## What changed
- Honor `RuntimeAgentInstances` and the configured runtime auth mode for Analytics plan discovery and report requests to OpenAI endpoints.
- Share installation ID resolution and Codex runtime registration setup through `codex-runtime-agent-instance`.
- Preserve typed runtime authentication errors so expired credentials retain the “Sign in again to load Analytics” guidance.
## Testing
Add coverage for both runtime auth modes across regional and staging endpoints, fresh assertions for each request, sign-in guidance after bootstrap failure, redirect rejection, and invalid organization/project selectors.
GitOrigin-RevId: 50e0d959b3abd81ebe7a6a584e272f14cf52e504
## Why
Invalid assertions and paused or revoked runtime instances cannot recover through request retries or credential refresh. Permanent refresh-token failures also need to retain their sign-in error instead of becoming retryable stream errors.
## What changed
- Recognize terminal runtime denial codes in `401` and `403` response bodies and identity error headers, preserving HTTP diagnostics while stopping retries.
- Skip credential recovery for runtime denials in runtime-enabled model providers and backend requests, while preserving recovery for ordinary credential expiration.
- Propagate permanent refresh-token failures through runtime authentication as `RefreshTokenFailed` errors.
## Testing
Add coverage for body and header denials, preserved HTTP diagnostics, provider-scoped credential recovery, and cached permanent refresh failures. Complete-turn tests verify that runtime denials stop without retries or refreshes while expired credentials recover in both runtime authentication modes.
GitOrigin-RevId: 33f6f707454130e97e13f3b53e29d2c484602152
## What changed
Make `ModelRequestContributor::budget_exhausted` return an `ExtensionFuture` and await budget checks before HTTP and WebSocket generation. WebSocket warmup continues to skip budget checks.
If the account changes during the post-connect budget check, rebuild the request setup and reconnect before sending the WebSocket request.
## Testing
Update tests to cover a pending budget check that resolves to exhaustion, warmup connection reuse, and an account switch while the post-connect budget check is awaiting completion.
GitOrigin-RevId: 462c74b86a46a4b2276f901c69187fc7cbc3ff81
## What changed
Make `AgentServiceTier` reads asynchronous and have updates return a receipt for local acceptance. Await acceptance during root startup and settings updates outside state and registry locks, sharing the receipt with explicit same-tier retries.
Await shared-tier reads during child preparation, startup prewarm, and step capture. Allow cancellation while capturing a step, and keep host propagation independent of the acceptance wait.
## Testing
Extend the host-child WebSocket test to cover delayed acceptance, same-tier retries without duplicate updates, accessible settings while acceptance is pending, and tier inheritance during prewarm and subsequent steps.
GitOrigin-RevId: 0e2e1899834c37684e904c4a36e66344a0c6c7f3
## Why
An inherited turn can suppress a fork's configured developer instructions, leaving the first side-chat request without its developer policy.
## What changed
- Move shared side-conversation instructions and the history boundary into `codex-context-fragments`.
- Inject the developer policy before the user-role boundary when creating a TUI side-chat fork, while retaining the configured instructions.
- Distinguish attached and temporary policies, applying the worktree restriction only to temporary side chats.
- Add guidance to set up recurring monitors in the main chat or a new chat because temporary side chats cannot run scheduled updates.
## Testing
Add a TUI integration test that checks the first side-chat model request contains the policy and boundary. Add a core request-history snapshot covering an attached side chat that preserves inherited context, policy, and its prior answer after resuming from disk.
GitOrigin-RevId: 889cb317dc3327457cd9ef0879ec9f77dbfaeeba
## Why
Guardian Decisions requests used bearer keys directly, bypassing runtime authentication. Memory startup quota checks used the app-level auth manager instead of the thread's provider auth context.
## What changed
- Bind Decisions credentials to runtime authentication and use route-aware HTTP clients with sensitive header protection. Preserve workload identity credentials, reuse the saved-login runtime binding, and isolate explicit API key bindings.
- Select the staging Decisions endpoint when the ChatGPT environment is staging.
- Use the thread's `ProviderAuthContext` for memory startup and quota checks, preserving account-bound network policy and applying runtime authentication.
- Keep custom destinations independent of runtime assertions.
## Testing
Add regression tests for dual-header and assertion-only authentication, fresh Decisions assertions, saved versus explicit credential isolation, workload identity, staging routing, redirect header protection, and memory quota authentication with custom destinations.
GitOrigin-RevId: 27bc7821a1cad1f5d1d2a71680527ea91ace95db
## Why
An open WebSocket can remain usable after its runtime is paused. Runtime-authenticated requests need a fresh handshake to revalidate access before submitting more work.
## What changed
- Reconnect before each runtime-authenticated Responses request and skip speculative preconnection. Preserve turn routing when the runtime identity is unchanged.
- Open a fresh connection for each runtime-authenticated Guardian classification instead of prewarming or reusing pooled sockets.
- Preserve HTTP fallback for unsupported upgrades and connection failures, while propagating authentication, authorization, rate-limit, and policy errors.
## Testing
Add regression coverage for pause and unpause behavior, credential changes, fresh assertions, and Guardian HTTP and WebSocket transports in both runtime authentication modes.
GitOrigin-RevId: 9f650147260da5cbbf5bb23dfff0af095fff3955
## Why
Child startup can lose remote model capabilities such as `tool_search` when the selected catalog is uninitialized or disk data is older than the parent's in-memory snapshot.
## What changed
- Initialize the final provider, auth, and originator catalog before resolving a child's startup model, then read it from memory.
- Preserve loaded catalogs, including empty responses and updates that failed to persist, without overwriting concurrent refreshes.
- Reuse catalogs across retry and WebSocket transport overrides while retaining routing and header distinctions.
## Testing
Add regression coverage for child tool search with warm, cold, and disabled caches; failed cache writes; concurrent refreshes; empty catalogs; and Guardian reviewer catalog reuse.
GitOrigin-RevId: 01d995a65b623cc7d6f26e2dc9b6e8cf380de782
## Why
Stale saved grants or malformed rules can cause valid network denials to be discarded. A failed rule write can also leave the in-memory policy inconsistent with native enforcement.
## What changed
- Add a helper to derive MCP network policy from controller and environment policies, permission profiles, approval settings, and saved rules. Preserve managed restrictions and conservatively deny traffic that requires review, request hooks, or DNS checks the metadata cannot express.
- Retain valid saved denials when grants violate managed constraints or a rule batch is malformed.
- Serialize runtime updates and persistence, publishing denials before the write so they remain effective if saving fails. Publish saved grants after a successful write.
- Extract validation of listener settings for running proxy updates.
## Testing
Add coverage for policy composition, mixed-executor local binding, native proxy denial parity, stale grants, malformed denials, failed persistence, and compatibility with trusted MCP servers without policy negotiation support.
GitOrigin-RevId: ef00632acb48a51fc582f18d20a3e713f953a191
## What changed
Gate `incremental_tools_legacy` on the `amazon-bedrock` and
`amazon-bedrock-runtime` provider IDs instead of the OpenAI provider for regular
Responses requests. Responses Lite continues to use `incremental_tools`.
## Testing
Expand the tool catalog update scenarios to cover both Bedrock provider IDs with
legacy incremental tools enabled and disabled. Update the regular Responses tool
removal scenario to use the Bedrock provider.
GitOrigin-RevId: ad0ff31975166a2a7fdcee6fefc272ecc79dd448
## Why
Regular chats start MCP servers eagerly even when cached tool definitions are available and the servers go unused. Allow those chats to use the cached catalog and defer eligible stdio servers until first use.
## What changed
- Add the disabled-by-default `mcp_lazy_stdio_startup` feature and expose it through experimental feature configuration.
- Defer cached stdio servers in regular chats when enabled, while keeping servers that require a live startup connection eager. Required servers with `startup_readiness = "catalog"` may defer; explicit reconnects remain eager.
- Announce the full eager startup batch before terminal statuses and exclude dormant servers from the initial startup summary. Update TUI tracking so deferred servers can report startup independently in later rounds.
## Testing
Add scenario coverage for a cached server staying dormant during unrelated work, starting on first use, and refreshing tool definitions and visibility. Cover required live startup, eager event ordering, experimental feature configuration, and TUI status handling.
GitOrigin-RevId: 74075fcd4f26c8c79b5901b6a8cb03fdb9e35a7f
## Why
Subagents reusing cached MCP tool definitions were forced to use the legacy protocol, preventing connection sharing from being negotiated on first use.
## What changed
Keep stdio protocol discovery enabled during deferred startup while allowing dormant subagents to advertise cached legacy tools. Track modern discovery separately from catalog updates so discovery clients reject older legacy catalogs while legacy clients can still reuse them. Keep modern tools out of the legacy catalog when joining pooled connections.
## Testing
Add coverage for deferred subagents negotiating sharing on first use and reusing the same server process, while a legacy sibling retains cached definitions without starting its server. Extend cache coverage to ensure older legacy fetches cannot undo modern discovery.
GitOrigin-RevId: 5f8f4deb22cfb81a08c05ff3fcd7ba5c9199551c
## What changed
Allow `requirements.toml` to pin `features.runtime_agent_instances.mode` to `dual_header` or `assertion_only`. Apply the required mode when no explicit mode is configured and reject conflicting explicit settings, while preserving legacy boolean requirements.
Document experimental runtime authentication configuration, credential lifecycle, and bootstrap authentication behavior.
## Testing
Add coverage for managed mode defaults and conflicts, runtime reuse and rotation across account requests and restarts, fresh assertions on Realtime and MCP reconnects, and Realtime destination and environment restrictions.
GitOrigin-RevId: bcf9502178f477c1e8232386f1f3e360bf23d667
## What changed
- When `multi_agent_v2.disable_native_tools` is enabled, use bundled mode policies instead of model catalog guidance, while preserving explicitly configured mode hints.
- Refer to multi-agent tools and instruct the model to read the full multi-agent skill before calling them. Keep proactive delegation enabled for `Ultra` reasoning and explicit-request-only delegation for other reasoning levels.
- Reset retained nonempty custom mode hints to explicit-request-only guidance when multi-agent support is disabled, including after a cold resume.
## Testing
Extend integration tests and request snapshots to cover hosted-tool guidance, configured hint precedence, proactive mode with `Ultra` reasoning, and the mode reset after a cold resume.
GitOrigin-RevId: 403791ef76f990e385d9c155d9c2edc9acfcd4fe
## What changed
Keep the advertised `_codex_apps.invocation_context` when an app's tool metadata refreshes on the same server connection, while using refreshed values for other metadata. If the invocation context changes on a different connection, skip the call as unavailable.
## Testing
Extend the code-mode compaction test to refresh app tools before resuming a cell and verify that calls retain the original invocation context while picking up the refreshed `resource_uri`.
GitOrigin-RevId: 1b6072faed74623994ea82035a6ed977451984a4
## What changed
Replace `ThreadManager::models_manager_for_startup` with `resolve_startup_model`, which accepts `StartThreadOptions` and returns the selected `ModelInfo` before starting or cold-resuming a thread.
Share model resolution and effective session source selection with thread startup so the lookup honors the same catalog, configuration overrides, and provider fallback setting.
## Testing
Update coverage to compare startup model information with the started thread's selected model, including provider catalog defaults and context window overrides. Add coverage for provider fallback being enabled and disabled.
GitOrigin-RevId: 57040c4afeacc47c7596832271898577a3584c89
## What changed
Extend remote network approval tests to cover executor-owned proxies. Verify that `exec_command` delivers the process result while a network review is pending, without waiting for the denial grace period.
Freeze Tokio time after command startup and use a real-time timeout to detect delayed results. Share the test setup with the existing controller-owned proxy cases, preserving local-binding policy and process-exit cleanup assertions.
GitOrigin-RevId: f07fe273c16d55305ee088223449def68384c104
## What changed
Mark `code_mode_host_grpc` and `code_mode_host_output_truncation` as stable and enable them by default. Code Mode now defaults to gRPC over stdio and truncates output in the host before sending it to Core.
## Testing
Update integration tests to exercise the default configuration and explicit feature opt-outs, covering output budgets, truncation notices, and wait termination. Keep the stdio reconnection test explicitly configured for that transport.
GitOrigin-RevId: 5847a249d698fb9b1ecf4921aca4e6efc501f890
## What changed
Make `TurnContextItem.permission_profile` required and remove its legacy `sandbox_policy` and `file_system_sandbox_policy` fields. Normalize older histories into a permission profile during deserialization, preserving the restrictive fallback for malformed filesystem rules.
Keep legacy compatibility fields in rollout serialization so older readers remain usable. Update turn recording, metadata extraction, and permission checks to consume the profile directly.
## Testing
Add coverage for legacy normalization, profile-only serialization, missing permissions, and malformed filesystem rules. Extend rollout round-trip fixtures to cover deny rules and filesystem roots from another platform.
GitOrigin-RevId: 27515fec60cccbac5806b98fb71f54e311a09701
## What changed
- Add `ThreadManager::models_manager_for_startup` to obtain the model catalog used when starting or cold-resuming a root thread, including its effective originator.
- Add `CodexThread::selected_model_info` to resolve the model for future turns using the thread's current settings, catalog, and model overrides.
- Share catalog selection logic between startup lookup and thread creation.
## Testing
Add coverage verifying that startup and thread lookups use the thread-specific catalog, preserve the configured context window, and reflect model selection updates.
GitOrigin-RevId: d7976caebb7459e1e9ca55f3c6f6bb2af92cf3de
## What changed
Refocus `openai-docs` on Codex and ChatGPT Work behavior and first-time API integrations. Skip API questions about existing integrations, action requests, and tasks fully answered by supplied text or data. Retain model migration guidance when users explicitly invoke `$openai-docs`.
Replace the broad routing workflow with guidance to check available tools and settings, consult documentation for the relevant product surface, and verify recent changes through the changelog and linked client changes or tests.
Update the skill's display metadata and affected skill catalog snapshots to match.
GitOrigin-RevId: 0a0e9abbee9975ebd30917b7477f475096f2c86b
## What changed
Check the effective permission profile directly when applying startup restrictions for models that require automatic review, instead of converting it to a legacy sandbox policy.
Preserve the downgrade to `workspace-write` for profiles with full disk write access and enabled network access, excluding external enforcement and writable paths that cannot be converted to local paths. Share writable-path conversion with the legacy sandbox adapter.
## Testing
Add startup regression coverage for profiles that are downgraded, preserved, or rejected, including read-only carveouts and writable paths that cannot be converted locally. Verify restored permissions, automatic review selection, and workspace settings.
GitOrigin-RevId: 256c949f23d84dfba185a45a01b638ff5f1df52e
## What changed
Read `final_answer_moderation` metadata and attach `moderation: { moderated: boolean }` to the completed final-answer message only when its item ID matches. Apply this in both normal and plan modes, and reset the pending decision when a new response starts.
Preserve the answer's native item ID and moderation flag through legacy events and history reconstruction. Combine text parts into one legacy event when a moderation decision is present.
Expose nullable moderation data on app-server agent messages and update the JSON schemas, TypeScript types, and Python models.
## Testing
Add an integration test for moderation on completed answers and their legacy events. Extend protocol conversion tests to cover populated moderation data and serialization as `null` when absent.
GitOrigin-RevId: f286b67731a84b3daf5d10b7644f2e31b62f0e53
## Why
Incremental tool declarations were limited to Responses Lite. Regular OpenAI Responses requests sent the full current tool catalog on each request.
## What changed
- Add the disabled-by-default `incremental_tools_legacy` feature for regular OpenAI Responses, independently of the Responses Lite `incremental_tools` flag.
- Support tool declarations and updates in conversation history, including during compaction, while preserving existing history prefixes.
- Keep hosted `web_search` configuration in top-level `tools` rather than `additional_tools`, including in compaction requests.
## Testing
Extend request-history scenarios and snapshots to cover regular Responses catalog updates, model switches, compaction, and MCP tool removal and restoration. Assert that incremental requests preserve input prefixes and keep web search out of history declarations.
GitOrigin-RevId: fa347409e387aa973ce2e41df8505769b7db1ec2
## Why
Gateway sign-in needs an alternative for terminals that cannot open a browser.
## What changed
- Add optional `gateway_oauth.device_authorization_url` configuration and a `login_with_device_code` API that presents a verification URL and user code, polls for approval, and persists the resulting credentials.
- Use the configured proxy and network policy, validate verification URLs, and bound OAuth responses. Support cancellation and report denied or expired codes without exposing issuer error details.
## Testing
Add tests for successful authorization and credential persistence, unsafe verification URLs, network-policy denials, denied and expired codes, and cancellation during approval or credential storage.
GitOrigin-RevId: 96398578fb866d34929e85c04eadf468d8cd3255
## Why
Cached gateway command credentials need to be refreshed when the gateway rejects them with a `401`.
## What changed
Clear the cached `credential_export` token after an inference HTTP `401` or a WebSocket upgrade rejected with `401`, then rerun the command for one retry. Preserve subsequent primary authentication recovery if the retry is also unauthorized, and document the behavior.
## Testing
Add integration coverage for using a new exported token, reporting an invalid export, recovering primary authentication after the gateway retry, and stopping after a second unauthorized WebSocket upgrade.
GitOrigin-RevId: 3397476dbfd3bec1bd44f90657c4f9e17bb7df67
## What changed
Add an optional `thread_id` to `HostedFileUploadContext` and include it as `codex_thread_id` in file creation requests when provided. Keep MCP app uploads without this field while retaining the thread ID in tool-call metadata.
## Testing
Extend upload tests to check inclusion and omission of `codex_thread_id`, and assert that MCP app calls retain `_meta.threadId` without adding it to file uploads.
GitOrigin-RevId: cff15b35e5130e56973f944b3b849807550d298b
## What changed
Add a default `ModelRequestContributor::budget_exhausted` hook and fail generation with `SessionBudgetExceeded` when any contributor reports an exhausted budget for the thread.
Check budgets before HTTP requests and before WebSocket connection setup, then check again after the connection is established. WebSocket warmup remains available when the budget is exhausted.
## Testing
Add coverage for budget changes during a tool call, verifying that exhaustion prevents the next model request while an available budget allows completion. Extend WebSocket coverage to verify that exhausted generation opens no connection and warmup still permits connection reuse once the budget becomes available.
GitOrigin-RevId: 97ce02dc7f9bd54830e4b73c4f0334a30367eebf
## What changed
Allow `model_providers.<id>.gateway_oauth.credential_export` to supply a gateway access token instead of browser OAuth. Run the configured command on first use, cache its token in memory, and deliver it through the configured header or cookie. Export failures surface directly, and command-backed providers do not require an OAuth session.
Require mutually exclusive OAuth and exporter settings, same-origin model catalog access, and rejection of HTTP redirects for command-backed gateway credentials. Share the bounded, timeout-controlled command runner with AWS credential export.
## Testing
Add tests for inference and model listing without OAuth, token caching and recovery after invalid output, preservation of primary authentication, and rejection of mixed OAuth/exporter configuration.
GitOrigin-RevId: e3dbfd8823b1992045f1c1efd56ec98ee17e07a5
## Why
A message's model-visible item ID may be unknown until the recipient records it. Message lifecycle observers need to capture publication state before that point.
## What changed
Remove `message_id` from `MessageLifecycleInput` and give each publication's `ExtensionData` a fresh UUID key. Stop assigning an item ID when publishing messages for lifecycle observers.
## Testing
Update the agent mailbox test to store a contributor-specific token in `ExtensionData` at publication and retrieve it at consumption, verifying that publication state survives queued delivery and recipient eviction.
GitOrigin-RevId: e254f94994d0976e61cb46ee23297f3248b9a389
## Why
Clients need to list models for a configured provider other than the app-server's startup default.
## What changed
Add an optional `modelProvider` parameter to `model/list` and expose it in the generated schemas and client types. Explicit selections use provider definitions loaded at startup and respect current managed provider requirements. Unknown providers return a structured `modelProviderNotConfigured` error.
Use a temporary catalog when selecting another provider, preserving the default catalog and its disk cache while retaining runtime authentication. Requests without a selector keep the existing provider and caching behavior.
## Testing
Add coverage for provider selection, preservation of the default catalog and disk cache, unknown-provider errors, managed requirement enforcement, and runtime authentication for temporary catalogs.
GitOrigin-RevId: 6092df9f6141810c6ac215a8e1fb601f77e54747
## What changed
Remove `FileSystemSandboxContext::from_legacy_sandbox_policy` and migrate its test callers to `from_permission_profile`. Construct read-only, disabled, and externally enforced sandbox contexts directly with `PermissionProfile`.
GitOrigin-RevId: e330b89d060061eda106232eab554be5ccd06149
## What changed
- Expose an optional `AgentServiceTier` provider so host-owned children, including detached children, inherit the root's committed tier during spawn preparation, startup prewarm, and each inference step.
- Reject per-turn tier overrides for children using the shared provider. Root updates apply to subsequent requests without changing requests already in flight.
- Preserve independent configured tiers and role overrides when no provider is installed, including across eviction and reload. Spawned children inherit the parent's thread preference rather than its per-turn override.
- Publish the latest committed root tier only after successful runtime registration, preventing failed duplicate starts from changing shared settings.
## Testing
Add coverage for detached-child WebSocket prewarm and between-step tier changes, shared-child override rejection, independent-tier inheritance and reload, and settings updates before registration.
GitOrigin-RevId: f0f3676813a1c59bd77baf95121e2d13e0163a8e
## Why
WebSocket telemetry reparses text frames to extract event kinds that the transport already decodes.
## What changed
Pass decoded event kinds to telemetry and report receive failures separately. Keep JSON parsing for timing metrics and as a fallback when stream event decoding fails. Remove the `tokio-tungstenite` dependency from `codex-otel` and restrict it to tests in `codex-core`.
Limit wrapped error parsing to error events or failed stream decoding, preserving HTTP error forwarding when unrelated stream fields are malformed.
## Testing
Update runtime summary coverage to include receive failures and extend the WebSocket error forwarding test with a malformed stream field.
GitOrigin-RevId: e1f9d200fd6d30ec124a2354bdbc01f3082ddde3
## What changed
- Expose `RequiredCyberAccessPrograms` so hosts can require an explicit allowed program on a thread. Snapshot the requirement before extension callbacks; hosts must reapply it on cold resume.
- Validate resolved `access_programs` before HTTP and WebSocket model requests, rejecting omitted or disallowed programs. Explicit `Standard` remains distinct from omission. Reject memory summarization and realtime requests when a requirement is present.
- Keep required programs scoped to the parent thread by preventing Guardian reviewers from inheriting its program, including Guardian v2 reviews.
## Testing
Add HTTP and WebSocket coverage for allowed programs, omission, disallowed programs, unsupported providers, and connection reuse. Extend Guardian tests to verify parent-only program scope and that removing the public attachment does not erase the startup snapshot.
GitOrigin-RevId: 9306a9af0e03e7a1728dfeb610cd7ec7517367fd
## What changed
- Select fresh authentication for each HTTP operation on eligible OpenAI MCP connections while preserving the connection's credential source and account network policy. Stop redirects when requests carry runtime assertions.
- Pass the owning thread's authentication and runtime context through app discovery, connector metadata, and trusted-access requests. Include the runtime authentication mode in MCP connection and tool-cache identities.
- Give resumed actors analytics clients bound to their own authentication context, and serialize stored-credential reloads with token refresh while preserving host-provided credentials.
## Testing
Add coverage for fresh request assertions, revoked account policies, redirect handling, resumed-actor isolation, and MCP uploads in dual-header and assertion-only modes.
GitOrigin-RevId: f06900a6db61cd6cf53c3aa8075afeec4d5706d9
## Why
Explicit cyber access program selections were dropped for requests using `CodexAuth::Headers`, preventing the server from evaluating the requested program.
## What changed
Forward explicit program selections for header-authenticated requests, leaving entitlement decisions to the server.
## Testing
Add integration tests covering explicit selections and omission over HTTP and a reused WebSocket connection, preservation of actor and account headers, and propagation of backend HTTP 403 denials without dropping the selected program.
GitOrigin-RevId: 5e549e87a1420ce8a5f1ce5c704cc6b7630af3ba
## What changed
Require the `openai` provider ID as well as `GuardianNativeMultiAgentHistory` to enable native agent history and review of multi-agent calls. Apply the same check to Guardian prompt construction, collaboration tool registration, and Guardian v2 configuration.
## Testing
Add coverage for fresh and resumed sessions with the feature enabled and disabled on OpenAI, and enabled on Bedrock and LiteLLM. Verify that only OpenAI sessions with the feature enabled request native review and include the agent call as evidence.
GitOrigin-RevId: bfbe547b0544e66763dca7d1e1376f805994bcb2
## What changed
Extend `guardian_review` to assess recorded MCP tool calls using the current tool catalog, bindings, and approval policy without executing the call or remembering an approval. Return no assessment when policy or a remembered approval skips review, and reject tools blocked by app configuration.
## Testing
Add a scenario test that compares direct and live MCP review inputs, verifies that neither dispatches the tool, and checks that the current app approval policy can skip review.
GitOrigin-RevId: 05746dd0804a0f96d7946468701d5222171ff64f
## Why
Multi-agent V2 still supplied native tool usage guidance when native tools were disabled, leaving instructions for unavailable tools in model requests.
## What changed
Skip bundled and model catalog role guidance for both root agents and subagents when `disable_native_tools` is enabled. Preserve explicitly configured usage hints.
## Testing
Add coverage for omitted bundled and catalog guidance and preserved configured hints with native tools disabled. Update the request snapshot and assert that spawned agents do not receive native tool call guidance.
GitOrigin-RevId: 6f2facabc95e78cbf64af19636a4daf488bbcc51
## What changed
Expose `AgentTurnOutcomeReporter` for hosts to install through `StartThreadOptions::thread_extension_init`. Await its callback after emitting the terminal turn event, independently of native parent notifications, so hosts can handle result delivery and retries.
Track outstanding outcome handoffs and wait for them during graceful shutdown before running thread-stop hooks. Prevent new turns from starting once handoff registration closes.
## Testing
Add integration coverage for completed and errored outcomes, turn lineage, queued follow-up turns, and shutdown waiting for handoffs. Extend Guardian tests to verify that strict safety stops reach the reporter while default interruptions remain silent.
GitOrigin-RevId: 0d825f6208f0250969734488881f32fd1dcd7509
Give each independent MCP server and session setup its own test identity
and timeout budget by replacing nested loops with `test_case::test_matrix`.
Preserve all 64 configuration combinations and the existing assertions for
direct tool exposure, tool search availability, and advertised tool calls.
GitOrigin-RevId: 74ef56d34b6bab3038b70d7d84183f7d104788a2
## What changed
When `features.guardian_denial_reconsideration` is enabled, retry the first terminal denial once using the unchanged inference request. Buffer provisional output so only the selected response enters reviewer history, while allowing tool calls to proceed normally.
Preserve the original denial if the retry fails or times out, and continue to honor cancellation. Account for token usage from both attempts, including failed reviews.
Remove `auto_review.experimental_denial_reconsideration_prompt` and warn when it remains in configuration.
## Testing
Update the Guardian scenario and snapshot to verify identical retry inputs, retained tool evidence, and reuse of the selected assessment in a subsequent review, with asynchronous compaction enabled.
GitOrigin-RevId: cc4e303d40a02acc824c8b4b954852325e64ad52
## Why
A Code Mode script can start a command without returning its session handle. Make retained sessions visible to the model so it can find running commands and collect exited results with `write_stdin`.
## What changed
- Add the disabled-by-default `command_sessions_world_state` feature.
- Publish snapshots of up to 16 retained sessions with their IDs, running or exited status, and whether they are in use. Report omitted sessions and suppress unchanged updates.
- Preserve session visibility when `write_stdin` is unavailable and refresh snapshots after compaction. Clear stale session handles after restart or when the feature is disabled.
## Testing
Add an end-to-end scenario and model-visible history snapshot covering a dropped command handle, unchanged state, unavailable polling, compaction, exit and result collection, and stale-handle cleanup after restart.
GitOrigin-RevId: 45704d8c6403149997231aafb8496c12879aff23
## What changed
- Use the shared runtime and effective configuration for account API clients and remote plugin requests, including standalone plugin commands.
- Support dual-header and assertion-only authentication for remote plugins and MCP file uploads when runtime agent instances are enabled.
- Keep plugin credentials and caches scoped to the thread's account when resuming with different credentials. Bind request pools and multi-step plugin storage operations to the selected account so account replacement revokes stale operations.
- Protect runtime credentials on cross-origin redirects while preserving configured routing policies and legacy authentication for custom backends.
- Apply server-provided `upload_headers` to file storage uploads.
## Testing
Add coverage for shared runtime registration, both authentication modes, configuration reloads, resumed-thread account selection, account replacement during plugin uploads and downloads, and credential stripping on redirects. Extend file upload tests to verify runtime assertions and storage-only upload headers.
GitOrigin-RevId: 68aef81051a6f9bf919fffda52f372b108fce805
## What changed
- Support `canonical_matching=True` in `prefix_rule` and `canonical_matching = true` in managed TOML prefix rules. Apply Unicode canonical caseless matching to every prefix token, including alternatives, while keeping exact matching as the default.
- Match case and canonically equivalent Unicode spellings, such as `bash` and `bAſh`, without resolving executables on the filesystem.
- Preserve managed restrictions when checking absolute-path rule amendments, and enforce applicable `host_executable` path allowlists during basename fallback.
## Testing
Add coverage for case folding, Unicode normalization, token alternatives, exact-match defaults, and host executable allowlists. Extend managed-policy and shell-execution tests to cover canonical matching.
GitOrigin-RevId: c2f79069dc38d55c77028c457b22beb468d5c571
## What changed
- Expose `AgentSessionReader` and `AgentRef` for read-only access to host-owned agent session membership.
- Read direct children when rendering V2 environment context, using the existing roster size limits. Refresh membership when rebuilding context after compaction, and omit the roster if the provider is absent or the read fails.
- Preserve unrecorded initial input across suspension or interruption while waiting for a roster read. Resolve the roster before advancing the compaction window.
## Testing
Add coverage for roster refreshes after compaction, unchanged environments avoiding extra reads, unavailable rosters, recoverable input during blocked reads, and stale compaction results rejected after a concurrent history replacement.
GitOrigin-RevId: 3c7e3822af09e9295d405e53dabb87b020c8f00c
## What changed
Add optional executor workspace roots to `SandboxTransformRequest` and resolve symbolic workspace rules after merging additional permissions. Preserve explicit deny rules and treat an empty root list as granting no workspace access.
Route Windows restricted-token preparation through the shared transform path and use explicit roots when building its direct-spawn wrapper. Update Windows MXC debug launches to bind configured roots before adding the managed CA read grant.
## Testing
Extend sandbox manager tests to cover workspace and subpath expansion, empty root lists, deny preservation, and the roots and write permissions serialized into the Windows wrapper.
GitOrigin-RevId: 0bebdb08b67cbbc182c18b031b9d13a21a799682
## Why
An enabled legacy feature flag could prevent a project's `agents.enabled = true` from overriding a lower-priority legacy opt-out, leaving V1 agent tools unavailable.
## What changed
Only stop scanning configuration layers at an explicit legacy feature opt-out. Enabled flags now allow the scan to continue, so project opt-ins can override lower-priority opt-outs while same-layer and higher-priority opt-outs remain effective.
## Testing
Extend the model runtime selector regression test to cover enabled `features.collab` flags in project configuration and CLI overrides, and verify that explicit `false` values still disable V1 agent tools.
GitOrigin-RevId: ca3dcf9dc6a642eb72e20929776fb74379715053
## Why
An MCP server can belong to a different environment from the turn's primary environment. An early Guardian score based on the issuing context must not bypass review when the server owner's permissions differ.
## What changed
- Capture the owning environment's permissions when preparing an MCP call and retain them for server-initiated approvals tied to that still-running call.
- Use the captured permissions consistently in Guardian review prompts and permission context.
- Require a fresh synchronous review when the captured owner permissions do not match the early score's authorization.
## Testing
Extend regression coverage for MCP score reuse across environments and for follow-up approvals from a local MCP server during a remote-primary turn. Assert that reviews use the owner's denied paths and require a fresh review when permissions differ.
GitOrigin-RevId: eb5eeb1259732c57f39765c38e34148fa0787dae
cooper-oai