mirror of
https://github.com/openai/codex.git
synced 2026-11-19 22:30:42 +00:00
## Why Clients sampling a thread could only use the source thread's model. ## What changed Add an optional `model` field to the experimental `thread/sample` request. Omitting it or passing `null` inherits the source thread's model. When an override is supplied, the server uses the selected model's capabilities to decide whether to apply the requested reasoning effort. ## Testing Add an app-server integration test that checks model selection and reasoning effort for the overridden sample, then verifies that a subsequent sample and a follow-up turn use the source model. GitOrigin-RevId: f5c54ca3d693d31e1f3e0628a520583330a5d56d
69 lines
2.7 KiB
Rust
69 lines
2.7 KiB
Rust
//! One model response on an ephemeral fork that inherits the source's configuration and context.
|
|
|
|
use super::ThreadSource;
|
|
use crate::JsonSchema;
|
|
use crate::RequestId;
|
|
use crate::TS;
|
|
use codex_protocol::openai_models::ReasoningEffort;
|
|
use serde::Deserialize;
|
|
use serde::Serialize;
|
|
use std::collections::HashMap;
|
|
|
|
#[derive(Serialize, Deserialize, Debug, Default, Clone, PartialEq, JsonSchema, TS)]
|
|
#[serde(rename_all = "camelCase")]
|
|
#[ts(export_to = "v2/")]
|
|
pub struct ThreadSampleParams {
|
|
pub thread_id: String,
|
|
/// The loaded source's latest turn, which must be finished (completed, failed, or interrupted) unless `allowInProgressTurn` is true.
|
|
pub expected_turn_id: String,
|
|
/// Allow sampling the latest turn before it finishes.
|
|
#[serde(default, skip_serializing_if = "std::ops::Not::not")]
|
|
pub allow_in_progress_turn: bool,
|
|
pub prompt: String,
|
|
/// Override the model for this sample.
|
|
/// Omit or pass `null` to inherit the source thread's model.
|
|
#[ts(optional = nullable)]
|
|
pub model: Option<String>,
|
|
/// Applied only when the provider and model support cache-preserving reasoning-effort updates.
|
|
#[ts(optional = nullable)]
|
|
pub effort: Option<ReasoningEffort>,
|
|
#[ts(optional = nullable)]
|
|
pub thread_source: Option<ThreadSource>,
|
|
#[ts(optional = nullable)]
|
|
pub turn_trigger: Option<String>,
|
|
/// Optional metadata to enrich Codex's ResponsesAPI turn metadata.
|
|
#[ts(optional = nullable)]
|
|
pub responsesapi_client_metadata: Option<HashMap<String, String>>,
|
|
/// Disable MCP servers when the inherited window uses incremental tools on Responses Lite.
|
|
#[serde(default, skip_serializing_if = "std::ops::Not::not")]
|
|
pub disable_mcp: bool,
|
|
/// Override upstream interruption on cancellation for this sample; otherwise inherit the parent.
|
|
#[ts(optional = nullable)]
|
|
pub interrupt_on_cancel: Option<bool>,
|
|
}
|
|
|
|
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
|
|
#[serde(rename_all = "camelCase")]
|
|
#[ts(export_to = "v2/")]
|
|
pub struct ThreadSampleResponse {
|
|
pub source_turn_id: String,
|
|
pub response_id: String,
|
|
/// Assistant text from the response, or null if it attempted a tool call or completed without text.
|
|
pub text: Option<String>,
|
|
pub input_tokens: Option<i64>,
|
|
pub cached_input_tokens: Option<i64>,
|
|
pub output_tokens: Option<i64>,
|
|
}
|
|
|
|
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
|
|
#[serde(rename_all = "camelCase", deny_unknown_fields)]
|
|
#[ts(export_to = "v2/")]
|
|
pub struct ThreadSampleCancelParams {
|
|
pub request_id: RequestId,
|
|
}
|
|
|
|
#[derive(Serialize, Deserialize, Debug, Default, Clone, PartialEq, Eq, JsonSchema, TS)]
|
|
#[serde(rename_all = "camelCase")]
|
|
#[ts(export_to = "v2/")]
|
|
pub struct ThreadSampleCancelResponse {}
|