Fix: Move project files to root directory

.trae/documents/Implement Dynamic Agent API with Video and Knowledge Base Support.md

@@ -0,0 +1,47 @@
+# Add Dynamic Agent API (Type=1) with Database Integration
+
+I will implement the Dynamic Agent feature by integrating it with the existing `agent_cards` system. Dynamic Agents will be distinguished by `type=1` and will store their extended data (videos, knowledge base) in a new linked table.
+
+## 1. Database Schema Extension
+I will create a new table `dynamic_agent_details` to store the specialized data for dynamic agents.
+*   **Table Name**: `dynamic_agent_details`
+*   **Columns**:
+    *   `id`: `SERIAL PRIMARY KEY`
+    *   `card_id`: `INTEGER` (Foreign Key linking to `agent_cards.card_id`)
+    *   `videos`: `JSONB` (Stores list of `{url, emotion}`, min 1, max 7)
+    *   `kb_id`: `VARCHAR` (Knowledge Base ID)
+    *   `kb_config`: `JSONB` (Additional Knowledge Base fields)
+    *   `created_at`: `TIMESTAMP`
+
+## 2. Code Implementation (`main.py`)
+
+### Pydantic Models
+I will define:
+*   `VideoItem`: `{url: str, emotion: str}`
+*   `DynamicAgentCreate`: Inherits/Includes fields from `AgentCard` (name, avatar, etc.) PLUS:
+    *   `videos`: List[VideoItem] (validated length 1-7)
+    *   `kb_id`: str
+    *   `kb_config`: dict
+
+### API Endpoints
+1.  **Create Dynamic Agent**
+    *   `POST /dynamic_agent/`
+    *   **Logic**:
+        1.  Insert the base agent info into `agent_cards` with `type=1` and `RETURNING card_id`.
+        2.  Insert the extended info (videos, kb details) into `dynamic_agent_details` using the returned `card_id`.
+        3.  Return the new `card_id`.
+
+2.  **Get Dynamic Agent Details**
+    *   `GET /dynamic_agent/{card_id}`
+    *   **Logic**:
+        1.  Fetch base info from `agent_cards`.
+        2.  Fetch extended info from `dynamic_agent_details`.
+        3.  Return combined result.
+
+### Helper Functions
+*   `init_dynamic_agent_db()`: Checks/Creates the `dynamic_agent_details` table on startup.
+
+## 3. Verification
+*   Create a dynamic agent via the new API.
+*   Verify it appears in the `agent_cards` table (as type 1).
+*   Verify extended data is in `dynamic_agent_details`.

.trae/documents/Implement Tool Management System for Dynamic Agents.md

@@ -0,0 +1,43 @@
+# Implement Tool Management for Dynamic Agents
+
+I will implement a system to manage "Tools" (Function Calls) and associate them with Dynamic Agents, allowing the frontend to easily configure which tools an agent can use.
+
+## 1. Database Schema Expansion
+I will create two new tables in PostgreSQL:
+*   `tools`: Stores reusable tool definitions (templates).
+    *   `tool_id`: `SERIAL PRIMARY KEY`
+    *   `name`: `VARCHAR` (Unique, e.g., "get_weather")
+    *   `description`: `TEXT` (For LLM understanding)
+    *   `parameters`: `JSONB` (JSON Schema for arguments)
+    *   `created_at`: `TIMESTAMP`
+*   `agent_tools`: Maps agents to tools (Many-to-Many).
+    *   `agent_card_id`: `INTEGER` (FK)
+    *   `tool_id`: `INTEGER` (FK)
+    *   `config`: `JSONB` (Optional, for agent-specific tool config if needed)
+
+## 2. API Implementation (`main.py`)
+
+### Pydantic Models
+*   `ToolCreate`: Validation for creating new tool definitions.
+*   `ToolResponse`: API response format.
+*   `AgentToolAssignment`: For linking tools to agents.
+
+### New Endpoints
+*   **Tool Management (CRUD)**:
+    *   `POST /tools/`: Create a new tool definition.
+    *   `GET /tools/`: List all available tools.
+    *   `PUT /tools/{tool_id}`: Update a tool.
+    *   `DELETE /tools/{tool_id}`: Delete a tool.
+*   **Agent Tool Association**:
+    *   `POST /agent/{card_id}/tools`: Assign a list of tools to an agent.
+    *   `GET /agent/{card_id}/tools`: Get all tools assigned to an agent.
+    *   `DELETE /agent/{card_id}/tools/{tool_id}`: Remove a tool from an agent.
+
+### Update Existing Logic
+*   **Modify `GET /dynamic_agent/{card_id}`**:
+    *   Update the query to automatically fetch and include the list of associated tools in the agent details response. This ensures the frontend gets everything in one call.
+
+## 3. Verification
+*   Create a "Weather Query" tool definition.
+*   Assign it to a Dynamic Agent.
+*   Verify the agent details endpoint returns the tool info correctly.