Skip to main content
POST
/
api
/
agent
/
resume
curl --request POST \
  --url https://zeus-api.agentspro.cn/api/agent/resume \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "session_id": "sess_456",
    "llm_config": {
      "baseUrl": "https://api.openai.com/v1",
      "apiKey": "sk-...",
      "modelName": "gpt-4o"
    },
    "tool_call_results": [
      {
        "tool_call_id": "call_abc",
        "tool_name": "sandbox_exec",
        "decision": "approved"
      }
    ],
    "human_order": "Make sure to back up the files before executing"
  }'

data: {"type": "tool_result", "tool_name": "sandbox_exec", "result": "..."}
data: {"type": "message_chunk", "content": "Operation completed. Files have been backed up."}
data: {"type": "done", "session_id": "sess_456"}
When a tool triggers an HITL (Human-in-the-Loop) interrupt during Agent execution, the frontend collects the user’s approval decision and uses this endpoint to resume execution. Returns an SSE streaming response, continuing execution from the interruption point. user_id is automatically extracted from the JWT Token and does not need to be passed in the body.
​
Authorization
string
required
Bearer JWT Token (user_id is automatically extracted)
​
session_id
string
required
The interrupted session ID
​
llm_config
object
required
LLM model configuration (same as invoke)
​
tool_call_results
array
required
List of tool call approval results
​
human_order
string
Human instruction — additional instructions passed to the Agent along with the approval result
​
hitl_config
object
Tool interrupt configuration (subsequent tool calls may still trigger interrupts)
curl --request POST \
  --url https://zeus-api.agentspro.cn/api/agent/resume \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "session_id": "sess_456",
    "llm_config": {
      "baseUrl": "https://api.openai.com/v1",
      "apiKey": "sk-...",
      "modelName": "gpt-4o"
    },
    "tool_call_results": [
      {
        "tool_call_id": "call_abc",
        "tool_name": "sandbox_exec",
        "decision": "approved"
      }
    ],
    "human_order": "Make sure to back up the files before executing"
  }'

data: {"type": "tool_result", "tool_name": "sandbox_exec", "result": "..."}
data: {"type": "message_chunk", "content": "Operation completed. Files have been backed up."}
data: {"type": "done", "session_id": "sess_456"}