wrapAgent - Trodo

One call to wrapAgent produces one run in your dashboard. Give it an agent name and an async function; the SDK generates a run_id, opens a tracing context, runs your function, captures every child span, and flushes the result.

Example

Node.js
Python

import trodo from 'trodo-node';

trodo.init({ siteId: process.env.TRODO_SITE_ID });

const { result, runId } = await trodo.wrapAgent(
  'support-agent',                         // agentName  (required)
  async (run) => {
    run.setInput({ question: 'refund policy?' });
    run.setMetadata({ env: 'prod', version: '1.2.0' });

    try {
      const answer = await askLlm(...);   // spans captured inside the callback
      run.setOutput({ answer });           // run.status becomes 'ok'
      return answer;
    } catch (err) {
      run.setErrorSummary(err.message);   // run.status becomes 'error'
      throw err;
    }
  },
  { distinctId: 'user-42', conversationId: 'thread-abc' },
);

import trodo, os

trodo.init(site_id=os.environ["TRODO_SITE_ID"])

with trodo.wrap_agent(
    "support-agent",
    distinct_id="user-42",
    conversation_id="thread-abc",
) as run:
    run.set_input({"question": "refund policy?"})
    run.set_metadata(env="prod", version="1.2.0")

    try:
        answer = ask_llm(...)          # spans captured inside the block
        run.set_output({"answer": answer})   # status becomes 'ok'
    except Exception as e:
        run.set_error_summary(str(e))   # status becomes 'error'
        raise

run_id = run.run_id

What you set vs what’s rolled up

You set on the RunHandle	Auto-rolled from spans
`agentName`, `distinctId`, `conversationId`	`duration_ms` (callback start → end)
`setInput` / `setOutput` / `setMetadata`	`total_tokens_in`, `total_tokens_out`
`setErrorSummary`	`total_cost`
—	`span_count`, `tool_count`, `error_count`
—	`status` (`ok` / `error` / `running`)

Duration, tokens, cost, and status are computed for you — you never write them. total_tokens_in / total_tokens_out / total_cost are summed across every kind='llm' span inside the run.

Options

Option (Node / Python)	Purpose
`agentName`	Required. Free-text identifier — `"support-bot"`, `"ticket-triage-v2"`.
`distinctId` / `distinct_id`	Your user id. Lets you filter runs per user.
`conversationId` / `conversation_id`	Groups runs from the same chat thread.
`parentRunId` / `parent_run_id`	Marks this run as a sub-agent. See Recipes → Sub-agents.
`metadata`	Free-form JSON tags. Same as calling `setMetadata` up-front.

Spans — what goes inside the callback.
Recipes → Basic agent — runnable copy of this example.

​Example

​What you set vs what’s rolled up

​Options

​Next

Example

What you set vs what’s rolled up

Options

Next