BYOK CustomEndpoint Model only thinks, cannot parse or strip `delta.reasoning`

Open
#323,172 1 comment 0 reactions 1 assignee View on GitHub

@vritant24 is already working on this.

Since Jun 26, 2026.

Assessment

This issue has not been assessed yet.

Description

bug model-byok
  • Copilot Chat Extension Version: GitHub.copilot-chat 0.41
  • VS Code Version: 1.126.0
  • OS Version: Win 11
  • Feature (e.g. agent/edit/ask mode): all responses
  • Selected model (e.g. GPT 4.1, Claude 3.7 Sonnet): CustomEndpoint (Qwen3-VL-235B-A22B-Thinking-FP8)

Steps to Reproduce:

  1. Assign a reasoning model as a custom endpoint.
  2. Ask it to do or say anything.
  3. Click on the "Finished in.." section when you receive the error to see the thinking.
Image

This does not happen with qwen3.6-27b, which can "think" and "respond" as normal. It seems to be that the extension does not expect and cannot handle delta.reasoning. Here is a partial raw response to a "Hello" outside of GHCchat:

curl ... '{"model":"billiken-coder-prodigy","messages":[{"role":"user","content":"Hello"}],"stream":true}'
data: {"id":"chatcmpl-be7c326e84b87a6e","object":"chat.completion.chunk","created":1782492920,"model":"billiken-coder-prodigy","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}],"prompt_token_ids":null,"prompt_text":null}

data: {"id":"chatcmpl-be7c326e84b87a6e","object":"chat.completion.chunk","created":1782492920,"model":"billiken-coder-prodigy","choices":[{"index":0,"delta":{"reasoning":"Okay"},"logprobs":null,"finish_reason":null,"token_ids":null}]}

data: {"id":"chatcmpl-be7c326e84b87a6e","object":"chat.completion.chunk","created":1782492920,"model":"billiken-coder-prodigy","choices":[{"index":0,"delta":{"reasoning":","},"logprobs":null,"finish_reason":null,"token_ids":null}]}

data: {"id":"chatcmpl-be7c326e84b87a6e","object":"chat.completion.chunk","created":1782492920,"model":"billiken-coder-prodigy","choices":[{"index":0,"delta":{"reasoning":" the"},"logprobs":null,"finish_reason":null,"token_ids":null}]}

data: {"id":"chatcmpl-be7c326e84b87a6e","object":"chat.completion.chunk","created":1782492920,"model":"billiken-coder-prodigy","choices":[{"index":0,"delta":{"reasoning":" user"},"logprobs":null,"finish_reason":null,"token_ids":null}]}

data: {"id":"chatcmpl-be7c326e84b87a6e","object":"chat.completion.chunk","created":1782492920,"model":"billiken-coder-prodigy","choices":[{"index":0,"delta":{"reasoning":" said"},"logprobs":null,"finish_reason":null,"token_ids":null}]}

...

data: {"id":"chatcmpl-be7c326e84b87a6e","object":"chat.completion.chunk","created":1782492920,"model":"billiken-coder-prodigy","choices":[{"index":0,"delta":{"content":" 😊"},"logprobs":null,"finish_reason":null,"token_ids":null}]}

data: {"id":"chatcmpl-be7c326e84b87a6e","object":"chat.completion.chunk","created":1782492920,"model":"billiken-coder-prodigy","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop","stop_reason":null,"token_ids":null}],"system_fingerprint":"vllm-0.23.0-tp4-ep-68660ca4"}

data: [DONE]
Dominant language
TypeScript
Stars
193k
Forks
42.9k
PR merge metrics
PR metrics pending

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from microsoft/vscode

All issues in microsoft/vscode

Similar issues

More TypeScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.