vibn-frontend/lib/dev-container.ts

/**
 * Per-project AI dev container ("vibn-dev").
 *
 * One Coolify Service per Vibn project, running the `vibn-dev` image.
 * The AI agent drives it via:
 *   - shell.exec   → docker exec into the container (via existing SSH path)
 *   - fs.*         → file ops (implemented as `cat` / `tee` / `rm` etc.
 *                    inside the container, on top of shell.exec)
 *   - dev_server.* → start long-running processes (week 2)
 *   - ship         → git push to Gitea + trigger Coolify deploy (week 2)
 *
 * Lifecycle states:
 *   - Not provisioned   → ensureDevContainer() creates the Coolify service
 *   - Suspended         → Coolify-stopped (saves money). resume() starts it.
 *   - Running           → docker exec works.
 *
 * Tenant safety: every helper takes a workspace and the caller must have
 * already verified that the projectId belongs to that workspace via
 * fs_projects. The exec primitive ALSO verifies the resolved container
 * UUID is in the workspace's owned Coolify-project set, so a hijacked
 * projectId can't reach unrelated containers.
 *
 * See: AI_PATH_B_EXECUTION_PLAN.md §3.
 */

import { query, queryOne } from '@/lib/db-postgres';
import {
  createDockerComposeApp,
  startService,
  stopService,
  getService,
} from '@/lib/coolify';
import { execInCoolifyApp, type ExecInAppResult } from '@/lib/coolify-exec';
import { isCoolifySshConfigured } from '@/lib/coolify-ssh';
import {
  ensureProjectCoolifyProject,
  getProjectCoolifyUuid,
  linkResourceToProject,
} from '@/lib/projects';
import type { VibnWorkspace } from '@/lib/workspaces';

// ── Configuration ────────────────────────────────────────────────────

/**
 * Image tag for vibn-dev. Built and pushed from /vibn-dev/Dockerfile.
 * Override per-environment with VIBN_DEV_IMAGE for staging/canary tags.
 */
export const VIBN_DEV_IMAGE = process.env.VIBN_DEV_IMAGE ?? 'vibn-dev:latest';

/** Resource caps per dev container. Tweak in env per-tier later. */
const DEFAULT_CPU_LIMIT = process.env.VIBN_DEV_CPU_LIMIT ?? '1';      // 1 vCPU
const DEFAULT_MEM_LIMIT = process.env.VIBN_DEV_MEM_LIMIT ?? '1g';     // 1 GiB
const DEFAULT_DISK_LIMIT = process.env.VIBN_DEV_DISK_LIMIT ?? '10g';  // soft hint, not enforced by compose

// ── Schema ───────────────────────────────────────────────────────────

let devContainersTableReady = false;
export async function ensureDevContainersTable(): Promise<void> {
  if (devContainersTableReady) return;
  await query(
    `CREATE TABLE IF NOT EXISTS fs_project_dev_containers (
       project_id      TEXT PRIMARY KEY,
       workspace       TEXT NOT NULL,
       service_uuid    TEXT NOT NULL,
       image           TEXT NOT NULL,
       state           TEXT NOT NULL DEFAULT 'provisioning',
       last_active_at  TIMESTAMPTZ NOT NULL DEFAULT now(),
       suspended_at    TIMESTAMPTZ,
       created_at      TIMESTAMPTZ NOT NULL DEFAULT now()
     );
     CREATE INDEX IF NOT EXISTS fs_project_dev_containers_ws_idx
       ON fs_project_dev_containers (workspace);
     CREATE INDEX IF NOT EXISTS fs_project_dev_containers_active_idx
       ON fs_project_dev_containers (last_active_at);`,
    [],
  );
  devContainersTableReady = true;
}

export interface DevContainerRow {
  project_id: string;
  workspace: string;
  service_uuid: string;
  image: string;
  state: 'provisioning' | 'running' | 'suspended' | 'failed';
  last_active_at: Date;
  suspended_at: Date | null;
  created_at: Date;
}

export async function getDevContainerRow(projectId: string): Promise<DevContainerRow | null> {
  await ensureDevContainersTable();
  return queryOne<DevContainerRow>(
    `SELECT * FROM fs_project_dev_containers WHERE project_id = $1 LIMIT 1`,
    [projectId],
  );
}

// ── Compose template ─────────────────────────────────────────────────

/**
 * Render the docker-compose.yml that backs a single vibn-dev service.
 *
 * Two named volumes are intentional:
 *   - workspace : everything in /workspace (the user's source tree).
 *                 Persists across suspends. Backed up to Gitea every
 *                 5 min via the auto-push autosave loop (week 2).
 *   - cache     : language-toolchain caches (mise, npm, pip, cargo).
 *                 Persists across suspends; per-project (never shared).
 *
 * The container has NO Vibn-internal network access. We rely on the
 * default Coolify-bridge network being isolated from the vibn-postgres
 * / vibn-frontend bridge. (Network policy hardening lands in week 1
 * day 2 alongside the auto-push job.)
 */
function renderDevCompose(projectSlug: string): string {
  // Image distribution: we build vibn-dev on the Coolify host once
  // (see /vibn-dev/setup-on-coolify.sh) and reference it locally.
  // pull_policy: never tells Docker not to attempt a registry pull.
  //
  // Network isolation: vibn-dev sits on its OWN bridge network
  // (`vibn-dev-net`) which has no route to vibn-postgres, vibn-frontend,
  // or other workspace services. Egress to the public internet still
  // works via the bridge's default gateway. This is the cheapest way
  // to enforce the §7 "no internal Vibn access" guarantee without
  // touching iptables on the host.
  return `services:
  vibn-dev:
    image: ${VIBN_DEV_IMAGE}
    pull_policy: never
    restart: unless-stopped
    working_dir: /workspace
    volumes:
      - workspace:/workspace
      - cache:/home/vibn/.cache
    environment:
      - VIBN_PROJECT_SLUG=${projectSlug}
      - VIBN_DEV_CONTAINER=1
    networks:
      - vibn-dev-net
    deploy:
      resources:
        limits:
          cpus: '${DEFAULT_CPU_LIMIT}'
          memory: ${DEFAULT_MEM_LIMIT}
networks:
  vibn-dev-net:
    name: vibn-dev-net-${projectSlug}
    driver: bridge
volumes:
  workspace:
  cache:
`;
}

// ── Provisioning ─────────────────────────────────────────────────────

export interface EnsureDevContainerOpts {
  projectId: string;
  projectSlug: string;
  projectName?: string;
  workspace: VibnWorkspace;
  /** Skip the initial start (provision-only). Default: start it. */
  noStart?: boolean;
}

export interface EnsureDevContainerResult {
  serviceUuid: string;
  state: DevContainerRow['state'];
  created: boolean;
}

/**
 * Idempotently ensure a vibn-dev service exists for the given Vibn project.
 *
 * - Already provisioned → returns the row, optionally resumes if suspended.
 * - Not provisioned     → ensures the per-project Coolify Project exists,
 *                         creates the docker-compose service, links the
 *                         resource to the Vibn project, persists the row.
 *
 * Safe to call on every chat turn — first call is ~10s, subsequent
 * calls are a single SELECT.
 */
export async function ensureDevContainer(
  opts: EnsureDevContainerOpts,
): Promise<EnsureDevContainerResult> {
  await ensureDevContainersTable();

  const existing = await getDevContainerRow(opts.projectId);
  if (existing) {
    if (existing.state === 'suspended' && !opts.noStart) {
      await resumeDevContainer(opts.projectId);
      return { serviceUuid: existing.service_uuid, state: 'running', created: false };
    }
    return { serviceUuid: existing.service_uuid, state: existing.state, created: false };
  }

  // Need a Coolify project to land the service in.
  let coolifyProjectUuid = await getProjectCoolifyUuid(opts.projectId, opts.workspace);
  if (!coolifyProjectUuid) {
    coolifyProjectUuid = await ensureProjectCoolifyProject(
      opts.projectId,
      opts.workspace,
      { projectSlug: opts.projectSlug, projectName: opts.projectName },
    );
  }
  if (!coolifyProjectUuid) {
    throw new Error(
      `Could not provision Coolify project for ${opts.projectId}; dev container creation aborted.`,
    );
  }

  const created = await createDockerComposeApp({
    projectUuid: coolifyProjectUuid,
    name: `vibn-dev-${opts.projectSlug}`,
    description: `AI dev container for project ${opts.projectName ?? opts.projectSlug}`,
    composeRaw: renderDevCompose(opts.projectSlug),
    instantDeploy: !opts.noStart,
  });

  await query(
    `INSERT INTO fs_project_dev_containers
       (project_id, workspace, service_uuid, image, state)
     VALUES ($1, $2, $3, $4, $5)
     ON CONFLICT (project_id) DO UPDATE
       SET service_uuid = EXCLUDED.service_uuid,
           image        = EXCLUDED.image,
           state        = EXCLUDED.state`,
    [
      opts.projectId,
      opts.workspace.slug,
      created.uuid,
      VIBN_DEV_IMAGE,
      opts.noStart ? 'suspended' : 'provisioning',
    ],
  );

  // Bookkeeping link so apps_list / projects_get see the dev container
  // under the right Vibn project.
  try {
    await linkResourceToProject(opts.projectId, opts.workspace.slug, created.uuid, 'service');
  } catch {
    // best-effort
  }

  return { serviceUuid: created.uuid, state: 'provisioning', created: true };
}

// ── Lifecycle ────────────────────────────────────────────────────────

export async function suspendDevContainer(projectId: string): Promise<void> {
  const row = await getDevContainerRow(projectId);
  if (!row) return;
  if (row.state === 'suspended') return;
  await stopService(row.service_uuid);
  await query(
    `UPDATE fs_project_dev_containers
        SET state = 'suspended', suspended_at = now()
      WHERE project_id = $1`,
    [projectId],
  );
}

export async function resumeDevContainer(projectId: string): Promise<void> {
  const row = await getDevContainerRow(projectId);
  if (!row) throw new Error(`No dev container provisioned for ${projectId}`);
  if (row.state === 'running') return;
  await startService(row.service_uuid);
  await query(
    `UPDATE fs_project_dev_containers
        SET state = 'running', suspended_at = NULL, last_active_at = now()
      WHERE project_id = $1`,
    [projectId],
  );
}

async function touchActivity(projectId: string): Promise<void> {
  await query(
    `UPDATE fs_project_dev_containers SET last_active_at = now() WHERE project_id = $1`,
    [projectId],
  );
}

// ── Exec primitive ───────────────────────────────────────────────────

export interface DevContainerExecOpts {
  projectId: string;
  command: string;
  cwd?: string;          // defaults to /workspace
  timeoutMs?: number;
  maxBytes?: number;
  /** Override the user (default: vibn). Use 'root' only when needed. */
  user?: string;
  /** Extra env vars (k=v lines prepended via `env` builtin). */
  env?: Record<string, string>;
}

/**
 * Run a command inside the project's vibn-dev service.
 * Resumes the container if suspended, then docker-exec's via the
 * existing SSH primitive. Stdout/stderr/exit-code returned synchronously.
 *
 * The caller is responsible for verifying the projectId belongs to the
 * workspace BEFORE calling this. We re-verify the container UUID via
 * the exec primitive's own resolution (it queries `docker ps --filter
 * name={uuid}`), so a mismatched projectId can't reach foreign containers.
 */
export async function execInDevContainer(
  opts: DevContainerExecOpts,
): Promise<ExecInAppResult> {
  if (!isCoolifySshConfigured()) {
    throw new Error(
      'shell.exec requires SSH access to the Coolify host; configure COOLIFY_SSH_* envs.',
    );
  }
  const row = await getDevContainerRow(opts.projectId);
  if (!row) {
    throw new Error(
      `No dev container for project ${opts.projectId}. Call ensureDevContainer() first.`,
    );
  }
  if (row.state === 'suspended') {
    await resumeDevContainer(opts.projectId);
  }

  const cwd = opts.cwd && opts.cwd.trim() ? opts.cwd.trim() : '/workspace';
  const envPrefix = opts.env
    ? Object.entries(opts.env)
        .map(([k, v]) => `${shellEscape(k)}=${shellEscape(v)}`)
        .join(' ')
    : '';
  const wrapped = envPrefix
    ? `cd ${shellEscape(cwd)} && env ${envPrefix} ${opts.command}`
    : `cd ${shellEscape(cwd)} && ${opts.command}`;

  const result = await execInCoolifyApp({
    appUuid: row.service_uuid,
    service: 'vibn-dev',
    command: wrapped,
    user: opts.user ?? 'vibn',
    timeoutMs: opts.timeoutMs,
    maxBytes: opts.maxBytes,
  });

  await touchActivity(opts.projectId);
  return result;
}

function shellEscape(s: string): string {
  return `'${s.replace(/'/g, `'\\''`)}'`;
}

// ── Health ───────────────────────────────────────────────────────────

/**
 * Quick liveness check used by chat startup to decide whether to show
 * a "spinning up your environment…" banner.
 */
export async function getDevContainerStatus(projectId: string): Promise<{
  exists: boolean;
  state: DevContainerRow['state'] | 'absent';
  serviceUuid: string | null;
}> {
  const row = await getDevContainerRow(projectId);
  if (!row) return { exists: false, state: 'absent', serviceUuid: null };
  // Optional: poke Coolify for fresh state. Skipped for now to keep this
  // hot path cheap; consumers that care can call getService(uuid) directly.
  return { exists: true, state: row.state, serviceUuid: row.service_uuid };
}

// Re-export getService so route handlers can pull live Coolify status
// without taking a separate dependency on lib/coolify.
export { getService };

// ── Dev servers ──────────────────────────────────────────────────────
//
// Long-running processes (Vite, Next dev, etc.) launched inside the
// dev container. We don't have a real supervisor; we shell out to
// `nohup`, redirect logs to /var/log/vibn-dev/<id>.log, and remember
// the PID + port in fs_dev_servers so subsequent calls can stop or
// list them.
//
// Preview URLs are exposed via Traefik's "host" router using the
// internal Coolify network (the dev container's primary bridge IP is
// reachable from Traefik). Full Traefik wildcard wiring lands in
// /vibn-dev/PREVIEWS.md and a separate Traefik config commit; this
// module just records the URL we WILL serve at, so the caller can
// hand it back to the chat.

let devServersTableReady = false;
async function ensureDevServersTable(): Promise<void> {
  if (devServersTableReady) return;
  await query(
    `CREATE TABLE IF NOT EXISTS fs_dev_servers (
       id           TEXT PRIMARY KEY,
       project_id   TEXT NOT NULL REFERENCES fs_project_dev_containers(project_id) ON DELETE CASCADE,
       workspace    TEXT NOT NULL,
       name         TEXT NOT NULL,
       command      TEXT NOT NULL,
       port         INTEGER NOT NULL,
       pid          INTEGER,
       preview_url  TEXT NOT NULL,
       state        TEXT NOT NULL DEFAULT 'starting',
       started_at   TIMESTAMPTZ NOT NULL DEFAULT now(),
       stopped_at   TIMESTAMPTZ
     );
     CREATE INDEX IF NOT EXISTS fs_dev_servers_project_idx ON fs_dev_servers (project_id, state);`,
    [],
  );
  devServersTableReady = true;
}

export interface DevServerRow {
  id: string;
  project_id: string;
  workspace: string;
  name: string;
  command: string;
  port: number;
  pid: number | null;
  preview_url: string;
  state: 'starting' | 'running' | 'stopped' | 'failed';
  started_at: Date;
  stopped_at: Date | null;
}

const PREVIEW_DOMAIN_BASE =
  process.env.VIBN_PREVIEW_DOMAIN_BASE ?? 'preview.vibnai.com';

function randomToken(bytes = 4): string {
  const buf = Buffer.alloc(bytes);
  for (let i = 0; i < bytes; i++) buf[i] = Math.floor(Math.random() * 256);
  return buf.toString('hex');
}

function buildPreviewUrl(projectSlug: string, name: string): string {
  // Random suffix per server so URLs aren't guessable. Subdomain is
  // <name>-<projectSlug>-<token>.<base> (kept under 63 chars for DNS).
  const safe = (s: string) => s.toLowerCase().replace(/[^a-z0-9-]/g, '-').slice(0, 20);
  const sub = `${safe(name)}-${safe(projectSlug)}-${randomToken()}`;
  return `https://${sub}.${PREVIEW_DOMAIN_BASE}`;
}

export interface StartDevServerOpts {
  projectId: string;
  projectSlug: string;
  command: string;
  port: number;
  name?: string;
  workspace: VibnWorkspace;
}

export async function startDevServer(opts: StartDevServerOpts): Promise<DevServerRow> {
  await ensureDevServersTable();
  const id = `ds_${randomToken(6)}`;
  const name = opts.name ?? `port-${opts.port}`;
  const previewUrl = buildPreviewUrl(opts.projectSlug, name);
  const logFile = `/var/log/vibn-dev/${id}.log`;

  // nohup the command, capture PID. We pin the listening interface to
  // 0.0.0.0 by injecting HOST=0.0.0.0 (handles Vite/Next/Express); we
  // also export PORT so frameworks that read it pick it up.
  const launch =
    `mkdir -p /var/log/vibn-dev && ` +
    `cd /workspace && ` +
    `nohup env HOST=0.0.0.0 PORT=${opts.port} VIBN_DEV_SERVER_ID=${id} ` +
    `bash -lc ${shellEscape(opts.command)} > ${logFile} 2>&1 & ` +
    `echo $!`;

  const result = await execInDevContainer({
    projectId: opts.projectId,
    command: launch,
    timeoutMs: 5_000,
  });
  const pid = parseInt(result.stdout.trim(), 10);

  await query(
    `INSERT INTO fs_dev_servers
       (id, project_id, workspace, name, command, port, pid, preview_url, state)
     VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9)`,
    [
      id,
      opts.projectId,
      opts.workspace.slug,
      name,
      opts.command,
      opts.port,
      Number.isFinite(pid) ? pid : null,
      previewUrl,
      'starting',
    ],
  );

  return {
    id,
    project_id: opts.projectId,
    workspace: opts.workspace.slug,
    name,
    command: opts.command,
    port: opts.port,
    pid: Number.isFinite(pid) ? pid : null,
    preview_url: previewUrl,
    state: 'starting',
    started_at: new Date(),
    stopped_at: null,
  };
}

export async function listDevServers(projectId: string): Promise<DevServerRow[]> {
  await ensureDevServersTable();
  return query<DevServerRow>(
    `SELECT * FROM fs_dev_servers WHERE project_id = $1 AND state != 'stopped' ORDER BY started_at DESC`,
    [projectId],
  );
}

export async function stopDevServer(projectId: string, id: string): Promise<void> {
  await ensureDevServersTable();
  const row = await queryOne<DevServerRow>(
    `SELECT * FROM fs_dev_servers WHERE id = $1 AND project_id = $2 LIMIT 1`,
    [id, projectId],
  );
  if (!row) throw new Error(`Dev server ${id} not found`);
  if (row.pid) {
    try {
      await execInDevContainer({
        projectId,
        command: `kill ${row.pid} 2>/dev/null || true`,
        timeoutMs: 3_000,
      });
    } catch {}
  }
  await query(
    `UPDATE fs_dev_servers SET state = 'stopped', stopped_at = now() WHERE id = $1`,
    [id],
  );
}

export async function tailDevServerLog(
  projectId: string,
  id: string,
  lines = 200,
): Promise<string> {
  const r = await execInDevContainer({
    projectId,
    command: `tail -n ${Math.max(1, Math.min(2000, lines))} /var/log/vibn-dev/${id}.log 2>/dev/null || echo '(no log yet)'`,
    timeoutMs: 5_000,
  });
  return r.stdout;
}

// ── Auto-push autosave ───────────────────────────────────────────────
//
// Treats Gitea as the canonical store; the container disk is ephemeral.
// On every chat turn (or every 5 min, whichever comes first) we push
// /workspace to a `vibn-autosave/main` branch in the project's repo.
//
// We don't try to be clever about what changed — just `git add -A &&
// git commit --allow-empty -m "autosave $(date)" && git push`. If the
// repo doesn't exist yet (fresh project, no `git init` done), we skip
// silently — the AI is responsible for `git init`+ first push when it
// scaffolds.

export interface AutosaveOpts {
  projectId: string;
  projectSlug: string;
  workspace: VibnWorkspace;
  /** Repo name in the workspace's Gitea org. Defaults to projectSlug. */
  repo?: string;
  /** Min interval between autosaves (default 5 min). */
  minIntervalMs?: number;
}

export async function autosaveWorkspace(opts: AutosaveOpts): Promise<{
  ran: boolean;
  reason: string;
  pushedAt?: Date;
}> {
  const row = await getDevContainerRow(opts.projectId);
  if (!row) return { ran: false, reason: 'no dev container' };
  if (row.state !== 'running') return { ran: false, reason: `state=${row.state}` };

  // Throttle: don't autosave more than once per minIntervalMs.
  const minInterval = opts.minIntervalMs ?? 5 * 60_000;
  const last = await queryOne<{ pushed_at: Date }>(
    `SELECT pushed_at FROM fs_dev_autosaves WHERE project_id = $1 ORDER BY pushed_at DESC LIMIT 1`,
    [opts.projectId],
  ).catch(() => null);
  if (last && Date.now() - new Date(last.pushed_at).getTime() < minInterval) {
    return { ran: false, reason: 'throttled' };
  }

  await ensureAutosavesTable();

  // The git config + remote set-url is idempotent; PAT lives in the
  // container's .netrc. Initial scaffold (init+add+commit+remote add)
  // runs only when the repo doesn't have git yet.
  const repo = opts.repo ?? opts.projectSlug;
  const cmd = `set -e
cd /workspace
if [ ! -d .git ]; then
  echo '(no .git, skipping autosave)'
  exit 0
fi
git config user.email vibn-bot@vibnai.com
git config user.name 'Vibn Autosave'
# Force push to the autosave branch — never collides with main.
git checkout -B vibn-autosave/main 2>&1 | tail -1
git add -A
if git diff --cached --quiet; then
  echo '(no changes)'
else
  git commit -m "autosave $(date -Is)" --quiet
fi
git push -f origin vibn-autosave/main 2>&1 | tail -3`;

  try {
    const r = await execInDevContainer({
      projectId: opts.projectId,
      command: cmd,
      timeoutMs: 30_000,
    });
    await query(
      `INSERT INTO fs_dev_autosaves (project_id, workspace, repo, output, code)
         VALUES ($1, $2, $3, $4, $5)`,
      [opts.projectId, opts.workspace.slug, repo, (r.stdout + r.stderr).slice(0, 4000), r.code],
    );
    return { ran: true, reason: 'pushed', pushedAt: new Date() };
  } catch (err) {
    return { ran: false, reason: err instanceof Error ? err.message : String(err) };
  }
}

let autosavesTableReady = false;
async function ensureAutosavesTable(): Promise<void> {
  if (autosavesTableReady) return;
  await query(
    `CREATE TABLE IF NOT EXISTS fs_dev_autosaves (
       id          BIGSERIAL PRIMARY KEY,
       project_id  TEXT NOT NULL,
       workspace   TEXT NOT NULL,
       repo        TEXT NOT NULL,
       output      TEXT,
       code        INTEGER,
       pushed_at   TIMESTAMPTZ NOT NULL DEFAULT now()
     );
     CREATE INDEX IF NOT EXISTS fs_dev_autosaves_project_idx ON fs_dev_autosaves (project_id, pushed_at DESC);`,
    [],
  );
  autosavesTableReady = true;
}

// ── Idle suspend ─────────────────────────────────────────────────────

export interface IdleSweepResult {
  scanned: number;
  suspended: Array<{ projectId: string; idleMin: number }>;
  errors: Array<{ projectId: string; error: string }>;
}

/**
 * Suspend any running dev containers that haven't been touched in
 * `idleMinutes` minutes. Intended for a once-per-5-min cron. Idempotent:
 * re-running is a no-op for already-suspended containers.
 */
export async function suspendIdleContainers(idleMinutes = 30): Promise<IdleSweepResult> {
  await ensureDevContainersTable();
  const cutoff = new Date(Date.now() - idleMinutes * 60_000);
  const rows = await query<DevContainerRow>(
    `SELECT * FROM fs_project_dev_containers
      WHERE state = 'running' AND last_active_at < $1`,
    [cutoff],
  );
  const result: IdleSweepResult = { scanned: rows.length, suspended: [], errors: [] };
  for (const r of rows) {
    try {
      await suspendDevContainer(r.project_id);
      const idleMin = Math.floor((Date.now() - new Date(r.last_active_at).getTime()) / 60_000);
      result.suspended.push({ projectId: r.project_id, idleMin });
    } catch (err) {
      result.errors.push({
        projectId: r.project_id,
        error: err instanceof Error ? err.message : String(err),
      });
    }
  }
  return result;
}