
## Why

Rewriting source agent names and instruction filenames inside URLs and email addresses can change their destinations when importing external agent content.

## What changed

Use `linkify` to preserve recognized URLs and email addresses while rewriting surrounding text, including Markdown link labels and titles. Continue migrating instruction filename references to `AGENTS.md`, including relative links and references with line or column suffixes.

## Testing

Add rewrite coverage for URLs, email addresses, Markdown links, and surrounding Unicode text. Extend skill import and app-server configuration import tests to verify that link labels migrate while URL destinations remain unchanged.

GitOrigin-RevId: c4d210a287c99b6440438c99527364d379c568bd
2026-10-13 16:15:41 +00:00
Keyan Zhang 044e74fef3 Preserve inherited context in prediction forks (#53678)
## Why

Prediction forks need to retain their parent's context even when it exceeds the automatic compaction threshold. Compaction or context resets can otherwise replace the history used for the prediction.

## What changed

- Apply a thread-local `AutoCompactionDisabled` policy to experimental prediction forks without changing model or skill budgets.
- Skip automatic compaction before, during, and after turns, including context-limit recovery, and suppress new token-budget reminders.
- Reject `new_context` requests for these threads and report context-limit failures without compacting their history.

## Testing

Add regression tests for legacy and paginated prediction forks across compaction thresholds, unchanged parent compaction and skill/tool inputs, context-limit failures, and rejected context resets. Add a request-history snapshot verifying inherited context and reminders survive without compaction or additional reminders after a tool call.

GitOrigin-RevId: 7df374287f4142f776981bb6c22e5caa564d74a5
2026-10-13 14:17:41 +00:00
jif fc4921f487 Add regression coverage for network grants on cold thread resume (#53424)
## What changed

Add a Linux app-server integration test that resumes a saved read-only thread after the default permissions change to `:danger-full-access`. Verify that the live network proxy honors restored grants, requests approval for a new host, persists the approved rule, and reuses it without another approval.

The test also verifies that proxied requests succeed while direct access remains blocked.

GitOrigin-RevId: 08f63efb8752d738df0ee97e4e98c3366ae54f56
2026-10-12 16:49:29 +00:00
jif bf4ca52b61 Restore saved thread permissions during configuration loading (#53419)
## Why

Restoring unnamed thread permissions after configuration loading leaves network proxy initialization and permission validation using the configured default. A saved read-only thread should also resume when that default is incompatible with current managed requirements.

## What changed

Apply eligible saved permission profiles during configuration loading, before network preparation and final validation. Keep explicit permission overrides and managed requirements authoritative, preserve managed deny-read restrictions, and reject saved external enforcement or materialized filesystem grants. Include the saved profile in the app-server's prepared resume configuration state.

## Testing

Add regression coverage for resuming saved read-only permissions with an incompatible full-access default and for retaining managed, remembered, and newly approved network domains in the restored profile's proxy allowlist.

GitOrigin-RevId: 73e32b0a31ac678fd3f60a8ccf8fa9df627f16c3
2026-10-12 16:09:41 +00:00
Eric Traut 7c9bfb910e Restore thread-owned permissions on cold resume (#53150)
## Why

Cold resume can replace saved unnamed permissions with current configuration defaults or recover an executor's permissions from turn context. A first-turn context can also predate an acknowledged settings update.

## What changed

- Restore eligible unnamed permission profiles from settings snapshots owned by the resumed thread, honoring explicit caller overrides and current managed requirements.
- Use owned snapshots as the authority for named permission profiles and reapply workspace permissions for the resumed workspace roots.
- Persist a thread-owned settings checkpoint after the first turn's context, serialized with settings updates so older checkpoints cannot supersede newer settings.

## Testing

Extend regression coverage for cold resume with changed defaults, managed permission restrictions, workspace-root overrides, foreign snapshots, and settings updates during first-turn processing.

GitOrigin-RevId: e411d9fd3d586a4162498c9c77c4184459071bd1
2026-10-11 15:48:35 +00:00
alishobeiri-oai de8fab6d7a Upgrade rmcp to 3.5.1 and harden lifecycle tests (#52972)
## What changed

- Update the pinned `rmcp` dependency and Cargo/Bazel lockfiles, and migrate MCP handlers and fixtures to `ClientConfig` and `ServerConfig`.
- Stop requiring responses for cancelled elicitation requests in cancellation tests while retaining checks for cleanup and continued connection usability.
- Handle client disconnects during WebSocket writes in the TUI test server, use an asynchronous HTTP mock for loopback proxy testing, and improve remote executor test diagnostics and the Windows subprocess fixture.
- Use `invalid_prompt` for the memory worker failure fixture.

## Testing

Add a regression test covering transport EOF during both form elicitation and user verification. Keep the client alive while checking that pending response channels close, the timeout pause clears, and the service exits with `QuitReason::Closed`.

GitOrigin-RevId: c0166b83fab3b59d84a5207c6630cb6adcf3b230
2026-10-10 19:43:24 +00:00
Adam Perry @ OpenAI be9060ff96 Stabilize the realtime steering timeline test (#52923)
The initial user item seals realtime transcript segments, so starting speech before it completes can split the segment under test. Wait for its `item/completed` notification and assert that it is a `ThreadItem::UserMessage` before triggering speech, so only the steering under test can split that segment.

GitOrigin-RevId: 932443f4a0d6c4284cf95f44e64912506769a180
2026-10-10 16:52:55 +00:00
pakrym-oai 5ef96ab278 Add opt-in output token replay for OpenAI requests (#52742)
## What changed

- Add the disabled-by-default `output_token_replay` feature to request `output.encrypted_content` from OpenAI providers.
- Preserve encrypted message and tool-call output, message and function-call status, and output-text `annotations` and `logprobs` through history and replay. Update the generated protocol schemas and SDK types.
- Strip output ciphertext from requests to other providers while retaining it in stored history, including after replay is disabled. Remove encrypted content from memory extraction inputs.

## Testing

Add integration coverage for the feature/provider combinations, metadata replay across follow-up requests, and history preservation when resuming with replay disabled.

GitOrigin-RevId: 77729a021b6771933402aebe74ece8eb39c057e2
2026-10-10 01:25:00 +00:00
Eric Traut 07757f448f Explain session creation failures during server shutdown (#52721)
## Why

Graceful shutdown rejects new sessions with an invalid-request error. Give clients a structured shutdown reason and show command center users why session creation is paused.

## What changed

- Add `data: {"reason":"serverShuttingDown"}` to app-server shutdown admission errors while retaining JSON-RPC code `-32600`.
- Show a dedicated shutdown message explaining the wait for active turns and automatic reconnection for non-embedded servers. Recognize older servers by their exact draining message only when error data is absent, and preserve retained-worktree cleanup guidance.
- Keep the command center reconnect presentation when a shutdown error covers the initial overview and no conversation is open.

## Testing

Extend admission and WebSocket shutdown assertions, add embedded and daemon shutdown message snapshots, and cover reconnection with a shutdown error over the initial command center.

GitOrigin-RevId: f167144c0ddc77872afdf3daac8bb1c89f3425b4
2026-10-09 23:16:46 +00:00
Dane Schneider 10da569252 Forward per-turn Cyber access programs to Guardian (#52689)
## What changed

Pass the parent turn's `cyber_access_program` to Guardian reviewers and asynchronous classifiers. Use `daybreak_blue` for either Daybreak selection, preserve `standard`, and omit `access_programs` when no program is selected.

Capture the selection with the owning turn so asynchronous observations retain it across later turns. Resolve classifier programs using current authentication and the same provider and API-key feature policy as ordinary model requests.

## Testing

Add regression tests for program changes across reused reviewer sessions with API-key and ChatGPT authentication, snapshot and conversation classifiers at low and high risk, and enabled, disabled, and unsupported-provider API-key policies. Verify parent requests retain their selected program.

GitOrigin-RevId: 447f306df3a6bd6805464b819950690c751b04b4
2026-10-09 20:14:04 +00:00
Won Park 45311351c2 Add opt-in retention for turn tool outputs (#52686)
## What changed

Add an optional `retain` flag to `TurnToolOutput` for `turn/start`. When set to `true`, pass the output to the core with a retention annotation to request retention in the thread's model history. The flag defaults to `false`, preserving existing behavior.

Update the generated JSON schemas, TypeScript types, and Python bindings to expose the flag.

## Testing

Add an integration test verifying that a retained tool output reaches the model and preserves client-authored sender metadata in persisted history, including the receiver message ID.

GitOrigin-RevId: 52893a8fcb308f26e77ba8f0bee9990073b26d54
2026-10-09 20:02:18 +00:00
Eric Traut 8ec80de0ef Count interrupted goal continuations toward the no-activity limit (#52640)
## Why

Interrupted automatic goal continuations reset the empty-response counter, allowing repeated interruptions without activity to keep a goal running indefinitely.

## What changed

Count interrupted automatic continuations without activity toward the existing three-turn limit that marks a goal as `blocked`. Defer evaluation until the thread is idle and serialize it with turn-start accounting. Activity and user turns still reset the counter.

## Testing

Extend accounting tests to cover interrupted and mixed empty continuations, including resets after tool activity or user turns. Add an app-server regression case where a `PreCompact` hook repeatedly interrupts automatic continuations and verify the `thread/goal/updated` notification reports `blocked`.

GitOrigin-RevId: 4c34e3ed1ae612e97cf067c2aa76836b10c50ef5
2026-10-09 16:58:24 +00:00
Brent Traut 47c063de51 Add experimental thread item lookup by ID (#52637)
## What changed

Add `thread/items/read` to retrieve persisted items by `threadId`, `turnId`, and 1–100 `itemIds`. Return matching items in canonical stored order, omitting missing IDs and items outside the requested turn.

Add item ID filtering to the thread store while preserving inherited history and fork cutoffs. Require the experimental API capability for the new endpoint.

## Testing

Add coverage for stored ordering, turn scoping, missing IDs, request size limits, experimental capability gating, and inherited items across fork cutoffs.

GitOrigin-RevId: 9b243dd87577bd4fe36900c388a386b2e26ff2e0
2026-10-09 16:50:24 +00:00
Joe Savona 751e7edd0b Skip background workspace routing reads without ChatGPT auth (#52635)
## Why

Background workspace routing reads reload configuration even when signed out or using an API key, although routing requires ChatGPT authentication.

## What changed

Check cached authentication before reading accounts for workspace routing at app-server startup and connection initialization. Skip these background reads without ChatGPT authentication, while preserving configuration reloads for explicit `account/read` requests.

## Testing

Add regression tests covering signed-out and API-key startup and connection initialization, explicit `account/read` configuration reloads, and routing after ChatGPT sign-in, including propagation of configuration errors.

GitOrigin-RevId: 8b90ee609ed24f8618cd21f160eb7001703b8bd1
2026-10-09 16:40:52 +00:00