Files
compose-files/deploy/provision-stack.py
Bot 89a1e030c0 Add deploy/provision-stack.py — generic manifest-driven provisioner
Carried over from secrets-provisioning-v2 (PR #15), content identical.
Whole-file template render (hard-fail naming missing vars), env + Docker
secrets shipped via ssh stdin only, sha256-checksum skip-if-unchanged,
never prints a value. Stacks absent from the manifest exit 0 so legacy
case-entries keep handling them.
2026-09-07 21:43:57 -07:00

199 lines
7.5 KiB
Python

#!/usr/bin/env python3
"""provision-stack.py — manifest-driven env-file rendering + Docker secret
provisioning for one stack.
Usage (from the CI workspace root, inside the provision-secrets step):
python3 deploy/provision-stack.py <stack>
Reads secrets/secrets-map.yaml (data only — no code, no values) and, for the
named stack:
1. env_template -> renders the COMPLETE env file. Placeholders of the form
dollar-brace VARNAME are resolved from this process's environment (the
Woodpecker from_secret-backed vars). The whole file is rendered every
run; nothing is line-edited in place, so keys can never silently go
missing (root cause of the 2026-09-03 ai.env incident).
2. env_dest -> ships the rendered file to the Swarm manager over ssh stdin
(write-to-temp + atomic mv, mode 600). The rendered file never touches
the CI workspace disk under the repo (no chance of being committed) and
never appears on a command line.
3. docker_secrets -> for each swarm-secret-name -> ENV_VAR mapping, creates
or rotates the Docker secret. Values are passed via ssh stdin only.
Rotation uses the same sha256-checksum-label convention as
deploy/create-secrets.sh (unchanged secrets are skipped silently).
Safety properties:
- FAILS HARD (non-zero) if any referenced env var is missing or empty, and
lists the missing NAMES. A partial/broken render can never ship.
- FAILS HARD if any unresolved placeholder remains after rendering.
- NEVER prints a secret value — names and counts only.
- Requires SWARM_MANAGER_IP in the environment and a usable ssh identity
(both already set up by the provision-secrets step).
Stacks not present in the manifest exit 0 with a notice, so this script is
safe to call unconditionally; legacy case-entries in deploy.yml keep handling
unmigrated stacks.
"""
import hashlib
import os
import re
import subprocess
import sys
REPO_ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
MANIFEST_PATH = os.path.join(REPO_ROOT, "secrets", "secrets-map.yaml")
REMOTE_BASE = "/volume1/docker/compose-files"
PLACEHOLDER_RE = re.compile(r"\$\{([A-Za-z_][A-Za-z0-9_]*)\}")
SSH_OPTS = ["-o", "StrictHostKeyChecking=no"]
def die(msg: str) -> None:
print(f"ERROR: {msg}", file=sys.stderr)
sys.exit(1)
def load_manifest() -> dict:
try:
import yaml # py3-yaml, installed by the provision-secrets step
except ImportError:
die("PyYAML not available — provision-secrets step must apk add py3-yaml")
if not os.path.isfile(MANIFEST_PATH):
die(f"manifest not found: {MANIFEST_PATH}")
with open(MANIFEST_PATH, "r", encoding="utf-8") as fh:
data = yaml.safe_load(fh) or {}
stacks = data.get("stacks")
if not isinstance(stacks, dict):
die("manifest has no 'stacks:' mapping")
return stacks
def ssh_target() -> str:
ip = os.environ.get("SWARM_MANAGER_IP", "").strip()
if not ip:
die("SWARM_MANAGER_IP is empty — check Woodpecker repo secrets")
return f"root@{ip}"
def ssh_run(target: str, remote_cmd: str, stdin_data: bytes | None = None,
check: bool = True) -> subprocess.CompletedProcess:
proc = subprocess.run(
["ssh", *SSH_OPTS, target, remote_cmd],
input=stdin_data, capture_output=True,
)
if check and proc.returncode != 0:
# stderr may be verbose but must never contain our secret values —
# we only ever send values via stdin, never embed them in remote_cmd.
die(f"remote command failed (rc={proc.returncode}): {remote_cmd}\n"
f"{proc.stderr.decode(errors='replace').strip()}")
return proc
def render_template(template_path: str) -> str:
if not os.path.isfile(template_path):
die(f"env_template not found: {template_path}")
with open(template_path, "r", encoding="utf-8") as fh:
raw = fh.read()
referenced = sorted(set(PLACEHOLDER_RE.findall(raw)))
missing = [v for v in referenced
if not os.environ.get(v, "").strip()]
if missing:
die("template references vars that are MISSING or EMPTY in the CI "
"environment (add them via from_secret in "
".woodpecker/deploy.yml provision-secrets, and as Woodpecker "
"secrets):\n " + "\n ".join(missing))
rendered = PLACEHOLDER_RE.sub(lambda m: os.environ[m.group(1)], raw)
# Belt-and-braces: nothing placeholder-shaped may survive the render.
leftover = sorted(set(PLACEHOLDER_RE.findall(rendered)))
if leftover:
die("unresolved placeholders remain after rendering: "
+ ", ".join(leftover))
print(f" [render] {template_path}: {len(referenced)} secret placeholder(s) "
f"resolved: {', '.join(referenced)}")
return rendered
def ship_env_file(target: str, rendered: str, dest_rel: str) -> None:
dest = f"{REMOTE_BASE}/{dest_rel}"
tmp = f"{dest}.provision-tmp"
# Value travels over ssh stdin; never on a command line; atomic mv.
ssh_run(target,
f"umask 077 && cat > {tmp} && chmod 600 {tmp} && mv {tmp} {dest}",
stdin_data=rendered.encode())
keys = [ln.split("=", 1)[0] for ln in rendered.splitlines()
if "=" in ln and not ln.lstrip().startswith("#") and ln.strip()]
print(f" [env] shipped {dest} ({len(keys)} keys): {', '.join(keys)}")
def provision_docker_secret(target: str, name: str, env_var: str) -> None:
value = os.environ.get(env_var, "")
if not value.strip():
die(f"docker secret '{name}': env var {env_var} is missing/empty")
new_hash = hashlib.sha256(value.encode()).hexdigest()
probe = ssh_run(
target,
f"docker secret inspect {name} "
"--format '{{index .Spec.Labels \"checksum\"}}' 2>/dev/null || true",
check=True)
old_hash = probe.stdout.decode().strip()
if old_hash == new_hash:
print(f" [skip] docker secret {name} (unchanged)")
return
if old_hash:
rm = ssh_run(target, f"docker secret rm {name}", check=False)
if rm.returncode != 0:
die(f"docker secret {name}: value changed but removal failed — "
"it is probably referenced by a running service. Provision "
"under a versioned name (see vaultwarden_database_url_v2 "
"precedent) or scale the service down first.")
action = "update"
else:
action = "create"
ssh_run(target,
f"docker secret create --label checksum={new_hash} "
f"--label managed-by=woodpecker {name} -",
stdin_data=value.encode())
print(f" [{action}] docker secret {name} (value via stdin)")
def main() -> None:
if len(sys.argv) != 2:
die("usage: provision-stack.py <stack>")
stack = sys.argv[1]
stacks = load_manifest()
cfg = stacks.get(stack)
if cfg is None:
print(f" [info] stack '{stack}' not in secrets-map.yaml — "
"legacy provisioning (deploy.yml case-entry) applies. Nothing to do.")
return
target = ssh_target()
print(f"==> provision-stack: {stack}")
template_rel = cfg.get("env_template")
dest_rel = cfg.get("env_dest")
if template_rel and not dest_rel:
die("env_template set but env_dest missing in manifest")
if template_rel:
rendered = render_template(os.path.join(REPO_ROOT, template_rel))
ship_env_file(target, rendered, dest_rel)
for name, env_var in (cfg.get("docker_secrets") or {}).items():
provision_docker_secret(target, name, env_var)
print(f"==> provision-stack: {stack} done")
if __name__ == "__main__":
main()