Files
codex/codex-rs/core/tests/suite/web_search.rs
Michael Bolin a118494323 feat: add support for allowed_web_search_modes in requirements.toml (#10964)
This PR makes it possible to disable live web search via an enterprise
config even if the user is running in `--yolo` mode (though cached web
search will still be available). To do this, create
`/etc/codex/requirements.toml` as follows:

```toml
# "live" is not allowed; "disabled" is allowed even though not listed explicitly.
allowed_web_search_modes = ["cached"]
```

Or set `requirements_toml_base64` MDM as explained on
https://developers.openai.com/codex/security/#locations.

### Why
- Enforce admin/MDM/`requirements.toml` constraints on web-search
behavior, independent of user config and per-turn sandbox defaults.
- Ensure per-turn config resolution and review-mode overrides never
crash when constraints are present.

### What
- Add `allowed_web_search_modes` to requirements parsing and surface it
in app-server v2 `ConfigRequirements` (`allowedWebSearchModes`), with
fixtures updated.
- Define a requirements allowlist type (`WebSearchModeRequirement`) and
normalize semantics:
  - `disabled` is always implicitly allowed (even if not listed).
  - An empty list is treated as `["disabled"]`.
- Make `Config.web_search_mode` a `Constrained<WebSearchMode>` and apply
requirements via `ConstrainedWithSource<WebSearchMode>`.
- Update per-turn resolution (`resolve_web_search_mode_for_turn`) to:
- Prefer `Live → Cached → Disabled` when
`SandboxPolicy::DangerFullAccess` is active (subject to requirements),
unless the user preference is explicitly `Disabled`.
- Otherwise, honor the user’s preferred mode, falling back to an allowed
mode when necessary.
- Update TUI `/debug-config` and app-server mapping to display
normalized `allowed_web_search_modes` (including implicit `disabled`).
- Fix web-search integration tests to assert cached behavior under
`SandboxPolicy::ReadOnly` (since `DangerFullAccess` legitimately prefers
`live` when allowed).
2026-02-07 05:55:15 +00:00

202 lines
6.6 KiB
Rust

#![allow(clippy::unwrap_used)]
use codex_core::features::Feature;
use codex_core::protocol::SandboxPolicy;
use codex_protocol::config_types::WebSearchMode;
use core_test_support::responses;
use core_test_support::responses::start_mock_server;
use core_test_support::skip_if_no_network;
use core_test_support::test_codex::test_codex;
use pretty_assertions::assert_eq;
use serde_json::Value;
#[allow(clippy::expect_used)]
fn find_web_search_tool(body: &Value) -> &Value {
body["tools"]
.as_array()
.expect("request body should include tools array")
.iter()
.find(|tool| tool.get("type").and_then(Value::as_str) == Some("web_search"))
.expect("tools should include a web_search tool")
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn web_search_mode_cached_sets_external_web_access_false() {
skip_if_no_network!();
let server = start_mock_server().await;
let sse = responses::sse(vec![
responses::ev_response_created("resp-1"),
responses::ev_completed("resp-1"),
]);
let resp_mock = responses::mount_sse_once(&server, sse).await;
let mut builder = test_codex()
.with_model("gpt-5-codex")
.with_config(|config| {
config
.web_search_mode
.set(WebSearchMode::Cached)
.expect("test web_search_mode should satisfy constraints");
});
let test = builder
.build(&server)
.await
.expect("create test Codex conversation");
test.submit_turn_with_policy("hello cached web search", SandboxPolicy::ReadOnly)
.await
.expect("submit turn");
let body = resp_mock.single_request().body_json();
let tool = find_web_search_tool(&body);
assert_eq!(
tool.get("external_web_access").and_then(Value::as_bool),
Some(false),
"web_search cached mode should force external_web_access=false"
);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn web_search_mode_takes_precedence_over_legacy_flags() {
skip_if_no_network!();
let server = start_mock_server().await;
let sse = responses::sse(vec![
responses::ev_response_created("resp-1"),
responses::ev_completed("resp-1"),
]);
let resp_mock = responses::mount_sse_once(&server, sse).await;
let mut builder = test_codex()
.with_model("gpt-5-codex")
.with_config(|config| {
config.features.enable(Feature::WebSearchRequest);
config
.web_search_mode
.set(WebSearchMode::Cached)
.expect("test web_search_mode should satisfy constraints");
});
let test = builder
.build(&server)
.await
.expect("create test Codex conversation");
test.submit_turn_with_policy("hello cached+live flags", SandboxPolicy::ReadOnly)
.await
.expect("submit turn");
let body = resp_mock.single_request().body_json();
let tool = find_web_search_tool(&body);
assert_eq!(
tool.get("external_web_access").and_then(Value::as_bool),
Some(false),
"web_search mode should win over legacy web_search_request"
);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn web_search_mode_defaults_to_cached_when_features_disabled() {
skip_if_no_network!();
let server = start_mock_server().await;
let sse = responses::sse(vec![
responses::ev_response_created("resp-1"),
responses::ev_completed("resp-1"),
]);
let resp_mock = responses::mount_sse_once(&server, sse).await;
let mut builder = test_codex()
.with_model("gpt-5-codex")
.with_config(|config| {
config
.web_search_mode
.set(WebSearchMode::Cached)
.expect("test web_search_mode should satisfy constraints");
config.features.disable(Feature::WebSearchCached);
config.features.disable(Feature::WebSearchRequest);
});
let test = builder
.build(&server)
.await
.expect("create test Codex conversation");
test.submit_turn_with_policy("hello default cached web search", SandboxPolicy::ReadOnly)
.await
.expect("submit turn");
let body = resp_mock.single_request().body_json();
let tool = find_web_search_tool(&body);
assert_eq!(
tool.get("external_web_access").and_then(Value::as_bool),
Some(false),
"default web_search should be cached when unset"
);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn web_search_mode_updates_between_turns_with_sandbox_policy() {
skip_if_no_network!();
let server = start_mock_server().await;
let resp_mock = responses::mount_sse_sequence(
&server,
vec![
responses::sse(vec![
responses::ev_response_created("resp-1"),
responses::ev_completed("resp-1"),
]),
responses::sse(vec![
responses::ev_response_created("resp-2"),
responses::ev_completed("resp-2"),
]),
],
)
.await;
let mut builder = test_codex()
.with_model("gpt-5-codex")
.with_config(|config| {
config
.web_search_mode
.set(WebSearchMode::Cached)
.expect("test web_search_mode should satisfy constraints");
config.features.disable(Feature::WebSearchCached);
config.features.disable(Feature::WebSearchRequest);
});
let test = builder
.build(&server)
.await
.expect("create test Codex conversation");
test.submit_turn_with_policy("hello cached", SandboxPolicy::ReadOnly)
.await
.expect("submit first turn");
test.submit_turn_with_policy("hello live", SandboxPolicy::DangerFullAccess)
.await
.expect("submit second turn");
let requests = resp_mock.requests();
assert_eq!(requests.len(), 2, "expected two response requests");
let first_body = requests[0].body_json();
let first_tool = find_web_search_tool(&first_body);
assert_eq!(
first_tool
.get("external_web_access")
.and_then(Value::as_bool),
Some(false),
"read-only policy should default web_search to cached"
);
let second_body = requests[1].body_json();
let second_tool = find_web_search_tool(&second_body);
assert_eq!(
second_tool
.get("external_web_access")
.and_then(Value::as_bool),
Some(true),
"danger-full-access policy should default web_search to live"
);
}