fix: enable per-turn updates to web search mode (#10040)

web_search can now be updated per-turn, for things like changes to
sandbox policy.

`SandboxPolicy::DangerFullAccess` now sets web_search to `live`, and the
default is still `cached`.

Added integration tests.
This commit is contained in:
sayan-oai
2026-01-27 18:09:29 -08:00
committed by GitHub
parent 3f3916e595
commit a90ab789c2
9 changed files with 187 additions and 102 deletions

View File

@@ -38,7 +38,7 @@ async fn collect_tool_identifiers_for_model(model: &str) -> Vec<String> {
.with_model(model)
// Keep tool expectations stable when the default web_search mode changes.
.with_config(|config| {
config.web_search_mode = WebSearchMode::Cached;
config.web_search_mode = Some(WebSearchMode::Cached);
config.features.enable(Feature::CollaborationModes);
});
let test = builder

View File

@@ -92,7 +92,7 @@ async fn prompt_tools_are_consistent_across_requests() -> anyhow::Result<()> {
config.user_instructions = Some("be consistent and helpful".to_string());
config.model = Some("gpt-5.1-codex-max".to_string());
// Keep tool expectations stable when the default web_search mode changes.
config.web_search_mode = WebSearchMode::Cached;
config.web_search_mode = Some(WebSearchMode::Cached);
config.features.enable(Feature::CollaborationModes);
})
.build(&server)

View File

@@ -1,6 +1,7 @@
#![allow(clippy::unwrap_used)]
use codex_core::features::Feature;
use codex_core::protocol::SandboxPolicy;
use codex_protocol::config_types::WebSearchMode;
use core_test_support::load_sse_fixture_with_id;
use core_test_support::responses;
@@ -25,7 +26,7 @@ fn find_web_search_tool(body: &Value) -> &Value {
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn web_search_mode_cached_sets_external_web_access_false_in_request_body() {
async fn web_search_mode_cached_sets_external_web_access_false() {
skip_if_no_network!();
let server = start_mock_server().await;
@@ -35,7 +36,7 @@ async fn web_search_mode_cached_sets_external_web_access_false_in_request_body()
let mut builder = test_codex()
.with_model("gpt-5-codex")
.with_config(|config| {
config.web_search_mode = WebSearchMode::Cached;
config.web_search_mode = Some(WebSearchMode::Cached);
});
let test = builder
.build(&server)
@@ -56,7 +57,7 @@ async fn web_search_mode_cached_sets_external_web_access_false_in_request_body()
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn web_search_mode_takes_precedence_over_legacy_flags_in_request_body() {
async fn web_search_mode_takes_precedence_over_legacy_flags() {
skip_if_no_network!();
let server = start_mock_server().await;
@@ -67,7 +68,7 @@ async fn web_search_mode_takes_precedence_over_legacy_flags_in_request_body() {
.with_model("gpt-5-codex")
.with_config(|config| {
config.features.enable(Feature::WebSearchRequest);
config.web_search_mode = WebSearchMode::Cached;
config.web_search_mode = Some(WebSearchMode::Cached);
});
let test = builder
.build(&server)
@@ -86,3 +87,90 @@ async fn web_search_mode_takes_precedence_over_legacy_flags_in_request_body() {
"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_unset() {
skip_if_no_network!();
let server = start_mock_server().await;
let sse = sse_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 = None;
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![sse_completed("resp-1"), sse_completed("resp-2")],
)
.await;
let mut builder = test_codex()
.with_model("gpt-5-codex")
.with_config(|config| {
config.web_search_mode = None;
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"
);
}