Commit Graph
10112 Commits
Author SHA1 Message Date
jif 612e6491d5 Prewarm shell snapshots for eligible turns (#42137)
## Why

Shell Snapshot V2 previously captured the login-shell environment lazily when a
command started, adding that work to the command path.

## What changed

- Start one asynchronous snapshot capture after turn hooks accept the turn, so
  eligible local `exec_command` calls can reuse it without blocking the model.
- Use the turn's resolved tools, permissions, sandbox, environment, and shell
  configuration, and skip prewarming for unsupported or network-managed cases.
- Cancel outstanding prewarming during shutdown. Keep failed speculative
  captures retryable by real commands without consuming their retry budget.

## Testing

Added coverage for non-blocking capture and reuse, failure recovery, sandbox and
permission isolation, shutdown cancellation, hook-stopped turns, eligibility
gates, and concurrent capture retries.

GitOrigin-RevId: ff24a4f0328c06653e09d03fd0a3db1eccd65030
2026-09-01 21:16:12 +00:00
Owen Lin c5b5fa8089 Support thread forks from symlinked session roots (#42135)
## Why

Forking a resumed paginated thread failed when the managed `sessions` directory was a symlink, even though the rollout remained under that managed root.

## What changed

- Validate rollout lineage references against the canonical `sessions` and `archived_sessions` roots.
- Accept rollouts beneath symlinked managed roots while rejecting nested symlinks that escape those roots.

## Testing

- Cover forking a resumed rollout under a symlinked `sessions` root.
- Cover rejection of rollout lineage paths that escape through a nested symlink.

GitOrigin-RevId: 0128ecde7087120ef510baa3ed62cdbb33073117
2026-09-01 21:03:30 +00:00
Alex Zamoshchin a30fa3d830 Include app link metadata in MCP approval elicitations (#42134)
## What changed

- Preserve the selected app account `link_id` when building native MCP tool
  approval requests.
- Add `link_id` and `link_is_implicit` to the elicitation metadata, recognizing
  IDs with the reserved `implicit_link::` prefix as implicit links.

## Testing

- Extend the app link policy integration test to verify elicitation metadata
  for default, explicitly selected, and implicit account links.

GitOrigin-RevId: a76731d9f5f3640318187511ccdc0dc82967a9c5
2026-09-01 20:54:25 +00:00
Alex Zamoshchin 2393b5c920 Scope session MCP approvals to app account links (#42133)
## Why

Remembering an app tool approval by connector and tool alone could reuse an
approval when the same tool was called with a different selected account.

## What changed

Include the app `link_id` in MCP tool approval keys so remembered session
approvals apply only to the account link that was approved. Calls for another
link, or calls without a link selector, request their own approval.

## Testing

Add an integration test covering calls across two link IDs and the legacy
no-selector case.

GitOrigin-RevId: 7dd88330b75de312469020d5892dfb2fa5d5fada
2026-09-01 20:46:17 +00:00
Charlie Marsh 8436b749a4 Bound Git root discovery for metadata enrichment (#42132)
## Why

Git root discovery is optional metadata work, but filesystem probes can block. They should not exhaust Tokio's blocking pool, delay runtime shutdown, or prevent later turns from observing repository changes.

## What changed

- Add a shared `GitRootDiscovery` service that coalesces concurrent lookups for the same working directory and limits probes across directories.
- Run probes on detached threads, retain in-flight work across caller cancellation, and discard completed results instead of caching them.
- Use the service for turn and memory metadata enrichment, abort unused turn enrichment when its state is dropped, and limit memory metadata waits to one second.

## Testing

Add coverage for probe sharing, capacity limits, cancellation, fresh discovery, runtime shutdown, memory timeouts, and repositories restored after startup prewarming.

GitOrigin-RevId: bca46fc263e7a12a2f69146d8a0b3e7c7e0846cb
2026-09-01 20:41:32 +00:00
Matthew Zeng bd89ce67cc Prepare MCP connections for coordinated OAuth refresh (#42128)
## What changed

- Add the under-development `mcp_oauth_refresh_coordination` feature and pin its selected refresh mode to each MCP connection.
- Treat the refresh mode as part of OAuth connection identity so runtime and MCP configuration refreshes reconnect when the mode changes.
- Keep legacy refresh behavior in builds where coordination is unavailable and emit a warning when coordinated mode is selected.

## Testing

- Cover connection replacement when the feature is toggled through both runtime and MCP configuration refresh paths.

GitOrigin-RevId: 89596150f0338e6ede0e712badecea4450831766
2026-09-01 20:26:57 +00:00
willwang-openai 7730edf62c Ignore non-JSON files in plugin catalog test helpers (#42126)
## What changed

Restrict cached remote plugin catalog test helpers to `.json` files when
reading plugin IDs or rewriting `fetched_at` timestamps.

GitOrigin-RevId: a144f44a8adc26a8d0aa0d85e95c8fe0366e8aa0
2026-09-01 20:18:10 +00:00
Benjamin Carlsson 0276f2ee55 Preserve descriptive labels on local file links (#42123)
## What changed

- Render descriptive Markdown labels alongside canonical local file targets instead of discarding them.
- Collapse labels that resolve to the same path, accounting for relative and absolute forms, `file://` URLs, percent encoding, case, separators, and location suffixes.
- Preserve `~/` destinations for display and keep absolute paths unless they can be shortened relative to the session working directory.

## Testing

- Add unit and snapshot coverage for descriptive and path-equivalent labels, invalid percent encoding, trailing separators, Unix and Windows paths, UNC paths, `file://` URLs, and table wrapping.

GitOrigin-RevId: 636bf4485b2899d96c6273be3f3b7f38728c9013
2026-09-01 19:51:05 +00:00
jif 9112564114 Allow updating the approval reviewer for active turns (#42121)
## What changed

- Add `approvalsReviewer` to the experimental `turn/settings/update` API.
- Apply reviewer changes to subsequently captured steps and new background approval requests while preserving pending approvals and future-thread defaults.
- Allow reviewer-only updates without `step_model_switching`, while continuing to enforce managed reviewer restrictions and model-required auto review.
- Use an explicit live reviewer update for MCP approvals while retaining refreshed thread defaults for clients that have not set one.

## Testing

- Cover switching between user and automatic review during a live turn, future-turn isolation, and managed-authority rejection.

GitOrigin-RevId: e1216b09c6a7972c2c9eaf4955d8d57d60604ca1
2026-09-01 19:19:52 +00:00
Abhinav bc39b0ed59 Refine hook activity rendering in the TUI (#42118)
## What changed

- Show revealed running hooks in the bottom activity area instead of the conversation viewport or transcript overlay. Fold the hook message into the active status row when space permits and reflow it below the row without displacing background-process controls or status details.
- Keep fast hooks hidden, collapse concurrent hooks to a shared summary when needed, and support hook activity outside an active agent turn.
- Simplify durable hook output into user-facing messages and actionable failure, block, and stop states. Suppress model-facing context and quiet successful completions from all TUI history surfaces.

## Testing

- Add lifecycle, layout, narrow-width, multi-width Unicode, transcript, restart, and completion-output coverage for hook status and history rendering.

GitOrigin-RevId: 4c52b7a736e9e466e109107eb3c04a39d089597f
2026-09-01 19:06:32 +00:00
Charlie Marsh ea7e0714da Fix relative MCP server spawning on macOS (#42117)
## Why

Rust falls back to `fork` when a macOS command combines a relative executable
path with a working directory, due to a historical `posix_spawnp` issue. This
can make local MCP server startup less reliable.

## What changed

- Spawn relative macOS MCP executables directly with `posix_spawn`, preserving
  the configured path, `argv[0]`, working directory, environment, stdio, and
  process group.
- Keep the existing launcher for `PATH` lookup and executable text files without
  a shebang.
- Use one local child wrapper for legacy and 2026-07-28 protocol framing, with
  cancellation-safe waiting and cleanup that kills and reaps dropped children.

## Testing

Add macOS regression coverage for relative scripts, argument and descriptor
preservation, launch errors, cancelled waits, and cleanup after runtime shutdown.

GitOrigin-RevId: 1cbc6b90aed6f67e0a38f551964d80496ebc4471
2026-09-01 18:53:06 +00:00
willwang-openai ef76e6ac30 Centralize remote plugin mutations in PluginsManager (#42114)
## What changed

- Move remote plugin install and uninstall orchestration from the app server into shared `PluginsManager` APIs.
- Keep cache and backend mutations coordinated by the installed-plugin sync gate, and retain install outcomes long enough to protect newly materialized bundles during downstream setup.
- Return structured operation errors and outcomes so callers can preserve JSON-RPC error mapping, telemetry, cache refreshes, and OAuth setup.

## Testing

- Add regression coverage that verifies uninstall holds the mutation gate, preserves the local cache when the backend operation fails, and refreshes installed state after a successful uninstall.

GitOrigin-RevId: de39f19a4e61c6e9c76ddc2c65d2ac130a4b7f88
2026-09-01 18:35:00 +00:00
iceweasel-oai 1f4c47343a Apply remote platform semantics to exec safety checks (#42113)
## Why

Unified exec can run commands on an OS that differs from the Codex host. Using
host path and shell semantics for approval checks can therefore miss dangerous
Windows and PowerShell commands sent to a remote executor.

## What changed

- Thread the executor platform through command parsing, executable-name
  normalization, and dangerous-command classification. Legacy executors fall
  back to the host platform, while unknown reported platforms use Windows rules
  conservatively.
- Bound model-facing `exec_command` rejection messages and avoid echoing the
  rejected command into the error.
- Keep deterministic process IDs reserved after release so rejected test
  commands cannot reuse an earlier ID.

## Testing

- Add coverage that a long dangerous PowerShell command targeting a remote
  Windows executor is rejected with a bounded response.
- Verify deterministic process IDs advance after release.

GitOrigin-RevId: a26b4a63ea3d6df7140032b88b3e7aec0b85b948
2026-09-01 18:24:56 +00:00
teddywyly-oai c7c824dce4 Treat bundled cleanup hooks as built-ins (#42110)
## What changed

- Centralize the allowlist for bundled MCP cleanup hooks and use it for both local and executor-discovered plugins, including `unified-computer-use` cleanup through `cua_repl`.
- Mark matching cleanup hooks as trusted built-ins so they run without saved hook trust and remain active when regular hooks or their per-hook state are disabled. Plugin enablement and managed-only policy still apply.
- Hide built-in cleanup hooks from hook listings and lifecycle notifications while retaining their metrics. Keep the built-in classification out of serialized protocol data.

## Testing

- Cover allowlist boundaries, trust and enablement behavior, inline and file-based hook declarations, MCP success and error responses, hook listing, lifecycle notifications, metrics, and protocol serialization.

GitOrigin-RevId: f93b7bc99f4ed9694f529def8ec383b45f31430e
2026-09-01 18:02:27 +00:00
Charlie Marsh 84aa75204a Format Python scripts across the repository (#42109)
## Why

The root Python formatting pass only covered `scripts/`, leaving Python utilities elsewhere in the repository outside `just fmt` and `just fmt-check`.

## What changed

- Run the scripts Ruff formatter from the repository root.
- Exclude `sdk/python`, which has its own formatter pass, and `codex-rs/vendor`.
- Apply Ruff formatting to the newly covered Python files and update the formatter coverage test.

GitOrigin-RevId: 73ac82b8bb9c713d589724f6c4f926399febb513
2026-09-01 17:47:29 +00:00
Benjamin Carlsson 6a479e1813 Show full patches and terminal input in TUI history (#42107)
## What changed

- Render complete patch contents directly in TUI history cells.
- Render all input sent to background terminals inline.
- Remove the preview row and byte limits and their transcript hints so inline and transcript views contain the same content.

## Testing

Update snapshots to cover patches and terminal input longer than the former 12-row preview limit.

GitOrigin-RevId: 9960818a9b51fc0c7f84d9def77b9b1bd8acad6c
2026-09-01 17:37:47 +00:00
Eric Traut f40e08478c Show recent sessions in the agent command center (#42104)
## Why

The agent command center only listed sessions currently loaded by the app server, so completed or otherwise unloaded tasks could not be revisited from the overview.

## What changed

- Seed the overview with up to 20 recent root sessions in addition to loaded sessions, retain discovered sessions for the lifetime of the TUI, and update rows from thread lifecycle notifications.
- Allow unloaded sessions to be resumed from the overview using the normal working-directory selection and configuration rebuild flow. Explicit runtime permission choices carry across a cold resume, while settings inherited from the previously selected task do not.
- Fall back from `recency_at` to `updated_at` when connected to an older server, and continue showing loaded sessions when recent-history listing is unavailable.

## Testing

Added coverage for recent-session discovery and retention, notification races, legacy and failed listing fallbacks, cold-resume working-directory and permission handling, reconnect behavior, and unloaded-session rendering and selection.

GitOrigin-RevId: 668068b1594eb24b2ea7faccd0327804b8cd22ef
2026-09-01 17:28:35 +00:00
Adam Perry @ OpenAI 9969043b95 Extract OTEL trace WebSocket into a reusable crate (#42102)
## What changed

- Add `codex-otel-trace-websocket` with a `TraceWebSocket` API that owns the
  loopback OTLP receiver and WebSocket listener.
- Bind both listeners during startup, expose the exporter and bound listener
  addresses, and surface listener failures through a single lifecycle method.
- Update `codex-code-mode-host` to use the new crate and shut down the bridge
  after flushing its trace provider.

GitOrigin-RevId: ec5ca4c4369b6b3b1232875c2699730eb748ab1c
2026-09-01 17:17:45 +00:00
Felipe Coury 8ea297ff60 Add a TUI setting to disable automatic recaps (#42101)
## What changed

- Add the `tui.auto_recap` configuration option, enabled by default.
- When disabled, cancel scheduled automatic recap checks, reject automatic
  requests, and discard pending automatic results without retrying.
- Keep manual `/recap` requests available regardless of the setting.

## Testing

- Cover configuration defaults and command-line overrides.
- Cover scheduling cancellation, pending request cleanup, discarded results,
  and manual recaps while automatic recaps are disabled.

GitOrigin-RevId: 7d5323f58a2c84e60683a25a8c77653097efe6e2
2026-09-01 17:09:13 +00:00
Jiwon Kim b6ab99ed87 Prefer remote Sites over the bundled plugin (#42100)
## Why

When the remote Sites plugin is installed and its local bundle is available, exposing the bundled copy as well creates duplicate catalog entries and can load the wrong skills.

## What changed

- Persist an account- and backend-scoped exclusion for `sites@openai-bundled` once the remote replacement is installed and loadable.
- Apply the exclusion to plugin catalogs, search, direct reads and installs, runtime loading, hooks, and skill caches while preserving the remote plugin's server-owned enabled state.
- Restore the bundled fallback when the remote plugin is absent or its local files are unavailable, and throttle repeated availability checks for 60 seconds.

## Testing

- Added manager tests for persistence across restarts, account/backend isolation, fallback restoration, concurrent checks, and refresh throttling.
- Added app-server and agent-turn tests confirming that catalog, search, and skill loading prefer remote Sites.

GitOrigin-RevId: bc1154f79d3107910fee9fa27389a0ddb48ce6cf
2026-09-01 16:58:54 +00:00
chess a17ee5705c Make diagnostic report uploads resilient to slow networks (#42096)
## Why

Diagnostic reports can span several envelopes, and the previous 10-second shared
network budget could expire before slow uploads and their attachments completed.

## What changed

- Give each diagnostic report a single five-minute deadline shared by the event,
  attachments, retries, and retry backoff.
- Stop reading or sending later attachments once the deadline or a Sentry rate
  limit is reached.
- Limit the app server to three concurrent report uploads and return an
  overloaded JSON-RPC error for additional requests until a slot is released.

## Testing

Add coverage for slow multi-envelope reports, deadline-aware retries, skipped
attachments, rate-limit handling, and concurrency-slot release after failures.

GitOrigin-RevId: bdacf6c9731df16d2763e204565986eb6d540233
2026-09-01 16:49:16 +00:00
iceweasel-oai ade0ccacf9 Record Windows MXC availability (#42094)
## What changed

- Probe whether the native Windows MXC process security environment is usable
  when selecting a sandbox.
- Emit `codex.windows_mxc.available` at most once per process, labeled with the
  probe result.
- Add the MXC workspace dependencies for Cargo and Bazel, and pin
  `tracelogging` to a version compatible with the GNU Windows toolchain.

GitOrigin-RevId: d7cfeed6f0333feda5764e1ee44fe5bbd50f9a58
2026-09-01 16:40:05 +00:00
Alec Barber f4e6cb7876 Attribute Guardian reviews to OpenAI app tools (#42086)
## Why

Custom MCP tool names may contain user data, so they should not be added to Guardian metric tags.

## What changed

- Add the sanitized `tool` tag to Guardian review counts for MCP calls served by the OpenAI Apps server.
- Keep custom MCP calls and Guardian duration and token-usage histograms on their existing tags.

## Testing

- Cover network access, OpenAI app tool calls, and custom MCP tool calls in the Guardian metrics test.

GitOrigin-RevId: 6bd09ae461eab504f8f07bf7d0c9d1c0aa1317c9
2026-09-01 16:04:32 +00:00
felixxia-oai 6127478086 Centralize Guardian context composition (#42085)
## What changed

- Add `SectionRegistry::compose` to group collected authorization fragments and transcript entries while preserving fragment boundaries and registration order.
- Use the shared composed context in the core Guardian prompt and Guardian V2 synchronous and asynchronous reviewers.
- Keep transcript rendering, retention, and delta handling with each caller while removing duplicated section grouping and authorization rendering.

## Testing

- Cover composition for synchronous and asynchronous targets, including root conversation role handling, trusted user answers, transcript entries, empty context, and contributor failures.
- Verify the synchronous reviewer preserves authorization fragment boundaries in prompt items.

GitOrigin-RevId: 9268343631fd6417bb05a3c0abce883559a37685
2026-09-01 15:54:18 +00:00
Ankush Gupta 67cc3c318d Attribute nested REPL reviews to their tool calls (#42082)
## What changed

- Retain MCP invocation metadata for Node-backed REPL servers so nested
  elicitations can resolve the enclosing tool call.
- Use a valid, same-server `callId` from the current turn as the Guardian
  assessment target while continuing to review each nested action and connector
  independently.
- Fall back to an elicitation-specific target when `callId` is missing,
  malformed, unknown, from another server, or from an earlier turn.

## Testing

- Cover ordinary and strict reviews for `node_repl` and `cua_repl`, multiple
  nested decisions, unrelated servers, and invalid or stale call IDs.

GitOrigin-RevId: adea4b5cff96726a540ff3b3ea902b0f5dd99299
2026-09-01 15:34:03 +00:00
felixxia-oai 2350823caa Unify Guardian context section collection (#42076)
## What changed

- Add typed context sections for root-conversation evidence, trusted user answers, and conversation transcripts to `codex-guardian-context`.
- Use the shared section registry when building core Guardian prompts and asynchronous Guardian V2 scoring context.
- Preserve source-role labeling while delivering authorization evidence as user-role context, and fail closed when context collection fails.

## Testing

- Cover shared section ordering and role preservation for synchronous and asynchronous targets.
- Verify trusted user answers appear exactly once as user-role input in Guardian V2 approval flows.

GitOrigin-RevId: 1d5d793ffbf166077411a66e85e039596907fb7e
2026-09-01 15:22:21 +00:00
Charlie Marsh d141438342 Detect Vite+-managed Codex installs (#42071)
## Why

Vite+ launches Codex through the same JavaScript shim as npm, so Codex could
misidentify Vite+-owned installations and recommend npm for updates.

## What changed

- Detect Vite+ global installs from their package ownership metadata and pass a
  dedicated `CODEX_MANAGED_BY_VITE_PLUS` marker to the native binary.
- Represent Vite+ in install context and `codex doctor` output.
- Recommend `vp install -g @openai/codex` in update and repair flows for
  Vite+-managed installs.

See https://github.com/openai/codex/pull/30880.

GitOrigin-RevId: 8add724eefd31170a078086392609dbbd7f20b26
2026-09-01 15:12:53 +00:00
jif 82461c9990 Remove redundant test coverage (#42069)
## What changed

- Remove standalone TUI configuration tests whose defaults or parsing paths are
  already covered by broader configuration tests.
- Remove a duplicate JSON-result test that invoked the same model as the
  retained test.
- Remove a service-tier test whose `None` input case is already asserted by
  the neighboring filtering test.

GitOrigin-RevId: ae1304e72d03a1d44a735b4e5816936e7e4e2de5
2026-09-01 15:04:11 +00:00
Eric Burke 3c6bb8b3eb Detect standalone installs from the macOS CLI bundle (#42068)
## What changed

- Recognize executables under `CodexCLI.app/Contents/MacOS` and resolve the
  surrounding standalone package layout from its sibling `bin` directory.
- Preserve standalone install detection and access to bundled resources and
  path entries when Codex is launched through the app bundle.

## Testing

- Add a regression test for package layout and install method discovery from a
  bundled executable.

GitOrigin-RevId: 02b41a978b256da43df95a922bc5ee99a78b8168
2026-09-01 14:51:54 +00:00
jif 25ba0ae6cd Remove selected core test cases (#42066)
## What changed

Remove targeted tests for history normalization, exec-policy amendments,
default reasoning effort, collaboration instruction overrides, and sandbox
approval telemetry.

GitOrigin-RevId: 6f79bf4cd4b625b4ff750e3aa00a88871afc97f4
2026-09-01 14:43:27 +00:00
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 3a04482645 Honor app link settings for MCP tool approvals (#42056)
## What changed

- Pass the resolved app `link_id` into MCP tool approval policy evaluation.
- Apply link-specific `default_tools_approval_mode` and `approvals_reviewer`
  settings before app and global defaults, while preserving per-tool and managed
  policy precedence.

## Testing

- Cover link-specific approval prompts, selected account links, reviewer
  routing, fallback behavior, and managed-policy overrides.

GitOrigin-RevId: caa07ec3e73c87aad9522bd69808cd1c0b1686f5
2026-09-01 13:43:27 +00:00
Alex Zamoshchin 0e37d834d4 Honor explicit account selectors for Apps tool calls (#42054)
## What changed

- Resolve `link_id` from tool-call arguments when Apps metadata sets
  `requires_explicit_link_id` to `true`.
- Reject the call before approval or execution when the required selector is
  missing, empty, or not a string.
- Preserve catalog-provided account metadata for legacy Apps tools and leave
  non-Apps MCP tools unchanged.

## Testing

- Add unit coverage for required selectors, malformed values, legacy
  fallbacks, and non-Apps tools.
- Add end-to-end coverage for execution, approval prompts, and rejection when
  an Apps call omits `link_id`.

GitOrigin-RevId: 667fd04102a3934d53ded020da6d1bf68a1ca3e5
2026-09-01 13:29:18 +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
jif 90ae0c4ef9 Tag Codex home size metrics with compression state (#42043)
## What changed

Add a `compression_enabled` attribute to each
`codex.app_server.codex_home.size_bytes` sample. The value reflects whether
`LocalThreadStoreCompression` is enabled in the effective startup configuration.

GitOrigin-RevId: c087d36b4e578245aee6cfe5257075dfd3bdd025
2026-09-01 12:41:37 +00:00
jif 9d0eae74cd Include shared histories in rollout compression (#42039)
## What changed

- Make `local_thread_store_compression` compress cold rollout files across shared and forked histories without a separate compression mode.
- Retire `local_thread_store_shared_compression` while continuing to accept it in strict configuration without changing compression behavior.
- Read rollout files through the compressed-rollout reader when `codex exec resume` determines the latest turn's working directory.

## Testing

- Cover compression and restoration of an archived fork chain.
- Cover cwd-based resume selection when only the compressed rollout remains.
- Cover the removed compatibility key in strict configuration.

GitOrigin-RevId: 8edebf61eccc1f79cabb8e641f8982c76f337bf1
2026-09-01 12:23:20 +00:00
jif 2e5ee418ad Improve Guardian report diagnostics (#42033)
## Why

Reports from a large thread tree can exceed the rollout attachment limit, making
the threads involved in a failed Guardian review harder to diagnose.

## What changed

- Prioritize descendants with retained failed reviews when selecting bounded
  report rollouts, while always preserving the reported thread.
- Include each selected thread's available Guardian trunk rollout alongside its
  conversation rollout.
- Add a thread index attachment with selected filenames, bounded omission details,
  retained failure threads, and the process-wide discarded-record count.
- Link failed-review records to their reviewed turn and target item when available.

## Testing

- Cover failed-review prioritization, bounded omission metadata, discarded-record
  accounting, and turn/item linkage in Guardian report records.

GitOrigin-RevId: ae7916c27a3c279e899cd5a6ead8a4b7e0cc26a1
2026-09-01 11:14:20 +00:00
felixxia-oai 8209978616 Share Guardian user-message retention logic (#42031)
## What changed

- Add a shared `select_user_messages` helper in `guardian-context` that always
  anchors the first user message and fills the remaining token budget from
  newest to oldest.
- Use the helper for both core Guardian prompt rendering and the Guardian V2
  async scorer so they apply the same retention policy.

## Testing

- Cover empty and single-message transcripts, over-budget anchors, and
  newest-first selection across multiple token budgets.

GitOrigin-RevId: 7db246013875263ceb5806d2a6a19b4e2a3db1c4
2026-09-01 10:40:33 +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
Eric Traut d038f3448f Move disable_paste_burst under [tui] (#41976)
## What changed

- Add `tui.disable_paste_burst` as the preferred configuration key.
- Keep the top-level `disable_paste_burst` key as a legacy fallback.
- Give the `[tui]` setting precedence when both keys are present, while preserving configuration-layer precedence.

## Testing

Add configuration tests covering defaults, both key locations, precedence between the keys, and command-line overrides.

GitOrigin-RevId: e7fc9337d5b19d2fd9407e08b8301cee77a11779
2026-09-01 04:53:57 +00:00
Eric Traut c7fced56eb Track TUI starts by app server mode (#41974)
## What changed

Emit the `codex.tui.start` counter once per TUI launch with an
`app_server_mode` label of `in_process`, `local_daemon`, or `remote`. Recording
the metric during startup keeps reconnects from counting as additional
launches.

GitOrigin-RevId: 7527f319b95ae53f5278fa16120120a433a29ae4
2026-09-01 04:33:38 +00:00
willwang-openai 633ab199cf Enforce marketplace source policy for curated plugins (#41953)
## Why

Marketplace source restrictions should cover curated plugins backed by the OpenAI plugins repository, not only user-configured marketplaces.

## What changed

- Validate both local curated catalogs against the existing OpenAI plugins Git source allowlist.
- Apply that policy to catalog discovery, installation, cached plugin and skill loading, and startup repository sync.
- Keep bundled and remote installed plugins independent of the curated Git source policy.

## Testing

Added coverage for exact and shorthand Git allowlist entries, host patterns, blocked and invalid rules, curated catalog variants, plugin skills, startup sync, and remote installed plugins.

GitOrigin-RevId: 04617acb4a93040c70a13759eb4ce872877ba211
2026-09-01 01:37:15 +00:00
Adam Perry @ OpenAI 55e5158e18 Improve tracing for nested tool calls and exec processes (#41950)
## Why

Code-mode callbacks can outlive their initial request and run in separate tasks,
so their trace context must be preserved explicitly.

## What changed

- Preserve the execution context for code-mode callbacks and add spans for
  nested tool invocations in the runtime and dispatch broker.
- Propagate each tool invocation span as the parent of its streamed gRPC
  callback, falling back to the outer execution context when needed.
- Add a `codex.exec_server.process` span for each process lifetime, including
  its process ID and completion result, without retaining the request span.

GitOrigin-RevId: a6059e34d895416f5517e51dad6ca0078355adca
2026-09-01 01:00:50 +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
Adam Perry @ OpenAI c2e5692e2c Expand extension permission regression coverage (#41946)
## What changed

- Verify image-generation extensions rebind permissions on every turn, preserving session grants while expiring turn-only grants.
- Cover executor skill reference reads under current filesystem permissions, including paginated reads, permission changes, and edits between pages.
- Verify oversized live executor skill prompts emit a warning without replacing previously injected prompt content.

GitOrigin-RevId: 1fc8eef409fa65db4bb1ab6a00408fe72c9e938f
2026-09-01 00:42:19 +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
Benjamin Carlsson 9c7edd4bc3 Add Vim undo to the TUI composer (#41941)
## Why

Composer drafts include attachments, mention targets, and deferred paste payloads in addition to visible text. Vim undo needs to restore that complete state as a single edit.

## What changed

- Add bounded, draft-level Vim undo history, with `u` as the configurable default binding in normal mode.
- Group complete Vim commands and insert sessions into undo steps, including direct composer changes such as pastes and attachments.
- Preserve undo, repeat, and search state when a reverse-history preview is canceled, and start fresh history when another prompt is accepted.

## Testing

- Cover grouped edits, custom bindings, history and search interactions, attachments, and large paste payloads.

GitOrigin-RevId: 12ecdb3c34a2d66f5d856aa2f82dc15bd91b230b
2026-09-01 00:21:22 +00:00
Benjamin Carlsson c5a3700dd7 Preserve transcript layout caches during backtrack selection (#41940)
## Why

Moving between prompts in backtrack mode rebuilt every transcript renderable and
discarded their cached heights, causing the entire transcript to be laid out
again for each selection change.

## What changed

Rerender only the previously highlighted cell and the newly highlighted cell.
Keep all other renderables, cached heights, and the live tail intact while
continuing to scroll the selected prompt into view.

## Testing

Add regression tests that verify selection changes preserve unrelated height
caches and produce the same viewport and scroll position as a full rebuild,
including with a live tail and terminal width changes.

GitOrigin-RevId: 685a8ce65ecadef20521ce2ded7b516fdf8499c9
2026-09-01 00:12:22 +00:00
Benjamin Carlsson 0e03f88a30 Clarify resume guidance in exit summaries (#41938)
## What changed

- Show the exact `codex resume <thread-id>` command on its own indented line.
- When a thread has a name, also explain that users can run `codex resume` and select the named thread from the picker.
- Apply command highlighting to both resume options when color is enabled.

## Testing

- Cover unnamed, empty-name, named, colored, and embedded-session exit summaries.

GitOrigin-RevId: d97c04db8a34376c6d9ea839b515b04a384b85d1
2026-09-01 00:02:38 +00:00