Compare commits
26 Commits
ops/runner
...
2bf339ce51
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2bf339ce51 | ||
|
|
0307ae16ae | ||
|
|
6c18f69cf2 | ||
|
|
47e2256556 | ||
|
|
9d77f8ba0e | ||
|
|
2f4be19c85 | ||
|
|
2a62c40990 | ||
|
|
7be98e5efc | ||
|
|
a65b356c9d | ||
|
|
08c17ef1b4 | ||
|
|
06f2f002b7 | ||
|
|
7ac4a8b4b7 | ||
|
|
90f2a86819 | ||
|
|
cbdefb2b23 | ||
|
|
1c36fe3a0a | ||
|
|
2b420ce8a4 | ||
|
|
5cbc1a06b1 | ||
|
|
9e7ee39b3a | ||
|
|
ae030a5f33 | ||
| bc8c35896f | |||
|
|
2cc91b6df0 | ||
| 0d2090fe81 | |||
|
|
bc3548e715 | ||
| 74333cc26b | |||
|
|
7310fb88c2 | ||
| 148bc87b9a |
@@ -532,7 +532,7 @@ spec:
|
||||
fsGroupChangePolicy: OnRootMismatch
|
||||
containers:
|
||||
- name: web
|
||||
image: localhost/fc-ttsreader-web:v20260518-sprint36-demo-finish-b132cbf
|
||||
image: localhost/fc-ttsreader-web:v20260603-s54cx14-pr29-live
|
||||
imagePullPolicy: Never
|
||||
ports:
|
||||
- containerPort: 5217
|
||||
@@ -554,6 +554,8 @@ spec:
|
||||
value: "/data/chapter-context.db"
|
||||
- name: TtsReader__Jobs__Root
|
||||
value: "/data/jobs"
|
||||
- name: TtsReader__Export__LocalCasRoot
|
||||
value: "/data/bundles/cas"
|
||||
- name: TtsReader__Piper__Host
|
||||
value: "10.0.57.17"
|
||||
- name: TtsReader__Piper__Port
|
||||
|
||||
@@ -58,7 +58,7 @@ spec:
|
||||
nodeName: rke2-server
|
||||
containers:
|
||||
- name: web
|
||||
image: localhost/fc-updater-web:v20260509-4162dca-authgate
|
||||
image: localhost/fc-updater-web:v202605310029-7974fc4
|
||||
imagePullPolicy: Never
|
||||
ports:
|
||||
- containerPort: 8080
|
||||
@@ -88,6 +88,8 @@ spec:
|
||||
value: Faith AI Mike Edition
|
||||
- name: FlowerCore__Updater__PublicShares__Links__0__Description
|
||||
value: Private release link for Mike's Faith AI bundle.
|
||||
- name: FlowerCore__Audit__Sinks__Loki__Enabled
|
||||
value: "false"
|
||||
- name: FlowerCore__Updater__Auth__Bootstrap__Enabled
|
||||
value: "true"
|
||||
- name: FlowerCore__Updater__Auth__Bootstrap__Username
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -46,7 +46,7 @@ spec:
|
||||
spec:
|
||||
containers:
|
||||
- name: intranet-web
|
||||
image: localhost/fc-intranet-web:v20260508-brochure-w1
|
||||
image: localhost/fc-intranet-web:v20260531-ttsreader-bridge
|
||||
imagePullPolicy: Never
|
||||
ports:
|
||||
- containerPort: 5300
|
||||
|
||||
@@ -25,7 +25,7 @@ metadata:
|
||||
role: github-actions-runner
|
||||
flowercore.io/managed-by: bluejay-infra
|
||||
spec:
|
||||
runStrategy: Always
|
||||
runStrategy: Halted
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
|
||||
@@ -207,20 +207,13 @@ spec:
|
||||
- port: 993
|
||||
targetPort: 993
|
||||
name: imaps
|
||||
---
|
||||
# TLS Certificate via cert-manager
|
||||
apiVersion: cert-manager.io/v1
|
||||
kind: Certificate
|
||||
metadata:
|
||||
name: mail-tls
|
||||
namespace: mail
|
||||
spec:
|
||||
secretName: mail-tls
|
||||
issuerRef:
|
||||
name: step-ca-acme
|
||||
kind: ClusterIssuer
|
||||
dnsNames:
|
||||
- mail.iamworkin.lan
|
||||
# --- mail-tls Certificate REMOVED 2026-06-01 ---
|
||||
# mail-tls is now managed OUTSIDE cert-manager: issued from step-ca's JWK 'admin'
|
||||
# provisioner and auto-renewed by a systemd timer on noc1 (step ca renew), which
|
||||
# writes the mail-tls secret directly. step-ca-acme only has an HTTP-01 (Traefik)
|
||||
# solver, but mail.iamworkin.lan must resolve to the dedicated MetalLB IP 10.0.56.202
|
||||
# (SMTP/IMAP), so HTTP-01 cannot validate. Do NOT re-add a cert-manager Certificate
|
||||
# here unless a DNS-01 solver is deployed for step-ca-acme.
|
||||
---
|
||||
# Traefik IngressRoute - Webmail placeholder
|
||||
apiVersion: traefik.io/v1alpha1
|
||||
|
||||
@@ -479,11 +479,11 @@ data:
|
||||
- "https://gitea.iamworkin.lan/"
|
||||
- "https://argocd.iamworkin.lan/"
|
||||
- "https://intranet.iamworkin.lan/"
|
||||
- "https://signage.iamworkin.lan/"
|
||||
- "https://signage.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
|
||||
- "https://kiosk.iamworkin.lan/"
|
||||
- "https://media.iamworkin.lan/"
|
||||
- "https://mysql.iamworkin.lan/"
|
||||
- "https://php.iamworkin.lan/"
|
||||
- "https://mysql.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
|
||||
- "https://php.iamworkin.lan/healthz" # root 401 auth-gated 2026-06-01; /healthz anon 200
|
||||
- "https://zabbix.iamworkin.lan/"
|
||||
- "https://desktop.iamworkin.lan/"
|
||||
- "https://print.iamworkin.lan/"
|
||||
|
||||
@@ -132,13 +132,18 @@ spec:
|
||||
initialDelaySeconds: 10
|
||||
periodSeconds: 5
|
||||
timeoutSeconds: 5
|
||||
# Hub baseline working set ~766Mi on 2026-05-25 (75% of prior 1Gi
|
||||
# limit). Bump to 1.5Gi / 1Gi to keep ~50% headroom; matches the
|
||||
# stampede-buffer pattern documented for multus
|
||||
# (feedback_k8s_cni_multus_sizing). CPU left alone — observed 54m
|
||||
# against a 500m limit, no contention.
|
||||
resources:
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 1Gi
|
||||
memory: 1536Mi
|
||||
requests:
|
||||
cpu: 250m
|
||||
memory: 512Mi
|
||||
memory: 1Gi
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
@@ -198,13 +203,18 @@ spec:
|
||||
port: 5555
|
||||
initialDelaySeconds: 15
|
||||
periodSeconds: 5
|
||||
# Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
|
||||
# -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
|
||||
# original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
|
||||
# was running 684Mi idle on the same cap. Matches the Firefox node's
|
||||
# tested-stable 2Gi limit. CPU unchanged.
|
||||
resources:
|
||||
limits:
|
||||
cpu: '1'
|
||||
memory: 1Gi
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: 500m
|
||||
memory: 512Mi
|
||||
memory: 1Gi
|
||||
volumeMounts:
|
||||
- mountPath: /dev/shm
|
||||
name: dshm
|
||||
@@ -378,13 +388,18 @@ spec:
|
||||
port: 5555
|
||||
initialDelaySeconds: 15
|
||||
periodSeconds: 5
|
||||
# Chromium-based browser node. Bumped from 1Gi -> 2Gi (req 512Mi
|
||||
# -> 1Gi) on 2026-05-25 — Edge had 51 OOMKills in 5d on the
|
||||
# original 1Gi cap (~1 OOM every 2.4h), and Chrome at maxSessions=2
|
||||
# was running 684Mi idle on the same cap. Matches the Firefox node's
|
||||
# tested-stable 2Gi limit. CPU unchanged.
|
||||
resources:
|
||||
limits:
|
||||
cpu: '1'
|
||||
memory: 1Gi
|
||||
memory: 2Gi
|
||||
requests:
|
||||
cpu: 500m
|
||||
memory: 512Mi
|
||||
memory: 1Gi
|
||||
volumeMounts:
|
||||
- mountPath: /dev/shm
|
||||
name: dshm
|
||||
|
||||
@@ -67,6 +67,7 @@ public sealed class FleetManifestLintTests
|
||||
["github-runner-chat"] = "https://github.com/astoltz/FlowerCore.Chat",
|
||||
["github-runner-mysql"] = "https://github.com/astoltz/FlowerCore.MySQL",
|
||||
["github-runner-kiosk-linux"] = "https://github.com/astoltz/FlowerCore.Kiosk.Linux",
|
||||
["github-runner-updater"] = "https://github.com/astoltz/FlowerCore.Updater",
|
||||
};
|
||||
|
||||
private static readonly HashSet<string> ScaledLinuxRunnerDeployments = new(StringComparer.Ordinal)
|
||||
@@ -80,6 +81,7 @@ public sealed class FleetManifestLintTests
|
||||
"github-runner-chat",
|
||||
"github-runner-mysql",
|
||||
"github-runner-kiosk-linux",
|
||||
"github-runner-updater",
|
||||
};
|
||||
|
||||
private static readonly IReadOnlyDictionary<string, string> WritableRunnerEnv = new Dictionary<string, string>(StringComparer.Ordinal)
|
||||
@@ -234,7 +236,7 @@ public sealed class FleetManifestLintTests
|
||||
{
|
||||
deployments.Should().ContainKey(expectedRunner.Key);
|
||||
|
||||
var container = deployments[expectedRunner.Key].ContainerMappings().Should().ContainSingle().Subject;
|
||||
var container = deployments[expectedRunner.Key].MainContainerMappings().Should().ContainSingle().Subject;
|
||||
EnvValue(container, "REPO_URL").Should().Be(expectedRunner.Value);
|
||||
EnvValue(container, "EPHEMERAL").Should().Be("true");
|
||||
EnvValue(container, "LABELS").Should().Be("self-hosted,linux,fc-build-linux");
|
||||
@@ -250,7 +252,7 @@ public sealed class FleetManifestLintTests
|
||||
{
|
||||
foreach (var deployment in GitHubRunnerDeployments().Values)
|
||||
{
|
||||
var container = deployment.ContainerMappings().Should().ContainSingle().Subject;
|
||||
var container = deployment.MainContainerMappings().Should().ContainSingle().Subject;
|
||||
|
||||
foreach (var expectedEnv in WritableRunnerEnv)
|
||||
{
|
||||
@@ -277,7 +279,10 @@ public sealed class FleetManifestLintTests
|
||||
foreach (var deploymentName in ScaledLinuxRunnerDeployments)
|
||||
{
|
||||
var deployment = deployments[deploymentName];
|
||||
ReplicaCount(deployment).Should().Be(2);
|
||||
// Scaled runners must have >= 2 replicas (avoid single-pod bottleneck).
|
||||
// Individual deployments may be tuned upward per CI activity — see
|
||||
// "runners: right-size replica counts per 14d CI activity (#24)".
|
||||
ReplicaCount(deployment).Should().BeGreaterOrEqualTo(2, $"{deploymentName} is in the scaled set and must run with at least 2 replicas");
|
||||
|
||||
var volumes = deployment.MappingSequence("spec", "template", "spec", "volumes");
|
||||
var claimNames = volumes
|
||||
@@ -303,6 +308,108 @@ public sealed class FleetManifestLintTests
|
||||
.Be("github-runner-nuget-cache");
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void Runners_MustNotPinToOperatorWorkstationHosts()
|
||||
{
|
||||
// CRITICAL SAFETY (operator directive 2026-05-26): BLUEJAY-WS is the
|
||||
// operator's primary workstation — host of the 1Password Connect
|
||||
// bearer token, fcadmin SSH keys to noc1, signing CA private keys,
|
||||
// and source for every FC repo. A self-hosted GitHub Actions runner
|
||||
// there would execute arbitrary PR code with that local access.
|
||||
// Build-side analog of the Sprint 9 NEW safe-account exclusion gate
|
||||
// (Puppet GPO/AppLocker/WDAC/audit-forwarder modules refuse to apply
|
||||
// on BLUEJAY-WS). This lint asserts no GitHub-runner Deployment in
|
||||
// apps/github-runner/ pins to a forbidden operator-workstation host
|
||||
// via nodeName, nodeSelector, nodeAffinity, or tolerations.
|
||||
// Existing legacy `bluejay-ws-sandbox-1` GitHub-registered runner is
|
||||
// out of scope here (it's a runtime registration, not a K8s
|
||||
// Deployment) — see CLAUDE.md "Common Mistakes" entry and
|
||||
// feedback_bluejay_ws_never_public_runner.md.
|
||||
var forbiddenHostPatterns = new[]
|
||||
{
|
||||
"bluejay-ws",
|
||||
"BLUEJAY-WS",
|
||||
"bluejay-ws.iamworkin.lan",
|
||||
"iamworkin-ws",
|
||||
};
|
||||
|
||||
bool ContainsForbidden(string? value) =>
|
||||
!string.IsNullOrWhiteSpace(value)
|
||||
&& forbiddenHostPatterns.Any(pattern => value!.Contains(pattern, StringComparison.OrdinalIgnoreCase));
|
||||
|
||||
var violations = GitHubRunnerDeployments().Values.SelectMany(deployment =>
|
||||
{
|
||||
var local = new List<string>();
|
||||
var podSpec = ManifestNodeExtensions.Mapping(deployment.Root, "spec", "template", "spec");
|
||||
if (podSpec is null)
|
||||
{
|
||||
return local;
|
||||
}
|
||||
|
||||
// nodeName: pins the pod to a specific node by name.
|
||||
var nodeName = ManifestNodeExtensions.Scalar(podSpec, "nodeName");
|
||||
if (ContainsForbidden(nodeName))
|
||||
{
|
||||
local.Add($"{deployment.Name} sets nodeName='{nodeName}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
|
||||
// nodeSelector: dict of label → value pinning the pod to nodes
|
||||
// carrying matching labels. Examples that would trip this:
|
||||
// kubernetes.io/hostname: bluejay-ws
|
||||
// flowercore.io/host: bluejay-ws.iamworkin.lan
|
||||
var nodeSelector = ManifestNodeExtensions.Mapping(podSpec, "nodeSelector");
|
||||
if (nodeSelector is not null)
|
||||
{
|
||||
foreach (var entry in nodeSelector.Children)
|
||||
{
|
||||
var key = entry.Key is YamlScalarNode keyScalar ? keyScalar.Value : null;
|
||||
var value = entry.Value is YamlScalarNode valueScalar ? valueScalar.Value : null;
|
||||
if (ContainsForbidden(value))
|
||||
{
|
||||
local.Add($"{deployment.Name} has nodeSelector entry '{key}: {value}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// nodeAffinity: matchExpressions over node labels.
|
||||
foreach (var term in ManifestNodeExtensions.MappingSequence(podSpec, "affinity", "nodeAffinity", "requiredDuringSchedulingIgnoredDuringExecution", "nodeSelectorTerms"))
|
||||
{
|
||||
foreach (var expr in ManifestNodeExtensions.MappingSequence(term, "matchExpressions"))
|
||||
{
|
||||
var key = ManifestNodeExtensions.Scalar(expr, "key");
|
||||
foreach (var valueNode in ManifestNodeExtensions.ScalarSequence(expr, "values"))
|
||||
{
|
||||
if (ContainsForbidden(valueNode))
|
||||
{
|
||||
local.Add($"{deployment.Name} has nodeAffinity matchExpression '{key}' value '{valueNode}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// tolerations: scheduling onto a tainted operator-workstation
|
||||
// node would let the runner run there. Forbid any toleration
|
||||
// value that names the workstation.
|
||||
foreach (var toleration in ManifestNodeExtensions.MappingSequence(podSpec, "tolerations"))
|
||||
{
|
||||
var key = ManifestNodeExtensions.Scalar(toleration, "key");
|
||||
var value = ManifestNodeExtensions.Scalar(toleration, "value");
|
||||
if (ContainsForbidden(key))
|
||||
{
|
||||
local.Add($"{deployment.Name} has toleration key '{key}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
if (ContainsForbidden(value))
|
||||
{
|
||||
local.Add($"{deployment.Name} has toleration value '{value}' which targets a forbidden operator-workstation host.");
|
||||
}
|
||||
}
|
||||
|
||||
return local;
|
||||
}).ToList();
|
||||
|
||||
violations.Should().BeEmpty("BLUEJAY-WS / iamworkin-ws must never host a fleet GitHub Actions runner; see CLAUDE.md 'Registering BLUEJAY-WS as a fleet GitHub Actions runner' and feedback_bluejay_ws_never_public_runner.md");
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void Monitoring_MustAlertWhenLinuxRunnerDeploymentIsUnavailable()
|
||||
{
|
||||
@@ -890,6 +997,22 @@ internal sealed record ManifestDocument(
|
||||
.ToList();
|
||||
}
|
||||
|
||||
// MainContainerMappings excludes initContainers. Use this when asserting
|
||||
// properties of the primary container (env, image, volumeMounts) where an
|
||||
// initContainer would be a false-positive match — e.g. the GitHub runner
|
||||
// image's `setup-runner-home` initContainer should not count toward the
|
||||
// single-container assertions on the runner deployments.
|
||||
public IReadOnlyList<YamlMappingNode> MainContainerMappings()
|
||||
{
|
||||
var podSpec = PodSpec();
|
||||
if (podSpec is null)
|
||||
{
|
||||
return Array.Empty<YamlMappingNode>();
|
||||
}
|
||||
|
||||
return ManifestNodeExtensions.MappingSequence(podSpec, "containers").ToList();
|
||||
}
|
||||
|
||||
public IReadOnlyList<ContainerSpec> ContainerSpecs()
|
||||
{
|
||||
return ContainerMappings()
|
||||
|
||||
Reference in New Issue
Block a user