vibn-frontend/lib/coolify-compose.ts

/**
 * Surgical post-deploy fixes for Coolify-managed Services.
 *
 * Why this exists
 * ---------------
 * Coolify's service-template deploy pipeline gets us 90% of the way:
 * it generates a docker-compose.yml + .env, runs `docker compose up`,
 * sets up volumes, and writes Traefik labels. But for many templates
 * (including the popular twenty/n8n/ghost/etc.) it consistently fails
 * to do three host-level things that the public REST API does NOT
 * expose:
 *
 *   1. Rewrite the auto-generated `SERVICE_FQDN_*` / `SERVICE_URL_*`
 *      env vars from sslip.io defaults to the user's real FQDN. The
 *      user's domain is correctly stored on `service.applications[].fqdn`
 *      (so Traefik routing rules use it), but the env vars that the
 *      app embeds into its frontend bundle (e.g. Twenty's SERVER_URL)
 *      keep pointing at sslip.io. Result: SPA loads on real HTTPS
 *      then makes XHRs to insecure sslip.io URLs → "Mixed Content"
 *      errors and the app appears broken.
 *
 *   2. Generate the `traefik.http.services.<svc>.loadbalancer.server.port`
 *      label. Without it Traefik logs `error: port is missing` and
 *      returns 503 on every request.
 *
 *   3. Connect `coolify-proxy` to the resource's project network.
 *      Coolify generates a label `caddy_ingress_network=<uuid>`
 *      hinting that the proxy SHOULD live there, but never actually
 *      runs `docker network connect`. Result: even if Traefik
 *      discovers the right routing rules, it can't reach the upstream
 *      container.
 *
 * This module fixes all three after Coolify's queue finishes its work.
 *
 * Permissions model
 * -----------------
 * The `vibn-logs` SSH user has docker-group membership but no shell
 * sudo and no read access to `/data/coolify/services/<uuid>/` (Coolify
 * chmods that to 0700 root). We work around both by running a one-shot
 * `python:alpine` container that bind-mounts the path. The docker
 * daemon runs as root so it can read the directory; vibn-logs only
 * needs the docker socket.
 */

import { runOnCoolifyHost, type CoolifySshResult } from './coolify-ssh';

/** Slug for the Coolify-managed compose dir. */
export type ResourceKind = 'service' | 'application';

function composeDir(kind: ResourceKind, uuid: string): string {
  return kind === 'service'
    ? `/data/coolify/services/${uuid}`
    : `/data/coolify/applications/${uuid}`;
}

/** Shell-quote a single argument as a POSIX single-quoted string. */
function sq(s: string): string {
  return `'${String(s).replace(/'/g, `'\\''`)}'`;
}

// ─────────────────────────────────────────────────────────────────────
// Manual recovery helpers (apps.containers.up / .ps)
// ─────────────────────────────────────────────────────────────────────

/**
 * Run a `docker compose` subcommand inside the rendered compose dir
 * via a one-shot `docker:cli` container. Used by `apps.containers.up`
 * and `apps.containers.ps` for manual user recovery.
 *
 * Note: the *deployment* path (apps.create) no longer uses this
 * helper. apps.create lets Coolify's own queue do the deploy, then
 * applies the post-deploy fixes via `applyCoolifyPostDeployFixes`.
 */
async function composeRun(
  kind: ResourceKind,
  uuid: string,
  args: string[],
  opts: { timeoutMs?: number } = {},
): Promise<CoolifySshResult> {
  const dir = composeDir(kind, uuid);
  const cmd = [
    'docker', 'run', '--rm',
    '-v', sq(`${dir}:/work`),
    '-w', '/work',
    '-v', '/var/run/docker.sock:/var/run/docker.sock',
    '--network', 'host',
    'docker:cli',
    'compose', ...args.map(sq),
  ].join(' ');
  return runOnCoolifyHost(cmd, { timeoutMs: opts.timeoutMs ?? 600_000, maxBytes: 2_000_000 });
}

/** `docker compose up -d` — exposed as `apps.containers.up` for manual user recovery. */
export async function composeUp(
  kind: ResourceKind,
  uuid: string,
  opts: { timeoutMs?: number } = {},
): Promise<CoolifySshResult> {
  return composeRun(kind, uuid, ['up', '-d', '--remove-orphans'], opts);
}

/** `docker compose down` — stops + removes containers; volumes preserved. */
export async function composeDown(
  kind: ResourceKind,
  uuid: string,
  opts: { timeoutMs?: number } = {},
): Promise<CoolifySshResult> {
  return composeRun(kind, uuid, ['down'], opts);
}

/** `docker compose ps -a` — exposed as `apps.containers.ps`. */
export async function composePs(
  kind: ResourceKind,
  uuid: string,
): Promise<CoolifySshResult> {
  return composeRun(kind, uuid, ['ps', '-a', '--format', 'table'], { timeoutMs: 30_000 });
}

/**
 * Verify the rendered compose dir exists. Returns a friendly
 * null-on-missing instead of an opaque ENOENT.
 */
export async function composeDirExists(
  kind: ResourceKind,
  uuid: string,
): Promise<boolean> {
  const dir = composeDir(kind, uuid);
  const cmd = `docker run --rm -v ${sq(`${dir}:/w`)} alpine sh -c 'test -f /w/docker-compose.yml && echo OK || echo MISSING'`;
  const r = await runOnCoolifyHost(cmd, { timeoutMs: 30_000 });
  return r.stdout.trim().endsWith('OK');
}

// ─────────────────────────────────────────────────────────────────────
// Post-deploy fixes (apps.create's reliability layer)
// ─────────────────────────────────────────────────────────────────────

export interface CoolifyPostDeployOptions {
  /** Coolify service UUID. */
  uuid: string;
  /** Real custom FQDN, e.g. "crm.mark.vibnai.com" — must NOT include scheme. */
  fqdn: string;
  /** Compose service name of the user-facing app, e.g. "twenty". */
  publicAppName: string;
  /**
   * HTTP port the public app listens on inside the container.
   * If omitted, we try to detect it from `.env` (looking for
   * `SERVICE_FQDN_<APP>_<PORT>`). Falls back to 3000.
   */
  port?: number;
}

export interface CoolifyPostDeployResult {
  ok: boolean;
  steps: {
    envRewrite: { ok: boolean; detail: string };
    portLabel: { ok: boolean; detail: string };
    proxyNetwork: { ok: boolean; detail: string };
    recreate: { ok: boolean; detail: string };
    proxyRestart: { ok: boolean; detail: string };
  };
}

/**
 * Embed a Python script (UTF-8 bytes, base64-encoded) as a here-doc
 * arg to a docker-run that mounts the resource's compose dir at /work
 * and exposes the inputs as env vars. We use base64 to sidestep all
 * shell-escaping issues with python triple-quoted strings.
 */
function buildPythonRunner(script: string, env: Record<string, string>, dir: string, networkAttach = false): string {
  const b64 = Buffer.from(script, 'utf8').toString('base64');
  const envFlags = Object.entries(env)
    .map(([k, v]) => `-e ${sq(`${k}=${v}`)}`)
    .join(' ');
  // We need a Python image with sed-style file editing. python:3-alpine
  // is ~50MB and ships with regex + os out of the box.
  return [
    `echo ${sq(b64)} | base64 -d |`,
    'docker run --rm -i',
    `-v ${sq(`${dir}:/work`)}`,
    networkAttach ? '-v /var/run/docker.sock:/var/run/docker.sock' : '',
    envFlags,
    'python:3-alpine',
    'python -',
  ].filter(Boolean).join(' ');
}

/**
 * Apply the three post-deploy fixes to a freshly-deployed Coolify
 * service so the user-facing URL works on the very first hit.
 *
 * Idempotent. Safe to call multiple times — each step detects
 * whether the change is already in place and no-ops if so.
 *
 * Sequencing:
 *   1. Rewrite .env's SERVICE_FQDN_* / SERVICE_URL_* (cosmetic for
 *      Traefik but critical for any frontend that bakes the URL into
 *      its bundle from these env vars at startup).
 *   2. Inject the missing `loadbalancer.server.port` label into the
 *      compose file.
 *   3. Connect coolify-proxy to the project network so Traefik can
 *      reach the public container by its compose name.
 *   4. `docker compose up -d --force-recreate <publicAppName>` — this
 *      applies the new env (step 1) and label (step 2) without
 *      touching internal services like postgres/redis (which would
 *      cause DNS collisions if their networks changed).
 *   5. `docker restart coolify-proxy` so Traefik re-discovers the
 *      newly-attached network and the recreated container's labels.
 */
export async function applyCoolifyPostDeployFixes(
  opts: CoolifyPostDeployOptions,
): Promise<CoolifyPostDeployResult> {
  const { uuid, fqdn, publicAppName, port = 3000 } = opts;
  const dir = composeDir('service', uuid);

  const result: CoolifyPostDeployResult = {
    ok: false,
    steps: {
      envRewrite:    { ok: false, detail: '' },
      portLabel:     { ok: false, detail: '' },
      proxyNetwork:  { ok: false, detail: '' },
      recreate:      { ok: false, detail: '' },
      proxyRestart:  { ok: false, detail: '' },
    },
  };

  // ── Step 1+2 fused: rewrite .env + inject port label in one Python pass
  const editorScript = `
import os, re, sys

env_file = "/work/.env"
compose_file = "/work/docker-compose.yml"
fqdn = os.environ["NEW_FQDN"]
app  = os.environ["APP"]               # e.g. "twenty"
APP  = app.upper()
uuid = os.environ["UUID"]
port = os.environ["PORT"]

env_changes = []
if os.path.exists(env_file):
    with open(env_file, "r", encoding="utf-8") as f:
        lines = f.readlines()
    out = []
    for line in lines:
        new = line
        # SERVICE_FQDN_<APP>=<host>
        if re.match(rf"^SERVICE_FQDN_{re.escape(APP)}=", line):
            new = f"SERVICE_FQDN_{APP}={fqdn}\\n"
        # SERVICE_URL_<APP>=<scheme://host>
        elif re.match(rf"^SERVICE_URL_{re.escape(APP)}=", line):
            new = f"SERVICE_URL_{APP}=https://{fqdn}\\n"
        else:
            m = re.match(rf"^SERVICE_FQDN_{re.escape(APP)}_(\\d+)=", line)
            if m:
                new = f"SERVICE_FQDN_{APP}_{m.group(1)}={fqdn}:{m.group(1)}\\n"
            else:
                m = re.match(rf"^SERVICE_URL_{re.escape(APP)}_(\\d+)=", line)
                if m:
                    new = f"SERVICE_URL_{APP}_{m.group(1)}=https://{fqdn}:{m.group(1)}\\n"
        if new != line:
            env_changes.append(line.strip() + "  =>  " + new.strip())
        out.append(new)
    with open(env_file, "w", encoding="utf-8") as f:
        f.writelines(out)

# Inject port label into compose if missing.
label_changes = []
svc_id = f"{app}-svc-{uuid}"
needed_router_svc  = f"traefik.http.routers.https-0-{uuid}-{app}.service={svc_id}"
needed_loadbalance = f"traefik.http.services.{svc_id}.loadbalancer.server.port={port}"
http_router_svc    = f"traefik.http.routers.http-0-{uuid}-{app}.service={svc_id}"

with open(compose_file, "r", encoding="utf-8") as f:
    s = f.read()

if needed_loadbalance not in s:
    # Anchor: the existing tls=true label for the https router.
    anchor = f"traefik.http.routers.https-0-{uuid}-{app}.tls=true"
    if anchor in s:
        replacement = (
            anchor
            + "\\n      - " + http_router_svc
            + "\\n      - " + needed_router_svc
            + "\\n      - " + needed_loadbalance
        )
        s = s.replace(anchor, replacement, 1)  # only on the twenty service block
        with open(compose_file, "w", encoding="utf-8") as f:
            f.write(s)
        label_changes.append(f"injected loadbalancer.server.port={port}")
    else:
        label_changes.append(f"WARN: anchor '{anchor}' not found; label NOT injected")
else:
    label_changes.append("loadbalancer.server.port already present")

print("ENV_CHANGES:" + str(len(env_changes)))
for c in env_changes:
    print("  " + c)
print("LABEL_CHANGES:")
for c in label_changes:
    print("  " + c)
`;

  try {
    const cmd = buildPythonRunner(
      editorScript,
      { NEW_FQDN: fqdn, APP: publicAppName, UUID: uuid, PORT: String(port) },
      dir,
    );
    const r = await runOnCoolifyHost(cmd, { timeoutMs: 60_000 });
    if (r.code === 0) {
      const text = r.stdout.trim().slice(-1500);
      result.steps.envRewrite = { ok: true, detail: text };
      result.steps.portLabel  = { ok: !text.includes('WARN:'), detail: text };
    } else {
      const detail = (r.stderr || r.stdout).trim().slice(-500);
      result.steps.envRewrite = { ok: false, detail };
      result.steps.portLabel  = { ok: false, detail };
    }
  } catch (e) {
    const detail = e instanceof Error ? e.message : String(e);
    result.steps.envRewrite = { ok: false, detail };
    result.steps.portLabel  = { ok: false, detail };
  }

  // ── Step 3: attach coolify-proxy to project network
  try {
    // `|| true` swallows the "endpoint with name coolify-proxy already
    // exists in network" error which is the success-already-applied case.
    const r = await runOnCoolifyHost(
      `docker network connect ${sq(uuid)} coolify-proxy 2>&1 || true`,
      { timeoutMs: 10_000 },
    );
    const text = (r.stdout || r.stderr).trim();
    const alreadyAttached = /already exists/i.test(text);
    result.steps.proxyNetwork = {
      ok: true,
      detail: alreadyAttached ? 'already attached' : (text || 'attached'),
    };
  } catch (e) {
    result.steps.proxyNetwork = {
      ok: false,
      detail: e instanceof Error ? e.message : String(e),
    };
  }

  // ── Step 4: recreate ONLY the public app to apply env+label changes
  // (not the whole stack — postgres/redis/worker stay where they are)
  try {
    const r = await composeRun('service', uuid, ['up', '-d', '--force-recreate', publicAppName], {
      timeoutMs: 300_000,
    });
    const detail = (r.stderr || r.stdout)
      .replace(/\x1b\[[0-9;]*[a-zA-Z]/g, '')
      .replace(/[\x00-\x08\x0B-\x1F]/g, '')
      .trim()
      .slice(-400);
    // compose returns 0 on success, non-zero on partial failure;
    // sidecar `depends_on` timeouts can produce a non-zero exit
    // even though the public container started successfully.
    const probe = await runOnCoolifyHost(
      `docker ps --filter name=${publicAppName}-${uuid} --format '{{.Names}}'`,
      { timeoutMs: 8_000 },
    );
    const running = probe.stdout.trim().length > 0;
    result.steps.recreate = {
      ok: running,
      detail: running ? `${publicAppName}-${uuid} running` : detail,
    };
  } catch (e) {
    result.steps.recreate = {
      ok: false,
      detail: e instanceof Error ? e.message : String(e),
    };
  }

  // ── Step 5: nudge Traefik to re-discover via proxy restart
  try {
    const r = await runOnCoolifyHost(`docker restart coolify-proxy`, { timeoutMs: 30_000 });
    result.steps.proxyRestart = {
      ok: r.code === 0,
      detail: r.code === 0 ? 'restarted' : (r.stderr || r.stdout).trim().slice(-200),
    };
  } catch (e) {
    result.steps.proxyRestart = {
      ok: false,
      detail: e instanceof Error ? e.message : String(e),
    };
  }

  result.ok = Object.values(result.steps).every(s => s.ok);
  return result;
}