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

2
open-sse/providers/capabilities.js
View File

@@ -125,6 +125,8 @@ export const MODEL_CAPABILITIES = {
"kimi-for-coding-highspeed": { vision: true, videoInput: true, reasoning: true, thinkingFormat: "kimi", thinkingCanDisable: false, contextWindow: 262144, maxOutput: 65536 },
"kimi-k2.7-code": { vision: true, videoInput: true, reasoning: true, thinkingFormat: "kimi", thinkingCanDisable: false, contextWindow: 262144, maxOutput: 65536 },
"kimi-k2.7-code-highspeed": { vision: true, videoInput: true, reasoning: true, thinkingFormat: "kimi", thinkingCanDisable: false, contextWindow: 262144, maxOutput: 65536 },
// OpenCode Free Muse Spark — OpenAI Responses reasoning supports up to xhigh.
"muse-spark-1.2-contributor-free": { reasoning: true, thinkingFormat: "openai", contextWindow: 1048576, maxOutput: 131072 },
};
const KIRO_GPT_5_6_CAPABILITIES = { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 272000, maxOutput: 128000 };

6
open-sse/providers/registry/opencode.js
View File

@@ -19,7 +19,11 @@ export default {
},
noAuth: true,
},
models: [],
models: [
// Only this model is served by /zen/v1/responses; the rest stay on
// /chat/completions, so the format is declared per-model, not per-provider.
{ id: "muse-spark-1.2-contributor-free", name: "Muse Spark 1.2 Contributor Free", targetFormat: "openai-responses" },
],
modelsFetcher: { url: "https://opencode.ai/zen/v1/models", type: "opencode-free" },
passthroughModels: true,
};