A served model's context can be changed, engine and memory with it

ctl model context MODEL TOKENS [--slots N], POST /api/v1/models/{name}/context
and the console's Context length…: the catalog, the engine's arguments and
the KV memory change together, refused past the trained context or what the
cards hold, then the replicas restart one by one.

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

docs/admin-api.openapi.json

@@ -2719,6 +2719,57 @@
         }
       }
     },
+    "/api/v1/models/{name}/context": {
+      "post": {
+        "operationId": "postModelsNameContext",
+        "summary": "Change a served model's context: the catalog, its engines' arguments and memory, then its replicas restarted",
+        "tags": [
+          "models"
+        ],
+        "parameters": [
+          {
+            "name": "name",
+            "in": "path",
+            "required": true,
+            "description": "The model's name in the catalog.",
+            "schema": {
+              "type": "string"
+            }
+          },
+          {
+            "$ref": "#/components/parameters/Actor"
+          }
+        ],
+        "requestBody": {
+          "required": true,
+          "content": {
+            "application/json": {
+              "schema": {
+                "$ref": "#/components/schemas/modelserve.ContextRequest"
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "OK",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/modelserve.ContextChange"
+                }
+              }
+            }
+          },
+          "401": {
+            "$ref": "#/components/responses/Unauthorized"
+          },
+          "default": {
+            "$ref": "#/components/responses/Error"
+          }
+        }
+      }
+    },
     "/api/v1/models/{name}/eval": {
       "post": {
         "operationId": "postModelsNameEval",
@@ -7749,6 +7800,13 @@
           "name": {
             "type": "string"
           },
+          "context_length": {
+            "type": "integer",
+            "description": "ContextLength is what one request may use, MaxOutput what it may answer; 0 when the catalog does not say."
+          },
+          "max_output": {
+            "type": "integer"
+          },
           "canary": {
             "$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."
@@ -11005,6 +11063,76 @@
           }
         }
       },
+      "modelserve.ContextChange": {
+        "type": "object",
+        "description": "ContextChange is what was changed, and the replicas started again on it.",
+        "properties": {
+          "model": {
+            "type": "string"
+          },
+          "before": {
+            "type": "integer"
+          },
+          "after": {
+            "type": "integer"
+          },
+          "max_output": {
+            "type": "integer"
+          },
+          "trained": {
+            "type": "integer"
+          },
+          "profiles": {
+            "type": "array",
+            "items": {
+              "$ref": "#/components/schemas/modelserve.ContextProfile"
+            }
+          },
+          "restarted": {
+            "type": "integer"
+          },
+          "note": {
+            "type": "string",
+            "description": "Note is what could not be checked, said once."
+          }
+        }
+      },
+      "modelserve.ContextProfile": {
+        "type": "object",
+        "description": "ContextProfile is what one profile needs before and after.",
+        "properties": {
+          "profile": {
+            "type": "string"
+          },
+          "engine": {
+            "type": "string"
+          },
+          "before": {
+            "type": "string"
+          },
+          "after": {
+            "type": "string"
+          },
+          "args": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            }
+          }
+        }
+      },
+      "modelserve.ContextRequest": {
+        "type": "object",
+        "description": "ContextRequest is the context to change to: tokens one request may use, and for llama.cpp how many at once (its pool is the two multiplied).",
+        "properties": {
+          "tokens": {
+            "type": "integer"
+          },
+          "slots": {
+            "type": "integer"
+          }
+        }
+      },
       "modelserve.Job": {
         "type": "object",
         "description": "Job is one model being served, and where it stands.",