Merge pull request 'Rename the owner agent host to worker.bstein.dev (supersedes #41)' (#42) from feature/hermes-domain-rename-agent-worker-v2 into main

Reviewed-on: atlas/titan-iac#42
Reviewed-by: bstein <bstein@noreply.scm.bstein.dev>

infrastructure/core/coredns-custom.yaml

@@ -49,6 +49,7 @@ data:
         192.168.22.9 triage.bstein.dev
         192.168.22.9 triage.hermes.bstein.dev
         192.168.22.9 vault.bstein.dev
+        192.168.22.9 worker.bstein.dev
         fallthrough
       }
     }

knowledge/catalog/atlas-summary.json

@@ -1,8 +1,8 @@
 {
   "counts": {
     "helmrelease_host_hints": 23,
-    "http_endpoints": 61,
+    "http_endpoints": 65,
-    "services": 91,
+    "services": 98,
-    "workloads": 125
+    "workloads": 130
   }
 }

knowledge/catalog/atlas.json

@@ -106,6 +106,31 @@
       "path": "services/hermes-chat",
       "targetNamespace": "hermes-chat"
     },
+    {
+      "name": "hermes-observer-bindings",
+      "path": "services/hermes-observer-bindings",
+      "targetNamespace": null
+    },
+    {
+      "name": "hermes-observer-rbac",
+      "path": "services/hermes-observer-rbac",
+      "targetNamespace": null
+    },
+    {
+      "name": "hermes-scm-broker",
+      "path": "services/hermes-scm-broker",
+      "targetNamespace": "hermes-scm"
+    },
+    {
+      "name": "hermes-scm-broker-code",
+      "path": "services/hermes/scm-common",
+      "targetNamespace": "hermes-scm"
+    },
+    {
+      "name": "hermes-scm-namespace",
+      "path": "services/hermes-scm-namespace",
+      "targetNamespace": null
+    },
     {
       "name": "hermes-triage-demo",
       "path": "services/hermes-triage-demo",
@@ -251,6 +276,11 @@
       "path": "infrastructure/vault-csi",
       "targetNamespace": "kube-system"
     },
+    {
+      "name": "vault-hermes-jenkins-token-seed",
+      "path": "services/vault-hermes-jenkins-token-seed",
+      "targetNamespace": "vault"
+    },
     {
       "name": "vault-injector",
       "path": "infrastructure/vault-injector",
@@ -304,7 +334,7 @@
         "node-role.kubernetes.io/worker": "true"
       },
       "images": [
-        "registry.bstein.dev/bstein/bstein-dev-home-backend:0.1.1-464"
+        "registry.bstein.dev/bstein/bstein-dev-home-backend:0.1.1-479"
       ]
     },
     {
@@ -320,7 +350,7 @@
         "node-role.kubernetes.io/worker": "true"
       },
       "images": [
-        "registry.bstein.dev/bstein/bstein-dev-home-frontend:0.1.1-464"
+        "registry.bstein.dev/bstein/bstein-dev-home-frontend:0.1.1-479"
       ]
     },
     {
@@ -902,7 +932,7 @@
       "serviceAccountName": "hermes-node-ssh-access",
       "nodeSelector": {},
       "images": [
-        "busybox:1.37"
+        "python@sha256:6d43704baacd1bfbe7c295d7f13079d5d8104ed33568873133f8fc69980419df"
       ]
     },
     {
@@ -915,8 +945,8 @@
       "serviceAccountName": "hermes-triage",
       "nodeSelector": {},
       "images": [
-        "registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8",
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37",
-        "registry.bstein.dev/bstein/hermes-webui@sha256:9c2fe8341c7b650e08d10acead3151b19e2af737863268bafb39b3d9517575b1"
+        "registry.bstein.dev/bstein/hermes-webui@sha256:ac6ba7bfd8a86227f31a9a96ebea41227ccf70391f7dcf34206f4d58e835e50e"
       ]
     },
     {
@@ -930,7 +960,7 @@
       "nodeSelector": {},
       "images": [
         "quay.io/oauth2-proxy/oauth2-proxy:v7.15.3@sha256:10a1165743a192e1940b4708fb9647027185ce11a681a1c5519b442ff7f1f561",
-        "registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8"
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
       ]
     },
     {
@@ -943,7 +973,7 @@
       "serviceAccountName": "hermes-chat",
       "nodeSelector": {},
       "images": [
-        "registry.bstein.dev/bstein/hermes-chat-router@sha256:a4010fdc5b6dce2696e6fec06eb38a3992817faa01ff3472122c870038b22bd2"
+        "registry.bstein.dev/bstein/hermes-chat-router@sha256:6744cb7b87c6050f1b97c0675cd280b8295b3b5826ba1d6d92e37aee6fd0b8c4"
       ]
     },
     {
@@ -1058,6 +1088,48 @@
         "registry.bstein.dev/bstein/hermes-chat-sandbox@sha256:17ee62b8e61c08573a3a8cca903b38ec43800cb44ec29340e1bc095176544bca"
       ]
     },
+    {
+      "kind": "Deployment",
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-0",
+      "labels": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "0"
+      },
+      "serviceAccountName": "hermes-execution-worker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
+      ]
+    },
+    {
+      "kind": "Deployment",
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-1",
+      "labels": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "1"
+      },
+      "serviceAccountName": "hermes-execution-worker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
+      ]
+    },
+    {
+      "kind": "Deployment",
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-2",
+      "labels": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "2"
+      },
+      "serviceAccountName": "hermes-execution-worker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
+      ]
+    },
     {
       "kind": "Deployment",
       "namespace": "hermes",
@@ -1177,8 +1249,36 @@
       "serviceAccountName": "hermes-chat",
       "nodeSelector": {},
       "images": [
-        "registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8",
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37",
-        "registry.bstein.dev/bstein/hermes-webui@sha256:9c2fe8341c7b650e08d10acead3151b19e2af737863268bafb39b3d9517575b1"
+        "registry.bstein.dev/bstein/hermes-webui@sha256:c276a9e17c9057237472f39640c9ebac9d4359d9f62a34df52a759eef43167bf"
+      ]
+    },
+    {
+      "kind": "StatefulSet",
+      "namespace": "hermes",
+      "name": "hermes-execution-worker",
+      "labels": {
+        "app": "hermes-execution-worker",
+        "app.kubernetes.io/name": "hermes-execution-worker",
+        "app.kubernetes.io/part-of": "hermes"
+      },
+      "serviceAccountName": "hermes-execution-worker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
+      ]
+    },
+    {
+      "kind": "Deployment",
+      "namespace": "hermes-scm",
+      "name": "hermes-scm-broker",
+      "labels": {
+        "app": "hermes-scm-broker"
+      },
+      "serviceAccountName": "hermes-scm-broker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:37ebf720c783ae908a602916ffccf88d43d205a157957f5dc4b487867aee45e7"
       ]
     },
     {
@@ -1528,7 +1628,7 @@
         "kubernetes.io/os": "linux"
       },
       "images": [
-        "registry.bstein.dev/bstein/metis-sentinel:0.1.0-293-amd64"
+        "registry.bstein.dev/bstein/metis-sentinel:0.1.0-304-amd64"
       ]
     },
     {
@@ -1544,7 +1644,7 @@
         "kubernetes.io/os": "linux"
       },
       "images": [
-        "registry.bstein.dev/bstein/metis-sentinel:0.1.0-293-arm64"
+        "registry.bstein.dev/bstein/metis-sentinel:0.1.0-304-arm64"
       ]
     },
     {
@@ -1633,7 +1733,7 @@
         "node-role.kubernetes.io/worker": "true"
       },
       "images": [
-        "registry.bstein.dev/bstein/ariadne:0.1.0-454"
+        "registry.bstein.dev/bstein/ariadne:0.1.0-464"
       ]
     },
     {
@@ -1661,7 +1761,7 @@
       "serviceAccountName": "metis",
       "nodeSelector": {},
       "images": [
-        "registry.bstein.dev/bstein/metis:0.1.0-293-arm64"
+        "registry.bstein.dev/bstein/metis:0.1.0-304-arm64"
       ]
     },
     {
@@ -3179,6 +3279,22 @@
         }
       ]
     },
+    {
+      "namespace": "hermes",
+      "name": "hermes-cli-lane-metrics",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-agent"
+      },
+      "ports": [
+        {
+          "name": "lane-metrics",
+          "port": 9011,
+          "targetPort": "lane-metrics",
+          "protocol": "TCP"
+        }
+      ]
+    },
     {
       "namespace": "hermes",
       "name": "hermes-codex-broker",
@@ -3195,6 +3311,82 @@
         }
       ]
     },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-0",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "0"
+      },
+      "ports": [
+        {
+          "name": "mediator",
+          "port": 9009,
+          "targetPort": "mediator",
+          "protocol": "TCP"
+        }
+      ]
+    },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-1",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "1"
+      },
+      "ports": [
+        {
+          "name": "mediator",
+          "port": 9009,
+          "targetPort": "mediator",
+          "protocol": "TCP"
+        }
+      ]
+    },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-2",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "2"
+      },
+      "ports": [
+        {
+          "name": "mediator",
+          "port": 9009,
+          "targetPort": "mediator",
+          "protocol": "TCP"
+        }
+      ]
+    },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-pool",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-agent"
+      },
+      "ports": [
+        {
+          "name": "http",
+          "port": 9007,
+          "targetPort": "execution-pool",
+          "protocol": "TCP"
+        }
+      ]
+    },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-worker",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-execution-worker"
+      },
+      "ports": []
+    },
     {
       "namespace": "hermes",
       "name": "hermes-gpu-handoff",
@@ -3393,6 +3585,22 @@
         }
       ]
     },
+    {
+      "namespace": "hermes-scm",
+      "name": "hermes-scm-broker",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-scm-broker"
+      },
+      "ports": [
+        {
+          "name": "http",
+          "port": 9081,
+          "targetPort": "http",
+          "protocol": "TCP"
+        }
+      ]
+    },
     {
       "namespace": "jellyfin",
       "name": "jellyfin",
@@ -4423,6 +4631,26 @@
         "source": "hermes"
       }
     },
+    {
+      "host": "chat.hermes.bstein.dev",
+      "path": "/",
+      "backend": {
+        "namespace": "hermes",
+        "service": "oauth2-proxy-hermes-chat",
+        "port": "http",
+        "workloads": [
+          {
+            "kind": "Deployment",
+            "name": "oauth2-proxy-hermes-chat"
+          }
+        ]
+      },
+      "via": {
+        "kind": "Ingress",
+        "name": "hermes-sites",
+        "source": "hermes"
+      }
+    },
     {
       "host": "ci.bstein.dev",
       "path": "/",
@@ -5183,6 +5411,26 @@
         "source": "hermes"
       }
     },
+    {
+      "host": "triage.hermes.bstein.dev",
+      "path": "/",
+      "backend": {
+        "namespace": "hermes",
+        "service": "oauth2-proxy-hermes-triage",
+        "port": "http",
+        "workloads": [
+          {
+            "kind": "Deployment",
+            "name": "oauth2-proxy-hermes-triage"
+          }
+        ]
+      },
+      "via": {
+        "kind": "Ingress",
+        "name": "hermes-sites",
+        "source": "hermes"
+      }
+    },
     {
       "host": "vault.bstein.dev",
       "path": "/",
@@ -5302,6 +5550,46 @@
         "name": "wolf",
         "source": "game-stream"
       }
+    },
+    {
+      "host": "worker.bstein.dev",
+      "path": "/",
+      "backend": {
+        "namespace": "hermes",
+        "service": "oauth2-proxy-hermes-agent",
+        "port": "http",
+        "workloads": [
+          {
+            "kind": "Deployment",
+            "name": "hermes-agent"
+          }
+        ]
+      },
+      "via": {
+        "kind": "Ingress",
+        "name": "hermes-agent-dashboard",
+        "source": "hermes"
+      }
+    },
+    {
+      "host": "worker.bstein.dev",
+      "path": "/terminal",
+      "backend": {
+        "namespace": "hermes",
+        "service": "oauth2-proxy-hermes-agent",
+        "port": "http",
+        "workloads": [
+          {
+            "kind": "Deployment",
+            "name": "hermes-agent"
+          }
+        ]
+      },
+      "via": {
+        "kind": "Ingress",
+        "name": "hermes-agent-terminal",
+        "source": "hermes"
+      }
     }
   ],
   "helmrelease_host_hints": {

knowledge/catalog/atlas.yaml

@@ -65,6 +65,21 @@ sources:
 - name: hermes-chat
   path: services/hermes-chat
   targetNamespace: hermes-chat
+- name: hermes-observer-bindings
+  path: services/hermes-observer-bindings
+  targetNamespace: null
+- name: hermes-observer-rbac
+  path: services/hermes-observer-rbac
+  targetNamespace: null
+- name: hermes-scm-broker
+  path: services/hermes-scm-broker
+  targetNamespace: hermes-scm
+- name: hermes-scm-broker-code
+  path: services/hermes/scm-common
+  targetNamespace: hermes-scm
+- name: hermes-scm-namespace
+  path: services/hermes-scm-namespace
+  targetNamespace: null
 - name: hermes-triage-demo
   path: services/hermes-triage-demo
   targetNamespace: null
@@ -152,6 +167,9 @@ sources:
 - name: vault-csi
   path: infrastructure/vault-csi
   targetNamespace: kube-system
+- name: vault-hermes-jenkins-token-seed
+  path: services/vault-hermes-jenkins-token-seed
+  targetNamespace: vault
 - name: vault-injector
   path: infrastructure/vault-injector
   targetNamespace: vault
@@ -187,7 +205,7 @@ workloads:
     kubernetes.io/arch: arm64
     node-role.kubernetes.io/worker: 'true'
   images:
-  - registry.bstein.dev/bstein/bstein-dev-home-backend:0.1.1-464
+  - registry.bstein.dev/bstein/bstein-dev-home-backend:0.1.1-479
 - kind: Deployment
   namespace: bstein-dev-home
   name: bstein-dev-home-frontend
@@ -198,7 +216,7 @@ workloads:
     kubernetes.io/arch: arm64
     node-role.kubernetes.io/worker: 'true'
   images:
-  - registry.bstein.dev/bstein/bstein-dev-home-frontend:0.1.1-464
+  - registry.bstein.dev/bstein/bstein-dev-home-frontend:0.1.1-479
 - kind: Deployment
   namespace: bstein-dev-home
   name: bstein-dev-home-vault-sync
@@ -604,7 +622,7 @@ workloads:
   serviceAccountName: hermes-node-ssh-access
   nodeSelector: {}
   images:
-  - busybox:1.37
+  - python@sha256:6d43704baacd1bfbe7c295d7f13079d5d8104ed33568873133f8fc69980419df
 - kind: Deployment
   namespace: hermes
   name: hermes
@@ -613,8 +631,8 @@ workloads:
   serviceAccountName: hermes-triage
   nodeSelector: {}
   images:
-  - registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
-  - registry.bstein.dev/bstein/hermes-webui@sha256:9c2fe8341c7b650e08d10acead3151b19e2af737863268bafb39b3d9517575b1
+  - registry.bstein.dev/bstein/hermes-webui@sha256:ac6ba7bfd8a86227f31a9a96ebea41227ccf70391f7dcf34206f4d58e835e50e
 - kind: Deployment
   namespace: hermes
   name: hermes-agent
@@ -624,7 +642,7 @@ workloads:
   nodeSelector: {}
   images:
   - quay.io/oauth2-proxy/oauth2-proxy:v7.15.3@sha256:10a1165743a192e1940b4708fb9647027185ce11a681a1c5519b442ff7f1f561
-  - registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
 - kind: Deployment
   namespace: hermes
   name: hermes-chat-router
@@ -633,7 +651,7 @@ workloads:
   serviceAccountName: hermes-chat
   nodeSelector: {}
   images:
-  - registry.bstein.dev/bstein/hermes-chat-router@sha256:a4010fdc5b6dce2696e6fec06eb38a3992817faa01ff3472122c870038b22bd2
+  - registry.bstein.dev/bstein/hermes-chat-router@sha256:6744cb7b87c6050f1b97c0675cd280b8295b3b5826ba1d6d92e37aee6fd0b8c4
 - kind: Deployment
   namespace: hermes
   name: hermes-chat-sandbox-0
@@ -714,6 +732,36 @@ workloads:
   nodeSelector: {}
   images:
   - registry.bstein.dev/bstein/hermes-chat-sandbox@sha256:17ee62b8e61c08573a3a8cca903b38ec43800cb44ec29340e1bc095176544bca
+- kind: Deployment
+  namespace: hermes
+  name: hermes-execution-mediator-0
+  labels:
+    app: hermes-execution-mediator
+    pool-ordinal: '0'
+  serviceAccountName: hermes-execution-worker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
+- kind: Deployment
+  namespace: hermes
+  name: hermes-execution-mediator-1
+  labels:
+    app: hermes-execution-mediator
+    pool-ordinal: '1'
+  serviceAccountName: hermes-execution-worker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
+- kind: Deployment
+  namespace: hermes
+  name: hermes-execution-mediator-2
+  labels:
+    app: hermes-execution-mediator
+    pool-ordinal: '2'
+  serviceAccountName: hermes-execution-worker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
 - kind: Deployment
   namespace: hermes
   name: hermes-local-image
@@ -797,8 +845,28 @@ workloads:
   serviceAccountName: hermes-chat
   nodeSelector: {}
   images:
-  - registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
-  - registry.bstein.dev/bstein/hermes-webui@sha256:9c2fe8341c7b650e08d10acead3151b19e2af737863268bafb39b3d9517575b1
+  - registry.bstein.dev/bstein/hermes-webui@sha256:c276a9e17c9057237472f39640c9ebac9d4359d9f62a34df52a759eef43167bf
+- kind: StatefulSet
+  namespace: hermes
+  name: hermes-execution-worker
+  labels:
+    app: hermes-execution-worker
+    app.kubernetes.io/name: hermes-execution-worker
+    app.kubernetes.io/part-of: hermes
+  serviceAccountName: hermes-execution-worker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
+- kind: Deployment
+  namespace: hermes-scm
+  name: hermes-scm-broker
+  labels:
+    app: hermes-scm-broker
+  serviceAccountName: hermes-scm-broker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:37ebf720c783ae908a602916ffccf88d43d205a157957f5dc4b487867aee45e7
 - kind: Deployment
   namespace: jellyfin
   name: jellyfin
@@ -1037,7 +1105,7 @@ workloads:
     kubernetes.io/arch: amd64
     kubernetes.io/os: linux
   images:
-  - registry.bstein.dev/bstein/metis-sentinel:0.1.0-293-amd64
+  - registry.bstein.dev/bstein/metis-sentinel:0.1.0-304-amd64
 - kind: DaemonSet
   namespace: maintenance
   name: metis-sentinel-arm64
@@ -1048,7 +1116,7 @@ workloads:
     kubernetes.io/arch: arm64
     kubernetes.io/os: linux
   images:
-  - registry.bstein.dev/bstein/metis-sentinel:0.1.0-293-arm64
+  - registry.bstein.dev/bstein/metis-sentinel:0.1.0-304-arm64
 - kind: DaemonSet
   namespace: maintenance
   name: node-image-sweeper
@@ -1108,7 +1176,7 @@ workloads:
     kubernetes.io/arch: arm64
     node-role.kubernetes.io/worker: 'true'
   images:
-  - registry.bstein.dev/bstein/ariadne:0.1.0-454
+  - registry.bstein.dev/bstein/ariadne:0.1.0-464
 - kind: Deployment
   namespace: maintenance
   name: maintenance-vault-sync
@@ -1127,7 +1195,7 @@ workloads:
   serviceAccountName: metis
   nodeSelector: {}
   images:
-  - registry.bstein.dev/bstein/metis:0.1.0-293-arm64
+  - registry.bstein.dev/bstein/metis:0.1.0-304-arm64
 - kind: Deployment
   namespace: maintenance
   name: oauth2-proxy-metis
@@ -2120,6 +2188,16 @@ services:
     port: 9006
     targetPort: claude-broker
     protocol: TCP
+- namespace: hermes
+  name: hermes-cli-lane-metrics
+  type: ClusterIP
+  selector:
+    app: hermes-agent
+  ports:
+  - name: lane-metrics
+    port: 9011
+    targetPort: lane-metrics
+    protocol: TCP
 - namespace: hermes
   name: hermes-codex-broker
   type: ClusterIP
@@ -2130,6 +2208,55 @@ services:
     port: 9003
     targetPort: codex-broker
     protocol: TCP
+- namespace: hermes
+  name: hermes-execution-mediator-0
+  type: ClusterIP
+  selector:
+    app: hermes-execution-mediator
+    pool-ordinal: '0'
+  ports:
+  - name: mediator
+    port: 9009
+    targetPort: mediator
+    protocol: TCP
+- namespace: hermes
+  name: hermes-execution-mediator-1
+  type: ClusterIP
+  selector:
+    app: hermes-execution-mediator
+    pool-ordinal: '1'
+  ports:
+  - name: mediator
+    port: 9009
+    targetPort: mediator
+    protocol: TCP
+- namespace: hermes
+  name: hermes-execution-mediator-2
+  type: ClusterIP
+  selector:
+    app: hermes-execution-mediator
+    pool-ordinal: '2'
+  ports:
+  - name: mediator
+    port: 9009
+    targetPort: mediator
+    protocol: TCP
+- namespace: hermes
+  name: hermes-execution-pool
+  type: ClusterIP
+  selector:
+    app: hermes-agent
+  ports:
+  - name: http
+    port: 9007
+    targetPort: execution-pool
+    protocol: TCP
+- namespace: hermes
+  name: hermes-execution-worker
+  type: ClusterIP
+  selector:
+    app: hermes-execution-worker
+  ports: []
 - namespace: hermes
   name: hermes-gpu-handoff
   type: ClusterIP
@@ -2254,6 +2381,16 @@ services:
     port: 80
     targetPort: http
     protocol: TCP
+- namespace: hermes-scm
+  name: hermes-scm-broker
+  type: ClusterIP
+  selector:
+    app: hermes-scm-broker
+  ports:
+  - name: http
+    port: 9081
+    targetPort: http
+    protocol: TCP
 - namespace: jellyfin
   name: jellyfin
   type: ClusterIP
@@ -2894,13 +3031,24 @@ http_endpoints:
     namespace: hermes
     service: oauth2-proxy-hermes-chat
     port: http
-    workloads:
+    workloads: &id004
     - kind: Deployment
       name: oauth2-proxy-hermes-chat
   via:
     kind: Ingress
     name: hermes-sites
     source: hermes
+- host: chat.hermes.bstein.dev
+  path: /
+  backend:
+    namespace: hermes
+    service: oauth2-proxy-hermes-chat
+    port: http
+    workloads: *id004
+  via:
+    kind: Ingress
+    name: hermes-sites
+    source: hermes
 - host: ci.bstein.dev
   path: /
   backend:
@@ -3005,7 +3153,7 @@ http_endpoints:
     namespace: comms
     service: matrix-guest-register
     port: 8080
-    workloads: &id005
+    workloads: &id006
     - kind: Deployment
       name: matrix-guest-register
   via:
@@ -3018,7 +3166,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: &id004
+    workloads: &id005
     - kind: Deployment
       name: matrix-authentication-service
   via:
@@ -3031,7 +3179,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3042,7 +3190,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3053,7 +3201,7 @@ http_endpoints:
     namespace: comms
     service: matrix-guest-register
     port: 8080
-    workloads: *id005
+    workloads: *id006
   via:
     kind: Ingress
     name: matrix-routing
@@ -3101,7 +3249,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3145,7 +3293,7 @@ http_endpoints:
     namespace: comms
     service: matrix-guest-register
     port: 8080
-    workloads: *id005
+    workloads: *id006
   via:
     kind: Ingress
     name: matrix-routing
@@ -3156,7 +3304,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3167,7 +3315,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3178,7 +3326,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3189,7 +3337,7 @@ http_endpoints:
     namespace: comms
     service: matrix-guest-register
     port: 8080
-    workloads: *id005
+    workloads: *id006
   via:
     kind: Ingress
     name: matrix-routing
@@ -3367,13 +3515,24 @@ http_endpoints:
     namespace: hermes
     service: oauth2-proxy-hermes-triage
     port: http
-    workloads:
+    workloads: &id007
     - kind: Deployment
       name: oauth2-proxy-hermes-triage
   via:
     kind: Ingress
     name: hermes-sites
     source: hermes
+- host: triage.hermes.bstein.dev
+  path: /
+  backend:
+    namespace: hermes
+    service: oauth2-proxy-hermes-triage
+    port: http
+    workloads: *id007
+  via:
+    kind: Ingress
+    name: hermes-sites
+    source: hermes
 - host: vault.bstein.dev
   path: /
   backend:
@@ -3406,7 +3565,7 @@ http_endpoints:
     namespace: veles
     service: veles-backend
     port: 80
-    workloads: &id006
+    workloads: &id008
     - kind: Deployment
       name: veles-backend
   via:
@@ -3419,7 +3578,7 @@ http_endpoints:
     namespace: veles
     service: veles-backend
     port: 80
-    workloads: *id006
+    workloads: *id008
   via:
     kind: Ingress
     name: veles
@@ -3430,7 +3589,7 @@ http_endpoints:
     namespace: veles
     service: veles-backend
     port: 80
-    workloads: *id006
+    workloads: *id008
   via:
     kind: Ingress
     name: veles
@@ -3448,6 +3607,28 @@ http_endpoints:
     kind: Ingress
     name: wolf
     source: game-stream
+- host: worker.bstein.dev
+  path: /
+  backend:
+    namespace: hermes
+    service: oauth2-proxy-hermes-agent
+    port: http
+    workloads: *id001
+  via:
+    kind: Ingress
+    name: hermes-agent-dashboard
+    source: hermes
+- host: worker.bstein.dev
+  path: /terminal
+  backend:
+    namespace: hermes
+    service: oauth2-proxy-hermes-agent
+    port: http
+    workloads: *id001
+  via:
+    kind: Ingress
+    name: hermes-agent-terminal
+    source: hermes
 helmrelease_host_hints:
   cert-manager:cert-manager/cert-manager:
   - atlas.bstein.dev

knowledge/catalog/metrics.json

@@ -1,4 +1,440 @@
 [
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Weekly Remaining",
+    "panel_id": 1,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_quota_remaining_percent{provider=\"openai\",limit=\"codex\",window=\"seven_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Spark Weekly Remaining",
+    "panel_id": 2,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_quota_remaining_percent{provider=\"openai\",limit=\"gpt-5-3-codex-spark\",window=\"seven_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Claude 5h Remaining",
+    "panel_id": 3,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_quota_remaining_percent{provider=\"anthropic\",window=\"five_hour\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"anthropic\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Claude 7d Remaining",
+    "panel_id": 4,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_quota_remaining_percent{provider=\"anthropic\",window=\"seven_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"anthropic\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Quota Collectors Healthy",
+    "panel_id": 5,
+    "panel_type": "stat",
+    "description": "Successful latest quota fetches. Providers are polled independently every five minutes.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(atlas_ai_quota_fetch_success) or on() vector(0)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Oldest Quota Sample",
+    "panel_id": 6,
+    "panel_type": "stat",
+    "description": "Age of the stalest successful provider quota snapshot.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "max((time() - atlas_ai_quota_last_success_timestamp_seconds) and (atlas_ai_quota_last_success_timestamp_seconds > 0)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Weekly Reset In",
+    "panel_id": 7,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(clamp_min(atlas_ai_quota_reset_timestamp_seconds{provider=\"openai\",limit=\"codex\",window=\"seven_day\"} - time(), 0) and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Claude 5h Reset In",
+    "panel_id": 8,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(clamp_min(atlas_ai_quota_reset_timestamp_seconds{provider=\"anthropic\",window=\"five_hour\"} - time(), 0) and on(provider) (atlas_ai_quota_fetch_success{provider=\"anthropic\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Claude 7d Reset In",
+    "panel_id": 9,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(clamp_min(atlas_ai_quota_reset_timestamp_seconds{provider=\"anthropic\",window=\"seven_day\"} - time(), 0) and on(provider) (atlas_ai_quota_fetch_success{provider=\"anthropic\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Tokens (Latest Day)",
+    "panel_id": 10,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_account_tokens{provider=\"openai\",period=\"latest_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Tokens (7d)",
+    "panel_id": 11,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_account_tokens{provider=\"openai\",period=\"seven_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Switchyard Requests",
+    "panel_id": 12,
+    "panel_type": "stat",
+    "description": "Hosted model requests observed by Switchyard in the selected dashboard range.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(increase(switchyard_requests_total[$__range])) or on() vector(0)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Model Selection Rate",
+    "panel_id": 13,
+    "panel_type": "timeseries",
+    "description": "AUTO and fixed-route decisions by selected provider, model family, and reasoning effort.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum by (selected_model) (rate(switchyard_decisions_total[5m]))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Provider Selections (Range)",
+    "panel_id": 14,
+    "panel_type": "bargauge",
+    "description": "Switchyard selections grouped by provider over the selected dashboard range.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sort_desc(sum by (provider) (label_replace(increase(switchyard_decisions_total{selected_model=~\"(route|worker)/(codex|claude|local)/.*\"}[$__range]), \"provider\", \"$2\", \"selected_model\", \"^(route|worker)/(codex|claude|local)/.*\")))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Token Throughput",
+    "panel_id": 15,
+    "panel_type": "timeseries",
+    "description": "Prompt, cache, reasoning, and completion token rates reported by hosted Switchyard calls.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(rate(switchyard_prompt_tokens_total[5m]))",
+      "sum(rate(switchyard_cached_tokens_total[5m]))",
+      "sum(rate(switchyard_cache_creation_tokens_total[5m]))",
+      "sum(rate(switchyard_reasoning_tokens_total[5m]))",
+      "sum(rate(switchyard_completion_tokens_total[5m]))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Model Call p95 Latency",
+    "panel_id": 16,
+    "panel_type": "timeseries",
+    "description": "95th percentile upstream latency for each selected model route.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "histogram_quantile(0.95, sum by (le, model) (rate(switchyard_model_call_latency_ms_bucket[5m])))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Prompt Cache Share",
+    "panel_id": 17,
+    "panel_type": "stat",
+    "description": "Cached tokens as a share of prompt plus cached tokens; higher generally means less repeated provider work.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "100 * sum(rate(switchyard_cached_tokens_total[5m])) / clamp_min(sum(rate(switchyard_prompt_tokens_total[5m])) + sum(rate(switchyard_cached_tokens_total[5m])), 1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Client Success Rate",
+    "panel_id": 18,
+    "panel_type": "stat",
+    "description": "Successful client-facing Switchyard responses in the selected range.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "100 * sum(increase(switchyard_client_responses_total{outcome=\"success\"}[$__range])) / clamp_min(sum(increase(switchyard_client_responses_total[$__range])), 1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Classifier Fail-Open (Range)",
+    "panel_id": 19,
+    "panel_type": "stat",
+    "description": "Local classifier failures that safely fell back to the conservative hosted route.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(increase(switchyard_classifier_fail_open_total[$__range])) or on() vector(0)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Upstream Errors (Range)",
+    "panel_id": 20,
+    "panel_type": "stat",
+    "description": "Hosted model attempts that returned errors in the selected range.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(increase(switchyard_errors_total[$__range])) or on() vector(0)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Local Classifier Calls",
+    "panel_id": 21,
+    "panel_type": "timeseries",
+    "description": "Local Qwen routing-classifier activity, split by successful and failed calls.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum by (outcome) (rate(switchyard_llm_calls_total{selected_model=~\"qwen.*\"}[5m]))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Routing Overhead p95",
+    "panel_id": 22,
+    "panel_type": "timeseries",
+    "description": "95th percentile time Switchyard spends selecting a model before the upstream call.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "histogram_quantile(0.95, sum by (le, algorithm) (rate(switchyard_routing_overhead_ms_bucket[5m])))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Traffic Lanes (Range)",
+    "panel_id": 23,
+    "panel_type": "bargauge",
+    "description": "Request volume split between interactive route traffic and durable worker traffic.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sort_desc(sum by (lane) (label_replace(increase(switchyard_requests_total{model=~\"(route|worker)/.*\"}[$__range]), \"lane\", \"$1\", \"model\", \"^(route|worker)/.*\")))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Hermes Workload CPU (Attribution Proxy)",
+    "panel_id": 25,
+    "panel_type": "timeseries",
+    "description": "Compute use by Hermes pod/container. Switchyard currently exposes model and worker-vs-route attribution, but not tenant-slot token labels; CPU is clearly marked as a proxy rather than token usage.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum by (pod, container) (rate(container_cpu_usage_seconds_total{namespace=\"hermes\",pod=~\"hermes-(agent|chat-tenant|switchyard|model-gate).*\",container!=\"\",image!=\"\"}[5m]))"
+    ]
+  },
   {
     "dashboard": "Atlas GitOps",
     "panel_title": "Flux Source",

knowledge/diagrams/atlas-http.mmd

@@ -56,6 +56,8 @@ flowchart LR
   host_chat_bstein_dev --> svc_hermes_oauth2_proxy_hermes_chat
   wl_hermes_oauth2_proxy_hermes_chat["hermes/oauth2-proxy-hermes-chat (Deployment)"]
   svc_hermes_oauth2_proxy_hermes_chat --> wl_hermes_oauth2_proxy_hermes_chat
+  host_chat_hermes_bstein_dev["chat.hermes.bstein.dev"]
+  host_chat_hermes_bstein_dev --> svc_hermes_oauth2_proxy_hermes_chat
   host_ci_bstein_dev["ci.bstein.dev"]
   svc_jenkins_jenkins["jenkins/jenkins (Service)"]
   host_ci_bstein_dev --> svc_jenkins_jenkins
@@ -175,6 +177,8 @@ flowchart LR
   host_triage_bstein_dev --> svc_hermes_oauth2_proxy_hermes_triage
   wl_hermes_oauth2_proxy_hermes_triage["hermes/oauth2-proxy-hermes-triage (Deployment)"]
   svc_hermes_oauth2_proxy_hermes_triage --> wl_hermes_oauth2_proxy_hermes_triage
+  host_triage_hermes_bstein_dev["triage.hermes.bstein.dev"]
+  host_triage_hermes_bstein_dev --> svc_hermes_oauth2_proxy_hermes_triage
   host_vault_bstein_dev["vault.bstein.dev"]
   svc_vaultwarden_vaultwarden_service["vaultwarden/vaultwarden-service (Service)"]
   host_vault_bstein_dev --> svc_vaultwarden_vaultwarden_service
@@ -194,6 +198,8 @@ flowchart LR
   host_wolf_bstein_dev --> svc_game_stream_oauth2_proxy_wolf
   wl_game_stream_oauth2_proxy_wolf["game-stream/oauth2-proxy-wolf (Deployment)"]
   svc_game_stream_oauth2_proxy_wolf --> wl_game_stream_oauth2_proxy_wolf
+  host_worker_bstein_dev["worker.bstein.dev"]
+  host_worker_bstein_dev --> svc_hermes_oauth2_proxy_hermes_agent
 
   subgraph bstein_dev_home[bstein-dev-home]
     svc_bstein_dev_home_bstein_dev_home_frontend

knowledge/runbooks/hermes-triage-demo.md

@@ -99,7 +99,7 @@ in-process call removed a whole pod launch from the critical path.
   `hermes-demo-test-<N>` (failed) and `hermes-demo-repair-<N>` (succeeded);
   both TTL-clean after 1 h.
 - Hermes side: the run appears in the dashboard at
-  `https://agent.hermes.bstein.dev` (session/run history).
+  `https://worker.bstein.dev` (session/run history).
 - Escalation path: alert `HermesTriageHumanRequired` in vmalert
   (`vmalert-atlas-availability` deployment, 1 m interval, `for: 2m`)
   fires to Alertmanager for any `human_required` incident. Gauges are

scripts/ops/hermes_triage_monitor.py

@@ -40,7 +40,7 @@ JENKINS = os.environ.get("JENKINS_URL", "https://ci.bstein.dev")
 GITEA = os.environ.get("GITEA_URL", "https://scm.bstein.dev")
 CODE_REPO_OWNER = os.environ.get("CODE_REPO_OWNER", "atlas")
 GRAFANA = os.environ.get("GRAFANA_URL", "https://metrics.bstein.dev")
-HERMES_UI = os.environ.get("HERMES_URL", "https://agent.hermes.bstein.dev")
+HERMES_UI = os.environ.get("HERMES_URL", "https://worker.bstein.dev")
 POLL_SECONDS = 6
 
 # `--filter <text>` restricts the monitor to incidents whose id contains that

services/comms/knowledge/catalog/atlas-summary.json

@@ -1,8 +1,8 @@
 {
   "counts": {
     "helmrelease_host_hints": 23,
-    "http_endpoints": 61,
+    "http_endpoints": 65,
-    "services": 91,
+    "services": 98,
-    "workloads": 125
+    "workloads": 130
   }
 }

services/comms/knowledge/catalog/atlas.json

@@ -106,6 +106,31 @@
       "path": "services/hermes-chat",
       "targetNamespace": "hermes-chat"
     },
+    {
+      "name": "hermes-observer-bindings",
+      "path": "services/hermes-observer-bindings",
+      "targetNamespace": null
+    },
+    {
+      "name": "hermes-observer-rbac",
+      "path": "services/hermes-observer-rbac",
+      "targetNamespace": null
+    },
+    {
+      "name": "hermes-scm-broker",
+      "path": "services/hermes-scm-broker",
+      "targetNamespace": "hermes-scm"
+    },
+    {
+      "name": "hermes-scm-broker-code",
+      "path": "services/hermes/scm-common",
+      "targetNamespace": "hermes-scm"
+    },
+    {
+      "name": "hermes-scm-namespace",
+      "path": "services/hermes-scm-namespace",
+      "targetNamespace": null
+    },
     {
       "name": "hermes-triage-demo",
       "path": "services/hermes-triage-demo",
@@ -251,6 +276,11 @@
       "path": "infrastructure/vault-csi",
       "targetNamespace": "kube-system"
     },
+    {
+      "name": "vault-hermes-jenkins-token-seed",
+      "path": "services/vault-hermes-jenkins-token-seed",
+      "targetNamespace": "vault"
+    },
     {
       "name": "vault-injector",
       "path": "infrastructure/vault-injector",
@@ -304,7 +334,7 @@
         "node-role.kubernetes.io/worker": "true"
       },
       "images": [
-        "registry.bstein.dev/bstein/bstein-dev-home-backend:0.1.1-464"
+        "registry.bstein.dev/bstein/bstein-dev-home-backend:0.1.1-479"
       ]
     },
     {
@@ -320,7 +350,7 @@
         "node-role.kubernetes.io/worker": "true"
       },
       "images": [
-        "registry.bstein.dev/bstein/bstein-dev-home-frontend:0.1.1-464"
+        "registry.bstein.dev/bstein/bstein-dev-home-frontend:0.1.1-479"
       ]
     },
     {
@@ -902,7 +932,7 @@
       "serviceAccountName": "hermes-node-ssh-access",
       "nodeSelector": {},
       "images": [
-        "busybox:1.37"
+        "python@sha256:6d43704baacd1bfbe7c295d7f13079d5d8104ed33568873133f8fc69980419df"
       ]
     },
     {
@@ -915,8 +945,8 @@
       "serviceAccountName": "hermes-triage",
       "nodeSelector": {},
       "images": [
-        "registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8",
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37",
-        "registry.bstein.dev/bstein/hermes-webui@sha256:9c2fe8341c7b650e08d10acead3151b19e2af737863268bafb39b3d9517575b1"
+        "registry.bstein.dev/bstein/hermes-webui@sha256:ac6ba7bfd8a86227f31a9a96ebea41227ccf70391f7dcf34206f4d58e835e50e"
       ]
     },
     {
@@ -930,7 +960,7 @@
       "nodeSelector": {},
       "images": [
         "quay.io/oauth2-proxy/oauth2-proxy:v7.15.3@sha256:10a1165743a192e1940b4708fb9647027185ce11a681a1c5519b442ff7f1f561",
-        "registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8"
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
       ]
     },
     {
@@ -943,7 +973,7 @@
       "serviceAccountName": "hermes-chat",
       "nodeSelector": {},
       "images": [
-        "registry.bstein.dev/bstein/hermes-chat-router@sha256:a4010fdc5b6dce2696e6fec06eb38a3992817faa01ff3472122c870038b22bd2"
+        "registry.bstein.dev/bstein/hermes-chat-router@sha256:6744cb7b87c6050f1b97c0675cd280b8295b3b5826ba1d6d92e37aee6fd0b8c4"
       ]
     },
     {
@@ -1058,6 +1088,48 @@
         "registry.bstein.dev/bstein/hermes-chat-sandbox@sha256:17ee62b8e61c08573a3a8cca903b38ec43800cb44ec29340e1bc095176544bca"
       ]
     },
+    {
+      "kind": "Deployment",
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-0",
+      "labels": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "0"
+      },
+      "serviceAccountName": "hermes-execution-worker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
+      ]
+    },
+    {
+      "kind": "Deployment",
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-1",
+      "labels": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "1"
+      },
+      "serviceAccountName": "hermes-execution-worker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
+      ]
+    },
+    {
+      "kind": "Deployment",
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-2",
+      "labels": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "2"
+      },
+      "serviceAccountName": "hermes-execution-worker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
+      ]
+    },
     {
       "kind": "Deployment",
       "namespace": "hermes",
@@ -1177,8 +1249,36 @@
       "serviceAccountName": "hermes-chat",
       "nodeSelector": {},
       "images": [
-        "registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8",
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37",
-        "registry.bstein.dev/bstein/hermes-webui@sha256:9c2fe8341c7b650e08d10acead3151b19e2af737863268bafb39b3d9517575b1"
+        "registry.bstein.dev/bstein/hermes-webui@sha256:c276a9e17c9057237472f39640c9ebac9d4359d9f62a34df52a759eef43167bf"
+      ]
+    },
+    {
+      "kind": "StatefulSet",
+      "namespace": "hermes",
+      "name": "hermes-execution-worker",
+      "labels": {
+        "app": "hermes-execution-worker",
+        "app.kubernetes.io/name": "hermes-execution-worker",
+        "app.kubernetes.io/part-of": "hermes"
+      },
+      "serviceAccountName": "hermes-execution-worker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37"
+      ]
+    },
+    {
+      "kind": "Deployment",
+      "namespace": "hermes-scm",
+      "name": "hermes-scm-broker",
+      "labels": {
+        "app": "hermes-scm-broker"
+      },
+      "serviceAccountName": "hermes-scm-broker",
+      "nodeSelector": {},
+      "images": [
+        "registry.bstein.dev/bstein/hermes-agent@sha256:37ebf720c783ae908a602916ffccf88d43d205a157957f5dc4b487867aee45e7"
       ]
     },
     {
@@ -1528,7 +1628,7 @@
         "kubernetes.io/os": "linux"
       },
       "images": [
-        "registry.bstein.dev/bstein/metis-sentinel:0.1.0-293-amd64"
+        "registry.bstein.dev/bstein/metis-sentinel:0.1.0-304-amd64"
       ]
     },
     {
@@ -1544,7 +1644,7 @@
         "kubernetes.io/os": "linux"
       },
       "images": [
-        "registry.bstein.dev/bstein/metis-sentinel:0.1.0-293-arm64"
+        "registry.bstein.dev/bstein/metis-sentinel:0.1.0-304-arm64"
       ]
     },
     {
@@ -1633,7 +1733,7 @@
         "node-role.kubernetes.io/worker": "true"
       },
       "images": [
-        "registry.bstein.dev/bstein/ariadne:0.1.0-454"
+        "registry.bstein.dev/bstein/ariadne:0.1.0-464"
       ]
     },
     {
@@ -1661,7 +1761,7 @@
       "serviceAccountName": "metis",
       "nodeSelector": {},
       "images": [
-        "registry.bstein.dev/bstein/metis:0.1.0-293-arm64"
+        "registry.bstein.dev/bstein/metis:0.1.0-304-arm64"
       ]
     },
     {
@@ -3179,6 +3279,22 @@
         }
       ]
     },
+    {
+      "namespace": "hermes",
+      "name": "hermes-cli-lane-metrics",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-agent"
+      },
+      "ports": [
+        {
+          "name": "lane-metrics",
+          "port": 9011,
+          "targetPort": "lane-metrics",
+          "protocol": "TCP"
+        }
+      ]
+    },
     {
       "namespace": "hermes",
       "name": "hermes-codex-broker",
@@ -3195,6 +3311,82 @@
         }
       ]
     },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-0",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "0"
+      },
+      "ports": [
+        {
+          "name": "mediator",
+          "port": 9009,
+          "targetPort": "mediator",
+          "protocol": "TCP"
+        }
+      ]
+    },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-1",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "1"
+      },
+      "ports": [
+        {
+          "name": "mediator",
+          "port": 9009,
+          "targetPort": "mediator",
+          "protocol": "TCP"
+        }
+      ]
+    },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-mediator-2",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-execution-mediator",
+        "pool-ordinal": "2"
+      },
+      "ports": [
+        {
+          "name": "mediator",
+          "port": 9009,
+          "targetPort": "mediator",
+          "protocol": "TCP"
+        }
+      ]
+    },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-pool",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-agent"
+      },
+      "ports": [
+        {
+          "name": "http",
+          "port": 9007,
+          "targetPort": "execution-pool",
+          "protocol": "TCP"
+        }
+      ]
+    },
+    {
+      "namespace": "hermes",
+      "name": "hermes-execution-worker",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-execution-worker"
+      },
+      "ports": []
+    },
     {
       "namespace": "hermes",
       "name": "hermes-gpu-handoff",
@@ -3393,6 +3585,22 @@
         }
       ]
     },
+    {
+      "namespace": "hermes-scm",
+      "name": "hermes-scm-broker",
+      "type": "ClusterIP",
+      "selector": {
+        "app": "hermes-scm-broker"
+      },
+      "ports": [
+        {
+          "name": "http",
+          "port": 9081,
+          "targetPort": "http",
+          "protocol": "TCP"
+        }
+      ]
+    },
     {
       "namespace": "jellyfin",
       "name": "jellyfin",
@@ -4423,6 +4631,26 @@
         "source": "hermes"
       }
     },
+    {
+      "host": "chat.hermes.bstein.dev",
+      "path": "/",
+      "backend": {
+        "namespace": "hermes",
+        "service": "oauth2-proxy-hermes-chat",
+        "port": "http",
+        "workloads": [
+          {
+            "kind": "Deployment",
+            "name": "oauth2-proxy-hermes-chat"
+          }
+        ]
+      },
+      "via": {
+        "kind": "Ingress",
+        "name": "hermes-sites",
+        "source": "hermes"
+      }
+    },
     {
       "host": "ci.bstein.dev",
       "path": "/",
@@ -5183,6 +5411,26 @@
         "source": "hermes"
       }
     },
+    {
+      "host": "triage.hermes.bstein.dev",
+      "path": "/",
+      "backend": {
+        "namespace": "hermes",
+        "service": "oauth2-proxy-hermes-triage",
+        "port": "http",
+        "workloads": [
+          {
+            "kind": "Deployment",
+            "name": "oauth2-proxy-hermes-triage"
+          }
+        ]
+      },
+      "via": {
+        "kind": "Ingress",
+        "name": "hermes-sites",
+        "source": "hermes"
+      }
+    },
     {
       "host": "vault.bstein.dev",
       "path": "/",
@@ -5302,6 +5550,46 @@
         "name": "wolf",
         "source": "game-stream"
       }
+    },
+    {
+      "host": "worker.bstein.dev",
+      "path": "/",
+      "backend": {
+        "namespace": "hermes",
+        "service": "oauth2-proxy-hermes-agent",
+        "port": "http",
+        "workloads": [
+          {
+            "kind": "Deployment",
+            "name": "hermes-agent"
+          }
+        ]
+      },
+      "via": {
+        "kind": "Ingress",
+        "name": "hermes-agent-dashboard",
+        "source": "hermes"
+      }
+    },
+    {
+      "host": "worker.bstein.dev",
+      "path": "/terminal",
+      "backend": {
+        "namespace": "hermes",
+        "service": "oauth2-proxy-hermes-agent",
+        "port": "http",
+        "workloads": [
+          {
+            "kind": "Deployment",
+            "name": "hermes-agent"
+          }
+        ]
+      },
+      "via": {
+        "kind": "Ingress",
+        "name": "hermes-agent-terminal",
+        "source": "hermes"
+      }
     }
   ],
   "helmrelease_host_hints": {

services/comms/knowledge/catalog/atlas.yaml

@@ -65,6 +65,21 @@ sources:
 - name: hermes-chat
   path: services/hermes-chat
   targetNamespace: hermes-chat
+- name: hermes-observer-bindings
+  path: services/hermes-observer-bindings
+  targetNamespace: null
+- name: hermes-observer-rbac
+  path: services/hermes-observer-rbac
+  targetNamespace: null
+- name: hermes-scm-broker
+  path: services/hermes-scm-broker
+  targetNamespace: hermes-scm
+- name: hermes-scm-broker-code
+  path: services/hermes/scm-common
+  targetNamespace: hermes-scm
+- name: hermes-scm-namespace
+  path: services/hermes-scm-namespace
+  targetNamespace: null
 - name: hermes-triage-demo
   path: services/hermes-triage-demo
   targetNamespace: null
@@ -152,6 +167,9 @@ sources:
 - name: vault-csi
   path: infrastructure/vault-csi
   targetNamespace: kube-system
+- name: vault-hermes-jenkins-token-seed
+  path: services/vault-hermes-jenkins-token-seed
+  targetNamespace: vault
 - name: vault-injector
   path: infrastructure/vault-injector
   targetNamespace: vault
@@ -187,7 +205,7 @@ workloads:
     kubernetes.io/arch: arm64
     node-role.kubernetes.io/worker: 'true'
   images:
-  - registry.bstein.dev/bstein/bstein-dev-home-backend:0.1.1-464
+  - registry.bstein.dev/bstein/bstein-dev-home-backend:0.1.1-479
 - kind: Deployment
   namespace: bstein-dev-home
   name: bstein-dev-home-frontend
@@ -198,7 +216,7 @@ workloads:
     kubernetes.io/arch: arm64
     node-role.kubernetes.io/worker: 'true'
   images:
-  - registry.bstein.dev/bstein/bstein-dev-home-frontend:0.1.1-464
+  - registry.bstein.dev/bstein/bstein-dev-home-frontend:0.1.1-479
 - kind: Deployment
   namespace: bstein-dev-home
   name: bstein-dev-home-vault-sync
@@ -604,7 +622,7 @@ workloads:
   serviceAccountName: hermes-node-ssh-access
   nodeSelector: {}
   images:
-  - busybox:1.37
+  - python@sha256:6d43704baacd1bfbe7c295d7f13079d5d8104ed33568873133f8fc69980419df
 - kind: Deployment
   namespace: hermes
   name: hermes
@@ -613,8 +631,8 @@ workloads:
   serviceAccountName: hermes-triage
   nodeSelector: {}
   images:
-  - registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
-  - registry.bstein.dev/bstein/hermes-webui@sha256:9c2fe8341c7b650e08d10acead3151b19e2af737863268bafb39b3d9517575b1
+  - registry.bstein.dev/bstein/hermes-webui@sha256:ac6ba7bfd8a86227f31a9a96ebea41227ccf70391f7dcf34206f4d58e835e50e
 - kind: Deployment
   namespace: hermes
   name: hermes-agent
@@ -624,7 +642,7 @@ workloads:
   nodeSelector: {}
   images:
   - quay.io/oauth2-proxy/oauth2-proxy:v7.15.3@sha256:10a1165743a192e1940b4708fb9647027185ce11a681a1c5519b442ff7f1f561
-  - registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
 - kind: Deployment
   namespace: hermes
   name: hermes-chat-router
@@ -633,7 +651,7 @@ workloads:
   serviceAccountName: hermes-chat
   nodeSelector: {}
   images:
-  - registry.bstein.dev/bstein/hermes-chat-router@sha256:a4010fdc5b6dce2696e6fec06eb38a3992817faa01ff3472122c870038b22bd2
+  - registry.bstein.dev/bstein/hermes-chat-router@sha256:6744cb7b87c6050f1b97c0675cd280b8295b3b5826ba1d6d92e37aee6fd0b8c4
 - kind: Deployment
   namespace: hermes
   name: hermes-chat-sandbox-0
@@ -714,6 +732,36 @@ workloads:
   nodeSelector: {}
   images:
   - registry.bstein.dev/bstein/hermes-chat-sandbox@sha256:17ee62b8e61c08573a3a8cca903b38ec43800cb44ec29340e1bc095176544bca
+- kind: Deployment
+  namespace: hermes
+  name: hermes-execution-mediator-0
+  labels:
+    app: hermes-execution-mediator
+    pool-ordinal: '0'
+  serviceAccountName: hermes-execution-worker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
+- kind: Deployment
+  namespace: hermes
+  name: hermes-execution-mediator-1
+  labels:
+    app: hermes-execution-mediator
+    pool-ordinal: '1'
+  serviceAccountName: hermes-execution-worker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
+- kind: Deployment
+  namespace: hermes
+  name: hermes-execution-mediator-2
+  labels:
+    app: hermes-execution-mediator
+    pool-ordinal: '2'
+  serviceAccountName: hermes-execution-worker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
 - kind: Deployment
   namespace: hermes
   name: hermes-local-image
@@ -797,8 +845,28 @@ workloads:
   serviceAccountName: hermes-chat
   nodeSelector: {}
   images:
-  - registry.bstein.dev/bstein/hermes-agent@sha256:cce1f65dc7d30fdce4b1748cc7d3434b9761ae9946a8c8be6049204c503d60a8
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
-  - registry.bstein.dev/bstein/hermes-webui@sha256:9c2fe8341c7b650e08d10acead3151b19e2af737863268bafb39b3d9517575b1
+  - registry.bstein.dev/bstein/hermes-webui@sha256:c276a9e17c9057237472f39640c9ebac9d4359d9f62a34df52a759eef43167bf
+- kind: StatefulSet
+  namespace: hermes
+  name: hermes-execution-worker
+  labels:
+    app: hermes-execution-worker
+    app.kubernetes.io/name: hermes-execution-worker
+    app.kubernetes.io/part-of: hermes
+  serviceAccountName: hermes-execution-worker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:4a385fbd04ae1e3e8ca0237db98a318606a2a03786ef467757b8da5eee4e4b37
+- kind: Deployment
+  namespace: hermes-scm
+  name: hermes-scm-broker
+  labels:
+    app: hermes-scm-broker
+  serviceAccountName: hermes-scm-broker
+  nodeSelector: {}
+  images:
+  - registry.bstein.dev/bstein/hermes-agent@sha256:37ebf720c783ae908a602916ffccf88d43d205a157957f5dc4b487867aee45e7
 - kind: Deployment
   namespace: jellyfin
   name: jellyfin
@@ -1037,7 +1105,7 @@ workloads:
     kubernetes.io/arch: amd64
     kubernetes.io/os: linux
   images:
-  - registry.bstein.dev/bstein/metis-sentinel:0.1.0-293-amd64
+  - registry.bstein.dev/bstein/metis-sentinel:0.1.0-304-amd64
 - kind: DaemonSet
   namespace: maintenance
   name: metis-sentinel-arm64
@@ -1048,7 +1116,7 @@ workloads:
     kubernetes.io/arch: arm64
     kubernetes.io/os: linux
   images:
-  - registry.bstein.dev/bstein/metis-sentinel:0.1.0-293-arm64
+  - registry.bstein.dev/bstein/metis-sentinel:0.1.0-304-arm64
 - kind: DaemonSet
   namespace: maintenance
   name: node-image-sweeper
@@ -1108,7 +1176,7 @@ workloads:
     kubernetes.io/arch: arm64
     node-role.kubernetes.io/worker: 'true'
   images:
-  - registry.bstein.dev/bstein/ariadne:0.1.0-454
+  - registry.bstein.dev/bstein/ariadne:0.1.0-464
 - kind: Deployment
   namespace: maintenance
   name: maintenance-vault-sync
@@ -1127,7 +1195,7 @@ workloads:
   serviceAccountName: metis
   nodeSelector: {}
   images:
-  - registry.bstein.dev/bstein/metis:0.1.0-293-arm64
+  - registry.bstein.dev/bstein/metis:0.1.0-304-arm64
 - kind: Deployment
   namespace: maintenance
   name: oauth2-proxy-metis
@@ -2120,6 +2188,16 @@ services:
     port: 9006
     targetPort: claude-broker
     protocol: TCP
+- namespace: hermes
+  name: hermes-cli-lane-metrics
+  type: ClusterIP
+  selector:
+    app: hermes-agent
+  ports:
+  - name: lane-metrics
+    port: 9011
+    targetPort: lane-metrics
+    protocol: TCP
 - namespace: hermes
   name: hermes-codex-broker
   type: ClusterIP
@@ -2130,6 +2208,55 @@ services:
     port: 9003
     targetPort: codex-broker
     protocol: TCP
+- namespace: hermes
+  name: hermes-execution-mediator-0
+  type: ClusterIP
+  selector:
+    app: hermes-execution-mediator
+    pool-ordinal: '0'
+  ports:
+  - name: mediator
+    port: 9009
+    targetPort: mediator
+    protocol: TCP
+- namespace: hermes
+  name: hermes-execution-mediator-1
+  type: ClusterIP
+  selector:
+    app: hermes-execution-mediator
+    pool-ordinal: '1'
+  ports:
+  - name: mediator
+    port: 9009
+    targetPort: mediator
+    protocol: TCP
+- namespace: hermes
+  name: hermes-execution-mediator-2
+  type: ClusterIP
+  selector:
+    app: hermes-execution-mediator
+    pool-ordinal: '2'
+  ports:
+  - name: mediator
+    port: 9009
+    targetPort: mediator
+    protocol: TCP
+- namespace: hermes
+  name: hermes-execution-pool
+  type: ClusterIP
+  selector:
+    app: hermes-agent
+  ports:
+  - name: http
+    port: 9007
+    targetPort: execution-pool
+    protocol: TCP
+- namespace: hermes
+  name: hermes-execution-worker
+  type: ClusterIP
+  selector:
+    app: hermes-execution-worker
+  ports: []
 - namespace: hermes
   name: hermes-gpu-handoff
   type: ClusterIP
@@ -2254,6 +2381,16 @@ services:
     port: 80
     targetPort: http
     protocol: TCP
+- namespace: hermes-scm
+  name: hermes-scm-broker
+  type: ClusterIP
+  selector:
+    app: hermes-scm-broker
+  ports:
+  - name: http
+    port: 9081
+    targetPort: http
+    protocol: TCP
 - namespace: jellyfin
   name: jellyfin
   type: ClusterIP
@@ -2894,13 +3031,24 @@ http_endpoints:
     namespace: hermes
     service: oauth2-proxy-hermes-chat
     port: http
-    workloads:
+    workloads: &id004
     - kind: Deployment
       name: oauth2-proxy-hermes-chat
   via:
     kind: Ingress
     name: hermes-sites
     source: hermes
+- host: chat.hermes.bstein.dev
+  path: /
+  backend:
+    namespace: hermes
+    service: oauth2-proxy-hermes-chat
+    port: http
+    workloads: *id004
+  via:
+    kind: Ingress
+    name: hermes-sites
+    source: hermes
 - host: ci.bstein.dev
   path: /
   backend:
@@ -3005,7 +3153,7 @@ http_endpoints:
     namespace: comms
     service: matrix-guest-register
     port: 8080
-    workloads: &id005
+    workloads: &id006
     - kind: Deployment
       name: matrix-guest-register
   via:
@@ -3018,7 +3166,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: &id004
+    workloads: &id005
     - kind: Deployment
       name: matrix-authentication-service
   via:
@@ -3031,7 +3179,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3042,7 +3190,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3053,7 +3201,7 @@ http_endpoints:
     namespace: comms
     service: matrix-guest-register
     port: 8080
-    workloads: *id005
+    workloads: *id006
   via:
     kind: Ingress
     name: matrix-routing
@@ -3101,7 +3249,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3145,7 +3293,7 @@ http_endpoints:
     namespace: comms
     service: matrix-guest-register
     port: 8080
-    workloads: *id005
+    workloads: *id006
   via:
     kind: Ingress
     name: matrix-routing
@@ -3156,7 +3304,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3167,7 +3315,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3178,7 +3326,7 @@ http_endpoints:
     namespace: comms
     service: matrix-authentication-service
     port: 8080
-    workloads: *id004
+    workloads: *id005
   via:
     kind: Ingress
     name: matrix-routing
@@ -3189,7 +3337,7 @@ http_endpoints:
     namespace: comms
     service: matrix-guest-register
     port: 8080
-    workloads: *id005
+    workloads: *id006
   via:
     kind: Ingress
     name: matrix-routing
@@ -3367,13 +3515,24 @@ http_endpoints:
     namespace: hermes
     service: oauth2-proxy-hermes-triage
     port: http
-    workloads:
+    workloads: &id007
     - kind: Deployment
       name: oauth2-proxy-hermes-triage
   via:
     kind: Ingress
     name: hermes-sites
     source: hermes
+- host: triage.hermes.bstein.dev
+  path: /
+  backend:
+    namespace: hermes
+    service: oauth2-proxy-hermes-triage
+    port: http
+    workloads: *id007
+  via:
+    kind: Ingress
+    name: hermes-sites
+    source: hermes
 - host: vault.bstein.dev
   path: /
   backend:
@@ -3406,7 +3565,7 @@ http_endpoints:
     namespace: veles
     service: veles-backend
     port: 80
-    workloads: &id006
+    workloads: &id008
     - kind: Deployment
       name: veles-backend
   via:
@@ -3419,7 +3578,7 @@ http_endpoints:
     namespace: veles
     service: veles-backend
     port: 80
-    workloads: *id006
+    workloads: *id008
   via:
     kind: Ingress
     name: veles
@@ -3430,7 +3589,7 @@ http_endpoints:
     namespace: veles
     service: veles-backend
     port: 80
-    workloads: *id006
+    workloads: *id008
   via:
     kind: Ingress
     name: veles
@@ -3448,6 +3607,28 @@ http_endpoints:
     kind: Ingress
     name: wolf
     source: game-stream
+- host: worker.bstein.dev
+  path: /
+  backend:
+    namespace: hermes
+    service: oauth2-proxy-hermes-agent
+    port: http
+    workloads: *id001
+  via:
+    kind: Ingress
+    name: hermes-agent-dashboard
+    source: hermes
+- host: worker.bstein.dev
+  path: /terminal
+  backend:
+    namespace: hermes
+    service: oauth2-proxy-hermes-agent
+    port: http
+    workloads: *id001
+  via:
+    kind: Ingress
+    name: hermes-agent-terminal
+    source: hermes
 helmrelease_host_hints:
   cert-manager:cert-manager/cert-manager:
   - atlas.bstein.dev

services/comms/knowledge/catalog/metrics.json

@@ -1,4 +1,440 @@
 [
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Weekly Remaining",
+    "panel_id": 1,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_quota_remaining_percent{provider=\"openai\",limit=\"codex\",window=\"seven_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Spark Weekly Remaining",
+    "panel_id": 2,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_quota_remaining_percent{provider=\"openai\",limit=\"gpt-5-3-codex-spark\",window=\"seven_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Claude 5h Remaining",
+    "panel_id": 3,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_quota_remaining_percent{provider=\"anthropic\",window=\"five_hour\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"anthropic\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Claude 7d Remaining",
+    "panel_id": 4,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_quota_remaining_percent{provider=\"anthropic\",window=\"seven_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"anthropic\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Quota Collectors Healthy",
+    "panel_id": 5,
+    "panel_type": "stat",
+    "description": "Successful latest quota fetches. Providers are polled independently every five minutes.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(atlas_ai_quota_fetch_success) or on() vector(0)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Oldest Quota Sample",
+    "panel_id": 6,
+    "panel_type": "stat",
+    "description": "Age of the stalest successful provider quota snapshot.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "max((time() - atlas_ai_quota_last_success_timestamp_seconds) and (atlas_ai_quota_last_success_timestamp_seconds > 0)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Weekly Reset In",
+    "panel_id": 7,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(clamp_min(atlas_ai_quota_reset_timestamp_seconds{provider=\"openai\",limit=\"codex\",window=\"seven_day\"} - time(), 0) and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Claude 5h Reset In",
+    "panel_id": 8,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(clamp_min(atlas_ai_quota_reset_timestamp_seconds{provider=\"anthropic\",window=\"five_hour\"} - time(), 0) and on(provider) (atlas_ai_quota_fetch_success{provider=\"anthropic\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Claude 7d Reset In",
+    "panel_id": 9,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(clamp_min(atlas_ai_quota_reset_timestamp_seconds{provider=\"anthropic\",window=\"seven_day\"} - time(), 0) and on(provider) (atlas_ai_quota_fetch_success{provider=\"anthropic\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Tokens (Latest Day)",
+    "panel_id": 10,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_account_tokens{provider=\"openai\",period=\"latest_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Codex Tokens (7d)",
+    "panel_id": 11,
+    "panel_type": "stat",
+    "description": "Live first-party CLI account telemetry. Unavailable means the provider did not return a fresh structured value.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "(atlas_ai_account_tokens{provider=\"openai\",period=\"seven_day\"} and on(provider) (atlas_ai_quota_fetch_success{provider=\"openai\"} == 1)) or on() vector(-1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Switchyard Requests",
+    "panel_id": 12,
+    "panel_type": "stat",
+    "description": "Hosted model requests observed by Switchyard in the selected dashboard range.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(increase(switchyard_requests_total[$__range])) or on() vector(0)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Model Selection Rate",
+    "panel_id": 13,
+    "panel_type": "timeseries",
+    "description": "AUTO and fixed-route decisions by selected provider, model family, and reasoning effort.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum by (selected_model) (rate(switchyard_decisions_total[5m]))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Provider Selections (Range)",
+    "panel_id": 14,
+    "panel_type": "bargauge",
+    "description": "Switchyard selections grouped by provider over the selected dashboard range.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sort_desc(sum by (provider) (label_replace(increase(switchyard_decisions_total{selected_model=~\"(route|worker)/(codex|claude|local)/.*\"}[$__range]), \"provider\", \"$2\", \"selected_model\", \"^(route|worker)/(codex|claude|local)/.*\")))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Token Throughput",
+    "panel_id": 15,
+    "panel_type": "timeseries",
+    "description": "Prompt, cache, reasoning, and completion token rates reported by hosted Switchyard calls.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(rate(switchyard_prompt_tokens_total[5m]))",
+      "sum(rate(switchyard_cached_tokens_total[5m]))",
+      "sum(rate(switchyard_cache_creation_tokens_total[5m]))",
+      "sum(rate(switchyard_reasoning_tokens_total[5m]))",
+      "sum(rate(switchyard_completion_tokens_total[5m]))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Model Call p95 Latency",
+    "panel_id": 16,
+    "panel_type": "timeseries",
+    "description": "95th percentile upstream latency for each selected model route.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "histogram_quantile(0.95, sum by (le, model) (rate(switchyard_model_call_latency_ms_bucket[5m])))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Prompt Cache Share",
+    "panel_id": 17,
+    "panel_type": "stat",
+    "description": "Cached tokens as a share of prompt plus cached tokens; higher generally means less repeated provider work.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "100 * sum(rate(switchyard_cached_tokens_total[5m])) / clamp_min(sum(rate(switchyard_prompt_tokens_total[5m])) + sum(rate(switchyard_cached_tokens_total[5m])), 1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Client Success Rate",
+    "panel_id": 18,
+    "panel_type": "stat",
+    "description": "Successful client-facing Switchyard responses in the selected range.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "100 * sum(increase(switchyard_client_responses_total{outcome=\"success\"}[$__range])) / clamp_min(sum(increase(switchyard_client_responses_total[$__range])), 1)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Classifier Fail-Open (Range)",
+    "panel_id": 19,
+    "panel_type": "stat",
+    "description": "Local classifier failures that safely fell back to the conservative hosted route.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(increase(switchyard_classifier_fail_open_total[$__range])) or on() vector(0)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Upstream Errors (Range)",
+    "panel_id": 20,
+    "panel_type": "stat",
+    "description": "Hosted model attempts that returned errors in the selected range.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum(increase(switchyard_errors_total[$__range])) or on() vector(0)"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Local Classifier Calls",
+    "panel_id": 21,
+    "panel_type": "timeseries",
+    "description": "Local Qwen routing-classifier activity, split by successful and failed calls.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum by (outcome) (rate(switchyard_llm_calls_total{selected_model=~\"qwen.*\"}[5m]))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Routing Overhead p95",
+    "panel_id": 22,
+    "panel_type": "timeseries",
+    "description": "95th percentile time Switchyard spends selecting a model before the upstream call.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "histogram_quantile(0.95, sum by (le, algorithm) (rate(switchyard_routing_overhead_ms_bucket[5m])))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Traffic Lanes (Range)",
+    "panel_id": 23,
+    "panel_type": "bargauge",
+    "description": "Request volume split between interactive route traffic and durable worker traffic.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sort_desc(sum by (lane) (label_replace(increase(switchyard_requests_total{model=~\"(route|worker)/.*\"}[$__range]), \"lane\", \"$1\", \"model\", \"^(route|worker)/.*\")))"
+    ]
+  },
+  {
+    "dashboard": "Atlas AI Operations",
+    "panel_title": "Hermes Workload CPU (Attribution Proxy)",
+    "panel_id": 25,
+    "panel_type": "timeseries",
+    "description": "Compute use by Hermes pod/container. Switchyard currently exposes model and worker-vs-route attribution, but not tenant-slot token labels; CPU is clearly marked as a proxy rather than token usage.",
+    "tags": [
+      "atlas",
+      "ai",
+      "hermes",
+      "switchyard"
+    ],
+    "datasource_uid": "atlas-vm",
+    "datasource_type": "prometheus",
+    "exprs": [
+      "sum by (pod, container) (rate(container_cpu_usage_seconds_total{namespace=\"hermes\",pod=~\"hermes-(agent|chat-tenant|switchyard|model-gate).*\",container!=\"\",image!=\"\"}[5m]))"
+    ]
+  },
   {
     "dashboard": "Atlas GitOps",
     "panel_title": "Flux Source",

services/comms/knowledge/diagrams/atlas-http.mmd

@@ -56,6 +56,8 @@ flowchart LR
   host_chat_bstein_dev --> svc_hermes_oauth2_proxy_hermes_chat
   wl_hermes_oauth2_proxy_hermes_chat["hermes/oauth2-proxy-hermes-chat (Deployment)"]
   svc_hermes_oauth2_proxy_hermes_chat --> wl_hermes_oauth2_proxy_hermes_chat
+  host_chat_hermes_bstein_dev["chat.hermes.bstein.dev"]
+  host_chat_hermes_bstein_dev --> svc_hermes_oauth2_proxy_hermes_chat
   host_ci_bstein_dev["ci.bstein.dev"]
   svc_jenkins_jenkins["jenkins/jenkins (Service)"]
   host_ci_bstein_dev --> svc_jenkins_jenkins
@@ -175,6 +177,8 @@ flowchart LR
   host_triage_bstein_dev --> svc_hermes_oauth2_proxy_hermes_triage
   wl_hermes_oauth2_proxy_hermes_triage["hermes/oauth2-proxy-hermes-triage (Deployment)"]
   svc_hermes_oauth2_proxy_hermes_triage --> wl_hermes_oauth2_proxy_hermes_triage
+  host_triage_hermes_bstein_dev["triage.hermes.bstein.dev"]
+  host_triage_hermes_bstein_dev --> svc_hermes_oauth2_proxy_hermes_triage
   host_vault_bstein_dev["vault.bstein.dev"]
   svc_vaultwarden_vaultwarden_service["vaultwarden/vaultwarden-service (Service)"]
   host_vault_bstein_dev --> svc_vaultwarden_vaultwarden_service
@@ -194,6 +198,8 @@ flowchart LR
   host_wolf_bstein_dev --> svc_game_stream_oauth2_proxy_wolf
   wl_game_stream_oauth2_proxy_wolf["game-stream/oauth2-proxy-wolf (Deployment)"]
   svc_game_stream_oauth2_proxy_wolf --> wl_game_stream_oauth2_proxy_wolf
+  host_worker_bstein_dev["worker.bstein.dev"]
+  host_worker_bstein_dev --> svc_hermes_oauth2_proxy_hermes_agent
 
   subgraph bstein_dev_home[bstein-dev-home]
     svc_bstein_dev_home_bstein_dev_home_frontend

services/comms/knowledge/runbooks/hermes-triage-demo.md

@@ -99,7 +99,7 @@ in-process call removed a whole pod launch from the critical path.
   `hermes-demo-test-<N>` (failed) and `hermes-demo-repair-<N>` (succeeded);
   both TTL-clean after 1 h.
 - Hermes side: the run appears in the dashboard at
-  `https://agent.hermes.bstein.dev` (session/run history).
+  `https://worker.bstein.dev` (session/run history).
 - Escalation path: alert `HermesTriageHumanRequired` in vmalert
   (`vmalert-atlas-availability` deployment, 1 m interval, `for: 2m`)
   fires to Alertmanager for any `human_required` incident. Gauges are

services/hermes/NOTES.md

@@ -5,7 +5,7 @@ This is the mental model and demonstration script for the operator instance at
 consumer instance at `chat.bstein.dev` is intentionally separate and is not the
 place to perform infrastructure triage.
 
-`agent.hermes.bstein.dev` is the owner-only engineering control plane. Its root
+`worker.bstein.dev` is the owner-only engineering control plane. Its root
 serves the stock Hermes dashboard, including embedded chat/TUI and the native
 sessions, files, models, logs, Kanban, skills, plugins, MCP, profiles, and
 configuration surfaces. `/terminal/` remains the raw full-screen TUI. The
@@ -177,7 +177,7 @@ off. The final TypeScript build, Python compile, and source assertions remain
 mandatory, so an omitted or drifted replay fails before any image can pass
 release verification.
 
-From agent.hermes, trigger that one fixed job with:
+From worker.bstein.dev, trigger that one fixed job with:
 
 ```sh
 jenkins_image_build_trigger.py '<reviewed full main commit>'

services/hermes/agent-certificate.yaml

@@ -17,3 +17,6 @@ spec:
     # the rename in #34 must not break links or sessions already in flight.
     - chat.hermes.bstein.dev
     - triage.hermes.bstein.dev
+    # worker.bstein.dev is the canonical owner-agent host; the legacy
+    # agent.hermes.bstein.dev SAN above stays until it is retired on purpose.
+    - worker.bstein.dev

services/hermes/agent-configmap.yaml

@@ -142,7 +142,7 @@ data:
         - "*git clean -f*"
 
     dashboard:
-      public_url: https://agent.hermes.bstein.dev
+      public_url: https://worker.bstein.dev
 
     display:
       compact: true
@@ -174,7 +174,7 @@ data:
       backup_keep: 5
       non_interactive_local_changes: stash
   SOUL.md: |
-    You are Brad's private Hermes coordinator at agent.hermes.bstein.dev. Turn
+    You are Brad's private Hermes coordinator at worker.bstein.dev. Turn
     objectives into organized, reviewable delivery without making Brad manage
     model names, terminals, or provider capacity.
 
@@ -408,7 +408,7 @@ data:
   START-HERE.md: |
     # Agent Hermes
 
-    The authenticated root of agent.hermes.bstein.dev opens Hermes' stock
+    The authenticated root of worker.bstein.dev opens Hermes' stock
     dashboard with embedded chat/TUI, sessions, files, models, logs, Kanban,
     skills, plugins, MCP, profiles, and configuration. `/terminal/` opens the
     raw full-screen Hermes TUI. Give Hermes

services/hermes/agent-deployment.yaml

@@ -624,14 +624,15 @@ spec:
             - {name: HERMES_DASHBOARD_HOST, value: 127.0.0.1}
             - {name: HERMES_DASHBOARD_PORT, value: "9119"}
             - {name: HERMES_DASHBOARD_FILES_ROOT, value: /opt/data/workspace}
-            - {name: HERMES_DASHBOARD_PUBLIC_URL, value: https://agent.hermes.bstein.dev}
+            - {name: HERMES_DASHBOARD_PUBLIC_URL, value: https://worker.bstein.dev}
             - {name: HERMES_TUI_AGENT_INIT_TIMEOUT_S, value: "180"}
             - {name: HERMES_STREAM_STALE_TIMEOUT, value: "600"}
             - {name: HERMES_API_CALL_STALE_TIMEOUT, value: "600"}
             - {name: API_SERVER_ENABLED, value: "true"}
             - {name: API_SERVER_HOST, value: 0.0.0.0}
             - {name: API_SERVER_PORT, value: "8642"}
-            - {name: API_SERVER_CORS_ORIGINS, value: https://agent.hermes.bstein.dev}
+            # Comma-separated; the legacy origin stays until agent.hermes.bstein.dev is retired.
+            - {name: API_SERVER_CORS_ORIGINS, value: "https://worker.bstein.dev,https://agent.hermes.bstein.dev"}
             - {name: HERMES_MEDIA_DELIVERY_STRICT, value: "1"}
             - {name: HERMES_MEDIA_ALLOW_DIRS, value: /opt/data/workspace}
             - {name: HERMES_AUTO_ROUTER_PROFILE, value: agent}
@@ -694,7 +695,11 @@ spec:
           args:
             - --provider=oidc
             - --config=/vault/secrets/oidc-config
-            - --redirect-url=https://agent.hermes.bstein.dev/oauth2/callback
+            # Single canonical callback. The __Host- cookie prefix below binds both the
+            # session and the CSRF cookie to one host, so a fresh login must start on
+            # worker.bstein.dev; agent.hermes.bstein.dev keeps serving already
+            # authenticated sessions until it is retired separately.
+            - --redirect-url=https://worker.bstein.dev/oauth2/callback
             - --oidc-issuer-url=https://sso.bstein.dev/realms/atlas
             - --user-id-claim=sub
             - --oidc-groups-claim=groups

services/hermes/agent-ingress.yaml

@@ -6,8 +6,10 @@ metadata:
   namespace: hermes
 spec:
   redirectRegex:
-    regex: ^https://agent\.hermes\.bstein\.dev/terminal$
+    # Host-preserving so the trailing-slash fixup works on both the canonical
-    replacement: https://agent.hermes.bstein.dev/terminal/
+    # worker.bstein.dev and the legacy agent.hermes.bstein.dev host.
+    regex: ^https://(worker\.bstein\.dev|agent\.hermes\.bstein\.dev)/terminal$
+    replacement: https://${1}/terminal/
     permanent: false
 ---
 apiVersion: traefik.io/v1alpha1
@@ -33,9 +35,21 @@ spec:
   ingressClassName: traefik
   tls:
     - hosts:
+        - worker.bstein.dev
         - agent.hermes.bstein.dev
       secretName: hermes-sites-tls
   rules:
+    - host: worker.bstein.dev
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: oauth2-proxy-hermes-agent
+                port:
+                  name: http
+    # Legacy host, served unchanged until it is retired in a separate change.
     - host: agent.hermes.bstein.dev
       http:
         paths:
@@ -60,9 +74,21 @@ spec:
   ingressClassName: traefik
   tls:
     - hosts:
+        - worker.bstein.dev
         - agent.hermes.bstein.dev
       secretName: hermes-sites-tls
   rules:
+    - host: worker.bstein.dev
+      http:
+        paths:
+          - path: /terminal
+            pathType: Prefix
+            backend:
+              service:
+                name: oauth2-proxy-hermes-agent
+                port:
+                  name: http
+    # Legacy host, served unchanged until it is retired in a separate change.
     - host: agent.hermes.bstein.dev
       http:
         paths:
@@ -90,6 +116,7 @@ spec:
         - agent.hermes.bstein.dev
         - chat.bstein.dev
         - triage.bstein.dev
+        - worker.bstein.dev
         - chat.hermes.bstein.dev
         - triage.hermes.bstein.dev
       secretName: hermes-sites-tls

services/hermes/configmap.yaml

@@ -113,7 +113,7 @@ data:
 
     This is the dedicated triage appliance at triage.bstein.dev. Keep
     automated Ariadne intake and testing conversations here. Project delivery
-    and coding orchestration belong to agent.hermes.bstein.dev; general user
+    and coding orchestration belong to worker.bstein.dev; general user
     chat belongs to chat.bstein.dev.
 
     Start in AUTO routing with a careful, intelligence-biased posture. Every

services/hermes/skills/master-hermes-on-atlas/references/architecture.md

@@ -8,7 +8,7 @@ asserting health, placement, ownership, or current model availability.
 | Surface | Purpose | Identity boundary | State and permissions |
 | --- | --- | --- | --- |
 | `triage.bstein.dev` | Brad's automated testing triage | Keycloak plus an outer oauth2-proxy exact-email allow-list for `brad@bstein.dev` | `hermes` namespace, its own PVC and service account; read-only cluster triage plus approved internal evidence endpoints |
-| `agent.hermes.bstein.dev` | Brad's project coordinator | Keycloak plus an outer oauth2-proxy exact-email allow-list for `brad@bstein.dev` | `hermes` namespace and separate PVC; native Hermes delegates bounded work while Herdr preserves real Codex and Claude Code CLI sessions when needed |
+| `worker.bstein.dev` | Brad's project coordinator | Keycloak plus an outer oauth2-proxy exact-email allow-list for `brad@bstein.dev` | `hermes` namespace and separate PVC; native Hermes delegates bounded work while Herdr preserves real Codex and Claude Code CLI sessions when needed |
 | `chat.bstein.dev` | Private consumer chat and research through Hermes WebUI or a linked Telegram DM | Keycloak login plus one-time Telegram account link | One Hermes process and PVC per assigned Keycloak subject; no Kubernetes RBAC, terminal, or private-service access |
 
 The instances do not share conversation state, credentials, profiles, skills

services/keycloak/bootstrap-jobs/hermes-access-oidc-client-job.yaml

@@ -3,7 +3,7 @@
 apiVersion: batch/v1
 kind: Job
 metadata:
-  name: hermes-access-oidc-client-ensure-11
+  name: hermes-access-oidc-client-ensure-12
   namespace: sso
 spec:
   backoffLimit: 3

services/keycloak/scripts/hermes_access_oidc_ensure.sh

@@ -343,7 +343,8 @@ ensure_telegram_config() {
 ensure_hermes_owner
 ensure_proxy_client "hermes-chat-proxy" "https://chat.bstein.dev" "hermes/chat-oidc" \
   "https://chat.hermes.bstein.dev"
-ensure_proxy_client "hermes-agent-proxy" "https://agent.hermes.bstein.dev" "hermes/agent-oidc"
+ensure_proxy_client "hermes-agent-proxy" "https://worker.bstein.dev" "hermes/agent-oidc" \
+  "https://agent.hermes.bstein.dev"
 ensure_proxy_client "hermes-triage-proxy" "https://triage.bstein.dev" "hermes/triage-oidc" \
   "https://triage.hermes.bstein.dev"
 ensure_service_account_client "hermes-automation" "hermes/developer-keycloak"

services/quality/zap-baseline-configmap.yaml

@@ -26,7 +26,7 @@ data:
     https://budget.bstein.dev
     https://money.bstein.dev
     https://health.bstein.dev
-    https://agent.hermes.bstein.dev
+    https://worker.bstein.dev
     https://chat.bstein.dev
     https://triage.bstein.dev
     https://cassandra.bstein.dev

testing/tests/test_hermes_agent_runtime_patches.py

@@ -63,7 +63,7 @@ def test_owner_agent_installs_the_pinned_operator_toolchain():
     assert 'chmod 0644 "${profile_file}"' in init_command
 
 
-def test_owner_agent_uses_only_the_canonical_hostname():
+def test_owner_agent_uses_the_canonical_hostname():
     paths = [
         HERMES / "agent-configmap.yaml",
         HERMES / "agent-deployment.yaml",
@@ -73,7 +73,40 @@ def test_owner_agent_uses_only_the_canonical_hostname():
     for path in paths:
         content = path.read_text()
         assert "agent.bstein.dev" not in content
-        assert "agent.hermes.bstein.dev" in content
+        assert "worker.bstein.dev" in content
+
+
+def test_legacy_owner_host_stays_served_until_it_is_retired_separately():
+    """The rename must not cut off the host the operator reaches Hermes on.
+
+    ``agent.hermes.bstein.dev`` keeps resolving, routing and validating TLS
+    until it is retired in its own change, so rolling the rename back never
+    needs more than reverting the oauth2-proxy callback.
+    """
+    legacy = "agent.hermes.bstein.dev"
+    canonical = "worker.bstein.dev"
+
+    coredns = (
+        Path(__file__).parents[2] / "infrastructure/core/coredns-custom.yaml"
+    ).read_text()
+    assert f"192.168.22.9 {legacy}" in coredns
+    assert f"192.168.22.9 {canonical}" in coredns
+
+    certificate = yaml.safe_load((HERMES / "agent-certificate.yaml").read_text())
+    assert {legacy, canonical} <= set(certificate["spec"]["dnsNames"])
+
+    ingresses = [
+        doc
+        for doc in yaml.safe_load_all((HERMES / "agent-ingress.yaml").read_text())
+        if doc
+        and doc.get("kind") == "Ingress"
+        and doc["metadata"]["name"].startswith("hermes-agent-")
+    ]
+    assert len(ingresses) == 2
+    for ingress in ingresses:
+        assert {legacy, canonical} <= {rule["host"] for rule in ingress["spec"]["rules"]}
+        for tls in ingress["spec"]["tls"]:
+            assert {legacy, canonical} <= set(tls["hosts"])
 
 
 def test_agent_reconnect_retains_complete_history_and_long_tool_budget():

testing/tests/test_hermes_cli_lanes_toolchain.py

@@ -122,7 +122,7 @@ def test_owner_agent_installs_the_pinned_operator_toolchain():
     assert 'chmod 0644 "${profile_file}"' in init_command
 
 
-def test_owner_agent_uses_only_the_canonical_hostname():
+def test_owner_agent_uses_the_canonical_hostname():
     paths = [
         HERMES / "agent-configmap.yaml",
         HERMES / "agent-deployment.yaml",
@@ -132,7 +132,7 @@ def test_owner_agent_uses_only_the_canonical_hostname():
     for path in paths:
         content = path.read_text()
         assert "agent.bstein.dev" not in content
-        assert "agent.hermes.bstein.dev" in content
+        assert "worker.bstein.dev" in content
 
 
 def test_agent_reconnect_retains_complete_history_and_long_tool_budget():

testing/tests/test_hermes_public_host_continuity.py

@@ -35,8 +35,10 @@ PUBLIC_HOSTS = {
     "triage.hermes.bstein.dev": "oauth2-proxy-hermes-triage",
 }
 
-# The agent surface was deliberately untouched by the rename.
+# The agent surface is mid-rename too: worker.bstein.dev is canonical and the
+# legacy name stays served until a deliberate retirement change removes it.
 AGENT_HOST = "agent.hermes.bstein.dev"
+AGENT_CANONICAL_HOST = "worker.bstein.dev"
 
 
 def _docs(path: Path) -> list[dict]:
@@ -107,21 +109,29 @@ def test_host_is_registered_with_keycloak(host: str, ensure_script: str):
     assert f"https://{host}" in ensure_script
 
 
-def test_agent_surface_was_not_touched_by_the_rename(
+@pytest.mark.parametrize("host", [AGENT_HOST, AGENT_CANONICAL_HOST])
-    certificate: dict, coredns_hosts: set[str], ensure_script: str
+def test_agent_surface_serves_both_hosts_during_its_rename(
+    host: str, certificate: dict, coredns_hosts: set[str], ensure_script: str
 ):
-    assert AGENT_HOST in certificate["spec"]["dnsNames"]
+    """Retiring the legacy owner host is a separate, deliberate change.
-    assert AGENT_HOST in coredns_hosts
+
-    assert f"https://{AGENT_HOST}" in ensure_script
+    The agent hosts are served by hermes-agent-dashboard/-terminal rather than
+    hermes-sites, so their Ingress rules are asserted in
+    ``test_hermes_agent_runtime_patches.py`` instead of the table above.
+    """
+    assert host in certificate["spec"]["dnsNames"]
+    assert host in coredns_hosts
+    assert f"https://{host}" in ensure_script
 
 
 def test_ensure_script_registers_legacy_and_renamed_origins_together(
     ensure_script: str,
 ):
-    """The renamed proxies must carry both origins; the agent proxy only one."""
+    """Every renamed proxy must accept its old and new origin at the same time."""
     for client, canonical, legacy in (
         ("hermes-chat-proxy", "chat.bstein.dev", "chat.hermes.bstein.dev"),
         ("hermes-triage-proxy", "triage.bstein.dev", "triage.hermes.bstein.dev"),
+        ("hermes-agent-proxy", "worker.bstein.dev", "agent.hermes.bstein.dev"),
     ):
         call = re.search(
             rf'ensure_proxy_client "{client}".*?(?=\nensure_)',