mirror of
https://github.com/pchuan98/codex.git
synced 2026-07-01 00:31:56 +08:00
sayan-oai
a22706dfae
## Summary Add the extension-backed standalone `web.run` tool so Codex can call the standalone search endpoint through the `codex-api` search client and return its encrypted output to Responses. - gate the new tool behind `standalone_web_search` - install the extension in the app-server thread registry and hide hosted `web_search` when standalone search is enabled for OpenAI providers so the two paths stay mutually exclusive - build search context from persisted history using a small tail heuristic: previous user message, assistant text between the last two user turns capped at about 1k tokens, and current user message ## Test Plan - `cargo test -p codex-web-search-extension` - `cargo test -p codex-api` - `cargo test -p codex-core hosted_tools_follow_provider_auth_model_and_config_gates`
286 lines
9.4 KiB
Rust
286 lines
9.4 KiB
Rust
use crate::common::Reasoning;
|
|
use codex_protocol::models::ResponseItem;
|
|
use schemars::JsonSchema;
|
|
use serde::Deserialize;
|
|
use serde::Serialize;
|
|
|
|
#[derive(Debug, Clone, Serialize, PartialEq)]
|
|
pub struct SearchRequest {
|
|
pub id: String,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub model: Option<String>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub reasoning: Option<Reasoning>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub input: Option<SearchInput>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub commands: Option<SearchCommands>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub settings: Option<SearchSettings>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub max_output_tokens: Option<u64>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, PartialEq)]
|
|
#[serde(untagged)]
|
|
pub enum SearchInput {
|
|
Text(String),
|
|
Items(Vec<ResponseItem>),
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq, JsonSchema)]
|
|
pub struct SearchCommands {
|
|
/// Query the internet search engine for a given list of queries.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub search_query: Option<Vec<SearchQuery>>,
|
|
/// Query the image search engine for a given list of queries.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub image_query: Option<Vec<SearchQuery>>,
|
|
/// Open pages by reference id or URL.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub open: Option<Vec<OpenOperation>>,
|
|
/// Open links from previously opened pages.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub click: Option<Vec<ClickOperation>>,
|
|
/// Find text patterns in pages.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub find: Option<Vec<FindOperation>>,
|
|
/// Take screenshots of PDF pages.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub screenshot: Option<Vec<ScreenshotOperation>>,
|
|
/// Look up prices for the given stock symbols.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub finance: Option<Vec<FinanceOperation>>,
|
|
/// Look up weather forecasts.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub weather: Option<Vec<WeatherOperation>>,
|
|
/// Look up sports schedules and standings.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub sports: Option<Vec<SportsOperation>>,
|
|
/// Get time for the given UTC offsets.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub time: Option<Vec<TimeOperation>>,
|
|
/// Set the length of the response to be returned.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub response_length: Option<SearchResponseLength>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, JsonSchema)]
|
|
pub struct SearchQuery {
|
|
/// Search query.
|
|
pub q: String,
|
|
/// Whether to filter by recency, as a number of recent days.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub recency: Option<u64>,
|
|
/// Whether to filter by a specific list of domains.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub domains: Option<Vec<String>>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, JsonSchema)]
|
|
pub struct OpenOperation {
|
|
/// Reference id or URL to open.
|
|
pub ref_id: String,
|
|
/// Line number to position the page at.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub lineno: Option<u64>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
|
pub struct ClickOperation {
|
|
/// Reference id containing the numbered link.
|
|
pub ref_id: String,
|
|
/// Numbered link id to open.
|
|
pub id: u64,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
|
pub struct FindOperation {
|
|
/// Reference id or URL to search within.
|
|
pub ref_id: String,
|
|
/// Text pattern to find.
|
|
pub pattern: String,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
|
pub struct ScreenshotOperation {
|
|
/// Reference id or URL to screenshot.
|
|
pub ref_id: String,
|
|
/// Zero-indexed PDF page number.
|
|
pub pageno: u64,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, JsonSchema)]
|
|
pub struct FinanceOperation {
|
|
/// Ticker symbol to look up.
|
|
pub ticker: String,
|
|
/// Asset type to look up.
|
|
pub r#type: FinanceAssetType,
|
|
/// ISO 3166-1 alpha-3 country code, "OTC", or "" for cryptocurrency.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub market: Option<String>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
|
#[serde(rename_all = "lowercase")]
|
|
pub enum FinanceAssetType {
|
|
Equity,
|
|
Fund,
|
|
Crypto,
|
|
Index,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, JsonSchema)]
|
|
pub struct WeatherOperation {
|
|
/// Location in "Country, Area, City" format.
|
|
pub location: String,
|
|
/// Start date in YYYY-MM-DD format. Defaults to today.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub start: Option<String>,
|
|
/// Number of days to return. Defaults to 7.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub duration: Option<u64>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, JsonSchema)]
|
|
pub struct SportsOperation {
|
|
/// Tool name for sports requests.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub tool: Option<SportsToolName>,
|
|
/// Sports function to call.
|
|
pub r#fn: SportsFunction,
|
|
/// League to look up.
|
|
pub league: SportsLeague,
|
|
/// Team to look up, using the common 3 or 4 letter alias used in broadcasts.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub team: Option<String>,
|
|
/// Opponent to use with `team` when narrowing the lookup.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub opponent: Option<String>,
|
|
/// Start date in YYYY-MM-DD format.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub date_from: Option<String>,
|
|
/// End date in YYYY-MM-DD format.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub date_to: Option<String>,
|
|
/// Number of games to return.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub num_games: Option<u64>,
|
|
/// Locale for the lookup.
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub locale: Option<String>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
|
#[serde(rename_all = "lowercase")]
|
|
pub enum SportsToolName {
|
|
Sports,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
|
#[serde(rename_all = "lowercase")]
|
|
pub enum SportsFunction {
|
|
Schedule,
|
|
Standings,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
|
#[serde(rename_all = "lowercase")]
|
|
pub enum SportsLeague {
|
|
Nba,
|
|
Wnba,
|
|
Nfl,
|
|
Nhl,
|
|
Mlb,
|
|
Epl,
|
|
Ncaamb,
|
|
Ncaawb,
|
|
Ipl,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
|
pub struct TimeOperation {
|
|
/// UTC offset formatted like "+03:00".
|
|
pub utc_offset: String,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq, JsonSchema)]
|
|
#[serde(rename_all = "lowercase")]
|
|
pub enum SearchResponseLength {
|
|
Short,
|
|
Medium,
|
|
Long,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq)]
|
|
pub struct SearchSettings {
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub user_location: Option<ApproximateLocation>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub search_context_size: Option<SearchContextSize>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub filters: Option<SearchFilters>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub image_settings: Option<SearchImageSettings>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub allowed_callers: Option<Vec<AllowedCaller>>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub external_web_access: Option<bool>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
|
|
pub struct ApproximateLocation {
|
|
pub r#type: LocationType,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub country: Option<String>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub region: Option<String>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub city: Option<String>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub timezone: Option<String>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
|
|
#[serde(rename_all = "lowercase")]
|
|
pub enum LocationType {
|
|
Approximate,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
|
|
#[serde(rename_all = "lowercase")]
|
|
pub enum SearchContextSize {
|
|
Low,
|
|
Medium,
|
|
High,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq, Eq)]
|
|
pub struct SearchFilters {
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub allowed_domains: Option<Vec<String>>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub blocked_domains: Option<Vec<String>>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Serialize, Deserialize, Default, PartialEq, Eq)]
|
|
pub struct SearchImageSettings {
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub max_results: Option<u64>,
|
|
#[serde(skip_serializing_if = "Option::is_none")]
|
|
pub caption: Option<bool>,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, Serialize, Deserialize, PartialEq, Eq)]
|
|
#[serde(rename_all = "snake_case")]
|
|
pub enum AllowedCaller {
|
|
Direct,
|
|
Shell,
|
|
CodeInterpreter,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Deserialize, PartialEq, Eq)]
|
|
pub struct SearchResponse {
|
|
pub encrypted_output: String,
|
|
}
|