[BUG]: (Incorrect) sampling parameters are hard-coded based on model name/id #42775

Activity

1. github-actions

   assigned

   rekram1-node

   on Aug 15, 2026
2. d9beuD commented on Aug 15, 2026

   

   d9beuD

   on Aug 15, 2026

   More actions

   Confirming this on a second adapter, with the request body captured off the wire.

   Setup: Qwen3.8-27B served locally by oMLX (Anthropic-compatible /v1/messages), provider declared with "npm": "@ai-sdk/anthropic", opencode 1.18.18. I put a logging reverse proxy between opencode and the server to see the real body rather than infer it.

   Captured request body (agent had "temperature": 0.33, "top_p": 0.77 configured):

   {
     "model": "Qwen3.8-27B-oQ6e-mtp",
     "max_tokens": 32000,
     "top_p": 1,
     "stream": true,
     "tool_choice": { "type": "auto" }
   }

   top_p: 1 comes from the substring match in ProviderTransform.topP() (transform.ts:550, if (id.includes("qwen")) return 1). Same as reported, so this is not specific to @ai-sdk/openai-compatible.

   Two things I ran into that might be worth folding into whatever opt-out lands:

   1. The documented workaround does not cover temperature for custom providers. Setting top_p on the agent does win (request.ts:127), but temperature is gated:

   temperature: input.model.capabilities.temperature
     ? (input.agent.temperature ?? ProviderTransform.temperature(input.model))
     : undefined,

   and capabilities.temperature defaults to false for user-declared models (provider.ts:1461, model.temperature ?? existingModel?.capabilities.temperature ?? false). So for a locally-declared model, agent-level temperature is silently dropped unless the model entry also sets "temperature": true. That took a packet capture to find — a config-level no-op with no warning.

   2. topK has no user override at all. Note the asymmetry at request.ts:127-128:

   topP: input.agent.topP ?? ProviderTransform.topP(input.model),
   topK: ProviderTransform.topK(input.model),

   AgentConfig exposes temperature and top_p but not top_k, so when ProviderTransform.topK() does return a value there is no way to override it from config. It does not bite Qwen today (topK() returns undefined for it), but it would for any model matching the minimax-m2 or gemini branches.

   I appreciate this may interact with the v2 direction in specs/v2/config.md ("Do not retain dedicated agent temperature or top_p fields", with agent-local options carrying body overrides instead) — in which case an options.body passthrough would address all three at once. Happy to help test whichever shape you settle on.
3. vektorprime commented on Aug 18, 2026

   

   vektorprime

   on Aug 18, 2026

   More actions

   FYI this works in the config so the top p 1.0 gets overridden with what you have in the model config (in opencode's json file)

   "Qwen3.8-27B": {
   "name": "Qwen3.8-27B",
   "reasoning": true,
   "tool_call": true,
   "options": {
   "top_p": 0.95
   },
   "limit": {
   "context": 260000,
   "output": 128535
   }
   },
4. rekram1-node

   closed this as completedin #43310on Aug 18, 2026