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>

skillopt/model/__init__.py

@@ -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(

skillopt/model/qwen_backend.py

@@ -191,7 +191,8 @@ def _chat_messages_impl(
         "messages": _json_safe(messages),
         "max_tokens": min(max_completion_tokens, config.max_tokens),
     }
-    payload["chat_template_kwargs"] = {"enable_thinking": config.enable_thinking}
+    if config.enable_thinking:
+        payload["chat_template_kwargs"] = {"enable_thinking": True}
     if config.temperature is not None:
         payload["temperature"] = config.temperature
     if tools: