Pi extension

Trace Pi agentic sessions, LLM calls, and tool executions in Weave.

Weave for Agents is in public preview. Features, APIs, and the Agents view UI may change before general availability.

Pi is a terminal-based coding agent. Weave traces Pi sessions, LLM calls, and tool executions automatically using the createOtelExtension integration, which conforms to the GenAI semantic conventions.

Pi is a TypeScript/Node.js framework with no Python equivalent. Pi requires the ESM module system — your project must use "type": "module" in package.json, or compile TypeScript to ESM output. CommonJS projects will error. For more information on setting up an ESM project, see Typescript SDK integration.

Prerequisites

• Node.js (v18 or later)
• A W&B account and API key set as a WANDB_API_KEY environment variable

Install packages

• Install Weave, Pi, and Node type definitions as local project dependencies:

npm install weave @earendil-works/pi-coding-agent
npm install --save-dev @types/node tsx typescript

Trace a Pi prompt and response

Call weave.init() before creating your agent session, then pass createOtelExtension() as an extension factory. Weave traces the full agent lifecycle: the session, each prompt/response cycle (invoke_agent), individual LLM calls (chat), and tool executions (execute_tool). The session ID is generated automatically by SessionManager.inMemory().

import {init, createOtelExtension} from 'weave';

import {
  createAgentSession,
  DefaultResourceLoader,
  SessionManager,
  getAgentDir,
} from '@earendil-works/pi-coding-agent';

async function main() {
  // 1. Initialize Weave — sets up the OTEL TracerProvider pointing at your
  //    Weave project. All spans created by createOtelExtension() are
  //    automatically exported here.
  await init('[YOUR-TEAM]/[YOUR-PROJECT]'); 

// 2. Create a resource loader and inject the Weave OTEL extension.
//    The resource loader provides the Pi runtime environment and
//    extension lifecycle used for tracing agent activity.
  const resourceLoader = new DefaultResourceLoader({
    cwd: process.cwd(),
    agentDir: getAgentDir(),
    extensionFactories: [createOtelExtension({})],
  });

  await resourceLoader.reload();

  // 3. Start the agent session
  const {session} = await createAgentSession({
    resourceLoader,
    sessionManager: SessionManager.inMemory(),
  });

  // 4. Bind extensions — triggers session_start event so the OTEL adapter
  //    creates the root session span and captures the conversation ID.
  await session.bindExtensions({});

  // 5. Stream assistant output to stdout
  session.subscribe(event => {
    if (
      event.type === 'message_update' &&
      event.assistantMessageEvent.type === 'text_delta'
    ) {
      process.stdout.write(event.assistantMessageEvent.delta);
    }
  });

  // 6. Send a prompt and wait for the full response
  await session.prompt('What files are in the current directory?');
  console.log();
}

main();

Build and run using:

npx tsx [filename].ts 

When you run your code, your traces appear in the Agents tab of your Weave project at https://wandb.ai/[YOUR-TEAM]/[YOUR-PROJECT]/weave/agents.

Next steps

You can turn this example into a multi-turn session by adding additional prompts. Each call to session.prompt() is traced as a separate invoke_agent span, all nested under a single root span. The agent retains context across prompts automatically.

After running the code, the Agents tab shows the full multi-turn timeline with nested LLM calls, tool executions, token usage, and cost.