fix: read default_temperature from team.yaml; update docstrings

- Add default_temperature: 0 to config/team.yaml models block
- Read self._default_temperature from models cfg in __init__
- Use self._default_temperature as fallback in complete() instead of hardcoded 0
- Update class docstring to document both default_max_tokens and default_temperature
- Update complete() context param docs to reference team.yaml keys

adapters/llm/anthropic.py

@@ -23,6 +23,8 @@ class AnthropicAdapter(LLMAdapter):
 
         models:
           provider: anthropic
+          default_max_tokens: 4096   # fallback max_tokens for all calls
+          default_temperature: 0     # fallback temperature for all calls
           capability_map:
             reasoning-heavy:
               anthropic: claude-opus-4-6
@@ -31,6 +33,9 @@ class AnthropicAdapter(LLMAdapter):
             fast-cheap:
               anthropic: claude-haiku-3-5
 
+    Both ``default_max_tokens`` and ``default_temperature`` can be overridden
+    per-call via the ``context`` dict passed to :meth:`complete`.
+
     Environment variables
     ---------------------
     ANTHROPIC_API_KEY : Required. Authenticates with the Anthropic API.
@@ -59,6 +64,7 @@ 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)
+        self._default_temperature: float = self._models_cfg.get("default_temperature", 0)
 
     def complete(self, prompt: str, capability: str, context: dict) -> str:
         """
@@ -68,10 +74,10 @@ class AnthropicAdapter(LLMAdapter):
         ----------
         prompt      : User-role prompt content.
         capability  : One of "reasoning-heavy" | "capable" | "fast-cheap".
-        context     : Optional overrides:
+        context     : Optional per-call overrides:
                         system_prompt (str)   — prepended as the system turn.
-                        max_tokens    (int)   — defaults to 4096.
+                        max_tokens    (int)   — defaults to models.default_max_tokens in team.yaml.
-                        temperature   (float) — defaults to 0.
+                        temperature   (float) — defaults to models.default_temperature in team.yaml.
 
         Returns
         -------
@@ -79,7 +85,7 @@ class AnthropicAdapter(LLMAdapter):
         """
         model = self.resolve_model(capability)
         max_tokens: int = context.get("max_tokens", self._default_max_tokens)
-        temperature: float = context.get("temperature", 0)
+        temperature: float = context.get("temperature", self._default_temperature)
         system_prompt: str = context.get("system_prompt", "")
 
         create_kwargs: dict = {
@@ -89,7 +95,7 @@ class AnthropicAdapter(LLMAdapter):
         }
         if system_prompt:
             create_kwargs["system"] = system_prompt
-        if temperature != 0:
+        if temperature != 0.0:
             create_kwargs["temperature"] = temperature
 
         response = self._client.messages.create(**create_kwargs)

config/team.yaml

@@ -12,6 +12,7 @@ adapters:
 models:
   provider: anthropic
   default_max_tokens: 4096
+  default_temperature: 0
   capability_map:
     reasoning-heavy:
       anthropic: claude-opus-4-6