Files
codex/codex-rs/tools/src/tool_spec_tests.rs
T
Winston Howes 3a2712ea14 Add indexed web search mode (#28489)
## Summary

- Add `web_search = "indexed"` alongside `disabled`, `cached`, and
`live`.
- Use that same resolved mode for both hosted and standalone web search.
- For hosted search, send `index_gated_web_access: true` with external
web access enabled only when `indexed` is selected.
- For standalone search, preserve the existing boolean wire values for
existing modes (`cached` maps to `false` and `live` to `true`) and send
`"indexed"` only for `indexed`; `disabled` keeps the tool unavailable.
- Carry the mode through managed configuration requirements and
generated schemas.

## Why

Indexed search provides a middle ground between cached-only search and
unrestricted live page fetching. Search queries can remain live while
direct page fetches are limited to URLs admitted by the server.

The existing `web_search` setting remains the single source of truth, so
hosted and standalone executors cannot drift into different access
modes. Without an explicit `indexed` selection, the existing
model-visible tool and request shapes are unchanged.

```toml
web_search = "indexed"

[features]
standalone_web_search = true
```

## Validation

- `just fmt`
- `just test -p codex-api` (`126 passed`)
- `just test -p codex-web-search-extension` (`7 passed`)
- `just test -p codex-core
code_mode_can_call_indexed_standalone_web_search` (`1 passed`)
- Focused configuration, hosted request, standalone request, and
managed-requirement coverage is included in the PR; remaining suites run
in CI.

The full workspace test suite was not run locally.
2026-06-19 05:35:57 -07:00

271 lines
8.9 KiB
Rust

use super::ResponsesApiNamespace;
use super::ResponsesApiWebSearchFilters;
use super::ResponsesApiWebSearchUserLocation;
use super::ToolSpec;
use crate::AdditionalProperties;
use crate::FreeformTool;
use crate::FreeformToolFormat;
use crate::JsonSchema;
use crate::ResponsesApiNamespaceTool;
use crate::ResponsesApiTool;
use crate::create_tools_json_for_responses_api;
use codex_protocol::config_types::WebSearchContextSize;
use codex_protocol::config_types::WebSearchFilters as ConfigWebSearchFilters;
use codex_protocol::config_types::WebSearchUserLocation as ConfigWebSearchUserLocation;
use codex_protocol::config_types::WebSearchUserLocationType;
use pretty_assertions::assert_eq;
use serde_json::json;
use std::collections::BTreeMap;
#[test]
fn tool_spec_name_covers_all_variants() {
assert_eq!(
ToolSpec::Function(ResponsesApiTool {
name: "lookup_order".to_string(),
description: "Look up an order".to_string(),
strict: false,
defer_loading: None,
parameters: JsonSchema::object(
BTreeMap::new(),
/*required*/ None,
/*additional_properties*/ None
),
output_schema: None,
})
.name(),
"lookup_order"
);
assert_eq!(
ToolSpec::Namespace(ResponsesApiNamespace {
name: "mcp__demo__".to_string(),
description: "Demo tools".to_string(),
tools: Vec::new(),
})
.name(),
"mcp__demo__"
);
assert_eq!(
ToolSpec::ToolSearch {
execution: "sync".to_string(),
description: "Search for tools".to_string(),
parameters: JsonSchema::object(
BTreeMap::new(),
/*required*/ None,
/*additional_properties*/ None
),
}
.name(),
"tool_search"
);
assert_eq!(
ToolSpec::ImageGeneration {
output_format: "png".to_string(),
}
.name(),
"image_generation"
);
assert_eq!(
ToolSpec::WebSearch {
external_web_access: Some(true),
index_gated_web_access: None,
filters: None,
user_location: None,
search_context_size: None,
search_content_types: None,
}
.name(),
"web_search"
);
assert_eq!(
ToolSpec::Freeform(FreeformTool {
name: "exec".to_string(),
description: "Run a command".to_string(),
format: FreeformToolFormat {
r#type: "grammar".to_string(),
syntax: "lark".to_string(),
definition: "start: \"exec\"".to_string(),
},
})
.name(),
"exec"
);
}
#[test]
fn web_search_config_converts_to_responses_api_types() {
assert_eq!(
ResponsesApiWebSearchFilters::from(ConfigWebSearchFilters {
allowed_domains: Some(vec!["example.com".to_string()]),
}),
ResponsesApiWebSearchFilters {
allowed_domains: Some(vec!["example.com".to_string()]),
}
);
assert_eq!(
ResponsesApiWebSearchUserLocation::from(ConfigWebSearchUserLocation {
r#type: WebSearchUserLocationType::Approximate,
country: Some("US".to_string()),
region: Some("California".to_string()),
city: Some("San Francisco".to_string()),
timezone: Some("America/Los_Angeles".to_string()),
}),
ResponsesApiWebSearchUserLocation {
r#type: WebSearchUserLocationType::Approximate,
country: Some("US".to_string()),
region: Some("California".to_string()),
city: Some("San Francisco".to_string()),
timezone: Some("America/Los_Angeles".to_string()),
}
);
}
#[test]
fn create_tools_json_for_responses_api_includes_top_level_name() {
assert_eq!(
create_tools_json_for_responses_api(&[ToolSpec::Function(ResponsesApiTool {
name: "demo".to_string(),
description: "A demo tool".to_string(),
strict: false,
defer_loading: None,
parameters: JsonSchema::object(
BTreeMap::from([("foo".to_string(), JsonSchema::string(/*description*/ None),)]),
/*required*/ None,
/*additional_properties*/ None
),
output_schema: None,
})])
.expect("serialize tools"),
vec![json!({
"type": "function",
"name": "demo",
"description": "A demo tool",
"strict": false,
"parameters": {
"type": "object",
"properties": {
"foo": { "type": "string" }
},
},
})]
);
}
#[test]
fn namespace_tool_spec_serializes_expected_wire_shape() {
assert_eq!(
serde_json::to_value(ToolSpec::Namespace(ResponsesApiNamespace {
name: "mcp__demo__".to_string(),
description: "Demo tools".to_string(),
tools: vec![ResponsesApiNamespaceTool::Function(ResponsesApiTool {
name: "lookup_order".to_string(),
description: "Look up an order".to_string(),
strict: false,
defer_loading: None,
parameters: JsonSchema::object(
BTreeMap::from([(
"order_id".to_string(),
JsonSchema::string(/*description*/ None),
)]),
/*required*/ None,
/*additional_properties*/ None,
),
output_schema: None,
})],
}))
.expect("serialize namespace tool"),
json!({
"type": "namespace",
"name": "mcp__demo__",
"description": "Demo tools",
"tools": [
{
"type": "function",
"name": "lookup_order",
"description": "Look up an order",
"strict": false,
"parameters": {
"type": "object",
"properties": {
"order_id": { "type": "string" },
},
},
},
],
})
);
}
#[test]
fn web_search_tool_spec_serializes_expected_wire_shape() {
assert_eq!(
serde_json::to_value(ToolSpec::WebSearch {
external_web_access: Some(true),
index_gated_web_access: None,
filters: Some(ResponsesApiWebSearchFilters {
allowed_domains: Some(vec!["example.com".to_string()]),
}),
user_location: Some(ResponsesApiWebSearchUserLocation {
r#type: WebSearchUserLocationType::Approximate,
country: Some("US".to_string()),
region: Some("California".to_string()),
city: Some("San Francisco".to_string()),
timezone: Some("America/Los_Angeles".to_string()),
}),
search_context_size: Some(WebSearchContextSize::High),
search_content_types: Some(vec!["text".to_string(), "image".to_string()]),
})
.expect("serialize web_search"),
json!({
"type": "web_search",
"external_web_access": true,
"filters": {
"allowed_domains": ["example.com"],
},
"user_location": {
"type": "approximate",
"country": "US",
"region": "California",
"city": "San Francisco",
"timezone": "America/Los_Angeles",
},
"search_context_size": "high",
"search_content_types": ["text", "image"],
})
);
}
#[test]
fn tool_search_tool_spec_serializes_expected_wire_shape() {
assert_eq!(
serde_json::to_value(ToolSpec::ToolSearch {
execution: "sync".to_string(),
description: "Search app tools".to_string(),
parameters: JsonSchema::object(
BTreeMap::from([(
"query".to_string(),
JsonSchema::string(Some("Tool search query".to_string()),),
)]),
Some(vec!["query".to_string()]),
Some(AdditionalProperties::Boolean(false))
),
})
.expect("serialize tool_search"),
json!({
"type": "tool_search",
"execution": "sync",
"description": "Search app tools",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Tool search query",
}
},
"required": ["query"],
"additionalProperties": false,
},
})
);
}