Repository navigation
[FEATURE]: Add reasoning as interleaved field option #19988
Description
Feature hasn't been suggested before.
- I have verified this feature I'm about to request hasn't been suggested before.
Describe the enhancement you want to request
vLLM renamed reasoning_content to reasoning on their chat completions API (vllm-project/vllm#27755) and dropped reasoning_content on input entirely. The interleaved config only allows "reasoning_content" and "reasoning_details" as field values, so there's no way to target the field name vLLM reads.
Result: on self-hosted vLLM with reasoning models (MiniMax-M2, DeepSeek, etc.), reasoning is sent back as reasoning_content on assistant messages but vLLM silently ignores it. The model never sees its prior thinking in multi-turn/tool-call chains.
Fix: add "reasoning" to the zod enum in models.ts:32 and provider.ts:807. The transform already handles it generically via [field].
Happy to open a PR for this.
Reacted by squall, KlarkC and Avenue9397
Metadata
Metadata
Assignees
Labels
No labels
Activity
Jason-Siu commentedon May 3, 2026
Hey @rekram1-node, I’m running into this same issue locally. Are you still planning to work on this, or would you like me to take a crack at the PR?
rekram1-node commentedon May 3, 2026
Go for it
The bot auto assigns
squallliu commentedon May 18, 2026
I'm facing the exact same issue.
klarkc commentedon Jun 2, 2026
I can confirm this is currently blocking self-hosted vLLM reasoning models as well.
My setup:
/v1/chat/completions--reasoning-parser qwen3choices[].message.reasoning/ streamingdelta.reasoningDirect curl against vLLM shows reasoning is produced correctly, but OpenCode cannot currently configure: