fix(oidc): remove the API-server restart Jobs from GitOps

The oidc-bootstrap ArgoCD Application runs with selfHeal and prune. Three Jobs in restart-apiserver.yaml kill the kube-apiserver process on each control plane, and bootstrap.yaml carried a fourth Job that deletes the mirror pods. ArgoCD recreated a deleted Job within two minutes, so the kill repeated and every API server reached CrashLoopBackOff. Remove all four. The OIDC authenticator already loaded, so the one-shot restart is not needed again.
fix(cluster): grant queue-operator watches and retire the macOS workload
2026-10-24 15:06:32 -07:00 · 2026-10-24 04:03:02 -07:00 · 2026-10-24 10:47:14 +00:00 · 2026-10-24 03:46:29 -07:00 · 2026-10-24 10:41:17 +00:00 · 2026-10-24 10:41:09 +00:00
20 changed files with 579 additions and 234 deletions
@@ -0,0 +1,37 @@
+{
+  "schema_version": 1,
+  "diagram_type": "architecture",
+  "meta": {
+    "title": "Poimen Memory — Schema Relations",
+    "quality_profile": "showcase",
+    "viewBox": [900, 480]
+  },
+  "components": [
+    { "id": "node", "type": "database", "label": "memory_node", "sublabel": "Episodes (raw messages)", "pos": [40, 60], "size": [150, 55], "tag": "BIGSERIAL" },
+    { "id": "entity", "type": "database", "label": "memory_entity", "sublabel": "Extracted entities", "pos": [260, 60], "size": [150, 55], "tag": "UUID" },
+    { "id": "edge", "type": "database", "label": "memory_edge", "sublabel": "Facts / relationships", "pos": [480, 60], "size": [150, 55], "tag": "UUID" },
+    { "id": "community", "type": "database", "label": "memory_community", "sublabel": "Entity clusters", "pos": [700, 60], "size": [150, 55], "tag": "UUID" },
+    { "id": "pgvector", "type": "cloud", "label": "pgvector HNSW", "sublabel": "768-dim cosine search", "pos": [140, 260], "size": [160, 55], "tag": "nomic-embed-v2" },
+    { "id": "tsvector", "type": "cloud", "label": "pg ts_rank", "sublabel": "Full-text search", "pos": [400, 260], "size": [160, 55], "tag": "GIN index" },
+    { "id": "tenant", "type": "security", "label": "tenant_id", "sublabel": "Multi-tenant isolation", "pos": [660, 260], "size": [140, 55], "tag": "W7 / mig 014" }
+  ],
+  "boundaries": [
+    { "kind": "region", "label": "Temporal Knowledge Graph (Zep §2)", "wraps": ["node", "entity", "edge", "community"] },
+    { "kind": "security-group", "label": "Search & Isolation", "wraps": ["pgvector", "tsvector", "tenant"] }
+  ],
+  "connections": [
+    { "id": "node-entity", "from": "node", "to": "entity", "variant": "emphasis" },
+    { "id": "entity-edge", "from": "entity", "to": "edge", "variant": "emphasis" },
+    { "id": "entity-community", "from": "community", "to": "entity", "variant": "dashed" },
+    { "id": "edge-node", "from": "edge", "to": "node", "variant": "dashed" },
+    { "id": "entity-vec", "from": "entity", "to": "pgvector", "variant": "default" },
+    { "id": "entity-fts", "from": "entity", "to": "tsvector", "variant": "dashed" },
+    { "id": "edge-fts", "from": "edge", "to": "tsvector", "variant": "dashed" },
+    { "id": "tenant-all", "from": "tenant", "to": "entity", "variant": "security" }
+  ],
+  "cards": [
+    { "dot": "emerald", "title": "Three-Tier Graph", "items": ["memory_node → episode subgraph", "memory_entity → entity subgraph", "memory_edge → fact relationships", "memory_community → clusters (Phase 4)"] },
+    { "dot": "rose", "title": "Bi-Temporal", "items": ["t_valid / t_invalid: event time", "t_created / t_expired: transaction time", "Contradiction: active → candidate → confirmed"] },
+    { "dot": "cyan", "title": "Search", "items": ["HNSW: name, summary, fact embeddings", "ts_rank: BM25 fallback (always available)", "tenant_id: per-table isolation (mig 014)"] }
+  ]
+}
@@ -0,0 +1,158 @@
+{
+  "schema_version": 1,
+  "diagram_type": "dataflow",
+  "meta": {
+    "title": "Poimen Memory \u2014 Schema Relations",
+    "viewBox": [
+      960,
+      480
+    ],
+    "quality_profile": "showcase"
+  },
+  "stages": [
+    {
+      "label": "Episodes"
+    },
+    {
+      "label": "Entities"
+    },
+    {
+      "label": "Relationships"
+    },
+    {
+      "label": "Indexes"
+    }
+  ],
+  "nodes": [
+    {
+      "id": "node",
+      "type": "database",
+      "label": "memory_node",
+      "sublabel": "Raw messages",
+      "stage": 0,
+      "row": 0,
+      "tag": "BIGSERIAL"
+    },
+    {
+      "id": "entity",
+      "type": "database",
+      "label": "memory_entity",
+      "sublabel": "Named entities",
+      "stage": 1,
+      "row": 0,
+      "tag": "UUID + tenant_id"
+    },
+    {
+      "id": "community",
+      "type": "database",
+      "label": "memory_community",
+      "sublabel": "Clusters (Phase 4)",
+      "stage": 1,
+      "row": 1,
+      "tag": "UUID"
+    },
+    {
+      "id": "edge",
+      "type": "database",
+      "label": "memory_edge",
+      "sublabel": "Facts + bi-temporal",
+      "stage": 2,
+      "row": 0,
+      "tag": "UUID + tenant_id"
+    },
+    {
+      "id": "hnsw",
+      "type": "cloud",
+      "label": "HNSW Index",
+      "sublabel": "768-dim cosine",
+      "stage": 3,
+      "row": 0,
+      "tag": "pgvector"
+    },
+    {
+      "id": "fts",
+      "type": "cloud",
+      "label": "GIN Index",
+      "sublabel": "ts_rank BM25",
+      "stage": 3,
+      "row": 1,
+      "tag": "full-text"
+    }
+  ],
+  "flows": [
+    {
+      "from": "node",
+      "to": "entity",
+      "label": "LLM extraction",
+      "classification": "ingest",
+      "variant": "emphasis",
+      "route": "straight"
+    },
+    {
+      "from": "entity",
+      "to": "edge",
+      "label": "source + target FK",
+      "classification": "foreign key",
+      "variant": "emphasis",
+      "route": "straight"
+    },
+    {
+      "from": "entity",
+      "to": "community",
+      "label": "community_id",
+      "classification": "membership",
+      "variant": "dashed",
+      "route": "straight",
+      "labelDy": 30
+    },
+    {
+      "from": "edge",
+      "to": "hnsw",
+      "classification": "vector",
+      "variant": "default",
+      "route": "straight",
+      "label": "embedding",
+      "labelDy": -30
+    },
+    {
+      "from": "edge",
+      "to": "fts",
+      "label": "fact text",
+      "classification": "text",
+      "variant": "dashed",
+      "route": "vertical-channel",
+      "labelDy": 30
+    }
+  ],
+  "cards": [
+    {
+      "dot": "emerald",
+      "title": "Three-Tier Graph",
+      "items": [
+        "memory_node \u2192 episodes (raw messages)",
+        "memory_entity \u2192 extracted entities",
+        "memory_edge \u2192 facts between entities",
+        "memory_community \u2192 clusters (Phase 4)"
+      ]
+    },
+    {
+      "dot": "rose",
+      "title": "Bi-Temporal + Tenant",
+      "items": [
+        "t_valid/t_invalid: when true in reality",
+        "t_created/t_expired: system transaction time",
+        "tenant_id: row-level multi-tenant isolation",
+        "Contradiction: active \u2192 candidate \u2192 confirmed"
+      ]
+    },
+    {
+      "dot": "cyan",
+      "title": "Search Indexes",
+      "items": [
+        "HNSW: name, summary, fact embeddings",
+        "GIN: ts_rank on name+summary and fact",
+        "RRF fusion: sem_weight + lex_weight"
+      ]
+    }
+  ]
+}
@@ -0,0 +1,63 @@
+{
+  "schema_version": 1,
+  "diagram_type": "sequence",
+  "meta": {
+    "title": "Service Acting on Behalf of User",
+    "viewBox": [1000, 600],
+    "column_fit": "spread",
+    "quality_profile": "showcase"
+  },
+  "participants": [
+    { "id": "user", "type": "external", "label": "User", "sublabel": "browser" },
+    { "id": "app", "type": "frontend", "label": "Web App", "sublabel": "poimen UI" },
+    { "id": "authentik", "type": "security", "label": "Authentik", "sublabel": "OIDC" },
+    { "id": "worker", "type": "backend", "label": "Backend Worker", "sublabel": "temporal/queue" },
+    { "id": "memory", "type": "backend", "label": "Memory API", "sublabel": "poimen-memory" },
+    { "id": "jwks", "type": "security", "label": "JWKS", "sublabel": "RS256" }
+  ],
+  "segments": [
+    { "from": 150, "to": 260, "label": "User Auth" },
+    { "from": 270, "to": 370, "label": "Delegation" },
+    { "from": 380, "to": 510, "label": "Downstream" }
+  ],
+  "messages": [
+    { "id": "login", "from": "user", "to": "app", "y": 165, "label": "login (OIDC)", "variant": "default" },
+    { "id": "oidc-flow", "from": "app", "to": "authentik", "y": 200, "label": "authorization_code flow", "variant": "emphasis" },
+    { "id": "user-jwt", "from": "authentik", "to": "app", "y": 235, "label": "user JWT {groups,roles}", "variant": "return" },
+    { "id": "trigger-job", "from": "user", "to": "app", "y": 285, "label": "trigger async job", "variant": "default" },
+    { "id": "queue-job", "from": "app", "to": "worker", "y": 320, "label": "enqueue job + user JWT", "variant": "emphasis", "note": "JWT passed as job metadata" },
+    { "id": "job-ack", "from": "worker", "to": "app", "y": 355, "label": "job queued", "variant": "return" },
+    { "id": "call-memory", "from": "worker", "to": "memory", "y": 400, "label": "POST /memory/ingest", "variant": "emphasis", "note": "Bearer <user JWT>" },
+    { "id": "fetch-jwks", "from": "memory", "to": "jwks", "y": 435, "label": "GET /jwks", "variant": "dashed" },
+    { "id": "jwks-keys", "from": "jwks", "to": "memory", "y": 470, "label": "RSA pubkey", "variant": "return" },
+    { "id": "ingest-ok", "from": "memory", "to": "worker", "y": 505, "label": "202 Accepted", "variant": "return", "note": "uses USER's groups/roles" }
+  ],
+  "activations": [
+    { "participant": "user", "from": 160, "to": 291, "type": "external" },
+    { "participant": "app", "from": 165, "to": 361, "type": "frontend" },
+    { "participant": "authentik", "from": 195, "to": 241, "type": "security" },
+    { "participant": "worker", "from": 315, "to": 511, "type": "backend" },
+    { "participant": "memory", "from": 395, "to": 511, "type": "backend" },
+    { "participant": "jwks", "from": 430, "to": 476, "type": "security" }
+  ],
+  "cards": [
+    {
+      "dot": "emerald",
+      "title": "Delegation Pattern",
+      "items": [
+        "User JWT travels with the job payload",
+        "Worker uses user's token for downstream",
+        "Memory sees USER as the principal"
+      ]
+    },
+    {
+      "dot": "rose",
+      "title": "Security Model",
+      "items": [
+        "No service-account escalation",
+        "User's permissions bound the action",
+        "Audit trail traces to user.sub"
+      ]
+    }
+  ]
+}
@@ -0,0 +1,42 @@
+{
+  "schema_version": 1,
+  "diagram_type": "architecture",
+  "meta": {
+    "title": "Memory Service Fine-Grained RBAC",
+    "quality_profile": "showcase",
+    "viewBox": [900, 520]
+  },
+  "components": [
+    { "id": "jwt", "type": "security", "label": "JWT Token", "sublabel": "groups[] + roles[]", "pos": [40, 60], "size": [140, 60], "tag": "Authentik" },
+    { "id": "cap-check", "type": "backend", "label": "Capability Check", "sublabel": "has_capability()", "pos": [260, 60], "size": [160, 60], "tag": "Phase 1" },
+    { "id": "scope-checker", "type": "backend", "label": "Scope Checker", "sublabel": "filter_resources()", "pos": [500, 60], "size": [160, 60], "tag": "Phase 2" },
+    { "id": "decision", "type": "backend", "label": "AccessDecision", "sublabel": "Allow / Deny", "pos": [740, 60], "size": [130, 60] },
+    { "id": "project-scope", "type": "database", "label": "ProjectScope", "sublabel": "dev/staging/prod/*", "pos": [40, 200], "size": [140, 55] },
+    { "id": "visibility-scope", "type": "database", "label": "VisibilityScope", "sublabel": "public/private", "pos": [220, 200], "size": [140, 55] },
+    { "id": "owner-scope", "type": "database", "label": "OwnerScope", "sublabel": "self/any/user", "pos": [400, 200], "size": [140, 55] },
+    { "id": "group-scope", "type": "database", "label": "GroupScope", "sublabel": "in_any_group()", "pos": [580, 200], "size": [140, 55] },
+    { "id": "entities", "type": "database", "label": "Entities", "sublabel": "memory_entity", "pos": [40, 340], "size": [120, 50] },
+    { "id": "edges", "type": "database", "label": "Edges", "sublabel": "memory_edge", "pos": [200, 340], "size": [120, 50] },
+    { "id": "projects", "type": "database", "label": "Projects", "sublabel": "project_id", "pos": [360, 340], "size": [120, 50] },
+    { "id": "convos", "type": "database", "label": "Conversations", "sublabel": "owner_id", "pos": [520, 340], "size": [120, 50] }
+  ],
+  "boundaries": [
+    { "kind": "security-group", "label": "Access Control Pipeline", "wraps": ["cap-check", "scope-checker", "decision"] },
+    { "kind": "region", "label": "Scope Checkers", "wraps": ["project-scope", "visibility-scope", "owner-scope", "group-scope"] },
+    { "kind": "region", "label": "Protected Resources", "wraps": ["entities", "edges", "projects", "convos"] }
+  ],
+  "connections": [
+    { "id": "jwt-to-cap", "from": "jwt", "to": "cap-check", "label": "claims", "variant": "emphasis" },
+    { "id": "cap-to-scope", "from": "cap-check", "to": "scope-checker", "variant": "emphasis" },
+    { "id": "scope-to-decision", "from": "scope-checker", "to": "decision", "variant": "emphasis" },
+    { "id": "scope-to-proj", "from": "scope-checker", "to": "project-scope", "variant": "dashed", "fromSide": "bottom", "toSide": "top" },
+    { "id": "scope-to-vis", "from": "scope-checker", "to": "visibility-scope", "variant": "dashed", "fromSide": "bottom", "toSide": "top" },
+    { "id": "scope-to-owner", "from": "scope-checker", "to": "owner-scope", "variant": "dashed", "fromSide": "bottom", "toSide": "top" },
+    { "id": "scope-to-group", "from": "scope-checker", "to": "group-scope", "variant": "dashed", "fromSide": "bottom", "toSide": "top" }
+  ],
+  "cards": [
+    { "dot": "emerald", "title": "Phase 1: Capability", "items": ["has_capability(memory:read)", "Checks roles[] claim", "Binary allow/deny"] },
+    { "dot": "rose", "title": "Phase 2: Scope", "items": ["Project: dev/staging/prod", "Visibility: public/private", "Owner: self-owned only", "Group: poimen-admins/devs"] },
+    { "dot": "cyan", "title": "JWT Claims", "items": ["groups: user.groups", "roles: attributes.roles", "permissions: group names"] }
+  ]
+}
@@ -0,0 +1,54 @@
+{
+  "schema_version": 1,
+  "diagram_type": "sequence",
+  "meta": {
+    "title": "Service-to-Service (M2M) Authentication",
+    "viewBox": [1080, 520],
+    "column_fit": "spread",
+    "quality_profile": "showcase"
+  },
+  "participants": [
+    { "id": "worker", "type": "backend", "label": "Ingest Worker", "sublabel": "temporal/cron" },
+    { "id": "authentik", "type": "security", "label": "Authentik", "sublabel": "OIDC provider" },
+    { "id": "memory", "type": "backend", "label": "Memory Service", "sublabel": "poimen-memory" },
+    { "id": "jwks", "type": "security", "label": "JWKS", "sublabel": "RS256 keys" }
+  ],
+  "segments": [
+    { "from": 150, "to": 230, "label": "Token Mint" },
+    { "from": 240, "to": 380, "label": "API + RBAC" }
+  ],
+  "messages": [
+    { "id": "token-req", "from": "worker", "to": "authentik", "y": 165, "label": "POST /token grant_type=password", "variant": "emphasis", "note": "client_id + username + app_password + scope" },
+    { "id": "jwt-resp", "from": "authentik", "to": "worker", "y": 205, "label": "JWT {groups,roles,aud,iss}", "variant": "return", "note": "groups=[poimen-admins] roles=[memory:write]" },
+    { "id": "api-call", "from": "worker", "to": "memory", "y": 260, "label": "POST /memory/ingest", "variant": "emphasis", "note": "Authorization: Bearer <JWT>" },
+    { "id": "fetch-jwks", "from": "memory", "to": "jwks", "y": 295, "label": "GET /jwks (cached)", "variant": "dashed" },
+    { "id": "jwks-resp", "from": "jwks", "to": "memory", "y": 330, "label": "RSA pubkey (kid)", "variant": "return" },
+    { "id": "verify-ok", "from": "memory", "to": "worker", "y": 365, "label": "202 Accepted", "variant": "return", "note": "sig ✓ iss ✓ aud ✓ has_capability ✓" }
+  ],
+  "activations": [
+    { "participant": "worker", "from": 160, "to": 371, "type": "backend" },
+    { "participant": "authentik", "from": 165, "to": 211, "type": "security" },
+    { "participant": "memory", "from": 255, "to": 371, "type": "backend" },
+    { "participant": "jwks", "from": 290, "to": 336, "type": "security" }
+  ],
+  "cards": [
+    {
+      "dot": "emerald",
+      "title": "M2M Pattern",
+      "items": [
+        "grant_type=password (Authentik aliases client_credentials)",
+        "App-password token authenticates the service account",
+        "NOT client_secret — that creates nameless SA"
+      ]
+    },
+    {
+      "dot": "rose",
+      "title": "JWT Claims",
+      "items": [
+        "groups: from user.groups (poimen-admins)",
+        "roles: from user.attributes.roles",
+        "iss/aud: per-provider issuer"
+      ]
+    }
+  ]
+}
@@ -0,0 +1,61 @@
+{
+  "schema_version": 1,
+  "diagram_type": "sequence",
+  "meta": {
+    "title": "User Direct Access with JWT",
+    "viewBox": [1000, 640],
+    "column_fit": "spread",
+    "quality_profile": "showcase"
+  },
+  "participants": [
+    { "id": "user", "type": "external", "label": "User", "sublabel": "browser" },
+    { "id": "app", "type": "frontend", "label": "Web App", "sublabel": "poimen UI" },
+    { "id": "authentik", "type": "security", "label": "Authentik", "sublabel": "OIDC provider" },
+    { "id": "memory", "type": "backend", "label": "Memory API", "sublabel": "poimen-memory" },
+    { "id": "jwks", "type": "security", "label": "JWKS", "sublabel": "RS256 keys" }
+  ],
+  "segments": [
+    { "from": 150, "to": 370, "label": "OIDC Login" },
+    { "from": 380, "to": 540, "label": "API + RBAC" }
+  ],
+  "messages": [
+    { "id": "click-login", "from": "user", "to": "app", "y": 165, "label": "click Login", "variant": "default" },
+    { "id": "redirect-auth", "from": "app", "to": "authentik", "y": 200, "label": "redirect /authorize", "variant": "emphasis", "note": "scope=openid groups roles" },
+    { "id": "show-login", "from": "authentik", "to": "user", "y": 235, "label": "login form", "variant": "default" },
+    { "id": "submit-creds", "from": "user", "to": "authentik", "y": 270, "label": "username + password", "variant": "security" },
+    { "id": "auth-code", "from": "authentik", "to": "app", "y": 305, "label": "redirect ?code=xxx", "variant": "return" },
+    { "id": "exchange-token", "from": "app", "to": "authentik", "y": 340, "label": "POST /token code=xxx", "variant": "emphasis" },
+    { "id": "jwt-resp", "from": "authentik", "to": "app", "y": 375, "label": "JWT {groups,roles,sub}", "variant": "return" },
+    { "id": "query-api", "from": "app", "to": "memory", "y": 420, "label": "GET /memory/query", "variant": "emphasis", "note": "Authorization: Bearer <JWT>" },
+    { "id": "fetch-jwks", "from": "memory", "to": "jwks", "y": 455, "label": "GET /jwks (cached)", "variant": "dashed" },
+    { "id": "jwks-keys", "from": "jwks", "to": "memory", "y": 490, "label": "RSA pubkey", "variant": "return" },
+    { "id": "query-resp", "from": "memory", "to": "app", "y": 525, "label": "200 JSON results", "variant": "return", "note": "has_capability(memory:read) ✓" }
+  ],
+  "activations": [
+    { "participant": "user", "from": 160, "to": 276, "type": "external" },
+    { "participant": "app", "from": 165, "to": 531, "type": "frontend" },
+    { "participant": "authentik", "from": 195, "to": 381, "type": "security" },
+    { "participant": "memory", "from": 415, "to": 531, "type": "backend" },
+    { "participant": "jwks", "from": 450, "to": 496, "type": "security" }
+  ],
+  "cards": [
+    {
+      "dot": "emerald",
+      "title": "Authorization Code Flow",
+      "items": [
+        "User authenticates directly with Authentik",
+        "App exchanges code for JWT",
+        "Scopes: openid groups roles permissions"
+      ]
+    },
+    {
+      "dot": "rose",
+      "title": "JWT Contents",
+      "items": [
+        "iss: .../application/o/poimen/",
+        "aud: poimen (provider client_id)",
+        "groups: user's group memberships"
+      ]
+    }
+  ]
+}
@@ -12,6 +12,19 @@ rules:
  - apiGroups: ["kmsvc.io"]
    resources: ["queues"]
    verbs: ["get", "list", "watch", "update", "patch"]
+  # The operator watches TemporalWorker objects and creates Deployments for
+  # them. Without these two rules the controller logs
+  # "cannot list resource temporalworkers/deployments ... at the cluster scope"
+  # and never reconciles.
+  - apiGroups: ["kmsvc.io"]
+    resources: ["temporalworkers"]
+    verbs: ["get", "list", "watch", "update", "patch"]
+  - apiGroups: ["kmsvc.io"]
+    resources: ["temporalworkers/status"]
+    verbs: ["get", "update", "patch"]
+  - apiGroups: ["apps"]
+    resources: ["deployments"]
+    verbs: ["get", "list", "watch", "create", "update", "patch"]
  - apiGroups: ["kmsvc.io"]
    resources: ["queues/status"]
    verbs: ["get", "update", "patch"]
@@ -34,7 +34,12 @@ metadata:
    app.kubernetes.io/name: macos-bluebubbles
    app.kubernetes.io/part-of: sms
 spec:
-  replicas: 1
+  # Scaled to 0 on 2026-10-24. The pod pinned itself to a node labelled
+  # workload=imessage, and no such node exists any more. The PVC macos-disk also
+  # uses StorageClass longhorn-imessage-local, which pins the same dead node and
+  # stayed unbound for 71 days. The macOS guest therefore cannot start. Raise
+  # this to 1 again only after a KVM-capable node carries that label and taint.
+  replicas: 0
  # Recreate: the qcow2 disk is RWO and a second pod must never attach it
  # concurrently — two QEMU processes on one image corrupts it.
  strategy:
@@ -1,36 +0,0 @@
-apiVersion: argoproj.io/v1alpha1
-kind: Application
-metadata:
-  name: azhi-riotpiao
-  namespace: argocd
-  annotations:
-    argocd.argoproj.io/sync-wave: '8'
-spec:
-  project: homelab
-  source:
-    # Private GitHub. The read-only credential is Secret azhi-infra-github in
-    # namespace argocd, created out-of-band.
-    repoURL: https://github.com/ToyoGlobal/azhi-infra.git
-    # The repository's default branch. It is not `main`: this repo's work
-    # happens on the staging slice branch, and `main` is behind it.
-    targetRevision: feat/azi-riotpiao-cnpg
-    # One directory, because ArgoCD reads a single path per source. That
-    # directory is a root kustomization over foundation, postgres and
-    # azhi-server.
-    path: k8s/overlays/azi-riotpiao
-  destination:
-    server: https://kubernetes.default.svc
-    namespace: azi-riotpiao
-  syncPolicy:
-    automated:
-      prune: true
-      selfHeal: true
-    syncOptions:
-    - CreateNamespace=true
-    # The two Secrets this namespace needs are credentials, so they are created
-    # by hand and NOT by this Application:
-    #   acr-pull                 — the private Alibaba ACR pull credential
-    #   azhi-riotpiao-app-env    — DB credentials, JWT secrets, AES key
-    # A missing imagePullSecret fails the pod outright and a missing app-env
-    # Secret leaves it in CreateContainerConfigError, which is the intended
-    # loud failure rather than a pod that runs against unknown values.
@@ -0,0 +1,20 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: talos-repair
+  namespace: argocd
+  annotations:
+    argocd.argoproj.io/sync-wave: "6"
+spec:
+  project: homelab
+  source:
+    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
+    targetRevision: main
+    path: k8s/infra/talos-repair
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: cicd
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
@@ -16,12 +16,6 @@ spec:
    - https://github.com/Riotpiaole/Poimen-memory.git
    - https://github.com/Riotpiaole/Poimen-workflows.git
    - https://github.com/Riotpiaole/poimen*.git
-    # ToyoGlobal (GitHub, private). The azhi-infra Application reads its
-    # manifests from here, so the URL must be listed or ArgoCD rejects the
-    # Application with "repository not permitted". A read-only credential for
-    # this repo lives in Secret azhi-infra-github in namespace argocd; it is
-    # created out-of-band and is not committed, because it is a credential.
-    - https://github.com/ToyoGlobal/azhi-infra.git
    # In-cluster Forgejo repos — explicit allowlist (no wildcard)
    - https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
    - https://forgejo.riotpiao.com/riotpiao-poimen/homelab-frontend.git
@@ -1,23 +0,0 @@
-apiVersion: ENC[AES256_GCM,data:ECE=,iv:bISz4HovH++X7DW1Qj8Cw0L6+EvPB0+68hh7tfyW5C0=,tag:w+SjD7MsfeIuSf62n+Zl7Q==,type:str]
-kind: ENC[AES256_GCM,data:AxXaV3Mb,iv:xfJb354Rrjz3zLctW2i6hl40yh9EsfIqKxDvmn8jqnU=,tag:1xQ/RR3KhPLKCTWCYjebJg==,type:str]
-metadata:
-    name: ENC[AES256_GCM,data:gdQ4OoMYKUPEbsUeA5OI4i1xnh8=,iv:IA2kaCyqQmkYpLolvcTF4aleh+yd/ImXJMhRMvpGCgo=,tag:8qyYYw4EhBKKPzEmpepAeQ==,type:str]
-    namespace: ENC[AES256_GCM,data:/mOSyXWmRg==,iv:cpeHUTlMqlJzJttGtuR3DoiMtvVqFmDS0/5Tl7K7c2M=,tag:q4GxWgWn2wQJxJHqnq4WQA==,type:str]
-type: ENC[AES256_GCM,data:92OcrsuV,iv:Z1XBy6iZ6unGrK4/SSdDa58pbPL3022gU/f1AOM4uvc=,tag:cd4wWRq/ohm6BJ/Eo6HOIw==,type:str]
-stringData:
-    REGISTRY_PAT: ENC[AES256_GCM,data:zDKruOXhzsIcFZTTp4r4r9rwHih9uf1cCp06KZ6eIXSIZDvR6aQY4A==,iv:5Vch5Z7xn1KkRxrgOs2p/M58nd6WhtcuUhoZDCi8LSY=,tag:14SAZIWGOxJMqLBtOorjYQ==,type:str]
-sops:
-    age:
-        - enc: |
-            -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBIaG5QVUYyNjhvaENPcUFy
-            K3RSSVM2N2hTeFhNK0M5YWZmODhzZU1HaHlFCmNGZWdFcFEvanVwcXpGSmVvRHVx
-            aG45c2lBY1RuSTYwbDZTVk1QeHNWOTQKLS0tIDg4TnVMNjNtaU1VQk5zQjUvU2hM
-            R245ZVdqc0ZWWVhJb3dOZ3lpU3JjUlUKawSg09ZPq8FKx5tvOVZZ+K4yh7eTQsUp
-            be8mWUpS0+eEmNqh35BwU3HrETMQFA6a1kjVp30JOMtqa5rbYlzF7w==
-            -----END AGE ENCRYPTED FILE-----
-          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
-    lastmodified: "2026-08-23T23:14:53Z"
-    mac: ENC[AES256_GCM,data:yzi6woUaUCi6w9pG/eKnU7k/VfZgoXg/tW8p9joG8p7iabLWMdlXlx23m/CItw/NE0zeGWA5iZPPFZXOit2vN36VzK3kQNoFW6QbhvYLZi+78C/RWIdcpZkxB/tPIRG0vq8Q1SA+rwGjG/0xeAFh+R7k+YBTMd2XWBH3P7EI5T4=,iv:kf6MDaAVrtDvPIEjHMMLxXDSDRC3I1GpsPeJFUYppiw=,tag:NukVbGLa9EoMYmRsa4nBtA==,type:str]
-    unencrypted_suffix: _unencrypted
-    version: 3.13.2
@@ -11,7 +11,6 @@ files:
    - agent-pod-ssh-key.enc.yaml
    - authentik-secrets.enc.yaml
    - cloudflare-secrets.enc.yaml
-    - forgejo-registry-pat.enc.yaml
    - forgejo-registry-pat-api.enc.yaml
    - forgejo-registry-pull.enc.yaml
    - forgejo-runner-token.enc.yaml
@@ -0,0 +1,23 @@
+apiVersion: v1
+kind: Secret
+metadata:
+    name: talos-repair-config
+    namespace: cicd
+type: Opaque
+stringData:
+    config: ENC[AES256_GCM,data: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,iv:a4NHhErZolhOuzNCUU51GQiCfCT8GzZ3GQ24s7fkuyU=,tag:w+GrXmaYWADTrBxMko3xtg==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBjQmk5aE1GN2dpVlREZU1s
+            N3V5ZUQweWxMaVo3Y1VjdzZTYW96eFBYZGxvCnNJcjVXKzI4VnliTWFXQy9iSy9k
+            eEZmWlVPQzhZK09NZGowZUVXc1BoZTQKLS0tIHIrMEpTM0lMU0w0eG02aUxJY2VZ
+            aUQ0cmkvK0UwdzhqcDJwM1RDcnpEU0UKQRiTa9/yNrqlkIdlNeaIDzIKa/xvx5nW
+            7wTNfjq2M3go0DMnaVjJA3e15JZBOpOs0QP9z9ydKF/FS4PeCIEFyQ==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-10-07T04:27:33Z"
+    mac: ENC[AES256_GCM,data:CxZdlGJdIFFTwaeeS9LW2XDDgvUmSsBeBKtFYyDM1JliS8BHtgEv48yuCWxP5sR3SaYtcgNSIQ55zUa89jM6dQHqvjK+1jSYu1xzFWPOlxUu8gVSlU0QLS4GU1RChXuPpTUOjxzn4ymZukGgclZk9iuMvI0/U+nGD8nvs8k0zpM=,iv:MGZ7YsOsjelJPjLYWtALOrM6r8Vd1HgbU/PKL4c3r3k=,tag:dIE38TCobESY3j56NVEvIw==,type:str]
+    version: 3.13.2
@@ -31,29 +31,3 @@ roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: Role
  name: oidc-bootstrap
---
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: oidc-bootstrap-restart-apiserver-v2
-  namespace: kube-system
-spec:
-  backoffLimit: 4
-  ttlSecondsAfterFinished: 7200
-  template:
-    spec:
-      serviceAccountName: oidc-bootstrap
-      restartPolicy: Never
-      containers:
-        - name: restart
-          image: docker.io/curlimages/curl:8.22.0
-          command: ["/bin/sh", "-c"]
-          args:
-            - |
-              set -u
-              TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
-              CA=/var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-              for pod in kube-apiserver-talos-cp-1 kube-apiserver-talos-cp-2 kube-apiserver-talos-cp-3; do
-                curl -sS --max-time 15 --cacert "$CA" -H "Authorization: Bearer $TOKEN"                   -X DELETE "https://kubernetes.default.svc/api/v1/namespaces/kube-system/pods/$pod?gracePeriodSeconds=0"                   -o /dev/null -w "$pod -> HTTP %{http_code}\n" || echo "$pod -> request failed"
-              done
-              echo "deletes requested; kubelet recreates each static pod in ~20-40s"
@@ -1,141 +0,0 @@
-# One-shot: restart the control-plane API servers so their OIDC authenticator initialises.
-#
-# Two earlier mechanisms failed and are documented so nobody repeats them:
-#   1. deleting the mirror pod does NOT restart a static pod (deletes returned 200, no restart);
-#   2. matching /proc/*/cmdline for 'kube-apiserver' also matched this script's own cmdline,
-#      so every pod SIGTERMed itself (exit 143) before reaching the real process.
-# This version matches /proc/<pid>/comm (the process name) and skips \$\$, so self-kill is
-# impossible. hostPID + privileged are permitted in the 'cicd' namespace. Delays stagger the
-# three control planes by 2 minutes each, so only one API server is down at a time.
---
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: oidc-restart-apiserver-cp1-v2
-  namespace: cicd
-spec:
-  backoffLimit: 0
-  ttlSecondsAfterFinished: 3600
-  template:
-    spec:
-      hostPID: true
-      restartPolicy: Never
-      nodeSelector:
-        kubernetes.io/hostname: talos-cp-1
-      tolerations:
-        - key: node-role.kubernetes.io/control-plane
-          operator: Exists
-          effect: NoSchedule
-        - key: node-role.kubernetes.io/master
-          operator: Exists
-          effect: NoSchedule
-      containers:
-        - name: kill
-          image: docker.io/library/busybox:1.36
-          securityContext:
-            privileged: true
-          command: ["/bin/sh", "-c"]
-          args:
-            - |
-              echo "sleeping 10s before restarting the API server on talos-cp-1"
-              sleep 10
-              self=$$
-              killed=0
-              for d in /proc/[0-9]*; do
-                pid=${d#/proc/}
-                [ "$pid" = "$self" ] && continue
-                comm=$(cat "$d/comm" 2>/dev/null)
-                [ "$comm" = "kube-apiserver" ] || continue
-                echo "SIGTERM -> pid $pid"
-                kill -TERM "$pid" 2>/dev/null && killed=$((killed+1))
-              done
-              echo "signalled $killed API server process(es); kubelet recreates the static pod"
-
---
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: oidc-restart-apiserver-cp2-v2
-  namespace: cicd
-spec:
-  backoffLimit: 0
-  ttlSecondsAfterFinished: 3600
-  template:
-    spec:
-      hostPID: true
-      restartPolicy: Never
-      nodeSelector:
-        kubernetes.io/hostname: talos-cp-2
-      tolerations:
-        - key: node-role.kubernetes.io/control-plane
-          operator: Exists
-          effect: NoSchedule
-        - key: node-role.kubernetes.io/master
-          operator: Exists
-          effect: NoSchedule
-      containers:
-        - name: kill
-          image: docker.io/library/busybox:1.36
-          securityContext:
-            privileged: true
-          command: ["/bin/sh", "-c"]
-          args:
-            - |
-              echo "sleeping 120s before restarting the API server on talos-cp-2"
-              sleep 120
-              self=$$
-              killed=0
-              for d in /proc/[0-9]*; do
-                pid=${d#/proc/}
-                [ "$pid" = "$self" ] && continue
-                comm=$(cat "$d/comm" 2>/dev/null)
-                [ "$comm" = "kube-apiserver" ] || continue
-                echo "SIGTERM -> pid $pid"
-                kill -TERM "$pid" 2>/dev/null && killed=$((killed+1))
-              done
-              echo "signalled $killed API server process(es); kubelet recreates the static pod"
-
---
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: oidc-restart-apiserver-cp3-v2
-  namespace: cicd
-spec:
-  backoffLimit: 0
-  ttlSecondsAfterFinished: 3600
-  template:
-    spec:
-      hostPID: true
-      restartPolicy: Never
-      nodeSelector:
-        kubernetes.io/hostname: talos-cp-3
-      tolerations:
-        - key: node-role.kubernetes.io/control-plane
-          operator: Exists
-          effect: NoSchedule
-        - key: node-role.kubernetes.io/master
-          operator: Exists
-          effect: NoSchedule
-      containers:
-        - name: kill
-          image: docker.io/library/busybox:1.36
-          securityContext:
-            privileged: true
-          command: ["/bin/sh", "-c"]
-          args:
-            - |
-              echo "sleeping 240s before restarting the API server on talos-cp-3"
-              sleep 240
-              self=$$
-              killed=0
-              for d in /proc/[0-9]*; do
-                pid=${d#/proc/}
-                [ "$pid" = "$self" ] && continue
-                comm=$(cat "$d/comm" 2>/dev/null)
-                [ "$comm" = "kube-apiserver" ] || continue
-                echo "SIGTERM -> pid $pid"
-                kill -TERM "$pid" 2>/dev/null && killed=$((killed+1))
-              done
-              echo "signalled $killed API server process(es); kubelet recreates the static pod"
-
@@ -0,0 +1,12 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+# Stable secret name: the job mounts talos-repair-config by name, so the generated
+# Secret must not get a hash suffix (same convention as k8s/argocd/secrets).
+generatorOptions:
+  disableNameSuffixHash: true
+# ksops decrypts talosconfig-secret.enc.yaml into the Secret the job mounts.
+# Kept local to this app on purpose: no edits to the shared secrets generator.
+generators:
+  - secret-generator.yaml
+resources:
+  - restart-kubelet.yaml
@@ -0,0 +1,57 @@
+# One-shot repair: the kubelets on cp-1, cp-2 and worker-1 stopped posting node status at
+# 04:11-04:14 UTC and never reconnected, so those nodes are NotReady/unreachable and every
+# pod on them (Cilium included) shows NotReady. This job runs on the one healthy node (cp-3),
+# talks to the Talos API on the LAN, and uses Talos' endpoint->node proxying to reach the
+# other three: it reports the kubelet service state, then restarts it.
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: talos-restart-stalled-kubelets
+  namespace: cicd
+spec:
+  backoffLimit: 1
+  ttlSecondsAfterFinished: 86400
+  template:
+    spec:
+      restartPolicy: Never
+      nodeSelector:
+        kubernetes.io/hostname: talos-cp-3
+      tolerations:
+        - key: node-role.kubernetes.io/control-plane
+          operator: Exists
+          effect: NoSchedule
+      containers:
+        - name: talosctl
+          image: docker.io/curlimages/curl:8.22.0
+          command: ["/bin/sh", "-c"]
+          args:
+            - |
+              set -u
+              echo "fetching talosctl v1.13.3 (matches the node version)"
+              curl -sSL -o /tmp/talosctl \
+                https://github.com/siderolabs/talos/releases/download/v1.13.3/talosctl-linux-amd64 \
+                || { echo "DOWNLOAD FAILED"; exit 1; }
+              chmod +x /tmp/talosctl
+              T="/tmp/talosctl --talosconfig /talos/config -e 192.168.1.162"
+              NODES="192.168.1.166 192.168.1.214 192.168.1.223"
+              echo "=== BEFORE: kubelet service state ==="
+              for n in $NODES; do echo "--- $n"; $T -n $n service kubelet 2>&1 || true; done
+              echo "=== kernel log tail (last 15 lines per node) ==="
+              for n in $NODES; do echo "--- $n"; $T -n $n dmesg --tail 15 2>&1 | tail -15 || true; done
+              echo "=== ACTION: restart kubelet ==="
+              for n in $NODES; do echo "--- restarting $n"; $T -n $n restart kubelet 2>&1 || true; sleep 20; done
+              sleep 60
+              echo "=== AFTER ==="
+              for n in $NODES; do echo "--- $n"; $T -n $n service kubelet 2>&1 || true; done
+          volumeMounts:
+            - name: talos
+              mountPath: /talos
+              readOnly: true
+      volumes:
+        - name: talos
+          secret:
+            secretName: talos-repair-config
+            defaultMode: 0444
+            items:
+              - key: config
+                path: config
@@ -0,0 +1,10 @@
+apiVersion: viaduct.ai/v1
+kind: ksops
+metadata:
+  name: talos-repair-secret-generator
+  annotations:
+    config.kubernetes.io/function: |
+      exec:
+        path: ksops
+files:
+  - talosconfig-secret.enc.yaml
@@ -0,0 +1,23 @@
+apiVersion: v1
+kind: Secret
+metadata:
+    name: talos-repair-config
+    namespace: cicd
+type: Opaque
+stringData:
+    config: ENC[AES256_GCM,data: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,iv:a4NHhErZolhOuzNCUU51GQiCfCT8GzZ3GQ24s7fkuyU=,tag:w+GrXmaYWADTrBxMko3xtg==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBjQmk5aE1GN2dpVlREZU1s
+            N3V5ZUQweWxMaVo3Y1VjdzZTYW96eFBYZGxvCnNJcjVXKzI4VnliTWFXQy9iSy9k
+            eEZmWlVPQzhZK09NZGowZUVXc1BoZTQKLS0tIHIrMEpTM0lMU0w0eG02aUxJY2VZ
+            aUQ0cmkvK0UwdzhqcDJwM1RDcnpEU0UKQRiTa9/yNrqlkIdlNeaIDzIKa/xvx5nW
+            7wTNfjq2M3go0DMnaVjJA3e15JZBOpOs0QP9z9ydKF/FS4PeCIEFyQ==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-10-07T04:27:33Z"
+    mac: ENC[AES256_GCM,data:CxZdlGJdIFFTwaeeS9LW2XDDgvUmSsBeBKtFYyDM1JliS8BHtgEv48yuCWxP5sR3SaYtcgNSIQ55zUa89jM6dQHqvjK+1jSYu1xzFWPOlxUu8gVSlU0QLS4GU1RChXuPpTUOjxzn4ymZukGgclZk9iuMvI0/U+nGD8nvs8k0zpM=,iv:MGZ7YsOsjelJPjLYWtALOrM6r8Vd1HgbU/PKL4c3r3k=,tag:dIE38TCobESY3j56NVEvIw==,type:str]
+    version: 3.13.2
Author	SHA1	Message	Date
rock	d1a7d3be6e	fix(oidc): remove the API-server restart Jobs from GitOps The oidc-bootstrap ArgoCD Application runs with selfHeal and prune. Three Jobs in restart-apiserver.yaml kill the kube-apiserver process on each control plane, and bootstrap.yaml carried a fourth Job that deletes the mirror pods. ArgoCD recreated a deleted Job within two minutes, so the kill repeated and every API server reached CrashLoopBackOff. Remove all four. The OIDC authenticator already loaded, so the one-shot restart is not needed again.	2026-10-24 15:06:32 -07:00
rock	2f664c32d9	fix(cluster): grant queue-operator watches and retire the macOS workload queue-operator could not list temporalworkers.kmsvc.io or deployments.apps at cluster scope, so its informers failed on every retry and it reconciled nothing. Add those rules to the ClusterRole. macos-bluebubbles pins itself to a node labelled workload=imessage, and no such node exists. Its PVC macos-disk uses StorageClass longhorn-imessage-local and stayed unbound for 71 days. Scale the Deployment to 0 and record why.	2026-10-24 04:03:02 -07:00
rock	6c98ca7436	Merge pull request 'fix(sops): drop the orphan forgejo-registry-pat file' (#65 ) from fix/sops-drop-orphan-forgejo-pat into main	2026-10-24 10:47:14 +00:00
rock	6ee22401fd	fix(sops): drop the orphan forgejo-registry-pat file ksops failed the whole sops-secrets application on this file: it declares Secret forgejo-registry-pat in namespace forgejo, and no such namespace exists. The failure blocks every other file in the generator list, including zitadel-masterkey. The same Secret name is already generated in namespace api by forgejo-registry-pat-api.enc.yaml, and that is the copy the gateway reads. The forgejo namespace copy is stale: Forgejo runs in namespace cicd, and namespace forgejo was never created. Remove the file and its generator entry. ArgoCD never created the Secret, so pruning has nothing to remove.	2026-10-24 03:46:29 -07:00
rock	e9817283e6	Merge pull request 'feat(iam): wire Zitadel as the Authentik replacement' (#63 ) from harness/zitadel-iam-wiring into main	2026-10-24 10:41:17 +00:00
rock	6e9586aa15	Merge pull request 'chore(argocd): delete the azhi-riotpiao Application' (#64 ) from chore/remove-azhi-riotpiao-app into main	2026-10-24 10:41:09 +00:00
rock	8e9ac37583	chore(argocd): delete the azhi-riotpiao Application The Application pointed at github.com/ToyoGlobal/azhi-infra, branch feat/azi-riotpiao-cnpg, path k8s/overlays/azi-riotpiao. It never reconciled: status stayed Unknown because the source repository could not be read, and the destination namespace azi-riotpiao was never created. ArgoCD reported it as an OutOfSync managed resource of homelab-root with nothing behind it. Also drops the ToyoGlobal URL from the AppProject allowlist. No manifest from that repository is referenced any more, so the allowlist entry is dead weight. Not touched here, because it is not in git: Secret azhi-infra-github in namespace argocd holds the read-only GitHub credential for that repository. Delete it separately once no other Application needs the repo. The live Application object was deleted by hand. Until this commit reaches main, the next homelab-root sync recreates it, because main still declares it.	2026-10-24 03:35:52 -07:00