Commit Graph
5410 Commits
Author SHA1 Message Date
sayan-oai 8a3c4ea3b5 Apply inherited environment settings at turn boundaries (#47428)
## Why

Thread permission updates could affect later steps of a running turn. Keep inherited environment settings consistent throughout the turn and apply saved updates when the next turn starts.

## What changed

Store active thread defaults alongside selected environments and refresh them when activating a new turn, even when its environment selections are unchanged. Resolve new selections from those active defaults while preserving owner-provided configuration, selection workspace roots, and the local Windows sandbox type.

## Testing

Add a regression test that changes permissions during a paused turn and verifies that both steps retain restricted filesystem access while the next turn receives unrestricted access. Update session and MCP elicitation tests to check that permission changes take effect on the next turn.

GitOrigin-RevId: 37ee44198fa40c138d140974dc90c4177d8c1f4c
2026-09-23 02:18:40 +00:00
acrognale-oai 8f8ace78cb Enforce application network policy for AWS auth and telemetry (#47408)
## Why

AWS credential discovery, analytics, and telemetry used clients that did not share the application's network policy. These requests need to honor destination restrictions and permission revocation.

## What changed

- Route AWS credential and region HTTP requests through the shared HTTP client, and check the signing destination before loading credentials. Skip discovery for static access keys with an explicit region.
- Apply account-scoped policy to Bedrock authentication. Require unrestricted policy for credential exporters and reauthentication commands, and cancel active work when permission is revoked. Document that AWS profile `credential_process` network traffic remains outside the application's HTTP policy.
- Send analytics through the authenticated account's HTTP client factory.
- Guard OTLP log, trace, and metric exports with revocable permits, disable them under destination restrictions, and make managed HTTP exports cancellable. Suppress global Statsig settings while managed policy is active.

## Testing

Add coverage for metadata credential request cancellation, allowed and denied SigV4 destinations, AWS credential precedence and endpoint configuration, and blocked credential exporter recovery. Update telemetry tests for account transitions and managed-policy Statsig suppression.

GitOrigin-RevId: d8a2018bfbbe971ec430699b0d3f86a7a9e1e072
2026-09-23 00:47:34 +00:00
acrognale-oai 22a3f6d5d8 Enforce application network policy across app-server requests (#47407)
## What changed

- Load `application.network` requirements at startup and explicit config/account reloads, applying local policy before authentication and cloud configuration bootstrap.
- Block traffic when policy loading fails, cancel requests that a new policy no longer permits, and reject configuration loads based on superseded policy snapshots. Local requirements edits take effect on the next explicit reload or restart.
- Bind authenticated clients to the current account and revoke them when account ownership changes. Carry policy enforcement through backend requests, realtime connections, workload identity exchanges, and code-mode gRPC streams while preserving gRPC trailers.
- Treat denied credential refreshes as policy errors without retrying them or invalidating stored credentials.

## Testing

Add regression coverage for startup restrictions, reload ordering, cancellation after restrictive or malformed requirements edits, account revocation, gRPC destination denial, workload identity cancellation, and credential preservation after denied OAuth refresh.

GitOrigin-RevId: 0cb4c720a906397e9df06675f01ecf60d741101f
2026-09-23 00:47:07 +00:00
andrewgu-oai 24462234b2 Refresh bundled model metadata and instructions (#47397)
## What changed

- Switch the GPT-6, GPT-5.6, GPT-5.5, and auto-review catalog entries to `shell_command` and expand their plan availability.
- Mark `gpt-6-astra` as supporting reasoning-effort updates and disable its experimental-context flag. Add explicit capability and instruction defaults to other entries.
- Update Astra's messaging guidance to recognize authorization from explicitly invoked skills or plugins, with attribution in the final response, and simplify its Default-mode clarification instructions.
- Revise auto-review guidance on autonomy, assumptions, and actions within the user's requested scope.
- Refresh seven scenario snapshots to reflect the updated prompts.

GitOrigin-RevId: b7ed8c413f6451008c982024506009b170e6311e
2026-09-23 00:07:56 +00:00
mtsui-oai 2c3295306f Retry transient OpenAI file blob upload failures (#47393)
## Why

A single blob upload failure previously aborted the file upload, even for a temporary `503` response or an interrupted stream.

## What changed

- Retry `503` responses and timeout, connection, body, or request errors, with at most five attempts within a shared five-minute deadline.
- Honor `x-ms-retry-after-ms` and `Retry-After`, falling back to backoff when no valid server delay is available.
- Reopen the contents for each retry while reusing the same file record and upload URL. Preserve the initial read permission check and reopen MCP file streams under the same sandbox policy.
- Record retry, recovery, and terminal failure events with a fresh client request ID for each attempt.

## Testing

Add coverage for recovery after `503` responses and interrupted streams, attempt and deadline limits, non-retryable responses, retry delay parsing, and unique request IDs. Extend the restricted-read MCP upload test to verify that both attempts send the complete file contents.

GitOrigin-RevId: 78089ecfd5076313f5784cbbc864df12d082e3b1
2026-09-22 23:56:23 +00:00
acrognale-oai 888e02db34 Enforce network policy throughout HTTP and WebSocket requests (#47389)
## Why

Destination restrictions and policy revocation must remain effective during redirects, response body reads, and established WebSocket traffic. Policy denials must also survive error handling so callers do not retry them or report a revoked operation as successful.

## What changed

- Route managed HTTP clients through a shared `RequestBuilder` and policy-aware execution, checking each redirect destination before route resolution and retaining a network permit while consuming response bodies.
- Guard WebSocket connection setup, reads, and writes with revocable permits, including independent wakeups for split readers and writers.
- Preserve `TransportError::Policy` through HTTP, SSE, and realtime error handling, and treat policy denials as non-retryable.
- Keep the supplied network policy in plugin startup HTTP requests and propagate response body failures from backend and plugin requests.

## Testing

Add regression coverage for rejection before connecting, revocation during redirect routing and streamed body reads, split WebSocket revocation, realtime writer error propagation, and revoked plugin upload responses.

GitOrigin-RevId: fba36700444c98a8364c09b4dc5452c4d78a90fb
2026-09-22 23:37:39 +00:00
guinness-oai 90e653014a Add opt-in reasoning status for realtime V3 delegations (#47377)
## What changed

Add `backend_reasoning_status`, disabled by default, to relay public reasoning summaries during active, server-managed realtime V3 delegations.

Use the last non-empty summary from each completed reasoning item, truncate it to 256 bytes at a character boundary, and append it as `[STATUS]` context on the `commentary` channel. Discard queued updates if their delegation is no longer active.

## Testing

Add an integration test covering enabled and disabled behavior, selection of the latest non-empty summary, exclusion of raw reasoning and partial summaries, and delivery without triggering `response.create` or changing the model's reasoning-summary setting.

GitOrigin-RevId: 75ce87dbbbab15a6d9d0ad0b23737738837192fd
2026-09-22 22:20:00 +00:00
iceweasel-oai 418199f6ad Add an opt-in preference for the local MXC sandbox (#47375)
## What changed

Add the default-off `features.prefer_mxc` flag to select MXC for local Windows execution when native support is available and effective network settings do not explicitly forbid local binding. Otherwise, retain the configured backend and legacy setup behavior.

Resolve the preference during config loading and use the effective local backend for execution, network proxy setup, sandbox diagnostics, and `windowsSandbox/readiness`. Preserve the configured backend for remote executors and `config/read`. Explicit `windows.sandbox = "mxc"` remains strict, and command failures do not trigger backend fallback.

## Testing

Add coverage for preference resolution, startup readiness without rewriting configuration, local and remote backend selection across environment updates and child threads, and workspace-write permission context in an agent turn.

GitOrigin-RevId: b51178f0371d38ebb58e41af54a068fca67fa316
2026-09-22 21:57:52 +00:00
vkg-oai 78fdcd2311 Overlap agent metadata reads when resuming a V2 root (#47369)
## Why

Restoring persisted V2 agent identities reads descendant metadata serially, making each storage read wait for the previous one.

## What changed

Read up to eight descendants concurrently while registering identities in graph order, preserving path and nickname reservation order. Skip identities already registered and continue restoring after individual read failures.

## Testing

Add a cold-resume regression test that gates child metadata reads to verify overlap, completes reads out of order to check deterministic path reservation, and injects a read failure. It also verifies that child runtimes remain unloaded until requested.

GitOrigin-RevId: ae90f24875966be83208884937621a6a9eb0d848
2026-09-22 21:42:11 +00:00
Owen Lin e7bbc79f48 Resume model context from the latest compaction boundary (#47365)
## Why

Resuming a compacted thread should use the compaction and its newer records without depending on older turn contexts or restoring stale state from before the compaction.

## What changed

- Stop paginated model-context scans at the newest compaction with `replacement_history` and `window_number`. Fall back to full replay if the newest compaction lacks either field.
- Align reconstruction with that boundary and restore `last_started_turn_id`, previous turn settings, and the multi-agent version from compaction resume metadata. Allow newer completed turns to override the saved settings.
- Keep canonical session metadata alongside the bounded replay and use the same scan boundary for subagent rollout migration.

## Testing

Add coverage for cold resume after mid-turn compaction, bounded/full replay equivalence, missing companion state, settings precedence, and incomplete-compaction fallback.

GitOrigin-RevId: f836464bb5cadd9be4a4e05b5d1679223713fc87
2026-09-22 21:17:08 +00:00
Rennie 559264d92e Preserve invalid_prompt as a distinct error classification (#47353)
## Why

`invalid_prompt` responses were classified as generic invalid requests, losing the server's specific error classification.

## What changed

Add `InvalidPrompt` variants to the API and core error types and serialize the core protocol classification as `invalid_prompt`. Recognize the code in HTTP 400 responses, wrapped WebSocket errors, and SSE `response.failed` events while preserving server messages and keeping the error non-retryable. Map it to `other` in the app-server v2 protocol.

## Testing

Extend coverage for typed error mapping, missing and blank messages, protocol conversion, and guardian retry handling. Exercise HTTP and SSE failures in core integration tests, asserting the error message, serialized classification, and a single request without retry.

GitOrigin-RevId: 5d9a299a013b06158a4dc27a4054f3dbc5fd0f4d
2026-09-22 20:07:50 +00:00
Henry Levy 8edfca892d Reuse cloud skill catalogs across turns until invalidated (#47350)
## Why

Cloud skill discovery ran on every turn, even when the Apps resource generation and authentication scope were unchanged.

## What changed

- Reuse warning-free catalogs, including empty catalogs, while their authentication scope and Apps resource cache key remain current.
- Refresh after invalidation and retry failed or partial discovery on the next turn.
- Reject discovery results if the Apps resource cache key changes during discovery.

## Testing

Update lifecycle tests to verify cached turns avoid catalog listings and skill reads, while connection and authentication changes trigger refreshes. Update the referenced-resource test to verify partial discovery retries on the next turn without an explicit MCP refresh.

GitOrigin-RevId: ac47d5202d76703c4946afef3b1a48eaf05b54c2
2026-09-22 19:58:52 +00:00
Alex Daley 9124e23e2c Move plugin recommendations into developer context (#47349)
## What changed

Emit `<recommended_plugins>` with the `developer` role and append it to the shared developer message after other context. Retain recognition of legacy user-role recommendations in existing rollouts.

## Testing

Add a startup context snapshot and assertions that recommendations share the developer message with permissions instructions. Update core and app-server tests to check developer-role recommendations, including across successive model requests.

GitOrigin-RevId: 0326ff347e86ec38b948f93e39e90e6a88a8730c
2026-09-22 19:51:33 +00:00
Owen Lin 5121aeff13 Overlap subagent spawn persistence and clean up cancelled children (#47348)
## Why

Forked subagent startup serializes history persistence and spawn-edge writes. Cancellation during startup can also leave a provisional child behind.

## What changed

- Defer copied-history durability so it can run alongside spawn-edge persistence, while still awaiting both before submitting the child's initial input.
- Commit agent and residency reservations and notify clients only after initial input is accepted.
- Guard provisional children so cancellation or startup failure removes and shuts them down, discards their stored state, and closes their spawn edge after any pending edge write finishes.

## Testing

Add coverage for cancellation at the child-history durability barrier, checking child termination, removal, and edge closure. Extend fork-context tests in legacy and paginated history modes to verify inherited context can be read from storage after spawn acknowledgment without flushing the live child first.

GitOrigin-RevId: e02dda57efc32b7237bb7af0ce5e5844922890c3
2026-09-22 19:39:18 +00:00
Keyan Zhang d93909a939 Skip stored title lookups for ephemeral forks (#47342)
## What changed

Skip the thread store title lookup when initializing an ephemeral fork, leaving its thread name unset.

## Testing

Add a regression test that forks an ephemeral thread from history and verifies that the in-memory thread store's `read_thread` count does not increase.

GitOrigin-RevId: 81180c4a836c932584d2cb94c0816eae33b04af3
2026-09-22 19:00:27 +00:00
pmccrary-oai 04fc75adbe Add conditional turn interruption that preserves pending input (#47340)
## Why

Callers need to interrupt a specific active turn without discarding queued input. Tool callbacks must be able to await the interruption decision without blocking task cancellation.

## What changed

- Add `CodexThread::interrupt_if_no_pending_input` and `Op::InterruptIfNoPendingInput`.
- Check the turn identity and pending user input or mailbox items before taking the active task. Leave the turn running for stale or abandoned requests.
- Acknowledge the decision before joining cancellation, and unblock pending submissions when the active task is cancelled.

## Testing

Add regression coverage for successful interruption, stale turns, preservation of queued user input and agent mail, abandoned requests, and cancellation while the submission queue is full.

GitOrigin-RevId: 42e31c09369fb070ba1b4b3c64ef45334dd872d8
2026-09-22 18:54:30 +00:00
andrewgu-oai 49e95cc73f Add GPT-6 Sol and Luna to the model catalog (#47332)
## What changed

- Add `gpt-6-sol` and `gpt-6-luna` catalog entries and refresh model descriptions.
- Offer migrations from `gpt-5.5`, `gpt-5.6-sol`, and `gpt-5.6-terra` to `gpt-6-sol`, and from `gpt-5.6-luna` to `gpt-6-luna`.
- Retarget retired `gpt-5.4` and `gpt-5.4-mini` selections to GPT-6 Sol and Luna, respectively.
- Recommend `gpt-6-luna` in the rate-limit switch prompt.

## Testing

Extend migration tests to cover the new targets, their default reasoning effort, and prompting again after a previously acknowledged migration to an older target. Update model-picker and rate-limit prompt snapshots.

GitOrigin-RevId: d3a093d18ce44a903383504ab8f5cbbc911d602d
2026-09-22 18:17:39 +00:00
Owen Lin 286d4ecf44 Persist resume metadata in compaction checkpoints (#47323)
## Why

Compaction companion records do not represent all resume state, including the last started turn and previous turn settings. The selected multi-agent runtime also needs a persisted value when no companion turn context is present.

## What changed

- Add optional `resume_metadata` to `CompactedItem`, recording the multi-agent version, last started turn ID, and previous turn settings. Preserve the distinction between absent metadata and explicitly empty values while retaining compatibility with older records.
- Capture this metadata under the settings persistence lock alongside the compaction checkpoint.
- Rewrite inherited metadata to use the child agent's runtime, and clear previous turn settings when the child must rebuild context.
- Clear pending continuation state before delivering acceptance of standalone settings updates, while holding the persistence lock.

## Testing

Add coverage for metadata round trips with empty values, legacy reader compatibility, checkpoint companion records, inherited fork metadata, and continuation invalidation while settings event delivery is blocked.

GitOrigin-RevId: f30b7feaa7e2fdb5b65fc3c53b37fd7a7fe27903
2026-09-22 16:35:30 +00:00
Eric Traut 5a11c45606 Render TUI Markdown lists with Unicode bullets and checkboxes (#47322)
## What changed

Render unordered bullets as `•` and task markers as `☐` or `☑`, preserving ordered numbering and continuation indentation in streaming and completed Markdown. Add `tui.rendering.lists`, enabled by default; setting it to `false` retains hyphen bullets and textual task markers.

## Testing

Add snapshot coverage for nested, ordered, quoted, and wrapped task lists, plus code and escaped markers. Add character-by-character streaming tests that compare incremental and emitted output with full rendering, with list rendering enabled and disabled.

GitOrigin-RevId: df9209d8c42f277dd2a2d7073ea19a6feb7dd706
2026-09-22 16:34:07 +00:00
jif 5c07856e25 Separate local agent runtime state from controller handles (#47301)
## What changed

Extract `LocalAgentRuntime` from `LocalAgentControl` to hold the shared registry, residency state, execution limiter, rollout budget, service tier, instruction provider, and thread-manager bindings. Keep session identity on the controller handle.

Store the runtime in `SessionServices` and use it to bind controllers for child startup, resume, delegation, and guardian reviews. Route ownership checks and residency handling through the shared runtime, preserving registry identity across handles. Update existing test fixtures to keep the controller and runtime paired.

GitOrigin-RevId: 846094657cbdf736da3149f0a1c96b4e01423dfe
2026-09-22 14:48:28 +00:00
jif c6c09fe29f Consolidate agent operations in the AgentControl implementation (#47292)
## What changed

Move `spawn`, `send`, and `inspect` into the `AgentControl` implementation for `LocalAgentControl`, removing the forwarding methods and the `spawn_request` module. Update tool handlers and existing tests to use the trait methods, and remove redundant boxing at spawn call sites.

Preserve spawn validation, message attribution, runtime loading, and queue-only delivery semantics.

GitOrigin-RevId: 6027d4d97d0dfb6763dc97ef92a2d7ef58de945d
2026-09-22 13:47:56 +00:00
felixxia-oai d9ac1f02ed Update the Guardian extra-policy snapshot for retained instructions (#47287)
## What changed

Update `extra_policy_reaches_guardian_review` to expect a retained user
instructions section before the transcript, including the source-order notice
and the original user request. Adjust the subsequent snapshot item numbers.

GitOrigin-RevId: 9e57f9bb7cdc9318787d083bf4350143a1353287
2026-09-22 13:17:13 +00:00
jif 89a7298aff Add regression coverage for message board unsubscribe persistence (#47281)
Verify that unsubscribing from a message board thread remains effective
after posting to that thread and resuming the session. The runtime test
checks that replies from a child agent produce no `CHANNEL_POST` notices
while unsubscribed and that explicit resubscription restores delivery.

Use gated streaming responses to keep the recipient active during each
reply and drain worker completion messages before checking notices.

GitOrigin-RevId: fe2695a46722a94e6fca86a3d3bd49c0b8bb7ee7
2026-09-22 13:02:44 +00:00
felixxia-oai 279ba89415 Enable Guardian thread context by default (#47275)
## What changed

Mark `guardianv2.thread_context` as stable and enable it by default for synchronous and asynchronous Guardian reviews. Keep it independent of the Guardian v2 `enabled` toggle and preserve explicit configuration and profile overrides. Update the configuration schema documentation to match.

## Testing

Update coverage for default configuration and sender user messages, review prompt snapshots, history retention across compaction, and checkpoint provenance. Assert that later user input invalidates an in-flight review's authorization. Keep legacy transcript budgeting coverage by explicitly disabling thread context in that test.

GitOrigin-RevId: 19afd34d7bfc0ee36bbf878089c68b732a21bc6a
2026-09-22 12:43:11 +00:00
felixxia-oai 99784bd09b Allow Guardian sync review across compaction hash differences (#47272)
## Why

Thread-owned Guardian review rejected usable parent compaction checkpoints when the reviewer's `comp_hash` differed or was unknown, even though the synchronous reviewer can consume those checkpoints.

## What changed

Remove the synchronous reviewer's compaction hash compatibility check and the associated hash plumbing. Pass usable checkpoints to the backend for payload validation, while continuing to fail closed on unusable checkpoints and review errors.

## Testing

Update compaction and resume tests to expect retained evidence with different, missing, or empty reviewer hashes, while preserving rejection of empty checkpoint content.

GitOrigin-RevId: bbc4f5a2e697f832f815dcf8bda4d4a652f06b8a
2026-09-22 12:37:11 +00:00
jif 16bb1b9d7e Implement AgentControl for LocalAgentControl (#47271)
## What changed

Add an adapter that delegates the shared controller interface to existing local agent operations, including lifecycle management, message delivery, status observation, budget accounting, and shared settings.

Align the trait signatures and documentation with local behavior: separate advisory capacity checks from execution tracking, preserve best-effort completion reporting, and return optional guardian evidence. Use `SessionId` for controller identity and replace paginated queries with loaded-agent listing by path prefix, removing the obsolete types and exports.

GitOrigin-RevId: 15bb7135e0f180d207390f6f2e75f63b9058816a
2026-09-22 12:19:05 +00:00
jif ac7634b9f7 Stream agent snapshots from local status subscriptions (#47267)
## What changed

- Return `StatusSubscription` streams of `AgentInfo` snapshots from local status subscriptions, including agent metadata and configuration.
- Emit the initial snapshot before subsequent coalesced updates. Use a weak thread reference and retain the last observed configuration so published final updates remain available after the runtime is dropped.
- Update completion notifications and `wait_agent` to consume snapshot streams, propagate subscription errors from `wait_agent`, and fall back to the latest status when a stream ends.

## Testing

Update the shutdown subscription test to verify that shutdown before the first poll preserves the initial `PendingInit` snapshot followed by `Shutdown`.

GitOrigin-RevId: beb46952cbcc9bddf65a4d6603fea939d5ace8b9
2026-09-22 11:44:00 +00:00
jif 3d5cdc51d0 Test spawn settings reporting after child removal (#47258)
## What changed

Add a V1 spawn regression test that removes the child from the thread manager during startup, before spawn reports its settings. Verify that the completed spawn event retains the role-configured model and reasoning effort, nickname, and role even when the child can no longer be looked up.

Also verify that the child receives its initial input with the effective settings and the parent receives a successful spawn result.

GitOrigin-RevId: 5e94e3ddb0feda0eaaa86e7539ef8c6720176f88
2026-09-22 11:10:29 +00:00
jif fdd89e78ac Return agent snapshots from close_agent (#47252)
## What changed

Return an `AgentInfo` snapshot captured before shutdown, including metadata for known unloaded agents. Use the snapshot's status and metadata in the tool's completion event and its status in `previous_status`, replacing the separate status subscription.

Preserve the pre-close status for error reporting when shutdown removes the target before a descendant fails to close. Propagate unexpected thread lookup errors before attempting shutdown.

GitOrigin-RevId: bdbd877aaf0389e830d6a7e84a5e14bb7d47277a
2026-09-22 10:58:32 +00:00
jif c117207a6f Drop descendant channel posts from retained remote compaction v2 history (#47249)
## Why

Remote compaction v2 excluded descendant progress messages from retained history but kept `CHANNEL_POST` messages from those same agents.

## What changed

Treat descendant `CHANNEL_POST` messages like `MESSAGE` progress updates when selecting history to retain after remote compaction v2.

## Testing

Extend the remote compaction test to verify that a child channel post is included in the compaction input and omitted from the follow-up request.

GitOrigin-RevId: 204bf44b8cddf1e6dc1e48234f51d4ac2aaf2e9f
2026-09-22 10:44:00 +00:00
jif c46aa58a7b Centralize agent resume handling in LocalAgentControl (#47244)
## What changed

Add `LocalAgentControl::resume_agent` to reuse an existing thread or restore it from its rollout when lookup returns `ThreadNotFound`. Return the agent's current status, metadata, and configuration snapshot.

Route the `resume_agent` tool through this method, replacing its status-based resume check and separate restoration helper.

GitOrigin-RevId: 2ae0572a030f169eca1760ba0aff1fb9e2ab6651
2026-09-22 10:27:19 +00:00
jif acc20df49f Prevent V2 agent eviction from racing with queued messages (#47240)
## Why

Accepted inter-agent messages can still be waiting in the submission queue when a worker appears idle. Evicting that worker can lose the queued work, while cancelling an eviction caller can leave shutdown unfinished and allow delivery to a closing runtime.

## What changed

- Pin V2 recipients until queued submissions are handled or dropped, and verify that delivery targets the registered runtime.
- Move `Submission` into core so it can carry the residency guard through queue handoffs.
- Give eviction exclusive access to each runtime and keep it counted against capacity until removal. Run teardown in a separate task so it completes even if its caller is cancelled, and remove registry and residency entries together.

## Testing

Add a regression test covering queued follow-up delivery, eviction refusal while mail is pending, cancelled eviction completing teardown, rejection of late delivery, and capacity reuse after removal.

GitOrigin-RevId: d6de3d68cb6b911942e9ddfc05c65b3741b796b2
2026-09-22 09:50:48 +00:00
jif b58b05e062 Suppress agent message board notifications to the post author (#47236)
## Why

Channel and thread subscriptions, or explicit `agents_to_notify`, could cause agents to receive notifications for their own posts.

## What changed

Exclude the author from notification recipients, even when explicitly targeted. Preserve the author's subscriptions so replies from other agents still reach them, and document this requirement in the board API.

## Testing

Update board tests to cover explicit self-targeting, subscribed authors, and delivery of other agents' replies. Update the model-context scenario and snapshot to verify posts remain searchable without a `CHANNEL_POST` self-notification.

GitOrigin-RevId: 0b2558e7df79122a6da06ad592f9735ba260cce1
2026-09-22 09:39:49 +00:00
jif f908e5a968 Route multi-agent spawning through SpawnRequest (#47235)
## What changed

- Route both multi-agent spawn handlers through `LocalAgentControl::spawn`, accepting user input or an agent message.
- Centralize spawn message attribution and canonical path validation, and require message input to use `TriggerTurn`.
- Return the child's configuration snapshot alongside `LiveAgent`, so handlers obtain effective settings directly from spawning without a separate lookup.
- Update child test fixtures to use the shared spawn entry point.

GitOrigin-RevId: 9f9278df08041a62215f9ec3d38688c78fc5e0e2
2026-09-22 09:32:22 +00:00
Ben Romano 94174e44cb Preserve MCP request trace context across transport workers (#47212)
## Why

MCP requests pass through background transport queues, so HTTP requests need the caller's trace context carried explicitly to preserve trace ancestry.

## What changed

- Capture W3C trace context in request metadata for tool and resource operations, custom requests, and event streams.
- Restore that context in an `mcp.http.request` span around HTTP POSTs, linking outgoing HTTP traces to the originating request.
- Preserve application metadata while replacing trace fields with the current caller's context and removing stale `tracestate`. Read the SDK's merged metadata so extension fields retain precedence over parameter metadata.

## Testing

Add a unit test for metadata merge precedence and an integration test covering concurrent paginated requests, tool calls, custom requests, and tool-call continuations across legacy and `2026-07-28` protocol modes. Verify HTTP trace ancestry, metadata preservation, and removal of stale `tracestate`.

GitOrigin-RevId: 0b22cd75f31f9fcb855b27fa8d34ecdffd6e3549
2026-09-22 06:47:07 +00:00
Celia Chen 6ea62c4396 Resolve proxy routes for standalone web search redirects (#47204)
## Why

Standalone web search selected a proxy route only for the initial endpoint. Redirect destinations can require a different system proxy route.

## What changed

- Add `RouteAwareClientPool` support to `ReqwestTransport` for both buffered and streaming requests, and use it for standalone web search.
- Preserve default Codex headers and Cloudflare cookie handling across routes, while retaining the default client behavior when route-aware handling is disabled or Codex is sandboxed.
- Share request construction so URL authentication and header precedence follow `reqwest` semantics, applying them once before redirects and TLS retries.
- Map route-aware failures to transport errors and remove request URLs from those errors.

## Testing

Add regression coverage for redirects through distinct proxies, preservation of POST bodies and default headers, URL authentication and header precedence, and transport error classification without URL leakage.

GitOrigin-RevId: 19a10a62118846db09dd95265dc277e54aac09ef
2026-09-22 06:24:49 +00:00
dermanyang-oai b781733f95 Separate thread preparation from execution persistence (#47199)
## Why

Injecting context before the first turn currently forces a full flush. Stores need a preparation checkpoint that can leave disposable context in memory, while local storage must keep prepared context durable before the first user input.

## What changed

- Add `PersistContext::ThreadPreparation` and `CodexThread::checkpoint_preparation()`, and use the checkpoint in `inject_response_items()`.
- Allow stores to defer rollout-derived metadata writes through `record_thread_metadata()`, including during preparation and execution checkpoints. Keep standard metadata updates synchronous.
- Flush local storage at preparation checkpoints so injected context survives restart.

## Testing

Add tests showing that preparation and first sampling can proceed without waiting for durable metadata. Cover prepared context in first and follow-up requests, plus durability before first input and restoration after restart, in both legacy and paginated history modes.

GitOrigin-RevId: 74f6bb1a5f8d47192364b8bba6afd703a3b7d688
2026-09-22 05:53:29 +00:00
Eric Traut 5106a5234f Enable the fullscreen transcript by default (#47178)
## What changed

Default `tui.fullscreen_transcript` to `true`, including when the `[tui]`
section is absent, and apply the same default to the first frame. Update the
configuration schema to match. Alternate-screen restrictions still take
precedence, and `tui.fullscreen_transcript=false` restores terminal scrollback.

## Testing

Update configuration and startup tests for the new default, including an empty
`[tui]` section and `--no-alt-screen`. Adjust PTY tests to cover default fullscreen
entry and explicit opt-out to terminal scrollback.

GitOrigin-RevId: e460dcd058d52c50da2abc5113bbb678e845d5fc
2026-09-22 03:20:04 +00:00
ningyi-oai a37f260dc6 Preserve empty cell metadata under pending tool-call pressure (#47174)
## Why

Reaching the pending tool-call limit could evict finished empty cells even though removing them frees no pending-call capacity. This loses the metadata needed to certify an empty tool-call inventory on a later `wait`.

## What changed

Only evict cells with pending calls when reclaiming pending-call capacity. Keep empty cells eligible for eviction when a cell slot is needed.

## Testing

Extend recorder coverage to check empty inventories under pending-call pressure in fresh and resumed sessions. Add a code-mode integration test verifying that `wait` serializes an empty inventory with `tool_calls_complete: true` while another cell has filled the pending-call budget.

GitOrigin-RevId: 559d0b4fdc9864c42a90b7d087eb2a3327272d5c
2026-09-22 03:03:52 +00:00
acrognale-oai 30daed37ad Apply workspace routing to Guardian v2 classifier requests (#47162)
## Why

Classifier requests need to preserve their owning thread's workspace routing and account binding, including when reusing pooled connections or retrying after authentication changes.

## What changed

- Share the thread's `WorkspaceRoutingContext` with Guardian v2 and resolve routing before leasing HTTP or pooled WebSocket connections.
- Reuse WebSockets only when their connection key and authentication state still match. Cache HTTP transports by URL and redirect policy, rejecting redirects when routing requires it.
- Stop classification requests and retries when the account owner changes while allowing token refreshes for the same user and workspace.

## Testing

Add regression coverage for routing failures with prewarmed sockets, shared thread routing state, account switches during HTTP and WebSocket requests, same-account token refreshes, and HTTP redirect-policy cache changes.

GitOrigin-RevId: 7b3efcadb4797b6a2de2e28e7506b297b0728d69
2026-09-22 02:33:29 +00:00
andrewgu-oai c11ed24c2a Update code mode catalog snapshot hashes (#47149)
Refresh the collaboration namespace hash and aggregate tools hash in the
`code_mode_catalog_messages` snapshot.

GitOrigin-RevId: bcfb793ba379760219cb4214d39f9c8bcd01e40c
2026-09-22 01:38:17 +00:00
Celia Chen b045757052 Honor system proxy settings for standalone web search (#47142)
## Why

Standalone web search used a default HTTP client, bypassing the configured system proxy route when `respect_system_proxy` was enabled.

## What changed

Pass the configured `HttpClientFactory` to the web search tool and create its client asynchronously for the provider's search URL using the API route policy. Export and reuse `SEARCH_ENDPOINT` so route selection and search requests use the same endpoint.

## Testing

Add an isolated regression test with environment proxies removed and a mock system proxy. Verify that standalone web search reaches the proxy and returns its result in the follow-up model request.

GitOrigin-RevId: 3b64803a777b9d1eb0ccf694e06658b0fd562129
2026-09-22 00:59:54 +00:00
andrewgu-oai cf6754e682 Remove the ultrafast service tier from gpt-5.6-sol (#47130)
## What changed

Remove `ultrafast` from the bundled `gpt-5.6-sol` model's `service_tiers`, leaving `priority` (Fast) as its only advertised service tier. Update scenario snapshots for the affected multi-agent tool definitions.

GitOrigin-RevId: 9a235d8f7ea8a72e71152708d2d602194256d420
2026-09-21 23:37:53 +00:00
Adam Perry @ OpenAI 69759baefd Preserve foreign working directories in extension tool environments (#47129)
## Why

Extension calls omitted environments whose working directories could not be converted to host-native paths, preventing extensions from receiving those environments.

## What changed

Store `ToolEnvironment.cwd` as `PathUri` and pass all turn environments to extension tools without requiring host-native path conversion. Keep image generation's existing path requirements by selecting the first environment with a convertible working directory when reading referenced images or saving generated images.

GitOrigin-RevId: b4320c6e07d27ef59885cd0013e5d1c535f69659
2026-09-21 23:27:42 +00:00
Won Park 26cb4d73e2 Add extra policy configuration for Guardian reviews (#47125)
## What changed

- Add `auto_review.extra_policy` and the managed `guardian_extra_policy` requirement to supply policy text alongside the resolved tenant policy. Nonblank managed values take precedence; blank values are ignored.
- Render the additional text through `{{ extra_policy }}` in Guardian reviewer templates and append it to the tenant policy for Guardian v2 classification before truncation.
- Preserve placeholder-like text inside supplied policies literally.

## Testing

Add coverage for configuration precedence, blank values, template substitution, and classifier prompts, plus a scenario verifying that managed tenant and extra policies reach the Guardian reviewer together.

GitOrigin-RevId: 180d8d716c63fe96a92ec5bfbd22db4ddccd4f1f
2026-09-21 23:06:36 +00:00
Krish Chainani 4a8cfe6bb7 Pass thread IDs to attachment uploads (#47121)
## Why

Attachment stores need the receiving thread ID to support thread-based placement.

## What changed

Add `thread_id` to `UploadRequest` and pass the session's thread ID through image preparation for messages and tool outputs. Include the ID in debug output while continuing to redact attachment bytes.

## Testing

Extend the image rollout test to assert that a new image uploaded after resume carries the resumed session's thread ID. Update the debug-output test for the new field.

GitOrigin-RevId: f81e3bd761dca704064287177b8ecd7175662f07
2026-09-21 22:58:49 +00:00
rhan-oai 5aa4939be4 Support model-catalog overrides for Code Mode tool messages (#47118)
## What changed

- Add `tools.code_mode` catalog messages for `exec`, `wait`, deferred-tool guidance, and shared MCP TypeScript definitions.
- Render `{{ default_exec_yield_time_ms }}` and `{{ image_helper }}` in `exec` descriptions while preserving runtime tool declarations and the freeform grammar.
- Resolve `wait` descriptions and parameter schemas independently, falling back to bundled parameters for invalid or unsupported schemas.
- Use the active model's Code Mode messages, including after mid-turn model changes. Missing overrides retain bundled defaults; empty text overrides suppress the corresponding text.

## Testing

Add coverage for literal template substitution, runtime section preservation, independent `wait` overrides and fallback behavior, mid-turn model changes, and a yielded cell completing through `wait` with catalog messages.

GitOrigin-RevId: e542a0cd47a7138a414871192cee47790ed1214e
2026-09-21 22:49:17 +00:00
Jesse Du 3fd5160cd6 Honor the configured product SKU in remote plugin requests (#47116)
## Why

Remote plugin requests always sent `OAI-Product-Sku: codex`, ignoring the existing `apps_mcp_product_sku` setting.

## What changed

Pass `apps_mcp_product_sku` through plugin configuration and use it for authenticated remote plugin requests, including discovery, search, installation, and sharing. Keep `codex` as the default and include the SKU when comparing remote service configurations.

## Testing

Extend app-server plugin listing and core agent-turn tests to check default and configured SKU headers. Update the CLI worktree test to wait for the user prompt's model request, skipping background title generation requests.

GitOrigin-RevId: 508c9ef9aa3e41b87c92383c3088eb1eb9227fd8
2026-09-21 22:30:43 +00:00
Jeremy Rose 23ae65bb06 Persist thread creator identity in rollouts and SQLite (#47113)
## What changed

- Capture optional `creator_user_id` and `creator_account_id` from authentication when creating a thread, including forks.
- Carry these fields through thread storage, rollout metadata, and a SQLite migration. Leave them absent when unavailable or when reading older threads.
- Preserve recorded creator values across resume and metadata updates. On revert, recover missing rollout values from SQLite before writing replacement metadata.

## Testing

Add coverage for ChatGPT and API-key sessions, resume under another account, forks using current authentication, metadata extraction and upserts, and repeated reverts after creator fields are removed from a rollout.

GitOrigin-RevId: 9839fa42f9392f12226002e2c27d05d5656f5695
2026-09-21 21:22:01 +00:00
Eddie Chen 6a601c00da Preserve originating turn metadata for yielded skill calls (#47106)
## Why

Code Mode callbacks can retain skill tools after another turn becomes active. Looking up the active turn when a delayed skill invocation completes can lose access to the originating turn's metrics and metadata.

## What changed

- Capture and retain the originating `SkillTurnMetrics` when constructing skill analytics.
- Expose turn analytics metadata through the turn extension store and carry it into skill telemetry.
- Add optional turn metadata to `TrackEventsContext` and pass it from app, skill, and plugin usage call sites.

## Testing

Add a regression test that yields a Code Mode cell, starts another turn, and releases both skill reads through a shared barrier. Assert that each `skill_invocation` event retains its originating `turn_id`.

GitOrigin-RevId: aa629dd5f84563d558aa6a86bfbdfc356f1b98e4
2026-09-21 20:34:46 +00:00