Merge pull request #617 from themavik/fix/523-clamp-max-tokens

fix(providers): clamp max_tokens to >= 1 before calling LiteLLM

nanobot/providers/litellm_provider.py

@@ -122,6 +122,10 @@ class LiteLLMProvider(LLMProvider):
         """
         model = self._resolve_model(model or self.default_model)
         
+        # Clamp max_tokens to at least 1 — negative or zero values cause
+        # LiteLLM to reject the request with "max_tokens must be at least 1".
+        max_tokens = max(1, max_tokens)
+        
         kwargs: dict[str, Any] = {
             "model": model,
             "messages": messages,