feat: add thinking mode toggle to suppress reasoning-only response loops

Adds `llm.thinking` config option (default: true) that when disabled:
- Injects /no_think into the last user message for Qwen 3.x compatibility
- Sends chat_template_kwargs in API payload for backends that support it
- Silently and immediately nudges on reasoning-only responses instead of
  showing warnings and wasting retry iterations

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app/services/llm.py

@@ -151,7 +151,11 @@ class LLMClient:
         if tools:
             payload["tools"] = tools
 
-        # Merge model-specific extra parameters (e.g., enable_thinking, reasoning_effort)
+        # When thinking is disabled, inject chat_template_kwargs for backends that support it
+        if not self._config.thinking:
+            payload.setdefault("chat_template_kwargs", {})["enable_thinking"] = False
+
+        # Merge model-specific extra parameters (e.g., reasoning_effort)
         if self._config.extra_body:
             payload.update(self._config.extra_body)