Files
dashcaddy/ops/shipdeck-bridge/bridge.py
T
DashCaddy Polish Loop 0dd8493f98 [grade=A] Shipdeck fleet module and manual deploy flow
Adds validated fleet install/lifecycle routes, bridge-backed Git and OCI workflows, persistent service cards, and the Local-tab Shipdeck deployment UI while preserving catalog and External flows.

Judge: urn:ump:if6udffdyelsf4qvskkr65ikhuprsjiajzij6h653fhf2zgyynzq
2026-09-15 11:13:29 -07:00

341 lines
14 KiB
Python

#!/usr/bin/env python3
"""shipdeck-bridge — token-gated HTTP wrapper around the shipdeck CLI.
Runs on the DNS2 HOST (not in the container) so that SSH keys, fleet-dns
credentials and root-level execution stay out of the DashCaddy web container.
The container reaches it via the docker bridge IP (172.17.0.1), the same
pattern as the Caddy admin API.
Endpoints (all require X-Shipdeck-Token matching /etc/shipdeck/bridge-token):
GET /api/health -> {ok, version}
GET /api/repos -> deployable repos (dirs with a Shipdeckfile)
GET /api/services -> journal-derived service inventory
GET /api/journal?service=N -> journal rows (newest first)
GET /api/status?service=N -> live re-probe output
POST /api/deploy {dir} -> run `shipdeck deploy <dir>` (serialized)
POST /api/rollback {service} -> run `shipdeck rollback <service>` (serialized)
POST /api/install {repo_url, service, subdomain?} -> GitHub clone+deploy+card (DC-131)
Security model:
- Listens on 127.0.0.1:8977 and 172.17.0.1:8977 ONLY (docker bridge + local).
- Every request must carry the shared token (0600 file, root-owned).
- Deploy dirs are validated: realpath must sit under SHIPDECK_REPOS_ROOT and
contain a Shipdeckfile. Service names are strict [a-z0-9-].
- The CLI is exec'd via argv lists — never a shell.
- Mutations (deploy/rollback) are serialized with a lock; status/journal are
concurrent.
"""
import json
import os
import re
import subprocess
import sys
import threading
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from urllib.parse import urlparse, parse_qs
from gh_install import gh_install # DC-131: GitHub -> card installs (init_shared below)
from gh_install import list_repos as gitea_list_repos # DC-133
from image_install import install_image
import image_install as _image
SHIPDECK_BIN = os.environ.get("SHIPDECK_BIN", "/usr/local/bin/shipdeck")
TOKEN_FILE = os.environ.get("SHIPDECK_BRIDGE_TOKEN_FILE", "/etc/shipdeck/bridge-token")
REPOS_ROOT = os.environ.get("SHIPDECK_REPOS_ROOT", "/root")
LISTEN_HOSTS = ["127.0.0.1", os.environ.get("SHIPDECK_BRIDGE_DOCKER_IP", "172.17.0.1")]
PORT = int(os.environ.get("SHIPDECK_BRIDGE_PORT", "8977"))
DEPLOY_TIMEOUT = int(os.environ.get("SHIPDECK_DEPLOY_TIMEOUT", "600"))
PROBE_TIMEOUT = 90
MAX_BODY = 65536
RE_SERVICE = re.compile(r"^[a-z0-9][a-z0-9-]{0,62}$")
mutation_lock = threading.Lock()
def read_token() -> str:
with open(TOKEN_FILE, "r", encoding="utf-8") as f:
token = f.read().strip()
if not token:
raise RuntimeError("SHIPDECK_BRIDGE_TOKEN_FILE is empty; refusing to start unauthenticated")
return token
TOKEN = read_token()
def run_shipdeck(args, timeout):
"""Exec the shipdeck CLI via argv (no shell). Returns (code, stdout+stderr)."""
try:
proc = subprocess.run(
[SHIPDECK_BIN] + args,
capture_output=True,
text=True,
timeout=timeout,
env={**os.environ, "SHIPDECK_JOURNAL": os.environ.get("SHIPDECK_JOURNAL", "/var/lib/shipdeck/journal.jsonl")},
)
return proc.returncode, (proc.stdout or "") + (proc.stderr or "")
except subprocess.TimeoutExpired:
return 124, f"shipdeck {' '.join(args)} timed out after {timeout}s"
except FileNotFoundError:
return 127, f"shipdeck binary not found at {SHIPDECK_BIN}"
# DC-131: hand shared state to the GitHub-install module (after run_shipdeck's
# def so everything it needs exists; avoids a circular import).
import gh_install as _gh
_gh.init_shared(RE_SERVICE, REPOS_ROOT, PORT, mutation_lock, run_shipdeck)
_image.init_shared(mutation_lock, run_shipdeck)
def parse_journal(raw: str):
"""Parse `shipdeck journal [name]` output rows robustly."""
rows = []
for line in raw.splitlines():
m = re.match(
r"^(\d{4}-\d{2}-\d{2}T[\d:]+Z)\s+(\S+)\s+(\S+)\s+epoch=(\d+)\s+(\S+)$",
line.strip(),
)
if m:
rows.append(
{
"time": m.group(1),
"service": m.group(2),
"action": m.group(3),
"epoch": int(m.group(4)),
"duration": m.group(5),
}
)
continue
# rollback rows can have 0.0s duration too; tolerate missing duration
m = re.match(r"^(\d{4}-\d{2}-\d{2}T[\d:]+Z)\s+(\S+)\s+(\S+)\s+epoch=(\d+)$", line.strip())
if m:
rows.append(
{
"time": m.group(1),
"service": m.group(2),
"action": m.group(3),
"epoch": int(m.group(4)),
"duration": None,
}
)
return rows
def service_inventory():
code, out = run_shipdeck(["journal"], PROBE_TIMEOUT)
if code != 0:
return None, out
rows = parse_journal(out)
inv = {}
for r in rows:
s = inv.setdefault(
r["service"],
{"name": r["service"], "host": None, "last_action": r["action"], "last_time": r["time"], "last_epoch": r["epoch"]},
)
if s["host"] is None:
code2, out2 = run_shipdeck(["status", r["service"]], PROBE_TIMEOUT)
m = re.search(r"host (\S+)", out2)
if m:
s["host"] = m.group(1)
return sorted(inv.values(), key=lambda x: x["last_time"], reverse=True), None
def list_repos():
"""Depth-1 scan of REPOS_ROOT for dirs containing a Shipdeckfile."""
repos = []
try:
for name in sorted(os.listdir(REPOS_ROOT)):
d = os.path.join(REPOS_ROOT, name)
if not os.path.isdir(d) or name.startswith("."):
continue
if os.path.isfile(os.path.join(d, "Shipdeckfile")):
repos.append({"dir": d, "name": name})
except OSError as e:
return None, str(e)
return repos, None
def resolve_deploy_dir(d):
"""Validate a deploy dir request. Returns (realpath, None) or (None, error)."""
if not isinstance(d, str) or not d.strip():
return None, "dir is required"
real = os.path.realpath(d)
root_real = os.path.realpath(REPOS_ROOT)
if real != root_real and not real.startswith(root_real + os.sep):
return None, "dir must be under " + root_real
if not os.path.isfile(os.path.join(real, "Shipdeckfile")):
return None, "no Shipdeckfile in " + real
return real, None
class Handler(BaseHTTPRequestHandler):
server_version = "shipdeck-bridge/1.0"
def log_message(self, fmt, *args): # quiet default access log
pass
def _authed(self) -> bool:
return bool(TOKEN) and self.headers.get("X-Shipdeck-Token", "") == TOKEN
def _send(self, code, payload):
body = json.dumps(payload).encode()
self.send_response(code)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
def _deny(self):
self._send(401, {"ok": False, "error": "invalid or missing X-Shipdeck-Token"})
# ----- GET -----
def do_GET(self):
if not self._authed():
return self._deny()
u = urlparse(self.path)
q = parse_qs(u.query)
if u.path == "/api/health":
code, out = run_shipdeck(["version"], 10)
return self._send(200, {"ok": code == 0, "shipdeck": out.strip()})
if u.path == "/api/repos":
repos, err = list_repos()
if err:
return self._send(500, {"ok": False, "error": err})
return self._send(200, {"ok": True, "repos": repos})
if u.path == "/api/services":
inv, err = service_inventory()
if err:
return self._send(500, {"ok": False, "error": err})
return self._send(200, {"ok": True, "services": inv})
if u.path == "/api/managed":
code, out = run_shipdeck(["ls", "--json"], PROBE_TIMEOUT)
if code != 0:
return self._send(500, {"ok": False, "error": "shipdeck ls failed", "output": out[-4000:]})
try:
services = json.loads(out)
except json.JSONDecodeError:
return self._send(500, {"ok": False, "error": "shipdeck ls returned invalid JSON"})
return self._send(200, {"ok": True, "services": services})
if u.path == "/api/logs":
service = (q.get("name") or [""])[0]
if not RE_SERVICE.match(service):
return self._send(400, {"ok": False, "error": "invalid service name"})
code, out = run_shipdeck(["logs", "-n", "300", service], PROBE_TIMEOUT)
return self._send(200 if code == 0 else 500, {"ok": code == 0, "output": out[-64000:]})
if u.path == "/api/shipdeckfile":
service = (q.get("name") or [""])[0]
if not RE_SERVICE.match(service):
return self._send(400, {"ok": False, "error": "invalid service name"})
code, out = run_shipdeck(["shipdeckfile", service], PROBE_TIMEOUT)
if code != 0:
return self._send(404, {"ok": False, "error": "Shipdeckfile not found"})
out = re.sub(r'(?im)^([A-Z0-9_]*(?:TOKEN|SECRET|PASSWORD|PASS|KEY)[A-Z0-9_]*)\s*=.*$', r'\1 = "<redacted>"', out)
return self._send(200, {"ok": True, "shipdeckfile": out})
if u.path == "/api/journal":
service = (q.get("service") or [""])[0]
args = ["journal"]
if service:
if not RE_SERVICE.match(service):
return self._send(400, {"ok": False, "error": "invalid service name"})
args.append(service)
code, out = run_shipdeck(args, PROBE_TIMEOUT)
return self._send(200 if code == 0 else 500, {"ok": code == 0, "rows": parse_journal(out), "raw": out[-4000:]})
if u.path == "/api/status":
service = (q.get("service") or [""])[0]
if not RE_SERVICE.match(service):
return self._send(400, {"ok": False, "error": "invalid service name"})
code, out = run_shipdeck(["status", service], PROBE_TIMEOUT)
return self._send(200 if code == 0 else 500, {"ok": code == 0, "output": out[-8000:]})
return self._send(404, {"ok": False, "error": "not found"})
# ----- POST -----
def do_POST(self):
if not self._authed():
return self._deny()
u = urlparse(self.path)
length = int(self.headers.get("Content-Length", "0") or 0)
if length > MAX_BODY:
return self._send(413, {"ok": False, "error": "body too large"})
raw = self.rfile.read(length) if length else b"{}"
try:
payload = json.loads(raw or b"{}")
except json.JSONDecodeError:
return self._send(400, {"ok": False, "error": "invalid JSON body"})
if u.path == "/api/deploy":
real, err = resolve_deploy_dir(payload.get("dir"))
if err:
return self._send(400, {"ok": False, "error": err})
with mutation_lock:
code, out = run_shipdeck(["deploy", real], DEPLOY_TIMEOUT)
return self._send(200 if code == 0 else 500, {"ok": code == 0, "exit": code, "output": out[-16000:]})
if u.path == "/api/rollback":
service = payload.get("service")
if not isinstance(service, str) or not RE_SERVICE.match(service):
return self._send(400, {"ok": False, "error": "invalid service name"})
with mutation_lock:
code, out = run_shipdeck(["rollback", service], DEPLOY_TIMEOUT)
return self._send(200 if code == 0 else 500, {"ok": code == 0, "exit": code, "output": out[-16000:]})
if u.path in {"/api/start", "/api/stop", "/api/restart", "/api/rm"}:
service = payload.get("name")
if not isinstance(service, str) or not RE_SERVICE.match(service):
return self._send(400, {"ok": False, "error": "invalid service name"})
action = u.path.rsplit("/", 1)[-1]
with mutation_lock:
code, out = run_shipdeck([action, service], DEPLOY_TIMEOUT)
return self._send(200 if code == 0 else 500, {"ok": code == 0, "exit": code, "output": out[-16000:]})
if u.path == "/api/image/install":
if not isinstance(payload, dict):
return self._send(400, {"ok": False, "error": "JSON object required"})
code, body = install_image(payload)
return self._send(code, body)
if u.path == "/api/gitea/repos":
code, body = gitea_list_repos(payload if isinstance(payload, dict) else {})
return self._send(code, body)
if u.path == "/api/install":
# DC-131: GitHub URL -> clone -> Shipdeckfile -> deploy -> metadata.
# Serialized with the same mutation lock; long timeout (build).
if not isinstance(payload, dict):
return self._send(400, {"ok": False, "error": "JSON object required"})
code, body = gh_install(payload)
return self._send(code, body)
return self._send(404, {"ok": False, "error": "not found"})
def main():
servers = []
last_err = None
for host in LISTEN_HOSTS:
try:
srv = ThreadingHTTPServer((host, PORT), Handler)
srv.daemon_threads = True
servers.append(srv)
except OSError as e:
last_err = e
print(f"shipdeck-bridge: FAILED to bind {host}:{PORT}: {e}", file=sys.stderr, flush=True)
if not servers:
# fail fast: systemd restarts us; a silently-dead daemon is worse
print(f"shipdeck-bridge: no listeners could bind on {LISTEN_HOSTS}:{PORT}; exiting", file=sys.stderr, flush=True)
sys.exit(1)
for srv in servers:
threading.Thread(target=srv.serve_forever, daemon=True).start()
print(f"shipdeck-bridge listening on {srv.server_address[0]}:{PORT}", flush=True)
if last_err is not None:
# degraded-but-alive: at least one listener bound; keep serving
print("shipdeck-bridge: running in DEGRADED mode (partial bind); check logs", file=sys.stderr, flush=True)
try:
threading.Event().wait()
except KeyboardInterrupt:
pass
if __name__ == "__main__":
main()