Commit Graph
9801 Commits
Author SHA1 Message Date
Won Park da4cf1cdea Preserve Windows proxy settings in Guardian sessions (#40641)
## Why

Guardian sessions can run alongside another Windows sandbox launch and should not reconcile the persistent proxy settings established by that launch.

## What changed

- Start internal Guardian sessions with `WindowsSandboxProxySettingsMode::Preserve`.
- Continue using `Reconcile` for other sessions.

## Testing

Added a thread manager test that verifies a parent session reconciles proxy settings while its internal Guardian session preserves them.

GitOrigin-RevId: c6a31637ecdf828548cfd7153da7e9405abe34fa
2026-08-25 16:53:47 +00:00
hefuc-oai 5ce04789fb Honor managed plugin disablement for executor capabilities (#40640)
## Why

Selected executor plugin roots could still expose capabilities when managed
requirements disabled the `plugins` feature.

## What changed

- Suppress MCP servers, skills, apps, and connectors from selected executor
  plugins when `plugins` is disabled, while preserving the selected-root
  identity used to filter those capabilities.
- Apply the policy consistently to direct selected-root discovery and batched
  executor capability discovery.

## Testing

- Add contributor-level and app-server coverage that verifies disabled plugin
  capabilities are absent and their MCP servers never start.

GitOrigin-RevId: e30bd8a936c4b0e083908b89a65f4d02e01747de
2026-08-25 16:47:13 +00:00
Abhinav e44bd9b64d Retry timed-out cloud config loads in the background (#40637)
## Why

A startup timeout leaves the cloud config loader with a cached error, while the
normal background refresh interval delays recovery for 15 minutes.

## What changed

- Retry timed-out cloud config bundle loads after 5 seconds through the existing
  background worker.
- Keep serving the cached snapshot to concurrent readers instead of triggering
  additional fetches.
- Restore the normal 15-minute refresh interval after a successful retry or a
  non-timeout error.

## Testing

Added paused-time tests covering repeated startup timeouts, successful recovery,
application of the recovered bundle to later config loads, and restoration of
the normal refresh interval after both success and validation failure.

GitOrigin-RevId: da62abbae9be7f40af61f4c4adaf4ea5c337ec88
2026-08-25 16:38:46 +00:00
Tamir Duberstein 20c3f9733f Restart pending MCP connections when startup timeout changes (#40636)
## Why

Reusing an MCP connection that is still starting after its
`startup_timeout_sec` changes leaves the old startup budget in effect.

## What changed

- Track the effective startup timeout on each MCP connection.
- Reuse a pending startup only when its timeout still matches the current
  configuration.
- Continue reusing ready connections when only the startup timeout changes.

## Testing

Added integration coverage that refreshes the timeout while one server is
still initializing and another is ready, verifying that only the pending
startup is replaced.

GitOrigin-RevId: 5ed71a57d3bf0dd6e227aacd16acd3a35bc37ecf
2026-08-25 16:20:38 +00:00
Tamir Duberstein f5853cbe90 Reconnect MCP servers when authentication mode changes (#40634)
## What changed

- Include the configured authentication mode in the MCP connection identity so
  runtime reconciliation replaces connections instead of reusing them after an
  authentication-mode change.
- Add a regression test covering a switch from OAuth to ChatGPT authentication
  for an executor-owned MCP server.

GitOrigin-RevId: 18cd9df62a9a5ee44594dcde6a844ad7d5e67ee2
2026-08-25 16:14:26 +00:00
Alex Zamoshchin 304c8de4c6 Allow extensions to skip host skill discovery (#40631)
## What changed

- Add the under-development `skip_host_skill_discovery` feature to bypass host
  skill snapshots during session warmup and turn setup.
- Let skill invocation contributors declare whether they require host-owned
  skills. Preserve host discovery when no contributors are registered or any
  contributor requires it.
- Keep executor and orchestrator skill catalogs and instruction loading
  available when host discovery is skipped.

## Testing

- Cover executor-only, orchestrator, mixed-contributor, and legacy host-skill
  behavior.

GitOrigin-RevId: 48169403090b234e1a304c6523633fd867df454a
2026-08-25 16:00:02 +00:00
Eric Traut a63cb33e8d Show reconnect guidance when disconnecting from tasks (#40629)
## Why

Exiting a TUI connected to a persistent app server can leave work running, so
the existing session-exit summary does not explain how to reconnect or stop the
active turn.

## What changed

- Distinguish disconnects, interrupted turns, and removed threads when building
  exit summaries.
- For daemon and remote sessions, report whether work may still be running and
  print commands to reconnect or stop the current turn.
- Sanitize remote WebSocket addresses in displayed commands and preserve the
  configured remote authentication environment-variable option.
- Keep the existing token-usage and resume summary for embedded sessions.

## Testing

Add coverage for daemon, remote, interrupted, embedded, archived, and deleted
session exits, including credential sanitization.

GitOrigin-RevId: 9cbbf9c7dd36423a5ed99909a2b4cb32e3e87712
2026-08-25 15:55:35 +00:00
Eric Traut 0cdb1f1c83 Harden goal continuation and remove duplicate prompt helpers (#40628)
## What changed

- Teach goal continuations to distinguish concrete progress, verified waits on live handles, and turns that made no progress.
- Re-poll live work after observation timeouts instead of treating the work as terminal or restarting it, and carry equivalent blockers through the existing blocked audit.
- Remove the duplicate goal prompt renderers and templates from `codex-prompts`; goal steering remains owned by the goal extension.

GitOrigin-RevId: 4ec64721164743e879ae946a2dd024bba5869fbe
2026-08-25 15:50:19 +00:00
Benjamin Carlsson 34c5303f49 Ignore closed agents when changing directories (#40625)
## Why

Closed agent channels can retain stale in-progress turns, which can incorrectly
block `/cd` or cause unnecessary background-terminal checks.

## What changed

- Mark agents closed whenever a `thread/closed` notification is routed, including
  for inactive event channels.
- Exclude closed agents from running-turn detection and background-terminal checks
  during working-directory changes.

## Testing

Cover directory-change recovery with both a routed close notification and a
replay-only closed thread that contains a stale in-progress turn.

GitOrigin-RevId: 1072456056f8c1a1b751a52635470b0be160d76c
2026-08-25 15:15:06 +00:00
Benjamin Carlsson f832b2fe7b Add worktree settings parser (#40624)
## What changed

- Add the `codex-worktree` crate for resolving managed worktree settings from
  the existing `[desktop]` configuration.
- Default the worktree root to `$CODEX_HOME/worktrees`, automatic cleanup to
  enabled, and retained worktrees to 15.
- Validate configured roots, cleanup flags, and retention counts before
  exposing the effective settings.

## Testing

- Cover defaults, configured values, and invalid root and retention settings.

GitOrigin-RevId: 1b279c62ef41e3c8eb540ce9beaf0f6cd96d903f
2026-08-25 15:10:27 +00:00
jif 4b81410a80 Treat user input answers as Guardian authorization changes (#40623)
## Why

Answers collected by `request_user_input` can change what the user authorizes, but post-tool hooks may replace or reject the tool output that Guardian normally sees.

## What changed

- Record bounded, host-observed answers before post-tool hooks run and provide them as trusted evidence to synchronous and asynchronous Guardian reviews.
- Include root-thread answers in worker review context.
- Count successful answers as authorization changes so earlier review evidence becomes stale, while ignoring empty or unrelated answers.

## Testing

Add coverage for allowed and denied stale reviews, empty and oversized answers, hook-modified output, and root-to-worker propagation.

GitOrigin-RevId: 970c52e40338ecd057c7cd2a69d04b06e97cd068
2026-08-25 15:03:46 +00:00
Tamir Duberstein c395364915 Keep the active goal clock current in the TUI (#40622)
## Why

The active goal's elapsed-time label could become stale while the TUI was idle because it was refreshed only as part of a redraw.

## What changed

- Refresh the goal status indicator when the terminal-title timer fires.
- Request a redraw only when the displayed elapsed-time label changes.

## Testing

- Add a regression test covering the minute transition and confirming that an unchanged label does not trigger another redraw.

GitOrigin-RevId: f10a1c2334cf7a5f1d2ee90d7138114479998c8d
2026-08-25 14:47:53 +00:00
jif e16d098c00 Instrument exec-server shell snapshot capture (#40620)
## What changed

- Emit `codex.shell_snapshot` and `codex.shell_snapshot.duration_ms` for each
  exec-server capture attempt, including success and failure tags.
- Label exec-server metrics as `v2` and existing core snapshot metrics as `v1`
  so the two implementations can be distinguished.
- Use the exec server's metrics client when available and fall back to the
  configured global client for local execution.

## Testing

- Extend the bounded-retry and single-flight snapshot test to verify metric
  counts and tags for first-attempt success, retries, recovery, and exhaustion.

GitOrigin-RevId: 94f73e58a4a1a90c518fa102f138ca7ee29b5627
2026-08-25 14:34:25 +00:00
Tamir Duberstein 6525b95dae Refresh animated terminal titles without redrawing the TUI (#40618)
## Why

Terminal title animations only need to update the title, but each animation tick
previously requested a full TUI frame.

## What changed

- Track the next terminal title refresh deadline on `ChatWidget`.
- Have the foreground event loop refresh the title when that deadline expires.
- Clear the deadline when title animations are disabled or the configured title is
  empty.

## Testing

- Verify spinner and action-required animations set the expected refresh deadlines.
- Verify refreshing an animated title does not enqueue a TUI draw request.

GitOrigin-RevId: 269347cd48de4ad9ba9a0aef9ed105c25d1a7dae
2026-08-25 14:24:18 +00:00
chess ed42068c45 Add a turn-scoped service tier override (#40616)
## What changed

- Add `serviceTierForTurn` to `turn/start` so a newly started turn can override the service tier without changing the thread's saved tier.
- Treat `"default"` as standard speed and omitted or `null` values as inheriting the thread tier.
- Keep `serviceTier` authoritative for subsequent turns when both fields are supplied, and ignore the turn-scoped override when steering an active turn.

## Testing

- Extend the app-server turn-start test to verify both the one-turn `"default"` override and inheritance on the following turn.

GitOrigin-RevId: 4c2c4db21d8d31617a7a6e6df65bf54834e72383
2026-08-25 14:04:32 +00:00
jif d7510aa4b4 Preserve pending input after terminal turn errors (#40613)
## Why

Pending user input or agent mail could cause a regular task to restart immediately after a terminal compaction error, retrying the failed turn instead of completing it and preserving the pending input.

## What changed

- Stop the regular-task continuation loop when the turn records a terminal error.
- Allow turn completion to persist pending input so a later explicit request can retry it after the error is resolved.

## Testing

Added coverage for pre-turn and mid-turn compaction failures with steered input, queued agent mail, and mail that triggers a turn.

GitOrigin-RevId: 48c7a2cba44ac2444957556dd94910fb34515f09
2026-08-25 13:59:52 +00:00
Tamir Duberstein 46aa019e80 Count serialized JSON bytes without allocating strings (#40604)
## Why

History estimation and executed-tool-call limits only need the size of serialized JSON, not the serialized output itself.

## What changed

- Add a shared `serialized_json_bytes` helper that streams JSON into a byte counter.
- Use it for response-item size estimates and executed-tool-call argument limits.
- Preserve serialization errors so callers can apply their existing fallback behavior.

## Testing

- Cover response-item sizing with escaped characters, newlines, and multibyte text.

GitOrigin-RevId: a4417996df96df5c51cae62830adc496912f69c7
2026-08-25 13:10:24 +00:00
Felipe Coury 70b5cfc73b Probe Windows terminal colors without risking startup input (#40598)
## Why

Windows Terminal and xterm.js can render a theme that differs from the
underlying console color table. Querying that visible theme through OSC shares
the console input queue with keystrokes, including input for security-sensitive
startup prompts.

## What changed

- Defer the Windows OSC color probe until protected startup decisions and the
  world-writable workspace scan have completed.
- Preserve and replay unrelated console input records around the probe, while
  removing only valid OSC 10 and 11 replies and retaining the console palette
  as a fallback.
- Require an explicit confirmation key after shortcuts select trust, sandbox,
  or world-writable warning choices, so a fragmented terminal reply cannot
  accept them.
- Accept one- through four-digit OSC RGB components so the visible terminal
  palette is applied across supported response formats.

## Testing

Added coverage for delayed startup scans, protected prompt confirmation,
console-record replay, bracketed paste and malformed OSC preservation, RGB
response parsing, and light-theme composer rendering.

GitOrigin-RevId: b8ae456fe32c701ba3af31e9cc452fc4e8bffa22
2026-08-25 12:20:41 +00:00
felixxia-oai 1f5c9ba183 Optimize Guardian transcript window retention (#40597)
## What changed

- Track protected messages, ordinary messages, and tool entries in separate pools with cached token totals.
- Evict the oldest eligible evidence across pools while preserving transcript token and entry limits and the reserved recent tool entries.

## Testing

- Add regression coverage that a small, tool-heavy transcript window retains the latest final assistant reply.

GitOrigin-RevId: 7aa78d0b0609d8e45cb82e4f7773c0877a4d8224
2026-08-25 12:12:01 +00:00
felixxia-oai 076f17c114 Preserve conversation context in Guardian transcripts (#40594)
## What changed

- Protect developer messages and final assistant replies from eviction by ordinary message evidence in bounded Guardian v2 transcripts.
- Exclude legacy inter-agent messages from that protection and keep recent tool evidence available when the entry limit is reached.
- Retain cache-friendly chunked eviction when protected messages themselves exceed transcript bounds.

## Testing

- Add transcript unit coverage for message and token limits, rejected commentary, legacy inter-agent messages, and recent tool evidence.
- Add an extension test for preserving a final assistant reply after older tool entries are evicted.

GitOrigin-RevId: f37d5f25e4105d2ec8fae226a558b703cda69288
2026-08-25 11:33:59 +00:00
jif 7c6eb0eef1 Scope stop hooks for memory consolidation (#40587)
## Why

Background memory consolidation must honor managed completion policies without
running project completion checks or sending user-facing notifications.

## What changed

- Add a memory-consolidation stop target that selects managed policy hooks and
  executor-scoped cleanup while excluding user, project, session, and plugin
  stop hooks.
- End memory consolidation with an error when a managed stop hook rejects it,
  and propagate that turn error into agent status.
- Disable legacy completion notifications for the background memory worker.

## Testing

- Cover hook selection, executor cleanup, managed rejection, agent error
  status, and notification suppression.

GitOrigin-RevId: be350679ddcde2dde8a408b0972f08facff01a37
2026-08-25 10:29:26 +00:00
jif 4fa6ad1730 Track remaining multi-agent v2 tools in analytics (#40585)
## What changed

- Record collaboration tool analytics for `send_message`, `followup_task`,
  `interrupt_agent`, and `list_agents`, including receiver attribution, duration,
  failures, and interrupted calls.
- Include these calls in per-turn subagent tool counts while keeping the existing
  `subAgentActivity` output unchanged and omitting additional public collaborator
  tool items.
- Extend the collaboration tool schemas with the new tool variants and the
  `interrupted` terminal status.

## Testing

- Add an app-server integration test covering successful and failed calls,
  receiver attribution, duration, prompt omission, activity items, and turn
  counts.

GitOrigin-RevId: e73eaa05c508261e5fc97e7d08d7881a31e04e22
2026-08-25 10:17:03 +00:00
zm-oai d52478c52e Preserve Unicode paths in Windows batch aliases (#40570)
## Why

Windows batch aliases can fail to invoke Codex when the executable path contains
characters that are not representable in the active console code page.

## What changed

- Generate same-volume executable paths relative to the batch file using `%~dp0`.
- Keep absolute paths as a fallback when the executable and alias are on different
  volumes.

## Testing

Added Windows tests covering a Unicode profile path under code page 437 and an
executable on a different volume.

GitOrigin-RevId: 10093bbc9f19e4fbe2e22d9397e211a113302f45
2026-08-25 07:37:42 +00:00
Benjamin Carlsson 4347f94d55 Register the transcript v2 feature flag (#40554)
## What changed

- Add the under-development `transcript_v2` feature for the interactive
  transcript composer and turn-selection UI.
- Keep it disabled by default and expose it through the configuration schema
  and `codex features enable transcript_v2`.

## Testing

- Verify explicit configuration overrides and CLI persistence for the new
  feature.

GitOrigin-RevId: 138ab7851621c066e8121cc3eb6cd4e7299f9c31
2026-08-25 05:35:25 +00:00
Adam Perry @ OpenAI 8444cf63b5 Derive sandbox contexts from turn environments (#40551)
## What changed

- Add Windows sandbox mode, private-desktop behavior, and legacy Landlock selection to each `EnvironmentConfig`.
- Centralize sandbox context construction on `TurnEnvironment`, preserving environment-owned permissions, paths, and backend settings while applying additional permission grants.
- Use the environment-derived context for project instructions, capability discovery, file uploads, and filesystem-oriented tools.

## Testing

- Verify capability discovery uses the selected environment's permission profile and sandbox backends when they differ from the thread defaults.

GitOrigin-RevId: 7ae2fed90c8ada950f2e8431e571e9b2c793c291
2026-08-25 05:16:45 +00:00
alicec-oai 348f49b292 Include transparent background in image generation analytics (#40544)
## What changed

Add the optional `transparent_background` value to image generation event
parameters and populate it from the corresponding image generation item.

## Testing

Add reducer coverage for completed events with true, false, and unset values,
as well as failed events where the value is unset.

GitOrigin-RevId: a9ee13696acb34feb998b345f54889cac7a401d9
2026-08-25 04:35:51 +00:00
pmccrary-oai 2e4675919e Inject history notes hints into context windows (#40539)
## What changed

- Register the history-notes extension as a context contributor and fetch `thread_hint` from the configured history-notes backend.
- Add non-empty hints of at most 4,000 bytes to the context-window prompt, and omit hints when the request fails or the response is missing, empty, or oversized.
- Verify that app-server sessions use the native backend when `use_history_notes_extension` is enabled and retain the MCP bridge behavior when it is disabled.

## Testing

- Cover hint injection, request context, response validation, backend failures, and disabled-extension behavior in history-notes and app-server tests.

GitOrigin-RevId: 344a7bb79d962ea8b7c969f25b67a79423fc7fcc
2026-08-25 04:05:38 +00:00
pmccrary-oai 3a469a297d Route extension hints into context-window metadata (#40533)
## What changed

- Add a `ContextWindow` prompt slot for thread-scoped extension contributions.
- Include fragments in that slot in the token-budget context-window message.
- Keep the MCP `notes/thread_hint` bridge when the native history-notes extension is disabled, without falling back to it after a native request failure.

GitOrigin-RevId: befcb7cc8570b846094b2b542a112b186b39a30a
2026-08-25 03:38:24 +00:00
Dylan Hurd 9c9675d3d0 Represent terminal input in approval reviews (#40528)
## What changed

- Add a `writeStdin` Guardian action carrying the approval, process, input, and working-directory details.
- Distinguish `command` and `writeStdin` execution approval requests while defaulting missing kinds to `command` for compatibility with older events.
- Render terminal-input review progress, denials, timeouts, and retry actions in the TUI, and record the action separately in analytics.
- Keep terminal-input reviews as child approvals so they do not change the parent command item's lifecycle or reconstructed history.

## Testing

- Cover Guardian serialization, app-server protocol conversion, command history reconstruction, analytics classification, and TUI review flows for terminal input.

GitOrigin-RevId: b083d5e2963bdd23b928644ec03c7eb68ebf2950
2026-08-25 03:08:33 +00:00
mpc-oai a7b86b6201 Retry provider auth commands after initial failures (#40523)
## Why

A provider auth command can fail during initial credential resolution, leaving
no cached authentication. A subsequent `401` should still give the configured
provider one bounded opportunity to recover.

## What changed

- Treat configured external authentication with an empty cache as eligible for
  unauthorized recovery.
- Allow authority refresh to invoke the external provider when no prior auth is
  cached, while preserving the existing requirements for managers without an
  external provider.

## Testing

Added unit and client coverage for a provider command that fails initially and
succeeds during `401` recovery.

GitOrigin-RevId: 7cab9a03f90ce29b412be8fbd97b297acdad4482
2026-08-25 02:38:22 +00:00
Benjamin Carlsson c1db22a3cd Add dot-repeat to Vim mode (#40521)
## What changed

- Bind `.` in Vim normal mode to repeat the last complete edit.
- Record semantic delete, change, replace, paste, and insert-mode actions so repeats preserve motions, text objects, inserted text, and editor actions across keymap changes.
- Expose `vim_normal.repeat_last_change` in the configurable keymap and keymap picker, including conflict handling for existing custom bindings.

## Testing

- Add coverage for repeating deletes, replacements, complete changes, pasted and literal text, insert-mode editor actions, custom bindings, unavailable motions, and cleared buffers.

GitOrigin-RevId: 3213df964811e7902377ff1d93641e59f4037914
2026-08-25 02:34:04 +00:00
Andrei Eternal cbfd999db7 Add hooks for interrupted turns (#40511)
## What changed

- Add an `Interrupt` hook event that runs for an active top-level turn before its
  interrupted abort event is emitted.
- Flush the turn transcript before invoking the hook and provide the session,
  turn, transcript, working directory, model, and permission mode in its input.
- Support command and MCP handlers, including asynchronous commands, with a
  one-second default timeout and a three-second maximum.
- Expose the event through hook configuration, managed requirements, app-server
  notifications, generated schemas, analytics, and the TUI hook views.

## Testing

- Cover handler discovery, timeout normalization, output parsing, protocol
  compatibility, TUI rendering, and interrupt execution ordering.

GitOrigin-RevId: 163fa7c098d94ac2775f6d137f8e916f8ea9b6eb
2026-08-25 01:27:18 +00:00
joeytrasatti-openai 9b2ef38f54 Add persisted thread artifact models (#40509)
## What changed

- Add a `thread_artifacts` SQLite table with per-thread typed identities,
  JSON payloads, cascade deletion, uniqueness enforcement, and an index for
  ordered per-thread reads.
- Export artifact records, attachment and removal outcomes, and paginated
  result models from `codex-state`.

## Testing

- Add a migration test covering preservation of existing thread-section
  metadata and compatibility with the previous migration set.

GitOrigin-RevId: 4e0a8e5bfa168ae2b8871970466e5055e142a4a6
2026-08-25 01:10:10 +00:00
guinness-oai 41ca88e95c Persist realtime events in the thread timeline (#40508)
## Why

Clients need a bounded view of realtime conversations that preserves the order of speech, agent work, and turn lifecycle events without loading the full thread history.

## What changed

- Persist realtime session boundaries, transcript segments, and promoted agent items in paginated thread rollouts.
- Add the experimental `thread/timeline/list` API to page ordinary items, realtime items, and turn boundaries in canonical rollout order. Include `activeRealtimeSessionAtPageStart` so each page can be rendered independently.
- Emit typed `thread/realtime/item/started`, `thread/realtime/item/transcript/delta`, and `thread/realtime/item/completed` notifications around durable realtime items.
- Keep the existing `thread/items/list` response and legacy thread history behavior unchanged.

## Testing

- Cover mixed timeline pagination, realtime-session state at page boundaries, rollout replay, subagent history prefixes, transcript streaming, steering, and promoted agent artifacts.

GitOrigin-RevId: faa2c420192d63e060e8fb32446e3c797422656e
2026-08-25 01:03:20 +00:00
Eric Traut 80e871309a Route cyber Trusted Access links by plan type (#40504)
## What changed

- Send `Free`, `Go`, `Plus`, `Pro`, and `ProLite` ChatGPT users to the individual Trusted Access page when a cybersecurity policy error ends a turn.
- Keep the enterprise Trusted Access application for other plans and sessions without a ChatGPT account or known plan.

## Testing

- Cover individual and enterprise link selection in chat widget tests and history-cell snapshots.

GitOrigin-RevId: a563560d15c401b47f1865a6f58ea4692d31d457
2026-08-25 00:39:27 +00:00
Eric Traut ebe18fc982 Collapse home paths in AGENTS.md status summaries (#40502)
## What changed

- Render AGENTS.md paths under the home directory with `~` in `/status`.
- Preserve project-relative paths for instruction files inside or above the current working directory.

## Testing

- Add coverage for home-relative, parent, current-directory, and nested AGENTS.md paths.

GitOrigin-RevId: 6dd1ddf481d95dda9d16f7c03a7431d1297f87ec
2026-08-25 00:34:53 +00:00
victor-openai 5918c743f3 Deduplicate plugin skills in unified mentions (#40501)
## Why

Unified `@` search could show a plugin alongside the skills it owns, creating duplicate entry points for the same capability.

## What changed

- Add a nullable `pluginId` to `SkillMetadata` returned by `skills/list` so clients can associate skills with their owning plugin without inspecting names or paths.
- Hide a plugin's owned skills from unified `@` results when that plugin is present, while retaining standalone skills and skills with unknown ownership.
- Keep `$` focused on individual skills and apps, and use it consistently as the skills-list shortcut. Preserve the legacy mention behavior when `mentions_v2` is disabled.

## Testing

- Cover plugin ownership in `skills/list` and the updated `@` and `$` composer results.

GitOrigin-RevId: e168cdff8d0c58f74ce4c228a683880a3167775b
2026-08-25 00:15:49 +00:00
Owen Lin 465eafacbc Harden startup rollout migration against concurrent updates (#40499)
## Why

Another Codex process can write, archive, or compress a rollout while startup
migration is inspecting it. This can leave a discovered path stale or make an
in-progress rollout look empty or busy.

## What changed

- Wait for rollout maintenance to finish before starting background migration.
- Re-read empty rollouts under their writer lock and retry busy rollouts on a
  later startup.
- Find archived or compressed rollouts again when their paths change after
  discovery, while keeping terminal failures from blocking the startup cursor.

## Testing

Added coverage for maintenance contention, writer-owned empty rollouts, busy
rollout retries after archive and compression moves, permanent failure skips,
pending recovery, and paths that move after discovery.

GitOrigin-RevId: 9708f212f2bbff88bd47a01ec4872bf6ce9af535
2026-08-25 00:03:23 +00:00
spasumar-oai 4ef1d4b89b Increase the app-server model refresh interval (#40498)
## What changed

Change the background model refresh interval from 3 minutes to 4 minutes 30
seconds.

GitOrigin-RevId: dcefe471c91dc94a04ddc74595c3ce00d9061e55
2026-08-24 23:29:10 +00:00
Won Park 8476434a97 Harden internal Guardian session isolation (#40497)
## Why

Internal Guardian reviews must remain independent of parent-session customization while still honoring managed execution and environment restrictions.

## What changed

- Apply the restricted Guardian session path to both internal and subagent review sources.
- Start internal reviews without inherited user instructions, extensions, MCP servers, or multi-agent behavior.
- Preserve managed execution policy and selected environment constraints while exposing only the allowed review tools. Honor shell feature restrictions across every selected environment and retain code mode when enabled.

## Testing

- Cover internal review isolation from parent state and managed instructions.
- Cover optional tool filtering, managed shell restrictions, code mode, and secondary environment profiles.

GitOrigin-RevId: edbf7d8a6fe3ee8213a1c75bc8ec331a1cf49006
2026-08-24 23:23:18 +00:00
jif be3a666143 Track history, notes, and async messages as control tools (#40496)
## What changed

- Emit control-tool analytics for history and notes extension calls and for
  `send_user_message_async`.
- Preserve non-default namespaces in reported tool names, such as
  `history.read_item` and `notes.write_file`.

## Testing

- Add an app-server integration test covering successful and failed calls,
  turn-level tool counts, and omission of tool argument values from analytics.

GitOrigin-RevId: b15a53a311228339f4d577a7b96146ed67f22253
2026-08-24 23:19:03 +00:00
Felipe Coury 5a51caf04d Suggest conversation-based thread titles in /rename (#40495)
## What changed

- Generate a title suggestion from the latest substantive user and assistant messages when the TUI `/rename` prompt opens.
- Prefill the prompt with the result while keeping it editable and preserving any text the user enters before generation finishes.
- Bound and escape the conversation context, omit commentary and IDE context, and correlate responses with the active thread and prompt so stale suggestions are ignored.

## Testing

- Cover conversation selection and prompt construction, generated-title delivery through the embedded app server, loading and prefilled prompt states, stale responses, and preservation of manual edits.

GitOrigin-RevId: 1e7f1d5d4f6503ff9da0548388f610c446c130ca
2026-08-24 23:15:04 +00:00
Felipe Coury 0c992c305d Hide ephemeral system threads from TUI routing (#40494)
## What changed

- Ignore `thread/started` notifications for ephemeral threads whose feature source is `system`, preventing hidden helper threads from entering TUI thread routing or refreshing the agents overview.
- Continue routing persisted system threads normally.

## Testing

- Add coverage for hidden and persisted system-thread notifications in the agents overview.
- Add generated-title normalization cases for wrapping quotes, trailing punctuation, and meaningful leading punctuation.

GitOrigin-RevId: e1ea48502b4f9aa7d5a187c7407df69c55abe2a9
2026-08-24 23:12:33 +00:00
Felipe Coury b3c7e1a47f Generate descriptive TUI thread titles (#40492)
## What changed

- Give unnamed TUI threads an immediate provisional title from the first user message, then replace it asynchronously with a normalized generated title.
- Preserve manual renames by applying a generated title only while the provisional title is still current, and keep automatic rename notifications out of the transcript.
- Run title generation in a bounded ephemeral structured request that preserves custom permission profiles, otherwise uses read-only access, and disables tools and MCP servers.

## Testing

- Cover prompt and response bounds, Unicode-safe truncation, title normalization, manual-rename races, silent automatic updates, permission preservation, and structured-response failures.

GitOrigin-RevId: 7ed73522f4f6c65a005f65f3a903974d8419e312
2026-08-24 23:06:06 +00:00
Tamir Duberstein c941572917 Honor response budgets when reading skill resources (#40491)
## Why

`skills.read` paginated resources against a fixed response limit, so a page could exceed a smaller tool-call response budget.

## What changed

- Size each serialized `skills.read` page to the current call's response budget, accounting for JSON escaping and UTF-8 boundaries.
- Cache one bounded executor-resource snapshot per thread so cursor continuations return consistent contents without rereading the file. Replace the snapshot when another resource is read, and reject stale cursors after a reread.
- Tie cached executor snapshots to the selected environment and sandbox context without keeping the environment alive.

## Testing

- Cover budget-constrained reads, escaped and multibyte contents, multi-page reconstruction, changed resources, snapshot eviction, and expired turn-scoped access.

GitOrigin-RevId: e515935b82771b3f29b3fb91ea7a7a72e19a65ee
2026-08-24 23:00:57 +00:00
Winston Howes fd1bf50410 Harden project config when credential brokering is active (#40490)
## Why

Project configuration must not influence credential-provider environment variables or shell startup behavior while credentials are being brokered.

## What changed

- Track credential brokering as unconfigured, disabled, or enabled, and apply effective network proxy requirements before sanitizing project layers.
- When brokering is enabled, ignore project settings for shell snapshots, profile loading, `ZDOTDIR`, `BASH_ENV`, and credential-provider environment variables.
- Preserve those project shell settings when requirements disable credential brokering.

## Testing

Added coverage for active and disabled broker states, protected credential environment variables, and shell startup settings.

GitOrigin-RevId: 6967cbffdfbb60424a2d2324bad5b91bd2ccfcf6
2026-08-24 22:58:18 +00:00
hefuc-oai 1e9e916923 Honor disabled managed network configuration (#40489)
## Why

Managed network requirements can remain present when `enabled = false`, but a
disabled configuration should not create or expose an active proxy runtime.

## What changed

- Start the managed network proxy only when its effective specification is
  enabled.
- Clear an existing proxy when a permission-profile refresh disables managed
  networking.
- Keep remote executor launches free of managed-network proxy settings when the
  requirements explicitly disable the feature.

## Testing

Added session and unified-exec coverage for initial startup and refresh with
disabled managed networking.

GitOrigin-RevId: f76699802e079eb746d5b1ea6547d19a4bfb7715
2026-08-24 22:51:36 +00:00
xli-oai 2497518490 Export turn cost as an OTEL metric (#40488)
## What changed

- Emit `codex.turn.cost_microusd` as a counter with turn, conversation,
  interruption, speed, and reasoning-effort attributes. Convert the estimated
  USD string to microdollars, rounding to the nearest microdollar and skipping
  values that cannot be represented safely.
- Start turn-cost collection when an OTLP metrics exporter is configured, even
  when the OTEL log exporter is disabled.

## Testing

- Verify cost conversion, rounding, and metric attributes with an in-memory
  metrics snapshot.
- Verify that a metrics-only OTLP configuration starts the turn-cost worker.

GitOrigin-RevId: e60587079f097f10cc1b6d1bf889d3f7a0dc3d5f
2026-08-24 22:44:33 +00:00
rhan-oai fb9311db5c Extract agent role loading into a dedicated crate (#40487)
## What changed

- Add `codex-agent-roles` for agent role configuration types, parsing,
  discovery, validation, and layered loading.
- Update `codex-core` to consume the new crate's public role configuration and
  parsing APIs.

GitOrigin-RevId: 5a963a219a581b2848dae6fd071aa31a0b5ff22c
2026-08-24 22:40:35 +00:00
Eddie Chen 49880081fe Add root turn IDs to turn and tool analytics (#40486)
## Why

Analytics need to associate subagent activity with the top-level turn that
caused it, while avoiding a stale association when steering makes that origin
ambiguous.

## What changed

- Add `root_turn_id` to turn and tool-item analytics events.
- Read the root from live turn metadata when each event is built, reporting
  `null` when the root is unknown or ambiguous.
- Propagate the metadata through control-tool and code-mode completion facts so
  correlated and background tool events retain the correct root.

## Testing

- Cover root IDs for top-level turns, subagent turns, correlated code-mode
  calls, and tool events emitted after turn completion.
- Verify that queued and subsequent events report `null` after the live root is
  invalidated.

GitOrigin-RevId: 42fd76541c3c716cec74787d47b50adb2d22e6d2
2026-08-24 22:30:59 +00:00