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>

config/config.yaml

@@ -10,13 +10,11 @@ llm:
   max_retries: 3
   retry_backoff_base: 1.0
   retry_backoff_max: 30.0
+  thinking: false  # Disable model thinking/reasoning mode (reduces reasoning-only loops)
   # Extra parameters merged into the API request body (model-specific).
   # Examples:
-  #   Qwen 3.x:  enable_thinking: false
-  #   DeepSeek:   enable_thinking: false
-  #   OpenAI:     reasoning_effort: "low"
-  extra_body:
-    enable_thinking: false
+  #   OpenAI: reasoning_effort: "low"
+  extra_body: {}
 
 agent:
   max_iterations: 25