feat(agent): Gradio-powered LangGraph agent chat with streaming, tool calls, file upload, conversation persistence

- Gradio 5.50.0 ChatInterface with type='messages' streaming
- LangGraph create_react_agent with InMemorySaver checkpointer
- 4 @tool functions: search_dashboards, get_health_summary, list_environments, get_task_status
- Structured ChatMessage metadata (7 discriminator types: stream_token, tool_start/end/error, confirm_required, confirm_resolved, error)
- HITL resume via second submit() with interrupt_before/Command
- Dual-identity RBAC: service JWT + user JWT for tool calls
- File upload (10 MB limit, pdfplumber/xlsx/JSON parser)
- Conversation persistence via POST /api/agent/conversations/save
- REST API: list, history, archive conversations; multi-tab gate; LLM config
- LLM provider selection via Admin -> LLM Settings (assistant_planner_provider)
- Svelte 5 AgentChatModel with stream event queue, dedup, stream_status watcher
- MarkdownRenderer using svelte-markdown with semantic Tailwind tokens
- ToolCallCard (3 states: executing/completed/failed)
- ConversationList with search, date grouping, infinite scroll
- ConnectionIndicator with Gradio health status
- /agent route with two-column layout
- Vite proxy /api/agent/gradio -> Gradio SSE
- Fixed: not_() SQLAlchemy operator, route collision with _admin_routes
- Fixed: conversation_id -> id normalization, .pyc cache staleness
- Fixed: event.data array parsing (Gradio returns [jsonStr, null])
- Requirements pinned: gradio==5.50.0, pydantic>=2.7,<=2.12.3

backend/src/models/agent.py

@@ -0,0 +1,60 @@
+# backend/src/models/agent.py
+# #region Models.Agent [C:2] [TYPE Module] [SEMANTICS agent,model,database]
+# @BRIEF SQLAlchemy models for Gradio Agent Chat conversations.
+
+import uuid
+
+from sqlalchemy import JSON, Boolean, Column, DateTime, ForeignKey, String, Text
+from sqlalchemy.orm import relationship
+
+from .mapping import Base
+
+
+def _uuid() -> str:
+    return str(uuid.uuid4())
+
+
+# #region Models.Agent.AgentConversation [C:2] [TYPE Class] [SEMANTICS agent,conversation,model]
+# @ingroup Models
+# @BRIEF A multi-turn agent chat conversation. Soft-delete via is_archived.
+# @RELATION DEPENDS_ON -> [Models.User]
+
+class AgentConversation(Base):
+    __tablename__ = "agent_conversations"
+
+    id = Column(String, primary_key=True, default=_uuid)
+    user_id = Column(String, nullable=False, index=True)
+    title = Column(String(256), nullable=False, server_default="New Conversation")
+    is_archived = Column(Boolean, default=False, server_default="false")
+    created_at = Column(DateTime, server_default="now()")
+    updated_at = Column(DateTime, server_default="now()", onupdate="now()")
+
+    messages = relationship(
+        "AgentMessage",
+        back_populates="conversation",
+        cascade="all, delete-orphan",
+        order_by="AgentMessage.created_at",
+    )
+# #endregion Models.Agent.AgentConversation
+
+
+# #region Models.Agent.AgentMessage [C:2] [TYPE Class] [SEMANTICS agent,message,model]
+# @ingroup Models
+# @BRIEF A single message in an agent conversation.
+# @RELATION DEPENDS_ON -> [Models.Agent.AgentConversation]
+
+class AgentMessage(Base):
+    __tablename__ = "agent_messages"
+
+    id = Column(String, primary_key=True, default=_uuid)
+    conversation_id = Column(String, ForeignKey("agent_conversations.id"), nullable=False, index=True)
+    role = Column(String(16), nullable=False)  # user | assistant | tool | system
+    text = Column(Text, nullable=True)
+    state = Column(String(32), nullable=True)
+    tool_calls = Column(JSON, nullable=True)  # [{tool, input, output, error, status}]
+    attachments = Column(JSON, nullable=True)  # [{name, type, size, extracted_text}]
+    created_at = Column(DateTime, server_default="now()")
+
+    conversation = relationship("AgentConversation", back_populates="messages")
+# #endregion Models.Agent.AgentMessage
+# #endregion Models.Agent