stack/packages/seat/src/session.mjs

// Managed role sessions (slice 1 S6): where a launch lives on disk, how its
// runner starts, and how the human stops it. The bus host
// (packages/cli/src/launcher.mjs) is the only caller that starts one; it
// decides authority and capacity first, and this module only does what it
// is told.
//
// A session is `node packages/harness/src/runner.mjs <run dir>` inside the
// bubblewrap sandbox of sandbox.mjs, which sees only its own workspace, its
// run directory and the files it runs from. The runner is pid 1 of its own
// PID namespace, so a child that detaches (`setsid -f`) is reparented to the
// runner and stays under the launch's pid, which the human CLI's ancestry
// check refuses. bwrap passes the runner's exit status on, a death by signal
// as 128 + the signal; `stop` signals the runner.
//
// On disk, under the data root:
//   launches/<business>/<run>/        the run directory (0700): session.json,
//                                     bundle/, session/, turns/, runner.log,
//                                     tools.sock, turn.done
//   launches/<business>.jsonl         the launch log (0600, append-only):
//                                     every launch, refusal and end
//   workspaces/<business>/<instance>/ the instance's workspace (0700), kept
//                                     across launches
//   bus-host/sessions.json            the running sessions (0600), written
//                                     only by the host; `mosaic stop` reads it

import { spawn } from "node:child_process";
import { randomBytes } from "node:crypto";
import { appendFileSync, closeSync, existsSync, mkdirSync, openSync, readFileSync, renameSync, writeFileSync } from "node:fs";
import { constants } from "node:os";
import { dirname, join } from "node:path";
import { childrenOf, cmdlineOf, startTimeOf } from "./proc.mjs";
import { binds, prepareRun, REPO, sandboxArgv } from "./sandbox.mjs";
import { SeatError } from "./seat.mjs";

export { REPO };
export const RUNNER = join(REPO, "packages", "harness", "src", "runner.mjs");
export const ADAPTERS = Object.freeze({
  pi: join(REPO, "adapters", "pi", "adapter.sh"),
  "claude-code": join(REPO, "adapters", "claude", "adapter.sh"),
});
export const SESSIONS_VERSION = 1;

export const sessionsFile = (dataRoot) => join(dataRoot, "bus-host", "sessions.json");
export const launchSocketPath = (dataRoot) => join(dataRoot, "bus-host", "launch.sock");
// Row 93 (#1587): packages/cli/src/git-socket.mjs.
export const gitSocketPath = (dataRoot) => join(dataRoot, "bus-host", "git.sock");
export const runsDir = (dataRoot, business) => join(dataRoot, "launches", business);
export const launchLogFile = (dataRoot, business) => join(dataRoot, "launches", `${business}.jsonl`);
export const workspaceDir = (dataRoot, business, instance) => join(dataRoot, "workspaces", business, instance);

// The capacity family of a model: the one key of the business file's
// launch.max that the model name contains (`claude-opus-5-5` is `opus`).
// None, or more than one, is null, and the launch refuses.
export function family(model, max) {
  const hits = Object.keys(max).filter((f) => model.toLowerCase().includes(f.toLowerCase()));
  return hits.length === 1 ? hits[0] : null;
}

// The session's environment is an allowlist: nothing else from the host's
// environment passes, so a founder credential variable (GITEA_TOKEN,
// GH_TOKEN, SSH_AUTH_SOCK, ...) never reaches a session (REQ-CRED-2).
// Provider variables pass because the harness needs them to reach a model.
// MOSAIC_CLAUDE_BIN, the host's pinned Claude Code binary, is a path. HOME
// passes to bwrap only; inside, HOME is the run's own home/.
export const ENV_ALLOW = Object.freeze([
  "HOME", "USER", "LOGNAME", "LANG", "LC_ALL", "TZ", "TERM",
  "ANTHROPIC_API_KEY", "ANTHROPIC_AUTH_TOKEN", "ANTHROPIC_BASE_URL", "CLAUDE_CODE_OAUTH_TOKEN",
  "OPENAI_API_KEY", "OPENROUTER_API_KEY",
  "MOSAIC_CLAUDE_BIN",
]);

// The ways a Claude Code session can log in, each a set of variables that
// must all be set; ENV_ALLOW passes them on. The bus unit loads them
// (packages/cli/README.md, "Unit"). The session gets nothing from ~/.claude,
// which the sandbox doesn't show.
export const SESSION_CREDENTIALS = Object.freeze([["CLAUDE_CODE_OAUTH_TOKEN"], ["ANTHROPIC_API_KEY"], ["ANTHROPIC_AUTH_TOKEN", "ANTHROPIC_BASE_URL"]].map((set) => Object.freeze(set)));
export const hasSessionCredential = (env) => SESSION_CREDENTIALS.some((set) => set.every((k) => Boolean(env[k])));

export function sessionEnv(env, run) {
  const out = {};
  for (const k of ENV_ALLOW) if (env[k] !== undefined) out[k] = env[k];
  out.PATH = [join(REPO, "node_modules", ".bin"), env.PATH ?? "/usr/bin:/bin"].join(":");
  out.MOSAIC_RUN_ID = run;
  return out;
}

// A new run id and its directory. Ids are short because the run directory
// holds a Unix socket (tools.sock), and socket paths stop at 107 bytes.
export function newRun(dataRoot, business) {
  const root = runsDir(dataRoot, business);
  mkdirSync(root, { recursive: true, mode: 0o700 });
  for (let i = 0; i < 5; i++) {
    const run = `r${randomBytes(6).toString("hex")}`;
    const runDir = join(root, run);
    try {
      mkdirSync(runDir, { mode: 0o700 });
    } catch (e) {
      if (e.code === "EEXIST") continue;
      throw e;
    }
    if (Buffer.byteLength(join(runDir, "tools.sock")) > 107) throw new SeatError(`data root path too long for a socket: ${runDir}`, 2);
    return { run, runDir };
  }
  throw new SeatError("could not pick a free run id", 1);
}

export function writeSessionFile(runDir, session) {
  writeFileSync(join(runDir, "session.json"), `${JSON.stringify(session, null, 2)}\n`, { mode: 0o600, flag: "wx" });
}

export function appendLaunchLog(dataRoot, business, entry) {
  const file = launchLogFile(dataRoot, business);
  mkdirSync(dirname(file), { recursive: true, mode: 0o700 });
  appendFileSync(file, `${JSON.stringify({ at: new Date().toISOString(), ...entry })}\n`, { mode: 0o600 });
}

// Start the runner in its sandbox. stdin stays open for the capability line
// the host writes once the broker has bound the launch; stdout and stderr go
// to runner.log. paths: what sandbox.mjs's binds() takes besides the run
// directory (workspace, adapter, harness, brokerSocket, launchSocket,
// claudeBin; readOnly for tests). `bwrap` is for the tests.
export function spawnSession({ runDir, env, paths, node = process.execPath, bwrap }) {
  prepareRun(runDir);
  const argv = sandboxArgv(binds({ ...paths, runDir, node }), runDir, [node, RUNNER, runDir], { bwrap });
  const out = openSync(join(runDir, "runner.log"), "a", 0o600);
  try {
    return spawn(argv[0], argv.slice(1), { cwd: runDir, env, stdio: ["pipe", out, out], detached: true });
  } finally {
    closeSync(out);
  }
}

// A runner's command line is `<node> <RUNNER> <run dir>`. Matching argv[1]
// rather than any argument skips bwrap's forked child before its exec, whose
// argv still names the runner.
export const isRunner = (pid) => (cmdlineOf(pid) ?? [])[1] === RUNNER;

// The runner's pid and start time as seen from here: the outer bwrap
// process's only child.
export async function runnerOf(child, { timeoutMs = 5000 } = {}) {
  const deadline = Date.now() + timeoutMs;
  while (Date.now() < deadline) {
    if (child.exitCode !== null || child.signalCode !== null) break;
    const pid = childrenOf(child.pid)[0];
    const start = pid ? startTimeOf(pid) : null;
    if (start && isRunner(pid)) return { pid, startTime: start };
    await new Promise((r) => setTimeout(r, 20));
  }
  throw new SeatError(`runner for ${child.pid} did not start`, 1);
}

// The outer bwrap's exit as the runner's: bwrap exits 128 + n when the
// runner dies of signal n, and the runner's own codes are all below 128.
const SIGNALS = Object.fromEntries(Object.entries(constants.signals).map(([name, n]) => [n, name]));
export function sessionExit(code, signal) {
  if (!signal && code > 128 && SIGNALS[code - 128]) return { code: null, signal: SIGNALS[code - 128] };
  return { code, signal };
}

// The launch end reason the broker records for a runner's exit
// (packages/harness/README.md, "The runner").
const REASONS = { 0: "stopped", 2: "failed", 20: "founder-credentials", 21: "claim-refused", 22: "session-invalid", 23: "broker-unreachable" };
export function endReason(code, signal) {
  if (signal) return "killed";
  return REASONS[code] ?? "failed";
}

// The host's view of its running sessions, kept in memory and mirrored to
// sessions.json for `mosaic stop` and `mosaic launches list`.
export class Registry {
  #dataRoot;
  #sessions = [];
  constructor(dataRoot) {
    this.#dataRoot = dataRoot;
    this.#write();
  }
  get sessions() {
    return this.#sessions.map((s) => ({ ...s }));
  }
  add(entry) {
    this.#sessions.push({ ...entry });
    this.#write();
  }
  remove(business, run) {
    this.#sessions = this.#sessions.filter((s) => !(s.business === business && s.run === run));
    this.#write();
  }
  count(business, fam) {
    return this.#sessions.filter((s) => s.business === business && s.family === fam).length;
  }
  running(business, instance) {
    return this.#sessions.find((s) => s.business === business && s.instance === instance) ?? null;
  }
  #write() {
    const file = sessionsFile(this.#dataRoot);
    mkdirSync(dirname(file), { recursive: true, mode: 0o700 });
    const tmp = `${file}.${process.pid}.tmp`;
    writeFileSync(tmp, `${JSON.stringify({ sessionsVersion: SESSIONS_VERSION, sessions: this.#sessions }, null, 2)}\n`, { mode: 0o600 });
    renameSync(tmp, file);
  }
}

// sessions.json as `mosaic stop` sees it. `live` is true only when the
// runner still runs with the recorded start time.
export function readSessions(dataRoot) {
  const file = sessionsFile(dataRoot);
  if (!existsSync(file)) return [];
  let doc;
  try {
    doc = JSON.parse(readFileSync(file, "utf8"));
  } catch {
    throw new SeatError(`sessions file is unreadable: ${file}`, 2);
  }
  if (doc?.sessionsVersion !== SESSIONS_VERSION || !Array.isArray(doc.sessions)) throw new SeatError(`sessions file is malformed: ${file}`, 2);
  return doc.sessions.map((s) => ({ ...s, live: startTimeOf(s.runnerPid) === s.runnerStartTime }));
}

// `mosaic stop <run>`: SIGTERM to the run's runner, after checking that the
// pid still has the recorded start time and runs the runner. Same-UID
// process control, not an authority check. The runner releases its role
// and the host records the end.
export async function stopSession(dataRoot, run, { timeoutMs = 30000 } = {}) {
  const hits = readSessions(dataRoot).filter((s) => s.run === run);
  if (hits.length === 0) throw new SeatError(`no running session has run id ${run}; see mosaic launches list`, 2);
  const s = hits[0];
  if (!s.live) return { stopped: false, reason: `run ${run} is not running (stale entry)` };
  if (!isRunner(s.runnerPid)) throw new SeatError(`pid ${s.runnerPid} is not a session runner; refusing to signal it`, 2);
  // Sent again every second: a runner that is still starting has no handler
  // yet, and as pid 1 of its namespace it never sees a signal sent before then.
  const deadline = Date.now() + timeoutMs;
  let next = 0;
  while (Date.now() < deadline) {
    if (startTimeOf(s.runnerPid) !== s.runnerStartTime) return { stopped: true, business: s.business, instance: s.instance, run };
    if (Date.now() >= next) {
      try {
        process.kill(s.runnerPid, "SIGTERM");
      } catch {}
      next = Date.now() + 1000;
    }
    await new Promise((r) => setTimeout(r, 100));
  }
  throw new SeatError(`run ${run} did not stop within ${Math.round(timeoutMs / 1000)} s`, 1);
}