Frank
02883d3ed2
Copy of the legacy ~/.pi/agent/docs tree rebuilt as the command-center knowledge base: concept files promoted to path identity, index listings stripped of frontmatter, all wikilinks/relative links resolved, every checkable claim verified against the live fleet (Dankserver = Ryzen 7 7700X + RTX 3090; Strix Halo is Dankclaw), unverifiable claims tagged. kb-lint exits 0.
69 lines
2.9 KiB
Markdown
69 lines
2.9 KiB
Markdown
---
|
|
type: reference
|
|
title: Pi Subagents
|
|
description: Core pi extension for delegating tasks to subagents with chains, parallel execution, and TUI clarification.
|
|
tags:
|
|
- pi
|
|
- subagents
|
|
- delegation
|
|
- chains
|
|
- limits
|
|
- unverified
|
|
timestamp: 2026-08-28
|
|
---
|
|
|
|
# Pi Subagents
|
|
|
|
**Package:** `pi-subagents`
|
|
**Version:** 0.36.0
|
|
|
|
Core pi extension for delegating tasks to subagents. Supports sequential chains, parallel execution, and TUI clarification workflows.
|
|
|
|
## Features
|
|
|
|
- **Sequential chains** — Pipeline tasks through multiple subagents
|
|
- **Parallel execution** — Fan out independent tasks simultaneously
|
|
- **TUI clarification** — Interactive preview and editing before execution
|
|
- **Watchdog** — Health monitoring for subagent runs
|
|
- **Model overrides** — Per-agent model selection
|
|
|
|
## Agent Roles
|
|
|
|
| Role | Default Model | Purpose |
|
|
|------|---------------|---------|
|
|
| `scout` | frank-default-small | Quick exploration |
|
|
| `researcher` | frank-default-small | Information gathering |
|
|
| `planner` | frank-default-large | Task planning |
|
|
| `worker` | frank-default-large | Implementation |
|
|
| `reviewer` | frank-default-large | Code/document review |
|
|
| `oracle` | frank-default-large | Complex reasoning |
|
|
| `context-builder` | frank-default-large | Context building |
|
|
|
|
## Parallel Execution and Limits
|
|
|
|
Parallel execution fans out independent tasks. The extension applies several limits to control the load.
|
|
|
|
| Limit | Effective value | Source |
|
|
|-------|-----------------|--------|
|
|
| `globalConcurrencyLimit` | **2** | `extensions/subagent/config.json` |
|
|
| `parallel.maxTasks` | 8 | default |
|
|
| `parallel.concurrency` | 4 | default |
|
|
| `maxSubagentSpawnsPerSession` | unlimited | default |
|
|
| `maxSubagentDepth` | 2 | default |
|
|
| `turnBudget.maxTurns` | 30 | `extensions/subagent/config.json` |
|
|
|
|
`globalConcurrencyLimit` caps the simultaneously-running subagent tasks within one run. The default is 20. The value here is 2. Effective concurrency is the lower of the local cap and the available global slots. Per-step `concurrency` and `parallel.concurrency` still apply. A value below 1 is clamped to 1.
|
|
|
|
Set `globalConcurrencyLimit` in `extensions/subagent/config.json`. The file also configures `artifactDir`, `turnBudget`, and proactive skill suggestions.
|
|
|
|
`maxSubagentSpawnsPerSession` caps the cumulative child launches during one parent session. It counts completed and failed children, parallel task counts, static chain steps, and bounded dynamic fanout children. The default is unlimited. Set the value to `0` to disable a configured cap.
|
|
|
|
`maxSubagentDepth` controls nested delegation. The default is 2. Each agent can tighten the limit for its own child runs. An agent cannot relax a stricter inherited limit.
|
|
|
|
No per-model limit exists. All caps are global to a run or a session. They do not depend on the child model.
|
|
|
|
## See Also
|
|
|
|
- [[settings|settings]] — Subagent configuration
|
|
- [[models|models]] — Model definitions
|