jb/pi-interactive-subagents
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adding support for herdr - agents in new tabs

Browse Source
This commit is contained in:
jb
2026-08-26 10:57:45 -04:00
parent c3e8b53c07
commit b3884f6c35
14 changed files with 660 additions and 331 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+18 -12
View File
@@ -1,12 +1,12 @@
# pi-interactive-subagents
Async subagents for [pi](https://github.com/badlogic/pi-mono), running in tmux panes. Spawn a sub-agent, keep working in the main session, and get the result steered back when it finishes. Fully non-blocking.
Async subagents for [pi](https://github.com/badlogic/pi-mono), running in Herdr tabs or tmux panes. Spawn a sub-agent, keep working in the main session, and get the result steered back when it finishes. Fully non-blocking.
**tmux-only fork.** See [Acknowledgements](#acknowledgements) for the upstream project, which also supports cmux, zellij, and WezTerm.
The backend is selected automatically: Herdr is used when Pi runs in a Herdr-managed pane (`HERDR_ENV=1`), otherwise tmux is used when available.
## How it works
`subagent()` returns immediately. The sub-agent runs in its own tmux pane — a right split off the parent pi pane, so pane creation never steals keyboard focus. A live widget above the input tracks every running sub-agent, and when one finishes, its result is steered into the main session as a notification that triggers a new turn.
`subagent()` returns immediately. In Herdr, the sub-agent runs in a new unfocused tab in the current workspace. In tmux, it runs in a right split off the parent Pi pane. A live widget above the input tracks every running sub-agent, and when one finishes, its result is steered into the main session as a notification that triggers a new turn.
```
╭─ Subagents ──────────────────────────── 2 running ─╮
@@ -17,19 +17,19 @@ Async subagents for [pi](https://github.com/badlogic/pi-mono), running in tmux p
Spawn several in parallel — they run concurrently and steer results back independently as each finishes.
Panes are kept evenly sized: the extension re-applies an `even-horizontal` layout after every spawn and exit (debounced). The layout is a single constant, `SUBAGENT_TMUX_LAYOUT` in `pi-extension/subagents/tmux.ts` — change it to any named tmux layout (`main-vertical`, `tiled`, …).
tmux panes are kept evenly sized: the extension re-applies an `even-horizontal` layout after every spawn and exit (debounced). The layout is a single constant, `SUBAGENT_TMUX_LAYOUT` in `pi-extension/subagents/tmux.ts` — change it to any named tmux layout (`main-vertical`, `tiled`, …). Herdr subagents use separate tabs, so they do not resize the parent tab.
If your shell startup is slow and launch commands get dropped before the prompt is ready, raise the delay:
```bash
export PI_SUBAGENT_SHELL_READY_DELAY_MS=2500 # default: 500
export PI_SUBAGENT_SHELL_READY_DELAY_MS=2500 # defaults: Herdr 1000, tmux 500
```
## Tools
| Tool | Description |
| --- | --- |
| `subagent` | Spawn a sub-agent in a dedicated tmux pane (async) |
| `subagent` | Spawn a sub-agent in a dedicated terminal surface (async) |
| `subagent_message` | Message a sub-agent by name — steers it if running, resumes its session if finished |
| `subagents_list` | List available agent definitions |
| `ask_question` | *(sub-agent sessions only)* Ask the orchestrator a question and wait for the reply |
@@ -76,9 +76,9 @@ If the reply arrives while the sub-agent is still mid-turn, it is absorbed into
| Agent | Model | Tools | Role |
| ----- | ----- | ----- | ---- |
| **scout** | `openrouter/z-ai/glm-5.3` | `read`, `grep`, `find`, `ls` | Fast read-only codebase recon |
| **researcher** | `openrouter/z-ai/glm-5.3` | `web_search`, `web_fetch`, `safe_bash` | Web research, synthesized into a sourced brief |
| **worker** | `openrouter/z-ai/glm-5.3` | `read`, `write`, `edit`, `bash`, `web_search`, `web_fetch` + spawning | General implementer; may spawn `scout` and `researcher` |
| **scout** | `openai-codex/gpt-5.6-luna` (`xhigh`) | `read`, `grep`, `find`, `ls` | Fast read-only codebase recon |
| **researcher** | `openai-codex/gpt-5.6-luna` (`xhigh`) | `web_search`, `web_fetch`, `safe_bash` | Web research, synthesized into a sourced brief |
| **worker** | `openai-codex/gpt-5.6-luna` (`xhigh`) | `read`, `write`, `edit`, `bash`, `web_search`, `web_fetch` + spawning | General implementer; may spawn `scout` and `researcher` |
All three are autonomous (`auto-exit: true`) and carry their identity in the system prompt (`system-prompt: append`).
@@ -90,8 +90,8 @@ Place a `.md` file in `.pi/agents/` (project) or `~/.pi/agent/agents/` (global).
---
name: my-agent
description: Does something specific
model: openrouter/z-ai/glm-5.3
thinking: medium
model: openai-codex/gpt-5.6-luna
thinking: xhigh
tools: read, edit, write, safe_bash, web_search
session-mode: lineage-only
auto-exit: true
@@ -178,7 +178,13 @@ Status display is configured via `config.json` in the extension directory (copy
## Requirements
- [pi](https://github.com/badlogic/pi-mono)
- [tmux](https://github.com/tmux/tmux)
- One supported terminal manager:
- [Herdr](https://herdr.dev), with Pi launched inside Herdr
- [tmux](https://github.com/tmux/tmux)
Herdr requires no extension configuration once its Pi integration is installed. The extension detects `HERDR_ENV=1` and creates subagents as unfocused tabs in the current workspace.
For tmux:
```bash
tmux new -A -s pi 'pi'