## Why
Direct executor skill discovery used unrestricted filesystem access, bypassing the turn's permission context. Cached catalogs also needed to account for changes in filesystem access within a turn.
## What changed
- Bind selected capability roots to callback-scoped filesystem access through `AccessedSelectedCapabilityRoot`.
- Pass accessors built with the turn's granted permissions into skill preparation and discovery, removing the executor skill provider's environment lookup and unrestricted accessor.
- Include filesystem access keys in the direct discovery cache so permission changes trigger rediscovery.
## Testing
Extend tests to verify that restricted discovery returns no skills when sandbox access is unavailable, restoring access restores discovery, and changing or restoring access invalidates the catalog cache.
GitOrigin-RevId: 0f7aa7646f65923f65f0cfc0b387d94bd7f2db05
## What changed
Mark `unified_image_budget` stable and enable it by default. Supported models now use unified image preparation with `original` detail, and `view_image` omits the `detail` parameter from its advertised schema.
## Testing
Update image input, MCP output, history replay, and tool schema expectations for the new default. Keep explicit coverage of the disabled feature and models that do not support original image detail.
GitOrigin-RevId: 2d6fc8019149fcf18b5813db2d2082ba95de2241
## Why
Repository skill discovery must reflect current filesystem access, including newly approved grants and narrower permissions. Previously listed skills can remain in conversation history after a turn-scoped grant expires, so catalog updates need to tell the model when availability changes.
## What changed
- Discover repository skills through the selected executor's permission-aware filesystem accessor and refresh snapshots when the working directory or access changes. Use the current step's snapshot for skill selection and invocation.
- Preserve repository boundaries even when project markers are hidden by read restrictions, and report unsupported sandbox backends as skill-loading errors.
- Track grant-dependent catalog entries and emit availability notices when skills disappear or return, even when the metadata budget is exhausted.
- Resolve implicit skill paths through their owning filesystem and exclude remote repository skills from local implicit command attribution.
## Testing
Add coverage for turn and session grants, grant expiry and restoration, hidden and newly created repository markers, cached read denials on Windows, unsupported remote sandboxes, and executor-backed implicit skill paths.
GitOrigin-RevId: ac1af483e73e3130524aeeabe218630435054028
## Why
A model requirement can force `auto_review` even when the requested reviewer is `user`. Persisting or sending that effective value back as an explicit choice loses the original selection, so removing the requirement cannot restore it on resume.
## What changed
- Retain `requested_approvals_reviewer` separately from the effective reviewer in configuration and thread settings, with a fallback for older histories.
- Restore the requested reviewer on resume while applying current model requirements and reviewer allowlists.
- Let ordinary TUI turns, continuations, retries, and forks inherit the server's reviewer instead of echoing its effective value as an explicit request.
- Preserve a worker's requested reviewer when reloading it rather than inheriting the sender's selection.
## Testing
Extend resume coverage for explicit `auto_review`, removal of a model requirement, and a tightened reviewer allowlist. Update TUI assertions for omitted reviewer overrides and verify worker reload preserves its reviewer.
GitOrigin-RevId: d8c9c3a7b89e55e63f0e8ae210d6a87cb5547933
## What changed
Track Guardian compaction and review turn execution within each tool's auto-review interval, and expose `critical_path_auto_review_overhead_ms` in turn analytics. This measures the portion of `auto_review_ms` outside observed Guardian turn execution; it is a subset, not an additional duration.
Freeze review observations when the review or tool invocation ends. Report unknown overhead as `null`, including when denial reconsideration runs an unobserved follow-up turn.
## Testing
Add coverage for shared compaction and review observations, cached reviews, unfinished reviews, reused tool call IDs, and execution timing with child critical-path capture enabled or disabled. Extend analytics and app-server tests to check the new field.
GitOrigin-RevId: a63dec2a75571a3167c8c3f0c1d21e11e4a8d050
## Why
Reusable clients need fresh authentication for each request while preserving the credential source and transport policy selected when the client was created.
## What changed
- Add runtime-aware backend client construction and per-request authentication. Allow token refresh within the original credential source, reject credential replacement, and validate destination and account/organization selectors.
- Let runtime authentication finish persisting rotated tokens when the requesting task is cancelled.
- Apply asynchronous authentication to file creation and finalization requests, generating fresh assertions while keeping credentials off blob uploads.
- Preserve direct sandbox routing without enabling legacy custom-CA fallback for protected clients that reject redirects.
- Exclude login account metadata from model cache identities when provider bearer credentials override the login, and record authentication selection outcomes and duration.
## Testing
Add regression coverage for credential refresh and replacement, organization selection, destination restrictions, transport policy preservation, cancellation during token rotation, credential stripping on redirects, and file upload authentication in both runtime authentication modes.
GitOrigin-RevId: d045595e869dfcdfd9f705a6228cf0eb4c2d2c12
## What changed
- Report sampling and compaction separately as `critical_path_sampling_ms` and `critical_path_compaction_ms`, retaining `critical_path_inference_ms` as their combined compatibility total.
- Enable critical path capture for subagent and Guardian turns when `CriticalPathTiming` is enabled, while continuing to exclude memory consolidation sessions.
- Preserve capture across incoming agent messages and support direct `spawn_agent` and `wait_agent` calls. Attribute these calls to the parent's tool time and keep child work on the child's own turn.
## Testing
Add runtime coverage for independent parent/child timing, incoming agent messages, Guardian turns, feature gating, and memory consolidation exclusion. Update phase accounting and analytics tests to cover the new fields and millisecond truncation.
GitOrigin-RevId: 09d4c0b853e817216bed173e4404d0d782de97ec
## What changed
- Share a lazily registered runtime across threads, model discovery, and extension clients when `runtime_agent_instances` is enabled, while honoring each thread's authentication mode and credential owner.
- Bind model catalogs to the effective provider and authentication context while preserving cache policy and live API-key discovery settings.
- Resolve credentials, routing, and transport policy together for each request. Preserve proxy and TLS settings, validate runtime account selectors, and prevent pooled connections from crossing runtime identities.
- Accept supported ChatGPT subdomains when selecting the registration environment.
## Testing
Add integration coverage for shared runtime registration, dual-header and assertion-only modes, disabled and third-party providers, credential replacement, subagents, and delegated review. Add coverage for catalog cache policy and runtime-aware connection reuse.
GitOrigin-RevId: 99dd9d987c29c93597a648f6586f98ac6a932c3c
## What changed
Move permanent agent message board deletion from `codex-core` into the app server's thread-store cleanup callback. Keep board cleanup active when the board feature is disabled, and run it before optional Guardian evidence-board cleanup.
Remove the message board extension dependency from `codex-core` and retain `codex-message-board` only as a development dependency. Update the core test harness to install the app server's cleanup callback.
GitOrigin-RevId: 61813bbdcd8b57073b8c249e1f771e3fb0ea061e
## What changed
Move the board host adapter and `install_agent_message_board` from `codex-core` to `codex-app-server`, using public core runtime interfaces. Update extension registration, test callers, dependencies, and installation documentation to use the new location.
Format `CHANNEL_POST` notification payloads in the host adapter and retain recognition of legacy board notices in core. Expose `MULTI_AGENT_V2_NAMESPACE_DESCRIPTION` for host extensions to share with native tools.
GitOrigin-RevId: 679b5751de102bff80e6b9d4b0728a84fbdedd85
## Why
Existing chats can retain reasoning effort and service tier selections that a refreshed provider catalog no longer supports.
## What changed
- Apply fresh provider catalogs to saved settings in open and resumed chats, and normalize incoming settings before capturing the next turn.
- Replace unsupported ranked reasoning efforts with the highest supported level at or below the selection. For unsupported `ultra` or `persistent` selections, use the model's supported default when available. Reset unsupported `priority` and `ultrafast` service tiers to `default`.
- Retire incompatible reasoning effort pins using each step's captured model metadata, preserving running steps and the live pin during compaction.
- Publish catalog updates only from successful provider responses for the current identity, and refresh retained originator catalogs through the periodic refresh worker.
## Testing
Add coverage for setting correction, reasoning effort pins, resumed chats, stale queued settings, retained history, refresh failures, identity changes, and isolated originator notifications.
GitOrigin-RevId: 2ef4605c4acba98db3fe9d0328e2752084e900a2
## What changed
- Gate GIF output behind `features.image_generation_animation`, disabled by default.
- Accept `gif` options for generation and editing, with optional `frame_count` and `frame_duration_ms` controls. Use `gif: {}` for API defaults.
- Preserve animated output with `.gif` filenames and `image/gif` data URLs while providing a still preview to the model.
- Add guidance for simple animations and spritesheet-based GIF edits.
## Testing
Add integration coverage for GIF generation and editing, explicit frame controls and API defaults, saved animation bytes, and still-preview replay across follow-up turns.
GitOrigin-RevId: 08afa0316ae3675921652157836191a649f563cf
## What changed
Add optional `contentTokenCount` metadata to `item/completed` notifications, carrying the producer-supplied token count for each completed assistant message in default and plan modes. Counts include any sampled footer and are `null` when unavailable.
Keep this telemetry separate from stored thread items and omit it from subsequent model requests. Update the protocol schemas and generated TypeScript and Python types.
## Testing
Add coverage for per-message counts, including zero, in default and plan modes; missing and malformed metadata; backward-compatible notification decoding; and exclusion from subsequent model requests.
GitOrigin-RevId: 35973037a42650fa2d7569da8e88cb81215cf971
## Why
Search discovery must account for the active model's supported tools while honoring host search restrictions. Automatic fallback must also preserve the provider that owns existing browsing references.
## What changed
- Resolve search from model metadata, client configuration, and managed requirements, exposing the selected provider's tools.
- Discover hosted search with the model's supported tools and carry the discovered invocation context into calls.
- Allow native fallback for eligible discovery failures only when search policy permits it and hosted search has not already been used. Do not replay failed hosted invocations through native search.
- Keep native fallback references on native search across later turns, discovery recovery, and resume. Release unused fallback offers and coordinate background calls to prevent conflicting provider use.
## Testing
Add app-server and core scenario coverage for provider selection, discovery failures, search restrictions, reference continuity, resume, and concurrent background search. Include a snapshot covering discovery and call history across a model switch.
GitOrigin-RevId: 0f22605722daaa424c4fa34660654cde5a6db049
## What changed
- Add optional `ModelInfo.web_search_provider` metadata with `standalone` and `search_mcp` values.
- Add `tools.client_search_provider` and expose its value as `client_search_provider` in app-server configuration responses, with updated JSON schemas, TypeScript types, and Python bindings.
- Register the `hosted_search_policy` feature flag as under development and disabled by default.
GitOrigin-RevId: 263c3f81a61b50f8bb53ff338b9de8186db316e0
## Why
SQLx's SQLite migration lock is a no-op, allowing concurrent database openers to race between schema version checks and migration changes.
## What changed
Run schema checks and migrations in one transaction, retrying SQLite busy errors from a fresh snapshot. Databases with a current schema need only a read lock, including on NFS. Include the error cause chain when the app server reports SQLite initialization failures.
## Testing
Add regression tests for eight concurrent database openers applying each migration once and for reopening a current schema while another connection holds a writer reservation with NFS settings.
GitOrigin-RevId: 38004d58a5c637ac1b2be53d07fd9a4c8efec7ab
## Why
A fork's inherited history can become unreadable when the preferred ancestor rollout is truncated or has an incomplete compressed frame, even when a usable archived copy exists.
## What changed
- Retry failed ancestor reads using another copy of the same rollout, validating its owner and location before rebuilding the lineage.
- Apply fallback to model-context loading, fork and revert preparation, and paginated history reads. Preserve the original error when no usable replacement exists.
- Validate inherited byte offsets when opening ancestors for consumption, allowing a newer model-context checkpoint to avoid reading an unusable ancestor.
- Limit ancestor materialization to the inherited history boundary while preserving any existing progress beyond it.
## Testing
Add regression coverage for incomplete compressed ancestors, replacement ownership checks, archived-copy recovery during resume and fork, and materialization boundaries. Add an app-server test that cold-resumes a fork and pages inherited turns and items from an archived copy when the active ancestor is too short.
GitOrigin-RevId: 43730c17329ac759f7292b16ddf0d9eb463e3310
## What changed
Register Guardian evidence-board cleanup with the app server's thread store when Guardian V3 is enabled. Leave Guardian storage untouched when the feature is disabled, and report cleanup failures as thread-store errors.
## Testing
Extend deletion tests to cover feature gating, preservation of unrelated boards and a surviving main thread's board, and corrupt-database recovery. Expand message-board tests to verify namespace isolation and persistent deletion markers that prevent later writes.
GitOrigin-RevId: d9119d22607769c92448d0f3cacbbfd03fbdf943
## What changed
Replace `thread_store_from_config` with `ThreadStoreBuilder`, exported through `codex_core` and `codex_core_api`, and migrate callers to the builder.
Allow hosts to register `with_additional_cleanup` for permanent deletion in local stores. The callback runs after successful agent-board cleanup and before rollout deletion, under the existing deletion locks. Document that cleanup must be idempotent and must avoid thread-store operations that reacquire those locks. In-memory stores do not invoke the callback.
Preserve the existing backend selection, startup rollout migration, and compression behavior.
GitOrigin-RevId: f2853d7de06fe12ef29451b204cf9fcbb349c359
## Why
After provider setup, new threads could still use the models manager created for the server's startup provider, leaving their default model inconsistent with the model picker.
## What changed
- Build a models manager from the thread's configuration when its provider differs from the startup provider.
- Invalidate the model catalog after successful Amazon Bedrock setup so subsequent model listings reflect the configured provider.
## Testing
Extend Bedrock and GCP setup integration tests to verify that a new thread's model matches the refreshed model listing. The Bedrock test also checks that the thread uses `amazon-bedrock`.
GitOrigin-RevId: 1db30ad040ba97e2f4f31c9e162a2b73af1377fa
## What changed
- Add `currentAccountOnly` to `thread/list` and `thread/search`, defaulting to `false`, and enable it for TUI history discovery, resume pickers, and task mentions.
- Mark newly created threads as account-scoped and require each recorded creator user or account ID to match the current login. Older threads and threads without creator IDs remain shared; API-key logins continue to see all local history.
- Preserve account scope through resume and revert, including fallback to original rollout metadata when an older binary drops the marker. Forks receive new-thread scope.
- Skip unreadable rollout headers in scoped discovery and filter search candidates before reading snippets. Direct access by thread ID remains available.
## Testing
Add coverage for account matching, shared legacy history, list page refilling, search pagination, API-key visibility, and scope preservation across reverts. Extend rollout lookup coverage to compressed active and archived files.
GitOrigin-RevId: aa374f5e69165be5a71c0716ded1b105f5fb51e0
## What changed
- Add `model_messages.plugins` overrides for generic usage guidance, selected-plugin hints, and recommendation introductions, with independent fallback to bundled wording for missing or invalid fields.
- Validate text limits and required template placeholders while keeping plugin identities, available capabilities, and eligibility controlled by the client.
- Track generic guidance changes across model switches and session resume, emitting replacement or retirement notices and supporting legacy snapshots and retained history.
## Testing
Add unit and scenario coverage for sparse overrides, literal text preservation, template validation, UTF-8 size bounds, capability filtering, recommendation fallback, and guidance recovery after resume.
GitOrigin-RevId: 148b658c2d8490c9d0dc208addbee1be5342a5f5
## What changed
Add the disabled-by-default `cli_resume_account_check` feature. When enabled for `codex-tui` and `codex_exec`, reject resuming or attaching to a local thread if its recorded creator user or workspace differs from the current ChatGPT account. Return an error directing the user to sign in with the original account.
Carry creator IDs through stored thread metadata and check them before loading resume history. Preserve existing behavior for untagged threads, other clients, and authentication modes without a comparable ChatGPT account.
## Testing
Add integration coverage for account and workspace mismatches, matching accounts, legacy and paginated history, ID and path lookup, and the feature's default and bypass behavior. Verify that switching back to the original account permits attachment to a loaded thread and that creator metadata remains unchanged.
GitOrigin-RevId: a3ab089254703417dde0890a5f8d6326c4cbb75a
## What changed
Add `modelProvider/config/write` to create custom gateways and patch existing custom gateway, Bedrock, and GCP settings. Return the saved provider using the same safe summary as `modelProvider/list`.
Omitted fields retain their values; explicit `null` clears nullable user overrides. Apply patches through the shared configuration queue with last-write-wins semantics, enforce field editability and validation, and preserve unexposed authentication settings.
Saving leaves provider selection and authentication unchanged. Saving the provider used by `model/list` invalidates its catalog for the next access. Include documentation and generated JSON, TypeScript, and Python protocol types.
## Testing
Add coverage for gateway creation and ID allocation, patch and null semantics, configuration policy enforcement, authentication preservation, and catalog refresh after active-provider edits. Extend Python protocol tests to verify wire round trips and reject mismatched provider IDs or fields.
GitOrigin-RevId: 850fe2c48ef5274944400efb5a859d720179c923
## What changed
- Add `modelProvider/list` to return OpenAI and explicitly configured providers, provider-specific settings, and the selected default provider.
- Report `canEdit` and `canChangeDefault` based on configuration requirements, layer precedence, and whether user configuration is enabled.
- Describe gateway authentication without resolving credentials, and omit endpoint URLs that are unsuitable for display.
- Document the API and update generated JSON schemas, TypeScript types, and Python models.
## Testing
Add app-server tests for provider discovery, authentication modes, unsafe URL suppression, and configuration editability, plus a Python wire-format round-trip test.
GitOrigin-RevId: 8ba26637cd6bdd075e0e815e88aeeb04c53a2364
## Why
`start_or_steer_turn` rejected agent messages, preventing callers from submitting follow-up work through the turn input API.
## What changed
Route `TurnInput::InterAgentCommunication` through native agent message delivery and return `TurnInputSubmission::Accepted`, without implying an immediate turn ID. These submissions request work regardless of `trigger_turn`, retain the recipient's settings, and forward turn-start options.
Wrap plaintext messages with agent context while preserving encrypted content. Reject submissions to idle recipients when the host is draining.
## Testing
Add scenario tests and snapshots covering queued-message ordering, encrypted follow-ups, preemption at reasoning boundaries, and follow-ups arriving before or after a final answer. Extend drain-gate coverage to agent submissions with parent-turn lineage.
GitOrigin-RevId: 92d49465f97bb366babbf1b1bc18a1e8a6c6ed1c
## Why
Live paginated history retains completed assistant text even when summaries only need the latest message. Release older text for threads with persisted history while preserving full resume responses.
## What changed
- Evict superseded assistant text from live turn state while preserving corrected items and the latest assistant message.
- Restore evicted text for full resume responses from prepared history pages, fetching remaining items by ID in bounded batches. Return an error if saved text is missing.
- Only load the active turn when it belongs in the requested initial page, and use the item ID index for targeted history reads.
## Testing
Add reducer coverage for text eviction and corrected messages. Extend running-thread resume coverage to compare full and summary items with live notifications, exercise restoration when the prepared page lacks the active turn, and check missing-text errors.
GitOrigin-RevId: 3229c0cea820f117dc6331312f1e6056a8d1d52c
## What changed
Add optional `ModelMessages.apps` and `AppsMessages.usage_instructions` fields to carry model catalog wording without runtime interpretation. Missing or null values become `None`, and strings retain their exact contents, including empty strings, whitespace, and template-like text.
## Testing
Add serialization coverage for nullable and literal Apps values, and extend existing tests to verify Apps messages survive model response round trips and base instruction overrides.
GitOrigin-RevId: 49b516656255e07b91f8f4679e2acb8e1b03f9e1
## What changed
- Allow audio inputs to carry uploaded file references via `fileId` in the app-server API and `file_id` in model content, preserving existing inline audio shapes and Python class names.
- Preserve mixed inline and file-backed audio ordering through history reconstruction and migration, and budget file-backed audio conservatively when duration is unknown.
- Keep uploaded audio disabled at runtime: reject it before inference or raw history injection, preserve accompanying text, and prevent rejected attachments from reaching follow-up or resumed requests.
## Testing
Add coverage for wire-format round trips, SDK compatibility, mixed audio history ordering, and rejection during turn start, steering, task completion, and raw injection.
GitOrigin-RevId: 70895c47a2494c0c9936348ad1250eb1b7b892a6
## What changed
Allow connector-wide app settings under `plugins.<plugin>.apps.<connector>` for plugins enabled by configuration. Merge these settings field by field, giving earlier plugin names precedence and applying explicit top-level `apps` fields last. Ignore nested `_default` settings.
Expose the merged app settings and their field origins through the config API. Keep app policy changes from invalidating the loaded-plugin cache.
## Testing
Add coverage for plugin enablement, merge precedence, field origins, config API output, cache reuse, and disabling an app through plugin configuration during explicit plugin mentions.
GitOrigin-RevId: a275319815915dc618ee606b10e0844248dbccb5
## Why
Clients need to refresh section membership and ordering when another client moves a thread.
## What changed
Broadcast `thread/section/changed` after a successful `thread/section/move`, including moves within the same section. Send the response before the notification, and include `threadId` and the destination `sectionId`, using `null` for removal. Failed moves do not emit the notification.
Add the notification to the protocol schemas, TypeScript exports, and Python SDK models and registry, and document its behavior.
## Testing
Add a WebSocket integration test with separate writer and observer clients covering section insertion, reordering, removal, and a failed move.
GitOrigin-RevId: 128ba7eddc9aae8e3bac766f47e4a2c55c64a6a5
## What changed
Return `CatalogModel` from model lookups, keeping metadata together with its `Bundled`, `Provider`, `ExplicitConfig`, or `Synthetic` origin through config overrides and runtime snapshots. Replace `used_fallback_model_metadata` checks with explicit `Synthetic` origin checks.
Share the underlying `Arc<ModelInfo>` with extension stores and use copy-on-write for metadata changes. Keep origin tracking outside serialized model metadata.
## Testing
Extend coverage for origin retention across cache reloads, namespaced model lookups, catalog fallback, and config overrides. Verify that step snapshots and extension stores share the same model metadata allocation.
GitOrigin-RevId: bb6130c94a7a795aa168ee24664a1dd453579fba
## Why
A network request can disappear while its approval prompt is still pending. Leaving that prompt active allows a late cancellation to interrupt the turn even though the request no longer needs approval.
## What changed
- Track network prompt lifetimes in core and notify the app server when a prompt is resolved or withdrawn.
- Cancel the corresponding server request, emit `serverRequest/resolved`, and release its permission guard. Resolve outstanding network prompts during thread shutdown as well.
- Claim a live pending approval and validate its originating turn before applying a decision, so stale responses cannot interrupt a turn or persist policy changes.
- Distinguish network approvals that require the originating turn from proxy approvals that can be serviced by a later active turn.
## Testing
Extend regression coverage for disconnected network requests, late cancellation responses, turn completion during review, shutdown cleanup, mismatched turn IDs, and command approvals from background code running during a later turn.
GitOrigin-RevId: 78f656d92607ec21ddd0c5d781ed0947588cb2eb
## Why
Long realtime conversations could lose speech when active transcripts and handoff transcript fields were truncated.
## What changed
- Record completed V3 transcript chunks in model and client history once the active transcript exceeds 4 KiB, without triggering inference.
- Keep unfinished utterances pending to preserve conversation order, and persist completed chunks before subsequent handoffs.
- Preserve full V3 transcript text at handoff and session-end tail flush, and avoid adding handoff input already recorded in transcript history.
## Testing
Add integration coverage for long transcripts, XML escaping, recording before handoff without inference, repeated handoff input, and both session-end tail flush settings.
GitOrigin-RevId: 62218b811809c4cf5b16fb0247a335eb474f9ab9
## What changed
Allow gateway OAuth configuration to select `credentials_store = "file"` to persist credentials in plaintext at `$CODEX_HOME/secrets/gateway_oauth.json`. Keep `keyring` as the default.
Read, update, and delete file-backed credentials by credential ID, using atomic writes and the existing cross-process lock. Preserve the serialized provider identity when using the default store.
## Testing
Add an app-server test that completes gateway OAuth login with file storage, verifies Unix file permissions are `0600`, and checks that login remains successful after a server restart.
GitOrigin-RevId: dc1d17922bd80bf65034cbc5aa3d97959e962dcc
## What changed
- Add a non-inlined `TryFrom<toml::Value>` implementation for `ConfigToml` and route callers through it to share the generated deserializer in `codex-config`.
- Reuse the ignored-field deserialization helper for strict validation, returning path-aware errors while preserving existing fallbacks for CLI validation and ignored-config warnings.
GitOrigin-RevId: 0208b314416ad4d3d7fbf3a30560a0c8c4035abd
## Why
Standalone web search must use the same permission mode as hosted search. Permission changes during a turn should take effect on the next turn, without changing web access for searches in the active turn.
## What changed
Pass the turn's `WebSearchMode` to the web search extension and use it to determine tool availability and `external_web_access`, while retaining provider support checks and thread-level search settings.
## Testing
Add an app-server regression test that switches from cached search to Full Access while a turn is paused. Searches before and after the update keep `external_web_access` disabled in that turn; the next turn enables it.
GitOrigin-RevId: 9e3b8598f2e491388b7e7d4840c849155ae95e88
## What changed
Allow shared network constraints in `[permissions.network]` in `requirements.toml`, alongside `[permissions.filesystem]`. Apply them throughout configuration loading, network approvals, Windows sandbox policy validation, and `configRequirements/read`, and show their source in `/debug-config`.
Retain `[network_proxy]` and `[experimental_network]`, but reject mixing either with `[permissions.network]`, even across requirements layers. Preserve independent network and filesystem precedence and source attribution, and report unknown nested network fields.
Reserve `network` as a managed requirements table name and reject empty or profile-shaped tables with migration guidance. Profiles named `network` remain valid in `config.toml`. Document that policy publishers must keep using `[experimental_network]` until all readers support the chosen replacement.
## Testing
Add coverage for layered constraints and source attribution, conflicting spellings, profile-name migration errors, unknown-field diagnostics, and cloud validation. Extend API, project discovery, network approval, and Windows policy tests to cover `[permissions.network]`, and verify managed proxy settings remain independent of disabled feature configuration.
GitOrigin-RevId: 994dfca9abf5a7aea914276c0ded8b40d7ed0372
## Why
Remote plugin bundle download URLs can contain signature tokens in query parameters. Including the full URL in errors or debug output exposes those tokens.
## What changed
Omit the download URL from `ValidatedRemotePluginBundle` debug output. Report download hosts instead of full URLs, strip URLs from underlying HTTP errors, and report only the scheme for unsupported final URLs. Invalid URL errors retain the parse error without echoing the input.
## Testing
Extend tests to check that signature tokens stay out of bundle debug output, unsupported final URL errors, and app-server installation errors while preserving signed request URLs and HTTP status diagnostics.
GitOrigin-RevId: 8edda4847feae4f2bcb12fbb414a3a25bde53814
## Why
Standalone web search errors currently abort the turn as fatal failures, preventing the model from responding to them.
## What changed
Return client setup errors to the model and represent failed search requests as unsuccessful tool outputs. Failed requests still emit search completion events and retain external-context handling. Limit error messages to 1,024 bytes, truncating at a UTF-8 character boundary with a truncation marker.
## Testing
Add coverage for failure status reporting and UTF-8-safe error truncation. Extend workspace routing tests to verify that a rejected redirect returns a bounded diagnostic to the model, allows the turn to complete, emits search lifecycle events, and marks thread memory as polluted.
GitOrigin-RevId: 9fb308990afa2ce0db5d9beed9bc66d9c1500418
## Why
Standalone web search could send requests to the bootstrap backend instead of the discovered workspace backend, bypassing workspace routing.
## What changed
Use the thread's shared `WorkspaceRoutingContext` when preparing search requests so they use the resolved backend, authentication, residency, and account routing headers. Reject redirects when required by the resolved routing policy or account routing header, and preserve the established routing context across configuration changes.
## Testing
Add an app-server integration test that verifies search reaches the discovered HTTPS backend with the expected credentials and routing headers, without contacting the bootstrap search endpoint. Add a regression test that verifies configuration changes preserve the thread's routing context.
GitOrigin-RevId: 67160f1b3e54231dc100ce3ed4cfcea965b56d26
## What changed
Expose `thread/guardianReview` to review an idle thread's final injected `exec_command` without executing it. Return the call ID and Guardian assessment, or `null` for the assessment when exec policy skips approval.
Subscribe the requesting connection to the thread, enforce input and model-provider restrictions, and cancel an in-flight review when the connection disconnects so the thread is released promptly.
## Testing
Add integration coverage for assessment responses, policy-skipped reviews, model-provider enforcement, and WebSocket disconnect cancellation.
GitOrigin-RevId: e8ad5598e8f101a937447ebe26136310bb76c8d1
## Why
Managed command policies need to require a human decision independently of automatic review, hook allowances, and saved approvals.
## What changed
- Support `decision = "prompt-user"` in managed `requirements.toml` prefix rules, requiring a fresh, one-time human decision for matching commands.
- Add experimental `humanCommand` approval requests for clients advertising both `experimentalApi` and `requiredHumanApproval`. Accept only `accept`, `decline`, or `cancel`; reject commands when no capable client is available.
- Restrict responses to capable clients that received the request, and replay pending prompts to compatible clients on reconnect.
- Enable the capability in the TUI and update protocol schemas and client bindings.
## Testing
Add coverage for fresh decisions overriding saved allowances, hook allowances, and automatic review, plus child-thread approval routing and rejection of responses from incompatible or unrelated clients.
GitOrigin-RevId: 0b95ff6aab7f8a04b7298c8a4329d1fddf6a603e
## What changed
Add `otel.log_sse_deltas`, enabled by default. Setting it to `false` suppresses successful SSE event logs whose kind ends in `.delta` while preserving errors, completion events, and metrics.
Apply the setting to session and memory telemetry, support managed requirements, and expose it in the app-server configuration requirements API and generated schemas and bindings.
## Testing
Add coverage for delta log suppression with errors, completion logs, event counts, and duration metrics preserved. Extend configuration and app-server tests to cover defaults, overrides, and managed requirements.
GitOrigin-RevId: 751c7f357c41f51848b025c838246a733eb92e2f
## What changed
Negotiate the `codex/connection-lease` extension for pooled stdio connections. For servers that advertise it, open a unique lease per chat and attach its host-owned ID to tool calls and resource reads via `codex/connectionLease`, overriding caller-supplied lease metadata.
When a chat releases its lease, write cancellations for pending requests before sending `codex/connection/release`. Preserve open-before-release ordering across startup timeouts, bound unload waits, and remove connections from the pool when lease cleanup fails or times out. Servers without the extension retain existing behavior.
## Testing
Add coverage for cancellation-before-release ordering, late open acknowledgements, and lease drops outside the runtime. Extend app-server sharing tests to verify distinct chat leases, metadata replacement, release on unload, and continued use by another chat.
GitOrigin-RevId: f4c8b606cb98b5697acab1c515e992ff80ec8425
## What changed
- Add the disabled-by-default `interrupt_on_cancel` feature to interrupt upstream inference when a Responses Lite turn is canceled, with a one-second cleanup deadline.
- Detach canceled WebSocket responses so replacement requests can open a new connection without waiting for cleanup.
- Add an optional `interrupt_on_cancel` override for thread samples, inheriting the parent setting when omitted.
## Testing
Add coverage for cancellation during inference and steering, replacement turns proceeding before cleanup finishes, and prompt cancellation of model response interceptors.
GitOrigin-RevId: 501368746fc04fd3fdbd45c1f34c75ce57f4e955
## Why
Hosted Apps returns no resource templates, so querying `resources/templates/list` is unnecessary.
## What changed
Return an empty template list for host-owned Apps in single-server binding requests and skip it during aggregate template discovery. Use server registration metadata so extension-provided servers named `codex_apps` continue to expose their templates.
## Testing
Add coverage for hosted Apps versus extension registrations and for full MCP server status with standalone and thread connections. Verify that status requests still call `resources/list` but omit `resources/templates/list`.
GitOrigin-RevId: 3182b619391aefbb2a47ca7b8d9611402846bfe3
## Why
Existing chats retain their provider configuration when the selected provider changes. Reject resume and input until the configured provider matches the chat, while keeping history readable and allowing recovery after configuration is restored.
## What changed
- Validate saved providers before applying resume overrides, preserving the provider when only model or reasoning settings change.
- Check the current provider selection, including profiles and launch overrides, before accepting input. Reject input when configuration cannot be loaded.
- Return structured `ModelProviderError` data for provider mismatches, missing definitions, and policy conflicts, with generated JSON Schema, TypeScript, and Python types.
## Testing
Add coverage for override bypass prevention, provider restoration, readable history after rejection, and blocked requests sending no inference traffic. Verify schema fields and Python round trips match the error wire format.
GitOrigin-RevId: 051f97c3815c547d8411c71b770df30eae969f68
## Why
Resuming or forking a thread loses the session flag indicating that reported token usage already includes retained reasoning. Counting that reasoning again can trigger automatic compaction too early.
## What changed
Persist `last_usage_includes_reasoning` with `TokenUsageInfo` and use it when estimating context usage. Record the flag with completed sampling and compaction usage, and mark local estimates as including reasoning. Older records without the field retain the existing accounting behavior.
## Testing
Add coverage for saved inclusive, exclusive, and legacy token counts. Extend the encrypted-reasoning compaction test to verify the compaction threshold for live, forked, and cold-resumed threads.
GitOrigin-RevId: 9f22262a693111ec0406dce11804eb4844ad8983
## What changed
Add an output schema for `image_gen.imagegen` so its code-mode declaration returns `Promise<{ image_url: string; output_hint?: string; }>`. Direct API tool serialization remains unchanged.
## Testing
Add coverage for the generated return type and unchanged direct API serialization, assert the full declaration in the app-server integration test, and verify that code-mode results omit oversized output hints.
GitOrigin-RevId: b3cee52a6b68c881f0c7507e791cc0fe86ca0d24
Dmitriy Kovalenko