37 lines
1.4 KiB
JavaScript
37 lines
1.4 KiB
JavaScript
|
import { DefaultExecutor } from "./default.js";
|
||
|
|
|
||
|
|
/**
|
||
|
|
* CodeBuddyExecutor — talks to https://copilot.tencent.com/v2/chat/completions
|
||
|
|
*
|
||
|
|
* CodeBuddy is OpenAI-compatible but rejects non-stream chat requests
|
||
|
|
* (HTTP 400, code 11101 "Non-stream chat request is currently not supported").
|
||
|
|
* The same-format (openai→openai) translator path leaves body.stream as the
|
||
|
|
* client sent it, so we force it true here — 9router still re-aggregates the
|
||
|
|
* SSE into a JSON response for non-streaming clients.
|
||
|
|
*/
|
||
|
|
export class CodeBuddyExecutor extends DefaultExecutor {
|
||
|
|
constructor() {
|
||
|
|
super("codebuddy-cn");
|
||
|
|
}
|
||
|
|
|
||
|
|
transformRequest(model, body, stream, credentials) {
|
||
|
|
const transformed = super.transformRequest(model, body, stream, credentials);
|
||
|
|
transformed.stream = true;
|
||
|
|
|
||
|
|
// CodeBuddy only surfaces model reasoning when the request carries the CLI's
|
||
|
|
// OpenAI-style params: reasoning_effort + reasoning_summary:"auto". 9router's
|
||
|
|
// thinking pipeline sets reasoning_effort only when the client asks, and never
|
||
|
|
// sets reasoning_summary — so reasoning never shows. Mirror the CLI here.
|
||
|
|
const eff = transformed.reasoning_effort;
|
||
|
|
if (eff === "none" || eff === "off") {
|
||
|
|
delete transformed.reasoning_effort; // gateway has no "none" — just omit
|
||
|
|
} else {
|
||
|
|
if (!eff) transformed.reasoning_effort = "medium";
|
||
|
|
transformed.reasoning_summary = "auto";
|
||
|
|
}
|
||
|
|
return transformed;
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
export default CodeBuddyExecutor;
|