acb5c34cdc
Route all Muse Spark models (not just 1.2) on OpenCode Free to /zen/v1/responses via isMuseSparkModel(), fixing HTTP 500 on muse-spark-1.3-contributor-free. Declare vision:true on Muse Spark models so image input is no longer stripped; register 1.3 in the registry and capabilities. Scoped to opencode only — other providers keep Chat Completions routing.
117 lines
4.3 KiB
JavaScript
117 lines
4.3 KiB
JavaScript
import crypto from "crypto";
|
|
import { BaseExecutor } from "./base.js";
|
|
import { PROVIDERS } from "../config/providers.js";
|
|
import { getThinkingLevels } from "../providers/thinkingLevels.js";
|
|
import { injectReasoningContent } from "../utils/reasoningContentInjector.js";
|
|
import { resolveSessionId } from "../utils/sessionManager.js";
|
|
import { isMuseSparkModel } from "../providers/models/helpers.js";
|
|
|
|
const OPENCODE_UA = "opencode";
|
|
// Models served by /zen/v1/responses; every other model stays on /chat/completions.
|
|
const RESPONSES_MODELS = new Set([
|
|
"muse-spark-1.2-contributor-free",
|
|
"muse-spark-1.3-contributor-free",
|
|
]);
|
|
|
|
function generateRequestId() {
|
|
return `msg_${crypto.randomUUID().replace(/-/g, "")}`;
|
|
}
|
|
|
|
function generateSessionId() {
|
|
return `ses_${crypto.randomUUID().replace(/-/g, "")}`;
|
|
}
|
|
|
|
// Strip the thinking suffix "model(level)" so registry lookups hit the base id.
|
|
function baseModelId(model) {
|
|
return String(model || "").replace(/\([^()]+\)\s*$/, "").trim();
|
|
}
|
|
|
|
function isResponsesModel(model) {
|
|
const base = baseModelId(model);
|
|
return RESPONSES_MODELS.has(base) || isMuseSparkModel(base);
|
|
}
|
|
|
|
function resolveOpencodeSession(body, credentials) {
|
|
const headers = credentials?.rawHeaders || {};
|
|
return resolveSessionId({
|
|
headers,
|
|
body,
|
|
connectionId: credentials?.connectionId,
|
|
scope: "opencode",
|
|
generate: generateSessionId,
|
|
});
|
|
}
|
|
|
|
function normalizeOpencodeReasoning(model, body) {
|
|
const current = body.reasoning;
|
|
const currentReasoning = current && typeof current === "object" && !Array.isArray(current)
|
|
? current
|
|
: null;
|
|
const requestedEffort = typeof body.reasoning_effort === "string"
|
|
? body.reasoning_effort
|
|
: currentReasoning?.effort;
|
|
if (typeof requestedEffort !== "string") return;
|
|
|
|
const cleanModel = baseModelId(model || body.model);
|
|
const supportedLevels = getThinkingLevels("opencode", cleanModel);
|
|
let effort = requestedEffort.toLowerCase().trim();
|
|
if ((effort === "max" || effort === "ultra") && supportedLevels?.length && !supportedLevels.includes(effort)) {
|
|
if (effort === "ultra" && supportedLevels.includes("max")) effort = "max";
|
|
else if (supportedLevels.includes("xhigh")) effort = "xhigh";
|
|
}
|
|
|
|
body.reasoning = { ...currentReasoning, effort };
|
|
if (!body.reasoning.summary) body.reasoning.summary = "auto";
|
|
delete body.reasoning_effort;
|
|
}
|
|
|
|
export class OpenCodeExecutor extends BaseExecutor {
|
|
constructor() {
|
|
super("opencode", PROVIDERS.opencode);
|
|
this._currentSessionId = null;
|
|
}
|
|
|
|
transformRequest(model, body, stream, credentials) {
|
|
this._currentSessionId = resolveOpencodeSession(body, credentials);
|
|
if (isResponsesModel(model)) {
|
|
// Responses API names the output cap max_output_tokens and takes thinking
|
|
// as reasoning:{effort,summary} — normalize the Chat fields at this boundary.
|
|
if (body.max_output_tokens === undefined) {
|
|
if (body.max_completion_tokens !== undefined) body.max_output_tokens = body.max_completion_tokens;
|
|
else if (body.max_tokens !== undefined) body.max_output_tokens = body.max_tokens;
|
|
}
|
|
delete body.max_tokens;
|
|
delete body.max_completion_tokens;
|
|
normalizeOpencodeReasoning(model, body);
|
|
}
|
|
return injectReasoningContent({ provider: this.provider, model, body });
|
|
}
|
|
|
|
buildUrl(model) {
|
|
const base = this.config.baseUrl;
|
|
return isResponsesModel(model)
|
|
? `${base}/zen/v1/responses`
|
|
: `${base}/zen/v1/chat/completions`;
|
|
}
|
|
|
|
buildHeaders(credentials, stream = true) {
|
|
const raw = credentials?.rawHeaders || {};
|
|
const lower = {};
|
|
for (const [k, v] of Object.entries(raw)) lower[k.toLowerCase()] = v;
|
|
|
|
const downstreamUa = lower["user-agent"] || "";
|
|
const isOpencodeDownstream = downstreamUa.toLowerCase().includes("opencode");
|
|
|
|
return {
|
|
"Content-Type": "application/json",
|
|
"Authorization": "Bearer public",
|
|
"User-Agent": isOpencodeDownstream ? downstreamUa : OPENCODE_UA,
|
|
"x-opencode-client": lower["x-opencode-client"] || "desktop",
|
|
"x-opencode-session": lower["x-opencode-session"] || this._currentSessionId || generateSessionId(),
|
|
"x-opencode-request": lower["x-opencode-request"] || generateRequestId(),
|
|
"x-opencode-project": lower["x-opencode-project"] || "global",
|
|
"Accept": stream ? "text/event-stream" : "*/*",
|
|
};
|
|
}
|
|
}
|