fix(adapter/llm): make max_tokens configurable via team.yaml models.default_max_tokens

adapters/llm/anthropic.py

@@ -58,6 +58,7 @@ class AnthropicAdapter(LLMAdapter):
             )
         self._client = anthropic.Anthropic(api_key=api_key)
         self._models_cfg: dict = config.get("models", {})
+        self._default_max_tokens: int = self._models_cfg.get("default_max_tokens", 4096)
 
     def complete(self, prompt: str, capability: str, context: dict) -> str:
         """
@@ -77,7 +78,7 @@ class AnthropicAdapter(LLMAdapter):
         The model's text completion as a plain string.
         """
         model = self.resolve_model(capability)
-        max_tokens: int = context.get("max_tokens", 4096)
+        max_tokens: int = context.get("max_tokens", self._default_max_tokens)
         temperature: float = context.get("temperature", 0)
         system_prompt: str = context.get("system_prompt", "")