## Why
An explicit denial from a workspace inference hook should stop the request, including retries and compaction model fallback.
## What changed
Recognize `inference_hook_denied` provider errors and preserve the provider's message, with a fallback when none is supplied. Expose the distinct `inferenceHookDenied` error through the app-server protocol and generated schemas and SDK types. Treat the denial as non-retryable during turns, compaction, and guardian review.
## Testing
Add coverage for terminal denials over HTTP, SSE, and WebSocket, error serialization and persistence in `thread/read`, and compaction failures that preserve token usage and history without retrying or falling back to another model.
GitOrigin-RevId: 2ebd480f01e52f4e6bd3db8a0f92d5814d18ccb1
## What changed
Route MCP elicitations through the standard handling paths for Xcode 26.4 clients. Remove the client-specific auto-deny flag and the synthetic acceptance of session elicitation requests without dispatching them to the client.
Simplify `request_mcp_server_elicitation` to return the optional response directly, and remove telemetry guards that depended on whether the workaround bypassed dispatch.
GitOrigin-RevId: ab540dcd67f8fa6d16c69bc7629f436e4b5aa73a
## What changed
Mark `untrusted_as_tool_output` as stable and enable it by default. Untrusted additional context, such as browser information and goal objectives, now reaches the model as `function_call_output` items in the `agent` namespace instead of user messages. Setting `features.untrusted_as_tool_output = false` preserves the message format.
## Testing
Update core, app-server, TUI, and Python SDK test expectations for the default output format. Cover context persistence, deduplication, goal continuation, and explicit opt-out behavior.
GitOrigin-RevId: 30828351e2ed584928f6055b6dcf276d8288c0fb
## Why
HTTP 400 responses with `context_length_exceeded` need to reach context-window recovery so manual compaction can retry with less history. Streaming context-window failures should end the stream immediately.
## What changed
- Map `context_length_exceeded` through the shared terminal provider error parser for HTTP 400 responses and events without an HTTP status.
- Return SSE context-window failures immediately.
- Preserve retryable handling for WebSocket errors carrying HTTP 503, even when their code is `context_length_exceeded`.
## Testing
Add coverage for WebSocket status handling and immediate SSE termination with retry headers. Update the manual compaction test to verify recovery from an HTTP 400 context-window error by dropping one history item and retrying.
GitOrigin-RevId: 56d8c831c2fad2ca1318318a3b4258fcc516d689
## Why
A `403` with `codex_workspace_access_denied` indicates that the account cannot use Codex in the selected workspace. Retrying or falling back to HTTP does not resolve that denial.
## What changed
Map `codex_workspace_access_denied` and `invalid_workspace_selected` responses to a shared workspace access denial error, and rename the error variant to reflect its broader scope. Keep workspace denials excluded from compaction model fallback.
## Testing
Extend API error mapping tests to cover the new code on `403` and preserve ordinary handling for `503`. Add WebSocket coverage verifying that an explicit workspace access denial does not trigger HTTP fallback.
GitOrigin-RevId: e601a22a0fa783a4ce5401a98ff9c8d3d9d1b074
## What changed
Recognize `content_policy_violation` in HTTP 400 responses and streamed errors as a dedicated, non-retryable error. Preserve the provider's message and available HTTP status, use a fallback message when needed, and report `CodexErrorInfo::InvalidPrompt` to clients.
End the response stream immediately on this error and stop compaction from falling back to the current model after a content policy rejection. Add redacted diagnostic output and a dedicated sampler failure reason.
## Testing
Extend coverage for HTTP and wrapped WebSocket errors, missing or blank provider messages, terminal stream failures with retry headers, and content policy rejections during local and remote compaction on model downshift.
GitOrigin-RevId: 592170ac30c07b0b303a8d5cb15bd35c8f821b55
## What changed
Recognize `access_program_not_enabled` in HTTP 403 responses and response stream errors as a dedicated, non-retryable error. Preserve HTTP diagnostic details and provider stream messages, with a default message when none is supplied.
Stop SSE streams immediately on this error and avoid triggering WebSocket fallback for explicit access program denials. Add a fixed diagnostic label for doctor output and telemetry.
## Testing
Extend coverage for HTTP and WebSocket denials, immediate SSE termination despite retry headers, and doctor diagnostic redaction.
GitOrigin-RevId: 3a41f7bb80ad5e13a87e831b458d17cdd19a4b62
## Why
HTTP 403 responses with `invalid_workspace_selected` were treated as unexpected status errors, allowing retries and compaction fallback to another model after the server rejected the selected workspace.
## What changed
Recognize the code in `detail.code` or `error.code`, falling back to the `x-error-json` header when the body has no code. Classify these 403 responses as `InvalidWorkspaceSelected` and disable retries and compaction model fallback while preserving the response details and HTTP status. Other 403 responses retain their existing retry behavior.
## Testing
Add coverage for body and header error codes, code precedence, HTTP and WebSocket retry behavior, and local and remote compaction during a model downshift.
GitOrigin-RevId: f44a3bee5ef06e601909839868ab99cea6dd7d03
## Why
Local compaction retried invalid requests and server overload errors without retry advice, and used local backoff even when the server supplied `Retry-After`.
## What changed
Use `CodexErr::retry_delay` to decide whether and when to retry local compaction. Honor the original `Retry-After` deadline when present, while retaining the configured retry limit and context-window trimming behavior.
## Testing
Add coverage verifying that manual local compaction does not retry invalid requests or overload responses without retry advice, but retries overload responses with `Retry-After`.
GitOrigin-RevId: abe6cbba661f701b97f8b1ab83b1fe86979f03c0
## Why
Approved filesystem access should make executor skills discoverable and readable for the lifetime of the grant. Turn-scoped access must not authorize persistent plugin servers or hooks, or bypass disabled-plugin policy.
## What changed
- Apply environment-specific session grants to capability discovery and refresh MCP after session grants change.
- Use a separate discovery inventory for skills with turn-scoped grants, keeping plugin servers and hooks on the session inventory. Reuse discovery results across unchanged model steps.
- Preserve disabled-plugin checks for unreadable manifests and symlinked manifest files or directories, including ancestor markers, while retaining standalone skill roots.
## Testing
Add coverage for V1 and V2 skill discovery before approval, after approval, and on the next turn; disabled-plugin ownership checks; discovery cache reuse; and session hooks surviving turn-scoped discovery failure.
GitOrigin-RevId: 929a7f8cb01f4bcfb4bee2c50ae02cd762066b2d
## Why
A pending realtime connection handshake can hold up subsequent attachment requests. Callers need to cancel obsolete attempts or limit how long they may take to establish a connection.
## What changed
- Add `RealtimeAttachmentOptions` with an optional cancellation receiver and `start_before` deadline to `Op::RealtimeConversationAttach`.
- Interrupt pending connection work and finish cleanup before acknowledging cancellation. Reject cancelled or expired requests before replacing an existing conversation, and recheck cancellation and the deadline before publishing a connection.
- Preserve a successfully published connection when cancellation arrives later. Dropping a cancellation sender whose value is `false` lets the attempt continue.
- Prepare the daemon startup test's socket directory with `codex_uds::prepare_private_socket_directory`.
## Testing
Add integration coverage for cancelling a held handshake, skipping cancelled or expired queued requests, preserving the next usable call, and releasing a pending handshake when its deadline expires without a cancellation receiver.
GitOrigin-RevId: 7144c1237bcbe3b859f10b654d919ae9ff20cbbb
## Why
Account changes during asynchronous request setup can invalidate the credentials selected for a generation request.
## What changed
- Restart HTTP request setup if the auth owner changes during the budget check.
- Validate the WebSocket connection's retained auth owner with `AuthOwner::is_current()` after budget checks.
## Testing
Add regression coverage for account switches during HTTP budget checks and external credential changes before WebSocket request setup, in both dual-header and assertion-only runtime auth modes.
GitOrigin-RevId: 7a1e1475a40aa2d34cd94f60f729ad697f3f7028
## Why
Aggregate resource listings omitted dormant MCP servers, leaving callers without their names for explicit queries.
## What changed
Include a sorted `deferredServers` list in aggregate `list_mcp_resources` and `list_mcp_resource_templates` results alongside resources from ready servers. Apply the listing filters to deferred servers and omit the field when empty. Discovery leaves dormant servers unstarted; callers can query them by passing `server` explicitly.
## Testing
Extend the resource discovery scenario for direct calls and Code Mode to verify deferred server names, confirm discovery leaves the server unstarted, and then list and read resources by server name.
GitOrigin-RevId: f95b8beb64bb1329f4ae3245e8c375614fcb3360
## What changed
Simplify the post-denial rule in the Guardian policy template: user re-approval after seeing the concrete risk sets `user_authorization` to `high`. Remove repeated qualifiers about explicit approval of the exact action and certainty that approval came from the user; the authorization scoring guidance still covers those requirements.
Update the Guardian extra-policy review snapshot to match the revised prompt.
GitOrigin-RevId: 63643222e8f9c46c9d902ac8f5d1e11d24fafe9c
## What changed
- Add `CodexThread::agent_tree_id()` to identify a loaded agent tree. The root and native children share an ID; loading a new tree produces a new ID even when reusing a persisted thread ID.
- Add `EnvironmentManager::remove_environment()` to unregister an environment while preserving existing handles and the default environment ID.
## Testing
Extend tests to check tree IDs across child creation, forks, warm reuse, and cold reloads, and to verify environment removal and re-registration.
GitOrigin-RevId: 43944ed6766374508d9862cd5d333bc4cb67c338
## What changed
Add `exec_tools_update_hint` and `exec_tools_removed_definitions_header` to `model_messages.tools.incremental_tools` and use them when rendering Code Mode catalog updates and removals.
Overrides are literal strings limited to 512 UTF-8 bytes per field. Missing, null, or oversized values use the existing bundled wording. Empty strings omit the guidance while retaining changed definitions and removal keys. Wording changes alone do not trigger catalog updates.
## Testing
Extend unit coverage for defaults, null fields, independent fallback, and UTF-8 byte limits. Add scenario assertions and a snapshot covering custom and empty wording, model switches, catalog changes, and restoration after compaction.
GitOrigin-RevId: da9e00fdb5197a2b5fa39ce533ba87c76ff3e82c
## What changed
- Cover incremental exec tool settings and catalog changes across resume, fork, tool mode switches, and compaction.
- Verify that adopting background compaction preserves live exec declarations, tool metadata updates, and retained conversation order after a model catalog refresh.
- Include an `exec` namespace in the top-level tool catalog ordering and snapshot round-trip test.
GitOrigin-RevId: 3df603b98a006abb55a5095b299080f036576242
## Why
Recovered answer history needs presentation instructions alongside the moderation flag so clients can apply the intended display behavior.
## What changed
- Add optional `display` metadata with an `action` and optional `blockType`, `cyberTrustedAccess`, and `checkTrustedContacts` fields.
- Carry display metadata through final answers, legacy events, thread history reconstruction, and legacy rollout migration.
- Expose the metadata in the app-server protocol and update generated JSON schemas, TypeScript types, and Python SDK models. Missing display fields remain compatible with existing stored moderation data; the app-server emits absent optional values as `null`.
## Testing
Extend the final-answer moderation test to cover display metadata in answer items and legacy events. Add serialization coverage for missing display data, nullable fields, and preservation of an explicit `false` value.
GitOrigin-RevId: b798a2ecc53c2a94c7659ef3d9663b3143b70a1a
## Why
Changes to nested tools should update the model's catalog without repeating the full `functions.exec` declaration or rewriting retained context.
## What changed
Pass structured exec definitions through the tool router into the session's tool world state. Enable granular updates for Responses Lite in `CodeModeOnly` when both `IncrementalTools` and `IncrementalExecTools` are enabled.
Append changed tool definitions, namespace instructions, and removals as developer messages. Keep common exec instructions and shared types frozen until compaction, then install the latest full catalog.
## Testing
Add feature-gating coverage and a scenario snapshot covering tool additions and removals, namespace instruction changes, eager/deferred transitions, re-enabling tools, retained context, and catalog restoration after compaction.
GitOrigin-RevId: bbf850d4e5018388eeb4c09345d885d776962e09
## 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
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
ccui-oai