Commit Graph
122 Commits
Author SHA1 Message Date
Dylan Hurd e52c35b000 Propagate approval rejection reasons (#34400)
## What changed

- Change `ReviewDecision::Denied` to carry a rejection string and update the generated protocol schemas.
- Preserve specific rejection reasons through command, patch, network, MCP, delegated, and automatic approval flows so tool results can return them to the model.
- Distinguish invalid approval responses from user declines and truncate oversized rejection messages before adding them to model context.

## Testing

- Add coverage for denial serialization, invalid app-server approval responses, dropped automatic reviews, network rejection propagation, and rejection-message truncation.

GitOrigin-RevId: d48a55643aa03c7ecfa08a8e4b669913eec5464a
2026-07-20 19:23:21 +00:00
nhamidi-oai 643de86a19 Add audio output support to dynamic tools and code mode (#34080)
## What changed

- Add `inputAudio` content items to dynamic tool responses, app-server events, thread history, and generated protocol schemas.
- Add an `audio()` code-mode helper that accepts inline data URLs, audio URL objects, and MCP audio blocks.
- Convert MCP audio blocks into model input when audio is supported, and replace unsupported audio with an explanatory text item.
- Reject non-data audio URLs and track audio item counts in dynamic tool analytics.

## Testing

- Cover audio serialization, protocol round trips, thread-history conversion, MCP modality filtering, code-mode helper inputs, and invalid URL handling.

GitOrigin-RevId: 1ed52a8f9c62d4840fb71c5ec736b4a3566243d6
2026-07-18 23:22:13 +00:00
sayan-oai c4ce0493dc Keep active-turn environments stable across settings updates (#33658)
## Why

With deferred execution enabled, rebuilding a step context from the latest
thread environment snapshot could apply a settings update to a turn that was
already in progress.

## What changed

- Preserve each turn's captured environment selections when creating later
  step contexts.
- Refresh only the readiness of environments that were already starting, while
  retaining their original selection order.
- Apply updated environment selections to the next turn.

## Testing

Add coverage for changing the selected workspace while a turn is paused,
verifying that the active turn keeps its original working directory and the
next turn uses the new one.

GitOrigin-RevId: c6f4388c843384ef045b7abdbc303dcfca11d230
2026-07-16 18:23:43 +00:00
Martin Au-Yeung 800715d201 Remove template IDs from MCP tool call metadata (#33467)
## What changed

- Remove `template_id` from MCP tool call items and lifecycle events.
- Remove `templateId` from app-server `McpToolCallAppContext` responses and generated schemas.
- Update protocol conversions, documentation, and existing test expectations for the revised metadata shape.

GitOrigin-RevId: f2b1304eadff661eec3966673ea71206b1542b98
2026-07-16 01:23:52 +00:00
jif 42c5d3c80d Reuse MCP tool catalogs across sessions (#33184)
## Why

Starting a new session should not have to wait for an unchanged stdio MCP
server to initialize before its tools can be presented to the model.

## What changed

- Cache recent tool catalogs for matching stdio MCP server configurations and
  use them while a new live connection starts in the background.
- Bound the process-wide cache to 32 entries with a 30-minute TTL, and key
  entries by the server configuration, environment, working directory, and
  elicitation capabilities that affect the catalog.
- Keep connection-specific instructions and tool annotations out of cached
  catalogs. Resolve tool calls against the live connection so tools that are
  unavailable or hidden in the new session cannot be invoked from stale data.
- Publish only the newest completed catalog fetch and do not cache HTTP servers
  or stdio configurations that depend on remotely sourced environment values.

## Testing

- Add coverage for cache expiration, environment changes, catalog sanitization,
  and out-of-order refreshes.
- Add an end-to-end test that starts inference from cached definitions while a
  replacement MCP process initializes, then verifies calls and visibility
  against the live process.

GitOrigin-RevId: 2ed0f29ba53ace12532730f951b175c588aa3ae7
2026-07-14 22:25:39 +00:00
thomas 8347b8de21 [codex-apps] Filter optional file fields by tool schema (#31686)
## Summary

Codex Apps file parameters are exposed to the model as local paths,
uploaded at execution time, and rewritten into provided-file payloads
before the MCP tool call.

The rewrite currently includes the documented optional fields
`mime_type` and `file_name` for every file parameter. Apps with strict
schemas can reject those fields when they are not declared.

## Changes

- Derive the supported optional file fields from each
`openai/fileParams` parameter's raw input schema before replacing it
with the model-visible local-path schema.
- Always include `download_url` and `file_id`.
- Include `mime_type` and `file_name` only when that specific file
parameter's schema accepts them, including schemas that allow additional
properties.
- Handle scalar and array file parameters, including items-only arrays,
composed schemas, and local JSON Schema references.
- Preserve the existing restriction that only the host-owned Codex Apps
MCP server can use this upload path.

This supports tools with different file contracts in the same app: one
parameter can accept the optional fields while another remains strict.

## Validation

- `just test -p codex-mcp`
- `just test -p codex-core mcp_openai_file`
- `just test -p codex-core codex_apps_file_params_`
- `just fix -p codex-mcp`
- `just fix -p codex-core`
- `just fmt`
- `git diff --check`
- Manually verified in the Codex Electron app that:
  - a strict file schema receives only `download_url` and `file_id`
  - a rich file schema also receives `mime_type` and `file_name`

Related: #31330
2026-07-09 14:32:23 -07:00
Alex Zamoshchin f6e251c3ac [codex-rs] Add writes app approval mode (#30482)
## Summary

- Adds `writes` to `AppToolApproval` and exposes it through config and
app-server schemas, including
`[apps._default].default_tools_approval_mode`.
- In `writes`, tools with `readOnlyHint = true` skip approval; all other
tools prompt, including non-destructive writes and tools without
annotations.
- Prevents session or persistent approval choices in this mode so later
writes still prompt.

## Why

`auto` only prompts for risk-hinted actions, while `prompt` also
interrupts reads. Apps need a middle mode that gates writes without
prompting for declared read-only actions.

## Validation

- `just write-config-schema`
- `just write-app-server-schema`
- `just fmt`
- `just test -p codex-core mcp_turn_metadata` (4 passed)
- `just test -p codex-core writes_mode` (2 passed)
- `just test -p codex-app-server config_read_includes_apps` (1 passed)
- `just test -p codex-app-server-protocol` (251 passed)
- `just test -p codex-config` (200 passed)
- `just test -p codex-cli` (300 passed)
- `just fix -p codex-core -p codex-config -p codex-app-server-protocol
-p codex-app-server -p codex-cli`
2026-07-07 13:13:59 -04:00
Martin Au-YeungandMartin Au-Yeung ec300bc7bd Expose MCP app identity in app context (#29934)
## Why

MCP tool-call events need to expose trusted app identity and action
metadata directly so v2 clients do not have to infer it from tool names
or resource URIs.

## What changed

- Add optional `appName`, `templateId`, and `actionName` fields to MCP
tool-call `appContext`.
- Populate `appName` and `templateId` from trusted Codex Apps metadata,
and derive `actionName` from the trusted app resource metadata.
- Preserve all three fields through core events, legacy protocol events,
persisted thread history, resume redaction, and app-server v2 responses.
- Document the public `appContext` fields in
`codex-rs/app-server/README.md`.
- Regenerate app-server JSON and TypeScript schemas and add coverage for
serialization, persistence, redaction, and metadata propagation.

## Validation

- `just test -p codex-app-server-protocol mcp_tool_call`
- `just test -p codex-core
mcp_tool_call_item_metadata_only_trusts_codex_apps_identity
mcp_tool_call_item_includes_app_identity`
- `just write-app-server-schema`

---------

Co-authored-by: Martin Au-Yeung <280153141+martinauyeung-oai@users.noreply.github.com>
2026-06-25 18:31:10 -07:00
jif ee9e0f6387 Pin MCP runtimes to model steps (#30101)
## Why

An MCP refresh can replace the session's current manager while a model
step is still running. The step must execute calls through the same
manager whose tools it advertised.

## Boundary

```text
current session MCP runtime
          |
          | capture once for this model step
          v
StepContext.mcp
  - exact MCP config
  - exact connection manager
  - exact runtime environment context
```

```rust
pub struct McpRuntimeSnapshot {
    config: Arc<McpConfig>,
    manager: Arc<McpConnectionManager>,
    runtime_context: McpRuntimeContext,
}
```

## Example

```text
step A captures runtime A and advertises A's tools
refresh publishes runtime B
step A tool call -> runtime A
next step        -> runtime B
```

Capturing the snapshot is only an `Arc` clone. It does not restart MCPs
or make an RPC.

## What changes

- Captures one MCP runtime in `StepContext`.
- Uses it for tool planning, tool calls, resources, approvals, connector
attribution, and elicitation.
- Publishes replacement runtimes atomically.
- Lets an old runtime live only while an in-flight step or request still
holds its `Arc`.

Most of this diff is mechanical routing from the session-global manager
to `step_context.mcp`; it does not introduce selected-plugin discovery
yet.

## What does not change

- No plugin or extension migration.
- No new MCP cache policy.
- No environment file watching.
- No client sharing between separate managers.

## Stack

1. Extension-owned World State sections.
2. Project executor skills through World State.
3. **This PR:** pin one MCP runtime to each model step.
4. Project selected MCP/app/connector metadata by environment
availability.
5. One end-to-end integration scenario.
2026-06-26 00:53:07 +01:00
Owen Lin 703793c22e feat(core, mcp): cache codex_apps tools in memory (#29003)
## Description

This makes Codex Apps tool reads use a shared in-memory snapshot instead
of rereading the disk cache every time `list_all_tools()` runs. Disk
still seeds the cache on startup and gets updated after successful
fetches, but it is no longer the live read path.

The core change is that `McpManager` now owns a process-scoped
`CodexAppsToolsCache`. Codex threads in the same app-server process now
share this Codex Apps in-memory tools snapshot. The snapshot is keyed by
the Codex home plus the Codex Apps identity: the active Codex auth
user/workspace and the effective Codex Apps MCP source config.

There's already code to hard-refresh the cache, so we respect it in this
PR.

## Local benchmark

I ran a local steady-state microbenchmark of the exact repeated Codex
Apps cached-tools read this PR removes, using the same real local cache
payload in both trees: `3,678,138` bytes and `381` tools. The cache file
was already warm in the OS page cache, so this measures same-process
reread/deserialization work rather than cold-disk latency or full turn
latency. Each run is 25 iterations (mimicking a turn that makes 25
inference calls).

| Version | Run 1 | Run 2 | Avg |
|---|---:|---:|---:|
| `origin/main` disk read + JSON deserialize + `filter_tools` | `50.755
ms` | `52.894 ms` | `51.825 ms` |
| This branch in-memory `current_tools` + `filter_tools` | `0.740 ms` |
`0.778 ms` | `0.759 ms` |

That removes about `51 ms` from each repeated Codex Apps cached-tools
read on this machine, roughly `68x` faster for that subpath. It is
useful evidence for the hot path this PR changes, but not a claim that
every production turn gets `51 ms` faster; end-to-end impact also
depends on the rest of `list_all_tools()` and tool-payload construction.

This is on my M2 Max macbook, so with a slower disk this would be much
worse (and indeed we did see this really blew up turn runtime with a
slow disk).
2026-06-25 20:54:48 +00:00
Ahmed Ibrahim cef5444a80 Report MCP error codes with server attribution (#29969)
## Why

MCP error-code telemetry special-cased Codex Apps: its reported error
codes were retained, while codes from every other MCP server were
replaced with `unknown`. Error reporting should behave consistently for
every MCP server. The server name already identifies where an error came
from, so telemetry does not need a separate Codex Apps classification.

This follows up on [#28976](https://github.com/openai/codex/pull/28976),
which introduced MCP error-code telemetry.

## What changed

- Add the MCP server name to call, duration, and error metrics.
- Retain bounded, sanitized tool error codes from every MCP server.
- Remove `McpErrorCodeSource` and the Codex Apps ownership lookup from
telemetry collection.
- Use the same metric-tagging path for blocked, rejected, and executed
MCP calls.

## Test plan

- Verify the complete metric tag set includes the sanitized MCP server
name.
- Verify error codes from ordinary MCP servers are retained, bounded,
and sanitized.
- Preserve coverage for request failures, tool-result failures, nested
auth failures, and span attributes.
2026-06-24 21:08:39 -07:00
Adam Perry @ OpenAI df1ee09ec5 mcp: keep elicitation requests below app wire types (#29724)
## Why

Core and tools need to request MCP elicitation without constructing
app-server wire payloads. The request should remain a neutral protocol
concept until app-server serializes it for a client.

## What changed

- Switched core and tools to
`codex_protocol::approvals::ElicitationRequest`.
- Derived turn and server context inside core instead of carrying
app-server request types through lower layers.
- Kept the app-server payload unchanged through an explicit boundary
conversion.
- Removed the remaining production app-server-protocol dependency from
tools.

## Stack

This is PR 5 of 6, stacked on [PR
#29723](https://github.com/openai/codex/pull/29723). Review only the
delta from `codex/split-connector-metadata-types`. Next: [PR
#29725](https://github.com/openai/codex/pull/29725).

## Validation

- `codex-core` MCP coverage passed: 87 tests.
- Tools elicitation and app-server round-trip coverage passed.
2026-06-24 20:53:27 +00:00
Adam Perry @ OpenAI 1d65ccabd5 config: own layer provenance types (#29722)
## Why

Config layer provenance describes how effective configuration was
assembled, so it belongs with the config loader rather than in
app-server's serialized API types.

## What changed

- Moved `ConfigLayerSource`, `ConfigLayerMetadata`, and `ConfigLayer`
ownership into `codex-config`.
- Kept app-server's wire payloads unchanged and added explicit
conversions at the app boundary.
- Removed lower-level app-server-protocol dependencies from config
consumers.

## Stack

This is PR 3 of 6, stacked on [PR
#29721](https://github.com/openai/codex/pull/29721). Review only the
delta from `codex/split-auth-domain-types`. Next: [PR
#29723](https://github.com/openai/codex/pull/29723).

## Validation

- `codex-config` coverage passed.
- App-server config-manager and config RPC coverage passed.
2026-06-24 04:03:04 +00:00
alexsong-oai 1acb722e8a Support thread-level originator overrides (#29477)
## Why

Work(TPP) threads can be launched from the Desktop app, but if they all
keep the Desktop app's default originator then downstream attribution
cannot distinguish local Work launches from cloud-backed Work launches.
`thread/start.serviceName` already carries that launch signal, while
`SessionMeta.originator` is the durable thread-level value that survives
resume and fork.

This change converts the Desktop Work service names into an effective
originator at thread creation time, persists that originator with the
thread, and keeps using it for later model requests and memory writes.

## What changed

- Map `CODEX_WORK_LOCAL` and `CODEX_WORK_CLOUD` service names to
per-thread originators, while preserving
`CODEX_INTERNAL_ORIGINATOR_OVERRIDE` as the highest-precedence override.
- Persist the effective originator in `SessionMeta.originator`, read it
back on resume/fork, and inherit the parent originator for subagent
spawns when there is no persisted session metadata.
- Handle truncated `SpawnAgentForkMode::LastNTurns` forks by falling
back to the live parent originator when the forked history no longer
includes `SessionMeta`.
- Thread the per-thread originator through Responses headers,
websocket/compaction request paths, thread-store creation, rollout
metadata, and memory stage-one telemetry.

## Verification

- `just test -p codex-core
agent::control::tests::spawn_thread_subagent_inherits_parent_originator_without_fork
agent::control::tests::spawn_thread_subagent_fork_last_n_turns_inherits_parent_originator_without_session_meta
thread_manager::tests::originator_override_precedes_service_name_remapping`
- `just test -p codex-core
agent::control::tests::resume_thread_subagent_restores_stored_metadata_and_effective_multi_agent_mode`
- `just test -p codex-memories-write`
- `just fix -p codex-core -p codex-memories-write`
- `git diff --check`
2026-06-23 17:23:38 -07:00
viyatb-oai 50eee505a3 feat(guardian): include connected account email in app reviews (#27045)
## Why

auto review reviews Codex App tool calls using connector metadata such
as the app ID, name, and description. That metadata does not identify
the account behind the OAuth connection.

For Google Drive, this means auto review cannot distinguish a Drive
connection authenticated as `user@email.com` from a personal Drive
account. Uploading work data can therefore look like a transfer to a
personal destination even though the connector service already knows the
authenticated account email.

## What changed

- Read `_meta._codex_apps.connected_account_email` while resolving
approval metadata for built-in Codex App tools.
- Include the connected account email in the structured MCP tool action
sent to auto review.
- Trim empty values and omit the field when the connector link has no
account email.
- Update existing auto review request constructors and add coverage for
request construction and JSON serialization.

## Security

Only metadata from the trusted built-in `codex_apps` MCP server is
accepted. Custom MCP servers cannot inject a connected account email
into auto review reviews; the new regression test verifies that spoofed
metadata is ignored.

The email is used only in auto review's private review request. This
change does not add it to model-visible tool descriptions, app-server
approval events, or auto review assessment/review analytics.
2026-06-23 20:33:44 +00:00
stevenlee-oai cbcf1f8ca3 Add MCP tool call error metrics (#28976)
[Codex Thread
019edc37-5345-7272-92c9-bf5494cf3819](https://codex-thread-link.openai.chatgpt-team.site/thread/019edc37-5345-7272-92c9-bf5494cf3819)

## Summary

- count MCP `CallToolResult.isError` responses as failed calls instead
of successful transport-level calls
- add `codex.mcp.call.error` with bounded `error_type` and trusted
plugin-service `error_code` dimensions
- record the same error classification on MCP tool-call spans while
keeping untrusted server error text out of metric labels

## Scope

- no changes to MCP routing, retries, tool behavior, configuration, or
public APIs
- request failures remain grouped as `mcp_request`; separating
connection, timeout, protocol, and JSON-RPC failures requires preserving
typed errors through the existing flattened error boundary

## Testing

- `just test -p codex-core 'mcp_tool_call::tests::'` (75 passed)
- `just fix -p codex-core`
- `just fmt`
- `just test -p codex-core` (2,676 passed; 80 unrelated environment
failures from missing test binaries, sandbox signals, and read-only
paths)
2026-06-23 13:33:23 -07:00
Dylan Hurd 2cf2a6a844 chore(core) rm AskForApproval::OnFailure (#28418)
## Summary
Deletes the OnFailure variant of the `AskForApproval` enum. This option
has been deprecated since #11631.

## Testing
- [x] Tests pass
2026-06-23 12:13:54 -07:00
jif d2484697b1 Allow codex sandbox to consume MCP sandbox state (#29358)
## Summary

- let `codex sandbox` accept the JSON value from
`codex/sandbox-state-meta`
- require the payload `permissionProfile` instead of falling back to
ambient permissions
- reuse the existing macOS, Linux, and Windows launch paths, treating
external sandbox state conservatively as read-only
- let opaque forwarders add runtime read roots and disable direct
network access without decoding the payload

Builds on #29113, which is now on `main`.

## Tests

- `just test -p codex-cli debug_sandbox::tests`
- `cargo build -p codex-rmcp-client --bin test_stdio_server`
- `just test -p codex-core
stdio_mcp_tool_call_includes_sandbox_state_meta`
- `just test -p codex-mcp`
- `just fmt`
2026-06-23 10:17:52 +02:00
martinauyeung-oaiandmartinauyeung-oai 765309d5a6 Emit Trusted MCP App Identity on Tool-Call Items (#27132)
## Summary

- Add optional `appContext` to app-server MCP tool-call items with
trusted `connectorId`, `linkId`, and `mcpAppResourceUri` metadata.
- Preserve that context across tool-call events, persisted history,
reconnects, and thread resume.
- Keep the deprecated top-level `mcpAppResourceUri` temporarily for
client migration.

The consumer contract is `{ appContext: { connectorId, linkId,
mcpAppResourceUri }, tool }`.

## Validation

- Full GitHub Actions suite passes, including CLA, Bazel tests, clippy,
release builds, and argument-comment lint.

---------

Co-authored-by: martinauyeung-oai <280153141+martinauyeung-oai@users.noreply.github.com>
2026-06-18 14:02:54 -07:00
jif 790213ded0 Scope MCP sandbox metadata to server environment (#28914)
Scope MCP sandbox metadata to the MCP server's owning environment.

Previously, `codex/sandbox-state-meta` always used the turn's primary
cwd and rebuilt a legacy sandbox policy from that cwd. That can be wrong
for MCP servers owned by a different execution environment.

This now sends the owning environment cwd as a `file:` URI in
`sandboxCwd`, keeps `permissionProfile` as the permission source of
truth, and omits sandbox-state metadata when a non-default server
environment is not selected for the turn. Local/default MCP servers keep
the existing fallback cwd behavior.

Tests:
- `just fmt`
- `just bazel-lock-update`
- `just bazel-lock-check`
- `just test -p codex-mcp`
- `just test -p codex-core mcp_sandbox_cwd`
- `cargo build -p codex-rmcp-client --bin test_stdio_server`
- `just test -p codex-core
stdio_mcp_tool_call_includes_sandbox_state_meta`
2026-06-18 19:31:07 +02:00
pakrym-oai 172b2218a5 core: remove redundant TurnContext and Prompt fields (#28638)
## Why

`TurnContext` had accumulated dead fields and cached projections of
values already owned by its per-turn `Config` or `ModelInfo`. Keeping
both copies made ownership unclear and allowed artificial split-brain
states, such as a compatibility hash differing from the model metadata
it came from.

`Prompt` similarly carried a write-only personality after personality
selection had already been materialized into its base instructions.

This makes the canonical owner explicit: configuration-backed values
come from `config`, model-derived values come from `model_info`, and
prompts contain only data consumed by request construction.

## What changed

- Remove the unused `ghost_snapshot`, `codex_self_exe`, and
`thread_source` fields.
- Remove duplicate `comp_hash`, `truncation_policy`, `features`,
`shell_environment_policy`, `codex_linux_sandbox_exe`, `compact_prompt`,
and `tool_mode` fields.
- Read those values directly from `TurnContext::config` or
`TurnContext::model_info` at their consumers.
- Remove the write-only `Prompt::personality` field and its constructor
assignments.
- Preserve review-turn inheritance of the parent turn's shell policy,
Linux sandbox executable, and compact prompt through the review config.

## Testing

- `cargo check -p codex-core --tests`
2026-06-16 22:17:24 -07:00
Matthew Zeng 1fbaac1e50 [codex] Reuse Apps policy evaluation across MCP tool exposure (#27813)
## Summary

- move `AppToolPolicyEvaluator` and the Apps config/requirements policy
logic from `codex-core` into `codex-connectors`
- resolve one immutable policy snapshot per exposure build and reuse it
across every Codex Apps MCP tool
- keep core as a thin adapter from MCP metadata to connector-owned
policy input while preserving the call-time defense-in-depth check

## Why

`build_mcp_tool_exposure` evaluates every Codex Apps tool on each
sampling request. The old path rebuilt effective Apps configuration for
every tool, and the policy implementation lived in the already-large
core crate even though it is connector-specific.

The connector-owned evaluator keeps the expensive config merge/decode
out of the loop and gives core only the effective policy result it
needs.

## Performance

With the real 557-tool Apps corpus, `build_mcp_tool_exposure` measured
3.74 ms and 3.33 ms after the extraction (3.54 ms mean). The original
path measured 807 ms mean, so the final result retains the 99.6%
reduction.

## Validation

- `cargo check -p codex-connectors -p codex-core`
- `just test -p codex-connectors` — 15 passed
- `just test -p codex-core --lib connectors` — 35 passed
- `just test -p codex-core --lib mcp_tool_exposure` — 5 passed
- `just test -p codex-core --lib mcp_tool_call` — 72 passed
- `just bazel-lock-update`
- `just bazel-lock-check`
- `just fix -p codex-connectors`
- `just fix -p codex-core`
- `just fmt`
2026-06-15 15:24:33 -07:00
jif c3a479620f Add selected-plugin precedence and attribution to the MCP catalog (#27884)
## Why

**In short:** this PR resolves already-discovered MCP registrations. It
does not read selected plugins or discover their MCP servers.

The resolved MCP catalog currently builds config and auto-discovered
plugin registrations before runtime contributors are applied. A
thread-selected plugin needs a distinct precedence tier in that same
initial resolution pass: otherwise a disabled lower-precedence winner
can leave stale name-level state behind, and the winning MCP tools
cannot be attributed to the selected package reliably.

This PR adds that catalog boundary before executor discovery is
connected.

## What changed

- Added an explicit selected-plugin registration tier between
auto-discovered plugins and explicit config.
- Collected selected-plugin contributions before the initial catalog
build, while leaving compatibility and generic extension overlays in
their existing runtime phase.
- Retained the winning plugin ID and display name directly on
plugin-owned catalog registrations.
- Derived MCP tool provenance from the winning catalog entry instead of
joining against local-only plugin summaries.
- Retained the winning selected server's tool approval policy in the
running connection manager, so a selected registration cannot inherit
approval behavior from a losing local plugin.
- Kept remembered approval session-scoped for selected plugins until
there is an authority-aware persistence contract; Codex will not write
approval back to an unrelated local plugin.
- Preserved existing name-level disabled vetoes for discovered plugins
and config, while keeping a selected package's own disabled registration
scoped to that registration.
- Preserved deterministic selection order and existing config,
compatibility, and extension precedence.

The resulting order is:

```text
auto-discovered plugin
  < selected plugin
  < explicit config
  < compatibility registration
  < extension overlay
```

## Behavior and scope

This is a catalog and provenance change only. No production host
contributes selected-plugin MCP registrations yet, so existing local MCP
behavior remains unchanged.

The stacked follow-up, #27870, installs the executor plugin provider
that produces these registrations. App-server activation remains a
separate final step.

## Verification

Focused tests cover precedence, deterministic selected-plugin conflicts,
disabled-veto behavior across catalog phases, managed requirements
before selected-plugin resolution, winning-server approval policy, and
attribution when local and selected packages share an ID or server name.
CI owns execution of the test suite.
2026-06-15 11:10:51 +02:00
Shijie Rao 216ce03031 Add request_user_input auto-resolution window contract (#27256)
## Why

`request_user_input` is moving beyond its original plan-mode-only
workflow, and future default/goal-mode usage needs a way for the model
to ask helpful but non-blocking questions without forcing the turn to
wait forever. This PR adds an explicit `autoResolutionMs` contract so a
later client/runtime change can auto-resolve unanswered prompts after a
bounded window while leaving truly blocking questions unchanged.

This is contract plumbing only; it does not implement the client-side
timer or auto-selection behavior, and the model-facing description
treats the field as reserved unless the current runtime explicitly
supports auto-resolution.

## What Changed

- Added optional `autoResolutionMs` to the model-facing
`request_user_input` args and core `RequestUserInputEvent`.
- Added model-facing schema text for `autoResolutionMs` while marking it
reserved for runtimes that explicitly support auto-resolution.
- Bounds `autoResolutionMs` to `60_000..=240_000` ms during argument
normalization by clamping out-of-range model-provided values.
- Propagated the field through app-server v2
`ToolRequestUserInputParams`, app-server request forwarding, generated
TypeScript, and JSON schema fixtures.
- Updated app-server, core, protocol, and TUI call sites/tests so
omitted values preserve existing `None`/`null` behavior and coverage
verifies a `Some(60_000)` round trip.

## Verification

- `just test -p codex-app-server-protocol`
- `just test -p codex-core request_user_input`
- `just test -p codex-app-server request_user_input_round_trip`
- `just test -p codex-tui request_user_input`
- `just test -p codex-protocol`
2026-06-11 22:30:41 -07:00
Charlie Marsh 41b4fabbb4 Use latest-wins MCP manager replacement (#27259)
## Summary

We originally addressed startup prewarming holding the read side of
`RwLock<McpConnectionManager>` by snapshotting tool-list state. Review
feedback identified the broader ownership problem: the outer
synchronization should only publish or retrieve the current manager,
while MCP operations rely on the manager's internal synchronization. A
follow-up preserved operation retirement with a separate gate, but
further review questioned whether that synchronization was actually
required and whether we could support latest-wins replacement instead.

This PR now stores the current MCP manager in `ArcSwap`. Each operation
uses `load_full()` to obtain an owned `Arc<McpConnectionManager>`, then
performs MCP I/O without retaining the publication mechanism. Refresh
cancels obsolete startup work, constructs a replacement, and atomically
publishes it. New operations see the latest manager, while operations
that already loaded the previous manager retain a valid handle. Refresh
happens at a turn boundary, so there should be no active user tool calls
to drain.

Git history supports dropping the outer `RwLock`. It was introduced in
`03ffe4d595` on November 17, 2025 for non-blocking MCP startup: the
session published an empty manager, startup initialized that same object
while holding the write lock, and readers waited for initialization.
`7cd2e84026` on February 19, 2026 removed that two-phase initialization
in favor of constructing a fresh manager and swapping it in, explicitly
noting that `Option` or `OnceCell` could replace the placeholder design.
Hot reload later reused the existing lock to publish a replacement, but
I found no indication that the lock was introduced to guarantee
in-flight tool calls finish before refresh or shutdown.

Terminal shutdown remains separate from refresh: it aborts startup
prewarming and active tasks before shutting down the current manager, so
tool calls may be interrupted and no model WebSocket work continues
after shutdown. Focused regression coverage exercises pending tool-list
cancellation, deferred refresh, and startup-prewarm shutdown.
2026-06-10 08:33:21 -07:00
jif c9ae0f48a1 chore: mechanical rename (#26156)
Rename `Session::conversation_id` to `Session::thread_id` with an auto
refactor in RustRover
2026-06-03 15:38:30 +02:00
Alex Zamoshchinandjif-oai 4d80d808b4 [app-server][core] Add connector-level Guardian reviewer overrides (#25167)
Context: https://openai.slack.com/archives/C0B4JAF0Q2C/p1779912328647229

```
approvals_reviewer = "auto_review"

[apps.connector_5f3c8c41a1e54ad7a76272c89e2554fa]
enabled = true
approvals_reviewer = "user"
default_tools_approval_mode = "prompt"
```

<img width="230" height="84" alt="Screenshot 2026-05-31 at 11 56 34 AM"
src="https://github.com/user-attachments/assets/e319f8f7-0983-42a7-98cd-3302732fa406"
/>

<img width="841" height="233" alt="Screenshot 2026-05-31 at 11 52 42 AM"
src="https://github.com/user-attachments/assets/7ac76645-4e90-4d00-8242-f031146a22a5"
/>

-------

```
approvals_reviewer = "user"

[apps.connector_5f3c8c41a1e54ad7a76272c89e2554fa]
enabled = true
approvals_reviewer = "auto_review"
default_tools_approval_mode = "prompt"
```
<img width="195" height="83" alt="Screenshot 2026-05-31 at 12 02 27 PM"
src="https://github.com/user-attachments/assets/3d374dc8-8aa2-466f-a13f-e4ed8567aa2e"
/>
<img width="771" height="207" alt="Screenshot 2026-05-31 at 12 05 42 PM"
src="https://github.com/user-attachments/assets/105c2575-68d6-4ca6-8e69-dc8c82da36a2"
/>



## Summary
- add `apps.<connector_id>.approvals_reviewer` to override Guardian or
user review routing per connected app
- apply overrides across direct app MCP calls, delegated MCP prompts,
and app-server MCP elicitation review while preserving global behavior
for non-app MCP servers
- expose and document the config through app-server v2 and generated
schemas, while honoring global managed reviewer requirements

---------

Co-authored-by: jif-oai <jif@openai.com>
2026-06-02 17:04:11 +02:00
pakrym-oai ff7513cd83 Move MCP tool naming mode into manager (#21576)
## Why

The `non_prefixed_mcp_tool_names` feature should be applied where MCP
tools become model-visible, not by remapping names later in core.
Keeping the decision in `McpConnectionManager` construction makes
`ToolInfo` the single shaped view that spec building, deferred tool
search, routing, and unavailable-tool placeholders can consume directly.

This also preserves the existing external behavior while the feature is
off, and keeps the feature-on behavior for code mode and hooks explicit
at the manager boundary.

## What Changed

- Add `McpToolNameMode` to `codex-mcp` and flow it through `McpConfig`
into `McpConnectionManager::new`.
- Normalize MCP `ToolInfo` names in the manager using either
legacy-prefixed namespaces or non-prefixed namespaces; the legacy path
adds `mcp__` without restoring the old trailing namespace suffix.
- Remove the core-side MCP name remapping path so specs, tool search,
session resolution, and unavailable-tool placeholder construction use
the manager-provided `ToolName` values directly.
- Keep code mode flattening on the `__` namespace separator.
- Preserve hook compatibility by giving non-prefixed MCP hook names
legacy `mcp__...` matcher aliases.
- Add/adjust integration and unit coverage for non-prefixed code-mode
behavior, hook matching with the feature on and off, and manager-level
legacy prefixing.

## Testing

- `cargo test -p codex-mcp --lib`
- `cargo test -p codex-core --lib tools::spec::tests -- --nocapture`
- `cargo test -p codex-core --lib mcp_tools -- --nocapture`
- `cargo test -p codex-core --lib mcp_tool_exposure -- --nocapture`
- `cargo test -p codex-core --test all mcp_tool -- --nocapture`
- `cargo test -p codex-core --test all search_tool -- --nocapture`
- `cargo test -p codex-core --test all hooks_mcp -- --nocapture`
- `cargo test -p codex-core --test all
code_mode_uses_non_prefixed_mcp_tool_names_when_feature_enabled --
--nocapture`
- `cargo test -p codex-tools`
- `cargo test -p codex-features`
2026-05-26 08:21:15 -07:00
Matthew Zeng 0a4179bb19 [codex] Add plugin id to MCP tool call items (#23737)
Add owning plugin id to MCP tool call items so we can better filter them
at plugin level.

## Summary
- add optional `plugin_id` to MCP tool-call items and legacy begin/end
events
- propagate plugin metadata into emitted core items and app-server v2
`ThreadItem::McpToolCall`
- preserve plugin ids through app-server replay/redaction paths and
regenerate v2 schema fixtures

## Testing
- `just write-app-server-schema`
- `just fmt`
- `just fix -p codex-core`
- `cargo test -p codex-protocol -p codex-app-server-protocol`
- `cargo test -p codex-app-server-protocol`
- `cargo test -p codex-core mcp_tool_call_item_includes_plugin_id --lib`
- `cargo check -p codex-tui --tests`
- `cargo check -p codex-app-server --tests`
- `git diff --check`

## Notes
- `just fix -p codex-core` completed with two non-fatal
`too_many_arguments` warnings on the touched MCP notification helpers.
- A broader `cargo test -p codex-core` run passed core unit tests, then
hit shell/sandbox/snapshot failures in the integration target.
- A broader app-server downstream run hit the existing
`in_process::tests::in_process_start_clamps_zero_channel_capacity` stack
overflow; `cargo test -p codex-exec` also hit the existing sandbox
expectation mismatch in
`thread_lifecycle_params_include_legacy_sandbox_when_no_active_profile`.
2026-05-20 17:02:10 -07:00
Matthew Zeng b019a678d8 Remove unused ARC monitor path (#23573)
## Summary
- remove the unreachable ARC monitor path from MCP tool approval
handling
- delete the unused ARC monitor module/tests and trim the orphaned
safety-monitor decision plumbing
- keep `always allow` approvals on the existing auto-approval
short-circuit without a dead monitor hop

## Testing
- `cargo test -p codex-core mcp_tool_call`
- `just fmt`
- `just fix -p codex-core`
- `git diff --check`

## Additional validation
- Attempted `cargo test -p codex-core`; the library test target passed,
then the integration target failed in this local environment.
- The narrower MCP-focused rerun passed its unit coverage and only hit
missing local `test_stdio_server` binaries in filtered integration
cases.
2026-05-19 16:23:25 -07:00
Matthew Zeng 8335b56c33 Split plugin install discovery into list and request tools (#23372)
## Summary
- Add `list_available_plugins_to_install` as the inventory step for
plugin and connector install suggestions.
- Slim `request_plugin_install` so it only handles the actual
elicitation, instead of carrying the full discoverable list in its
prompt.
- Emit send-time telemetry when an install elicitation is dispatched,
including requested tool identity in the event payload.
- Emit install-result telemetry through `SessionTelemetry`, including
tool type, user response action, and completion status.
- Update registration and tests to cover the new two-step flow while
keeping the existing `tool_suggest` feature gate unchanged.

## Testing
- `just fmt`
- `cargo test -p codex-tools`
- `cargo test -p codex-core request_plugin_install`
- `cargo test -p codex-core list_available_plugins_to_install`
- `cargo test -p codex-core
install_suggestion_tools_can_be_registered_without_search_tool`
- `cargo test -p codex-otel
manager_records_plugin_install_suggestion_metric`
- `cargo test -p codex-otel
manager_records_plugin_install_elicitation_sent_metric`
- `just fix -p codex-core`
- `just fix -p codex-tools`
- `just fix -p codex-otel`
- `cargo check -p codex-core`
2026-05-19 14:45:37 -07:00
Matthew Zeng a66e0e9c4b Include plugin id in plugin MCP tool metadata (#23353)
Adding the id of the plugin that contains the MCP (if any) so we can
apply filters at plugin level.

## Summary
- carry the plugin owner into MCP runtime provenance
- attach `plugin_id` to outbound plugin-backed MCP tool-call `_meta`
- avoid misattributing user-configured MCP servers that shadow plugin
server names

## Testing
- `just fmt`
- `just fix -p codex-mcp`
- `just fix -p codex-core`
- `cargo test -p codex-mcp`
- `cargo test -p codex-core
plugin_mcp_tool_call_request_meta_includes_plugin_id`
- `cargo test -p codex-core
to_mcp_config_omits_plugin_id_when_user_server_shadows_plugin_mcp`
- `cargo test -p codex-core
rebuild_preserving_session_layers_refreshes_plugin_derived_mcp_config`
- `git diff --check`

## Notes
- Attempted `cargo test -p codex-core`; it aborted in
`agent::control::tests::resume_agent_from_rollout_skips_descendants_when_parent_resume_fails`
with a stack overflow before the full suite completed.
2026-05-18 15:33:33 -07:00
mchen-oai 10cf1f79dd Add user_input_requested_during_turn to MCP turn metadata (#22237)
## Why
- Similar change as https://github.com/openai/codex/pull/21219
- Without change: MCP tool calls receive
`_meta["x-codex-turn-metadata"]` with various key values.
- Issue: MCP servers currently do not know if user input was requested
during the turn (Ex: Model decides to prompt the user for approval
mid-turn before making a possibly risky tool call). MCP servers may want
to know this when tracking latency metrics because these instances are
inflated.

## What Changed
- With change: MCP turn metadata now includes
`user_input_requested_during_turn` when a model-visible
`request_user_input` call happened earlier in the turn, propagated in
`_meta["x-codex-turn-metadata"]`.
- `mark_turn_user_input_requested()` is called when user input is
requested through either MCP elicitation (`mcp.rs`) or the
`request_user_input` tool (`mod.rs`).
- MCP tool call `_meta` is now built immediately before execution
(`mcp_tool_call.rs`) so user input requested earlier in the same turn,
including within the same tool call via elicitation, is reflected in the
metadata.
- Normal `/responses` turn metadata headers are unchanged.

## Verification
- `codex-rs/core/src/session/mcp_tests.rs`
- `codex-rs/core/src/tools/handlers/request_user_input_tests.rs`
- `codex-rs/core/src/turn_metadata_tests.rs`
- `codex-rs/core/tests/suite/search_tool.rs`
2026-05-15 01:26:50 +00:00
jif-oaiandCodex deedf3b2c4 feat: add layered --profile-v2 config files (#17141)
## Why

`--profile-v2 <name>` gives launchers and runtime entry points a named
profile config without making each profile duplicate the base user
config. The base `$CODEX_HOME/config.toml` still loads first, then
`$CODEX_HOME/<name>.config.toml` layers above it and becomes the active
writable user config for that session.

That keeps shared defaults, plugin/MCP setup, and managed/user
constraints in one place while letting a named profile override only the
pieces that need to differ.

## What Changed

- Added the shared `--profile-v2 <name>` runtime option with validated
plain names, now represented by `ProfileV2Name`.
- Extended config layer state so the base user config and selected
profile config are both `User` layers; APIs expose the active user layer
and merged effective user config.
- Threaded profile selection through runtime entry points: `codex`,
`codex exec`, `codex review`, `codex resume`, `codex fork`, and `codex
debug prompt-input`.
- Made user-facing config writes go to the selected profile file when
active, including TUI/settings persistence, app-server config writes,
and MCP/app tool approval persistence.
- Made plugin, marketplace, MCP, hooks, and config reload paths read
from the merged user config so base and profile layers both participate.
- Updated app-server config layer schemas to mark profile-backed user
layers.

## Limits

`--profile-v2` is still rejected for config-management subcommands such
as feature, MCP, and marketplace edits. Those paths remain tied to the
base `config.toml` until they have explicit profile-selection semantics.

Some adjacent background writes may still update base or global state
rather than the selected profile:

- marketplace auto-upgrade metadata
- automatic MCP dependency installs from skills
- remote plugin sync or uninstall config edits
- personality migration marker/default writes

## Verification

Added targeted coverage for profile name validation, layer
ordering/merging, selected-profile writes, app-server config writes,
session hot reload, plugin config merging, hooks/config fixture updates,
and MCP/app approval persistence.

---------

Co-authored-by: Codex <noreply@openai.com>
2026-05-14 15:16:15 +02:00
pakrym-oai 4454e1411b Deprecate TurnContext cwd and resolve_path (#22519)
## Why

`TurnContext::cwd` and `TurnContext::resolve_path` are being phased out
in favor of using the selected turn environment cwd directly.
Deprecating both APIs makes any new direct dependency visible while
preserving the existing migration path for current callers.

## What Changed

- Marked `TurnContext::cwd` and `TurnContext::resolve_path` as
deprecated with guidance to use the selected turn environment cwd
instead.
- Added exact `#[allow(deprecated)]` suppressions at each existing
direct usage site, including tests, rather than adding crate-wide
suppression.
- Kept the change behavior-preserving: current cwd reads, writes, and
path resolution continue to use the same values.

## Verification

- `just fmt`
- `cargo check -p codex-core`
- `cargo check -p codex-core --tests`
- `git diff --check`
2026-05-13 11:15:25 -07:00
cassirer-openai 702e6a3c64 [rollout-trace] Add a trace ID to MCP calls. (#22326)
This allows us to connect individual tool calls to the logs of the
invocations.
2026-05-13 16:03:33 +00:00
pakrym-oai 857e731478 [codex] Remove string-keyed MCP tool maps (#21454)
## Summary

This PR removes the synthetic `HashMap<String, ToolInfo>` keys from MCP
tool discovery. `McpConnectionManager::list_all_tools()` now returns
normalized `Vec<ToolInfo>`, and downstream code derives identity from
`ToolInfo::canonical_tool_name()`.

The motivation is to keep model-visible tool identity on
`ToolName`/`ToolInfo` instead of parallel string map keys, so future
namespace changes do not have to preserve otherwise-unused lookup keys.

## Changes

- Rename the MCP normalization path from `qualify_tools` to
`normalize_tools_for_model` and return tool values directly.
- Flow MCP tool lists through connectors, plugin injection, router/spec
building, code mode, and tool search as vectors/slices.
- Keep direct/deferred subtraction local to `mcp_tool_exposure`, using
`ToolName` values.
- Update tests to compare `ToolName` instances where MCP identity
matters.

## Validation

- `cargo test -p codex-mcp test_normalize_tools`
- `cargo test -p codex-core mcp_tool_exposure`
- `cargo test -p codex-core
direct_mcp_tools_register_namespaced_handlers`
- `cargo test -p codex-core
search_tool_registers_namespaced_mcp_tool_aliases`
- `just fix -p codex-mcp`
- `just fix -p codex-core`
2026-05-07 10:16:10 -07:00
jif-oaiandCodex b2268999fe feat: make built-in MCPs first-class runtime servers (#21356)
## DISCLAIMER
This is experimental and no production service must rely on this

## Why

Built-in MCPs are product-owned runtime capabilities, but they were
previously flattened into the same config-backed stdio path as
user-configured servers. That made them depend on a hidden `codex
builtin-mcp` re-exec path, exposed them through config-oriented CLI
flows, and erased distinctions the runtime needs to preserve—most
notably whether an MCP call should count as external context for
memory-mode pollution.

## What changed

- Model product-owned built-ins separately from config-backed MCP
servers via `BuiltinMcpServer` and `EffectiveMcpServer`.
- Launch built-ins in process through a reusable async transport instead
of the hidden `builtin-mcp` stdio subcommand.
- Keep config-oriented CLI operations such as `codex mcp
list/get/login/logout` scoped to configured servers, while merging
built-ins only into the effective runtime server set.
- Retain server metadata after launch so parallel-tool support and
context classification come from the live server set; built-in
`memories` is now classified as local Codex state rather than external
context.

## Test plan

- `cargo test -p codex-mcp`
- `cargo test -p codex-core --test suite
builtin_memories_mcp_call_does_not_mark_thread_memory_mode_polluted_when_configured`

---------

Co-authored-by: Codex <noreply@openai.com>
2026-05-07 10:36:32 +02:00
Clark DuVall 346070a424 Route opted-in MCP elicitations through Guardian (#19431)
# Motivation

Browser Use origin-access prompts are MCP elicitations, not direct
tool-call approval prompts, so they were bypassing the Guardian approval
path. We need a generic opt-in that lets eligible MCP elicitations use
Guardian when the current turn already routes approvals there.

# Description

Add a generic elicitation reviewer hook in codex-mcp and wire codex-core
to pass a Guardian reviewer callback when creating the MCP connection
manager. The reviewer validates explicit mcp_tool_call opt-in metadata,
builds a Guardian MCP tool-call review request from
server/tool/connector metadata and tool params, and maps Guardian
approval, denial, timeout, and cancellation decisions back to MCP
elicitation responses.

The new option to trigger this in the `_meta` object is:
```
"codex_request_type": "approval_request",
```

# Testing

- RUST_MIN_STACK=8388608 NEXTEST_STATUS_LEVEL=leak cargo nextest run
--no-fail-fast --cargo-profile ci-test --test-threads 2
- cargo clippy --tests -- -D warnings
- cargo fmt -- --config imports_granularity=Item --check
- cargo shear
- pnpm run format
- python3 .github/scripts/verify_cargo_workspace_manifests.py
- python3 .github/scripts/verify_tui_core_boundary.py
- python3 .github/scripts/verify_bazel_clippy_lints.py
- git diff --check
2026-05-06 19:42:45 +00:00
Matthew Zeng f9a907aebe Support Codex Apps auth elicitations (#19193)
## Summary

- request URL-mode MCP elicitations when Codex Apps tool calls fail with
connector auth metadata
- route Codex Apps auth URL elicitations into the TUI app-link flow

## Test plan

- `just fmt`
- `cargo test -p codex-core mcp_tool_call::tests`
- `cargo test -p codex-mcp`
- `cargo test -p codex-tui bottom_pane::app_link_view::tests`
- `just fix -p codex-core`
- `just fix -p codex-mcp`
- `just fix -p codex-tui`

Also attempted broader local runs:

- `cargo test -p codex-core` fails in unrelated
config/request-permission/proxy-sensitive tests under the current Codex
Desktop environment.
- `cargo test -p codex-tui` fails in unrelated status
snapshots/trust-default tests because the ambient environment renders
workspace-write/network permission defaults.
2026-05-06 07:18:00 +00:00
mchen-oai 794c240f25 Add model and reasoning effort to MCP turn metadata (#21219)
## Why
- Similar change as https://github.com/openai/codex/pull/19473.
- Without change: MCP tool calls receive
`_meta["x-codex-turn-metadata"]` with `session_id`, `turn_id`, and
`turn_started_at_unix_ms`.
- Issue: MCP servers may want the model and reasoning effort to better
understand tool-call behavior and latency relative to turn start.

## What Changed
- With change: MCP turn metadata now includes `model` and
`reasoning_effort`, propagated in `_meta["x-codex-turn-metadata"]`.
- Normal `/responses` turn metadata headers are unchanged.

## Verification
- `codex-rs/core/src/mcp_tool_call_tests.rs`
- `codex-rs/core/src/turn_metadata_tests.rs`
- `codex-rs/core/tests/suite/search_tool.rs`
2026-05-05 17:37:48 -07:00
pakrym-oai c8c30d9d75 [codex] Emit MCP tool calls as turn items (#20677)
## Why

`McpToolCall` was still an app-server item synthesized from deprecated
legacy begin/end events. Recent item migrations moved this ownership
into core `TurnItem`s, so MCP tool calls now follow the same canonical
lifecycle and leave legacy events as compatibility fanout.

Keeping the core item close to the v2 `ThreadItem::McpToolCall` shape
also avoids spreading MCP result semantics across app-server conversion
code. Core now owns whether a completed call is `completed` or `failed`,
and whether the payload is a tool result or an error.

## What changed

- Added core `TurnItem::McpToolCall` with flattened `server`, `tool`,
`arguments`, `status`, `result`, and `error` fields.
- Updated MCP tool call emitters, including MCP resource tools, to emit
`ItemStarted`/`ItemCompleted` around directly constructed core MCP
items.
- Updated app-server v2 conversion to project the core MCP item into
`ThreadItem::McpToolCall` without deriving status or splitting `Result`
locally.
- Ignored live deprecated MCP legacy fanout in app-server v2 to avoid
duplicate item notifications, while keeping thread history replay on the
legacy event path.

## Verification

- `cargo test -p codex-protocol`
- `cargo test -p codex-app-server-protocol`
- `cargo test -p codex-core --lib mcp_tool_call`
- `cargo check -p codex-app-server`
- `cargo test -p codex-app-server
mcp_tool_call_completion_notification_contains_truncated_large_result`
2026-05-03 22:50:13 -07:00
maja-openai a5ebedef67 Bypass review for always-allow MCP tools in auto-review (#20069)
## Why

When an MCP or app tool is configured with approval mode `approve`
(always allow), users expect that decision to be authoritative. In
guardian auto-review mode, ARC could still return `ask-user`, which then
routed the approval question into guardian with the ARC reason as
context. That meant a tool explicitly configured as always allowed still
went through both safety monitors before running.

This change keeps the existing ARC behavior for non-auto-review
sessions, but avoids the ARC-to-guardian sequence when
`approvals_reviewer = auto_review` and the tool approval mode is
`approve`.

## What changed

- Short-circuit MCP tool approval handling when `approval_mode ==
approve` and `approvals_reviewer == auto_review`.
- Updated the MCP approval regression test so the auto-review case
asserts neither ARC nor guardian is called.
- Preserved existing tests that verify ARC can still block always-allow
MCP tools outside guardian auto-review mode.

## Verification

- `cargo test -p codex-core --lib mcp_tool_call`
2026-04-30 16:44:09 -07:00
xl-openai 7b3de63041 Move plugin out of core. (#20348) 2026-04-30 14:26:14 -07:00
Owen Lin 3516cb9751 fix(core): truncate large mcp tool outputs in rollouts (#20260)
## Why
Large MCP tool call outputs can make rollout JSONL files enormous. In
the session that motivated this change, the biggest JSONL records were:
- `event_msg/mcp_tool_call_end`
- `response_item/function_call_output`

both containing the same unbounded MCP payloads - just 3 MCP tool calls
that each were multi-hundred MBs 😱

This PR truncates both of those JSONL records.

## How

#### For `response_item/function_call_output`
Unified exec already bounds tool output before it is injected into
model-facing history, which also keeps the corresponding rollout
`response_item/function_call_output` records small.

MCP should follow the same pattern: truncate the model-facing tool
output at the tool-output boundary, while leaving code-mode/raw hook
consumers alone.

#### For `event_msg/mcp_tool_call_end`
`McpToolCallEnd` also needs its own bounded event copy because it is the
app-server/replay/UI event shape that backs `ThreadItem::McpToolCall`.
Unfortunately this is _not_ downstream of the `ToolOutput` trait.

## Model behavior 
Model behavior is actually unchanged as a result of this PR. 

Before this PR, MCP output was:
1. Converted to `FunctionCallOutput`.
2. Recorded into in-memory history.
3. Truncated by `ContextManager::record_items()` before later model
turns saw it.

After this branch, MCP output is truncated earlier, in
`McpToolOutput::response_payload()`, using the same helper. Then
`ContextManager::record_items()` sees an already-truncated output and
effectively has little/no additional work to do.

So the model should still see the same kind of truncated function-call
output. The practical difference is where truncation happens: earlier,
before rollout persistence/app-server emission can see the giant
payload.

## Verification

- `cargo test -p codex-core mcp_tool_output`
- `cargo test -p codex-core
mcp_tool_call::tests::truncate_mcp_tool_result_for_event`
- `cargo test -p codex-core
mcp_post_tool_use_payload_uses_model_tool_name_args_and_result`
- `just fmt`
- `just fix -p codex-core`
- `git diff --check`
2026-04-30 16:30:43 +00:00
Matthew Zeng e20391e567 [mcp] Fix plugin MCP approval policy. (#19537)
Plugin MCP servers are loaded from plugin manifests rather than
top-level `[mcp_servers]`, so their tool approval preferences need to be
stored and applied through the owning plugin config. Without this,
choosing "Always allow" for a plugin MCP tool could write a preference
that was not reliably used on later tool calls.

## Summary
- Add plugin-scoped MCP policy config under
`plugins.<plugin>.mcp_servers`, including server enablement, tool
allow/deny lists, server defaults, and per-tool approval modes.
- Overlay plugin MCP policy onto manifest-provided server configs when
plugins are loaded.
- Route persistent "Always allow" writes for plugin MCP tools back to
the owning `plugins.<plugin>.mcp_servers.<server>.tools.<tool>` config
entry.
- Reload user config after persisting an approval and make the plugin
load cache config-aware so stale plugin MCP policy is not reused after
`config.toml` changes.
- Regenerate the config schema and add coverage for plugin MCP policy
loading, approval lookup, persistence, and stale-cache prevention.

## Testing
- `cargo test -p codex-config`
- `cargo test -p codex-core-plugins`
- `cargo test -p codex-core --lib plugin_mcp`
2026-04-29 15:40:03 -07:00
mchen-oai 01de13b7e6 Record MCP result telemetry on mcp.tools.call spans (#19509)
## Why
- Without change: MCP tool call spans include request-side details such
as server, tool, call ID, connector, session, and turn.
- Issue: Some useful telemetry is only known by the MCP server after it
handles the tool call, such as target identity or whether the call
triggered a user-facing flow.

## What Changed
- With change: Codex reads allowlisted telemetry from
`_meta["codex/telemetry"]["span"]` and records it on the
`mcp.tools.call` span.
- Adds span fields for `codex.mcp.target.id` and
`codex.mcp.user_flow.triggered`, with strict type checks and bounded
target ID length.


## Verification
`codex-rs/core/src/mcp_tool_call_tests.rs`
2026-04-28 17:20:38 +00:00
colby-oai 2f3b5ed81a disallow fileparams metadata for custom mcps (#19836)
## Summary
Disallow fileParams metadata for custom MCPs 

Restricts Codex openai/fileParams handling to the first-party codex_apps
MCP server. Custom MCP servers may still advertise the metadata, but
Codex now ignores it for upload rewriting, preventing non-Apps tools
from receiving signed OpenAI file refs for local paths. Added a
regression test for the allowed and denied cases.
2026-04-27 20:42:10 -04:00
Michael Bolin deaa307fb2 permissions: derive compatibility policies from profiles (#19392)
## Why

After #19391, `PermissionProfile` and the split filesystem/network
policies could still be stored in parallel. That creates drift risk: a
profile can preserve deny globs, external enforcement, or split
filesystem entries while a cached projection silently loses those
details. This PR makes the profile the runtime source and derives
compatibility views from it.

## What Changed

- Removes stored filesystem/network sandbox projections from
`Permissions` and `SessionConfiguration`; their accessors now derive
from the canonical `PermissionProfile`.
- Derives legacy `SandboxPolicy` snapshots from profiles only where an
older API still needs that field.
- Updates MCP connection and elicitation state to track
`PermissionProfile` instead of `SandboxPolicy` for auto-approval
decisions.
- Adds semantic filesystem-policy comparison so cwd changes can preserve
richer profiles while still recognizing equivalent legacy projections
independent of entry ordering.
- Updates config/session tests to assert profile-derived projections
instead of parallel stored fields.

## Verification

- `cargo test -p codex-core direct_write_roots`
- `cargo test -p codex-core runtime_roots_to_legacy_projection`
- `cargo test -p codex-app-server
requested_permissions_trust_project_uses_permission_profile_intent`



































































---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/19392).
* #19395
* #19394
* #19393
* __->__ #19392
2026-04-26 15:06:42 -07:00
rreichel3-oai 219c65dc2f [codex] Forward Codex Apps tool call IDs to backend metadata (#19207)
## Summary
- include the outer tool `call_id` in Codex Apps MCP request metadata
under `_meta._codex_apps.call_id`
- preserve existing Codex Apps metadata like `resource_uri` and
`contains_mcp_source`
- add request metadata coverage for both the existing-metadata and
no-existing-metadata cases

## Why
The paired backend change in
[openai/openai#850796](https://github.com/openai/openai/pull/850796)
updates MCP compliance logging to prefer `_meta._codex_apps.call_id`
instead of the JSON-RPC request id. This client change sends that outer
tool call id so the backend can record the model/tool call identifier
when it is available.

This is wire-compatible with older backends because `_meta._codex_apps`
is already reserved backend-only metadata. Backends that do not read
`call_id` will ignore the extra field.

## Testing
- `cargo test -p codex-core request_meta`
- `just fmt`
- `just fix -p codex-core`
2026-04-24 18:49:34 -04:00