## Why
Network access and Unix-socket allowlists must not let commands with filesystem restrictions reach the privileged app-server RPC transport.
## What changed
- Bind Unix control sockets in a fixed, user-owned directory with mode `0700`, independent of environment settings, and expose the advertised paths as symlinks. Preserve existing parent permissions, reject unsafe parents, and serialize socket setup and publication.
- Mask the socket directory in Linux bubblewrap sandboxes after each bind that exposes it. Reject host mount aliases and nested mounts that compromise isolation.
- Deny access to the directory and outbound connections to its sockets in macOS Seatbelt policies, including when network access or Unix-socket allowlists grant broader access.
- Require bubblewrap for filesystem-restricted Linux execution. Users with `features.use_legacy_landlock` enabled must disable it for these policies.
## Testing
Add regression coverage for direct and symlink socket access, hardlink attempts, Linux host-process links and bind-mount aliases, and continued use of unrelated and sandbox-local sockets. Add transport coverage for parent permissions, concurrent restart after a stale symlink, and cleanup that preserves a replacement at the advertised path.
GitOrigin-RevId: 53372c27eea278d964f2cf68aed24323ef3b7082
## Why
Permission profile changes reloaded configuration without the thread's session overrides, so profiles defined at thread start could be unavailable to `thread/settings/update`.
## What changed
Reload permission configuration with the thread's merged, enabled `SessionFlags` layers, the effective working directory, and the requested profile. Preserve sandbox executable paths through `ConfigManager`.
## Testing
Add regression coverage for switching away from and back to session-defined and disk-defined profiles, including top-level profile selection. Add a config manager test for merging session layers, excluding disabled layers, and retaining filesystem access to the exec wrapper directory.
GitOrigin-RevId: b0271e28a90cd55d3faf5fdf5f044d768395b0b6
## Why
Executor profile roots can use path conventions that are not native to the current host. Converting them to host paths during configuration or turn reconstruction can reject or drop those roots, while case-insensitive comparison can hide Windows path spelling changes.
## What changed
- Store profile roots as URI-backed `ProfileWorkspaceRoot` values throughout permission snapshots and thread settings, preserving spelling in equality and deduplication.
- Keep effective workspace roots as `PathUri` values for permission materialization and status summaries. Convert Windows sandbox root hints to native paths only at native Windows sandbox boundaries, rejecting incompatible roots.
- Omit the legacy rollout `workspace_roots` field when profile roots cannot be represented as host paths, retaining the compiled permission profile.
## Testing
Add regression coverage for Windows and UNC root spelling changes, settings restoration and turn recording with foreign roots, executor-root status display, and backend-specific Windows root conversion.
GitOrigin-RevId: 903c068fd74959bdd10e7cb1141aa42b953a59a4
## What changed
Keep `shutdown_signal()` pinned across `tokio::select!` iterations and reset it only when it completes, so other events do not cancel and recreate the pending signal listener.
## Testing
Update the WebSocket drain interruption test to use gated responses and keep a second turn active until the `turn/interrupt` reply arrives, preventing shutdown from racing the reply.
GitOrigin-RevId: c939d84ed0e09c2ee49229e81a3becdfa6a4c7f1
## Why
Daemon recovery reloads threads but leaves interrupted work unfinished. Resume eligible work automatically from the saved conversation, even without a connected client.
## What changed
- Attempt one new continuation turn immediately after restoration, including in Plan mode. Mark the old turn interrupted and supply recovery context without creating a user message or granting new authorization.
- Require an idle thread, matching permissions, and the same single local environment configured by the thread. Skip completed, aborted, or superseded work and snapshots without environment identity.
- Add `continue_turn_if_idle` with an atomic previous-turn check so newer tasks or standalone settings changes invalidate pending continuation.
- Preserve the output schema, service tier, and root turn ID, and emit a “Resuming interrupted work” warning when continuation starts.
## Testing
Add daemon restart coverage for continuation without a client, Plan mode, permission and environment mismatches, and legacy snapshots. Add core coverage for preserved continuation metadata, absence of user-message events, rejection of superseded continuations, and exclusion of remote execution from recovery snapshots.
GitOrigin-RevId: 2b290b75d9399fc58258bcda2e85c74e9b5b3b09
## What changed
- Add an optional `WorkspaceRoutingResolver` to `AuthManager` and pass session configuration into routing lookups. Callers without a resolver retain existing routing behavior.
- Apply resolved backend origins and account routing overrides to eligible ChatGPT Responses HTTP requests and WebSocket handshakes. Preserve endpoint paths, validate routing values, and reject HTTP redirects for routed requests, including `NO_CONSTRAINT` routes.
- Key cached WebSocket connections by destination, routing header, and auth revision. Rebuild request setup after credential refreshes and reject account changes during setup or routing discovery.
- Serialize routing lookups per session and retain whether the session has previously been routed.
## Testing
Add tests for path preservation, provider exclusions, concurrent routing lookups, unavailable resolvers, workspace mismatches, redirect rejection, and credential refresh or account changes during request setup.
GitOrigin-RevId: 2b6609019e84a315745c94858955f3f16426fe7f
## What changed
- Accept and ignore `features.personality` in user configuration, profiles, and managed requirements.
- Remove feature gating from `personality = "none"`, which strips the literal `# Personality` section when preparing model catalog instructions. Preserve explicit base instructions and existing thread instructions.
- Document deprecated personality fields in configuration, app-server schemas, and the Python SDK: `friendly` and `pragmatic` no longer select a style, and `supportsPersonality` is always `false`.
## Testing
Add regression coverage for ignored legacy flag values and managed requirements, personality opt-out behavior with the flag absent or set to either value, role overrides, and preservation of explicit base instructions, including empty strings.
GitOrigin-RevId: 4e12c66b42bfc59d6f151a5b3c28fadc6654ae99
## Why
Managed daemon recovery snapshots previously saved only loaded thread IDs, without identifying active turns or preserving their turn-specific options.
## What changed
- Capture regular, uncanceled turns after their input is recorded, saving the turn ID, output schema, service tier, and cyber access program alongside persisted thread IDs.
- Store interruption metadata atomically in the existing candidate array format so older servers can still read thread candidates.
- Begin snapshotting once admitted operations drain, while turns may still be running. Run snapshot collection and thread listener attachment independently of the event loop to keep forced shutdown responsive.
## Testing
Add coverage for running, completed, canceled, and compacting turns; recovery readiness for automatic and user turns; admitted resumes during shutdown; forced shutdown with a blocked rollout writer and child listener attachment; and legacy candidate-array compatibility.
GitOrigin-RevId: ed46342c3a5c71b09c48fa9acece2f15ae748e2f
## Why
Clients need widget presentation details to render MCP Apps without waiting for the full MCP catalog, including when replaying saved history.
## What changed
- Add `mcpToolCall.mcpAppUi` with the invoked descriptor's `resourceUri` and `preferredModelDisplayMode`, and carry it through tool-call events and saved history.
- Support `fullscreen` and default to `inline` when the display preference is missing or unsupported.
- Keep existing resource URI fields for compatibility. Leave `mcpAppUi` null for older history and tools that declare widgets only in result metadata, where clients still use catalog discovery.
- Update protocol schemas, TypeScript and Python types, and app-server documentation.
## Testing
Add parameterized integration coverage for fullscreen, missing and unsupported preferences, legacy URI metadata, and result-only widgets, verifying consistent tool events and preservation across session resume.
GitOrigin-RevId: 2a9bed804dcea8c2b4903b8406fa6710681f7f5e
## What changed
- Accept `fileId` alongside the existing `url` form for app-server image inputs, and forward file references to the Responses API as `file_id`. Update generated schemas and client types.
- Preserve file references, image detail hints, and mixed inline/file image ordering through user-message events, thread history, and rollout migration. Retain file images when truncating tool output.
- Pass file references through image preparation without resolving them, while keeping resize-notice numbering correct. Omit them from unsupported TUI display and Guardian image context.
- Reject image-edit requests whose recent-image window includes a file reference, preventing selection of an older inline image instead.
## Testing
Add coverage for serialization, request and rollout preservation, mixed-image history ordering, incomplete ordering metadata, tool-output truncation, and rejection of unsupported image-edit selections.
GitOrigin-RevId: 6ca20a8577155cc934b720803c3b7b3bffdf972a
## Why
Token plan claims can be stale, and the active account or user can change while a request is in flight. Analytics report selection and account-bound response data need to reflect the verified identity and current server plan.
## What changed
- Fetch the active account's plan once per analytics session and use it to select report endpoints and supported credit breakdowns.
- Add report loading with a fixed end date, account-scoped response caching, and token model filtering. Reuse payloads across grouping changes and evict invalid cached responses so requests can retry.
- Prefer complete attribution for usage breakdowns within the requested range; retain legacy surface/model data when attribution is incomplete and include all features in turn-start breakdowns.
- Add cancellable report-loading state with timeout and interruption errors, and preserve actionable sign-in and retry messages.
- Recheck the active identity after rate-limit reads before exposing account-bound fields.
## Testing
Add regression tests for server plan discovery, report routing and caching, model filtering, attribution fallback, failed-request retries, load cancellation, authentication recovery, and account or user changes during requests.
GitOrigin-RevId: 45c4c09f108c9703893f3ed15613437ebd7c74a8
## What changed
- Track the Windows sandbox implementation separately from its legacy setup level.
- Select dedicated proxy listeners for `WindowsMxc` on Windows across sessions, app-server command execution, and the sandbox CLI.
- Rebuild the session proxy when routing changes, retaining its network policy decider.
- Add a sandbox CLI execution path through the MXC sandbox transform when `WindowsMxc` is selected.
## Testing
Extend configuration assertions for the selected sandbox type and the session refresh test to verify dedicated routing and policy decider retention on Windows.
GitOrigin-RevId: 2a22192636c542022ec81a378a16c1bb6867e145
## Why
`allowedWindowsSandboxImplementations` uses the legacy setup-mode type, which cannot represent `mxc`.
## What changed
- Introduce `WindowsSandboxImplementation` with `elevated`, `unelevated`, and `mxc` variants for configuration requirements, and update the generated schemas and TypeScript and Python types.
- Keep `WindowsSandboxSetupMode` limited to `elevated` and `unelevated`, and update the requirements mapping and its test assertions to use the new type.
- Document that clients selecting `mxc` skip the legacy setup and readiness APIs and use the standard `command/exec` streaming and process-control path.
GitOrigin-RevId: c926e853f0bbdb29d4b437866c284c1394a7ea13
## Why
MXC is a sandbox implementation, not a restricted-token sandbox level. Executor requests need to represent that choice separately from `WindowsSandboxLevel`.
## What changed
- Introduce `WindowsSandboxSelection` for executor sandbox contexts and remove `Mxc` from `WindowsSandboxLevel`.
- Preserve the `windowsSandboxLevel` wire field and its serialized values for compatibility.
- Share sandbox selection between executor process launches and filesystem helpers, and use the new selection in capability discovery and skill reads.
- Disable Windows sandbox selection for executor paths that do not use Windows path conventions.
## Testing
Extend coverage for MXC wire serialization, Windows skill-read sandbox checks, and capability discovery with distinct permissions. Exercise remote filesystem write restrictions with both restricted-token and MXC sandboxes, including rejection when native MXC is unavailable.
GitOrigin-RevId: 266211377bcb138a0dc75861e9ff2225fa37a53d
## What changed
- Capture `CODEX_WINDOWS_REGISTERED_CORE=1` at startup and propagate the selected runtime to sandbox wrappers.
- Launch registered runners through service-recorded execution aliases, validating ownership, OS package identity, and the staged runner image before sending commands. Require service provisioning without falling back to copied helpers or `PATH` lookup.
- Preserve package context for sandboxed child processes and descendants so they can launch executables from the protected package directory.
- Refresh stale package registrations during readiness checks without blocking unrelated RPCs, and reconcile effective proxy settings through the service.
- Resolve setup ownership from the process token and avoid treating the server directory as a writable workspace when setup omits `cwd`.
- Record startup and command outcomes by runtime.
## Testing
Add coverage for runtime selection, package query validation, helper resolution, setup roots, proxy reconciliation, and command result reporting. Add an ignored integration test for environment forwarding, output, and exit status that requires an installed test MSIX and service provisioning in a Windows VM.
GitOrigin-RevId: 976d64039d611be4406c3d0e354820775f8eb6e4
## What changed
Represent images in `ContentItem` and `FunctionCallOutputContentItem` with `ImageReference::Inline`, flattened to preserve the existing `image_url` wire format. Update image producers and consumers and regenerate app-server schemas and SDK artifacts.
Preserve the Python SDK's `InputImageContentItem` and `InputImageFunctionCallOutputContentItem` class names during generation.
## Testing
Add a regression test for stable Python image class names and adapt existing image tests to the shared representation.
GitOrigin-RevId: c38a780ac3314c2ac2deb3afc1b93b94b6f93fec
## What changed
- Add experimental `account/read.workspaceRouting` metadata containing the selected ChatGPT workspace ID, resolved HTTPS backend origin, and routing override (`us`, `us_cr`, or `NO_CONSTRAINT`).
- Discover and cache routing through `accounts/check` for saved logins, new logins, and workspace switches. Return `null` for signed-out accounts, API-only accounts, and saved credentials without a selected workspace.
- Validate discovered origins against required `chatgpt_base_url` origins. Return errors for failed or malformed discovery and retry on later reads.
- Wait for requirements and routing before publishing account updates, including to newly initialized connections. Clear routing on logout, discard stale discovery results, and guard queued notifications against account changes.
## Testing
Add unit and integration coverage for origin resolution and validation, discovery failures and retries, startup discovery, workspace switching, logout, configuration changes during discovery, and authentication changes while notifications wait for queue capacity.
GitOrigin-RevId: 2c5367bb01dd7543b08d374f44444323e40f1981
## Why
Resuming a thread initialized its collaboration mode to Default, losing the saved Plan mode and its developer instructions. Reconnecting clients also lacked a server-reported mode to reconcile changes made by another client.
## What changed
- Restore the saved collaboration mode from the latest matching `ThreadSettingsApplied` event, falling back to the last legacy `TurnContext`. Apply the effective model and reasoning effort while retaining the saved mode and developer instructions.
- Include `collaborationMode` in `thread/resume` responses and update the generated schemas and bindings.
- Use the restored mode in the TUI, including the first prompt after resume. Prefer the server's mode when restoring disconnected input, while preserving the local selection for older servers that omit it.
## Testing
Add regression coverage for persisted and legacy collaboration modes, model and reasoning-effort overrides, the resumed Plan mode display and first prompt, and reconnect behavior with and without a server-reported mode.
GitOrigin-RevId: ed064516e7fae1c1668152ab448f510cbcacfe06
## What changed
Add experimental `thread/start.daybreakEnabled` so clients can set the initial preference for persistent threads. Omitted or null values leave it unset; explicit values are rejected for ephemeral threads.
Return the choice in the start response, `thread/started`, and reads before persistence. Stage it with the initial thread metadata and save it when the thread is persisted. Later changes still use `thread/metadata/update`. The preference does not select `turn/start.cyberAccessProgram` or grant access.
## Testing
Add coverage for true, false, and unset values in responses, notifications, reads, and reads after persistence and restart, plus rejection for ephemeral threads. Update existing metadata and access-program tests to exercise threads with an initial preference.
GitOrigin-RevId: 3bff3dc55a18436067bc2a3f156f5abf52d7321b
## Why
Configuration requirements did not report which login methods the running app server permits after applying managed policy, forced login settings, and workspace restrictions.
## What changed
- Add `allowedLoginMethods` to `configRequirements/read`, using the running authentication manager's effective policy rather than newly read authentication settings.
- Return requirements when login methods are restricted even without managed requirements, while preserving `requirements: null` for the unrestricted default.
- Update protocol schemas and generated TypeScript and Python types. An empty list permits no login method; older servers may omit the field.
## Testing
Add coverage for managed and forced login restrictions, workspace intersections, policy reporting after requirements files change, invalid login methods, and API-only Amazon Bedrock without ChatGPT requests. Extend tests for conflicting authentication requirements and cloud policy precedence.
GitOrigin-RevId: 56c0767a74143e793aac2ac165d0cbe98a09469b
## What changed
- Remove `AgentSpawner` and `AgentSpawnFuture` from the extension API, along with the Guardian wrapper, thread lifecycle context, and app-server injection plumbing.
- Define `InternalSessionSpawnFuture` directly as a boxed future instead of aliasing `AgentSpawnFuture`.
- Raise the workspace `rustls` minimum version to `0.23.45`.
GitOrigin-RevId: b7319dee41bfb869479afeb7555a6f050c4d00a5
## What changed
- Extract helper copying, token-user SID queries, provisioning pipe ownership, and service runtime lifecycle into dedicated modules.
- Simplify command-runner resolution and extract setup configuration loading, payload execution, provisioning request exchange, and response handling into helpers.
- Parameterize installation-record registry access and return the saved installation record from authenticated user registration.
## Testing
Add tests for explicit setup `cwd` selection and effective workspace roots, plus valid and invalid token-user SID queries. Move existing helper-copy and freshness tests alongside the extracted copy implementation.
GitOrigin-RevId: ffb39adae7611baa95e85c89f9a31ef7a779e217
## Why
Command execution and plugin measurement events lack model and reasoning-effort labels. Attribution needs to reflect the step that invoked the command, even when model settings change before a background process finishes.
## What changed
- Add `model_slug` and `reasoning_effort` to command execution and plugin measurement analytics.
- Capture model context from resolved step settings and carry it through execution, approval, Guardian review, and plugin metrics collection.
- Preserve the first command-start model context when subsequent start notifications arrive.
- Keep the carried context out of serialized protocol items and generated schemas.
## Testing
Extend analytics tests to cover model switches before invocation and during background execution, default reasoning effort, Guardian-denied commands, and repeated start notifications retaining the original model context.
GitOrigin-RevId: af90e1c0d39bab625f2e89786085b61a9b96c0ce
Remove entries from the owned snapshot maps when building MCP server status
responses, moving server metadata, tools, resources, and auth statuses into
the response instead of cloning them. Preserve pagination and missing-entry
defaults.
GitOrigin-RevId: 012301f55ddb9c52c7934a638bdd0310f11077fa
## Why
Desktop uninstall cleanup needs an installation owner even when the user has not signed in or configured the Windows sandbox. Recording ownership only during provisioning leaves those installations unregistered.
## What changed
- Add an authenticated installation registration request and attempt it during Windows desktop stdio initialization, with a five-second timeout before the initialization response.
- Persist ownership independently of provisioning, preserve existing desktop ownership, and prevent another user or home from replacing the registered owner.
- Validate write authority and retain directory handles and guards to protect the registered home against junction conversion through privileged cleanup.
- Preserve existing CLI homes during desktop uninstall while removing their `CodexSandboxUsers` ACL entries. Report ACL revocation errors and avoid propagating unchanged ACLs.
- Grant the owner `WRITE_DAC` on `.sandbox-bin` and allow elevated-helper fallback when older permissions need repair or the service cannot establish an uninstall watcher.
## Testing
Add tests for installation registration without sandbox settings and for preserving a child's null DACL when revoking an absent SID from its parent.
GitOrigin-RevId: fb48923e9d76758d1bf5b50c7305aa60f91629db
## Why
Direct tool-call records need to stay associated with the invocation that produced each output, including when call IDs are reused. Completeness must describe the recorded call inventory, independently of tool success.
## What changed
- Attach direct-call records to outputs before they enter history, and set `tool_calls_complete` when the invocation's arguments are fully recorded.
- Bound pending recordings and retained metadata, release reservations on completion or cancellation, and invalidate pending records when capture is disabled.
- Apply request budgets to direct metadata and strip it from inference and compaction inputs when capture is disabled.
- Remove executed-call metadata from app-server raw response notifications and exclude its size from Guardian history retention budgets.
- Track call IDs that bypass dispatch so their reuse cannot incorrectly establish Code Mode completeness.
## Testing
Add regression coverage for direct-call attribution, malformed calls, metadata budgets, cancellation, configuration changes, compaction, notification filtering, and Guardian context isolation.
GitOrigin-RevId: 2ebd39c7f141d04788736491495109841656b4c0
## What changed
- Add explicit MXC backend selection and carry its identity through exec-server process reporting and sandbox violation classification.
- Launch MXC through the Codex executable with the effective permission profile and command environment.
- Reject exec-server MXC requests when native MXC is unavailable or when they request a TTY, an `arg0` override, or managed networking. Reject private desktop isolation during MXC preparation.
- Allow an explicitly empty child environment and avoid exposing request payload values in launcher decode errors.
## Testing
Add coverage for sandbox selection and unsupported-request rejection, plus Windows RPC tests for stdin writes and temporary-directory permissions derived from the command environment. Native MXC tests skip when MXC is unavailable.
GitOrigin-RevId: 3626ff0f9ad7f9b812ce09b68c31ea9a5a9c72b1
## Why
Existing threads retain their model provider configuration, which can stop matching managed requirements after those requirements change.
## What changed
- Check retained providers against current managed `model_provider` and `model_providers` requirements before turn start/steer, review, compaction, manual queue start, and active goal updates. Reject requests when requirements cannot be loaded or no longer match; provider mismatches prompt users to restart Codex.
- Load managed requirements independently of user, project, system defaults, and thread configuration, and resolve Bedrock provider overrides before comparison.
- Keep interrupt, realtime stop, and goal pause/clear available. Realtime connections use separate routing and are outside these checks.
- Make detached reviews inherit their parent thread's configuration.
## Testing
Add unit and integration coverage for provider selection and definition changes, Bedrock overrides, requirement load failures, unchanged queue and goal state after rejection, and continued operation after local configuration changes. Extend detached review coverage to verify inheritance of the parent's provider route.
GitOrigin-RevId: 21abf08ad2bcc2ea4698209fa33a17485eed4740
## What changed
Remove `thread/rollback`, its request and response types, generated bindings, and the core `Op::ThreadRollback` operation. Requests now follow the generic unknown-method rejection path. Document `thread/revert` as the alternative for paginated threads.
Keep historical `ThreadRolledBack` markers and legacy error deserialization so existing rollouts remain compatible with replay and migration.
## Testing
Adapt retained-context and Guardian history tests to append legacy rollback markers and resume threads, preserving coverage of surviving instructions, answers, and review history.
GitOrigin-RevId: b3da1becdf86b1869275aacb0ffc2817cee5af2e
## What changed
- Accept `disabledPluginIds` in `thread/settings/update` and `turn/start`. A supplied list replaces the saved selection; omission or `null` preserves it, and `[]` clears it.
- Return the selection in thread start, resume, and fork responses and `thread/settings/updated` notifications. Update generated schemas and client types.
- Restore disabled plugin IDs from the history retained at the requested fork boundary, preserving explicit overrides.
The selection persists across resume but does not yet filter plugin capabilities.
## Testing
Add coverage for replacing, preserving, and clearing selections without inference; turn-start notifications; resume; and fork boundaries across legacy and paginated history, with loaded and restarted parents. Add a core regression test for history restoration and explicit clearing.
GitOrigin-RevId: 654a8c2a0527228d422c0dd4919228447e2663db
## What changed
Carry optional `available_access_programs` metadata through model information, presets, caches, and the TUI, and expose it as `availableAccessPrograms` in app-server `model/list` responses. Update the generated JSON schemas, TypeScript types, and Python models.
Preserve the distinction between missing metadata and an empty `cyber` list. Ignore unknown cyber program names when reading the catalog so new server programs do not prevent older clients from loading it. Discovery metadata does not grant access; inference still enforces authorization.
## Testing
Add coverage for absent, null, empty, and populated metadata, unknown program names, and app-server serialization. Extend cache tests and verify that online refreshes persist changed access metadata even when the catalog ETag stays unchanged.
GitOrigin-RevId: b3ef5805c1c61b8d64b9b896c9c0a79120143667
## Why
The trusted UI host needs the local credential's public metadata to complete backend registration. `userVerification/enroll` previously returned only `credentialId`.
## What changed
- Return `algorithm` and `publicKey` for newly created or reused credentials. The algorithm is `ecdsaP256Sha256X962`; the public key is unpadded base64url SPKI-DER.
- Keep both fields optional in the protocol for compatibility with older app-servers, while current servers populate both.
- Document caller-owned backend registration and revocation, including checking metadata, signing an enrollment challenge with `userVerification/verify`, matching credential IDs, and preserving the authenticated account throughout registration.
## Testing
Add protocol coverage for absent or null metadata and populated-response round trips. Add an RPC assertion for enrollment metadata and extend the local enrollment test to check metadata when creating and reusing a key.
GitOrigin-RevId: f0726e8c430e27559e1a01ba2ea635993cbeba09
## Why
Enterprise MCP authorization must remain controlled by host, user, or managed configuration. Project settings and plugin declarations must not redirect enterprise credentials or downgrade the selected authentication mode.
## What changed
- Add `auth = "ema_auth"`, shared `mcp_enterprise_managed_auth` IdP configuration, and per-plugin enterprise registration settings.
- Require enterprise registrations to come from one non-project configuration layer, preserve managed IdP precedence, and reject project overrides that change authorization or re-enable disabled enterprise servers.
- Add the disabled-by-default `use_xaa` feature flag and require non-project opt-in or a managed requirement.
- Reject plugin declarations that select `ema_auth`. Keep EMA connections unsupported and block ordinary MCP OAuth login and credential fallback for this mode.
- Extend the configuration schema and serialization for the new settings.
## Testing
Add coverage for IdP precedence, incomplete registrations, alternate credential validation, project-only opt-in, plugin self-declaration rejection, configuration round-tripping, and trusted-project attempts to downgrade enterprise auth to OAuth or ChatGPT auth.
GitOrigin-RevId: f193bdfda74208c98e496a23bf2916955b131a1c
## What changed
Add `serverCapabilities` to `mcpServerStatus/list` responses in both `full` and `toolsAndAuthOnly` modes, including thread-scoped reads. Return the initialized server's capabilities object, including its `extensions` map, or `null` when unavailable.
Capture capabilities during initialization so they remain available when tool discovery fails. Clear them on each new connection attempt and keep them independent of shared tool caches. Update the protocol schemas, generated TypeScript and Python types, and documentation.
## Testing
Add coverage for extension capabilities surviving tool-discovery failures in both detail modes. Extend existing tests to check advertised extensions, absent capabilities after initialization failure, and serialization of unavailable capabilities as `null`.
GitOrigin-RevId: 8e9d67c10fac3a54e82bef8be5d99caaf82597d1
## Why
Unrecognized settings can be silently ignored, leaving typos or deprecated configuration unnoticed.
## What changed
- Collect warnings for unrecognized fields in effective configuration and requirements layers, including unknown feature keys in configuration.
- Report sources and field names without configuration values, show up to three entries, and provide migration hints for `network_proxy`, `allowed_permissions`, and `include_view_image_tool`.
- Emit project-specific warnings when starting a thread and suppress repeated startup warnings in the app server and TUI.
## Testing
Add coverage for merged configuration, disabled layers, startup and project warning delivery, omission of configuration values, and warning deduplication.
GitOrigin-RevId: 464cef87882502b19865ae10b50b6f82defb7296
## Why
Permission paths need to follow the execution host's path conventions and home directory. Literal directory names containing glob syntax must not change the meaning of deny patterns, and profile availability checks need to account for configured workspace roots.
## What changed
- Use `ConfigPathContext` to compile built-in and custom profiles, returning the resolved profile and deduplicated `PathUri` workspace roots. Materialize configured roots while retaining runtime workspace symbols.
- Use the same compiler for configuration loading, persisted profile validation, and profile catalogs. Resolve roots against the requested `cwd` when listing profiles.
- Resolve home-relative scoped rules using the supplied home directory and reject unsafe directory prefixes when constructing globs.
- Share workspace-root materialization across native paths and URIs. Deny the affected root when a workspace glob cannot be safely resolved, and clear grants for legacy home-relative workspace denials whose target is unknown.
## Testing
Add coverage for POSIX, Windows, and UNC path resolution, inherited workspace roots, scoped home denials, missing home context, and conservative denial behavior for unsafe globs. Add an app-server test verifying that profile availability reflects the requested `cwd`.
GitOrigin-RevId: ca259434742365c16d0b72629cabfbab41513a80
## What changed
- Support `model_provider` and `model_providers` in managed requirements. Required selection overrides local and session configuration; each required provider definition replaces the corresponding local entry, including its authentication and headers.
- Merge provider requirement fragments before validation, preserving source-relative `auth.cwd` paths. Reject invalid cloud provider definitions before replacing the cached bundle, including unsupported Bedrock overrides.
- Expose `modelProvider` and `modelProviders` through the configuration requirements API and generated schemas. Reject writes to managed provider settings and omit their local origins, including for provider IDs containing dots.
## Testing
Add tests for requirement precedence, authentication fragment merging, path resolution, cloud cache preservation, and read-only configuration RPCs. Integration tests verify that model discovery and inference use the required gateway and ChatGPT authentication without leaking local headers, and that provider requirements survive configuration rebuilds.
GitOrigin-RevId: d1448604d4ef5662ebb5df7b693712d3b8ad6d54
## What changed
Allow app-server to advertise `openai/elicitation.userVerification` and route verification requests to local stdio clients named `Codex Desktop` when `experimentalApi` is enabled and the device supports verification. Preserve support for the in-process `codex-tui` client.
Document the experimental verification API, local credential lifecycle, transport restrictions, and GUI requirements for cancellation and late proofs.
## Testing
Extend activation tests to cover desktop capability advertisement and request eligibility, including rejection for other transports, unrecognized client names, missing opt-in, and unsupported devices.
GitOrigin-RevId: ba4fd4b83b9c24541df3a490396d6c715e7b7433
## Why
Persisted turn-start events lack the originating root turn ID, so they cannot directly associate child turns with the root turn that initiated them.
## What changed
- Add optional `root_turn_id` to `TurnStartedEvent`. Use the inherited root turn ID when available, otherwise the turn's own ID.
- Centralize turn-start emission for regular turns, shell commands, and manual compaction so they record attribution consistently.
- Carry attribution into `ThreadHistoryTurnChange` when processing turn-start events and retain it through completion in the history builder.
- Keep older records compatible by defaulting missing attribution to `None`.
## Testing
Add coverage for root and child turn attribution, persistence when tool collisions fail a turn before sampling, history change propagation, and deserialization of older turn-start records.
GitOrigin-RevId: 54a80b828ca7d1c4c19f13d468c01d052e1b9130
## What changed
- Add `thread/attachment/add`, `thread/attachment/list`, and `thread/attachment/remove` to manage durable resource references without loading the owning thread or changing conversation history.
- Identify attachments by thread, `attachmentType`, and `identityKey`. Repeated adds return the existing attachment; repeated removals succeed without emitting another update. Listing supports cursor pagination.
- Broadcast `thread/attachment/updated` after creation or deletion, after responding to the requester. Serialize attachment mutations with thread lifecycle operations and reject stores that do not support attachments.
- Update protocol schemas, TypeScript and Python bindings, documentation, and TUI notification handling so attachment updates do not add untracked threads to the agent picker.
## Testing
Add coverage for unloaded threads, pagination, idempotent addition and removal, reattachment, invalid inputs, unsupported stores, response-before-notification ordering across clients, and TUI notification routing.
GitOrigin-RevId: 0d29cf903afd4e931a70a9cf96300475213b34aa
## Why
Stdio shutdown can hang on open pipes or blocked I/O, and Unix `SIGTERM` needs to run connection cleanup so owned commands terminate and session-end hooks execute.
## What changed
- Handle `SIGTERM` on a dedicated signal thread and close the stdio connection through the existing cleanup path.
- Move blocking stdin and stdout operations to dedicated threads so they do not hold the Tokio runtime open. Cancel message forwarding on `SIGTERM` to release blocked producers.
- When shutdown signal handling is enabled on Unix, start a shared 45-second watchdog on EOF or `SIGTERM`. Preserve the first deadline and exit with status `1` if cleanup or runtime teardown stalls, even when logging is blocked.
## Testing
Add Unix integration coverage for shutdown with open pipes, blocked stdout, blocked stderr, and a stalled filesystem write. Verify command and child-process termination, preserve the EOF deadline when `SIGTERM` follows, and extend session-end hook coverage to `SIGTERM`.
GitOrigin-RevId: 43a80b8277eb50519cdc293eb3b5dc2cad00b3aa
## What changed
Add the default-off `api_key_model_discovery` feature and expose it through app-server experimental feature enablement, respecting user configuration overrides.
When enabled, fetch OpenAI API-key model metadata from the Codex backend, honoring explicit provider base URLs. Treat remote catalogs containing visible models as authoritative. When disabled at startup, skip discovery requests and cached catalogs and retain bundled models.
## Testing
Add coverage for feature enablement and user overrides, cached catalogs across sessions, provider routing, and API-key `model/list` results. Extend coverage for remote instructions and auth-specific cache isolation.
GitOrigin-RevId: 4b189c37c615a7f808cb6ff5f0858a9a55f36ebc
## Why
Attachment mutations must coordinate with thread deletion so queued requests cannot use metadata belonging to a deleted thread.
## What changed
- Add typed `ThreadStore` operations for idempotent attachment creation, paginated listing, and removal, with capability detection and unsupported defaults.
- Implement attachment operations for SQLite-backed `LocalThreadStore`, including unloaded threads, and preserve invalid-request and missing-thread errors.
- Coordinate attachment mutations with lifecycle locks and move SQLite cleanup into thread-store deletion. Remove state rows only after rollout deletion, preserving retries after cleanup failures.
- Give the in-memory store ownership of its associated SQLite cleanup and remove duplicate cleanup from the app-server.
## Testing
Add coverage for attachment pagination and idempotency, unsupported stores, error categories, lifecycle exclusion, mutations queued behind single and batch deletion, cleanup failure retries, and in-memory state cleanup. Extend the app-server descendant deletion test to verify SQLite rows are removed.
GitOrigin-RevId: f0157538c7c5c2ee1362ce40eac157101c5d4505
## Why
Remote-control connections and queued operations must not carry over to a different signed-in user or account. Token refreshes for the same identity should preserve the live relay connection.
## What changed
- Scope relay state and authentication recovery to a login lifetime. Retire the session on logout or identity changes and leave remote control disabled until enabled again.
- Reject stale incoming messages and queued RPCs, and cancel pending remote-control operations when their authentication owner changes.
- Start replacement sessions with fresh client, replay, and enrollment state, and prevent retired sessions from publishing status into their replacements.
- Serialize enrollment and preference persistence across sessions, retaining write permits through caller cancellation and draining admitted writes on shutdown.
## Testing
Add regression coverage for same-owner refreshes, user and account changes, stale pairing and client-revocation work, unauthorized enrollment recovery after logging in again, and persistence during cancellation.
GitOrigin-RevId: 5e6ecd23588aab1e2e6168a21f575fb24bbb341c
## What changed
- Add `disabled_plugin_ids` to thread startup options, settings overrides, snapshots, and persisted turn contexts. Omitted overrides preserve the current list; an empty list clears it.
- Restore the selection on resume and capture it before truncating history for a fork. Prefer the owning thread's latest settings snapshot, falling back only to the latest turn context so stale history cannot resurrect an older selection.
- Freeze the selection at turn admission and retain compatibility with histories that lack the new fields.
## Testing
Add coverage for owned settings, explicit clears, latest-turn fallback, and legacy snapshots. Extend settings tests to cover plugin selection during runtime restoration and compaction, and verify initial turn persistence without extra settings checkpoints in both history modes.
GitOrigin-RevId: 75ffbff5763cd93cc5ac69d73b08b237f59bc009
## Why
The elevated Windows sandbox requires effective `:root` read access and cannot safely enforce policies that deny reads at the filesystem root.
## What changed
- Validate root read access before elevated setup, service provisioning, and setup refresh, rejecting root-denying globs before expansion.
- Reject filesystem-root deny-read ACL targets after canonicalization and check the opened handle before applying an ACL, so aliases cannot bypass the root guard.
- Read and update deny ACLs through the same handle, and allow an existing deny ACE to be recognized when write access to the ACL is unavailable.
## Testing
Add regression coverage for default root denial, root-denying globs, allowed root reads with narrower deny rules, handle-based root detection, and reading existing deny ACEs without `WRITE_DAC`.
GitOrigin-RevId: b904e7cdbc09ee0147e1818c898b0382b5820c1b
## What changed
Add nullable `promptHash` to the upload response, populated from the uploaded `prompt_hash` tag. It identifies the whitespace-normalized SHA-256 of the session base instructions, excludes later developer messages, and is `null` when the reported rollout has no prompt metadata.
Update the protocol schemas, precomputed exports, and generated TypeScript and Python types.
GitOrigin-RevId: 6fa70fbe7a06604ac1cd0ea363eb4f192083dad9
## Why
Hosted Codex Apps shared the `mcp_2026_07_28` protocol setting with other MCP servers, preventing independent protocol selection.
## What changed
- Add `features.codex_apps_mcp_2026_07_28`, disabled by default, for the host-owned HTTP `codex_apps` server. Enabling it attempts 2026-07-28 discovery with Legacy fallback.
- Keep other servers, including third-party registrations with Apps-like names or URLs and local stdio servers, governed by `mcp_2026_07_28`.
- Support the new flag through `experimentalFeature/enablement/set` and refresh protocol settings in existing sessions. Track protocol mode per server when deciding whether to reuse connections.
## Testing
Add coverage for independent feature and protocol selection, hosted event-stream protocol selection, standalone Legacy defaults and discovery fallback, and runtime enablement refreshing an existing app-server thread.
GitOrigin-RevId: 640e8e251f0c45e5f4829cc2b73c3082cf42f715
## Why
Saved threads need to resume after a managed daemon restart so active goals can continue without waiting for a client to reconnect.
## What changed
- Consume the recovery snapshot at startup and restore threads in the background through the shared cold-resume path.
- Trigger idle lifecycle work without attaching a client subscription, and leave already-loaded threads untouched.
- Continue recovery after individual thread failures and abort background recovery during shutdown.
## Testing
Extend the daemon restart integration test to verify goal continuation before client reconnection, restored conversation history and tools, idle-thread restoration, and recovery snapshot consumption. Include malformed snapshots and an invalid thread ID.
GitOrigin-RevId: 90e7b8f74ddc0ae327bacde1b2108b9749c65f2a
## What changed
- Atomically save successfully persisted, loaded root thread IDs to `app-server-daemon/loaded-threads.json` during graceful managed shutdown, excluding ephemeral threads and threads pending unload.
- Clear stale recovery state at startup and around daemon lifecycle operations, including explicit stops and fresh starts.
- Probe support for `--managed-daemon` before launching managed app servers, and clear recovery state best-effort when launching older binaries.
- Keep forced shutdown responsive while saving the snapshot and log snapshot failures without preventing shutdown.
## Testing
Add coverage for snapshots after active turns finish, forced shutdown without a snapshot, excluded threads, snapshot write failures, and recovery-state cleanup for stops, fresh starts, and legacy launches.
GitOrigin-RevId: 422dc32b85355510f7e4c57b7540597b47d9f0b2
