Commit Graph
1264 Commits
Author SHA1 Message Date
jif 28097e98eb Preserve Guardian history across thread reconstruction (#42065)
## Why

Guardian review evidence must remain available after a compacted thread is resumed or forked, while rolled-back or parent-local evidence must not grant authorization in a different context.

## What changed

- Store the bounded, model-invisible Guardian transcript alongside compacted rollout history and restore it from the newest surviving checkpoint during replay.
- Trim Guardian history at rollback boundaries, clearing it when the boundary has already been evicted.
- Preserve the checkpoint for user-initiated forks, but remove it when spawning a subagent so parent review evidence is not inherited.
- Keep the new rollout field optional for compatibility with existing compacted records and legacy readers.

## Testing

- Cover Guardian history across compaction, restart, paginated and pathless stores, user forks, rollback, bounded replay, serialization, and subagent forks.

GitOrigin-RevId: 6ab076d5e0c3aac4d6a41ebd50ba2b200c90213e
2026-09-01 14:33:58 +00:00
Alex Zamoshchin 0ec375eb70 Add per-account approval settings for apps (#42047)
## What changed

- Add `apps.<app_id>.links.<link_id>` configuration for overriding
  `approvals_reviewer` and `default_tools_approval_mode` per connected account.
- Expose link settings through the app-server protocol and generated JSON and
  TypeScript schemas.

## Testing

- Extend `config/read` coverage for populated, empty, and absent `links`
  sections.

GitOrigin-RevId: 43004d2722439060fdadc5e5cd9ed3108774ecaf
2026-09-01 13:07:56 +00:00
Eddie Chen 2b7c279735 Report turn trigger and source in turn analytics (#42003)
## What changed

- Add `turn_trigger` and `codex_turn_source` to `codex_turn_event` analytics.
- Read the source from effective Responses metadata, preserving configured-over-client precedence and reflecting accepted steer metadata.
- Omit trigger and source values from analytics when they exceed the existing Responses metadata value limit.

## Testing

- Cover event serialization, turn lifecycle emission, configured and client source precedence, size limits, and source updates after steering.

GitOrigin-RevId: bbd45af4c6af52956d2394b722ea78e65e5b9bd7
2026-09-01 07:32:54 +00:00
sayan-oai e017e93ace Preserve raw response usage metadata (#41980)
## What changed

- Include the complete upstream `response.usage` object in
  `ResponseUsageMetadata.metadata` while retaining the existing `amount` field.
- Expose the metadata through `rawResponse/completed` notifications and update
  the generated JSON and TypeScript schemas.

## Testing

- Cover SSE, WebSocket, turn, and compaction completion paths.

GitOrigin-RevId: 6d79b1b4c92ac11abf43ec98f380b4868288a701
2026-09-01 05:17:11 +00:00
Matthew Zeng bfa9646787 Add plugin reconciliation app-server API (#41949)
## What changed

- Add the `plugin/reconcile` JSON-RPC method to synchronize installed remote plugin bundles and wait for required hook updates.
- Return affected plugin IDs with MCP, Apps, hooks, and skills refresh hints, plus remote update and materialization failures.
- Refresh loaded hook runtimes after relevant updates and return an empty result when plugins or backend authentication are unavailable.

## Testing

- Cover workspace and global bundle installs, unchanged passes, enablement changes, updates, removals, materialization failures, hook refreshes, and disabled plugins.

GitOrigin-RevId: 45c02518d71990d13eb09d56ed51505c91c66956
2026-09-01 00:50:11 +00:00
xli-oai e39ab0c185 Emit turn cost telemetry for ChatGPT sessions (#41944)
## What changed

- Query workspace-visible turn estimates for ChatGPT-authenticated sessions through the appropriate Codex or ChatGPT endpoint.
- Track completed response IDs and emit `codex.turn.cost_microusd` only when the estimate is nonnegative, visible, and covers every observed response.
- Keep error response bodies out of turn-cost worker logs.

## Testing

- Cover both endpoint styles, nullable estimates, settlement validation, exact micro-USD conversion, and response-ID tracking.
- Add an app-server integration test that verifies a settled ChatGPT turn reaches the OTLP metrics exporter with its turn, conversation, and auth-mode attributes.

GitOrigin-RevId: 6ae3f8df729fad52984a0c6efafd8c96c7214e55
2026-09-01 00:30:55 +00:00
guinness-oai 64c9cde458 Record realtime conversation history in Core (#41924)
## Why

Realtime history should be recorded consistently for every Core host, including
when no app-server event listener is attached.

## What changed

- Move transcript segmentation, session boundaries, and backing-agent artifact
  promotion into Core for paginated threads.
- Persist canonical realtime items through the thread store in event order and
  emit dedicated history lifecycle events for hosts to present.
- Translate those Core events into the existing app-server realtime item
  notifications without app-server persisting the items a second time.

## Testing

- Cover Core-only persistence across repeated sessions, ephemeral sessions,
  accepted and rejected steering, typed input ordering, and artifact promotion.
- Verify app-server notifications correspond to the persisted timeline.

GitOrigin-RevId: 7cbef14129d77f6d6d7099b733be91f5279c55f5
2026-08-31 22:38:23 +00:00
Owen Lin 5f79a92e39 Persist response token usage in rollout history (#41912)
## Why

Resumed threads need to continue per-turn and per-thread token totals without scanning arbitrarily far beyond the latest compaction checkpoint.

## What changed

- Add durable `TokenUsageRecord` rollout items with response, turn, thread, session, and root-turn attribution.
- Restore accumulated usage on resume and snapshot the latest record plus the compaction response ID in compaction checkpoints.
- Preserve root-turn lineage in persisted turn context, while ensuring forked child threads start with their own usage totals.

## Testing

- Cover usage accumulation across multiple responses and resumed turns.
- Cover local and remote compaction checkpoints, invalid remote compaction output, rollout reconstruction, and fork isolation.

GitOrigin-RevId: ef9e0c4a9102a08a2c382be4cdac68c84353c90a
2026-08-31 21:15:38 +00:00
felixxia-oai 9f97cb79eb Preserve Guardian review evidence across compaction (#41879)
## Why

Guardian reviews need the original conversation evidence even after the parent context has been compacted, while rollback must still remove evidence from reverted turns.

## What changed

- Build synchronous and asynchronous Guardian transcripts from the retained review-history snapshot.
- Use the shared Guardian transcript collector for consistent entry formatting, tool attribution, and per-entry truncation while preserving the existing transcript retention budgets.

## Testing

- Add app-server coverage for retaining user and tool evidence after compaction and discarding it after rollback.
- Extend transcript tests for standalone tool outputs, shell calls, attribution, truncation, and retention limits.

GitOrigin-RevId: a18b1176f14a4d006c263aa82d4e593afee66bc3
2026-08-31 17:10:38 +00:00
jif 2c8cfbf44f Keep history extension tools out of Guardian reviews (#41861)
## What changed

- Initialize Guardian reviewer subthreads with empty extension data.
- Remove the special registration that exposed inherited read-only `history`
  tools in the Guardian tool plan.

GitOrigin-RevId: 7700f033faab125d59d11bc2d82955c67689e3c3
2026-08-31 15:19:38 +00:00
stefanstokic-oai 79b04f1ab5 Show actionable rate-limit banners in the TUI (#41742)
## What changed

- Carry optional backend-owned banner and account identity data through
  `account/rateLimits/read`, filtering banners that do not match the authenticated
  account and user.
- Render supported rate-limit notices above the composer with actions for usage,
  credits, resets, owner notifications, and plan management while preserving the
  existing fallback UI for absent or unsupported banners.
- Refresh usage after limit errors, reject stale responses, and keep queued input
  paused until recovery completes. When instructed by the banner, switch to the
  first available fallback model without changing unrelated thread settings.

## Testing

- Add protocol, banner parsing and rendering, CTA, identity filtering, refresh
  ordering, fallback-model, account-change, and queued-input recovery coverage.

GitOrigin-RevId: e03d75a82e425deb87f4b120a71cf2286c0ef6cc
2026-08-31 00:20:06 +00:00
jif cefa060695 Approve the first Node REPL execution without a Guardian wait (#41666)
## Why

The first REPL execution should proceed while its initial asynchronous Guardian
classification is still pending.

## What changed

- Fast-approve the first `js` execution from a Node REPL-backed server while
  continuing its asynchronous classification.
- Track `js` executions separately so setup and reset tools do not consume the
  first-execution allowance.
- Apply the normal Guardian review policy to subsequent executions.

## Testing

Add coverage for browser and computer-use startup, reset, and module-directory
setup sequences, verifying that only the first `js` execution skips the wait.

GitOrigin-RevId: 7297b35411a6317bcf9e7058c08c6db3e3310ac8
2026-08-30 13:02:11 +00:00
rka-oai 28327355b8 Update tests for default-enabled update_plan (#41630)
## What changed

- Cover the default, explicitly enabled, and explicitly disabled states of
  `tools.update_plan.enabled`.
- Verify prompt tool lists remain consistent across requests, including when
  custom base and developer instructions are configured.
- Explicitly enable `update_plan` in existing fixtures that depend on the tool.

GitOrigin-RevId: 3be279cb5195dfc5892c2c8ff6a1461fac879309
2026-08-30 07:40:36 +00:00
rhan-oai f5636bb733 Restore thread cwd from owned settings snapshots (#41567)
## Why

Resuming a thread without an explicit `cwd` should restore that thread's latest
retained setting. Forked history can contain settings copied from another
thread, while compaction can move the latest setting outside the replay window.

## What changed

- Record the owning thread ID on new settings snapshots and only use snapshots
  owned by the resumed thread when restoring `cwd`. Older snapshots without an
  owner remain readable but do not override the startup `cwd`.
- Checkpoint the current settings after compaction and serialize checkpoints
  with settings updates so the retained history contains an accepted, current
  snapshot.
- Cover resume behavior across compaction, forks, reverts, legacy histories,
  and concurrent settings updates.

GitOrigin-RevId: 1efc9cf55472d6b88c465c4efe44672a232dbf64
2026-08-29 19:57:06 +00:00
Eric Traut 4210c08def Preserve turn lineage across goal continuations (#41562)
## Why

Automatic goal continuations should remain attributable to the turn that created the goal. External input, hook context, or goal edits can make that attribution ambiguous and must not leave stale lineage metadata behind.

## What changed

- Carry the trusted root and previous parent turn through successive automatic goal continuations.
- Invalidate stored lineage when external context reaches an active turn or when a goal is edited or cleared.
- Preserve lineage for async hook results only when they belong to the receiving turn.

## Testing

- Cover goal continuations across intervening user turns and external objective edits.
- Cover active, buffered, and externally injected hook or response context.

GitOrigin-RevId: 22ccc07961cd0ed8f4b17912b7efa416b342bf50
2026-08-29 18:51:11 +00:00
Eric Traut 62b458c931 Block goals after repeated execution host failures (#41454)
## What changed

- Track failed `exec` attempts whose handler ran for each active goal.
- Mark the goal as blocked after three qualifying failure turns.
- Reset the failure streak when any tool succeeds, and keep failures from carrying over to a replacement goal.

## Testing

- Cover failure classification, streak resets, goal replacement, and end-to-end goal blocking through the app server.

GitOrigin-RevId: 14dac7f4eb35507f12df3b2a82ab97bdafe7b897
2026-08-29 03:04:26 +00:00
Adam Perry @ OpenAI 48e22a5fa0 Report code mode host request durations (#41452)
## Why

Code mode wall time should measure the host operation itself, without including
client-side response delays or idle time between requests.

## What changed

- Measure each execute, wait, and terminate request in the code mode host.
- Carry the duration through the stdio and gRPC protocols and use it for
  model-visible wall time.
- Emit a structured `codex.code_mode.host_timing` event correlated with the
  conversation, turn, tool call, and cell.

## Testing

- Cover successful and failed execution timing, delayed response reads,
  repeated waits, termination, and missing cells across stdio and gRPC.
- Verify timing survives protocol serialization and is reflected in app-server
  model output and structured telemetry.

GitOrigin-RevId: d24af30c3fc5820521b4beba1f9970714dad6482
2026-08-29 02:52:58 +00:00
victor-openai eec4a23cb1 Support openai/elicitation form requests (#41447)
## What changed

- Advertise `openai/elicitation` form support when the client declares an
  object-valued `form` capability, without deriving it from the legacy
  `openai/form` capability.
- Handle `openai/elicitation/create` requests in `form` mode and forward their
  metadata and opaque schema through app-server as `openaiForm`, preserving
  `x-openai-*` annotations.
- Keep legacy form handling independent and have the TUI automatically decline
  the new form requests it cannot render.

## Testing

- Add an app-server round-trip test for capability negotiation, request
  forwarding, and accepted responses.
- Extend MCP capability filtering coverage for `openai/elicitation.form`.

GitOrigin-RevId: 88f39257bffafe4ee98a9c910e38507843cd7eeb
2026-08-29 02:43:10 +00:00
Vivian Fang 03147407e3 Add app-server notification media filtering (#41416)
## What changed

- Add the disabled-by-default `omit_app_server_notification_media` feature.
- When enabled, remove inline image and audio content from `item/started`,
  `item/completed`, and `rawResponseItem/completed` notifications, including
  tool output and image-generation results.
- Keep the media in model input; the filter only changes app-server
  notifications.

## Testing

- Verify that image content is absent from all three notification types while
  the model request still receives it.

GitOrigin-RevId: 9a4434d18a3dac6d67c2e0c3723ff4595a9b3797
2026-08-28 21:06:35 +00:00
gero-oai e4d0ba4e92 Support configurable timeouts for thread shell commands (#41384)
## What changed

- Add an optional `timeoutMs` parameter to `thread/shellCommand` and propagate it to user shell execution.
- Preserve the one-hour default when the parameter is omitted or `null`, allow longer deadlines, and treat `0` as an immediate timeout.
- Reject negative or otherwise invalid values before execution. Timing out an auxiliary shell command leaves its active turn running.

## Testing

- Cover default, extended, immediate, invalid, standalone, active-turn, and interruption behavior.

GitOrigin-RevId: d72f67793d9766b7383f28d30140270a4a76a495
2026-08-28 18:07:40 +00:00
jif 430d26b543 Classify clock tools as built-in control tools (#41331)
## What changed

- Mark `clock.curr_time` and `clock.sleep` as built-in control tools so their calls emit control-tool analytics.
- Cover completed, failed, and interrupted calls, verify analytics omit tool arguments and output, and keep the calls out of the dynamic-tool count.

GitOrigin-RevId: 489c8015f836be146ccc2c7e96ef7243b0599e16
2026-08-28 12:40:10 +00:00
jif 31d338a1ea Isolate required-model Guardian approval coverage (#41322)
## What changed

Update the Guardian v2 required-model-switch test to continue the thread with
empty input. This keeps authorization unchanged, so the test specifically
verifies that the required-model check prevents reuse of a cached approval for
the sandboxed command.

Continue asserting that a Guardian review starts and that the command skips a
second classification.

GitOrigin-RevId: 5ce914cb6e66f0527d9ec154331cc356104bfb72
2026-08-28 11:22:20 +00:00
jif f98649cde9 Honor required reviews when reusing Guardian scores (#41309)
## Why

After switching a thread to a model that requires automatic review, a
standard-scope approval could reuse a cached low-risk score for an action that
skipped classification. This allowed the action to bypass the required full
review.

## What changed

Check the thread's current model requirements before making a fast Guardian
decision. Defer required models to the full review path instead of approving
from cached scoring state.

## Testing

Add coverage for switching to a required model and reviewing a sandboxed
command without running another classification.

GitOrigin-RevId: e79e6a5df19c46acd5c4176f522a859793177639
2026-08-28 10:03:19 +00:00
willwang-openai e9a6d731b7 Apply app routing policy to unauthenticated plugin reads (#41230)
## What changed

Apply the legacy plugin app/MCP routing policy even when no authentication mode is available. Unauthenticated plugin reads now omit unavailable app declarations while retaining their MCP server alternatives.

## Testing

Extend plugin manager coverage for unauthenticated reads and provide ChatGPT authentication in the app-server bundle-details test.

GitOrigin-RevId: d90d29d0702488eb7413c6779254a9e6aae615c0
2026-08-28 00:07:32 +00:00
Anton Panasenko f6726e8986 Add recency sorting to project/list (#41223)
## What changed

- Include `recencyAt`, derived from the newest non-archived assigned thread, in project responses.
- Let `project/list` sort by `position` or `recencyAt` in either direction, with recency as the default descending order for that key and projects without activity placed last.
- Encode the sort key, direction, and millisecond-precision anchor in new cursors while retaining existing ascending-position cursors.
- Add an index for project recency lookups and document the API's sorting and pagination behavior.

## Testing

- Cover recency updates when threads are assigned, archived, unarchived, or deleted.
- Cover ordering, null handling, tie-breaking, cursor pagination, invalid sort combinations, and cursor mismatches.

GitOrigin-RevId: 6165e2b9976b0b45cfa16bcd42978b67811f6df5
2026-08-27 23:43:46 +00:00
willwang-openai c4c51c56e4 Honor per-repository plugin configuration in catalog requests (#41208)
## What changed

- Load the effective plugin configuration for every requested `cwd` in
  `plugin/list` and `plugin/installed`.
- Combine local marketplaces in request order, keeping the first source for
  duplicates while merging installed and enabled state across repositories.
- Report invalid project configurations through `marketplaceLoadErrors` without
  dropping valid local catalogs or globally enabled remote catalogs.
- Use the combined marketplace context for forced and background cache refreshes,
  while keeping remote plugin feature gating request-wide.

## Testing

- Cover distinct and duplicate marketplaces, cross-repository enabled state,
  invalid project configuration, local cache refresh, and global versus
  project-local feature flags.

GitOrigin-RevId: 53c8e0e9c760dc2b969ab10d0e63fb439673c230
2026-08-27 21:10:10 +00:00
rka-oai 035295b46e Improve sandboxing, MCP errors, and cached approvals (#41196)
Expand Windows deny-read globs robustly across protected directories while preserving filesystem enforcement. Preserve structured MCP tool and resource errors through app-server responses. Bind cached Guardian classifications to current local and root authorization state so stale scores cannot approve actions.

Add regression coverage for the sandbox resolver, structured protocol errors, and authorization changes.

GitOrigin-RevId: 4b80ed724d869afeca79204222d8465fa99d3a24
2026-08-27 20:05:08 +00:00
felixxia-oai 694edc23b2 Propagate trusted root skills to delegated workers (#41118)
## Why

Guardian reviews for delegated workers need to recognize skills explicitly
invoked by the user on the root turn.

## What changed

- Record verified user-owned skill paths as bounded, turn-matched Guardian
  evidence.
- Include trusted paths from the current worker and its root snapshot when
  building review context.
- Exclude skill trust from later root turns so stale authorization is not
  inherited.

## Testing

- Add an app-server lifecycle test covering inheritance of a root-invoked
  skill by a delegated worker and its removal on the next root turn.

GitOrigin-RevId: aa28f485edb7a447e51d51de8dc89b959fd63d40
2026-08-27 11:31:40 +00:00
Ankush Gupta 89650c66f2 Require synchronous review for sensitive MCP actions (#41094)
## What changed

- Recognize `codex_sensitive_action: true` on MCP approval elicitations.
- Route marked actions to the synchronous Guardian reviewer instead of extension fast approval. Absent or false values preserve the existing path.
- Cover ordinary and strict auto-review configurations, including marked, unmarked, and explicitly false metadata.

GitOrigin-RevId: dce13d1696568ca81c8d2b08a7ef0d5f13e155bf
2026-08-27 08:44:54 +00:00
Dylan Hurd 2c4a95736b Expose response usage metadata in completion events (#41087)
## What changed

- Parse optional `usage_metadata.amount` values from Responses API completion events without converting their string representation.
- Propagate the metadata through SSE and WebSocket streams, regular turns, and remote compaction.
- Add `usageMetadata` to the app-server `rawResponse/completed` notification and its generated schemas.

## Testing

- Cover missing, null, zero, and high-precision amounts, including completion events emitted during compaction.

GitOrigin-RevId: b16d81e8350eab0dc7ff613d0dc9dbed73041713
2026-08-27 07:50:05 +00:00
pmccrary-oai 57e2edc6e9 Encrypt sensitive history and notes tool arguments (#41041)
## What changed

- Mark history and notes search queries, appended note text, and replacement note text as encrypted in their tool schemas.
- Send `x-openai-encrypted-tool-arguments: true` for the corresponding backend routes without changing the JSON request body.

## Testing

- Cover encrypted schema fields and backend headers for history search, notes search, append, and write calls.
- Verify unrelated history and notes requests do not receive the encrypted-arguments header.

GitOrigin-RevId: 58263cff832c979b436ddb4013b5c27218aca678
2026-08-27 03:59:54 +00:00
marksteinbrick-oai 307ce6cda9 Track Guardian reviewer turn and tool analytics (#41023)
## Why

Trusted Guardian reviewer sessions can emit events without an app-server listener, leaving their turns and tool usage absent from analytics.

## What changed

- Translate Guardian session lifecycle and canonical tool item events into analytics notifications while excluding messages, reasoning, and review content.
- Preserve Guardian lineage during prewarming even when inherited client metadata is not yet available, without emitting an incomplete thread initialization event.
- Limit direct session tracking to trusted Guardian children so resumed threads that have an app-server listener do not report duplicate events.

## Testing

- Cover completed, failed, and interrupted Guardian turns, tool counts and timing, lineage, content exclusion, prewarmed lineage, and resumed-thread deduplication.

GitOrigin-RevId: 70ace5f7ed30a7e3b6a9d6097c8b2a6a326dc4f7
2026-08-27 02:19:10 +00:00
xl-openai 7c3747941a Reduce skill catalog prompts with path aliases (#41011)
## Why

Repeated skill locator roots can make catalog prompts larger even when the
catalog fits within its metadata budget.

## What changed

Evaluate aliased catalogs regardless of budget pressure and select them when
they preserve skill inclusion and description content while reducing prompt
size. Apply the same selection to combined host, executor, and orchestrator
catalogs.

## Testing

Add coverage for alias selection in full host-only catalogs and update skill,
symlink, and orchestrator resource tests to expect shortened locators and their
root mappings.

GitOrigin-RevId: ccedd3f3f6c7efaa1e5177a2d8c3d81d59239f52
2026-08-27 01:22:23 +00:00
felixxia-oai b68acc4d4b Trust invoked user skills in Guardian reviews (#41006)
## Why

Guardian treated all skill instructions as untrusted, so it could not use the
invocation of a user-owned skill as authorization evidence.

## What changed

- Record explicit and implicit skill invocations through extension contributors.
- Send Guardian a bounded, deduplicated list of canonical skill paths only when
  they resolve under the user's Codex or `.agents` skill directories.
- Keep repository skills and symlinks that escape trusted roots untrusted, and
  send only verified paths rather than skill contents to the classifier.
- Avoid recording host skill prompts that were superseded by core skill
  injection.

## Testing

- Added unit coverage for trusted roots, symlink escapes, deduplication, and
  size limits.
- Added integration coverage showing that Guardian trusts invoked user skills
  while rejecting a forged repository skill.

GitOrigin-RevId: 1cc0be230f7e6649110201c23c3de8f26447ff36
2026-08-27 00:07:26 +00:00
soyeon-oai ae357e7250 Attach verified access context to eligible plugin MCP calls (#41005)
## What changed

- Fetch ChatGPT account access and attach `cyber_trusted_access` under
  `openai/entitlementContext` when an installed or selected plugin explicitly
  requests it from a local, read-only stdio tool with no arguments.
- Reject caller-supplied entitlement context on direct MCP calls, and fall back
  to an `unknown` status when access cannot be verified or the account changes
  during the lookup.
- Count entitlement lookup time against the MCP tool-call timeout.

## Testing

- Cover eligible calls plus unowned, remote, HTTP, mutable, argument-bearing,
  API-key, undeclared, direct, and account-switch cases in core and app-server
  integration tests.

GitOrigin-RevId: 303b61585ef4530276c373d914a2d0ccef1f4ac2
2026-08-27 00:02:26 +00:00
rka-oai e56e4922eb Support standalone tool outputs in turn/start (#41002)
## What changed

- Add an optional `toolOutput` to `turn/start` for starting or steering a turn with a named function-call output instead of user input.
- Emit standalone outputs as `functionCallOutput` thread items, persist them in durable history, and include them in resumed threads.
- Validate that tool outputs have a name, are not combined with nonempty `input`, satisfy the text-size limit, and use supported image URLs.

## Testing

- Cover standalone tool-output notifications, model input, and resumed history in both legacy and paginated history modes.
- Cover the text-size limit for structured tool output.

GitOrigin-RevId: a1eeec7b9b7de67b1a1c5e829a54552b85ec118b
2026-08-26 23:58:10 +00:00
andrewgu-oai f3741880f6 Harden managed proxy listener handoff (#40999)
## Why

Linux managed networking routed proxy connections through filesystem-backed Unix sockets, requiring an extra readable sandbox path and stale socket cleanup.

## What changed

- Transfer loopback TCP listeners from the sandbox namespace to host bridge processes over anonymous Unix socket pairs.
- Validate transferred descriptors, keep bootstrap channels private to each sandbox launch, and close them before running untrusted commands.
- Tie proxy bridge lifetime to the sandbox so cancellation closes active upstream connections.

## Testing

- Cover descriptor validation and interrupted handoffs.
- Verify concurrent sandboxes keep proxy endpoints isolated and do not inherit privileged sockets.
- Exercise managed networking end to end through `app-server`, confirming proxied access succeeds while direct host access remains blocked.

GitOrigin-RevId: 6561e09c83b927c604951bf2aa00ff532d179da5
2026-08-26 23:41:18 +00:00
Brandon Zhang 0d654e6536 Track window and fork positions in turn metadata (#40987)
## What changed

- Add the zero-based `window_number` to Responses turn metadata and include it in prewarm requests.
- Persist `forked_from_ordinal_exclusive` separately from the physical history base so fork lineage remains accurate after reverts and cold resumes.
- Report context-inheriting subagents through `parent_thread_id` without also emitting fork lineage.
- Reserve the new metadata keys while accepting and filtering previously valid configured values so Codex-owned values take precedence.

## Testing

- Cover window numbering across compaction, resume, and fork operations.
- Cover fork cutoff persistence across direct forks, legacy rollouts, reverts into inherited history, and cold resumes.

GitOrigin-RevId: 288f6cd632254814c1f166668b33828082d799a1
2026-08-26 22:37:59 +00:00
jif 102ae5e2e6 Prewarm Guardian WebSockets without blocking thread startup (#40985)
## Why

Opening Guardian's initial WebSocket connections can be delayed, but thread startup and resume do not need to wait for those connections.

## What changed

- Install the Guardian sampler and related thread state before opening its initial connections.
- Prewarm the sampler's WebSocket pool in a background task while retaining the existing on-demand connection behavior.

## Testing

- Verify extension startup returns before a delayed WebSocket handshake completes, then warms the full initial connection pool.
- Verify resuming a thread likewise returns before Guardian's delayed handshake completes.

GitOrigin-RevId: 58c91cf045b223f917c67d7e8dc82eac529db4ce
2026-08-26 22:10:47 +00:00
felixxia-oai d61ba72f2f Give Guardian trusted context for configured MCP tools (#40982)
## What changed

- Add a bounded developer context fragment identifying the MCP server or connector and the user-owned configuration that declared it.
- Emit the fragment only when the effective entry matches the user configuration or an active plugin declaration resolves inside the Codex home directory.
- Keep tool descriptions, outputs, and unrelated tools untrusted, and reject unsupported sources or paths that escape through symlinks.

## Testing

- Cover user-configured servers and connectors, plugin-provided capabilities, token truncation, symlink escapes, and app-server request integration.

GitOrigin-RevId: 0bfe2a2f3a48334d1d5faad692b5d36452febb68
2026-08-26 21:48:05 +00:00
jif daa3eaf10f Allow Guardian scoring for required computer-use models (#40967)
## Why

Models that require automatic review previously skipped Guardian v2 risk scoring
entirely, even when Guardian was limited to computer-use tools. That scope cannot
use a low-risk result to approve unrelated tools, so the blanket skip is
unnecessary.

## What changed

- Retain Guardian v2 risk scoring for required-review models in
  `ComputerUseOnly` scope while continuing to skip it in standard scope.
- Preserve strict automatic approval review for Node REPL-backed tools, including
  when classification fails.

## Testing

Added coverage for low-risk, high-risk, and invalid classifications across the
Node REPL and computer-use REPL paths, plus an unrelated MCP tool.

GitOrigin-RevId: ee38fabf82e196df0ae13b4216b5892be9b799cf
2026-08-26 20:07:39 +00:00
Channing Conger ac644ed112 Stop preserving bounds in tool input schemas (#40966)
## What changed

Remove `minimum`, `maximum`, and `maxLength` from the supported tool input
schema representation. Schema parsing now drops these bounds instead of
including them in generated tool declarations, including declarations for
reserved history and notes tools.

GitOrigin-RevId: b7c7733651e65d38cc3d0cef2efa127ab3f8a32f
2026-08-26 19:59:08 +00:00
willwang-openai 6ac012a0d4 Honor layered configuration when loading plugins (#40954)
## What changed

- Resolve plugin activation, MCP server policy, and marketplace definitions from the effective configuration stack, including system settings and trusted project overrides.
- Load plugin skills independently for each working directory passed to `skills/list`.
- Exclude project configuration from catalog requests whose `cwds` are omitted or empty.
- Cache up to eight loaded plugin configurations with least-recently-used eviction so requests for different working directories can reuse their results.

## Testing

- Cover layered plugin and MCP policy across trusted and untrusted projects.
- Cover per-directory skill and plugin catalog results, cache reuse and eviction, and system-defined marketplaces.

GitOrigin-RevId: cb68b2b1bdab1da48e05ca7562bc05014431fc71
2026-08-26 19:02:02 +00:00
Francis Chalissery 7276d67081 Expose resumable misalignment details through app server (#40952)
## Why

App-server clients need the explanation and steering instruction returned with a
misalignment policy violation to offer a user-confirmed continuation. Missing or
incomplete details must continue to behave as a terminal block.

## What changed

- Parse optional misalignment classification, explanation, and steering details
  from streamed and HTTP Responses errors and propagate them through core errors.
- Include the details in live app-server `error` and `turn/completed` payloads and
  export the corresponding protocol schemas and TypeScript types.
- Keep explanations and steering messages out of serialized rollout events and
  redact them from debug output.
- Document how clients can resume with `turn/start` after user confirmation.

## Testing

- Cover streamed, HTTP, and WebSocket-wrapped errors, including malformed and
  classification-only details.
- Verify live app-server notifications expose resumable details without writing
  the explanation or steering message to the rollout.

GitOrigin-RevId: 329258a444c2cd91d0c57ab1720830b33ddcfac5
2026-08-26 18:42:44 +00:00
jif 10d5a603ae Persist Guardian V2 risk scores without restoring them (#40884)
## What changed

- Append accepted Guardian V2 classification results to rollout history for non-ephemeral threads.
- Keep resumed and forked threads from restoring a persisted score into active Guardian state.

## Testing

- Verify that asynchronous scoring records the resulting `SecurityRiskScore` rollout item.
- Seed resume and fork tests with a persisted score and verify that approvals ignore it.

GitOrigin-RevId: 40d63a2ea7e7cf6398402c6aed7d5e5727dc9d68
2026-08-26 13:54:36 +00:00
jif 039eb58a0b Give Guardian reviewers read-only access to parent history (#40848)
## Why

Guardian approval reviews may need the original user instructions to decide
whether a command is authorized.

## What changed

- Forward the parent thread's `history.list_windows`, `history.list_items`,
  `history.read_item`, and `history.search_contents` executors to Guardian
  reviewer sessions.
- Keep other parent extension tools, including the `notes` namespace, isolated
  from Guardian reviewers.

## Testing

Add an app-server integration test that reads parent history during a Guardian
review and verifies that `notes` tools are not exposed.

GitOrigin-RevId: 65a90036577050adfa23b1d98f862233c994d9d7
2026-08-26 09:23:41 +00:00
olliem-oai 9dea1f709f Default Guardian v2 to computer-use reviews with images (#40846)
## What changed

- Default Guardian v2's review scope to computer-use tools. Set
  `features.guardianv2.review_scope.computer_use_only = false` to retain the
  broader tool review scope.
- Include images in Guardian transcripts by default. Set
  `features.guardianv2.transcript.include_images = false` to disable them.

## Testing

- Update configuration and app-server coverage for the new defaults and
  explicit broader-scope overrides.

GitOrigin-RevId: 88c3cfe6dd2a96df052111794ad59c5c9ea39b78
2026-08-26 09:13:33 +00:00
Brandon Zhang 25a6e316c8 Make history and notes tools Bridge-compatible (#40775)
## What changed

- Express nullable history and notes arguments with `anyOf` and remove unsupported schema constraints.
- Forward valid JSON object arguments to the backend without enforcing client-side limits.
- Clarify history ID, ordering, cross-agent path, and consistency semantics in the tool descriptions.

## Testing

- Cover forwarding previously restricted argument values for every history and notes tool.
- Verify app-server requests expose the Bridge-compatible schemas and still reject non-object arguments locally.

GitOrigin-RevId: 28809fe9da5099944fd04962b5e71ffda4163eea
2026-08-26 03:46:23 +00:00
pakrym-oai 75cb7c903d Preserve MCP tool output as content items (#40737)
## What changed

- Convert unstructured MCP results into typed function-call output items instead of serializing the entire content array as a text string.
- Keep structured MCP results as serialized text and preserve media, encrypted content, and unknown content through their existing item conversions.
- Drop empty text items during output truncation so they do not consume API array slots.

## Testing

- Cover text-only, mixed unstructured, structured, and image-sanitized MCP results.
- Verify empty text items are discarded under byte- and token-based truncation policies.

GitOrigin-RevId: fa1c5b7dee6f003a094265379dcabdd060386a48
2026-08-25 23:42:50 +00:00
sayan-oai 4213b38f3c Honor attachment-owned permissions for MCP servers (#40728)
## Why

MCP servers attached to executor environments must retain their owner's
permission profile instead of inheriting the thread-wide sandbox authority.

## What changed

- Resolve and capture a permission profile for each enabled MCP server when
  publishing the runtime, and reject calls or elicitations when that authority
  is unavailable.
- Use the captured server profile for tool approval decisions, elicitation, and
  sandbox metadata, including after runtime refreshes.
- Materialize `:workspace_roots` from `PathUri` values so permissions preserve
  the path convention of remote executor environments.
- Give threadless app discovery and resource reads an explicit default
  permission profile.

## Testing

Added coverage for per-server elicitation authority, unresolved attachments,
runtime refreshes, restricted tool calls, and foreign-platform workspace roots.

GitOrigin-RevId: 6b188d4b08b29e9971ff7aa68a7785a0cdf9e394
2026-08-25 22:50:49 +00:00