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/worker_individual/skill_individual.py

@@ -12,14 +12,18 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-from pretor.worker_individual.base_individual import BaseIndividual, WorkerIndividualDeps
+from pretor.worker_individual.base_individual import (
+    BaseIndividual,
+    WorkerIndividualDeps,
+)
 from pretor.utils.logger import get_logger
 import os
 import json
 from pydantic_ai import Tool
 import importlib.util
 
-logger = get_logger('skill_individual')
+logger = get_logger("skill_individual")
+
 
 class SkillIndividual(BaseIndividual):
     """
@@ -43,7 +47,9 @@ class SkillIndividual(BaseIndividual):
         elif isinstance(bound_skill, dict):
             skill_mapper = bound_skill
 
-        skill_base_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "plugin", "skill"))
+        skill_base_dir = os.path.abspath(
+            os.path.join(os.path.dirname(__file__), "..", "plugin", "skill")
+        )
 
         for skill_name, _ in skill_mapper.items():
             skill_path = os.path.join(skill_base_dir, skill_name)
@@ -52,7 +58,7 @@ class SkillIndividual(BaseIndividual):
                 continue
 
             try:
-                with open(metadata_path, 'r', encoding='utf-8') as f:
+                with open(metadata_path, "r", encoding="utf-8") as f:
                     metadata = json.load(f)
             except Exception as e:
                 logger.error(f"Failed to load metadata for skill {skill_name}: {e}")
@@ -72,18 +78,28 @@ class SkillIndividual(BaseIndividual):
                     func_name = func_info.get("name")
                     try:
                         # Dynamically load the python module
-                        spec = importlib.util.spec_from_file_location(func_name, script_path)
+                        spec = importlib.util.spec_from_file_location(
+                            func_name, script_path
+                        )
                         module = importlib.util.module_from_spec(spec)
                         spec.loader.exec_module(module)
 
                         func = getattr(module, func_name)
                         if callable(func):
                             # Convert to PydanticAI Tool
-                            tool = Tool(func, name=func_name, description=func_info.get("docstring", ""))
+                            tool = Tool(
+                                func,
+                                name=func_name,
+                                description=func_info.get("docstring", ""),
+                            )
                             tools.append(tool)
-                            logger.info(f"Loaded skill tool: {func_name} from {skill_name}")
+                            logger.info(
+                                f"Loaded skill tool: {func_name} from {skill_name}"
+                            )
                     except Exception as e:
-                        logger.error(f"Failed to load function {func_name} from {script_path}: {e}")
+                        logger.error(
+                            f"Failed to load function {func_name} from {script_path}: {e}"
+                        )
 
         return tools
 
@@ -91,10 +107,12 @@ class SkillIndividual(BaseIndividual):
         """执行与 run 相关的核心业务流转操作。
         该方法封装了具体的算法策略或状态控制逻辑，确保操作能够在事务上下文中被原子且一致地执行。
         Args:        task_event (dict): 由事件总线或工作流引擎分发过来的事件载荷，封装了触发此次调用的上下文快照与任务目标指令。
-        Returns:         (dict): 高度聚合的字典结构数据，将多维度的属性特征或统计指标组合后一并返回。    """
+        Returns:         (dict): 高度聚合的字典结构数据，将多维度的属性特征或统计指标组合后一并返回。"""
         if self.agent is None:
-            system_prompt = self.agent_config.get("prompt",
-                                                  "你是一个拥有专业技能的专家级AI助手，请利用你的专业知识完成给定的任务。")
+            system_prompt = self.agent_config.get(
+                "prompt",
+                "你是一个拥有专业技能的专家级AI助手，请利用你的专业知识完成给定的任务。",
+            )
             await self._init_agent("skill_individual", system_prompt)
 
         deps = WorkerIndividualDeps(task_event=task_event)
@@ -106,7 +124,7 @@ class SkillIndividual(BaseIndividual):
             result = await self.agent.run(
                 f"请执行以下任务：\n{task_event}",
                 deps=deps,
-                tools=tools if tools else None
+                tools=tools if tools else None,
             )
             return {"output": result.data.output}
         except Exception as e: