made extension tmux-only, replaced cmux.ts with tmux.ts (~1368 -> 354 lines)

Removed the cmux, zellij, and wezterm backends, the MuxBackend type, the
PI_SUBAGENT_MUX override, and dead exports (renameCurrentTab, renameWorkspace,
sendEscape, isFishShell, exitStatusVar). The ten-function surface API used by
index.ts is unchanged. Integration harness and tests are tmux-only; README and
package.json now state tmux-only with a fork note pointing multi-multiplexer
users at the upstream project.
This commit is contained in:
Amos
2026-08-20 18:48:14 +03:00
parent 865648c4f1
commit 9cbc5b4878
9 changed files with 421 additions and 1848 deletions
+9 -23
View File
@@ -1,6 +1,6 @@
# pi-interactive-subagents # pi-interactive-subagents
Async subagents for [pi](https://github.com/badlogic/pi-mono) — spawn, orchestrate, and manage sub-agent sessions in multiplexer panes. **Fully non-blocking** — the main agent keeps working while subagents run in the background. Async subagents for [pi](https://github.com/badlogic/pi-mono) — spawn, orchestrate, and manage sub-agent sessions in tmux panes. **Fully non-blocking** — the main agent keeps working while subagents run in the background.
## How It Works ## How It Works
@@ -27,13 +27,13 @@ If your shell startup is slow and subagent commands sometimes get dropped before
export PI_SUBAGENT_SHELL_READY_DELAY_MS=2500 export PI_SUBAGENT_SHELL_READY_DELAY_MS=2500
``` ```
Subagent panes are created without stealing keyboard focus (cmux, tmux). Launch commands target child surfaces by explicit ID, so focus and command delivery are independent. Note: the `interactive` option controls parent status notifications, not terminal focus. Subagent panes are created without stealing keyboard focus: splits target the parent pi pane by explicit id, so focus and pane creation are independent. Launch commands target child panes by id as well.
### Pane layout (tmux) ### Pane layout
Under tmux, each subagent is a horizontal split off the parent pi pane. Left to itself, tmux halves the target pane on every split and dumps freed space onto a neighbor on close, so panes drift to wildly uneven widths. To prevent that, the extension automatically re-applies an even layout to the subagent window after every spawn and every exit (debounced so a burst of parallel spawns or staggered exits collapses into a single layout call). This only runs under tmux — cmux uses tabs, and zellij/wezterm manage their own layouts. Each subagent is a horizontal split off the parent pi pane. Left to itself, tmux halves the target pane on every split and dumps freed space onto a neighbor on close, so panes drift to wildly uneven widths. To prevent that, the extension automatically re-applies an even layout to the subagent window after every spawn and every exit (debounced so a burst of parallel spawns or staggered exits collapses into a single layout call).
The layout is a single constant in `pi-extension/subagents/cmux.ts`: The layout is a single constant in `pi-extension/subagents/tmux.ts`:
```ts ```ts
const SUBAGENT_TMUX_LAYOUT = "even-horizontal"; const SUBAGENT_TMUX_LAYOUT = "even-horizontal";
@@ -57,7 +57,7 @@ The value is passed straight to `tmux select-layout`, so any named tmux layout w
| Tool | Description | | Tool | Description |
| ------------------ | ------------------------------------------------------------------------------------------------- | | ------------------ | ------------------------------------------------------------------------------------------------- |
| `subagent` | Spawn a sub-agent in a dedicated multiplexer pane (async — returns immediately) | | `subagent` | Spawn a sub-agent in a dedicated tmux pane (async — returns immediately) |
| `subagent_message` | Steer a running subagent or resume a finished one — by `name` either way | | `subagent_message` | Steer a running subagent or resume a finished one — by `name` either way |
| `subagents_list` | List available agent definitions | | `subagents_list` | List available agent definitions |
@@ -83,7 +83,7 @@ Agent discovery follows priority: **project-local** (`.pi/agents/`) > **global**
``` ```
1. Agent calls subagent() → returns immediately ("started") 1. Agent calls subagent() → returns immediately ("started")
2. Sub-agent runs in mux pane → widget shows live status 2. Sub-agent runs in tmux pane → widget shows live status
3. User keeps chatting → main session fully interactive 3. User keeps chatting → main session fully interactive
4. Sub-agent finishes → result steered back as a normal completion/failure 4. Sub-agent finishes → result steered back as a normal completion/failure
5. Main agent processes result → continues with new context 5. Main agent processes result → continues with new context
@@ -420,33 +420,19 @@ Every sub-agent session displays a compact tools widget showing the agent's allo
## Requirements ## Requirements
- [pi](https://github.com/badlogic/pi-mono) — the coding agent - [pi](https://github.com/badlogic/pi-mono) — the coding agent
- One supported multiplexer:
- [cmux](https://github.com/manaflow-ai/cmux)
- [tmux](https://github.com/tmux/tmux) - [tmux](https://github.com/tmux/tmux)
- [zellij](https://zellij.dev)
- [WezTerm](https://wezfurlong.org/wezterm/)
```bash ```bash
cmux pi
# or
tmux new -A -s pi 'pi' tmux new -A -s pi 'pi'
# or
zellij --session pi # then run: pi
# or
# just run pi inside WezTerm
``` ```
Optional backend override: > This fork is **tmux-only**. It was forked from [HazAT/pi-interactive-subagents](https://github.com/HazAT/pi-interactive-subagents), which also supports cmux, zellij, and WezTerm — look there if you need another multiplexer.
```bash
export PI_SUBAGENT_MUX=cmux # or tmux, zellij, wezterm
```
--- ---
## Acknowledgements ## Acknowledgements
The sub-agent status supervision and turn-only interruption features were inspired by [RepoPrompt](https://repoprompt.com/)'s sub-agent snapshot polling and run cancellation features. Forked from [HazAT/pi-interactive-subagents](https://github.com/HazAT/pi-interactive-subagents), which originated the subagent architecture, the multi-multiplexer surface layer, and the status widget. The sub-agent status supervision and turn-only interruption features were inspired by [RepoPrompt](https://repoprompt.com/)'s sub-agent snapshot polling and run cancellation features.
--- ---
+3 -3
View File
@@ -1,15 +1,15 @@
{ {
"name": "pi-interactive-subagents", "name": "pi-interactive-subagents",
"version": "3.7.2", "version": "3.7.2",
"description": "Interactive subagents for pi - spawn, orchestrate, and manage sub-agent sessions in cmux/tmux/zellij terminals", "description": "Interactive subagents for pi - spawn, orchestrate, and manage sub-agent sessions in tmux",
"keywords": [ "keywords": [
"pi-package" "pi-package"
], ],
"license": "MIT", "license": "MIT",
"author": "HazAT", "author": "Amos Blomqvist",
"repository": { "repository": {
"type": "git", "type": "git",
"url": "https://github.com/HazAT/pi-interactive-subagents" "url": "https://github.com/amosblomqvist/pi-interactive-subagents"
}, },
"type": "module", "type": "module",
"scripts": { "scripts": {
File diff suppressed because it is too large Load Diff
+4 -6
View File
@@ -22,10 +22,9 @@ import {
sendLongCommand, sendLongCommand,
pollForExit, pollForExit,
closeSurface, closeSurface,
getMuxBackend,
shellEscape, shellEscape,
readScreen, readScreen,
} from "./cmux.ts"; } from "./tmux.ts";
import { import {
countSessionEntryLines, countSessionEntryLines,
@@ -509,10 +508,10 @@ function muxUnavailableResult() {
content: [ content: [
{ {
type: "text" as const, type: "text" as const,
text: `Subagents require a supported terminal multiplexer. ${muxSetupHint()}`, text: `Subagents require tmux. ${muxSetupHint()}`,
}, },
], ],
details: { error: "mux not available" }, details: { error: "tmux not available" },
}; };
} }
@@ -1007,10 +1006,9 @@ function steerSubagent(
send(running.surface, flattened); send(running.surface, flattened);
return { ok: true }; return { ok: true };
} catch (error: any) { } catch (error: any) {
const backend = getMuxBackend() ?? "unknown";
return { return {
error: error:
`Failed to deliver message to subagent "${running.name}" via ${backend}: ` + `Failed to deliver message to subagent "${running.name}" via tmux: ` +
`${error?.message ?? String(error)}`, `${error?.message ?? String(error)}`,
}; };
} }
+354
View File
@@ -0,0 +1,354 @@
/**
* tmux surface layer — the only terminal multiplexer this extension supports.
*
* Everything the extension does to a pane goes through the small API in this
* file: create/split a pane, type a command into it, read its screen, close
* it, and poll for exit. Keeping the tmux calls isolated here means index.ts
* stays testable without a multiplexer running.
*
* Panes are identified by tmux pane ids (e.g. `%12`). Splits always target
* the parent pi's pane (`$TMUX_PANE`) so they follow the agent rather than
* the user's focus.
*/
import { execFile, execFileSync } from "node:child_process";
import { promisify } from "node:util";
import { existsSync, readFileSync, rmSync, writeFileSync, mkdirSync } from "node:fs";
import { tmpdir } from "node:os";
import { dirname, join } from "node:path";
const execFileAsync = promisify(execFile);
// ── Availability ──
const commandAvailability = new Map<string, boolean>();
function hasCommand(command: string): boolean {
if (commandAvailability.has(command)) {
return commandAvailability.get(command)!;
}
let available = false;
try {
execFileSync("sh", ["-c", `command -v ${command}`], { stdio: "ignore" });
available = true;
} catch {
available = false;
}
commandAvailability.set(command, available);
return available;
}
/**
* True when running inside tmux with the tmux binary on PATH.
* `TMUX` is set by tmux in every process it spawns (shell or pane).
*/
export function isTmuxAvailable(): boolean {
return !!process.env.TMUX && hasCommand("tmux");
}
export function isMuxAvailable(): boolean {
return isTmuxAvailable();
}
export function muxSetupHint(): string {
return "Start pi inside tmux (`tmux new -A -s pi 'pi'`).";
}
function requireTmux(): void {
if (!isTmuxAvailable()) {
throw new Error(`tmux is required for subagents. ${muxSetupHint()}`);
}
}
// ── Shell helpers ──
export function shellEscape(s: string): string {
return "'" + s.replace(/'/g, "'\\''") + "'";
}
// ── Pane layout ──
/**
* tmux layout applied to the subagent window to keep panes evenly sized.
* Switchable: "even-horizontal" (equal columns, matches Ctrl+b Alt+1),
* "main-vertical" (big main pane + tiled column), "tiled" (grid).
*/
const SUBAGENT_TMUX_LAYOUT = "even-horizontal";
let rebalanceTimer: ReturnType<typeof setTimeout> | null = null;
/**
* Re-balance subagent panes so repeated splits don't leave them lopsided.
* tmux halves the target pane on every split and dumps freed space onto a
* neighbor on close, so without this panes drift to wildly uneven widths.
* Applies SUBAGENT_TMUX_LAYOUT to the parent pi window. Debounced so a burst
* of parallel spawns or staggered exits collapses into a single layout call,
* and non-fatal: a cosmetic resize must never break spawning or watching.
*/
function rebalanceSurfaces(hintPane?: string): void {
// Prefer the parent pi pane (stable; survives a closing subagent pane).
const target = process.env.TMUX_PANE ?? hintPane;
if (!target) return;
if (rebalanceTimer) clearTimeout(rebalanceTimer);
rebalanceTimer = setTimeout(() => {
rebalanceTimer = null;
try {
// -t <pane> resolves to that pane's window; does not change focus.
execFileSync("tmux", ["select-layout", "-t", target, SUBAGENT_TMUX_LAYOUT], {
encoding: "utf8",
});
} catch {
// Pane/window may be gone; balancing is best-effort.
}
}, 120);
}
// ── Surface primitives ──
/**
* Create a new pane for a subagent: a right split off the parent pi's pane,
* so new panes follow the agent rather than the user's focus.
* See https://github.com/HazAT/pi-interactive-subagents/issues/12
*
* Returns the new pane id (e.g. `%12`).
*/
export function createSurface(name: string): string {
void name; // tmux panes are not named; the pi process inside shows its own title.
return createSurfaceSplit(name, "right", process.env.TMUX_PANE);
}
/**
* Create a new split in the given direction from an optional source pane.
* Returns the new pane id (e.g. `%12`).
*/
export function createSurfaceSplit(
name: string,
direction: "left" | "right" | "up" | "down",
fromSurface?: string,
): string {
void name;
requireTmux();
const args = ["split-window", "-d"];
if (direction === "left" || direction === "right") {
args.push("-h");
} else {
args.push("-v");
}
if (direction === "left" || direction === "up") {
args.push("-b");
}
if (fromSurface) {
args.push("-t", fromSurface);
}
args.push("-P", "-F", "#{pane_id}");
const pane = execFileSync("tmux", args, { encoding: "utf8" }).trim();
if (!pane.startsWith("%")) {
throw new Error(`Unexpected tmux split-window output: ${pane}`);
}
rebalanceSurfaces(pane);
return pane;
}
/**
* Send a command string to a pane and execute it.
* Typed literally (`-l`) so special characters are not interpreted as keys,
* then submitted with Enter.
*/
export function sendCommand(surface: string, command: string): void {
requireTmux();
execFileSync("tmux", ["send-keys", "-t", surface, "-l", command], { encoding: "utf8" });
execFileSync("tmux", ["send-keys", "-t", surface, "Enter"], { encoding: "utf8" });
}
/**
* Send a long command to a pane by writing it to a script file first.
* This avoids terminal line-wrapping issues that break commands exceeding the
* pane's column width when sent character-by-character via sendCommand.
*
* By default the script is written to a temp directory, but callers can pass a
* stable path (for example under session artifacts) so the exact invocation is
* preserved for debugging.
*
* Returns the script path.
*/
export function sendLongCommand(
surface: string,
command: string,
options?: { scriptPath?: string; scriptPreamble?: string },
): string {
const scriptPath =
options?.scriptPath ??
join(
tmpdir(),
"pi-subagent-scripts",
`cmd-${Date.now()}-${Math.random().toString(16).slice(2, 8)}.sh`,
);
mkdirSync(dirname(scriptPath), { recursive: true });
const scriptParts = ["#!/bin/bash"];
if (options?.scriptPreamble) {
scriptParts.push(options.scriptPreamble.trimEnd());
}
scriptParts.push(command);
writeFileSync(scriptPath, scriptParts.join("\n") + "\n", {
mode: 0o755,
});
sendCommand(surface, `bash ${shellEscape(scriptPath)}`);
return scriptPath;
}
/**
* Read the screen contents of a pane (sync).
*/
export function readScreen(surface: string, lines = 50): string {
requireTmux();
return execFileSync(
"tmux",
["capture-pane", "-p", "-t", surface, "-S", `-${Math.max(1, lines)}`],
{
encoding: "utf8",
},
);
}
/**
* Read the screen contents of a pane (async).
*/
export async function readScreenAsync(surface: string, lines = 50): Promise<string> {
requireTmux();
const { stdout } = await execFileAsync(
"tmux",
["capture-pane", "-p", "-t", surface, "-S", `-${Math.max(1, lines)}`],
{ encoding: "utf8" },
);
return stdout;
}
/**
* Close a pane.
*/
export function closeSurface(surface: string): void {
requireTmux();
execFileSync("tmux", ["kill-pane", "-t", surface], { encoding: "utf8" });
rebalanceSurfaces();
}
// ── Exit polling ──
export interface PollResult {
/** How the subagent exited */
reason: "done" | "sentinel" | "error";
/** Shell exit code (from sentinel). 0 for file-based exits. */
exitCode: number;
/** Error message if reason is "error" (auto-retry exhausted, provider overload, etc.) */
errorMessage?: string;
}
/**
* Interpret an `.exit` sidecar payload (written by the error path in
* subagent-done.ts). Centralized so both the fast and slow paths in
* pollForExit decode the payload the same way. Clean completions write no
* sidecar and are detected via the terminal sentinel instead.
*
* Note: ask_question does NOT write a `.exit` sidecar — it keeps the session
* open and signals the parent via a separate `.ask` file (see deliverPendingQuestion).
*/
function interpretExitSidecar(data: any): PollResult {
if (data?.type === "error") {
const errorMessage =
typeof data.errorMessage === "string" && data.errorMessage.trim() !== ""
? data.errorMessage
: "Subagent exited with stopReason=error (no errorMessage in sidecar).";
return { reason: "error", exitCode: 1, errorMessage };
}
return { reason: "done", exitCode: 0 };
}
export const __pollForExitTest__ = { interpretExitSidecar };
/**
* Poll until the subagent exits. Checks for a `.exit` sidecar file first
* (written by the error path), falling back to the terminal sentinel for
* clean-completion and crash detection.
*/
export async function pollForExit(
surface: string,
signal: AbortSignal,
options: {
interval: number;
sessionFile?: string;
sentinelFile?: string;
onTick?: (elapsed: number) => void;
},
): Promise<PollResult> {
const start = Date.now();
for (;;) {
if (signal.aborted) {
throw new Error("Aborted while waiting for subagent to finish");
}
// Fast path: check for .exit sidecar file (written by the error path)
if (options.sessionFile) {
try {
const exitFile = `${options.sessionFile}.exit`;
if (existsSync(exitFile)) {
const data = JSON.parse(readFileSync(exitFile, "utf-8"));
rmSync(exitFile, { force: true });
return interpretExitSidecar(data);
}
} catch {}
}
// Check Claude sentinel file (written by plugin Stop hook)
if (options.sentinelFile) {
try {
if (existsSync(options.sentinelFile)) {
return { reason: "sentinel", exitCode: 0 };
}
} catch {}
}
// Slow path: read terminal screen for sentinel (crash detection)
try {
const screen = await readScreenAsync(surface, 5);
const match = screen.match(/__SUBAGENT_DONE_(\d+)__/);
if (match) {
return { reason: "sentinel", exitCode: parseInt(match[1], 10) };
}
} catch {
// Surface may have been destroyed — check if .exit file appeared in the meantime
if (options.sessionFile) {
try {
const exitFile = `${options.sessionFile}.exit`;
if (existsSync(exitFile)) {
const data = JSON.parse(readFileSync(exitFile, "utf-8"));
rmSync(exitFile, { force: true });
return interpretExitSidecar(data);
}
} catch {}
}
}
const elapsed = Math.floor((Date.now() - start) / 1000);
options.onTick?.(elapsed);
await new Promise<void>((resolve, reject) => {
if (signal.aborted) return reject(new Error("Aborted"));
const timer = setTimeout(() => {
signal.removeEventListener("abort", onAbort);
resolve();
}, options.interval);
function onAbort() {
clearTimeout(timer);
reject(new Error("Aborted"));
}
signal.addEventListener("abort", onAbort, { once: true });
});
}
}
+18 -83
View File
@@ -2,11 +2,11 @@
* Integration test harness for pi-interactive-subagents. * Integration test harness for pi-interactive-subagents.
* *
* Provides utilities to: * Provides utilities to:
* - Detect available mux backends (cmux, tmux, zellij) * - Detect whether tmux is available
* - Create isolated test environments with test agent definitions * - Create isolated test environments with test agent definitions
* - Start real pi sessions in mux surfaces * - Start real pi sessions in tmux panes
* - Poll for file creation and screen output * - Poll for file creation and screen output
* - Clean up surfaces and temp files after tests * - Clean up panes and temp files after tests
*/ */
import { execFileSync } from "node:child_process"; import { execFileSync } from "node:child_process";
import { import {
@@ -23,7 +23,7 @@ import { join, resolve, dirname } from "node:path";
import { fileURLToPath } from "node:url"; import { fileURLToPath } from "node:url";
import { tmpdir } from "node:os"; import { tmpdir } from "node:os";
import { import {
getMuxBackend, isMuxAvailable,
createSurface, createSurface,
createSurfaceSplit, createSurfaceSplit,
sendCommand, sendCommand,
@@ -31,14 +31,10 @@ import {
readScreen, readScreen,
readScreenAsync, readScreenAsync,
closeSurface, closeSurface,
sendEscape,
shellEscape, shellEscape,
parseCmuxFocusedSnapshotFromJson, } from "../../pi-extension/subagents/tmux.ts";
parseCmuxPaneRefForSurfaceFromJson,
type MuxBackend,
} from "../../pi-extension/subagents/cmux.ts";
// Re-export mux primitives for tests // Re-export tmux primitives for tests
export { export {
createSurface, createSurface,
createSurfaceSplit, createSurfaceSplit,
@@ -47,10 +43,8 @@ export {
readScreen, readScreen,
readScreenAsync, readScreenAsync,
closeSurface, closeSurface,
sendEscape,
shellEscape, shellEscape,
}; };
export type { MuxBackend };
// ── Paths ── // ── Paths ──
@@ -82,60 +76,18 @@ export const PI_TIMEOUT = Number(process.env.PI_TEST_TIMEOUT ?? "120000");
// ── Backend detection ── // ── Backend detection ──
/** /**
* Detect which mux backends are actually available in the current environment. * Detect whether tmux is available in the current environment.
* Temporarily sets PI_SUBAGENT_MUX to probe each backend. * Returns ["tmux"] or [].
*/ */
export function getAvailableBackends(): MuxBackend[] { export function getAvailableBackends(): string[] {
const backends: MuxBackend[] = []; return isMuxAvailable() ? ["tmux"] : [];
const orig = process.env.PI_SUBAGENT_MUX;
for (const backend of ["cmux", "tmux", "zellij"] as MuxBackend[]) {
process.env.PI_SUBAGENT_MUX = backend;
try {
if (getMuxBackend() === backend) backends.push(backend);
} catch {}
} }
if (orig === undefined) delete process.env.PI_SUBAGENT_MUX; export function focusSurface(surface: string): void {
else process.env.PI_SUBAGENT_MUX = orig;
return backends;
}
export function setBackend(backend: MuxBackend): string | undefined {
const prev = process.env.PI_SUBAGENT_MUX;
process.env.PI_SUBAGENT_MUX = backend;
return prev;
}
export function restoreBackend(prev: string | undefined): void {
if (prev === undefined) delete process.env.PI_SUBAGENT_MUX;
else process.env.PI_SUBAGENT_MUX = prev;
}
export function focusSurface(backend: MuxBackend, surface: string): void {
if (backend === "cmux") {
const pane = getSurfacePane(backend, surface);
if (pane) execFileSync("cmux", ["focus-pane", "--pane", pane], { encoding: "utf8" });
execFileSync("cmux", ["focus-panel", "--panel", surface], { encoding: "utf8" });
return;
}
if (backend === "tmux") {
execFileSync("tmux", ["select-pane", "-t", surface], { encoding: "utf8" }); execFileSync("tmux", ["select-pane", "-t", surface], { encoding: "utf8" });
return;
} }
throw new Error(`Focus helpers are not implemented for ${backend}`); export function getFocusedSurface(): string | null {
}
export function getFocusedSurface(backend: MuxBackend): string | null {
if (backend === "cmux") {
const info = execFileSync("cmux", ["identify", "--json"], { encoding: "utf8" });
return parseCmuxFocusedSnapshotFromJson(info)?.surfaceRef ?? null;
}
if (backend === "tmux") {
try { try {
const panes = execFileSync("tmux", ["list-panes", "-F", "#{pane_id} #{pane_active}"], { const panes = execFileSync("tmux", ["list-panes", "-F", "#{pane_id} #{pane_active}"], {
encoding: "utf8", encoding: "utf8",
@@ -147,34 +99,19 @@ export function getFocusedSurface(backend: MuxBackend): string | null {
} }
} }
throw new Error(`Focus helpers are not implemented for ${backend}`);
}
export function getSurfacePane(backend: MuxBackend, surface: string): string | null {
if (backend === "cmux") {
const info = execFileSync("cmux", ["identify", "--surface", surface], { encoding: "utf8" });
return parseCmuxPaneRefForSurfaceFromJson(info, surface);
}
if (backend === "tmux") return surface;
throw new Error(`Pane lookup is not implemented for ${backend}`);
}
export async function waitForFocusedSurface( export async function waitForFocusedSurface(
backend: MuxBackend,
surface: string, surface: string,
timeout: number = PI_TIMEOUT, timeout: number = PI_TIMEOUT,
): Promise<void> { ): Promise<void> {
const start = Date.now(); const start = Date.now();
while (Date.now() - start < timeout) { while (Date.now() - start < timeout) {
if (getFocusedSurface(backend) === surface) return; if (getFocusedSurface() === surface) return;
await sleep(200); await sleep(200);
} }
throw new Error( throw new Error(
`Timeout (${timeout}ms) waiting for focused ${backend} surface ${surface}; ` + `Timeout (${timeout}ms) waiting for focused tmux pane ${surface}; ` +
`current focus is ${getFocusedSurface(backend) ?? "unknown"}`, `current focus is ${getFocusedSurface() ?? "unknown"}`,
); );
} }
@@ -183,9 +120,7 @@ export async function waitForFocusedSurface(
export interface TestEnv { export interface TestEnv {
/** Temp directory serving as the test project root */ /** Temp directory serving as the test project root */
dir: string; dir: string;
/** Active mux backend for this test run */ /** Panes created during the test (cleaned up automatically) */
backend: MuxBackend;
/** Surfaces created during the test (cleaned up automatically) */
surfaces: string[]; surfaces: string[];
/** Temp files to clean up */ /** Temp files to clean up */
tempFiles: string[]; tempFiles: string[];
@@ -195,7 +130,7 @@ export interface TestEnv {
* Create an isolated test environment with test agent definitions. * Create an isolated test environment with test agent definitions.
* The temp dir has `.pi/agents/` containing copies of all test agents. * The temp dir has `.pi/agents/` containing copies of all test agents.
*/ */
export function createTestEnv(backend: MuxBackend): TestEnv { export function createTestEnv(): TestEnv {
const dir = mkdtempSync(join(tmpdir(), "pi-integ-")); const dir = mkdtempSync(join(tmpdir(), "pi-integ-"));
const agentsDir = join(dir, ".pi", "agents"); const agentsDir = join(dir, ".pi", "agents");
mkdirSync(agentsDir, { recursive: true }); mkdirSync(agentsDir, { recursive: true });
@@ -209,7 +144,7 @@ export function createTestEnv(backend: MuxBackend): TestEnv {
} }
} }
return { dir, backend, surfaces: [], tempFiles: [] }; return { dir, surfaces: [], tempFiles: [] };
} }
/** /**
+5 -11
View File
@@ -2,14 +2,13 @@
* Integration tests for the full subagent lifecycle. * Integration tests for the full subagent lifecycle.
* *
* These tests spawn REAL pi sessions with REAL LLM calls (haiku by default). * These tests spawn REAL pi sessions with REAL LLM calls (haiku by default).
* Each test creates a mux surface, runs pi with a task that uses the subagent * Each test creates a tmux pane, runs pi with a task that uses the subagent
* tool, and verifies the outcome via marker files and screen output. * tool, and verifies the outcome via marker files and screen output.
* *
* Costs: ~$0.01-0.05 per test run (haiku). * Costs: ~$0.01-0.05 per test run (haiku).
* Duration: ~30-90s per test. * Duration: ~30-90s per test.
* *
* Run inside a supported multiplexer: * Run inside tmux:
* cmux bash -c 'npm run test:integration'
* tmux new 'npm run test:integration' * tmux new 'npm run test:integration'
* *
* Configuration: * Configuration:
@@ -21,8 +20,6 @@ import assert from "node:assert/strict";
import { existsSync, readFileSync, unlinkSync } from "node:fs"; import { existsSync, readFileSync, unlinkSync } from "node:fs";
import { import {
getAvailableBackends, getAvailableBackends,
setBackend,
restoreBackend,
createTestEnv, createTestEnv,
cleanupTestEnv, cleanupTestEnv,
createTrackedSurface, createTrackedSurface,
@@ -40,23 +37,20 @@ import {
const backends = getAvailableBackends(); const backends = getAvailableBackends();
if (backends.length === 0) { if (backends.length === 0) {
console.log("⚠️ No mux backend available — skipping subagent lifecycle integration tests"); console.log("⚠️ tmux is not available — skipping subagent lifecycle integration tests");
console.log(" Run inside cmux or tmux to enable these tests."); console.log(" Run inside tmux to enable these tests.");
} }
for (const backend of backends) { for (const backend of backends) {
describe(`subagent-lifecycle [${backend}]`, { timeout: PI_TIMEOUT * 3 }, () => { describe(`subagent-lifecycle [${backend}]`, { timeout: PI_TIMEOUT * 3 }, () => {
let prevMux: string | undefined;
let env: TestEnv; let env: TestEnv;
before(() => { before(() => {
prevMux = setBackend(backend); env = createTestEnv();
env = createTestEnv(backend);
}); });
after(() => { after(() => {
cleanupTestEnv(env); cleanupTestEnv(env);
restoreBackend(prevMux);
}); });
// ── Basic spawn + completion ── // ── Basic spawn + completion ──
@@ -1,29 +1,24 @@
/** /**
* Integration tests for the multiplexer surface layer. * Integration tests for the tmux surface layer.
* *
* These tests exercise real mux operations: creating panes, * These tests exercise real tmux operations: creating panes,
* sending commands, reading screen output, and closing surfaces. * sending commands, reading screen output, and closing panes.
* No LLM calls — fast and free. * No LLM calls — fast and free.
* *
* Run inside a supported multiplexer: * Run inside tmux:
* cmux bash -c 'npm run test:integration'
* tmux new 'npm run test:integration' * tmux new 'npm run test:integration'
* zellij --session pi # then run: npm run test:integration
*/ */
import { describe, it, before, after } from "node:test"; import { describe, it, before, after } from "node:test";
import assert from "node:assert/strict"; import assert from "node:assert/strict";
import { unlinkSync } from "node:fs"; import { unlinkSync } from "node:fs";
import { import {
getAvailableBackends, getAvailableBackends,
setBackend,
restoreBackend,
createTestEnv, createTestEnv,
cleanupTestEnv, cleanupTestEnv,
createTrackedSurface, createTrackedSurface,
createTrackedSurfaceSplit, createTrackedSurfaceSplit,
focusSurface, focusSurface,
getFocusedSurface, getFocusedSurface,
getSurfacePane,
waitForFocusedSurface, waitForFocusedSurface,
untrackSurface, untrackSurface,
sendCommand, sendCommand,
@@ -31,7 +26,6 @@ import {
readScreen, readScreen,
readScreenAsync, readScreenAsync,
closeSurface, closeSurface,
sendEscape,
sleep, sleep,
uniqueId, uniqueId,
trackTempFile, trackTempFile,
@@ -44,47 +38,36 @@ const backends = getAvailableBackends();
const FOCUS_TEST_SHELL_READY_DELAY_MS = Number(process.env.PI_SUBAGENT_SHELL_READY_DELAY_MS ?? "2500"); const FOCUS_TEST_SHELL_READY_DELAY_MS = Number(process.env.PI_SUBAGENT_SHELL_READY_DELAY_MS ?? "2500");
if (backends.length === 0) { if (backends.length === 0) {
console.log("⚠️ No mux backend available — skipping mux-surface integration tests"); console.log("⚠️ tmux is not available — skipping tmux-surface integration tests");
console.log(" Run inside cmux or tmux to enable these tests."); console.log(" Run inside tmux to enable these tests.");
} }
for (const backend of backends) { for (const backend of backends) {
describe(`mux-surface [${backend}]`, { timeout: 60_000 }, () => { describe(`tmux-surface [${backend}]`, { timeout: 60_000 }, () => {
let prevMux: string | undefined;
let env: TestEnv; let env: TestEnv;
before(() => { before(() => {
prevMux = setBackend(backend); env = createTestEnv();
env = createTestEnv(backend);
}); });
after(() => { after(() => {
cleanupTestEnv(env); cleanupTestEnv(env);
restoreBackend(prevMux);
}); });
it("keeps focus on the active surface while creating and targeting subagent surfaces", async () => { it("keeps focus on the active surface while creating and targeting subagent surfaces", async () => {
const anchor = createTrackedSurfaceSplit(env, "focus-anchor", "right"); const anchor = createTrackedSurfaceSplit(env, "focus-anchor", "right");
await sleep(1000); await sleep(1000);
focusSurface(backend, anchor); focusSurface(anchor);
await waitForFocusedSurface(backend, anchor, 10_000); await waitForFocusedSurface(anchor, 10_000);
const childA = createTrackedSurface(env, "focus-child-a"); const childA = createTrackedSurface(env, "focus-child-a");
await sleep(FOCUS_TEST_SHELL_READY_DELAY_MS); await sleep(FOCUS_TEST_SHELL_READY_DELAY_MS);
assert.equal(getFocusedSurface(backend), anchor); assert.equal(getFocusedSurface(), anchor);
const childB = createTrackedSurface(env, "focus-child-b"); const childB = createTrackedSurface(env, "focus-child-b");
await sleep(FOCUS_TEST_SHELL_READY_DELAY_MS); await sleep(FOCUS_TEST_SHELL_READY_DELAY_MS);
assert.equal(getFocusedSurface(backend), anchor); assert.equal(getFocusedSurface(), anchor);
if (backend === "cmux") {
const paneA = getSurfacePane(backend, childA);
const paneB = getSurfacePane(backend, childB);
assert.ok(paneA, `Expected pane ref for ${childA}`);
assert.ok(paneB, `Expected pane ref for ${childB}`);
assert.equal(paneB, paneA);
}
const markerA = uniqueId(); const markerA = uniqueId();
const markerB = uniqueId(); const markerB = uniqueId();
@@ -95,7 +78,7 @@ for (const backend of backends) {
waitForScreen(childA, new RegExp(`FOCUS_A_${markerA}`), 20_000, 50), waitForScreen(childA, new RegExp(`FOCUS_A_${markerA}`), 20_000, 50),
waitForScreen(childB, new RegExp(`FOCUS_B_${markerB}`), 20_000, 50), waitForScreen(childB, new RegExp(`FOCUS_B_${markerB}`), 20_000, 50),
]); ]);
assert.equal(getFocusedSurface(backend), anchor); assert.equal(getFocusedSurface(), anchor);
}); });
it("creates a surface, sends a command, reads output, and closes it", async () => { it("creates a surface, sends a command, reads output, and closes it", async () => {
@@ -197,7 +180,7 @@ for (const backend of backends) {
await sleep(1000); await sleep(1000);
const marker = uniqueId(); const marker = uniqueId();
const filePath = `/tmp/pi-mux-test-${marker}.txt`; const filePath = `/tmp/pi-tmux-test-${marker}.txt`;
sendCommand(surface, `echo "FILE_${marker}" > ${filePath} && echo "WRITTEN_${marker}"`); sendCommand(surface, `echo "FILE_${marker}" > ${filePath} && echo "WRITTEN_${marker}"`);
@@ -210,34 +193,5 @@ for (const backend of backends) {
unlinkSync(filePath); unlinkSync(filePath);
} catch {} } catch {}
}); });
it("delivers Escape as byte 27 to the target surface", async () => {
const surface = createTrackedSurface(env, "escape-byte-test");
await sleep(1000);
const marker = uniqueId();
const byteFile = `/tmp/pi-mux-escape-${marker}.txt`;
trackTempFile(env, byteFile);
const nodeProgram =
"const fs = require('node:fs');" +
"if (!process.stdin.isTTY) throw new Error('stdin is not a TTY');" +
"process.stdin.setRawMode(true);" +
"process.stdin.resume();" +
"process.stdout.write('ESC_READY\\n');" +
"process.stdin.once('data', (chunk) => {" +
`fs.writeFileSync(${JSON.stringify(byteFile)}, Array.from(chunk).join(','));` +
"process.exit(0);" +
"});";
const command = `node -e ${JSON.stringify(nodeProgram)}`;
sendLongCommand(surface, command);
await waitForScreen(surface, /ESC_READY/, 15_000, 50);
sendEscape(surface);
const content = await waitForFile(byteFile, 15_000, /^27$/);
assert.equal(content.trim(), "27");
});
}); });
} }
+4 -284
View File
@@ -30,20 +30,7 @@ import {
summarizeSessionStats, summarizeSessionStats,
} from "../pi-extension/subagents/session.ts"; } from "../pi-extension/subagents/session.ts";
import { import { shellEscape } from "../pi-extension/subagents/tmux.ts";
shellEscape,
isCmuxAvailable,
isWezTermAvailable,
parseCmuxFocusedSnapshot,
parseCmuxFocusedSnapshotFromJson,
parseCmuxJson,
parseCmuxPaneRefForSurface,
parseCmuxPaneRefForSurfaceFromJson,
canSplitZellijPane,
predictZellijSplitDirection,
selectZellijPlacement,
selectZellijStackPlacement,
} from "../pi-extension/subagents/cmux.ts";
import { import {
advanceStatusState, advanceStatusState,
capStatusLines, capStatusLines,
@@ -69,7 +56,7 @@ import {
runningChildrenCount, runningChildrenCount,
} from "../pi-extension/subagents/subagent-done.ts"; } from "../pi-extension/subagents/subagent-done.ts";
import subagentDoneExtension from "../pi-extension/subagents/subagent-done.ts"; import subagentDoneExtension from "../pi-extension/subagents/subagent-done.ts";
import { __pollForExitTest__ } from "../pi-extension/subagents/cmux.ts"; import { __pollForExitTest__ } from "../pi-extension/subagents/tmux.ts";
// --- Helpers --- // --- Helpers ---
@@ -1754,7 +1741,7 @@ describe("subagent-done.ts", () => {
}); });
}); });
describe("cmux.ts interpretExitSidecar", () => { describe("tmux.ts interpretExitSidecar", () => {
const { interpretExitSidecar } = __pollForExitTest__; const { interpretExitSidecar } = __pollForExitTest__;
it("no longer decodes ping payloads (ask_question keeps the session open instead)", () => { it("no longer decodes ping payloads (ask_question keeps the session open instead)", () => {
@@ -2665,7 +2652,7 @@ describe("subagent display helpers", () => {
}); });
}); });
describe("cmux.ts", () => { describe("tmux.ts", () => {
describe("shellEscape", () => { describe("shellEscape", () => {
it("wraps in single quotes", () => { it("wraps in single quotes", () => {
assert.equal(shellEscape("hello"), "'hello'"); assert.equal(shellEscape("hello"), "'hello'");
@@ -2688,271 +2675,4 @@ describe("cmux.ts", () => {
assert.ok(escaped.includes("$world")); assert.ok(escaped.includes("$world"));
}); });
}); });
describe("parseCmuxFocusedSnapshot", () => {
it("parses focused surface and pane refs", () => {
assert.deepEqual(
parseCmuxFocusedSnapshot({ focused: { surface_ref: "surface:3", pane_ref: "pane:2" } }),
{ surfaceRef: "surface:3", paneRef: "pane:2" },
);
});
it("does not fall back to caller refs", () => {
assert.equal(
parseCmuxFocusedSnapshot({ caller: { surface_ref: "surface:1", pane_ref: "pane:1" } }),
null,
);
});
it("returns null for malformed values", () => {
assert.equal(parseCmuxFocusedSnapshot(null), null);
assert.equal(parseCmuxFocusedSnapshot({ focused: {} }), null);
});
});
describe("parseCmuxJson", () => {
it("returns null for malformed JSON text", () => {
assert.equal(parseCmuxJson("not json"), null);
});
it("parses valid JSON text", () => {
assert.deepEqual(parseCmuxJson('{"ok":true}'), { ok: true });
});
});
describe("parseCmuxFocusedSnapshotFromJson", () => {
it("returns null for malformed JSON text", () => {
assert.equal(parseCmuxFocusedSnapshotFromJson("not json"), null);
});
it("returns null when focused is absent or not an object", () => {
assert.equal(
parseCmuxFocusedSnapshotFromJson('{"focused":null,"caller":{"surface_ref":"surface:1","pane_ref":"pane:1"}}'),
null,
);
assert.equal(
parseCmuxFocusedSnapshotFromJson('{"caller":{"surface_ref":"surface:1","pane_ref":"pane:1"}}'),
null,
);
});
it("parses focused refs without falling back to caller refs", () => {
assert.deepEqual(
parseCmuxFocusedSnapshotFromJson(
'{"caller":{"surface_ref":"surface:1","pane_ref":"pane:1"},"focused":{"surface_ref":"surface:2","pane_ref":"pane:3"}}',
),
{ surfaceRef: "surface:2", paneRef: "pane:3" },
);
});
});
describe("parseCmuxPaneRefForSurface", () => {
it("parses top-level pane refs for a surface", () => {
assert.equal(
parseCmuxPaneRefForSurface({ surface_ref: "surface:7", pane_ref: "pane:4" }, "surface:7"),
"pane:4",
);
});
it("parses caller pane refs for identify --surface output", () => {
assert.equal(
parseCmuxPaneRefForSurface(
{ caller: { surface_ref: "surface:7", pane_ref: "pane:4" } },
"surface:7",
),
"pane:4",
);
});
it("returns null when the surface does not match", () => {
assert.equal(
parseCmuxPaneRefForSurface({ surface_ref: "surface:8", pane_ref: "pane:4" }, "surface:7"),
null,
);
});
});
describe("parseCmuxPaneRefForSurfaceFromJson", () => {
it("returns null for malformed JSON text", () => {
assert.equal(parseCmuxPaneRefForSurfaceFromJson("not json", "surface:7"), null);
});
it("parses caller refs from cmux identify --surface JSON text", () => {
assert.equal(
parseCmuxPaneRefForSurfaceFromJson(
'{"caller":{"surface_ref":"surface:7","pane_ref":"pane:4"}}',
"surface:7",
),
"pane:4",
);
});
});
describe("zellij placement", () => {
const pane = (overrides: any) => ({
id: 1,
is_plugin: false,
is_floating: false,
is_selectable: true,
exited: false,
pane_rows: 20,
pane_columns: 80,
tab_id: 1,
...overrides,
});
it("matches Zellij direction and minimum split rules", () => {
assert.equal(predictZellijSplitDirection(pane({ pane_rows: 5, pane_columns: 11 })), "right");
assert.equal(predictZellijSplitDirection(pane({ pane_rows: 11, pane_columns: 5 })), "down");
assert.equal(predictZellijSplitDirection(pane({ pane_rows: 5, pane_columns: 10 })), null);
assert.equal(predictZellijSplitDirection(pane({ pane_rows: 4, pane_columns: 80 })), null);
assert.equal(canSplitZellijPane(pane({ pane_rows: 5, pane_columns: 11 })), true);
assert.equal(canSplitZellijPane(pane({ pane_rows: 11, pane_columns: 5 })), true);
assert.equal(canSplitZellijPane(pane({ pane_rows: 5, pane_columns: 10 })), false);
assert.equal(canSplitZellijPane(pane({ pane_rows: 4, pane_columns: 80 })), false);
assert.equal(canSplitZellijPane(pane({ pane_rows: 30, pane_columns: 100 }), 80, 20), false);
assert.equal(canSplitZellijPane(pane({ pane_rows: 45, pane_columns: 100 }), 80, 20), true);
assert.equal(canSplitZellijPane(pane({ pane_rows: 30, pane_columns: 170 }), 80, 20), true);
assert.equal(canSplitZellijPane(pane({ pane_rows: 31, pane_columns: 47 }), 50, 10), false);
assert.equal(canSplitZellijPane(pane({ pane_rows: 31, pane_columns: 77 }), 50, 10), true);
});
it("uses tab-scoped split only when all Zellij split candidates are safe", () => {
const plan = selectZellijPlacement(
[
pane({ id: 10, tab_id: 1, pane_rows: 40, pane_columns: 120 }),
pane({ id: 11, tab_id: 1, pane_rows: 120, pane_columns: 100 }),
pane({ id: 12, tab_id: 2, pane_rows: 60, pane_columns: 200 }),
],
10,
);
assert.deepEqual(plan, {
mode: "split",
anchorPaneId: 11,
targetPaneId: 11,
tabId: 1,
splitDirection: "down",
});
});
it("stacks when any Zellij split candidate would fall below Pi's configured minimum", () => {
const plan = selectZellijPlacement(
[
pane({ id: 10, tab_id: 1, pane_rows: 100, pane_columns: 47 }),
pane({ id: 11, tab_id: 1, pane_rows: 31, pane_columns: 77 }),
],
10,
50,
10,
);
assert.deepEqual(plan, {
mode: "stack",
anchorPaneId: 11,
targetPaneId: 11,
tabId: 1,
});
});
it("stacks when Zellij would split a pane below Pi's usable minimum", () => {
const plan = selectZellijPlacement(
[
pane({ id: 10, tab_id: 1, pane_rows: 20, pane_columns: 20 }),
pane({ id: 11, tab_id: 1, pane_rows: 18, pane_columns: 60 }),
pane({ id: 12, tab_id: 1, pane_rows: 10, pane_columns: 70 }),
],
10,
);
assert.deepEqual(plan, {
mode: "stack",
anchorPaneId: 11,
targetPaneId: 11,
tabId: 1,
});
});
it("never chooses the parent pane as the stack target", () => {
const plan = selectZellijStackPlacement(
[
pane({ id: 10, tab_id: 1, pane_rows: 60, pane_columns: 200 }),
pane({ id: 11, tab_id: 1, pane_rows: 10, pane_columns: 20 }),
pane({ id: 12, tab_id: 1, pane_rows: 8, pane_columns: 30 }),
],
10,
);
assert.deepEqual(plan, {
mode: "stack",
anchorPaneId: 12,
targetPaneId: 12,
tabId: 1,
});
});
it("does not stack when the only usable pane is the parent", () => {
const plan = selectZellijStackPlacement(
[pane({ id: 10, tab_id: 1, pane_rows: 60, pane_columns: 200 })],
10,
);
assert.equal(plan, null);
});
it("stacks on the largest usable non-parent pane when none can split", () => {
const plan = selectZellijPlacement(
[
pane({ id: 10, tab_id: 1, pane_rows: 5, pane_columns: 10 }),
pane({ id: 11, tab_id: 1, pane_rows: 6, pane_columns: 8 }),
pane({ id: 12, tab_id: 2, pane_rows: 60, pane_columns: 200 }),
],
10,
);
assert.deepEqual(plan, {
mode: "stack",
anchorPaneId: 11,
targetPaneId: 11,
tabId: 1,
});
});
it("ignores floating, plugin, exited, unselectable, and other-tab panes", () => {
const plan = selectZellijPlacement(
[
pane({ id: 10, tab_id: 1, pane_rows: 5, pane_columns: 10 }),
pane({ id: 11, tab_id: 1, pane_rows: 60, pane_columns: 200, is_floating: true }),
pane({ id: 12, tab_id: 1, pane_rows: 60, pane_columns: 200, is_plugin: true }),
pane({ id: 13, tab_id: 1, pane_rows: 60, pane_columns: 200, exited: true }),
pane({ id: 14, tab_id: 1, pane_rows: 60, pane_columns: 200, is_selectable: false }),
pane({ id: 15, tab_id: 2, pane_rows: 60, pane_columns: 200 }),
],
10,
);
assert.equal(plan, null);
});
it("returns null when the parent pane cannot be found", () => {
assert.equal(selectZellijPlacement([pane({ id: 10 })], 99), null);
});
});
describe("isCmuxAvailable", () => {
it("returns boolean based on CMUX_SOCKET_PATH", () => {
// Can't easily mock env in node:test, just verify it returns a boolean
const result = isCmuxAvailable();
assert.equal(typeof result, "boolean");
});
});
describe("isWezTermAvailable", () => {
it("returns boolean based on WEZTERM_UNIX_SOCKET", () => {
const result = isWezTermAvailable();
assert.equal(typeof result, "boolean");
});
});
}); });