Commit Graph
2281 Commits
Author SHA1 Message Date
Roy Han 6d40e7bede restore dropped tests 2026-03-12 17:02:32 -07:00
xl-openai 1ea69e8d50 feat: add plugin/read. (#14445)
return more information for a specific plugin.
2026-03-12 16:52:21 -07:00
Jack Mousseau b7dba72dbd Rename reject approval policy to granular (#14516) 2026-03-12 16:38:04 -07:00
Eric Traut d32820ab07 Fix codex exec --profile handling (#14524)
PR #14005 introduced a regression whereby `codex exec --profile`
overrides were dropped when starting or resuming a thread. That causes
the thread to miss profile-scoped settings like
`model_instructions_file`.

This PR preserve the active profile in the thread start/resume config
overrides so the
app-server rebuild sees the same profile that exec resolved. 

Fixes #14515
2026-03-12 17:34:25 -06:00
Rasmus Rygaard 53d5972226 Reapply "Pass more params to compaction" (#14298) (#14521)
This reverts commit 8af97ce4b0.

Confirmed that this runs locally without the previous issues with tool
use
2026-03-12 23:27:21 +00:00
Roy Han 7f8cfe2fb2 fmt 2026-03-12 16:20:58 -07:00
Roy Han 43e6cb4e68 test fixes 2026-03-12 16:16:26 -07:00
Anton Panasenko 651717323c feat(search_tool): gate search_tool on model supports_search_tool field (#14502) 2026-03-12 16:03:50 -07:00
pakrym-oai a2546d5dff Expose code-mode tools through globals (#14517)
Summary
- make all code-mode tools accessible as globals so callers only need
`tools.<name>`
- rename text/image helpers and key globals (store, load, ALL_TOOLS,
etc.) to reflect the new shared namespace
- update the JS bridge, runners, descriptions, router, and tests to
follow the new API

Testing
- Not run (not requested)
2026-03-12 15:43:59 -07:00
Curtis 'Fjord' Hawthorne b560494c9f Persist js_repl codex helpers across cells (#14503)
## Summary

This changes `js_repl` so saved references to `codex.tool(...)` and
`codex.emitImage(...)` keep working across cells.

Previously, those helpers were recreated per exec and captured that
exec's `message.id`. If a persisted object or saved closure reused an
old helper in a later cell, the nested tool/image call could fail with
`js_repl exec context not found`.

This patch:
- keeps stable `codex.tool` and `codex.emitImage` helper identities in
the kernel
- resolves the current exec dynamically at call time using
`AsyncLocalStorage`
- adds regression coverage for persisted helper references across cells
- updates the js_repl docs and project-doc instructions to describe the
new behavior and its limits

## Why

We already support persistent top-level bindings across `js_repl` cells,
so persisted objects should be able to reuse `codex` helpers in later
active cells. The bug was that helper identity was exec-scoped, not
kernel-scoped.

Using `AsyncLocalStorage` fixes the cross-cell reuse case without
falling back to a single global active exec that could accidentally
attribute stale background callbacks to the wrong cell.
2026-03-12 15:41:54 -07:00
Roy Han 9a7549c9bd steering and queue tests 2026-03-12 15:40:22 -07:00
Jack Mousseau a314c7d3ae Decouple request permissions feature and tool (#14426) 2026-03-12 14:47:08 -07:00
Matthew Zeng bc48b9289a Update tool search prompts (#14500)
- [x] Add mentions of connectors because model always think in connector
terms in its CoT.
- [x] Suppress list_mcp_resources in favor of tool search for available
apps.
2026-03-12 14:28:51 -07:00
pakrym-oai 04e14bdf23 Rename exec session IDs to cell IDs (#14510)
- Update the code-mode executor, wait handler, and protocol plumbing to
use cell IDs instead of session IDs for node communication
- Switch tool metadata, wait description, and suite tests to refer to
cell IDs so user-visible messages match the new terminology

**Testing**
- Not run (not requested)
2026-03-12 14:05:30 -07:00
Andi Liu 11812383c5 memories: focus write prompts on user preferences (#14493)
## Summary
- update `codex-rs/core/templates/memories/stage_one_system.md` so phase
1 captures stronger user-preference signals, richer task summaries, and
cwd provenance without branch-specific fields
- update `codex-rs/core/templates/memories/consolidation.md` so phase 2
keeps separate sections for user preferences, reusable knowledge, and
failure shields while staying cwd-aware but branchless
- document the `codex` prompt-template maintenance rule in
`codex-rs/core/src/memories/README.md`: the undated templates are
canonical here and should be edited in place

## Testing
- cargo test -p codex-core memories --manifest-path codex-rs/Cargo.toml
2026-03-12 20:39:59 +00:00
pakrym-oai dadffd27d4 Fix MCP tool calling (#14491)
Properly escape mcp tool names and make tools only available via
imports.
2026-03-12 13:38:52 -07:00
pakrym-oai a5a4899d0c Skip nested tool call parallel test on Windows (#14505)
**Summary**
- disable the `code_mode_nested_tool_calls_can_run_in_parallel` test on
Windows where `exec_command` is unavailable

**Testing**
- Not run (not requested)
2026-03-12 13:32:11 -07:00
aaronl-openaiandCodex f35d46002a Fix js_repl hangs on U+2028/U+2029 dynamic tool responses (#14421)
## Summary
Dynamic tool responses containing literal U+2028 / U+2029 would cause
await codex.tool(...) to hang even though the response had already
arrived. This PR replaces the kernel’s readline-based stdin handling
with byte-oriented JSONL framing that handles these characters properly.

## Testing
- `cargo test -p codex-core`
- tested the binary on a repro case and confirmed it's fixed

---------

Co-authored-by: Codex <noreply@openai.com>
2026-03-12 13:01:02 -07:00
pakrym-oai 09ba6b47ae Reuse tool runtime for code mode worker (#14496)
## Summary
- create the turn-scoped `ToolCallRuntime` before starting the code mode
worker so the worker reuses the same runtime and router
- thread the shared runtime through the code mode service/worker path
and use it for nested tool calls
- model aborted tool calls as a concrete `ToolOutput` so aborted
responses still produce valid tool output shapes

## Testing
- `just fmt`
- `cargo test -p codex-core` (still running locally)
2026-03-12 12:48:32 -07:00
pakrym-oai 25e301ed98 Add parallel tool call test (#14494)
Summary
- pin tests to `test-gpt-5.1-codex` so code-mode suites exercise that
model explicitly
- add a regression test that ensures nested tool calls can execute in
parallel and assert on timing
- refresh `codex-rs/Cargo.lock` for the updated dependency tree (add
`codex-utils-pty`, drop `codex-otel`)

Testing
- Not run (not requested)
2026-03-12 12:10:14 -07:00
pakrym-oai d1b03f0d7f Add default code-mode yield timeout (#14484)
Summary
- expose the default yield timeout through code mode runtime so the
handler, wait tool, and protocol share the same 10s value that matches
unified exec
- document the timeout change in the tool descriptions and propagate the
value all the way into the runner metadata
- adjust Cargo.lock to keep the dependency tree in sync with the added
code mode tool dependency

Testing
- Not run (not requested)
2026-03-12 12:06:23 -07:00
jgershen-oai 3e96c867fe use scopes_supported for OAuth when present on MCP servers (#14419)
Fixes [#8889](https://github.com/openai/codex/issues/8889).

## Summary
- Discover and use advertised MCP OAuth `scopes_supported` when no
explicit or configured scopes are present.
- Apply the same scope precedence across `mcp add`, `mcp login`, skill
dependency auto-login, and app-server MCP OAuth login.
- Keep discovered scopes ephemeral and non-persistent.
- Retry once without scopes for CLI and skill auto-login flows if the
OAuth provider rejects discovered scopes.

## Motivation
Some MCP servers advertise the scopes they expect clients to request
during OAuth, but Codex was ignoring that metadata and typically
starting OAuth with no scopes unless the user manually passed `--scopes`
or configured `server.scopes`.

That made compliant MCP servers harder to use out of the box and is the
behavior described in
[#8889](https://github.com/openai/codex/issues/8889).

This change also brings our behavior in line with the MCP authorization
spec's scope selection guidance:

https://modelcontextprotocol.io/specification/2025-11-25/basic/authorization#scope-selection-strategy

## Behavior
Scope selection now follows this order everywhere:
1. Explicit request scopes / CLI `--scopes`
2. Configured `server.scopes`
3. Discovered `scopes_supported`
4. Legacy empty-scope behavior

Compatibility notes:
- Existing working setups keep the same behavior because explicit and
configured scopes still win.
- Discovered scopes are never written back into config or token storage.
- If discovery is missing, malformed, or empty, behavior falls back to
the previous empty-scope path.
- App-server login gets the same precedence rules, but does not add a
transparent retry path in this change.

## Implementation
- Extend streamable HTTP OAuth discovery to parse and normalize
`scopes_supported`.
- Add a shared MCP scope resolver in `core` so all login entrypoints use
the same precedence rules.
- Preserve provider callback errors from the OAuth flow so CLI/skill
flows can safely distinguish provider rejections from other failures.
- Reuse discovered scopes from the existing OAuth support check where
possible instead of persisting new config.
2026-03-12 11:57:06 -07:00
Roy Han 8270e0b977 separate emittance test 2026-03-12 11:41:42 -07:00
iceweasel-oai fa26597689 Do not allow unified_exec for sandboxed scenarios on Windows (#14398)
as reported in https://github.com/openai/codex/issues/14367 users can
explicitly enable unified_exec which will bypass the sandbox even when
it should be enabled.

Until we support unified_exec with the Windows Sandbox, we will disallow
it unless the sandbox is disabled
2026-03-12 11:21:30 -07:00
gabec-openaiandCodex 4fa7d6f444 Handle malformed agent role definitions nonfatally (#14488)
## Summary
- make malformed agent role definitions nonfatal during config loading
- drop invalid agent roles and record warnings in `startup_warnings`
- forward startup warnings through app-server `configWarning`
notifications

## Testing
- `cargo test -p codex-core agent_role_ -- --nocapture`
- `just fix -p codex-core`
- `just fmt`
- `cargo test -p codex-app-server config_warning -- --nocapture`

Co-authored-by: Codex <noreply@openai.com>
2026-03-12 11:20:31 -07:00
pakrym-oai cfe3f6821a Cleanup code_mode tool descriptions (#14480)
Move to separate files and clarify a bit.
2026-03-12 11:13:35 -07:00
Roy Han c9b6c970fe Merge remote-tracking branch 'origin/rhan/surface-updates' into rhan/emittance 2026-03-12 11:08:32 -07:00
Roy Han a51db905a0 fix again 2026-03-12 10:43:25 -07:00
Roy Han d8b457c841 Merge origin/main into rhan/surface-updates to resolve PR #14374 conflicts 2026-03-12 10:31:10 -07:00
daveaitel-openai 4e99c0f179 rename spawn_csv feature flag to enable_fanout (#14475)
## Summary
- rename the public feature flag for `spawn_agents_on_csv()` from
`spawn_csv` to `enable_fanout`
- regenerate the config schema so only `enable_fanout` is advertised
- keep the behavior the same: enabling `enable_fanout` still pulls in
`multi_agent`

## Notes
- this is a hard rename with no `spawn_csv` compatibility alias
- the internal enum remains `Feature::SpawnCsv` to keep the patch small

## Testing
- `cd codex-rs && just fmt`
- `cd codex-rs && cargo test -p codex-core` (running locally;
`suite::agent_jobs::*` and rename-specific coverage passed so far)
2026-03-12 13:27:05 -04:00
pakrym-oai c0528b9bd9 Move code mode tool files under tools/code_mode and split functionality (#14476)
- **Summary**
- migrate the code mode handler, service, worker, process, runner, and
bridge assets into the `tools/code_mode` module tree
- split Execution, protocol, and handler logic into dedicated files and
relocate the tool definition into `code_mode/spec.rs`
- update core references and tests to stitch the new organization
together
- **Testing**
  - Not run (not requested)
2026-03-12 09:54:11 -07:00
Roy Han 6323382f29 fix flaky test 2026-03-12 09:43:43 -07:00
viyatb-oai a30b807efe fix(cli): support legacy use_linux_sandbox_bwrap flag (#14473)
## Summary
- restore `use_linux_sandbox_bwrap` as a removed feature key so older
`--enable` callers parse again
- keep it as a no-op by leaving runtime behavior unchanged
- add regression coverage for the legacy `--enable` path

## Testing
- Not run (updated and pushed quickly)
2026-03-12 16:33:58 +00:00
pakrym-oai 2f03b1a322 Dispatch tools when code mode is not awaited directly (#14437)
## Summary
- start a code mode worker once per turn and let it pump nested tool
calls through a dedicated queue
- simplify code mode request/response dispatch around request ids and
generic runner-unavailable errors
- clean up the code mode process API and runner protocol plumbing

## Testing
- not run yet
2026-03-12 09:00:20 -07:00
Michael Bolin 0c8a36676a fix: move inline codex-rs/core unit tests into sibling files (#14444)
## Why
PR #13783 moved the `codex.rs` unit tests into `codex_tests.rs`. This
applies the same extraction pattern across the rest of `codex-rs/core`
so the production modules stay focused on runtime code instead of large
inline test blocks.

Keeping the tests in sibling files also makes follow-up edits easier to
review because product changes no longer have to share a file with
hundreds or thousands of lines of test scaffolding.

## What changed
- replaced each inline `mod tests { ... }` in `codex-rs/core/src/**`
with a path-based module declaration
- moved each extracted unit test module into a sibling `*_tests.rs`
file, using `mod_tests.rs` for `mod.rs` modules
- preserved the existing `cfg(...)` guards and module-local structure so
the refactor remains structural rather than behavioral

## Testing
- `cargo test -p codex-core --lib` (`1653 passed; 0 failed; 5 ignored`)
- `just fix -p codex-core`
- `cargo fmt --check`
- `cargo shear`
2026-03-12 08:16:36 -07:00
Jack Mousseau 745ed4e5e0 Use granted permissions when invoking apply_patch (#14429) 2026-03-12 01:30:13 -07:00
Matthew Zeng 23e55d7668 [elicitation] User-friendly tool call messages. (#14403)
- [x] Add a curated set of tool call messages and human-readable tool
param names.
2026-03-12 00:35:21 -07:00
Jack Mousseau 19d0949aab Handle pre-approved permissions in zsh fork (#14431) 2026-03-12 00:27:11 -07:00
viyatb-oai e99e8e4a6b fix: follow up on linux sandbox review nits (#14440)
## Summary
- address the follow-up review nits from #13996 in a separate PR
- make the approvals test command a raw string and keep the
managed-network path using env proxy routing
- inline `--apply-seccomp-then-exec` in the Linux sandbox inner command
builder
- remove the bubblewrap-specific sandbox metric tag path and drop the
`use_legacy_landlock` shim from `sandbox_tag`/`TurnMetadataState::new`
- restore the `Feature` import that `origin/main` currently still needs
in `connectors.rs`

## Testing
- `cargo test -p codex-linux-sandbox`
- focused `codex-core` tests were rerun/started, but the final
verification pass was interrupted when I pushed at request
2026-03-11 23:59:50 -07:00
viyatb-oai 04892b4ceb refactor: make bubblewrap the default Linux sandbox (#13996)
## Summary
- make bubblewrap the default Linux sandbox and keep
`use_legacy_landlock` as the only override
- remove `use_linux_sandbox_bwrap` from feature, config, schema, and
docs surfaces
- update Linux sandbox selection, CLI/config plumbing, and related
tests/docs to match the new default
- fold in the follow-up CI fixes for request-permissions responses and
Linux read-only sandbox error text
2026-03-11 23:31:18 -07:00
xl-openai b5f927b973 feat: refactor on openai-curated plugins. (#14427)
- Curated repo sync now uses GitHub HTTP, not local git.
- Curated plugin cache/versioning now uses commit SHA instead of local.
- Startup sync now always repairs or refreshes curated plugin cache from
tmp (auto update to the lastest)
2026-03-11 23:18:58 -07:00
pakrym-oai f6c6128fc7 Support waiting for code_mode sessions (#14295)
## Summary
- persist the code mode runner process in the session-scoped code mode
store
- switch the runner protocol from `init` to `start` with explicit
session ids
- handle runner-side session processing without the init waiter queue

## Validation
- just fmt
- cargo check -p codex-core
- node --check codex-rs/core/src/tools/code_mode_runner.cjs
2026-03-11 23:13:54 -07:00
Roy Han 6af6704e28 config update 2026-03-11 23:07:08 -07:00
Ahmed Ibrahim 367a8a2210 Clarify spawn agent authorization (#14432)
- Clarify that spawn_agent requires explicit user permission for
delegation or parallel agent work.
- Add a regression test covering the new description text.
2026-03-11 23:03:07 -07:00
Roy Han 2f71969267 response wiring 2026-03-11 22:51:17 -07:00
+15 ba5b94287e [apps] Add tool_suggest tool. (#14287)
- [x] Add tool_suggest tool.
- [x] Move chatgpt/src/connectors.rs and core/src/connectors.rs into a
dedicated mod so that we have all the logic and global cache in one
place.
- [x] Update TUI app link view to support rendering the installation
view for mcp elicitation.

---------

Co-authored-by: Shaqayeq <shaqayeq@openai.com>
Co-authored-by: Eric Traut <etraut@openai.com>
Co-authored-by: pakrym-oai <pakrym@openai.com>
Co-authored-by: Ahmed Ibrahim <aibrahim@openai.com>
Co-authored-by: guinness-oai <guinness@openai.com>
Co-authored-by: Eugene Brevdo <ebrevdo@users.noreply.github.com>
Co-authored-by: Charlie Guo <cguo@openai.com>
Co-authored-by: Fouad Matin <fouad@openai.com>
Co-authored-by: Fouad Matin <169186268+fouad-openai@users.noreply.github.com>
Co-authored-by: xl-openai <xl@openai.com>
Co-authored-by: alexsong-oai <alexsong@openai.com>
Co-authored-by: Owen Lin <owenlin0@gmail.com>
Co-authored-by: sdcoffey <stevendcoffey@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Won Park <won@openai.com>
Co-authored-by: Dylan Hurd <dylan.hurd@openai.com>
Co-authored-by: celia-oai <celia@openai.com>
Co-authored-by: gabec-openai <gabec@openai.com>
Co-authored-by: joeytrasatti-openai <joey.trasatti@openai.com>
Co-authored-by: Leo Shimonaka <leoshimo@openai.com>
Co-authored-by: Rasmus Rygaard <rasmus@openai.com>
Co-authored-by: maja-openai <163171781+maja-openai@users.noreply.github.com>
Co-authored-by: pash-openai <pash@openai.com>
Co-authored-by: Josh McKinney <joshka@openai.com>
2026-03-11 22:06:59 -07:00
Roy Han 5d63c86d53 emittance 2026-03-11 21:48:01 -07:00
sayan-oai 917c2df201 chore: use AVAILABLE and ON_INSTALL as default plugin install and auth policies (#14407)
make `AVAILABLE` the default plugin installPolicy when unset in
`marketplace.json`. similarly, make `ON_INSTALL` the default authPolicy.

this means, when unset, plugins are available to be installed (but not
auto-installed), and the contained connectors will be authed at
install-time.

updated tests.
2026-03-11 20:33:17 -07:00
Owen Lin 5bc82c5b93 feat(app-server): propagate traces across tasks and core ops (#14387)
## Summary

This PR keeps app-server RPC request trace context alive for the full
lifetime of the work that request kicks off (e.g. for `thread/start`,
this is `app-server rpc handler -> tokio background task -> core op
submissions`). Previously we lose trace lineage once the request handler
returns or hands work off to background tasks.

This approach is especially relevant for `thread/start` and other RPC
handlers that run in a non-blocking way. In the near future we'll most
likely want to make all app-server handlers run in a non-blocking way by
default, and only queue operations that must operate in order (e.g.
thread RPCs per thread?), so we want to make sure tracing in app-server
just generally works.

Depends on https://github.com/openai/codex/pull/14300

**Before**
<img width="155" height="207" alt="image"
src="https://github.com/user-attachments/assets/c9487459-36f1-436c-beb7-fafeb40737af"
/>


**After**
<img width="299" height="337" alt="image"
src="https://github.com/user-attachments/assets/727392b2-d072-4427-9dc4-0502d8652dea"
/>

## What changed

- Keep request-scoped trace context around until we send the final
response or error, or the connection closes.
- Thread that trace context through detached `thread/start` work so
background startup stays attached to the originating request.
- Pass request trace context through to downstream core operations,
including:
  - thread creation
  - resume/fork flows
  - turn submission
  - review
  - interrupt
  - realtime conversation operations
- Add tracing tests that verify:
  - remote W3C trace context is preserved for `thread/start`
  - remote W3C trace context is preserved for `turn/start`
  - downstream core spans stay under the originating request span
  - request-scoped tracing state is cleaned up correctly
- Clean up shutdown behavior so detached background tasks and spawned
threads are drained before process exit.
2026-03-11 20:18:31 -07:00
Ahmed IbrahimandCodex bf5e997b31 Include spawn agent model metadata in app-server items (#14410)
- add model and reasoning effort to app-server collab spawn items and
notifications
- regenerate app-server protocol schemas for the new fields

---------

Co-authored-by: Codex <noreply@openai.com>
2026-03-11 19:25:21 -07:00