6999 Commits

This Branch

This Branch

All Branches

• [codex] fix compressed rollout fixture SessionMeta initialization (#25628)

  ## Summary
  - initialize `parent_thread_id` in the compressed rollout test fixture's
  `SessionMeta`
  - restore rollout test compilation across Bazel test, clippy,
  release-build, and argument-comment-lint jobs
  
  ## Root cause
  PR #25087 (`Read compressed rollouts and materialize before append`)
  added `codex-rs/rollout/src/compression_tests.rs` in merge commit
  `a8a6071279b6f3112fcc5fc3fee69c48473d7149`. Its `write_rollout` fixture
  constructs `SessionMeta` without the required `parent_thread_id` field,
  causing `error[E0063]` when Bazel compiles `rollout-unit-tests-bin` on
  `main` and downstream PRs.
  
  ## Validation
  - `UV_CACHE_DIR=/private/tmp/codex-uv-cache just fmt`
  - `just test -p codex-rollout` (`59` tests passed; bench smoke passed)
  - `git diff --check`
  - manually audited the touched Rust diff for positional literal argument
  comments; the change adds no positional callsite
  
  ## Local lint blocker
  - `just argument-comment-lint` could not reach source inspection locally
  because Bazel's LLVM dependency fails analysis:
  `compiler-rt/BUILD.bazel` glob `include/sanitizer/*.h` matched no files.

  Felipe Coury · 2026-06-01 16:43:21 +02:00
  4eded02f52
• Read compressed rollouts and materialize before append (#25087)

  ## Why
  
  Local rollout compression needs a cold `.jsonl.zst` representation
  without letting compressed physical paths leak into append-mode writers.
  The unsafe case is resume or metadata update code successfully reading a
  compressed rollout and then appending raw JSONL bytes to the zstd file.
  
  This PR folds the former #25088 materialization slice into the
  read-support PR so the reader changes and append-safety invariant land
  together.
  
  ## What Changed
  
  - Teach rollout readers, discovery, listing, search, and ID lookup to
  understand compressed `.jsonl.zst` rollouts.
  - Keep `.jsonl` as the logical/stored rollout path while allowing read
  paths to open either plain or compressed storage.
  - Materialize compressed rollouts back to plain `.jsonl` before
  append-mode writes, including resume and direct metadata append paths.
  - Preserve compressed-file permissions when materializing back to plain
  JSONL.
  - Refresh thread-store resolved rollout paths after compatibility
  metadata writes so reconciliation follows the materialized file.
  - Avoid treating transient compression temp files as real rollout lookup
  results.
  
  ## Remaining Stack
  
  #25089 remains the separate worker PR. It is based directly on this PR
  and stays behind the disabled `local_thread_store_compression` feature
  flag.
  
  The worker still has a broader coordination question: a resume or
  metadata update can race with background compression while a plain file
  is being replaced by `.jsonl.zst`. This PR handles the read and
  materialize-before-append primitives; it does not make the worker
  production-ready.
  
  ## Validation
  
  - `just test -p codex-rollout`
  - `just test -p codex-thread-store`
  - `just fix -p codex-rollout`
  - `just fix -p codex-thread-store`
  - `just bazel-lock-check`

  jif-oai · 2026-06-01 15:14:19 +02:00
  a8a6071279
• Add goal extension GoalApi (#25096)

  ## Summary
  
  - add an extension-owned `GoalApi` for thread goal get/set/clear
  operations
  - register live goal runtimes with the API from the goal extension
  backend
  - cover the API and runtime-effect paths in goal extension tests
  
  ## Stack
  
  Follow-up app-server wiring PR: #25108
  
  ## Validation
  
  - `just fmt`
  - `just fix -p codex-goal-extension`
  - `just test -p codex-goal-extension`

  jif-oai · 2026-06-01 11:32:13 +02:00
  f27bbbd49c
• Remove Plan-mode gate from idle turn injection (#25577)

  ## Why
  
  `try_start_turn_if_idle` is the core helper for starting injected input
  only when the session is actually idle. It should stay focused on
  generic turn-lifecycle safety. The previous `ModeKind::Plan` guard mixed
  caller policy into that helper: Plan mode may choose not to auto-start
  some extension work, but that decision belongs at the extension or
  caller boundary rather than in the session injection primitive.
  
  ## What changed
  
  - Removed the `ModeKind::Plan` early return from
  `Session::try_start_turn_if_idle`.
  - Removed the now-unused `ModeKind` import from
  `core/src/session/inject.rs`.
  
  ## Testing
  
  Not run locally.

  jif-oai · 2026-06-01 11:06:38 +02:00
  48c16b8bcb
• Use templates for goal steering prompts (#25576)

  ## Why
  
  Goal steering prompts have grown into long inline Rust strings, which
  makes the authored prompt text hard to review and easy to damage while
  changing the surrounding plumbing. Moving those prompts into embedded
  Markdown templates keeps the policy text in the shape reviewers actually
  read, while preserving the existing runtime substitution and objective
  escaping behavior.
  
  ## What changed
  
  - Added `ext/goal/templates/goals/continuation.md`, `budget_limit.md`,
  and `objective_updated.md` for the three goal steering prompts.
  - Updated `ext/goal/src/steering.rs` to parse those embedded templates
  once with `codex-utils-template` and render the existing goal values
  into them.
  - Kept user objectives XML-escaped before rendering and converted budget
  counters into template variables.
  - Added the template directory to `ext/goal/BUILD.bazel` `compile_data`
  so Bazel has the same embedded prompt inputs as Cargo.
  
  ## Testing
  
  - Not run locally.

  jif-oai · 2026-06-01 10:55:14 +02:00
  c875bc8a33
• Add goal extension idle continuation (#25060)

  ## Why
  
  The goal extension needs a way to resume an active goal after the thread
  becomes idle, but the old core goal runtime should not be refactored as
  part of this step. The missing piece is a small core-owned turn-start
  primitive: let an extension ask for a normal model turn only when the
  thread is idle, and otherwise fail without injecting into whatever is
  currently active.
  
  ## What Changed
  
  - Adds `CodexThread::try_start_turn_if_idle(...)` as the narrow
  extension-facing primitive for synthetic idle work.
  - Implements the session side so it refuses to start when:
    - the provided input is empty,
    - the session is in plan mode,
    - a turn is already active, or
    - trigger-turn mailbox work is pending.
  - Gives trigger-turn mailbox work priority if it appears while the idle
  turn is being prepared.
  - Wires `GoalExtension::on_thread_idle` to read the active persisted
  goal and submit the continuation prompt through this idle-only
  primitive.
  - Keeps the legacy core goal continuation implementation in place
  instead of folding it into this PR.
  
  ## Behavior
  
  This is intentionally best-effort. If `try_start_turn_if_idle` observes
  that the thread is not idle, or that higher-priority mailbox work should
  run first, it returns the input to the caller. The goal extension drops
  that continuation prompt and waits for a future idle opportunity instead
  of injecting stale synthetic goal text into an active turn.
  
  ## Validation
  
  - `just test -p codex-core
  try_start_turn_if_idle_rejects_active_turn_without_injecting`
  - `just test -p codex-goal-extension`

  jif-oai · 2026-06-01 10:42:01 +02:00
  f1b1b64005
• Set multi-agent v2 dogfood defaults (#25266)

  ## Summary
  - default multi-agent v2 to direct-model-only tools so code mode does
  not wrap subagent tools
  - add default root/subagent team prompts aligned with dogfood training
  assumptions
  - tighten spawn-agent model override wording to prefer the inherited
  model by default
  
  ## Tests
  - just fmt
  - just test -p codex-core
  spawn_agent_description_lists_visible_models_and_reasoning_efforts
  - just test -p codex-core
  multi_agent_v2_default_session_thread_cap_counts_root
  - just test -p codex-rollout-trace
  - just fix -p codex-core
  - just fix -p codex-rollout-trace
  
  Note: a broad just test -p codex-core run was attempted locally, but
  this sandbox produced unrelated environment failures around
  sandbox-exec, missing test_stdio_server, and realtime timeouts.

  jif-oai · 2026-06-01 10:24:46 +02:00
  8d49394feb
• store and expose parent_thread_id on Threads (#25113)

  ## Why
  
  This PR
  https://github.com/openai/codex/pull/24161#discussion_r3325692763
  revealed a subagent data modeling issue, where we overloaded
  `forked_from_id` to also mean `parent_thread_id`. That's incorrect since
  guardian and review subagents can be a subagent and NOT fork the main
  thread's history.
  
  The solution here is to explicitly store a new `parent_thread_id` on
  `SessionMeta`, alongside `forked_from_id` which already exists. While
  we're at it, also expose it in the app-server protocol on the `Thread`
  object.
  
  A thread->subagent relationship and a fork of thread history are
  orthogonal concepts.
  
  ## What Changed
  
  - Added top-level `parent_thread_id` persistence on `SessionMeta` and
  runtime/session plumbing through `SessionConfiguredEvent`,
  `CodexSpawnArgs`, `SessionConfiguration`, `ThreadConfigSnapshot`,
  `TurnContext`, and `ModelClient`.
  - Made turn metadata, request headers, analytics, and subagent-start
  events read the separate runtime/top-level parent field instead of
  deriving general parent lineage from `SessionSource` or
  `forked_from_thread_id`.
  - Passed parent lineage separately at delegated subagent, review,
  guardian, agent-job, and multi-agent spawn construction sites;
  copied-history fork lineage remains derived only from `InitialHistory`.
  - Persisted and exposed parent lineage through rollout/thread-store
  projections and app-server v2 `Thread.parentThreadId`.
  - Updated app-server README text and regenerated app-server schema
  fixtures for the additive `parentThreadId` response field.

  Owen Lin · 2026-06-01 04:33:20 +00:00
  cf0911076f
• Revert "Add build_unsigned_archive release mode" (#25462)

  Reverts openai/codex#25435

  Shijie Rao · 2026-05-31 16:05:33 -07:00
  3b7334d099
• Add cloud-managed config layer support (#24620)

  ## Summary
  
  PR 3 of 5 in the cloud-managed config client stack.
  
  Adds enterprise-managed cloud config as a first-class config layer
  source. The layer metadata is preserved through config loading,
  diagnostics, debug output, hook attribution, and app-server protocol
  surfaces.
  
  ## Details
  
  - Enterprise-managed config becomes a normal config layer source with
  backend-supplied `id` and display `name` attached for provenance.
  - These layers are designed to behave like non-file managed config: they
  can surface syntax/type diagnostics by layer name even though there is
  no physical config file.
  - Relative path settings are resolved from a stored config base so
  cloud-delivered config remains consistent with existing MDM-delivered
  config semantics.
  - Hook attribution distinguishes config-delivered hooks from
  requirements-delivered hooks via `HookSource::CloudManagedConfig`.
  - This remains pull-based and snapshot-oriented; the PR adds layer
  identity/diagnostics, not dynamic reload behavior.
  
  ## Validation
  
  Validated through the targeted stack checks after rebasing onto current
  `main`:
  
  - Rust crate tests for
  config/hooks/cloud-config/backend-client/app-server-protocol
  - Filtered `codex-core` and `codex-app-server` `cloud_config_bundle`
  tests
  - Python generated-file contract test
  - `cargo shear --deny-warnings`
  - Targeted `argument-comment-lint` for config/hooks

  joeflorencio-openai · 2026-05-31 15:54:31 -07:00
  8a556296f0
• Compose requirements layers (#24619)

  ## Summary
  
  PR 2 of 5 in the cloud-managed config client stack.
  
  Adds a shared requirements-layer composition engine. The composer
  defines how ordered requirements layers combine, with focused tests for
  the merge semantics and provenance behavior. The final PR in the stack
  wires runtime requirements sources into this path.
  
  ## Details
  
  - Mental model: requirements layers are ordered lowest priority first,
  matching `ConfigLayerStack`; lower-priority layers provide defaults
  while higher-priority layers win scalar/list conflicts.
  - Regular fields use config-style TOML merging, including recursive
  table merging, so requirements layering follows the same broad model as
  `config.toml` layering.
  - Domain-specific fields keep explicit semantics: `rules.prefix_rules`
  and hooks preserve high-priority-first output, hooks fail closed on
  active managed-dir conflicts, and `permissions.filesystem.deny_read`
  dedupes as a stable high-priority-first union.
  - `remote_sandbox_config` is evaluated within each layer before the
  regular TOML merge, so host-specific sandbox constraints do not leak
  across layers.
  - Provenance points at the exact source when one layer owns a value and
  uses composite provenance when a table field is assembled from multiple
  layers.
  
  ## Validation
  
  Local validation:
  
  - `just fmt`
  - `cargo check -p codex-config`
  - `just test -p codex-config requirements_composition`
  - `git diff --check`
  
  CI will run the broader test matrix.

  joeflorencio-openai · 2026-05-31 15:14:06 -07:00
  20debf746b
• Add build_unsigned_archive release mode (#25435)

  ## Why
  We want a manual mode that produces the full packaged unsigned macOS
  Codex archive, including bundled resources like `rg`, without mixing
  those archives into the signing and publishing flow.
  
  The existing `build_unsigned` mode is the handoff used by external
  signing and `promote_signed`, so archive-only inspection and local
  packaging should live in a separate mode and artifact namespace.
  
  ## What Changed
  - added `build_unsigned_archive` as a new manual `release_mode`
  - kept the existing `build` matrix running for that mode instead of
  introducing a separate archive-only job
  - wrote unsigned macOS package archives to
  `codex-rs/unsigned-archive-dist/...` instead of the normal `dist/...`
  tree
  - uploaded those packaged macOS outputs as dedicated
  `*-unsigned-archive` workflow artifacts
  - kept `build_unsigned` and `promote_signed` on their existing raw
  unsigned binary path
  
  ## Validation
  - parsed `.github/workflows/rust-release.yml` with `ruby -e 'require
  "yaml"; YAML.load_file(".github/workflows/rust-release.yml")'`
  - ran `git diff --check -- .github/workflows/rust-release.yml`
  - reviewed the workflow diff to confirm `build_unsigned_archive` now
  reuses the existing `build` job while isolating the unsigned macOS
  package archives under dedicated artifact names
  - locally verified the package builder layout against unsigned macOS
  binaries to confirm the packaged archive contains `bin/codex`,
  `codex-path/rg`, and `codex-resources/zsh/bin/zsh`

  Shijie Rao · 2026-05-31 14:56:06 -07:00
  5f60b01352
• Add config bundle transport types (#24617)

  ## Summary
  
  PR 1 of 5 in the cloud-managed config client stack.
  
  Adds the generated backend models and client transport surface for the
  config bundle endpoint. This bundle endpoint is the replacement backend
  surface for legacy cloud requirements; the final PR in the stack
  switches runtime consumers over to it.
  
  ## Details
  
  - This is transport-only plumbing: no runtime config behavior changes in
  this PR.
  - The bundle endpoint is the new shared backend surface for
  cloud-delivered config and requirements data.
  - Both supported path styles are wired here: `/api/codex/config/bundle`
  and `/wham/config/bundle`.
  - The response types come from generated backend models so later PRs
  consume the backend contract directly instead of maintaining
  hand-written mirror structs.
  
  ## Validation
  
  Validated through the targeted stack checks after rebasing onto current
  `main`:
  
  - Rust crate tests for
  config/hooks/cloud-config/backend-client/app-server-protocol
  - Filtered `codex-core` and `codex-app-server` `cloud_config_bundle`
  tests
  - Python generated-file contract test
  - `cargo shear --deny-warnings`
  - Targeted `argument-comment-lint` for config/hooks

  joeflorencio-openai · 2026-05-31 11:52:18 -07:00
  e93dc98a48
• feat(tui): allow function keys through f24 in keymaps (#25329)

  ## Why
  
  Closes #25006.
  
  `tui.keymap` currently rejects `F13` even though Codex's terminal event
  layer can report higher function keys. This prevents users from using
  common remappings such as Caps Lock to `F13`.
  
  ## What Changed
  
  - Define a shared portable upper bound of `F24` for stored TUI
  keybindings.
  - Accept `f13` through `f24` in config normalization and runtime
  parsing.
  - Allow `/keymap` capture to persist `F13` through `F24`.
  - Update the unsupported-function-key error and add boundary tests for
  `F13`, `F24`, and `F25`.
  
  ## How to Test
  
  1. Add a binding such as:
  
     ```toml
     [tui.keymap.global]
     open_transcript = "f13"
     ```
  
  2. Start Codex and press the remapped `F13` key.
  3. Confirm Codex loads the config without the previous `F1 through F12`
  error and the action runs.
  4. Open `/keymap`, capture `F13` for an action, and confirm the saved
  binding is `f13`.
  5. As a regression check, try to capture `F25` and confirm Codex reports
  that only `F1` through `F24` can be stored.
  
  Targeted tests:
  
  - `just test -p codex-config`
  - `just test -p codex-tui function_keys`
  
  Full `just test -p codex-tui` completed with 2,752 passing tests, 4
  skipped tests, and two unrelated guardian feature-flag failures:
  
  -
  `app::tests::update_feature_flags_disabling_guardian_clears_review_policy_and_restores_default`
  -
  `app::tests::update_feature_flags_disabling_guardian_clears_manual_review_policy_without_history`

  Felipe Coury · 2026-05-31 15:42:39 -03:00
  2f0726ad6d
• [codex] Avoid forced directory refresh during plugin install auth checks (#25381)

  ## Summary
  - Use normal directory loading for plugin install app metadata so
  install avoids forced directory refresh while still loading metadata on
  cold cache.
  - Continue force-refreshing codex_apps tools for auth state.
  - Add regression coverage that pre-warms the directory cache and asserts
  install returns cached app metadata without extra directory requests.
  
  ## Validation
  - just fmt
  - git diff --check
  - just test -p codex-app-server plugin_install_returns_apps_needing_auth
  plugin_install_filters_disallowed_apps_needing_auth (blocked locally:
  cargo-nextest is not installed)

  xl-openai · 2026-05-31 02:14:15 -07:00
  cdde711fac
• fix: Limit Bedrock GPT models to default service tier (#25318)

  ## Description
  
  Bedrock currently only supports the implicit `default` service tier for
  GPT models. This PR strips non-default service tier metadata from
  Bedrock model catalogs so Codex does not advertise or send unsupported
  tiers.
  
  ## What changed
  
  - Normalize both built-in and configured Bedrock catalogs to
  default-only service tier behavior.
  - Add regression coverage for built-in and configured Bedrock catalogs.
  
  ## Validation
  
  - `just fmt`
  - `just test -p codex-model-provider`

  Owen Lin · 2026-05-30 11:54:58 -07:00
  966932124c
• Rename multi-agent v2 assignment tool (#25267)

  ## Summary
  - rename the multi-agent v2 follow-up task tool surface to assign_task
  - update core tests and spec-plan expectations
  - keep rollout-trace classification backward-compatible with legacy
  followup_task
  
  ## Tests
  - just fmt
  - just test -p codex-core
  multi_agents_spec::tests::assign_task_tool_requires_message_and_has_no_output_schema
  - just test -p codex-rollout-trace
  - just fix -p codex-core
  - just fix -p codex-rollout-trace
  
  Note: a broad just test -p codex-core run was attempted locally, but
  this sandbox produced unrelated environment failures around
  sandbox-exec, missing test_stdio_server, and realtime timeouts.

  jif-oai · 2026-05-30 14:13:05 +02:00
  8acaec73b6
• Add thread archive CLI commands (#25021)

  ## Problem
  
  Saved threads can already be archived through app-server RPCs, but the
  command line did not expose direct archive or unarchive commands.
  
  ## Solution
  
  Add `codex archive <thread>` and `codex unarchive <thread>`, resolving
  UUIDs or exact thread names before calling the existing `thread/archive`
  and `thread/unarchive` RPCs. The commands support scoped remote flags so
  callers can target remote app-server endpoints when archiving or
  unarchiving threads.
  
  This also fixes a long-standing bug in `codex resume <thread id>` and
  `codex fork <thread id>` that I found when testing the new commands.
  These operations shouldn't be allowed on archived sessions. They now
  fail with an error that tells the user to run `codex unarchive <thread
  id>` first.
  
  ## Verification
  
  Added app-server coverage for rejecting archived thread resume by id and
  checking that the error includes the matching `codex unarchive <thread
  id>` command.

  Eric Traut · 2026-05-29 23:37:26 -07:00
  3e7baa00e4
• feat(config) experimental_request_user_input toggle (#24541)

  ## Summary
  Experimental flag to allow toggling `request_user_input`:
  
  ```
  tools.experimental_request_user_input = false
  ```
  
  ## Testing
  - [x] Added unit tests

  Dylan Hurd · 2026-05-29 21:35:53 -07:00
  e0435afb72
• fix: Bedrock API key region fallback (#25171)

  ## Why
  
  Users following the Amazon Bedrock API-key setup can export
  `AWS_BEARER_TOKEN_BEDROCK` and `AWS_REGION`, but Codex's bearer-token
  auth path only accepted `model_providers.amazon-bedrock.aws.region`.
  That made the documented env-based setup fail with a missing-region
  error even though the standard AWS region environment variable was
  present.
  
  ## What Changed
  
  - Updates Bedrock bearer-token region resolution to use
  `model_providers.amazon-bedrock.aws.region` first, then fall back to
  `AWS_REGION`, then `AWS_DEFAULT_REGION`.
  - Updates the missing-region error to list all supported region sources.
  - Adds focused coverage for config precedence, `AWS_REGION`,
  `AWS_DEFAULT_REGION`, and the missing-region failure.

  Celia Chen · 2026-05-30 01:17:38 +00:00
  00ca857d3f
• [codex] Update remote connector suggestions (#25172)

  ## Summary
  
  - Use the session-loaded plugin app IDs as the source of connector
  suggestion candidates.
  - Remove the redundant plugin reload from
  `tool_suggest_connector_ids()`.
  - Add regression coverage for connectors declared by a loaded remote
  plugin, using the Databricks app case.
  
  ## Context
  
  Loaded remote plugins can declare app connector IDs in `.app.json`. The
  session-owned `PluginsManager` already loads those plugins and exposes
  their effective app IDs.
  
  The connector suggestion path was creating a separate `PluginsManager`
  and recomputing plugin app IDs. That new manager does not share the
  session manager’s remote installed plugin cache, so app IDs from loaded
  remote plugins were missing from connector suggestions.
  
  ## Fix
  
  Pass the already-loaded effective app IDs into connector suggestion
  generation and use them directly as the plugin-derived connector
  candidate set.
  
  Connector candidates are now built from:
  
  - App IDs declared by loaded plugins
  - Explicitly configured connector discoverables
  - Existing disabled-suggestion filtering
  
  This avoids a second plugin-manager lookup and keeps connector
  suggestions aligned with the plugins actually loaded for the turn.
  
  ## Behavior
  
  For example, when a plugin is loaded and its `.app.json` declares data
  apps, `list_available_plugins_to_install` can now return those data
  connectors.
  
  This does not create plugin suggestions from the plugin itself. Plugin
  suggestions still come from eligible uninstalled entries in the
  marketplace catalog and require existing matching/filtering rules.
  
  ## Validation
  
  - `just fmt`
  - Added regression coverage for a loaded-plugin connector ID appearing
  in discoverable tools
  - Attempted `just test -p codex-core`; the command exited unsuccessfully
  in the local test environment without useful failure detail captured in
  the run output

  Eric Ning · 2026-05-29 17:57:34 -07:00
  e929bb5c88
• Constrain Windows sandbox requirements (#23766)

  # Why
  
  Managed requirements can already constrain sandbox policy choices, but
  Windows sandbox implementation selection was still resolved
  independently from those requirements. That left the TUI able to
  continue through the unelevated fallback even when an organization wants
  to require the elevated Windows sandbox implementation.
  
  # What
  
  - Add `[windows].allowed_sandbox_implementations` requirements support
  for the Windows `elevated` and `unelevated` implementations.
  - Apply that allowlist during core config resolution so disallowed
  configured or feature-selected Windows sandbox implementations fall back
  to an allowed implementation with the existing requirements warning
  path.
  - Reuse the existing TUI Windows setup prompts to block disallowed
  unelevated continuation, keep required elevated setup in front of the
  user, and refuse to persist a TUI-selected Windows sandbox mode that
  requirements disallow.
  
  # Semantics
  
  | Allowed | Selected | Effective |
  | --- | --- | --- |
  | `["elevated"]` | `unelevated` / unset | `elevated` |
  | `["unelevated"]` | `elevated` / unset | `unelevated` |
  | `["elevated", "unelevated"]` | `elevated` | `elevated` |
  | `["elevated", "unelevated"]` | `unelevated` | `unelevated` |
  | `["elevated", "unelevated"]` | unset | `elevated` |
  
  Availability is handled by interactive setup surfaces after allowlist
  resolution. If the effective elevated implementation is not ready,
  elevated-only requirements block on setup. When unelevated is also
  allowed, the UI may offer the existing unelevated fallback.
  
  ## TUI Screens
  
  If elevated setup is not already complete:
  ```
    Your organization requires the default Codex agent sandbox to continue. Set it up to protect your files and control
    network access.
    Learn more <https://developers.openai.com/codex/windows>
  
  › 1. Set up default sandbox (requires Administrator permissions)
    2. Quit
  ```
  
  If admin setup fails under `["elevated"]`:
  ```
    Couldn't set up your sandbox with Administrator permissions
  
    Your organization requires the default sandbox before Codex can continue.
    Learn more <https://developers.openai.com/codex/windows>
  
  › 1. Try setting up admin sandbox again
    2. Quit
  ```
  
  # Next Steps
  
  
  - extend the requirements/readout surface, such as
  `configRequirements/read`, so clients can inspect the loaded
  `[windows].allowed_sandbox_implementations` requirement instead of
  inferring it from Windows setup state
  - consider extending `windowsSandbox/readiness` as well
  - update the App startup guide, setup flow, and banner surfaces so an
  elevated-only requirement omits any continue-unelevated escape hatch and
  blocks startup until a permitted implementation is ready;
  - preserve the existing unelevated fallback path when requirements allow
  it, including the `["unelevated"]` case where elevated is disallowed

  Abhinav · 2026-05-29 16:31:33 -07:00
  a5a94ee5a7
• Filter plugin install suggestions by installed apps (#24996)

  ## Summary
  
  - Keep the original `TOOL_SUGGEST_DISCOVERABLE_PLUGIN_ALLOWLIST` as a
  fallback seed list, so users with no installed plugins still get initial
  install suggestions.
  - Allow additional install suggestions from trusted marketplaces:
  `openai-curated` and `openai-bundled`.
  - Require non-fallback, non-configured marketplace candidates to share
  `.app.json` connector IDs with already installed plugins.
  - Preserve explicit configured plugin discoverables as an override,
  while still omitting installed, disabled, and `NOT_AVAILABLE` plugins.
  
  ## Context
  
  `list_available_plugins_to_install` controls which plugins the model can
  trigger via `request_plugin_install`. We want a small starter set for
  empty/new users, but we also want installed workflow plugins to unlock
  relevant source plugins without maintaining every source plugin ID by
  hand.
  
  This keeps the legacy plugin ID allowlist only as the starter fallback.
  For everything else, the trusted marketplace is the candidate boundary,
  and installed app connector overlap is the relevance filter. For
  example, an installed Sales plugin can make HubSpot and Granola
  suggestible when those source plugins are in `openai-curated` and share
  Sales app connector IDs, while an unrelated test-source plugin with an
  app connector not declared by Sales stays hidden.
  
  ## Test Coverage
  
  - Empty/no-installed-plugin case: returns the fallback seed plugins from
  the original allowlist.
  - Installed-app expansion: returns non-fallback marketplace plugins only
  when their app connector IDs overlap with an installed plugin.
  - Sales workflow case: installed Sales declares HubSpot and Granola
  apps, so `hubspot@openai-curated` and `granola@openai-curated` are
  returned.
  - Sales negative case: `test-source@openai-curated` has an app connector
  not declared by Sales, so it is not returned.
  - Existing guardrails: installed plugins, disabled suggestions, and
  `NOT_AVAILABLE` plugins remain omitted; explicit configured
  discoverables still work as an override.
  
  ## Validation
  
  - `just fmt`
  - `just test -p codex-core plugins::discoverable::tests`
  - `just test -p codex-core` was attempted earlier, but current `main` /
  local env failed with unrelated existing failures around missing
  `test_stdio_server`, CLI/code-mode MCP tool setup, and
  unified_exec/shell snapshot flakes/timeouts. The touched discoverable
  tests pass.

  Noah MacCallum · 2026-05-29 15:32:04 -07:00
  8e5f561697
• Recommend Bazel VSCode extension. (#25161)

  Provides starlark syntax highlighting and editor formatting.

  Adam Perry @ OpenAI · 2026-05-29 15:24:41 -07:00
  a076b21730
• [codex] Fix Vim normal mode editing (#25022)

  ## Summary
  - add Vim normal-mode `s` support to substitute the character under the
  cursor and enter insert mode
  - fix Vim normal-mode `o` so opening below the final line moves the
  cursor onto the new blank line
  - update keymap config/schema and keymap picker snapshots for the new
  action
  
  ## Validation
  - `just fmt`
  - `just write-config-schema`
  - `just test -p codex-config`
  - focused `just test -p codex-tui` coverage for the Vim `s` and `o`
  behavior, keymap conflict handling, and keymap picker snapshots
  - `cargo insta pending-snapshots --manifest-path tui/Cargo.toml`
  - `git diff --check`
  
  ## Notes
  A full `just test -p codex-tui` run still has two unrelated Guardian
  feature-flag failures in this checkout:
  -
  `app::tests::update_feature_flags_disabling_guardian_clears_review_policy_and_restores_default`
  -
  `app::tests::update_feature_flags_disabling_guardian_clears_manual_review_policy_without_history`

  Jinghan Xu · 2026-05-29 14:01:27 -07:00
  f2e7b462a9
• exec-server: preserve fs helper CoreFoundation env (#25118)

  ## Summary
  - preserve macOS `__CF_USER_TEXT_ENCODING` when launching the sandboxed
  fs helper
  - keep the fs-helper env narrow; this adds only the CoreFoundation
  startup var instead of copying the broader MCP stdio baseline
  - add focused coverage that the helper keeps that var without admitting
  `HOME`
  
  ## Diagnosis
  The sandboxed fs helper is not launched like a normal child process.
  Exec-server rebuilds its environment from an allowlist, then calls
  `env_clear()` before re-execing Codex with `--codex-run-as-fs-helper`.
  That helper dispatches before the normal Codex startup path and only
  needs to boot a small Tokio runtime, read one JSON request from stdin,
  perform the direct filesystem operation, and write one JSON response.
  
  The reported macOS hang sampled the helper before Rust main, in
  CoreFoundation initialization while resolving the default text encoding:
  `_CFStringGetUserDefaultEncoding -> getpwuid_r -> notify_register_check
  -> bootstrap_look_up3 -> mach_msg2_trap`. The fs-helper allowlist kept
  `PATH` and temp vars for runtime needs, but it dropped macOS
  `__CF_USER_TEXT_ENCODING`. Other Codex subprocess launchers that
  intentionally build a minimal Unix baseline, such as MCP stdio, already
  preserve that variable.
  
  My read is that stripping `__CF_USER_TEXT_ENCODING` forced this internal
  helper down CoreFoundation's fallback user-lookup path, and that lookup
  intermittently wedged on the affected machine before the helper could
  read stdin or touch the target file. Preserving only this macOS startup
  variable avoids that fallback without broadening the fs-helper
  environment to shell-like vars such as `HOME`, `USER`, locale settings,
  terminal settings, or proxy credentials.
  
  Internal Slack thread omitted from the public PR body.
  
  ## Validation
  - `cd codex-rs && just fmt`
  - `git diff --check`

  starr-openai · 2026-05-29 12:20:17 -07:00
  a717e4ef31
• ci: use issue triage environment for issue workflows (#25134)

  ## Summary
  
  This adds `environment: issue-triage` to the Codex-calling issue
  workflow jobs so they can read the GitHub Environment Secret while
  staying on GitHub-hosted runners for public issue-triggered workflows.

  Eric Traut · 2026-05-29 12:06:55 -07:00
  20da4c37c5
• [codex] Require model for standalone web search (#25131)

  ## Why
  
  The standalone `/v1/alpha/search` request now requires a `model`, but
  the `web.run` extension currently omits it.
  
  Adds `model` to extension `ToolCall` invocation.
  
  Follow-up to #23823.
  
  ## What changed
  
  - Make `SearchRequest.model` required.
  - Expose the effective per-turn model on extension tool calls and pass
  it in standalone web-search requests.
  - Assert the model is forwarded in the app-server round-trip test.
  
  ## Testing
  
  - `just test -p codex-api -p codex-tools -p codex-web-search-extension
  -p codex-memories-extension -p codex-goal-extension`
  - `just test -p codex-core -E
  'test(passes_turn_fields_and_scoped_turn_item_emitter_to_extension_call)'`
  - `just test -p codex-app-server -E
  'test(standalone_web_search_round_trips_encrypted_output)'`

  sayan-oai · 2026-05-29 12:03:04 -07:00
  1f93706e99
• thread-store: store permission profiles (#23165)

  ## Why
  
  `SandboxPolicy` is the legacy compatibility shape, but
  `codex-thread-store` still exposed it through `StoredThread`,
  `ThreadMetadataPatch`, and live metadata sync. That kept thread-store
  consumers tied to the legacy representation and meant richer permission
  profile data could not round-trip through thread metadata or cold
  rollout reconciliation.
  
  ## What Changed
  
  - Replaced thread-store `sandbox_policy` API fields with canonical
  `PermissionProfile` fields.
  - Persist new permission-profile metadata as canonical JSON in the
  existing SQLite metadata slot while continuing to read older legacy
  sandbox policy values.
  - Updated local, in-memory, live metadata sync, and rollout extraction
  paths to propagate `TurnContextItem::permission_profile()`.
  - Re-materialize legacy permission metadata against the final rollout
  cwd when rollout-derived metadata replaces stale SQLite summaries.
  - Updated affected app-server and core test constructors to build
  `PermissionProfile` values directly.
  
  ## Test Plan
  
  - `cargo test -p codex-state`
  - `cargo test -p codex-thread-store`
  - `cargo test -p codex-app-server
  summary_from_stored_thread_preserves_millisecond_precision --lib`
  - `cargo test -p codex-core realtime_context --lib`

  Michael Bolin · 2026-05-29 11:55:31 -07:00
  a1ecf0cf1c
• code-mode: introduce durable session interface (#24180)

  ## Summary
  
  Introduce a `CodeModeSession` interface for executing and managing
  code-mode cells.
  
  This moves cell lifecycle, callback delegation, termination, and
  shutdown behind a session abstraction, while continuing to use the
  existing in-process implementation, and the ability to implement an
  external process one behind this interface.
  
  A Codex session owns one `CodeModeSession`, which in turn owns its
  running cells and stored code-mode state. Each cell is represented to
  the caller as a `StartedCell`, exposing its cell ID and initial
  response.
  
  It also introduces a `CodeModeSessionDelegate` callback interface. A
  session uses the delegate to invoke nested host tools and emit
  notifications while a cell is running, allowing the runtime to
  communicate with its owning Codex session without depending directly on
  core turn handling.
  
  <img width="2121" height="1001" alt="image"
  src="https://github.com/user-attachments/assets/c349a819-2a59-485c-bda4-2caf68ac4c31"
  />

  Channing Conger · 2026-05-29 11:42:52 -07:00
  c9dc0f6338
• [exec-server] Kill dropped filesystem helpers (#25116)

  ## Summary
  - terminate sandbox filesystem helpers when the Tokio child handle is
  dropped
  
  ## Why
  A sandbox filesystem helper can stall during process startup before
  reading stdin. If the owning async operation is cancelled or torn down,
  the spawned helper should not remain running as an orphaned process.
  
  Setting `kill_on_drop(true)` gives the filesystem helper the cleanup
  behavior that Tokio child processes otherwise do not enable by default.
  
  This intentionally does not add a timeout. It does not detect or recover
  an active hung file edit while the owning future remains alive. A more
  precise startup-health mechanism can be handled separately.
  
  ## Validation
  - `just test -p codex-exec-server` (186 tests passed; benchmark smoke
  passed)
  - `just fmt`
  - `just fix -p codex-exec-server`
  - `git diff --check`

  Eric Horacek · 2026-05-29 11:40:44 -07:00
  451b386442
• Add subagent lineage metadata for responsesapi (#24161)

  ## Why
  
  We recently added `forked_from_thread_id` which lets us trace where a
  thread's _context_ comes from, but we also want to understand subagent
  lineage (e.g. which parent thread spawned this subagent? what kind of
  subagent is it?) which is orthogonal.
  
  This PR adds `parent_thread_id` and `subagent_kind` to the
  `x-codex-turn-metadata` header sent to ResponsesAPI.
  
  ## What changed
  
  - Adds `parent_thread_id` and `subagent_kind` to core-owned
  `x-codex-turn-metadata`.
  - Restores persisted `SessionSource` and `ThreadSource` from resumed
  session metadata so cold-resumed subagent threads keep their lineage on
  later Responses API requests.
  - Centralizes parent-thread extraction on `SessionSource` /
  `SubAgentSource` and reuses it in the Responses client, analytics, agent
  control, and state parsing paths.
  - Extends reserved-key, git-enrichment, thread-spawn, and app-server v2
  metadata coverage for the new lineage fields.
  
  ## Verification
  
  - Not run locally per request.
  - Added focused coverage in `core/src/turn_metadata_tests.rs` and
  `app-server/tests/suite/v2/client_metadata.rs`.

  Owen Lin · 2026-05-29 11:28:12 -07:00
  fc9cf62efb
• Use session wording in /rename confirmation (#25035)

  ## Why
  
  The TUI `/rename` confirmation should use the term "session" for
  consistency.

  Eric Traut · 2026-05-29 11:09:40 -07:00
  62039e8d35
• Add /archive slash command (#25027)

  ## Why
  
  TUI users can archive saved sessions from other surfaces, but there is
  no in-session command for archiving the active session. Since archiving
  the active session also exits the TUI, the command should ask for
  explicit confirmation instead of firing immediately.
  
  I'm also working on [a companion
  PR](https://github.com/openai/codex/pull/25021) that adds `codex
  archive` and `codex unarchive` top-level CLI commands.
  
  ## What changed
  
  - Adds a new `/archive` slash command described as `archive this session
  and exit`.
  - Shows a confirmation dialog with `No, don't archive` selected first
  and `Yes, archive and exit` as the explicit action.
  - On confirmation, calls the existing `thread/archive` app-server RPC
  for the active main session and exits after success.
  - Keeps `/archive` disabled while a task is running and unavailable in
  side conversations.
  
  ## Verification
  
  Added focused TUI coverage for the `/archive` confirmation flow,
  disabled-while-task-running behavior, and the `/ar` slash-command popup
  snapshot.

  Eric Traut · 2026-05-29 11:07:19 -07:00
  36cd36626d
• Align TUI permissions labels with app (#25017)

  ## Summary
  
  The desktop app now presents the on-request permissions mode as `Ask for
  approval` and the manual-review-backed mode as `Approve for me`. The TUI
  still exposed older/internal labels like `Default` and `Auto-review`,
  which made the same underlying settings look different across clients.
  
  This updates the TUI UX copy to match the app without changing the
  underlying default behavior. Fresh threads continue to use the existing
  on-request approval mode, now displayed as `Ask for approval`.
  
  The label changes cover `/permissions`, explicit profile permissions
  menus, status surfaces, config persistence history/error text, and the
  corresponding TUI snapshots.
  
  ### Before
  <img width="1181" height="119" alt="Screenshot 2026-05-28 at 10 19
  47 PM"
  src="https://github.com/user-attachments/assets/0664846b-b6dd-4931-b4dd-d0af0d42058e"
  />
  <img width="523" height="19" alt="Screenshot 2026-05-28 at 10 21 29 PM"
  src="https://github.com/user-attachments/assets/7899c33e-b35d-4684-8389-97e357803423"
  />
  
  ### After
  <img width="1216" height="117" alt="Screenshot 2026-05-28 at 10 19
  32 PM"
  src="https://github.com/user-attachments/assets/015aab43-ac97-411f-8031-75cdd887251b"
  />
  <img width="567" height="18" alt="Screenshot 2026-05-28 at 10 20 24 PM"
  src="https://github.com/user-attachments/assets/28b6422c-b823-4298-b221-c83d46d09d66"
  />

  Eric Traut · 2026-05-29 11:06:40 -07:00
  1333f4a689
• Add Windows sandbox provisioning setup command (#24831)

  ## Why
  
  Some Windows users do not have local admin access, so they cannot
  complete the elevated portion of the Windows sandbox setup when Codex
  first needs it. This adds an alpha provisioning path that an admin or IT
  deployment script can run ahead of time for the Codex user.
  
  The intended managed-deployment shape is:
  
  ```powershell
  codex sandbox setup --elevated --user "$env:COMPUTERNAME\Alice" --codex-home "C:\Users\Alice\.codex"
  ```
  
  `--elevated` is treated as the requested sandbox setup level, not as
  proof that the process is elevated. The Windows sandbox setup
  orchestration still checks that the caller is actually elevated before
  launching the helper without a UAC prompt.
  
  ## What changed
  
  - Added `codex sandbox setup --elevated` with explicit user selection
  via either `--current-user` or `--user ... --codex-home ...`.
  - Moved the CLI implementation into `cli/src/sandbox_setup.rs` instead
  of growing `cli/src/main.rs`.
  - Added a Windows sandbox `ProvisionOnly` helper mode that runs the
  elevation-required provisioning work without requiring a workspace cwd
  or runtime sandbox policy.
  - Reused the existing elevated helper path for creating/updating sandbox
  users, configuring firewall/WFP rules, and applying sandbox directory
  ACLs.
  - Persisted `windows.sandbox = "elevated"` into the target `CODEX_HOME`
  so the desktop app does not show the initial sandbox setup banner after
  pre-provisioning succeeds.
  
  ## Validation
  
  - `cargo fmt -p codex-windows-sandbox -p codex-core -p codex-cli`
  - `cargo test -p codex-cli sandbox_setup --target-dir
  target\sandbox-setup-check`
  - `cargo test -p codex-windows-sandbox
  payload_accepts_provision_only_mode --target-dir
  target\sandbox-setup-check`
  - `git diff --check`
  - Manual Windows alpha flow with a standard local user (`Mandi Lavida`):
  ran the new setup command from an admin shell, verified the target
  `.codex` contents, sandbox marker/secrets, ACLs, firewall rules, and
  desktop startup without the sandbox setup banner once experimental
  network proxy requirements were disabled.
  
  ## Notes
  
  This intentionally does not solve later elevated update coordination for
  IT-managed deployments. The setup command can still apply provisioning
  updates when run again, but a broader coordination/process story is out
  of scope for this alpha.

  iceweasel-oai · 2026-05-29 11:01:44 -07:00
  cb9178e8b3
• Route extension image generation through the native image completion pipeline (#24972)

  ## Why
  
  The standalone `image_gen.imagegen` extension should behave like native
  image generation for artifact persistence and UI completion, while
  returning its save-location guidance as part of the tool result instead
  of injecting a developer message.
  
  ## What Changed
  
  - Added an image-generation completion hook for extension tools so core
  can persist generated images and emit the existing `ImageGeneration`
  lifecycle events.
  - Reused core image artifact persistence for extension output and
  removed extension-local save-path/file-writing logic.
  - Split shared image persistence from built-in finalization so native
  image generation keeps its existing developer-message instruction
  behavior.
  - Returned the generated image save-location instruction through the
  extension `FunctionCallOutput`, alongside the generated image input for
  model follow-up.
  - Preserved the existing image-generation event shape for current UI and
  replay compatibility.
  - Avoided cloning the full generated-image base64 payload when emitting
  the in-progress image item.
  - Removed dependencies no longer needed after moving persistence out of
  the extension crate.
  
  ## Fast Follow
  - Adjust the existing Extension API and add a general `TurnItem`
  finalization path for re-usability of code
  
  ## Validation
  
  - Ran `just fmt`.
  - Ran `just bazel-lock-update`.
  - Ran `just bazel-lock-check`.
  - Ran `just test -p codex-tools -p codex-extension-api -p
  codex-image-generation-extension`.
  - Ran `just test -p codex-core
  image_generation_publication_is_finalized_by_core`.
  - Ran `just test -p codex-core
  handle_output_item_done_records_image_save_history_message`.
  - Ran `just fix -p codex-tools -p codex-extension-api -p codex-core -p
  codex-image-generation-extension`.

  Won Park · 2026-05-29 17:33:13 +00:00
  10b0399034
• [codex] Wait for MCP readiness in core integration tests (#24964)

  Ensures MCP-backed `codex-core` integration tests exercise initialized
  servers instead of racing server startup.
  
  I've been idly investigating a few flakes and the failure modes are much
  more confusing when a tool call fails because of a failed server start
  than when the failed server start causes the test to fail directly.

  Adam Perry @ OpenAI · 2026-05-29 10:22:27 -07:00
  3e666dd32a
• feat: Add focused diagnostics for MCP HTTP send failures (#25013)

  Adds failure-only logging for MCP streamable HTTP post_message calls and
  the underlying reqwest send path, capturing the MCP method/request id,
  endpoint shape, auth-header presence, timeout/connect classification,
  and sanitized error source chain without logging headers, bodies,
  tokens, or full URLs.

  xl-openai · 2026-05-29 10:09:33 -07:00
  e29bbb5368
• Move config document helpers into their own module (#25110)

  ## Why
  
  `core/src/config/edit.rs` owns the config edit state machine, but it
  also carried the TOML document helper code inline as a nested module.
  Moving those helpers into their own file keeps the edit orchestration
  easier to scan without changing the config persistence behavior.
  
  ## What changed
  
  - Moved the existing `document_helpers` module from
  `core/src/config/edit.rs` into
  `core/src/config/edit/document_helpers.rs`.
  - Added `mod document_helpers;` so the existing `pub(super)` helper API
  remains available to the rest of `config::edit`.
  
  ## Testing
  
  Not run; this is a refactor-only module extraction with no intended
  behavior change.

  jif-oai · 2026-05-29 18:49:21 +02:00
  f4e9d2caac
• Show activity for standalone web search calls (#24693)

  ## Why
  
  Standalone `web.run` calls run in the extension, so they need normal
  web-search progress activity while a request is in flight and durable
  completed activity after a thread is reloaded.
  
  Follow-up to #23823; uses the extension turn-item emission path added in
  #24813.
  
  ## What changed
  
  - Emit standalone `web.run` start/completion items through the host
  turn-item emitter, preserving standard client delivery and rollout
  persistence.
  - Include useful completion detail for queries, image queries, and
  literal-URL `open`/`find` commands.
  - Render completed searches as `Searched the web` or `Searched the web
  for <detail>`, with snapshot coverage for the detail-free case.
  - Extend the app-server round-trip test to verify completed search
  activity is reconstructed by `thread/read` after a fresh-process reload.
  
  ## Testing
  
  - `just test -p codex-web-search-extension`
  - `just test -p codex-app-server -E
  "test(standalone_web_search_round_trips_encrypted_output)"`

  sayan-oai · 2026-05-29 16:12:58 +00:00
  96f1347fa3
• [codex] Add model tool mode selector (#25031)

  ## Why
  Some models need to select their code-execution behavior through model
  catalog metadata. Models without that metadata must continue to follow
  the existing `CodeMode` and `CodeModeOnly` feature flags, including when
  a newer server sends an enum value this client does not recognize.
  
  ## What changed
  - add optional `ModelInfo.tool_mode` metadata with `direct`,
  `code_mode`, and `code_mode_only`
  - treat omitted and unknown wire values as `None`
  - resolve `None` from the existing feature flags
  - carry the resolved `ToolMode` directly on `TurnContext`, outside
  `Config`
  - use the resolved value for turn creation, model switches, review
  turns, tool planning, and code execution
  
  ## Coverage
  - add protocol coverage for omitted, known, and unknown enum values
  - add focused coverage for flag fallback and explicit metadata
  overriding feature flags
  - add core integration coverage that fetches remote model metadata
  through `/v1/models` and verifies the outbound `/responses` tools for
  explicit `direct` and `code_mode_only` selectors
  
  ## Stack
  - followed by #25032

  Ahmed Ibrahim · 2026-05-29 09:05:05 -07:00
  5577a9e148
• Render multiline hook output in TUI (#24965)

  # Why
  
  Fixes #24529. Completed hook output in the TUI rendered each
  `HookOutputEntry` as one ratatui line, so explicit newlines inside hook
  output were not shown as separate transcript rows. That made multiline
  `SessionStart.additionalContext` hard to inspect even though the
  model-facing context path preserved the original text.
  
  # What
  
  - Split completed hook output entries on explicit newlines before
  rendering them in `codex-rs/tui/src/history_cell/hook_cell.rs`.
  - Keep the hook output prefix, such as `hook context:` or `warning:`, on
  the first physical line only.
  - Preserve explicit blank lines and render continuation lines with the
  hook body indent.
  - Add unit coverage for multiline context and warning output, plus a
  chatwidget snapshot regression for `SessionStart` history output.
  
  # Testing
  
  - `cargo nextest run -p codex-tui completed_hook_multiline
  hook_completed_before_reveal_renders_completed_without_running_flash`
  - `just argument-comment-lint -p codex-tui -- --ignore-rust-version
  --lib --tests`

  Abhinav · 2026-05-29 15:12:40 +00:00
  251b2412b2
• Remove stale rollout TODO tests (#25106)

  ## Summary
  
  Remove a stale `TODO(jif)` block of commented-out rollout listing tests
  that still referenced an older listing API.
  
  The current rollout listing behavior is covered by the active state DB
  and filesystem fallback tests, so keeping the dead commented tests just
  adds noise.
  
  ## Validation
  
  - `just fmt`
  - `just test -p codex-rollout`

  jif-oai · 2026-05-29 17:09:00 +02:00
  b40ad0d84d
• Handle goal usage limits from turn errors (#25095)

  ## Summary
  - handle goal usage-limit turn errors in the goal extension
  - exercise the extension path in the goal backend test
  
  ## Tests
  - just fmt
  - just test -p codex-goal-extension
  - just fix -p codex-goal-extension

  jif-oai · 2026-05-29 15:39:05 +02:00
  27e256bc40
• [codex] Improve built-in tool schema docs (#24794)

  ## Summary
  - Clarify default, omission, and bounded behavior across built-in tool
  schemas, including unified exec, classic shell, Code Mode exec/wait,
  multi-agent, agent job, MCP resource, image, goal, plan, tool_search,
  and test-sync fields.
  - Convert update_plan status to an enum and add short field descriptions
  where the schema previously relied on surrounding context.
  - Remove the dedicated permission-approval schema test and keep only
  updates to existing expected-spec tests.
  
  ## Validation
  - Ran `just fmt`.
  - Ran `git diff --check`.
  - Did not run clippy or tests, per request.
  
  Regression has been eval
  [here](https://openai.slack.com/archives/C09GDSP1J9X/p1779905065496949)
  and we proved there are no regressions

  jif-oai · 2026-05-29 13:32:19 +02:00
  1c55bb2702
• fix: main (#25075)
  jif-oai · 2026-05-29 12:53:31 +02:00
  3deda3116c
• Drop debug-client prompt state tracking (#25070)

  Deletes `codex-rs/debug-client/src/state.rs` as one step in removing the
  stale app-server debug client.
  
  This intentionally leaves Cargo workspace and lockfile cleanup for a
  later follow-up PR.

  jif-oai · 2026-05-29 12:51:23 +02:00
  191c39aa75
• Remove debug-client server event reader (#25069)

  Deletes `codex-rs/debug-client/src/reader.rs` as one step in removing
  the stale app-server debug client.
  
  This intentionally leaves Cargo workspace and lockfile cleanup for a
  later follow-up PR.

  jif-oai · 2026-05-29 12:51:19 +02:00
  43fa4e5d25
• Delete debug-client JSONL output helper (#25068)

  Deletes `codex-rs/debug-client/src/output.rs` as one step in removing
  the stale app-server debug client.
  
  This intentionally leaves Cargo workspace and lockfile cleanup for a
  later follow-up PR.

  jif-oai · 2026-05-29 12:51:16 +02:00
  5c1387846d