Commit Graph
9053 Commits
Author SHA1 Message Date
Channing Conger c0ad3ab014 Add gRPC TCP transport to the code-mode host (#37745)
## What changed

- Accept `grpc://IP:PORT` endpoints through `--listen` and serve the existing
  code-mode gRPC service over TCP.
- Print the bound HTTP endpoint to stdout so callers can discover the port when
  binding to port `0`.
- Apply the protocol frame-size limits and disable Nagle's algorithm on accepted
  connections.

## Testing

- Add an end-to-end test that starts the host on an ephemeral port, connects a
  gRPC client, and opens a session.
- Verify accepted gRPC sockets have `TCP_NODELAY` enabled.

GitOrigin-RevId: 51d6c21dff8cffb47068c0677ba10ff370385cec
2026-08-09 23:39:25 +00:00
charlesgong-openai 50ef7395fa Report I/O subtypes for session config import failures (#37723)
## What changed

- Append a stable `std::io::ErrorKind` category to the
  `failed_to_load_session_config` subtype, including categories such as
  `invalid_data`, `not_found`, and `permission_denied`.
- Propagate the categorized subtype through session import failure reporting.

## Testing

- Add an app-server test that verifies an invalid config reports
  `failed_to_load_session_config_invalid_data` in both the import completion
  notification and analytics event.

GitOrigin-RevId: e9a1a7cd36979911f422805180dd91b6ed65e14e
2026-08-09 18:42:06 +00:00
Charlie Marsh a16863f870 Keep wrapped composer whitespace with following text (#37709)
## Why

Overflowing whitespace in the TUI composer could occupy a separate blank row
instead of remaining attached to the text that follows it.

## What changed

- Add composer-specific, grapheme-safe wrapping that keeps breakable Unicode
  whitespace with the following word while preserving semantic breakpoints such
  as hyphens and nonbreaking spaces.
- Preserve cursor insertion rows and positions as content reflows, including
  across full lines and wrapped fragments.
- Keep wrapping linear for maximum-length unbroken input.

## Testing

Add focused rendering and cursor tests for ASCII and Unicode whitespace,
hyphenated words, reflowed fragments, and maximum-length input.

GitOrigin-RevId: fb7713e33bfddf37460b6c2f6f0c9700f31d86bf
2026-08-09 15:49:17 +00:00
sayan-oai 646f7c0a91 Advertise environment config read support (#37654)
## What changed

- Add `environmentConfigRead` to exec-server environment capabilities and advertise it for local executors.
- Default the capability to `false` when deserializing responses from older executors.

## Testing

- Verify legacy capability responses remain compatible and the environment config integration reports support.

GitOrigin-RevId: c2110fea9e0e6e756eaeaaad096c50a943668c99
2026-08-09 03:05:10 +00:00
charlesgong-openai 94937de51b Improve plugin install failure analytics (#37645)
## Why

Plugin install failures need stable, low-cardinality details that distinguish
actionable causes without relying on error messages.

## What changed

- Add HTTP status subtypes for remote catalog, mutation, and bundle download
  failures, including specific common statuses and a general `http_5xx` bucket.
- Emit failure analytics when a remote plugin is disabled by an administrator or
  unavailable under its install policy.
- Preserve marketplace I/O, configuration, and task failure subtypes, including
  failures that occur before a plugin ID can be resolved.

## Testing

Add app-server coverage for catalog and install HTTP failures, unavailable
remote plugins, unreadable marketplace files, and oversized bundle error
responses.

GitOrigin-RevId: 71a4888c492d1806bf4ff92bebc48f40cfb89300
2026-08-09 01:03:34 +00:00
Abhinav a875dd6b22 Generalize hook handler execution (#37644)
## What changed

- Represent configured handlers by handler kind and route execution through the
  hooks engine, while preserving command hook behavior.
- Reject MCP tool inputs containing values such as `null` that cannot be
  represented in TOML for trust hashing.

## Testing

- Add coverage for rejecting `null` at the top level and within nested MCP tool
  input objects and arrays.

GitOrigin-RevId: 3854a349c2a721691450467592f99cf57e6260ef
2026-08-09 00:57:15 +00:00
sayan-oai 420accf199 Use the step context for command approval prefix rules (#37641)
## What changed

Read `allow_prefix_rules` from the turn attached to the active step context
when selecting the exec policy and constructing unified exec approval requests.

GitOrigin-RevId: d2d26e88b9cefa28bb2df5b9f71aa7b30b7ea331
2026-08-09 00:29:14 +00:00
Eric Traut 266c6920d9 Include buffered turns when editing prompts (#37622)
## Why

Prompt editing looks up the selected user message in the thread's turns, but
new live turns may still exist only in the replay buffer.

## What changed

Reconstruct buffered turns from turn and item notifications before locating
the prompt to edit. Preserve completion metadata and avoid duplicating turns
or items already present in the snapshot.

## Testing

Extend the prompt-edit fork test to cover a selected turn supplied through the
replay buffer and verify that the source thread remains unchanged.

GitOrigin-RevId: e357098085a4def871f3df65b6721a31e07b737f
2026-08-08 21:01:19 +00:00
sayan-oai dd43a9967f Use step environments for Guardian approval reviews (#37618)
## Why

Deferred environments can become ready after a turn starts. Guardian approval
reviews must use the environment selected for the current step so their working
directory and permission context are not taken from the stale turn snapshot.

## What changed

- Carry `StepContext` through tool execution and approval handling.
- Add a Guardian review context that pairs the parent turn with the current
  step's environment snapshot.
- Use that snapshot for Guardian prompts, reviewer sessions, and delegated
  reviewer threads while retaining turn-level fallbacks for callers without a
  step context.

## Testing

Added an integration test that makes a deferred remote environment ready before
an escalated command and verifies Guardian receives that environment's working
directory and denied-read policy instead of the initial local environment's.

GitOrigin-RevId: 779096bc7d0e0c7453a009c02141029714b9b407
2026-08-08 20:07:27 +00:00
cooper-oai 936f5eb3ee Add workload identity token exchange support (#37610)
## What changed

- Add the `codex-workload-identity` crate for exchanging a file-backed JWT assertion and federation rule ID for short-lived ChatGPT credentials.
- Cache valid access tokens, refresh them before expiry or after rejection, and coalesce concurrent exchanges. Continue using a still-valid cached token when a proactive refresh fails transiently.
- Validate assertion files, token endpoints, and exchange responses; honor outbound proxy policy for HTTPS endpoints and redact access tokens from debug output.

## Testing

- Cover request encoding, assertion rotation, caching, concurrent refreshes, transient-failure fallback, configuration validation, and malformed inputs and responses.

GitOrigin-RevId: 5496851683c2dcf6aaad6840053b97f7c0be076e
2026-08-08 17:18:02 +00:00
cooper-oai c4513cb982 Prevent launch context from reaching child processes (#37607)
## Why

Model-reachable child processes should not inherit Codex launch context.

## What changed

- Treat `OPENAI_FEDERATION_RULE_ID` and `OPENAI_IDENTITY_TOKEN_FILE` as non-inheritable environment variables, with case-insensitive matching.
- Remove them after shell environment policy overrides and before spawning commands across execution, MCP, hooks, Git helpers, and remote helper processes.

## Testing

- Cover inherited and explicitly configured variants, including mixed-case names.
- Verify the variables are absent from real child environments and app-server command and process execution.

GitOrigin-RevId: 2535527893985fef0995617f4c5b2462bea7c136
2026-08-08 16:58:26 +00:00
Abhinav 3aae5d885b Expose execution mode in hook listings (#37538)
## What changed

- Add `executionMode` to `HookMetadata` returned by `hooks/list`, with `sync` as the default for compatibility.
- Propagate each discovered hook's `sync` or `async` mode through the app-server protocol and generated schemas.
- Show the execution mode in the TUI hooks browser.

## Testing

- Cover async and default-sync modes in `hooks/list` tests and TUI snapshots.

GitOrigin-RevId: 9c9f2890798fe417face76c15847616b2dea9db4
2026-08-08 04:57:06 +00:00
Abhinav 6f647caa9b Support asynchronous command hooks (#37533)
## Why

Hook configurations can mark command handlers as asynchronous, but Codex previously skipped those handlers outside `SessionEnd`.

## What changed

- Run asynchronous command hooks in the background with a per-session concurrency limit, while keeping `SessionEnd` hooks synchronous.
- Prevent asynchronous hooks from blocking, stopping, rewriting, or otherwise controlling the operation that launched them.
- Deliver warnings and additional context at safe turn boundaries: inject results into an active turn after sampling, or buffer them ahead of the next user prompt when the session is idle.
- Preserve in-flight hooks across configuration reloads, scope spilled output to the thread, and abort outstanding work during session shutdown.

## Testing

Add unit and integration coverage for background scheduling, concurrency, output parsing, active and idle result delivery, configuration reloads, and shutdown cleanup.

GitOrigin-RevId: 8094552e4afe7b47b09a61bb575bb20f4e491d8d
2026-08-08 04:24:12 +00:00
Channing Conger 61a3dd4387 Implement the gRPC code-mode host service (#37530)
## What changed

- Export `GrpcCodeModeHost` as a transport-independent implementation of the
  code-mode gRPC API.
- Support leased sessions, execution and wait lifecycle operations, filtered
  nested tool-call subscriptions, tool completions, and notification
  acknowledgements.
- Share host-wide request and active-cell limits across the existing and gRPC
  transports, and bound identifiers, metadata, subscriptions, and pending
  callbacks.

## Testing

- Add coverage for request conversion, ordered callback routing, cancellation,
  session cleanup, backpressure, malformed input, and resource-limit handling.

GitOrigin-RevId: f146ba7e6fe4e4aa02f25dd3f961120980516d0e
2026-08-08 04:13:55 +00:00
stefanstokic-oai f65ea998c7 Keep external agent detection from blocking config requests (#37528)
## Why

External agent detection can spend time reading session transcripts. Sharing the
configuration serialization queue causes unrelated configuration requests to
wait for detection to finish.

## What changed

- Give `externalAgentConfig/detect` its own global serialization queue.
- Keep configuration reads, requirements reads, writes, and external agent
  imports responsive while detection is still running.

## Testing

Add a Unix app-server test that blocks transcript detection on a FIFO and
verifies the unrelated requests complete before detection is released.

GitOrigin-RevId: d2764dcdb0e96d810c790c570c48fa45690a3dc1
2026-08-08 03:52:37 +00:00
Abhinav dd916428cd Terminate timed-out hook process trees (#37527)
## Why

Timing out a command hook can leave descendant processes running after the hook itself is stopped.

## What changed

- Run hook commands in a process group on Unix and a job object on Windows.
- Terminate the full process tree when hook execution is cancelled or fails, with `taskkill` as a Windows fallback.
- Preserve descendants when a hook completes successfully so intentionally detached helpers can continue running.

GitOrigin-RevId: 1a18653d34c6f1685ef8c4f8e8546663b276292a
2026-08-08 03:48:34 +00:00
Won Park 2e3a1702c2 Expose auto-review ignore rules in config requirements (#37519)
## What changed

- Add `ignoreRules` to `AutoReviewRequirements` in the app-server v2 protocol and generated schemas.
- Return configured `auto_review.ignore_rules` values from `configRequirements/read`.
- Document that listed models ignore saved command-prefix approvals.

## Testing

- Extend config mapping and RPC tests to cover `ignore_rules`.

GitOrigin-RevId: ed74fbba7693176fe09b161bbee2cb27847e0e1e
2026-08-08 01:37:02 +00:00
andrewgu-oai e734a1a5c1 Ignore reusable command approvals for cyber models (#37516)
## What changed

- Filter saved `allow` prefix rules from the execution policy for cyber-specialized models and models listed in `auto_review.ignore_rules`, while preserving prompt, forbidden, network, and host-executable policy entries.
- Apply the filtered policy consistently to permission instructions, shell commands, unified exec, and the zsh-fork backend.
- Limit cyber-model command approvals to one-time decisions without proposing reusable policy amendments. General models continue to honor saved prefixes, including after switching models within a thread.

## Testing

- Add policy-level coverage for filtering allow-prefix rules while retaining restrictive and network rules.
- Add end-to-end coverage across shell and unified exec paths, zsh-fork execution, user and automatic review, and model switching.

GitOrigin-RevId: f3bd3872424291b12354ec415f33986ec369a368
2026-08-08 00:59:39 +00:00
Won Park c2bcb9a26b Reuse parent compactions in Guardian review sessions (#37513)
## What changed

- Add the under-development `guardian_reuse_parent_compaction` feature.
- Restart Guardian review sessions after parent history rewrites and seed them with the latest encrypted compaction that has a response item ID.
- Keep the existing reviewer when a rewritten history has no reusable compaction, preserving authorization and restriction context held by that session.

## Testing

- Cover reuse-key invalidation and compaction eligibility.
- Verify review-session behavior across parent compaction and a subsequent summary-free history reset.

GitOrigin-RevId: 891805d3c3dca34ddda6e3bfc5097be4ff164267
2026-08-07 23:49:12 +00:00
viyatb-oai 208f05b233 Enforce automatic review for managed models (#37511)
## What changed

- Add the managed `auto_review.required_on_models` requirement, unioning model slugs across requirement layers and exposing the result through `configRequirements/read`.
- Force listed models to use `on-request` approvals with the `auto_review` reviewer. Downgrade Full Access to workspace-write when starting a protected session, and reject incompatible runtime overrides or use when automatic review is disabled.
- Preserve these protections across thread starts, resumes, forks, model changes, turn overrides, MCP approvals, and TUI session attachment.

## Testing

- Add coverage for layered model requirements and exact provider-alias matching.
- Add app-server tests for protected thread lifecycle operations, unsafe setting overrides, legacy thread upgrades, disabled automatic review, and requirements API output.

GitOrigin-RevId: c4b1d52c3b5b75e86880725412b8f0812e0dfcd9
2026-08-07 23:43:14 +00:00
Channing Conger 8073dbb20b Define the code-mode host gRPC protocol (#37510)
## What changed

- Add the `codex.code_mode.v1` protobuf API for managing code-mode sessions, executions, waits, tool callbacks, notifications, and content results.
- Generate and export the Rust client/server bindings with `tonic` under Cargo.
- Add Bazel protobuf targets and a `prost` toolchain that uses the workspace's Rust runtime versions.

GitOrigin-RevId: 51d9d044e01dab2f4d25ab79aa7a52585485eee3
2026-08-07 23:27:39 +00:00
sayan-oai 4ca25a2c4e Include sandbox mode in response metadata (#37507)
## What changed

- Add the effective permission profile as `sandbox_mode` in turn metadata for regular, prewarm, compaction, and detached memory requests.
- Reserve `sandbox_mode` so client-provided metadata cannot override the computed value.

## Testing

- Cover metadata headers and request bodies for read-only and danger-full-access modes.

GitOrigin-RevId: 13c690cc99bc2691023f281ca527af049bb1286f
2026-08-07 22:41:20 +00:00
felixxia-oai 45f8cafa4e Remove the codex-core-skills crate (#37505)
## What changed

- Move `SkillLoadOutcome` and its implicit-path indexing into
  `codex-skills-extension`.
- Import shared skill types directly from `codex-skills` and keep the skill
  prompt size limit with the extension renderer that uses it.
- Remove `codex-core-skills` from the Cargo workspace and dependent crates.

GitOrigin-RevId: 4e9e84909fa2f692bcc94af990bb4671affd776f
2026-08-07 21:36:33 +00:00
Sean Huang abc5d0b552 Disable Nagle's algorithm for code-mode WebSockets (#37504)
## Why

Code-mode WebSocket connections are latency-sensitive, so buffering small TCP
writes can delay request and response traffic.

## What changed

- Enable `TCP_NODELAY` on outbound remote-session WebSocket connections.
- Enable `TCP_NODELAY` on sockets accepted by the code-mode host, logging a
  warning if the socket option cannot be set.

## Testing

- Add a listener test that connects to the host and verifies the accepted
  socket has `TCP_NODELAY` enabled.

GitOrigin-RevId: e51c781c4b47c6a4ae1c32c93cd79768719a68d9
2026-08-07 21:10:49 +00:00
felixxia-oai beac16cccd Move host skill prompt injection into the skills extension (#37503)
## What changed

- Add `HostSkillsSnapshot::load_skill_prompts` so the skills extension owns reading and rendering selected host skills.
- Keep explicit invocation telemetry, unreadable-skill warnings, plugin prompt ordering, and suppression of host prompts superseded by provider prompts.
- Remove the legacy prompt injection and fragment implementation from `codex-core-skills`.

## Testing

- Cover prompt truncation without an installed skills extension, skill/plugin ordering, selective provider supersession, unreadable skills, and contextual fragment detection.

GitOrigin-RevId: 9c8b84ad54b90d174abc287ab49cc5a231e9e1aa
2026-08-07 21:04:16 +00:00
rka-oai 8e4b10446e Remove the legacy code-mode tool metadata inventory (#37500)
## What changed

- Stop adding `code_mode_tool_names` to Responses Lite turn metadata.
- Keep `code_mode_tool_names` reserved so client metadata cannot reintroduce the removed, unbounded inventory.
- Use the opt-in `tool_namespaces_info` metadata, including each function's `code_mode_name`, when authoritative tool details are requested.

## Testing

- Update Responses Lite and code-mode tests to verify the opt-in namespace metadata and normalized code-mode names.

GitOrigin-RevId: cbfb9af984de71c7cc175d0cd47ae799a5275309
2026-08-07 20:26:08 +00:00
Eric Traut 6db53df37f Preserve child waiters during process termination (#37498)
## Why

Aborting the child waiter during termination can leave an exited PTY child
unreaped and prevent the session from recording its exit status.

## What changed

- Detach the child waiter instead of aborting it when terminating or dropping a
  `ProcessHandle`, while continuing to abort the I/O helper tasks.
- Cover explicit termination and handle drops for pipe processes, plus queued
  PTY waiters and PTY process-group termination on Unix.

GitOrigin-RevId: 313787f4edec80b30cf5a78f0cc6733f1520d9a4
2026-08-07 20:10:08 +00:00
dshakiba-OAI 62b7386b07 Limit payload traces in diagnostic logs (#37497)
## Why

High-volume request and streamed-response payloads can overwhelm the SQLite log database and diagnostic ring buffer used for reports.

## What changed

- Limit HTTP transport, SSE, and WebSocket diagnostics to `DEBUG` in persistent log sinks while leaving unrelated trace diagnostics available.
- Log known unhandled response events and delta events at `TRACE`, and surface unexpected event kinds at `DEBUG` without including their payloads.
- Report structured parse-error metadata instead of logging an unparseable SSE payload.

## Testing

- Cover filtering for transport, SSE, WebSocket, and unrelated trace records in both report and SQLite log sinks.
- Cover unknown and unsupported delta response events.

GitOrigin-RevId: 6d9121e093ddadf6834da394df544d9c09d8aeb9
2026-08-07 19:56:29 +00:00
Evan Fannin 41014b11bd Add MCP event discovery and subscriptions (#37494)
## What changed

- Expose hosted Plugin Runtime event definitions through `McpResourceClient::list_events`.
- Add cancellable `events/stream` subscriptions that route lifecycle notifications to the matching request and cancel when the stream is dropped.
- Bound event notification and queue sizes, time out stalled response headers, and close streamable HTTP responses locally on cancellation.

## Testing

- Add streamable HTTP integration coverage for isolated concurrent subscriptions, local cancellation, and stalled response-header timeouts.

GitOrigin-RevId: 98c6fffa8f004eb2638c1b0705f659222cbbdfdb
2026-08-07 19:36:52 +00:00
rka-oai 2b1811e562 Include tool namespace inventory in turn metadata (#37492)
## What changed

- Add opt-in `tool_namespaces_info` metadata for Responses Lite turns when
  `tool_registry.turn_metadata_includes_tool_info` is enabled.
- Describe each model-visible function's namespace, direct and deferred
  exposure, Code Mode name, and harness or MCP ownership.
- Reject visible namespaces shared by different owners when strict collision
  checking and tool inventory metadata are enabled.
- Keep tool inventories out of compatibility headers and metadata sent to MCP
  servers.

## Testing

- Cover opt-in behavior, MCP exposure details, namespace ownership collisions,
  reserved metadata handling, and Responses Lite request serialization.

GitOrigin-RevId: 6a6965d2ba98e29444fdfbb4ccec6aafcf0391e6
2026-08-07 19:32:15 +00:00
rphilizaire-openai ba94150c2a Alias resource-backed skill locators under context pressure (#37489)
## Why

Long executor and orchestrator resource identifiers can consume enough of the
skills context budget to omit otherwise available skills.

## What changed

- Add source-aware root aliases for executor, orchestrator, and host skill
  catalogs, including catalogs with a single shared root.
- Select the best combination of aliased catalogs under the shared metadata
  budget while accounting for root tables and alias usage instructions.
- Explain how to expand shortened `skill://` locators and accept the resulting
  description-shortening warning in app-server coverage.

## Testing

- Add rendering and production-turn coverage for singleton, executor,
  orchestrator, host, and combined catalog aliases.

GitOrigin-RevId: c1bc1f3d371eae9526232674060235272cc28f16
2026-08-07 19:09:46 +00:00
rphilizaire-openai ce22ea9712 Generalize skill locator aliases across providers (#37488)
## What changed

- Compact executor and orchestrator skill locators under metadata pressure, using provider-specific `e` and `o` aliases alongside host `r` aliases.
- Derive alias roots from executor discovery paths and orchestrator namespaces while preserving host plugin root handling.
- Centralize alias ordering, deduplication, and longest-prefix matching across skill providers.

## Testing

- Cover alias planning, cross-platform executor roots, and host plugin discovery.

GitOrigin-RevId: e7d15bd3891c08ae20170e96c4ad45c76d353707
2026-08-07 19:04:39 +00:00
jif 27e4a05cd3 Expose runtime activity in server diagnostics (#37486)
## What changed

- Add lifecycle-backed gauges for in-flight and queued app requests, pending server requests and mailbox messages, active turns, and live MCP connections.
- Register each gauge on first use and decrement it when the tracked work or resource is dropped.
- Document the new `server/diagnostics` gauge names and account for the diagnostics request itself in the response example and test.

GitOrigin-RevId: 4bb82a3918af0b502d149b5d761ad669b2083f39
2026-08-07 18:38:24 +00:00
jif 5a0d0929e2 Keep response streams alive through connection failures (#37485)
## What changed

- Classify HTTP connection failures separately from other network errors without exposing request URLs.
- For sampling requests, retry connection failures with exponential delays from 5 to 60 seconds and show a `Reconnecting... waiting for network` stream error.
- Preserve the normal stream retry budget while waiting for the provider to become reachable. Keep the existing bounded retry behavior for other retryable errors.

## Testing

- Verify connection errors are classified without leaking URL contents.
- Verify a turn recovers after its provider becomes reachable and still applies the configured retry limit to a subsequent incomplete stream.

GitOrigin-RevId: 646553290c865a1332abd30c4a64ed9266bbfc6f
2026-08-07 18:33:46 +00:00
pakrym-oai 509565820f Interrupt active code-mode cells with their turn (#37483)
## Why

Interrupting a turn should also stop code-mode work that the turn left running.

## What changed

- Add the disabled-by-default `code_mode_interrupt` feature.
- When an interrupted turn has the feature enabled, terminate all active code-mode cells and propagate cancellation through nested tool calls.
- Keep the reusable code-mode session alive so its stored state remains available to later turns.

## Testing

Add an integration test that interrupts a long-running nested tool, verifies that active and background cells are removed, and confirms that session state is preserved.

GitOrigin-RevId: 2b8634776a89b636318a39b9e9ad2eefc07cead8
2026-08-07 18:22:42 +00:00
iceweasel-oai 511262b984 Delegate remote process sandboxing to the executor (#37480)
## What changed

- Preserve executor-native working directories, workspace roots, and permission profiles when preparing remote `exec_command` requests instead of resolving them through the host platform.
- Send sandbox intent to the remote executor, including a restricted-token default for Windows executors and `-NoProfile` for elevated PowerShell commands.
- Reject intercepted cross-platform `apply_patch` commands when filesystem writes are restricted, while continuing to allow them for unsandboxed or full-disk-write profiles.

## Testing

Extended remote unified-exec coverage for foreign Windows workspaces, elevated PowerShell, sandbox metadata, and restricted and unrestricted intercepted patches.

GitOrigin-RevId: 9fd328879fa2c15594fd58e40b6b32e8ba0847e7
2026-08-07 18:05:17 +00:00
iceweasel-oai 92fb33b758 Report temporary directories in exec-server environment info (#37479)
## What changed

- Add optional `temporaryDirectories` file URIs to `EnvironmentInfo` so clients can resolve `:tmpdir` against executor-local defaults.
- Populate local environment info from `TMPDIR` on Unix and `TEMP`/`TMP` on Windows, resolving relative Unix paths against the working directory and removing duplicates.
- Cover protocol round trips, platform environment discovery, relative Unix paths, and the exec-server response.

GitOrigin-RevId: a41580f783b004011c064c7a4f9fdc7adf4fba10
2026-08-07 17:54:41 +00:00
andrewgu-oai 204389afcc Shard state unit tests under Bazel (#37478)
## Why

Windows runs the state crate's database-heavy Rust tests serially within each
shard.

## What changed

Configure `state-unit-tests` to run across four Bazel shards.

GitOrigin-RevId: f540f3c157734a2b9944bae9af554ad9dbc4a69b
2026-08-07 17:49:48 +00:00
tongzhou wang 248d8c0e22 Include call IDs in MCP requests and clarify metadata config (#37477)
## What changed

- Add the tool call ID to `_meta.callId` for every MCP tool request.
- Rename `features.tool_registry.include_tool_metadata` to
  `features.tool_registry.turn_metadata_includes_tool_info` to clarify that the
  setting controls authoritative tool information in per-turn metadata.
- Update config parsing, schema generation, and session config locking for the
  renamed setting.

## Testing

- Cover `callId` metadata for custom, plugin, and Codex Apps MCP calls.
- Update strict-config, config-loading, feature-config, and config-lock tests for
  the renamed setting.

GitOrigin-RevId: ac0e58c489b03bd9b55a356f545de86c8ecaf865
2026-08-07 17:44:05 +00:00
jif 5729546839 Expose app-server diagnostics through the experimental API (#37470)
## What changed

- Add the experimental `server/diagnostics` request, returning the app-server process ID, resident memory, platform-dependent physical footprint, and registered diagnostic gauges.
- Export the new protocol types in the generated JSON and TypeScript schemas and document the request.

## Testing

- Verify the response includes process measurements and the registered live-thread gauge.
- Verify the request is rejected unless `capabilities.experimentalApi` is enabled.

GitOrigin-RevId: 099d60a9c421a74ff1a72fe524e0dfeb89cf1057
2026-08-07 16:57:47 +00:00
felixxia-oai b3278e96cb Move skill config rule resolution into codex-config (#37466)
## What changed

- Define skill config selectors, ordered rules, and layer-stack parsing in `codex-config`.
- Resolve disabled skill paths from generic skill name/path pairs, so configuration logic no longer depends on `SkillMetadata`.
- Update plugin and host skill consumers to use the `codex-config` API and consolidate the rule tests with the skill config tests.

GitOrigin-RevId: 3fe67869708df2652befe28d58cdeba933256f84
2026-08-07 16:20:38 +00:00
felixxia-oai 3b366654f1 Remove the unused remote skills client (#37461)
## What changed

- Remove the unused `core-skills` client for listing and exporting remote
  skills.
- Remove its `codex-core-skills` and `codex-core` exports and dependencies that
  are no longer needed.

GitOrigin-RevId: 747f760dc97da3d4dea10d619a2341f43410d0bf
2026-08-07 15:38:22 +00:00
felixxia-oai 33e365b19e Remove the legacy core skill loader (#37457)
## What changed

- Use `HostSkillRoot` throughout host root resolution and loading, including plugin roots.
- Remove the duplicate loader, root snapshot, and product-filtering implementation from `core-skills` now that loading is owned by the skills extension.
- Move and expand loader coverage for discovery, namespaces, filesystem routing, root merging, symlinks, and frontmatter parsing.

## Testing

- Added focused unit and integration tests under `ext/skills` and `skills` for the consolidated loader behavior.

GitOrigin-RevId: 214d06d59bf3033ee0f220ea5959ee4feff66782
2026-08-07 15:16:06 +00:00
felixxia-oai c5d9431971 Unify plugin skill loading through the shared loader (#37452)
## What changed

- Route plugin inventory loading and capability summaries through the injected
  `SkillRootLoader`.
- Preserve recursive discovery for legacy plugins while restricting agent-plugin
  skill discovery to direct children of the skills root.

## Testing

- Verify `plugin/read` excludes nested agent-plugin skills.
- Verify installed agent-plugin telemetry reports skills only for portable,
  direct-child layouts.

GitOrigin-RevId: 9e78dd0c70a632d510c780963a6ceb3ad4bc2522
2026-08-07 14:35:42 +00:00
felixxia-oai a9d59d8b8e Respect plugin skill availability in tool suggestions (#37447)
## Why

Plugin suggestions should report skills only when the plugin has an enabled skill.

## What changed

- Load suggestion metadata through the shared plugin skill-root loader.
- Apply skill configuration when setting `has_skills` on suggestion candidates.

## Testing

Added coverage for local plugin suggestions with the plugin skill both enabled and disabled.

GitOrigin-RevId: bceb14528c9042b474eaad6efaf919bef72e0ca4
2026-08-07 14:17:14 +00:00
jif 964a227d8c Preserve base instruction provenance across sessions (#37446)
## Why

Persisted base instructions need to retain whether they were explicitly customized or generated from a model template. Without that distinction, forks and config-lock replays can treat model-generated instructions as custom and keep the wrong template after a model or personality change.

## What changed

- Record custom or model provenance with base instructions in rollouts and config locks.
- Preserve custom instructions across model changes, while allowing model-generated instructions to follow the selected model and personality.
- Keep legacy rollouts without provenance compatible and propagate provenance through forks and spawned agents.

## Testing

- Cover provenance serialization and legacy rollout decoding.
- Cover role personality changes, forked model changes, config-lock replay, and multi-agent configuration.

GitOrigin-RevId: 801c26559835f558027ce5112700c0cd31fcb21b
2026-08-07 14:08:13 +00:00
felixxia-oai e58d9ef447 Unify plugin skill loading with the host skill service (#37444)
## What changed

- Inject the host skill loader into `PluginsManager` so plugin discovery and agent turns use the same loading and product-policy behavior.
- Share plugin skill snapshots across those paths, preserving a consistent view of skills across workspaces.
- Apply migrated-command precedence after product filtering, allowing an eligible migrated command to replace a filtered native skill with the same name.

## Testing

- Add coverage for product-restricted plugin skills, native-versus-migrated command precedence, and the skills exposed to agent turns.

GitOrigin-RevId: f5ef0d0766ebeeb30d73ffaf044d003c2906ea4d
2026-08-07 13:54:24 +00:00
felixxia-oai e75a1888d7 Load plugin skill roots through the host skills service (#37440)
## What changed

- Implement `SkillRootLoader<PluginSkillRoot>` for `HostSkillsService`.
- Load roots concurrently while preserving request order, product restrictions, cached snapshots, skill errors, and per-skill filesystem metadata.
- Deduplicate overlapping roots and prefer native plugin skills over migrated commands with the same plugin ID and skill name.

## Testing

- Cover native and migrated skill precedence, nested and overlapping roots, product filtering, snapshot reuse, error propagation, and symlinked migration roots.

GitOrigin-RevId: 2270d10616b3a0463852c563ee071c524cd11e6b
2026-08-07 13:23:23 +00:00
felixxia-oai a4b129eb3e Add shared skill root loading interfaces (#37439)
## What changed

- Add `SkillRootLoader` and its request/result types to `codex-skills` so skill roots can be loaded through a shared, object-safe interface.
- Add owner-managed snapshot cache handles that support reuse and use cache allocation identity for equality and hashing.
- Move `SkillError` into `codex-skills` and re-export the new loading API.

## Testing

- Verify snapshot sharing and identity semantics.
- Verify loaders can be used as shared trait objects.

GitOrigin-RevId: a26a8101008a6c862824a7346cdbe6d05f4bcc01
2026-08-07 12:47:14 +00:00
jif a7dcd20d38 Add process diagnostics snapshots (#37434)
## What changed

- Add a `codex-diagnostics` crate that snapshots the process ID, available
  resident-memory measurements, and registered process-wide gauges.
- Provide guards that update gauges for the lifetime of measured objects.
- Track live `CodexThread` instances with the `core.threads.live` gauge.

## Testing

- Add unit coverage for gauge registration, guard lifetimes, process memory
  snapshots, and live-thread reporting.

GitOrigin-RevId: 3236b086bd4ebe31ed4768ab87a5fa288b0891b0
2026-08-07 11:30:17 +00:00