Commit Graph

9386 Commits

Author SHA1 Message Date
felixxia-oai
3711943d11 Parse model annotations from skill frontmatter (#38467)
## What changed

- Add an optional `model` field to parsed and loaded skill metadata.
- Recognize `model: luna` while ignoring unsupported model values without
  preventing the rest of the skill metadata from loading.

## Testing

- Cover supported, absent, unsupported, and repaired frontmatter model values.

GitOrigin-RevId: 376b65555e81d29a5eae93cc4c2633aacf7cd7c8
2026-08-14 00:54:45 +00:00
Owen Lin
c6dee5f49f Preserve thread subscriptions across revert reloads (#38463)
## Why

The connection that requested `thread/revert` may close while the thread is
being reloaded, but the replacement listener still needs to serve the thread's
existing subscriptions.

## What changed

Restart the listener task from the preserved thread state after a paginated
thread reload instead of attaching it through the requesting connection.

GitOrigin-RevId: 603ec3331c59bdde48faa2f4cb0fd1032ec8dbd8
2026-08-14 00:27:39 +00:00
sayan-oai
535795f7d1 Centralize turn environment selection state (#38461)
## What changed

- Store `TurnEnvironmentSelection` directly on each resolved `TurnEnvironment`
  instead of copying its environment ID, working directory, and workspace roots
  into separate fields.
- Update environment resolution, tool execution, approvals, and related tests to
  access selection state through the retained value.

GitOrigin-RevId: ab723d21e112b8af5bcaf1f772a5e376553312bc
2026-08-14 00:22:54 +00:00
iceweasel-oai
18bbb585e7 Add an AbsolutePathBuf conversion for FileSystemPath (#38460)
## What changed

Implement `From<AbsolutePathBuf>` for `FileSystemPath` and use the conversion
when constructing concrete filesystem permission paths.

GitOrigin-RevId: 244bcbd0c3f76cd87cc1240458fcac6c9ef0a8e3
2026-08-14 00:18:29 +00:00
efrazer-oai
9341b38310 Add experimental thread queue APIs to app server (#38456)
## What changed

- Add experimental `thread/queue/add`, `list`, `update`, `delete`, `reorder`, and `start` requests for persistent queued user submissions.
- Automatically dispatch queued submissions in FIFO order after completed or failed turns, while leaving the queue paused after interruption.
- Emit `thread/queue/changed` notifications and expose paginated queue contents with stable submission and client message IDs.
- Export the new protocol types through the generated JSON Schema and TypeScript bindings.

## Testing

- Add app-server integration coverage for capability gating, CRUD, pagination, capacity limits, notifications, automatic dispatch, cold-thread resume, interruption, and explicit queue starts.

GitOrigin-RevId: 89caf5577192199bda77cf6c372a59d26cdd910e
2026-08-13 23:38:02 +00:00
Ankush Gupta
4d9f3021c8 Include node_repl images in Guardian review evidence (#38454)
## What changed

- Preserve valid image content from completed `node_repl` Code Mode responses alongside text evidence for Guardian reviews.
- Enable multimodal evidence for models that require automatic `node_repl` review, or when both `guardian_enhanced_node_repl_transcripts` and `guardian_node_repl_transcript_images` are enabled.
- Bound retained and rendered evidence, deduplicate images already present in review history, and fall back to text-only evidence when the reviewer lacks image support or prompt capacity.
- Keep review evidence out of the parent turn input.

## Testing

- Cover feature gating, mixed text and image ordering, truncation and eviction, unsupported reviewers, prompt pressure, image detail normalization, and reused review sessions.

GitOrigin-RevId: a3e482402f7b3484401b231dadc662e6e3504fdf
2026-08-13 23:29:52 +00:00
Adam Perry @ OpenAI
1b4ea8b3be Add structured telemetry for response retries (#38452)
## What changed

- Emit trace-safe `codex.retry` events immediately before retry delays, including the attempt number, selected delay, retry layer, and operation.
- Cover HTTP requests, sampling streams, remote compaction, and sampling connection recovery. Track connection-recovery attempts separately from the stream retry budget.
- Add integration coverage for retry timing and terminal behavior across HTTP, SSE, WebSocket, and remote-compaction paths, including rate limits, overloads, connection failures, and `Retry-After` inputs.

GitOrigin-RevId: dae38900a0579cf8ba062c3f3d90ee61851c1c99
2026-08-13 23:13:37 +00:00
Adam Perry @ OpenAI
813dc5f08d Embed the Windows sandbox setup manifest in Bazel builds (#38450)
## Why

`rules_rust` drops the build script's per-binary linker directives, so Bazel
builds can omit the `asInvoker` manifest from the Windows sandbox setup helper.

## What changed

- Add per-binary compile data and Rust flags to `codex_rust_crate` so linker
  inputs remain scoped to the setup helper.
- Embed the manifest directly for MSVC builds and compile it into a resource
  with hermetic LLVM tooling for GNU/LLVM cross-builds.
- Disable the redundant build script under Bazel and avoid duplicating binary
  runfiles in integration test data.

## Testing

Add a Windows integration test that loads the setup executable's manifest
resource and verifies that it requests `asInvoker` execution with UI access
disabled.

GitOrigin-RevId: a77e7e627ee43810f5eaf7701bb4909bf855216b
2026-08-13 23:04:38 +00:00
Shijie Rao
5cc65ecb98 Expose model upgrade retirement times (#38449)
## What changed

- Parse the optional `retirement_at` RFC 3339 value from model upgrade metadata, treating missing, null, or malformed values as unknown.
- Expose known retirement times from `model/list` as nullable Unix timestamps in `upgradeInfo.retirementAt` and preserve them when converting app-server models back into model presets.
- Update the generated protocol schemas and app-server documentation.

## Testing

- Cover absent, null, valid, and malformed catalog values.
- Verify `model/list` serialization and app-server model conversion for known, missing, and out-of-range timestamps.

GitOrigin-RevId: 969baf9f5b012997f460fb4611ba63c963ee658c
2026-08-13 22:59:54 +00:00
willwang-openai
1da59ad257 Support per-server MCP OAuth callback ports (#38448)
## What changed

- Add `oauth.callback_port` to MCP server configuration and preserve it when
  serializing configuration edits.
- Accept `oauth.callbackPort` from plugin MCP declarations and skill dependency
  metadata.
- Prefer the server-specific callback port over `mcp_oauth_callback_port` for
  CLI login, app-server, plugin installation, executor, and skill dependency
  OAuth flows.

## Testing

- Cover configuration parsing, serialization, and fallback behavior.
- Verify plugin, executor, and skill OAuth registrations use their configured
  callback ports instead of the global port.

GitOrigin-RevId: 7f65e5e7869358307e49779f1b75e8672b607736
2026-08-13 22:42:12 +00:00
Eric Traut
ca83f7908c Add running-task exit choices to local daemon sessions (#38447)
## What changed

When `Ctrl-C` is pressed with an empty composer while a task is running in a local daemon session, show a menu that lets the user:

- cancel the task and stay in Codex;
- exit Codex while leaving the task running; or
- stop the task and exit Codex.

Do not offer background execution for side-thread tasks or when follow-up messages are queued. Preserve existing `Ctrl-C` behavior for non-daemon sessions, drafts, paste bursts, MCP startup, and returning from an active side thread.

## Testing

Add TUI tests for each exit action, menu dismissal, side threads, queued follow-ups, composer input, MCP startup, and non-daemon sessions.

GitOrigin-RevId: 539c33d3a4ff288a015bddbe9465d2bbdbe018d0
2026-08-13 22:38:46 +00:00
rka-oai
6344a655a5 Refresh current-time reminders for full-history subagents (#38446)
## What changed

- Exclude current-time reminder developer messages when copying parent history into a full-history subagent.
- Keep the child's newly generated reminder, preventing inherited reminders from accumulating while preserving the rest of the forked context.

## Testing

- Extend the full-history V2 spawn test to verify that two reminders in the parent become one fresh reminder in the child request.

GitOrigin-RevId: fb61c72f7f0d61d1068f2c599a8b8caf1788b7e2
2026-08-13 22:30:59 +00:00
rka-oai
bff03ecce5 Retain client developer messages across context compaction (#38445)
## Why

Client-authored developer instructions should remain available after a context
window is compacted when `retain_client_developer_messages` is enabled.

## What changed

- Preserve annotated client-authored developer messages during remote compaction
  v2 and local token-budget context resets.
- Apply the existing retained-message token budget when carrying those messages
  into the new context window.

## Testing

- Cover enabled and disabled retention for remote compaction v2, manual
  token-budget compaction, and mid-turn automatic compaction.

GitOrigin-RevId: 4cb3782cb86ef46458413a17a3255d0016fd675f
2026-08-13 22:21:18 +00:00
rka-oai
3ba52d6075 Tag current time reminders in model context (#38443)
## What changed

- Wrap injected current time reminders in `<current_time_reminder>` tags.
- Keep direct `clock.curr_time` tool output and log previews as plain text.

## Testing

- Update core and app-server coverage for tagged reminders and untagged tool output.

GitOrigin-RevId: ad27f1fa10cca7f83d1ac731e01255320bb60f47
2026-08-13 21:53:52 +00:00
felixxia-oai
53eaa297e5 Give Guardian V2 full tool action context (#38441)
## Why

Guardian V2 needs the requested action and its conversation context to assess
risk; a tool name and call ID alone do not describe what the tool will do.

## What changed

- Expose the original, pre-hook `ToolPayload` to tool lifecycle contributors.
- Build Guardian V2 classifier input from the bounded conversation transcript
  and a structured planned-action object containing the tool name and arguments.
- Warn and skip classification if the planned action cannot be serialized.

## Testing

- Verify lifecycle contributors receive tool arguments.
- Verify Guardian V2 sends transcript history and planned-action JSON to the
  classifier.

GitOrigin-RevId: 28266ef7c1d2267ba705fcfbd9be4ef48e64e104
2026-08-13 21:49:32 +00:00
Owen Lin
4343b2bdc4 Add app-server support for reverting paginated threads (#38440)
## What changed

- Add the experimental `thread/revert` request, which replaces a loaded paginated thread's durable history with the prefix before `beforeTurnId` while preserving the thread ID.
- Interrupt any active turn, reload the replacement history without unloading the thread, preserve mutable thread settings, and emit `thread/reverted`.
- Return backward pagination cursors for the retained turns and items, reject stale rollout paths after a revert, and document that local file changes are unaffected.

## Testing

- Cover history replacement, pagination, stale paths, missing turns, subsequent turns, active-turn interruption, and preserved thread settings.

GitOrigin-RevId: 435a8163ad4f310cc47219b436f6bdde21f2b83a
2026-08-13 21:45:02 +00:00
viyatb-oai
1992f8c018 Preserve approval policies for auto-reviewed models (#38439)
## What changed

- Keep the configured `approvalPolicy` when a model in
  `auto_review.required_on_models` selects the `auto_review` reviewer.
- Continue downgrading full-access sessions to workspace-write and rejecting
  incompatible reviewer overrides.

## Testing

- Cover supported approval policies across thread start, settings updates,
  turn-time model switches, resume, and fork flows.

GitOrigin-RevId: 2bd3e2dcd46f3cadeb2fad20222cf8917c267208
2026-08-13 21:40:42 +00:00
Celia Chen
b87327f4e5 Add rustls fallback for local MCP HTTP requests (#38436)
## Why

Local MCP requests can fail when the platform TLS backend cannot negotiate a
protocol version with an HTTPS endpoint.

## What changed

- Retry replayable local MCP requests once with rustls after a recognized TLS
  protocol-version negotiation failure. Keep certificate, timeout, and unrelated
  connection failures on the existing error path.
- Remember successful fallback per HTTPS origin and outbound route, while keeping
  the platform TLS backend as the default for other destinations.
- Share the fallback-enabled client across local MCP resolution, CLI login, and
  OAuth discovery while preserving remote environment HTTP clients.

## Testing

Added coverage for platform-specific error detection, request replay, cached
fallback reuse and isolation, non-replayable requests, redirects, and remote MCP
client selection.

GitOrigin-RevId: 39a2d96fdb2ea0e51df14f652ba2a953d24e69a1
2026-08-13 21:13:07 +00:00
Ankush Gupta
93327c852a Gate Node REPL Guardian guidance on model metadata (#38432)
## What changed

- Use the specialized Node REPL approval guidance only when the parent turn's
  model sets `node_repl_auto_review_required`.
- Keep Node REPL JavaScript requests on the generic approval prompt otherwise.
- Cover both prompt paths in the Guardian tests.

GitOrigin-RevId: e3eb89a59cc74fe2b53bb1c3f29a30d450e173de
2026-08-13 20:43:13 +00:00
willwang-openai
f898ebcafd Route curated plugin catalogs by authentication mode (#38429)
## Why

The model provider does not reliably identify which curated plugin catalog is
available. ChatGPT authentication can be used with a custom provider, while an
unauthenticated session should use the API-compatible catalog regardless of its
provider.

## What changed

- Select the ChatGPT curated catalog only for authentication modes that use the
  Codex backend; use the API curated catalog for API-key and unauthenticated
  sessions.
- Initialize standalone plugin managers with the current authentication mode
  across CLI, app-server, MCP, and external-agent migration paths.
- Preserve authentication mode while detecting and importing migrated plugins.

## Testing

- Cover catalog and skill routing across ChatGPT, API-key, unauthenticated,
  Bedrock, and custom-provider configurations.
- Verify authenticated plugin migration uses the ChatGPT curated marketplace.

GitOrigin-RevId: 660a339ee8891c33aad961078d3a979242a6a166
2026-08-13 20:20:01 +00:00
socrates-oai
507ef0b371 Add Guardian guidance for Node REPL tool calls (#38427)
## Why

JavaScript executed through the Node REPL can invoke connected MCP, browser,
or computer-use tools, so reviewing only the outer tool call does not capture
its immediate effects.

## What changed

- Add dedicated Guardian review guidance for `node_repl` `js` requests that
  evaluates nested calls, authorization boundaries, staged data, and concrete
  side effects.
- Keep the existing generic approval prompt for other MCP tools and shell
  requests.

## Testing

- Cover the dedicated Node REPL prompt, retry reasons, serialized request data,
  and the generic fallback behavior.

GitOrigin-RevId: bf8d49d7e3dc3d36aa41b6b56ff8a0eb02da3e53
2026-08-13 20:11:38 +00:00
cooper-oai
5ed321ce00 Protect workload identity auth in app-server account RPCs (#38426)
## Why

Workload identity credentials are owned by the app-server host and must not be replaced, removed, or exported through client account operations.

## What changed

- Reject account login and logout RPCs while workload identity is selected.
- Continue reporting the active authentication method from `getAuthStatus`, but omit the host-owned token even when `includeToken` is requested.

GitOrigin-RevId: 750c9d07ed2f4ba7007bbe75f188573e79749647
2026-08-13 20:04:57 +00:00
cooper-oai
990218bbbd Fail closed when workload identity initialization fails (#38424)
## What changed

- Treat workload identity environment markers as an explicit authentication selection, even when another process credential is present.
- Return initialization errors from `AuthManager` and propagate them through commands and services instead of continuing with an unusable authentication state.
- Make `codex login status` validate workload identity, keep the TUI on an embedded app server for local workload identity, and reject workload identity in `codex mcp-server`, where it is unsupported.

## Testing

- Cover workload identity precedence and partial configuration errors.
- Verify login status reports an unreadable identity assertion and app-server routing enforces the supported workload identity topology.

GitOrigin-RevId: efc6b6b4cd4d61652617de82aaa3d7ffc75d6618
2026-08-13 19:35:22 +00:00
sayan-oai
781445f7c6 Centralize thread environment selection state (#38423)
## What changed

- Make `ThreadEnvironments` the source of truth for live environment selections and use it when building configuration snapshots, permission profiles, per-turn configuration, and MCP refresh inputs.
- Keep settings previews side-effect free while applying accepted environment updates consistently to subsequent turns.
- Move `EnvironmentConfig` into `codex-protocol` so environment ownership no longer depends on a core-only type.

## Testing

- Cover environment previews and snapshots, accepted and rejected steer updates, and active-turn environment stability.

GitOrigin-RevId: 7bcf8fb5df1215f720e4e9c419541a51a871aa5e
2026-08-13 19:25:05 +00:00
hesham-oai
588e18aae5 Recover capability discovery after executor disconnects (#38420)
## Why

Transient executor disconnects could leave capability discovery and skill catalogs
stuck on a cached failure for the rest of a thread, even after the executor
reconnected.

## What changed

- Replay capability discovery after executor recovery and retry transient failures
  on later requests while continuing to cache permanent failures.
- Avoid caching skill catalogs produced from failed discovery so a later step can
  load the recovered catalog.
- Mark the MCP runtime dirty when recovered manifests change the projected MCP
  servers, and allow discovery to be cancelled with the turn.

## Testing

- Cover same-request recovery after a disconnect and recovery on a later request.
- Cover retry classification through connection-attempt errors and skill catalog
  caching after discovery recovers.

GitOrigin-RevId: a57f90844351e73ea831931f72a9ddc4e4f3335c
2026-08-13 19:14:30 +00:00
jay
9946da9af1 Apply Codex attribution to app-created commits (#38419)
## What changed

Clarify that commits created through a GitHub app or plugin must include the
Codex co-author trailer in the tool's `message` argument. This covers commits
that create, update, or delete files.

GitOrigin-RevId: 58be9302da9f8d4f11aa100c32f779fac9cc05e9
2026-08-13 18:50:43 +00:00
Eric Traut
f8a3db0b99 Clarify MCP OAuth reauthentication errors (#38418)
## Why

When an MCP server rejects existing OAuth credentials, reporting that the server
is merely not logged in obscures that the user needs to authenticate again.

## What changed

Pass the MCP startup failure reason into error formatting and report that the
server requires OAuth reauthentication when appropriate. Preserve the existing
recovery hint for either `codex mcp login` or the client's OAuth sign-in flow.

## Testing

Cover the reauthentication message for both login flows and verify it in the
streamable HTTP OAuth round-trip test.

GitOrigin-RevId: 6f6d5fe7519b1a476f8b70d976223b2ea1ec938e
2026-08-13 18:45:13 +00:00
jif
4f7032173e Honor filesystem permissions for app file uploads (#38416)
## Why

App tool file arguments could read and upload files without applying the active
filesystem sandbox policy.

## What changed

- Apply the effective filesystem policy, including session and turn grants, when
  reading metadata and streaming files for upload.
- Reject uploads before contacting the files endpoint when the selected path is
  denied.
- Report an error when the executor cannot provide sandboxed file streaming for
  a restricted policy.

## Testing

Added integration coverage showing that restricted policies allow permitted
files and reject denied files before upload.

GitOrigin-RevId: 63b239c5066dcb9d18b5050089c659fb2a784909
2026-08-13 18:36:12 +00:00
iceweasel-oai
2aba3219e6 Recognize PowerShell Get-Content file reads (#38415)
## What changed

- Classify simple PowerShell `Get-Content` commands, including `gc` and `type` aliases, as file reads while preserving Windows paths.
- Reuse the shared classification for implicit skill invocation detection on Windows and render recognized commands as `Read <file>` in the TUI.
- Leave commands with unsupported flags, multiple operands, wildcards, or expressions unclassified.

## Testing

- Cover supported and rejected PowerShell forms, Windows executor skill detection, and the TUI read summary.

GitOrigin-RevId: 4e8f5470f2ae31c08d74091f9634c2926e516ccf
2026-08-13 18:30:51 +00:00
felixxia-oai
73862481e5 Add bounded transcript rendering for Guardian v2 (#38414)
## What changed

- Add a configurable renderer that converts conversation messages, agent
  messages, tool calls and outputs, and reasoning into a numbered plaintext
  transcript.
- Keep only relevant readable content, including manual-approval developer
  messages, while omitting media payloads, encrypted content, and unsupported
  response items.
- Limit transcripts to the most recent 320 KiB without splitting UTF-8
  characters.

## Testing

- Cover source selection, content filtering, tool-name correlation, and bounded
  UTF-8 truncation with unit tests.

GitOrigin-RevId: e2c6535f4a895862ca744258399fb36fc92e42c6
2026-08-13 18:17:03 +00:00
Rasmus Rygaard
42bb50d502 Allow metadata updates without materializing threads (#38413)
## Why

Thread stores may filter a metadata patch to a no-op. Requiring every successful
update to return a `StoredThread` forces those implementations to materialize a
thread even when the caller does not need one.

## What changed

- Let `ThreadStore::update_thread_metadata` return `None` after a successful
  update that did not materialize a thread.
- Preserve the materialized-thread contract of `LiveThread` and `ThreadManager`
  metadata updates by reading the thread when the store returns `None`.
- Keep completion-only metadata updates from issuing that fallback read.

## Testing

Cover materialized in-memory updates and verify that fallback reads occur only
for callers that require the updated thread.

GitOrigin-RevId: 3059efc9d5b69e0b46e35fb5b5aa9638086654f2
2026-08-13 18:12:27 +00:00
jif
d167a3604c Classify tool calls in the Guardian V2 extension (#38409)
## What changed

- Register a tool lifecycle contributor when Guardian V2 is installed.
- On tool start, asynchronously ask the existing Luna sampler for a low-effort
  `action_risk` score constrained to the range from `0.0` to `1.0`.
- Bound the tool metadata supplied to the classifier and treat it as untrusted
  input.
- Emit an extension warning if classification sampling fails.

## Testing

Add an integration test that verifies the contributor reuses the configured
Luna pool and sends the expected model, attribution metadata, reasoning effort,
strict output schema, and tool-call context.

GitOrigin-RevId: 6b69fcc0443086544086849c38bcdd90560a291f
2026-08-13 17:32:10 +00:00
jif
66919805ea Pool Guardian sampling WebSocket connections (#38406)
## What changed

- Prewarm two Responses WebSocket connections and grow the pool on demand, up to eight connections, so overlapping samples can run concurrently.
- Lease each connection to a single sample and return healthy connections to the idle pool after completion.
- Replace closed or 55-minute-old connections and retry a sample once after a retryable or stream error.
- Keep the sampler available when the second prewarm connection cannot be opened.

## Testing

- Cover connection reuse, partial prewarm success, concurrent pool growth, and retrying an expired connection on another warm connection.

GitOrigin-RevId: 3ee7b05adc00a2135ba7cb35f6e4455199bf3784
2026-08-13 17:00:59 +00:00
felixxia-oai
a70211249a Expose conversation history to tool lifecycle extensions (#38403)
## What changed

- Add a shared, read-only `ConversationHistorySnapshot` capability to the extension API.
- Include the snapshot in `ToolStartInput`, preserving conversation order while excluding contextual user messages.
- Avoid acquiring a history snapshot when no tool lifecycle contributors are registered.

## Testing

- Verify snapshots share existing response items, remain stable as history changes, and filter contextual user messages.
- Verify tool-start callbacks receive the history available for successive tool calls.

GitOrigin-RevId: 822cae33781dd876ea628f104be08d8a449a4900
2026-08-13 16:43:23 +00:00
Tamir Duberstein
6851fae57c Refresh tracing interest in the token estimate test (#38400)
## What changed

Rebuild the tracing callsite interest cache after installing the test-local
subscriber so the `event_enabled!` assertion uses that subscriber's filters.

GitOrigin-RevId: d221dca4d7e7cb2ddd492a46f7a9d5c977088593
2026-08-13 16:08:34 +00:00
Tamir Duberstein
2bd8727a0c Preserve floating-point values when decoding rollout lines (#38399)
## Why

Serde's generic buffering for flattened and internally tagged fields is incompatible with `serde_json`'s `arbitrary_precision` representation. As a result, persisted rollout items containing nested floating-point values can fail to decode.

## What changed

- Decode the rollout envelope at the JSON persistence boundary before deserializing the item payload.
- Use the shared decoder for both session resume and thread-history projection.
- Cover token-count floats, response-item metadata, field ordering, and ignored metadata in the decoder compatibility test.

GitOrigin-RevId: 59c7f6fbcf83162b5ed6980a69381fe45fc20a0a
2026-08-13 16:03:20 +00:00
Ankush Gupta
053dda6b89 Include Node REPL results in Guardian reviews (#38397)
## What changed

- Capture accepted, successful `node_repl` results from Code Mode and include them as bounded, untrusted evidence in Guardian review prompts.
- Enable the enhanced transcript through `guardian_enhanced_node_repl_transcripts` or when the selected model requires automatic Node REPL review.
- Keep this evidence out of the parent model history, exclude encrypted and failed results, and avoid resending admitted evidence when a Guardian session is reused.
- Clear retained evidence and invalidate review sessions when a thread is rolled back.

## Testing

- Add unit coverage for evidence ordering, escaping, truncation, and empty responses.
- Add an integration test covering feature-disabled, feature-enabled, and model-required behavior, including filtering and review-session reuse.

GitOrigin-RevId: edc3dca5d5b88d472a492f35531ec46889a89d72
2026-08-13 15:50:48 +00:00
viyatb-oai
779e9114ae Reap orphaned processes in Linux sandboxes (#38396)
## Why

Sandboxed descendants can outlive their immediate parent and must be collected by
PID 1 in the Bubblewrap namespace.

## What changed

- Launch `codex-linux-sandbox` with Bubblewrap's `--as-pid-1` option, and fall
  back to the bundled Bubblewrap when the system version does not support it.
- Run the sandboxed command as a child, forward signals to it, reap other exited
  descendants, and preserve the command's exit status.
- Verify proxy bridge parent identity when arming its parent-death signal.

## Testing

Added Linux sandbox coverage for the filtered namespace reaper, orphan
collection, and fallback from an incompatible system Bubblewrap.

GitOrigin-RevId: 379f08d6c2732ea0a4caeb61f93ae302e16d2458
2026-08-13 15:45:51 +00:00
viyatb-oai
ef596c68ca Reject sessions with unloadable required managed hooks (#38394)
## Why

Hooks supplied as managed requirements must not be silently skipped when their
handlers cannot be loaded.

## What changed

- Fail session and app-server thread startup when an enabled managed requirement
  contains an invalid matcher, an empty command, or an unsupported handler type.
- Keep load failures for ordinary managed configuration hooks as warnings, and do
  not enforce managed hook requirements while the hooks feature is disabled.

## Testing

Added hook-engine, core session, and app-server coverage for valid and invalid
managed hook requirements.

GitOrigin-RevId: 91a23b0c1d85e143aba6aabe874c5274e52fc6b2
2026-08-13 15:23:09 +00:00
jif
683716cee9 Use effective permissions when trusting app-server projects (#38390)
## Why

Project-local configuration can launch host processes. Requested write access may be reduced to read-only by managed constraints or platform support, so the request alone must not cause the app server to trust a project and load its configuration.

## What changed

- Base automatic project trust on the effective permission profile after configuration is loaded.
- Trust managed profiles only when their effective filesystem policy allows writes to the working directory.
- Continue resolving trusted nested working directories to the repository root.

## Testing

- Verify that managed read-only permissions neither persist project trust nor load a project-local MCP server when workspace-write access was requested.
- Cover effective read-only fallback for workspace-write requests and nested repository working directories.

GitOrigin-RevId: e548fd9c4552c328f779cc0365fe86f37d4a9b71
2026-08-13 14:55:00 +00:00
provencher-oai
5e32f728f1 Refine skill creation guidance and validation (#38384)
## What changed

- Rework the bundled `skill-creator` guidance around concise, scoped instructions, progressive disclosure, optional resources, invocation policy, and risk-based forward-testing.
- Simplify generated skill and reference templates so new skills start with only the placeholders and resources they need.
- Reject unfinished `[TODO: ...]` placeholders in skill descriptions and instruction bodies while allowing examples inside fenced code blocks.

GitOrigin-RevId: b0871aaeeb768c12b1a467d48037eecc8db5d52b
2026-08-13 14:24:53 +00:00
jif
911012490c Return Luna samples when streamed JSON completes (#38383)
## Why

Structured output can be complete before the Responses stream emits its terminal
events. Waiting for those events unnecessarily delays the sampler and can leave it
waiting after usable output has arrived.

## What changed

- Return a Luna sample as soon as accumulated text deltas parse as a complete JSON
  object.
- Continue draining the remaining response events in the background so the
  authenticated WebSocket stays reusable for subsequent samples.
- Enforce the output-size limit while accumulating deltas on the early-return path.

## Testing

- Cover returning complete JSON without terminal response events.
- Verify that early return still allows the authenticated WebSocket to be reused.

GitOrigin-RevId: 80c9963f1540f7862356aaad3503e3071a8fb92a
2026-08-13 14:20:38 +00:00
Tamir Duberstein
6fc6b9d6d2 Prevent unread events from blocking in-process requests (#38381)
## Why

Awaiting a bounded consumer event queue can stall the in-process app-server
worker when notifications are not being drained, preventing it from delivering
a request response queued behind them.

## What changed

- Use an unbounded queue for caller-facing in-process events while keeping
  command and embedded-runtime queues bounded.
- Preserve all events in order instead of dropping best-effort events and
  emitting lag markers when the consumer queue fills.
- Document that callers can await requests without concurrently draining
  notifications.

## Testing

Add a regression test that fills a capacity-one client with unread settings
notifications, verifies subsequent requests complete, and then confirms the
notifications remain readable in order.

GitOrigin-RevId: 6ca6cfb9349dfa04a613236836f813c1f799783e
2026-08-13 13:57:25 +00:00
Felipe Coury
d09cf7e5f4 Preserve user message styling when wrapping long URLs (#38380)
## Why

Terminal autowrap for oversized URL tokens can drop the user-message gutter and background on continuation rows.

## What changed

- Explicitly wrap long URLs within the available message width.
- Preserve the complete OSC 8 hyperlink destination on every wrapped fragment.
- Keep the user-message gutter and background styling across continuation rows.

## Testing

Add history-cell and VT100 coverage for URL content, hyperlink targets, gutters, and backgrounds across wrapped rows.

GitOrigin-RevId: 59514eee4ab967bd937b55574b9f8d0d1c82df7c
2026-08-13 13:52:18 +00:00
jif
a7e9fb5480 Constrain Guardian reviews to parent filesystem permissions (#38377)
## Why

Guardian review sessions must not gain access to paths that the parent turn is
not allowed to read.

## What changed

- Derive Guardian permissions by intersecting managed parent filesystem rules
  with read-only access, preserving denied paths and restricting network access.
- Offer Guardian execution tools only when a managed sandbox can enforce those
  rules.
- Include the selected environment IDs in the review-session reuse key so a
  session is not reused across different environment sets.

## Testing

Update the Guardian reuse integration test to verify that a review cannot read
a parent-denied file or write a local file while consecutive reviews still
reuse the same session.

GitOrigin-RevId: 20f17a6c379f1eda651e8508459d642a51e4ce94
2026-08-13 13:41:08 +00:00
jif
a7b8c074b5 Add the Guardian V2 Luna sampler (#38368)
## What changed

- Add a `LunaSampler` that opens an authenticated Responses WebSocket and reuses it for structured, tool-free `gpt-5.6-luna` requests.
- Carry the host's provider, authentication, proxy, attribution, and service-tier configuration into the connection and requests.
- Require strict JSON schemas, preserve per-request reasoning effort and turn metadata, and reject missing or oversized output.

## Testing

- Add a WebSocket test covering authentication and attribution headers, connection reuse, structured request fields, per-turn metadata, reasoning effort, and returned output.

GitOrigin-RevId: aef85fd8ddcfcb7c76a9ede0d3191e3a0321656b
2026-08-13 12:35:56 +00:00
jif
72fa74fbc9 Persist security risk scores in rollout history (#38363)
## What changed

- Add a `SecurityRiskScore` rollout item containing a category and numeric score.
- Persist the item in both thread history modes while excluding it from model context, user-visible thread history, search text, forks, and reconstructed conversation history.
- Re-export the score type from the extension API.

## Testing

- Cover serialization, persistence and loading, thread history projection, session reconstruction, append planning, and memory filtering.

GitOrigin-RevId: 1926fe366aeaa75052708a6da589f45a38eefb52
2026-08-13 12:04:29 +00:00
jif
9ed0047a61 Stabilize exec-server byte-budget tests (#38362)
## What changed

- Send the scripted HTTP response before queuing body deltas in the
  single-stream byte-budget test.
- Allow 30 seconds for barrier requests in both byte-budget tests while
  retaining the default timeout for other operations.

GitOrigin-RevId: ac65580b479d93fcbcca787f15e04c084f0aa56b
2026-08-13 12:00:19 +00:00
jif
4ca1af77a5 Test hook rejection for explicitly started queue items (#38361)
## What changed

- Add dedicated coverage for explicitly starting a queued item that a prompt hook rejects.
- Verify the rejected item is consumed and no model request is sent.
- Keep the automatic queue dispatch test focused on consuming a rejected item while allowing later queued input to proceed.

GitOrigin-RevId: e01cefb9d8581b0d4be05d4595f279d61e628e83
2026-08-13 11:55:10 +00:00
Charlie Marsh
80ceab7aaa Optimize orphan output normalization (#38358)
## What changed

- Collect borrowed call IDs in a single pass instead of cloning IDs across
  separate sets.
- Record orphan positions and compact the history only when orphan outputs are
  present, while preserving the existing matching and error behavior.

GitOrigin-RevId: de399ba92ff451cb12fc69218d60d3ac29fccb3d
2026-08-13 11:39:57 +00:00