pi-interactive-subagents/pi-extension/subagents/orca.ts

/**
 * Orca surface backend. Subagents run in unfocused terminal tabs in the
 * current Orca worktree.
 *
 * Detection relies on ORCA_TERMINAL_HANDLE, which Orca exports inside its
 * managed terminals. Inside those terminals `orca` resolves to the Orca CLI
 * shim; outside them bare `orca` on Linux is usually the GNOME screen reader,
 * so resolution explicitly rejects /usr/bin/orca.
 */
import { execFile, execFileSync } from "node:child_process";
import { promisify } from "node:util";

const execFileAsync = promisify(execFile);

/** GNOME screen reader path — never a valid Orca CLI. */
const GNOME_SCREEN_READER = "/usr/bin/orca";

let cachedCli: string | null | undefined;

/** Terminal handles created as whole tabs (vs splits), mapped for tab close. */
const tabByHandle = new Map<string, string>();

interface OrcaResponse {
  ok?: boolean;
  error?: { message?: unknown };
}

interface OrcaTerminalCreated extends OrcaResponse {
  result?: {
    terminal?: { handle?: unknown; tabId?: unknown };
  };
}

interface OrcaSplitCreated extends OrcaResponse {
  result?: {
    split?: { handle?: unknown };
  };
}

interface OrcaTerminalRead extends OrcaResponse {
  result?: {
    terminal?: { tail?: unknown; status?: unknown };
  };
}

/**
 * Marker echoed by the startup command once the new terminal has cd'd into
 * the target directory and is about to exec bash. Written with a quote split
 * (`__PI_SURFACE_''READY__`) so the typed command line on screen never
 * matches, only the echoed output does.
 */
const READY_MARKER = "__PI_SURFACE_READY__";

function resolveCli(): string | null {
  if (cachedCli !== undefined) return cachedCli;

  const override = process.env.ORCA_CLI_COMMAND?.trim();
  if (override) {
    cachedCli = override;
    return cachedCli;
  }

  try {
    const resolved = execFileSync("sh", ["-c", "command -v orca"], { encoding: "utf8" }).trim();
    cachedCli = resolved && resolved !== GNOME_SCREEN_READER ? "orca" : null;
  } catch {
    cachedCli = null;
  }
  return cachedCli;
}

export function isAvailable(): boolean {
  return !!process.env.ORCA_TERMINAL_HANDLE && resolveCli() !== null;
}

export function setupHint(): string {
  return "Start pi inside an Orca-managed terminal with the `orca` CLI on PATH.";
}

function requireOrca(): string {
  const cli = resolveCli();
  if (!isAvailable() || !cli) {
    throw new Error(`Orca is required for this surface. ${setupHint()}`);
  }
  return cli;
}

function shellEscape(value: string): string {
  return "'" + value.replace(/'/g, "'\\''") + "'";
}

/** Startup command that lands the new terminal in pi's cwd with a bash shell. */
function startupCommand(): string {
  return `cd ${shellEscape(process.cwd())} && echo __PI_SURFACE_''READY__ && exec bash`;
}

function sleepSync(seconds: number): void {
  try {
    execFileSync("sleep", [String(seconds)], { stdio: "ignore" });
  } catch {}
}

/** Probe marker proving the shell reads and executes typed input. */
const SHELL_UP_MARKER = "__PI_SHELL_UP__";

/**
 * Block until the new terminal's shell is genuinely interactive.
 *
 * Two races exist at startup: input typed before the initial shell execs bash
 * is swallowed with it, and input typed while bash itself initializes can be
 * flushed (observed as stray kitty-keyboard residue like `0u` at the prompt).
 * So first wait for the startup command's ready marker, then repeatedly send a
 * probe echo until its output appears — an executed probe also clears any
 * residue from the readline buffer. Falls through after the deadline as
 * best-effort.
 */
function waitForSurfaceReady(surface: string, timeoutMs = 15_000): void {
  const deadline = Date.now() + timeoutMs;

  while (Date.now() < deadline) {
    try {
      if (readScreen(surface, 40).includes(READY_MARKER)) break;
    } catch {}
    sleepSync(0.25);
  }

  while (Date.now() < deadline) {
    try {
      sendCommand(surface, "echo __PI_SHELL_''UP__");
    } catch {
      sleepSync(0.25);
      continue;
    }
    const probeDeadline = Math.min(Date.now() + 2_000, deadline);
    while (Date.now() < probeDeadline) {
      sleepSync(0.25);
      try {
        if (readScreen(surface, 40).includes(SHELL_UP_MARKER)) return;
      } catch {}
    }
  }
}

function parseResponse<T extends OrcaResponse>(command: string, output: string): T {
  let response: T;
  try {
    response = JSON.parse(output) as T;
  } catch {
    throw new Error(`Unexpected Orca ${command} output: ${output.trim() || "(empty)"}`);
  }
  if (response.ok === false) {
    const message =
      typeof response.error?.message === "string" ? response.error.message : "unknown error";
    throw new Error(`Orca ${command} failed: ${message}`);
  }
  return response;
}

function requireId(value: unknown, command: string, field: string): string {
  if (typeof value !== "string" || value.length === 0) {
    throw new Error(`Orca ${command} did not return ${field}`);
  }
  return value;
}

export function parseCreatedTerminal(output: string): { handle: string; tabId: string } {
  const response = parseResponse<OrcaTerminalCreated>("terminal create", output);
  return {
    handle: requireId(response.result?.terminal?.handle, "terminal create", "result.terminal.handle"),
    tabId: requireId(response.result?.terminal?.tabId, "terminal create", "result.terminal.tabId"),
  };
}

export function parseCreatedSplit(output: string): string {
  const response = parseResponse<OrcaSplitCreated>("terminal split", output);
  return requireId(response.result?.split?.handle, "terminal split", "result.split.handle");
}

export function parseReadTail(output: string): string {
  const response = parseResponse<OrcaTerminalRead>("terminal read", output);
  const status = response.result?.terminal?.status;
  if (typeof status === "string" && status !== "running") {
    throw new Error(`Orca terminal read: terminal is not running (status: ${status})`);
  }
  const tail = response.result?.terminal?.tail;
  if (!Array.isArray(tail)) {
    throw new Error("Orca terminal read did not return result.terminal.tail");
  }
  return tail.filter((line): line is string => typeof line === "string").join("\n");
}

export function createSurface(name: string): string {
  const cli = requireOrca();
  // Target the enclosing terminal's worktree explicitly: pi's cwd (which the
  // CLI would otherwise resolve against) may live outside any Orca worktree.
  const worktreeId = process.env.ORCA_WORKTREE_ID;
  const output = execFileSync(
    cli,
    [
      "terminal",
      "create",
      ...(worktreeId ? ["--worktree", `id:${worktreeId}`] : []),
      "--title",
      name,
      "--command",
      startupCommand(),
      "--json",
    ],
    { encoding: "utf8" },
  );
  const { handle, tabId } = parseCreatedTerminal(output);
  tabByHandle.set(handle, tabId);
  waitForSurfaceReady(handle);
  return handle;
}

export function createSurfaceSplit(
  name: string,
  direction: "left" | "right" | "up" | "down",
  fromSurface?: string,
): string {
  void name;
  const cli = requireOrca();
  if (direction === "left" || direction === "up") {
    throw new Error(`Orca terminal splits only support right or down, not ${direction}`);
  }

  const source = fromSurface ?? process.env.ORCA_TERMINAL_HANDLE!;
  const output = execFileSync(
    cli,
    [
      "terminal",
      "split",
      "--terminal",
      source,
      "--direction",
      direction === "right" ? "horizontal" : "vertical",
      "--command",
      startupCommand(),
      "--json",
    ],
    { encoding: "utf8" },
  );
  const handle = parseCreatedSplit(output);
  waitForSurfaceReady(handle);
  return handle;
}

export function sendCommand(surface: string, command: string): void {
  const cli = requireOrca();
  const output = execFileSync(
    cli,
    ["terminal", "send", "--terminal", surface, "--text", command, "--enter", "--json"],
    { encoding: "utf8" },
  );
  parseResponse("terminal send", output);
}

function readScreenArgs(surface: string, lines: number): string[] {
  return [
    "terminal",
    "read",
    "--terminal",
    surface,
    "--screen",
    "--limit",
    String(Math.max(1, lines)),
    "--json",
  ];
}

export function readScreen(surface: string, lines = 50): string {
  const cli = requireOrca();
  const output = execFileSync(cli, readScreenArgs(surface, lines), { encoding: "utf8" });
  return parseReadTail(output);
}

export async function readScreenAsync(surface: string, lines = 50): Promise<string> {
  const cli = requireOrca();
  const { stdout } = await execFileAsync(cli, readScreenArgs(surface, lines), {
    encoding: "utf8",
  });
  return parseReadTail(stdout);
}

export function closeSurface(surface: string): void {
  const cli = requireOrca();
  const args = ["terminal", "close", "--terminal", surface];
  if (tabByHandle.has(surface)) args.push("--tab");
  args.push("--json");
  const output = execFileSync(cli, args, { encoding: "utf8" });
  parseResponse("terminal close", output);
  tabByHandle.delete(surface);
}