## 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
## 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
## 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
## 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
## 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
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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
Refresh the collaboration namespace hash and aggregate tools hash in the
`code_mode_catalog_messages` snapshot.
GitOrigin-RevId: bcfb793ba379760219cb4214d39f9c8bcd01e40c
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## Why
Realtime WebSockets connected directly, bypassing the configured proxy policy for Voice's WebRTC sideband.
## What changed
Pass the configured `HttpClientFactory` into `RealtimeWebsocketClient` and connect through the shared `WebSocketConnector`. Add support for supplying an existing Rustls configuration to preserve custom CA handling and Windows platform trust.
## Testing
Add an integration test that enables `respect_system_proxy`, starts a WebRTC conversation, and verifies that the sideband establishes its session through an HTTP `CONNECT` proxy and closes successfully.
GitOrigin-RevId: d974c9275d7fe29f388d56a9d5d8ce0c483eb8d0
## What changed
- Describe GPT-5.6-Sol as a reliable agentic workhorse for everyday tasks and change its catalog `priority` from `6` to `4`.
- Describe GPT-5.5 as a proven previous-generation model for coding and general work.
- Refresh model picker, migration prompt, and agent tool snapshots to reflect the catalog updates.
GitOrigin-RevId: b39f51c22862b8cef585ed76f3973c9f4b670c27
## What changed
- Record each MCP source and its first turn, including connector and plugin identifiers when available. Cover direct and Code Mode calls, including returned errors and results that are not printed.
- Persist cumulative attribution checkpoints and restore them across compaction, resume, and forks, including forks limited to recent turns.
- Attach fresh attribution to Responses API `client_metadata` under `mcp_attribution`, outside model-visible content. Restrict transmission to allowed OpenAI HTTPS destinations for both HTTP and WebSocket requests.
- Report `attribution_error` for legacy history without checkpoints, malformed or conflicting attribution, and serialized attribution exceeding 16 KiB.
## Testing
Add coverage for source deduplication, checkpoint persistence and restoration, recent-turn forks, direct and Code Mode calls, destination filtering, and the serialized size limit.
GitOrigin-RevId: fd285e152ca9e24bfa000debb20013709d67a86e
## Why
Concurrent credential refreshes could restore a removed environment by overwriting the selection list with stale state. Unpolled snapshot futures could also keep pending configuration alive after an environment was removed.
## What changed
- Protect environment selections with a mutex and update them in place to serialize selection changes, configuration refreshes, and connection listener setup.
- Capture only selection metadata and resolution futures in snapshots so they do not retain pending configuration senders.
## Testing
Add regression tests for removal during credential refresh and cancellation while an unpolled snapshot is held. Strengthen the pending attachment integration test to check that `wait_for_environment` returns the expected environment ID and `ready` status.
GitOrigin-RevId: c6f933e8d3031b05335ddcfed00ab400aa5bad2a
## Why
Message board notifications exposed only post and thread IDs, requiring a read to see any post content.
## What changed
Deliver notifications as `agent_message` items with author and recipient attribution. Include a `CHANNEL_POST` payload with the sender, channel, message and thread IDs, and up to 150 characters of post text. Direct agents to `read_post` when the preview is truncated, and retain recognition of legacy user-role notices.
## Testing
Update the model-context scenario to assert the notification's author, recipient, and preview payload, and update the idle-agent scenario to check for the new notification format.
GitOrigin-RevId: e0e2794be82e38bba47f41fb4fc8128eb5e47619
## What changed
- Replace the built-in orchestrator skill provider with a host-supplied cloud provider, using `cloud` authority and `c` root aliases in skill tools and prompts.
- Add `cloud.skills.enabled`, defaulting to true but requiring a supplied provider. Keep `orchestrator.skills` accepted as a legacy no-op setting, and remove the app server's automatic orchestrator provider registration.
- Discover cloud skills once per turn during cancellable startup. Serve catalog snapshots to prompts and tools without triggering discovery or retries.
- Scope cached catalogs and resources to authentication state. Preserve them on refresh failures within the same scope, invalidate them when that scope changes, and reject late discovery or read results from replaced cache generations.
- Reuse executor discovery catalogs only when successful discovery inputs and bundled-skill settings match.
## Testing
Add coverage for per-turn refresh, skill removal, same-account failures and reconnects, authentication changes, and stale in-flight results. Update configuration and tool tests for cloud authority, provider gating, and resource reads without an executor.
GitOrigin-RevId: c57e38ec7dcc880c0d4c8a2995adfd3e28301079
## Why
`TurnComplete` precedes active-turn cleanup, so injecting follow-up history immediately afterward can race with cleanup.
## What changed
Register the `ThreadIdle` lifecycle contributor in `review_preserves_user_instructions_until_request_budgeting` and wait for the thread to become idle after the initial and follow-up turns.
GitOrigin-RevId: 1ae6c80593a71d331c5c6ddf85bbe10822a68afe
## Why
Guardian can lose a confirmed User Messaging message from its parent context when a `PostToolUse` hook blocks the result or is cancelled. The message has already been sent and remains relevant to interpreting the user's authorization.
## What changed
Capture confirmed message text after input-rewriting hooks in shared per-call state before awaiting post-tool processing. Attach that evidence to the response metadata even when dispatch returns a blocked or aborted result, while keeping post-tool hooks cancellable. Calls cancelled before delivery confirmation contribute no message evidence.
## Testing
Extend Guardian subagent authorization coverage to verify retained messages after post-tool hook blocking and cancellation, and their absence when cancellation precedes delivery confirmation.
GitOrigin-RevId: 9abb7959980eada20d0fb5c0b3a4a8669e4cd0a3
## Why
Extension tool calls eagerly copied and converted conversation history even when the tool never read it.
## What changed
Retain a shared invocation-time snapshot and defer conversion to raw response items until `ConversationHistory::items()` is called. Cache the result across clones with `LazyLock`, and keep debug formatting from triggering materialization. Release unrelated history metadata when capturing the shared items.
## Testing
Extend the extension executor test to verify that history first read after a later turn still reflects the invocation-time snapshot, in both legacy and paginated history modes. Update the history API test to check that shared items preserve their envelopes.
GitOrigin-RevId: c737b765b7e4889735dc78e12d685d36e854570b
## Why
Guardian's retained root context appended assistant messages after user evidence and omitted questions sent through User Messaging. This could leave subagent authorization reviews with missing or misplaced conversational context.
## What changed
- Record assistant messages and function calls in the same order sequence as accepted user inputs, then merge retained review context by recorded position while prioritizing user evidence within the message budget.
- Capture bounded User Messaging text after input hooks when a send succeeds, and match it to the original call for assistant context.
- Label assistant context without a recorded position explicitly and clear parent assistant and tool positions when forking agent history.
- Clarify that recorded order does not establish delivery order or pair ordinary replies with questions; assistant messages remain untrusted context.
## Testing
Add coverage for hook-rewritten messages, failed or unconfirmed sends, queued replies with delayed tool results, ordering across resume, and removal of inherited assistant positions from forked history.
GitOrigin-RevId: ac717cf0f5efe4b05c18f2d8370dd48453ac4e35
## Why
Permanent thread deletion needs to remove persisted agent message board data even when the message board feature has been disabled.
## What changed
- Add a cleanup hook for single and batch thread deletion, invoked after reference and writer checks but before rollout removal so cleanup failures remain retryable.
- Remove the deleted roots' channels, posts, and subscriptions regardless of the current feature setting.
- Record board tombstones and check them within write transactions to prevent delayed writes from recreating deleted data.
## Testing
Add an app-server regression test that creates a board, archives its root thread, restarts with the feature disabled, and verifies that permanent deletion removes the persisted channels, posts, and subscriptions.
GitOrigin-RevId: 4ea71559a8df0814dffda23a056a9bbaf6e0a0cb
## Why
Message-board tools hardcoded the `collaboration` namespace and used a different namespace description from the multi-agent tools. This ignored custom namespace configuration and caused conflicts under strict tool collision checking.
## What changed
- Use `multi_agent_v2.tool_namespace` and the shared multi-agent namespace description for message-board tools, resolving the namespace at runtime startup.
- Support unnamespaced tool specifications when no namespace is supplied.
- Remove hardcoded `collaboration` prefixes from message-board notifications.
## Testing
Add app-server integration coverage for the default `collaboration` namespace and a configured `agents` namespace with strict collision checking enabled. Verify that both tool families are advertised together and that `get_channels` executes through the installed extension.
GitOrigin-RevId: fef7be51ea2a84bbdb6d3491606db442ed4e6ea3
## What changed
- Register the existing message-board tools with the app server through a lifecycle extension, gated on `agent_message_board`, multi-agent v2, and non-ephemeral sessions. The new feature flag is disabled by default.
- Bind tools to each agent's identity and share the SQLite-backed board across the agent tree and runtime resumes.
- Use the runtime clock for posts and deliver ID-only notifications to running agents, with tools to retrieve post contents. Skip inactive recipients without starting them or queuing notices.
- Emit a warning and leave board tools unavailable if initialization fails.
## Testing
Add runtime scenarios and a context snapshot covering feature gating without creating storage, posting and searching, active-only notifications, sharing with child agents, persistence across resume, and clock failure without channel creation.
GitOrigin-RevId: a81bd85cd372b0d122ba375ed1a1bfd3ba3a3b7c
## Why
Agent inspection needs to distinguish registered but unloaded agents from missing identities and backend failures without restoring a runtime.
## What changed
- Add inspection returning `AgentInfo` with metadata, status, and configuration for loaded agents, or metadata for unloaded agents.
- Use inspection for configuration snapshots and to capture an agent's state before interruption.
- Add `AgentInfo` accessors and share V2 error mapping between interruption and messaging tools, preserving the distinction between invalid requests and a dropped thread manager.
## Testing
Extend the V2 reload test helper to assert that inspecting a registered, unloaded agent returns `AgentInfo::Unloaded` and leaves its runtime unloaded.
GitOrigin-RevId: fa897264ff3ff3ec6cc76259d8482be55dec0c0a
## Why
Tool allowlists alone cannot express the reviewer's sandbox and shell restrictions, which previously depended on session identity. Threads need to supply these restrictions explicitly at startup.
## What changed
- Replace `AllowedTools` with `ToolPolicy`, combining an optional allowlist with managed-sandbox requirements, unified-exec requirements, and control over additional-permission arguments.
- Capture the policy once at startup and apply it during tool registration and construction, including hosted tool filtering. Later extension-state changes cannot relax it.
- Supply the reviewer policy explicitly while retaining the fallback for reviewer sessions without a supplied policy. Explicit policies take precedence over session identity; ordinary defaults preserve existing tool setup.
## Testing
Update tool-planning tests to use explicit policies and add startup coverage for additional-permission schemas, ordinary defaults, reviewer fallbacks, explicit-policy precedence, and policy capture despite later extension-state changes.
GitOrigin-RevId: 71e561d76ea24d961f5b29c7c619bdb1356c216a
## What changed
Replace `LocalAgentControl::deliver_message` with `send(SendRequest)`, accepting both user input and agent messages with captured resume configuration and turn options. Resolve target references relative to the caller's registered identity and return recipient metadata and a submission ID in `DeliveryReceipt`.
Migrate the V2 messaging tools to the new entry point and use receipt metadata for activity events. Preserve recipient reload behavior, non-waking queue-only messages, and rejection of follow-up tasks targeting the root agent.
## Testing
Update the cold-resume and sibling-reload tests to exercise `SendRequest` while checking instruction inheritance.
GitOrigin-RevId: 8fd330b8a9c3510483110ed05c4c9d3d616db237
## Why
Native `openai/userVerification` requests need to carry optional `_meta` to clients for extension-specific presentation.
## What changed
- Accept optional metadata objects with the same validation as MCP elicitation.
- Restore metadata from the MCP request context, excluding `progressToken`, and forward it through `mcpServer/elicitation/request`.
- Update protocol types, schemas, and documentation while retaining support for requests without metadata. Challenge bytes and acceptance proofs remain unchanged.
## Testing
Add coverage for metadata validation, transport context restoration, and protocol round trips. Extend MCP integration tests to check that verification metadata reaches the client.
GitOrigin-RevId: 5d04004244cf33effac675c19e543157c48d1504
Owen Lin