Files
codex/codex-rs/core/tests/suite/model_overrides.rs
Charley Cunningham bc24017d64 Add Smart Approvals guardian review across core, app-server, and TUI (#13860)
## Summary
- add `approvals_reviewer = "user" | "guardian_subagent"` as the runtime
control for who reviews approval requests
- route Smart Approvals guardian review through core for command
execution, file changes, managed-network approvals, MCP approvals, and
delegated/subagent approval flows
- expose guardian review in app-server with temporary unstable
`item/autoApprovalReview/{started,completed}` notifications carrying
`targetItemId`, `review`, and `action`
- update the TUI so Smart Approvals can be enabled from `/experimental`,
aligned with the matching `/approvals` mode, and surfaced clearly while
reviews are pending or resolved

## Runtime model
This PR does not introduce a new `approval_policy`.

Instead:
- `approval_policy` still controls when approval is needed
- `approvals_reviewer` controls who reviewable approval requests are
routed to:
  - `user`
  - `guardian_subagent`

`guardian_subagent` is a carefully prompted reviewer subagent that
gathers relevant context and applies a risk-based decision framework
before approving or denying the request.

The `smart_approvals` feature flag is a rollout/UI gate. Core runtime
behavior keys off `approvals_reviewer`.

When Smart Approvals is enabled from the TUI, it also switches the
current `/approvals` settings to the matching Smart Approvals mode so
users immediately see guardian review in the active thread:
- `approval_policy = on-request`
- `approvals_reviewer = guardian_subagent`
- `sandbox_mode = workspace-write`

Users can still change `/approvals` afterward.

Config-load behavior stays intentionally narrow:
- plain `smart_approvals = true` in `config.toml` remains just the
rollout/UI gate and does not auto-set `approvals_reviewer`
- the deprecated `guardian_approval = true` alias migration does
backfill `approvals_reviewer = "guardian_subagent"` in the same scope
when that reviewer is not already configured there, so old configs
preserve their original guardian-enabled behavior

ARC remains a separate safety check. For MCP tool approvals, ARC
escalations now flow into the configured reviewer instead of always
bypassing guardian and forcing manual review.

## Config stability
The runtime reviewer override is stable, but the config-backed
app-server protocol shape is still settling.

- `thread/start`, `thread/resume`, and `turn/start` keep stable
`approvalsReviewer` overrides
- the config-backed `approvals_reviewer` exposure returned via
`config/read` (including profile-level config) is now marked
`[UNSTABLE]` / experimental in the app-server protocol until we are more
confident in that config surface

## App-server surface
This PR intentionally keeps the guardian app-server shape narrow and
temporary.

It adds generic unstable lifecycle notifications:
- `item/autoApprovalReview/started`
- `item/autoApprovalReview/completed`

with payloads of the form:
- `{ threadId, turnId, targetItemId, review, action? }`

`review` is currently:
- `{ status, riskScore?, riskLevel?, rationale? }`
- where `status` is one of `inProgress`, `approved`, `denied`, or
`aborted`

`action` carries the guardian action summary payload from core when
available. This lets clients render temporary standalone pending-review
UI, including parallel reviews, even when the underlying tool item has
not been emitted yet.

These notifications are explicitly documented as `[UNSTABLE]` and
expected to change soon.

This PR does **not** persist guardian review state onto `thread/read`
tool items. The intended follow-up is to attach guardian review state to
the reviewed tool item lifecycle instead, which would improve
consistency with manual approvals and allow thread history / reconnect
flows to replay guardian review state directly.

## TUI behavior
- `/experimental` exposes the rollout gate as `Smart Approvals`
- enabling it in the TUI enables the feature and switches the current
session to the matching Smart Approvals `/approvals` mode
- disabling it in the TUI clears the persisted `approvals_reviewer`
override when appropriate and returns the session to default manual
review when the effective reviewer changes
- `/approvals` still exposes the reviewer choice directly
- the TUI renders:
- pending guardian review state in the live status footer, including
parallel review aggregation
  - resolved approval/denial state in history

## Scope notes
This PR includes the supporting core/runtime work needed to make Smart
Approvals usable end-to-end:
- shell / unified-exec / apply_patch / managed-network / MCP guardian
review
- delegated/subagent approval routing into guardian review
- guardian review risk metadata and action summaries for app-server/TUI
- config/profile/TUI handling for `smart_approvals`, `guardian_approval`
alias migration, and `approvals_reviewer`
- a small internal cleanup of delegated approval forwarding to dedupe
fallback paths and simplify guardian-vs-parent approval waiting (no
intended behavior change)

Out of scope for this PR:
- redesigning the existing manual approval protocol shapes
- persisting guardian review state onto app-server `ThreadItem`s
- delegated MCP elicitation auto-review (the current delegated MCP
guardian shim only covers the legacy `RequestUserInput` path)

---------

Co-authored-by: Codex <noreply@openai.com>
2026-03-13 15:27:00 -07:00

90 lines
3.1 KiB
Rust

use codex_protocol::openai_models::ReasoningEffort;
use codex_protocol::protocol::EventMsg;
use codex_protocol::protocol::Op;
use core_test_support::responses::start_mock_server;
use core_test_support::test_codex::test_codex;
use core_test_support::wait_for_event;
use pretty_assertions::assert_eq;
const CONFIG_TOML: &str = "config.toml";
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn override_turn_context_does_not_persist_when_config_exists() {
let server = start_mock_server().await;
let initial_contents = "model = \"gpt-4o\"\n";
let mut builder = test_codex()
.with_pre_build_hook(move |home| {
let config_path = home.join(CONFIG_TOML);
std::fs::write(config_path, initial_contents).expect("seed config.toml");
})
.with_config(|config| {
config.model = Some("gpt-4o".to_string());
});
let test = builder.build(&server).await.expect("create conversation");
let codex = test.codex.clone();
let config_path = test.home.path().join(CONFIG_TOML);
codex
.submit(Op::OverrideTurnContext {
cwd: None,
approval_policy: None,
approvals_reviewer: None,
sandbox_policy: None,
windows_sandbox_level: None,
model: Some("o3".to_string()),
effort: Some(Some(ReasoningEffort::High)),
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await
.expect("submit override");
codex.submit(Op::Shutdown).await.expect("request shutdown");
wait_for_event(&codex, |ev| matches!(ev, EventMsg::ShutdownComplete)).await;
let contents = tokio::fs::read_to_string(&config_path)
.await
.expect("read config.toml after override");
assert_eq!(contents, initial_contents);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn override_turn_context_does_not_create_config_file() {
let server = start_mock_server().await;
let mut builder = test_codex();
let test = builder.build(&server).await.expect("create conversation");
let codex = test.codex.clone();
let config_path = test.home.path().join(CONFIG_TOML);
assert!(
!config_path.exists(),
"test setup should start without config"
);
codex
.submit(Op::OverrideTurnContext {
cwd: None,
approval_policy: None,
approvals_reviewer: None,
sandbox_policy: None,
windows_sandbox_level: None,
model: Some("o3".to_string()),
effort: Some(Some(ReasoningEffort::Medium)),
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await
.expect("submit override");
codex.submit(Op::Shutdown).await.expect("request shutdown");
wait_for_event(&codex, |ev| matches!(ev, EventMsg::ShutdownComplete)).await;
assert!(
!config_path.exists(),
"override should not create config.toml"
);
}