Commit Graph
1493 Commits
Author SHA1 Message Date
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
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
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
andrewgu-oai 4610b573e5 Run environment hooks on their owning executors (#56343)
## What changed

- Include ready environments' configured hooks in lifecycle events and execute command hooks using each owner's shell, working directory, shell environment policy, and managed network policy.
- Resolve tool environments before `PreToolUse` and use those targets for tool hooks, execution, and permission review. Route MCP hooks by server ownership and file-copy hooks to both endpoints.
- Preserve environment, MCP server, and terminal session selectors across hook input rewrites, rejecting attempts to switch targets.

## Testing

Add regression coverage for permission-request selector preservation, MCP resource hook ownership, and file-copy hooks that rewrite paths while preserving source and target environments.

GitOrigin-RevId: 31a3a6830523965285dab451cfc866c620ef6c83
2026-10-23 04:01:39 +00:00
alishobeiri-oai 8531184b49 Make agent-message wakes respect interrupts and Plan mode (#56330)
## Why

A pending agent-message wake can outlive an interrupt or a switch to Plan mode while model discovery is waiting. It must recheck whether it can start before consuming queued messages.

## What changed

- Revalidate reserved wakes after discovery and build the turn with the configuration selected during admission.
- Mark interrupted wake reservations as stopped so later agent messages cannot restart automatic work, while preserving queued messages for explicit turns.
- Keep finishing turns marked as running until completion is persisted, protecting their rollout writer from capacity eviction.

## Testing

Add regression tests for interrupts and Plan-mode changes during discovery, queued-message preservation, explicit follow-ups with `wake_on_agent_messages` disabled, and completion status and persistence with the feature enabled and disabled.

GitOrigin-RevId: afe1d57063a5ec491e8b16d6c62135caa69c0a3c
2026-10-23 02:21:49 +00:00
rhan-oai e103bbc06f Apply model catalog overrides to history, notes, and context tools (#56313)
## What changed

- Read optional tool descriptions and parameter schemas for `history`, `notes`, `new_context`, and `get_context_remaining` from the acting model's catalog messages.
- Support catalog namespace descriptions for history and notes, preserving explicit empty and whitespace descriptions.
- Share catalog override handling across native tools and MCP resource helpers. Keep bundled schemas when overrides are invalid, preserve encrypted parameters, and leave tool identity and transport fields unchanged.

## Testing

Add coverage for sparse catalog serialization, schema fallback and encryption preservation, per-step tool definitions, and context tool updates when switching models. Extend outgoing-request tests to verify history and notes overrides while retaining history image attachments.

GitOrigin-RevId: 1adac8b5009f95c91adba491f20a4e2e2dc91475
2026-10-23 00:46:28 +00:00
goodman-oai 878070b5a6 Support model-specific writable-root permission wording (#56309)
## What changed

Add optional `writable_root` and `writable_roots` templates to model-catalog permission messages. Select the template by the number of displayed roots and substitute exactly one `{{ roots }}` placeholder with the existing formatted path list.

Fall back to the bundled sentence for missing, empty, invalid, or oversized templates. Preserve path contents, permission-path limits, and denied-read instructions. Update the permission wording when the selected model changes.

## Testing

Add coverage for template validation and size limits, singular/plural selection after path truncation, path preservation, sparse serialization, and model switches that append changed permissions once while preserving request history.

GitOrigin-RevId: 4dcfb7ff70b91db3dba3dda684b355b920e07974
2026-10-23 00:40:04 +00:00
andrewgu-oai 75a4146411 Add support for environment-scoped managed hooks (#56304)
## What changed

- Add discovery and listing APIs for environment-owned required hooks, with command and MCP execution routed to the owning environment.
- Use each environment's working directory in hook input, withhold controller transcript paths, and prevent environment hooks from granting permission requests.
- Resolve `command_windows` against the environment's platform and, when hooks are enabled, reject unloadable required hooks before accepting environment configurations at startup or readiness.

## Testing

Add regression coverage for invalid managed hook matchers at startup and readiness, successful readiness after correction, and per-hook working directory and transcript path scoping for `SubagentStop`.

GitOrigin-RevId: 1ac0ab3778ba608c72e5917fcbaebcc1d454887f
2026-10-23 00:09:23 +00:00
andrewgu-oai 7a5860da35 Add hook configuration to environment attachments (#56302)
## What changed

- Add `environment_hooks` to `EnvironmentConfig` for hooks from an environment's effective managed requirements. Initialize it empty for inferred thread configurations and report the handler count in debug output.
- Move `HookEventsToml`, `MatcherGroup`, and `HookHandlerConfig` into `codex_protocol::hooks`, with re-exports from `codex_config::hook_config`.
- Validate MCP hook input recursively to reject nulls and integers outside the signed 64-bit range without converting through `toml::Value`.

GitOrigin-RevId: 410506c8e2b89c9519c81d86b44ccd760d751693
2026-10-23 00:02:29 +00:00
viyatb-oai d124fe9de1 Add negotiated network policy metadata support for MCP calls (#56278)
## What changed

Add an optional `NetworkPolicyMetadataProvider` to the MCP runtime. Advertise `codex/network-policy-meta` only to trusted ChatGPT origins when a provider is available, and attach policy metadata only when the sending session also advertises support.

Strip caller-supplied policy metadata and derive restrictions from the call's captured permission profile and server environment. Resolve metadata against each session's capabilities, including after recovery, while retaining one policy snapshot per call. Fail the call before sending if policy resolution fails. Existing runtime callers leave the provider unset.

## Testing

Add tests for capability negotiation, trusted-origin restrictions, forged metadata removal, both tool dispatch paths, and policy snapshot reuse. Add HTTP session-recovery coverage for changing capabilities and policy-resolution failures while preserving caller metadata and read-only restrictions.

GitOrigin-RevId: 4b978f986abc0475fc67659be98fc01a2d6ce7cd
2026-10-22 22:33:07 +00:00
Owen Lin 40db507eec Avoid redundant settings checkpoints when resuming threads (#56250)
## Why

Resuming a thread with unchanged settings appended another `ThreadSettingsApplied` event to its rollout.

## What changed

Compare the effective settings with the latest persisted settings for the same thread before writing a checkpoint. Persist settings when they differ or no matching checkpoint exists, even if no turn follows the resume.

## Testing

Add a regression test that restarts the app server, resumes a materialized thread without overrides, and verifies that its persisted settings events remain unchanged.

GitOrigin-RevId: c545791ed3bb4020fa3da6d233607a9ba73e5c8d
2026-10-22 20:06:07 +00:00
Abhinav 8c7affbe1b Emit prompt telemetry only after hooks accept input (#56234)
## Why

Prompt telemetry can include full user text. Emitting it before hook acceptance logs prompts that `UserPromptSubmit` hooks subsequently block.

## What changed

Move prompt telemetry from input submission to hook acceptance, including queued and steered input. Preserve telemetry for accepted Guardian review prompts that are converted to response items during finalization.

## Testing

Extend hook regression tests to assert that blocked prompts are absent from telemetry and rollouts, while accepted queued prompts are logged exactly once. Extend Guardian review coverage to assert exactly one prompt event across inspection steps.

GitOrigin-RevId: aa71f98de2356dd08f62ff492e897ab3a43b54c9
2026-10-22 17:48:34 +00:00
jif 07316174c6 Forward Guardian reviewer events to parent raw-event subscribers (#56124)
## What changed

Add the disabled-by-default `guardian_recorded_items` feature to forward recorded reviewer items and interruptions through the parent's raw-event subscription, preserving reviewer thread and turn IDs without modifying the parent's history or completing its turn.

Emit reviewer items as `rawResponseItem/completed` notifications and interruptions as interrupted `turn/completed` notifications. Mark opted-in reviewer requests with `guardian_recorded_items` metadata.

## Testing

Extend Guardian integration tests to cover reviewer identity, recorded-item metadata replay, concurrent reviewer interruptions, independent parent completion, and behavior without the feature enabled.

GitOrigin-RevId: beb4dbf6c6f2a800a2fbf3cfd11ae174a1382386
2026-10-22 09:20:00 +00:00
smurching-oai 342ed69a17 Require managed configuration from the configured server (#56055)
## Why

Local administrators need to require managed configuration from a specific customer-hosted server before a session can start.

## What changed

- Add a local managed `config_server` requirement with an HTTPS base URL and optional OAuth settings. Validate endpoints and derive the bundle route as `codex/config/bundle` beneath the base URL.
- Replace the entire `config_server` block when a higher-priority requirements layer supplies one, keeping the endpoint and OAuth settings together. Reject this setting in fetched policy.
- Track the applied server through configuration snapshots, role overrides, and refreshes. Reject session startup and managed refreshes when the applied server does not match the requirement; user refreshes retain the session's managed configuration.

## Testing

Add coverage for missing, mismatched, and matching server configuration at session startup, whole-block replacement, rejection of server settings in fetched policy, and preservation across role overrides and refreshes.

GitOrigin-RevId: 51e8a1738dabdb117ae858120f6fb09ae2ff1261
2026-10-22 02:15:00 +00:00
Anthony Tafoya 0769c6aeeb Enable executor cleanup hooks with V2 capability discovery (#56044)
## Why

Executor hooks depended on V1 discovery snapshots, so plugins discovered through V2 could not run their cleanup hooks.

## What changed

Prepare executor hook sources during step setup from either V1 or V2 discovery and capture them in `StepContext` for stop, interrupt, and memory consolidation hooks. Restrict V2 sources to selected plugin installations while preserving plugin enablement, hook admission, MCP routing, and app tool policy checks.

## Testing

Add unit coverage for V2 hook admission, environment routing, disabled plugins, and failed discovery. Add integration coverage showing that `Stop` and `Interrupt` cleanup hooks run with V2 discovery alone and remain silent when the plugin is disabled.

GitOrigin-RevId: a4c0e9c56bdebcdf22cea63f02f8fb4c5eed358e
2026-10-22 01:42:11 +00:00
Dmitriy Kovalenko 07cc649c65 Avoid double-counting retained reasoning in token usage (#55991)
## Why

Responses Lite includes retained reasoning in its reported token usage even without an `X-Reasoning-Included` header. Adding a separate reasoning estimate can trigger automatic compaction prematurely. Locally recomputed usage also already includes retained reasoning.

## What changed

Initialize reasoning accounting from `use_responses_lite` before each sampling or compaction request, while allowing server events to override it. Mark locally recomputed token usage as including reasoning.

## Testing

Update the compaction regression test to verify that Responses Lite usage without the header stays below an 81-token limit at 80 tokens and triggers compaction at 81 tokens.

GitOrigin-RevId: 06f9272cb3c259e927941f1d2a1d7096310ffb2c
2026-10-21 21:23:01 +00:00
Dmitriy Kovalenko 17a0e6f63f Route SQLite logs to an explicitly configured log_dir (#55978)
## What changed

- Store `logs_2.sqlite` in `log_dir` when explicitly configured, unless a managed `sqlite_home` requirement applies. Keep other databases in `sqlite_home` and preserve the existing SQLite log location when `log_dir` is unset.
- Initialize and lock the selected log directory only when opening its database, so an unavailable directory does not prevent authentication commands from loading configuration. Share the cleanup lock across configuration clones and allow failed initialization to be retried.
- Leave existing logs in place. Read legacy logs for diagnostic submissions when the current query returns no logs, attaching them as `codex-logs-legacy.log`. Continue retention cleanup and page reclamation for both locations, with independent maintenance locks and filesystem checks.

## Testing

Add coverage for configuration routing and managed requirements, deferred initialization and lock lifetimes, authentication with an unavailable log directory, legacy log attachments, and cleanup of current and legacy databases.

GitOrigin-RevId: 48216694596d738eff1b3c5eef6c4e7ada6d0137
2026-10-21 19:53:00 +00:00
jif 02c6a2d3f1 Drain WebSocket responses on mailbox preemption (#55969)
## Why

Mailbox preemption can discard completed response items and lose the response ID needed for incremental continuation. Buffered tool calls must also wait for queued agent messages to be read.

## What changed

- Gracefully interrupt and drain Responses Lite streams, retaining completed items and the response ID for the next request.
- Cancel buffered tool calls before dispatch and suppress partial items that may be discarded during the drain.
- Keep user steering queued until draining finishes. Include pending mail in follow-up requests after disconnects and preserve content-filter recovery guidance.

## Testing

Add WebSocket regression coverage for buffered completion, interrupts without acknowledgement, buffered tools and partial items, user steering during draining, disconnects, and content-filter recovery.

GitOrigin-RevId: c9d3fb87a81850e5686e07f28103e2ff4378ddec
2026-10-21 19:29:08 +00:00
Anthony Tafoya 9e12b14891 Refresh cloud plugin and skill catalogs after mid-turn auth changes (#55957)
## Why

Authentication can change between model steps. Refresh cloud catalogs before the next step so plugin acceptance and skill instructions reflect the current auth scope, including plugins that are no longer available.

## What changed

- Add a `refresh_catalog_for_step` lifecycle hook and rebuild MCP when plugin catalogs change.
- Reuse successful discovery within a turn and auth scope, serialize concurrent refreshes, and allow retries after failures or cancellation. Limit cloud skill discovery warnings to once per turn.
- Skip cloud discovery during prewarm and other context-only captures, and check hosted plugins even when no executor roots are selected.

## Testing

Add regression coverage for mid-turn auth rotation and plugin removal, serialized refreshes and retries, stale discovery results, and prewarm boundaries.

GitOrigin-RevId: 355681e84dc765e8dc1a04608779d95c706c2188
2026-10-21 18:37:30 +00:00
Eric Traut 430a16799d Preserve thread model settings across resume and revert (#55923)
## Why

Resuming a thread can replace saved model settings with global defaults. A selected service tier can also be lost when the current model does not support it.

## What changed

- Restore saved service tier, reasoning summary, and personality on resume unless the caller explicitly overrides them, respecting thread ownership of settings snapshots.
- Retain the selected service tier for persistence, settings notifications, and resume comparisons while filtering the effective tier against the current model's capabilities.
- Carry the runtime model, service tier, and personality into thread revert reconstruction.
- Persist initial thread settings before user input during MCP startup so an interrupted first turn retains its settings checkpoint.

## Testing

Extend regression coverage for cold resume and explicit overrides, unsupported service tiers, settings preservation during revert, and settings checkpoints before user input when MCP startup is interrupted.

GitOrigin-RevId: e5ec012a5678048c5eedd443e524f38c142bf9fd
2026-10-21 15:34:43 +00:00
Charlie Marsh c7234c1174 Box session metadata and compaction payloads in RolloutItem (#55733)
## What changed

Store `RolloutItem::SessionMeta` and `RolloutItem::Compacted` payloads in `Box` values and update their producers, consumers, and test fixtures. Preserve the existing serialized rollout format.

GitOrigin-RevId: 59fcc4beb47d23160872dcb6e95ace9b142d3d11
2026-10-21 02:41:05 +00:00
jif feadd9441e Preserve enterprise MCP authorization across runtime refreshes (#55696)
## Why

Configuration reloads must cancel stale enterprise MCP startups while preserving access for running threads that still pass validation. Replacing a runtime during `thread/revert` must also leave the replacement able to use enterprise tools.

## What changed

- Separate pending startup cancellation from published thread lifetimes, with independent startup state for forks and replacement runtimes.
- Retain eligible enterprise MCP connections across refreshes and explicit reconnects while applying updated tool restrictions and approvals. Do not create replacement enterprise connections after initial startup.
- Revoke enterprise authorization when a thread is removed, drain requests when access is disabled, and revoke a connection's authority when token renewal requires authentication.

## Testing

Extend regression coverage to verify enterprise tool calls survive `thread/revert`, inherited fork configurations are cancelled after a reload, and enterprise calls fail after logout while ordinary MCP calls remain available.

GitOrigin-RevId: 2d634be3011854b57f73c741bd1ec6b5aed94ee5
2026-10-20 23:03:56 +00:00
Alex Kira d4e03acb61 Tag tool registration metrics with effective incremental tools mode (#55692)
## What changed

Add an `incremental_tools` attribute to `codex.tools.registered` using the effective mode for the current sampling request. Compute the mode once and reuse it for registration metrics and prompt construction across transport retries.

## Testing

Extend integration tests to verify the attribute for incremental and non-incremental requests, including when the feature flag is enabled but the Responses API does not support incremental tools. Assert registration sample counts and retain coverage that stream retries do not duplicate registration metrics.

GitOrigin-RevId: e5b7a1075fe722ef6bdf900ae07e2b1b06aecfb5
2026-10-20 22:34:40 +00:00
Ruslan Nigmatullin 66d0de9983 Add lifecycle hooks for inter-agent messages (#55657)
## What changed

Add `MessageLifecycleContributor` hooks to capture extension state when local agent control publishes a message and notify contributors when the recipient commits it to history, before sampling.

Carry shared delivery state through submissions, input queues, and mailbox eviction with `PendingAgentMessage`. Notify consumption at most once per delivery, release captured state when consumed or abandoned, and drop pending mail outside queue locks. Preserve the serialized message format without republishing restored history.

## Testing

Extend the mailbox eviction test to verify that publication state survives eviction and retained messages are consumed before the first resumed model sample.

GitOrigin-RevId: 9a1f6832bd48ec646a3fd179485c095e8dcc72cc
2026-10-20 19:39:43 +00:00
jif 305db3808c Make pending injections interrupt agent waits and sleep (#55644)
## Why

Input injected before `wait_agent` or `clock.sleep` begins must still interrupt the wait and reach the next model request.

## What changed

Track notifying response-item injections as pending steering activity. Reset that state when pending input is consumed or cleared so later passive context does not interrupt waits.

## Testing

Extend wait and sleep tests to cover injections queued before the wait and delivered while waiting, alongside user steering. Add queue coverage for pending injection detection and reset after consumption.

GitOrigin-RevId: 90f8d968336082c76271d1ca4f81b855bafc72c6
2026-10-20 17:56:07 +00:00
Rohan Mehta ab6095dde0 Allow callers to control prompt cache keys independently of session IDs (#55587)
## What changed

Expose `PromptCacheKey` through `StartThreadOptions` with three policies: retain the default session-derived key, send a custom key, or omit `prompt_cache_key` from model requests. Keep session identity headers independent of this policy.

Propagate the policy to child agents, delegated sessions, and guardian review sessions. Hosts must reapply the policy when resuming a thread from storage.

## Testing

Add coverage for all three policies across turns, including unchanged session and thread headers. Extend subagent coverage to verify inheritance of the default and omitted-key policies.

GitOrigin-RevId: f9e8ab31fcf568636f9712726760e4e9a4672428
2026-10-20 14:14:59 +00:00
jif e8aa7c1678 Avoid panics after background compaction fails before a checkpoint (#55581)
## Why

Polling a failed background compaction consumes the closed oneshot receiver.
Keeping that receiver in session state can cause a later await to panic instead
of falling back to foreground compaction.

## What changed

Remove the receiver from session state before polling it, restoring it only when
its result is still pending. Discard closed receivers so compaction can fall back
normally.

## Testing

Add a regression scenario where background compaction fails before the next
checkpoint and automatic compaction falls back successfully.

GitOrigin-RevId: 1461bb403f4b0b8b7e171d1b3cba41411f2014b4
2026-10-20 13:50:13 +00:00
liame-oai 014489466a Add optional MCP disablement for prediction forks and samples (#55463)
## What changed

Add `experimentalDisablePredictionMcp` to `thread/fork` and `disableMcp` to `thread/sample`. Disable MCP servers when requested and the inherited history contains incremental tools on Responses Lite. The fork option requires `experimentalPredictionMode: true`.

Apply disablement through a thread-local policy that excludes configured MCP servers and runtime contributions, including after MCP refresh. Preserve the inherited history prefix and append tool-removal instructions without changing the parent's tools.

## Testing

Add coverage for prediction forks with legacy and paginated history, flag validation, conditional disablement, MCP refresh, and sample/fork request parity. Add a request-history snapshot covering preserved history, tool removal across child turns, and unchanged parent tools.

GitOrigin-RevId: e31d602480e6550ed130d8152f538b8668280fa0
2026-10-20 05:25:43 +00:00
jif 896604a12d Record OAuth provenance and login identity for account tokens (#55397)
## Why

Token refresh needs the issuer and client ID used at login. Unverified token claims cannot establish that authority, and OAuth error bodies may echo credentials.

## What changed

- Save `oauth_provenance` and a new `login_owner_id` on browser and device-code login. Preserve the login identifier through token rotation.
- Refresh using the recorded issuer and client ID, retaining the existing endpoint override and fallback behavior for legacy records. Clear provenance when an override changes the endpoint or when a response without token rotation encounters a concurrently replaced refresh token.
- Keep both metadata fields optional for older records without inferring provenance from token claims.
- Remove backend token error details from structured logs and refresh error messages.
- Box large futures in token refresh, MCP initialization, and embedded app-server test startup to reduce surrounding async frame sizes.

## Testing

Add coverage for legacy record compatibility and metadata round trips, browser and device-code login persistence, refresh using recorded OAuth settings, metadata preservation through rotation, and provenance clearing for a superseded refresh token.

GitOrigin-RevId: b6b5d2fcbe2a284a171a242c1a17128af55f1024
2026-10-19 22:21:13 +00:00
jif e389b2444c Add configured thread environment inheritance for subagents (#55375)
## Why

Temporary environment attachments for a parent turn should not become a
subagent's persistent environments. Children also need to retain their
configured executor bindings when their runtime is evicted and reloaded.

## What changed

- Add the disabled-by-default `subagent_thread_environments` feature flag.
  When enabled, both subagent implementations inherit configured thread
  environments captured with the invoking step, excluding turn-only attachments.
- Track configured bindings separately from active turn attachments, preserving
  pending configuration ownership and sharing completed executor startup.
- Retain configured selections and bindings across idle eviction. Reload children
  using retained bindings when the parent changes workspace, while continuing to
  validate current parent roots and permissions for matching workspaces.

## Testing

Extend regression coverage for configured, empty, forked, pending, and legacy
inheritance; temporary attachment removal across eviction; and reload behavior
with changed workspaces, deferred startup, and restricted permissions.

GitOrigin-RevId: 15692ecd99deb38002014b44fd859d793bd54373
2026-10-19 20:30:44 +00:00
Anthony Tafoya 9b865ab31e Prepare skill catalogs before building step tools (#55357)
## Why

Skill tools depended on World State rendering to initialize their catalogs and could return `skill catalog is not ready for this step` before rendering completed.

## What changed

- Add an asynchronous `ToolContributor::prepare_for_step` hook and await all contributors before constructing tools.
- Prepare immutable skill catalogs, aliases, plugin policy, and configuration for each step. Tools, invocation detection, and World State rendering consume the prepared state without relying on rendering to perform discovery.
- Apply configuration reloads to subsequent steps while preserving live authorization checks for skill reads.

## Testing

Add coverage for preparation completing before tool construction and World State rendering, skill tools working before rendering, catalogs remaining stable across steps, and configuration reloads during discovery.

GitOrigin-RevId: 1fb95c58c412488353f3bd4403824d6d1476d3d0
2026-10-19 19:33:11 +00:00
jif fbb2f9dbec Use step environment snapshots for subagent inheritance (#55331)
## What changed

- Remove `subagent_thread_environments` and the separate configured environment bindings. Spawned agents inherit the invoking step's environment snapshot.
- Retain environment selections across child eviction without retaining executor bindings. Reload V2 children against the parent's captured environments, requiring matching environment IDs, working directories, and workspace roots while preserving permission validation.

GitOrigin-RevId: d820c63ea20f5834ed88071d16c60683f2545406
2026-10-19 17:43:31 +00:00
jif d70c2c2cdf Add configured thread environment inheritance for subagents (#55327)
## Why

Temporary environment attachments for a parent's turn should not become a child's persistent environment configuration or survive child eviction.

## What changed

- Add the default-disabled `subagent_thread_environments` feature flag. When enabled, subagents inherit configured thread environments captured with the spawning step instead of active turn selections.
- Track configured bindings separately from turn attachments, preserving pending configuration ownership when turn selections change.
- Retain configured bindings across child eviction and reload, excluding temporary attachments. Preserve the child's workspace when the parent switches workspaces, while enforcing current roots and permissions when the parent still configures the same workspace.

## Testing

Extend coverage for both multi-agent versions, forked children, empty configured environments, pending configuration, and legacy inheritance. Add eviction and reload cases covering temporary attachments, workspace changes, deferred executor startup, and permission validation.

GitOrigin-RevId: 4533645503d5f863a9ccc064386ed7ca169d98b7
2026-10-19 17:16:22 +00:00
Anthony Tafoya a309f9206a Integrate discovery V2 with step-scoped skill catalogs (#55322)
## What changed

- Build executor skill catalogs from discovery V2 inventories without reopening host paths or falling back to legacy discovery.
- Merge Cloud and executor skills by remote plugin identity and skill name, retaining Cloud metadata and accepted provider read routes. Apply plugin selection and disablement before merging.
- Share a stable catalog across each step's rendering, list/read tools, and explicit and implicit skill invocations.
- Preserve unmatched executor entries when Cloud catalogs are unavailable or partial; only complete Cloud catalogs disable unmatched remote entries.
- Bind discovery caches to captured environments and executor sessions, and refresh MCP when V2 inventories change. Preserve pending invalidations when forced MCP refreshes fail.

## Testing

Add regression coverage for V2 inventory sharing and refresh, environment isolation, catalog merging, partial Cloud results, disabled plugins, and catalog consistency across steps and read routes.

GitOrigin-RevId: 842bdcbc9e19364dd69a9abf9e48330b7425a76c
2026-10-19 17:02:20 +00:00
Anthony Tafoya f7a135ec61 Reconcile V2 executor plugins with cloud catalogs (#55301)
## What changed

- Use V2 discovery inventories for plugin MCP contributions when supplied, including empty or failed inventories; retain legacy discovery when no V2 snapshot is supplied.
- Merge plugins by canonical identity, using cloud metadata and enablement for remote plugins and attaching executor installations only when versions match. Preserve configured executor-local plugins and executor enablement when cloud data is unavailable.
- Keep installation order stable across refreshes and run merged MCP declarations on the first retained executor installation while preserving attribution for the others.
- Carry local and remote identities through selected-plugin snapshots, skill attribution, and active-plugin telemetry. Track disabled plugin IDs alongside disabled roots.
- Preserve a complete cloud catalog when a partial refresh arrives, and cap tool-description plugin attribution at 1,024 bytes while retaining all plugin associations.

## Testing

Add coverage for catalog parsing and reconciliation, enablement and discovery-mode selection, installation refresh ordering, executor-specific MCP normalization, selected-plugin snapshots, and bounded UTF-8 attribution text.

GitOrigin-RevId: a8ad352de6a2b8dc4bfd1ff6a5c62ee8ed1d1664
2026-10-19 15:15:17 +00:00
jif cca40e57a4 Track MCP enterprise auth cancellation across config reloads (#55287)
## Why

Configuration loading can finish before a pending startup is visible to the thread manager. Reloads need a cancellation scope that also covers these configuration snapshots.

## What changed

- Capture an enterprise managed authentication (EMA) cancellation token before loading configuration and carry it through config layers, role overrides, runtime refreshes, and `McpConfig`.
- Cancel the previous scope on MCP or user configuration reloads and cloud config loader changes, then create a fresh scope for subsequent loads.
- Cancel the session's token when enterprise MCP authentication is disabled or a refresh leaves it unavailable.

## Testing

Extend the MCP reload test to verify that existing thread and pending startup tokens are cancelled while a fresh startup receives an uncancelled token.

GitOrigin-RevId: 5fc0658b74c360e7dc9ab3488339fcf19bfe9fae
2026-10-19 14:07:10 +00:00
Charlie Marsh c0ce901923 Share dynamic tool specifications across turn snapshots (#55261)
## What changed

Store dynamic tool specifications in an `Arc<[DynamicToolSpec]>` so session configuration and turn snapshots share the list fixed at thread startup instead of copying it on each clone.

Keep the `dynamic_tools()` accessor returning a `Vec<DynamicToolSpec>`, but copy the specifications after releasing the session state lock.

GitOrigin-RevId: 092c5f9ea6cc390d948c27cd11340aeb12bd6037
2026-10-19 11:35:08 +00:00
Vivian Fang 70b3bb6d88 Add observation-only model request lifecycle hooks (#55144)
## What changed

- Add `PreModelRequest` and `PostModelRequest` hooks around model request attempts, including retries. Pass model, session, turn, and optional subagent context; report completion, failure, or cancellation with errors and token usage when available.
- Treat hook output as diagnostic data without allowing it to veto requests or alter model context. Wait for synchronous post-request hooks before dispatching tools, while asynchronous hooks allow streaming tool dispatch to continue.
- Apply memory-consolidation hook filtering and expose the new events through configuration, protocol schemas, generated clients, and the hooks browser.

## Testing

Add integration coverage for failures and retries, ignored control directives, cancellation, synchronous and asynchronous tool ordering, interrupted-turn resume and token accounting, and memory-consolidation filtering. Update hook schema fixtures and hooks browser snapshots.

GitOrigin-RevId: 6ed7b39fc8bb94cf467e350d07d97fcc729c21ce
2026-10-18 22:43:56 +00:00
alishobeiri-oai 8c076942cb Allow agent messages to wake idle root sessions behind a feature flag (#54961)
## Why

A worker can finish after its parent has returned a final answer. Agent messages without `trigger_turn` previously needed an outstanding durable sleep to wake an idle session.

## What changed

Add the disabled-by-default `wake_on_agent_messages` feature to start a new root turn when agent mail arrives through direct delivery or the host mailbox. Reuse the previous turn context for messages without `trigger_turn`. Keep these automatic wakes disabled for interrupted sessions, Plan mode, and child agents.

## Testing

Add coverage for both delivery paths waking a completed root exactly once, child completion waking a parent after its final answer, and the interruption, Plan mode, and child-agent boundaries.

GitOrigin-RevId: f1a4fc7c22be8ca46b2173a85445126cbdd6c4b6
2026-10-18 01:58:02 +00:00
Charlie Marsh 1cc7dc8f2a Share additional tool declarations across response item clones (#54945)
## Why

Cloning `ResponseItem::AdditionalTools` deep-copies its tool declarations for history and request copies.

## What changed

Store `tools` in an `Arc<[serde_json::Value]>` so clones share immutable declarations. Update constructors and existing test fixtures to use the shared representation.

GitOrigin-RevId: eb8831774afb45fe8431a796f34ae9d1243e884a
2026-10-17 23:17:51 +00:00
pakrym-oai ce0323f2f2 Support typed content in contextual prompt fragments (#54776)
## Why

Contextual fragments and extension-owned world-state sections currently return strings, limiting them to text content.

## What changed

- Return `ContentItem` from fragment bodies and rendering, preserving classification and attribution. Apply text markers only to `InputText`; pass other content through unchanged.
- Allow extension prompt and world-state contributions to carry typed content, and preserve media in context-window hints.
- Hash non-text world-state fragments by their serialized content and role while retaining the existing text hashing behavior.
- Add shared content-to-tool-output conversion that preserves image references, image detail, and audio.

## Testing

Add coverage for typed world-state hashing and preservation of image content and attribution. Expand code-mode output tests to cover input text, output text, file-backed and inline images, and audio.

GitOrigin-RevId: 2ed00d466a3f169b151202f3eef71e667ea64be1
2026-10-17 04:02:21 +00:00
Michael Zeng 341de32c33 Allow root turn suspension with live descendants (#54414)
## Why

Live descendants previously blocked suspension of an unfinished root turn, requiring callers to stop and unload them before recovering the root elsewhere.

## What changed

Allow `suspend_turn_and_shutdown` to suspend the root and initiate shutdown of all sessions sharing its local agent runtime, fencing new starts. Remove `SuspendTurnOutcome::HasLiveDescendants`.

Success confirms that the root has stopped and its history writer is flushed and closed; descendant cleanup completes separately. Callers must finish tree shutdown or fence and terminate the tree's persistence writers before transferring ownership. Interrupted descendants are not automatically recovered.

## Testing

Extend integration coverage to verify child shutdown, recovery under the original root turn ID without restarting children, and separate reporting of child writer failures.

GitOrigin-RevId: 5adc240ae6e34654209154ee9324621a2bd604d5
2026-10-15 20:57:39 +00:00
Owen Lin b7ba02f880 Support store-owned preparation when resuming threads (#54059)
## Why

Thread stores need a way to reuse history and writer state loaded while preparing a resume, rather than loading them again during session startup.

## What changed

- Add an opaque, single-use `ThreadStoreResumePreparation` and an optional preparation in `StartThreadOptions`.
- Pass preparation through session startup to `ThreadStore::resume_thread_with_preparation`, which defaults to an unsupported-operation error.
- Reject preparation for ephemeral threads or threads without resumed history. Continue using `resume_thread` when no preparation is supplied.

## Testing

Add a regression test verifying that supplied preparation selects the prepared store path and propagates its unsupported-operation error instead of falling back to ordinary resume.

GitOrigin-RevId: 26537d9b83443bd56341d6afc713f32b999dc67c
2026-10-14 18:02:25 +00:00
marksteinbrick-oai 2b21129c6b Add Responses API client metadata patches for turn start and steer (#54053)
## Why

Clients need a way to update individual turn metadata entries without replacing the existing client metadata map.

## What changed

Add the experimental `responsesapiClientMetadataPatch` field to `turn/start` and `turn/steer`. Patches add or overwrite entries while retaining other keys and apply after `responsesapiClientMetadata` when both are supplied. The existing field retains replacement semantics, including clearing unprotected entries with an empty map.

Continue protecting reserved metadata keys and preserving targeted `misalignment_override` continuations across updates.

## Testing

Extend the app-server metadata integration test to cover replacement and patch steering, patch precedence at turn start, preservation of unrelated entries during patches, and protection of targeted continuations.

GitOrigin-RevId: 8c4da3ba1b87329da20b5295846bdcf3a88126de
2026-10-14 17:39:43 +00:00
jif 0b73618146 Keep host MCP and plugin configuration local with remote environments (#53990)
## Why

A remote primary environment could supply its working directory and workspace roots to host plugins and MCP processes, breaking relative MCP executable resolution and applying the wrong workspace permissions.

## What changed

- Build host configuration from the local environment, falling back to the session's host working directory and runtime workspace roots when no local environment is selected. Preserve explicitly empty local roots.
- Use the same host configuration for MCP startup and refresh, and refresh MCP state when runtime workspace roots change.
- Keep repository skill discovery paired with the primary executor's working directory and filesystem.
- Box skill warmup and turn context construction futures to reduce enclosing future sizes.

## Testing

Extend the MCP integration test to cover a remote primary with populated, empty, or absent local roots; relative executable resolution before and after refresh; workspace-root revocation; and remote repository skill discovery.

GitOrigin-RevId: 21a73c90507b55fd94261e7bf348695ff8466a24
2026-10-14 14:08:26 +00:00
Benjamin Carlsson 7eed30ad1b Preserve running turn recovery across thread settings updates (#53879)
## Why

Standalone thread settings updates cleared the running turn's continuation lineage, preventing recovery after a daemon restart.

## What changed

Preserve continuation lineage while a task is registered. Continue invalidating pending continuations for idle, reserved, and finishing turns, and record started-turn lineage atomically with task registration.

## Testing

Extend settings invalidation coverage to idle, reserved, and finishing turns. Exercise an in-flight reasoning effort update before compaction, then verify cold resume preserves the turn's frozen settings and allows continuation. Wait for thread idle before testing idle continuation.

GitOrigin-RevId: d7c316af6a4c871790bb57f0af9892bb30871ac8
2026-10-14 06:03:02 +00:00
rhan-oai cb03f28a40 Refresh model instructions in incremental-tool context windows (#53872)
## Why

Incremental-tool windows recorded base instructions only at setup, so a catalog refresh for the same model could leave active instructions stale. Instruction changes need to reach the model without rewriting the existing history prefix.

## What changed

- Track model identity and instruction content independently, appending a `model_instructions` developer message when either changes. Explicitly mark replacement or removal of base instructions, and avoid repeating unchanged updates.
- Start new windows after compaction with the latest model instructions while preserving custom base instructions.
- Preserve the recorded window base during local compaction retries, including empty instructions, and rebuild current model instructions when reconstructing child context.

## Testing

Add integration tests and request snapshots for catalog refreshes, instruction removal, model switches, compaction, restart, and forks. Extend regression coverage for legacy snapshots and local compaction retries.

GitOrigin-RevId: eeca69067b4d9cd91c817732d79b4d5c1faa18b9
2026-10-14 05:36:44 +00:00
tongzhou wang 1b6e0d8145 Track content provenance through prompt assembly and compaction (#53831)
## Why

Message roles and content classifications do not identify who supplied each context part. Source attribution needs to survive prompt assembly and history truncation, including messages that combine text from different producers.

## What changed

- Add per-part `ContentItemMetadata` for user input, developer instructions, `AGENTS.md`, skills, harness context, command hooks, and tool context with optional callable namespaces.
- Carry attribution alongside content and classifications through contextual fragments, extension prompts, hook output, and agent messages. Keep tool-provided context-window hints separate from harness text.
- Preserve the source of retained text slices during compaction and attribute generated truncation notices to the harness. Default missing historical attribution to unknown.
- Attribute host MCP calls using cached tool namespaces only when catalog revisions remain stable, without starting servers or refreshing catalogs for attribution.
- Send the new metadata to Responses Lite and strip it from requests to endpoints that do not support it.

## Testing

Extend compaction tests to cover mixed sources, missing or extra metadata entries, and discarded media. Update Responses Lite request assertions to verify endpoint-specific attribution handling.

GitOrigin-RevId: b0ebc929b7c60f3ec49d1affbf897312d63edcc8
2026-10-14 02:01:49 +00:00
rka-oai 9e03960cf8 Wire background compaction into the turn lifecycle (#53800)
## What changed

- Launch background compaction at eligible pre-turn, mid-turn, and post-turn checkpoints when `AsyncCompaction` is enabled, capturing the current world state and client routing state.
- Adopt ready results at compaction checkpoints while preserving newer messages, tool outputs, and world-state updates. Continue normally if an optional result is rejected.
- Run one foreground compaction if an adopted result still exceeds the context limit.
- Prevent cancelled turns from launching new background work while preserving already-running work for later reuse.

## Testing

Add unit and scenario coverage for stale history and account changes, cancellation, pending-result reuse and fallback, retained tool outputs, compaction event pairing, and token usage accounting. Add a context snapshot covering a collaboration-mode change while compaction runs.

GitOrigin-RevId: 04ac028d9fe2e3ea64aacaaeb351c3c776cf3940
2026-10-13 23:51:47 +00:00