Commit Graph

9188 Commits

Author SHA1 Message Date
Adam Perry @ OpenAI
27a98dde4d Use protobuf's built-in Bazel proto rule (#38280)
## What changed

- Load `proto_library` for the code-mode protocol directly from the
  `com_google_protobuf` repository.
- Remove the now-unneeded direct `rules_proto` module dependency.

GitOrigin-RevId: 5a01191b2c46c7fafd263ed93f153a878b09aaa8
2026-08-13 00:26:06 +00:00
Kyle Brown
c38d59fca0 Add app-server coverage for plugin measurement analytics (#38278)
## What changed

- Add end-to-end tests for curated plugin measurements through classic shell execution and unified exec.
- Cover unified background commands whose measurements arrive after the turn completes.
- Verify command attribution and measurement payloads, including values, dimensions, execution IDs, and thread, turn, and item IDs.

GitOrigin-RevId: 866103aafef8d3454123c40aee7041912ad0b7fc
2026-08-13 00:08:57 +00:00
Kyle Brown
96e8afbfb8 Track plugin metrics for background unified exec commands (#38276)
## Why

Unified exec can yield while a command is still running. Plugin measurement
collection must remain active until that background command exits, including
when its item completion arrives after the turn has completed.

## What changed

- Keep the plugin metrics sidecar with the stored process and let either the
  exit watcher or a poll that observes completion finalize it exactly once.
- Retain completed turn analytics state while tool items are pending so late
  command completion events can be emitted without duplicating the turn event.

## Testing

- Verify that a background command completed after its turn emits a command
  execution event and does not emit a second turn event.

GitOrigin-RevId: ecf715b3e047aa29ca9a417d12d955257fed8557
2026-08-13 00:04:57 +00:00
Owen Lin
cbb7e82a8b Unify turn input submission and routing (#38275)
## What changed

- Add `TurnInputRequest` and typed submission results for atomically starting a turn, steering the active turn, or declining input with a specific reason.
- Expose `start_or_steer_turn`, `start_turn_if_idle`, and `steer_turn` on `CodexThread`, and migrate Core consumers to these APIs.
- Make app-server `turn/start` steer an active regular turn and return that turn's ID. Reject incompatible output schemas and non-steerable turns without applying settings or enqueueing input.

## Testing

- Cover concurrent start-or-steer submissions, accepted and rejected settings updates, output-schema compatibility, idle-start rejection, and app-server steering.

GitOrigin-RevId: dd9b5528d76ec650c019e97af420bc13190ea86a
2026-08-13 00:00:16 +00:00
Tamir Duberstein
4b07886d59 Represent persisted world state as JSON objects (#38274)
## Why

World-state snapshots and merge patches are keyed collections of sections. Allowing
their persisted `state` field to contain any JSON value required replay code to
handle shapes that cannot represent world state.

## What changed

- Type `WorldStateItem.state` and snapshot patches as JSON object maps.
- Reconstruct full snapshots directly from those maps and apply patches without
  fallible arbitrary-value conversions.
- Regenerate the app-server protocol schema for the object-only representation.

GitOrigin-RevId: 3d7662b74f3dd1f3ccc5fdd0200074c13a73cbe5
2026-08-12 23:56:45 +00:00
ashwinnathan-openai
361fe2d202 Stamp conversation history items with creation times (#38272)
## What changed

- Add fractional Unix creation times to locally authored user, developer, agent, and tool-output items when they enter durable conversation history.
- Preserve any creation time already supplied with an item across subsequent requests, remote compaction, and resumed history.

## Testing

- Cover timestamp assignment and preservation in session, client, tool, agent-spawn, and remote-compaction tests.

GitOrigin-RevId: 431d1770b9746005c808bc0a43953845166d68ad
2026-08-12 23:04:42 +00:00
Felipe Coury
842fae26c9 Add per-thread usage queries to the backend client (#38270)
## What changed

- Add `Client::get_thread_usage` for querying authoritative estimated credit
  and dollar usage for a thread across both supported backend path styles.
- Expose usage totals and optional model, reasoning effort, speed, and token
  breakdowns through `ThreadUsage` and `ThreadUsageBreakdownGroup`.
- Reject responses that do not include the requested thread.

## Testing

- Cover endpoint paths, request serialization, complete and partial usage
  responses, and mismatched thread IDs.

GitOrigin-RevId: 16c83590b2c804e0182b4493cf2aa39206029c77
2026-08-12 22:58:46 +00:00
jif
5664a5c07c Expose executor skill roots from skills.read (#38268)
## Why

Executor-backed skills can include bundled scripts, so skill readers need the
skill directory in the executor filesystem to locate them.

## What changed

- Add `skill_root` to `skills.read` responses for executor-backed skills.
- Derive the root from the parent directory of the skill's main resource and
  omit the field for other skill authorities.

## Testing

- Verify executor skill reads return the expected root for both `SKILL.md` and
  a referenced resource.

GitOrigin-RevId: b7035c7e2e62155890795fb508fefe3a1c17805b
2026-08-12 22:54:35 +00:00
chess
631bbb33cc Use bounded fallback ports for Windows managed proxies (#38265)
## What changed

- Try the explicitly configured Windows HTTP or SOCKS5 proxy port first, then scan the protocol's preferred port range when that port is unavailable.
- Reserve HTTP and SOCKS5 listeners independently so a SOCKS5 collision does not replace an already available HTTP listener.
- Retain ephemeral loopback fallback when all preferred ports are unavailable, and document the HTTP (`3128-3159`) and SOCKS5 (`8081-8112`) ranges.

## Testing

- Cover bounded HTTP and SOCKS5 fallback, independent listener reservation, and ephemeral fallback after preferred-port exhaustion.

GitOrigin-RevId: 002c641f5bd70fedf04cca96c65c5fee2c5ebcac
2026-08-12 22:33:18 +00:00
jif
130c7c93a9 Resolve skill package aliases in skills.read (#38261)
## Why

Skill catalogs can present shortened package locators, but callers previously had
to expand those aliases before reading a skill.

## What changed

- Resolve catalog aliases automatically when `skills.read` looks up a
  model-visible executor or orchestrator skill package.
- Update skill prompts and tool documentation to tell models to pass the listed
  package locator directly.

## Testing

- Exercise reading an executor skill through its shortened package locator when
  the skills catalog exceeds its context budget.

GitOrigin-RevId: d1cdfd64002510b616146929deb5b7077850b951
2026-08-12 22:10:55 +00:00
cooper-oai
18dcc7646f Unify external authentication provider handling (#38258)
## What changed

- Use each `ExternalAuth` provider's error classification for resolve, refresh,
  and validation failures.
- Allow runtime providers to be replaced, clearing any recorded permanent
  refresh failure after the replacement resolves successfully.
- Preserve workload identity as immutable, host-managed authentication while
  sharing external ChatGPT credentials through the process-local store.

## Testing

- Cover provider replacement after a permanent failure, provider-defined error
  classification, workload identity immutability, and refreshed headers after
  an unauthorized response.

GitOrigin-RevId: ec75cf9224dc82d3fd10063606c724e3b06fb1e7
2026-08-12 22:04:27 +00:00
Channing Conger
bde723ae7d Reconnect gRPC code-mode sessions after host restarts (#38257)
## What changed

- Reopen a cached code-mode session when its gRPC host stops, while
  serializing concurrent reconnection attempts and coordinating shutdown.
- Scope cell IDs to the new host generation so callbacks remain consistent
  and stale `wait` or `terminate` requests are rejected.
- Accept both `unix://` and `unix:` endpoints for gRPC hosts on Unix systems.

## Testing

- Cover host restart recovery, concurrent execution after reconnection,
  generation-aware callbacks and cell operations, stale cell rejection, and
  Unix socket execution.

GitOrigin-RevId: 548e168fdcef7f7d54bd32262e614886bf7bdd32
2026-08-12 22:00:20 +00:00
Dylan Hurd
020f6c963e Report the latest rejection from multiple network reviews (#38256)
## Why

A single execution can trigger multiple network approval reviews. Its tool
result should reflect the latest specific rejection.

## What changed

- Let each explicit network review outcome replace the previously recorded
  outcome for the execution.
- Keep generic blocked-request messages as fallbacks that cannot overwrite an
  explicit review outcome.

## Testing

- Add unit coverage for outcome precedence.
- Add an integration test that rejects two network requests from one execution
  and verifies that only the latest rejection is returned.

GitOrigin-RevId: 644a01e5c49855adcdc48ba8f91baededce26875
2026-08-12 21:55:31 +00:00
Kyle Brown
6e7daed1e9 Collect plugin metrics from unified exec commands (#38253)
## What changed

- Create a metrics sidecar for attributed local plugin commands launched through unified exec, and grant the sandbox access to its output file.
- Publish valid measurements when the initial command exits, while discarding the sidecar when the process remains live for later polling.
- Strip inherited or configured `CODEX_PLUGIN_METRICS_OUTPUT` values so each command can only use its own sidecar.

GitOrigin-RevId: 43e669e4c77171aec8a798de0c12ca13bfb8adee
2026-08-12 21:27:30 +00:00
Kyle Brown
9ca0337dbf Collect metrics from plugin shell commands (#38252)
## What changed

- Provide matching local plugin commands with a sandbox-writable temporary output file through `CODEX_PLUGIN_METRICS_OUTPUT` when analytics is enabled.
- Validate successful command output against the plugin's `analytics.yaml` declaration, including measurement names, enum dimensions, finite values, duplicate rows, and size limits, before publishing analytics events.
- Keep the output path reserved from user overrides and clean up the temporary file after execution.

## Testing

- Cover output validation, limits, cleanup, sandbox permissions, environment handling, and path replacement.
- Verify measurement collection through both classic and zsh-fork shell runtimes.

GitOrigin-RevId: 88af0f87dc2f207fcbcca6af498f5c940d79349d
2026-08-12 21:23:21 +00:00
pakrym-oai
8bb8d60234 Read model ETags from WebSocket metadata events (#38251)
## What changed

- Extract `x-models-etag` from `codex.response.metadata` events and emit it as a `ModelsEtag` response event.
- Stop reading or reporting the model ETag from WebSocket upgrade headers.

## Testing

- Update the WebSocket response-stream test to deliver the ETag through a metadata event and verify that it is emitted.

GitOrigin-RevId: 9b9cff3d8a0a914549aca62d8d316483a9a47f69
2026-08-12 21:18:15 +00:00
xl-openai
379cb68444 Add dynamic HTTP header helpers for MCP servers (#38245)
## What changed

- Add `http_headers_helper` configuration for local streamable HTTP MCP servers. The configured shell command runs once per connection and returns a JSON object of headers that is cached across requests.
- Apply helper headers to MCP startup and OAuth flows while restricting them to the server origin, stopping redirects, rejecting reserved or duplicate headers, and enforcing output and execution limits.
- Reject helpers for remote or managed-disabled servers, use the local environment working directory, and redact helper commands from `codex mcp list` and `codex mcp get` output.

## Testing

- Cover configuration validation, helper lifecycle and output parsing, origin isolation, OAuth discovery and token refresh, managed requirements, environment selection, and CLI redaction.

GitOrigin-RevId: 84e0e26ce75520b0869d37c72b1678e033bd6818
2026-08-12 20:36:32 +00:00
Owen Lin
8d4d57387a Resolve paginated thread history by rollout ID (#38244)
## Why

`thread/revert` keeps the logical thread ID while selecting a new immutable
rollout. Using the thread ID for persisted history can therefore read or update
the wrong rollout.

## What changed

- Centralize resolution of a thread's current rollout across live writers,
  SQLite metadata, and filesystem fallbacks.
- Key history materialization, lineage traversal, paging, turn lookup, and fork
  boundaries by immutable rollout ID while retaining the thread ID for the
  logical thread.
- Treat SQLite's selected rollout as authoritative for paginated threads so a
  filesystem scan cannot select an older rollout after `thread/revert`.

## Testing

Add a regression test showing that update-ordinal item paging reads from the
selected rollout ID when it differs from the thread ID.

GitOrigin-RevId: 1101e548a6e6c6d319996e24cb650e5b03ab7fbb
2026-08-12 20:31:52 +00:00
rka-oai
0e0ef5d818 Track client-authored developer messages in rollout history (#38243)
## What changed

- Mark developer messages received from clients with `client_authored` harness
  metadata when `retain_client_developer_messages` is enabled.
- Carry that provenance through pending input and persist it alongside rollout
  response items without adding it to provider requests or the serialized
  `TurnInput` payload.
- Preserve existing behavior for unannotated response items and when the
  feature is disabled.

## Testing

- Cover client item injection before and during turns, additional application
  context, rollout replay, image resize notices, and serialization boundaries.

GitOrigin-RevId: f385c177732becde732272e4b8440eb91f5c1039
2026-08-12 20:05:49 +00:00
Charlie Marsh
3d7bb2dd2e Cache stable active-cell layout measurements (#38242)
## What changed

- Reuse desired and rendered heights for active transcript cells that report a stable height.
- Invalidate the cached layout when the cell identity, revision, width, render mode, or syntax theme changes, and when the active cell is removed.
- Continue rebuilding display lines on every frame so animated content stays live, while dynamic-height cells bypass the persistent cache.

## Testing

- Add rendering tests for height reuse, bottom-anchored overflow, cache invalidation, animated display lines, and dynamic-height cells.

GitOrigin-RevId: 414cc4269bfb6b68105837c82e31787272d335a7
2026-08-12 19:43:32 +00:00
Ankush Gupta
74004b5397 Include Node REPL policy in turn metadata (#38241)
## What changed

- Parse `node_repl_auto_review_required` and `node_repl_disabled` from model catalog entries and include their values in each turn's Responses API metadata.
- Treat both fields as reserved metadata so client-provided values cannot override the selected model's policy.
- Use the selected review model's catalog entry when building metadata for review turns.

## Testing

- Cover metadata propagation across model switches, review turns, Responses API requests, and MCP tool calls.

GitOrigin-RevId: c1f63426eeb8e559abff439fbc618716a4908aff
2026-08-12 19:37:51 +00:00
Kyle Brown
d6eefb26a6 Add bounded plugin measurement analytics (#38239)
## What changed

- Add `PluginMeasurementsInput` and `PluginMeasurementRow`, plus an analytics
  client method for recording batches and checking whether analytics are enabled.
- Emit each valid row as a `codex_plugin_measurement_event` with thread, turn,
  item, plugin, execution, and operation context.
- Bound batches at 100 rows and reject non-finite values, invalid identifiers,
  and rows with more than eight dimensions.
- Treat measurement events as plugin events when routing API-key analytics.

## Testing

- Cover batch limits, row filtering, serialized event payloads, and API-key
  plugin-event routing.

GitOrigin-RevId: f949ed06246ee1e22466df2660076f2d4f556444
2026-08-12 19:14:09 +00:00
Kyle Brown
dc8562d672 Add manifest-defined metrics for trusted plugin scripts (#38238)
## What changed

- Load version 1 `analytics.yaml` manifests from trusted plugin roots and map declared operations, measurements, and enum dimensions to exact script paths.
- Expose resolution types and bind a declared operation to the plugin identity returned by fresh command attribution.
- Reject malformed, oversized, ambiguous, or unsafe manifests without disabling normal script attribution.

## Testing

- Cover exact script resolution, measurement names shared across operations, and invalid manifests including duplicate keys, path traversal, symlink escapes, invalid identifiers, and oversized files.

GitOrigin-RevId: 1e2f221b9f2c3d7faffe578c7a8499ad4ed933ca
2026-08-12 19:09:48 +00:00
Eddie Chen
1f4ea79853 Track root turns across delegated Codex requests (#38232)
## Why

`parent_turn_id` identifies the immediate caller of a nested request, but not the
top-level turn that initiated a multi-level chain of work.

## What changed

- Add `root_turn_id` to turn state, submissions, and Responses API metadata.
- Propagate the root through spawned agents, delegated work, review sessions, and
  turn-triggering inter-agent messages.
- Omit the root when background work has no user turn or combined input makes the
  root ambiguous.

## Testing

Added coverage for nested agent resumes, reviews, mailbox delivery, steered input,
and reserved metadata handling.

GitOrigin-RevId: 60057db2ee81f4efefa946a9f63c74ff98b93929
2026-08-12 18:11:13 +00:00
ryanleeoai
9df9ff6ad9 Detect implicit skill invocations from PowerShell reads (#38228)
## What changed

- Recognize `Get-Content` reads of indexed `SKILL.md` files as implicit skill invocations.
- Support the optional `-Raw` flag, quoted paths containing spaces, and Windows paths without stripping backslashes.

## Testing

- Add unit coverage for the supported `Get-Content` forms and Windows path parsing.

GitOrigin-RevId: 681f2e2fff9a597326bc94b97a31e311ef21b949
2026-08-12 18:04:20 +00:00
rka-oai
1ad4397821 Add a flag to retain client developer messages (#38227)
## What changed

- Register `retain_client_developer_messages` as an under-development feature
  that is disabled by default.
- Expose the feature in the configuration schema.

GitOrigin-RevId: dc56c48fe79a9f288b7fe0a11d97af992d36797f
2026-08-12 17:49:36 +00:00
jif
7093e8c480 Start required cached MCP servers lazily for subagents (#38217)
## Why

Subagents can reuse cached MCP tool definitions without opening another server
connection immediately, but marking a server as required previously forced eager
startup even when its cached tools were available.

## What changed

- Allow required MCP servers with usable cached tools to remain dormant under
  the lazy startup policy.
- Treat those cached tools as satisfying required-server validation and tool
  catalog capture until the server is needed.
- Preserve eager startup for required servers without cached tools and start a
  dormant server when one of its tools is called.

## Testing

Extend the cached HTTP MCP subagent test to cover both optional and required
servers, verifying that the required server stays dormant until its cached tool
is called.

GitOrigin-RevId: 48ea20b9ae447eef27461caee2320ea78465bb6a
2026-08-12 16:50:23 +00:00
Tamir Duberstein
91d6f48992 Avoid allocations when sanitizing TUI user text (#38214)
## Why

Sanitizing user messages and pasted text always allocated a new string, even
when the input contained no terminal control characters.

## What changed

- Return a `Cow<str>` from `sanitize_user_text` so clean borrowed input remains
  borrowed.
- Reuse owned input buffers when sanitization leaves the text intact or only
  removes content at the edges.
- Update transcript rendering, history cells, and paste handling to consume the
  borrowed-or-owned result without unnecessary cloning.

## Testing

Add sanitizer coverage for clean text, control sequences, Unicode control
characters, incomplete escape sequences, buffer reuse, and multi-fragment
output.

GitOrigin-RevId: 9e39cbc0d83c5791941b37a7eb4bb918c1a05f68
2026-08-12 16:33:32 +00:00
Dylan Hurd
95aada11c4 Enforce non-interactive approval policy for Codex delegates (#38205)
## What changed

- Require delegated Codex sessions to use the `never` approval policy and reject
  delegate creation with any prompt-capable policy.
- Stop forwarding delegate approval and permission requests to the parent
  session. Approval-requiring commands and MCP tool calls are denied within the
  delegate instead.
- Skip prompts for missing skill MCP dependencies when approvals are disabled.

## Testing

Add coverage for review and Guardian delegates to verify that command
escalations, MCP approvals, and skill dependency installation do not prompt or
execute approval-gated actions.

GitOrigin-RevId: fee96a97624352cd25c904592ba7eebe2ae3fd63
2026-08-12 15:31:47 +00:00
jif
3d7f9b4637 Fuse recent and lexical skills in shadow selection (#38204)
## What changed

- Add the `lru_plus_lexical_v1` selector, combining the 50 most recent skills
  with weighted lexical matches through reciprocal rank fusion.
- Include the combined selector in the shadow-selection experiment and propagate
  query and candidate truncation metadata from both inputs.
- Generalize the existing reciprocal-rank fusion helper to accept a rank
  constant while preserving the existing lexical/character selector behavior.

## Testing

- Cover lexical-only selection, merging recent and matching skills, promotion
  from agreement between both rankings, and weak overlaps.
- Extend the skills extension test to verify invocation metrics for the new
  selector alongside `lru_v1`.

GitOrigin-RevId: 1b7b82bc97ea919c719cd05a009351b701019306
2026-08-12 15:17:54 +00:00
jif
9dd22890f5 Add an LRU baseline to skill shadow selection (#38197)
## What changed

- Track the 50 most recently invoked skills for each thread and evaluate them
  as the `lru_v1` shadow-selection method.
- Filter stale and duplicate entries while preserving recency order.
- Increase the shadow result limit to 50 and add a `21_50` rank bucket.

## Testing

- Add unit coverage for recency refresh, eviction, filtering, limits, and rank
  buckets.
- Add an extension test showing that `lru_v1` recovers a skill invoked on an
  earlier turn.

GitOrigin-RevId: 7aa56514db57cf180cc3f57b4d493dee3304e766
2026-08-12 14:09:44 +00:00
felixxia-oai
eb752e43d9 Run plugin app-server tests in automatic environments (#38189)
## What changed

- Use the standard automatic test environment for plugin list, install, and
  uninstall app-server tests.
- Keep the bundled stdio MCP test host-local because its fixture is a local
  executable.
- Strengthen that test to verify the bundled server initializes and exposes
  its `echo` tool.

GitOrigin-RevId: 06dac135b0cc0b28fc235d95a02129eecf8f8c09
2026-08-12 13:33:01 +00:00
cooper-oai
96c8be200c Integrate workload identity with Codex authentication (#38188)
## What changed

- Select workload identity authentication from `OPENAI_FEDERATION_RULE_ID` and
  `OPENAI_IDENTITY_TOKEN_FILE`, while preserving explicit API key and access
  token precedence.
- Adapt workload identity exchanges to the shared authentication manager and
  reuse a compatible process-scoped session for token resolution and refresh.
- Reject incomplete, conflicting, or unsupported configurations and exchanged
  tokens that change the authenticated subject.
- Classify exchange failures for authentication retry handling and invalidate
  rejected cached tokens without discarding a newer concurrent exchange.

## Testing

- Cover configuration selection and validation, session reuse and conflicts,
  identity-preserving refreshes, concurrent refreshes, and retry classification.

GitOrigin-RevId: 62afb514b4e0a59effb08f464ac929633462a71b
2026-08-12 13:27:57 +00:00
felixxia-oai
e1b7b1acb3 Stop overriding environments in the skills user-turn test (#38186)
GitOrigin-RevId: d72b6751ba5dc180857992780093dc40dbc7d20e
2026-08-12 13:14:30 +00:00
felixxia-oai
c4b287cf57 Run search tool integration tests on Windows (#38184)
## Why

The search tool integration test suite was disabled entirely on Windows.

## What changed

- Remove the suite-wide Windows exclusion and build test fixtures with automatic environment selection.
- Configure stdio MCP fixtures with environment-aware server paths and environment IDs for local and remote runs.
- Skip the three stdio MCP cases that still require a native Windows test server when running through Wine.

GitOrigin-RevId: cf6f919bed28722996680dd0a085c1d1f80e4dcb
2026-08-12 12:59:34 +00:00
jif
93beee910d Add conservative restriction helpers for tool policies (#38183)
## What changed

- Add `restrict_to` helpers that combine parent and requested `WebSearchMode`
  and `AppToolApproval` values without granting access beyond either policy.
- Treat `Auto` and `Writes` approval modes as incomparable, falling back to
  `Prompt` when they are combined.

## Testing

- Cover every pair of web search and app tool approval modes.

GitOrigin-RevId: 41b3da5ace2fbdaab667c4b834bc2051a8e5e9cf
2026-08-12 12:53:07 +00:00
jif
0e82c62a44 Embed defaults in the packaged config layer (#38179)
## What changed

- Add an embedded `defaults.toml` and always install it as the lowest-precedence configuration layer when no packaged-defaults path is supplied.
- Keep packaged defaults out of config RPC layer and origin metadata.
- Report a user setting as overridden only when the effective layer has higher precedence, so clearing a setting can fall back to its packaged default without a false override.

## Testing

- Cover loading the packaged layer when other configuration files are absent.
- Cover config RPC filtering and clearing a user value that falls back to a packaged default.

GitOrigin-RevId: c1c0e1e681e4ac1be2602550972533443c5df51b
2026-08-12 12:15:47 +00:00
jif
8270a7c74d Update lru and webbrowser dependencies (#38172)
## What changed

- Update the workspace `lru` requirement to `0.18.2`, consolidating consumers on a single version.
- Raise the `webbrowser` requirement to `1.2.2` and refresh the Cargo and Bazel lockfiles.

GitOrigin-RevId: c70dce42f4b6e0dc5567a28f778fd12c720d8f4c
2026-08-12 11:36:41 +00:00
Tamir Duberstein
16fbfe5574 Notify running turn watchers only on count changes (#38170)
## What changed

- Publish the running-turn count while holding the thread state lock so updates
  remain ordered with their corresponding state mutations.
- Use `watch::Sender::send_if_modified` to avoid waking subscribers when a
  thread status update leaves the count unchanged.

## Testing

- Add a test that verifies turn start and shutdown notify the count watcher,
  while a permission request during the turn does not.

GitOrigin-RevId: 50fe6bcfb2cac7392715263cfdde0f382fe21502
2026-08-12 11:07:46 +00:00
rphilizaire-openai
69ae78291d Read executor skill packages directly (#38167)
## Why

Executor skills required a `skills.list` lookup before their contents could be
read, even when the catalog already identified the skill.

## What changed

- Render executor skill catalog entries as package locators, including shortened
  locators when skill roots are aliased.
- Tell the model to pass those packages directly to `skills.read`, while keeping
  `skills.list` as the fallback when no package is available.
- Use the shorter package locators when applying the skills context budget.

## Testing

Update catalog, aliasing, budget-pressure, and selected-skill coverage, including
an executor package ID containing a literal backslash.

GitOrigin-RevId: 2ace5e527dc4f29651a8f3214475ccc90d52c73f
2026-08-12 10:34:25 +00:00
Tamir Duberstein
3fe19fcd81 Resolve subagent analytics connections lazily (#38165)
## Why

Subagent-start facts can arrive before their parent's connection context is
recorded, leaving later analytics events without client metadata.

## What changed

- Resolve a thread's connection by walking its parent-thread chain when the
  connection was not captured directly.
- Use the resolved connection for subagent setup, tool-call analytics, and
  completed turn events.

## Testing

Extend the subagent analytics test to start the child before the parent context
arrives and verify both command-execution and dynamic-tool-call events.

GitOrigin-RevId: c4d74a22de34abd6c6c5df1717a49ae0e1a9445d
2026-08-12 10:24:34 +00:00
Owen Lin
4ef836f883 Distinguish rollout IDs from thread IDs (#38127)
## Why

`thread/revert` preserves a thread ID while creating a new immutable rollout. Rollout persistence and filesystem fallback therefore need to distinguish the logical thread from each physical history file.

## What changed

- Add a `RolloutId` alias and canonical filename parsing for both ordinary rollouts and reverted rollouts with a distinct rollout ID.
- Allow the recorder to create a replacement rollout without changing the thread ID, and add lookup by either the stable thread ID or an exact rollout ID.
- Index history references and compression safety checks by rollout ID so multiple rollouts for one thread remain distinct.
- Preserve the rollout path selected in SQLite when filesystem repair encounters another rollout for the same thread.

## Testing

Add coverage for filename round trips, replacement rollout metadata, thread and rollout lookup, reference indexing, compression, and database path preservation.

GitOrigin-RevId: 14b1d0b4a9432b341a1307afc0abadd507e7ae7d
2026-08-12 05:20:32 +00:00
Dylan Hurd
2230d64464 Route MCP tool calls through shared approval handling (#38108)
## What changed

- Represent MCP tool calls as approval actions and route them through the
  session-level approval flow for permission hooks, reviewer selection,
  rejection handling, and resolution telemetry.
- Preserve MCP-specific user prompts, session and persistent approval choices,
  and the approval policy and reviewer captured for the tool call.

## Testing

- Add coverage for permission hooks resolving MCP calls before user or
  automatic review, persistence choices, captured policy routing, and MCP turn
  metadata with strict automatic review enabled.

GitOrigin-RevId: 8e134b3d17a19dc62b3b56076d2cd05a54c9f638
2026-08-12 03:00:47 +00:00
Charlie Marsh
eb9dceba1a Avoid cloning MCP invocations in TUI history (#38103)
## What changed

Update MCP invocation formatting to borrow the invocation and its server and
tool names instead of cloning them when rendering TUI history cells.

GitOrigin-RevId: ac824d86d445215d6b730c6a28b4ec4dfc4f5b8c
2026-08-12 01:54:13 +00:00
wencongli-oai
c909d1bc04 Attach hosted app context to file uploads (#38101)
## What changed

- Include the connector ID, action name, and model in file creation requests for hosted app tool calls.
- Use the file size returned by upload finalization when available, while falling back to the local size for older server responses.
- Keep upload finalization requests empty for compatibility with older servers.

## Testing

- Cover hosted app upload metadata and legacy finalization responses.

GitOrigin-RevId: 1bc834736db4fe3515f8224965cde0e5d6955ca3
2026-08-12 01:45:20 +00:00
Dylan Hurd
ca4d532b2a Test Guardian context for code mode commands (#38094)
## What changed

Add integration coverage verifying that Guardian receives both the user prompt
and the outer code mode `exec` source when reviewing a nested escalated
`exec_command` call.

GitOrigin-RevId: e78e9d4d69e7ebccc935c548565a07600659f65a
2026-08-12 00:46:11 +00:00
Owen Lin
da2803c73c Simplify queued user message admission (#38092)
## What changed

- Resolve user message admission when Core accepts the input as a new turn or a steer, without waiting for rollout persistence.
- Remove persistence- and hook-specific admission errors and task bookkeeping.
- Delete queued messages after Core accepts them for turn processing, including messages subsequently stopped by a prompt hook.

## Testing

- Update concurrent admission and queue service tests for acceptance-based admission.

GitOrigin-RevId: 7dcc311cfecd3d710733b420f2add546edb86153
2026-08-12 00:41:53 +00:00
stevenlee-oai
4c89139da9 Add CIMD support to MCP OAuth registration (#38089)
## What changed

- Make automatic MCP OAuth registration prefer Client ID Metadata Documents
  (CIMD) when the authorization server advertises support for public clients and
  Codex is using its native loopback callback. Fall back to advertised Dynamic
  Client Registration (DCR) otherwise.
- Add explicit `cimd` and `dcr` registration overrides to the CLI and app-server
  OAuth login API. Validate CIMD metadata and callback URLs before starting the
  authorization flow.
- Use a callback-specific Codex client metadata URL for CIMD and retain the
  exact redirect URI through authorization and token exchange.

## Testing

- Cover automatic and forced CIMD selection, DCR fallback, invalid metadata and
  redirects, token refresh, authenticated MCP requests, and conformance
  regression checks.

GitOrigin-RevId: 4238372ca53b0f38e781e141ab5da97e0a6ddf45
2026-08-12 00:01:01 +00:00
Channing Conger
85f331772f Route gRPC code-mode sessions through the shared HTTP client (#38087)
## What changed

- Build URL-based gRPC code-mode connections with `HttpClientFactory` so they support the application's outbound proxy and custom CA configuration.
- Accept `http` and `https` origins while rejecting endpoints with unsupported schemes, paths, queries, or fragments.
- Preserve custom tonic channel injection and gRPC frame-size limits through the new transport adapter.

GitOrigin-RevId: 142f0b572b3ab0154e8fe860cb304752a9af5784
2026-08-11 23:40:07 +00:00
sayan-oai
f4936d7aba Support execution-host context when resolving cloud config (#38086)
## What changed

- Add a scoped `AbsolutePathBufGuard::with_home_directory` override so `~`
  paths can resolve against an explicitly supplied home directory while
  preserving the existing base-directory behavior. Nested overrides restore
  the previous home directory.
- Expose `compose_requirements_for_hostname` so callers can evaluate
  `remote_sandbox_config` for a supplied execution-host hostname.
- Cover cloud bundle conversion with execution-host path expansion and
  hostname-specific sandbox requirements.

GitOrigin-RevId: 6fd486992b45ff92e22bb4073b888252b544f285
2026-08-11 23:31:26 +00:00