Agent Adapter Contract

Wendell runs your production agent through agent_command.

The command receives a JSON work item on stdin and must print a JSON response on stdout.

Input shape

The payload includes:

{
  "schema_version": "wendell.agent_input.v1",
  "task": "Respond as an agent in a Wendell remote runtime scenario.",
  "scenario": {
    "id": "playbook_workflow_1",
    "title": "Evaluate refund request",
    "customer_goal": "Request a refund that must follow policy."
  },
  "transcript": [],
  "available_tools": [
    {
      "name": "orders.lookup",
      "arguments": {"order_id": "str"},
      "description": "Look up an order."
    }
  ],
  "case": {
    "case_id": "case_123",
    "request": "I need help with this refund."
  },
  "instruction": "Return JSON with `message`, `tool_calls`, and optional `metrics`."
}

Fields may grow over time. Adapters should ignore unknown fields.

Wendell does not send scoring rubrics, hidden facts, expected outcomes, source lineage, terminal outcomes, or success/failure criteria to the agent process. Those stay inside Wendell's evaluator.

Output shape

Return a JSON object:

{
  "message": "I can help with that refund. I need to look up the order first.",
  "tool_calls": [
    {
      "name": "orders.lookup",
      "args": {"order_id": "example"},
      "result": {"found": true}
    }
  ],
  "metrics": {
    "latency_ms": 1200
  }
}

Required fields:

Field	Type	Description
message	string	Agent response text.
tool_calls	array	Tool calls made by the agent. Use [] if none.

Optional fields:

Field	Type	Description
metrics	object	Runtime metrics to attach to the turn.

Example Python adapter

import json
import sys


def main() -> None:
    payload = json.load(sys.stdin)
    scenario = payload.get("scenario", {})
    customer_goal = scenario.get("customer_goal", "the request")

    response = {
        "message": f"I will handle {customer_goal} according to the approved Playbook.",
        "tool_calls": [],
        "metrics": {},
    }
    print(json.dumps(response))


if __name__ == "__main__":
    main()

Configure it:

agent_command = "python scripts/wendell_agent_adapter.py"

Failure behavior

If the command exits nonzero, Wendell records an agent error for the turn.

If stdout is not valid JSON, the generated adapter template fails fast with a clear error. Some lower-level Wendell runtime paths can wrap raw stdout as a plain text message, but production adapters should always print the JSON object above.

If tool_calls is missing, use [] in your adapter to keep behavior explicit.