Commit Graph
1501 Commits
Author SHA1 Message Date
Winston Howes ed4ca07ba6 Handle credential provider source remapping across config layers (#44241)
## What changed

- Let higher-priority providers in `features.network_proxy.credentials` displace lower-priority providers with overlapping `env` sources, including in profiles. Preserve inherited settings when providers swap sources, and compare environment names case-insensitively on Windows.
- Preserve provider definitions across ordered batch remaps and persist displaced-provider removals without overwriting unrelated sibling updates.
- Validate remapped providers using the credential broker's compilation rules before persisting writes, while allowing incomplete drafts and explicit deletions.
- Omit displaced providers from config origins and report writes overridden by another provider's source ownership.
- Build trusted credential-broker configuration before merging managed layers for project discovery, preserving remapped providers' environment protections.

## Testing

Add unit and config RPC regression tests for source precedence, source swaps, ordered edits, concurrent sibling updates, atomic rejection of invalid remaps, persistence, and override reporting. Add a macOS managed-config regression test for remapped provider bindings during project discovery.

GitOrigin-RevId: b7d402727acf4e5b0f25946db1cf18811f5e2679
2026-09-09 17:45:17 +00:00
jif 0df1daf526 Attach compressed rollouts to diagnostic reports as JSONL (#44175)
## Why

Diagnostic attachment reads assume the queued file path still exists and contains plain bytes. Compressed rollouts can therefore be omitted when only the logical `.jsonl` path is available, or attached as compressed data when a `.jsonl.zst` path is supplied.

## What changed

- Read rollout attachments through a bounded decoder that resolves plain or compressed representations without materializing a durable JSONL file.
- Use canonical `.jsonl` filenames for attachments and app-server report metadata, while preserving filename overrides.
- Apply size limits to decoded bytes and preserve JSONL prefix truncation.

## Testing

Add regression tests for compressed attachments, representation changes after queuing, plain-sibling preference, filename overrides, decoded size limits, truncation, nonregular files, and unrelated `.zst` attachments.

GitOrigin-RevId: b30f7dd08a741b0c99283460a1ce8933d2920ddf
2026-09-09 15:12:19 +00:00
Winston Howes 38cbebaf3f Support configured credential providers across shell snapshots (#44072)
## Why

Credential brokerage must retain trusted destination hints even when shell environment policy hides them from child processes. Snapshot replay also needs to preserve credential aliases when tokens are short or captured dummy values change.

## What changed

- Add `features.network_proxy.credentials` and preserve provider settings when toggling the proxy. Prevent project configuration from overriding providers or their credential and destination environment variables.
- Use provider metadata throughout snapshot capture and replay, and pass hidden destination context to the broker without exposing it in the child environment.
- Rewrite aliases containing short credentials or previously captured dummies, respecting environment filters and explicit overrides.
- Preserve case-distinct `shell_environment_policy.set` keys so Windows credential ambiguity checks survive configuration merging and permission profile changes.
- Restore independent MITM settings when credential brokerage is disabled.

## Testing

Add regression coverage for custom providers, hidden destination hints, Bash and Zsh alias replay, configuration edits and merging, Windows ambiguity handling, and credential protection during approved execution.

GitOrigin-RevId: b2bd935d2d8555be56baf8feb1a8e5b3a0c666bc
2026-09-09 06:04:59 +00:00
vkg-oai 283f34387b Use StartThreadOptions across thread fork APIs (#44043)
## What changed

Pass `StartThreadOptions` through rollout, loaded-history, and prepared forks instead of separate configuration and startup arguments. Replace `options.initial_history` with the fork snapshot while preserving the other supplied startup options, and update app-server and test callers.

Box the app-server's `thread_fork_inner` future to keep the large fork future out of the shared request dispatcher's stack frame.

GitOrigin-RevId: d54eb8b212dedabaf2c5d99d155637cefd7deb7a
2026-09-09 04:07:40 +00:00
alexsong-oai fe52d795c9 Add AWS credential export commands for Amazon Bedrock (#44028)
## What changed

Support `model_providers.amazon-bedrock.aws.credential_export` with `command`, `args`, and `timeout_ms` to supply SigV4 signing credentials from a command's JSON output. Accept both flat credential-process output and nested STS `Credentials` objects.

Cache credentials in memory, refresh before expiration, and share exports across sessions with matching AWS configuration. On recoverable authentication failures, run the optional `aws.auth_refresh` command before exporting fresh credentials, coalescing concurrent recovery attempts.

Bound command execution time and output size, and keep credential values out of errors. Reject combining `aws.credential_export` with `aws.profile`. Bedrock setup and login reject changes while an exporter is configured, preserving configuration and saved credentials.

## Testing

Add coverage for output formats, expiration, credential precedence, caching, concurrent recovery, command failures, and secret redaction. Integration tests verify request signing with rotated credentials, bounded recovery attempts, and setup/login rejection across configuration layers.

GitOrigin-RevId: 4ef799f88ab5e3b2578f8f41a5e56e4f30e2cd81
2026-09-09 03:17:48 +00:00
Eric Traut c3eeaae9a3 Gate new app-server work during graceful shutdown (#43959)
## Why

New client requests and automatic continuations can start more work while the app-server is draining. Shutdown also needs to account for requests still preparing or submitting work before they appear as running turns.

## What changed

- Close a shared admission gate when shutdown begins, rejecting new turn work and thread lifecycle changes with the server-draining error.
- Apply the gate to automatic turn starts, including queued work and goal continuations, and recheck serialized turn requests before execution.
- Wait for admitted requests and running turns to finish, while preserving forced shutdown. Keep reads and `turn/interrupt` available during drain.

## Testing

Add coverage for admission permit tracking, discarded queued requests, forced shutdown, and WebSocket drain behavior, including request rejection, interruption, and suppression of automatic continuations.

GitOrigin-RevId: 1bc108aa00a427cfa41974fa9ec60754c2b968c2
2026-09-09 01:03:42 +00:00
Chris Dong 929389f596 Preserve per-image generation IDs in image generation analytics (#43953)
## What changed

Parse optional `generation_id` values from image API responses and carry the selected image's ID through the image generation tool into analytics events. Keep the ID out of serialized extension items, JSON schemas, and TypeScript types. Responses without an ID remain supported.

## Testing

Add coverage for distinct IDs in multi-image responses and responses without IDs. Extend analytics and app-server tests to verify that the selected image's ID reaches analytics, and item tests to verify that it is omitted from serialization and TypeScript types.

GitOrigin-RevId: 70a600856990140b76fdbda51a0d73b3414338b1
2026-09-09 00:34:45 +00:00
Eric Traut 102e1763b9 Keep app-server thread RPCs active until delegated work completes (#43950)
## Why

Thread startup, running-thread resume, and rollback could outlive their request handlers, allowing connection draining and request serialization to finish too early.

## What changed

- Await thread startup and listener completion for running-thread resume and rollback.
- Release the thread-list permit before waiting for resume completion so the listener can finish rollback responses.
- Release pending rollback waiters when clearing a listener, and discard queued requests when their connection closes.

## Testing

Add coverage for releasing queued requests and rollback waiters, and pipeline resume during rollback to check that both responses complete. Update diagnostics expectations to allow startup to remain in flight after its response is queued.

GitOrigin-RevId: 138156179afbc40de29965820db7fa9cd3669cc7
2026-09-09 00:25:02 +00:00
Eric Traut 7c098d8741 Gate new turn submissions on host shutdown admission (#43943)
## Why

Hosts need to stop new turn-input work during shutdown without consuming pending input or preventing already-running delegated work from finishing.

## What changed

- Add an optional `TurnStartAdmission` extension gate, checked before reserving or starting a new turn. Hosts without a gate retain existing behavior.
- Return `NotSubmittedReason::ServerDraining` for refused starts and surface an app-server error instructing clients to reconnect and retry.
- Keep steering, parent-delegated subagent input, and memory-only mailbox wakeups available during drain, while gating automatic starts.
- Close realtime conversations with an ordered handoff, error, and close event sequence when a handoff is refused during drain.

## Testing

Add regression coverage for rejected input staying out of subsequent requests, persisted queue items remaining available for later starts, delegated agent and review work completing during drain, mailbox wakeups, and realtime handoff error ordering.

GitOrigin-RevId: 03dbdcd71eab200e597c0649e6eb39bd92dbc82f
2026-09-08 23:45:10 +00:00
riley-oai 82d4a98912 Add cancellation for native user-verification RPCs (#43925)
## Why

Canceling an elicitation does not stop a separate native verification RPC. Clients need a way to cancel that work and prevent a canceled proof from being delivered while it waits for outbound queue capacity.

## What changed

- Add experimental `userVerification/cancel` with `{requestId}` to signal cancellation of status, enroll, delete, or verify requests on the same connection.
- Return an empty acknowledgment without waiting for native work to exit. Unknown, finished, unrelated, and other-connection requests are no-ops.
- Retain request cancellation state until outbound capacity is available so canceled proofs are checked before enqueueing. Already enqueued responses and completed effects cannot be retracted.
- Document the API, request ID requirements, and independent lifetimes of elicitations and native verification RPCs.

## Testing

Add coverage for experimental opt-in, parameter validation, connection and request ID isolation, cancellation before native dispatch, repeated cancellation, worker-slot retention, and proof cancellation while waiting for outbound capacity.

GitOrigin-RevId: 03fcb83fcc5fab4169c68668822fc0bbb4970938
2026-09-08 21:48:53 +00:00
Ahmed Ibrahim f31bd3adff Persist provider and auth identity with model catalog caches (#43897)
## What changed

Add a SHA-256 identity derived from provider routing, headers, and authentication scope. Return it with each model catalog response and persist it in `ModelsCacheEntry`. ChatGPT credentials with stable account and user metadata retain the same identity across token refreshes; opaque API credentials contribute to the digest.

## Testing

Add identity tests covering account, user, email, plan, auth mode, provider routing, headers, and API credential changes, plus stability across ChatGPT token refreshes. Update cache tests to include the persisted identity.

GitOrigin-RevId: 3f51c6cabcb01bc03505150a768a61dfe5d6569f
2026-09-08 19:48:37 +00:00
rhan-oai 6515a72db7 Preserve runtime workspace roots across thread resume (#43848)
## Why

Resuming a thread should retain its selected workspace folders, including additional roots and explicit empty selections. Resume overrides also need to survive a subsequent resume when no turn has run.

## What changed

- Persist `runtime_workspace_roots` in startup metadata and thread settings snapshots, separately from explicit environment selections and permission-profile roots.
- Restore roots from the latest snapshot owned by the resumed thread, falling back to owned startup metadata only when no snapshot exists. Honor explicit `runtimeWorkspaceRoots` overrides, retarget the old `cwd` root when `cwd` changes, deduplicate roots, and validate restored paths for the current host.
- Checkpoint effective settings on resume and restored settings after revert. Reload resume configuration if saved workspace roots change during loading.
- Normalize Windows rollout path spellings when matching thread search results, preserving selection of the correct rollout after revert, including compressed rollouts.

## Testing

Add regression coverage for workspace restoration, empty and explicit overrides, foreign paths, compaction and revert, resume checkpoints without recency changes, concurrent settings persistence, and rollout search path matching.

GitOrigin-RevId: d98d9d34dd63934d441120916c61c12b69e7f062
2026-09-08 16:24:38 +00:00
jif 2cbbf0c9b5 Add memory dual writing and v2 readiness reporting (#43827)
## Why

Allow v2 memories to build in the background while the selected memory version continues supplying context, and let clients check whether v2 has enough consolidated data and a valid summary to use.

## What changed

- Add `memories.dual_write`, disabled by default, to run v1 and v2 extraction and consolidation concurrently with separate stores and directories.
- Add the experimental `memory/status` endpoint, returning `v2ConsolidatedThreads` and `v2Ready`. Readiness requires a valid v2 summary and a consolidation thread count meeting `minConsolidatedThreads` (default 20, supported range 1–4096).
- Persist the largest thread count from a successful consolidation across pruning and clear it on memory reset.
- Share v2 summary validation between consolidation and status reporting, and tag memory metrics with `memory_version`.

## Testing

Add tests for independent dual-write outputs, preserving existing notes without importing them into v2, and readiness behavior across consolidation ownership checks, missing summaries, configurable thresholds, thread deletion, and memory reset.

GitOrigin-RevId: 54417cc60bf419062401355c0da8c79119995f61
2026-09-08 14:23:23 +00:00
jif 3f76e88a48 Add configurable memory versions with isolated storage (#43797)
## What changed

- Add `memories.version` with `v1` as the default and `v2` as an opt-in selection.
- Route memory generation, summaries, and retrieval tools through the selected version. Store `v2` artifacts in `memories_v2` and lazily create a separate SQLite database, keeping jobs and outputs isolated while sharing the thread catalog.
- Preserve the initial memory version across extension config updates so summaries and retrieval tools use the same namespace.
- Clear both versions on memory reset and remove thread memory from both stores on thread deletion. Recognize both artifact roots in shell usage telemetry.

## Testing

Add regression coverage for version defaults and validation, independent job claims and outputs, deletion and reset across versions, and shell usage classification for both memory roots.

GitOrigin-RevId: aa799bf87ab6ec10c8f5668213931e57547d080b
2026-09-08 10:55:48 +00:00
jif df522cae16 Limit app-server storage metrics to session directories (#43790)
## What changed

Restrict the startup size scan to `sessions` and `archived_sessions` under
`CODEX_HOME`, and stop emitting the aggregate `directory=codex_home` sample.
Skip missing session directories and inspect scan roots without following
symlinks.

GitOrigin-RevId: c046d097de9b630af68cc9ad70e87cdd63e49319
2026-09-08 10:18:59 +00:00
riley-oai d6489472f3 Enable user verification for the bundled TUI on supported devices (#43715)
## Why

The app server's device-support probe always returned `false`, preventing the bundled TUI from advertising user verification even on supported hardware.

## What changed

Use `native::device_supported` to enable the existing initialization path for in-process `codex-tui` clients that opt into `experimentalApi`. Eligible clients advertise the `userVerification` MCP extension capability and can receive verification requests.

## Testing

Add tests covering initialization eligibility, rejection of responses from non-owning connections, ownership release before disconnected RPC handlers finish draining, and cancellation of pending requests when authentication changes.

GitOrigin-RevId: cdacc026e8f830b3340f2e6f273851c4a3031a7e
2026-09-08 05:57:24 +00:00
jif 98a5cb46b1 Manage synchronous Guardian reviewers through the thread manager (#43570)
## What changed

- Store the shared `GuardianReviewSessionManager` in thread extension data and let the Guardian extension spawn and fork reviewers through `ThreadManager`, independently of async scorer startup.
- Preserve reviewer reuse, concurrent forks, cancellation, inherited environments, and user instructions. Gate managed reviewer startup on parent registration and remove terminated reviewers from the manager.
- Retain the `guardian` subagent identity in saved conversations. Reject resume of live Guardian reviewers and reject client archive or delete of live owner-managed workers with JSON-RPC error `-32600`; allow normal access after the owner releases them.
- Keep standalone reviewer support for inline delegates and remove duplicated extension prompt and configuration code.

## Testing

Add app-server tests covering reviewer reuse and concurrent forks, inherited instructions and prompt cache keys, live resume and removal rejection, saved reviewer discovery and resume after parent shutdown, and strict Guardian assessment inside an inline review.

GitOrigin-RevId: 4f9893c1ade151eacb4c11ffeae3d9e9ec019187
2026-09-07 19:43:10 +00:00
riley-oai ca6fb194b6 Wire app-server user verification RPCs to the native provider (#43568)
## Why

The existing `userVerification/*` handlers always returned unavailability, leaving local clients unable to use the native verification provider.

## What changed

- Dispatch status, enrollment, deletion, and challenge signing through an account-scoped provider. Enrollment creates or reuses a local key; it does not register credentials with a server.
- Restrict enrollment, deletion, and signing to stdio and in-process connections, rejecting WebSocket and remote-control callers before parameter validation.
- Bound native work to one operation per service with a 120-second timeout, and propagate in-process caller cancellation. Recheck connection, cancellation, and authentication state before delivering results, including after waiting for response queue capacity.
- Add device-gated verification capability wiring for the experimental in-process `codex-tui` client, with automatic activation still disabled by default.

## Testing

Add tests for local key reuse and deletion, decoded challenge signing, cancellation, authentication changes during verification and response queuing, concurrent worker rejection, and stdio/WebSocket RPC behavior.

GitOrigin-RevId: 7eac15a5ffb049d27bf8fedcfbae19a49a3f6a3d
2026-09-07 19:34:23 +00:00
riley-oai b7ad941b1f Add user-verification provider abstractions and RPC adapters (#43547)
## What changed

- Introduce `codex-user-verification` with a provider interface for credential status, creation, deletion, and challenge signing. Include typed errors, shared cancellation guards, and hashed account-user key namespaces.
- Add P-256 public-key encoding as unpadded base64url SPKI DER, derive credential IDs from its SHA-256 digest, and redact proof fields in debug output.
- Add app-server helpers to validate challenge and display-text bounds and map provider errors to typed RPC errors without exposing provider diagnostics.

The platform implementation reports verification as unsupported. App-server requests still return typed unavailability, with the message updated to mention build or account availability.

## Testing

Add tests for credential encoding and signature verification, invalid curve points, cancellation across guard clones, stable and distinct account namespaces, and invalid challenge or display values. Update the app-server unavailability test for the revised message.

GitOrigin-RevId: fe4a4eb37c68d7fdc547704e76aa257abf3e9c81
2026-09-07 18:43:20 +00:00
jif 4f1a2bb5ff Preserve fork runtime versions without loading full model context (#43545)
## Why

A fork cutoff can exclude the `TurnContext` that records the source's multi-agent runtime version. Recovering that version should not require loading the source's full model context.

## What changed

- Preserve `multi_agent_version` in fork session metadata before applying the cutoff. If absent, scan backward for the newest version-bearing `TurnContext`, respecting inherited segment boundaries and stopping once resolved.
- Load the latest model context for paginated forks only when approval or permission settings need to be restored.

## Testing

Add regression tests covering stored-version precedence, early termination without reading older segments, and version recovery within inherited segment cutoffs.

GitOrigin-RevId: 00e66bcce6f4092805e273cde99bd50f304fb39e
2026-09-07 18:34:49 +00:00
jif cc737efd65 Preserve the multi-agent version when forking at a turn cutoff (#43540)
## Why

A fork cutoff can remove the only `TurnContext` recording the source thread's selected multi-agent version. Forking before the first turn must preserve that version, including when the child is resumed before its first turn.

## What changed

Recover the version from the untrimmed source history or loaded parent, independently of permission overrides, and carry it into the fork's session metadata for `last_turn_id` and `before_turn_id` cutoffs.

## Testing

Add regression coverage for forks before the first turn across legacy and paginated history modes, with loaded and unloaded parents and explicit permission overrides. Verify that the child persists `MultiAgentVersion::V2` and still uses the `collaboration` tools after restarting and resuming.

GitOrigin-RevId: d7e30cf8bfdeb4f755fefab3d1d0884964d7c977
2026-09-07 18:17:39 +00:00
jif b1205c12d5 Set recursion_limit to 256 for app-server, exec, and TUI (#43519)
GitOrigin-RevId: 62707b30a8a786143739300f307875e615d81acc
2026-09-07 17:09:04 +00:00
jif ce5c4133bd Route MCP elicitations through the shared approval decision path (#43447)
## What changed

- Use `decide_approval` for MCP elicitations, carrying the effective approval policy, reviewer, and synchronous-review requirement into the decision.
- Preserve unsupported form and URL elicitations for user review.
- Use `computer_use_review_required()` for review evidence, session policy, and turn metadata so model policy takes precedence over the legacy flag.
- Derive strict-review notifications from each assessment's review reason.

## Testing

Add coverage for model policy precedence, user and full-access modes, sensitive elicitations, independent code-mode and nested-tool policies, cached score reuse, and user review of unsupported elicitations.

GitOrigin-RevId: d0a9c40572dca7b3dbf876230d2162b72728084d
2026-09-07 12:04:27 +00:00
jif e1eb98461c Route approvals through the extension decision API (#43432)
## What changed

- Let approval extensions choose between cached approval, synchronous review, and a user prompt for tool and permission requests, while core enforces mandatory Guardian and fresh-review requirements.
- Carry an optional `review_reason` on Guardian assessment events and use it to trigger strict-review notifications, retaining the fallback for older events.
- Require synchronous review when cached evidence has an unusable encrypted parent compaction.

## Testing

Add regression coverage for manual prompts and cached approvals with non-UTF-8 working directories. Update approval contributors in existing tests to use the decision API.

GitOrigin-RevId: a4e66416070bdaa881daa41429c49021629f44c1
2026-09-07 11:07:28 +00:00
riley-oai 555b82afa9 Add opt-in MCP user-verification transport (#43352)
## Why

Device-authenticated verification needs an app response outside automated approval and review. Previously, MCP user-verification requests were always cancelled.

## What changed

- Add typed `openai/userVerification` elicitations carrying a title, description, and challenge through core and app-server.
- Route verification to one connection enabled by trusted host activation. Restrict responses to that owner, exclude requests from replay, and cancel on disconnect or authentication changes, including account switches away and back.
- Return proofs in `content`, discard response metadata, and cancel malformed acceptances. Suppress verification response logging and analytics, and send only a generic verification notice to realtime.
- Keep the mode experimental and exclude it from stable schema exports. Capability advertisement remains disabled, and the TUI cancels verification requests.

## Testing

Add coverage for owner isolation, disconnect and authentication races, proof response handling, automated-review bypass, inactive-host cancellation, stable schema filtering, and realtime payload exclusion. Update the MCP integration test to verify that an activated request holds the tool until the client responds.

GitOrigin-RevId: c8c7b6691a3f7756682bbcca9def1df0d1feb906
2026-09-07 04:33:22 +00:00
Eric Traut 455318c202 Replace Windows app-server shutdown files with socket requests (#43308)
## What changed

Route managed Windows app-server shutdown through `/daemon/shutdown` on the local control socket. Require the server's PID and acknowledge it before triggering shutdown through the existing drain logic. Enable the endpoint only for managed Windows launches via `CODEX_DAEMON_SHUTDOWN_SOCKET`.

Watch running-turn changes whenever shutdown is requested so socket-triggered shutdown can finish draining. Keep the updater's file-based shutdown mechanism and retain forced termination as the manager's timeout fallback.

## Testing

Add a transport test covering rejection of unmanaged shutdown requests and mismatched PIDs, plus acknowledgment before emitting the shutdown event.

GitOrigin-RevId: 3e95dc1914f61e8a131f9b6fd56b6c63688d1744
2026-09-07 00:00:23 +00:00
riley-oai ad931a45b2 Add experimental user verification API contracts (#43265)
## What changed

Add `userVerification/status`, `userVerification/enroll`, `userVerification/delete`, and `userVerification/verify` behind the `experimentalApi` capability. Define request, response, proof, and typed error contracts, export their schemas, and document the API.

All four methods currently return `unavailable` with reason `providerUnavailable`; native verification operations are not implemented by this change.

## Testing

Add tests for experimental opt-in, typed provider unavailability, readiness serialization, and rejection of mismatched error reasons and native diagnostic payloads.

GitOrigin-RevId: a858ab41523c5acec7dbf3cfa7fcab693ac44a8c
2026-09-06 18:39:32 +00:00
Alex Daley 2cfee7de25 Refresh live thread tools through app/installed (#43039)
## Why

Calling `app/installed` with `threadId` and `forceRefresh: true` refreshed a separate runtime snapshot without updating the thread's tools for subsequent turns.

## What changed

Use the thread's current configuration and refresh its live app tools when a thread is specified. Account for the refreshed snapshot's model-visible tools when reporting `callable`. Requests without `threadId` continue to use a separate runtime for refreshes.

## Testing

Add integration coverage verifying that refreshed tools replace previous tools in subsequent model requests and can be called, and that a failed refresh preserves the last working tools. Extend thread configuration coverage to include forced refreshes.

GitOrigin-RevId: fc13e28a59da00af470cf25c0cde356504e1575b
2026-09-05 15:30:18 +00:00
jif a7a4321593 Preserve the resolved multi-agent version when reverting threads (#43000)
## Why

Reverting a paginated thread can remove the turn context that records its resolved multi-agent version. Preserve that version so a model-selected V2 thread keeps its collaboration tools after reload or a server restart.

## What changed

Pass the live thread's `multi_agent_version` into the thread store and persist it in the replacement rollout's session metadata. When no live version is supplied, retain the existing metadata value. Document this guarantee for `thread/revert`.

## Testing

Add regression tests for model-selected V2 across live reload and cold resume, plus metadata preservation for `V1`, `V2`, and `Disabled` across repeated reverts.

GitOrigin-RevId: bd7d4d76a50d23da16caa2a0631acf10bfa49629
2026-09-05 12:58:26 +00:00
faizan-oai 3921a30d6b Persist Daybreak preferences in thread metadata (#42854)
## Why

Clients need a per-thread Daybreak toggle that survives restarts and can be
restored on resume without changing the access program of an active or future
turn.

## What changed

- Add experimental `daybreakEnabled` support to `thread/metadata/update` and
  expose the saved value on thread responses.
- Store the preference in SQLite, including for threads without a first turn,
  and preserve it through reads, resumes, reconciliation, and restarts.
- Copy the preference when forking a thread while keeping subsequent updates
  independent.
- Keep `daybreakEnabled` separate from the per-turn `cyberAccessProgram` field;
  app-server does not derive one from the other.

## Testing

- Cover persistence across restarts, cold reads, reconciliation, and forks.
- Verify metadata updates do not alter the access program of active or later
  turns.

GitOrigin-RevId: bcf987a9fcd7b0ac8a88b1c8f0df06b33ed8ad6e
2026-09-04 21:17:25 +00:00
efrazer-oai 8e4b7d31de Use jemalloc for Linux musl binaries (#42850)
## What changed

- Configure the CLI and app server to use `tikv-jemallocator` on
  `x86_64-unknown-linux-musl` and `aarch64-unknown-linux-musl`.
- Keep the dependency and global allocator selection scoped to those targets.

GitOrigin-RevId: 93c54c90d9acb7e48edffd032cd8ec685a782210
2026-09-04 20:48:16 +00:00
iceweasel-oai 773f0b081d Preserve executor paths in Guardian approval reviews (#42838)
## Why

Guardian approval actions can contain paths from a remote executor whose path convention differs from the host, such as Windows paths reviewed on a POSIX host. Converting those paths to host-native absolute paths prevents the action from being reviewed.

## What changed

- Render command working directories using the executor's reported path convention, and preserve URI-backed paths for attribution.
- Carry foreign command and patch paths through Guardian events and app-server schemas as legacy path strings.
- Bound remote plugin attribution within the overall review deadline and reject Guardian action payloads that exceed the review byte limit.

## Testing

- Cover Windows and POSIX executor path rendering, foreign patch paths, protocol round trips, oversized payload rejection, and remote Guardian review context.

GitOrigin-RevId: 38be0fcdac897139519e74e077eb5cb4f8f8017e
2026-09-04 19:56:31 +00:00
nmccormack-oai 0f64d70808 Expose managed WebMCP policy through the app server (#42823)
## What changed

- Parse the optional `[browser_use].allow_webmcp` boolean from managed requirements and preserve requirement-layer precedence.
- Return the policy as `browserUse.allowWebmcp` from `configRequirements/read`, including explicit `true`, explicit `false`, and `null` when omitted.
- Update the generated JSON and TypeScript protocol schemas.

## Testing

- Cover parsing, invalid values, layered overrides, and app-server response serialization.

GitOrigin-RevId: a3fd7d1a6f838bb3ab0ac2a644409101a2338ca6
2026-09-04 18:30:26 +00:00
alishobeiri-oai 86b1b359cf Enable staging login issuer overrides in packaged builds (#42811)
## Why

Packaged clients need to pair a staging OAuth client ID with the matching
issuer. The issuer override was previously limited to debug builds.

## What changed

- Apply `CODEX_APP_SERVER_LOGIN_ISSUER` in all builds when it contains a
  non-empty value.
- Keep `CODEX_APP_SERVER_DEV_OPEN_APP_URL` debug-only.

## Testing

Exercise the complete app-server OAuth flow with the issuer and client ID
overrides, including authorization, token exchange, and login completion.

GitOrigin-RevId: 13d290b9dae689cd811361b1b549953a3b52db42
2026-09-04 17:51:32 +00:00
Chris Hayduk c9fac4dd5a Avoid holding metadata permit during cold resume config load (#42773)
## Why

Cold `thread/resume` configuration loading can call back into the host. Holding the global metadata permit during that work blocks unrelated thread metadata updates and MCP requests.

## What changed

- Release the metadata permit while loading configuration for a cold resume.
- Reacquire the permit and reload the resolved thread history before startup.
- Reload configuration when persisted metadata, settings, or the history working directory changed during the unlocked interval.
- Rejoin a thread that another request resumed concurrently, and avoid reopening threads that were archived or deleted.

## Testing

Add coverage for unrelated metadata and MCP requests during a blocked config load, concurrent resume mutations, and the extra history read required for non-local thread stores.

GitOrigin-RevId: 8cbd3868eeff84968765b1e3dbc7590ebe5fa892
2026-09-04 14:23:27 +00:00
jif d13aeb77ea Allow trusted symlinks beneath CODEX_HOME on macOS (#42716)
## What changed

- Add the macOS-only `allow_symlinked_codex_home` user setting. When enabled in the execution host's `$CODEX_HOME/config.toml`, writable roots at or beneath that home may traverse symlinks.
- Keep the exception disabled by default and prevent project config, command-line overrides, and ignored user config from enabling it. Other writable roots remain subject to symlink checks.
- Propagate the resolved setting through local, interactive, and exec-server sandbox paths, including `CODEX_HOME` aliases.
- Explain the opt-out in symlink rejection errors, including that it trusts targets outside `CODEX_HOME` and targets that change between commands.

## Testing

- Add macOS coverage for shell commands, patches, filesystem helpers, process execution, and interactive startup with enabled, disabled, aliased, and out-of-scope homes.

GitOrigin-RevId: 99fcdf611200c9e1b7713cf06f7fdea5bfa7f089
2026-09-04 10:12:03 +00:00
ningyi-oai ea2046f36d Cancel remote control enrollment on stdio shutdown (#42668)
## Why

A pending remote control enrollment could prevent the app server from exiting
after stdio EOF, leaving resources such as thread writers held by the process.

## What changed

- Give remote control its own child shutdown token and cancel it before draining
  RPCs when the stdio connection closes.
- Interrupt enrollment requests that require network access after shutdown has
  begun, while still allowing in-memory or persisted enrollments to be enabled
  and durably saved.

## Testing

- Cover stdio shutdown during a blocked enrollment and verify that another app
  server can acquire the released thread writer.
- Cover durable enablement after shutdown with in-memory, persisted, and missing
  enrollments.

GitOrigin-RevId: ef9ab49672f273a4cf8257188454a154c03088bd
2026-09-04 03:40:37 +00:00
Krish Chainani 03467026f2 Add an injectable attachment store to ThreadManager (#42634)
## What changed

- Add the `codex-attachment-store` crate with storage-neutral attachment metadata, references, errors, and an asynchronous persistence interface.
- Provide an inline implementation that preserves attachment bytes as media-typed base64 data URLs.
- Inject the store into `ThreadManager`, expose it to consumers, and retain inline storage as the default for existing entry points.

## Testing

- Verify inline storage round-trips binary, text, PNG, and JPEG data.
- Verify attachment debug output redacts URLs while retaining file IDs.

GitOrigin-RevId: 7688dcd3c89d7540ed2398f3e7c63881fbfcda97
2026-09-03 23:20:54 +00:00
yansenzhou-oai f84c9776dc Deprecate detached review delivery (#42602)
## What changed

- Emit a connection-scoped `deprecationNotice` when `review/start` uses
  `delivery: "detached"`, including when validation later rejects the request.
- Preserve detached review behavior while directing callers to use `thread/start`
  followed by an inline review for a separate review thread.
- Document the deprecation and migration options in the app-server protocol and
  README.

## Testing

- Cover the notice for accepted and rejected detached reviews.
- Verify that omitted, null, and inline delivery do not emit the notice.

GitOrigin-RevId: 4234a09d2bb7ef8053091580175dc8cbe8d7512c
2026-09-03 19:36:11 +00:00
victor-openai 8f31b64c7f Report MCP tool discovery errors in server status (#42598)
## Why

An empty tool map does not distinguish a successfully returned empty catalog from a server whose startup or tool discovery failed.

## What changed

- Add nullable `toolsError` to each `mcpServerStatus/list` entry when no catalog is available because startup or tool discovery failed.
- Keep `toolsError` null for returned catalogs, including cached and empty catalogs, and continue returning healthy servers when another server fails.
- Update the protocol schemas and generated TypeScript type.

## Testing

- Extend the app-server status integration test with a broken MCP server and verify its error without losing the healthy server's inventory.

GitOrigin-RevId: 30b4ca4d9a45cec6998f5f626d3fddbee90a525d
2026-09-03 18:36:58 +00:00
victor-openai 2387310b52 Reload user config after local plugin installation (#42593)
## Why

Loaded threads can retain their previous configuration after a local plugin is
installed, preventing the plugin's bundled MCP servers and pending user-config
changes from taking effect in the current session.

## What changed

- Reload user configuration for loaded threads after installing a local plugin.
- Refresh MCP and hook runtimes only after the new configuration is applied.
- Keep installation successful if configuration reload fails, while logging the
  failure.

## Testing

- Verify an installed plugin's MCP tool can be called from a thread that was
  started before installation.
- Update the hook runtime test to verify installation applies a staged hook
  configuration change to the loaded session.

GitOrigin-RevId: 63f5a5c7f16303e51cf940e8d9dc3b45c50ae2a9
2026-09-03 18:20:59 +00:00
iceweasel-oai 7a7c188682 Preserve target-native paths in command approvals (#42577)
## What changed

- Pass the selected executor's `PathUri` through user command approval requests instead of converting the working directory to a host-native path.
- Make native-path permission helpers explicitly local and require executor-aware permission transforms to receive a `FileSystemSandboxPolicyContext`.
- Cover approved remote commands to verify that the approval request reports the selected remote working directory and execution resumes after approval.

GitOrigin-RevId: 0aa3042f2d7594af6c7d0abf31d7f99cf67d5556
2026-09-03 16:21:10 +00:00
Can Sar 728cb12fe5 Expose thread originators through the app-server API (#42458)
## What changed

- Add the creation-time `originator` to app-server thread responses and `thread/started` notifications.
- Persist originators in thread metadata and preserve the first recorded value across list, read, resume, rollout, and SQLite paths.
- Add an `originators` allowlist to `thread/list` for hosted backends. The local app-server accepts omitted or empty values but rejects nonempty filters.

## Testing

- Cover originator persistence across server restarts and list, read, and resume requests.
- Verify local `thread/list` handling for nonempty, omitted, null, and empty originator filters.
- Heap-allocate large TUI dispatcher futures in affected tests to keep them within the Windows test-thread stack.

GitOrigin-RevId: 73ad6e61b8fdd2d93a22d1f971723a19ec7be3fc
2026-09-03 06:02:25 +00:00
acrognale-oai b27a6321fa Expose managed application network requirements (#42417)
## What changed

- Add `application.network` managed requirements with exact-domain allow/deny
  rules, default-enabled behavior, domain normalization, and normal managed TOML
  precedence.
- Return the policy separately from agent network requirements through the
  experimental `configRequirements/read` API. The endpoint reports the policy
  but does not enforce it.
- Export the new protocol types and schemas, and document the TOML format.

## Testing

- Cover parsing, validation, normalization, layered precedence, and cloud
  requirement composition.
- Verify app-server responses, defaults, separation from agent policy, and
  rejection of invalid domains.

GitOrigin-RevId: 563eeed296d9748430b819797204a44a8db92f3b
2026-09-03 02:09:10 +00:00
Anton Panasenko 2b554fd3f9 Expose loaded thread environments in app-server responses (#42386)
## What changed

- Add the experimental `Thread.environments` field with each selected environment's ID, working directory, and runtime workspace roots.
- Populate the field from live thread state in start, resume, read, list, and unarchive responses. Use `null` for unloaded threads and an empty list when a loaded thread has no environment selection.
- Document that the field reports selection rather than connection status and does not affect executor selection or resume behavior.

## Testing

- Cover selection updates, unloaded and resumed threads, loaded pathless unarchives, and clients that subscribe after environment connection notifications.

GitOrigin-RevId: a6daa06aff7089d7c5a1e4c7d03109b41f12fa3c
2026-09-02 23:41:14 +00:00
guinness-oai e1d0ef995f Make app-server realtime sessions always available (#42377)
## What changed

- Remove the per-thread `RealtimeConversation` feature check when starting a realtime session.
- Retain `features.realtime_conversation` as a removed compatibility setting that has no effect, even when set to `false`.
- Document the always-available behavior for `thread/realtime/start`.

## Testing

- Cover realtime startup on forked and cold-resumed threads with the legacy setting absent, disabled, or enabled.

GitOrigin-RevId: d9cd9aa3898d1c2efb9414a8f40c86be8951e210
2026-09-02 22:30:30 +00:00
dhruvgupta-oai 5037919777 Add Luna Reserve usage fallback to the TUI (#42372)
## Why

When ordinary included usage is exhausted, eligible users need a way to keep working with the backend-provided Luna Reserve quota and return to their previous model once ordinary usage recovers.

## What changed

- Automatically switch eligible TUI tasks to Luna Reserve after an authoritative account usage read, preserving the prior model and reasoning effort per task.
- Restrict model selection while on Reserve to its supported reasoning levels, keep queued turns on the accepted model, and restore the saved model after a fresh read confirms recovery.
- Surface Reserve usage in the composer and `/status`, and expose `normalModelSlug` in app-server rate-limit snapshots so clients can use the associated model's display metadata without changing the request model.
- Poll account limits more frequently near exhaustion and retain compatibility with app servers that only accept the legacy null request parameters.

## Testing

- Added coverage for Reserve entry, queued-turn handling, task reconstruction, recovery authorization, account changes, model selection, usage rendering, and banner dismissal.

GitOrigin-RevId: 46a435e9531051f8cec3f6a46c4b9f7cfa479747
2026-09-02 21:50:51 +00:00
Eric Traut 10aca93f18 Support graceful daemon shutdown on Windows (#42364)
## Why

Detached Windows processes cannot receive console signals, so app-server daemons
need another way to enter the existing graceful and forced shutdown flow.

## What changed

- Watch the path in `CODEX_DAEMON_SHUTDOWN_FILE` for a request addressed to the
  current process, and consume only a matching PID.
- Race daemon shutdown requests with Ctrl-C on Windows while leaving unmanaged
  launches on the existing console-signal path.
- Exercise the SIGTERM-equivalent graceful and forced WebSocket shutdown cases
  on Windows.

## Testing

Added unit coverage ensuring inherited control paths and malformed requests
cannot consume another process's shutdown request.

GitOrigin-RevId: 426a3c12edc344802395d4d26288f2bb015c484f
2026-09-02 21:20:03 +00:00
dhruvgupta-oai 577a4fcd06 Extend rate limit reads with usage capabilities (#42358)
## What changed

- Accept optional `account/rateLimits/read` capabilities for Luna Reserve support
  and lightweight background polling while preserving omitted and `null` params.
- Forward the Luna Reserve capability only for eligible ChatGPT sessions, and let
  lightweight polls skip the separate reset-credit detail request.
- Return the backend's `ordinaryUsageAllowed` decision only when its account and
  user identity match the active session.

## Testing

- Cover capability defaults, eligible and restricted authentication modes,
  lightweight polling, identity filtering, and backend permission handling.

GitOrigin-RevId: f407a3ae1e70e411fdf245f072a16e453f59cd87
2026-09-02 21:01:04 +00:00
johnl-oai 830363bd7c Add experimental Windows sandbox service provisioning (#42353)
## What changed

- Add the default-off `windows_sandbox_service` feature and expose it through
  app-server experimental feature enablement.
- When enabled, attempt service provisioning during elevated Windows sandbox
  setup, using the effective network proxy ports and listener roles. Continue
  through the existing setup path when the service is unavailable or the
  configuration is unsupported.
- Report unsupported Codex home drives as service unavailability so the client
  can fall back to the elevated helper.

## Testing

- Add a Windows-only unit test covering HTTP and SOCKS listener derivation from
  the effective proxy configuration.

GitOrigin-RevId: 40b119cf51f84e5d0e94d6a0a8d5b506d1123526
2026-09-02 20:30:45 +00:00