phase 2 checkpoint

src/models.py

@@ -435,3 +435,53 @@ class BiasProfile:
    tool_weights=data.get("tool_weights", {}),
    category_multipliers=data.get("category_multipliers", {}),
   )
+
+@dataclass
+class Persona:
+ name: str
+ provider: Optional[str] = None
+ model: Optional[str] = None
+ preferred_models: List[str] = field(default_factory=list)
+ system_prompt: str = ''
+ temperature: Optional[float] = None
+ top_p: Optional[float] = None
+ max_output_tokens: Optional[int] = None
+ tool_preset: Optional[str] = None
+ bias_profile: Optional[str] = None
+
+ def to_dict(self) -> Dict[str, Any]:
+  res = {
+   "system_prompt": self.system_prompt,
+  }
+  if self.provider is not None:
+   res["provider"] = self.provider
+  if self.model is not None:
+   res["model"] = self.model
+  if self.preferred_models:
+   res["preferred_models"] = self.preferred_models
+  if self.temperature is not None:
+   res["temperature"] = self.temperature
+  if self.top_p is not None:
+   res["top_p"] = self.top_p
+  if self.max_output_tokens is not None:
+   res["max_output_tokens"] = self.max_output_tokens
+  if self.tool_preset is not None:
+   res["tool_preset"] = self.tool_preset
+  if self.bias_profile is not None:
+   res["bias_profile"] = self.bias_profile
+  return res
+
+ @classmethod
+ def from_dict(cls, name: str, data: Dict[str, Any]) -> "Persona":
+  return cls(
+   name=name,
+   provider=data.get("provider"),
+   model=data.get("model"),
+   preferred_models=data.get("preferred_models", []),
+   system_prompt=data.get("system_prompt", ""),
+   temperature=data.get("temperature"),
+   top_p=data.get("top_p"),
+   max_output_tokens=data.get("max_output_tokens"),
+   tool_preset=data.get("tool_preset"),
+   bias_profile=data.get("bias_profile"),
+  )