fix(model): forward Qwen timeout and only set enable_thinking when true

Two bugs made local vLLM targets score acc=0.000: the router did not
forward 'timeout' to the Qwen backend (so runs used the 300s default),
and qwen_backend always injected chat_template_kwargs.enable_thinking,
which non-Qwen vLLM servers reject or answer with <think> output and no
<answer> tag. Forward timeout and only set the field when enabled.

Closes #28

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Matt Van Horn
2026-06-07 07:41:35 -07:00
parent ee9931ec01
commit c31c50be51
3 changed files with 231 additions and 1 deletions
+2
View File
@@ -142,6 +142,7 @@ def chat_target(
retries=retries,
stage=stage,
reasoning_effort=reasoning_effort,
timeout=timeout,
)
if get_target_backend() == "minimax_chat":
return _minimax.chat_target(
@@ -249,6 +250,7 @@ def chat_target_messages(
tools=tools,
tool_choice=tool_choice,
return_message=return_message,
timeout=timeout,
)
if get_target_backend() == "minimax_chat":
return _minimax.chat_target_messages(