2420 Commits

• Use AbsolutePathBuf for cwd state (#15710)

  Migrate `cwd` and related session/config state to `AbsolutePathBuf` so
  downstream consumers consistently see absolute working directories.
  
  Add test-only `.abs()` helpers for `Path`, `PathBuf`, and `TempDir`, and
  update branch-local tests to use them instead of
  `AbsolutePathBuf::try_from(...)`.
  
  For the remaining TUI/app-server snapshot coverage that renders absolute
  cwd values, keep the snapshots unchanged and skip the Windows-only cases
  where the platform-specific absolute path layout differs.

  pakrym-oai · 2026-03-25 16:02:22 +00:00
  504aeb0e09
• chore: remove grep_files handler (#15775)

  # External (non-OpenAI) Pull Request Requirements
  
  Before opening this Pull Request, please read the dedicated
  "Contributing" markdown file or your PR may be closed:
  https://github.com/openai/codex/blob/main/docs/contributing.md
  
  If your PR conforms to our contribution guidelines, replace this text
  with a detailed and high quality description of your changes.
  
  Include a link to a bug report or enhancement request.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  jif-oai · 2026-03-25 16:01:45 +00:00
  178c3b15b4
• fix(core): default approval behavior for mcp missing annotations (#15519)

  - Changed `requires_mcp_tool_approval` to apply MCP spec defaults when
  annotations are missing.
  - Unannotated tools now default to:
    - `readOnlyHint = false`
    - `destructiveHint = true`
    - `openWorldHint = true`
  - This means unannotated MCP tools now go through approval/ARC
  monitoring instead of silently bypassing it.
  - Explicitly read-only tools still skip approval unless they are also
  explicitly marked destructive.
  
  **Previous behavior**
  Failed open for missing annotations, which was unsafe for custom MCP
  tools that omitted or forgot annotations.
  
  ---------
  
  Co-authored-by: colby-oai <228809017+colby-oai@users.noreply.github.com>

  Fouad Matin · 2026-03-25 07:55:41 -07:00
  32c4993c8a
• chore: tty metric (#15766)
  jif-oai · 2026-03-25 13:34:43 +00:00
  047ea642d2
• [plugins] Add a flag for tool search. (#15722)

  - [x] Add a flag for tool search.

  Matthew Zeng · 2026-03-25 07:00:25 +00:00
  e590fad50b
• fix: support split carveouts in windows restricted-token sandbox (#14172)

  ## Summary
  - keep legacy Windows restricted-token sandboxing as the supported
  baseline
  - support the split-policy subset that restricted-token can enforce
  directly today
  - support full-disk read, the same writable root set as legacy
  `WorkspaceWrite`, and extra read-only carveouts under those writable
  roots via additional deny-write ACLs
  - continue to fail closed for unsupported split-only shapes, including
  explicit unreadable (`none`) carveouts, reopened writable descendants
  under read-only carveouts, and writable root sets that do not match the
  legacy workspace roots
  
  ## Example
  Given a filesystem policy like:
  
  ```toml
  ":root" = "read"
  ":cwd" = "write"
  "./docs" = "read"
  ```
  
  the restricted-token backend can keep the workspace writable while
  denying writes under `docs` by layering an extra deny-write carveout on
  top of the legacy workspace-write roots.
  
  A policy like:
  
  ```toml
  "/workspace" = "write"
  "/workspace/docs" = "read"
  "/workspace/docs/tmp" = "write"
  ```
  
  still fails closed, because the unelevated backend cannot reopen the
  nested writable descendant safely.
  
  ## Stack
  -> fix: support split carveouts in windows restricted-token sandbox
  #14172
  fix: support split carveouts in windows elevated sandbox #14568

  viyatb-oai · 2026-03-24 22:54:18 -07:00
  95ba762620
• [plugins] Flip on additional flags. (#15719)

  - [x] Flip on additional flags.

  Matthew Zeng · 2026-03-24 21:52:11 -07:00
  8c62829a2b
• [plugins] Flip the flags. (#15713)

  - [x] Flip the `plugins` and `apps` flags.

  Matthew Zeng · 2026-03-25 03:31:21 +00:00
  0bff38c54a
• [codex] Defer fork context injection until first turn (#15699)

  ## Summary
  - remove the fork-startup `build_initial_context` injection
  - keep the reconstructed `reference_context_item` as the fork baseline
  until the first real turn
  - update fork-history tests and the request snapshot, and add a
  `TODO(ccunningham)` for remaining nondiffable initial-context inputs
  
  ## Why
  Fork startup was appending current-session initial context immediately
  after reconstructing the parent rollout, then the first real turn could
  emit context updates again. That duplicated model-visible context in the
  child rollout.
  
  ## Impact
  Forked sessions now behave like resume for context seeding: startup
  reconstructs history and preserves the prior baseline, and the first
  real turn handles any current-session context emission.
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-24 18:34:44 -07:00
  d72fa2a209
• Extract rollout into its own crate (#15548)
  Ahmed Ibrahim · 2026-03-24 18:10:53 -07:00
  2e03d8b4d2
• Expand ~ in MDM workspace write roots (#15351)

  ## Summary
  - Reuse the existing config path resolver for the macOS MDM managed
  preferences layer so `writable_roots = ["~/code"]` expands the same way
  as file-backed config
  - keep the change scoped to the MDM branch in `config_loader`; the
  current net diff is only `config_loader/mod.rs` plus focused regression
  tests in `config_loader/tests.rs` and `config/service_tests.rs`
  - research note: `resolve_relative_paths_in_config_toml(...)` is already
  used in several existing configuration paths, including [CLI
  overrides](https://github.com/openai/codex/blob/74fda242d3651f0a43ec8657bdbc7bde426dce0e/codex-rs/core/src/config_loader/mod.rs#L152-L163),
  [file-backed managed
  config](https://github.com/openai/codex/blob/74fda242d3651f0a43ec8657bdbc7bde426dce0e/codex-rs/core/src/config_loader/mod.rs#L274-L285),
  [normal config-file
  loading](https://github.com/openai/codex/blob/74fda242d3651f0a43ec8657bdbc7bde426dce0e/codex-rs/core/src/config_loader/mod.rs#L311-L331),
  [project `.codex/config.toml`
  loading](https://github.com/openai/codex/blob/74fda242d3651f0a43ec8657bdbc7bde426dce0e/codex-rs/core/src/config_loader/mod.rs#L863-L865),
  and [role config
  loading](https://github.com/openai/codex/blob/74fda242d3651f0a43ec8657bdbc7bde426dce0e/codex-rs/core/src/agent/role.rs#L105-L109)
  
  ## Validation
  - `cargo fmt --all --check`
  - `cargo test -p codex-core
  managed_preferences_expand_home_directory_in_workspace_write_roots --
  --nocapture`
  - `cargo test -p codex-core
  write_value_succeeds_when_managed_preferences_expand_home_directory_paths
  -- --nocapture`
  
  ---------
  
  Co-authored-by: Michael Bolin <mbolin@openai.com>
  Co-authored-by: Michael Bolin <bolinfest@gmail.com>

  evawong-oai · 2026-03-24 17:55:06 -07:00
  ea3f3467e2
• fix: keep rmcp-client env vars as OsString (#15363)

  ## Why
  
  This is a follow-up to #15360. That change fixed the `arg0` helper
  setup, but `rmcp-client` still coerced stdio transport environment
  values into UTF-8 `String`s before program resolution and process spawn.
  If `PATH` or another inherited environment value contains non-UTF-8
  bytes, that loses fidelity before it reaches `which` and `Command`.
  
  ## What changed
  
  - change `create_env_for_mcp_server()` to return `HashMap<OsString,
  OsString>` and read inherited values with `std::env::var_os()`
  - change `TransportRecipe::Stdio.env`, `RmcpClient::new_stdio_client()`,
  and `program_resolver::resolve()` to keep stdio transport env values in
  `OsString` form within `rmcp-client`
  - keep the `codex-core` config boundary stringly, but convert configured
  stdio env values to `OsString` once when constructing the transport
  - update the rmcp-client stdio test fixtures and callers to use
  `OsString` env maps
  - add a Unix regression test that verifies `create_env_for_mcp_server()`
  preserves a non-UTF-8 `PATH`
  
  ## How to verify
  
  - `cargo test -p codex-rmcp-client`
  - `cargo test -p codex-core mcp_connection_manager`
  - `just argument-comment-lint`
  
  Targeted coverage in this change includes
  `utils::tests::create_env_preserves_path_when_it_is_not_utf8`, while the
  updated stdio transport path is exercised by the existing rmcp-client
  tests that construct `RmcpClient::new_stdio_client()`.

  Michael Bolin · 2026-03-24 23:32:31 +00:00
  4a210faf33
• Move string truncation helpers into codex-utils-string (#15572)

  - move the shared byte-based middle truncation logic from `core` into
  `codex-utils-string`
  - keep token-specific truncation in `codex-core` so rollout can reuse
  the shared helper in the next stacked PR
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-03-24 15:45:40 -07:00
  062fa7a2bb
• Drop sandbox_permissions from sandbox exec requests (#15665)

  ## Summary
  - drop `sandbox_permissions` from the sandboxing `ExecOptions` and
  `ExecRequest` adapter types
  - remove the now-unused plumbing from shell, unified exec, JS REPL, and
  apply-patch runtime call sites
  - default reconstructed `ExecParams` to `SandboxPermissions::UseDefault`
  where the lower-level API still requires the field
  
  ## Testing
  - `just fmt`
  - `just argument-comment-lint`
  - `cargo test -p codex-core` (still running locally; first failures
  observed in `suite::cli_stream::responses_mode_stream_cli`,
  `suite::cli_stream::responses_mode_stream_cli_supports_openai_base_url_config_override`,
  and
  `suite::cli_stream::responses_mode_stream_cli_supports_openai_base_url_env_fallback`)

  pakrym-oai · 2026-03-24 15:42:45 -07:00
  0b619afc87
• [plugins] Additional gating for tool suggest and apps. (#15573)

  - [x] Additional gating for tool suggest and apps.

  Matthew Zeng · 2026-03-24 15:10:00 -07:00
  b32d921cd9
• Move git utilities into a dedicated crate (#15564)

  - create `codex-git-utils` and move the shared git helpers into it with
  file moves preserved for diff readability
  - move the `GitInfo` helpers out of `core` so stacked rollout work can
  depend on the shared crate without carrying its own git info module
  
  ---------
  
  Co-authored-by: Ahmed Ibrahim <219906144+aibrahim-oai@users.noreply.github.com>
  Co-authored-by: Codex <noreply@openai.com>

  Ahmed Ibrahim · 2026-03-24 13:26:23 -07:00
  0f957a93cd
• fix: keep zsh-fork release assets after removing shell-tool-mcp (#15644)

  ## Why
  
  `shell-tool-mcp` and the Bash fork are no longer needed, but the patched
  zsh fork is still relevant for shell escalation and for the
  DotSlash-backed zsh-fork integration tests.
  
  Deleting the old `shell-tool-mcp` workflow also deleted the only
  pipeline that rebuilt those patched zsh binaries. This keeps the package
  removal, while preserving a small release path that can be reused
  whenever `codex-rs/shell-escalation/patches/zsh-exec-wrapper.patch`
  changes.
  
  ## What changed
  
  - removed the `shell-tool-mcp` workspace package, its npm
  packaging/release jobs, the Bash test fixture, and the remaining
  Bash-specific compatibility wiring
  - deleted the old `.github/workflows/shell-tool-mcp.yml` and
  `.github/workflows/shell-tool-mcp-ci.yml` workflows now that their
  responsibilities have been replaced or removed
  - kept the zsh patch under
  `codex-rs/shell-escalation/patches/zsh-exec-wrapper.patch` and updated
  the `codex-rs/shell-escalation` docs/code to describe the zsh-based flow
  directly
  - added `.github/workflows/rust-release-zsh.yml` to build only the three
  zsh binaries that `codex-rs/app-server/tests/suite/zsh` needs today:
    - `aarch64-apple-darwin` on `macos-15`
    - `x86_64-unknown-linux-musl` on `ubuntu-24.04`
    - `aarch64-unknown-linux-musl` on `ubuntu-24.04`
  - extracted the shared zsh build/smoke-test/stage logic into
  `.github/scripts/build-zsh-release-artifact.sh`, made that helper
  directly executable, and now invoke it directly from the workflow so the
  Linux and macOS jobs only keep the OS-specific setup in YAML
  - wired those standalone `codex-zsh-*.tar.gz` assets into
  `rust-release.yml` and added `.github/dotslash-zsh-config.json` so
  releases also publish a `codex-zsh` DotSlash file
  - updated the checked-in `codex-rs/app-server/tests/suite/zsh` fixture
  comments to explain that new releases come from the standalone zsh
  assets, while the checked-in fixture remains pinned to the latest
  historical release until a newer zsh artifact is published
  - tightened a couple of follow-on cleanups in
  `codex-rs/shell-escalation`: the `ExecParams::command` comment now
  describes the shell `-c`/`-lc` string more clearly, and the README now
  points at the same `git.code.sf.net` zsh source URL that the workflow
  uses
  
  ## Testing
  
  - `cargo test -p codex-shell-escalation`
  - `just argument-comment-lint`
  - `bash -n .github/scripts/build-zsh-release-artifact.sh`
  - attempted `cargo test -p codex-core`; unrelated existing failures
  remain, but the touched `tools::runtimes::shell::unix_escalation::*`
  coverage passed during that run

  Michael Bolin · 2026-03-24 12:56:26 -07:00
  e89e5136bd
• Trim pre-turn context updates during rollback (#15577)

  ## Summary
  - trim contiguous developer/contextual-user pre-turn updates when
  rollback cuts back to a user turn
  - add a focused history regression test for the trim behavior
  - update the rollback request-boundary snapshots to show the fixed
  non-duplicating context shape
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-24 12:43:53 -07:00
  2d61357c76
• chore: stop app-server auth refresh storms after permanent token failure (#15530)

  built from #14256. PR description from @etraut-openai:
  
  This PR addresses a hole in [PR
  11802](https://github.com/openai/codex/pull/11802). The previous PR
  assumed that app server clients would respond to token refresh failures
  by presenting the user with an error ("you must log in again") and then
  not making further attempts to call network endpoints using the expired
  token. While they do present the user with this error, they don't
  prevent further attempts to call network endpoints and can repeatedly
  call `getAuthStatus(refreshToken=true)` resulting in many failed calls
  to the token refresh endpoint.
  
  There are three solutions I considered here:
  1. Change the getAuthStatus app server call to return a null auth if the
  caller specified "refreshToken" on input and the refresh attempt fails.
  This will cause clients to immediately log out the user and return them
  to the log in screen. This is a really bad user experience. It's also a
  breaking change in the app server contract that could break third-party
  clients.
  2. Augment the getAuthStatus app server call to return an additional
  field that indicates the state of "token could not be refreshed". This
  is a non-breaking change to the app server API, but it requires
  non-trivial changes for all clients to properly handle this new field
  properly.
  3. Change the getAuthStatus implementation to handle the case where a
  token refresh fails by marking the AuthManager's in-memory access and
  refresh tokens as "poisoned" so it they are no longer used. This is the
  simplest fix that requires no client changes.
  
  I chose option 3.
  
  Here's Codex's explanation of this change:
  
  When an app-server client asks `getAuthStatus(refreshToken=true)`, we
  may try to refresh a stale ChatGPT access token. If that refresh fails
  permanently (for example `refresh_token_reused`, expired, or revoked),
  the old behavior was bad in two ways:
  
  1. We kept the in-memory auth snapshot alive as if it were still usable.
  2. Later auth checks could retry refresh again and again, creating a
  storm of doomed `/oauth/token` requests and repeatedly surfacing the
  same failure.
  
  This is especially painful for app-server clients because they poll auth
  status and can keep driving the refresh path without any real chance of
  recovery.
  
  This change makes permanent refresh failures terminal for the current
  managed auth snapshot without changing the app-server API contract.
  
  What changed:
  - `AuthManager` now poisons the current managed auth snapshot in memory
  after a permanent refresh failure, keyed to the unchanged `AuthDotJson`.
  - Once poisoned, later refresh attempts for that same snapshot fail fast
  locally without calling the auth service again.
  - The poison is cleared automatically when auth materially changes, such
  as a new login, logout, or reload of different auth state from storage.
  - `getAuthStatus(includeToken=true)` now omits `authToken` after a
  permanent refresh failure instead of handing out the stale cached bearer
  token.
  
  This keeps the current auth method visible to clients, avoids forcing an
  immediate logout flow, and stops repeated refresh attempts for
  credentials that cannot recover.
  
  ---------
  
  Co-authored-by: Eric Traut <etraut@openai.com>

  Celia Chen · 2026-03-24 12:39:58 -07:00
  88694e8417
• chore: use access token expiration for proactive auth refresh (#15545)

  Follow up to #15357 by making proactive ChatGPT auth refresh depend on
  the access token's JWT expiration instead of treating `last_refresh` age
  as the primary source of truth.

  Celia Chen · 2026-03-24 19:34:48 +00:00
  7dc2cd2ebe
• feat: include marketplace loading error in plugin/list (#15438)

  Include error.

  xl-openai · 2026-03-24 11:47:23 -07:00
  621862a7d1
• feat: communication pattern v2 (#15647)

  See internal communication

  jif-oai · 2026-03-24 18:45:49 +00:00
  773fbf56a4
• core: Make FileWatcher reusable (#15093)

  ### Summary
  Make `FileWatcher` a reusable core component which can be built upon.
  Extract skills-related logic into a separate `SkillWatcher`.
  Introduce a composable `ThrottledWatchReceiver` to throttle filesystem
  events, coalescing affected paths among them.
  
  ### Testing
  Updated existing unit tests.

  Ruslan Nigmatullin · 2026-03-24 11:04:47 -07:00
  daf5e584c2
• Pretty plugin labels, preserve plugin app provenance during MCP tool refresh (#15606)

  - Prefer plugin manifest `interface.displayName` for plugin labels.
  - Preserve plugin provenance when handling `list_mcp_tools` so connector
  `plugin_display_names` are not clobbered.
  - Add a TUI test to ensure plugin-owned app mentions are deduped
  correctly.

  canvrno-oai · 2026-03-24 10:34:19 -07:00
  66edc347ae
• [codex] Stabilize second compaction history test (#15605)

  ## Summary
  - replace the second-compaction test fixtures with a single ordered
  `/responses` sequence
  - assert against the real recorded request order instead of aggregating
  per-mock captures
  - realign the second-summary assertion to the first post-compaction user
  turn where the summary actually appears
  
  ## Root cause
  `compact_resume_after_second_compaction_preserves_history` collected
  requests from multiple `mount_sse_once_match` recorders. Overlapping
  matchers could record the same HTTP request more than once, so the test
  indexed into a duplicated synthetic list rather than the true request
  stream. That made the summary assertion depend on matcher evaluation
  order and platform-specific behavior.
  
  ## Impact
  - makes the flaky test deterministic by removing duplicate request
  capture from the assertion path
  - keeps the change scoped to the test only
  
  ## Validation
  - `just fmt`
  - `just argument-comment-lint`
  - `env -u CODEX_SANDBOX_NETWORK_DISABLED cargo test -p codex-core
  compact_resume_after_second_compaction_preserves_history -- --nocapture`
  - repeated the same targeted test 10 times
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-24 10:14:21 -07:00
  910cf49269
• feat: disable notifier v2 and start turn on agent interaction (#15624)

  Make the inter-agent communication start a turn
  
  As part of this, we disable the v2 notifier to prevent some odd
  behaviour where the agent restart working while you're talking to it for
  example

  jif-oai · 2026-03-24 17:01:24 +00:00
  b51d5f18c7
• Extract sandbox manager and transforms into codex-sandboxing (#15603)

  Extract sandbox manager

  pakrym-oai · 2026-03-24 08:20:57 -07:00
  f49eb8e9d7
• nit: optim on list agents (#15623)

  Lazy computation

  jif-oai · 2026-03-24 12:01:01 +00:00
  95e1d59939
• feat: list agents for sub-agent v2 (#15621)

  Add a `list_agents` for multi-agent v2, optionally path based
  
  This return the task and status of each agent in the matched path

  jif-oai · 2026-03-24 11:24:08 +00:00
  38c088ba8d
• fix: flaky test (#15614)
  jif-oai · 2026-03-24 11:01:54 +00:00
  567832c6fe
• nit: split v2 wait (#15613)
  jif-oai · 2026-03-24 09:57:19 +00:00
  f9545278e2
• Remove filter from plugins/list result (#15580)

  Show all plugin marketplaces in the /plugins popup by removing the
  `openai-curated` marketplace filter, and update plugin popup
  copy/tests/snapshots to match the new behavior in both TUI codepaths.

  canvrno-oai · 2026-03-23 23:41:01 -07:00
  c850607129
• Move sandbox policy transforms into codex-sandboxing (#15599)

  ## Summary
  - move the pure sandbox policy transform helpers from `codex-core` into
  `codex-sandboxing`
  - move the corresponding unit tests with the extracted implementation
  - update `core` and `app-server` callers to import the moved APIs
  directly, without re-exports or proxy methods
  
  ## Testing
  - cargo test -p codex-sandboxing
  - cargo test -p codex-core sandboxing
  - cargo test -p codex-app-server --lib
  - just fix -p codex-sandboxing
  - just fix -p codex-core
  - just fix -p codex-app-server
  - just fmt
  - just argument-comment-lint

  pakrym-oai · 2026-03-23 22:22:44 -07:00
  9deb8ce3fc
• [codex-cli][app-server] Update self-serve business usage limit copy in error returned (#15478)

  ## Summary
  - update the self-serve business usage-based limit message to direct
  users to their admin for additional credits
  - add a focused unit test for the self_serve_business_usage_based plan
  branch
  
  Added also: 
  
  If you are at a rate limit but you still have credits, codex cli would
  tell you to switch the model. We shouldnt do this if you have credits so
  fixed this.
  
  ## Test
  - launched the source-built CLI and verified the updated message is
  shown for the self-serve business usage-based plan
  
  ![Test
  screenshot](https://raw.githubusercontent.com/openai/codex/5cc3c013ef17ac5c66dfd9395c0d3c4837602231/docs/images/self-serve-business-usage-limit.png)

  dhruvgupta-oai · 2026-03-24 04:41:38 +00:00
  c2410060ea
• Move macOS sandbox builders into codex-sandboxing (#15593)

  ## Summary
  - move macOS permission merging/intersection logic and tests from
  `codex-core` into `codex-sandboxing`
  - move seatbelt policy builders, permissions logic, SBPL assets, and
  their tests into `codex-sandboxing`
  - keep `codex-core` owning only the seatbelt spawn wrapper and switch
  call sites to import the moved APIs directly
  
  ## Notes
  - no re-exports added
  - moved the seatbelt tests with the implementation so internal helpers
  could stay private
  - local verification is still finishing while this PR is open

  pakrym-oai · 2026-03-23 21:26:35 -07:00
  431af0807c
• Extract landlock helpers into codex-sandboxing (#15592)

  ## Summary
  - add a new `codex-sandboxing` crate for sandboxing extraction work
  - move the pure Linux sandbox argv builders and their unit tests out of
  `codex-core`
  - keep `core::landlock` as the spawn wrapper and update direct callers
  to use `codex_sandboxing::landlock`
  
  ## Testing
  - `cargo test -p codex-sandboxing`
  - `cargo test -p codex-core landlock`
  - `cargo test -p codex-cli debug_sandbox`
  - `just argument-comment-lint`
  
  ## Notes
  - this is step 1 of the move plan aimed at minimizing per-PR diffs
  - no re-exports or no-op proxy methods were added

  pakrym-oai · 2026-03-23 20:56:15 -07:00
  2227248cd6
• Add fork snapshot modes (#15239)

  ## Summary
  - add `ForkSnapshotMode` to `ThreadManager::fork_thread` so callers can
  request either a committed snapshot or an interrupted snapshot
  - share the model-visible `<turn_aborted>` history marker between the
  live interrupt path and interrupted forks
  - update the small set of direct fork callsites to pass
  `ForkSnapshotMode::Committed`
  
  Note: this enables /btw to work similarly as Esc to interrupt (hopefully
  somewhat in distribution)
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-23 19:05:42 -07:00
  f547b79bd0
• feat: custom watcher for multi-agent v2 (#15576)

  The new wait tool just returns `Wait timed out.` or `Wait completed.`.
  The actual content is done through the notification watcher

  jif-oai · 2026-03-23 23:27:55 +00:00
  527244910f
• feat: custom watcher for multi-agent v2 (#15570)

  Custom watcher that sends an InterAgentCommunication on end of turn

  jif-oai · 2026-03-23 22:56:17 +00:00
  4605c65308
• [codex] Add rollback context duplication snapshot (#15562)

  ## What changed
  - adds a targeted snapshot test for rollback with contextual diffs in
  `codex_tests.rs`
  - snapshots the exact model-visible request input before the rolled-back
  turn and on the follow-up request after rollback
  - shows the duplicate developer and environment context pair appearing
  again before the follow-up user message
  
  ## Why
  Rollback currently rewinds the reference context baseline without
  rewinding the live session overrides. On the next turn, the same
  contextual diff is emitted again and duplicated in the request sent to
  the model.
  
  ## Impact
  - makes the regression visible in a canonical snapshot test
  - keeps the snapshot on the shared `context_snapshot` path without
  adding new formatting helpers
  - gives a direct repro for future fixes to rollback/context
  reconstruction
  
  ---------
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-23 15:36:23 -07:00
  0f34b14b41
• chore(core) Add approvals reviewer to UserTurn (#15426)

  ## Summary
  Adds support for approvals_reviewer to `Op::UserTurn` so we can migrate
  `[CodexMessageProcessor::turn_start]` to use Op::UserTurn
  
  ## Testing
  - [x] Adds quick test for the new field
  
  Co-authored-by: Codex <noreply@openai.com>

  Dylan Hurd · 2026-03-23 15:19:01 -07:00
  67c1c7c054
• feat: use serde to differenciate inter agent communication (#15560)

  Use `serde` to encode the inter agent communication to an assistant
  message and use the decode to see if this is such a message
  
  Note: this assume serde on small pattern is fast enough

  jif-oai · 2026-03-23 22:09:55 +00:00
  191fd9fd16
• [hooks] add non-streaming (non-stdin style) shell-only PreToolUse support (#15211)

  - add `PreToolUse` hook for bash-like tool execution only at first
  - block shell execution before dispatch with deny-only hook behavior
  - introduces common.rs matcher framework for matching when hooks are run
  
  example run:
  
  ```
  › run three parallel echo commands, and the second one should echo "[block-pre-tool-use]" as a test
  
  
  • Running the three echo commands in parallel now and I’ll report the output directly.
  
  • Running PreToolUse hook: name for demo pre tool use hook
  
  • Running PreToolUse hook: name for demo pre tool use hook
  
  • Running PreToolUse hook: name for demo pre tool use hook
  
  PreToolUse hook (completed)
    warning: wizard-tower PreToolUse demo inspected Bash: echo "first parallel echo"
    
  PreToolUse hook (blocked)
    warning: wizard-tower PreToolUse demo blocked a Bash command on purpose.
    feedback: PreToolUse demo blocked the command. Remove [block-pre-tool-use] to continue.
  
  PreToolUse hook (completed)
    warning: wizard-tower PreToolUse demo inspected Bash: echo "third parallel echo"
  
  • Ran echo "first parallel echo"
    └ first parallel echo
  
  • Ran echo "third parallel echo"
    └ third parallel echo
  
  • Three little waves went out in parallel.
  
    1. printed first parallel echo
    2. was blocked before execution because it contained the exact test string [block-pre-tool-use]
    3. printed third parallel echo
  
    There was also an unrelated macOS defaults warning around the successful commands, but the echoes
    themselves worked fine. If you want, I can rerun the second one with a slightly modified string so
    it passes cleanly.
  ```

  Andrei Eternal · 2026-03-23 14:32:59 -07:00
  73bbb07ba8
• feat: new op type for sub-agents communication (#15556)

  Add `InterAgentCommunication` for v2 agent communication

  jif-oai · 2026-03-23 21:09:00 +00:00
  18f1a08bc9
• feat: support disable skills by name. (#15378)

  Support disabling skills by name, primarily for plugin skills. We can’t
  use the path, since plugin skill paths may change across versions.

  xl-openai · 2026-03-23 12:57:40 -07:00
  9a33e5c0a0
• Thread guardian Responses API errors into denial rationale (#15516)

  ## Summary
  - capture the last guardian `EventMsg::Error` while waiting for review
  completion
  - reuse that error as the denial rationale when the review turn
  completes without an assessment payload
  - add a regression test for the `/responses` HTTP 400 path
  
  ## Testing
  - `just fmt`
  - `cargo test -p codex-core
  guardian_review_surfaces_responses_api_errors_in_rejection_reason`
  - `just argument-comment-lint -p codex-core`
  
  ## Notes
  - `cargo test -p codex-core` still fails on the pre-existing unrelated
  test
  `tools::js_repl::tests::js_repl_imported_local_files_can_access_repl_globals`
  in this environment (`mktemp ... Operation not permitted` while
  downloading `dotslash`)
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-23 12:46:49 -07:00
  332edba78e
• chore: split sub-agent v2 implementation (#15540)

  Just to make things cleaner

  jif-oai · 2026-03-23 19:41:53 +00:00
  450dc289c3
• Fix: proactive auth refresh to reload guarded disk state first (#15357)

  ## Summary
  
  Fix a managed ChatGPT auth bug where a stale Codex process could
  proactively refresh using an old in-memory refresh token even after
  another process had already rotated auth on disk.
  
  This changes the proactive `AuthManager::auth()` path to reuse the
  existing guarded `refresh_token()` flow instead of calling the refresh
  endpoint directly from cached auth state.
  
  ## Original Issue
  
  Users reported repeated `codexd` log lines like:
  
  ```text
  ERROR codex_core::auth: Failed to refresh token: error sending request for url (https://auth.openai.com/oauth/token)
  ```
  
  In practice this showed up most often when multiple `codexd` processes
  were left running. Killing the extra processes stopped the noise, which
  suggested the issue was caused by stale auth state across processes
  rather than invalid user credentials.
  
  ## Diagnosis
  
  The bug was in the proactive refresh path used by `AuthManager::auth()`:
  
  - Process A could refresh successfully, rotate refresh token `R0` to
  `R1`, and persist the updated auth state plus `last_refresh` to disk.
  - Process B could keep an older auth snapshot cached in memory, still
  holding `R0` and the old `last_refresh`.
  - Later, when Process B called `auth()`, it checked staleness from its
  cached in-memory auth instead of first reloading from disk.
  - Because that cached `last_refresh` was stale, Process B would
  proactively call `/oauth/token` with stale refresh token `R0`.
  - On failure, `auth()` logged the refresh error but kept returning the
  same stale cached auth, so repeated `auth()` calls could keep retrying
  with dead state.
  
  This differed from the existing unauthorized-recovery flow, which
  already did the safer thing: guarded reload from disk first, then
  refresh only if the on-disk auth was unchanged.
  
  ## What Changed
  
  - Switched proactive refresh in `AuthManager::auth()` to:
    - do a pure staleness check on cached auth
    - call `refresh_token()` when stale
  - return the original cached auth on genuine refresh failure, preserving
  existing outward behavior
  - Removed the direct proactive refresh-from-cached-state path
  - Added regression tests covering:
    - stale cached auth with newer same-account auth already on disk
  - the same scenario even when the refresh endpoint would fail if called
  
  ## Why This Fix
  
  `refresh_token()` already contains the right cross-process safety
  behavior:
  
  - guarded reload from disk
  - same-account verification
  - skip-refresh when another process already changed auth
  
  Reusing that path makes proactive refresh consistent with unauthorized
  recovery and prevents stale processes from trying to refresh
  already-rotated tokens.
  
  ## Testing
  
  Test shape:
  
  - create a fresh temp `CODEX_HOME` from `~/.codex/auth.json`
  - force `last_refresh` to an old timestamp so proactive refresh is
  required
  - start two long-lived helper processes against the same auth file
  - start `B` first so it caches stale auth and sleeps
  - start `A` second so it refreshes first
  - point both at a local mock `/oauth/token` server
  - inspect whether `B` makes a second refresh request with the stale
  in-memory token, or reloads the rotated token from disk
  
  ### Before the fix
  
  The repro showed the bug clearly: the mock server saw two refreshes with
  the same stale token, `A` rotated to a new token, and `B` still returned
  the stale token instead of reloading from disk.
  
  ```text
  POST /oauth/token refresh_token=rt_j6s0...
  POST /oauth/token refresh_token=rt_j6s0...
  
  B:cached_before=rt_j6s0...
  B:cached_after=rt_j6s0...
  B:returned=rt_j6s0...
  
  A:cached_before=rt_j6s0...
  A:cached_after=rotated-refresh-token-logged-run-v2
  A:returned=rotated-refresh-token-logged-run-v2
  ```
  
  ### After the fix
  
  After the fix, the mock server saw only one refresh request. `A`
  refreshed once, and `B` started with the stale token but reloaded and
  returned the rotated token.
  
  ```text
  POST /oauth/token refresh_token=rt_j6s0...
  
  B:cached_before=rt_j6s0...
  B:cached_after=rotated-refresh-token-fix-branch
  B:returned=rotated-refresh-token-fix-branch
  
  A:cached_before=rt_j6s0...
  A:cached_after=rotated-refresh-token-fix-branch
  A:returned=rotated-refresh-token-fix-branch
  ```
  
  This shows the new behavior: `A` refreshes once, then `B` reuses the
  updated auth from disk instead of making a second refresh request with
  the stale token.

  Celia Chen · 2026-03-23 12:07:59 -07:00
  f55f5c258f
• feat: structured multi-agent output (#15515)

  Send input now sends messages as assistant message and with this format:
  
  ```
  author: /root/worker_a
  recipient: /root/worker_a/tester
  other_recipients: []
  Content: bla bla bla. Actual content. Only text for now
  ```

  jif-oai · 2026-03-23 18:53:54 +00:00
  37ac0c093c
• tui: queue follow-ups during manual /compact (#15259)

  ## Summary
  - queue input after the user submits `/compact` until that manual
  compact turn ends
  - mirror the same behavior in the app-server TUI
  - add regressions for input queued before compact starts and while it is
  running
  
  Co-authored-by: Codex <noreply@openai.com>

  Charley Cunningham · 2026-03-23 10:19:44 -07:00
  e838645fa2