7919 Commits

This Branch

This Branch

All Branches

• Add environmentId to request_permissions (#25858)

  ## Stack
  
  1. #25850 - Key request-permission grants by environment: stores and
  applies sticky permission grants per environment id.
  2. This PR (#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.
  
  This PR is stacked on #25850; #25862 and #25867 are stacked on this PR.
  
  ## Why
  
  PR1 made request-permission grants internally environment-keyed, but the
  model-facing `request_permissions` tool could still only target the
  primary environment. For CCA and multi-environment turns, the tool needs
  an explicit way to bind a permission request to a selected attached
  environment before resolving relative paths.
  
  ## What Changed
  
  - Added optional `environmentId` to `RequestPermissionsArgs`, with
  `environment_id` accepted as an alias.
  - Exposed `environmentId` in the `request_permissions` tool schema and
  description.
  - Resolve the selected environment before parsing filesystem permission
  paths, so relative paths bind to the selected environment cwd.
  - Route validated tool calls through
  `request_permissions_for_environment` directly instead of duplicating
  environment lookup in `Session::request_permissions`.
  - Reject unknown environment ids with a model-facing error.
  - Updated focused request-permissions and Guardian call sites for the
  new optional field.
  
  ## Testing
  
  Not run locally per instruction.

  jif · 2026-06-02 20:51:25 +02:00
  e29071e4c9
• [codex-analytics] Track CodexErr details in turn analytics (#25707)

  ## Summary
  - add analytics-only `CodexErr` telemetry to `codex_turn_event` while
  leaving existing `turn_error` unchanged
  - record terminal `CodexErr` facts from core immediately before the
  existing turn error event is sent
  - emit source-truth `codex_error_*` fields for downstream analytics,
  including the raw `CodexErr::InvalidRequest(String)` message as
  `codex_error_subreason`
  
  ## Validation
  - `just test -p codex-analytics`
  - attempted `just test -p codex-core`, but the local run timed out
  across unrelated integration suites in this environment and is not being
  used as validation

  rhan-oai · 2026-06-02 11:40:35 -07:00
  8e4b92d294
• 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
• [codex] Revert shared BuildBuddy Bazel wrapper (#25909)

  ## Why
  
  PR #25905 intentionally adds a failing `codex-core` unit test, but its
  [Bazel test on Windows
  check](https://github.com/openai/codex/actions/runs/26837526950/job/79135369259)
  passed. That shows the Bazel configuration introduced by #25156 is not
  behaving as expected, so revert it while the configuration can be
  investigated separately.
  
  ## What changed
  
  Revert #25156 in full, restoring the previous Bazel remote
  configuration, CI scripts, workflows, `rusty_v8` handling, and
  documentation. This removes the shared BuildBuddy wrapper and its tests.
  
  ## Validation
  
  Not run locally; this exact revert was prioritized for a fast rollback.

  Adam Perry @ OpenAI · 2026-06-02 11:06:01 -07:00
  9e3d5f29e2
• core: derive built-in permission profiles from raw policies (#25739)

  ## Why
  
  Permission profiles that extend a built-in profile should behave like
  other TOML inheritance: parent entries provide defaults, and child keys
  override matching fields before the profile is compiled.
  
  That was not true for `:workspace`. Previously, a profile with `extends
  = ":workspace"` seeded the compiled runtime
  `PermissionProfile::workspace_write()` policy and then appended child
  filesystem entries. A child override such as `":tmpdir" = "read"`
  therefore left the inherited `":tmpdir" = "write"` entry in the final
  policy. Since same-target `write` wins over `read` during runtime
  resolution, the child override was ineffective.
  
  This also needs a clear source of truth for the built-in profiles. The
  protocol-level sandbox policy constructors now define the raw built-in
  filesystem entries, and both `PermissionProfile` presets and
  config-profile inheritance derive from those same values.
  
  ## What Changed
  
  - Add a canonical `FileSystemSandboxPolicy::read_only()` constructor
  while keeping the read-only and workspace-write raw filesystem entries
  explicit and independent.
  - Derive `PermissionProfile::read_only()` from
  `FileSystemSandboxPolicy::read_only()`;
  `PermissionProfile::workspace_write()` continues to derive from
  `FileSystemSandboxPolicy::workspace_write()`.
  - Build extensible `:read-only` and `:workspace` parent profiles by
  projecting those canonical sandbox policies into
  `PermissionProfileToml`, then merge user overrides at the TOML layer
  before compilation.
  - Add config parsing support for `:slash_tmp` so the built-in
  `:workspace` parent can be expressed in the same TOML-shaped filesystem
  table as user profiles.
  - Document that `PermissionsToml::resolve_profile()` returns an
  already-merged `PermissionProfileToml`, and return that profile directly
  after removing the resolved-profile wrapper.
  - Extend the config test for `extends = ":workspace"` to assert that
  inherited `":slash_tmp" = "write"` is preserved and that a child
  `":tmpdir" = "read"` entry replaces the inherited `write` entry.
  
  ## Verification
  
  - `just test -p codex-config`
  - `just test -p codex-protocol`
  - `just test -p codex-core
  permissions_profiles_resolve_extends_parent_first_with_child_overrides`
  - `just test -p codex-core
  default_permissions_profile_can_extend_builtin_workspace`
  - `just test -p codex-core`
    - Result: 2596 passed, 4 failed, 1 timed out.
  - The failures were existing sandbox/environment-sensitive tests
  unrelated to this permissions change:
  
  `suite::user_shell_cmd::user_shell_command_does_not_set_network_sandbox_env_var`,
  
  `suite::user_shell_cmd::user_shell_command_history_is_persisted_and_shared_with_model`,
  
  `suite::abort_tasks::interrupt_persists_turn_aborted_marker_in_next_request`,
      `suite::abort_tasks::interrupt_tool_records_history_entries`, and
  
  `thread_manager::tests::start_thread_uses_all_default_environments_from_codex_home`.

  Michael Bolin · 2026-06-02 10:57:35 -07:00
  593df8773d
• Route Bazel CI through shared BuildBuddy remote config wrapper (#25156)

  ## Why
  
  Bazel remote configuration was selected in several CI scripts and
  workflow steps. That made the BuildBuddy tenant policy easy to duplicate
  and harder to audit, especially for fork pull requests that must not use
  the OpenAI tenant.
  
  This builds on
  [sluongng/buildbuddy-ci-host-routing](https://github.com/openai/codex/compare/main...sluongng:codex:sluongng/buildbuddy-ci-host-routing)
  and consolidates the policy in one place.
  
  ## What to do if this breaks you
  
  See `codex-rs/docs/bazel.md` for details. TLDR:
  
  1. make a BuildBuddy API key and put it in `~/.bazelrc`
  2. if you're an OpenAI employee, add `common
  --config=buildbuddy-openai-rbe` to `user.bazelrc` in the repo root
  
  Run `just bazel-test` to ensure it works.
  
  Note that `just bazel-remote-test` no longer exists, you need to select
  a remote configuration as documented to use RBE.
  
  ## What changed
  
  - Add `.github/scripts/run_bazel_with_buildbuddy.py` as the shared Bazel
  wrapper and Python library. It selects the OpenAI host only for trusted
  upstream GitHub Actions runs, routes keyed fork runs to the generic
  host, and falls back to local Bazel execution when no key is available.
  - Move endpoint selection into explicit `.bazelrc` configurations and
  update Bazel CI, query helpers, and `rusty_v8` staging to use the shared
  policy. Loading-phase target-discovery queries remain local.
  - Add wrapper and `rusty_v8` unit coverage, plus `just test-scripts` for
  the `.github/scripts` Python tests.
  - Document local Bazel usage, `user.bazelrc` setup, BuildBuddy
  configurations, and CI behavior in `codex-rs/docs/bazel.md`.
  
  ## Validation
  
  - `just test-scripts`
  - `bash -n .github/scripts/run-bazel-ci.sh
  .github/scripts/run-bazel-query-ci.sh
  .github/scripts/run-argument-comment-lint-bazel.sh
  scripts/list-bazel-clippy-targets.sh`
  - `python3 -m py_compile .github/scripts/run_bazel_with_buildbuddy.py
  .github/scripts/test_run_bazel_with_buildbuddy.py
  .github/scripts/test_rusty_v8_bazel.py
  .github/scripts/rusty_v8_bazel.py`
  - `ruff check .github/scripts/run_bazel_with_buildbuddy.py
  .github/scripts/test_run_bazel_with_buildbuddy.py
  .github/scripts/test_rusty_v8_bazel.py
  .github/scripts/rusty_v8_bazel.py`

  Adam Perry @ OpenAI · 2026-06-02 09:56:20 -07:00
  ebb7980369
• Skip startup prewarm when websockets are disabled (#25868)

  ## Summary
  - skip startup websocket prewarm setup when the model client has
  Responses-over-WebSocket disabled
  - avoid making HTTP-only sessions build prewarm prompt/tool state that
  cannot produce a reusable websocket session
  
  ## Why
  Recent macOS timing flakes were timing out while waiting for first-turn
  events in HTTP-only core tests. Startup prewarm is only useful for
  websocket-capable providers, but it was scheduled for every session. For
  HTTP-only test providers this added unnecessary async startup work
  before the regular turn could reach the mocked response flow.
  
  ## Testing
  - bazel test //codex-rs/core:core-all-test
  --test_filter=suite::auto_review::remote_model_override_uses_catalog_model_for_strict_auto_review
  --test_output=errors
  - bazel test //codex-rs/core:core-all-test
  --test_filter=suite::request_permissions_tool::approved_folder_write_request_permissions_unblocks_later_apply_patch
  --test_output=errors

  jif · 2026-06-02 17:27:30 +02:00
  859dbe2761
• [app-server][core] Add connector-level Guardian reviewer overrides (#25167)

  Context: https://openai.slack.com/archives/C0B4JAF0Q2C/p1779912328647229
  
  ```
  approvals_reviewer = "auto_review"
  
  [apps.connector_5f3c8c41a1e54ad7a76272c89e2554fa]
  enabled = true
  approvals_reviewer = "user"
  default_tools_approval_mode = "prompt"
  ```
  
  <img width="230" height="84" alt="Screenshot 2026-05-31 at 11 56 34 AM"
  src="https://github.com/user-attachments/assets/e319f8f7-0983-42a7-98cd-3302732fa406"
  />
  
  <img width="841" height="233" alt="Screenshot 2026-05-31 at 11 52 42 AM"
  src="https://github.com/user-attachments/assets/7ac76645-4e90-4d00-8242-f031146a22a5"
  />
  
  -------
  
  ```
  approvals_reviewer = "user"
  
  [apps.connector_5f3c8c41a1e54ad7a76272c89e2554fa]
  enabled = true
  approvals_reviewer = "auto_review"
  default_tools_approval_mode = "prompt"
  ```
  <img width="195" height="83" alt="Screenshot 2026-05-31 at 12 02 27 PM"
  src="https://github.com/user-attachments/assets/3d374dc8-8aa2-466f-a13f-e4ed8567aa2e"
  />
  <img width="771" height="207" alt="Screenshot 2026-05-31 at 12 05 42 PM"
  src="https://github.com/user-attachments/assets/105c2575-68d6-4ca6-8e69-dc8c82da36a2"
  />
  
  
  
  ## Summary
  - add `apps.<connector_id>.approvals_reviewer` to override Guardian or
  user review routing per connected app
  - apply overrides across direct app MCP calls, delegated MCP prompts,
  and app-server MCP elicitation review while preserving global behavior
  for non-app MCP servers
  - expose and document the config through app-server v2 and generated
  schemas, while honoring global managed reviewer requirements
  
  ---------
  
  Co-authored-by: jif-oai <jif@openai.com>

  Alex Zamoshchin · 2026-06-02 17:04:11 +02:00
  4d80d808b4
• [codex] Use git CLI for Cargo fetches across Rust workflows (#25775)

  ## Why
  Cargo's libgit2 transport has intermittently failed while fetching git
  dependencies with nested submodules.
  [#25644](https://github.com/openai/codex/pull/25644) applied
  `CARGO_NET_GIT_FETCH_WITH_CLI=true` to the main Rust release build after
  macOS SecureTransport/libgit2 failures while cloning `libwebrtc`'s
  nested `libyuv` submodule. Similar flakes can affect other Cargo-bearing
  Rust jobs.
  
  ## What changed
  Configure `CARGO_NET_GIT_FETCH_WITH_CLI=true` at workflow scope for the
  remaining Cargo-bearing Rust workflows:
  
  - fast Rust CI and `cargo-deny`
  - reusable Windows and argument-comment-lint release workflows
  - `rusty-v8-release` and `v8-canary` Cargo builds and smoke tests
  
  The full Rust CI, reusable nextest workflow, and primary Rust release
  build already had the override. Bazel-only workflows are unchanged
  because they use a different dependency fetch path.
  
  ## Validation
  - Parsed all `.github/workflows/*.yml` files as YAML.
  - Scanned Cargo-bearing workflows to confirm they configure
  `CARGO_NET_GIT_FETCH_WITH_CLI`.

  Adam Perry @ OpenAI · 2026-06-02 07:39:41 -07:00
  c097ad3e9e
• Run Codex async main on a sized stack (#25847)

  ## Why
  
  `Runtime::block_on` executes the top-level future on the caller's OS
  thread, not on one of Tokio's worker threads. That matters for the
  interactive CLI because the Tokio runtime already configures larger
  worker stacks, while the process main thread can still have a smaller
  platform default stack.
  
  This showed up as a `/clear` crash on macOS: starting a fresh TUI thread
  reloads config, and the stack-heavy TOML deserialization path can
  overflow before the new session is actually started.
  
  ## What Changed
  
  - Run the regular `arg0_dispatch_or_else` async entrypoint on a named
  `codex-main` thread.
  - Give that thread the same `TOKIO_WORKER_STACK_SIZE_BYTES` stack budget
  already used for Tokio worker threads.
  - Keep `Arg0DispatchPaths` and the arg0 alias guard lifetime behavior
  the same.
  - Resume panics from the spawned main thread so panic behavior is
  preserved.
  
  ## Verification
  
  - `cargo check -p codex-cli` currently fails because the top-level
  CLI/TUI future is not `Send` under the new thread boundary.

  jif · 2026-06-02 16:34:48 +02:00
  3766941161
• flake: Keep plugin test homes alive (#25857)

  ## Summary
  
  Keep the full `TestCodex` harness alive in plugin integration tests
  instead of returning only the `CodexThread`.
  
  ## Why
  
  The helper was moving a temporary `codex_home` into `TestCodex`, then
  immediately dropping the harness and returning only the thread. For
  plugin MCP tests, the MCP server cwd is inside that temporary home. If
  the temp directory is removed while MCP startup is still racing, the
  server launch can fail with `No such file or directory`.
  
  Keeping the harness in scope keeps the temp home alive for the test
  duration and removes the lifetime race behind the recent
  `explicit_plugin_mentions_inject_plugin_guidance` flake.
  
  ## Validation
  
  - `just fmt`
  - `just test -p codex-core
  explicit_plugin_mentions_inject_plugin_guidance`

  jif · 2026-06-02 16:21:22 +02:00
  b9af5d1234
• Reduce stack pressure in session startup and config rebuilds (#25844)

  ## Why
  
  `/clear` starts a fresh thread with `InitialHistory::Cleared`, which
  re-enters the thread/session startup path. That path now builds large
  async futures through `ThreadManagerState::spawn_thread_with_source`,
  `Codex::spawn`, and `Session::new`. Separately, TUI config rebuilds for
  cwd and permission-profile changes build a similarly heavy
  `ConfigBuilder::build()` future inside the app task. In debug and Bazel
  runs, those call chains can put enough state on the caller stack to
  abort before startup or config refresh completes.
  
  This change keeps the behavior the same while moving the heaviest future
  frames off the caller stack.
  
  ## What changed
  
  - Box `Codex::spawn(...)` in `codex-rs/core/src/thread_manager.rs`
  before awaiting it from `spawn_thread_with_source`.
  - Box `Session::new(...)` in `codex-rs/core/src/session/mod.rs` before
  awaiting it from `Codex::spawn_internal`.
  - Route `ConfigBuilder::build()` through a small `tokio::spawn` helper
  in `codex-rs/tui/src/app/config_persistence.rs` so cwd and
  permission-profile config rebuilds run on a runtime worker stack while
  preserving error context.
  
  ## Verification
  
  CI is running on the PR.
  
  No new targeted tests were added. This is a mechanical stack-pressure
  reduction that keeps the existing behavior and error propagation intact.

  jif-oai · 2026-06-02 15:42:47 +02:00
  1dd731305a
• Test runtime selector before first turn (#25724)

  Stack split from #25708. Original PR intentionally left open. This fifth
  PR adds coverage that a remotely selected multi-agent runtime is applied
  when the model is selected before the first turn.

  jif-oai · 2026-06-02 15:01:10 +02:00
  33273e4258
• Test remote multi-agent runtime selector override (#25723)

  Stack split from #25708. Original PR intentionally left open. This
  fourth PR adds coverage that remote model multi-agent runtime selectors
  override local feature flag defaults.

  jif-oai · 2026-06-02 14:48:13 +02:00
  66991c949f
• fix: main oops (#25840)

  Fix main, comment is self-explainatory

  jif-oai · 2026-06-02 14:48:04 +02:00
  06e9a33d09
• session: keep startup prewarm aligned with resolved multi-agent runtime (#25841)

  ## Why
  
  Follow-up to #25722. Startup prewarm builds a preview `TurnContext`
  before the first real turn so it can precompute the initial prompt and
  tool surface. After the per-thread runtime work landed, that preview
  path still recomputed multi-agent mode from `model_info` and feature
  defaults instead of reusing the runtime the session had already resolved
  from persisted metadata or inheritance.
  
  That could leave the prewarmed session primed for a different
  multi-agent mode than the first real turn, which is especially risky
  because collaboration tool exposure depends on
  `turn_context.multi_agent_version`.
  
  ## What changed
  
  - In the `TurnMultiAgentRuntime::Preview` path, prefer
  `Session::multi_agent_version()` when it is already known.
  - Only fall back to `model_info.multi_agent_version` and feature
  defaults when the session has not resolved a runtime yet.
  - Keep preview mode read-only: this still avoids storing a runtime
  during startup prewarm.
  
  ## Testing
  
  - Not run (small runtime-selection follow-up)

  jif-oai · 2026-06-02 14:35:26 +02:00
  3cf6f08da5
• Resolve per-thread multi-agent runtime (#25722)

  Stack split from #25708. Original PR intentionally left open. This third
  PR resolves the effective per-thread multi-agent runtime from persisted
  metadata, inherited runtime, and current model selection.

  jif-oai · 2026-06-02 14:31:00 +02:00
  bf9fd885b2
• Persist multi-agent runtime metadata (#25721)

  Stack split from #25708. Original PR intentionally left open. This
  second PR persists multi-agent runtime metadata through thread creation,
  rollout recording, and thread storage.

  jif-oai · 2026-06-02 13:05:20 +02:00
  0c5ccd18ab
• Add multi-agent runtime metadata types (#25720)

  Stack split from #25708. Original PR intentionally left open. This first
  PR adds the multi-agent runtime metadata types and catalog plumbing used
  by the rest of the stack.

  jif-oai · 2026-06-02 12:10:14 +02:00
  3f1fb7ed8b
• feat: reuse compressed rollout search snippets (#25814)

  ## Summary
  - teach rollout search to return precomputed snippets for compressed
  rollouts
  - reuse those snippets in local thread search instead of reopening
  matching compressed files
  - keep the no-`rg` fallback single-pass and add regression coverage for
  the compressed path
  
  ## Why
  `thread/search` currently decodes matching compressed rollouts twice:
  once to discover the matching path and again to extract the snippet
  shown in results. That defeats a meaningful part of the compressed-read
  optimization work.
  
  ## Impact
  Compressed rollout hits now pay one decode pass on the search path while
  plain `.jsonl` hits keep the existing ripgrep-driven flow.
  
  ## Validation
  - `just test -p codex-rollout`
  - `just test -p codex-thread-store`
  - `just fix -p codex-rollout`
  - `just fix -p codex-thread-store`
  - `just fmt`

  jif-oai · 2026-06-02 11:32:36 +02:00
  45912a6dc6
• [codex] Validate plugin skill base names (#25782)

  ## Summary
  
  - Validate skill base name length before plugin namespacing.
  - Bound the composed `plugin:skill` qualified name to 128 characters.
  - Keep plugin skill runtime names in the existing `plugin:skill` form.
  - Add regression tests for the max qualified-name boundary and rejection
  path.
  
  ## Root Cause
  
  Plugin skills are represented as `plugin_name:skill_name`, but the
  loader previously applied the 64-character skill name limit after adding
  the plugin namespace. Moving that check to the base name fixes valid
  plugin skills with longer namespaces, and the separate 128-character
  qualified-name limit keeps model-visible skill names bounded.
  
  ## Validation
  
  - `just fmt`
  - `just test -p codex-core-skills plugin_skill_name_length_limit`
  - `git diff --check`

  xl-openai · 2026-06-02 06:33:02 +00:00
  67b805fc11
• [codex] Move plugin discoverable logic into core-plugins (#25783)

  ## Summary
  - Move plugin discoverable recommendation filtering from `codex-core`
  into `codex-core-plugins` behind `ToolSuggestPluginDiscoveryInput`.
  - Keep `codex-core` as a thin adapter from `Config` to the core-plugins
  API and back to `DiscoverablePluginInfo`.
  - Keep the existing discoverable allowlist private to the core-plugins
  implementation.
  
  ## Validation
  - `just fmt`
  - `just test -p codex-core list_tool_suggest_discoverable_plugins`
  - `git diff --check`
  - Read-only subagent review: no findings

  xl-openai · 2026-06-01 23:25:37 -07:00
  07f04cc3c7
• [codex] Cache remote plugin catalog for suggestions (#25457)

  ## Summary
  - cache the global remote plugin catalog when remote plugin listing runs
  and warm it during startup
  - use the cached remote catalog in plugin install recommendations with
  canonical `plugin@openai-curated-remote` ids
  - reuse the session `PluginsManager` for plugin recommendations so
  remote cache state is visible on the recommend path
  - skip core installed-state verification for remote plugin install
  suggestions while leaving local plugin and connector verification
  unchanged
  
  ## Testing
  - `just fmt`
  - `git diff --check`
  - `cargo test -p codex-core
  list_tool_suggest_discoverable_plugins_includes_cached_remote_global_plugins`
  - `cargo test -p codex-core
  remote_plugin_install_suggestions_skip_core_installed_verification`
  - `cargo test -p codex-app-server
  plugin_list_includes_remote_marketplaces_when_remote_plugin_enabled`
  
  Earlier focused checks during the same branch: codex-tools TUI filter
  test, request_plugin_install tests, and codex-app-server build.

  xl-openai · 2026-06-01 22:10:52 -07:00
  f2b725102b
• [codex] Add plugin list JSON output (#25330)

  ## Summary
  - add `--json` output to `codex plugin list` with `installed` and
  `available` arrays
  - add `--available` for JSON output only; using it without `--json` is
  rejected
  - keep the existing non-JSON table output unchanged
  - add CLI coverage for JSON installed/available output and the
  `--available`/`--json` requirement
  
  ## Validation
  - `just test -p codex-cli plugin_list`
  - `just fix -p codex-cli`
  - `git diff --check`
  
  Note: `just fmt` ran Rust formatting first, then failed in the Python
  ruff step because `openai-codex-cli-bin==0.132.0` has no wheel for this
  Linux platform.

  xl-openai · 2026-06-01 21:27:06 -07:00
  cb63ee7f5d
• 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
• Move code review rules into AGENTS (#25738)

  ## Why
  Codex Review now supports repository-specific review rules in AGENTS.md.
  Adding the review prompts there makes the guidance available as
  repository review rules next to the code it governs while keeping the
  existing local review skills intact.
  
  ## What changed
  - Added a `## Code Review Rules` section to `AGENTS.md` with the
  existing review prompts for model context, breaking changes, test
  authoring, and change size.
  - Preserved the existing `.codex/skills/code-review*` skill files.
  
  ## Verification
  - `git diff --check origin/main...HEAD`

  pakrym-oai · 2026-06-02 01:41:04 +00:00
  c955f73078
• [codex] Add comprehensive root formatting check (#25683)

  ## Why
  
  The root formatting entrypoints could drift: `just fmt` did not format
  the Justfile itself, and the CI-facing check recipe only checked Python
  scripts instead of matching everything formatted by `just fmt`.
  
  ## What changed
  
  - Add a shared cross-platform Python formatter driver used by both `just
  fmt` and `just fmt-check`.
  - Run Justfile, Rust, Python SDK, and internal-script formatter groups
  concurrently while buffering each formatter group's output until it
  finishes.
  - Log formatter starts immediately, then print each formatter group's
  labeled output when it completes.
  - Keep the SDK lint-fix and Ruff formatting passes ordered, with source
  comments explaining their distinct roles and the check-mode equivalents.
  - Run Ruff through shared `uv run --no-sync --with ruff` overlays so
  formatting works on clean glibc Linux checkouts without installing the
  platform-specific SDK runtime wheel.
  - Show `fmt-check` help text in `just -l` and simplify CI to call the
  shared driver through `just fmt-check`.
  - Pin the general CI workflow to `just@1.51.0` so its formatter agrees
  with the checked-in Justfile.
  - Add regression coverage for the thin Just recipes and the driver's
  formatter graph.
  
  ## Validation
  
  - `just fmt`
  - `just fmt-check`
  - `python3 -m pytest
  sdk/python/tests/test_artifact_workflow_and_binaries.py -k 'root_fmt or
  root_format' -q`
  - `pnpm run format`
  - `git diff --check`
  - `just -l | rg -n '^    fmt|fmt-check'`
  - `uvx --from uv==0.7.22 uv run --frozen --project sdk/python --no-sync
  --with ruff ruff check --diff sdk/python`

  Adam Perry @ OpenAI · 2026-06-02 01:20:25 +00:00
  747f1003dd
• feat(remote-control): add pairing start (#25675)

  ## Why
  
  Remote control enrollment authorizes a desktop server, but app-server v2
  did not expose the follow-up pairing operation needed to mint a
  short-lived controller pairing artifact from that enrolled server.
  Clients need a narrow RPC that starts pairing without exposing the
  backend `serverId` or conflating pairing with websocket connection
  state.
  
  Issue: N/A; internal remote-control pairing API change.
  
  ## What Changed
  
  Added experimental app-server v2 `remoteControl/pairing/start` with
  `manualCode` input and `pairingCode`, nullable `manualPairingCode`,
  `environmentId`, and Unix-seconds `expiresAt` output. The method
  serializes under its own `global("remote-control-pairing")` scope and is
  documented in `app-server/README.md`.
  
  Extended the remote-control transport with private `/server/pair`
  request/response types and normalized `pair_url` handling. Pairing uses
  the current enrolled server bearer, refreshes that bearer when needed,
  keeps backend `server_id` private, validates returned `server_id` and
  `environment_id` against the current enrollment, and preserves backend
  status/header/body context for failures and malformed responses.
  
  Wired the request through `RemoteControlRequestProcessor` and
  `MessageProcessor`, mapping unavailable/disabled pairing to
  `invalid_request` and backend failures to internal errors.
  
  ## Verification
  
  - `just test -p codex-app-server-transport`
  - `just test -p codex-app-server
  remote_control_pairing_start_returns_pairing_artifacts`

  Anton Panasenko · 2026-06-02 01:05:50 +00:00
  0002316687
• Handle invalid plugin skills manifest field (#25717)

  ## Summary
  - Treat invalid `plugin.json` `skills` shapes as a field-level warning
  instead of rejecting the whole manifest
  - Keep valid string path behavior unchanged and continue falling back to
  the default `skills/` root
  - Add regression coverage for array-shaped `skills`
  
  ## Tests
  - `just fmt`
  - `cargo test -p codex-core-plugins`

  xli-oai · 2026-06-01 17:19:34 -07:00
  1ad0d7aa4b
• Move cloud requirements crate to cloud config (#24621)

  ## Summary
  
  - Moves the existing `codex-cloud-requirements` crate to
  `codex-cloud-config`.
  - Updates workspace dependencies and imports to the new crate name.
  - Intentionally keeps runtime behavior unchanged: this still fetches the
  legacy cloud requirements endpoint.
  
  ## Details
  
  This PR exists to make the lineage obvious before the bundle migration.
  GitHub should show the old `codex-rs/cloud-requirements/src/lib.rs`
  implementation as moved to `codex-rs/cloud-config/src/lib.rs`, rather
  than as unrelated new code.
  
  The follow-up PR adapts this moved crate to the new config bundle API
  and switches runtime consumers over.

  joeflorencio-openai · 2026-06-01 16:43:52 -07:00
  0b3a6f7185
• app-server: remove experimental persist_extended_history bool flag (#25712)

  ## Summary
  
  Remove the dead experimental `persistExtendedHistory` app-server flag
  and collapse rollout persistence to the single policy app-server already
  used.
  
  ## What Changed
  
  - Removed `persistExtendedHistory` from v2 thread start/resume/fork
  params and deleted its deprecation notice path.
  - Removed the persistence-mode enums and plumbing through core, rollout,
  and thread-store.
  - Made rollout filtering mode-free, keeping the existing limited
  persisted-history behavior.
  
  ## Test Plan
  
  - `just write-app-server-schema`
  - `cargo nextest run --no-fail-fast -p codex-app-server-protocol
  schema_fixtures`
  - `cargo nextest run --no-fail-fast -p codex-app-server
  thread_shell_command_history_responses_exclude_persisted_command_executions`
  - `cargo nextest run --no-fail-fast -p codex-rollout -p
  codex-thread-store`
  - final `rg` for removed flag/type names

  Owen Lin · 2026-06-01 23:33:42 +00:00
  11e0f3d3ae
• Wire managed MITM CA trust into child env (#22668)

  ## Stack
  1. Parent PR: #18240 uses named MITM permissions config.
  2. This PR wires managed MITM CA trust into spawned child processes.
  
  ## Why
  When Codex terminates HTTPS for limited mode or MITM hooks, child HTTPS
  clients need to trust Codex's managed MITM CA. Exporting proxy URLs
  alone is not enough, but blindly replacing user CA settings would be
  wrong: it can break custom enterprise/test roots, leak unreadable CA
  files into generated bundles, or make the child env disagree with its
  sandbox policy.
  
  ## Summary
  1. Build immutable managed CA bundles under `$CODEX_HOME/proxy` that
  include native roots, the managed MITM CA, and only inherited or
  command-scoped CA bundles the child is allowed to read.
  2. Export curated CA env vars alongside managed proxy env vars while
  preserving user CA override semantics, including nested Codex
  `SSL_CERT_FILE` precedence.
  3. Thread generated CA bundle paths into child sandbox readable roots,
  including debug sandbox execution, so the exported env vars work inside
  sandboxed commands.
  4. Remove only Codex-generated MITM CA bundle env when a child
  intentionally drops managed proxying for escalation or no-proxy retry.
  5. Document the managed CA bundle behavior and cover env injection,
  per-child bundle generation, sandbox readable roots, and no-proxy
  cleanup in tests.
  
  ## Validation
  1. Ran `just test -p codex-network-proxy`.
  2. Ran `just test -p codex-protocol`.
  3. Ran `just fix -p codex-network-proxy -p codex-protocol`.
  4. Tried focused `codex-core` validation, but the crate currently fails
  to compile in `core/tests/suite/guardian_review.rs` because an existing
  `Op::UserInput` initializer is missing `additional_context`.
  
  ---------
  
  Co-authored-by: Eva Wong <evawong@openai.com>

  Winston Howes · 2026-06-01 23:23:59 +00:00
  bca18cba40
• Reject directory rollout paths for pathless side chats (#25661)

  ## Why
  
  Fixes openai/codex#20944.
  
  Desktop side chats are intentionally ephemeral and pathless. They can
  still accept live turns while loaded, but after a reload there is no
  persisted rollout to resume. In the reported failure mode, Desktop could
  send `$CODEX_HOME` as the resume/fork path for one of these pathless
  side chats.
  
  `thread/resume` and `thread/fork` prefer an explicit `path` over
  `threadId`, and rollout path lookup only checked that a candidate
  existed. That let `$CODEX_HOME` pass as a rollout path, so the later
  rollout reader tried to open a directory and surfaced the low-level `Is
  a directory` error.
  
  ## What Changed
  
  - Reject explicit rollout paths that resolve to a directory or other
  non-file before attempting to read rollout history.
  - Make `codex_rollout::existing_rollout_path` return only plain or
  compressed rollout candidates that are actual files.
  - Add an app-server regression test that creates an ephemeral fork, runs
  a turn while the side thread is loaded, simulates reload, then verifies
  both `thread/resume` and `thread/fork` reject `$CODEX_HOME` with `path
  is a directory` instead of the OS-level directory-read error.
  - Rebase over the `TestAppServer` rename and update the remaining stale
  test harness call sites to use `TestAppServer` with `app_server` local
  variables.
  
  Relevant code:
  
  - `thread-store/src/local/read_thread.rs` validates explicit rollout
  paths before rollout reading:
  https://github.com/openai/codex/blob/25b47c8f425d351aaba4baa955a8092064a1707b/codex-rs/thread-store/src/local/read_thread.rs#L146-L165
  - `rollout/src/compression.rs` now requires file metadata for plain and
  compressed rollout candidates:
  https://github.com/openai/codex/blob/25b47c8f425d351aaba4baa955a8092064a1707b/codex-rs/rollout/src/compression.rs#L940-L950
  - The repro test covers the pathless ephemeral side-chat reload case:
  https://github.com/openai/codex/blob/25b47c8f425d351aaba4baa955a8092064a1707b/codex-rs/app-server/tests/suite/v2/thread_fork.rs#L774-L886
  
  ## Verification
  
  - `just test -p codex-app-server
  pathless_ephemeral_thread_rejects_codex_home_path_after_reload`

  Michael Bolin · 2026-06-01 16:02:06 -07:00
  b89bf1ef47
• [codex] Publish release symbol artifacts (#25649)

  ## Why
  
  Production Codex binaries are stripped for distribution, which leaves
  crashes and samples from released builds without the symbols needed for
  useful stack traces. Publish symbols as separate release assets so
  production artifacts stay small while released builds remain
  symbolicateable.
  
  ## What changed
  
  - Add `.github/scripts/archive-release-symbols-and-strip-binaries.sh` to
  package platform-native symbols into `codex-symbols-<artifact>.tar.gz`
  assets while stripping the corresponding Unix binaries before signing.
  - Build release binaries with full debug information before producing
  distribution artifacts.
  - Publish macOS `.dSYM` bundles, Linux `.debug` files with
  `.gnu_debuglink`, and Windows `.pdb` files.
  - Strip Linux `bwrap` before computing its packaged-resource digest, but
  intentionally omit `bwrap` from symbol archives.
  - Preserve symbols artifacts in the unsigned macOS promotion flow.
  
  ## Verification
  
  - Ran `shellcheck` and `bash -n` on
  `.github/scripts/archive-release-symbols-and-strip-binaries.sh`.
  - Parsed the modified workflow YAML files and ran `git diff --check`.
  - Built a macOS release smoke binary and verified that the archived
  `.dSYM` contains DWARF application source information and has the same
  UUID as the stripped production binary.
  - Built Linux smoke binaries and verified that the symbol archive
  contains `codex.debug`, excludes `bwrap.debug`, leaves the expected
  `.gnu_debuglink` in `codex`, and does not mutate the separately stripped
  `bwrap` digest.
  - Staged a Windows smoke archive and verified that it contains the
  expected `.pdb` file.

  Jeremy Rose · 2026-06-01 15:49:54 -07:00
  75a08def98
• fix(tui): clarify footer shortcut overlay hints (#25625)

  ## Why
  
  The TUI shortcut overlay used static labels for `Tab` and `Ctrl+C`, even
  though both keys change behavior while a task is running. That made the
  visible help misleading: idle `Tab` submits rather than queues, and
  active-turn `Ctrl+C` interrupts rather than exits.
  
  Closes #25531.
  Closes #25564.
  
  ## What Changed
  
  - Pass task-running state into the shortcut overlay renderer.
  - Render `Tab` as `submit message` while idle and `queue message` while
  work is running.
  - Render `Ctrl+C` as `exit` while idle and `interrupt` while work is
  running.
  - Add snapshot coverage for the active-work shortcut overlay and update
  idle overlay snapshots.
  
  ## How to Test
  
  1. Start Codex and open the shortcut overlay with `?` while no task is
  running.
  2. Confirm the overlay shows `tab to submit message` and `ctrl + c to
  exit`.
  3. Start a task, then open or keep the shortcut overlay visible while
  work is running.
  4. Confirm the overlay shows `tab to queue message` and `ctrl + c to
  interrupt`.
  5. Type a follow-up prompt during active work and press `Tab`; confirm
  it queues rather than submitting immediately.
  
  Targeted tests:
  
  - `just test -p codex-tui footer_snapshots`
  - `just test -p codex-tui footer_mode_snapshots`
  
  ## Validation Notes
  
  `just test -p codex-tui` currently has two unrelated guardian
  feature-flag test failures on this base:
  
  -
  `app::tests::update_feature_flags_disabling_guardian_clears_manual_review_policy_without_history`
  -
  `app::tests::update_feature_flags_disabling_guardian_clears_review_policy_and_restores_default`
  
  `just argument-comment-lint codex-rs/tui/src/bottom_pane/footer.rs`
  could not run locally because the prebuilt wrapper requires `dotslash`;
  the touched Rust diff was manually inspected for opaque positional
  literals.

  Felipe Coury · 2026-06-01 19:41:22 -03:00
  4e540b1076
• Move tool search metadata onto ToolExecutor (#25684)

  Deferred tools need to be searchable even when they are not implemented
  inside `codex-core`. Extension-provided tools can be registered for
  later discovery, but the search metadata path was still owned by
  core-specific runtime hooks, which meant the shared `ToolExecutor`
  abstraction could not describe how a deferred extension tool should
  appear in `tool_search`.
  
  ## Changes
  
  - Move `ToolSearchEntry` and `ToolSearchInfo` into `codex-tools` and
  re-export them from the shared tools crate.
  - Add a default `ToolExecutor::search_info` implementation that derives
  loadable tool-search metadata from function and namespace specs.
  - Forward search metadata through extension adapters and exposure
  overrides while keeping custom search text/source metadata for dynamic,
  MCP, and multi-agent tools.
  - Remove the old core-local `tool_search_entry` module now that search
  metadata lives with the shared executor APIs.
  
  ## Testing
  
  - Added `deferred_extension_tools_are_discoverable_with_tool_search`
  coverage in `core/src/tools/spec_plan_tests.rs`.

  jif-oai · 2026-06-02 00:24:41 +02:00
  8d720feb69
• Fix stale TestAppServer rename in plugin_list test (#25705)

  ## Why
  
  #25701 renamed the app-server test harness to `TestAppServer`, but it
  raced with #25681, which added a new `plugin_list` test call site still
  using the old `McpProcess` name. Once both changes met on `main`,
  app-server test builds failed before running the suite because
  `McpProcess` no longer exists in that scope.
  
  This PR fixes that CI break by updating the remaining stale call site to
  the renamed helper.
  
  ## What Changed
  
  - Replaced the `McpProcess::new(...)` use in
  `codex-rs/app-server/tests/suite/v2/plugin_list.rs` with
  `TestAppServer::new(...)`.
  - Renamed the local variable from `mcp` to `app_server` at the same call
  site to match the helper rename.
  
  Relevant code:
  https://github.com/openai/codex/blob/aadd9c999b4e0789f7afb2b9b8cc43000bb47e86/codex-rs/app-server/tests/suite/v2/plugin_list.rs#L234-L246
  
  ## Verification
  
  Not run locally; this is a compile fix for the app-server test harness
  rename.

  Michael Bolin · 2026-06-01 15:14:03 -07:00
  8ee49a2f74
• [codex] enable parallel standalone web search calls (#25702)

  ## Summary
  - opt the extension-backed standalone `web.run` tool into parallel tool
  execution
  - update the existing extension registration test to assert that the
  tool advertises parallel-call support
  
  ## Why
  The standalone web-search API endpoint now supports parallel requests.
  The extension executor still inherited the shared serial default,
  causing multiple `web.run` calls to acquire the exclusive runtime lock.
  
  ## Impact
  Models that emit multiple standalone web-search calls can now execute
  them concurrently when model-level parallel tool calls are enabled.
  
  ## Validation
  - `just fmt`
  - `just test -p codex-web-search-extension`
  - `git diff --check origin/main...HEAD`

  sayan-oai · 2026-06-01 15:04:11 -07:00
  b3c4157034
• fix: rename McpServer to TestAppServer (#25701)

  This PR brought to you via VS Code rather than Codex...
  
  - opened `codex-rs/app-server/tests/common/mcp_process.rs`
  - put the cursor on `McpServer`
  - hit `F2` and renamed the symbol to `TestAppServer`
  - went to the file tree
  - hit enter and renamed `mcp_process.rs` to `test_app_server.rs`
  - ran **Save All Files** from the Command Palette
  - ran `just fmt`
  
  The End
  
  (Admittedly, most of the local variables for `TestAppServer` are still
  named `mcp`, though.)

  Michael Bolin · 2026-06-01 21:49:38 +00:00
  6536841d89
• fix: Deduplicate installed local and remote curated plugins (#25681)

  ## Summary
  - Deduplicate installed `openai-curated` and `openai-curated-remote`
  plugin conflicts by feature flag.
  - Prefer remote when remote plugins are enabled; otherwise prefer local,
  while preserving one-sided installs.
  
  ## Testing
  - `just fmt`
  - `git diff --check`
  - Targeted `just test` was blocked locally because `cargo-nextest` is
  not installed.

  xl-openai · 2026-06-01 14:27:18 -07:00
  6ae99fd35f
• Add Python version compatibility guidance (#25690)

  ## Why
  
  Python contributions in this repository should target the declared
  Python 3 runtime instead of carrying Python 2 compatibility patterns
  forward. When compatibility across Python 3 point releases matters,
  contributors need a consistent source of truth for the minimum supported
  version.
  
  ## What changed
  
  - Added Python development guidance to `AGENTS.md` stating that the
  repository uses Python 3+ and should not use the `__future__` module.
  - Documented that contributors should check the nearest `pyproject.toml`
  `requires-python` field when evaluating Python 3 point-release
  compatibility.
  
  ## Testing
  
  Not run (guidance-only change).

  Adam Perry @ OpenAI · 2026-06-01 14:05:54 -07:00
  433ac84102
• [codex] Generalize deferred nested tool guidance (#25689)

  ## Summary
  - describe omitted code-mode tools as deferred nested tools instead of
  MCP/app tools
  - update the prompt-description assertion to match
  
  ## Why
  Deferred dynamic tools are also callable through `tools` and
  discoverable in `ALL_TOOLS`, so the previous MCP/app-specific wording
  was too narrow.
  
  ## Validation
  - `just fmt`
  - `just test -p codex-code-mode`
  - `git diff --check`

  sayan-oai · 2026-06-01 21:01:30 +00:00
  f0e15b916f
• Add rollout compression histograms (#25680)

  ## Summary
  
  Stacked on #25679. Add histogram telemetry for rollout compression
  runtime, per-file compression time, byte sizes, and compression ratio.
  
  ## Changes
  
  - Emit `codex.rollout_compression.run.duration_ms` tagged by final run
  status.
  - Emit `codex.rollout_compression.file.duration_ms` tagged by file
  outcome.
  - Emit source and compressed byte histograms for compression
  candidates/results.
  - Emit `codex.rollout_compression.file.compression_ratio` for successful
  compressions, recorded as integer basis points.
  
  ## Validation
  
  - `just fmt`
  - `just test -p codex-rollout`
  - `just fix -p codex-rollout`

  jif-oai · 2026-06-01 22:54:25 +02:00
  7c285f9e9c
• [codex] document out-of-line test module convention (#25682)

  ## Why
  
  New unit test modules should follow one consistent layout so
  implementation files stay focused and test suites remain easy to locate,
  without creating cleanup churn in existing inline test modules.
  
  ## What changed
  
  - Added `AGENTS.md` guidance requiring new test modules to use separate
  sibling `*_tests.rs` files with an explicit `#[path = "..._tests.rs"]`
  attribute.
  - Clarified that existing inline `#[cfg(test)] mod tests { ... }`
  modules should not be moved solely to follow the new convention.
  
  ## Validation
  
  - Ran `git diff --check`.

  Adam Perry @ OpenAI · 2026-06-01 13:36:16 -07:00
  a29a5b0861
• Add rollout compression counters (#25679)

  ## Summary
  
  Add counter telemetry for the local rollout compression worker so we can
  see when it runs, why it skips, and how individual file/materialization
  paths resolve.
  
  ## Changes
  
  - Emit `codex.rollout_compression.run` with statuses for start,
  completion, failure, duplicate-run skip, and missing runtime skip.
  - Emit `codex.rollout_compression.file` outcomes for scanned,
  compressed, skipped, and failed compression candidates.
  - Emit `codex.rollout_compression.temp_cleanup` and
  `codex.rollout_compression.materialize` counters for cleanup and
  decompression paths.
  
  ## Validation
  
  - `just fmt`
  - `just test -p codex-rollout`
  - `just fix -p codex-rollout`

  jif-oai · 2026-06-01 22:26:32 +02:00
  9f4fac8ec4
• refactor: hide shell override for zsh fork unified exec (#24980)

  ## Why
  
  When unified exec is configured to launch through the zsh fork, local
  commands should not let the model override the shell binary with the
  `shell` parameter. The configured zsh fork is the mechanism that makes
  `execv(2)` interception reliable, so exposing `shell` for local zsh-fork
  execution would create a confusing API surface and undermine the
  composition.
  
  Remote environments are different: zsh-fork interception is local-only,
  so remote unified-exec calls must keep direct unified-exec behavior and
  still expose `shell` when a remote environment can be selected.
  
  ## What Changed
  
  - Taught the `exec_command` schema builder to omit the `shell` parameter
  when requested.
  - Hid `shell` from the unified-exec tool schema only when zsh-fork
  unified exec applies to all selectable environments.
  - Kept `shell` visible when any remote environment can be targeted,
  because those calls run through direct unified exec.
  - Made unified exec choose the effective shell mode per selected
  environment: local environments keep zsh-fork mode, remote environments
  use direct mode.
  - Left direct unified-exec behavior unchanged, including support for
  model-specified shells there.
  
  ## Verification
  
  - Added schema coverage showing `exec_command` can hide `shell`.
  - Added planner coverage showing zsh-fork unified exec hides `shell` for
  local-only execution while direct unified exec still exposes it.
  - Added planner coverage showing `shell` remains visible when a remote
  environment is available.
  - Added handler coverage showing remote environments use direct
  unified-exec shell mode instead of zsh-fork mode.
  - Ran the focused `codex-core` shell-parameter and zsh-fork tests.
  
  
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/24980).
  * #24982
  * #24981
  * __->__ #24980

  Michael Bolin · 2026-06-01 20:22:28 +00:00
  feb9eddc51
• feat: gate unified exec zsh fork composition (#24979)

  ## Why
  
  `shell_zsh_fork` and unified exec need to remain independently
  controllable for enterprise rollouts, but we also need a third mode that
  composes them. That composed mode is intended to preserve unified exec
  command lifecycle support while letting the zsh fork provide more
  accurate `execv(2)` interception.
  
  Enabling `unified_exec_zsh_fork` by itself is intentionally not
  sufficient. It is a composition gate, not a dependency-enabling
  shortcut:
  
  - `unified_exec` selects the PTY-backed unified exec tool.
  - `shell_zsh_fork` opts into the zsh fork backend.
  - `unified_exec_zsh_fork` only allows those two already-enabled modes to
  be composed so local zsh unified exec commands can launch through the
  zsh fork.
  
  This separation is deliberate. Enterprises and staged rollouts must be
  able to enable or disable unified exec and zsh-fork independently. If
  `unified_exec_zsh_fork` implied either dependency, then enabling one
  under-development composition flag would silently activate a shell
  backend that the configured feature set left disabled.
  
  This PR introduces only the configuration and planning gate for that
  composition. Existing `shell_zsh_fork` behavior continues to use the
  standalone shell tool unless the new composition feature is explicitly
  enabled alongside both dependencies.
  
  ## What Changed
  
  - Added the under-development feature flag `unified_exec_zsh_fork`.
  - Added `UnifiedExecFeatureMode` so the three input feature flags
  collapse into `Disabled`, `Direct`, or `ZshFork` mode before tool
  planning.
  - Updated tool selection so zsh-fork composition requires
  `unified_exec`, `shell_zsh_fork`, and `unified_exec_zsh_fork`.
  - Kept the existing standalone zsh-fork shell tool behavior when only
  `shell_zsh_fork` is enabled.
  - Updated config schema output for the new feature flag.
  
  ## Verification
  
  - Added feature and tool-config coverage for the new gate.
  - Added planner coverage proving `shell_zsh_fork` remains standalone
  until composition is explicitly enabled.
  - Ran focused tests for `codex-features`, `codex-tools`, and the
  affected `codex-core` planner case.
  
  
  
  
  
  ---
  [//]: # (BEGIN SAPLING FOOTER)
  Stack created with [Sapling](https://sapling-scm.com). Best reviewed
  with [ReviewStack](https://reviewstack.dev/openai/codex/pull/24979).
  * #24982
  * #24981
  * #24980
  * __->__ #24979

  Michael Bolin · 2026-06-01 13:01:36 -07:00
  d6748f741a
• fix: deflake zsh-fork approval test (#25669)

  Fixes this flake:
  https://github.com/openai/codex/actions/runs/26773809591/job/78919970410?pr=25659
  
  This test is about zsh-fork subcommand approval behavior, not workspace
  sandboxing, so it now runs with `DangerFullAccess` to avoid macOS
  sandbox setup failures before the second subcommand approval.

  jif-oai · 2026-06-01 21:55:44 +02:00
  009e6c4817
• exec-server: canonicalize bound filesystem paths (#25149)

  ## Summary
  - add executor filesystem canonicalization as a bound-path operation
  - route remote canonicalization through the exec-server filesystem RPC
  surface
  - keep path normalization attached to the filesystem that owns the path
  
  ## Stack
  - 2/5 in the skills path authority stack extracted from
  https://github.com/openai/codex/pull/25098
  - follows merged https://github.com/openai/codex/pull/25121
  
  ## Validation
  - `cd
  /Users/starr/code/codex-worktrees/pr-25098-restack-review-pr1b/codex-rs
  && just fmt`
  - Not run: tests/checks (not requested)
  - GitHub CI pending on rewritten head

  starr-openai · 2026-06-01 11:53:31 -07:00
  53ac02356e
• [codex-rs] auto-review model override (#23767)

  ## Why
  
  Guardian auto-review normally uses the provider-preferred review model
  when one is available. Some parent models need model-catalog metadata to
  select a different review model while keeping older `/models` payloads
  compatible when that metadata is absent.
  
  ## What changed
  
  - Added optional `ModelInfo::auto_review_model_override` metadata to the
  public model payload as a review-model slug.
  - Updated Guardian review model selection to prefer the catalog override
  when present, while preserving the existing provider preferred-model
  path and parent-model fallback when it is omitted.
  - Added focused Guardian coverage for override and no-override model
  selection.
  - Added an `auto_review` core integration suite test that loads override
  metadata from a remote model catalog path and asserts the strict
  auto-review `/responses` request uses the catalog-selected review model.
  - Updated existing `ModelInfo` fixtures and local catalog constructors
  for the new optional field.
  
  ## Validation
  
  - `cargo test -p codex-protocol
  model_info_defaults_availability_nux_to_none_when_omitted`
  - `cargo test -p codex-core guardian_review_uses_`
  - `cargo test -p codex-core
  remote_model_override_uses_catalog_model_for_strict_auto_review --test
  all`
  - `just fix -p codex-protocol`
  - `just fix -p codex-core`
  - `just fmt`
  - `git diff --check`

  Won Park · 2026-06-01 11:51:15 -07:00
  f1609d9fb6