A model can be stopped and kept, or removed with its files from the mirror and the nodes

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

docs/admin-api.openapi.json

@@ -2387,7 +2387,7 @@
       "delete": {
         "operationId": "deleteModelsName",
         "summary": "Remove a model added at runtime",
-        "description": "A model declared in the cluster's settings is refused: it is changed there.",
+        "description": "A model declared in the cluster's settings is refused: it is changed there. With purge, its files go too: every version of it the mirror holds (a peer mirror follows), and the nodes' copies once its replicas have stopped, waiting up to a minute for them; what another model uses stays. The answer is then a PurgeView.",
         "tags": [
           "models"
         ],
@@ -2401,6 +2401,14 @@
               "type": "string"
             }
           },
+          {
+            "name": "purge",
+            "in": "query",
+            "description": "Delete its files from the mirror and the nodes as well.",
+            "schema": {
+              "type": "boolean"
+            }
+          },
           {
             "$ref": "#/components/parameters/Actor"
           }
@@ -3400,6 +3408,89 @@
         }
       }
     },
+    "/api/v1/models/{name}/start": {
+      "post": {
+        "operationId": "postModelsNameStart",
+        "summary": "Run a stopped model again, scaled as it was",
+        "tags": [
+          "models"
+        ],
+        "parameters": [
+          {
+            "name": "name",
+            "in": "path",
+            "required": true,
+            "description": "The model's name in the catalog.",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "$ref": "#/components/parameters/Actor"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ScaleResponse"
+                }
+              }
+            }
+          },
+          "401": {
+            "$ref": "#/components/responses/Unauthorized"
+          },
+          "default": {
+            "$ref": "#/components/responses/Error"
+          }
+        }
+      }
+    },
+    "/api/v1/models/{name}/stop": {
+      "post": {
+        "operationId": "postModelsNameStop",
+        "summary": "Take a model out of service and keep it",
+        "description": "None of its replicas run, and requests are told an administrator stopped it; what it was scaled to is kept for start.",
+        "tags": [
+          "models"
+        ],
+        "parameters": [
+          {
+            "name": "name",
+            "in": "path",
+            "required": true,
+            "description": "The model's name in the catalog.",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "$ref": "#/components/parameters/Actor"
+          }
+        ],
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ScaleResponse"
+                }
+              }
+            }
+          },
+          "401": {
+            "$ref": "#/components/responses/Unauthorized"
+          },
+          "default": {
+            "$ref": "#/components/responses/Error"
+          }
+        }
+      }
+    },
     "/api/v1/models/{name}/target": {
       "get": {
         "operationId": "getModelsNameTarget",
@@ -7859,6 +7950,10 @@
           "max_output": {
             "type": "integer"
           },
+          "stopped": {
+            "type": "boolean",
+            "description": "Stopped is a model an administrator took out of service, kept."
+          },
           "canary": {
             "$ref": "#/components/schemas/catalog.Canary",
             "description": "Canary is a share of its requests sent to a candidate; CanaryOf is set on the candidate, naming the model it is a canary of."
@@ -8939,6 +9034,10 @@
           },
           "on_demand": {
             "type": "boolean"
+          },
+          "stopped": {
+            "type": "boolean",
+            "description": "Stopped is a model taken out of service, kept, until it is started."
           }
         }
       },
@@ -10064,6 +10163,10 @@
           "scaling": {
             "$ref": "#/components/schemas/catalog.Scaling"
           },
+          "stopped": {
+            "$ref": "#/components/schemas/catalog.Scaling",
+            "description": "Stopped is the scaling a model had when an administrator stopped it: kept in the catalog with none running (Scaling 0/0) until started again with this. Nil for a model not stopped."
+          },
           "class": {
             "type": "string",
             "description": "Class is how much this model's capacity is worth against another's, when there is not enough for both: critical, standard or opportunistic. Empty is standard, or opportunistic for a model loaded on demand. See EffectiveClass."