mirror of
https://github.com/kevinveenbirkenbach/computer-playbook.git
synced 2026-11-10 12:47:04 +00:00
kevinveenbirkenbachandClaude Opus 4.8
f4172c547a
A native-metrics app on a node-local force_bridge network cannot be joined or resolved by a swarm-wide prometheus: the stack deploy fails with the network scope error and the scrape job would flap as permanently down. native_metrics_apps now drops those apps at the source (DEPLOYMENT_MODE swarm + networks.local.force_bridge), covering all four call sites (network precreate, compose service networks, external-networks block, scrape include) without per-template guards. DEPLOYMENT_MODE is templated without a default so a missing value fails loudly. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
84 lines
2.9 KiB
Python
84 lines
2.9 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
from ansible.plugins.loader import lookup_loader
|
|
from ansible.plugins.lookup import LookupBase
|
|
|
|
from utils.cache import ROLES_DIR
|
|
from utils.roles.applications.config import get as get_app_conf
|
|
|
|
|
|
class LookupModule(LookupBase):
|
|
"""
|
|
Return a sorted list of deployed application IDs that satisfy all of:
|
|
1. services.prometheus.native_metrics.enabled: true in their role config
|
|
2. a prometheus.yml.j2 template at roles/<app_id>/templates/
|
|
3. reachable from this prometheus: NOT on a node-local force_bridge
|
|
network under swarm, which a swarm prometheus can neither join nor
|
|
resolve. This is the single point that gates force_bridge apps out of
|
|
the native-metrics precreate + scrape.
|
|
|
|
Used by web-app-prometheus/templates/configuration/prometheus.yml.j2 to auto-discover apps
|
|
that expose a native /metrics endpoint without hardcoding each app name.
|
|
|
|
Usage in a template:
|
|
{% for app_id in lookup('native_metrics_apps') %}
|
|
{% include 'roles/' + app_id + '/templates/prometheus.yml.j2' %}
|
|
{% endfor %}
|
|
|
|
'applications' is obtained via lookup('applications'), the merged-config SPOT.
|
|
"""
|
|
|
|
def run(
|
|
self,
|
|
terms: list[Any],
|
|
variables: dict[str, Any] | None = None,
|
|
**kwargs: Any,
|
|
) -> list[list[str]]:
|
|
vars_ = variables or getattr(self._templar, "available_variables", {}) or {}
|
|
|
|
roles_dir = ROLES_DIR
|
|
applications = lookup_loader.get(
|
|
"applications", loader=self._loader, templar=getattr(self, "_templar", None)
|
|
).run([], variables=vars_)[0]
|
|
|
|
group_names: list[str] = vars_.get("group_names", [])
|
|
is_swarm = (
|
|
str(self._templar.template(vars_["DEPLOYMENT_MODE"])).strip() == "swarm"
|
|
)
|
|
|
|
result: list[str] = []
|
|
for app_id in sorted(applications.keys()):
|
|
if app_id not in group_names:
|
|
continue
|
|
enabled = get_app_conf(
|
|
applications=applications,
|
|
application_id=app_id,
|
|
config_path="services.prometheus.native_metrics.enabled",
|
|
strict=False,
|
|
default=False,
|
|
skip_missing_app=True,
|
|
)
|
|
if not enabled:
|
|
continue
|
|
|
|
scrape_template = roles_dir / app_id / "templates" / "prometheus.yml.j2"
|
|
if not scrape_template.exists():
|
|
continue
|
|
|
|
force_bridge = get_app_conf(
|
|
applications=applications,
|
|
application_id=app_id,
|
|
config_path="networks.local.force_bridge",
|
|
strict=False,
|
|
default=False,
|
|
skip_missing_app=True,
|
|
)
|
|
if is_swarm and bool(force_bridge):
|
|
continue
|
|
|
|
result.append(app_id)
|
|
|
|
return [result]
|