refactor(core): decouple actors and remove workflow templates (#67)

Removes the deprecated `workflow_template` concept entirely across both backend API routers, internal logic handling within the `supervisory_node` and `consciousness_node`, and front-end components. Enables `consciousness_node` to work autonomously.

Also refactors core package structure to enforce the "one python package, one Ray Actor" architectural rule. `GlobalWorkflowManager`, `WorkflowRunningEngine`, `PostgresDatabase`, and `WorkerCluster` have been moved to their own top-level decoupled package directories with properly exported `__init__.py` modules. Test suites have been relocated and import paths updated across the system.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>

pretor/adapter/model_adapter/agent_factory.py

@@ -22,22 +22,28 @@ from pretor.core.global_state_machine.model_provider import Provider
 from pretor.utils.agent_model import ResponseModel, DepsModel
 from pretor.utils.error import ModelNotExistError
 
+
 class AgentFactory:
     """AgentFactory 核心组件类。
-    这是一个领域数据模型或功能封装类，承载了 AgentFactory 相关的内聚属性定义与状态维护。它的存在隔离了局部的业务复杂性，并对外提供了类型安全的访问接口。    """
-    def __init__(self):
-        self._models_mapping = {"openai": (OpenAIChatModel, OpenAIProvider),
-                                "claude": (AnthropicModel, AnthropicProvider),
-                                "deepseek": (OpenAIChatModel, OpenAIProvider),}
+    这是一个领域数据模型或功能封装类，承载了 AgentFactory 相关的内聚属性定义与状态维护。它的存在隔离了局部的业务复杂性，并对外提供了类型安全的访问接口。"""
 
-    def create_agent(self,
-                     provider: Provider,
-                     model_id: str,
-                     output_type: ResponseModel,
-                     system_prompt: str,
-                     deps_type: DepsModel,
-                     agent_name: str,
-                     tools: list = None) -> Agent:
+    def __init__(self):
+        self._models_mapping = {
+            "openai": (OpenAIChatModel, OpenAIProvider),
+            "claude": (AnthropicModel, AnthropicProvider),
+            "deepseek": (OpenAIChatModel, OpenAIProvider),
+        }
+
+    def create_agent(
+        self,
+        provider: Provider,
+        model_id: str,
+        output_type: ResponseModel,
+        system_prompt: str,
+        deps_type: DepsModel,
+        agent_name: str,
+        tools: list = None,
+    ) -> Agent:
         """
             create_agent方法，将输入的provider对象实例化为一个pydantic-ai的agent对象
 
@@ -58,22 +64,30 @@ class AgentFactory:
         if provider.provider_type not in self._models_mapping:
             raise ValueError(f"不支持的协议类型: {provider.provider_type}")
         model_class, provider_class = self._models_mapping[provider.provider_type]
-        model = model_class(model_id, provider=provider_class(api_key=provider.provider_apikey, base_url=provider.provider_url))
+        model = model_class(
+            model_id,
+            provider=provider_class(
+                api_key=provider.provider_apikey, base_url=provider.provider_url
+            ),
+        )
         match provider.provider_type:
             case "deepseek":
-                agent = DeepSeekReasonerAgent(model=model,
-                                              name=agent_name,
-                                              output_type=output_type,
-                                              deps_type=deps_type,
-                                              system_prompt=system_prompt,
-                                              tools=tools,
-                                              retries=3,
-                                              )
+                agent = DeepSeekReasonerAgent(
+                    model=model,
+                    name=agent_name,
+                    output_type=output_type,
+                    deps_type=deps_type,
+                    system_prompt=system_prompt,
+                    tools=tools,
+                    retries=3,
+                )
             case _:
-                agent = Agent(model=model,
-                              name=agent_name,
-                              system_prompt=system_prompt,
-                              output_type=output_type,
-                              deps_type=deps_type,
-                              tools=tools)
-        return agent
+                agent = Agent(
+                    model=model,
+                    name=agent_name,
+                    system_prompt=system_prompt,
+                    output_type=output_type,
+                    deps_type=deps_type,
+                    tools=tools,
+                )
+        return agent