PI Integration

​

Integration Modes

​

1) PI as Workflow Agent

import { PiAgent } from "smthrs";

const pi = new PiAgent({
  provider: "openai",
  model: "gpt-5.6-luna",
  mode: "text",
});

{/* outputs comes from createSmithers() */}
<Task id="implementation" output={outputs.implementation} agent={pi}>
  {`Implement feature X and explain tradeoffs.`}
</Task>

​

2) PI Server Client

import { runWorkflow, approve, streamEvents } from "@smthrs/pi-plugin";

​

3) Hybrid: PI Extensibility + Smithers Orchestration

• Keep orchestration in Smithers (<Sequence>, <Parallel>, <Branch>, <Loop>).
• Run adaptive logic in PI tasks (extensions/skills/provider overrides).

1. PI skill-driven coding task inside a Smithers <Task>.
2. PI extension command that starts/resumes Smithers workflows via server API or @smthrs/pi-plugin.
3. Smithers workflow output persisted to SQLite and consumed by later PI-assisted tasks.

​

Hijacking PI Sessions

• Live run: Smithers watches PI’s event stream, waits between blocking tool calls, then hands off the session.
• Finished/cancelled run: Smithers reopens the latest persisted PI session.
• Relaunch uses the stored session ID: pi --session <id>.
• Clean exit resumes the workflow automatically.

• PiAgent defaults noSession to true for one-shot calls.
• For workflow hijack/resume/streaming, Smithers keeps session persistence enabled automatically.
• mode: "json" is not required for hijack support.

​

Setup

1. Install PI CLI and add to PATH.
2. Configure PI credentials via env/config (prefer over CLI args for API keys).
3. Instantiate PiAgent with explicit options in workflows.
4. For server-driven workflows, use @smthrs/pi-plugin.

# Verify PI is installed
pi --version

​

Design Guidance

​

Limitations