fix: Remove hard-coded token limits on LLM responses

- Add max_response_tokens config (8192) to LLMConfig
- Use config value in router.py instead of hardcoded 500
- Update base.py default from 300 to 8192
- Lets LLM generate full responses; chunker handles size limits

Fixes truncated responses like Here are three nodes in the freq

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

meshai/backends/base.py

@@ -12,7 +12,7 @@ class LLMBackend(ABC):
         self,
         messages: list[dict],
         system_prompt: str,
-        max_tokens: int = 300,
+        max_tokens: int = 8192,
         user_id: Optional[str] = None,
     ) -> str:
         """Generate a response from the LLM.

meshai/config.py

@@ -94,6 +94,7 @@ class LLMConfig:
     base_url: str = "https://api.openai.com/v1"
     model: str = "gpt-4o-mini"
     timeout: int = 30
+    max_response_tokens: int = 8192  # Let LLM generate full responses; chunker handles size
 
     system_prompt: str = (
         "RESPONSE RULES:\n"

meshai/router.py

@@ -643,7 +643,7 @@ class MessageRouter:
             response = await self.llm.generate(
                 messages=history,
                 system_prompt=system_prompt,
-                max_tokens=500,
+                max_tokens=self.config.llm.max_response_tokens,
             )
         except asyncio.TimeoutError:
             logger.error("LLM request timed out")