7686 Commits

This Branch

This Branch

All Branches

• [codex] configure rollout budget reminder thresholds (#29423)

  ## Summary
  
  Instead of:
  
      reminder_interval_tokens = 65_536
  
  allow users to configure explicit remaining-token reminder thresholds:
  
  reminder_at_remaining_tokens = [65_536, 32_768, 16_384, 8_192, 4_096,
  2_048, 1_024, 512]
  
  ## Validation
  
  - CARGO_INCREMENTAL=0 just test -p codex-core rollout_budget: 9 passed
  - just fix -p codex-core
  - just fmt

  rka-oai · 2026-06-22 13:25:48 -07:00
  bd5bd953fb
• Allow ChatGPT accounts without email (#28991)

  # Summary
  
  Codex required every ChatGPT account to have an email address. A
  service-account personal access token can return valid account metadata
  without one, so PAT login failed while decoding the metadata response.
  
  This change makes email optional in the account metadata type that owns
  it and preserves that absence through authentication, provider account
  state, the app-server API, generated clients, and TUI bootstrap.
  Existing accounts with email addresses keep the same behavior.
  
  ## Behavior-changing call sites
  
  | Call site | Behavior after this change |
  | --- | --- |
  | `login/src/auth/personal_access_token.rs` | PAT metadata accepts a
  missing or null email and retains `None`. |
  | `agent-identity/src/lib.rs` | Agent Identity JWT claims accept an
  omitted email. |
  | `login/src/auth/storage.rs` and `login/src/auth/agent_identity.rs` |
  Stored and managed Agent Identity records carry `Option<String>`.
  Deserialization maps the legacy empty-string sentinel to `None`. |
  | `login/src/auth/manager.rs` | `get_account_email` returns the stored
  option, and managed identity bootstrap no longer converts `None` to an
  empty string. |
  | `model-provider/src/provider.rs` and `protocol/src/account.rs` | A
  ChatGPT provider account requires a plan type but may carry no email. |
  | `app-server-protocol/src/protocol/v2/account.rs` | `account/read`
  keeps the `email` field on the wire and returns `null` when the account
  has no email. Generated TypeScript and JSON schemas describe a required,
  nullable field. |
  | `sdk/python/src/openai_codex/generated/v2_all.py` | The generated
  Python `ChatgptAccount` model accepts `None` for email. |
  | `tui/src/app_server_session.rs` | Email-less ChatGPT accounts
  bootstrap normally, keep external feedback routing, omit account-email
  telemetry, and display the plan in account status. |
  
  ## Design decisions
  
  - Missing email remains `None` at every layer. The code never uses an
  empty string as a substitute.
  - The app-server response includes `"email": null` instead of omitting
  the field. Clients retain a stable response shape.
  - Plan type remains required for provider account state. This change
  relaxes only the email assumption.
  
  ## Testing
  
  Tests: affected test targets compile, scoped Clippy and formatting pass,
  a focused TUI snapshot covers plan-only account status, real
  before/after PAT login smoke covers metadata without email, app-server
  smoke covers `account/read` with `email: null`, and a regression smoke
  covers an existing email-bearing PAT. Unit tests run in CI.
  
  ## Evidence
  
  Visual smoke evidence will be attached here.

  efrazer-oai · 2026-06-22 13:19:40 -07:00
  5a67d898a5
• PAC 2 - Add shared auth system proxy contract (#26707)

  ## Summary
  
  Stacked on #26706.
  
  Adds the shared auth/system-proxy contract that later platform resolver
  PRs plug into. This PR moves Codex-owned auth and startup HTTP clients
  through a common route-aware boundary, but does not yet add Windows or
  macOS system proxy resolution.
  
  The default path remains unchanged when `respect_system_proxy` is absent
  or disabled.
  
  ## Implementation
  
  - Adds `codex-client/src/outbound_proxy.rs` with the shared
  route-selection model:
    - `OutboundProxyConfig`;
    - `ClientRouteClass`;
    - `RouteFailureClass`;
    - `build_reqwest_client_for_route`.
  - Preserves the existing reqwest/default-client behavior when no route
  config is supplied.
  - Uses the fixed MVP routing policy when route config is supplied:
  platform system/PAC/WPAD discovery, then explicit env proxy variables,
  then direct connection.
  - Keeps platform-specific system discovery behind the shared client
  boundary. This PR provides the contract and fallback behavior; later
  resolver PRs plug in Windows and macOS discovery.
  - Adds `login::AuthRouteConfig` so auth call sites depend on a small
  policy type instead of platform resolver details.
  - Maps the resolved `Config.respect_system_proxy` boolean into
  `AuthRouteConfig` for auth-owned clients.
  - Wires the route config through browser login, device-code login,
  access-token login, login status, logout/revoke, token refresh, API-key
  exchange, app-server account login, TUI/app startup, cloud-config
  bootstrap, cloud tasks, plugin auth, and exec startup config loading.
  
  ## End-user behavior
  
  - No behavior changes by default.
  - When `respect_system_proxy = true`, auth-owned clients opt into the
  shared route-aware client path.
  - On platforms without a resolver implementation in this PR, system
  discovery is unavailable and the route-aware path falls back to explicit
  env proxy handling, then direct connection.
  - Custom CA handling remains separate from proxy route selection and
  still runs through the shared client builder.
  - No proxy URLs, PAC contents, or resolved platform details are exposed
  through the public config surface introduced here.
  
  ## Tests
  
  Adds or updates coverage for:
  
  - preserving default auth-client fallback behavior when no route config
  is provided;
  - injected environment-proxy fallback without mutating process
  environment;
  - existing login-server E2E flows using explicit `auth_route_config:
  None` to guard unchanged default behavior;
  - updated auth manager, login, logout, cloud-config, startup, and
  plugin-auth call sites passing route config explicitly.

  canvrno-oai · 2026-06-22 13:03:11 -07:00
  1659c4a629
• core: remove unused permissions cwd plumbing (#29468)

  ## Why
  
  `compile_scoped_filesystem_pattern()` accepted a `_policy_cwd` parameter
  even though scoped glob compilation no longer uses the policy working
  directory. Keeping that unused argument forced the surrounding
  permissions compilation path to keep forwarding `policy_cwd` through
  call sites that did not need it, making the API look more dependent on
  cwd resolution than it is.
  
  ## What changed
  
  Removed the unused cwd parameter from
  `compile_scoped_filesystem_pattern()` and the callers that only
  forwarded it: `compile_filesystem_permission()`,
  `compile_permission_profile()`, and
  `compile_permission_profile_selection()`. Workspace root resolution
  still keeps `policy_cwd`, because that path still resolves relative
  roots against the active policy cwd.
  
  Relevant code:
  [`codex-rs/core/src/config/permissions.rs`](https://github.com/openai/codex/blob/b8b9816102e064dae4488ec130cf560f63c1ab78/codex-rs/core/src/config/permissions.rs#L346).
  
  ## Verification
  
  - `just test -p codex-core config::permissions`
  - `just test -p codex-core` was also run after building
  `test_stdio_server`; it passed the touched permissions coverage but
  still reported unrelated existing failures in `cli_stream` and shell
  snapshot tests.

  Michael Bolin · 2026-06-22 12:31:52 -07:00
  e48ab86693
• [codex] Start the guardian child session when parent session is started (#27982)

  ## Why
  
  The first auto-review currently creates its Guardian child session on
  demand, adding avoidable latency before the review can begin. Creating
  the ordinary Guardian child during parent-session initialization lets
  that child use the existing session startup WebSocket prewarm before the
  first escalation. This does not introduce a Guardian-specific prewarm
  mechanism.
  
  ## What changed
  
  - initialize the existing Guardian review-session manager owned by
  `Session` when a thread starts with auto-review enabled and an approval
  policy that routes to Guardian
  - use the standard Guardian child-session construction and the existing
  session startup WebSocket prewarm
  - preserve the existing reuse-key invalidation and lazy creation
  fallback when startup initialization fails or the effective review
  configuration changes
  - add an integration test that verifies normal root-session startup
  emits a Guardian `generate=false` prewarm request
  
  ## Benchmark
  
  I compared release builds against main. Each prompt first ran a
  non-escalated `sleep 3`, then requested an escalated marker command.
  
  | binary | count | avg Guardian duration | median Guardian duration |
  avg Guardian TTFT |
  |---|---:|---:|---:|---:|
  | origin-main | 10 | 4008.7 ms | 3949.5 ms | 3746.5 ms |
  | session-fix | 10 | 2865.0 ms | 2594.0 ms | 2492.7 ms |
  
  Guardian duration fell by 28.5% and Guardian TTFT fell by 33.5%. These
  measurements cover Guardian review latency; they do not measure parent
  thread-start latency.

  jgershen-oai · 2026-06-22 11:54:44 -07:00
  15f448d8b0
• [codex] Fix usage-limit reset copy and state (#28793)

  ## Why
  
  The reset flow introduced in #28154 still describes earned reset credits
  as "rate-limit resets" and uses generic reset-scope copy. It can also
  retain a stale available-credit count after redemption or an account
  change, leaving the reset action enabled after the last credit is used.
  
  This follow-up updates terminology only within that reset feature.
  Existing rate-limit wording elsewhere in the CLI and TUI is unchanged.
  
  ## What changed
  
  - Rename reset-specific `/usage` menu items, startup hints, and reset
  dialogs to "usage limit reset."
  - Describe monthly resets for Free, Go, and accounts that report a
  monthly usage window; otherwise describe the current 5-hour and weekly
  limits.
  - Recheck a cached zero balance when `/usage` is reopened, and refresh
  the balance after redemption so the final reset immediately disables the
  action.
  - Correlate async refresh results before updating snapshots and clear
  account-derived reset state, warnings, prompts, and status surfaces when
  the account changes.
  
  ## Validation
  
  - `just test -p codex-tui chatwidget::tests::usage` — 29 passed.
  - `just test -p codex-tui chatwidget::tests::status_command_tests` — 7
  passed.
  - Account-boundary prompt and plan-mode prompt regression tests passed.
  - `cargo insta pending-snapshots` from `codex-rs/tui` — no pending
  snapshots.\
  
  <img width="814" height="318" alt="image"
  src="https://github.com/user-attachments/assets/2a460e96-458b-4805-8d9f-c759382d21a4"
  />
  view for monthly
  <img width="905" height="243" alt="image"
  src="https://github.com/user-attachments/assets/179f88e3-08fb-4af5-8dc6-ce6a944ed681"
  />

  jay · 2026-06-22 18:45:41 +00:00
  5c0fbf3492
• [sdk/python] Stop advertising HTTP image URLs (#29464)

  ## Summary
  
  - use generated image data URLs in the Python SDK examples and notebook
  - document HTTP and HTTPS image URLs as deprecated and recommend
  `LocalImageInput`
  - replace the remote-URL integration test with data-URL coverage
  
  `ImageInput` remains available for data URLs. The SDK does not duplicate
  app-server URL validation.
  
  ## Testing
  
  - `uv run --frozen --no-sync ruff check --output-format=full .`
  - `uv run --frozen --no-sync ruff format --check .`
  - full Python SDK test suite with an isolated writable
  `CODEX_SQLITE_HOME` (119 passed, 38 skipped)

  rka-oai · 2026-06-22 11:34:14 -07:00
  20431d49a0
• core: rename metadata -> internal_chat_message_metadata_passthrough (#28968)

  ## Description
  This PR cuts Codex over from generic `ResponseItem.metadata` (introduced
  here: https://github.com/openai/codex/pull/28355) to
  `ResponseItem.internal_chat_message_metadata_passthrough`, which is the
  blessed path and has strongly-typed keys.
  
  For now we have to drop this MAv2 usage of `metadata`:
  https://github.com/openai/codex/pull/28561 until we figure out where
  that should live.

  Owen Lin · 2026-06-22 11:11:25 -07:00
  5b95745eae
• Report remote sandbox denials semantically (#29424)

  ## Why
  
  #29113 moved remote sandbox setup and enforcement to the exec server.
  That gives the executor ownership of the platform-specific work: a Linux
  executor chooses and runs a Linux sandbox even when the Codex
  orchestrator is running on macOS or Windows.
  
  It also means the orchestrator no longer knows which concrete sandbox
  the executor selected. When that sandbox blocks a remote command, the
  orchestrator currently sees only a failed process and can treat the
  denial as an ordinary command failure. The existing sandbox approval and
  retry path is then skipped.
  
  This PR lets the executor report one portable fact:
  
  > This command probably failed because the executor sandbox blocked it.
  
  The executor keeps its concrete sandbox type private. The protocol sends
  only the semantic result.
  
  ## Example
  
  Suppose a local macOS Codex session asks a Linux devbox to write outside
  the allowed workspace.
  
  Before this PR:
  
  ```text
  Linux sandbox blocks the write
      -> remote process exits with "Permission denied"
      -> local orchestrator sees an ordinary command failure
      -> the normal sandbox approval and retry path can be skipped
  ```
  
  With this PR:
  
  ```text
  Linux sandbox blocks the write
      -> executor reports sandboxDenied: true
      -> unified exec returns UnifiedExecError::SandboxDenied
      -> the existing approval prompt is shown
      -> an approved retry runs through the existing unsandboxed retry path
  ```
  
  ## What changes
  
  ### The executor remembers its selected sandbox
  
  The prepared remote process now retains the executor-selected
  `SandboxType`. This value never crosses the executor boundary.
  
  Commands started without a sandbox retain `SandboxType::None` and are
  never reported as sandbox denials.
  
  ### The executor uses the existing denial heuristic
  
  The existing local denial heuristic moves from `codex-core` into the
  shared `codex-sandboxing` crate.
  
  When a sandboxed remote process exits, the executor:
  
  1. waits the same short output grace period used by local unified exec;
  2. reads the output currently available in the existing retained output
  buffer;
  3. runs the existing heuristic using the exit code and common denial
  messages;
  4. stores the yes/no result before publishing the process exit.
  
  This deliberately matches the old local unified-exec behavior. It does
  not add a new streaming classifier, another output buffer, or stronger
  output-retention guarantees.
  
  ### The protocol reports a portable boolean
  
  `process/read` gains `sandboxDenied`:
  
  ```json
  {
    "exited": true,
    "exitCode": 1,
    "closed": false,
    "sandboxDenied": true
  }
  ```
  
  The field defaults to `false` when an older executor omits it. The
  response does not expose the executor sandbox implementation or
  executor-native paths.
  
  ### Unified exec uses the existing error path
  
  The exec-server client carries `sandboxDenied` into the unified process
  state. If it is true, unified exec returns the existing `SandboxDenied`
  error instead of trying to classify remote output using an
  orchestrator-side sandbox type.
  
  Remote process exit remains visible as soon as the process exits. This
  PR does not wait for stdout or stderr to close and does not change the
  existing process lifecycle.
  
  ## Scope
  
  This PR is intentionally limited to matching the existing local
  unified-exec behavior for the initial command execution path.
  
  It does not add:
  
  - incremental denial tracking across the full output stream;
  - new denial handling for commands completed later through
  `write_stdin`;
  - new guarantees for preserving the semantic flag during the narrow
  reconnect-recovery race.
  
  Those can be considered separately if the same behavior is added for
  local execution.
  
  ## Test coverage
  
  One remote end-to-end integration test covers the complete intended
  flow:
  
  ```text
  remote read-only sandbox
      -> denied write
      -> executor reports the denial
      -> Codex requests approval
      -> user approves
      -> retry succeeds on the remote executor
  ```
  
  Existing lifecycle coverage continues to verify that remote process exit
  is reported before late output streams close.

  jif · 2026-06-22 19:33:28 +02:00
  9f06cf1a09
• TUI Plugin Sharing 3 - render remote plugin catalog sections (#26703)

  ## Summary
  
  [#26701](https://github.com/openai/codex/pull/26701) added remote plugin
  identity support, [#26702](https://github.com/openai/codex/pull/26702)
  added remote-section fetching and state, and
  [#28768](https://github.com/openai/codex/pull/28768) extracted the
  catalog rendering module. This PR builds the product-facing `/plugins`
  catalog on that foundation so remote records appear as OpenAI Curated,
  Workspace, and Shared with me sections rather than backend marketplace
  implementation details.
  
  Plugin details remain read-only for sharing metadata. This PR does not
  add share-authoring actions or change the app-server protocol.
  
  ## Changes
  
  - Renders OpenAI Curated, Workspace, and Shared with me sections with
  loading, empty, and error states.
  - Preserves section selection and stable tab ordering as remote sections
  transition between fallback and populated states.
  - Shows OpenAI Curated loading only when the explicit vertical fallback
  request was issued.
  - Centralizes remote marketplace identity matching around the existing
  marketplace constants.
  - Uses product labels for remote marketplaces and identifies the
  personal marketplace as Local by its path.
  - Shows read-only source, authentication, version, and sharing metadata
  in plugin detail views.
  - Applies narrow display deduplication for local and remote records
  sharing a remote plugin ID:
    - installed records take precedence;
  - local mapped sources are preferred for details only when their
  installed state matches the selected record.
  - Returns from detail and confirmation views through the current plugin
  cache so newly loaded remote sections are not overwritten by an older
  captured response.
  - Keeps admin-disabled plugins view-only and labels default-installed
  plugins as Available by default.
  
  ## Tests
  
  New tests:
  
  - `plugins_popup_admin_disabled_available_plugin_has_view_only_hint`
  - `plugins_popup_remote_section_fallback_states_snapshot`
  -
  `plugins_popup_installed_remote_row_keeps_remote_detail_when_local_share_is_uninstalled`
  
  Updated existing plugin catalog tests and snapshots for product labels,
  detail metadata, personal-marketplace labeling, and stable tab ordering.
  
  Verification:
  
  - `cargo clippy -p codex-tui --all-targets -- -D warnings`
  
  ## Follow-ups
  
  - Local/remote duplicate normalization should eventually move into
  app-server. This PR intentionally keeps the compatibility behavior
  narrow and display-only.
  - PR5 will sanitize sensitive components before displaying Git source
  URLs.

  canvrno-oai · 2026-06-22 10:30:16 -07:00
  f6fa259312
• [codex] Centralize Plugin Analytics Metadata (#27102)

  This PR moves construction of `PluginTelemetryMetadata` from loader and
  model helpers into `PluginsManager`, which already owns installed plugin
  state and will eventually perform remote identity enrichment. The
  metadata type remains in `codex-plugin`, and serialized analytics events
  remain unchanged.
  
  ## Before
  
  ```mermaid
  flowchart LR
      subgraph Events["Analytics event paths"]
          direction TB
          Lifecycle["Local install / uninstall"]
          Config["Enable / disable"]
          Remote["Remote install"]
          Used["Plugin used"]
      end
  
      subgraph Construction["Metadata construction"]
          direction TB
          Loader["Loader telemetry helpers"]
          Summary["PluginCapabilitySummary::telemetry_metadata"]
          Override["Caller adds remote_plugin_id"]
      end
  
      Metadata["PluginTelemetryMetadata"]
  
      Lifecycle --> Loader
      Config --> Loader
      Remote --> Loader
      Loader -->|"local events"| Metadata
      Loader -->|"remote install"| Override
      Override --> Metadata
      Used --> Summary
      Summary --> Metadata
  ```
  
  Telemetry metadata was constructed through loader helpers, a
  capability-summary method, and a remote-install call-site override.
  
  ## After
  
  ```mermaid
  flowchart LR
      subgraph Events["Analytics event paths"]
          direction TB
          Lifecycle["Local install / uninstall"]
          Config["Enable / disable"]
          Remote["Remote install"]
          Used["Plugin used"]
      end
  
      Manager["PluginsManager — single construction owner"]
      Metadata["PluginTelemetryMetadata"]
  
      Lifecycle --> Manager
      Config --> Manager
      Remote -->|"authoritative remote ID"| Manager
      Used -->|"capability summary"| Manager
      Manager --> Metadata
  ```
  
  Every analytics path delegates metadata construction to
  `PluginsManager`. Remote install still supplies its authoritative
  backend ID explicitly.
  
  ## What Changes
  
  - Make loader code return a focused plugin capability summary instead of
  constructing analytics metadata.
  - Centralize immutable plugin telemetry metadata construction in
  `PluginsManager`.
  - Route local install/uninstall, remote install, enable/disable, and
  plugin-used emitters through the manager.
  - Preserve the current serialized analytics contract exactly.
  
  Normal metadata still has no remote override. Remote install continues
  to provide its authoritative backend ID explicitly, so the existing
  serializer continues reporting that ID through `plugin_id`.
  Snapshot-based enrichment is intentionally deferred to the final PR.
  
  ## Testing
  
  - `just test -p codex-core-plugins` (238 tests passed)
  - `just test -p codex-plugin` (3 tests passed)
  - Scoped Clippy/compile checks passed for `codex-plugin`,
  `codex-core-plugins`, `codex-app-server`, and `codex-core`.
  
  ## Split Overview
  
  ```text
  main
  ├── #27093  Debug analytics capture                 (merged)
  ├── #27099  Non-mutating plugin smoke               (merged)
  ├── #27100  Remote install/uninstall smoke          (merged)
  └── #27102  Plugin telemetry metadata refactor      ← you are here
      └── #27669  Persist remote plugin identity
  
  After #27102 and #27669 merge:
  └── Final PR: add explicit local and remote IDs to plugin analytics
  ```
  
  Review order and dependencies:
  
  1. [#27093 Add debug-only analytics event
  capture](https://github.com/openai/codex/pull/27093) (merged)
  2. [#27099 Add a plugin analytics smoke
  workflow](https://github.com/openai/codex/pull/27099) (merged)
  3. [#27100 Add a remote plugin analytics mutation smoke
  workflow](https://github.com/openai/codex/pull/27100) (merged)
  4. This metadata refactor, independent and based on `main`
  5. [#27669 Persist remote plugin
  identity](https://github.com/openai/codex/pull/27669), stacked on this
  PR
  6. Final remote-ID behavior PR, created after the prerequisites merge
  
  The original [#26281](https://github.com/openai/codex/pull/26281)
  remains open as the aggregate reference until the final replacement PR
  is published.

  jameswt-oai · 2026-06-22 10:27:23 -07:00
  44dbae90eb
• ci: restore custom Windows runner with hermetic LLVM 0.7.9 (#29143)

  The custom Windows argument-comment-lint job was temporarily moved to
  `windows-2022` in #28940 after hermetic LLVM source extraction failed on
  the newer runner. This takes the upstream extraction fix so the job can
  return to the intended custom runner.
  
  This upgrades `llvm` to `0.7.9` and `rules_cc` to `0.2.18`, refreshes
  the module lock, rebases the remaining Windows and custom libc++
  patches, drops the obsolete symlink-extraction workaround, and restores
  the `windows-x64` runner configuration.
  
  Validation:
  
  - Verified all LLVM patches apply cleanly against the `0.7.9` source.
  - Built `@llvm-project//compiler-rt:clang_rt.builtins.static`.

  Adam Perry @ OpenAI · 2026-06-22 17:26:30 +00:00
  c1f8b280b5
• remove flag for image preparation (#29429)

  ## What
  
  - make Fjord's centralized response-item image preparation unconditional
  for new and resumed history
  - have local user images and `view_image` outputs always defer decoding
  and resizing to that path
  - retain `resize_all_images` as an ignored, removed compatibility key
  for released clients
  - delete the flag-off producer paths and obsolete policy-specific tests
  
  ## Why
  
  Centralized preparation is now the intended image path. Keeping the
  runtime feature checks also kept two image-processing implementations
  alive and allowed client config to select the legacy behavior.
  
  This is a clean replacement for #28975, rebuilt from the latest `main`.
  
  ## How
  
  `prepare_response_items` now runs whenever items enter history and
  whenever persisted history is reconstructed. Producers emit deferred
  image data, so malformed images become the existing model-visible
  placeholder instead of failing the session at the producer.
  
  ## Test plan
  
  - `just fmt`
  - `just fix -p codex-core -p codex-features`
  - `just test -p codex-features` — 52 passed
  - focused affected `codex-core` set — 20 passed
  - `just test -p codex-core handle_accepts_explicit_high_detail` — 1
  passed
  - full `just test -p codex-core` attempt — 2,723 passed; 88 unrelated
  environment failures from read-only `~/.codex` SQLite state and
  unavailable integration helper binaries

  rka-oai · 2026-06-22 10:05:11 -07:00
  e79d72d75d
• Filter noisy targets from persistent logs (#29457)

  ## Why
  
  The local SQLite log sink currently enables TRACE for every target. This
  persists high-volume dependency logs bridged through `target=log` and
  duplicates OpenTelemetry mirror events in `codex_otel.log_only` and
  `codex_otel.trace_safe`.
  
  These records rapidly consume the per-partition log budget and cause
  unnecessary SQLite insert-and-prune churn.
  
  ## What changed
  
  - Keep TRACE persistence for other targets.
  - Exclude bridged `target=log` events from the SQLite sink.
  - Exclude the two `codex_otel` mirror targets from the SQLite sink.
  - Share the same filter between app-server and TUI.
  
  Remote OpenTelemetry export and metrics are unchanged.

  jif · 2026-06-22 18:17:04 +02:00
  e98d43ac37
• fix(core): restore thread_source in x-codex-turn-metadata (#29455)

  ## Description
  
  Restore `thread_source` in `x-codex-turn-metadata`.
  
  Inadvertently removed `thread_source` from `x-codex-turn-metadata` in
  https://github.com/openai/codex/pull/27122 - didn't realize it was a
  top-level thread app-server API field, not passed in
  `responsesapi_client_metadata`.
  
  This also reserves the key so `responsesapi_client_metadata` cannot
  override it.

  Owen Lin · 2026-06-22 09:05:27 -07:00
  8f8de7844f
• core: refresh environment context before sampling (#29073)

  ## Why
  
  Nonblocking environment snapshots allow a turn to reach the model while
  a remote environment is still starting. The initial context can describe
  that environment as still loading, but nothing currently refreshes the
  model-visible environment context when startup finishes during the same
  turn.
  
  This adds the first request-scoped reconciliation slice on top of
  #28683. It is gated by `DeferredExecutor` and intentionally updates only
  model-visible environment context; tools and other environment-derived
  state will migrate separately.
  
  ## What
  
  - Add a minimal `StepContext` containing the environment snapshot
  captured before each sampling request.
  - Render attached environments with their resolved shell and starting
  environments with `still loading`.
  - Track the latest environment state recorded in model history and
  append a bounded update only when it changes.
  - Seed that baseline from full initial context so ready-at-start
  environments are not duplicated.
  - Clear the in-memory baseline when history is rewritten so replacement
  history can be refreshed safely.
  
  ## Testing
  
  - `just test -p codex-core deferred_executor`
  - `just test -p codex-core
  environment_context_baseline_deduplicates_until_history_is_replaced`
  
  The integration coverage verifies that a pending environment reaches the
  first request, the ready state reaches the next request, later requests
  do not duplicate it, and ready-at-start environments remain
  single-injected.
  
  <details>
  <summary>Live verification</summary>
  
  - Connected to a real remote executor with startup deliberately delayed
  and forced three sampling requests in one turn.
  - Inspected the raw model inputs: request 1 showed the remote
  environment as `still loading`, request 2 appended its ready shell and
  cwd, and request 3 contained no duplicate ready update.
  - With the feature disabled, startup waited for the delayed executor and
  the first request contained only the ready environment.
  - With a synchronously ready environment and the feature enabled, the
  first request contained one environment context with no duplicate.
  - Executed `pwd` and read a marker file through the remote process
  runner; the command exited successfully and returned the remote cwd and
  marker contents.
  
  </details>

  sayan-oai · 2026-06-22 08:47:43 -07:00
  22886f21de
• Stop logging every Responses WebSocket event (#29432)

  ## Why
  
  Every successful Responses WebSocket event currently produces three
  local log records: the full payload at TRACE, an OpenTelemetry log
  event, and an OpenTelemetry trace event.
  
  On busy threads these records fill the 1,000-row log partition in
  seconds and cause continuous SQLite insert-and-prune churn.
  
  Related to
  https://openai.slack.com/archives/C095U48JNL9/p1782128972644209
  
  ## What changed
  
  - Stop logging each successful Responses WebSocket payload at TRACE.
  - Stop emitting `codex.websocket_event` as OpenTelemetry log and trace
  events.
  - Keep WebSocket event counters, duration metrics, response timing
  metrics, parsing, and error handling.

  jif · 2026-06-22 17:43:08 +02:00
  91e6da943b
• Add workspace messages app-server API (#29001)

  ## Summary
  
  - Add backend-client types and fetch support for active workspace
  messages.
  - Add the app-server v2 `account/workspaceMessages/read` method,
  generated schemas, and README documentation.
  - Delegate workspace-message eligibility to the Codex backend feature
  gate; map a backend 404 to `featureEnabled: false`.
  
  ## Testing
  
  - `just write-app-server-schema`
  - `just test -p codex-backend-client`
  - `just test -p codex-app-server-protocol`
  - `just test -p codex-app-server workspace_messages`
  - `just fix -p codex-backend-client -p codex-app-server-protocol -p
  codex-app-server`
  - `just fmt`
  
  ## Stack
  
  - Base PR for #28232, which adds the TUI status-line integration.

  xli-oai · 2026-06-22 04:25:07 -07:00
  21d36296f1
• Apply sandbox intent inside remote exec servers (#29113)

  ## Why
  
  PR #29108 lets the orchestrator send sandbox intent with `process/start`
  without wrapping the command for its own operating system.
  
  This PR completes that boundary by making the executor interpret and
  enforce the intent using its own filesystem paths and sandbox
  implementation.
  
  For example, a macOS TUI targeting a Linux devbox sends `/bin/bash -lc
  pwd`. The Linux executor turns that into its own `codex-linux-sandbox
  ... /bin/bash -lc pwd` launch.
  
  ## What changes
  
  - Keep `process/start` unchanged when no sandbox intent is present.
  - Convert sandbox `PathUri` values into native paths on the executor.
  - Bind symbolic `:workspace_roots` permissions to the executor's native
  sandbox cwd.
  - Select the sandbox implementation on the executor and wrap the
  original command immediately before spawning it.
  - Reject sandbox-required execution before spawning when the executor
  cannot enforce the intent.
  - Pass exec-server runtime paths into process creation so Linux can
  locate `codex-linux-sandbox`.
  
  The boundary is therefore:
  
  ```text
  orchestrator                         executor
  original argv + sandbox intent  ->  select and enforce local sandbox
  ```
  
  This PR intentionally treats a denied remote command as an ordinary
  command failure. Draft follow-up #29424 carries a semantic
  `sandboxDenied` result back to unified exec for the existing approval
  and retry flow.
  
  ## Platform scope
  
  Linux and macOS use their existing direct-spawn sandbox transforms.
  
  Windows sandboxed remote process launch is intentionally unsupported in
  this PR. The current Windows direct-spawn wrapper does not correctly
  preserve arbitrary argv, TTY behavior, or pass the full child
  environment out of band. The executor rejects the request instead of
  running it incorrectly or unsandboxed.
  
  ## Known follow-ups
  
  - The transported permission profile can still contain
  orchestrator-materialized helper or explicit paths. A `TODO(jif)` marks
  where the executor boundary should receive pre-host-materialization
  permission intent.
  - The sandbox wrapper currently replaces a requested custom inner
  `arg0`. A `TODO(jif)` marks where this must be preserved or rejected
  explicitly.
  - Draft PR #29424 contains the deferred sandbox-denial classification
  and approval/retry behavior.
  
  ## Rollout assumption
  
  This executor-sandbox stack is unreleased and its client and executor
  are expected to move together. This PR does not add mixed-version
  negotiation with older exec servers.

  jif · 2026-06-22 12:45:37 +02:00
  9c3b10e5d4
• Simplify multi-agent mode controls (#29324)

  ## Why
  
  Multi-agent delegation policy was split across `multiAgentMode`,
  `features.multi_agent_mode`, and `usage_hint_enabled`. These controls
  could disagree: a requested mode could be downgraded by the feature
  flag, and disabling usage hints also disabled mode instructions.
  
  Some clients also need multi-agent tools without adding
  delegation-policy text to model context. The previous two-mode API could
  not express that directly.
  
  ## What changed
  
  `multiAgentMode` is now the only live delegation-policy control:
  
  | Mode | Behavior |
  | --- | --- |
  | `none` | Keep multi-agent tools available without adding mode
  instructions. |
  | `explicitRequestOnly` | Only delegate after an explicit user request.
  |
  | `proactive` | Delegate when parallel work materially improves speed or
  quality. |
  
  - new threads default to `explicitRequestOnly`; omitting the mode on
  later turns keeps the current value
  - thread start, resume, fork, and settings responses always report the
  concrete current mode instead of `null`
  - mode selection remains sticky across turns and resume
  - usage-hint text no longer controls whether mode instructions apply
  - `features.multi_agent_mode` and `usage_hint_enabled` remain accepted
  as ignored compatibility settings so existing configs continue to load
  - app-server documentation and generated schemas describe the three-mode
  API
  
  ## Tests
  
  - `just test -p codex-core multi_agent_mode`
  - `just test -p codex-core multi_agent_v2_config_from_feature_table`
  - `just test -p codex-core spawn_agent_description`
  - `just test -p codex-features`
  - `just test -p codex-app-server-protocol`
  - `just test -p codex-app-server multi_agent_mode`

  jif · 2026-06-22 10:05:36 +02:00
  c03742ca0a
• Persist session IDs across thread resume (#29327)

  ## Summary
  
  A cold-resumed subagent kept its durable thread ID but could receive a
  new session ID, splitting one agent tree across multiple sessions after
  a restart.
  
  Persist the root session ID in every rollout `SessionMeta`, carry it
  through thread creation, and restore it before initializing the resumed
  `Session` and `AgentControl`.
  
  ## Behavior
  
  For a nested agent tree:
  
  ```text
  root session R
    parent thread P
      child thread C
  ```
  
  The child rollout stores:
  
  ```text
  session_id:       R
  parent_thread_id: P
  id:               C
  ```
  
  After a cold resume, the child still belongs to root session `R` while
  its immediate parent remains `P`. The integration coverage uses distinct
  values for all three IDs so it catches restoring the session from
  `parent_thread_id`.
  
  ## Legacy rollouts
  
  Previous rollouts have `id` but no `session_id`. `SessionMetaLine`
  deserialization treats a missing `session_id` as `id`, keeping those
  files readable, listable, and resumable. When a legacy subagent is
  resumed through its root, that synthesized child ID no longer overrides
  the inherited root-scoped `AgentControl`. New rollouts always persist
  the explicit root session ID.

  jif · 2026-06-22 09:36:08 +02:00
  6d15bb3d17
• chore: fix merge race (auto-compaction feature access) (#29393)

  ## Summary
  
  - read the `AutoCompaction` feature flag through `TurnContext::config`
  - fix both the mid-turn and pre-sampling compaction checks
  
  ## Why
  
  #28260 was validated against an older base where `TurnContext` exposed a
  direct `features` field. It was then merged after that field had moved
  under `config`, leaving the merge result unable to compile with `E0609`
  on `turn_context.features`.
  
  This restores compilation for Bazel, SDK, and argument-comment-lint jobs
  that build `codex-core`. Behavior is unchanged: disabling
  `auto_compaction` still skips automatic compaction.
  
  ## Validation
  
  - `just fmt`
  - `CODEX_HOME=/private/tmp/codex-fix-auto-compaction-test-home just test
  -p codex-core auto_compaction_feature_disabled` — 4 passed
  - `just test -p codex-core` — `codex-core` compiled; 2,722 passed and 89
  unrelated local-environment failures remained because the sandbox could
  not write the default Codex SQLite/proxy paths and some first-party test
  binaries were unavailable

  sayan-oai · 2026-06-22 05:11:42 +00:00
  98845e4840
• Propagate safety buffering events to app-server clients (#29371)

  Responses API safety buffering metadata currently stops at the transport
  boundary, so app-server clients cannot render the in-progress safety
  review state.
  
  This change:
  - decodes and deduplicates `safety_buffering` metadata from Responses
  API SSE and WebSocket events without suppressing the original response
  event
  - emits a typed core event containing the requested model plus backend
  use cases and reasons
  - forwards that event as `turn/safetyBuffering/updated` through
  app-server v2 and updates generated protocol schemas
  - keeps the side-channel event out of persisted rollouts and turn timing
  
  This supports the Codex Apps buffering UX and depends on the Responses
  API backend work in https://github.com/openai/openai/pull/1044569 and
  https://github.com/openai/openai/pull/1044571.
  
  Validation:
  - focused `codex-core` safety-buffering integration test passes
  - `cargo check -p codex-core -p codex-app-server -p
  codex-app-server-protocol`
  - `just fix -p codex-api -p codex-protocol -p codex-core -p
  codex-app-server-protocol -p codex-app-server -p codex-rollout -p
  codex-rollout-trace -p codex-otel`
  - `just fmt`
  - broad package test run: 4,430/4,492 passed; 62 unrelated
  local-environment/concurrency failures involved unavailable test
  binaries, MCP subprocess setup, and app-server timeouts

  Francis Chalissery · 2026-06-22 03:39:14 +00:00
  566f7bf631
• [codex] Add internal auto-compaction opt-out (#28260)

  ## Summary
  
  - add a default-on `auto_compaction` feature flag as an internal escape
  hatch
  - skip pre-turn, model-switch/hash, and mid-turn automatic compaction
  when the flag is disabled
  - preserve manual `/compact` behavior and surface the existing
  context-window error when the provider runs out of room
  - add integration coverage for disabled pre-turn and mid-turn compaction
  
  ## Motivation
  
  Long-running SPO optimization rollouts need the option to preserve their
  full context and fail on context exhaustion instead of entering another
  compaction window. This deliberately uses the existing feature-flag
  mechanism rather than adding a dedicated public config or app-server
  API.
  
  Disable it with:
  
  ```sh
  codex --disable auto_compaction
  ```
  
  ## Testing
  
  - `just test -p codex-features` — 51 passed
  - `just test -p codex-core auto_compaction_feature_disabled` — 2 passed
  - `just fix -p codex-core -p codex-features`
  - `just write-config-schema`
  - `just test -p codex-core` — the new compaction tests passed; the
  overall local run had 54 unrelated environment failures, primarily
  missing first-party test binaries and shell-snapshot timeouts

  rhan-oai · 2026-06-21 20:11:50 -07:00
  b21f0e7a98
• code-mode: preserve initial yield at completion (#29289)

  ## Summary
  
  - Retain the first pre-observation `yield_control()` boundary when a
  cell completes before observation.
  - Deliver the preserved yield before the buffered completion.
  - Keep later unattached yields as no-ops.
  
  ## Why
  
  Create followed by the initial wait must preserve the former execute
  response boundary even when the script runs to completion first.
  
  ## Impact
  
  The first wait observes the same initial yield boundary as before create
  and observe were decoupled.
  
  ## Validation
  
  - Focused initial-yield signature regression passed.
  - Stack-tip validation: `just test -p codex-code-mode -p
  codex-code-mode-protocol` (70 passed).
  - Parent branch:
  `cconger/code-mode-runtime-compact-03e2-observation-delivery`.

  Channing Conger · 2026-06-21 15:35:01 -07:00
  eb8c1ee85f
• code-mode: preserve dropped observation output (#29288)

  ## Summary
  
  - Restore yielded output when an observation receiver disappears before
  delivery.
  - Preserve pending-frontier output and tool IDs across failed delivery.
  - Add dropped-observer coverage for yield and pending observations.
  
  ## Why
  
  Canceling a wait must not consume output or a pending frontier that the
  caller never received.
  
  ## Impact
  
  A later observation can recover undelivered incremental output without
  duplication.
  
  ## Validation
  
  - Stack-tip validation: `just test -p codex-code-mode -p
  codex-code-mode-protocol` (70 passed).
  - Parent branch:
  `cconger/code-mode-runtime-compact-03e-shutdown-hierarchy`.

  Channing Conger · 2026-06-21 13:53:37 -07:00
  3b605b9c63
• [prompting] updated plan mode prompt (#29301)

  Update plan mode prompt to render the implementation plan to the user on
  relevant follow-ups, such that the user can exit out of plan mode to
  implement rather than manually switch of plan mode.

  rhan-oai · 2026-06-21 13:35:25 -07:00
  6bfc58a688
• code-mode: make session shutdown authoritative (#29287)

  ## Summary
  
  - Give each session and cell a hierarchical cancellation token.
  - Track cell tasks so shutdown waits for admitted actors without polling
  the registry.
  - Make shutdown authoritative across concurrent admission and
  non-cooperative callbacks.
  
  ## Why
  
  A best-effort registry scan can miss cells admitted concurrently or
  blocked behind the registry lock.
  
  ## Impact
  
  Session shutdown reliably stops every admitted cell and rejects new work
  once shutdown begins.
  
  ## Validation
  
  - Stack-tip validation: `just test -p codex-code-mode -p
  codex-code-mode-protocol` (70 passed).
  - Parent branch: `cconger/code-mode-runtime-compact-03c-terminal-state`.

  Channing Conger · 2026-06-21 13:15:38 -07:00
  9c79d87d06
• code-mode: linearize cell terminal state (#29286)

  ## Summary
  
  - Introduce a single cell terminal-state machine for completion and
  termination.
  - Make stored-value commits atomic with the winning terminal outcome.
  - Buffer terminal results for later observation and cover
  termination-before-commit behavior.
  
  ## Why
  
  Completion, termination, observation, and stored-value updates must
  agree on one linearized outcome under cancellation races.
  
  ## Impact
  
  Terminal delivery becomes deterministic and terminated cells cannot
  commit state after termination wins.
  
  ## Validation
  
  - Focused terminal-state regression passed.
  - Stack-tip validation: `just test -p codex-code-mode -p
  codex-code-mode-protocol` (70 passed).
  - Parent branch:
  `cconger/code-mode-runtime-compact-03b-session-runtime`.

  Channing Conger · 2026-06-21 12:05:24 -07:00
  f774455c3a
• code-mode: move session ownership into runtime (#29285)

  ## Summary
  
  - Move code-mode cell ownership and shared stored values from
  `CodeModeService` into `SessionRuntime`.
  - Keep the protocol-facing execute/wait behavior behind the existing
  service adapter.
  - Add runtime-level ownership and isolation coverage.
  
  ## Why
  
  This establishes a transport-neutral session boundary before later
  lifecycle and create/observe changes.
  
  ## Impact
  
  No intended model-facing behavior change. This is an ownership and
  layering refactor.
  
  ## Validation
  
  - Stack-tip validation: `just test -p codex-code-mode -p
  codex-code-mode-protocol` (70 passed).
  - Parent branch: `cconger/code-mode-runtime-compact-03a-runtime-types`.

  Channing Conger · 2026-06-21 11:18:36 -07:00
  63f009e9da
• code-mode: define transport-neutral runtime types (#29170)

  ## Summary
  
  - introduce a private `session_runtime` boundary for cell creation
  requests, observation modes, lifecycle events, output items, and tool
  metadata
  - update the cell actor and in-process service to use those
  transport-neutral types
  - keep cell ID allocation on the owning session side
  
  ## Motivation
  
  Cell lifecycle vocabulary currently lives inside the cell actor
  implementation. That makes the service adapter and future session
  runtime depend on actor-specific types, increasing the size and
  complexity of the runtime ownership change.
  
  This is the first reviewable slice of the session-runtime stack. It
  separates the transport-neutral data model without moving lifecycle
  ownership or changing behavior.
  
  Later slices will move session state behind this boundary, harden
  terminal and shutdown behavior, and split cell creation from
  observation.
  
  ## Behavior
  
  There are no public API or user-visible behavior changes in this PR.
  
  In particular:
  
  - `CodeModeSession::execute` and `wait` are unchanged
  - cell IDs remain allocated by the owning session
  - cell admission, observation, termination, and shutdown behavior are
  unchanged

  Channing Conger · 2026-06-21 10:49:31 -07:00
  6d993ca646
• Use controlled time for remote initialization timeout test (#29329)

  ## Summary
  
  The remote-control initialization timeout test used a 50 ms wall-clock
  deadline around a 10 ms transport timeout. A busy CI runner could miss
  that outer deadline even when the rollback behavior was correct.
  
  Pause Tokio time and advance it explicitly through the transport timeout
  instead. The test still verifies that initialization fails and emits the
  matching connection-closed event, without depending on scheduler speed.

  jif · 2026-06-21 14:53:16 +02:00
  6f5dd7b422
• Parallelize skill metadata stats (#29326)

  ## Summary
  
  This switches skill discovery to the simpler same-connection scalar
  request shape.
  
  After reading a skills directory, discovery now starts the existing
  `fs/getMetadata` calls for all visible entries in that directory before
  awaiting the results. There is no JSON-RPC batch frame and no new
  filesystem API; remote filesystems use the existing request-id
  multiplexing on the same exec-server connection.
  
  This is the scoped alternative to the batch-frame approach in #29074 /
  #29075.
  
  ## What changed
  
  - Collect visible directory entries before processing them.
  - Run their existing `fs.get_metadata(...)` calls with `join_all`.
  - Process the results in the original directory order, so skill
  discovery behavior stays the same.
  
  ## Benchmarks
  
  Fresh local benchmark against generated skill trees over a real
  exec-server remote filesystem. The benchmark calls the actual
  `load_skills_from_roots` path, so this includes directory reads,
  metadata stats, `SKILL.md` reads, and parsing.
  
  Times are p50 milliseconds from 5 samples after 1 warmup, using warmed
  runs.
  
  | Scenario | Legacy `main` | Batch frame stack (#29074 / #29075) |
  Same-connection scalar stack |
  | --- | ---: | ---: | ---: |
  | 100 flat skills | 377.4 | 389.0 | 378.6 |
  | 500 flat skills | 1983.2 | 1856.6 | 1757.5 |
  
  Takeaway: for the actual skill discovery path, same-connection scalar is
  tied with legacy at 100 skills and best at 500 skills. The batch-frame
  stack does not show enough win here to justify the extra protocol/API
  surface.
  
  Benchmark command:
  
  - `just test -p codex-exec-server benchmark_remote_skill_discovery
  --run-ignored ignored-only --no-capture`
  
  Checked locally with:
  
  - `just test -p codex-core-skills`
  - `just bazel-lock-update`
  - `just bazel-lock-check`

  jif · 2026-06-21 14:04:18 +02:00
  c2fbf4247a
• Test pipelined scalar exec-server requests (#29325)

  ## Summary
  
  This adds focused coverage for the simpler same-connection scalar
  request path.
  
  The exec-server connection already supports multiple in-flight JSON-RPC
  scalar requests on one connection. This test locks in that behavior by
  sending two normal requests before reading either response, without
  adding a batch frame or any new API surface.
  
  ## What changed
  
  - Added a processor-level test that initializes an exec-server
  connection.
  - Sends two scalar `environment/info` requests back-to-back on the same
  connection.
  - Verifies both responses come back on the same connection by request
  id.
  
  Checked locally with:
  
  - `just test -p codex-exec-server
  connection_accepts_pipelined_scalar_requests`

  jif · 2026-06-21 13:40:51 +02:00
  1088b30fda
• Carry sandbox intent to remote exec servers (#29108)

  ## What changed
  
  PR #29099 stopped sending the orchestrator's concrete sandbox wrapper to
  a remote exec-server. Remote commands now arrive as plain native argv.
  
  This PR adds the next piece: Codex also sends portable sandbox intent
  next to that plain argv.
  
  For a remote unified-exec command, the request can now include:
  
  - the canonical permission profile before local workspace-root
  materialization
  - the sandbox cwd and workspace roots as `PathUri` values
  - Windows sandbox settings
  - the legacy Landlock setting
  - whether managed networking must be enforced
  
  The important part is that symbolic entries such as `:workspace_roots`
  stay symbolic while crossing the boundary. The executor can then bind
  them to its own workspace-root paths instead of receiving
  orchestrator-local absolute paths.
  
  The data travels through `ExecRequest` into `ExecParams`. Older
  exec-servers can still deserialize requests because the new fields have
  defaults.
  
  ## Why
  
  The orchestrator should not decide how another machine implements
  sandboxing.
  
  For example:
  
  - a local macOS Codex would normally build a Seatbelt command
  - a remote Linux executor needs a Linux sandbox command instead
  
  The orchestrator now sends the plain command plus the policy it intended
  to enforce. A later PR can let the exec-server choose and build the
  correct sandbox for its own operating system.
  
  ## Important detail
  
  This keeps the portable intent separate from the local `SandboxType`.
  
  `SandboxType::None` is ambiguous:
  
  - it can mean the command was explicitly approved to run without a
  sandbox
  - it can also mean the orchestrator host has no concrete sandbox
  implementation available
  
  Those cases are different for remote execution. This PR adds
  `sandbox_requested` so an executor can still receive sandbox intent when
  the orchestrator cannot build a local wrapper. Explicit unsandboxed
  retries still send no sandbox context.
  
  ## Behavior today
  
  This PR only transports the intent. The exec-server accepts the new
  fields but does not apply them yet.
  
  Remote commands therefore remain unsandboxed after this PR, just as they
  are after PR #29099.
  
  ## Follow-up
  
  The next PR will make exec-server read this portable intent, bind
  symbolic workspace permissions to executor-native roots, choose the
  sandbox for its own operating system, build the wrapper locally, and
  then spawn the command.

  jif · 2026-06-21 12:33:21 +02:00
  bd2968a4db
• [codex] simplify token budget context (#29295)

  ## Why
  
  The token-budget feature currently adds remaining-token messages
  whenever usage crosses the 25%, 50%, and 75% thresholds. Those periodic
  inserts create prompt churn without requiring action, while the
  near-compaction reminder and explicit `get_context_remaining` tool
  already cover actionable and on-demand budget information.
  
  The context-window lineage block is also easier to scan as plain labeled
  text than as a `<token_budget>`-wrapped fragment.
  
  ## What changed
  
  - Stop recording automatic remaining-token messages at percentage
  thresholds.
  - Render context-window lineage in `First`, `Current`, `Previous` order
  with colon-separated labels.
  - Omit the `Previous` line for the first context window.
  - Remove `<token_budget>` wrappers from newly rendered lineage,
  near-compaction reminders, and `get_context_remaining` output.
  - Keep recognizing legacy wrapped fragments so existing rollouts remain
  compatible.
  - Remove the post-sampling token snapshot that was only needed by the
  periodic threshold path.
  
  ## Testing
  
  - `just test -p codex-core token_budget` (11 tests passed)

  pakrym-oai · 2026-06-20 21:50:09 -07:00
  aaf737fa59
• [codex] add configurable token budget compaction reminder (#29255)

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

  pakrym-oai · 2026-06-20 19:13:42 -07:00
  6df037d47f
• [codex] prototype mcp_history thread hint injection (#29259)

  ## Why
  
  Prototype whether the harness can invoke the `mcp_history` MCP while
  constructing full initial context and expose its thread hint to the
  model without requiring a model-issued tool call.
  
  The prototype builds on the context-window lineage added by #29256 and
  is now based directly on `main`.
  
  ## What changed
  
  - Call `mcp_history/thread_hint` with no arguments while building the
  full `<token_budget>` context.
  - Pass the current `threadId` through MCP request metadata, matching the
  normal MCP tool-call path.
  - Serialize only the unstructured `content` result and append it inside
  `<token_budget>` when the call succeeds.
  - Omit the additional context when the MCP call or content serialization
  fails.
  
  ## Prototype limitations
  
  - The direct call bypasses the normal model-initiated MCP approval,
  lifecycle-event, telemetry, and result-sanitization path.
  - The call has no prototype-specific timeout, result-size cap, or
  per-window cache.
  - MCP latency is added to full-context construction, including
  applicable compaction paths.
  
  ## Validation
  
  - `just test -p codex-core token_budget`

  pakrym-oai · 2026-06-20 18:02:02 -07:00
  b6d6be2a84
• core: add context window lineage IDs (#29256)

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

  pakrym-oai · 2026-06-20 13:15:49 -07:00
  d1209bddfc
• Allow resume and settings commands during tasks and MCP startup (#29154)

  ## Why
  
  The TUI treats both an active turn and MCP startup as a running task.
  That currently blocks `/resume` and several settings commands even
  though they do not compete with turn execution, which is especially
  frustrating when MCP startup is slow.
  
  Model, permissions, personality, and service-tier selections already
  update thread settings independently of the running turn. Other clients
  can send those updates mid-turn, while the current turn continues with
  its captured settings. Allowing the same updates from local slash
  commands makes the TUI consistent with that existing behavior.
  
  ## What changed
  
  - Allow `/resume` while a task is running.
  - Allow `/model`, `/permissions`, `/personality`, and service-tier
  commands such as `/fast` while a task is running.
  - Keep the existing behavior where the active turn uses its captured
  settings and updates apply to subsequent turns.
  - Exercise the commands under the busy state in the existing TUI tests
  and retain coverage for commands that should remain blocked.
  
  ## Behavior note
  
  Turn settings such as model selection and reasoning effort are captured
  when a turn starts. Changing them during an active turn affects the next
  turn, not the turn already in progress. The status bar updates
  immediately, so it may temporarily display the newly selected setting
  before that setting is actually in effect.
  
  ## Verification
  
  - Focused `codex-tui` tests for resume dispatch, settings popups,
  `/fast`, and disabled-command behavior.
  
  ## Related issues
  
  Closes #19015.
  
  Addresses the next-turn-safe model/reasoning switching portion of
  #14356; dedicated shortcuts and the proposed depth meter remain out of
  scope.

  Eric Traut · 2026-06-19 21:37:01 -07:00
  d667082322
• [codex] Preserve skill descriptions outside model context (#29006)

  ## Why
  
  Skill descriptions are used in model-visible lists: the default
  available-skills catalog that supports implicit selection, and the
  on-demand `skills.list` tool response used to discover orchestrator
  skills. A single overlong description should not consume a
  disproportionate share of either list.
  
  Enforcing the 1024-character limit while loading or migrating skills is
  the wrong boundary: it rejects otherwise-valid skills and discards
  metadata that non-model consumers and full skill reads may need. Skill
  metadata and `SKILL.md` content should remain intact; the cap belongs at
  model-visible list rendering boundaries.
  
  ## What changed
  
  - Preserve full `description` and `metadata.short-description` values
  when loading skills.
  - Preserve full external-agent command descriptions during
  `source-command-*` migration instead of skipping commands solely because
  their descriptions exceed 1024 characters.
  - Preserve full normalized orchestrator descriptions in the underlying
  skills catalog.
  - Cap each description at 1024 Unicode characters when rendering the
  default available-skills context in `codex-core-skills` and
  `codex-skills-extension`.
  - Apply the same cap when serializing descriptions in the model-visible
  `skills.list` response.
  - Render truncated descriptions as 1021 original characters plus `...`.
  - Leave explicit `$skill` injection, `skills.read`, underlying metadata,
  and on-disk `SKILL.md` files unchanged and full-fidelity.
  
  ## Implicit skill selection
  
  Codex injects a bounded catalog containing each implicitly allowed
  skill's name, description, and source locator, together with
  instructions to use a skill when the task clearly matches its
  description. The model makes that semantic choice; after selecting a
  skill, it reads the full `SKILL.md` from its filesystem or provider
  resource. Explicit `$skill` mentions remain a separate path that injects
  the full skill instructions. For orchestrator skills, `skills.list`
  provides bounded discovery metadata before `skills.read` returns the
  full selected resource.
  
  ## Test plan
  
  - `just test -p codex-core-skills`
  - `just test -p codex-skills-extension`
  - `just test -p codex-external-agent-migration`
  
  The focused regressions verify that overlong metadata is preserved at
  load and migration boundaries while default available-skills rendering
  and `skills.list` output produce the 1021-character prefix plus `...`.

  charlesgong-openai · 2026-06-19 12:47:53 -07:00
  64bdeed9f7
• chore(deps): advance tokio-tungstenite (#29132)

  ## Why
  
  Responses websocket connections use `tokio-tungstenite`. When DNS
  returns an unusable native IPv6 address before a working IPv4 address,
  sequential dialing can consume Codex's outer websocket timeout before
  reaching IPv4. The merged fork change adds Happy Eyeballs-style
  alternate-family racing so websocket dialing matches the recovery
  behavior already present in the HTTP path.
  
  ## What Changed
  
  Advance the workspace `tokio-tungstenite` patch from `132f5b39` to
  merged commit `e5e64b86`, and update the matching lockfile source. The
  new revision comes from
  [openai-oss-forks/tokio-tungstenite#1](https://github.com/openai-oss-forks/tokio-tungstenite/pull/1).

  Anton Panasenko · 2026-06-19 12:02:12 -07:00
  abd901770e
• [codex] trace pre-sampling skill and persistence latency (#29042)
  rphilizaire-openai · 2026-06-19 10:13:27 -07:00
  a57b268d61
• Use cached and live web access terminology (#29095)

  ## Summary
  
  - Rename the string-valued external web access enum variants from
  `Offline` / `Online` to `Cached` / `Live`.
  - Align the transport names with the existing `web_search = "cached"` /
  `"live"` configuration vocabulary.
  
  Existing behavior is unchanged: `WebSearchMode::Cached` and
  `WebSearchMode::Live` continue to send the backward-compatible boolean
  values `false` and `true`; `Indexed` remains the only mode currently
  sent as a string.
  
  ## Validation
  
  - `just fmt`
  - `just test -p codex-api` (127 passed)

  Winston Howes · 2026-06-19 09:00:44 -07:00
  c83618ab20
• Keep remote exec commands native to the executor (#29099)

  ## Summary
  
  - Remote unified-exec now sends the original command argv to exec-server
  instead of materializing the orchestrator's sandbox wrapper first.
  - Local unified-exec keeps the existing sandbox path unchanged.
  - Add a focused regression test for a macOS-selected sandbox producing
  plain remote argv.
  
  Before:
  
      macOS orchestrator -> /usr/bin/sandbox-exec ... -> Linux exec-server
  
  After:
  
      macOS orchestrator -> /bin/bash -lc pwd -> Linux exec-server
  
  This is intentionally only the first cleanup step. Remote unified-exec
  commands are sent without a process sandbox until the targeted
  follow-ups below land. For the macOS-to-Linux path this is not a
  practical regression: the old sandboxed attempt failed before process
  launch because the Linux executor could not spawn macOS sandbox paths.
  
  ## Targeted follow-ups
  
  1. Carry sandbox intent separately from argv.
     - Add an optional sandbox field to exec-server process params.
  - Reuse FileSystemSandboxContext rather than introducing a new sandbox
  model.
     - Carry managed-network enforcement as one explicit bit.
     - Keep argv plain.
  
  2. Apply that intent inside exec-server.
     - Add a small process-start adapter before LocalProcess::exec.
  - Reuse the existing codex-sandboxing SandboxManager and exec-server
  runtime paths.
  - Follow the same shape already used by exec-server filesystem
  sandboxing.
     - Do not duplicate or move the sandbox implementations.
  
  3. Report the sandbox actually used.
     - Return the executor-selected sandbox type from process/start.
  - Use that value in core for sandbox-denial detection and retry
  behavior.
  
  ## End state
  
  The orchestrator sends plain commands plus portable sandbox intent. The
  executor chooses and applies its own native sandbox: Linux executors use
  Linux sandboxing, macOS executors use Seatbelt, and Windows executors
  use Windows sandboxing. Concrete wrapper argv, helper paths, and sandbox
  env markers never cross the executor boundary.

  jif · 2026-06-19 17:05:51 +02:00
  04483f4ce5
• Add config toggles for orchestrator skills and MCP (#28942)

  ## Why
  
  Orchestrator-provided skills and Codex Apps MCP tools add model-visible
  instructions, resources, and tools beyond the local workspace. Hosts
  need config-level switches to disable those orchestrator-owned surfaces
  independently, without disabling regular skills or regular MCP servers.
  
  ## What changed
  
  - Adds `[orchestrator.skills].enabled` and `[orchestrator.mcp].enabled`
  config entries, both defaulting to `true`.
  - Includes the new settings in `config.schema.json` and in the config
  lock so resolved thread configuration preserves the same orchestrator
  exposure decisions.
  - Threads `orchestrator.skills.enabled` through the app-server skills
  extension so disabled orchestrator skills do not expose the `skills`
  namespace or inject orchestrator skill context.
  - Gates Codex Apps MCP exposure, app instructions, and app auth
  eligibility on `orchestrator.mcp.enabled` while leaving non-Codex-Apps
  MCP tools available.
  - Updates the thread-manager sample config to disable both
  orchestrator-owned surfaces.
  
  ## Verification
  
  - Added config parsing, loading, defaulting, and schema coverage for the
  new settings.
  - Added MCP exposure coverage that `orchestrator.mcp.enabled = false`
  removes Codex Apps tools while preserving regular MCP tools.
  - Added app-server coverage that `orchestrator.skills.enabled = false`
  prevents orchestrator skill tools, prompts, and resource reads from
  reaching the model turn.

  jif · 2026-06-19 14:42:26 +02:00
  81b000421d
• Add indexed web search mode (#28489)

  ## Summary
  
  - Add `web_search = "indexed"` alongside `disabled`, `cached`, and
  `live`.
  - Use that same resolved mode for both hosted and standalone web search.
  - For hosted search, send `index_gated_web_access: true` with external
  web access enabled only when `indexed` is selected.
  - For standalone search, preserve the existing boolean wire values for
  existing modes (`cached` maps to `false` and `live` to `true`) and send
  `"indexed"` only for `indexed`; `disabled` keeps the tool unavailable.
  - Carry the mode through managed configuration requirements and
  generated schemas.
  
  ## Why
  
  Indexed search provides a middle ground between cached-only search and
  unrestricted live page fetching. Search queries can remain live while
  direct page fetches are limited to URLs admitted by the server.
  
  The existing `web_search` setting remains the single source of truth, so
  hosted and standalone executors cannot drift into different access
  modes. Without an explicit `indexed` selection, the existing
  model-visible tool and request shapes are unchanged.
  
  ```toml
  web_search = "indexed"
  
  [features]
  standalone_web_search = true
  ```
  
  ## Validation
  
  - `just fmt`
  - `just test -p codex-api` (`126 passed`)
  - `just test -p codex-web-search-extension` (`7 passed`)
  - `just test -p codex-core
  code_mode_can_call_indexed_standalone_web_search` (`1 passed`)
  - Focused configuration, hosted request, standalone request, and
  managed-requirement coverage is included in the PR; remaining suites run
  in CI.
  
  The full workspace test suite was not run locally.

  Winston Howes · 2026-06-19 05:35:57 -07:00
  3a2712ea14
• Document raw response item compatibility (#29086)

  Adds a short AGENTS.md note asking reviewers to treat raw response item
  events as compatibility-sensitive, even while they are experimental.
  
  This keeps future app-server changes from accidentally breaking Codex
  Cloud consumers of raw response item events.

  jif · 2026-06-19 14:08:31 +02:00
  7951397e4a
• Scope network approvals by environment (#28899)

  Stacked on #28766.
  
  ## Why
  
  Network approvals are environment-scoped: allowing a host in one
  execution environment should not allow the same host in another
  environment.
  
  #28766 adds the inert IDs and constructor plumbing. This PR applies the
  behavior on top.
  
  ## What changed
  
  - Route managed network traffic through per-environment HTTP and SOCKS
  proxy listeners.
  - Stamp HTTP, HTTPS CONNECT, SOCKS TCP, and SOCKS UDP policy requests
  with the source environment at the proxy boundary.
  - Carry the selected execution environment through shell, unified exec,
  zsh-fork, and sandbox transform paths.
  - Include the environment in pending, approved-for-session, and
  denied-for-session network approval cache keys.
  - Include the environment in approval IDs and approval prompts.
  - Preserve legacy fallback for unattributed requests, but deny when
  active-call attribution is ambiguous.
  - Fail closed if an environment-specific proxy endpoint cannot be
  prepared.
  
  ## Validation
  
  - just fmt
  - CI will run tests and clippy

  jif · 2026-06-19 13:49:45 +02:00
  bd5d31b250
• [codex] abort turns when rollout budgets expire (token budget 3/3) (#28707)

  ## Stack
  
  Depends on #28494.
  
  ## Description
  
  This PR propagates shared rollout-budget exhaustion through the existing
  `CodexErr::TurnAborted` task result.
  
  Each thread records its model usage against the same ledger. Once the
  ledger is exhausted, that usage update and all later usage updates
  return `TurnAborted`. The task wrapper emits the normal aborted-turn
  event and lifecycle instead of completing the turn.
  
  This is intentionally a soft boundary: there is no cross-thread
  `Op::Interrupt` fanout. An in-flight thread can finish its current
  response before it observes the exhausted ledger, but every thread
  aborts at its next usage-accounting boundary.
  
  ## Tests
  
  The integration coverage verifies that:
  
  - the response that exhausts the budget aborts its turn;
  - a later response also aborts because the shared ledger remains
  exhausted; and
  - sub-agent usage draws from the same shared ledger; and
  - local and remote-v2 compaction abort without retrying or emitting a
  generic error.
  
  Local checks:
  
  - `just test -p codex-core
  exhausted_budget_aborts_current_and_later_turns`
  - `just test -p codex-core subagent_usage_draws_from_the_shared_budget`
  - `just test -p codex-core
  abort_regular_task_emits_marker_before_turn_aborted`
  - `just test -p codex-core
  compaction_budget_exhaustion_aborts_without_error_or_retry`
  - `just fix -p codex-core`
  - `just fmt`
  - `git diff --check`
  
  The full workspace test suite was not run locally.

  rka-oai · 2026-06-19 02:00:01 -07:00
  dac588f413