system_update/server/services/rebootVerify.ts

// server/services/rebootVerify.ts
import { runPlain, type SshCreds } from "../ssh/client.js";
import type { RebootResult } from "@shared/types.js";

export function parseBootIdBefore(raw: string): string | null {
  const s = raw.indexOf("===SU:BOOT_ID_BEFORE===");
  if (s === -1) return null;
  const from = s + "===SU:BOOT_ID_BEFORE===".length;
  const e = raw.indexOf("===SU:REBOOT_NOW===", from);
  const id = raw.slice(from, e === -1 ? undefined : e).trim();
  return id || null;
}

export interface RebootSignals {
  beforeBootId: string | null;
  afterBootId: string | null;
  wentDown: boolean;
  cameBack: boolean;
}

/** Détermine le statut d'un reboot vérifié (fonction pure). */
export function classifyReboot(s: RebootSignals): { status: RebootResult["status"] } {
  if (!s.wentDown) return { status: "ssh_never_went_down" };
  if (!s.cameBack || s.afterBootId === null) return { status: "machine_did_not_return" };
  if (s.beforeBootId !== null && s.afterBootId === s.beforeBootId) return { status: "boot_id_unchanged" };
  return { status: "ok" };
}

async function readBootId(creds: SshCreds): Promise<string | null> {
  try {
    const res = await runPlain(creds, "cat /proc/sys/kernel/random/boot_id");
    const id = res.stdout.trim();
    return id || null;
  } catch {
    return null; // connexion impossible (machine down)
  }
}

const sleep = (ms: number) => new Promise((r) => setTimeout(r, ms));

export interface VerifyOptions {
  beforeBootId: string | null;
  requestedAt: string;
  downTimeoutMs?: number;   // détection de la coupure
  upTimeoutMs?: number;     // attente du retour
  pollMs?: number;
}

/**
 * Orchestration : attend la coupure SSH (machine qui reboote) puis le retour,
 * relit le boot_id, et classe le résultat. Réseau ; non testé unitairement.
 */
export async function verifyReboot(creds: SshCreds, opt: VerifyOptions): Promise<RebootResult> {
  const downTimeoutMs = opt.downTimeoutMs ?? 60000;
  const upTimeoutMs = opt.upTimeoutMs ?? 600000;
  const pollMs = opt.pollMs ?? 5000;
  const t0 = Date.now();

  // Phase A : attendre que la machine devienne injoignable.
  let wentDown = false;
  let sshWentDownAt: string | null = null;
  while (Date.now() - t0 < downTimeoutMs) {
    const id = await readBootId(creds);
    if (id === null) { wentDown = true; sshWentDownAt = new Date().toISOString(); break; }
    await sleep(pollMs);
  }

  // Phase B : attendre le retour (seulement si on a vu la coupure).
  let cameBack = false;
  let sshCameBackAt: string | null = null;
  let afterBootId: string | null = null;
  if (wentDown) {
    const tB = Date.now();
    while (Date.now() - tB < upTimeoutMs) {
      const id = await readBootId(creds);
      if (id !== null) { cameBack = true; sshCameBackAt = new Date().toISOString(); afterBootId = id; break; }
      await sleep(pollMs);
    }
  }

  const { status } = classifyReboot({ beforeBootId: opt.beforeBootId, afterBootId, wentDown, cameBack });
  const waitedSeconds = Math.round((Date.now() - t0) / 1000);
  return {
    beforeBootId: opt.beforeBootId,
    afterBootId,
    requestedAt: opt.requestedAt,
    sshWentDownAt,
    sshCameBackAt,
    waitedSeconds,
    status,
    lastRebootDurationSeconds: status === "ok" ? waitedSeconds : undefined,
    nextRecommendedWaitSeconds: status === "ok" ? Math.round(waitedSeconds * 1.5) + 30 : undefined,
  };
}