feat: replace hardcoded service names with ServiceRegistry-driven Caddy and CoreDNS config
Unit Tests / test (push) Failing after 11s

Previously, CaddyManager and NetworkManager contained hardcoded lists of
service names (calendar, files, mail, webdav, etc.), meaning every new
service required a code change to appear in Caddy routes and DNS records.
Now both managers accept a service_registry parameter and derive their
service lists dynamically from the registry at runtime.

- CaddyManager: new _build_registry_service_routes() and
  _http01_service_pairs() methods pull routes from the registry
- NetworkManager: new _get_service_subdomains() method returns registry
  subdomains with a hardcoded fallback when no registry is wired in;
  _build_dns_records, stale-record detection, and service name sets all
  use the registry
- managers.py: service_registry constructed before network_manager so it
  can be injected into both CaddyManager and NetworkManager
- service_registry.py: validation chokepoint in get_caddy_routes() rejects
  invalid subdomain/backend values and reserved service names
- service_store_manager.py: _validate_manifest now validates top-level
  subdomain, backend, extra_subdomains, and extra_backends fields
- tests: 24 new tests covering registry-driven routing and DNS subdomain
  generation (test_caddy_registry_integration.py)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-28 18:27:52 -04:00
parent 63c0dfb9d9
commit 16fb362df7
12 changed files with 1312 additions and 46 deletions
+97 -13
View File
@@ -52,11 +52,13 @@ class CaddyManager(BaseServiceManager):
def __init__(self, config_manager=None,
data_dir: str = '/app/data',
config_dir: str = '/app/config',
service_bus=None):
service_bus=None,
service_registry=None):
super().__init__('caddy', data_dir, config_dir)
self.config_manager = config_manager
self.container_name = 'cell-caddy'
self.caddyfile_path = LIVE_CADDYFILE
self._service_registry = service_registry
# Consecutive health-check failure counter (reset on success or when
# the caller restarts the container).
self._health_failures = 0
@@ -187,6 +189,69 @@ class CaddyManager(BaseServiceManager):
f" }}"
)
def _build_registry_service_routes(self, domain: str) -> str:
"""Build named-matcher + handle blocks from the service registry.
Falls back to the hardcoded ``_build_core_service_routes`` when no
registry is wired or the registry returns nothing, so the method is
always safe to call even in tests that don't supply a registry.
"""
routes: List[Dict] = []
if self._service_registry is not None:
try:
routes = self._service_registry.get_caddy_routes()
except Exception as exc:
logger.warning('_build_registry_service_routes: registry error: %s', exc)
if not routes:
return self._build_core_service_routes(domain)
# Pre-seed with reserved names so no registry entry can squat them.
seen_matchers: set = {'api', 'webui'}
blocks: List[str] = []
for route in routes:
primary_sub = route['subdomain']
backend = route['backend']
extra_subs: List[str] = route.get('extra_subdomains') or []
extra_backends: Dict[str, str] = route.get('extra_backends') or {}
if primary_sub in seen_matchers:
logger.warning('Caddy: skipping duplicate/reserved matcher %r', primary_sub)
continue
seen_matchers.add(primary_sub)
# Subdomains that share the primary backend go in one matcher block.
shared = [primary_sub] + [s for s in extra_subs if s not in extra_backends]
host_list = ' '.join(f'{s}.{domain}' for s in shared)
blocks.append(
f' @{primary_sub} host {host_list}\n'
f' handle @{primary_sub} {{\n'
f' reverse_proxy {backend}\n'
f' }}'
)
# Extra subdomains with their own backends each get their own block.
for sub, sub_backend in extra_backends.items():
if sub in seen_matchers:
logger.warning('Caddy: skipping duplicate/reserved matcher %r', sub)
continue
seen_matchers.add(sub)
blocks.append(
f' @{sub} host {sub}.{domain}\n'
f' handle @{sub} {{\n'
f' reverse_proxy {sub_backend}\n'
f' }}'
)
# The api subdomain is always infrastructure — not delegated to the registry.
blocks.append(
f' @api host api.{domain}\n'
f' handle @api {{\n'
f' reverse_proxy cell-api:3000\n'
f' }}'
)
return '\n'.join(blocks)
@staticmethod
def _indent_routes(routes: str, spaces: int = 4) -> str:
"""Indent a multi-line route block by ``spaces`` columns."""
@@ -230,7 +295,7 @@ class CaddyManager(BaseServiceManager):
service_routes: str, core_routes: str) -> str:
"""pic_ngo mode: wildcard DNS-01 via the pic_ngo plugin."""
domain = f"{cell_name}.pic.ngo"
body = [self._build_core_service_routes(domain)]
body = [self._build_registry_service_routes(domain)]
if service_routes:
body.append(self._indent_routes(service_routes))
body.append(core_routes)
@@ -253,7 +318,7 @@ class CaddyManager(BaseServiceManager):
def _caddyfile_cloudflare(self, custom_domain: str,
service_routes: str, core_routes: str) -> str:
"""cloudflare mode: wildcard DNS-01 via the cloudflare plugin."""
body = [self._build_core_service_routes(custom_domain)]
body = [self._build_registry_service_routes(custom_domain)]
if service_routes:
body.append(self._indent_routes(service_routes))
body.append(core_routes)
@@ -273,7 +338,7 @@ class CaddyManager(BaseServiceManager):
service_routes: str, core_routes: str) -> str:
"""duckdns mode: DNS-01 via the duckdns plugin."""
domain = f"{cell_name}.duckdns.org"
body = [self._build_core_service_routes(domain)]
body = [self._build_registry_service_routes(domain)]
if service_routes:
body.append(self._indent_routes(service_routes))
body.append(core_routes)
@@ -299,15 +364,8 @@ class CaddyManager(BaseServiceManager):
out.append(core_routes)
out.append("}")
# One block per core service subdomain.
_core_services = [
('calendar', 'cell-radicale:5232'),
('mail', 'cell-rainloop:8888'),
('webmail', 'cell-rainloop:8888'),
('files', 'cell-filegator:8080'),
('webdav', 'cell-webdav:80'),
('api', 'cell-api:3000'),
]
# Build (subdomain, backend) pairs from registry when available.
_core_services = self._http01_service_pairs()
for subdomain, backend in _core_services:
out.append("")
out.append(f"{subdomain}.{host} {{")
@@ -330,6 +388,32 @@ class CaddyManager(BaseServiceManager):
out.append("}")
return "\n".join(out) + "\n"
def _http01_service_pairs(self) -> List[tuple]:
"""Return (subdomain, backend) pairs for http01 per-host blocks."""
pairs: List[tuple] = []
if self._service_registry is not None:
try:
for route in self._service_registry.get_caddy_routes():
pairs.append((route['subdomain'], route['backend']))
extra_subs: List[str] = route.get('extra_subdomains') or []
extra_backends: Dict[str, str] = route.get('extra_backends') or {}
for sub in extra_subs:
backend = extra_backends.get(sub, route['backend'])
pairs.append((sub, backend))
except Exception as exc:
logger.warning('_http01_service_pairs: registry error: %s', exc)
pairs = []
if not pairs:
pairs = [
('calendar', 'cell-radicale:5232'),
('mail', 'cell-rainloop:8888'),
('webmail', 'cell-rainloop:8888'),
('files', 'cell-filegator:8080'),
('webdav', 'cell-webdav:80'),
]
pairs.append(('api', 'cell-api:3000'))
return pairs
# ── filesystem + admin-API operations ─────────────────────────────────
def write_caddyfile(self, caddyfile_content: str) -> bool: