Commit Graph

4448 Commits

Author SHA1 Message Date
Owen Lin
2be648ba4a Preserve paginated history for spawned subagents (#33432)
## What changed

- Inherit paginated history mode when spawning or forking a subagent from a paginated parent.
- Load the parent's model context when forking and persist it as an inherited rollout prefix, while excluding that prefix from the child's projected turns, items, and metadata.
- Record the boundary between inherited context and child history, and reject partially initialized paginated subagent rollouts on resume.
- Resume paginated subagents from their stored model context instead of legacy rollout history.

## Testing

Added coverage for fresh and forked paginated subagents, compacted-history forks, model-context resume, inherited-prefix projection, metadata isolation, and incomplete-prefix detection.

GitOrigin-RevId: e57dc37c29aa4aaaf57b052b991be591d730e5ba
2026-07-15 21:25:24 +00:00
iceweasel-oai
cb79b3cdf9 Avoid creating metadata paths in the Windows sandbox (#33430)
## Why

Elevated Windows sandbox setup could turn the built-in read-only protections
for workspace metadata into deny-write paths, creating metadata directories
that did not already exist.

## What changed

- Track whether filesystem permission entries come from a built-in profile or
  were explicitly configured.
- Exclude generated metadata defaults from direct Windows deny-write overrides
  while continuing to enforce explicit read-only carveouts for the same paths.
- Preserve the distinction while materializing and normalizing permission
  paths, without exposing generated defaults as user configuration.

## Testing

Added Windows coverage confirming that elevated sandbox setup leaves missing
workspace metadata absent and still produces overrides for explicit metadata
carveouts.

GitOrigin-RevId: 701bcb229f631b18ab5ced22f3edf6f303d932f3
2026-07-15 21:19:14 +00:00
jif
79177c3e20 Propagate deferred environment capability roots to MCP (#33427)
## What changed

- Let deferred environments provide selected capability roots with their ready signal.
- Validate that those roots have unique, non-empty IDs, belong to the registering environment, and stay within the root limit.
- Include roots from ready turn environments when resolving MCP contributions, and refresh the MCP runtime when the selected root set changes.
- Expose the exact ready root set to MCP contributors so executor plugins become available with their environment.

## Testing

- Cover ready-root propagation, validation failures, replacement isolation, reconnection, and MCP plugin availability refresh.

GitOrigin-RevId: ec3498aab1164824025094e96a9b1063b7b731ad
2026-07-15 21:07:43 +00:00
jif
0f2321f244 Refresh host skill catalogs through world state (#33425)
## Why

Host skills can change after a thread starts. Subsequent turns need the updated
catalog without reinjecting an unchanged catalog on every turn.

## What changed

- Register the host skill provider in app-server and project its catalog through
  a dedicated World State section.
- Render host skills with the existing metadata budget and usage instructions,
  including skill-root aliases when available.
- Suppress the legacy host catalog and contextual fragment when World State owns
  the catalog, while preserving host skills for explicit and shadow selection.

## Testing

Added an app-server test that installs a host skill at runtime and verifies the
catalog updates once and remains stable on the following turn.

GitOrigin-RevId: 4cacc6b2258fc3cab8499fbdf9aa6ab0324ec10d
2026-07-15 20:59:21 +00:00
pakrym-oai
8530440b91 Refactor world-state rendering tests into snapshots (#33412)
## What changed

- Add a shared test helper that renders before-and-after section states alongside the resulting role and content.
- Convert the agents, environment, apps, and plugins world-state tests to snapshot tables covering absent, unknown, unchanged, changed, and removed states.

GitOrigin-RevId: 03372a5f925d2019f37bf5a5a2f060261899026c
2026-07-15 20:01:33 +00:00
jif
c28770a42f Respect final-answer boundaries for queued agent mail (#33367)
## Why

Queue-only child-agent updates that arrive around a final answer should not
restart sampling, but they must remain available to the next turn. Explicitly
injected response items still need to reopen the current turn.

## What changed

- Defer queue-only inter-agent mail after a final answer without treating it as
  same-turn pending input.
- Re-enable current-turn mailbox delivery when the model requests a follow-up,
  a stop hook continues the turn, or a response item is explicitly injected.
- Check for turn-triggering mailbox work after clearing the completed active
  turn so pending work can start safely.

## Testing

Added coverage that queued child mail waits for the next user turn and that an
injected response item after a final answer triggers a follow-up request.

GitOrigin-RevId: aa81d00707943284b7ab069b60970e547908c895
2026-07-15 15:48:12 +00:00
jiayuhuang-openai
2e1607ee2f Add Frameless Bidi support for realtime conversations (#33261)
## What changed

- Add realtime conversation version `v3`, which preserves the V1 Codex Voice behavior while using Frameless Bidi `delegation.*` events.
- Translate audio, transcripts, handoffs, session context, and lifecycle events between the app server and the Frameless Bidi wire protocol.
- Support `v3` over WebSocket and WebRTC, including the Frameless `/live` endpoint, session configuration, headers, and default model selection.
- Update the app-server protocol schemas and documentation for the new version.

## Testing

- Add unit coverage for Frameless event parsing, outbound messages, context chunking, URL construction, and call creation.
- Add app-server end-to-end coverage for WebSocket delegation and WebRTC session startup.

GitOrigin-RevId: 79a3307bc209e1a54582ebd2febc07c909fca016
2026-07-15 05:59:37 +00:00
rka-oai
768330dd6c Add a fallback phase before automatic context rollover (#33255)
## Why

Token-budget sessions need a final opportunity to preserve important state before the current context is compacted.

## What changed

- When `auto_compact_fallback_prompt` is configured, reserve `auto_compact_fallback_buffer_tokens` beyond the base auto-compaction limit.
- At the base limit, inject the fallback prompt once as a developer message while keeping the normal tool surface available. Continue reporting zero base-window tokens during this reserve.
- Roll over when the reserve or full model context is exhausted, and skip the fallback when a new context was already requested.

## Testing

Added coverage for using the fallback reserve, rolling over after it is exhausted, and bypassing the fallback for an explicit `new_context` request.

GitOrigin-RevId: 32983ecadc5cb4927e15ecd7b1e896cb52a9ad3b
2026-07-15 05:45:43 +00:00
sayan-oai
3afbd8dd45 Report selected environment connection transitions (#33251)
## What changed

- Track connected and disconnected states across initial remote exec-server connections and reconnection attempts.
- Emit experimental `thread/environment/connected` and `thread/environment/disconnected` app-server notifications for each thread selecting the environment. Each payload identifies the thread and environment; current state is not replayed when a thread starts.
- Stop forwarding connection events when an environment selection is removed or replaced.

## Testing

- Cover connection, disconnection, reconnection, shared-environment notifications, and replacement of a selected environment.

GitOrigin-RevId: 5dd767372363c4a2a8319fc16164be117d5bd20c
2026-07-15 05:21:13 +00:00
rka-oai
8aae858958 Add auto-compaction fallback token-budget settings (#33243)
## What changed

- Add `auto_compact_fallback_prompt` and
  `auto_compact_fallback_buffer_tokens` to `features.token_budget` and the
  generated configuration schema.
- Trim empty fallback prompts, limit prompts to 2,000 bytes, require a buffer
  when a prompt is configured, and reject non-positive buffer values.
- Preserve the new settings when locking resolved session configuration.

## Testing

- Cover config resolution and validation for overlong prompts, missing
  buffers, and non-positive buffers.
- Extend the configuration-lock test to cover both settings.

GitOrigin-RevId: 6463f963ba1dbd633d76601b8344360a8c85cf8b
2026-07-15 04:48:45 +00:00
rphilizaire-openai
35b33e4304 Instrument environment and plugin resolution paths (#33223)
## What changed

Add named tracing spans around step environment snapshots, capability and
executor plugin resolution, `AGENTS.md` refreshes, and MCP runtime projection
and refresh operations. Skip recording function arguments to keep these spans
focused on timing and execution flow.

GitOrigin-RevId: 73a452ef1b5da6f7f2b00d24421a815c5d514eaf
2026-07-15 03:27:16 +00:00
Felipe Coury
d88db19144 Preserve thread context when retrying or editing turns (#33211)
## What changed

- Add experimental `beforeTurnId` support to `thread/fork` for copying history strictly before a turn, including an in-progress turn.
- Use before-turn forks for TUI backtracking and safety retries so the replacement prompt retains thread context instead of recreating the branch from the preceding turn or a new thread.
- Add experimental `deferGoalContinuation` support so safety-retry forks can inherit an active goal while waiting for the replacement turn before automatic continuation resumes.
- Hide duplicated nested-review prompts when replaying history or selecting a prompt to edit.

## Testing

- Cover before-turn truncation, fork validation, active-goal inheritance, TUI safety retries, backtracking, and nested-review replay.

GitOrigin-RevId: 4915d85ae1929a0b8c40f3ed7dca29c7a5bdcdf3
2026-07-15 02:35:49 +00:00
pakrym-oai
e4711f2a3b Separate session state from session I/O (#33209)
## What changed

- Replace the combined `Codex` wrapper with an `Arc<Session>` and a dedicated
  `SessionIo` handle for submissions, events, status, and loop termination.
- Make `Session::spawn` return the session and I/O handle separately, and have
  `CodexThread` own both.
- Update thread management, delegated sessions, guardian reviews, and agent
  control to use the appropriate session or I/O interface.

GitOrigin-RevId: 8523bad7e7366e2969fd0cc3849b4247b141427a
2026-07-15 02:16:53 +00:00
Adam Perry @ OpenAI
72b41c55fb Separate exec permission paths from core models (#33200)
## Why

Core filesystem permission models operate on native absolute paths, while exec
sandbox contexts must serialize paths as portable URIs.

## What changed

- Make the core filesystem permission and profile types concrete over
  `AbsolutePathBuf` instead of generic over their path representation.
- Add exec-specific permission types that convert native permission paths to
  `PathUri` values at the sandbox protocol boundary.
- Replace the legacy read/write-roots tuple with a named
  `LegacyReadWriteRoots` struct.

## Testing

- Add coverage that exec sandbox permission paths serialize as URIs and round
  trip through the filesystem protocol.

GitOrigin-RevId: a0ef5f8aba9bbfdf00a00fcc4f199314836bc85d
2026-07-15 01:31:40 +00:00
stefanstokic-oai
4df8027a97 Honor workspace spend controls in rate-limit handling (#33187)
## Why

Sparse and out-of-order rate-limit updates can omit account metadata or let an
older full read overwrite a newer workspace hard stop. Credit availability also
does not always include a displayable balance.

## What changed

- Propagate the backend's `spendControlReached` state through rate-limit
  snapshots and the app-server protocol, preserving it across sparse updates.
- Keep workspace hard-stop classifications for error routing and ignore stale
  full-read results after a newer hard-stop notification.
- Base TUI warnings and model-switch prompts on credit availability and hard-stop
  state, and show `Credits: Available` when a finite balance is hidden.

## Testing

Added coverage for spend-control mapping, snapshot merging, out-of-order reads,
workspace error routing, warning and prompt behavior, and credit status display.

GitOrigin-RevId: 18b09d493d5a620a7c079fb721ec50b38dd5b04c
2026-07-14 22:43:26 +00:00
jif
42c5d3c80d Reuse MCP tool catalogs across sessions (#33184)
## Why

Starting a new session should not have to wait for an unchanged stdio MCP
server to initialize before its tools can be presented to the model.

## What changed

- Cache recent tool catalogs for matching stdio MCP server configurations and
  use them while a new live connection starts in the background.
- Bound the process-wide cache to 32 entries with a 30-minute TTL, and key
  entries by the server configuration, environment, working directory, and
  elicitation capabilities that affect the catalog.
- Keep connection-specific instructions and tool annotations out of cached
  catalogs. Resolve tool calls against the live connection so tools that are
  unavailable or hidden in the new session cannot be invoked from stale data.
- Publish only the newest completed catalog fetch and do not cache HTTP servers
  or stdio configurations that depend on remotely sourced environment values.

## Testing

- Add coverage for cache expiration, environment changes, catalog sanitization,
  and out-of-order refreshes.
- Add an end-to-end test that starts inference from cached definitions while a
  replacement MCP process initializes, then verifies calls and visibility
  against the live process.

GitOrigin-RevId: 2ed0f29ba53ace12532730f951b175c588aa3ae7
2026-07-14 22:25:39 +00:00
rhan-oai
68c6e5df2b Support model catalog templates for Guardian policy prompts (#33177)
## What changed

- Add an optional `policy_template` field to auto-review model messages.
- Build Guardian instructions from the catalog template when present, while
  preserving the existing precedence for managed and catalog policy content.
- Fall back independently to the bundled template and bundled policy, and
  preserve explicit empty catalog values.

## Testing

- Cover missing and empty template deserialization, policy precedence, bundled
  fallbacks, and Guardian prewarm instructions.

GitOrigin-RevId: 93116dadbc9bf40527882844a428caed4159fff6
2026-07-14 22:01:11 +00:00
iceweasel-oai
a2fb3f048d Document the Windows exec yield time range (#33167)
## What changed

Document that `exec_command.yield_time_ms` has an effective range of
2,000–30,000 ms on Windows, and update the tool specification test to match.

GitOrigin-RevId: aa20bbb2ad82d162d29d93f3bfbe1b970445f44e
2026-07-14 21:11:32 +00:00
pakrym-oai
5d325ba223 Move sleep items to the extension-owned lifecycle path (#33159)
## What changed

- Define `SleepItem` in `codex-extension-items` and carry `clock.sleep` events through `TurnItem::Extension`.
- Preserve sleep persistence, thread-history reconstruction, and the app-server's `type: "sleep"` schema while reusing the extension-owned type.

## Testing

- Add serialization coverage for the `clock.sleep` extension wire shape and its protocol wrapper.
- Update sleep lifecycle and thread-history tests to exercise the extension-owned item.

GitOrigin-RevId: 34bb33ed9b90a09bf4744aafdb56e019c717a168
2026-07-14 21:01:54 +00:00
rphilizaire-openai
2012d87211 Trace startup prewarm tasks (#33155)
## What changed

Instrument the spawned WebSocket startup prewarm task with a
`startup_prewarm` trace span. Set its OpenTelemetry name and attach the
session's `thread.id` so prewarm work can be associated with its session.

GitOrigin-RevId: f2d642d145686b883cd82be8a594bd2383470651
2026-07-14 20:52:12 +00:00
iceweasel-oai
4da39dbea7 Clarify exec yield timing on Windows (#33150)
## Why

The generic `yield_time_ms` description does not explain the Windows-specific
initial wait behavior or when callers should choose a shorter value.

## What changed

- Describe `yield_time_ms` on Windows as the maximum wait before a running
  command returns a session ID, while commands that finish sooner still return
  immediately.
- Recommend the 10-second default for ordinary commands and shorter waits for
  intentionally long-lived or interactive processes.
- Keep the existing parameter description on other platforms.

## Testing

- Update the expected `exec_command` tool schema for both platform variants.

GitOrigin-RevId: 32f90b3a56604fcf1734cc81ba7ab2f0bec41643
2026-07-14 20:44:07 +00:00
jif
1447cee36b Build MCP tool runtimes before router planning (#33149)
## What changed

- Convert filtered MCP tool metadata into `CoreToolRuntime` instances before constructing the tool router.
- Pass those runtimes through the shared tool-planning path instead of maintaining separate direct and deferred MCP tool lists.
- Preserve MCP visibility, app policy filtering, and direct versus deferred exposure behavior.

GitOrigin-RevId: 67f7fbeecc2992318c859e038cd97938833911db
2026-07-14 20:36:29 +00:00
rhan-oai
eb80df0317 Support model catalog permission messages (#33147)
## What changed

- Add per-sandbox-mode permission messages to `ModelMessages` and preserve them when applying model configuration overrides.
- Use the selected catalog message in permission instructions, substituting `{{ network_access }}` with the active network policy. Fall back to the existing sandbox text when no override is provided, and allow an empty override to omit only the sandbox section.
- Apply catalog permission messages when a session starts and when its model changes.

## Testing

- Cover catalog deserialization, mode selection, network substitution, fallback and empty-message behavior, remote model catalogs, and model changes.

GitOrigin-RevId: cd5ed3aee3155dca0e7b2358c0f09bae73236856
2026-07-14 20:14:29 +00:00
Bryan Ashley
8604689ec5 Allow injecting the Codex Apps tools cache (#33113)
## What changed

- Accept a caller-provided `CodexAppsToolsCache` when constructing a `ThreadManager` and pass it through to the MCP manager.
- Add `ConnectorRuntimeManager::new_without_cache()` for an in-memory runtime that neither loads nor persists connector state on disk.
- Re-export `CodexAppsToolsCache` from `codex-core` and `codex-core-api` for embedders.

## Testing

- Verify that a cache-disabled connector runtime ignores existing disk state and publishes live tools without creating cache files.

GitOrigin-RevId: f52f4f27c425a8d84ad0d0987b30a6fc3c14d702
2026-07-14 17:10:04 +00:00
Adam Perry @ OpenAI
0396f99cf1 Preserve special filesystem subpaths as wire strings (#33107)
## Why

Special filesystem subpaths can contain relative or foreign-platform path
spellings. Treating this wire text as a host-native path can reinterpret it.

## What changed

- Store special filesystem subpaths as strings in the core permissions model.
- Represent app-server subpaths as `LegacyAppPathString` and convert them at
  the protocol boundary without changing their spelling.
- Add `LegacyAppPathString::from_string` for callers that already own legacy
  app-server path text.

GitOrigin-RevId: 2214f03aa997fd0e6eb2ab60d425304bb4bd6132
2026-07-14 16:40:13 +00:00
jif
4aa950d456 Use session IDs for prompt cache keys (#33035)
## What changed

- Default `prompt_cache_key` to the session ID from response metadata instead of the thread ID.
- Preserve explicit prompt cache key overrides.
- Verify that API-key-authenticated root and subagent requests use the same session-based cache key even though they have different thread IDs.

GitOrigin-RevId: cb1bf21a3cb8fa2c5083c5c6afd4829ff2adcf1f
2026-07-14 10:37:23 +00:00
jif
64c0e2fa1b Remove task messages from list_agents output (#33030)
## What changed

- Return only each live agent's name and status from `list_agents`.
- Stop tracking the most recent task message in agent metadata.

GitOrigin-RevId: 91836fe8efad7ea6b7305f0b409081ec77419cfd
2026-07-14 10:22:04 +00:00
Dylan Hurd
1c9f890c05 Expose exact per-response usage in raw app-server events (#32985)
## Why

Clients that account for individual upstream Responses API calls need the exact
usage for each completion rather than accumulated or estimated thread usage.

## What changed

- Add the opt-in `rawResponse/completed` app-server notification with the
  `threadId`, `turnId`, `responseId`, and upstream `usage` payload.
- Emit the transient event for normal turns and compaction requests when
  `experimentalRawEvents` is enabled. The event is not persisted or replayed,
  and `usage` is `null` when the upstream response omits it.
- Export the notification in the app-server schemas and document its behavior.

## Testing

- Cover exact token breakdowns for turn and compaction completions.

GitOrigin-RevId: 49040a060bf1784c1ff1dd62112efb4a778428c4
2026-07-14 06:39:42 +00:00
pakrym-oai
393f64565a Scope runtime workspace roots to execution environments (#32952)
## Why

Multi-environment turns can run against different filesystems, so a single
thread-wide workspace-root list cannot accurately describe every selected
environment.

## What changed

- Add optional `runtimeWorkspaceRoots` to each app-server environment selection.
  Omitted roots default to that environment's `cwd`, while an empty list selects
  no roots.
- Carry environment-native roots through turn selection, model-visible context,
  permission materialization, and tool sandboxing.
- Keep the top-level `runtimeWorkspaceRoots` field as a compatibility input when
  constructing default environment selections; explicit selections use their
  own roots.

## Testing

- Cover thread and turn API defaults, overrides, empty roots, and schema
  round-tripping.
- Verify foreign roots remain model-visible and remote execution applies the
  target environment's roots before sandbox selection.

GitOrigin-RevId: c6e7a62883c45c676c153055f46a55ee15a323a4
2026-07-14 04:41:08 +00:00
Matthew Zeng
b019a5577c Tighten recommended plugin install suggestions (#32949)
## What changed

- Limit `request_plugin_install` guidance to explicitly requested plugins after tool search has been exhausted.
- Exclude adjacent capabilities, broad recommendations, and plugins that only seem potentially useful.
- Clarify that `plugin_id` is the parenthesized ID from `<recommended_plugins>` and prohibit parallel tool calls.
- Keep the recommendation context focused on listing available plugins while the tool specification owns the installation criteria.

## Testing

- Update tool specification tests to verify the stricter eligibility and serialization guidance.

GitOrigin-RevId: 6ebfdd864a76316ab59a0624dc4d7d3abda39a98
2026-07-14 04:29:57 +00:00
Won Park
0d78fa8846 Restrict Guardian reviewer tools (#32945)
## What changed

- Limit Guardian reviewer sessions with an environment to `exec_command`,
  `write_stdin`, and `view_image`.
- Exclude general tool sources from Guardian reviewer tool planning.

## Testing

- Extend the Guardian request snapshot test to assert the exact model-visible
  tool list.

GitOrigin-RevId: 80ba7011c23c32d163aaad906087fac396cc70fa
2026-07-14 04:15:19 +00:00
richardopenai
80c6cd3014 Allow injecting the models manager into ThreadManager (#32911)
## Why

Embedding callers need to control whether model catalogs are persisted to disk.

## What changed

- Accept a shared models manager when constructing `ThreadManager` instead of always creating a cached manager internally.
- Add provider APIs for creating uncached model managers. OpenAI-compatible providers fetch on each `OnlineIfUncached` refresh without reading or writing `models_cache.json`.
- Keep existing app server, MCP server, sample, and test callers on the standard cached manager.

## Testing

- Verify an uncached manager fetches on every refresh.
- Verify an injected uncached manager controls thread refresh behavior and does not create `models_cache.json`.

GitOrigin-RevId: 8bb646054ecec4ccb865b2bf56249384916ea9db
2026-07-14 01:06:11 +00:00
Ahmed Ibrahim
4657ab06c6 Derive collaboration settings from turn context (#32900)
## Why

`TurnContext` stored model and reasoning settings both as resolved turn fields and inside `CollaborationMode`, requiring the copies to stay synchronized when the model changed.

## What changed

- Store the mode and collaboration-mode developer instructions directly on `TurnContext`.
- Reconstruct `CollaborationMode` from those values plus the turn's current model and reasoning effort when callers need it.
- Read the mode directly for plan-mode checks, lifecycle events, and telemetry.

GitOrigin-RevId: b8fccafdd5d5cbccc84bc70d542588087ddf0093
2026-07-13 23:48:42 +00:00
briansong-oai
2ca20d5224 Expose structured standalone web search results (#32898)
## Why

Standalone web search can return structured result DTOs separately from its
model-facing text output. App-server clients need access to that data without
coupling Codex to every result type or field.

## What changed

- Preserve the optional `results` array from `/v1/alpha/search` as opaque JSON
  through web-search completion events, thread history, and app-server
  `webSearch` items.
- Keep responses from older endpoints compatible when `results` is absent, and
  allow clients to ignore result types and fields they do not understand.
- Regenerate the protocol schemas and TypeScript definitions for the optional
  field.

## Testing

- Cover responses with missing, empty, and forward-compatible result payloads.
- Verify standalone web-search results round-trip through app-server item
  notifications and thread-item conversion.

GitOrigin-RevId: 739ef5694ece5733f7b8749ec41d6bfa3f33c8c5
2026-07-13 23:37:35 +00:00
Dylan Hurd
090f4de37b Route blocked network requests to their owning calls (#32897)
## Why

Policy-blocked proxy requests must terminate the corresponding active tool call and preserve the correct approval result, including when multiple calls are running concurrently.

## What changed

- Resolve a blocked request's execution ID to its registered active network call before recording the policy denial.
- Preserve an outcome already recorded for that call, and cancel the owning call after storing a new denial.

## Testing

Expand network approval integration coverage for Guardian and user decisions, permission hooks, persisted policy amendments, concurrent calls, timeouts, cancellations, and unattributed proxy requests.

GitOrigin-RevId: 961901bbc07cc498309453ec78cda1a56ab00a4b
2026-07-13 23:33:58 +00:00
Matthew Zeng
7fdf2f254b Serialize plugin install requests (#32894)
## What changed

- Mark `request_plugin_install` as not supporting parallel tool calls so install requests execute serially.
- Add a unit test covering the handler's parallel-call capability.

GitOrigin-RevId: 5f2c8184562bd776b0e527e5e258c61c604a0910
2026-07-13 23:17:38 +00:00
jif
bb947e8e36 Tag shell tool telemetry by command category (#32887)
## What changed

Add a `command_category` tag to tool result telemetry for `exec_command` and
`shell_command` invocations. Classify parsed commands as `read`, `list_files`,
`search`, or `unknown`; use `mixed` when a script contains multiple categories.

GitOrigin-RevId: 1edacb38c7be9b03af4f2fc86746184f19067592
2026-07-13 22:34:16 +00:00
Celia Chen
0877afbe85 Broaden remote compaction model fallback (#32881)
## Why

Compacting a resumed conversation can fail when its previous model is no longer
available. Some model-specific failures, such as a model-not-found response, are
not represented as invalid requests and therefore did not trigger the existing
fallback to the currently selected model.

## What changed

- Share a retry predicate between both remote compaction implementations.
- Fall back to the current model for invalid requests, unexpected statuses,
  context-window and usage-limit errors, server failures, and exhausted retries.

## Testing

Add an integration test that resumes a conversation whose previous model returns
model-not-found and verifies that compaction and the next turn use the renamed
model.

GitOrigin-RevId: c3857beae2ce79b50589deb13c2e59710ce14725
2026-07-13 21:54:04 +00:00
rhan-oai
60b9b551c1 Use model catalog policies for Guardian auto review (#32875)
## What changed

- Add an `auto_review.policy` field to model catalog messages.
- Use the selected Guardian model's catalog policy for review-session instructions, while preserving the precedence of `guardian_policy_config` and falling back to the built-in policy when neither is present.
- Preserve auto-review messages when model instruction overrides remove catalog instruction templates.

## Testing

- Cover configured-policy precedence, explicit empty catalog policies, catalog-message preservation, and propagation of the catalog policy into a prewarmed Guardian session.

GitOrigin-RevId: 26b61ae2958ea8325a64834dcf91f47e140d74b3
2026-07-13 21:25:28 +00:00
iceweasel-oai
abbb8c569c Require the elevated Windows sandbox for network proxies (#32857)
## Why

Network proxy enforcement on Windows requires the elevated sandbox backend. Silently selecting that backend for an unelevated configuration makes the effective sandbox differ from the configured mode.

## What changed

- Reject enabled network proxy configurations on Windows unless managed requirements allow only the elevated sandbox and `windows.sandbox` resolves to `"elevated"`.
- Preserve the configured sandbox backend during execution and validate proxy compatibility at config loading, sandbox setup, and process launch boundaries.
- Defer this validation during cloud-config bootstrap so authoritative managed requirements can be loaded first.
- Do not start or expose disabled Windows proxies, and render transitions to disabled networking as `<network enabled="false"></network>`.

## Testing

- Cover Windows requirement and sandbox compatibility matrices, bootstrap behavior, backend selection, disabled proxy handling, and environment-context updates.

GitOrigin-RevId: bfa1dda98594e0db61883f8e7f65bd560e3453e6
2026-07-13 19:04:22 +00:00
jif
088239294a Restore V2 agent identities on root thread resume (#32837)
## Why

After a cold resume, a Multi-Agent V2 root thread must still be able to
address its persisted descendants even though their runtimes are not reopened
eagerly.

## What changed

- Restore metadata for open descendant agents when resuming a V2 root thread.
- Preserve each descendant's path, nickname, and role while leaving its runtime
  unloaded until a message targets it.
- Reuse the spawn metadata preparation path so restored identities retain the
  same reservation and naming checks as newly spawned agents.

## Testing

Added an end-to-end cold-resume test that follows up with a persisted agent by
name and verifies that the original agent thread is loaded on demand.

GitOrigin-RevId: a1663c1ae60eefadb948cd39f933cd3bbb49a492
2026-07-13 17:24:10 +00:00
XMLIU-oai
19a000259d Forward turn metadata in standalone web search (#32835)
## What changed

- Add optional serialized Codex turn metadata to extension tool calls.
- Populate it from the current turn context and send it as the
  `x-codex-turn-metadata` header on standalone web search requests.

## Testing

- Extend the app-server web search integration test to verify that client
  metadata, including the model ID, reaches the standalone search request.

GitOrigin-RevId: c0950108d89a1d317ac94ccd23efcee72fffc6f0
2026-07-13 16:52:18 +00:00
jif
2e156cbe31 Avoid blocking thread startup on MCP OAuth discovery (#32825)
## Why

OAuth metadata discovery for an optional HTTP MCP server can stall, delaying
`thread/start` even though that server is not required.

## What changed

- Remove eager MCP authentication-status discovery from session and connection
  manager startup.
- When an MCP connection reports an authentication error, inspect configured and
  stored credentials locally to preserve login and reauthentication failure
  reasons without making another discovery request.
- Continue using server configuration directly for startup error messages and
  timeout hints.

## Testing

Add an app-server regression test with an optional HTTP MCP endpoint that accepts
a connection but never responds, and verify that `thread/start` completes without
waiting for its configured startup timeout.

GitOrigin-RevId: 56fe0188cc1ceaf746b0b65e8b7dd1fd2e13420d
2026-07-13 15:47:03 +00:00
jif
4ebc61c0f8 Make explicit multi-agent mode override proactive delegation (#32822)
## Why

After switching from proactive delegation to explicit-request-only mode, an
earlier proactive instruction can remain in the conversation context. The new
mode must clearly supersede that instruction.

## What changed

Update the explicit-request-only developer message to cancel earlier proactive
delegation instructions before requiring delegation to be explicitly requested
by the user, `AGENTS.md`, or a skill.

## Testing

Update the multi-agent mode integration test expectation for the explicit-mode
instruction emitted after a cold resume.

GitOrigin-RevId: 0a6d18f38ef82d29cf4f3bfcfd4ac84738a39598
2026-07-13 15:39:24 +00:00
jif
92938d880e Restrict spawned-agent models to the active backend (#32751)
## Why

Model overrides for `spawn_agent` must be compatible with the multi-agent backend used by the current turn.

## What changed

- Carry each model's multi-agent backend metadata into `ModelPreset`.
- Filter the advertised `spawn_agent` model overrides for multi-agent v2 and reject overrides assigned to another backend.
- Limit error suggestions to picker-visible, backend-compatible models.

## Testing

Added coverage for hiding incompatible models from the tool description and rejecting them during spawn validation.

GitOrigin-RevId: 22c12aba67df46e9743a74f019b72a1b8b76b308
2026-07-13 09:52:27 +00:00
jif
ea15456284 Expose model overrides for multi-agent v2 spawns (#32749)
## What changed

- Add the `features.multi_agent_v2.expose_spawn_agent_model_overrides` setting, enabled by default, to expose `model` and `reasoning_effort` on the v2 `spawn_agent` tool.
- Keep these controls available when other spawn metadata is hidden, while allowing them to be disabled independently.
- Add root-agent and subagent guidance that overrides require a partial or context-free fork and should only be used when explicitly authorized.

## Testing

- Cover configuration parsing and defaults, usage-hint preservation, and tool-schema behavior with override exposure enabled and disabled.

GitOrigin-RevId: 92370498108c96fbd51f32965624ce531e991d9a
2026-07-13 09:48:33 +00:00
Dylan Hurd
ea0fd84d94 Align Guardian reviews with session configuration (#32747)
## What changed

- Include permission instructions in Guardian review requests and let the review model use its configured tool mode and standard tool plan instead of a Guardian-specific direct-tool override.
- Refine the Guardian policy for tenant policy precedence, authorization scoring, prompt-injection handling, read-only investigation, and post-denial user approval.
- Simplify low-risk allow responses to `{"outcome":"allow"}` regardless of authorization scoring.

## Testing

- Update Guardian request-layout snapshots to cover the permission instructions included in initial and follow-up reviews.

GitOrigin-RevId: eb83571ef61f7b4e854c12e13e7163c6fab43f00
2026-07-13 09:44:56 +00:00
Matthew Zeng
2f7d89b141 Extract connector runtime snapshot management (#32698)
## What changed

- Move the Codex Apps tool cache into a reusable `codex-connectors` runtime manager keyed by account and workspace.
- Represent cached tools as atomically published snapshots with refresh timestamps while preserving the newest accepted fetch generation.
- Harden disk persistence with bounded reads, atomic file replacement, and serialized writes so an older fetch cannot overwrite newer state.

## Testing

Add coverage for identity isolation, snapshot timestamps, oversized cache files, atomic replacement, and concurrent persistence ordering.

GitOrigin-RevId: 5ea2234469daae3abf54b030244c3251de62ca5a
2026-07-13 05:02:52 +00:00
Eric Traut
bbdf3030de Emit thread-idle lifecycle after guardian interrupts (#32460)
## What changed

- Emit the thread-idle extension lifecycle when the guardian successfully aborts an active turn after repeated automatic review denials.
- Keep user-initiated interrupt behavior unchanged.
- Add a regression test that waits for the thread-idle callback after a guardian interrupt.

GitOrigin-RevId: 6622c35361a3da9126c11bd6ca49a532c1bd6e27
2026-07-11 17:13:16 +00:00
pakrym-oai
c9d52de5ca Require prefixes for outbound response item IDs (#32312)
## What changed

- Add a `ResponseItemId` type that generates item-specific prefixes with UUIDv7 suffixes and use it across response items.
- Keep deserialization permissive for legacy histories, but omit empty or unprefixed item IDs from HTTP and WebSocket requests.
- Export the new type in the generated TypeScript protocol schema.

## Testing

- Cover prefixed ID generation, legacy deserialization, prefix recognition, and outbound request filtering.

GitOrigin-RevId: 0209fe430c826d0ae88bc4648652c4ebf390c4a4
2026-07-11 02:29:14 +00:00