luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(opencode): route Muse Spark through the Responses API

Browse Source 
muse-spark-1.2-contributor-free returned HTTP 500 on /zen/v1/chat/completions.
The model is only served by /zen/v1/responses, so route it there via a per-model
targetFormat and normalize the Chat fields the Responses API rejects
(max_tokens -> max_output_tokens, reasoning_effort -> reasoning{effort,summary}),
clamping max/ultra down to the highest effort the model accepts (xhigh).

Routing stays per-model: the other free models (big-pickle, hy3-free, mimo,
nemotron, laguna) are not served by /responses and keep /chat/completions.
This commit is contained in:
anojndr
2026-08-28 11:32:56 +07:00
parent 14401c433c
commit ab044e6d6d
6 changed files with 203 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
open-sse/translator/request/openai-responses.js
View File

@@ -300,7 +300,16 @@ function buildReasoningInputItem(msg) {
*/
export function openaiToOpenAIResponsesRequest(model, body, stream, credentials) {
// Body already in Responses API format (e.g. Cursor CLI calling /chat/completions with input[])
if (body.input) return { ...body, model, stream: true };
if (body.input) {
const out = { ...body, model, stream: true };
if (out.max_output_tokens === undefined) {
if (out.max_completion_tokens !== undefined) out.max_output_tokens = out.max_completion_tokens;
else if (out.max_tokens !== undefined) out.max_output_tokens = out.max_tokens;
}
delete out.max_tokens;
delete out.max_completion_tokens;
return out;
}
const result = {
model,
@@ -416,7 +425,13 @@ export function openaiToOpenAIResponsesRequest(model, body, stream, credentials)
// Pass through other relevant fields
if (body.temperature !== undefined) result.temperature = body.temperature;
if (body.max_tokens !== undefined) result.max_tokens = body.max_tokens;
if (body.max_output_tokens !== undefined) {
result.max_output_tokens = body.max_output_tokens;
} else if (body.max_completion_tokens !== undefined) {
result.max_output_tokens = body.max_completion_tokens;
} else if (body.max_tokens !== undefined) {
result.max_output_tokens = body.max_tokens;
}
if (body.top_p !== undefined) result.top_p = body.top_p;
if (body.reasoning !== undefined) result.reasoning = body.reasoning;
if (body.reasoning_effort !== undefined) result.reasoning = { effort: body.reasoning_effort, summary: "auto" };