Refactor Workflow and Chat Architecture (#68)

* refactor: overhaul workflow and chat architecture

- Separate Chat and Workflow API endpoints and database models
- Use JSONB to store workflow execution context in Postgres
- Convert workflow engine to use pydantic-ai execution graphs inside a Ray task
- Update frontend React components to support standalone workflow creation
- Remove obsolete and broken workflow runner tests

Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>

* refactor: overhaul workflow and chat architecture

- Separate Chat and Workflow API endpoints and database models
- Use JSONB to store workflow execution context in Postgres
- Convert workflow engine to use pydantic-ai execution graphs inside a Ray task
- Update frontend React components to support standalone workflow creation
- Remove obsolete and broken workflow runner tests

Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>

* refactor: overhaul workflow and chat architecture

- Separate Chat and Workflow API endpoints and database models
- Use JSONB to store workflow execution context in Postgres
- Convert workflow engine to use pydantic-ai execution graphs inside a Ray task
- Update frontend React components to support standalone workflow creation
- Move workflow_engine inside workflow package to keep core root clean
- Remove obsolete and broken workflow runner tests

Co-authored-by: zhaoxi826 <198742034+zhaoxi826@users.noreply.github.com>

---------

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>

kilostar/core/postgres_database/model/individual.py

@@ -44,10 +44,7 @@ class BaseIndividualModel(BaseDataModel):
 
     agent_type: Mapped[str] = mapped_column(String(32))
 
-    __mapper_args__ = {
-        "polymorphic_on": "agent_type",
-        "polymorphic_identity": "base"
-    }
+    __mapper_args__ = {"polymorphic_on": "agent_type", "polymorphic_identity": "base"}
 
 
 # ==========================================
@@ -57,8 +54,7 @@ class SpecialistIndividualModel(BaseIndividualModel):
     __tablename__ = "specialist_individual"
 
     agent_id: Mapped[str] = mapped_column(
-        ForeignKey("base_individual.agent_id", ondelete="CASCADE"),
-        primary_key=True
+        ForeignKey("base_individual.agent_id", ondelete="CASCADE"), primary_key=True
     )
     bound_skill: Mapped[Optional[Dict[str, Any]]] = mapped_column(JSONB)
     workspace: Mapped[Optional[List[str]]] = mapped_column(JSONB)
@@ -70,12 +66,12 @@ class SpecialistIndividualModel(BaseIndividualModel):
     sub_ordinary_agents: Mapped[List["OrdinaryIndividualModel"]] = relationship(
         back_populates="manager",
         cascade="all, delete-orphan",
-        foreign_keys="[OrdinaryIndividualModel.manager_id]"
+        foreign_keys="[OrdinaryIndividualModel.manager_id]",
     )
     sub_special_agents: Mapped[List["SpecialIndividualModel"]] = relationship(
         back_populates="manager",
         cascade="all, delete-orphan",
-        foreign_keys="[SpecialIndividualModel.manager_id]"
+        foreign_keys="[SpecialIndividualModel.manager_id]",
     )
 
     __mapper_args__ = {
@@ -90,8 +86,7 @@ class OrdinaryIndividualModel(BaseIndividualModel):
     __tablename__ = "ordinary_individual"
 
     agent_id: Mapped[str] = mapped_column(
-        ForeignKey("base_individual.agent_id", ondelete="CASCADE"),
-        primary_key=True
+        ForeignKey("base_individual.agent_id", ondelete="CASCADE"), primary_key=True
     )
     finetuned_from: Mapped[Optional[str]] = mapped_column(String(100))
     tools: Mapped[Optional[List[str]]] = mapped_column(
@@ -106,7 +101,7 @@ class OrdinaryIndividualModel(BaseIndividualModel):
     # 逻辑关联：指向上级专家
     manager: Mapped[Optional["SpecialistIndividualModel"]] = relationship(
         back_populates="sub_ordinary_agents",
-        foreign_keys=[manager_id]  # 显式指定使用 manager_id 解析关系
+        foreign_keys=[manager_id],  # 显式指定使用 manager_id 解析关系
     )
 
     __mapper_args__ = {
@@ -121,12 +116,10 @@ class SpecialIndividualModel(BaseIndividualModel):
     __tablename__ = "special_individual"
 
     agent_id: Mapped[str] = mapped_column(
-        ForeignKey("base_individual.agent_id", ondelete="CASCADE"),
-        primary_key=True
+        ForeignKey("base_individual.agent_id", ondelete="CASCADE"), primary_key=True
     )
     modality_type: Mapped[ModalityType] = mapped_column(
-        default=ModalityType.MULTIMODAL,
-        server_default=text("'multimodal'")
+        default=ModalityType.MULTIMODAL, server_default=text("'multimodal'")
     )
     multimodal_config: Mapped[Optional[Dict[str, Any]]] = mapped_column(JSONB)
 
@@ -137,10 +130,9 @@ class SpecialIndividualModel(BaseIndividualModel):
 
     # 【修复2】：修正 back_populates 指向正确的变量名
     manager: Mapped[Optional["SpecialistIndividualModel"]] = relationship(
-        back_populates="sub_special_agents",
-        foreign_keys=[manager_id]
+        back_populates="sub_special_agents", foreign_keys=[manager_id]
     )
 
     __mapper_args__ = {
         "polymorphic_identity": "special",
-    }
+    }