Skip to main content
POST
/
api
/
agent
/
invoke
curl --request POST \
  --url https://zeus-api.agentspro.cn/api/agent/invoke \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "message": "Analyze the data trends in sales.csv",
    "llm_config": {
      "baseUrl": "https://api.openai.com/v1",
      "apiKey": "sk-...",
      "modelName": "gpt-4o",
      "temperature": 0.7
    },
    "session_id": "sess_456",
    "mode": "agent",
    "enable_sandbox": true,
    "knowledge_base_ids": ["kb_789"],
    "enable_memory": true,
    "tools": [
      {
        "type": "mcp",
        "name": "tavily",
        "base_url": "https://mcp.tavily.com/mcp",
        "api_key": "tvly-..."
      }
    ]
  }'

data: {"type": "message_chunk", "content": "Let me help you analyze"}
data: {"type": "message_chunk", "content": " the data trends in sales.csv"}
data: {"type": "tool_call", "tool_name": "sandbox_exec", "tool_args": {...}}
data: {"type": "tool_result", "tool_name": "sandbox_exec", "result": "..."}
data: {"type": "message_chunk", "content": "Based on the analysis..."}
data: {"type": "done", "session_id": "sess_456"}
The core entry point for Zeus. Starts an Agent conversation with full capabilities including MCP/OAuth tools, knowledge base RAG, memory, sandbox code execution, Skills, HITL approval, and more. Returns an SSE streaming response. See Streaming for message format details.
​
Authorization
string
required
Bearer JWT Token (user_id is automatically extracted for store isolation)

​
Core Parameters

​
message
string
required
User message content
​
llm_config
object
required
LLM model configuration (sourced from the frontend localStorage)
​
session_id
string
Session ID for Checkpointer persistence. Auto-generated if not provided
​
mode
string
default:"agent"
Conversation mode:
  • agent — Full capability mode (default)
  • ask — Read-only Q&A mode, write tools disabled
  • plan — Interactive planning mode

​
Tool Configuration

​
tools
array
default:"[]"
Unified tool list. Each tool is distinguished by its type field
​
enable_sandbox
boolean
default:"true"
Whether to enable the sandbox code execution tool (E2B)
​
enable_web_search
boolean
default:"false"
Whether to enable the Web Search Tool (Tavily + DuckDuckGo)

​
RAG & Memory

​
knowledge_base_ids
array
default:"[]"
List of knowledge base IDs. When provided, the search_knowledge_base tool is automatically registered
​
enable_memory
boolean
default:"false"
Whether to enable the Memory Tool (long-term memory read/write)

​
Skills

​
skills
object
Skills activation configuration

​
Context

​
chat_history
array
default:"[]"
List of historical conversation messages [{ role, content, timestamp? }]
​
resource_files
array
default:"[]"
List of resource files [{ name, content, type }] (e.g. Markdown prompts)
​
sandbox_files
array
default:"[]"
Files uploaded to the sandbox [{ name, path, type, size? }]
​
chat_attachments
array
default:"[]"
User-added chat attachments [{ id, name, size, type, content }]

​
HITL Approval

​
tool_interrupt_config
object
Tool interrupt configuration (Human-in-the-Loop)
curl --request POST \
  --url https://zeus-api.agentspro.cn/api/agent/invoke \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "message": "Analyze the data trends in sales.csv",
    "llm_config": {
      "baseUrl": "https://api.openai.com/v1",
      "apiKey": "sk-...",
      "modelName": "gpt-4o",
      "temperature": 0.7
    },
    "session_id": "sess_456",
    "mode": "agent",
    "enable_sandbox": true,
    "knowledge_base_ids": ["kb_789"],
    "enable_memory": true,
    "tools": [
      {
        "type": "mcp",
        "name": "tavily",
        "base_url": "https://mcp.tavily.com/mcp",
        "api_key": "tvly-..."
      }
    ]
  }'

data: {"type": "message_chunk", "content": "Let me help you analyze"}
data: {"type": "message_chunk", "content": " the data trends in sales.csv"}
data: {"type": "tool_call", "tool_name": "sandbox_exec", "tool_args": {...}}
data: {"type": "tool_result", "tool_name": "sandbox_exec", "result": "..."}
data: {"type": "message_chunk", "content": "Based on the analysis..."}
data: {"type": "done", "session_id": "sess_456"}