Resume Agent

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"}

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.

string

required

Bearer JWT Token (user_id is automatically extracted)

string

required

The interrupted session ID

object

required

LLM model configuration (same as invoke)

Show llm_config

string

required

API base URL

string

required

API key

string

required

Model name

number

default:"0.7"

Temperature parameter

array

required

List of tool call approval results

Show tool_call_result

string

required

Tool call ID

string

required

Tool name

string

required

Approval decision: approved | rejected | modified | timeout

string

Custom tool return value (used with modified)

object

Original tool parameters

object

Modified tool parameters (used with modified)

string

Rejection reason (used with rejected)

boolean

default:"false"

Whether to mark as an error

string

Human instruction — additional instructions passed to the Agent along with the approval result

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"}

Auth

Agent API

Tools API

Knowledge Base API

Document API

Search API

Node API

Scheduled Tasks API

Channels API

WebSocket

Resume Agent