Pi Dynamic Workflows

Pi Dynamic Workflows, a new extension for the Pi AI assistant, enables users to run complex, multi-step tasks by having the model write a JavaScript script that distributes work across isolated subagents and synthesizes results. The tool, inspired by Anthropic's Claude Code dynamic workflows, supports codebase audits, multi-perspective reviews, and large refactors, with live progress tracking and cancellation capabilities.

Claude-Code-style dynamic workflows for Pi . A Pi extension that adds a workflow tool. Instead of one assistant doing everything sequentially, the model writes a small JavaScript script that fans out the work across many isolated subagents, then synthesizes the results. Great for codebase audits, multi-perspective review, large refactors, and fan-out research. Inspired by Anthropic's dynamic workflows in Claude Code https://claude.com/blog/introducing-dynamic-workflows-in-claude-code . pi install npm:pi-dynamic-workflows or from a local checkout pi install /path/to/pi-dynamic-workflows Then in Pi: /reload That's it. The extension registers a workflow tool and activates it on session start. Just ask Pi for a workflow in plain language: Run a workflow to inspect this repository and summarize the main modules. The model will write a workflow script and call the workflow tool. Live progress shows up inline: ◆ Workflow: inspect project 3/3 done ✓ Scan 1/1 1 ✓ repo inventory ✓ Analyze 2/2 2 ✓ source modules 3 ✓ final summary Press Esc to cancel a running workflow. Active subagents are aborted and surfaced as skipped. A workflow is plain JavaScript. The first statement must export literal metadata. name and description are required; phases is optional documentation for an expected outline. The live progress view is driven by phase ... calls at runtime: js export const meta = { name: 'inspect project', description: 'Inspect a repository and summarize the main modules', phases: { title: 'Scan' }, { title: 'Analyze' }, , } phase 'Scan' const inventory = await agent 'Inspect the repository structure.', { label: 'repo inventory', } phase 'Analyze' const summary = await agent 'Summarize the main modules from this inventory:\n' + inventory, { label: 'module summary' }, return { inventory, summary } Phases are discovered as the script runs, so conditional and loop-created phases work naturally. If a branch is skipped, its phase does not show up as an empty progress row. Reusable workflow files can opt into editor hints for workflow globals: /// <reference types="pi-dynamic-workflows/workflow" / This declares agent , parallel , pipeline , phase , log , args , cwd , and budget for TypeScript-aware editors. | Global | Description | |---|---| agent prompt, opts | Spawn an isolated subagent. Returns its final text or, with opts.schema , a validated object. | parallel thunks | Run an array of = agent ... thunks concurrently. Results are returned in input order. | pipeline items, ...stages | Run each item through sequential stages while items fan out. Each stage receives prev, original, index . | phase title | Mark the current phase. Used for grouping in the live progress view. | log message | Append a workflow-level log line. | args | Optional JSON value passed in via the tool's args parameter. | cwd , process.cwd | Current working directory for subagents. | budget | { total, spent , remaining } token budget tracker. | Workflow scripts are evaluated inside a Node vm sandbox. The following are intentionally unavailable: Date.now , new Date Math.random require , import , fs , network APIs- spreads, computed keys, template interpolation, function calls inside meta This keeps meta parseable, runs reproducible, and the surface area small. Pass a JSON Schema via opts.schema and the subagent will return a validated object: js const finding = await agent 'Find security-sensitive files.', { label: 'security scan', schema: { type: 'object', properties: { paths: { type: 'array', items: { type: 'string' } }, reason: { type: 'string' }, }, required: 'paths', 'reason' , }, } Under the hood this is a Pi structured output tool with terminate: true , so the subagent ends on that call without an extra assistant turn. user prompt → Pi model writes a workflow script → workflow tool parses + runs script in a vm sandbox → script calls agent , parallel , pipeline → each agent spawns an in-memory Pi subagent session → snapshots stream back as compact progress → final structured result returned to the parent assistant Subagents run in fresh in-memory Pi sessions with the standard coding tools, so they can read files, run shell commands, and call structured output exactly like a normal Pi turn. | File | Purpose | |---|---| src/workflow.ts | AST-validated parser and sandboxed workflow runtime. | src/workflow-tool.ts | The Pi workflow tool, prompt guidelines, rendering, abort handling. | src/agent.ts | WorkflowAgent , an in-memory Pi subagent runner. | src/structured-output.ts | Terminating structured-output tool backed by TypeBox/JSON Schema. | src/display.ts | Workflow snapshots and compact text renderers. | extensions/workflow.ts | The Pi extension entrypoint. | npm install npm test biome check + tsc + unit tests npm run dev Parser unit tests live in tests/workflow-parser.test.ts and cover both accepted and rejected script shapes. This is a prototype. It implements the core workflow primitive script, subagents, parallel/pipeline, phases, abort, structured output but does not yet implement persisted or resumable runs, or a /workflows manager. MIT