Commit Graph
6001 Commits
Author SHA1 Message Date
Sean Huang e963cab11a Add code-mode output truncation protocol contracts (#57272)
## What changed

Add session options for client- or server-owned output truncation and optional `max_output_tokens` budgets for wait and terminate observations. Introduce `TerminateRequest` and update session implementations and callers to use it.

Extend the stdio and gRPC schemas with optional truncation settings and budgets, and define the `bounded-output-v1` capability. Existing sessions retain client-side truncation; providers reject server mode by default. This change defines the contracts without enabling server-side truncation.

## Testing

Extend protocol serialization coverage for `outputTruncation: "server"` while preserving existing wire shapes when optional fields are absent.

GitOrigin-RevId: 22145897ea16d385c5ba9e7549109f7a669fceb4
2026-10-26 21:36:35 +00:00
goodman-oai 698599a411 Support model-catalog wording for permission path warnings (#57263)
## What changed

- Add optional `omitted_paths` and `denied_reads` fields to catalog permission messages. The latter requires exactly one `{{ denied_reads }}` placeholder.
- Preserve mandatory denial and no-bypass warnings, path/glob facts, and existing path selection limits. Limit each override to 500 UTF-8 bytes and fall back independently to bundled wording for invalid overrides.
- Pin `i18n-config` to an upstream revision that removes the unmaintained `basic-toml` dependency, updating Cargo and Bazel lockfiles.

## Testing

Add serialization and rendering coverage for sparse values, invalid templates, byte limits, and preserved policy facts. Extend model-switch scenarios to verify that warning wording follows the selected model while preserving request history and permission annotations.

GitOrigin-RevId: f5fa1a978abe07d90917f552c64e7c8fc257c061
2026-10-26 21:20:52 +00:00
Alex Daley 3cacafa0b7 Add incremental skill catalogs behind skill_catalog_deltas (#57262)
## What changed

- Add the disabled-by-default `skill_catalog_deltas` feature flag to append new and updated skills without repeating unchanged catalog entries.
- Share a cumulative metadata budget across executor, cloud, and host catalogs, preserving usage across turns and resume. Removals emit no update and do not refund budget.
- Rebuild the current catalog and reset its budget after compaction, including any required skill root mappings in updates.

## Testing

Add unit and integration coverage for update costs, shared source budgets, feature rollback, and catalog updates across resume and compaction, with a request-history snapshot.

GitOrigin-RevId: e88b4265d7361498113d43fdc2e0260a9f930bbc
2026-10-26 21:20:21 +00:00
swastik-oai bd72161881 Separate apply_patch request preparation from execution (#57261)
## What changed

Extract patch parsing, verification, and permission assessment into request preparation helpers used by the tool handler and intercepted shell patches. Execute the prepared `ApplyPatchRequest` through the existing runtime and derive auto-approval status from its approval requirement.

Move approval action construction onto `ApplyPatchRequest` and update the existing approval tests to use the new helpers.

GitOrigin-RevId: 7f07d38f0dbf2a971c94b897281651b7a174fd05
2026-10-26 21:15:23 +00:00
swastik-oai 51849772f0 Centralize permission request preparation and approval actions (#57260)
## What changed

Introduce `PreparedPermissionRequest` to encapsulate argument parsing, path resolution, permission normalization, and approval action construction. Pass the prepared request, including the selected environment ID, into session permission handling.

## Testing

Extend the selected-environment path resolution test to assert that the prepared approval action carries the expected environment, reason, and resolved permissions, matching the emitted permission request.

GitOrigin-RevId: ebd34fad0e5d4c9f98330d17a6254325526b8c78
2026-10-26 21:14:59 +00:00
Charlie Marsh eb3572f9d7 Avoid unnecessary connector directory work for tool suggestions (#57257)
## Why

Tool suggestions loaded and cloned the cached connector directory even when no candidates remained after excluding accessible apps.

## What changed

- Filter out accessible connectors before loading the directory, skipping the lookup when no candidates remain.
- Share cached directory entries through `Arc<[AppInfo]>` and clone only matching entries for suggestions.
- Preserve placeholder suggestions for candidate connectors missing from the directory.

## Testing

Add coverage for skipping directory lookups with no remaining candidates, sharing cached storage, and preserving directory metadata and missing-connector fallbacks while excluding accessible apps, including disabled ones.

GitOrigin-RevId: acaf3e1564fb4e2b4f805cffe1d7db8e40d5fe3d
2026-10-26 21:08:15 +00:00
Alex Zamoshchin 3ad642e520 Allow disabling plugin discovery prefetch at app-server startup (#57249)
## Why

Hosts that only need installed plugin inventory should be able to skip startup requests for plugin discovery.

## What changed

Add the stable, default-enabled `features.plugin_discovery_prefetch` flag. Setting it to `false` skips startup prefetching of the plugin directory, featured plugins, and recommendations while preserving installed plugin cache refreshes and bundle downloads.

## Testing

Update app-server integration coverage to verify that installed plugin bundles download with discovery prefetch disabled and that no directory, featured, or suggested plugin requests are made during startup. Also cover listing remote marketplaces with the flag disabled.

GitOrigin-RevId: 7cc3072f6045131b9f1acb851f6240db75ac173e
2026-10-26 20:54:08 +00:00
goodman-oai cc6baf9c32 Wait for process completion in the unified exec reuse test (#57244)
Replace the fixed 200 ms sleep in
`reusing_completed_process_returns_unknown_process` with polling until
`write_stdin` reports no process ID, bounded by a 10-second timeout. This
ensures the shell has completed before asserting that reusing its process
ID returns `UnknownProcessId`.

GitOrigin-RevId: c752e9c2c0a419fa5a06ba957bee49dcaeb5d6d2
2026-10-26 20:46:21 +00:00
jif db7516f41b Reduce the default thread unload delay to one minute (#57242)
## What changed

Change the default `thread_unload_delay_secs` from 1800 to 60 seconds. App-server threads become eligible for unloading after one minute with no subscribers and no activity. Update the configuration documentation, schema, and thread manager sample to match.

## Testing

Update the configuration test to cover the 60-second default, zero for immediate unloading, and an explicit 1800-second override.

GitOrigin-RevId: 0da8454eb25a6ef4b7e3665601982d2e0c183f7c
2026-10-26 20:44:30 +00:00
Tamir Duberstein 49d6fe5bd0 Exercise V2 spawning in subagent context inheritance tests (#57238)
## Why

The context inheritance tests enabled `MultiAgentV2` but invoked `spawn_agent` through the V1 namespace, leaving the V2 path untested.

## What changed

- Share a helper that spawns through the V2 namespace, waits for child completion, and identifies the child's request by its thread ID.
- Assert that the child receives inherited instructions in a `developer` message and its task in an `agent_message` addressed to `/root/worker`.
- Test skill instructions both enabled and disabled for parent and child requests, with an explicit skills extension and discovery isolated to the fixture skill.

GitOrigin-RevId: 193fca57398e950acad1f020382dc1bae6453df4
2026-10-26 20:36:17 +00:00
jif f427056ff6 Tag exec_command telemetry with the configured shell snapshot mode (#57235)
## Why

Commands that fall back without using a shell snapshot should remain associated with their configured snapshot mode in telemetry.

## What changed

Add a `shell_snapshot_mode` telemetry tag to `exec_command` with values `disabled`, `v1`, or `v2`. Give `v2` precedence when enabled. The tag records configuration, not whether a command actually used a snapshot.

## Testing

Add parameterized coverage for all four combinations of snapshot feature flags using a non-login command, which cannot use V2 snapshots.

GitOrigin-RevId: 2dd9e79b9e02448938166254ea1b988034a81b5e
2026-10-26 20:27:25 +00:00
Dmitriy Kovalenko 480ab2d006 Add managed enforcement of DELETE journaling on NFS (#57225)
## Why

Existing databases retain their journal mode, so selecting `DELETE` for new NFS databases leaves existing WAL databases unchanged.

## What changed

- Add the managed `unsafe_enforce_sqlite_journal_mode` requirement to migrate existing NFS databases before opening writable pools and require `DELETE` on each connection.
- Share migration code between startup and `codex migrate-nfs-db`, preserving WAL backups and resuming interrupted replacements, including lazily opened databases.
- Hold the migration lock through pool initialization and keep migration failures out of automatic corruption recovery.
- Preserve local logs behavior and skip legacy NFS logs cleanup when enforcement is enabled.

## Testing

Add coverage for requirement precedence, database settings, data and backup preservation across restarts, interrupted replacement recovery, refusal of active WAL databases, migration lock waiting, and local logs remaining in WAL mode.

GitOrigin-RevId: da41ec1b58b1ee8092591cdf8b358280928ff9d4
2026-10-26 20:10:45 +00:00
Felipe Coury 9f622c2abb Wire keyboard selection into transcript overlays (#57223)
## What changed

- Add `tui.keymap.global.select_transcript` with an implicit `leader [` shortcut that follows the configured leader, respects explicit remapping or unbinding, and yields to existing bindings.
- Connect transcript overlays to keyboard selection, including Find, mouse selection, and navigation to the beginning of paged history. Give selection commands priority over remapped pager shortcuts.
- Close selection overlays on exit or after a confirmed copy-and-follow operation, preserving the pending close decision while clipboard confirmation is asynchronous.
- Show selection navigation and copy hints that adapt to the available footer width.

## Testing

Add coverage for shortcut dispatch, remapping, unbinding, and conflicts; overlay exit behavior; selection across history paging; mouse and keyboard selection interaction; and cursor and footer rendering snapshots.

GitOrigin-RevId: 8a920e5fa2b06ff0544d829ba30f8ecb654db0ee
2026-10-26 20:09:54 +00:00
Charlie Marsh 5e3496e0ad Share eligible local stdio MCP connections across chats (#57211)
## What changed

Extend `mcp_connection_sharing` to pool compatible local stdio connections that negotiate MCP `2026-07-28`. Keep legacy servers and servers that request input during startup private.

Preserve each chat's tool catalog and route input requests to the calling chat. Release connections independently for each chat, shutting down the shared server after the final release, and retire pooled connections on forced refresh without interrupting other chats.

## Testing

Add pool, runtime, app-server, and core scenario tests covering protocol gating, startup cancellation, refresh, final-release shutdown, and separate tool visibility and simultaneous input responses across chats sharing one process.

GitOrigin-RevId: 896b107267a20ec1bffccdefca6c40fe2945a022
2026-10-26 19:37:32 +00:00
Charlie Marsh 0bc73bbeb1 Add opt-in protocol discovery for local stdio MCP servers (#57210)
## Why

Stdio servers without `CODEX_MCP_PROTOCOL_VERSION` use the legacy handshake, even when they support MCP `2026-07-28`.

## What changed

- Add the disabled-by-default `mcp_connection_sharing` feature to enable discovery for eligible local stdio servers.
- Recover from failed or late discovery with a fresh handshake when needed, waiting for the previous helper to release resources before restarting.
- Retain a working legacy connection when an upgrade attempt fails for the same account, except on authentication errors.
- Keep tool catalogs separate by protocol and invalidate legacy catalogs when discovery negotiates the modern protocol.

## Testing

Add regression coverage for failed and late discovery, legacy fallback, protocol-specific catalog reuse, message limits, and Windows descendant cleanup.

GitOrigin-RevId: 36c675ef3b81d32fccf06ccbddda2312cfe602c9
2026-10-26 19:37:06 +00:00
taohong-oai 33b16a9306 Report turn critical-path timing in analytics (#57209)
## What changed

Include critical-path capture status and duration totals in `codex_turn_event`, with categories for inference, auto review, user wait, tools, overhead, and unknown time. Count sampling and compaction as inference.

Distinguish `disabled`, `incomplete`, and `complete` capture. Emit null durations for disabled or incomplete capture so missing measurements are not reported as zero. Freeze the completion timestamp so repeated terminal notifications preserve the original measurement window.

## Testing

Add core and analytics tests for capture status, duration reporting, rounding, and repeated completion. Add app-server integration coverage for completed and interrupted turns with default, enabled, and disabled capture.

GitOrigin-RevId: c6c867120ee563ac48584c2f4b12df23acbabe06
2026-10-26 19:35:31 +00:00
taohong-oai 7c997fe2de Attribute approval waits to tool critical-path timing (#57207)
## Why

Automatic reviews and user prompts previously invalidated critical-path captures even when their owning tool invocation was known.

## What changed

Record automatic review time as `auto_review` and waits for approvals, permission requests, and user input as `user_wait` when `CriticalPathTiming` is enabled. Bind timing to the owning invocation before asynchronous work begins, and use the triggering tool's identity for network approvals. Continue invalidating captures when a wait cannot be attributed.

## Testing

Add coverage for cancellation, reused call IDs, network ownership, and disabled capture. Update the automatic review integration test to verify attributed review duration.

GitOrigin-RevId: 0a1f5feebd0c4f5ed67dc058e832ec5f8818db02
2026-10-26 19:28:51 +00:00
Alex Kira 85f29b453a Register the untrusted_as_tool_output feature flag (#57204)
## What changed

Add `untrusted_as_tool_output` as an under-development feature, disabled by default, and expose it in the configuration schema. The flag is intended for rendering client-supplied untrusted context as standalone named tool outputs.

GitOrigin-RevId: 6fe630c8d380a87edb48e08887215c1ec17447ed
2026-10-26 19:27:29 +00:00
Andrei Eternal beb34ce8d0 Preserve command cwd in permission and post-tool hooks (#57203)
## Why

`PermissionRequest` and `PostToolUse` hook inputs could report the turn's working directory instead of the local command's execution directory. This also affected commands whose results were collected in a later turn after the working directory changed.

## What changed

- Report the local command's execution directory in hook input `cwd`, consistent with `PreToolUse`.
- Preserve the original directory through `write_stdin` approvals and delayed completion, including network permission requests.
- Retain the host directory for remote commands and keep hook process working directories unchanged.

## Testing

Add coverage for relative and absolute workdirs, approval denials, command rewrites, completion and stdin approval across turns, remote command fallback, network approvals, and Unix and Windows path formatting.

GitOrigin-RevId: ef5dad2a0634dda9edb2f841ef4fe49ae0d1187d
2026-10-26 19:21:08 +00:00
trpcic-openai 536d1f5b68 Preserve the tool dispatch span across runtime futures (#57202)
## What changed

Instrument the returned tool runtime future with the same dispatch span as the spawned dispatch task, keeping completion and cancellation handling in that span.

## Testing

Extend the detached code-mode callback test to assert that the router's `dispatch_tool_call_with_state` span has `dispatch_tool_call_with_code_mode_result` as its parent.

GitOrigin-RevId: e4d4bef26563554bf703b3e4f05490e25d8eb0ad
2026-10-26 19:20:44 +00:00
taohong-oai f371f9701f Capture direct-tool critical paths behind a feature flag (#57201)
## What changed

Add the default-disabled `critical_path_timing` feature to capture dependency paths for root-agent turns. Connect direct tool dispatch, execution-lock handoffs, and completed tool batches to turn timing so overlapping work shares its common history without double counting.

Omit captures for unsupported dependencies, including CodeMode, agent communication, approval review, and user waits. Settle aborted tasks before freezing timing, invalidate captures on forced teardown, and apply runtime feature changes only to future turns.

## Testing

Add coverage for serial and overlapping tool dispatch, execution-lock dependency handoffs, cancellation, unsupported paths, frozen timing after completion, and configuration refresh boundaries.

GitOrigin-RevId: 71458b654b1c4a05799886928b449c948ea33109
2026-10-26 19:19:10 +00:00
Andrei Eternal fe15bd38de Report the local command working directory in PreToolUse hooks (#57198)
## Why

`PreToolUse` hooks receive the host working directory even when a local
`exec_command` call specifies a different `workdir`. This prevents hooks from
seeing the directory in which the command will execute.

## What changed

- Share working-directory resolution between command execution and hook input,
  using the selected environment and the command's `workdir`.
- Report the resolved local directory in the hook input's `cwd`. Keep hook
  processes in the host directory and retain the host `cwd` for remote commands.
- Reject invalid environment selections or paths before running hooks and record
  failures in tool-result telemetry.

## Testing

Add unit and integration coverage for default, empty, relative, and absolute
working directories; Windows path conventions; remote commands; hook denial and
input rewriting; and invalid arguments that fail without running hooks.

GitOrigin-RevId: 97f71f6d3e21a5d95a7abf5384f06f4993241797
2026-10-26 19:11:28 +00:00
Anthony Tafoya 6654f7a7ab Gate capability discovery V2 on executor version (#57192)
## Why

Executors older than `0.164.0` can advertise V2 discovery support without implementing the final contract. Enabling V2 also suppressed V1 discovery for incompatible executors, hiding selected capability roots and skills.

## What changed

Require both the V2 capability flag and an executor version of at least `0.164.0` before issuing `capabilities/discoverV2`. Share this compatibility check between session discovery and the exec-server client. Fall back to V1 when incompatible executors provide no V2 snapshots, clearing any previously stored V2 inventory.

## Testing

Add coverage for version boundaries, prereleases, missing and malformed versions, and transport recovery for compatible executors. Verify that an older executor retains selected plugins and skill instructions through V1 with V2 enabled.

GitOrigin-RevId: 93adf52fc91f02b58fd14f8ff3b093712b3346b8
2026-10-26 19:03:08 +00:00
Adam Perry @ OpenAI 245691b2dc Read unified exec output directly from stdout and stderr (#57191)
## What changed

Consume local stdout and stderr receivers directly with `tokio::select!`, removing the intermediate broadcast channel and its lag-related chunk skipping. Drain both streams until they close.

Pass `ExecOutputStream` through local and remote output collection to `OutputBuffers::push_chunk`, while retaining combined output buffers.

## Testing

Update output-buffer tests for the stream argument and exercise stderr chunks in pushed-event and replay test fixtures.

GitOrigin-RevId: be7804fd30cefeb812e372454665923ba051ddb4
2026-10-26 19:01:45 +00:00
alexsong-oai be7cd6fd9e Add a credential file override for GCP provider authentication (#57188)
## What changed

Support `model_providers.gcp.credential_file` as an absolute path to a Google Application Default Credentials (ADC) file. Pass it as `GOOGLE_APPLICATION_CREDENTIALS` in the provider auth command's environment, retaining the override for token refreshes without changing the parent process environment.

Validate the path before merging GCP defaults and preserve the setting in thread configuration serialization.

## Testing

Add coverage for invalid paths, configuration round trips, separate provider token caches, and credential overrides retained after a `401` refresh. Include a Windows regression test for credential paths containing command metacharacters.

GitOrigin-RevId: d9a1d4b3775a9a4c4325dddaa153d92a2d1430a0
2026-10-26 18:33:05 +00:00
nvogt-oai 77eb019ad0 Allow advisory rollout budgets with optional limit enforcement (#57187)
## What changed

Add `features.rollout_budget.enforce_limit`, defaulting to `true`. Setting it to `false` keeps shared usage accounting and budget reminders active while allowing turns to continue after the budget is exhausted.

## Testing

Extend coverage to check enforced and advisory budgets on the current and subsequent turns, including a zero-remaining-budget reminder in advisory mode. Verify that configuration defaults to enforcing the limit.

GitOrigin-RevId: deeac8dae5714cc7c10d030cade6f3bfbfc8d3a7
2026-10-26 18:31:49 +00:00
Adam Perry @ OpenAI 090bea7b71 Centralize unified exec output rendering (#57185)
## What changed

Introduce `CapturedStream` to keep retained output text and omitted-byte counts together. Use its shared renderer for unified exec logs and model-facing output, preserving omission markers and truncation notices.

GitOrigin-RevId: 045d925df1e31945755196dafed5f78ed507b33b
2026-10-26 18:29:53 +00:00
Alex Kira 8ebd272491 Add optional names to untrusted additional context (#57181)
## What changed

- Add an optional `name` to `AdditionalContextEntry` across the protocol, app-server schemas, and generated clients.
- Accept names matching `[a-z][a-z0-9_]{0,63}` only for `untrusted` context. Reject invalid names and names on `application` context before admitting turn input, returning invalid-request errors from `turn/start` and `turn/steer`.
- Preserve existing model-input rendering and deduplicate context when only its name changes.

## Testing

Add coverage for valid name boundaries, callers that omit `name`, invalid-name rejection without admitting input, and deduplication across name changes.

GitOrigin-RevId: 2caffa6fddd40ddb178733b335f520f317239edd
2026-10-26 18:23:07 +00:00
lsingh-oai 3d1001e865 Route FedRAMP API keys to government endpoints by default (#57178)
## Why

API keys with FedRAMP issuance markers previously used commercial endpoint defaults without a FedRAMP request header.

## What changed

- Recognize `sk-proj-fedramp-` and `sk-svcacct-fedramp-` prefixes as routing hints and send `X-OpenAI-Fedramp: true`, preserving the complete key for authentication.
- Select `https://gov.api.openai.com/v1` for default OpenAI API routing and `https://gov.chatgpt.com/backend-api/` for default ChatGPT backend requests, including model discovery and analytics.
- Preserve explicit endpoint overrides, including an explicitly configured commercial default URL.
- Resolve provider routing and authentication from the same credential snapshot, and apply key-dependent routing to realtime WebSocket startup.

## Testing

Add regression coverage for prefix recognition, unchanged key storage and authorization, provider credential precedence, endpoint overrides, credential rotation, model discovery, analytics routing, and realtime request preparation.

GitOrigin-RevId: a62576ce205c34e067532b8e6c0e431f87a157e2
2026-10-26 18:20:30 +00:00
ioanbudea-OAI 83a9600acb Defer Guardian Node REPL output truncation until prompt preparation (#57176)
## What changed

Preserve complete Node REPL tool outputs during synchronous transcript collection and apply the configured output token limit during prompt preparation, after full or delta transcript selection.

## Testing

Update transcript assertions to verify that oversized Node REPL outputs remain intact during collection and are truncated to the selected token cap when rendered.

GitOrigin-RevId: 30ced935c04db456a277f7e58281d45e0e2047dd
2026-10-26 18:15:37 +00:00
viyatb-oai 619531225b Add scoped request-body secret substitution to MITM hooks (#57174)
## What changed

- Add `body_secret_substitution` actions to version 2 MITM configuration, replacing exact opaque placeholders with secrets from environment variables or files within the matching hook's scope.
- Bound body size, expansion, replacement count, and search work. Reject overlapping matches, compressed payloads, trailers, and supplied payload-integrity headers.
- Recompute `Content-Length` and substitute before SigV4 signing so signatures cover the transmitted body.

## Testing

Add coverage for markers split across chunks, expansion limits, invalid payloads, overlapping bindings, secret redaction, and search limits. Add a TLS forwarding test that verifies hook scope and independently checks the signature of the substituted body.

GitOrigin-RevId: fa95c9ae0c8fc8f695e03c0e87a0a4875d8418fd
2026-10-26 18:14:26 +00:00
Charlie Marsh a797dd7c6f Expose lifecycle timestamps on app-server thread items (#57172)
## What changed

- Add nullable `startedAtMs` and `completedAtMs` fields to `ThreadItem` in live notifications and turn history. Values are Unix milliseconds when recorded.
- Preserve recorded item times through history reconstruction, pagination, and resume, including command start times recorded during approval.
- Separate the Rust item payload into `ThreadItemPayload` while keeping the JSON payload flat, and update consumers, schemas, and generated TypeScript and Python types.

## Testing

Extend coverage for timestamp serialization, history reconstruction, paginated reads and resume, and persisted Python SDK items.

GitOrigin-RevId: ecbcee95af52db7c807b46a6e9deb30e5fba1f80
2026-10-26 18:13:00 +00:00
cooper-oai cf29971d93 Integrate runtime authentication into model requests (#57171)
## What changed

- Add opt-in runtime authentication through `ModelClient::with_runtime_auth`, requiring the provider and runtime manager to share the selected OpenAI credentials.
- Keep runtime identity, credentials, routing, and transport selection consistent for each request and its retries, signing a fresh assertion for each attempt.
- Apply authentication asynchronously to WebSocket handshakes, replace stale authentication headers, and reconnect when the runtime changes.
- Reject account, organization, or project selectors that conflict with the registered runtime, and preserve gateway OAuth composition.

## Testing

Add coverage for dual-header and assertion-only authentication, HTTP retries, runtime replacement and account switches, stale WebSocket headers, selector mismatches, gateway OAuth failures, transport revocation, and Realtime compatibility.

GitOrigin-RevId: 45b9efc2c80481406a0f6f6396a8cdd21d933c12
2026-10-26 18:06:07 +00:00
alexsong-oai 970111f6cb Allow configuring GCP project and location in provider settings (#56560)
## Why

Deriving a Vertex AI endpoint previously required environment variables. Allow the project and location to be specified directly in GCP provider configuration.

## What changed

- Add `model_providers.gcp.project_id` and `model_providers.gcp.location`, with each taking precedence over its corresponding environment variable. Keep `global` as the default location and preserve explicit `base_url` overrides.
- Validate configured endpoint fields and preserve them through thread configuration serialization.
- Apply built-in GCP defaults, including default command authentication, when checking managed provider requirements so unchanged requirements are accepted.

## Testing

Add coverage for endpoint precedence, invalid explicit configuration, provider construction, thread configuration round trips, and managed GCP requirement checks, including repeated model listing.

GitOrigin-RevId: c3704bcc0b7d4872374e2cae623fd24d75fb02b4
2026-10-23 18:50:54 +00:00
felixxia-oai 4b1cf9a4c9 Use conversations for all Guardian v2 async classification (#56556)
## What changed

- Always use the retained conversation backend for asynchronous classification; keep snapshot sampling test-only.
- Accept legacy `async_classifier_mode` values in configuration and model metadata but ignore them. Emit a startup warning when `[features.guardianv2].async_classifier_mode` is configured.
- Ignore legacy classifier mode differences when checking model-switch compatibility, and fail closed if the conversation backend is missing.

## Testing

Update coverage for legacy configuration warnings, model-switch compatibility, retained approval-review context, and conversation-based scoring.

GitOrigin-RevId: 5e8bb7e4e6e7d1589572f38bfe2498c9fa6825a0
2026-10-23 18:48:10 +00:00
ioanbudea-OAI 5deceaa927 Apply sync Guardian message limits during transcript preparation (#56555)
## What changed

Defer truncation of synchronous Guardian assistant and reasoning entries until `ContextProfile::prepare_transcript`, so the resolved profile's message limit applies before rendering and retention accounting. Keep encrypted agent messages whole when they fit, or replace them with an omission notice at the same transcript position when they exceed the limit.

## Testing

Extend coverage to verify that oversized-action reviews retain assistant commentary and final-answer evidence up to the synchronous message cap, and that encrypted-message omission produces equivalent output through synchronous transcript collection.

GitOrigin-RevId: e17fbfa7b7131559b0599ac1d57987a8d94e137c
2026-10-23 18:41:23 +00:00
viyatb-oai 15fbcac045 Enable masked AWS credentials for local proxy signing (#56554)
## What changed

- Expose `aws_sigv4` actions in version 2 MITM permissions configuration and the config schema, rejecting multiple signing actions per hook.
- Give local managed commands placeholder AWS credentials for the selected signing pair, and mask configured credentials in environment values and protected shell snapshots.
- Set `AWS_CA_BUNDLE` to the managed proxy CA bundle when unset, and require `features.credential_masking` for local AWS signing hooks.
- Validate placeholders against every configured signing pair to prevent overlap with real credentials.

## Testing

Extend configuration, signing, and TLS forwarding tests to cover action resolution, invalid signing configuration, credential masking, CA trust, snapshot protection, and exclusion of local AWS defaults from remote environments.

GitOrigin-RevId: 81dfdea30ebde74829882b38891ea41e9737058a
2026-10-23 18:40:55 +00:00
andrewgu-oai c483edf177 Include environment hooks in thread hook listings (#56553)
## Why

Listing hooks by working directory alone omits hooks supplied by a thread's selected execution environments, including hooks that can block a turn.

## What changed

- Add `threadId` to `hooks/list` to return a loaded thread's current hook inventory, including selected, ready environments. Reject requests that also specify `cwds`.
- Expose `environmentId` in hook metadata and have the TUI hooks browser query the current thread and label environment-owned hooks. Keep working-directory lookup for startup review.
- Represent environment hook source paths with `PathUri` and use `LegacyAppPathString` in hook run summaries to preserve native path conventions.

## Testing

Add coverage for listing a blocking environment hook and removing it after environment failure, delivering prompt input and reporting exit status in PowerShell and Bash, and running `PreToolUse` hooks only on the command's owning executor. Extend remote network tests to verify that environment hooks use the command's network policy while retaining their filesystem access.

GitOrigin-RevId: 97229e22793df51f4bd502c1f9e19f0c52fb2305
2026-10-23 18:39:28 +00:00
Sean Huang 7c568b331b Extract the head-tail buffer into a utility crate (#56535)
## What changed

Move `HeadTailBuffer` and `format_output_omission_marker` into the new
`codex-utils-head-tail-buffer` crate, exposing the buffer API with an explicit
const-generic byte budget. Update core callers to use the crate and add Cargo
and Bazel definitions.

Move the existing buffer tests alongside the implementation, preserving the
prefix/suffix retention and omission-marker behavior.

GitOrigin-RevId: ff488d0a0a62c39c0e11c11ebb539166cc4c6e74
2026-10-23 17:35:25 +00:00
ioanbudea-OAI 0efc474605 Defer sync Guardian tool-output truncation to transcript preparation (#56533)
## What changed

Preserve tool outputs during sync transcript collection and apply the profile's `tool_tokens` limit during transcript preparation, matching tool-call handling. Keep async and Node REPL output truncation unchanged.

GitOrigin-RevId: cf1594bcf25553c08d53b86bee1dd151e4c5db64
2026-10-23 17:28:33 +00:00
bkotsopoulos b82d542aef Add turn, tool, and skill attribution to traces (#56524)
## What changed

- Emit `codex.turn_profile` events with finalized sampling request and retry counts when turns complete or abort, and preserve the caller's tracing span for detached extension interrupts.
- Add conversation and turn identifiers to turn and tool dispatch spans, identify tool sources, and include dispatch-to-result-ready duration on tool completion events.
- Emit `codex.skill_read.source_selected` before cache or provider access, recording the selected cloud or executor source, skill and plugin identity, resource kind, and continuation status.

## Testing

Add regression coverage for trace correlation, tool completion timing, turn profile counters on completion and interruption, detached interrupt span propagation, and skill source attribution including cached cloud reads.

GitOrigin-RevId: db78aa270bbcb8dc9e4558d202c109ad54141811
2026-10-23 16:55:32 +00:00
bkotsopoulos 810501d60d Add trace instrumentation for turn startup and response streaming (#56515)
## What changed

- Record time spent waiting for each stream event in `codex.response.receive_wait_ms` on the existing `handle_responses` span.
- Add trace spans for startup prewarm consumption, turn-start lifecycle callbacks, assistant text flushing, and response stream error handling.
- Include the turn ID and lifecycle phase on the turn-start span and the request type on the error-handling span.

GitOrigin-RevId: 7792508c830ef05b03aed01eb840ca7e6577ad0b
2026-10-23 16:09:06 +00:00
bkotsopoulos bca6f238cb Preserve tracing context throughout tool dispatch (#56514)
## Why

Tool readiness waits, execution-lock waits, and result-ready events occur outside the dispatch span. Tracing should cover the full spawned dispatch task while retaining caller context when TRACE spans are disabled.

## What changed

- Instrument the entire spawned task with the dispatch span, falling back to the current span when it is disabled.
- Add child spans for readiness waits and parallel or exclusive execution-lock waits.
- Record `turn_id` and `codex.tool.phase = "dispatch"` on the dispatch span.

## Testing

Add regression tests that dispatch an unknown tool through the spawned task and verify that `codex.tool_result_ready` retains caller context at both INFO and TRACE levels, with the dispatch span present only at TRACE.

GitOrigin-RevId: 18026750af58347c38a4c2752cdd6165d73a3eab
2026-10-23 16:07:55 +00:00
ioanbudea-OAI 1c0c45bfc3 Defer synchronous Guardian tool-call truncation to preparation (#56505)
## What changed

Preserve complete tool-call text when collecting synchronous Guardian context, then apply the profile's tool token limit when preparing the transcript. Calculate retained bytes and token usage from the truncated text.

## Testing

Extend the oversized-action regression test to verify that a subsequent review includes the previous call's arguments truncated to the 1,000-token history limit.

GitOrigin-RevId: 2b52505d9ccfa3651b3535e67cc12597be819459
2026-10-23 15:37:39 +00:00
ioanbudea-OAI e52045f989 Move Guardian tool description preparation into context composition (#56493)
## What changed

Move `GuardianToolDescriptions` into `codex-guardian-context` and carry structured tool and connector descriptions in `PlannedAction` instead of pre-rendered text. Prepare them during synchronous context composition, escaping closing tags before applying the existing 400-token limit to each source and rendering the untrusted-description fragment.

Keep descriptions optional under the context budget and preserve the complete action JSON. Reject descriptions that reach rendering without preparation.

## Testing

Strengthen the MCP approval integration test to assert the exact rendered descriptions, including independent truncation and escaped closing markers. Adapt the budget enforcement test to use structured descriptions.

GitOrigin-RevId: 4a9f1855f2958758b4be711914c00e4d954cee39
2026-10-23 14:58:20 +00:00
ioanbudea-OAI 7d592f6dd9 Move Guardian approval reason caps into context composition (#56477)
## What changed

Apply the 512-token approval reason cap in `guardian-context` when composing synchronous full and delta reviews, before request budget enforcement. Remove truncation from the requesting host and preserve exact action JSON.

## Testing

Extend the planned-action budget test to cover long approval reasons in both synchronous presentations, verifying that optional tool descriptions can be omitted without changing action arguments.

GitOrigin-RevId: 8cdb6aadd5f50194f63ebd2402193e69bed127cc
2026-10-23 13:32:34 +00:00
felixxia-oai f71c6afc30 Add Guardian V3 feature configuration (#56459)
## What changed

Register `guardianv3` as an under-development feature disabled by default. Accept either a boolean toggle or a table with an optional `enabled` field, and include both forms in the configuration schema.

## Testing

Add coverage for boolean and table configuration, default behavior, and profile overrides, including inheritance when a profile omits `enabled`.

GitOrigin-RevId: 75333be61b2e336e22fef907d6363b70f9f7225b
2026-10-23 12:16:36 +00:00
Charlie Marsh 60adfa8513 Treat model-not-found provider errors as terminal failures (#56445)
## Why

Provider errors with code `model_not_found` should end the turn immediately and preserve the provider's message instead of triggering retries.

## What changed

- Recognize `model_not_found` in HTTP 400, 403, and 404 responses and in streamed `error` and `response.failed` events.
- Preserve the provider message and any available HTTP status, and expose `modelNotFound` through the app-server protocol and generated schemas and SDK types.

## Testing

Add coverage for HTTP classification, statusless stream errors, and terminal failures without retries across HTTP, SSE, and WebSocket responses. Verify that `thread/read` preserves the error reported by the live notification.

GitOrigin-RevId: 88f824ac03c8c9669915b1e40c67b76c08326fbe
2026-10-23 11:43:14 +00:00
Vivian Fang d6817454d7 Make the Guardian review timeout configurable (#56371)
## What changed

Add `auto_review.timeout_ms` to configure the overall Guardian review budget, including setup and retries. Keep the default at 90,000 milliseconds; setting it to `0` disables the review deadline while preserving cancellation, retry attempt limits, and independent transport timeouts.

Carry the configured deadline through review execution and report the configured budget in review telemetry, using zero for unlimited reviews.

## Testing

Add coverage for shared setup budgets, configured timeouts, cancellation with unlimited reviews, and retry attempt limits without a deadline.

GitOrigin-RevId: 00404e0cb2f2cfaf6de183d6e27f5e4a371942a8
2026-10-23 06:34:00 +00:00
Brent Traut 30587d7885 Add experimental attached thread forks (#56351)
## What changed

- Add `attachToSource` to `thread/fork` to persist a fork attached to its source without emitting `thread/started`. Attached forks require local storage and cannot use `ephemeral` or `deferGoalContinuation`.
- Hide attached threads from ordinary listings and add `attachedToThreadId` to `thread/list` for explicit discovery, including empty threads. Keep this relationship separate from spawned-agent parent and ancestor filters.
- Persist attachment metadata in rollouts and SQLite so it survives restarts and database recovery. Reject source deletion until its attached threads are deleted.

## Testing

Add coverage for legacy and paginated history, restart and missing or corrupt database recovery, filtered listings and pagination, resume, conflicting options, and deletion safeguards across store instances.

GitOrigin-RevId: 589f3174fc36f6054e75d65818360695645a5913
2026-10-23 04:52:47 +00:00