fix(zitadel): raise setup job deadline to 20m

The chart default killed zitadel-setup at ~5.5 minutes while it was still
replaying projections.projects4, which failed the whole PreSync and left the
Application OutOfSync/Missing. 1200s leaves room for a cold database without
masking a genuine hang.

.env.example

@@ -31,6 +31,17 @@ AUTHENTIK_BOOTSTRAP_TOKEN=
 #   openssl rand -base64 24
 AUTHENTIK_PG_PASSWORD=
 
+# ── ZITADEL (Authentik replacement) ─────────────────────────────────────────────
+# Instance URL, same hostname as the OIDC issuer.
+ZITADEL_URL="https://zitadel.riotpiao.com"
+
+# PAT of the 'iam-admin' machine user, created by the chart's setup job on the
+# first sync. Leave empty until then. Read it with:
+#   kubectl -n iam get secret iam-admin-pat -o jsonpath='{.data.pat}' | base64 -d
+# scripts/iam/zitadel-provision.py reads this variable first, then the cluster
+# Secret. The masterkey and the client secrets never live in this file.
+ZITADEL_BOOTSTRAP_TOKEN=
+
 # ── MinIO ──────────────────────────────────────────────────────────────────────
 MINIO_ROOT_USER=
 MINIO_ROOT_PASSWORD=

.gitignore

@@ -47,6 +47,15 @@ k8s/storage/test/test
 terraform/.terraform/
 terraform/*.tfstate
 terraform/*.tfstate.*
+# The Zitadel root module keeps its own state (see terraform/zitadel/providers.tf).
+# That state carries generated client secrets and machine keys.
+terraform/zitadel/*.tfstate
+terraform/zitadel/*.tfstate.*
+terraform/zitadel/*.tfvars
+terraform/edge/*.tfstate
+terraform/edge/*.tfstate.*
+terraform/edge/*.tfvars
+terraform/edge/terraform.tfvars.local
 terraform.tfvars.local
 skills-lock.json
 secrets-plaintext.yaml
@@ -69,3 +78,10 @@ k8s/**/*-secret.yaml
 
 # IAM provisioning scripts contain credential references — never commit
 scripts/iam/*.py
+# Exception: this one reads every credential from the cluster at run time and
+# embeds none. Keep it reviewable in git.
+!scripts/iam/zitadel-provision.py
+
+# Runtime credential export from the old Authentik provisioning run. Holds live
+# M2M tokens; never commit it.
+/authentik-m2m-tokens.env

.sops.yaml

@@ -2,4 +2,5 @@ creation_rules:
   # `secrets?` — singular too. A `seed-repo-secret.yaml` once slipped this regex
   # and was committed in plaintext to a public remote.
   - path_regex: k8s/.*secrets?.*\.ya?ml
+    encrypted_regex: ^(data|stringData)$
     age: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla

diagram/poimen-schema-relations.architecture.json

@@ -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)"] }
+  ]
+}

diagram/poimen-schema-relations.dataflow.json

@@ -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"
+      ]
+    }
+  ]
+}

diagram/rbac-delegation-flow.sequence.json

@@ -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"
+      ]
+    }
+  ]
+}

diagram/rbac-fine-grained.architecture.json

@@ -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"] }
+  ]
+}

diagram/rbac-m2m-flow.sequence.json

@@ -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"
+      ]
+    }
+  ]
+}

diagram/rbac-user-flow.sequence.json

@@ -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"
+      ]
+    }
+  ]
+}

k8s/apps/comfyui/ingress.yaml

@@ -4,7 +4,9 @@ metadata:
   name: comfyui
   namespace: comfyui
   annotations:
-    cert-manager.io/cluster-issuer: letsencrypt-prod
+    # No cert-manager annotation and no tls: block. This host is covered by
+    # the *.riotpiao.com wildcard, which nginx serves as its
+    # default-ssl-certificate (ingress-nginx/riotpiao-com-tls).
     nginx.ingress.kubernetes.io/proxy-read-timeout: "600"
     nginx.ingress.kubernetes.io/proxy-send-timeout: "600"
     nginx.ingress.kubernetes.io/proxy-body-size: "0"
@@ -16,10 +18,6 @@ metadata:
       proxy_set_header Connection "upgrade";
 spec:
   ingressClassName: nginx
-  tls:
-    - secretName: comfyui-tls
-      hosts:
-        - comfyui.riotpiao.com
   rules:
     - host: comfyui.riotpiao.com
       http:

k8s/apps/gotify/deployment.yaml

@@ -23,7 +23,7 @@ spec:
       containers:
         # --- Gotify server ---
         - name: gotify
-          image: ghcr.io/gotify/server:2.6.1
+          image: ghcr.io/gotify/server:3.1.0
           command: ["/bin/sh", "-c"]
           args:
             - |
@@ -84,7 +84,7 @@ spec:
         # Watches Gotify WebSocket stream, forwards messages as email.
         # https://github.com/eternal-flame-AD/gotify-broadcast
         - name: smtp-emailer
-          image: ghcr.io/gotify/server:2.6.1
+          image: ghcr.io/gotify/server:3.1.0
           command:
             - /bin/sh
             - -c

k8s/apps/gotify/igotify-deployment.yaml

@@ -0,0 +1,59 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: igotify
+  namespace: notifications
+  labels:
+    app: igotify
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: igotify
+  template:
+    metadata:
+      labels:
+        app: igotify
+    spec:
+      containers:
+        - name: igotify
+          image: ghcr.io/androidseb25/igotify-notification-assist:v1.6.0.1
+          ports:
+            - containerPort: 8080
+              protocol: TCP
+          env:
+            - name: ENABLE_CONSOLE_LOG
+              value: "true"
+            - name: ENABLE_SCALAR_UI
+              value: "true"
+            # GOTIFY_URLS / GOTIFY_CLIENT_TOKENS / SECNTFY_TOKENS intentionally
+            # left unset — not required when Gotify is reachable via public domain
+            # (gotify.riotpiao.com). iGotify iOS app registers itself at runtime.
+          volumeMounts:
+            - name: data
+              mountPath: /app/data
+          livenessProbe:
+            httpGet:
+              path: /Version
+              port: 8080
+            initialDelaySeconds: 10
+            periodSeconds: 30
+          readinessProbe:
+            httpGet:
+              path: /Version
+              port: 8080
+            initialDelaySeconds: 5
+            periodSeconds: 10
+          resources:
+            requests:
+              cpu: 50m
+              memory: 64Mi
+            limits:
+              cpu: 200m
+              memory: 128Mi
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: igotify-data

k8s/apps/gotify/igotify-ingress.yaml

@@ -0,0 +1,22 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: igotify
+  namespace: notifications
+  annotations:
+    nginx.ingress.kubernetes.io/proxy-read-timeout: "600"
+    nginx.ingress.kubernetes.io/proxy-send-timeout: "600"
+    nginx.ingress.kubernetes.io/proxy-http-version: "1.1"
+spec:
+  ingressClassName: nginx
+  rules:
+    - host: igotify.riotpiao.com
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: igotify
+                port:
+                  number: 80

k8s/apps/gotify/igotify-pvc.yaml

@@ -0,0 +1,11 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: igotify-data
+  namespace: notifications
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 1Gi

k8s/apps/gotify/igotify-service.yaml

@@ -0,0 +1,14 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: igotify
+  namespace: notifications
+  labels:
+    app: igotify
+spec:
+  selector:
+    app: igotify
+  ports:
+    - port: 80
+      targetPort: 8080
+      protocol: TCP

k8s/apps/gotify/ingress.yaml

@@ -6,11 +6,9 @@ metadata:
   annotations:
     nginx.ingress.kubernetes.io/proxy-read-timeout: "600"
     nginx.ingress.kubernetes.io/proxy-send-timeout: "600"
-    # WebSocket support for Gotify client connections
+    # WebSocket support for Gotify client connections (/stream endpoint)
+    # nginx-ingress handles Upgrade/Connection headers natively with http/1.1
     nginx.ingress.kubernetes.io/proxy-http-version: "1.1"
-    nginx.ingress.kubernetes.io/configuration-snippet: |
-      proxy_set_header Upgrade $http_upgrade;
-      proxy_set_header Connection "upgrade";
 spec:
   ingressClassName: nginx
   rules:

k8s/apps/gotify/kustomization.yaml

@@ -6,3 +6,7 @@ resources:
   - deployment.yaml
   - service.yaml
   - ingress.yaml
+  - igotify-pvc.yaml
+  - igotify-deployment.yaml
+  - igotify-service.yaml
+  - igotify-ingress.yaml

k8s/apps/llm-serving/networkpolicy.yaml

@@ -52,6 +52,20 @@ spec:
           port: 8080
         - protocol: TCP
           port: 9000
+    # Allow from paperless namespace (paperless-ai auto-tagging)
+    # Bypasses gateway until service-account JWT token exchange is implemented.
+    # paperless-ai-agent has llm:inference role in Authentik.
+    - from:
+        - namespaceSelector:
+            matchLabels:
+              kubernetes.io/metadata.name: paperless
+      ports:
+        - protocol: TCP
+          port: 8080
+        - protocol: TCP
+          port: 80
+        - protocol: TCP
+          port: 8000
     # Allow intra-namespace (pod-to-pod within llm-serving)
     - from:
         - podSelector:

k8s/apps/llm-serving/ornith.yaml

@@ -44,7 +44,7 @@ spec:
       - name: OLLAMA_MODELS
         value: /mnt/models/ollama
       - name: OLLAMA_CONTEXT_LENGTH
-        value: '32768'
+        value: '65536'
       - name: OLLAMA_KEEP_ALIVE
         value: '-1'
       - name: OLLAMA_NUM_PARALLEL

k8s/apps/llm-serving/reasoning.yaml

@@ -28,9 +28,14 @@ spec:
       # KV cache math: 256KB/token total (64 layers, 8 KV heads, 128
       # head_dim, fp16), PP=2 splits both weights and KV load ~evenly, so
       # each GPU carries ~9.67GB weights + ~128KB/token KV. At
-      # gpu-memory-utilization=0.90 (28.8GB/GPU usable), that leaves
-      # ~19.1GB/GPU for KV cache -> ~156k tokens/GPU capacity, comfortably
-      # above the 131072 target with room to spare -- the old
+      # gpu-memory-utilization=0.95 (30.4GB/GPU usable), that leaves
+      # ~20.7GB/GPU for KV cache. NOTE this is a projection, not a
+      # measurement: the live reading at 0.90 is num_gpu_blocks=9527 x
+      # block_size=16 = 152,432 tokens (vllm:cache_config_info). Re-read that
+      # metric after the rollout -- max_num_batched_tokens=8192 also raises
+      # activation memory out of the same budget, so the post-boot
+      # num_gpu_blocks is the authoritative number, and --max-num-seqs=5 is
+      # only valid if it still covers 2x65k + 3x8k. The old
       # OffloadingConnector CPU-DRAM spillover (tuned for the previous
       # model's much smaller 16384 context) is no longer needed and is
       # dropped. Staying on PP=2 and vLLM 0.11.0 (no version bump needed,
@@ -54,10 +59,37 @@ spec:
       - --tensor-parallel-size=1
       - --pipeline-parallel-size=2
       - --max-model-len=131072
-      - --gpu-memory-utilization=0.90
-      - --max-num-seqs=4
+      - --gpu-memory-utilization=0.95
+      - --max-num-seqs=5
+      # Prefill scheduling -- see the measured starvation this fixes.
+      # V1's scheduler has no prefill/decode phase: it walks self.running and
+      # hands out tokens from one shared budget (vllm/v1/core/sched/scheduler.py:
+      # "There's no decoding phase nor prefill phase in the scheduler"). The cap
+      # per request is applied BEFORE the budget clamp:
+      #     if 0 < long_prefill_token_threshold < num_new_tokens: take = threshold
+      #     take = min(take, token_budget)
+      # The loop is `while ... and token_budget > 0`. With the threshold at its
+      # default of 0 the cap is disabled, so one long prompt takes the ENTIRE
+      # budget, token_budget hits 0, the loop exits and every other request is
+      # skipped for that step -- measured as 262 tok/s contended prefill and
+      # 0.0-0.1 tok/s generation for everything else, Running: 2-4 reqs.
+      # Hence threshold must be strictly BELOW the budget or it never binds:
+      # at 8192/8192 a single request is served per step (still starved), while
+      # 8192/2048 serves four. Verified by replaying the loop.
+      - --max-num-batched-tokens=8192
+      - --long-prefill-token-threshold=2048
       - --enable-chunked-prefill
       - --enable-prefix-caching
+      #
+      # NOT set, deliberately: --max-num-partial-prefills and
+      # --max-long-partial-prefills. Those are V0-only knobs. vLLM 0.11.0 ships
+      # V1 only (vllm/core/ absent), and EngineArgs._is_v1_supported_oracle
+      # rejects any value other than the default for either one, calling
+      # _raise_or_fallback("Concurrent Partial Prefill") -> "Falling back to V0"
+      # -> AssertionError, because there is no V0 engine to fall back to.
+      # The Deployment uses strategy Recreate, so setting them is an outage.
+      # V1 does concurrent chunked prefill natively; it needs no flag, only the
+      # budget/threshold ratio above.
       # qwen3 is vLLM's dedicated reasoning parser for this family's <think>
       # blocks.
       - --reasoning-parser=qwen3

k8s/apps/messaging/queue-crd/templates/rbac.yaml

@@ -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"]

k8s/apps/paperless/backup-cronjob.yaml

@@ -48,7 +48,7 @@ spec:
                   mountPath: /backup
           containers:
             - name: mc-mirror
-              image: quay.io/minio/mc:latest
+              image: docker.io/bitnamilegacy/minio-client:2025.7.21-debian-12-r3@sha256:73bd39f7899a0cef12b8dd5df13aa93a3ed1aaa44236542442e9ac76819ac158
               env:
                 - name: ACCESS_KEY
                   valueFrom:

k8s/apps/paperless/configmap.yaml

@@ -20,3 +20,7 @@ data:
   # wire up allauth's confirm-email view, so signup 500s with NoReverseMatch
   # on 'account_confirm_email' without this.
   PAPERLESS_ACCOUNT_EMAIL_VERIFICATION: "none"
+  # Auto-connect social accounts to existing users with matching email
+  PAPERLESS_SOCIAL_AUTO_SIGNUP: "true"
+  # Allow automatic linking of social accounts to existing users
+  PAPERLESS_ACCOUNT_ALLOW_SIGNUPS: "true"

k8s/apps/paperless/kustomization.yaml

@@ -4,6 +4,7 @@ namespace: paperless
 resources:
   - pvc.yaml
   - configmap.yaml
+  - paperless-ai-config.yaml
   - redis.yaml
   - deployment.yaml
   - service.yaml

k8s/apps/paperless/paperless-ai-config.yaml

@@ -0,0 +1,49 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: paperless-ai-env
+  namespace: paperless
+data:
+  paperless-ai-config.env: |
+    # Paperless-NGX API configuration
+    PAPERLESS_URL=http://paperless.paperless.svc.cluster.local:8000
+    PAPERLESS_API_TOKEN=7b89463e04c141f4172fbcddf78d623547d327ec
+
+    # AI Processing settings
+    ENABLE_AI_PROCESSING=yes
+    AI_MODEL=reasoning
+    LLM_API_URL=https://api.riotpiao.com/v1
+    LLM_API_TOKEN_FILE=/app/data/llm_token.txt
+
+    # Auto-tagging configuration
+    ENABLE_AUTO_TAGGING=yes
+    ENABLE_CORRESPONDENT_EXTRACTION=yes
+    ENABLE_DOCUMENT_TYPE_EXTRACTION=yes
+    ENABLE_TITLE_GENERATION=yes
+    
+    # Advanced tagging with AI
+    ENABLE_INTELLIGENT_TAGGING=yes
+    ENABLE_DATE_EXTRACTION=yes
+    ENABLE_TIMELINE_TAGGING=yes
+    AUTO_CREATE_TAGS=yes
+    
+    # Tagging prompts for custom extraction
+    CUSTOM_EXTRACTION_PROMPT=Extract document date, time period, financial year, and temporal context. Create tags like YYYY, Q1-YYYY, Last-Month, Current-Year, Historic
+    TAG_EXTRACTION_MODEL=reasoning
+
+    # Scanning behavior
+    SCAN_INTERVAL_SECONDS=60
+    PROCESS_EXISTING_DOCUMENTS=no
+    ADD_AI_TAG=yes
+    AI_TAG_NAME=ai-processed
+
+    # Date/Timeline tagging configuration
+    DATE_EXTRACTION_FORMAT=iso8601
+    TIMELINE_TAG_GRANULARITY=year,quarter,month
+    AUTO_TAG_HISTORICAL=yes
+    AUTO_TAG_RECENT=yes
+    
+    # Performance
+    MAX_CONCURRENT_REQUESTS=2
+    REQUEST_TIMEOUT=60
+    DATE_EXTRACTION_TIMEOUT=30

k8s/apps/paperless/paperless-ai-new.yaml

@@ -0,0 +1,127 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: paperless-ai-data
+  namespace: paperless
+spec:
+  accessModes:
+    - ReadWriteOnce
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 2Gi
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: paperless-ai
+  namespace: paperless
+  labels:
+    app.kubernetes.io/name: paperless-ai
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: paperless-ai
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: paperless-ai
+    spec:
+      tolerations:
+        - key: node-role.kubernetes.io/control-plane
+          operator: Exists
+          effect: NoSchedule
+      
+      volumes:
+        - name: paperless-ai-data
+          persistentVolumeClaim:
+            claimName: paperless-ai-data
+      
+      initContainers:
+        - name: fetch-llm-token
+          image: curlimages/curl:8.12.0
+          command:
+            - sh
+            - -c
+            - |
+              set -e
+              echo "[init] Fetching JWT token from Authentik for paperless-ai-agent..."
+              
+              # Get JWT token via client_credentials grant
+              TOKEN_RESPONSE=$(curl -s -X POST https://authentik.riotpiao.com/application/o/token/ \
+                -d "grant_type=client_credentials" \
+                -d "client_id=paperless-ai-agent" \
+                -d "client_secret=29skAhE0tBzWn0qrPvmPTQMva0joFjcCr7msDQr_VXQ" \
+                -d "scope=openid llm:inference" 2>/dev/null)
+              
+              # Extract token
+              TOKEN=$(echo "$TOKEN_RESPONSE" | grep -o '"access_token":"[^"]*' | cut -d'"' -f4)
+              
+              if [ -z "$TOKEN" ]; then
+                echo "[error] Failed to get token. Response: $TOKEN_RESPONSE"
+                exit 1
+              fi
+              
+              # Store token in file for main container to read
+              mkdir -p /data
+              echo "$TOKEN" > /data/llm_token.txt
+              echo "[init] Token fetched and stored successfully"
+          volumeMounts:
+            - name: paperless-ai-data
+              mountPath: /data
+      
+      containers:
+        - name: paperless-ai
+          image: clusterzx/paperless-ai:latest
+          imagePullPolicy: Always
+          env:
+            # Paperless-ngx connection
+            - name: PAPERLESS_API_URL
+              value: "http://paperless.paperless.svc.cluster.local:8000"
+            - name: PAPERLESS_API_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: paperless-ai-config
+                  key: PAPERLESS_API_TOKEN
+            - name: PAPERLESS_USERNAME
+              value: "admin"
+            
+            # LLM API configuration
+            - name: AI_PROVIDER
+              value: "custom"
+            - name: CUSTOM_BASE_URL
+              value: "https://api.riotpiao.com/v1"
+            # Token file created by init container with JWT from Authentik
+            - name: CUSTOM_API_KEY_FILE
+              value: "/app/data/llm_token.txt"
+            - name: CUSTOM_MODEL
+              value: "qwen2.5:3b-instruct"
+            
+            # Scanning behavior
+            - name: SCAN_INTERVAL
+              value: "60"
+            - name: PROCESS_PREDEFINED_DOCUMENTS
+              value: "no"
+            
+            # Tagging configuration
+            - name: ADD_AI_TAG
+              value: "yes"
+            - name: AI_TAG_NAME
+              value: "ai-processed"
+            - name: ADD_AI_DESCRIPTIONS
+              value: "yes"
+            - name: USE_PROMPT_TAGS
+              value: "yes"
+          
+          volumeMounts:
+            - name: paperless-ai-data
+              mountPath: /app/data
+          
+          resources:
+            requests:
+              cpu: 100m
+              memory: 512Mi
+            limits:
+              cpu: "1"
+              memory: 2Gi

k8s/apps/paperless/paperless-ai.yaml

@@ -21,6 +21,59 @@ spec:
         - key: node-role.kubernetes.io/control-plane
           operator: Exists
           effect: NoSchedule
+      volumes:
+        - name: paperless-ai-data
+          persistentVolumeClaim:
+            claimName: paperless-ai-data
+        - name: paperless-ai-env-config
+          configMap:
+            name: paperless-ai-env
+      initContainers:
+        - name: fetch-llm-token
+          image: curlimages/curl:8.12.0
+          securityContext:
+            runAsUser: 0
+            fsGroup: 0
+          command:
+            - sh
+            - -c
+            - |
+              set -e
+              echo "[init] Fetching JWT token from Authentik for paperless-ai-agent..."
+              
+              # Get JWT token via client_credentials grant
+              # Client secret sourced from environment (injected from paperless-ai-config Secret)
+              TOKEN_RESPONSE=$(curl -s -X POST https://authentik.riotpiao.com/application/o/token/ \
+                -d "grant_type=client_credentials" \
+                -d "client_id=paperless-ai-agent" \
+                -d "client_secret=${LLM_AUTH_CLIENT_SECRET}" \
+                -d "scope=openid llm:inference" 2>/dev/null)
+              
+              # Extract token from JSON response using sed (handles spaces after colons)
+              TOKEN=$(echo "$TOKEN_RESPONSE" | sed -n 's/.*"access_token"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p')
+              
+              if [ -z "$TOKEN" ]; then
+                echo "[error] Failed to get token. Response: $TOKEN_RESPONSE"
+                exit 1
+              fi
+              
+              # Store token in file for main container to read
+              # Write to both locations for compatibility
+              mkdir -p /tmp/llm-token /app/data 2>/dev/null || true
+              echo "$TOKEN" | tee /tmp/llm-token/llm_token.txt > /dev/null 2>&1
+              echo "$TOKEN" > /app/data/llm_token.txt 2>/dev/null || true
+              echo "[init] Token fetched and stored"
+              [ -f /tmp/llm-token/llm_token.txt ] && echo "  -> /tmp/llm-token/llm_token.txt"
+              [ -f /app/data/llm_token.txt ] && echo "  -> /app/data/llm_token.txt"
+          env:
+            - name: LLM_AUTH_CLIENT_SECRET
+              valueFrom:
+                secretKeyRef:
+                  name: paperless-ai-config
+                  key: LLM_AUTH_CLIENT_SECRET
+          volumeMounts:
+            - name: paperless-ai-data
+              mountPath: /app/data
       containers:
         - name: paperless-ai
           image: clusterzx/paperless-ai:latest
@@ -35,18 +88,20 @@ spec:
                   key: PAPERLESS_API_TOKEN
             - name: PAPERLESS_USERNAME
               value: "admin"
-            # LLM API — local gateway, no auth required (phase 3 not built yet)
+            # LLM API — via public gateway with JWT auth
             - name: AI_PROVIDER
               value: "custom"
             - name: CUSTOM_BASE_URL
-              value: "http://api-gateway.api.svc.cluster.local:8080/v1"
-            - name: CUSTOM_API_KEY
-              value: "not-required"
+              value: "https://api.riotpiao.com/v1"
+            # Token will be read from file at runtime by the application
+            # The init container fetches it and stores in /app/data/llm_token.txt
+            - name: CUSTOM_API_KEY_FILE
+              value: "/app/data/llm_token.txt"
             - name: CUSTOM_MODEL
-              value: "reasoning"
-            # Behavior
+              value: "qwen2.5:3b-instruct"
+            # Behavior - scan for new documents and tag them
             - name: SCAN_INTERVAL
-              value: "300"
+              value: "60"
             - name: PROCESS_PREDEFINED_DOCUMENTS
               value: "no"
             - name: ADD_AI_TAG
@@ -55,6 +110,14 @@ spec:
               value: "ai-processed"
             - name: USE_PROMPT_TAGS
               value: "yes"
+            - name: ADD_AI_DESCRIPTIONS
+              value: "yes"
+          volumeMounts:
+            - name: paperless-ai-data
+              mountPath: /app/data
+            - name: paperless-ai-env-config
+              mountPath: /app/data/.env
+              subPath: paperless-ai-config.env
           resources:
             requests:
               cpu: 100m

k8s/apps/poimen-frontend/ingress.yaml

@@ -0,0 +1,24 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: poimen-frontend
+  namespace: poimen
+  annotations:
+    # Next.js SSE + LLM streaming responses need long timeouts + no buffering.
+    nginx.ingress.kubernetes.io/proxy-read-timeout: "3600"
+    nginx.ingress.kubernetes.io/proxy-send-timeout: "3600"
+    nginx.ingress.kubernetes.io/proxy-buffering: "off"
+    nginx.ingress.kubernetes.io/proxy-body-size: "10m"
+spec:
+  ingressClassName: nginx
+  rules:
+    - host: poimen.riotpiao.com
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: poimen-frontend
+                port:
+                  number: 3000

k8s/apps/poimen-frontend/kustomization.yaml

@@ -0,0 +1,8 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+# Edge Ingress for poimen.riotpiao.com.
+# Same pattern as k8s/apps/api/ (api-gw ingress).
+# App manifests (Deployment, Service, NetworkPolicy) live in
+# riotpiao-poimen/poimen-frontend.git k8s/ — each repo owns its own k8s.
+resources:
+  - ingress.yaml

k8s/apps/sms/deployment-macos.yaml

@@ -1,115 +0,0 @@
-# macOS VM (Docker-OSX) hosting the BlueBubbles server.
-#
-# ── Why a VM and not a container ────────────────────────────────────────────
-# Containers share the host kernel. macOS binaries are Mach-O and need XNU plus
-# Cocoa/IOKit, which a Linux kernel cannot provide, so no macOS container exists
-# or can exist. Docker-OSX is QEMU running a macOS guest, packaged in a
-# container — a VM in a box, not a macOS container.
-#
-# ── Why this works on worker-2 ──────────────────────────────────────────────
-# Verified on the existing hardware: amd64, `vmx` (Intel VT-x) present, and
-# /dev/kvm exists on Talos nodes (KVM is compiled into Talos' kernel, not a
-# module). Bare metal, so no nested virtualisation needed.
-#
-# ── Read this before relying on it ──────────────────────────────────────────
-# 1. Setup is INTERACTIVE. First boot runs the macOS installer: connect over
-#    VNC (:5999), erase the disk in Disk Utility, install, create a user, sign
-#    into iMessage, THEN install BlueBubbles inside the guest. This manifest
-#    only provides the machine; it does not provision macOS.
-# 2. iMessage activation on non-Apple hardware is a coin flip. BlueBubbles'
-#    own guidance: "test sending an iMessage to yourself. If it does not
-#    succeed, it's likely best to restart from the beginning."
-# 3. Apple's macOS licence permits virtualisation only on Apple hardware. This
-#    is a Hackintosh. Use a throwaway Apple ID, not a primary one.
-# 4. BlueBubbles labels this path "not for beginners", "no guarantees or
-#    warranty".
-#
-# Private API (reactions, typing indicators, edit/unsend) needs SIP disabled
-# inside the guest and is NOT required for plain send/receive. Skip it.
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: macos-bluebubbles
-  labels:
-    app.kubernetes.io/name: macos-bluebubbles
-    app.kubernetes.io/part-of: sms
-spec:
-  replicas: 1
-  # Recreate: the qcow2 disk is RWO and a second pod must never attach it
-  # concurrently — two QEMU processes on one image corrupts it.
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: macos-bluebubbles
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: macos-bluebubbles
-        app.kubernetes.io/part-of: sms
-    spec:
-      # Dedicated node. The taint keeps everything else off worker-2; this
-      # toleration is what lets the VM on. Both halves are required.
-      nodeSelector:
-        workload: imessage
-      tolerations:
-        - key: workload
-          operator: Equal
-          value: imessage
-          effect: NoSchedule
-      containers:
-        - name: macos
-          image: sickcodes/docker-osx:latest@sha256:3a3c82c79bc4e73531f819ccdfa4053b3084efd7c1f645678dbf8b4b3a24369c
-          # QEMU needs /dev/kvm; Talos enforces `baseline` cluster-wide, so this
-          # only schedules because the sms namespace is labelled privileged.
-          securityContext:
-            privileged: true
-          env:
-            # Generates a unique serial / board-serial / UUID / MAC and persists
-            # them to bootdisk.qcow2. This synthetic identity is what iMessage
-            # activates against — it must stay stable across restarts, which is
-            # why the PVC matters.
-            - name: GENERATE_UNIQUE
-              value: "true"
-            # Identity is only plausible if it matches a real product line.
-            - name: DEVICE_MODEL
-              value: "iMacPro1,1"
-            - name: RAM
-              value: "12"
-            - name: CORES
-              value: "6"
-            - name: EXTRA
-              # Expose the BlueBubbles server port from the guest to the pod.
-              # Guest :1234 (BlueBubbles default) -> pod :1234.
-              value: "-device virtio-net-pci,netdev=net0 -netdev user,id=net0,hostfwd=tcp::1234-:1234"
-          ports:
-            - name: vnc
-              containerPort: 5999
-              protocol: TCP
-            - name: bluebubbles
-              containerPort: 1234
-              protocol: TCP
-          resources:
-            requests:
-              cpu: "6"
-              memory: 14Gi
-            limits:
-              cpu: "12"
-              memory: 20Gi
-          volumeMounts:
-            - name: macos-disk
-              mountPath: /home/arch/OSX-KVM/disk
-            - name: kvm
-              mountPath: /dev/kvm
-          # No readiness probe on purpose. The guest takes many minutes to boot,
-          # and until macOS + BlueBubbles are installed BY HAND there is nothing
-          # listening on 1234. A probe here would crash-loop the pod through the
-          # entire interactive install.
-      volumes:
-        - name: macos-disk
-          persistentVolumeClaim:
-            claimName: macos-disk
-        - name: kvm
-          hostPath:
-            path: /dev/kvm
-            type: CharDevice

k8s/apps/sms/kustomization.yaml

@@ -1,10 +0,0 @@
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-namespace: sms
-resources:
-  - namespace.yaml
-  - storageclass.yaml
-  - pvc-macos.yaml
-  - deployment-macos.yaml
-  - service.yaml
-  - networkpolicy.yaml

k8s/apps/sms/namespace.yaml

@@ -1,19 +0,0 @@
-# iMessage delivery for the cluster.
-#
-# BlueBubbles' server is a macOS Electron app paired with an Objective-C helper
-# that hooks Messages.app private APIs — it cannot be containerised on Linux,
-# because containers share the host kernel and macOS needs XNU + Cocoa. The only
-# way to run it on Talos is a full macOS VM under QEMU/KVM (Docker-OSX), which
-# needs a privileged pod with /dev/kvm.
-#
-# Hence privileged PodSecurity: the cluster default from the Talos controlplane
-# is `enforce: baseline`, which forbids privileged containers and host devices.
-# Scope is limited to this namespace.
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: sms
-  labels:
-    pod-security.kubernetes.io/enforce: privileged
-    pod-security.kubernetes.io/audit: privileged
-    pod-security.kubernetes.io/warn: privileged

k8s/apps/sms/networkpolicy.yaml

@@ -1,22 +0,0 @@
-# Default-deny. This namespace runs a privileged QEMU VM signed into an Apple
-# ID and exposes an unauthenticated VNC console; nothing should reach it except
-# opted-in clients.
-apiVersion: networking.k8s.io/v1
-kind: NetworkPolicy
-metadata:
-  name: sms-default-deny
-spec:
-  podSelector:
-    matchLabels:
-      app.kubernetes.io/part-of: sms
-  policyTypes:
-    - Ingress
-  ingress:
-    - from:
-        - namespaceSelector: {}
-          podSelector:
-            matchLabels:
-              sms-client: "true"
-      ports:
-        - protocol: TCP
-          port: 1234

k8s/apps/sms/pvc-macos.yaml

@@ -1,25 +0,0 @@
-# Persistent macOS disk image + generated hardware identity (bootdisk.qcow2).
-#
-# This volume is NOT disposable: it holds the VM's serial number, board serial,
-# UUID and MAC, which together form the identity iMessage was activated against.
-# Losing it means re-running activation, which is the least reliable step of the
-# whole setup.
-#
-# Docker-OSX documents 128GB minimum for the guest image; 200Gi leaves room for
-# the installer, the base system, and qcow2 growth.
-#
-# ⚠️ Single replica (see storageclass.yaml — capacity and IO both rule out 3).
-# Losing worker-2's disk therefore means losing the activated identity and
-# redoing iMessage activation. Once the guest is installed and activated, take
-# a Longhorn snapshot/backup of this volume; that is the only redundancy here.
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: macos-disk
-spec:
-  accessModes:
-    - ReadWriteOnce
-  storageClassName: longhorn-imessage-local
-  resources:
-    requests:
-      storage: 200Gi

k8s/apps/sms/service.yaml

@@ -1,31 +0,0 @@
-# VNC is how you drive the interactive macOS install. Deliberately ClusterIP —
-# it is an unauthenticated console onto a machine holding a live Apple ID
-# session. Reach it with `kubectl port-forward`, never an Ingress.
-apiVersion: v1
-kind: Service
-metadata:
-  name: macos-vnc
-spec:
-  type: ClusterIP
-  selector:
-    app.kubernetes.io/name: macos-bluebubbles
-  ports:
-    - name: vnc
-      port: 5999
-      targetPort: vnc
----
-# The BlueBubbles REST API, once installed inside the guest. This is the stable
-# name cluster services use, so callers never depend on the pod IP or on whether
-# the backend is this VM or a real Mac mini later.
-apiVersion: v1
-kind: Service
-metadata:
-  name: bluebubbles
-spec:
-  type: ClusterIP
-  selector:
-    app.kubernetes.io/name: macos-bluebubbles
-  ports:
-    - name: http
-      port: 1234
-      targetPort: bluebubbles

k8s/apps/sms/storageclass.yaml

@@ -1,32 +0,0 @@
-# Dedicated StorageClass for the macOS VM disk.
-#
-# The default `longhorn` class does not work here, for two independent reasons:
-#
-# 1. Replica count. Default is 3, and Longhorn schedules against
-#    storageMaximum - storageScheduled with over-provisioning at 100%. Free
-#    space is cp-1 146Gi / cp-2 8Gi / cp-3 146Gi / worker-1 292Gi, so a 200Gi
-#    volume has only one node that can hold even a single replica — a 3-replica
-#    volume fails outright with ReplicaSchedulingFailure.
-# 2. Binding mode. `Immediate` provisions the volume the moment the PVC is
-#    created, before any pod is scheduled. Combined with strict-local that
-#    pins the data to an arbitrary node, not the one the VM runs on.
-#
-# So: one replica, kept local to the VM, bound only once the pod has a node.
-apiVersion: storage.k8s.io/v1
-kind: StorageClass
-metadata:
-  name: longhorn-imessage-local
-provisioner: driver.longhorn.io
-allowVolumeExpansion: true
-reclaimPolicy: Delete
-# The pod is pinned to worker-2 by nodeSelector; wait for it to be scheduled so
-# the replica is placed on that node and not somewhere else.
-volumeBindingMode: WaitForFirstConsumer
-parameters:
-  # A qcow2 backing a live VM is latency-sensitive and rewritten constantly.
-  # Serving it over the network from another node's disk would be the single
-  # worst thing for guest responsiveness, so force it local.
-  numberOfReplicas: "1"
-  dataLocality: "strict-local"
-  staleReplicaTimeout: "30"
-  fsType: "ext4"

k8s/argocd/apps/01-image-updater.yaml

@@ -1,33 +0,0 @@
-# ArgoCD Image Updater - auto-updates Application images from registry
-# Watches forgejo.riotpiao.com for new image tags and updates Applications
-apiVersion: argoproj.io/v1alpha1
-kind: Application
-metadata:
-  name: argocd-image-updater
-  namespace: argocd
-  finalizers:
-    - resources-finalizer.argocd.argoproj.io
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
-spec:
-  project: homelab
-  revisionHistoryLimit: 3
-  sources:
-    - repoURL: https://argoproj.github.io/argo-helm
-      chart: argocd-image-updater
-      targetRevision: "0.11.2"
-      helm:
-        valueFiles:
-          - $values/k8s/infra/argocd-image-updater/values.yaml
-    - repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
-      targetRevision: main
-      ref: values
-  destination:
-    server: https://kubernetes.default.svc
-    namespace: argocd
-  syncPolicy:
-    automated:
-      prune: true
-      selfHeal: true
-    syncOptions:
-      - CreateNamespace=false

k8s/argocd/apps/06-ci-cd.yaml

@@ -0,0 +1,55 @@
+# Tekton Pipelines v0.68.0
+#
+# Install method: vendored release.yaml in k8s/infra/tekton/
+# downloaded from https://storage.googleapis.com/tekton-releases/pipeline/previous/v0.68.0/release.yaml
+#
+# To upgrade:
+#   1. Download new release.yaml from https://github.com/tektoncd/pipeline/releases
+#   2. Replace k8s/infra/tekton/release.yaml
+#   3. Commit and push — ArgoCD syncs automatically
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: tekton-pipelines
+  namespace: argocd
+  labels:
+    app.kubernetes.io/name: tekton-pipelines
+    app.kubernetes.io/part-of: homelab-infra
+    wave: "06"
+spec:
+  project: homelab
+
+  source:
+    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
+    targetRevision: main
+    path: k8s/infra/tekton
+
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: tekton-pipelines
+
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+    - CreateNamespace=true
+    - ServerSideApply=true
+    retry:
+      limit: 5
+      backoff:
+        duration: 5s
+        factor: 2
+        maxDuration: 3m
+
+  ignoreDifferences:
+  - group: admissionregistration.k8s.io
+    kind: ValidatingWebhookConfiguration
+    jsonPointers:
+    - /webhooks/0/clientConfig/caBundle
+    - /webhooks
+  - group: admissionregistration.k8s.io
+    kind: MutatingWebhookConfiguration
+    jsonPointers:
+    - /webhooks/0/clientConfig/caBundle
+    - /webhooks

k8s/argocd/apps/10-storage-observability.yaml

@@ -249,3 +249,26 @@ spec:
       selfHeal: true
     syncOptions:
       - CreateNamespace=true
+---
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: local-path-provisioner
+  namespace: argocd
+  annotations:
+    argocd.argoproj.io/sync-wave: "1"
+spec:
+  project: homelab
+  source:
+    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
+    targetRevision: main
+    path: k8s/infra/local-path
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: local-path-storage
+  # No CreateNamespace: the Namespace object (with its privileged PSA label,
+  # which the helper Pods need for their hostPath) is part of the manifest.
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true

k8s/argocd/apps/30-security.yaml

@@ -57,6 +57,55 @@ spec:
       prune: true
       selfHeal: true
 ---
+# ZITADEL — the Authentik replacement. Coexistence, not cutover: Authentik keeps
+# serving in the same `iam` namespace until the last consumer moves, then this
+# becomes the only IdP. Migration plan (outside git):
+# ~/workplace/homelab-doc/ZITADEL_MIGRATION.html
+#
+# Wave 3 ordering: sops-secrets (wave 0) creates the `zitadel-masterkey` Secret,
+# databases (wave 2) creates the `zitadel-db` CNPG cluster and its
+# `zitadel-db-app` DSN secret. Both must exist before the init job starts.
+#
+# automated sync is deliberately absent for the first sync — same reason as
+# forgejo. The chart ships `pre-install,pre-upgrade` Helm hooks (zitadel-init,
+# zitadel-setup), which ArgoCD maps to PreSync and re-runs on every sync, manual
+# or automated. A human reads the first sync's hook output before any repeat can
+# run. The init job runs `init zitadel` only (CNPG owns the database and the app
+# user), and the setup job creates the first org and the `iam-admin` machine key
+# that Terraform consumes. Read the SECOND-SYNC HAZARD block at the top of
+# k8s/infra/iam/zitadel-values.yaml before enabling automated sync.
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: zitadel
+  namespace: argocd
+  finalizers:
+    - resources-finalizer.argocd.argoproj.io
+  annotations:
+    argocd.argoproj.io/sync-wave: "3"
+spec:
+  project: homelab
+  revisionHistoryLimit: 3
+  sources:
+    - repoURL: https://charts.zitadel.com
+      chart: zitadel
+      # Pinned: the chart trails the upstream app release, and the verified
+      # masterkey/passwap facts were read at v4.19.x. A floating tag would
+      # change the app version without a diff anyone reviews.
+      targetRevision: 10.4.0
+      helm:
+        valueFiles:
+          - $values/k8s/infra/iam/zitadel-values.yaml
+    - repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
+      targetRevision: main
+      ref: values
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: iam
+  syncPolicy:
+    syncOptions:
+      - CreateNamespace=true
+---
 # Raw IAM manifests: key-rotation cronjob + authentik migration job.
 apiVersion: argoproj.io/v1alpha1
 kind: Application
@@ -152,13 +201,8 @@ metadata:
   namespace: argocd
   annotations:
     argocd.argoproj.io/sync-wave: "3"
-    argocd-image-updater.argoproj.io/image-list: runner=forgejo.riotpiao.com/rock/forgejo-runner-golang
-    argocd-image-updater.argoproj.io/runner.update-strategy: newest-build
-    argocd-image-updater.argoproj.io/runner.allow-tags: regexp:^[0-9a-f]{7}$|^latest$|^v[0-9]+$
-    argocd-image-updater.argoproj.io/runner.helm.image-name: runner.image.repository
-    argocd-image-updater.argoproj.io/runner.helm.image-tag: runner.image.tag
-    argocd-image-updater.argoproj.io/write-back-method: git
-    argocd-image-updater.argoproj.io/git-branch: main
+    # Image promotion: Forgejo package webhook → api-gw.
+    # Replaced ArgoCD Image Updater (removed 2026-09-10).
 spec:
   project: homelab
   source:
@@ -180,13 +224,8 @@ metadata:
   namespace: argocd
   annotations:
     argocd.argoproj.io/sync-wave: "3"
-    argocd-image-updater.argoproj.io/image-list: runner=forgejo.riotpiao.com/rock/forgejo-runner-node
-    argocd-image-updater.argoproj.io/runner.update-strategy: newest-build
-    argocd-image-updater.argoproj.io/runner.allow-tags: regexp:^[0-9a-f]{7}$|^latest$|^v[0-9]+$
-    argocd-image-updater.argoproj.io/runner.helm.image-name: runner.image.repository
-    argocd-image-updater.argoproj.io/runner.helm.image-tag: runner.image.tag
-    argocd-image-updater.argoproj.io/write-back-method: git
-    argocd-image-updater.argoproj.io/git-branch: main
+    # Image promotion: Forgejo package webhook → api-gw.
+    # Replaced ArgoCD Image Updater (removed 2026-09-10).
 spec:
   project: homelab
   source:
@@ -211,13 +250,8 @@ metadata:
   namespace: argocd
   annotations:
     argocd.argoproj.io/sync-wave: "3"
-    argocd-image-updater.argoproj.io/image-list: runner=forgejo.riotpiao.com/rock/forgejo-runner-rust
-    argocd-image-updater.argoproj.io/runner.update-strategy: newest-build
-    argocd-image-updater.argoproj.io/runner.allow-tags: regexp:^[0-9a-f]{7}$|^latest$|^v[0-9]+$
-    argocd-image-updater.argoproj.io/runner.helm.image-name: runner.image.repository
-    argocd-image-updater.argoproj.io/runner.helm.image-tag: runner.image.tag
-    argocd-image-updater.argoproj.io/write-back-method: git
-    argocd-image-updater.argoproj.io/git-branch: main
+    # Image promotion: Forgejo package webhook → api-gw.
+    # Replaced ArgoCD Image Updater (removed 2026-09-10).
 spec:
   project: homelab
   source:

k8s/argocd/apps/55-api-gateway.yaml

@@ -36,11 +36,9 @@ metadata:
     app.kubernetes.io/component: gateway
   annotations:
     argocd.argoproj.io/sync-wave: "7"
-    # ArgoCD Image Updater - auto-update on new image push
-    argocd-image-updater.argoproj.io/image-list: gw=forgejo.riotpiao.com/rock/api-gateway
-    argocd-image-updater.argoproj.io/gw.update-strategy: digest
-    argocd-image-updater.argoproj.io/gw.allow-tags: regexp:^latest$
-    argocd-image-updater.argoproj.io/write-back-method: argocd
+    # Image promotion: Forgejo package webhook → api-gw /v1/webhooks/forgejo
+    # → patches this Application's kustomize.images via k8s API.
+    # Replaced ArgoCD Image Updater (removed 2026-09-10).
 spec:
   project: homelab
   revisionHistoryLimit: 3

k8s/argocd/apps/60-applications.yaml

@@ -110,37 +110,6 @@ spec:
     syncOptions:
       - CreateNamespace=true
 ---
-# iMessage/SMS delivery. Raw manifests: a privileged macOS VM (Docker-OSX)
-# running the BlueBubbles server, plus its dedicated local StorageClass.
-#
-# Pinned to worker-2 via nodeSelector `workload: imessage` + a matching
-# toleration for that node's taint. Until worker-2 is provisioned this app
-# syncs everything except the pod, which stays Pending — that is expected.
-#
-# No CreateNamespace: namespace.yaml carries `pod-security: privileged`, which
-# the VM needs (/dev/kvm, privileged), and an ArgoCD-created namespace would
-# not have those labels.
-apiVersion: argoproj.io/v1alpha1
-kind: Application
-metadata:
-  name: sms
-  namespace: argocd
-  annotations:
-    argocd.argoproj.io/sync-wave: "8"
-spec:
-  project: homelab
-  source:
-    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
-    targetRevision: main
-    path: k8s/apps/sms
-  destination:
-    server: https://kubernetes.default.svc
-    namespace: sms
-  syncPolicy:
-    automated:
-      prune: true
-      selfHeal: true
----
 # Document management. Raw manifests (no Helm): postgres is the dedicated
 # paperless-db CNPG cluster in k8s/infra/databases (wave 2), redis is
 # in-cluster only (no PVC), media lives on the cp-3 USB HDD (see
@@ -246,11 +215,8 @@ metadata:
   namespace: argocd
   annotations:
     argocd.argoproj.io/sync-wave: "8"
-    # ArgoCD Image Updater - auto-update on new image push
-    argocd-image-updater.argoproj.io/image-list: app=forgejo.riotpiao.com/rock/portfolio
-    argocd-image-updater.argoproj.io/app.update-strategy: digest
-    argocd-image-updater.argoproj.io/app.allow-tags: regexp:^latest$
-    argocd-image-updater.argoproj.io/write-back-method: argocd
+    # Image promotion: Forgejo package webhook → api-gw.
+    # Replaced ArgoCD Image Updater (removed 2026-09-10).
 spec:
   project: homelab
   source:

k8s/argocd/apps/70-poimen.yaml

@@ -1,37 +1,81 @@
+# Poimen — unified ArgoCD Application (wave 7).
+#
+# Consolidates what was previously five separate apps:
+#   poimen            → source 1 (poimen-workflows workers)
+#   poimen-workflows  → duplicate of source 1 (deleted)
+#   poimen-memory     → source 2 (memory service + redis)
+#   poimen-memory-app → duplicate of source 2 (deleted)
+#   poimen-memory-database → source 3 (CNPG cluster, moved to k8s/infra/poimen)
+#
+# poimen-toolkit is intentionally kept as a separate Application because it
+# manages cluster-scoped CRDs (ToolDefinition). A bad CRD can affect the
+# whole cluster; keeping it separate means it has its own sync history,
+# independent rollback, and can be paused without touching app workloads.
+#
+# Sync ordering via argocd sync-wave annotations:
+#   wave -1 → DB (CNPG Cluster) — must be Ready before app pods start
+#   wave  0 → all application Deployments (default)
+#
+# Image Updater tracks all four images. Write-back via argocd (in-cluster
+# annotation patch — no git commit per image update).
 apiVersion: argoproj.io/v1alpha1
 kind: Application
 metadata:
   name: poimen
   namespace: argocd
+  labels:
+    app.kubernetes.io/part-of: poimen
   annotations:
     argocd.argoproj.io/sync-wave: "7"
-    # Image Updater: auto-update on new image push (SHA tag filter)
-    argocd-image-updater.argoproj.io/image-list: |
-      memory=forgejo.riotpiao.com/rock/poimen-memory
-      workflows=forgejo.riotpiao.com/rock/poimen-workflows
-      frontend=forgejo.riotpiao.com/rock/poimen-frontend
-    argocd-image-updater.argoproj.io/memory.update-strategy: digest
-    argocd-image-updater.argoproj.io/memory.allow-tags: regexp:^latest$
-    argocd-image-updater.argoproj.io/workflows.update-strategy: digest
-    argocd-image-updater.argoproj.io/workflows.allow-tags: regexp:^latest$
-    argocd-image-updater.argoproj.io/frontend.update-strategy: digest
-    argocd-image-updater.argoproj.io/frontend.allow-tags: regexp:^latest$
-    argocd-image-updater.argoproj.io/write-back-method: argocd
+    # ── Image promotion ──────────────────────────────────────────────────────
+    # Forgejo package webhook → api-gw patches kustomize.images per source.
+    # Source index mapping: 0=workflows, 1=memory, 3=frontend.
+    # Replaced ArgoCD Image Updater (removed 2026-09-10).
 spec:
   project: homelab
-  source:
-    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/poimen-workflows.git
-    targetRevision: main
-    path: k8s
+  # Multi-source: each repo owns its own k8s manifests.
+  # ArgoCD syncs all sources in parallel; sync-wave annotations on individual
+  # resources control ordering within the sync operation.
+  sources:
+    # 1. Workers — Temporal activity + workflow workers, pi-worker pool
+    - repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/poimen-workflows.git
+      targetRevision: main
+      path: k8s
+
+    # 2. Memory service — poimen-memory API, Redis cache, NetworkPolicies
+    - repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/poimen-memory.git
+      targetRevision: main
+      path: k8s/app
+
+    # 3. Database infrastructure — CNPG Postgres cluster (wave -1)
+    #    Moved from k8s/infra/databases to isolate poimen DB from other tenants.
+    - repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
+      targetRevision: main
+      path: k8s/infra/poimen
+
+    # 4. Frontend app manifests — Deployment, Service, NetworkPolicy.
+    #    Each repo owns its own k8s/ (same pattern as homelab-frontend for api-gw).
+    - repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/poimen-frontend.git
+      targetRevision: main
+      path: k8s
+
+    # 5. Frontend ingress — poimen.riotpiao.com edge route.
+    #    Lives in homelab (same pattern as k8s/apps/api/ for api-gw).
+    - repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
+      targetRevision: main
+      path: k8s/apps/poimen-frontend
+
   destination:
     server: https://kubernetes.default.svc
     namespace: poimen
+
   syncPolicy:
     automated:
       prune: true
       selfHeal: true
     syncOptions:
       - CreateNamespace=true
+      - SkipDryRunOnMissingResource=true
     retry:
       limit: 5
       backoff:

k8s/argocd/apps/71-poimen-toolkit.yaml

@@ -0,0 +1,32 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: poimen-toolkit
+  namespace: argocd
+  annotations:
+    argocd.argoproj.io/sync-wave: "7"
+    # Image promotion: Forgejo package webhook → api-gw.
+    # Tracks: poimen-toolkit-controller, pi-worker.
+    # Replaced ArgoCD Image Updater (removed 2026-09-10).
+spec:
+  project: homelab
+  source:
+    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/poimen-toolkit.git
+    targetRevision: main
+    path: k8s
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: poimen
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+      - CreateNamespace=true
+      - ServerSideApply=true
+    retry:
+      limit: 5
+      backoff:
+        duration: 5s
+        factor: 2
+        maxDuration: 3m

k8s/argocd/apps/98-talos-repair.yaml

@@ -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

k8s/argocd/apps/99-oidc-bootstrap.yaml

@@ -0,0 +1,20 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: oidc-bootstrap
+  namespace: argocd
+  annotations:
+    argocd.argoproj.io/sync-wave: "5"
+spec:
+  project: homelab
+  source:
+    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/homelab.git
+    targetRevision: main
+    path: k8s/infra/oidc-bootstrap
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: kube-system
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true

k8s/argocd/projects/homelab-project.yaml

@@ -24,6 +24,7 @@ spec:
     - https://forgejo.riotpiao.com/riotpiao-poimen/poimen-memory.git
     - https://forgejo.riotpiao.com/riotpiao-poimen/poimen-workflows.git
     - https://forgejo.riotpiao.com/riotpiao-poimen/poimen-frontend.git
+    - https://forgejo.riotpiao.com/riotpiao-poimen/poimen-toolkit.git
     - https://forgejo.riotpiao.com/rock/riotpiao.com.git
     # Public Helm chart repos referenced by k8s/argocd/apps/* and bootstrap/*
     - https://cloudnative-pg.github.io/charts
@@ -34,6 +35,7 @@ spec:
     - https://grafana.github.io/helm-charts
     - https://helm.releases.hashicorp.com
     - https://charts.goauthentik.io
+    - https://charts.zitadel.com
     - https://strimzi.io/charts/
     - https://charts.bitnami.com/bitnami
     - https://homarr-labs.github.io/charts

k8s/argocd/secrets/etcd-defrag-creds.enc.yaml

@@ -0,0 +1,27 @@
+apiVersion: v1
+kind: Secret
+metadata:
+    name: etcd-defrag-creds
+    namespace: kube-system
+    labels:
+        app.kubernetes.io/name: etcd-defrag
+type: Opaque
+stringData:
+    ca.crt: ENC[AES256_GCM,data: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,iv:KnW9LYNzxZ6r3Q6LTeOrgSLLPgiJlibVp6YmTEKBkjE=,tag:KTL1nOWdNWDA4dLVaA4//g==,type:str]
+    client.crt: ENC[AES256_GCM,data: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,iv:l8BwxxEfHfYrm+mM5UE6Yj42DeeU9y23jjIE1KjIiME=,tag:HwRT6/myIsxc84BYDj3K6w==,type:str]
+    client.key: ENC[AES256_GCM,data:QD/Glf3lFslBEdEoJ3CNrYzlw2HLCvGSeVuJLtxnFne2aJOuw0sk/e0h/kSAxvG4dZ+LIWJLLbqTjKHOAhkvS/ZOA7GSea4ubNkvTkw8+JBRuYwb2D2iB8kZhlER/CpiGkYJukjkgGP1CzHdvBY1M88pW9w6rH74MD3jY47qExIaNduQj5vkUQZ8ajqkd79l0nk98ZTawfPG4AFcEtAIKAPIuubT2GZ3qqNLjOI7agbtRv8xI44hhb2wj5J9xdl1GrbOWwG5EOo+hLNrcAAOCcWBpNTUCKBy7mrk2ID8jX3HsFWN76DDlQzkhcphMhlM7g==,iv:49HGJAEgllEkB3YSiZLmbWs/vlbFbY52kiKesdGVC/Y=,tag:g8YZ9at3V2l6RFRfvO2lAQ==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB4Z0h0R2dhbDdRcFJydE9o
+            R0hWeCtwVzluZWZlR0VtOXcxdW9FbklOQXlzCmo3eXNyNlFjejNETkJiVVRVWFhr
+            a2pORnhIQTI0UUk2N3dWMDZJcEhYU1UKLS0tIEduaHlmMHQza1A0TGVZb0JrbTYz
+            MWJwQjcrdkkzQXhOTmhycERsM0FtNVEKG+gBRcvUsyfRzuW999EQNzyDh2/5fY6p
+            8ab2xvTOJPiMUBTBuQZsA+iDImytUO/02ROQsbEZkALijp1nqrsV/g==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-10-07T05:37:26Z"
+    mac: ENC[AES256_GCM,data:vu6ltV0jYQNGV4eqIcqAp9p2TJ8ULBX5JBELUgm/nA9GX+I6Pv3fyjpcHRSWY0HbLvCwgXd22CG4IYcj4HJFtQGZR7OcQA5WM5plZH3RCPdvPNix/798vkETfpJxorQjlHoq4nlr3dEmUCbzdtE07qV2W1M6GJr4C9xKvB947bQ=,iv:aA9mjZCFAoLEhGqkl6NfyBZ3x3vWGfLYYAEe8jXuA4U=,tag:Drdiji33ckDd8ildpvSEXw==,type:str]
+    version: 3.13.2

k8s/argocd/secrets/forgejo-registry-pat-api.enc.yaml

@@ -0,0 +1,23 @@
+apiVersion: v1
+kind: Secret
+metadata:
+    name: forgejo-registry-pat
+    namespace: api
+type: Opaque
+stringData:
+    pat: ENC[AES256_GCM,data:alYPvHBVqnf13NZu6jtgA6WdFM4x46s5mIY8uEnfWdq0Vp+7oKrY1A==,iv:JbUjes5ZB9eKQ1nkV02++7F/BaWIROfT6gjShzajXro=,tag:ApjawJold0QApnX1GUXGhw==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB6bFZhU3JLSUZEVWhYdEdZ
+            MURoSWNlZjY0RkxyaWlwU2ZTVjJ5V2FnMVVZCis5YlBwQnZrWnVJNFh4UnNldmx6
+            Y2JjdnpkRTVGSjRSZ0U0THdDZHIrNHcKLS0tIHZDd1BDVGRDSHJEQThuTExORWs2
+            b3BxenY4WHhpRkRTZHJGMkNYMm14RnMKH//Xpqbf/ZBNFQ43D0eFUWwRcQWqA3CC
+            RG8U9wyxC6YrlruU2hY6eB2x0OjsVic34ZGaR752Bwyp0Pz49C/k3g==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-09-28T03:10:55Z"
+    mac: ENC[AES256_GCM,data:nLZueHygckw+Gddlea90tRU8h8nEGpe21JUi9nCdpc0ctkSlTDqcR3Q7JFPwbEGHGFU5UJ2xnkBZEDIVmExJryqPBMXT7hQd3ySeQgPwAPGt6zEhlRc5jXhqmmrpJiiN5XUL52AZVDwcWACg7kVzBXIClzihFRW+UqjJZhdtELM=,iv:C0H4AFfdfpsBvP1z2chVvW/VTejxYxwNn/KuA50LeH0=,tag:ZEkTCTKvoZH7DjrcwfL3dw==,type:str]
+    version: 3.13.2

k8s/argocd/secrets/forgejo-registry-pat.enc.yaml

@@ -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

k8s/argocd/secrets/forgejo-registry-token.enc.yaml

@@ -0,0 +1,24 @@
+apiVersion: v1
+kind: Secret
+type: Opaque
+metadata:
+    name: forgejo-registry-token
+    namespace: cicd
+data:
+    username: ENC[AES256_GCM,data:oRNecs0a7rs=,iv:/5EFdNqpSjoxe7XDmAEDMd6lXd0SMsRiMmBM9SIwDHY=,tag:Wi+ggoP+9/vgz9rHrxB9nA==,type:str]
+    password: ENC[AES256_GCM,data:HbmwnWk3ST5SDWXwIhu+M5f/FOfFbJHaG0Q/IWrO63HRXmJTmLMpbjtWIXC9IMFoHeDZ1MNAV8A=,iv:ztJZgpaS//yYCiyr6/ubs/UiXkbGMnokvy4Pe45jQMk=,tag:WMpawc/SVAV4mxsCd6XqAA==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBjQmhxN2E3ZnNTdkR6U2c1
+            ZStsQktkeWUwMEdmdFIyMkRYRVk1ZGppWlZ3CmUzR2JubWw2VjdWUGt6S2lpNmQ3
+            cDdSWjJiYzRIWS9UVERpVDFJenFnaDAKLS0tIGhDSmNMSjZwcDVPR3U0dUcwNk9Q
+            WmdGS1lyS3dkSXIvOFhyRklGRll2UlUK8NGts6a6Fv10c6gxIIPqIIqfgzQ3EEyk
+            SFrMThwbdaOqLY4AMeDrg+k0Y2t1Xj/XOvdNbRCRictDwZUsptvO7A==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-10-06T02:01:24Z"
+    mac: ENC[AES256_GCM,data:imebczVzG9YWd42ER4a+w+Bi3dxbN0HFm/1igxzJt6Z0HG/q6i0s59swpGVruk9dQJWrlO8KKqX739ATp2KGC5szrEuRFvPemF594XFCg6ykW+ZeP5VtTvpJg2nHv7/Pu+71ljKKi4gqOJ4SJDn8owAbSN+su6PiT323wax930A=,iv:iG/G2+qQkvbBU95w/GG2PrbAHDOaamuvjqMDBxSW6zI=,tag:wy9Vn72HBDHqCyzTcV15/Q==,type:str]
+    version: 3.13.2

k8s/argocd/secrets/memory-agent-oidc.enc.yaml

@@ -0,0 +1,26 @@
+apiVersion: v1
+kind: Secret
+type: Opaque
+metadata:
+    name: memory-agent-oidc
+    namespace: poimen
+data:
+    CLIENT_ID: ENC[AES256_GCM,data:c/RvtV6anofX8h1BmlKu9w==,iv:3lQ1BR8kVvF1RHVfKstmb0Y7u/uX5OrvmGiCi/xTpjw=,tag:9JC2WkfQFWaiZroAEmPenw==,type:str]
+    CLIENT_SECRET: ENC[AES256_GCM,data:I258/6O43PccyllYN/wfoKvTgNgZONTivM/KFIr8TGqSl+2XQkwBXvK2VQc5Xgc5cpwlrgnjk8pjQbqr,iv:MZyA+V5z9Po2VoxqvOSlWh1fZp1lrkcbYMx7VcSIaJs=,tag:gXH0BpA8KOZiVd+4RnhRzg==,type:str]
+    ISSUER: ENC[AES256_GCM,data:GX/uQPDoeJWXXQZlzD6oOIvxo7H4LRAv4MrPAiCgmv6WxW59+KKkymuDT/T9MiDm4bNhxVPgB7nHbDcMHfPvU2zCNM2TWYUsNOgGwxNAqM8=,iv:5OEsdrUZvMLO2C8Ea2i5alsyFGtmEk3othTemk8fOk4=,tag:8CMlRY2JCe4z4fv4WuWjRQ==,type:str]
+    TOKEN_URL: ENC[AES256_GCM,data:KeU1pQzvQ2/1lQhOqNtcR7t5TGVx1J7NY8ogxCXS6IuHhVe0zWYIbC4BYFc2H9PAjsMJwCCg75N1FrIiCYBvpfK8ln0=,iv:NbPiJC/B7W1Zm+JwnEGDikE2cb3L4l6TBeQTKEb2boM=,tag:FRmllFLZzQW03lsCu9mAUA==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBmK0dPSmhKT01FSitDdUNW
+            Um1XQU9FVnBUeDdoWXpCcXRzVXh0VXkvNGxNClZaQ3R5U2NkYTJjaFdHRWhUVmFS
+            K0tHZVRFRDZGREVRZzZqcWJ6dnRpUUEKLS0tIE15UUNtMStKbWwzb3dEVGEwN1VQ
+            cktlVTM2SUhpOGJZMXJOOG84RnhCQzAKOdM0pThEaN37SJtRrKIivncMu8Z91Btq
+            es6NOlJdBUhzIhnEJWfDzZ9aA6I/fYzugKbC+AfUwdGgThAgHx9crg==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-10-06T02:01:24Z"
+    mac: ENC[AES256_GCM,data:/BTQ984D+hsk0LmnjD3hxopB65NAR54LhoAPNcATWA7MCTJXfdnYRu3gNxUzyiyCBd+rDaPp77TBnak4jVjMnOiYJsYLj1R7hrrhTZopz8pT+YNMupperwsirKZwK8it4Mu+fnpCyox2mtGED0hk+Nh/b6IteTRt5lS7noumo2M=,iv:RWIrVkNYj+8mqMSPiLueToexabzAtVbIR525m6bUrlg=,tag:5+wcNoNYsjGKpFlML+N70Q==,type:str]
+    version: 3.13.2

k8s/argocd/secrets/oauth2-credentials.enc.yaml

@@ -0,0 +1,27 @@
+apiVersion: v1
+kind: Secret
+type: Opaque
+metadata:
+    name: oauth2-credentials
+    namespace: iam
+data:
+    api-gw-client-secret: ENC[AES256_GCM,data:YiUCk61cCsTJE8gTLZWhqVPsCSu3b4OnG+Oh456A+mnxip0FjLTTqV+kYBdfZivIkn9ua4RcVW+rYILu,iv:K08m1EaB7/SIVNWZ3FfeRP4tbCAo6KeiNC0NpE9VO1o=,tag:ZXV9YRWUOPJ/vdoqMtvQeA==,type:str]
+    minio-client-secret: ENC[AES256_GCM,data:vcwLo1cJqbZr2MwkAKO09xPjb09ss7+s6HIvEfaLxt8ka5PUAlXQ37pTkynuktlKq/t0DvSk+x1+5G7QqVD1JJlwyDGM6yuOhBQ3MwucLNl+T4RDKtgGuA==,iv:sCdd+UNX2TfTAM6Zslrh8KrvBSzqpe67F3YMGrl4YDU=,tag:9Tpzm9NEXNuXyCd7l7GeHw==,type:str]
+    poimen-client-secret: ENC[AES256_GCM,data:dYtCiMGZaOFokihfGD2SXJDfXrhfwEQcTOPNu7JNHDUnx0hqwAdYAPAJTEN21p0OpHYDINMs5lwUpMwY,iv:ll8USuzs0881ryHImVjHGO0iFxUzqg5XtI6Ekd+EFXE=,tag:I/4ZfB9Ss4zEP57sRtRTXQ==,type:str]
+    paperless-client-secret: ENC[AES256_GCM,data:XMj9rHkI20lI37vChq9wS5lUq7l95SisRX0LChuj09O5w76Zt9NdG6OEUYQFf1z8vCfMJxBInIEEIq0e,iv:UpYy2ZEZ4AgBACEyrlxEcr13V+8Ksu4p8JHYApmyYHo=,tag:o9Z+/b6T9POgowIsks56kw==,type:str]
+    grafana-client-secret: ENC[AES256_GCM,data:V/j0+P3HoDLqYjRalWK4v1hvJTuVmzxVra47HsF1/BZvWZjIyEIH3Pt8BekT3O1dUFynxjcaxdZMBVYg,iv:9pMp+vIsp/sA7GP9wqNDf5DdZVLDow46OURW0mMRXIc=,tag:i7VJFA5o0hToZEJ5JPWIvw==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB2amZPendIOU9PeStOcmJG
+            c1dzOFVvd3RoT3dXQlJUNkdCSytEZUVGVEJJCklMUkNjUytBMXh0OVUrNUlpMWw3
+            aHRFT1hBZTZHNHVtaGJCTEFyT2ZWNWsKLS0tIENxR3FKMEplV0V5Y0dsZzBkODVG
+            U0ZlT2R0VFdEQmpsakVvZ1FJRkRQYTAKESQcSlMAuCG0/tLWWZaeoPayf1EKxSaf
+            e4o8TmjmSgPEhepQ/LmNXl6obyuqUxztkh4Mm6pocqDp+gfzt7X/1g==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-10-06T02:01:24Z"
+    mac: ENC[AES256_GCM,data:AI/znHiUa/Rwg0YRz65qUZ+b6V73oi3ZfAG/V5uZZvrGFrA0EISzD5LaP5Kl4GUU1svo4G5EI4aftPDgpdPptz21CCa8iYkXGe9pTDmtaE5ZICQAUbRcVhGMTfuWFhrgEhMfCJdOpfHaIQVEsQJQJgrnkXQVuUe9aT75LQz7pnY=,iv:KbIaYT0VeBT2WeSU5V5ZB4e+04JICYaY+egGN1Pv5bM=,tag:pPbhDxeLUx6V1XC/LPwxTg==,type:str]
+    version: 3.13.2

k8s/argocd/secrets/paperless-ai-secrets.enc.yaml

@@ -1,23 +1,24 @@
-apiVersion: ENC[AES256_GCM,data:l7I=,iv:NZY7r3JVW3zVwxeiScvWKpAQUDa9+nckHd0qWVrGU88=,tag:qpowp5OILdYKtTux/nlWpg==,type:str]
-kind: ENC[AES256_GCM,data:6oeEbuIk,iv:5flI9TtcYQ961wOYPBPhvQpitHFYAf8yMdNBXqytbJs=,tag:WNhlbKmSeZEqZ9ZgiB/BYg==,type:str]
+apiVersion: v1
+kind: Secret
 metadata:
-    name: ENC[AES256_GCM,data:fvJMsgy+wPZqMCdxm9hoV3n/+Q==,iv:I3rVtHIJBOME+bxhPws58Zjhj5i+KT5UtB9o7Vus5EU=,tag:6h4FnUu7PGxlQPIQxPYCRg==,type:str]
-    namespace: ENC[AES256_GCM,data:CDriLoLovROW,iv:rHXcN1xm5+t2D/Tq/2sx9lQFF8anD5jH24ZntPuBA8U=,tag:XstJAz6S8IM1c/pp9Cg0Ww==,type:str]
-type: ENC[AES256_GCM,data:JdTwBbag,iv:9Ys15Ketl0ghNK0u0N8IOpUt7+KoloutiG5M9zHPXxw=,tag:teau/udf41Ty34A5wLAm6Q==,type:str]
+    name: paperless-ai-config
+    namespace: paperless
+type: Opaque
 stringData:
-    PAPERLESS_API_TOKEN: ENC[AES256_GCM,data:TuQeDx8po3h4loTRABlItVYQJ7gFjnmIn3zQQGtUcoNFMKpkqLK/GQ==,iv:TDg0stpca5pDtatqu8DFU7R0Bm/S/BI9ZoiG4K8mCT4=,tag:BfjX25V5gL7AeIsscClRAg==,type:str]
+    PAPERLESS_API_TOKEN: ENC[AES256_GCM,data:wlBC85ep6zioWLhfhNczkKfTMR8tmciN+4r3of8GpQoJmKyE2r7pOg==,iv:Rem/UJl5wUNi8G+uEV7f2eCLabaY26sZ7+AsKYiOZ4I=,tag:bGS1fu13Mwsrr+5NUEzzLw==,type:str]
+    LLM_AUTH_CLIENT_SECRET: ENC[AES256_GCM,data:co7FfmRXKgrz9fNgR10KtlHL/iG4F5WKJgjcKem1H5hF5FviVi4+CQNekA==,iv:ADtBHiI6BtrkuH1iIfKV3I5odNLMQe5y/9GGTJrPNN0=,tag:j6wX6zO5VhKoLzdr7BQZCw==,type:str]
 sops:
     age:
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBKVDN3aFVqVmFXY1VQVXZP
-            OUsrNHdNdlRvRFgvTDQrNE5uL2xaazVENTBjCkNPbGR5Vk16RXNDOW15OGNTRmFR
-            U0JOeTllaWU1dzNVY3lBbEVyVG5tOEkKLS0tIEZvajlvcUtJdFNNUkkzV3FKOFRj
-            UUE2TDBzT0xVc2E1NlUvQXAyZytMZEUKBv+ChaoQCstA742L3Bq5mBJlW/UC4Pyw
-            ZvFAyYbs1NaEqhjtHq+4T62jTWcH/St/vKgUuFQ9LCUQhYd8DUzAow==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBJWDZwTE1haUY5ZkgybnBx
+            WEFVSzQvNjlGaDlvaHhuSTVCY2dYb0s1NW4wCmhkM0N6YlNIRTYrVkdxaHJaVHVG
+            bUEzTVV3WFQ0OWwrdEZnanJJa09Nb3MKLS0tIGduNEFtT2hCUDlkZWpWZmliZy83
+            cUoxcXp1NFF3SFpBVVdSZE5GY1VIWmsKH+cMqasOVxgCnGedaM2IAsgwOzEsOMct
+            0XjmInpppWNe+t7leEb6MqEY2cPQHL+l2L5jkZzAOfImwaIwMQnghw==
             -----END AGE ENCRYPTED FILE-----
           recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
-    lastmodified: "2026-09-12T21:04:26Z"
-    mac: ENC[AES256_GCM,data:0ks96xQzOa8ygNDDYfKV8EJ8dWLBaC0PCnLG73NinMByF/KoWkCdwMDPC34W9xxVoTD2NiF1i/3pgCG4QFezTE7tPHPPKdYcQfwda9fkooiXW4Nh2M/sgbq/xgsy9N3qpHD/O5iILgpehb9y0DuErOyxcn2AIYizynU7m8e63pc=,iv:fvPWBsfE6YHskKzdlxJidp14dUgRR0XdMkEu6IxMMSo=,tag:5FiuIrFOg/GXvlQVy7drJQ==,type:str]
-    unencrypted_suffix: _unencrypted
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-09-14T14:19:39Z"
+    mac: ENC[AES256_GCM,data:jDdmiFg6uB1za7sAjO1CnGHdRPyUnmWCMJxqHrE3BO82pNbtm8yLOf+W6CfFKAjfZYqEE2mdKhABm7zeJgJlub3eXJbAirAFrp5jrbfHw0qsFo85Gj/BsrSDB401Aky6PxvRomz66FyX5zDDXIGAMEMlyNEadMplTfrZQQ9hQWM=,iv:UTSF72ofUyWs1LXGKQwBP60hK64UxhqTFM8QTVozGoo=,tag:OKivMDAqwWgrX+kNjvQrPg==,type:str]
     version: 3.13.2

k8s/argocd/secrets/pi-sandbox-secrets.enc.yaml

@@ -0,0 +1,24 @@
+apiVersion: v1
+kind: Secret
+type: Opaque
+metadata:
+    name: pi-code-agent-api-keys
+    namespace: poimen-sandbox
+stringData:
+    ANTHROPIC_API_KEY: ENC[AES256_GCM,data:TBcno/dzj3qykHjeX96UKZekuA/WMQT2E7a1ziPyYo5J6lWLPydgli84KeJZhH62/8CnnFtFOhVIe4FWCGPGjvqKH6M8WbiQHaP9y7FN0qQUpFHKNVAQ2R+s0wInhw0eUmANvd7bRx8aIZ2X,iv:oex19yVtWUevoJ0A3mkMLCfWu85o1gPSNp43x1iV0LE=,tag:BW3zQnwvagPceeNird9CZg==,type:str]
+    DEEPSEEK_API_KEY: ENC[AES256_GCM,data:vq/5gOsMVjlVMd0oXiBtHFHFEr+IF2YR2iP2OBFWx3ZFNoQ=,iv:QhLU/BRIJb/7QKDCRyw+HWPphZifVEhIOLywYDgOb20=,tag:BZdtXw+WsuK+P4E0caTa0Q==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBqNm1LNE5nWktnd3c3STg3
+            UlVWbWJxWElxUHMwa0JVMk81Z0c4d0JaQm1vCnpLQWJWV3hxOU00NzJIaG51Mmlr
+            ZWpNTFJWcmdtV0w4YndQeHpvSUx2MTAKLS0tIDVnNkNuVWhPUFZ5V2hFOEt1eitG
+            blVqRy8yNnYzSU1FNzZGNkxrRElvWVEKL3J77INje75+CvKXaJHC3CvONgHv7d0a
+            a10MITvfreFr6M4AN3Z/mno49SDMp15Q4oQRagHHxSTS1K54mWHo8g==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-10-06T01:19:49Z"
+    mac: ENC[AES256_GCM,data:GpYl8IRefms36GvO3RW41c0US7SOgoOhd4rumxsCdEf5ME9kJ0eOxPx8klMgnlYrkBnwHmad8jj7C+HcA5Eim7mdUaYOZZWPFohvC6N4GLHX85aH78P09CelqG5tdm/Gm+1QfxYu0vANYGCAVjLK7YbBbZjbZmbvVfQvAbs3mOY=,iv:y3lglGu8FhTHQpO1poSIKgGYJFu5J9yjIaOjulda6fY=,tag:5Sgh4TbtNFMw7xOJjYRn0g==,type:str]
+    version: 3.13.2

k8s/argocd/secrets/secret-generator.yaml

@@ -7,28 +7,34 @@ metadata:
       exec:
         path: ksops
 files:
-  - agent-pod-models.enc.yaml
-  - agent-pod-ssh-key.enc.yaml
-  - authentik-secrets.enc.yaml
-  - cloudflare-secrets.enc.yaml
-  - forgejo-registry-pat.enc.yaml
-  - forgejo-registry-pull.enc.yaml
-  - forgejo-runner-token.enc.yaml
-  - forgejo-secrets.enc.yaml
-  - grafana-oidc-secrets.enc.yaml
-  - grafana-secrets.enc.yaml
-  - homarr-auth-oidc.enc.yaml
-  - homarr-db-encryption.enc.yaml
-  - homarr-secrets.enc.yaml
-  - homelab-ca-secrets.enc.yaml
-  - loki-secrets.enc.yaml
-  - minio-secrets.enc.yaml
-  - paperless-secrets.enc.yaml
-  - vault-secrets.enc.yaml
-  - vault-unseal-keys.enc.yaml
-  - portfolio-secrets.enc.yaml
-  - gotify-admin-secrets.enc.yaml
-  - gotify-tokens-secrets.enc.yaml
-  - gotify-smtp-secrets.enc.yaml
-  - forgejo-smtp-secrets.enc.yaml
-  - paperless-ai-secrets.enc.yaml
+    - agent-pod-models.enc.yaml
+    - agent-pod-ssh-key.enc.yaml
+    - authentik-secrets.enc.yaml
+    - cloudflare-secrets.enc.yaml
+    - forgejo-registry-pat-api.enc.yaml
+    - forgejo-registry-pull.enc.yaml
+    - forgejo-runner-token.enc.yaml
+    - forgejo-secrets.enc.yaml
+    - grafana-oidc-secrets.enc.yaml
+    - grafana-secrets.enc.yaml
+    - homarr-auth-oidc.enc.yaml
+    - homarr-db-encryption.enc.yaml
+    - homarr-secrets.enc.yaml
+    - homelab-ca-secrets.enc.yaml
+    - loki-secrets.enc.yaml
+    - minio-secrets.enc.yaml
+    - paperless-secrets.enc.yaml
+    - vault-secrets.enc.yaml
+    - vault-unseal-keys.enc.yaml
+    - portfolio-secrets.enc.yaml
+    - gotify-admin-secrets.enc.yaml
+    - gotify-tokens-secrets.enc.yaml
+    - gotify-smtp-secrets.enc.yaml
+    - forgejo-smtp-secrets.enc.yaml
+    - paperless-ai-secrets.enc.yaml
+    - memory-agent-oidc.enc.yaml
+    - oauth2-credentials.enc.yaml
+    - forgejo-registry-token.enc.yaml
+    - pi-sandbox-secrets.enc.yaml
+    - etcd-defrag-creds.enc.yaml
+    - zitadel-masterkey.enc.yaml

k8s/argocd/secrets/talos-repair-config.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

k8s/argocd/secrets/zitadel-masterkey.enc.yaml

@@ -0,0 +1,23 @@
+apiVersion: v1
+kind: Secret
+metadata:
+    name: zitadel-masterkey
+    namespace: iam
+type: Opaque
+stringData:
+    masterkey: ENC[AES256_GCM,data:Da543Jt48o6p3f6/AbZRsjChz3NexPJoi/mC/LB6jUI=,iv:irS0n76tZ6QzoQMm0dWrvbw+SPfXz4h13jQb/Bjfgwg=,tag:tfbgaAdxmPIjleB1OXLn0Q==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBOZld2VG9NaFhIVWpBcGpO
+            SmVwNm9FT2wrQmFKb0RGQmY4TCtITjFEZjBjCmNuNXNJYTdsZE44cDNzR2hiNTdy
+            QWlVdzBtdjd0cSsxUjQxMzNyblhWTkkKLS0tIHBLT2x1MDBGdjE1eHFOdHVGa1NO
+            ZGM1K2lDTksraFdPeFdSZ1JyU1VtcjAKgTjjhr7u4YRuQVZQ7kAa1clJ0Rzy10hQ
+            Umcd4/YStyXHZjsJJpFSpOFdP5cZscGo3xBgpXtxAscKTS1Nw4derg==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1e5fq3hwxy78psus2nfvmtmua36g0u3suk78ephw6246l974d2utsvn0hla
+    encrypted_regex: ^(data|stringData)$
+    lastmodified: "2026-10-25T01:24:21Z"
+    mac: ENC[AES256_GCM,data:QFVk7KLsMLCAMH/PHVGCRyfU3k2JiO8AE3jJXmhnlUB4C8MYCTyOWQbnTFXozCMOr0kp+hAt3dYn/e23SWhyvJ7BgVLRb5QF1py704Dr46atVoLUvwHpFI7dyGK/LDTxqiM40RXAnDtWUJlTkVCzKdSFiV8CokIoByKWwxFPayM=,iv:t7HWMcpQl/DJ8Rp51Du7b5gURZO+C+FodsZSJuy5jBc=,tag:qEXSS4S0Y5cvn7T6EjakhA==,type:str]
+    version: 3.13.2

k8s/bootstrap/cert-manager/cert-manager-values.yaml

@@ -8,6 +8,19 @@
 # depend on them existing first.
 installCRDs: true
 
+# Point the ACME DNS-01 self-check at the public resolvers directly.
+#
+# Without these flags cert-manager resolves through the pod resolver
+# (CoreDNS at 10.96.0.10). The self-check then never saw the TXT record and
+# reported "Waiting for DNS-01 challenge propagation" forever. The wildcard
+# certificate renewal stalled on 2026-09-23 and the cert expired on
+# 2026-10-23, which broke every Cloudflare Tunnel origin with
+# "x509: certificate has expired".
+#
+extraArgs:
+  - --dns01-recursive-nameservers=1.1.1.1:53,8.8.8.8:53
+  - --dns01-recursive-nameservers-only
+
 # Tolerate the control-plane taint (talos-cp-1 is the only schedulable node).
 tolerations:
   - key: node-role.kubernetes.io/control-plane

k8s/bootstrap/ingress/riotpiao-com-cert.yaml

@@ -1,13 +1,21 @@
 # k8s/bootstrap/ingress/riotpiao-com-cert.yaml
 # Public wildcard cert for *.riotpiao.com, signed by Let's Encrypt (DNS-01 via
-# Cloudflare, see ../cert-manager/letsencrypt-issuer.yaml). Distinct from
-# homelab-tls (self-signed homelab-ca, internal *.riotpiao.com) —
-# reference riotpiao-com-tls explicitly on ingresses that expose riotpiao.com
-# hosts to the internet; it is not nginx's default-ssl-certificate.
+# Cloudflare, see ../cert-manager/letsencrypt-issuer.yaml).
 #
-# issuerRef starts on letsencrypt-staging. Switch to letsencrypt-prod once the
-# staging cert issues cleanly, then delete this Certificate's Secret to force
-# a re-issue against prod (staging certs aren't browser-trusted).
+# nginx serves this secret as its default-ssl-certificate
+# (../ingress/nginx-values.yaml), so every Ingress that omits a tls: block uses
+# it. Do not add per-host tls: blocks for *.riotpiao.com hosts: they create a
+# second, single-host certificate and split the wildcard coverage.
+#
+# Renewal is automatic and does not drop traffic:
+#   - cert-manager starts a new order 30 days before expiry (renewBefore).
+#   - cert-manager writes the renewed pair into the same secret.
+#   - ingress-nginx watches the secret and hot-reloads. No pod restart.
+#   - The old pair stays valid until the new one is written, so no gap exists.
+#
+# The DNS-01 self-check must reach the public resolvers directly. Without the
+# --dns01-recursive-nameservers flags in ../../cert-manager/cert-manager-values.yaml
+# the self-check never sees the TXT record and renewal stalls until expiry.
 apiVersion: cert-manager.io/v1
 kind: Certificate
 metadata:

k8s/bootstrap/phase3-forgejo/forgejo-values.yaml

@@ -45,7 +45,13 @@ gitea:
       SSH_DOMAIN: git.riotpiao.com
       SSH_PORT: 2222
       SSH_LISTEN_PORT: 2222
-      
+
+    # Self-signup was open (GET /user/sign_up returned 200), so anyone reaching
+    # forgejo.riotpiao.com could create an account. Accounts are provisioned by
+    # the admin only; admin create-user via UI/API is unaffected by this flag.
+    service:
+      DISABLE_REGISTRATION: true
+
     database:
       DB_TYPE: postgres
       HOST: forgejo-db-rw.cicd.svc.cluster.local:5432
@@ -101,7 +107,9 @@ ingress:
   enabled: true
   className: nginx
   annotations:
-    cert-manager.io/cluster-issuer: letsencrypt-prod
+    # No cert-manager annotation. forgejo.riotpiao.com is covered by the
+    # *.riotpiao.com wildcard, served as nginx's default-ssl-certificate.
+    #
     # This chart Ingress and the hand-written one in
     # k8s/bootstrap/ingress/ingress.yaml both claim forgejo.riotpiao.com.
     # ingress-nginx breaks the tie by oldest creationTimestamp, and the chart's
@@ -119,10 +127,9 @@ ingress:
       paths:
         - path: /
           pathType: Prefix
-  tls:
-    - secretName: forgejo-tls
-      hosts:
-        - forgejo.riotpiao.com
+  # tls: intentionally omitted. The chart would create a second, single-host
+  # certificate (forgejo-tls) that expired on 2026-10-23 and competed with the
+  # wildcard. The wildcard covers this host.
 
 # Resources
 resources:
@@ -166,3 +173,8 @@ deployment:
         secretKeyRef:
           name: forgejo-smtp
           key: password
+    # Allow webhooks to reach api-gw through the cluster ingress (resolves to
+    # internal ClusterIP 10.101.x.x which is blocked by default ALLOWED_HOST_LIST).
+    # api.riotpiao.com is our own gateway — safe to allowlist.
+    - name: GITEA__WEBHOOK__ALLOWED_HOST_LIST
+      value: "external,api.riotpiao.com"

k8s/infra/argocd-image-updater/values.yaml

@@ -1,70 +0,0 @@
-# ArgoCD Image Updater configuration
-# Watches Forgejo registry and updates ArgoCD Applications with new image tags
-
-config:
-  # Registry configuration - Forgejo allows anonymous pulls
-  registries:
-    - name: forgejo
-      api_url: https://forgejo.riotpiao.com
-      prefix: forgejo.riotpiao.com
-      default: true
-      insecure: false
-
-  # Log level
-  logLevel: debug
-
-  # ArgoCD API server
-  argocd:
-    grpcWeb: true
-    serverAddress: argocd-server.argocd.svc.cluster.local
-    insecure: true
-    plaintext: true
-
-  # Git write-back configuration (for multi-source Applications)
-  git:
-    # Commit author for image updates
-    user:
-      name: "ArgoCD Image Updater"
-      email: "[email protected]"
-    # Use SSH keys from ArgoCD's known hosts + credentials
-    # Image Updater inherits ArgoCD's git credentials (mounted via ArgoCD secret)
-
-# Mount ArgoCD's git credentials for write-back
-extraVolumes:
-  - name: argocd-ssh-known-hosts-cm
-    configMap:
-      name: argocd-ssh-known-hosts-cm
-      defaultMode: 0644
-  - name: argocd-gpg-keys-cm
-    configMap:
-      name: argocd-gpg-keys-cm
-      optional: true
-      defaultMode: 0644
-  - name: argocd-gpg-pubring
-    configMap:
-      name: argocd-gpg-pubring-cm
-      optional: true
-      defaultMode: 0644
-
-extraVolumeMounts:
-  - name: argocd-ssh-known-hosts-cm
-    mountPath: /etc/ssh/ssh_known_hosts.d/argocd-ssh-known-hosts
-    subPath: ssh_known_hosts
-  - name: argocd-gpg-keys-cm
-    mountPath: /etc/gpg/source
-  - name: argocd-gpg-pubring
-    mountPath: /etc/gpg/pubring
-
-# Extra environment variables
-extraEnv:
-  - name: GIT_SSH_KNOWN_HOSTS_CONFIG_MAP_ENABLED
-    value: "true"
-
-# Resources
-resources:
-  requests:
-    cpu: 50m
-    memory: 64Mi
-  limits:
-    cpu: 200m
-    memory: 128Mi

k8s/infra/cluster-maintenance/etcd-defrag-cronjob.yaml

@@ -0,0 +1,177 @@
+# etcd backend maintenance: compact, defrag, disarm NOSPACE.
+#
+# Why this exists
+# ---------------
+# etcd's backend file only grows. The apiserver compacts every 5m, but
+# compaction marks superseded revisions free *inside* the file; only `defrag`
+# returns that space to the filesystem. Nothing ran defrag, so the file grew
+# until it crossed the 2 GiB quota:
+#
+#   2026-10-07  backend 2,148,843,520 B (2.1 GB) on talos-cp-1 and talos-cp-3
+#               -> etcd raised NOSPACE on those two members
+#               -> etcd rejected ALL writes cluster-wide
+#               -> kubelets could not post node status: 3 nodes NotReady
+#               -> apiserver writes returned 500, the tunnel API path 502
+#
+# The live data was tiny: 15,943 keys, 69 MB after compaction. The rest was
+# dead pages. Recovery was `compact <current-revision>` then `defrag` per
+# member then `alarm disarm`. Compaction had also stalled while the alarm was
+# up, so `dbSizeInUse` read 100% of the file - defrag alone would NOT have
+# worked. Order matters: compact first, then defrag.
+#
+# The earlier revision of this file never ran, for two independent reasons:
+#   1. it existed only on branch fix/etcd-defrag-cron; the ArgoCD application
+#      `cluster-maintenance` tracks `main` (targetRevision: main), so the
+#      cluster never had the CronJob or the Secret.
+#   2. the image was quay.io/coreos/etcd, which has NO /bin/sh (verified:
+#      `exec: "/bin/sh": no such file or directory`). Any container that runs
+#      a shell script needs an image that ships one.
+# This revision fixes both: image bitnamilegacy/etcd (ships bash + etcdctl
+# 3.6.4, matching the 3.6.11 servers) pinned by digest.
+#
+# Cadence: every 15 days. Measured growth is ~29 MB/day, so a 15-day cycle
+# peaks near 500 MB - comfortably under the 2 GiB quota. The schedule is daily
+# and the script exits unless the UTC epoch day is a multiple of 15. That gives
+# an exact 15-day interval; `*/15` in the day-of-month field does not (it fires
+# on the 1st, 16th and 31st, which puts two runs one day apart).
+#
+# Safety
+# ------
+# 1. Compaction uses the MINIMUM revision across members. Compacting to a
+#    revision a member has not reached wedges that member - measured on
+#    2026-10-07, when talos-cp-2 froze ~1.2M entries behind the leader and
+#    needed a reboot to rejoin.
+# 2. A member whose raft applied index lags the leader by more than 100000 is
+#    skipped and reported. Defragging a frozen member reclaims nothing.
+# 3. Members are defragged one at a time. A defrag pauses the member's apply
+#    loop for the duration of the file copy.
+#
+# Credentials: Secret etcd-defrag-creds in kube-system, SOPS-managed in
+# k8s/argocd/secrets/etcd-defrag-creds.enc.yaml (ksops generator 00-secrets).
+# Its client certificate is signed by the cluster's etcd CA and expires
+# 2036-10; rotate it before then by re-running the mint and re-encrypting.
+#
+# Companion alerts (monitoring): etcd_mvcc_db_total_size_in_bytes /
+# etcd_server_quota_backend_bytes > 0.8, and an etcd NOSPACE alarm alert.
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: etcd-defrag
+  namespace: kube-system
+  labels:
+    app.kubernetes.io/name: etcd-defrag
+    app.kubernetes.io/part-of: cluster-maintenance
+spec:
+  schedule: "0 3 * * *"            # daily; the script acts only every 15th day
+  concurrencyPolicy: Forbid
+  startingDeadlineSeconds: 600
+  successfulJobsHistoryLimit: 3
+  failedJobsHistoryLimit: 3
+  jobTemplate:
+    spec:
+      backoffLimit: 2
+      template:
+        spec:
+          restartPolicy: OnFailure
+          tolerations:
+            - key: node-role.kubernetes.io/control-plane
+              operator: Exists
+              effect: NoSchedule
+          containers:
+            - name: defrag
+              image: bitnamilegacy/etcd:3.6.4@sha256:c86c06f1ce6a08b6df21eb7a9655b1818778b64c85b5cbb8413ebf7534789730
+              env:
+                - name: ETCDCTL_API
+                  value: "3"
+                - name: ETCDCTL_CACERT
+                  value: /etc/etcd/ca.crt
+                - name: ETCDCTL_CERT
+                  value: /etc/etcd/client.crt
+                - name: ETCDCTL_KEY
+                  value: /etc/etcd/client.key
+                - name: EPS
+                  value: "https://192.168.1.166:2379 https://192.168.1.214:2379 https://192.168.1.162:2379"
+              command: ["/bin/bash", "-c"]
+              args:
+                - |
+                  set -u
+
+                  DAY=$(( $(date -u +%s) / 86400 ))
+                  if [ $(( DAY % 15 )) -ne 0 ]; then
+                    echo "skip: UTC epoch day $DAY is not a 15-day boundary"
+                    exit 0
+                  fi
+
+                  echo "== before =="
+                  for ep in $EPS; do
+                    etcdctl --endpoints="$ep" endpoint status -w table || true
+                  done
+
+                  MINREV=""
+                  MAXAPPLIED=0
+                  for ep in $EPS; do
+                    json=$(etcdctl --endpoints="$ep" endpoint status -w json 2>/dev/null) || continue
+                    rev=$(printf '%s' "$json" | sed -n 's/.*"revision":\([0-9]*\).*/\1/p' | head -1)
+                    app=$(printf '%s' "$json" | sed -n 's/.*"raftAppliedIndex":\([0-9]*\).*/\1/p' | head -1)
+                    echo "member $ep revision=${rev:-?} raftAppliedIndex=${app:-?}"
+                    if [ -n "$rev" ] && { [ -z "$MINREV" ] || [ "$rev" -lt "$MINREV" ]; }; then
+                      MINREV="$rev"
+                    fi
+                    if [ -n "$app" ] && [ "$app" -gt "$MAXAPPLIED" ]; then
+                      MAXAPPLIED="$app"
+                    fi
+                  done
+
+                  if [ -z "$MINREV" ]; then
+                    echo "FATAL: no member returned a revision; nothing attempted"
+                    exit 1
+                  fi
+
+                  echo "== compact to revision $MINREV =="
+                  etcdctl --endpoints="$(echo "$EPS" | awk '{print $1}')" compact "$MINREV" || echo "COMPACT-FAILED (continuing: defrag still reclaims free pages)"
+
+                  # Physical deletion of superseded keys runs in the background
+                  # after the compaction commit; give it a moment to drain.
+                  sleep 20
+
+                  echo "== defrag each member (sequential, one at a time) =="
+                  rc=0
+                  for ep in $EPS; do
+                    json=$(etcdctl --endpoints="$ep" endpoint status -w json 2>/dev/null) || { echo "SKIP $ep (unreachable)"; rc=1; continue; }
+                    app=$(printf '%s' "$json" | sed -n 's/.*"raftAppliedIndex":\([0-9]*\).*/\1/p' | head -1)
+                    if [ -n "$app" ] && [ "$app" -lt $(( MAXAPPLIED - 100000 )) ]; then
+                      echo "SKIP $ep (applied index $app lags leader $MAXAPPLIED; defrag would reclaim nothing)"
+                      rc=1
+                      continue
+                    fi
+                    echo "-- $ep"
+                    if ! etcdctl --endpoints="$ep" defrag; then
+                      echo "DEFRAG-FAILED $ep"
+                      rc=1
+                    fi
+                  done
+
+                  echo "== disarm NOSPACE =="
+                  for ep in $EPS; do
+                    etcdctl --endpoints="$ep" alarm list 2>/dev/null || true
+                    etcdctl --endpoints="$ep" alarm disarm 2>/dev/null || true
+                  done
+
+                  echo "== after =="
+                  for ep in $EPS; do
+                    etcdctl --endpoints="$ep" endpoint status -w table || true
+                  done
+                  etcdctl --endpoints="$(echo "$EPS" | awk '{print $1}')" alarm list || true
+                  exit $rc
+              resources:
+                requests: { cpu: 10m, memory: 32Mi }
+                limits:   { cpu: 200m, memory: 128Mi }
+              volumeMounts:
+                - name: creds
+                  mountPath: /etc/etcd
+                  readOnly: true
+          volumes:
+            - name: creds
+              secret:
+                secretName: etcd-defrag-creds
+                defaultMode: 0444

k8s/infra/cluster-maintenance/stale-job-cleanup.yaml

@@ -1,12 +1,12 @@
 # Cluster-wide cleanup of stale failed/completed Jobs and Pods.
-# Runs daily at 04:00 UTC. Deletes:
-#   - Failed Jobs older than 24h (any namespace)
-#   - Completed Jobs older than 72h with no owning CronJob
-#   - Orphan pods in Error/Failed/Evicted state older than 1h
+# Runs every 2 minutes. Deletes:
+#   - Failed Jobs older than 2m (any namespace)
+#   - Completed standalone Jobs older than 2m with no owning CronJob
+#   - Orphan pods in Error/Failed/Evicted/Completed state older than 2m
 #
 # CronJob-owned Jobs are managed by failedJobsHistoryLimit/successfulJobsHistoryLimit,
-# but standalone Jobs (helm hooks, one-off runs, longhorn maintenance) have no TTL
-# and linger forever.
+# but standalone Jobs (helm hooks, one-off runs, CI TaskRuns) have no TTL
+# and linger forever. Aggressive schedule keeps the cluster clean.
 
 apiVersion: v1
 kind: ServiceAccount
@@ -47,7 +47,7 @@ metadata:
   labels:
     app: stale-job-cleanup
 spec:
-  schedule: "0 4 * * *"
+  schedule: "*/2 * * * *"
   concurrencyPolicy: Forbid
   successfulJobsHistoryLimit: 3
   failedJobsHistoryLimit: 3
@@ -74,7 +74,9 @@ spec:
                   set -e
                   NOW=$(date +%s)
 
-                  echo "=== Cleaning failed Jobs older than 24h ==="
+                  TTL=120  # 2 minutes in seconds
+
+                  echo "=== Cleaning failed Jobs older than 2m ==="
                   kubectl get jobs --all-namespaces -o json | \
                     jq -r '.items[] |
                       select(.status.conditions[]?.type == "Failed") |
@@ -82,15 +84,15 @@ spec:
                       "\(.metadata.namespace) \(.metadata.name) \(.status.startTime // .status.completionTime // .metadata.creationTimestamp)"' | \
                   while read -r NS NAME TS; do
                     JOB_EPOCH=$(date -d "$TS" +%s 2>/dev/null || echo 0)
-                    AGE_H=$(( (NOW - JOB_EPOCH) / 3600 ))
-                    if [ "$AGE_H" -ge 24 ]; then
-                      echo "[delete] $NS/$NAME (failed ${AGE_H}h ago)"
+                    AGE=$(( NOW - JOB_EPOCH ))
+                    if [ "$AGE" -ge "$TTL" ]; then
+                      echo "[delete] $NS/$NAME (failed ${AGE}s ago)"
                       kubectl delete job "$NAME" -n "$NS" --cascade=foreground 2>/dev/null || true
                     fi
                   done
 
                   echo ""
-                  echo "=== Cleaning completed standalone Jobs older than 72h ==="
+                  echo "=== Cleaning completed standalone Jobs older than 2m ==="
                   kubectl get jobs --all-namespaces -o json | \
                     jq -r '.items[] |
                       select(.status.succeeded >= 1) |
@@ -98,20 +100,20 @@ spec:
                       "\(.metadata.namespace) \(.metadata.name) \(.status.completionTime // .metadata.creationTimestamp)"' | \
                   while read -r NS NAME TS; do
                     JOB_EPOCH=$(date -d "$TS" +%s 2>/dev/null || echo 0)
-                    AGE_H=$(( (NOW - JOB_EPOCH) / 3600 ))
-                    if [ "$AGE_H" -ge 72 ]; then
-                      echo "[delete] $NS/$NAME (completed ${AGE_H}h ago, no owner)"
+                    AGE=$(( NOW - JOB_EPOCH ))
+                    if [ "$AGE" -ge "$TTL" ]; then
+                      echo "[delete] $NS/$NAME (completed ${AGE}s ago, no owner)"
                       kubectl delete job "$NAME" -n "$NS" --cascade=foreground 2>/dev/null || true
                     fi
                   done
 
                   echo ""
-                  echo "=== Cleaning orphan Error/Failed/Evicted pods older than 1h ==="
-                  # Evicted pods show as Failed with reason Evicted
+                  echo "=== Cleaning orphan Error/Failed/Evicted/Completed pods older than 2m ==="
                   kubectl get pods --all-namespaces -o json | \
                     jq -r '.items[] |
                       select(
                         .status.phase == "Failed" or
+                        .status.phase == "Succeeded" or
                         (.status.reason // "") == "Evicted" or
                         (.status.containerStatuses // [] | any(.state.terminated.reason == "Error"))
                       ) |
@@ -119,9 +121,9 @@ spec:
                       "\(.metadata.namespace) \(.metadata.name) \(.metadata.creationTimestamp)"' | \
                   while read -r NS NAME TS; do
                     POD_EPOCH=$(date -d "$TS" +%s 2>/dev/null || echo 0)
-                    AGE_H=$(( (NOW - POD_EPOCH) / 3600 ))
-                    if [ "$AGE_H" -ge 1 ]; then
-                      echo "[delete] $NS/$NAME (error/evicted ${AGE_H}h ago)"
+                    AGE=$(( NOW - POD_EPOCH ))
+                    if [ "$AGE" -ge "$TTL" ]; then
+                      echo "[delete] $NS/$NAME (stale ${AGE}s ago)"
                       kubectl delete pod "$NAME" -n "$NS" --force 2>/dev/null || true
                     fi
                   done

k8s/infra/databases/kustomization.yaml

@@ -7,6 +7,6 @@ kind: Kustomization
 resources:
   - namespaces.yaml
   - authentik-db.yaml
+  - zitadel-db.yaml
   - temporal-db.yaml
-  - memory-db.yaml
   - paperless-db.yaml

k8s/infra/databases/zitadel-db.yaml

@@ -0,0 +1,42 @@
+# Dedicated CNPG Postgres for ZITADEL (GitOps, wave 2 — before the zitadel
+# chart at wave 3). Same shape as authentik-db.yaml: CNPG generates the secret
+# `zitadel-db-app` and the service `zitadel-db-rw` in ns iam, and
+# k8s/infra/iam/zitadel-values.yaml reads the DSN from that secret locally (no
+# cross-namespace secret copy).
+#
+# ZITADEL requires PostgreSQL 14+; the repo convention image is 16.2.
+apiVersion: postgresql.cnpg.io/v1
+kind: Cluster
+metadata:
+  name: zitadel-db
+  namespace: iam
+  annotations:
+    argocd.argoproj.io/sync-options: SkipDryRunOnMissingResource=true
+spec:
+  instances: 3
+  imageName: ghcr.io/cloudnative-pg/postgresql:16.2
+  bootstrap:
+    initdb:
+      database: zitadel
+      owner: app
+      encoding: UTF8
+      localeCollate: C
+      localeCType: C
+  enableSuperuserAccess: false
+  resources:
+    requests: { memory: "512Mi", cpu: "250m" }
+    limits: { memory: "2Gi", cpu: "1" }
+  storage:
+    size: 10Gi
+    storageClass: longhorn-cnpg
+  monitoring:
+    enablePodMonitor: true
+  affinity:
+    # preferred + tolerations: HA across nodes without deadlocking a partly-
+    # schedulable 3-CP (same as authentik-db and forgejo-db).
+    podAntiAffinityType: preferred
+    topologyKey: kubernetes.io/hostname
+    tolerations:
+      - key: node-role.kubernetes.io/control-plane
+        operator: Exists
+        effect: NoSchedule

k8s/infra/forgejo-runner/templates/cilium-apiserver-egress.yaml

@@ -0,0 +1,25 @@
+# CiliumNetworkPolicy for kube-apiserver access.
+#
+# Standard K8s NetworkPolicy ipBlock rules don't work for the API server
+# under Cilium — the except clause on 192.168.1.0/24 blocks the post-DNAT
+# destination even when a separate rule re-allows a /32 or subnet.
+#
+# Cilium's native `kube-apiserver` entity resolves this correctly: it
+# tracks the API server endpoints regardless of ClusterIP vs node-IP
+# routing, so the policy stays valid across node changes and NAT paths.
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: {{ .Release.Name }}-apiserver
+  namespace: {{ .Release.Namespace }}
+spec:
+  endpointSelector:
+    matchLabels:
+      app: {{ .Release.Name }}
+  egress:
+  - toEntities:
+    - kube-apiserver
+    toPorts:
+    - ports:
+      - port: "6443"
+        protocol: TCP

k8s/infra/iam/zitadel-values.yaml

@@ -0,0 +1,142 @@
+# k8s/infra/iam/zitadel-values.yaml
+# ZITADEL — Authentik replacement. Coexistence is deliberate: Authentik keeps
+# running, read-only, in the same `iam` namespace until the last consumer moves.
+# Migration plan: ~/workplace/homelab-doc/ZITADEL_MIGRATION.html (outside git).
+#
+# Chart: zitadel/zitadel 10.4.0, app v4.19.2. The plan cites v4.19.4; the chart
+# has not published it yet. Pin the chart, never `*`, until the v4.19.4 chart
+# exists — a silent app bump invalidates the verified masterkey/passwap facts.
+#
+# URL: https://zitadel.riotpiao.com. TLS terminates at ingress-nginx, which
+# serves the wildcard riotpiao-com-tls as its default-ssl-certificate, so
+# ExternalSecure=true and TLS.Enabled=false (no per-rule tls: block needed).
+#
+# Database: CNPG cluster zitadel-db (wave 2). The DSN comes from CNPG's
+# generated `zitadel-db-app` secret. When ZITADEL_DATABASE_POSTGRES_DSN is set,
+# ZITADEL ignores the discrete Database.Postgres.* fields, so neither a
+# password nor a host is written into this file.
+#
+# Masterkey: Secret `zitadel-masterkey` (k8s/argocd/secrets/
+# zitadel-masterkey.enc.yaml), key `masterkey`, exactly 32 bytes. It wraps the
+# rows in system.encryption_keys, which encrypt every client secret and private
+# key. Losing it makes those values unreadable: keep the offline sealed copy.
+#
+# Ingress uses the chart's own objects (controller: nginx adds the gRPC backend
+# annotation ZITADEL needs for its HTTP/2 API). Do not hand-write a second
+# Ingress for this host.
+
+zitadel:
+  configmapConfig:
+    ExternalSecure: true
+    ExternalDomain: zitadel.riotpiao.com
+    TLS:
+      Enabled: false
+
+  # Rendered into a Secret by the chart; read by pods and init jobs alike.
+  masterkeySecretName: zitadel-masterkey
+
+  resources:
+    requests: { memory: "512Mi", cpu: "250m" }
+    limits: { memory: "2Gi", cpu: "1" }
+
+  # FirstInstance defaults stay for the FIRST sync: the chart creates org
+  # `zitadel` plus the `iam-admin` machine user and its machine-key Secret.
+  # Terraform consumes that key to declare projects, roles, OIDC apps and the
+  # groups action.
+  #
+  # SECOND-SYNC HAZARD — read before enabling automated sync.
+  # The chart marks eight objects as `pre-install,pre-upgrade` hooks (two
+  # ServiceAccounts, two ConfigMaps, Role, RoleBinding, zitadel-init,
+  # zitadel-setup), and one cleanup Job as `post-delete`. ArgoCD maps the first
+  # eight to PreSync with `before-hook-creation`: it deletes and re-creates them
+  # on EVERY sync, not only on a chart change.
+  #   - zitadel-init  (`init zitadel`) — schema step
+  #   - zitadel-setup (`setup`)        — first instance + iam-admin machine key
+  # On an initialized instance the setup step can fail, which aborts the sync
+  # before the Deployment is applied. If it succeeds instead, its
+  # machinekeyWriter container re-applies the iam-admin key Secret that
+  # Terraform reads, which silently rotates a credential in use.
+  # After the first sync reports healthy:
+  #   1. set configmapConfig.FirstInstance.Skip: true here — permanently: the
+  #      setup steps are schema-only once the instance exists, and Skip alone
+  #      stops the machinekeyWriter rotation
+  #   2. set initJob.enabled: false below
+  #   3. commit, sync once, then enable automated+selfHeal on the Application
+  # For a later schema upgrade, re-enable initJob.enabled only — never set
+  # FirstInstance.Skip back to false.
+  # ArgoCD never prunes a hook Job, so a Job that failed before step 2 stays and
+  # keeps ZitadelSetupJobFailed firing until a human deletes it.
+
+# DSN mode (chart renders this through the zitadel.dbEnv helper). CNPG's `uri`
+# key is a postgresql:// URL, which ZITADEL accepts as a DSN.
+env:
+  - name: ZITADEL_DATABASE_POSTGRES_DSN
+    valueFrom:
+      secretKeyRef:
+        name: zitadel-db-app
+        key: uri
+
+# Bundled Bitnami Postgres is disabled: the CNPG cluster above is the system of
+# record. Enabling it would create a second, unmanaged database.
+postgresql:
+  enabled: false
+
+# CNPG already created the database, the `app` user and its grants, so the init
+# job runs only the ZITADEL-internal step. Running the full default command
+# would try to create a database and a superuser it does not own.
+initJob:
+  command: "zitadel"
+  activeDeadlineSeconds: 600
+
+# The setup job runs the full first-instance creation: schema migrations, the
+# system org, the iam-admin machine key, and 13 projection replays. The chart
+# default killed it at ~5.5 minutes on 2026-10-25 while it was still replaying
+# projections.projects4, which failed the whole sync. 20 minutes leaves room for
+# a cold database without masking a genuine hang.
+setupJob:
+  activeDeadlineSeconds: 1200
+
+# Two API replicas: the read path survives one node drain, and both share the
+# same masterkey and database. The login UI stays at one replica — a session
+# cookie is not shared, so a second pod buys nothing.
+replicaCount: 2
+revisionHistoryLimit: 3
+
+ingress:
+  enabled: true
+  className: nginx
+  controller: nginx
+
+login:
+  enabled: true
+  replicaCount: 1
+  ingress:
+    enabled: true
+    className: nginx
+
+# Chart-owned ServiceMonitor. The cluster's Prometheus runs with
+# serviceMonitorSelectorNilUsesHelmValues=false, so the release label is not
+# required for discovery. Endpoint is /debug/metrics on port http2-server.
+metrics:
+  enabled: true
+  serviceMonitor:
+    enabled: true
+    scrapeInterval: 30s
+    scrapeTimeout: 10s
+
+# The 3-CP / 2-worker cluster mixes control-plane taints with worker capacity.
+# Without the toleration a rolling upgrade can leave both replicas Pending.
+tolerations:
+  - key: node-role.kubernetes.io/control-plane
+    operator: Exists
+    effect: NoSchedule
+
+affinity:
+  podAntiAffinity:
+    preferredDuringSchedulingIgnoredDuringExecution:
+      - weight: 100
+        podAffinityTerm:
+          topologyKey: kubernetes.io/hostname
+          labelSelector:
+            matchLabels:
+              app.kubernetes.io/name: zitadel

k8s/infra/local-path/kustomization.yaml

@@ -0,0 +1,7 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+# No commonLabels on purpose: this is a vendored third-party manifest and
+# kustomize would also rewrite the provisioner Deployment's selector, which
+# is immutable on re-apply.
+resources:
+  - local-path-storage.yaml

k8s/infra/local-path/local-path-storage.yaml

@@ -0,0 +1,200 @@
+# Vendored from https://github.com/rancher/local-path-provisioner
+#   deploy/local-path-storage.yaml @ v0.0.37 (release 2026-08-05)
+#
+# Local modifications (the only three; re-apply them on any re-vendor):
+#   1. the namespace carries pod-security.kubernetes.io/enforce=privileged, because the
+#      provisioner's helper Pods mount a hostPath and this cluster defaults to the
+#      baseline policy, which forbids that;
+#   2. config.json nodePathMap is /var/lib/local-path-provisioner — Talos mounts the root
+#      filesystem read-only, so upstream's /opt path cannot be created;
+#   3. the helper Pod's busybox image is pinned to a tag instead of a floating name.
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: local-path-storage
+  labels:
+    pod-security.kubernetes.io/enforce: privileged
+    pod-security.kubernetes.io/audit: privileged
+    pod-security.kubernetes.io/warn: privileged
+
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: local-path-provisioner-service-account
+  namespace: local-path-storage
+
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: local-path-provisioner-role
+  namespace: local-path-storage
+rules:
+  - apiGroups: [""]
+    resources: ["pods"]
+    verbs: ["get", "list", "watch", "create", "patch", "update", "delete"]
+
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: local-path-provisioner-role
+rules:
+  - apiGroups: [""]
+    resources: ["nodes", "persistentvolumeclaims", "configmaps", "pods", "pods/log"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: [""]
+    resources: ["persistentvolumes"]
+    verbs: ["get", "list", "watch", "create", "patch", "update", "delete"]
+  - apiGroups: [""]
+    resources: ["events"]
+    verbs: ["create", "patch"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["storageclasses"]
+    verbs: ["get", "list", "watch"]
+
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: local-path-provisioner-bind
+  namespace: local-path-storage
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: local-path-provisioner-role
+subjects:
+  - kind: ServiceAccount
+    name: local-path-provisioner-service-account
+    namespace: local-path-storage
+
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: local-path-provisioner-bind
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: local-path-provisioner-role
+subjects:
+  - kind: ServiceAccount
+    name: local-path-provisioner-service-account
+    namespace: local-path-storage
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: local-path-provisioner
+  namespace: local-path-storage
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: local-path-provisioner
+  template:
+    metadata:
+      labels:
+        app: local-path-provisioner
+    spec:
+      serviceAccountName: local-path-provisioner-service-account
+      containers:
+        - name: local-path-provisioner
+          image: docker.io/rancher/local-path-provisioner:v0.0.37
+          imagePullPolicy: IfNotPresent
+          command:
+            - local-path-provisioner
+            - --debug
+            - start
+            - --config
+            - /etc/config/config.json
+          ports:
+            - name: health
+              containerPort: 8080
+              protocol: TCP
+          startupProbe:
+            httpGet:
+              path: /health
+              port: health
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            failureThreshold: 12
+          livenessProbe:
+            httpGet:
+              path: /health
+              port: health
+            initialDelaySeconds: 10
+            periodSeconds: 10
+          readinessProbe:
+            httpGet:
+              path: /ready
+              port: health
+            initialDelaySeconds: 5
+            periodSeconds: 5
+          volumeMounts:
+            - name: config-volume
+              mountPath: /etc/config/
+          env:
+            - name: POD_NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+            - name: CONFIG_MOUNT_PATH
+              value: /etc/config/
+            - name: HEALTH_PORT
+              value: "8080"
+      volumes:
+        - name: config-volume
+          configMap:
+            name: local-path-config
+
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: local-path
+provisioner: rancher.io/local-path
+volumeBindingMode: WaitForFirstConsumer
+reclaimPolicy: Delete
+
+---
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: local-path-config
+  namespace: local-path-storage
+data:
+  config.json: |-
+    {
+            "nodePathMap":[
+            {
+                    "node":"DEFAULT_PATH_FOR_NON_LISTED_NODES",
+                    "paths":["/var/lib/local-path-provisioner"]
+            }
+            ]
+    }
+  setup: |-
+    #!/bin/sh
+    set -eu
+    mkdir -m 0777 -p "$VOL_DIR"
+  teardown: |-
+    #!/bin/sh
+    set -eu
+    rm -rf "$VOL_DIR"
+  helperPod.yaml: |-
+    apiVersion: v1
+    kind: Pod
+    metadata:
+      name: helper-pod
+    spec:
+      priorityClassName: system-node-critical
+      tolerations:
+        - key: node.kubernetes.io/disk-pressure
+          operator: Exists
+          effect: NoSchedule
+      containers:
+      - name: helper-pod
+        image: docker.io/library/busybox:1.36
+        imagePullPolicy: IfNotPresent

k8s/infra/logging/grafana-values.yaml

@@ -73,7 +73,7 @@ grafana.ini:
   auth.generic_oauth:
     enabled: true
     name: Authentik
-    allow_sign_up: true
+    allow_sign_up: true  # Allow sync to create/update users from OAuth claims
     client_id: grafana
     scopes: openid email profile groups
     auth_url: https://authentik.riotpiao.com/application/o/authorize/
@@ -84,13 +84,13 @@ grafana.ini:
     # Authentik doesn't serve — request 404s with "Error getting email address"
     # and the whole OAuth login fails.
     email_attribute_path: email
-    login_attribute_path: preferred_username
+    login_attribute_path: preferred_username  # Use preferred_username — OpenID standard claim, always present
     name_attribute_path: name
     role_attribute_path: "preferred_username == 'akadmin' && 'GrafanaAdmin' || contains(groups[*], 'homelab-admins') && 'Admin' || 'Viewer'"
     allow_assign_grafana_admin: true
     use_pkce: false
     use_refresh_token: false
-    skip_org_role_sync: false
+    skip_org_role_sync: false  # Sync org roles from OAuth groups
     tls_skip_verify_insecure: true   # Authentik uses self-signed cert; verify in prod
 
 # GF_AUTH_GENERIC_OAUTH_CLIENT_SECRET is injected from the grafana-oidc K8s

k8s/infra/longhorn/longhorn-add-disks-job.yaml

@@ -41,13 +41,24 @@ spec:
           # - /var/lib/longhorn-disk1 (sdb1, 600GB)
           # - /var/lib/longhorn-disk2 (sdc1, 500GB)
           # - /var/lib/longhorn-disk3 (sdd1, 160GB)
-          # - /var/lib/longhorn-disk4 (sde1, 2TB)
+          #
+          # /var/lib/longhorn-disk4 (sde1, the 2TB PERC virtual disk) was RETIRED
+          # on 2026-10-12 and must not be re-added. The device returned SCSI I/O
+          # errors at ~7,000/minute, the XFS filesystem on it hung, and every
+          # process that touched it blocked in unkillable D state. Those unkillable
+          # processes held Longhorn's per-node rebuild slots forever, so no new
+          # replica could start on talos-cp-2 and every new volume there failed to
+          # attach. It is removed from the Terraform disk list too, so a re-render
+          # does not put it back.
           
           echo "Checking talos-cp-2..."
           CURRENT_DISKS=$(kubectl -n longhorn-system get nodes.longhorn.io talos-cp-2 -o json | jq -r '.spec.disks | keys | length')
           echo "  Current disk count: $CURRENT_DISKS"
           
-          if [ "$CURRENT_DISKS" -lt 5 ]; then
+          # 4 = default-disk-080400000000 + disk1..disk3. It was 5 while disk4
+          # existed; leaving the old threshold would re-apply the patch on every
+          # run once disk4 is gone.
+          if [ "$CURRENT_DISKS" -lt 4 ]; then
             echo "  Adding extra disks to talos-cp-2..."
             kubectl -n longhorn-system patch nodes.longhorn.io talos-cp-2 --type merge -p '{
               "spec": {
@@ -75,14 +86,6 @@ spec:
                     "path": "/var/lib/longhorn-disk3",
                     "storageReserved": 5368709120,
                     "tags": []
-                  },
-                  "disk4": {
-                    "allowScheduling": true,
-                    "diskType": "filesystem",
-                    "evictionRequested": false,
-                    "path": "/var/lib/longhorn-disk4",
-                    "storageReserved": 21474836480,
-                    "tags": []
                   }
                 }
               }
@@ -117,6 +120,22 @@ spec:
             echo "  ✓ talos-cp-3 already has $CP3_DISKS disks configured"
           fi
 
+          # worker-1: enable scheduling, reserve 400Gi for LLM weights,
+          # clear eviction flag that was set when scheduling was disabled.
+          echo "Configuring worker-1 disk..."
+          kubectl -n longhorn-system patch nodes.longhorn.io worker-1 --type merge -p '{
+            "spec": {
+              "disks": {
+                "default-disk-1030400000000": {
+                  "allowScheduling": true,
+                  "evictionRequested": false,
+                  "storageReserved": 429496729600
+                }
+              }
+            }
+          }'
+          echo "  ✓ worker-1 disk configured (400Gi reserved)"
+
           echo
           echo "Waiting for disks to be ready..."
           sleep 10

k8s/infra/longhorn/longhorn-nodes.yaml

@@ -1,33 +1,25 @@
-# Longhorn Node CRDs for cp-2 and cp-3.
-# These nodes have the control-plane taint, so Longhorn doesn't auto-discover them.
-# Explicit Node CRDs + the taint-toleration setting enable storage across all 3 nodes.
+# Longhorn Node CRDs — enable scheduling on nodes that need explicit opt-in.
 #
-# `spec.disks` is deliberately absent. Longhorn owns disk identity: it names the
-# entry itself (`default-disk-080400000000`, not `default-disk`) and writes
-# `storageReserved`, `diskType` and `evictionRequested` into it. Declaring a
-# `default-disk` key here never matched the live one, so the Application sat
-# OutOfSync and selfHeal kept trying to add a SECOND disk record pointing at the
-# same /var/lib/longhorn path — which is worse than the drift it was fixing.
+# Control-plane nodes (cp-2, cp-3) have taints so Longhorn doesn't auto-discover.
+# worker-1 was manually disabled; re-enabled 2026-09-28 to relieve degraded-volume
+# pressure (400Gi reserved for LLM weights via the add-disks-job, ~300Gi available
+# for general replica scheduling).
 #
-# What these objects are actually for is `allowScheduling: true` on tainted
-# control-plane nodes. That is all they need to declare.
+# `spec.disks` deliberately absent — Longhorn owns disk identity and writes
+# storageReserved/diskType/evictionRequested itself. Disk-level config lives in
+# longhorn-add-disks-job.yaml. These objects only set `allowScheduling: true`.
 ---
 apiVersion: longhorn.io/v1beta2
 kind: Node
-metadata:
-  name: talos-cp-2
-  namespace: longhorn-system
-spec:
-  name: talos-cp-2
-  allowScheduling: true
-  tags: []
+metadata: { name: talos-cp-2, namespace: longhorn-system }
+spec: { name: talos-cp-2, allowScheduling: true, tags: [] }
 ---
 apiVersion: longhorn.io/v1beta2
 kind: Node
-metadata:
-  name: talos-cp-3
-  namespace: longhorn-system
-spec:
-  name: talos-cp-3
-  allowScheduling: true
-  tags: []
+metadata: { name: talos-cp-3, namespace: longhorn-system }
+spec: { name: talos-cp-3, allowScheduling: true, tags: [] }
+---
+apiVersion: longhorn.io/v1beta2
+kind: Node
+metadata: { name: worker-1, namespace: longhorn-system }
+spec: { name: worker-1, allowScheduling: true, tags: [] }

k8s/infra/minio/minio-provision-paperless-job.yaml

@@ -52,14 +52,14 @@ spec:
       restartPolicy: Never
       initContainers:
         - name: kubectl-copy
-          image: bitnami/kubectl:latest
+          image: bitnami/kubectl:latest@sha256:f7f9e4f64d9e114650c115a4ac6fd383394b3d494061a8f17b1a0f6c8d55bc25
           command: ["sh", "-c", "cp $(which kubectl) /shared/kubectl"]
           volumeMounts:
             - name: shared
               mountPath: /shared
       containers:
         - name: provision
-          image: quay.io/minio/mc:latest
+          image: docker.io/bitnamilegacy/minio-client:2025.7.21-debian-12-r3@sha256:73bd39f7899a0cef12b8dd5df13aa93a3ed1aaa44236542442e9ac76819ac158
           volumeMounts:
             - name: shared
               mountPath: /shared

k8s/infra/minio/minio-tenant.yaml

@@ -11,7 +11,15 @@ metadata:
     prometheus.io/port: "9000"
     prometheus.io/scrape: "true"
 spec:
-  image: minio/minio:RELEASE.2025-07-23T15-54-02Z
+  # Was minio/minio:RELEASE.2025-07-23T15-54-02Z — that Docker Hub repository no longer
+  # exists (404 for every tag), so the tenant sat in ImagePullBackOff and Vault's S3
+  # backend could not resolve minio-cluster-hl. Official images now need registry auth
+  # (quay.io/minio/minio returns 401), so this pins a public mirror of the same upstream
+  # release; swap it for the official image once MinIO registry credentials exist.
+  # The digest freezes those bytes, so a retag or a deletion on the mirror cannot break
+  # the pull again. The same digest already sits in the containerd cache on talos-cp-1,
+  # so the first start needs no registry access.
+  image: docker.io/coollabsio/minio:RELEASE.2025-10-15T17-29-55Z@sha256:69b55a1c1c5dc285ce04db96689f5b2102317fc77a50680a1874ca6efd1c87f9
 
   # Disable operator auto-TLS: MinIO serves plain HTTP internally on 9000.
   # External TLS is terminated at nginx ingress (wildcard riotpiao-com-tls cert).
@@ -112,10 +120,16 @@ spec:
           name: minio-oidc
           key: MINIO_IDENTITY_OPENID_CLIENT_SECRET
     - name: MINIO_IDENTITY_OPENID_CLAIM_NAME
-      value: "policy"
+      value: "groups"
+    - name: MINIO_IDENTITY_OPENID_CLAIM_PREFIX
+      value: ""
     - name: MINIO_IDENTITY_OPENID_REDIRECT_URI
       value: "https://minio.riotpiao.com/oauth_callback"
     - name: MINIO_IDENTITY_OPENID_DISPLAY_NAME
       value: "Authentik"
     - name: MINIO_IDENTITY_OPENID_SCOPES
-      value: "openid,profile,email,minio"
+      value: "openid,profile,email,groups"
+    - name: MINIO_BROWSER_LOGIN_ANIMATION
+      value: "off"
+    - name: MINIO_BROWSER_REDIRECT_URL
+      value: "https://minio.riotpiao.com"

k8s/infra/monitoring/alerts/api-gateway-alerts.yaml

@@ -158,3 +158,66 @@ spec:
             severity: warning
           annotations:
             summary: "Gateway pod {{ $labels.pod }} memory at {{ $value | humanizePercentage }} of limit"
+
+    - name: api-gateway.admission
+      # The admission gate fails OPEN when its view of the engine gauges goes
+      # stale, so a broken observer degrades silently to the pre-#64 behaviour
+      # of admitting everything. These two series are the only detection —
+      # the gate has no automated tests.
+      rules:
+        # The gate fails OPEN when it cannot read the engine, so "no data" must
+        # alert: otherwise a missing emitter, a renamed metric, or a broken
+        # scrape is indistinguishable from a healthy observer. Both expressions
+        # therefore OR in an absent() guard on the metric itself.
+        - alert: APIGatewayObserverDegraded
+          expr: observer_degraded == 1 or absent(observer_degraded)
+          for: 2m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Gateway admission observer degraded or not reporting — gate is failing open"
+            description: "observer_degraded is either 1 or absent. Absent means the emitter is missing, renamed, or unscraped, which is the fail-open case."
+
+        # Engine gauges went stale, or are not being reported at all
+        - alert: GatewayEngineStateStale
+          expr: increase(engine_state_stale_total[15m]) > 0 or absent(engine_state_stale_total)
+          for: 2m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Gateway engine state stale or not reporting — admission may be based on stale gauges"
+            description: "Non-zero means the observer lost the engine; absent means the metric is not being emitted at all."
+
+        # The acceptance metric for reasoning.yaml's prefill change. Preemption
+        # of a 65k prompt costs a full re-prefill (~250s at the measured
+        # 262 tok/s), so any sustained rate is a regression, not noise.
+        - alert: LLMPreemptions
+          # Guarded absent() is deliberately NOT used bare here: the engine
+          # restarts (strategy Recreate) and the series legitimately vanishes
+          # for the length of a boot, so a bare absent() would false-fire on
+          # every rollout. It only fires when the metric is missing WHILE the
+          # predictor is up, which is the real "renamed or unscraped" case.
+          expr: |
+            increase(vllm:num_preemptions_total[15m]) > 0
+            or (absent(vllm:num_preemptions_total) and on() up{job="reasoning-predictor"} == 1)
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "vLLM preempting requests ({{ $value }} in 15m) — KV cache over-committed, re-prefill cost is severe"
+            description: "Any sustained preemption rate is a regression for the reasoning prefill change: evicting a 65k-token prompt costs a full re-prefill (~250s at the measured 262 tok/s). Orchestrator verified `up{job=\"reasoning-predictor\"}` is the live job label — if that label is wrong the guard is inert but harmless."
+
+        # This change trades single-request latency for fairness: capping a long
+        # prompt at 2048 tokens/step means it takes more steps to finish, so a
+        # lone large prompt can now be slower even while preemptions stay 0.
+        # Without this alert the change has no way to show a regression.
+        - alert: LLMPrefillStarvation
+          expr: |
+            (sum(vllm:num_requests_waiting) > 0 and max(vllm:kv_cache_usage_perc) < 0.5)
+            or histogram_quantile(0.95, sum(rate(vllm:time_to_first_token_seconds_bucket[10m])) by (le)) > 60
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "reasoning queueing or TTFT p95 above 60s while KV is under 50% — scheduling, not capacity"
+            description: "Queue depth with spare KV means requests are being starved rather than blocked on memory; a high TTFT p95 with headroom points at the same. Both series verified live (vllm:num_requests_waiting and vllm:time_to_first_token_seconds exist)."

k8s/infra/monitoring/alerts/cag-kv-cache-rules.yaml

@@ -0,0 +1,76 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: cag-kv-cache-rules
+  namespace: monitoring
+  labels:
+    release: prometheus
+spec:
+  groups:
+    # Recording rules: derive vLLM prefix cache hit rate from raw counters.
+    # Metric names verified against live vLLM 0.11.0 scrape (2026-09-29).
+    # The previous names (vllm:cache_query_hit_total / vllm:cache_query_miss_total)
+    # do not exist in this version — vLLM exposes prefix_cache_hits_total and
+    # prefix_cache_queries_total — so this rule produced no data and
+    # VLLMPrefixCacheHitRateLow could never fire.
+    - name: vllm.recording
+      rules:
+        - record: vllm:prefix_cache_hit_rate
+          expr: |
+            rate(vllm:prefix_cache_hits_total[5m])
+            /
+            clamp_min(
+              rate(vllm:prefix_cache_queries_total[5m]),
+              0.001
+            )
+          labels:
+            job: "reasoning-predictor"
+
+    # Alert rules: CAG pipeline health
+    - name: cag.alerts
+      rules:
+        # KV warmup consistently failing — cache never gets warm
+        - alert: KVWarmupFailureHigh
+          expr: |
+            rate(memory_kv_cache_warmup_error_total[5m]) > 0.01
+          for: 5m
+          labels:
+            severity: warning
+            team: poimen
+          annotations:
+            summary: "KV warmup errors elevated ({{ $value | humanize }}/s)"
+            description: |
+              The KV cache warmer is failing to reach vLLM at a rate > 0.01/s
+              for 5 consecutive minutes. The prefix KV cache is not being warmed;
+              agents will see full prefill latency on every call.
+              Check reasoning-predictor health and poimen-memory NetworkPolicy.
+
+        # Warmup misses: vLLM reachable but not caching
+        - alert: KVWarmupMissHigh
+          expr: |
+            rate(memory_kv_cache_warmup_miss_total[5m]) > 0.01
+          for: 5m
+          labels:
+            severity: warning
+            team: poimen
+          annotations:
+            summary: "KV warmup cache misses elevated ({{ $value | humanize }}/s)"
+            description: |
+              vLLM is reachable but cached_tokens=0 on warmup responses.
+              Possible causes: prefix caching disabled in vLLM, max-num-seqs
+              saturated during warmup, or context format changed.
+
+        # Prefix cache hit rate low after warmup should be established
+        - alert: VLLMPrefixCacheHitRateLow
+          expr: |
+            vllm:prefix_cache_hit_rate < 0.70
+          for: 10m
+          labels:
+            severity: warning
+            team: poimen
+          annotations:
+            summary: "vLLM prefix cache hit rate low ({{ $value | humanizePercentage }})"
+            description: |
+              vLLM prefix cache hit rate below 70% for 10 minutes.
+              Expected >= 85% in steady state with CAG warming active.
+              Check KVWarmupFailureHigh / KVWarmupMissHigh alerts for root cause.

k8s/infra/monitoring/alerts/cluster-alerts.yaml

@@ -27,6 +27,24 @@ spec:
           annotations:
             summary: "{{ $value }} pod(s) stuck in Pending state for >10m"
 
+        # ImagePullBackOff on a vendor-deleted image produced no alert for 13 days
+        - alert: PodImagePullFailure
+          expr: sum(kube_pod_container_status_waiting_reason{reason=~"ImagePullBackOff|ErrImagePull"}) by (namespace, pod) > 0
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            summary: "{{ $labels.namespace }}/{{ $labels.pod }} cannot pull its image"
+
+        # Pod not ready
+        - alert: PodNotReady
+          expr: sum(kube_pod_status_ready{condition="false"}) by (namespace, pod) > 0
+          for: 15m
+          labels:
+            severity: warning
+          annotations:
+            summary: "{{ $labels.namespace }}/{{ $labels.pod }} is not ready"
+
         # CrashLoopBackOff
         - alert: PodCrashLooping
           expr: sum(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff"}) by (namespace, pod) > 0

k8s/infra/monitoring/alerts/svc-zitadel-rules.yaml

@@ -0,0 +1,68 @@
+# ZITADEL alert parity with the Authentik rules it will replace.
+#
+# Only two signals are ported at this point. The metrics endpoint
+# (/debug/metrics, scraped by the chart's own ServiceMonitor in ns iam) exposes
+# no request or error counters that this cluster has verified, so no error-rate
+# rule is written here. Writing one against a guessed series name would produce
+# a permanently-firing or permanently-silent alert — both worse than none.
+# AuthentikOutpostDown is deliberately not ported: it monitors an outpost that
+# carries zero providers and is deleted with the migration, not migrated.
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: zitadel-rules
+  namespace: iam
+spec:
+  groups:
+    - name: zitadel.rules
+      interval: 30s
+      rules:
+        - alert: ZitadelDown
+          # absent() is required: equality alone cannot fire when the series is
+          # gone (ServiceMonitor deleted, Service selector changed, pods scaled
+          # to zero). Those are exactly the outages a target-down rule exists for.
+          expr: absent(up{job="zitadel"}) or up{job="zitadel"} == 0
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            summary: "ZITADEL API target is down"
+            description: "Prometheus cannot scrape the ZITADEL API for 10 minutes. Token issuance and every OIDC login depend on it. Check the zitadel pods and the zitadel-db cluster in namespace iam. Value: {{ $value }}"
+
+        - alert: ZitadelLoginUIDown
+          expr: absent(kube_deployment_status_replicas_available{namespace="iam",deployment="zitadel-login"}) or kube_deployment_status_replicas_available{namespace="iam",deployment="zitadel-login"} == 0
+          for: 10m
+          labels:
+            severity: warning
+          annotations:
+            summary: "ZITADEL login UI has no available replica"
+            description: "The login UI serves /ui/v2/login. With zero available replicas a browser login completes at the IdP but cannot render. Value: {{ $value }}"
+
+        - alert: ZitadelRestarting
+          # pod!~"zitadel-db-.*" matters: the CNPG database pods share the
+          # `zitadel` name prefix, and a database restart must not page as an
+          # IdP crash loop.
+          expr: absent(kube_pod_container_status_restarts_total{namespace="iam",pod=~"zitadel.*",pod!~"zitadel-db-.*"}) or increase(kube_pod_container_status_restarts_total{namespace="iam",pod=~"zitadel.*",pod!~"zitadel-db-.*"}[1h]) > 3
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "ZITADEL pod restarts more than 3 times per hour"
+            description: "A crash loop on the IdP is a cluster-wide login outage. Check the pod logs and the masterkey/database secret references. Value: {{ $value }}"
+
+        # The chart's zitadel-init and zitadel-setup Jobs are PreSync hooks with
+        # restartPolicy: Never, so their restart counter stays 0. Without this
+        # rule a failed schema init or first-instance setup reaches nobody but
+        # the person who runs `kubectl -n iam get job`.
+        # No absent() guard here on purpose: the chart ships only
+        # `before-hook-creation`, so a successful hook Job is replaced at the
+        # next PreSync. Once the jobs are retired, absent() would fire on a
+        # healthy cluster.
+        - alert: ZitadelSetupJobFailed
+          expr: kube_job_status_failed{namespace="iam",job_name=~"zitadel-(init|setup).*"} > 0
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "ZITADEL init/setup job failed"
+            description: "A PreSync job failed, so ArgoCD aborted the sync before the Deployment was applied. Read the job pod logs, then delete the Job object to let the next sync retry. Value: {{ $value }}"

k8s/infra/monitoring/dashboards/generate-dashboards.py

@@ -26,20 +26,23 @@ def stat_panel(id, title, expr, x, y, w=4, h=4, unit="short", mappings=None, thr
     return p
 
 
-def ts_panel(id, title, exprs, x, y, w=8, h=8, unit="short"):
+def ts_panel(id, title, exprs, x, y, w=8, h=8, unit="short", description=None):
     targets = []
     for e in exprs:
         if isinstance(e, tuple):
             targets.append({"expr": e[0], "legendFormat": e[1]})
         else:
             targets.append({"expr": e, "legendFormat": "{{pod}}"})
-    return {
+    p = {
         "id": id, "title": title, "type": "timeseries",
         "gridPos": {"h": h, "w": w, "x": x, "y": y},
         "datasource": DS_PROM,
         "fieldConfig": {"defaults": {"unit": unit}},
         "targets": targets,
     }
+    if description:
+        p["description"] = description
+    return p
 
 
 def table_panel(id, title, expr, x, y, w=12, h=8):
@@ -265,6 +268,237 @@ def build_api_gateway():
     }
 
 
+# ============================================================================
+# Dashboard 4: LLM Observability (vLLM / TEI engines + gateway)
+# ============================================================================
+#
+# Two independent metric sources, deliberately both shown:
+#
+#   vLLM + TEI (llm-serving)  — engine-truth, but only for the three engines
+#                               that expose /metrics. Ollama (ornith:35b,
+#                               qwen2.5:3b-instruct) exposes nothing at all.
+#   api-gateway (/metrics)    — covers EVERY model including the two Ollama
+#                               ones, derived from the SSE byte stream: TTFT is
+#                               request-start to first byte, ITL is the gap
+#                               between SSE writes carrying "data: ", so it
+#                               counts SSE chunks rather than true tokens.
+#                               vLLM's own histograms remain authoritative for
+#                               `reasoning`.
+#
+# These three series ARE live as of 2026-09-29 — 3 series each, one per replica,
+# verified against the running gateway and Prometheus:
+#   llm_ttft_seconds, llm_itl_seconds, llm_tokens_total
+#
+# History, recorded so nobody re-derives it the hard way: on 2026-09-29 these
+# recorded nothing at all. internal/proxy/llm_metrics.go declared a capture
+# wrapper that was never constructed, so the exporter emitted HELP-only stubs.
+# homelab-frontend#63 fixed exactly that — the wrapper is now
+# ResponseWriterWrapper, constructed by NewResponseWriterWrapper
+# (internal/proxy/llm_metrics.go:38) and installed on the streaming proxy path.
+# The "dead code" note that used to live in this header is superseded.
+#
+# Panels backed by queue_full_requests_total, warmup_requests_delayed_total and
+# vllm_prefix_cache_hit_tokens_total also work (3 series, one per replica).
+#
+#
+# All metric names below were verified against a live scrape, not assumed:
+#   vLLM 0.11.0 exposes prefix_cache_hits_total / prefix_cache_queries_total,
+#   NOT cache_query_hit_total / cache_query_miss_total.
+
+def build_llm_observability():
+    def hq(metric, q, by="le"):
+        return (
+            f"histogram_quantile({q}, sum(rate({metric}_bucket[5m])) by ({by}, model_name))",
+            f"p{int(q * 100)}",
+        )
+
+    def hq_gw(metric, q):
+        return (
+            f"histogram_quantile({q}, sum(rate({metric}_bucket[5m])) by (le, model))",
+            f"p{int(q * 100)} · {{{{model}}}}",
+        )
+
+    def avg_of(metric):
+        # mean = rate(_sum) / rate(_count) — valid for cumulative histograms
+        return f"rate({metric}_sum[5m]) / clamp_min(rate({metric}_count[5m]), 0.001)"
+
+    panels = []
+
+    # ── TTFT ────────────────────────────────────────────────────────────────
+    panels.append(row(100, "Latency — Time To First Token", 0, [
+        stat_panel(101, "TTFT p95 (gateway)",
+                   "histogram_quantile(0.95, sum(rate(llm_ttft_seconds_bucket[5m])) by (le))",
+                   0, 1, w=4, h=4, unit="s"),
+        stat_panel(102, "TTFT p95 (vLLM)",
+                   "histogram_quantile(0.95, sum(rate(vllm:time_to_first_token_seconds_bucket[5m])) by (le))",
+                   4, 1, w=4, h=4, unit="s"),
+        stat_panel(103, "KV cache in use",
+                   "max(vllm:kv_cache_usage_perc)",
+                   8, 1, w=4, h=4, unit="percentunit"),
+        stat_panel(104, "Requests running",
+                   "sum(vllm:num_requests_running)",
+                   12, 1, w=4, h=4, unit="short"),
+        stat_panel(105, "Requests waiting",
+                   "sum(vllm:num_requests_waiting)",
+                   16, 1, w=4, h=4, unit="short"),
+        stat_panel(106, "Preemptions (5m)",
+                   "increase(vllm:num_preemptions_total[5m])",
+                   20, 1, w=4, h=4, unit="short"),
+        ts_panel(110, "TTFT percentile by model (gateway)",
+                 [hq_gw("llm_ttft_seconds", 0.50),
+                  hq_gw("llm_ttft_seconds", 0.95),
+                  hq_gw("llm_ttft_seconds", 0.99)],
+                 0, 2, w=12, h=8, unit="s"),
+        ts_panel(111, "TTFT percentile — vLLM reasoning",
+                 [hq("vllm:time_to_first_token_seconds", 0.50),
+                  hq("vllm:time_to_first_token_seconds", 0.95),
+                  hq("vllm:time_to_first_token_seconds", 0.99)],
+                 12, 2, w=12, h=8, unit="s"),
+        ts_panel(112, "Prefill vs decode (mean)",
+                 [(avg_of("vllm:request_prefill_time_seconds"), "prefill"),
+                  (avg_of("vllm:request_decode_time_seconds"), "decode")],
+                 0, 3, w=12, h=8, unit="s"),
+        ts_panel(113, "Queue wait before scheduling (mean)",
+                 [(avg_of("vllm:request_queue_time_seconds"), "queue")],
+                 12, 3, w=12, h=8, unit="s"),
+    ]))
+
+    # ── Inter-token latency ─────────────────────────────────────────────────
+    panels.append(row(120, "Latency — Inter-Token", 4, [
+        ts_panel(121, "Inter-token latency by model (gateway)",
+                 [hq_gw("llm_itl_seconds", 0.50),
+                  hq_gw("llm_itl_seconds", 0.95),
+                  hq_gw("llm_itl_seconds", 0.99)],
+                 0, 5, w=12, h=8, unit="s"),
+        ts_panel(122, "Inter-token latency — vLLM reasoning",
+                 [hq("vllm:inter_token_latency_seconds", 0.50),
+                  hq("vllm:inter_token_latency_seconds", 0.95),
+                  hq("vllm:inter_token_latency_seconds", 0.99)],
+                 12, 5, w=12, h=8, unit="s"),
+        ts_panel(123, "Decode throughput (tokens/s per request)",
+                 [(f"1 / clamp_min({avg_of('vllm:time_per_output_token_seconds')}, 0.0001)", "tok/s")],
+                 0, 6, w=12, h=8, unit="short"),
+        ts_panel(124, "End-to-end request latency p50/p95/p99",
+                 [hq("vllm:e2e_request_latency_seconds", 0.50),
+                  hq("vllm:e2e_request_latency_seconds", 0.95),
+                  hq("vllm:e2e_request_latency_seconds", 0.99)],
+                 12, 6, w=12, h=8, unit="s"),
+    ]))
+
+    # ── Batching / scheduling ───────────────────────────────────────────────
+    panels.append(row(130, "Batching & Scheduling", 7, [
+        ts_panel(131, "vLLM running vs waiting requests (batch depth)",
+                 [("sum(vllm:num_requests_running)", "running (in batch)"),
+                  ("sum(vllm:num_requests_waiting)", "waiting (queued)")],
+                 0, 8, w=12, h=8, unit="short"),
+        ts_panel(132, "Preemption rate (KV cache eviction pressure)",
+                 [("rate(vllm:num_preemptions_total[5m])", "preemptions/s")],
+                 12, 8, w=12, h=8, unit="short"),
+        ts_panel(133, "TEI batch size (embeddings / reranker)",
+                 [("avg(te_batch_next_size_sum / clamp_min(te_batch_next_size_count, 1)) by (app)",
+                   "{{app}}")],
+                 0, 9, w=12, h=8, unit="short"),
+        ts_panel(134, "TEI queue depth",
+                 [("max(te_queue_size) by (app)", "{{app}}")],
+                 12, 9, w=12, h=8, unit="short"),
+    ]))
+
+    # ── KV cache ────────────────────────────────────────────────────────────
+    panels.append(row(140, "KV Cache", 10, [
+        ts_panel(141, "KV cache utilisation (GPU memory pressure)",
+                 [("max(vllm:kv_cache_usage_perc) by (model_name)", "{{model_name}}")],
+                 0, 11, w=12, h=8, unit="percentunit"),
+        ts_panel(142, "Prefix cache hit rate (CAG effectiveness)",
+                 [("vllm:prefix_cache_hit_rate", "{{model_name}}")],
+                 12, 11, w=12, h=8, unit="percentunit"),
+        ts_panel(143, "Prefix cache hits vs queries",
+                 [("rate(vllm:prefix_cache_hits_total[5m])", "hits/s"),
+                  ("rate(vllm:prefix_cache_queries_total[5m])", "queries/s")],
+                 0, 12, w=12, h=8, unit="short"),
+        ts_panel(144, "Prefix cache hit tokens (gateway-observed, all models)",
+                 [("rate(vllm_prefix_cache_hit_tokens_total[5m])", "hit tokens/s")],
+                 12, 12, w=12, h=8, unit="short"),
+    ]))
+
+    # ── Throughput & health ─────────────────────────────────────────────────
+    panels.append(row(150, "Throughput & Health", 13, [
+        ts_panel(151, "Token throughput",
+                 [("sum(rate(vllm:prompt_tokens_total[5m]))", "prompt tok/s"),
+                  ("sum(rate(vllm:generation_tokens_total[5m]))", "generation tok/s"),
+                  ("rate(llm_tokens_total[5m])", "gateway SSE chunks/s (all models)")],
+                 0, 14, w=12, h=8, unit="short"),
+        ts_panel(152, "Successful requests/s",
+                 [("sum(rate(vllm:request_success_total[5m]))", "vLLM"),
+                  ("sum(rate(te_request_count[5m]))", "TEI")],
+                 12, 14, w=12, h=8, unit="short"),
+        ts_panel(153, "Backpressure — queue-full rejects",
+                 [("rate(queue_full_requests_total[5m])", "rejected/s")],
+                 0, 15, w=8, h=8, unit="short"),
+        ts_panel(154, "KV warmup requests delayed",
+                 [("rate(warmup_requests_delayed_total[5m])", "delayed/s")],
+                 8, 15, w=8, h=8, unit="short"),
+        ts_panel(155, "Embedding / rerank latency p95",
+                 [("histogram_quantile(0.95, sum(rate(te_embed_duration_bucket[5m])) by (le, app))",
+                   "{{app}} embed"),
+                  ("histogram_quantile(0.95, sum(rate(te_embed_queue_duration_bucket[5m])) by (le, app))",
+                   "{{app}} queue")],
+                 16, 15, w=8, h=8, unit="s"),
+    ]))
+
+    # ── Admission control ───────────────────────────────────────────────────
+    # These four panels read the gateway's admission gate, which is the
+    # companion change in homelab-frontend#64. That emitter is NOT deployed
+    # yet (verified against the live /metrics endpoint: 0 series matching
+    # ^(admission_|observer_|engine_state_)), so they render "No data" until
+    # #64 ships. That is expected, and each panel carries a description
+    # saying so — an unexplained blank panel would read as a broken
+    # dashboard, which is exactly the failure mode this row exists to catch.
+    panels.append(row(160, "Admission Control", 16, [
+        ts_panel(161, "Admission parked (5m)",
+                 [("increase(admission_parked_total[5m])", "parked")],
+                 0, 17, w=8, h=8, unit="short",
+                 description="Requests the gateway held back rather than admitting. "
+                             "Emitted by the admission gate (homelab-frontend#64); "
+                             "empty until that change is deployed."),
+        ts_panel(162, "Admission rejected by reason",
+                 [("sum by (reason) (increase(admission_rejected_total[5m]))", "{{reason}}")],
+                 8, 17, w=8, h=8, unit="short",
+                 description="Admission rejections split by the gate's own reason label. "
+                             "Emitted by homelab-frontend#64; empty until deployed."),
+        ts_panel(163, "Engine state stale",
+                 [("increase(engine_state_stale_total[5m])", "stale")],
+                 16, 17, w=8, h=8, unit="short",
+                 description="Times the gateway's view of the engine gauges went stale. "
+                             "The gate fails OPEN when this happens, so any non-zero rate "
+                             "means admission is silently degraded to admit-everything. "
+                             "Emitted by homelab-frontend#64; empty until deployed."),
+        ts_panel(164, "Gateway view vs engine truth",
+                 [("max(vllm_requests_running)", "gateway: running"),
+                  ("sum(vllm:num_requests_running)", "engine: running"),
+                  ("max(vllm_kv_usage_perc)", "gateway: kv (fraction)  [same as engine if healthy]"),
+                  ("max(vllm:kv_cache_usage_perc)", "engine: kv (fraction)")],
+                 0, 18, w=24, h=8, unit="short",
+                 description="The gateway's own reading of the engine against the engine's "
+                             "self-reported value. A disagreement between a pair is how a "
+                             "stale observer or a mistuned admission target shows itself, "
+                             "and nothing else in this dashboard reveals it. The two "
+                             "gateway series (vllm_requests_running, vllm_kv_usage_perc) "
+                             "ship with homelab-frontend#64 and are absent until it is "
+                             "deployed — until then this panel shows the engine's pair only."),
+    ]))
+
+    return {
+        "title": "LLM Observability",
+        "uid": "llm-observability",
+        "schemaVersion": 39,
+        "timezone": "browser",
+        "time": {"from": "now-6h", "to": "now"},
+        "refresh": "30s",
+        "tags": ["llm", "vllm", "tei", "gpu", "observability"],
+        "panels": panels,
+    }
+
+
 # ============================================================================
 # Generate
 # ============================================================================
@@ -277,4 +511,7 @@ write_dashboard("cluster-infrastructure.yaml", build_cluster_infrastructure(), "
 # Dashboard 3
 write_dashboard("api-gateway.yaml", build_api_gateway(), "API")
 
+# Dashboard 4
+write_dashboard("llm-observability.yaml", build_llm_observability(), "LLM")
+
 print("Done.")

k8s/infra/monitoring/dashboards/llm-observability.yaml

@@ -0,0 +1,95 @@
+apiVersion: v1
+data:
+  llm-observability.json: '{"title":"LLM Observability","uid":"llm-observability","schemaVersion":39,"timezone":"browser","time":{"from":"now-6h","to":"now"},"refresh":"30s","tags":["llm","vllm","tei","gpu","observability"],"panels":[{"id":100,"title":"Latency
+    \u2014 Time To First Token","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":0},"panels":[{"id":101,"title":"TTFT
+    p95 (gateway)","type":"stat","gridPos":{"h":4,"w":4,"x":0,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"histogram_quantile(0.95,
+    sum(rate(llm_ttft_seconds_bucket[5m])) by (le))"}]},{"id":102,"title":"TTFT p95
+    (vLLM)","type":"stat","gridPos":{"h":4,"w":4,"x":4,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"histogram_quantile(0.95,
+    sum(rate(vllm:time_to_first_token_seconds_bucket[5m])) by (le))"}]},{"id":103,"title":"KV
+    cache in use","type":"stat","gridPos":{"h":4,"w":4,"x":8,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"targets":[{"expr":"max(vllm:kv_cache_usage_perc)"}]},{"id":104,"title":"Requests
+    running","type":"stat","gridPos":{"h":4,"w":4,"x":12,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"sum(vllm:num_requests_running)"}]},{"id":105,"title":"Requests
+    waiting","type":"stat","gridPos":{"h":4,"w":4,"x":16,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"sum(vllm:num_requests_waiting)"}]},{"id":106,"title":"Preemptions
+    (5m)","type":"stat","gridPos":{"h":4,"w":4,"x":20,"y":1},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"increase(vllm:num_preemptions_total[5m])"}]},{"id":110,"title":"TTFT
+    percentile by model (gateway)","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"histogram_quantile(0.5,
+    sum(rate(llm_ttft_seconds_bucket[5m])) by (le, model))","legendFormat":"p50 \u00b7
+    {{model}}"},{"expr":"histogram_quantile(0.95, sum(rate(llm_ttft_seconds_bucket[5m]))
+    by (le, model))","legendFormat":"p95 \u00b7 {{model}}"},{"expr":"histogram_quantile(0.99,
+    sum(rate(llm_ttft_seconds_bucket[5m])) by (le, model))","legendFormat":"p99 \u00b7
+    {{model}}"}]},{"id":111,"title":"TTFT percentile \u2014 vLLM reasoning","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":2},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"histogram_quantile(0.5,
+    sum(rate(vllm:time_to_first_token_seconds_bucket[5m])) by (le, model_name))","legendFormat":"p50"},{"expr":"histogram_quantile(0.95,
+    sum(rate(vllm:time_to_first_token_seconds_bucket[5m])) by (le, model_name))","legendFormat":"p95"},{"expr":"histogram_quantile(0.99,
+    sum(rate(vllm:time_to_first_token_seconds_bucket[5m])) by (le, model_name))","legendFormat":"p99"}]},{"id":112,"title":"Prefill
+    vs decode (mean)","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":3},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"rate(vllm:request_prefill_time_seconds_sum[5m])
+    / clamp_min(rate(vllm:request_prefill_time_seconds_count[5m]), 0.001)","legendFormat":"prefill"},{"expr":"rate(vllm:request_decode_time_seconds_sum[5m])
+    / clamp_min(rate(vllm:request_decode_time_seconds_count[5m]), 0.001)","legendFormat":"decode"}]},{"id":113,"title":"Queue
+    wait before scheduling (mean)","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":3},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"rate(vllm:request_queue_time_seconds_sum[5m])
+    / clamp_min(rate(vllm:request_queue_time_seconds_count[5m]), 0.001)","legendFormat":"queue"}]}]},{"id":120,"title":"Latency
+    \u2014 Inter-Token","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":4},"panels":[{"id":121,"title":"Inter-token
+    latency by model (gateway)","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":5},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"histogram_quantile(0.5,
+    sum(rate(llm_itl_seconds_bucket[5m])) by (le, model))","legendFormat":"p50 \u00b7
+    {{model}}"},{"expr":"histogram_quantile(0.95, sum(rate(llm_itl_seconds_bucket[5m]))
+    by (le, model))","legendFormat":"p95 \u00b7 {{model}}"},{"expr":"histogram_quantile(0.99,
+    sum(rate(llm_itl_seconds_bucket[5m])) by (le, model))","legendFormat":"p99 \u00b7
+    {{model}}"}]},{"id":122,"title":"Inter-token latency \u2014 vLLM reasoning","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":5},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"histogram_quantile(0.5,
+    sum(rate(vllm:inter_token_latency_seconds_bucket[5m])) by (le, model_name))","legendFormat":"p50"},{"expr":"histogram_quantile(0.95,
+    sum(rate(vllm:inter_token_latency_seconds_bucket[5m])) by (le, model_name))","legendFormat":"p95"},{"expr":"histogram_quantile(0.99,
+    sum(rate(vllm:inter_token_latency_seconds_bucket[5m])) by (le, model_name))","legendFormat":"p99"}]},{"id":123,"title":"Decode
+    throughput (tokens/s per request)","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":6},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"1
+    / clamp_min(rate(vllm:time_per_output_token_seconds_sum[5m]) / clamp_min(rate(vllm:time_per_output_token_seconds_count[5m]),
+    0.001), 0.0001)","legendFormat":"tok/s"}]},{"id":124,"title":"End-to-end request
+    latency p50/p95/p99","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":6},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"histogram_quantile(0.5,
+    sum(rate(vllm:e2e_request_latency_seconds_bucket[5m])) by (le, model_name))","legendFormat":"p50"},{"expr":"histogram_quantile(0.95,
+    sum(rate(vllm:e2e_request_latency_seconds_bucket[5m])) by (le, model_name))","legendFormat":"p95"},{"expr":"histogram_quantile(0.99,
+    sum(rate(vllm:e2e_request_latency_seconds_bucket[5m])) by (le, model_name))","legendFormat":"p99"}]}]},{"id":130,"title":"Batching
+    & Scheduling","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":7},"panels":[{"id":131,"title":"vLLM
+    running vs waiting requests (batch depth)","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":8},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"sum(vllm:num_requests_running)","legendFormat":"running
+    (in batch)"},{"expr":"sum(vllm:num_requests_waiting)","legendFormat":"waiting
+    (queued)"}]},{"id":132,"title":"Preemption rate (KV cache eviction pressure)","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":8},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"rate(vllm:num_preemptions_total[5m])","legendFormat":"preemptions/s"}]},{"id":133,"title":"TEI
+    batch size (embeddings / reranker)","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":9},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"avg(te_batch_next_size_sum
+    / clamp_min(te_batch_next_size_count, 1)) by (app)","legendFormat":"{{app}}"}]},{"id":134,"title":"TEI
+    queue depth","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":9},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"max(te_queue_size)
+    by (app)","legendFormat":"{{app}}"}]}]},{"id":140,"title":"KV Cache","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":10},"panels":[{"id":141,"title":"KV
+    cache utilisation (GPU memory pressure)","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":11},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"targets":[{"expr":"max(vllm:kv_cache_usage_perc)
+    by (model_name)","legendFormat":"{{model_name}}"}]},{"id":142,"title":"Prefix
+    cache hit rate (CAG effectiveness)","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":11},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"targets":[{"expr":"vllm:prefix_cache_hit_rate","legendFormat":"{{model_name}}"}]},{"id":143,"title":"Prefix
+    cache hits vs queries","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":12},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"rate(vllm:prefix_cache_hits_total[5m])","legendFormat":"hits/s"},{"expr":"rate(vllm:prefix_cache_queries_total[5m])","legendFormat":"queries/s"}]},{"id":144,"title":"Prefix
+    cache hit tokens (gateway-observed, all models)","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":12},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"rate(vllm_prefix_cache_hit_tokens_total[5m])","legendFormat":"hit
+    tokens/s"}]}]},{"id":150,"title":"Throughput & Health","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":13},"panels":[{"id":151,"title":"Token
+    throughput","type":"timeseries","gridPos":{"h":8,"w":12,"x":0,"y":14},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"sum(rate(vllm:prompt_tokens_total[5m]))","legendFormat":"prompt
+    tok/s"},{"expr":"sum(rate(vllm:generation_tokens_total[5m]))","legendFormat":"generation
+    tok/s"},{"expr":"rate(llm_tokens_total[5m])","legendFormat":"gateway SSE chunks/s
+    (all models)"}]},{"id":152,"title":"Successful requests/s","type":"timeseries","gridPos":{"h":8,"w":12,"x":12,"y":14},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"sum(rate(vllm:request_success_total[5m]))","legendFormat":"vLLM"},{"expr":"sum(rate(te_request_count[5m]))","legendFormat":"TEI"}]},{"id":153,"title":"Backpressure
+    \u2014 queue-full rejects","type":"timeseries","gridPos":{"h":8,"w":8,"x":0,"y":15},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"rate(queue_full_requests_total[5m])","legendFormat":"rejected/s"}]},{"id":154,"title":"KV
+    warmup requests delayed","type":"timeseries","gridPos":{"h":8,"w":8,"x":8,"y":15},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"rate(warmup_requests_delayed_total[5m])","legendFormat":"delayed/s"}]},{"id":155,"title":"Embedding
+    / rerank latency p95","type":"timeseries","gridPos":{"h":8,"w":8,"x":16,"y":15},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"s"}},"targets":[{"expr":"histogram_quantile(0.95,
+    sum(rate(te_embed_duration_bucket[5m])) by (le, app))","legendFormat":"{{app}}
+    embed"},{"expr":"histogram_quantile(0.95, sum(rate(te_embed_queue_duration_bucket[5m]))
+    by (le, app))","legendFormat":"{{app}} queue"}]}]},{"id":160,"title":"Admission
+    Control","type":"row","collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":16},"panels":[{"id":161,"title":"Admission
+    parked (5m)","type":"timeseries","gridPos":{"h":8,"w":8,"x":0,"y":17},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"increase(admission_parked_total[5m])","legendFormat":"parked"}],"description":"Requests
+    the gateway held back rather than admitting. Emitted by the admission gate (homelab-frontend#64);
+    empty until that change is deployed."},{"id":162,"title":"Admission rejected by
+    reason","type":"timeseries","gridPos":{"h":8,"w":8,"x":8,"y":17},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"sum
+    by (reason) (increase(admission_rejected_total[5m]))","legendFormat":"{{reason}}"}],"description":"Admission
+    rejections split by the gate''s own reason label. Emitted by homelab-frontend#64;
+    empty until deployed."},{"id":163,"title":"Engine state stale","type":"timeseries","gridPos":{"h":8,"w":8,"x":16,"y":17},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"increase(engine_state_stale_total[5m])","legendFormat":"stale"}],"description":"Times
+    the gateway''s view of the engine gauges went stale. The gate fails OPEN when
+    this happens, so any non-zero rate means admission is silently degraded to admit-everything.
+    Emitted by homelab-frontend#64; empty until deployed."},{"id":164,"title":"Gateway
+    view vs engine truth","type":"timeseries","gridPos":{"h":8,"w":24,"x":0,"y":18},"datasource":{"type":"prometheus","uid":"prometheus"},"fieldConfig":{"defaults":{"unit":"short"}},"targets":[{"expr":"max(vllm_requests_running)","legendFormat":"gateway:
+    running"},{"expr":"sum(vllm:num_requests_running)","legendFormat":"engine: running"},{"expr":"max(vllm_kv_usage_perc)","legendFormat":"gateway:
+    kv (fraction)  [same as engine if healthy]"},{"expr":"max(vllm:kv_cache_usage_perc)","legendFormat":"engine:
+    kv (fraction)"}],"description":"The gateway''s own reading of the engine against
+    the engine''s self-reported value. A disagreement between a pair is how a stale
+    observer or a mistuned admission target shows itself, and nothing else in this
+    dashboard reveals it. The two gateway series (vllm_requests_running, vllm_kv_usage_perc)
+    ship with homelab-frontend#64 and are absent until it is deployed \u2014 until
+    then this panel shows the engine''s pair only."}]}]}'
+kind: ConfigMap
+metadata:
+  annotations:
+    grafana_folder: LLM
+  labels:
+    grafana_dashboard: '1'
+  name: llm-observability-dashboard
+  namespace: logging

k8s/infra/monitoring/kustomization.yaml

@@ -8,16 +8,21 @@ resources:
   - alerts/ingress-alerts.yaml
   - alerts/svc-argocd-rules.yaml
   - alerts/svc-authentik-rules.yaml
+  - alerts/svc-zitadel-rules.yaml
   - alerts/svc-forgejo-rules.yaml
   - alerts/svc-grafana-rules.yaml
   - alerts/svc-minio-rules.yaml
   - alerts/svc-vault-rules.yaml
   - alerts/cluster-alerts.yaml
   - alerts/api-gateway-alerts.yaml
+  - alerts/cag-kv-cache-rules.yaml
   - servicemonitors/argocd.yaml
   - servicemonitors/authentik.yaml
   - servicemonitors/forgejo.yaml
   - servicemonitors/minio.yaml
   - servicemonitors/ingress-nginx.yaml
+  - servicemonitors/vllm.yaml
+  - servicemonitors/api-gateway.yaml
   - dashboards/cluster-infrastructure.yaml
   - dashboards/api-gateway.yaml
+  - dashboards/llm-observability.yaml

k8s/infra/monitoring/prometheus-values.yaml

@@ -54,7 +54,10 @@ alertmanager:
 # ── Prometheus ────────────────────────────────────────────────────────────────
 prometheus:
   prometheusSpec:
-    retention: 15d
+    retention: 30d
+    # Must stay under the PVC size below (25Gi). At 95GB the limit never
+    # triggered, the volume filled, and Prometheus crashlooped with
+    # "no space left on device" writing /prometheus/queries.active.
     retentionSize: "18GB"
 
     # scrapeTimeout MUST be <= scrapeInterval or the operator refuses to generate
@@ -64,10 +67,9 @@ prometheus:
     scrapeTimeout: 60s
     evaluationInterval: 30s
 
-    # Pin to az-a (talos-cp-1) — sole Longhorn node; else the RWO PVC can't
-    # attach on cp-2/cp-3 (CSINode lacks driver.longhorn.io).
+    # Pin to worker-1 for more storage capacity
     nodeSelector:
-      topology.kubernetes.io/zone: az-a
+      kubernetes.io/hostname: worker-1
 
     # Persistent storage — metrics survive node reboots and pod restarts.
     # Uses the default `longhorn` StorageClass; nodeSelector above already pins
@@ -79,7 +81,7 @@ prometheus:
           accessModes: ["ReadWriteOnce"]
           resources:
             requests:
-              storage: 20Gi
+              storage: 25Gi
 
     resources:
       requests:

k8s/infra/monitoring/servicemonitors/api-gateway.yaml

@@ -0,0 +1,62 @@
+# History, recorded so nobody re-derives it the hard way: on 2026-09-29 the
+# three latency series below recorded nothing. internal/proxy/llm_metrics.go
+# declared a capture wrapper (LLMMetricsCapture) that was never constructed
+# anywhere, so the exporter emitted HELP-only stubs and the dashboard panels
+# stayed empty.
+#
+# homelab-frontend#63 fixed exactly that. The wrapper is now
+# ResponseWriterWrapper, constructed by NewResponseWriterWrapper
+# (internal/proxy/llm_metrics.go:38) and installed on the streaming proxy
+# request path. Verified live on 2026-09-29:
+#   llm_ttft_seconds  count=7  sum=598.212s
+#   llm_itl_seconds   count=16116
+#   llm_tokens_total  3 series
+#
+# These derived-from-SSE series cover EVERY model including the two Ollama ones
+# (ornith:35b, qwen2.5:3b-instruct), which expose no metrics endpoint at all.
+# They are proxy-side: TTFT is request-start to first byte and ITL is the gap
+# between SSE writes, so both are granular to SSE write boundaries rather than
+# to the engine's own token cadence. llm_tokens_total counts `data:` events,
+# and the documented assumption in internal/proxy/llm_metrics.go is that these
+# upstreams emit one such event per token — so it is a token count only as far
+# as that assumption holds. vLLM's own histograms remain authoritative.
+#
+# Also recorded and working (3 series, one per replica):
+#   queue_full_requests_total           counter    backpressure rejects
+#   warmup_requests_delayed_total       counter    vLLM slot contention
+#   vllm_prefix_cache_hit_tokens_total  counter    prefix-cache hits
+#
+# NOT working, do not build on it: request_duration_seconds is declared and
+# exported but has 0 samples, and its only writer Metrics.RecordRequest has
+# zero call sites outside _test.go — verified by ast-grep, not assumed. It is
+# the same dead-code shape this branch already corrected for the latency
+# series, so it is listed here rather than left to be rediscovered.
+#
+# Also note the Deployment already carried prometheus.io/scrape annotations,
+# but kube-prometheus-stack ignores pod annotations (no additionalScrapeConfigs,
+# serviceMonitorSelectorNilUsesHelmValues: false) — so nothing at all was being
+# collected before this ServiceMonitor existed.
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: api-gateway
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/name: api-gateway
+    app.kubernetes.io/part-of: api
+spec:
+  namespaceSelector:
+    matchNames:
+      - api
+  selector:
+    matchLabels:
+      app: api-gateway
+  endpoints:
+    # api-gateway Service port IS named `http` (unlike the KServe ones), so
+    # the name form works here.
+    - port: http
+      interval: 30s
+      scrapeTimeout: 10s
+      path: /metrics
+      scheme: http
+

k8s/infra/monitoring/servicemonitors/vllm.yaml

@@ -11,20 +11,39 @@ spec:
     matchNames:
       - llm-serving
   selector:
-    matchLabels:
-      app.kubernetes.io/part-of: llm-serving
+    # Only the three engines that actually serve /metrics.
+    # ornith-predictor and qwen-cpu are Ollama, which has no Prometheus
+    # endpoint (/metrics returns 404) — selecting them would add permanently
+    # DOWN targets. Ollama-model visibility comes from the api-gateway
+    # ServiceMonitor instead (llm_ttft_seconds / llm_itl_seconds are
+    # measured at the proxy, so they cover every model including Ollama).
+    matchExpressions:
+      - key: app.kubernetes.io/name
+        operator: In
+        values:
+          - llm-reasoning   # vLLM 0.11.0 — full engine metrics
+          - llm-embeddings  # TEI 1.8.2 — CPU
+          - llm-reranker    # TEI 1.8.2 — CPU
   endpoints:
-    - port: http
+    # targetPort, not port: the KServe-generated Services on llm-serving have
+    # UNNAMED ports, so `port: <name>` can never match. Naming them would mean
+    # editing the InferenceServices (predictor restart = full weights reload,
+    # tens of seconds on the vLLM slot), so scrape the pod port directly.
+    # prometheus-operator v0.94.1 supports targetPort on ServiceMonitor.
+    - targetPort: 8080
       interval: 30s
       scrapeTimeout: 10s
       path: /metrics
       scheme: http
       relabelings:
-        - sourceLabels: [__meta_kubernetes_namespace]
-          targetLabel: namespace
-        - sourceLabels: [__meta_kubernetes_pod_name]
-          targetLabel: pod
-        - sourceLabels: [__meta_kubernetes_service_name]
-          targetLabel: service
-        - sourceLabels: [__meta_kubernetes_pod_label_app_kubernetes_io_name]
+        # Prometheus's Kubernetes service discovery already supplies the
+        # namespace, pod and service labels; the only one that needs deriving
+        # is `app`, since the TEI panels aggregate by it (by (app)) and SD does
+        # not promote arbitrary pod labels.
+        #
+        # `action: replace` is written explicitly. It is the API server's
+        # default for relabeling rules, so omitting it leaves the live object
+        # diverged from this manifest and ArgoCD reports permanent OutOfSync.
+        - action: replace
+          sourceLabels: [__meta_kubernetes_pod_label_app_kubernetes_io_name]
           targetLabel: app

k8s/infra/oidc-bootstrap/bootstrap.yaml

@@ -0,0 +1,33 @@
+# One-shot bootstrap: restart the control-plane apiservers ONCE so they pick up the
+# OIDC authenticator (they last started before the Authentik provider existed, so OIDC
+# tokens were never accepted -> every login got 401). Delete this whole directory after.
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: oidc-bootstrap
+  namespace: kube-system
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: oidc-bootstrap
+  namespace: kube-system
+rules:
+  - apiGroups: [""]
+    resources: ["pods"]
+    verbs: ["get", "list", "delete"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: oidc-bootstrap
+  namespace: kube-system
+subjects:
+  - kind: ServiceAccount
+    name: oidc-bootstrap
+    namespace: kube-system
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: oidc-bootstrap

k8s/infra/poimen/kustomization.yaml

@@ -0,0 +1,12 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+# Poimen infrastructure — CNPG Postgres for memory service.
+# Part of the `poimen` ArgoCD Application (multi-source, source 3).
+# Sync-wave -1 ensures the DB cluster is healthy before application
+# deployments (wave 0) are applied.
+resources:
+  - memory-db.yaml
+  - poimen-sandbox-namespace.yaml
+  - poimen-sandbox-quota.yaml
+  - pi-session-netpol.yaml
+  - pi-agent-workspace-pv.yaml

k8s/infra/poimen/memory-db.yaml

@@ -0,0 +1,37 @@
+# Dedicated CNPG Postgres for Poimen Memory (GitOps, wave 2).
+# Uses default longhorn storage class (3 replicas, dataLocality disabled).
+# CNPG generates secret `memory-db-app` + service `memory-db-rw` in ns poimen.
+apiVersion: postgresql.cnpg.io/v1
+kind: Cluster
+metadata:
+  name: memory-db
+  namespace: poimen
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+    argocd.argoproj.io/sync-options: SkipDryRunOnMissingResource=true
+spec:
+  instances: 3
+  imageName: ghcr.io/cloudnative-pg/postgresql:16.2
+  bootstrap:
+    initdb:
+      database: memory
+      owner: app
+      encoding: UTF8
+      localeCollate: C
+      localeCType: C
+      postInitApplicationSQL:
+        - "CREATE EXTENSION vector;"
+  enableSuperuserAccess: false
+  resources:
+    requests: { memory: "512Mi", cpu: "250m" }
+    limits: { memory: "2Gi", cpu: "1" }
+  storage:
+    size: 20Gi
+    storageClass: longhorn
+  affinity:
+    podAntiAffinityType: preferred
+    topologyKey: kubernetes.io/hostname
+    tolerations:
+      - key: node-role.kubernetes.io/control-plane
+        operator: Exists
+        effect: NoSchedule

k8s/infra/poimen/pi-agent-workspace-pv.yaml

@@ -0,0 +1,57 @@
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  finalizers:
+  - kubernetes.io/pv-protection
+  labels:
+    app: pi-coding-agent-sandbox
+    part-of: poimen-toolkit
+  name: pi-agent-workspace-pv
+  annotations:
+    argocd.argoproj.io/sync-wave: '-1'
+spec:
+  accessModes:
+  - ReadWriteOnce
+  capacity:
+    storage: 10Gi
+  claimRef:
+    apiVersion: v1
+    kind: PersistentVolumeClaim
+    name: pi-agent-workspace
+    namespace: poimen-sandbox
+  hostPath:
+    path: /var/lib/pi-agent-sandbox
+    type: DirectoryOrCreate
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+      - matchExpressions:
+        - key: kubernetes.io/hostname
+          operator: In
+          values:
+          - talos-cp-2
+  persistentVolumeReclaimPolicy: Retain
+  volumeMode: Filesystem
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  annotations:
+    pv.kubernetes.io/bind-completed: 'yes'
+    argocd.argoproj.io/sync-wave: '-1'
+  finalizers:
+  - kubernetes.io/pvc-protection
+  labels:
+    app: pi-coding-agent-sandbox
+    part-of: poimen-toolkit
+  name: pi-agent-workspace
+  namespace: poimen-sandbox
+spec:
+  accessModes:
+  - ReadWriteOnce
+  resources:
+    requests:
+      storage: 10Gi
+  storageClassName: ''
+  volumeMode: Filesystem
+  volumeName: pi-agent-workspace-pv

k8s/infra/poimen/pi-session-netpol.yaml

@@ -0,0 +1,12 @@
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: pi-session-deny-kube-api
+  namespace: poimen-sandbox
+spec:
+  endpointSelector:
+    matchLabels:
+      app: pi-session
+  egressDeny:
+    - toEntities:
+        - kube-apiserver

k8s/infra/poimen/poimen-sandbox-namespace.yaml

@@ -0,0 +1,9 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: poimen-sandbox
+  labels:
+    pod-security.kubernetes.io/enforce: restricted
+    pod-security.kubernetes.io/enforce-version: latest
+    pod-security.kubernetes.io/audit: restricted
+    pod-security.kubernetes.io/warn: restricted

k8s/infra/poimen/poimen-sandbox-quota.yaml

@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: ResourceQuota
+metadata:
+  name: sandbox-quota
+  namespace: poimen-sandbox
+spec:
+  hard:
+    pods: "20"
+    requests.cpu: "10"
+    requests.memory: 20Gi
+    limits.cpu: "20"
+    limits.memory: 40Gi

k8s/infra/rbac/kustomization.yaml

@@ -16,6 +16,7 @@ resources:
   - temporal-operator-role.yaml
   - llm-serving-operator-role.yaml
   - poimen-memory-operator-role.yaml
+  - sandbox-observer-role.yaml
 # paperless's Role/RoleBinding lives in k8s/apps/paperless/rbac.yaml instead -
 # that app already has its own kustomization + namespace, no need to
 # duplicate it here. All of these stay inert (grant nothing) until

k8s/infra/rbac/sandbox-observer-role.yaml

@@ -0,0 +1,23 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: sandbox-observer
+  namespace: poimen-sandbox
+rules:
+  - apiGroups: [""]
+    resources: [pods, pods/log, services]
+    verbs: [get, list, watch]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: poimen-devs-sandbox
+  namespace: poimen-sandbox
+subjects:
+  - kind: Group
+    apiGroup: rbac.authorization.k8s.io
+    name: "oidc:poimen-devs"
+roleRef:
+  kind: Role
+  name: sandbox-observer
+  apiGroup: rbac.authorization.k8s.io

k8s/infra/talos-repair/kustomization.yaml

@@ -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

k8s/infra/talos-repair/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

k8s/infra/talos-repair/secret-generator.yaml

@@ -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

k8s/infra/talos-repair/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