A2A Sample Methods and JSON Responses

This section provides illustrative JSON examples of common A2A interactions. Timestamps, context IDs, and request/response IDs are for demonstration purposes. For brevity, some optional fields might be omitted if not central to the example.

1. Fetching Authenticated Extended Agent Card

Scenario: A client discovers a public Agent Card indicating support for an authenticated extended card and wants to retrieve the full details.

Client fetches the public Agent Card:
```
GET https://example.com/.well-known/agent.json
```
Server responds with the public Agent Card (like the example in Section 5.6), including supportsAuthenticatedExtendedCard: true (at the root level) and securitySchemes.
Client identifies required authentication from the public card.
Client obtains necessary credentials out-of-band (e.g., performs OAuth 2.0 flow with Google, resulting in an access token).

Client fetches the authenticated extended Agent Card:

GET https://example.com/a2a/agent/authenticatedExtendedCard
Authorization: Bearer <obtained_access_token>

Server authenticates and authorizes the request.
Server responds with the full Agent Card:

2. Basic Execution (Synchronous / Polling Style)

2.1. Task-based Response

Scenario: Client asks a simple question, and the agent responds quickly with a task

Client sends a message using message/send:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "message/send",
  "params": {
    "message": {
      "role": "user",
      "parts": [
        {
          "kind": "text",
          "text": "tell me a joke"
        }
      ],
      "messageId": "9229e770-767c-417b-a0b0-f0741243c589"
    },
    "metadata": {}
  }
}

Server processes the request, creates a task and responds (task completes quickly)

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "id": "363422be-b0f9-4692-a24d-278670e7c7f1",
    "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
    "status": {
      "state": "completed"
    },
    "artifacts": [
      {
        "artifactId": "9b6934dd-37e3-4eb1-8766-962efaab63a1",
        "name": "joke",
        "parts": [
          {
            "kind": "text",
            "text": "Why did the chicken cross the road? To get to the other side!"
          }
        ]
      }
    ],
    "history": [
      {
        "role": "user",
        "parts": [
          {
            "kind": "text",
            "text": "tell me a joke"
          }
        ],
        "messageId": "9229e770-767c-417b-a0b0-f0741243c589",
        "taskId": "363422be-b0f9-4692-a24d-278670e7c7f1",
        "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4"
      }
    ],
    "kind": "task",
    "metadata": {}
  }
}

2.2. Direct Message Response

Scenario: Client asks a simple question, and the agent responds quickly without a task

Client sends a message using message/send:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "message/send",
  "params": {
    "message": {
      "role": "user",
      "parts": [
        {
          "kind": "text",
          "text": "tell me a joke"
        }
      ],
      "messageId": "9229e770-767c-417b-a0b0-f0741243c589"
    },
    "metadata": {}
  }
}

Server processes the request, responds quickly without a task

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "messageId": "363422be-b0f9-4692-a24d-278670e7c7f1",
    "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
    "parts": [
      {
        "kind": "text",
        "text": "Why did the chicken cross the road? To get to the other side!"
      }
    ],
    "kind": "message",
    "metadata": {}
  }
}

If the task were longer-running, the server might initially respond with status.state: "working". The client would then periodically call tasks/get with params: {"id": "363422be-b0f9-4692-a24d-278670e7c7f1"} until the task reaches a terminal state.

3. Streaming Task Execution (SSE)

Scenario: Client asks the agent to write a long paper describing an attached picture.

Client sends a message and subscribes using message/stream:

{
  "method": "message/stream",
  "params": {
    "message": {
      "role": "user",
      "parts": [
        {
          "kind": "text",
          "text": "write a long paper describing the attached pictures"
        },
        {
          "kind": "file",
          "file": {
            "mimeType": "image/png",
            "data": "<base64-encoded-content>"
          }
        }
      ],
      "messageId": "bbb7dee1-cf5c-4683-8a6f-4114529da5eb"
    },
    "metadata": {}
  }
}

Server responds with HTTP 200 OK, Content-Type: text/event-stream, and starts sending SSE events:

Event 1: Task status update - working

data: {
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "id": "225d6247-06ba-4cda-a08b-33ae35c8dcfa",
    "contextId": "05217e44-7e9f-473e-ab4f-2c2dde50a2b1",
    "status": {
      "state": "submitted",
      "timestamp":"2025-04-02T16:59:25.331844"
    },
    "history": [
      {
        "role": "user",
        "parts": [
          {
            "kind": "text",
            "text": "write a long paper describing the attached pictures"
          },
          {
            "kind": "file",
            "file": {
              "mimeType": "image/png",
              "data": "<base64-encoded-content>"
            }
          }
        ],
        "messageId": "bbb7dee1-cf5c-4683-8a6f-4114529da5eb",
        "taskId": "225d6247-06ba-4cda-a08b-33ae35c8dcfa",
        "contextId": "05217e44-7e9f-473e-ab4f-2c2dde50a2b1"
      }
    ],
    "kind": "task",
    "metadata": {}
  }
}

data: {
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "taskId": "225d6247-06ba-4cda-a08b-33ae35c8dcfa",
    "contextId": "05217e44-7e9f-473e-ab4f-2c2dde50a2b1",
    "artifact": {
      "artifactId": "9b6934dd-37e3-4eb1-8766-962efaab63a1",
      "parts": [
        {"type":"text", "text": "<section 1...>"}
      ]
    },
    "append": false,
    "lastChunk": false,
    "kind":"artifact-update"
  }
}

data: {
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "taskId": "225d6247-06ba-4cda-a08b-33ae35c8dcfa",
    "contextId": "05217e44-7e9f-473e-ab4f-2c2dde50a2b1",
    "artifact": {
      "artifactId": "9b6934dd-37e3-4eb1-8766-962efaab63a1",
      "parts": [
        {"type":"text", "text": "<section 2...>"}
      ],
    },
    "append": true,
    "lastChunk": false,
    "kind":"artifact-update"
  }
}


data: {
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "taskId": "225d6247-06ba-4cda-a08b-33ae35c8dcfa",
    "contextId": "05217e44-7e9f-473e-ab4f-2c2dde50a2b1",
    "artifact": {
      "artifactId": "9b6934dd-37e3-4eb1-8766-962efaab63a1",
      "parts": [
        {"type":"text", "text": "<section 3...>"}
      ]
    },
    "append": true,
    "lastChunk": true,
    "kind":"artifact-update"
  }
}

data: {
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "taskId": "225d6247-06ba-4cda-a08b-33ae35c8dcfa",
    "contextId": "05217e44-7e9f-473e-ab4f-2c2dde50a2b1",
    "status": {
      "state": "completed",
      "timestamp":"2025-04-02T16:59:35.331844"
    },
    "final": true,
    "kind":"status-update"
  }
}

(Server closes the SSE connection after the final:true event).

4. Multi-Turn Interaction (Input Required)

Scenario: Client wants to book a flight, and the agent needs more information.

Client sends a message using message/send:

{
  "jsonrpc": "2.0",
  "id": "req-003",
  "method": "message/send",
  "params": {
    "message": {
      "role": "user",
      "parts": [{ "kind": "text", "text": "I'd like to book a flight." }]
    },
    "messageId": "c53ba666-3f97-433c-a87b-6084276babe2"
  }
}

Server responds, task state is input-required:

{
  "jsonrpc": "2.0",
  "id": "req-003",
  "result": {
    "id": "3f36680c-7f37-4a5f-945e-d78981fafd36",
    "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
    "status": {
      "state": "input-required",
      "message": {
        "role": "agent",
        "parts": [
          {
            "kind": "text",
            "text": "Sure, I can help with that! Where would you like to fly to, and from where? Also, what are your preferred travel dates?"
          }
        ],
        "messageId": "c2e1b2dd-f200-4b04-bc22-1b0c65a1aad2",
        "taskId": "3f36680c-7f37-4a5f-945e-d78981fafd36",
        "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4"
      },
      "timestamp": "2024-03-15T10:10:00Z"
    },
    "history": [
      {
        "role": "user",
        "parts": [
          {
            "kind": "text",
            "text": "I'd like to book a flight."
          }
        ],
        "messageId": "c53ba666-3f97-433c-a87b-6084276babe2",
        "taskId": "3f36680c-7f37-4a5f-945e-d78981fafd36",
        "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4"
      }
    ],
    "kind": "task"
  }
}

Client message/send (providing the requested input, using the same task ID):

{
  "jsonrpc": "2.0",
  "id": "req-004",
  "method": "message/send",
  "params": {
    "message": {
      "role": "user",
      "parts": [
        {
          "kind": "text",
          "text": "I want to fly from New York (JFK) to London (LHR) around October 10th, returning October 17th."
        }
      ],
      "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
      "taskId": "3f36680c-7f37-4a5f-945e-d78981fafd36",
      "messageId": "0db1d6c4-3976-40ed-b9b8-0043ea7a03d3"
    },
    "configuration": {
      "blocking": true
    }
  }
}

Server processes the new input and responds (e.g., task completed or more input needed):

{
  "jsonrpc": "2.0",
  "id": "req-004",
  "result": {
    "id": "3f36680c-7f37-4a5f-945e-d78981fafd36",
    "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
    "status": {
      "state": "completed",
      "message": {
        "role": "agent",
        "parts": [
          {
            "kind": "text",
            "text": "Okay, I've found a flight for you. Confirmation XYZ123. Details are in the artifact."
          }
        ]
      }
    },
    "artifacts": [
      {
        "artifactId": "9b6934dd-37e3-4eb1-8766-962efaab63a1",
        "name": "FlightItinerary.json",
        "parts": [
          {
            "kind": "data",
            "data": {
              "confirmationId": "XYZ123",
              "from": "JFK",
              "to": "LHR",
              "departure": "2024-10-10T18:00:00Z",
              "arrival": "2024-10-11T06:00:00Z",
              "returnDeparture": "..."
            }
          }
        ]
      }
    ],
    "history": [
      {
        "role": "user",
        "parts": [
          {
            "kind": "text",
            "text": "I'd like to book a flight."
          }
        ],
        "messageId": "c53ba666-3f97-433c-a87b-6084276babe2",
        "taskId": "3f36680c-7f37-4a5f-945e-d78981fafd36",
        "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4"
      },
      {
        "role": "agent",
        "parts": [
          {
            "kind": "text",
            "text": "Sure, I can help with that! Where would you like to fly to, and from where? Also, what are your preferred travel dates?"
          }
        ],
        "messageId": "c2e1b2dd-f200-4b04-bc22-1b0c65a1aad2",
        "taskId": "3f36680c-7f37-4a5f-945e-d78981fafd36",
        "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4"
      },
      {
        "role": "user",
        "parts": [
          {
            "kind": "text",
            "text": "I want to fly from New York (JFK) to London (LHR) around October 10th, returning October 17th."
          }
        ],
        "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
        "taskId": "3f36680c-7f37-4a5f-945e-d78981fafd36",
        "messageId": "0db1d6c4-3976-40ed-b9b8-0043ea7a03d3"
      }
    ],
    "kind": "task",
    "metadata": {}
  }
}

5. Push Notification Setup and Usage

5.1. Webhook Configuration and Notification Flow

Scenario: Client requests a long-running report generation and wants to be notified via webhook when it's done.

Client message/send with pushNotification config:

{
  "jsonrpc": "2.0",
  "id": "req-005",
  "method": "message/send",
  "params": {
    "message": {
      "role": "user",
      "parts": [
        {
          "kind": "text",
          "text": "Generate the Q1 sales report. This usually takes a while. Notify me when it's ready."
        }
      ],
      "messageId": "6dbc13b5-bd57-4c2b-b503-24e381b6c8d6"
    },
    "configuration": {
      "pushNotificationConfig": {
        "url": "https://client.example.com/webhook/a2a-notifications",
        "token": "secure-client-token-for-task-aaa",
        "authentication": {
          "schemes": ["Bearer"]
          // Assuming server knows how to get a Bearer token for this webhook audience,
          // or this implies the webhook is public/uses the 'token' for auth.
          // 'credentials' could provide more specifics if needed by the server.
        }
      }
    }
  }
}

Server acknowledges the task (e.g., status submitted or working):

{
  "jsonrpc": "2.0",
  "id": "req-005",
  "result": {
    "id": "43667960-d455-4453-b0cf-1bae4955270d",
    "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
    "status": { "state": "submitted", "timestamp": "2024-03-15T11:00:00Z" }
    // ... other fields ...
  }
}

(Later) A2A Server completes the task and POSTs a notification to https://client.example.com/webhook/a2a-notifications:
- HTTP Headers might include:
  - Authorization: Bearer <server_jwt_for_webhook_audience> (if server authenticates to webhook)
  - Content-Type: application/json
  - X-A2A-Notification-Token: secure-client-token-for-task-aaa
- HTTP Body (Task object is sent as JSON payload):
```
{
  "id": "43667960-d455-4453-b0cf-1bae4955270d",
  "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
  "status": { "state": "completed", "timestamp": "2024-03-15T18:30:00Z" },
  "kind": "task"
  // ... other fields ...
}
```
Client's Webhook Service:
- Receives the POST.
- Validates the Authorization header (if applicable).
- Validates the X-A2A-Notification-Token.
- Internally processes the notification (e.g., updates application state, notifies end user).

6. File Exchange (Upload and Download)

6.1. Image Processing Workflow

Scenario: Client sends an image for analysis, and the agent returns a modified image.

Client message/send with a FilePart (uploading image bytes):

{
  "jsonrpc": "2.0",
  "id": "req-007",
  "method": "message/send",
  "params": {
    "message": {
      "role": "user",
      "parts": [
        {
          "kind": "text",
          "text": "Analyze this image and highlight any faces."
        },
        {
          "kind": "file",
          "file": {
            "name": "input_image.png",
            "mimeType": "image/png",
            "bytes": "iVBORw0KGgoAAAANSUhEUgAAAAUA..." // Base64 encoded image data
          }
        }
      ],
      "messageId": "6dbc13b5-bd57-4c2b-b503-24e381b6c8d6"
    }
  }
}

Server processes the image and responds with a FilePart in an artifact (e.g., providing a URI to the modified image):

{
  "jsonrpc": "2.0",
  "id": "req-007",
  "result": {
    "id": "43667960-d455-4453-b0cf-1bae4955270d",
    "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
    "status": { "state": "completed", "timestamp": "2024-03-15T12:05:00Z" },
    "artifacts": [
      {
        "artifactId": "9b6934dd-37e3-4eb1-8766-962efaab63a1",
        "name": "processed_image_with_faces.png",
        "parts": [
          {
            "kind": "file",
            "file": {
              "name": "output.png",
              "mimeType": "image/png",
              // Server might provide a URI to a temporary storage location
              "uri": "https://storage.example.com/processed/task-bbb/output.png?token=xyz"
              // Or, alternatively, it could return bytes directly:
              // "bytes": "ASEDGhw0KGgoAAAANSUhEUgAA..."
            }
          }
        ]
      }
    ],
    "kind": "task"
  }
}

7. Structured Data Exchange (Requesting and Providing JSON)

7.1. Schema-based Data Request

Scenario: Client asks for a list of open support tickets in a specific JSON format.

Client message/send, Part.metadata hints at desired output schema/Media Type: (Note: A2A doesn't formally standardize schema negotiation in v0.2.0, but metadata can be used for such hints by convention between client/server).

{
  "jsonrpc": "2.0",
  "id": 9,
  "method": "message/send",
  "params": {
    "message": {
      "role": "user",
      "parts": [
        {
          "kind": "text",
          "text": "Show me a list of my open IT tickets",
          "metadata": {
            "mimeType": "application/json",
            "schema": {
              "type": "array",
              "items": {
                "type": "object",
                "properties": {
                  "ticketNumber": { "type": "string" },
                  "description": { "type": "string" }
                }
              }
            }
          }
        }
      ],
      "messageId": "85b26db5-ffbb-4278-a5da-a7b09dea1b47"
    },
    "metadata": {}
  }
}

Server responds with structured JSON data:

{
  "jsonrpc": "2.0",
  "id": 9,
  "result": {
    "id": "d8c6243f-5f7a-4f6f-821d-957ce51e856c",
    "contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
    "status": {
      "state": "completed",
      "timestamp": "2025-04-17T17:47:09.680794"
    },
    "artifacts": [
      {
        "artifactId": "c5e0382f-b57f-4da7-87d8-b85171fad17c",
        "parts": [
          {
            "kind": "text",
            "text": "[{\"ticketNumber\":\"REQ12312\",\"description\":\"request for VPN access\"},{\"ticketNumber\":\"REQ23422\",\"description\":\"Add to DL - team-gcp-onboarding\"}]"
          }
        ]
      }
    ],
    "kind": "task"
  }
}

8. Summary

These examples illustrate the flexibility of A2A in handling various interaction patterns and data types. The workflows covered include:

Authentication: Fetching authenticated extended agent cards
Execution Patterns: Synchronous, asynchronous, and streaming task execution
Interaction Models: Single-turn and multi-turn conversations
Notification Systems: Push notifications via webhooks
Data Exchange: File uploads/downloads and structured JSON data

Implementers should refer to the detailed object definitions for all fields and constraints when implementing these workflows.

Go A2A

A2A Sample Methods and JSON Responses

1. Fetching Authenticated Extended Agent Card

2. Basic Execution (Synchronous / Polling Style)

2.1. Task-based Response

2.2. Direct Message Response

3. Streaming Task Execution (SSE)

4. Multi-Turn Interaction (Input Required)

5. Push Notification Setup and Usage

5.1. Webhook Configuration and Notification Flow

6. File Exchange (Upload and Download)

6.1. Image Processing Workflow

7. Structured Data Exchange (Requesting and Providing JSON)

7.1. Schema-based Data Request

8. Summary

Related Articles