1568 Commits

• Fixed a hole in token refresh logic for app server (#11802)

  We've continued to receive reports from users that they're seeing the
  error message "Your access token could not be refreshed because your
  refresh token was already used. Please log out and sign in again." This
  PR fixes two holes in the token refresh logic that lead to this
  condition.
  
  Background: A previous change in token refresh introduced the
  `UnauthorizedRecovery` object. It implements a state machine in the core
  agent loop that first performs a load of the on-disk auth information
  guarded by a check for matching account ID. If it finds that the on-disk
  version has been updated by another instance of codex, it uses the
  reloaded auth tokens. If the on-disk version hasn't been updated, it
  issues a refresh request from the token authority.
  
  There are two problems that this PR addresses:
  
  Problem 1: We weren't doing the same thing for the code path used by the
  app server interface. This PR effectively replicates the
  `UnauthorizedRecovery` logic for that code path.
  
  Problem 2: The `UnauthorizedRecovery` logic contained a hole in the
  `ReloadOutcome::Skipped` case. Here's the scenario. A user starts two
  instances of the CLI. Instance 1 is active (working on a task), instance
  2 is idle. Both instances have the same in-memory cached tokens. The
  user then runs `codex logout` or `codex login` to log in to a separate
  account, which overwrites the `auth.json` file. Instance 1 receives a
  401 and refreshes its token, but it doesn't write the new token to the
  `auth.json` file because the account ID doesn't match. Instance 2 is
  later activated and presented with a new task. It immediately hits a 401
  and attempts to refresh its token but fails because its cached refresh
  token is now invalid. To avoid this situation, I've changed the logic to
  immediately fail a token refresh if the user has since logged out or
  logged in to another account. This will still be seen as an error by the
  user, but the cause will be clearer.
  
  I also took this opportunity to clean up the names of existing functions
  to make their roles clearer.
  * `try_refresh_token` is renamed `request_chatgpt_token_refresh`
  * the existing `refresh_token` is renamed `refresh_token_from_authority`
  (there's a new higher-level function named `refresh_token` now)
  * `refresh_tokens` is renamed `refresh_and_persist_chatgpt_token`, and
  it now implicitly reloads
  * `update_tokens` is renamed `persist_tokens`

  Eric Traut · 2026-02-18 09:27:04 -08:00
  999576f7b8
• Disable collab tools during review delegation (#12157)

  Summary
  - prevent delegated review agents from re-enabling blocked tools by
  explicitly disabling the Collab feature alongside web search and view
  image controls
  
  Testing
  - Not run (not requested)

  jif-oai · 2026-02-18 17:02:49 +00:00
  9f5b17de0d
• feat: better slug for rollout summaries (#12135)
  jif-oai · 2026-02-18 16:39:38 +00:00
  18206a9c1e
• Stop filtering model tools in js_repl_tools_only mode (#12069)

  ## Summary
  This change removes tool-list filtering in `js_repl_tools_only` mode and
  relies on the normal model tool descriptions, while still enforcing that
  tool execution must go through `js_repl` + `codex.tool(...)`.
  
  ## Motivation
  The previous `js_repl_tools_only` filtering hid most tools from the
  model request, which diverged from standard tool-list behavior and made
  signatures less discoverable. I tested that this filtering is not
  needed, and the model can follow the prompt to only call tools via
  `js_repl`.
  
  ## What Changed
  - `filter_tools_for_model(...)` in `core/src/tools/spec.rs` is now a
  pass-through (no filtering when `js_repl_tools_only` is enabled).
  - Updated tests to assert that model tools are not filtered in
  `js_repl_tools_only` mode.
  - Updated dynamic-tool test to assert dynamic tools remain visible in
  model tool specs.
  - Removed obsolete test helper used only by the old filtering
  assertions.
  
  ## Safety / Behavior
  - This commit does **not** relax execution policy.
  - Direct model tool calls remain blocked in `js_repl_tools_only` mode
  (except internal `js_repl` tools), and callers are instructed to use
  `js_repl` + `codex.tool(...)`.
  
  ## Testing
  - `cargo test -p codex-core js_repl_tools_only`
  - Manual rollout validation showed the model can follow the `js_repl`
  routing instructions without needing filtered tool lists.
  
  
  
  #### [git stack](https://github.com/magus/git-stack-cli)
  - 👉 `1` https://github.com/openai/codex/pull/12069
  - ⏳ `2` https://github.com/openai/codex/pull/10673
  - ⏳ `3` https://github.com/openai/codex/pull/10670

  Curtis 'Fjord' Hawthorne · 2026-02-18 07:31:15 -08:00
  491b4946ae
• nit: change model for phase 1 (#12137)
  jif-oai · 2026-02-18 13:55:30 +00:00
  cc3bbd7852
• feat: validate agent config file paths (#12133)
  jif-oai · 2026-02-18 13:48:52 +00:00
  7b65b05e87
• feat: memory usage metrics (#12120)
  jif-oai · 2026-02-18 12:45:19 +00:00
  a9f5f633b2
• feat: phase 2 usage (#12121)
  jif-oai · 2026-02-18 11:33:55 +00:00
  2293ab0e21
• feat: phase 1 and phase 2 e2e latencies (#12124)
  jif-oai · 2026-02-18 11:30:20 +00:00
  f0ee2d9f67
• Enable default status line indicators in TUI config (#12015)

  Default statusline to something
  <img width="307" height="83" alt="Screenshot 2026-02-17 at 18 16 12"
  src="https://github.com/user-attachments/assets/44e16153-0aa2-4c1a-9b4a-02e2feb8b7f6"
  />

  jif-oai · 2026-02-18 09:51:15 +00:00
  0dcf8d9c8f
• fix: Restricted Read: /System is too permissive for macOS platform de… (#11798)

  …fault
  
  Update the list of platform defaults included for `ReadOnlyAccess`.
  
  When `ReadOnlyAccess::Restricted::include_platform_defaults` is `true`,
  the policy defined in
  `codex-rs/core/src/seatbelt_platform_defaults.sbpl` is appended to
  enable macOS programs to function properly.

  Leo Shimonaka · 2026-02-17 23:56:35 -08:00
  1946a4c48b
• [js_repl] paths for node module resolution can be specified for js_repl (#11944)

  # External (non-OpenAI) Pull Request Requirements
  
  In `js_repl` mode, module resolution currently starts from
  `js_repl_kernel.js`, which is written to a per-kernel temp dir. This
  effectively means that bare imports will not resolve.
  
  This PR adds a new config option, `js_repl_node_module_dirs`, which is a
  list of dirs that are used (in order) to resolve a bare import. If none
  of those work, the current working directory of the thread is used.
  
  For example:
  ```toml
  js_repl_node_module_dirs = [
      "/path/to/node_modules/",
      "/other/path/to/node_modules/",
  ]
  ```

  aaronl-openai · 2026-02-17 23:29:49 -08:00
  f600453699
• got rid of experimental_mode for configtoml (#12077)
  won-openai · 2026-02-17 21:10:30 -08:00
  189f592014
• feat(core): zsh exec bridge (#12052)

  zsh fork PR stack:
  - https://github.com/openai/codex/pull/12051 
  - https://github.com/openai/codex/pull/12052 👈 
  
  ### Summary
  This PR introduces a feature-gated native shell runtime path that routes
  shell execution through a patched zsh exec bridge, removing MCP-specific
  behavior from the shell hot path while preserving existing
  CommandExecution lifecycle semantics.
  
  When shell_zsh_fork is enabled, shell commands run via patched zsh with
  per-`execve` interception through EXEC_WRAPPER. Core receives wrapper
  IPC requests over a Unix socket, applies existing approval policy, and
  returns allow/deny before the subcommand executes.
  
  ### What’s included
  **1) New zsh exec bridge runtime in core**
  - Wrapper-mode entrypoint (maybe_run_zsh_exec_wrapper_mode) for
  EXEC_WRAPPER invocations.
  - Per-execution Unix-socket IPC handling for wrapper requests/responses.
  - Approval callback integration using existing core approval
  orchestration.
  - Streaming stdout/stderr deltas to existing command output event
  pipeline.
  - Error handling for malformed IPC, denial/abort, and execution
  failures.
  
  **2) Session lifecycle integration**
  SessionServices now owns a `ZshExecBridge`.
  Session startup initializes bridge state; shutdown tears it down
  cleanly.
  
  **3) Shell runtime routing (feature-gated)**
  When `shell_zsh_fork` is enabled:
  - Build execution env/spec as usual.
  - Add wrapper socket env wiring.
  - Execute via `zsh_exec_bridge.execute_shell_request(...)` instead of
  the regular shell path.
  - Non-zsh-fork behavior remains unchanged.
  
  **4) Config + feature wiring**
  - Added `Feature::ShellZshFork` (under development).
  - Added config support for `zsh_path` (optional absolute path to patched
  zsh):
  - `Config`, `ConfigToml`, `ConfigProfile`, overrides, and schema.
  - Session startup validates that `zsh_path` exists/usable when zsh-fork
  is enabled.
  - Added startup test for missing `zsh_path` failure mode.
  
  **5) Seatbelt/sandbox updates for wrapper IPC**
  - Extended seatbelt policy generation to optionally allow outbound
  connection to explicitly permitted Unix sockets.
  - Wired sandboxing path to pass wrapper socket path through to seatbelt
  policy generation.
  - Added/updated seatbelt tests for explicit socket allow rule and
  argument emission.
  
  **6) Runtime entrypoint hooks**
  - This allows the same binary to act as the zsh wrapper subprocess when
  invoked via `EXEC_WRAPPER`.
  
  **7) Tool selection behavior**
  - ToolsConfig now prefers ShellCommand type when shell_zsh_fork is
  enabled.
  - Added test coverage for precedence with unified-exec enabled.

  Owen Lin · 2026-02-17 20:19:53 -08:00
  edacbf7b6e
• Use V2 websockets if feature enabled (#12071)
  pakrym-oai · 2026-02-17 18:32:16 -08:00
  fc810ba045
• feat(core): plumb distinct approval ids for command approvals (#12051)

  zsh fork PR stack:
  - https://github.com/openai/codex/pull/12051 👈 
  - https://github.com/openai/codex/pull/12052
  
  With upcoming support for a fork of zsh that allows us to intercept
  `execve` and run execpolicy checks for each subcommand as part of a
  `CommandExecution`, it will be possible for there to be multiple
  approval requests for a shell command like `/path/to/zsh -lc 'git status
  && rg \"TODO\" src && make test'`.
  
  To support that, this PR introduces a new `approval_id` field across
  core, protocol, and app-server so that we can associate approvals
  properly for subcommands.

  Owen Lin · 2026-02-18 01:55:57 +00:00
  db4d2599b5
• Chore: remove response model check and rely on header model for downgrade (#12061)

  ### Summary
  Ensure that we use the model value from the response header only so that
  we are guaranteed with the correct slug name. We are no longer checking
  against the model value from response so that we are less likely to have
  false positive.
  
  There are two different treatments - for SSE we use the header from the
  response and for websocket we check top-level events.

  Shijie Rao · 2026-02-18 01:50:06 +00:00
  b3a8571219
• Use prompt-based co-author attribution with config override (#11617)
  gabec-openai · 2026-02-17 20:15:54 +00:00
  5341ad08f8
• [apps] Expose more fields from apps listing endpoints. (#11706)

  - [x] Expose app_metadata, branding, and labels in AppInfo.

  Matthew Zeng · 2026-02-17 11:45:04 -08:00
  16fa195fce
• chore: rm remote models fflag (#11699)

  rm `remote_models` feature flag.
  
  We see issues like #11527 when a user has `remote_models` disabled, as
  we always use the default fallback `ModelInfo`. This causes issues with
  model performance.
  
  Builds on #11690, which helps by warning the user when they are using
  the default fallback. This PR will make that happen much less frequently
  as an accidental consequence of disabling `remote_models`.

  sayan-oai · 2026-02-17 11:43:16 -08:00
  41800fc876
• Add remote skill scope/product_surface/enabled params and cleanup (#11801)

  skills/remote/list: params=hazelnutScope, productSurface, enabled;
  returns=data: { id, name, description }[]
  skills/remote/export: params=hazelnutId; returns={ id, path }

  xl-openai · 2026-02-17 11:05:22 -08:00
  314029ffa3
• Feat: add model reroute notification (#12001)

  ### Summary
  Builiding off
  https://github.com/openai/codex/pull/11964/files/5c75aa7b89a70bc2cc410a6fd238749306ec4c5e#diff-058ae8f109a8b84b4b79bbfa45f522c2233b9d9e139696044ae374d50b6196e0,
  we have created a `model/rerouted` notification that captures the event
  so that consumers can render as expected. Keep the `EventMsg::Warning`
  path in core so that this does not affect TUI rendering.
  
  `model/rerouted` is meant to be generic to account for future usage
  including capacity planning etc.

  Shijie Rao · 2026-02-17 11:02:23 -08:00
  48018e9eac
• chore: clarify web_search deprecation notices and consolidate tests (#11224)

  follow up to #10406, clarify default-enablement of web_search.
  
  also consolidate pseudo-redundant tests
  
  Tests pass

  sayan-oai · 2026-02-17 18:20:24 +00:00
  a1b8e34938
• feat: move agents config to main config (#11982)
  jif-oai · 2026-02-17 18:17:19 +00:00
  76283e6b4e
• Centralize context update diffing logic (#11807)

  ## Summary
  This PR centralizes model-visible state diffing for turn context updates
  into one module, while keeping existing behavior and call sites stable.
  
  ### What changed
  - Added `core/src/context_updates.rs` with the consolidated diffing
  logic for:
    - environment context updates
    - permissions/policy updates
    - collaboration mode updates
    - model-instruction switch updates
    - personality updates
  - Added `BuildSettingsUpdateItemsParams` so required dependencies are
  passed explicitly.
  - Updated `Session::build_settings_update_items` in `core/src/codex.rs`
  to delegate to the centralized module.
  - Reused the same centralized `personality_message_for` helper from
  initial-context assembly to avoid duplicated logic.
  - Registered the new module in `core/src/lib.rs`.
  
  ## Why
  This is a minimal, shippable step toward the model-visible-state design:
  all state diff decisions for turn-context update items now live in one
  place, improving reviewability and reducing drift risk without expanding
  scope.
  
  ## Behavior
  - Intended to be behavior-preserving.
  - No protocol/schema changes.
  - No call-site behavior changes beyond routing through the new
  centralized logic.
  
  ## Testing
  Ran targeted tests in this worktree:
  - `cargo test -p codex-core
  build_settings_update_items_emits_environment_item_for_network_changes`
  - `cargo test -p codex-core collaboration_instructions --test all`
  
  Both passed.
  
  ## Codex author
  `codex resume 019c540f-3951-7352-a3fa-6f07b834d4ce`

  Charley Cunningham · 2026-02-17 09:21:44 -08:00
  cab607befb
• Don't allow model_supports_reasoning_summaries to disable reasoning (#11833)

  The `model_supports_reasoning_summaries` config option was originally
  added so users could enable reasoning for custom models (models that
  codex doesn't know about). This is how it was documented in the source,
  but its implementation didn't match. It was implemented such that it can
  also be used to disable reasoning for models that otherwise support
  reasoning. This leads to bad behavior for some reasoning models like
  `gpt-5.3-codex`. Diagnosing this is difficult, and it has led to many
  support issues.
  
  This PR changes the handling of `model_supports_reasoning_summaries` so
  it matches its original documented behavior. If it is set to false, it
  is a no-op. That is, it never disables reasoning for models that are
  known to support reasoning. It can still be used for its intended
  purpose -- to enable reasoning for unknown models.

  Eric Traut · 2026-02-17 07:19:28 -08:00
  281b0eae8b
• nit: wording multi-agent (#11986)
  jif-oai · 2026-02-17 11:45:59 +00:00
  56cd85cd4b
• fix: race in js repl (#11922)

  js_repl_reset previously raced with in-flight/new js_repl executions
  because reset() could clear exec_tool_calls without synchronizing with
  execute(). In that window, a running exec could lose its per-exec
  tool-call context, and subsequent kernel RunTool messages would fail
  with js_repl exec context not found. The fix serializes reset and
  execute on the same exec_lock, so reset cannot run concurrently with
  exec setup/teardown. We also keep the timeout path safe by performing
  reset steps inline while execute() already holds the lock, avoiding
  re-entrant lock acquisition. A regression test now verifies that reset
  waits for the exec lock and does not clear tool-call state early.

  jif-oai · 2026-02-17 11:06:14 +00:00
  77f74a5c17
• fix: js_repl reset hang by clearing exec tool calls without waiting (#11932)

  Remove the waiting loop in `reset` so it no longer blocks on potentially
  hanging exec tool calls + add `clear_all_exec_tool_calls_map` to drain
  the map and notify waiters so `reset` completes immediately

  jif-oai · 2026-02-17 08:40:54 +00:00
  846464e869
• fix(core) exec_policy parsing fixes (#11951)

  ## Summary
  Fixes a few things in our exec_policy handling of prefix_rules:
  1. Correctly match redirects specifically for exec_policy parsing. i.e.
  if you have `prefix_rule(["echo"], decision="allow")` then `echo hello >
  output.txt` should match - this should fix #10321
  2. If there already exists any rule that would match our prefix rule
  (not just a prompt), then drop it, since it won't do anything.
  
  
  ## Testing
  - [x] Updated unit tests, added approvals ScenarioSpecs

  Dylan Hurd · 2026-02-16 23:11:59 -08:00
  0fbe10a807
• add(core): safety check downgrade warning (#11964)

  Add per-turn notice when a request is downgraded to a fallback model due
  to cyber safety checks.
  
  **Changes**
  
  - codex-api: Emit a ServerModel event based on the openai-model response
  header and/or response payload (SSE + WebSocket), including when the
  model changes mid-stream.
  - core: When the server-reported model differs from the requested model,
  emit a single per-turn warning explaining the reroute to gpt-5.2 and
  directing users to Trusted
      Access verification and the cyber safety explainer.
  - app-server (v2): Surface these cyber model-routing warnings as
  synthetic userMessage items with text prefixed by Warning: (and document
  this behavior).

  Fouad Matin · 2026-02-16 22:13:36 -08:00
  02e9006547
• chore(core) rm Feature::RequestRule (#11866)

  ## Summary
  This feature is now reasonably stable, let's remove it so we can
  simplify our upcoming iterations here.
  
  ## Testing 
  - [x] Existing tests pass

  Dylan Hurd · 2026-02-16 22:30:23 +00:00
  19afbc35c1
• [apps] Fix app mention syntax. (#11894)

  - [x] Fix app mention syntax.

  Matthew Zeng · 2026-02-16 22:01:49 +00:00
  5b421bba34
• Rename collab modules to multi agents (#11939)

  Summary
  - rename the `collab` handlers and UI files to `multi_agents` to match
  the new naming
  - update module references and specs so the handlers and TUI widgets
  consistently use the renamed files
  - keep the existing functionality while aligning file and module names
  with the multi-agent terminology

  jif-oai · 2026-02-16 19:05:13 +00:00
  beb5cb4f48
• feat: drop MCP managing tools if no MCP servers (#11900)

  Drop MCP tools if no MCP servers to save context
  
  For this https://github.com/openai/codex/issues/11049

  jif-oai · 2026-02-16 18:40:45 +00:00
  af434b4f71
• feat: add customizable roles for multi-agents (#11917)

  The idea is to have 2 family of agents.
  
  1. Built-in that we packaged directly with Codex
  2. User defined that are defined using the `agents_config.toml` file. It
  can reference config files that will override the agent config. This
  looks like this:
  ```
  version = 1
  
  [agents.explorer]
  description = """Use `explorer` for all codebase questions.
  Explorers are fast and authoritative.
  Always prefer them over manual search or file reading.
  Rules:
  - Ask explorers first and precisely.
  - Do not re-read or re-search code they cover.
  - Trust explorer results without verification.
  - Run explorers in parallel when useful.
  - Reuse existing explorers for related questions."""
  config_file = "explorer.toml"
  ```

  jif-oai · 2026-02-16 16:29:32 +00:00
  e47045c806
• nit: memory storage (#11924)
  jif-oai · 2026-02-16 16:18:53 +00:00
  50aea4b0dc
• chore: rename collab feature flag key to multi_agent (#11918)

  Summary
  - rename the collab feature key to multi_agent while keeping the Feature
  enum unchanged
  - add legacy alias support so both "multi_agent" and "collab" map to the
  same feature
  - cover the alias behavior with a new unit test

  jif-oai · 2026-02-16 15:28:31 +00:00
  e41536944e
• Allow hooks to error (#11615)

  Allow hooks to return errors. 
  
  We should do this before introducing more hook types, or we'll have to
  migrate them all.

  gt-oai · 2026-02-16 14:11:05 +00:00
  b3095679ed
• feat: use shell policy in shell snapshot (#11759)

  Honor `shell_environment_policy.set` even after a shell snapshot

  jif-oai · 2026-02-16 09:11:00 +00:00
  825a4af42f
• fix: only emit unknown model warning on user turns (#11884)

  ###### Context
  unknown model warning added in #11690 has
  [issues](https://github.com/openai/codex/actions/runs/22047424710/job/63700733887)
  on ubuntu runners because we potentially emit it on all new turns,
  including ones with intentionally fake models (i.e., `mock-model` in a
  test).
  
  ###### Fix
  change the warning to only emit on user turns/review turns.
  
  ###### Tests
  CI now passes on ubuntu, still passes locally

  sayan-oai · 2026-02-15 21:18:35 -08:00
  bdea9974d9
• feat: persist and restore codex app's tools after search (#11780)

  ### What changed
  1. Removed per-turn MCP selection reset in `core/src/tasks/mod.rs`.
  2. Added `SessionState::set_mcp_tool_selection(Vec<String>)` in
  `core/src/state/session.rs` for authoritative restore behavior (deduped,
  order-preserving, empty clears).
  3. Added rollout parsing in `core/src/codex.rs` to recover
  `active_selected_tools` from prior `search_tool_bm25` outputs:
     - tracks matching `call_id`s
     - parses function output text JSON
     - extracts `active_selected_tools`
     - latest valid payload wins
     - malformed/non-matching payloads are ignored
  4. Applied restore logic to resumed and forked startup paths in
  `core/src/codex.rs`.
  5. Updated instruction text to session/thread scope in
  `core/templates/search_tool/tool_description.md`.
  6. Expanded tests in `core/tests/suite/search_tool.rs`, plus unit
  coverage in:
     - `core/src/codex.rs`
     - `core/src/state/session.rs`
  
  ### Behavior after change
  1. Search activates matched tools.
  2. Additional searches union into active selection.
  3. Selection survives new turns in the same thread.
  4. Resume/fork restores selection from rollout history.
  5. Separate threads do not inherit selection unless forked.

  Anton Panasenko · 2026-02-15 19:18:41 -08:00
  02abd9a8ea
• fix: show user warning when using default fallback metadata (#11690)

  ### What
  It's currently unclear when the harness falls back to the default,
  generic `ModelInfo`. This happens when the `remote_models` feature is
  disabled or the model is truly unknown, and can lead to bad performance
  and issues in the harness.
  
  Add a user-facing warning when this happens so they are aware when their
  setup is broken.
  
  ### Tests
  Added tests, tested locally.

  sayan-oai · 2026-02-15 18:46:05 -08:00
  060a320e7d
• fix(core): add linux bubblewrap sandbox tag (#11767)

  ## Summary
  - add a distinct `linux_bubblewrap` sandbox tag when the Linux
  bubblewrap pipeline feature is enabled
  - thread the bubblewrap feature flag into sandbox tag generation for:
    - turn metadata header emission
    - tool telemetry metric tags and after-tool-use hooks
  - add focused unit tests for `sandbox_tag` precedence and Linux
  bubblewrap behavior
  
  ## Validation
  - `just fmt`
  - `cargo clippy -p codex-core --all-targets`
  - `cargo test -p codex-core sandbox_tags::tests`
  - started `cargo test -p codex-core` and stopped it per request
  
  Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>

  viyatb-oai · 2026-02-14 19:00:01 +00:00
  db6aa80195
• feat(core): add structured network approval plumbing and policy decision model (#11672)

  ### Description
  #### Summary
  Introduces the core plumbing required for structured network approvals
  
  #### What changed
  - Added structured network policy decision modeling in core.
  - Added approval payload/context types needed for network approval
  semantics.
  - Wired shell/unified-exec runtime plumbing to consume structured
  decisions.
  - Updated related core error/event surfaces for structured handling.
  - Updated protocol plumbing used by core approval flow.
  - Included small CLI debug sandbox compatibility updates needed by this
  layer.
  
  #### Why
  establishes the minimal backend foundation for network approvals without
  yet changing high-level orchestration or TUI behavior.
  
  #### Notes
  - Behavior remains constrained by existing requirements/config gating.
  - Follow-up PRs in the stack handle orchestration, UX, and app-server
  integration.
  
  ---------
  
  Co-authored-by: Codex <199175422+chatgpt-codex-connector[bot]@users.noreply.github.com>

  viyatb-oai · 2026-02-14 04:18:12 +00:00
  b527ee2890
• Handle model-switch base instructions after compaction (#11659)

  Strip trailing <model_switch> during model-switch compaction request,
  and append <model_switch> after model switch compaction

  Charley Cunningham · 2026-02-13 19:02:53 -08:00
  67e577da53
• add perf metrics for connectors load (#11803)
  alexsong-oai · 2026-02-13 18:15:07 -08:00
  8156c57234
• feat(skills): add permission profiles from openai.yaml metadata (#11658)

  ## Summary
  
  This PR adds support for skill-level permissions in .codex/openai.yaml
  and wires that through the skill loading pipeline.
  
    ## What’s included
  
  1. Added a new permissions section for skills (network, filesystem, and
  macOS-related access).
  2. Implemented permission parsing/normalization and translation into
  runtime permission profiles.
  3. Threaded the new permission profile through SkillMetadata and loader
  flow.
  
    ## Follow-up
  
  A follow-up PR will connect these permission profiles to actual sandbox
  enforcement and add user approval prompts for executing binaries/scripts
  from skill directories.
  
  
   ## Example 
  `openai.yaml` snippet:
  ```
    permissions:
      network: true
      fs_read:
        - "./data"
        - "./data"
      fs_write:
        - "./output"
      macos_preferences: "readwrite"
      macos_automation:
        - "com.apple.Notes"
      macos_accessibility: true
      macos_calendar: true
  ```
  
  compiled skill permission profile metadata (macOS): 
  ```
  SkillPermissionProfile {
        sandbox_policy: SandboxPolicy::WorkspaceWrite {
            writable_roots: vec![
                AbsolutePathBuf::try_from("/ABS/PATH/TO/SKILL/output").unwrap(),
            ],
            read_only_access: ReadOnlyAccess::Restricted {
                include_platform_defaults: true,
                readable_roots: vec![
                    AbsolutePathBuf::try_from("/ABS/PATH/TO/SKILL/data").unwrap(),
                ],
            },
            network_access: true,
            exclude_tmpdir_env_var: false,
            exclude_slash_tmp: false,
        },
        // Truncated for readability; actual generated profile is longer.
        macos_seatbelt_permission_file: r#"
    (allow user-preference-write)
    (allow appleevent-send
        (appleevent-destination "com.apple.Notes"))
    (allow mach-lookup (global-name "com.apple.axserver"))
    (allow mach-lookup (global-name "com.apple.CalendarAgent"))
    ...
    "#.to_string(),
  ```

  Celia Chen · 2026-02-14 01:43:44 +00:00
  5b6911cb1b
• Fix js_repl in-flight tool-call waiter race (#11800)

  ## Summary
  
  This PR fixes a race in `js_repl` tool-call draining that could leave an
  exec waiting indefinitely for in-flight tool calls to finish.
  
  The fix is in:
  
  -
  `/Users/fjord/code/codex-jsrepl-seq/codex-rs/core/src/tools/js_repl/mod.rs`
  
  ## Problem
  
  `js_repl` tracks in-flight tool calls per exec and waits for them to
  drain on completion/timeout/cancel paths.
  The previous wait logic used a check-then-wait pattern with `Notify`
  that could miss a wakeup:
  
  1. Observe `in_flight > 0`
  2. Drop lock
  3. Register wait (`notified().await`)
  
  If `notify_waiters()` happened between (2) and (3), the waiter could
  sleep until another notification that never comes.
  
  ## What changed
  
  - Updated all exec-tool-call wait loops to create an owned notification
  future while holding the lock:
  - use `Arc<Notify>::notified_owned()` instead of cloning notify and
  awaiting later.
  - Applied this consistently to:
    - `wait_for_exec_tool_calls`
    - `wait_for_all_exec_tool_calls`
    - `wait_for_exec_tool_calls_map`
  
  This preserves existing behavior while eliminating the lost-wakeup
  window.
  
  ## Test coverage
  
  Added a regression test:
  
  - `wait_for_exec_tool_calls_map_drains_inflight_calls_without_hanging`
  
  The test repeatedly races waiter/finisher tasks and asserts bounded
  completion to catch hangs.
  
  ## Impact
  
  - No API changes.
  - No user-facing behavior changes intended.
  - Improves reliability of exec lifecycle boundaries when tool calls are
  still in flight.
  
  
  #### [git stack](https://github.com/magus/git-stack-cli)
  - ✅ `1` https://github.com/openai/codex/pull/11796
  - 👉 `2` https://github.com/openai/codex/pull/11800
  - ⏳ `3` https://github.com/openai/codex/pull/10673
  - ⏳ `4` https://github.com/openai/codex/pull/10670

  Curtis 'Fjord' Hawthorne · 2026-02-14 01:24:52 +00:00
  0d76d029b7
• Fix js_repl view_image test runtime panic (#11796)

  ## Summary
  Fixes a flaky/panicking `js_repl` image-path test by running it on a
  multi-thread Tokio runtime and tightening assertions to focus on real
  behavior.
  
  ## Problem
  `js_repl_can_attach_image_via_view_image_tool` in  
  
  `/Users/fjord/code/codex-jsrepl-seq/codex-rs/core/src/tools/js_repl/mod.rs`
  can panic under single-thread test runtime with:
  
  `can call blocking only when running on the multi-threaded runtime`
  
  It also asserted a brittle user-facing text string.
  
  ## Changes
  1. Updated the test runtime to:
     `#[tokio::test(flavor = "multi_thread", worker_threads = 2)]`
  2. Removed the brittle `"attached local image path"` string assertion.
  3. Kept the concrete side-effect assertions:
     - tool call succeeds
  - image is actually injected into pending input (`InputImage` with
  `data:image/png;base64,...`)
  
  ## Why this is safe
  This is test-only behavior. No production runtime code paths are
  changed.
  
  ## Validation
  - Ran:
  `cargo test -p codex-core
  tools::js_repl::tests::js_repl_can_attach_image_via_view_image_tool --
  --nocapture`
  - Result: pass
  
  
  #### [git stack](https://github.com/magus/git-stack-cli)
  - 👉 `1` https://github.com/openai/codex/pull/11796
  - ⏳ `2` https://github.com/openai/codex/pull/11800
  - ⏳ `3` https://github.com/openai/codex/pull/10673
  - ⏳ `4` https://github.com/openai/codex/pull/10670

  Curtis 'Fjord' Hawthorne · 2026-02-14 01:11:13 +00:00
  6cbb489e6e