fix: accept vLLM thinking in reasoning or reasoning_content

Newer vLLM parsers put CoT in reasoning; older builds and DeepSeek still use reasoning_content. Canonicalize to the UI field and echo only the original wire field so other ChatOpenAI models stay unchanged. Point qwen3.6 at VllmChatModel.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
董宏凯andCursor committed 2026-09-09 22:46:08 +08:00
1 parent d765afe2ac
commit f4c7d41a60
10 files changed
+371 -123

No files matched your search

+10 -2
View File
@@ -69,16 +69,24 @@ models:
supports_vision: false
- name: qwen3.6
display_name: qwen3.6
use: langchain_openai:ChatOpenAI
use: deerflow.models.vllm_provider:VllmChatModel
model: qwen3.6
api_key: sk-6AqP_UYpPYJKdclYWR-FSA
base_url: http://119.254.86.251:8001/v1
request_timeout: 30.0
max_retries: 2
stream_usage: true
supports_thinking: false
supports_thinking: true
supports_reasoning_effort: false
supports_vision: false
when_thinking_enabled:
extra_body:
chat_template_kwargs:
enable_thinking: true
when_thinking_disabled:
extra_body:
chat_template_kwargs:
enable_thinking: false
- name: zai-org/GLM-5-FP8
display_name: zai-org/GLM-5-FP8
use: langchain_openai:ChatOpenAI