175 Commits

• Pin MCP runtimes to model steps (#30101)

  ## Why
  
  An MCP refresh can replace the session's current manager while a model
  step is still running. The step must execute calls through the same
  manager whose tools it advertised.
  
  ## Boundary
  
  ```text
  current session MCP runtime
            |
            | capture once for this model step
            v
  StepContext.mcp
    - exact MCP config
    - exact connection manager
    - exact runtime environment context
  ```
  
  ```rust
  pub struct McpRuntimeSnapshot {
      config: Arc<McpConfig>,
      manager: Arc<McpConnectionManager>,
      runtime_context: McpRuntimeContext,
  }
  ```
  
  ## Example
  
  ```text
  step A captures runtime A and advertises A's tools
  refresh publishes runtime B
  step A tool call -> runtime A
  next step        -> runtime B
  ```
  
  Capturing the snapshot is only an `Arc` clone. It does not restart MCPs
  or make an RPC.
  
  ## What changes
  
  - Captures one MCP runtime in `StepContext`.
  - Uses it for tool planning, tool calls, resources, approvals, connector
  attribution, and elicitation.
  - Publishes replacement runtimes atomically.
  - Lets an old runtime live only while an in-flight step or request still
  holds its `Arc`.
  
  Most of this diff is mechanical routing from the session-global manager
  to `step_context.mcp`; it does not introduce selected-plugin discovery
  yet.
  
  ## What does not change
  
  - No plugin or extension migration.
  - No new MCP cache policy.
  - No environment file watching.
  - No client sharing between separate managers.
  
  ## Stack
  
  1. Extension-owned World State sections.
  2. Project executor skills through World State.
  3. **This PR:** pin one MCP runtime to each model step.
  4. Project selected MCP/app/connector metadata by environment
  availability.
  5. One end-to-end integration scenario.

  jif · 2026-06-26 00:53:07 +01:00
  ee9e0f6387
• Persist selected capability roots and resolve availability per model step (#29856)

  ## Why
  
  `selectedCapabilityRoots` is durable thread intent: “use this capability
  root from environment `worker`.”
  
  The important product assumption is:
  
  > One environment ID always names the same logical executor and stable
  contents.
  
  `worker` does not silently change from executor A to an unrelated
  executor B. The process-local connection handle for `worker` can still
  be replaced while Codex is running, though, for example when
  `environment/add` registers a fresh handle for the same logical
  environment.
  
  The thread should persist only the stable selection. Each model step
  should pair that selection with the exact ready handle captured for that
  step.
  
  ## The boundary
  
  ```text
  persisted thread intent
    plugin@1 -> environment "worker"
                  |
                  | capture the current step
                  v
  model-step view
    unavailable, or
    plugin@1 + worker's exact captured ready handle
  ```
  
  The environment ID is the stable identity and cache key. The
  `Arc<Environment>` is only a process-local handle retained so consumers
  of one model step use the same captured environment. It is never
  persisted and it does not imply different environment contents.
  
  ## What changes
  
  ### Persist the stable selection
  
  Selected roots are written into `SessionMeta` and restored with the
  thread. Forked subagents inherit the same selections, including
  bounded-history forks.
  
  Only stable data is persisted: root ID, environment ID, and root path.
  
  ### Capture readiness together with the exact handle
  
  The environment snapshot records:
  
  ```rust
  environment_id -> Some(Arc<Environment>) // ready in this step
  environment_id -> None                   // still starting in this step
  ```
  
  This prevents readiness and execution from coming from different
  registry snapshots.
  
  For example:
  
  ```text
  step snapshot: worker -> handle A, ready
  environment/add: worker -> fresh handle B for the same logical environment
  current step: plugin@1 still uses captured handle A
  ```
  
  Without carrying handle A in the snapshot, the resolver could combine “A
  was ready” with handle B and treat B as ready before it had finished
  starting.
  
  This does not change cache invalidation. Stable capability metadata
  remains identified by environment ID and capability root. Replacing a
  process-local handle under the same stable environment ID does not
  invalidate or rediscover that metadata.
  
  ### Resolve availability per model step
  
  - A ready captured environment produces resolved roots using its
  captured handle.
  - A starting, missing, or failed environment is omitted from that step.
  - A selected lazy environment that is outside the turn's captured
  environment set is asked to start, and a later step can observe it as
  ready.
  - No capability files are scanned here.
  
  Transient transport disconnects remain the remote client's reconnect
  concern. This PR models initial attachment/readiness; it does not add
  live socket-connectivity state.
  
  ## Example
  
  ```text
  thread selection: plugin@1 -> environment "worker"
  
  step 1: worker is starting -> plugin@1 unavailable
  step 2: worker is ready    -> plugin@1 resolves through worker's captured handle
  step 3: fresh local handle -> current step remains pinned; a later step captures its own view
  ```
  
  Temporary unavailability does not discard the durable selection. Later
  PRs can retain stable metadata caches while projecting only currently
  available capabilities into model-visible World State.
  
  ## Compatibility
  
  The app-server request shape does not change. Older rollouts without
  `selected_capability_roots` deserialize to an empty list.
  
  ## Stack
  
  1. **This PR:** persist stable selected roots and resolve them through
  an exact model-step handle.
  2. #29960: cache stable skill metadata and project available skills into
  World State.
  3. #29946: cache stable plugin declarations and manage the separate live
  MCP runtime.

  jif · 2026-06-25 17:49:43 +00:00
  8f02973d25
• core: make AGENTS.md react to environment changes (#29810)

  ## Why
  
  With deferred executors, a turn can begin before a remote environment
  attaches. AGENTS.md discovery previously ran only during session setup,
  so instructions from a later environment never reached the model or the
  session instruction sources.
  
  WorldState persistence has now landed, so this uses the durable
  model-visible baseline directly instead of carrying a temporary
  resume/fork compatibility path.
  
  ## What
  
  - Add an `AgentsMdManager` in `SessionServices` to own host
  instructions, loaded state, and refresh caching.
  - When `DeferredExecutor` is enabled, refresh AGENTS.md when attached
  environment selections change and freeze the result in the corresponding
  `StepContext`.
  - Represent AGENTS.md as a persisted WorldState section for every
  session, with bounded initial, replacement, and removal updates.
  - Remove duplicate AGENTS.md state and rendering from
  `SessionConfiguration` and `TurnContext`.
  - Build initial context, per-request updates, and compaction context
  from the same step-scoped value.
  - On resume and fork, compare current instructions with the restored
  WorldState baseline and inject a replacement exactly once when they
  differ.
  
  Builds on #29833, #29835, and #29837.
  
  ## Tests
  
  - Covers a remote environment becoming ready mid-turn, with AGENTS.md
  appearing on the next request exactly once and updating canonical
  instruction sources.
  - Covers full, unchanged, replaced, and removed AGENTS.md WorldState
  rendering.
  - Covers changed instructions across cold resume and fork without
  duplicate reinjection.
  - Covers remote-v2 compaction retaining creation-time instructions in
  the live session and cold resume appending one replacement when the
  source changed.
  - Ran focused `codex-core` AGENTS.md, WorldState, and context-update
  test suites.

  sayan-oai · 2026-06-24 22:57:42 -07:00
  f2f80ef442
• core: reset context for token budget compaction (#29743)

  ## Why
  
  When `Feature::TokenBudget` is enabled, compaction should behave like
  `new_context`: start a fresh context window with the standard injected
  context, without asking the server to summarize old history and without
  carrying prior user or assistant messages into the next model request.
  
  This is still a compaction operation from the client lifecycle
  perspective. Manual `/compact` and auto-compaction should keep the same
  observable side effects that clients and hooks expect, including compact
  hooks and `TurnItem::ContextCompaction`.
  
  ## What changed
  
  - Added `compact_token_budget` to run token-budget manual and inline
  auto-compaction through a shared compaction lifecycle.
  - Split pending `new_context` requests from forced context-window
  startup: `take_new_context_window_request()` consumes pending requests,
  and `start_new_context_window()` installs a fresh context window.
  - Routed token-budget manual `/compact` and inline auto-compaction to
  install a fresh context window locally instead of calling server/local
  summarization.
  - Preserved compact lifecycle side effects for token-budget compaction
  by running pre/post compact hooks and emitting `ContextCompaction` item
  start/completion events.
  - Updated token-budget tests to assert fresh window IDs, absence of
  server-side compaction calls, dropped prior transcript messages/tool
  output after reset, and compact hook/item lifecycle behavior.
  
  ## Testing
  
  - `just test -p codex-core
  token_budget_context_uses_new_window_after_compaction`
  - `just test -p codex-core token_budget_compaction_runs_compact_hooks`
  - `just test -p codex-core
  token_budget_mid_turn_auto_compaction_resets_before_active_follow_up`
  
  ---------
  
  Co-authored-by: pakrym-oai <pakrym@openai.com>

  Michael Bolin · 2026-06-23 16:59:04 -07:00
  32b65bbf7a
• core: persist initial context window metadata (#29519)

  ## Why
  
  PR #29494 made context-window IDs visible to the model by wrapping the
  token-budget window payload in `<context_window>`, but rollout JSONL
  consumers still could not see the initial window identity by tailing the
  session file. Compacted rollout items carry window IDs only after
  compaction has happened, so a session with no compaction had no durable
  JSONL record for window 0.
  
  This change gives tailing consumers a stable initial-window record at
  session creation time.
  
  ## What Changed
  
  - Added `session_meta.context_window.window_id` for the initial
  context-window identity.
  - `CreateThreadParams` now requires `initial_window_id: String`, so
  thread-store callers cannot accidentally create new threads without
  window-0 metadata.
  - Live thread creation derives the persisted initial window ID from the
  same `AutoCompactWindowIds` used to initialize `SessionState`, keeping
  runtime state and JSONL metadata aligned.
  - Rollout reconstruction uses `session_meta.context_window.window_id` as
  the initial-window fallback and derives `window_number = 0`,
  `first_window_id = window_id`, and `previous_window_id = None`
  internally.
  - Fork reconstruction intentionally uses the same rollout reconstruction
  path; consumers that need to distinguish copied initial-window metadata
  can use the rollout `thread_id`.
  - Legacy compactions without `window_number` still use compaction-count
  fallback accounting instead of being reset to window 0 by the
  initial-window fallback.
  - Compacted rollout metadata still takes precedence once compaction
  records exist, preserving the richer chain fields there.
  
  ## JSONL Shape
  
  Real rollout JSONL is one object per line. This example is expanded for
  readability, but shows the new initial `session_meta.context_window`
  record followed by the existing compacted rollout item shape that also
  carries window IDs:
  
  ```jsonl
  {
    "timestamp": "2026-06-22T12:00:00.000Z",
    "type": "session_meta",
    "payload": {
      "session_id": "<THREAD_ID>",
      "id": "<THREAD_ID>",
      "timestamp": "2026-06-22T12:00:00.000Z",
      "cwd": "/repo",
      "originator": "codex",
      "cli_version": "0.0.0",
      "source": "cli",
      "model_provider": "<MODEL_PROVIDER>",
      "context_window": {
        "window_id": "<INITIAL_WINDOW_ID>"
      }
    }
  }
  ...
  {
    "timestamp": "2026-06-22T12:34:56.000Z",
    "type": "compacted",
    "payload": {
      "message": "<COMPACTION_SUMMARY>",
      "replacement_history": [
        "..."
      ],
      "window_number": 1,
      "first_window_id": "<INITIAL_WINDOW_ID>",
      "previous_window_id": "<INITIAL_WINDOW_ID>",
      "window_id": "<NEXT_WINDOW_ID>"
    }
  }
  ```
  
  The nested `context_window` object is intentional: it gives rollout
  consumers a stable namespace for context-window metadata while only
  writing the non-derivable initial `window_id`. For the initial window,
  `window_number`, `first_window_id`, and `previous_window_id` are derived
  internally instead of being written to the rollout.
  
  ## Verification
  
  - `just test -p codex-protocol`
  - `just test -p codex-rollout
  recorder_materializes_on_flush_with_pending_items`
  - `just test -p codex-core reconstruct_history`
  - `just test -p codex-core
  record_initial_history_reconstructs_forked_transcript`
  - `just test -p codex-thread-store`
  - `just test -p codex-state`
  - `just test -p codex-app-server
  thread_read_returns_summary_without_turns`
  - `just test -p codex-rollout persistence_metrics`

  Michael Bolin · 2026-06-23 21:50:50 +00:00
  01f89c8c59
• [codex] add configurable token budget compaction reminder (#29255)

  ## Why
  
  The token-budget feature reports coarse remaining-context milestones,
  but it does not give the model a configurable wrap-up prompt before
  automatic compaction. A strict threshold-crossing check can also miss
  resumed or reconfigured windows that are already inside the threshold.
  
  ## What changed
  
  - Add structured `[features.token_budget]` configuration for an absolute
  `reminder_threshold_tokens` and bounded `reminder_message_template`;
  `{n_remaining}` is expanded when the reminder is delivered.
  - Compute remaining tokens against the next effective auto-compaction
  boundary, including scoped `body_after_prefix` accounting and the full
  context-window limit.
  - Make reminder delivery level-triggered before and after sampling, with
  one-shot state owned by `AutoCompactWindow` and re-armed on compaction,
  `new_context`, restore, or history replacement.
  - Leave the existing initial full-window token-budget context, 25/50/75%
  notices, and token-budget tools unchanged.
  - Persist the resolved feature configuration in the session config lock
  and regenerate the config schema.
  
  ## Validation
  
  - `just test -p codex-core token_budget`
  - `just test -p codex-core
  token_budget_reminder_emits_after_crossing_compaction_threshold`
  - `just test -p codex-core auto_compact_window`
  - `just test -p codex-core
  lock_contains_prompts_and_materializes_features`
  - `just test -p codex-features`
  - `just test -p codex-config`

  pakrym-oai · 2026-06-20 19:13:42 -07:00
  6df037d47f
• core: add context window lineage IDs (#29256)

  ## Why
  
  The rendered `<token_budget>` fragment identifies the thread and current
  context window, but it does not expose enough lineage to identify the
  first window in the thread or the immediately preceding window. Those
  IDs also need to remain stable across compaction, resume, and rollback.
  
  ## What changed
  
  - Track first, previous, and current UUIDv7 context-window IDs in
  auto-compaction state.
  - Render `thread_id`, `first_window_id`, `previous_window_id`, and the
  current window ID in the full `<token_budget>` fragment.
  - Persist the first and previous window IDs in compacted rollout
  checkpoints and restore them during rollout reconstruction.
  - Preserve compatibility with older compacted records that do not
  contain the new optional fields.
  - Update focused state, rendering, reconstruction, rollback, and
  serialization coverage.
  
  ## Validation
  
  - `just test -p codex-core token_budget`
  - `just test -p codex-protocol compacted_item::tests`
  - `just test -p codex-core tracks_prefill_and_window_boundaries`
  - `just test -p codex-core
  reconstruct_history_uses_replacement_history_verbatim`
  - `just test -p codex-core
  thread_rollback_restores_cleared_reference_context_item_after_compaction`

  pakrym-oai · 2026-06-20 13:15:49 -07:00
  d1209bddfc
• core: add UUIDv7 context window IDs (#28953)

  ## Why
  
  The token-budget context currently identifies a context window by its
  thread-local sequence number. A UUIDv7 gives the model a stable opaque
  identity that remains fixed for a window and rotates when compaction or
  `new_context` starts the next one.
  
  ## What changed
  
  - Preserve the existing monotonic value as `window_number` and add a
  UUIDv7 `window_id` to `CompactedItem`.
  - Generate and rotate the UUID with auto-compaction window state,
  persist it alongside the number, and reconstruct it on resume and
  rollback.
  - Accept legacy compacted rollout records where the numeric `window_id`
  represented the window number.
  - Use the UUID only in token-budget context; existing request headers
  and metadata continue using `thread_id:window_number`.
  
  ## Testing
  
  - `just test -p codex-protocol compacted_item::tests`
  - `just test -p codex-core token_budget`

  pakrym-oai · 2026-06-18 17:00:49 -07:00
  5c12034e42
• current time reminders impl for system clock (varlatency 2/n) (#28824)

  Stacked on #28822.
  
  ## Summary
  
  - add a host-injectable current-time provider with a built-in system
  implementation
  - record UTC developer reminders in history immediately before due model
  requests
  - keep cadence state per session and force a refresh after compaction
  
  This does NOT include the app server client <-> server clock logic. This
  PR is only for the reminder message & system clock that will be used in
  prod.
  
  ## Testing
  
  - `just test -p codex-core varlatency_`
  - `just clippy -p codex-core -p codex-app-server -p codex-mcp-server -p
  codex-thread-manager-sample`
  - `just fmt`

  rka-oai · 2026-06-18 19:18:42 +00:00
  752ed90d78
• Support openai/form extended form elicitations (#27500)

  # Summary
  Allow App Server clients to opt into `openai/form` MCP elicitations.

  Gabriel Peal · 2026-06-18 11:54:49 -07:00
  21a599fa56
• Replace SkillsManager with SkillsService (#28705)

  ## Why
  
  Host skill discovery was still exposed as a manager even though it is a
  process-owned service shared by sessions, the app-server catalog, and
  file-watcher invalidation. The skills extension also consumed an ad hoc
  loaded-skills wrapper instead of a named immutable snapshot.
  
  ## What changed
  
  - replace `SkillsManager` with concrete `SkillsService`
  - make the service cache and return immutable `HostSkillsSnapshot`
  values
  - migrate the skills extension host provider to the snapshot boundary
  - migrate app-server catalog, watcher, and invalidation paths to the
  service
  
  This keeps the service limited to host discovery, caching, roots, and
  invalidation. Catalog rendering and invocation remain extension
  responsibilities for the next stacked change.

  jif · 2026-06-17 17:01:06 +02:00
  0318381762
• [codex] Bind shell snapshots to retained thread environments (#28421)

  ## Why
  
  Shell snapshots are currently session-scoped even though shell and cwd
  are properties of a selected turn environment. That makes snapshot
  refresh depend on separate session-cwd plumbing, prevents retained
  environments from retaining their snapshot work, and can make snapshot
  construction use a different shell than command execution.
  
  This follows #27955 by making the retained thread-environment service
  own environment snapshot lifecycles. Session configuration remains the
  requested selection state, while `ThreadEnvironments` remains the source
  of successfully resolved environments.
  
  ## What changed
  
  - Configure the shell-snapshot builder before initial environment
  resolution.
  - Start each local environment snapshot task when its `TurnEnvironment`
  is built and retain that shared task while environment ID and cwd still
  match.
  - Inherit retained environment snapshots into spawned child threads.
  - Carry the selected `TurnEnvironment` through shell runtimes so
  snapshot construction and command execution use the same
  environment-specific shell and cwd.
  - Load project instructions and warm plugins/skills after initial
  environment resolution.
  - Continue decoding invalid UTF-8 instruction files lossily without
  emitting a startup warning.
  - Keep requested selections in `SessionConfiguration`; failed or
  duplicate resolutions only affect the resolved environment snapshot.
  
  ## Validation
  
  - `cargo check -p codex-core --tests`
  - `just test -p codex-home instructions` (6 passed)
  - Focused environment, instruction, shell-snapshot, and user-shell tests
  (84 passed)
  - Focused shell-snapshot, user-shell, and unified-exec tests (126
  passed; two event-timing tests passed on retry)

  pakrym-oai · 2026-06-15 20:10:53 -07:00
  022f1221e8
• [codex] retain resolved environments across turns (#27955)

  ## Why
  
  Selected execution environments are thread-scoped resources, but startup
  and turn construction repeatedly resolved their IDs and working
  directories. That discarded existing environment handles and shell
  metadata even when a selection had not changed.
  
  Session configuration updates also need to affect future turns without
  changing the resolved environment set already captured by a running
  turn.
  
  ## What changed
  
  - Create a `ThreadEnvironments` service inside `Codex` from the spawned
  `EnvironmentManager` and raw environment selections, then store it on
  `SessionServices`.
  - Split service construction from `update_selections`, allowing session
  configuration updates to mutate the resolved set in place.
  - Retain an existing `TurnEnvironment` when its environment ID and
  working directory match; resolve only added or changed selections and
  remove selections that are no longer present.
  - Normalize duplicate IDs by keeping the first selection and skip
  individual selections that fail to resolve instead of rejecting the
  entire update.
  - Give each `TurnContext` a cloned `TurnEnvironmentSnapshot`, so later
  session configuration updates affect future turns without rewriting an
  active turn.
  - Reuse the service-owned environment manager and resolved snapshot for
  startup work, MCP initialization, and child-thread spawning instead of
  flowing resolved environments through spawn arguments.
  
  ## Test plan
  
  - `cargo check -p codex-core --tests`
  - `just test -p codex-core environment_selection`
  - `just test -p codex-core turn_environments`
  - `just test -p codex-core
  session_update_settings_does_not_rewrite_sticky_environment_cwds`
  - `just test -p codex-core
  default_turn_does_not_overlay_legacy_fallback_cwd_onto_stored_thread_environments`

  pakrym-oai · 2026-06-15 16:15:07 -07:00
  9728992fab
• core: cache the tool search handler per session (#27258)

  ## Why
  
  Tool router construction rebuilds the deferred-tool BM25 index during
  session initialization and before each sampling continuation, even when
  the searchable tool metadata is unchanged. Local profiling measured
  `append_tool_search_executor` at roughly 113 ms per continuation, making
  repeated index construction the largest measured router-building cost.
  
  ## What changed
  
  - Add a session-scoped `ToolSearchHandlerCache` so continuations and
  user turns can reuse the existing handler.
  - Key reuse on the complete ordered `Vec<ToolSearchInfo>`, rebuilding
  when searchable text, loadable tool specs, source metadata, or ordering
  changes.
  - Build handlers outside the cache lock and recheck before publishing
  them, avoiding holding the mutex during index construction.
  
  ## Verification
  
  - `cache_reuses_identical_search_infos_and_rebuilds_changed_inputs`
  covers exact cache reuse and invalidation when the ordered search
  metadata changes.
  - Local rollout profiling showed the initial router build populating the
  cache and unchanged later continuations reusing it:
    - uncached: 118 ms median across 14 spans from 3 rollouts
    - cached: 4 ms median across 12 spans from 3 rollouts

  mchen-oai · 2026-06-15 14:48:30 -07:00
  af99f6a72f
• [codex] simplify shell snapshot ownership (#27756)

  ## Why
  
  Shell snapshot lifecycle state was split between `Shell` and
  `SessionServices`: `Shell` carried the receiver while session code
  exposed and forwarded the raw sender. That coupled shell identity to
  mutable snapshot state and made refresh, inheritance, and file lifetime
  harder to reason about.
  
  ## What changed
  
  - make each `Arc<ShellSnapshot>` represent one cwd-specific snapshot
  generation
  - store the active generation in `SessionServices` with `ArcSwapOption`
  - have construction start the background build and expose only a
  cwd-validated snapshot path
  - use `ShellSnapshotFile` ownership to delete snapshot files
  automatically
  - pass snapshot paths explicitly to shell runtimes instead of storing
  snapshot state on `Shell`
  - preserve inherited and in-flight generations by pinning their `Arc`
  while they are in use
  
  ## Test plan
  
  - `cargo check -p codex-core --lib`
  - `just test -p codex-core 'shell_snapshot::tests'`
  - `just test -p codex-core
  shell_command_snapshot_still_intercepts_apply_patch`
  - `just test -p codex-core
  shell_snapshot_deleted_after_shutdown_with_skills`

  pakrym-oai · 2026-06-15 08:18:13 -07:00
  1aa3e432cc
• Make MCP server contributions thread-scoped (#27670)

  ## Why
  
  `selectedCapabilityRoots` belongs to one thread, but MCP contributors
  previously received only the global Codex config. That left no clean way
  for a selected executor capability to contribute MCP servers to its own
  thread.
  
  ## What this PR does
  
  - Gives MCP contributors a small context containing the config and, for
  a running thread, its frozen host-seeded inputs.
  - Uses the same thread inputs during startup, status queries, refreshes,
  and skill dependency checks.
  - Keeps threadless MCP operations and the existing hosted Apps behavior
  unchanged.
  - Adds coverage showing that two threads resolve independent
  registrations and that later lifecycle mutations do not change the
  frozen MCP inputs.
  
  This PR does not discover plugin manifests, add MCP servers, or launch
  anything new. It only establishes the thread-scoped registration
  boundary.
  
  ## Follow-ups
  
  - Resolve selected executor plugin roots through their owning
  environment filesystem.
  - Convert their stdio MCP declarations into environment-bound
  registrations and add an executor MCP end-to-end test.
  
  ## Verification
  
  - `just fmt`
  - `cargo check --tests -p codex-protocol -p codex-extension-api -p
  codex-mcp-extension -p codex-core -p codex-app-server`
  
  Tests and Clippy were not run.

  jif · 2026-06-12 11:20:34 +02:00
  693082f3c4
• skills: make backend plugin skills invocable without an executor (#27387)

  ## Why
  
  #27198 made the extension-owned `codex_apps` MCP connection the hosted
  plugin runtime, but its `mcp/skill` resources still bypassed the skills
  extension. App-server could list and read those resources through
  generic MCP APIs, but a thread with no selected environment did not
  expose them in the model's skills catalog or load their `SKILL.md`
  through `$skill`.
  
  Hosted skills should stay remote while using the same typed catalog,
  source authority, deduplication, bounded contextual catalog, and
  selected-skill prompt injection as host and executor skills. They should
  not be downloaded or exposed as ambient filesystem paths.
  
  ## What changed
  
  - Add a session-scoped `McpResourceClient` over the replaceable MCP
  connection manager so resource list/read calls follow startup and
  refresh replacements.
  - Add a `BackendSkillProvider` that pages `codex_apps` resources,
  accepts bounded and validated `mcp/skill` entries, and reads a selected
  skill's `SKILL.md` through the same MCP connection.
  - Register the remote provider in app-server and include it in the
  skills catalog even when a thread has no selected capability roots or
  executor.
  - Contribute hosted skill metadata through the bounded
  `AvailableSkillsInstructions` developer-context path, exclude remote
  entries from per-turn catalog injection, and classify `<skills>`
  messages as contextual developer content so rollback can trim and
  rebuild them correctly.
  
  ## Testing
  
  - Extend the app-server MCP resource integration test with
  `environments: []` to exercise two-page discovery, filter a
  non-`mcp/skill` resource, verify the escaped developer catalog entry and
  user-role `<skill>` fragment containing the fetched `SKILL.md`, and
  preserve generic MCP resource reads.
  - Add core event-mapping coverage that classifies `<skills>` developer
  messages as contextual history.

  jif · 2026-06-11 11:28:16 +02:00
  a287c5dffd
• [codex] Add new context window tool (#27488)

  ## Why
  
  The token budget feature tells the model how much room remains in the
  current context window. When the model decides the current window is no
  longer useful, it needs a way to ask Codex to start over with a fresh
  context window without spending tokens on a compaction summary.
  
  This PR adds that model-requestable escape hatch on top of #27438.
  
  ## What changed
  
  - Added a direct-model-only `new_context` tool behind
  `Feature::TokenBudget`.
  - Stores the tool request on `AutoCompactWindow` and consumes it after
  sampling so the next follow-up request in the same turn starts in the
  new window.
  - Starts the new window as a no-summary compaction checkpoint that
  contains only fresh initial context, not preserved conversation history.
  - Keeps the new window aligned with token-budget startup context,
  including the `Current context window Z` message.
  - Added integration coverage and a snapshot showing the same-turn
  `new_context` flow into a fresh full-context follow-up request.
  
  ## Validation
  
  - `just test -p codex-core token_budget`

  pakrym-oai · 2026-06-11 03:39:07 +00:00
  87ab01834a
• [codex] Store compact window id in rollout (#27264)

  ## Why
  
  Compaction window identity is part of session history, not model-client
  transport state. Persisting it with the compacted rollout item lets
  resumed threads continue from the reconstructed window without keeping
  mutable window state on `ModelClient`.
  
  ## What changed
  
  - Added `window_id` to `CompactedItem` and stamp it when
  `replace_compacted_history` installs compacted history.
  - Moved auto-compact window id ownership into `AutoCompactWindow` /
  `SessionState`; `ModelClient` now receives the request window id from
  callers instead of storing it.
  - Returned `window_id` from rollout reconstruction for resume.
  Reconstruction uses the newest surviving compacted item's stored
  `window_id` when present, and falls back to the legacy compacted-item
  count when it is absent.
  - Kept fork startup at the fresh default window id and updated direct
  model-client tests to pass explicit test window ids.
  
  ## Validation
  
  - `cargo check -p codex-core --tests`

  pakrym-oai · 2026-06-10 08:47:16 -07:00
  30ddb3325e
• Use latest-wins MCP manager replacement (#27259)

  ## Summary
  
  We originally addressed startup prewarming holding the read side of
  `RwLock<McpConnectionManager>` by snapshotting tool-list state. Review
  feedback identified the broader ownership problem: the outer
  synchronization should only publish or retrieve the current manager,
  while MCP operations rely on the manager's internal synchronization. A
  follow-up preserved operation retirement with a separate gate, but
  further review questioned whether that synchronization was actually
  required and whether we could support latest-wins replacement instead.
  
  This PR now stores the current MCP manager in `ArcSwap`. Each operation
  uses `load_full()` to obtain an owned `Arc<McpConnectionManager>`, then
  performs MCP I/O without retaining the publication mechanism. Refresh
  cancels obsolete startup work, constructs a replacement, and atomically
  publishes it. New operations see the latest manager, while operations
  that already loaded the previous manager retain a valid handle. Refresh
  happens at a turn boundary, so there should be no active user tool calls
  to drain.
  
  Git history supports dropping the outer `RwLock`. It was introduced in
  `03ffe4d595` on November 17, 2025 for non-blocking MCP startup: the
  session published an empty manager, startup initialized that same object
  while holding the write lock, and readers waited for initialization.
  `7cd2e84026` on February 19, 2026 removed that two-phase initialization
  in favor of constructing a fresh manager and swapping it in, explicitly
  noting that `Option` or `OnceCell` could replace the placeholder design.
  Hot reload later reused the existing lock to publish a replacement, but
  I found no indication that the lock was introduced to guarantee
  in-flight tool calls finish before refresh or shutdown.
  
  Terminal shutdown remains separate from refresh: it aborts startup
  prewarming and active tasks before shutting down the current manager, so
  tool calls may be interrupted and no model WebSocket work continues
  after shutdown. Focused regression coverage exercises pending tool-list
  cancellation, deferred refresh, and startup-prewarm shutdown.

  Charlie Marsh · 2026-06-10 08:33:21 -07:00
  41b4fabbb4
• [codex] Make MCP connection startup fallible (#27261)

  ## Why
  
  Required MCP server startup was enforced in `Session::new` after
  `McpConnectionManager` had already created the clients. That split let
  other manager construction paths bypass the same requirement and exposed
  manager internals solely so the session could validate them. Keeping
  required-server readiness in the constructor gives every caller one
  consistent startup contract.
  
  ## What changed
  
  - make `McpConnectionManager::new` return `anyhow::Result<Self>` and
  fail when an enabled, required server cannot initialize
  - pass the startup cancellation token into the constructor so
  required-server waits remain cancellable
  - propagate constructor failures through resource reads, connector
  discovery, and MCP status collection
  - preserve the active manager and cancellation token when a refreshed
  replacement fails
  - keep required-startup failure collection private and cover the
  constructor error contract directly
  
  ## Validation
  
  - updated the focused connection-manager test to assert the complete
  required-server startup error
  - local tests not run; relying on CI

  Ahmed Ibrahim · 2026-06-10 00:17:58 -07:00
  a7b6baecc6
• feat: count V2 concurrency by active execution (#26969)

  ## Why
  
  Multi-Agent V2 concurrency should count active non-root turns, not
  resident or durable agent threads. The limit is intentionally best
  effort: admission checks are synchronous, but concurrent successful
  checks may overshoot slightly.
  
  ## What changed
  
  - Keep one root-derived execution limit on the shared `AgentControl`.
  - Count active V2 subagent turns with an RAII guard owned by
  `RunningTask`.
  - Check capacity before spawning or starting an idle agent, including
  direct app-server `turn/start` submissions.
  - Preserve queued delivery for agents that are already running.
  - Exempt automatic idle continuations so `/goal` work is not dropped
  when capacity is temporarily full.
  - Keep root and V1 turns outside this limiter.
  
  ## Test coverage
  
  - `execution_guards_count_active_v2_subagent_turns`
  - `execution_guards_ignore_root_and_v1_turns`
  - `v2_nested_spawn_checks_shared_active_execution_capacity`

  jif · 2026-06-08 14:21:28 +02:00
  743f5aad38
• Key request-permission grants by environment (#25850)

  ## Stack
  
  1. This PR (#25850) - Key request-permission grants by environment:
  stores and applies sticky permission grants per environment id.
  2. #25858 - Add `environmentId` to `request_permissions`: lets the model
  target a selected environment and resolves relative permission paths
  against it.
  3. #25862 - Propagate permission approval environment id: carries the
  selected environment id through approval events, app-server requests,
  TUI prompts, and delegate forwarding.
  4. #25867 - Add remote request permissions integration coverage:
  verifies the selected remote environment across request, approval, grant
  reuse, and exec.
  
  #25858, #25862, and #25867 are stacked on this PR and should be reviewed
  after it.
  
  ## Why
  
  Multi-environment CCA turns can attach both local and remote executors,
  but request-permission grants were still effectively cwd-only. Pending
  permission requests tracked a cwd, while stored turn/session grants had
  no environment identity, so sticky grants could be reused through the
  wrong executor context.
  
  This makes the first permission-grant step environment-aware without
  changing the external `request_permissions` payload shape: omitted
  environment targeting remains bound to the primary turn environment.
  
  ## What Changed
  
  - Store turn- and session-scoped request-permission grants by
  `environment_id`.
  - Keep the selected `TurnEnvironmentSelection` with pending
  `request_permissions` calls so approval responses normalize and record
  grants against the same environment.
  - Resolve relative `request_permissions` file paths against the primary
  turn environment cwd instead of deprecated `turn.cwd`.
  - Apply sticky grants in `shell`, `exec_command`, and `apply_patch` by
  selected environment id while still using the actual tool cwd for
  cwd-relative permission materialization.
  - Update Guardian and request-permissions coverage for the
  environment-keyed grant behavior.
  
  ## Testing
  
  Not run locally. Added or updated focused coverage for:
  
  - `request_permission_grants_are_environment_keyed`
  -
  `request_permissions_tool_resolves_relative_paths_against_primary_environment`
  - related Guardian/request-permissions sticky grant tests

  jif · 2026-06-02 20:16:57 +02:00
  503ec190a8
• feat: show enterprise monthly credit limits in status (#24812)

  ## Summary
  
  Enterprise users can have an effective monthly credit limit, but Codex
  `/status` currently drops that metadata from the account-usage response.
  
  This change adds the optional `spend_control.individual_limit`
  projection to the existing rate-limit snapshot flow. The backend client
  reads the monthly limit, app-server exposes it as `individualLimit`, and
  the TUI renders a `Monthly credit limit` row through the existing
  progress-bar renderer.
  
  When the backend does not return an effective monthly limit, existing
  rate-limit behavior is unchanged.
  
  ## Existing backend state
  
  The account-usage backend already returns the effective monthly limit
  and current usage together:
  
  ```json
  {
    "spend_control": {
      "reached": false,
      "individual_limit": {
        "limit": "25000",
        "used": "8000",
        "remaining": "17000",
        "used_percent": 32,
        "remaining_percent": 68,
        "reset_after_seconds": 86400,
        "reset_at": 1778137680
      }
    }
  }
  ```
  
  Before this change, Codex projected rolling `primary` and `secondary`
  windows plus `credits`. It ignored `spend_control.individual_limit`, so
  app-server clients and `/status` could not render the monthly cap.
  
  The updated flow is:
  
  ```text
  account usage backend
    -> backend-client reads spend_control.individual_limit
    -> existing rate-limit snapshot carries optional individual_limit
    -> app-server exposes optional individualLimit
    -> TUI renders Monthly credit limit
  ```
  
  ## App-server contract
  
  `account/rateLimits/read` and sparse `account/rateLimits/updated`
  notifications now include an additive nullable
  `rateLimits.individualLimit` field:
  
  ```json
  {
    "individualLimit": {
      "limit": "25000",
      "used": "8000",
      "remainingPercent": 68,
      "resetsAt": 1778137680
    }
  }
  ```
  
  In an `account/rateLimits/read` response, `null` means no monthly limit
  is available. `account/rateLimits/updated` remains a sparse rolling
  notification: clients merge available values into their most recent
  `account/rateLimits/read` snapshot or refetch. Nullable account metadata
  in a rolling notification does not clear a previously observed value.
  
  ## Design decisions
  
  - Extend the existing rate-limit snapshot instead of introducing a
  separate request or wire-level update protocol.
  - Keep the Codex projection narrow: `/status` needs the effective limit,
  current usage, remaining percentage, and reset timestamp.
  - Render the monthly row through the existing progress-bar renderer,
  with one optional detail line for `8,000 of 25,000 credits used`.
  - Keep the backend response optional so existing accounts and older
  usage states preserve their current behavior.
  - Preserve cached monthly metadata when sparse rolling notifications
  omit it. Live account-usage reads remain authoritative and can clear a
  removed limit.
  
  ## Visual evidence
  
  ```text
   Monthly credit limit:   [██████████████░░░░░░] 68% left (resets 07:08 on 7 May)
                           8,000 of 25,000 credits used
  ```
  
  Snapshot:
  `codex-rs/tui/src/status/snapshots/codex_tui__status__tests__status_snapshot_includes_enterprise_monthly_credit_limit.snap`
  
  ## Testing
  
  Tests: generated app-server schema verification, protocol tests,
  backend-client tests, app-server integration coverage, TUI snapshot
  coverage, formatting, and workspace lint cleanup.

  efrazer-oai · 2026-06-01 21:25:42 -07:00
  c8e5db16c9
• Add experimental turn additional context (#24154)

  ## Summary
  
  Adds experimental `additionalContext` support to `turn/start` and
  `turn/steer` so clients can provide ephemeral external context, such as
  browser or automation state, without turning that plumbing into a
  visible user prompt or triggering user-prompt lifecycle behavior.
  
  ## API Shape
  
  The parameter shape is:
  
  ```ts
  additionalContext?: Record<string, {
    value: string
    kind: "untrusted" | "application"
  }> | null
  ```
  
  Example:
  
  ```json
  {
    "additionalContext": {
      "browser_info": {
        "value": "Active tab is CI failures.",
        "kind": "untrusted"
      },
      "automation_info": {
        "value": "CI rerun is in progress.",
        "kind": "application"
      }
    }
  }
  ```
  
  The keys are opaque and caller-defined.
  
  ## Context Injection
  
  When provided, accepted entries are inserted into model context as
  hidden contextual message items, not as visible thread user-message
  items.
  
  `kind: "untrusted"` entries are inserted with role `user`:
  
  ```text
  <external_${key}>${value}</external_${key}>
  ```
  
  `kind: "application"` entries are inserted with role `developer`:
  
  ```text
  <${key}>${value}</${key}>
  ```
  
  Values are not escaped. Each value is truncated to 1k approximate tokens
  before wrapping.
  
  For `turn/start`, accepted additional context is inserted before normal
  user input. For `turn/steer`, additional context is merged only when the
  steer includes non-empty user input; context-only steers still reject as
  empty input.
  
  ## Dedupe Strategy
  
  `AdditionalContextStore` lives on session state and stores the latest
  complete additional-context map.
  
  Each `turn/start` or non-empty `turn/steer` treats its
  `additionalContext` as the current complete set of values. Entries are
  injected only when the key is new or the exact entry for that key
  changed, including `value` or `kind`. After merging, the store is
  replaced with the provided map, so omitted keys are removed from the
  retained set and can be injected again later if reintroduced.
  
  Omitting `additionalContext`, passing `null`, or passing an empty object
  resets the store to empty and injects nothing.
  
  ## What Changed
  
  - Threads experimental v2 `additionalContext` through app-server into
  core turn start and steer handling.
  - Adds separate contextual fragment types for untrusted user-role
  context and application developer-role context.
  - Uses pending response input items so additional context can be
  combined with normal user input without treating it as prompt text.
  - Adds integration coverage for start/steer flow, role routing,
  dedupe/reset behavior, deletion/re-add behavior, hook-blocked input
  behavior, empty context-only steer rejection, external-fragment marker
  matching, and truncation.

  pakrym-oai · 2026-05-26 13:02:34 -07:00
  768848ab6f
• [codex] Make active turn task singular (#24105)

  ## Why
  
  `ActiveTurn` already runs at most one task: starting a task requires
  that no task is present, and replacement aborts existing work first.
  Representing that state as an `IndexMap` leaves a multi-task shape for a
  single-task invariant and makes each lifecycle lookup operate like a
  collection lookup.
  
  The slot remains optional because goal continuation uses an empty active
  turn as a reservation while deciding whether to start continuation work.
  
  ## What changed
  
  - Replace `ActiveTurn.tasks` with `task: Option<RunningTask>`.
  - Update task abort/completion, session lookup and steering, input-queue
  matching, goal reservation, and network-approval lookup to operate on
  the singular slot.
  - Mutate the singular task slot directly instead of retaining
  collection-era add/remove/take helpers.
  - Record token usage on the completing active task span without a
  regular-task-only opt-in flag.
  
  ## Validation
  
  - `cargo test -p codex-core --lib session::tests::steer_input`
  - `cargo test -p codex-core --lib
  session::tests::abort_empty_active_turn_preserves_pending_input`
  - `cargo test -p codex-core --lib
  session::tests::queued_response_items_for_next_turn_move_into_next_active_turn`
  - `cargo test -p codex-core --lib
  session::tests::active_goal_continuation_runs_again_after_no_tool_turn`
  - `cargo test -p codex-core --lib
  session::tests::abort_regular_task_emits_turn_aborted_only`
  - `cargo test -p codex-core --lib session::input_queue::tests`

  pakrym-oai · 2026-05-26 08:20:58 -07:00
  b637fd26aa
• core: refresh active permission profiles at runtime (#22931)

  ## Why
  
  Once a named permission profile is selected, runtime state has to keep
  that profile identity intact instead of collapsing back to anonymous
  effective permissions. The session refresh path also needs to rebuild
  profile-derived network proxy state so active profile switches take
  effect consistently.
  
  ## What changed
  
  - Preserve the active permission profile through session updates.
  - Rebuild profile-derived runtime/network configuration when the active
  profile changes.
  - Keep the runtime path aligned with the current session configuration
  APIs.
  - Tighten the affected tests, including the Windows delete-pending
  memory-file case that was intermittently tripping CI.
  
  ## Stack
  
  1. **This PR**: runtime/session/network propagation for active
  permission profiles.
  2. [#23708](https://github.com/openai/codex/pull/23708): TUI selection
  plumbing and guardrail flow.
  3. [#21559](https://github.com/openai/codex/pull/21559): profile-aware
  `/permissions` menu and custom profile display.
  
  <img width="1296" height="906" alt="image"
  src="https://github.com/user-attachments/assets/077fa3a7-80cb-4925-80b1-d2395018d90a"
  />

  viyatb-oai · 2026-05-20 21:55:21 +00:00
  40ad7be2b5
• Support compact SessionStart hooks (#21272)

  # Why
  
  Compaction replaces the live conversation history, so hooks that use
  `SessionStart` to re-inject durable model context need a way to run
  again after that rewrite.
  
  Related - #19905 adds dedicated compact lifecycle hooks
  
  # What
  
  - add `compact` as a supported `SessionStart` source and matcher value
  - change pending `SessionStart` state from a single slot to a small FIFO
  queue so `resume` / `startup` / `clear` can be preserved alongside a
  later `compact`
  - drain all queued `SessionStart` sources before the next model request,
  preserving their original order
  
  # Testing
  
  The new integration coverage verifies both the basic `compact` matcher
  path and the stacked `resume` -> `compact` case where both hooks
  contribute `additionalContext` to the next model turn.

  Abhinav · 2026-05-20 20:46:19 +00:00
  af49d38373
• Add body_after_prefix auto-compact token limit scope (#22870)

  ## Why
  
  `model_auto_compact_token_limit` has only been able to budget the full
  active context. That makes it hard to set a small "growth since
  compaction" budget for sessions that preserve a large carried window
  prefix: the preserved prefix can consume the whole budget and force
  immediate repeated compaction.
  
  This PR adds an opt-in `body_after_prefix` scope so callers can apply
  `model_auto_compact_token_limit` to sampled output and later growth
  after the current carried prefix, while still forcing compaction before
  the full model context window is exhausted.
  
  ## What changed
  
  - Adds `AutoCompactTokenLimitScope` with the existing `total` behavior
  as the default and a new `body_after_prefix` mode:
  [`config_types.rs`](https://github.com/openai/codex/blob/973806b1cb35792555bead994cb3ed94656eb171/codex-rs/protocol/src/config_types.rs#L24-L37).
  - Threads `model_auto_compact_token_limit_scope` through config loading,
  `Config`, `core-api`, and app-server v2 schema/TypeScript generation.
  - Records the first observed input-token count for a `body_after_prefix`
  compaction window and uses it as the baseline when deciding whether the
  scoped auto-compaction budget is exhausted:
  [`turn.rs`](https://github.com/openai/codex/blob/973806b1cb35792555bead994cb3ed94656eb171/codex-rs/core/src/session/turn.rs#L743-L781).
  - Keeps a hard context-window cap in `body_after_prefix`, so scoped
  budgeting cannot let the active context overrun the usable window.
  
  ## Verification
  
  Added compact-suite coverage for the two key behaviors:
  `body_after_prefix` does not re-compact just because the carried prefix
  is larger than the scoped budget, and it still compacts when the total
  active context reaches the configured context window:
  [`compact.rs`](https://github.com/openai/codex/blob/973806b1cb35792555bead994cb3ed94656eb171/codex-rs/core/tests/suite/compact.rs#L3003-L3128).

  jif-oai · 2026-05-19 10:19:46 +00:00
  80fdd4688f
• cleanup: Remove skill env var dependency prompting (#22721)

  Deletes the skill env var dependency prompt feature and its runtime
  path. env_var entries in skill dependency metadata are now silently
  ignored during skill loading.

  xl-openai · 2026-05-19 01:24:19 +00:00
  6b54ced108
• [codex] Move pending input into input queue (#22728)

  ## Why
  
  Pending model input was split across `Session`, `TurnState`, and the
  agent mailbox. That made it easy for new paths to manage queued user
  input or mailbox delivery outside the intended ownership boundary.
  
  This PR consolidates the model-facing input lifecycle behind the session
  input queue so turn-local pending input, next-turn queued items, and
  mailbox delivery coordination are owned in one place.
  
  ## What Changed
  
  - Added `session/input_queue.rs` to own pending input queues and mailbox
  delivery coordination.
  - Removed the standalone `agent/mailbox.rs` channel wrapper and store
  mailbox items directly in the input queue.
  - Moved pending-input mutations off `TurnState`; `TurnState` now exposes
  the queue-owned storage directly for now.
  - Routed abort cleanup, mailbox delivery phase changes, next-turn queued
  items, and active-turn pending input through `InputQueue`.
  - Boxed stack-heavy agent resume/fork startup futures that the refactor
  pushed over the default test stack.
  - Updated session, task, goal, stream-event, and multi-agent call sites
  and tests to use the new queue ownership.
  
  ## Verification
  
  - `cargo test -p codex-core --lib agent::control::tests`
  - `cargo test -p codex-core --lib
  agent::control::tests::resume_closed_child_reopens_open_descendants --
  --exact`
  - `cargo test -p codex-core --lib
  agent::control::tests::spawn_agent_fork_last_n_turns_keeps_only_recent_turns
  -- --exact`
  - `cargo test -p codex-core --lib
  agent::control::tests::resume_thread_subagent_restores_stored_nickname_and_role
  -- --exact`
  - `cargo test -p codex-core` was also run; it completed with 1814
  passed, 4 ignored, and one timeout in
  `agent::control::tests::resume_thread_subagent_restores_stored_nickname_and_role`,
  which passed when rerun in isolation.

  pakrym-oai · 2026-05-18 15:43:01 -07:00
  afa0101ae2
• Fix turn extension data task plumbing (#22646)

  ## Summary
  - carry the per-turn extension data through RunningTask so abort
  handling can rebuild SessionTaskContext
  - update stale test ExtensionData::new() callsites to pass the turn id
  
  ## Testing
  - Not run after PR branch creation; CI will cover.

  jif-oai · 2026-05-14 16:00:06 +02:00
  12bfb57139
• feat: move extension scope ids into ExtensionData (#22490)

  ## Summary
  - add a scoped level_id to ExtensionData and expose it through
  level_id()
  - remove thread_id/turn_id parameters from extension contributor inputs
  where the scoped ExtensionData already carries that identity
  - move turn-scoped extension data onto TurnContext so token usage and
  lifecycle contributors can share the same turn store
  
  ## Testing
  - cargo check -p codex-extension-api -p codex-core --tests
  - cargo test -p codex-extension-api
  - cargo test -p codex-guardian
  - cargo test -p codex-core --lib
  record_token_usage_info_notifies_extension_contributors
  - cargo test -p codex-core --lib
  submission_loop_channel_close_emits_thread_stop_lifecycle
  - cargo test -p codex-core --lib
  submission_loop_channel_close_aborts_active_turn_before_thread_stop_lifecycle
  - just fix -p codex-extension-api
  - just fix -p codex-guardian
  - just fix -p codex-core
  - just fmt
  
  ## Note
  - Attempted cargo test -p codex-core; it aborted in
  agent::control::tests::spawn_agent_fork_last_n_turns_keeps_only_recent_turns
  with the existing stack overflow before the full suite completed.

  jif-oai · 2026-05-13 16:13:16 +02:00
  1dcc89f1d4
• feat: add turn lifecycle contributors (#22480)

  ## Why
  
  Extensions can already contribute prompt, tool, turn-item, and
  thread-lifecycle behavior, but there was no explicit host-owned hook for
  per-turn setup and cleanup. That makes extension-private turn state
  awkward: an extension either has to stash it outside the turn lifecycle
  or depend on core runtime objects.
  
  This adds a small turn lifecycle boundary. Extensions receive stable
  identifiers plus the existing session, thread, and turn `ExtensionData`
  stores, while core keeps owning task scheduling, cancellation, and turn
  teardown.
  
  ## What Changed
  
  - Added `TurnLifecycleContributor` with `on_turn_start`, `on_turn_stop`,
  and `on_turn_abort` callbacks in `codex-rs/ext/extension-api`.
  - Added typed `TurnStartInput`, `TurnStopInput`, and `TurnAbortInput`
  payloads that expose `thread_id`, `turn_id`, `session_store`,
  `thread_store`, and `turn_store`.
  - Registered and re-exported turn lifecycle contributors through
  `ExtensionRegistry` and `ExtensionRegistryBuilder`.
  - Wired `Session` to emit turn start, stop, and abort callbacks from the
  existing turn/task lifecycle paths.
  - Carried the turn-scoped `ExtensionData` through `RunningTask` and
  `RemovedTask` so stop/abort callbacks receive the same turn store
  created at turn start.
  
  ## Verification
  
  - Not run locally.

  jif-oai · 2026-05-13 13:47:27 +02:00
  27e67a8c2a
• extension: wire extension registries into sessions (#21737)

  ## Why
  
  [#21736](https://github.com/openai/codex/pull/21736) introduces the
  typed extension API, but the runtime does not yet carry a registry
  through thread/session startup or give contributors host-owned stores to
  read from. This PR wires that host-side path so later feature migrations
  can move product-specific behavior behind typed contributions without
  adding another bespoke seam directly to `codex-core`.
  
  ## What changed
  
  - Thread `ExtensionRegistry<Config>` through `ThreadManager`,
  `CodexSpawnArgs`, `Session`, and sub-agent spawn paths.
  - Wire `ThreadStartContributor` and `ContextContributor`
  - Expose the small supporting surface needed by non-core callers that
  construct threads directly, including `empty_extension_registry()`
  through `codex-core-api`.
  
  This PR lands the host plumbing only: the app-server registry is still
  empty, and concrete feature migrations are intended to follow
  separately.

  jif-oai · 2026-05-11 11:38:18 +02:00
  436c0df658
• Reapply "Move skills watcher to app-server" (#21652)

  ## Why
  
  PR #21460 reverted the earlier move of skills change watching from
  `codex-core` into app-server. This reapplies that boundary change so
  app-server owns client-facing `skills/changed` notifications and core no
  longer carries the watcher.
  
  ## What
  
  - Restore the app-server `SkillsWatcher` and register it from thread
  listener setup.
  - Remove the core-owned skills watcher and its core live-reload
  integration surface.
  - Restore app-server coverage for `skills/changed` notifications after a
  watched skill file changes.
  
  ## Validation
  
  - `cargo test -p codex-app-server --test all
  suite::v2::skills_list::skills_changed_notification_is_emitted_after_skill_change
  -- --exact --nocapture`
  - `cargo test -p codex-core --lib --no-run`

  pakrym-oai · 2026-05-08 17:41:15 -07:00
  408e6218ab
• [codex] request desktop attestation from app (#20619)

  ## Summary
  
  TL;DR: teaches `codex-rs` / app-server to request a desktop-provided
  attestation token and attach it as `x-oai-attestation` on the scoped
  ChatGPT Codex request paths.
  
  ![DeviceCheck attestation
  interface](https://raw.githubusercontent.com/openai/codex/dev/jm/devicecheck-diagram-assets/pr-assets/devicecheck-attestation-interface.png)
  
  ## Details
  
  This PR teaches the Codex app-server runtime how to request and attach
  an attestation token. It does not generate DeviceCheck tokens directly;
  instead, it relies on the connected desktop app to advertise that it can
  generate attestation and then asks that app for a fresh header value
  when needed.
  
  The flow is:
  
  1. The Codex desktop app connects to app-server.
  2. During `initialize`, the app can advertise that it supports
  `requestAttestation`.
  3. Before app-server calls selected ChatGPT Codex endpoints, it sends
  the internal server request `attestation/generate` to the app.
  4. app-server receives a pre-encoded header value back.
  5. app-server forwards that value as `x-oai-attestation` on the scoped
  outbound requests.
  
  The code in this repo is mostly protocol and runtime plumbing: it adds
  the app-server request/response shape, introduces an attestation
  provider in core, wires that provider into Responses / compaction /
  realtime setup paths, and covers the intended scoping with tests. The
  signed macOS DeviceCheck generation remains owned by the desktop app PR.
  
  ## Related PR
  
  - Codex desktop app implementation:
  https://github.com/openai/openai/pull/878649
  
  ## Validation
  
  <details>
  <summary>Tests run</summary>
  
  ```sh
  cargo test -p codex-app-server-protocol
  cargo test -p codex-core attestation --lib
  cargo test -p codex-app-server --lib attestation
  ```
  
  Also ran:
  
  ```sh
  just fix -p codex-core
  just fix -p codex-app-server
  just fix -p codex-app-server-protocol
  just fmt
  just write-app-server-schema
  ```
  
  </details>
  
  <details>
  <summary>E2E DeviceCheck validation</summary>
  
  First validated the signed desktop app boundary directly: launched a
  packaged signed `Codex.app`, sent `attestation/generate`, decoded the
  returned `v1.` attestation header, and validated the extracted
  DeviceCheck token with `personal/jm/verify_devicecheck_token.py` using
  bundle ID `com.openai.codex`. Apple returned `status_code: 200` and
  `is_ok: true`.
  
  Then ran the fuller app + app-server flow. The packaged `Codex.app`
  launched a current-branch app-server via `CODEX_CLI_PATH`, and a local
  MITM proxy intercepted outbound `chatgpt.com` traffic. The app-server
  requested `attestation/generate` from the real Electron app process, and
  the intercepted `/backend-api/codex/responses` traffic included
  `x-oai-attestation` on both routes:
  
  ```text
  GET  /backend-api/codex/responses  Upgrade: websocket  x-oai-attestation: present
  POST /backend-api/codex/responses  Upgrade: none       x-oai-attestation: present
  ```
  
  The captured header decoded to a DeviceCheck token that also validated
  with Apple for `com.openai.codex` (`status_code: 200`, `is_ok: true`,
  team `2DC432GLL2`).
  
  </details>
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Jiaming Zhang · 2026-05-08 12:36:02 -07:00
  5f4d0ec343
• Revert "Move skills watcher to app-server" (#21460)

  Reverts openai/codex#21287

  pakrym-oai · 2026-05-07 02:24:20 +00:00
  103dc2b6ae
• Move skills watcher to app-server (#21287)

  ## Why
  
  Skills update notifications are app-server API behavior, but the watcher
  lived in `codex-core` and surfaced through
  `EventMsg::SkillsUpdateAvailable`. Moving the watcher out keeps core
  focused on thread execution and lets app-server own both cache
  invalidation and the `skills/changed` notification.
  
  ## What changed
  
  - Added an app-server-owned skills watcher that watches local skill
  roots, clears the shared skills cache, and emits `skills/changed`
  directly.
  - Registers skill watches from the common app-server thread listener
  attach path, including direct starts, resumes, and app-server-observed
  child or forked threads.
  - Stores the `WatchRegistration` on `ThreadState`, so listener
  replacement, thread teardown, idle unload, and app-server shutdown
  deregister by dropping the RAII guard.
  - Removed `EventMsg::SkillsUpdateAvailable`, the core watcher, and the
  old core live-reload test.
  - Extended the app-server skills change test to verify a cached skills
  list is refreshed after a filesystem change without forcing reload.
  
  ## Validation
  
  - `cargo check -p codex-core -p codex-app-server -p codex-mcp-server -p
  codex-rollout -p codex-rollout-trace`
  - `cargo test -p codex-app-server
  skills_changed_notification_is_emitted_after_skill_change`

  pakrym-oai · 2026-05-06 15:38:11 -07:00
  d5eea229cc
• Move plugin out of core. (#20348)
  xl-openai · 2026-04-30 14:26:14 -07:00
  7b3de63041
• Add persisted hook enablement state (#19840)

  ## Why
  
  After `hooks/list` exposes the hook inventory, clients need a way to
  persist user hook preferences, make those changes effective in
  already-open sessions, and distinguish user-controllable hooks from
  managed requirements without adding another bespoke app-server write
  API.
  
  ## What
  
  - Extends `hooks/list` entries with effective `enabled` state.
  - Persists user-level hook state under `hooks.state.<hook-id>` so the
  model can grow beyond a single boolean over time.
  - Uses the existing `config/batchWrite` path for hook state updates
  instead of introducing a dedicated hook write RPC.
  - Refreshes live session hook engines after config writes so
  already-open threads observe updated enablement without a restart.
  
  ## Stack
  
  1. openai/codex#19705
  2. openai/codex#19778
  3. This PR - openai/codex#19840
  4. openai/codex#19882
  
  ## Reviewer Notes
  
  The generated schema files account for much of the raw diff. The core
  behavior is in:
  
  - `hooks/src/config_rules.rs`, which resolves per-hook user state from
  the config layer stack.
  - `hooks/src/engine/discovery.rs`, which projects effective enablement
  into `hooks/list` from source-derived managedness.
  - `config/src/hook_config.rs`, which defines the new `hooks.state`
  representation.
  - `core/src/session/mod.rs`, which rebuilds live hook state after user
  config reloads.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Abhinav · 2026-04-30 04:46:32 +00:00
  8f3c06cc97
• [codex] Add token usage to turn tracing spans (#19432)

  ## Why
  
  Slow Codex turns are easier to debug when token usage is visible in the
  trace itself, without joining against separate analytics. This adds
  token usage to existing turn-handling spans for regular user turns only.
  
  [Example
  turn](https://openai.datadoghq.com/apm/trace/9d353efa2cb5de1f4c5b93dc33c3df04?colorBy=service&graphType=flamegraph&shouldShowLegend=true&sort=time&spanID=3555541504891512675&spanViewType=metadata&traceQuery=)
  <img width="1447" height="967" alt="Screenshot 2026-04-24 at 3 03 07 PM"
  src="https://github.com/user-attachments/assets/ab7bb187-e7fc-41f0-a366-6c44610b2b2c"
  />
  
  ## What Changed
  
  Added response-level token fields on completed handle_responses spans:
  
  gen_ai.usage.input_tokens
  gen_ai.usage.cache_read.input_tokens
  gen_ai.usage.output_tokens
  codex.usage.reasoning_output_tokens
  codex.usage.total_tokens
  Added aggregate token fields on regular turn spans:
  
  codex.turn.token_usage.*
  Added an explicit regular-turn opt-in via
  SessionTask::records_turn_token_usage_on_span() so this is not coupled
  to span-name strings.
  
  ## Testing
  
  - `cargo test -p codex-otel`
  - `cargo test -p codex-core
  turn_and_completed_response_spans_record_token_usage`
  - `just fmt`
  - `just fix -p codex-core`
  - `just fix -p codex-otel`
  - Manual local Electron/app-server smoke test: regular user turn emits
  the new span fields
  
  Known status: `cargo test -p codex-core` was attempted and failed in
  unrelated existing areas: config approvals, request-permissions,
  git-info ordering, and subagent metadata persistence.

  charley-openai · 2026-04-28 11:41:32 -07:00
  de2ccf9473
• Add goal core runtime (4 / 5) (#18076)

  Adds the core runtime behavior for active goals on top of the model
  tools from PR 3.
  
  ## Why
  
  A long-running goal should be a core runtime concern, not something
  every client has to implement. Core owns the turn lifecycle, tool
  completion boundaries, interruptions, resume behavior, and token usage,
  so it is the right place to account progress, enforce budgets, and
  decide when to continue work.
  
  ## What changed
  
  - Centralized goal lifecycle side effects behind
  `Session::goal_runtime_apply(GoalRuntimeEvent::...)`.
  - Starts goal continuation turns only when the session is idle; pending
  user input and mailbox work take priority.
  - Accounts token and wall-clock usage at turn, tool, mutation,
  interrupt, and resume boundaries; `get_thread_goal` remains read-only.
  - Preserves sub-second wall-clock remainder across accounting boundaries
  so long-running goals do not drift downward over time.
  - Treats token budget exhaustion as a soft stop by marking the goal
  `budget_limited` and injecting wrap-up steering instead of aborting the
  active turn.
  - Suppresses budget steering when `update_goal` marks a goal complete.
  - Pauses active goals on interrupt and auto-reactivates paused goals
  when a thread resumes outside plan mode.
  - Suppresses repeated automatic continuation when a continuation turn
  makes no tool calls.
  - Added continuation and budget-limit prompt templates.
  
  ## Verification
  
  - Added focused core coverage for continuation scheduling, accounting
  boundaries, budget-limit steering, completion accounting, interrupt
  pause behavior, resume auto-activation, and wall-clock remainder
  accounting.

  Eric Traut · 2026-04-24 21:16:00 -07:00
  4167628622
• permissions: make profiles represent enforcement (#19231)

  ## Why
  
  `PermissionProfile` is becoming the canonical permissions abstraction,
  but the old shape only carried optional filesystem and network fields.
  It could describe allowed access, but not who is responsible for
  enforcing it. That made `DangerFullAccess` and `ExternalSandbox` lossy
  when profiles were exported, cached, or round-tripped through app-server
  APIs.
  
  The important model change is that active permissions are now a disjoint
  union over the enforcement mode. Conceptually:
  
  ```rust
  pub enum PermissionProfile {
      Managed {
          file_system: FileSystemSandboxPolicy,
          network: NetworkSandboxPolicy,
      },
      Disabled,
      External {
          network: NetworkSandboxPolicy,
      },
  }
  ```
  
  This distinction matters because `Disabled` means Codex should apply no
  outer sandbox at all, while `External` means filesystem isolation is
  owned by an outside caller. Those are not equivalent to a broad managed
  sandbox. For example, macOS cannot nest Seatbelt inside Seatbelt, so an
  inner sandbox may require the outer Codex layer to use no sandbox rather
  than a permissive one.
  
  ## How Existing Modeling Maps
  
  Legacy `SandboxPolicy` remains a boundary projection, but it now maps
  into the higher-fidelity profile model:
  
  - `ReadOnly` and `WorkspaceWrite` map to `PermissionProfile::Managed`
  with restricted filesystem entries plus the corresponding network
  policy.
  - `DangerFullAccess` maps to `PermissionProfile::Disabled`, preserving
  the “no outer sandbox” intent instead of treating it as a lax managed
  sandbox.
  - `ExternalSandbox { network_access }` maps to
  `PermissionProfile::External { network }`, preserving external
  filesystem enforcement while still carrying the active network policy.
  - Split runtime policies that legacy `SandboxPolicy` cannot faithfully
  express, such as managed unrestricted filesystem plus restricted
  network, stay `Managed` instead of being collapsed into
  `ExternalSandbox`.
  - Per-command/session/turn grants remain partial overlays via
  `AdditionalPermissionProfile`; full `PermissionProfile` is reserved for
  complete active runtime permissions.
  
  ## What Changed
  
  - Change active `PermissionProfile` into a tagged union: `managed`,
  `disabled`, and `external`.
  - Keep partial permission grants separate with
  `AdditionalPermissionProfile` for command/session/turn overlays.
  - Represent managed filesystem permissions as either `restricted`
  entries or `unrestricted`; `glob_scan_max_depth` is non-zero when
  present.
  - Preserve old rollout compatibility by accepting the pre-tagged `{
  network, file_system }` profile shape during deserialization.
  - Preserve fidelity for important edge cases: `DangerFullAccess`
  round-trips as `disabled`, `ExternalSandbox` round-trips as `external`,
  and managed unrestricted filesystem + restricted network stays managed
  instead of being mistaken for external enforcement.
  - Preserve configured deny-read entries and bounded glob scan depth when
  full profiles are projected back into runtime policies, including
  unrestricted replacements that now become `:root = write` plus deny
  entries.
  - Regenerate the experimental app-server v2 JSON/TypeScript schema and
  update the `command/exec` README example for the tagged
  `permissionProfile` shape.
  
  ## Compatibility
  
  Legacy `SandboxPolicy` remains available at config/API boundaries as the
  compatibility projection. Existing rollout lines with the old
  `PermissionProfile` shape continue to load. The app-server
  `permissionProfile` field is experimental, so its v2 wire shape is
  intentionally updated to match the higher-fidelity model.
  
  ## Verification
  
  - `just write-app-server-schema`
  - `cargo check --tests`
  - `cargo test -p codex-protocol permission_profile`
  - `cargo test -p codex-protocol
  preserving_deny_entries_keeps_unrestricted_policy_enforceable`
  - `cargo test -p codex-app-server-protocol
  permission_profile_file_system_permissions`
  - `cargo test -p codex-app-server-protocol serialize_client_response`
  - `cargo test -p codex-core
  session_configured_reports_permission_profile_for_external_sandbox`
  - `just fix`
  - `just fix -p codex-protocol`
  - `just fix -p codex-app-server-protocol`
  - `just fix -p codex-core`
  - `just fix -p codex-app-server`

  Michael Bolin · 2026-04-23 23:02:18 -07:00
  4816b89204
• feat: let model providers own model discovery (#18950)

  ## Why
  
  `codex-models-manager` had grown to own provider-specific concerns:
  constructing OpenAI-compatible `/models` requests, resolving provider
  auth, emitting request telemetry, and deciding how provider catalogs
  should be sourced. That made the manager harder to reuse for providers
  whose model catalog is not fetched from the OpenAI `/models` endpoint,
  such as Amazon Bedrock.
  
  This change moves provider-specific model discovery behind
  provider-owned implementations, so the models manager can focus on
  refresh policy, cache behavior, picker ordering, and model metadata
  merging.
  
  ## What Changed
  
  - Introduced a `ModelsManager` trait with separate `OpenAiModelsManager`
  and `StaticModelsManager` implementations.
  - Added `ModelsEndpointClient` so OpenAI-compatible HTTP fetching lives
  outside `codex-models-manager`.
  - Moved `/models` request construction, provider auth resolution,
  timeout handling, and request telemetry into `codex-model-provider` via
  `OpenAiModelsEndpoint`.
  - Added provider-owned `models_manager(...)` construction so configured
  OpenAI-compatible providers use `OpenAiModelsManager`, while
  static/catalog-backed providers can return `StaticModelsManager`.
  - Added an Amazon Bedrock static model catalog for the GPT OSS Bedrock
  model IDs.
  - Updated core/session/thread manager code and tests to depend on
  `Arc<dyn ModelsManager>`.
  - Moved offline model test helpers into
  `codex_models_manager::test_support`.
  ## Metadata References
  
  The Bedrock catalog metadata is based on the official Amazon Bedrock
  OpenAI model documentation:
  
  - [Amazon Bedrock OpenAI
  models](https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-openai.html)
  lists the Bedrock model IDs, text input/output modalities, and `128,000`
  token context window for `gpt-oss-20b` and `gpt-oss-120b`.
  - [Amazon Bedrock `gpt-oss-120b` model
  card](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html)
  lists the `bedrock-runtime` model ID `openai.gpt-oss-120b-1:0`, the
  `bedrock-mantle` model ID `openai.gpt-oss-120b`, text-only modalities,
  and `128K` context window.
  - [OpenAI `gpt-oss-120b` model
  docs](https://developers.openai.com/api/docs/models/gpt-oss-120b)
  document configurable reasoning effort with `low`, `medium`, and `high`,
  plus text input/output modality.
  
  The display names, default reasoning effort, and priority ordering are
  Codex-local catalog choices.
  
  ## Test Plan
  - Manually verified app-server model listing with an AWS profile:
  
  ```shell
  CODEX_HOME="$(mktemp -d)" cargo run -p codex-app-server-test-client -- \
    --codex-bin ./target/debug/codex \
    -c 'model_provider="amazon-bedrock"' \
    -c 'model_providers.amazon-bedrock.aws.profile="codex-bedrock"' \
    -c 'model_providers.amazon-bedrock.aws.region="us-west-2"' \
    model-list
  ```
  
  The response returned the Bedrock catalog with `openai.gpt-oss-120b-1:0`
  as the default model and `openai.gpt-oss-20b-1:0` as the second listed
  model, both text-only and supporting low/medium/high reasoning effort.

  Celia Chen · 2026-04-24 04:28:25 +00:00
  e8d8080818
• [rollout_trace] Add debug trace reduction command (#18880)

  ## Summary
  
  Adds the debug CLI entry point for reducing recorded rollout traces.
  This gives developers a direct way to inspect whether the emitted trace
  stream reduces into the expected conversation/runtime model.
  
  ## Stack
  
  This is PR 5/5 in the rollout trace stack.
  
  - [#18876](https://github.com/openai/codex/pull/18876): Add rollout
  trace crate
  - [#18877](https://github.com/openai/codex/pull/18877): Record core
  session rollout traces
  - [#18878](https://github.com/openai/codex/pull/18878): Trace tool and
  code-mode boundaries
  - [#18879](https://github.com/openai/codex/pull/18879): Trace sessions
  and multi-agent edges
  - [#18880](https://github.com/openai/codex/pull/18880): Add debug trace
  reduction command
  
  ## Review Notes
  
  This PR is intentionally last: it depends on the trace crate, core
  recorder, runtime/tool events, and session/agent edge data all existing.
  The command should remain a debug/developer tool and avoid adding new
  runtime behavior.
  
  The useful review question is whether the CLI exposes the reducer in the
  smallest practical way for local inspection without turning the debug
  command into a supported user-facing workflow.

  cassirer-openai · 2026-04-24 01:56:48 +00:00
  e3c8720a99
• [codex] Route live thread writes through ThreadStore (#18882)

  Begin migrating the thread write codepaths to ThreadStore.
  
  This starts using ThreadStore inside of core session code, not only in
  the app server code.
  
  Rework the interfaces around thread recording/persistence. We're left
  with the following:
  
  * `ThreadManager`: owns the process-level registry of loaded threads and
  handles cross-thread orchestration: start, resume, fork, lookup, remove,
  and route ops to running CodexThreads.
  * `CodexThread`: represents one loaded/running thread from the outside.
  It is the handle app-server and callers use to submit ops, inspect
  session metadata, and shut the thread down.
  * `LiveThread`: session-owned persistence lifecycle handle for one
  active thread. Core session code uses it to append rollout items,
  materialize lazy persistence, flush, shutdown, discard init-failed
  writers, and load that thread’s persisted history.
  * `ThreadStore`: storage backend abstraction. It answers “how are
  threads persisted, read, listed, updated, archived?” Local and remote
  implementations live behind this trait.
  * `LocalThreadStore`: local ThreadStore implementation. It owns the
  file/sqlite-specific details and keeps RolloutRecorder as a local
  implementation detail.
  
  This is a few too many Thread abstractions for my liking, but they do
  all represent different concepts / needs / layers.
  
  Migration note: in places where the core code explicitly requires a
  path, rather than a thread ID, throw an error if we're running with a
  remote store.
  
  Cover the new local live-writer lifecycle with focused tests and
  preserve app-server thread-start behavior, including ephemeral pathless
  sessions.

  Tom · 2026-04-23 10:17:09 -07:00
  f1923a38b1
• feat(request-permissions) approve with strict review (#19050)

  ## Summary
  Allow the user to approve a request_permissions_tool request with the
  condition that all commands in the rest of the turn are reviewed by
  guardian, regardless of sandbox status.
  
  ## Testing
  - [x] Added unit tests
  - [x] Ran locally

  Dylan Hurd · 2026-04-23 01:56:32 +00:00
  5e71da1424
• feat(auto-review) short-circuit (#18890)

  ## Summary
  Short circuit the convo if auto-review hits too many denials
  
  ## Testing
  - [x] Added unit tests
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Dylan Hurd · 2026-04-22 20:34:15 +00:00
  ed4def8286
• [rollout_trace] Record core session rollout traces (#18877)

  ## Summary
  
  Wires rollout trace recording into `codex-core` session and turn
  execution. This records the core model request/response, compaction, and
  session lifecycle boundaries needed for replay without yet tracing every
  nested runtime/tool boundary.
  
  ## Stack
  
  This is PR 2/5 in the rollout trace stack.
  
  - [#18876](https://github.com/openai/codex/pull/18876): Add rollout
  trace crate
  - [#18877](https://github.com/openai/codex/pull/18877): Record core
  session rollout traces
  - [#18878](https://github.com/openai/codex/pull/18878): Trace tool and
  code-mode boundaries
  - [#18879](https://github.com/openai/codex/pull/18879): Trace sessions
  and multi-agent edges
  - [#18880](https://github.com/openai/codex/pull/18880): Add debug trace
  reduction command
  
  ## Review Notes
  
  This layer is the first live integration point. The important review
  question is whether trace recording is isolated from normal session
  behavior: trace failures should not become user-visible execution
  failures, and recording should preserve the existing turn/session
  lifecycle semantics.
  
  The PR depends on the reducer/data model from the first stack entry and
  only introduces the core recorder surface that later PRs use for richer
  runtime and relationship events.

  cassirer-openai · 2026-04-22 17:00:48 +00:00
  f67383bcba