Remove deprecated code

docs/swagger.yaml

@@ -39,11 +39,6 @@ definitions:
     type: object
   config.AuthConfig:
     properties:
-      inference_keys:
-        description: List of keys for OpenAI compatible inference endpoints
-        items:
-          type: string
-        type: array
       management_keys:
         description: List of keys for management endpoints
         items:
@@ -118,10 +113,6 @@ definitions:
       auto_create_dirs:
         description: Automatically create the data directory if it doesn't exist
         type: boolean
-      configs_dir:
-        description: Instance config directory override (relative to data_dir if not
-          absolute)
-        type: string
       default_auto_restart:
         description: Default auto-restart setting for new instances
         type: boolean
@@ -137,6 +128,18 @@ definitions:
       enable_lru_eviction:
         description: Enable LRU eviction for instance logs
         type: boolean
+      logRotationCompress:
+        default: false
+        description: Whether to compress rotated log files
+        type: boolean
+      logRotationEnabled:
+        default: true
+        description: Log rotation enabled
+        type: boolean
+      logRotationMaxSize:
+        default: 100
+        description: Maximum log file size in MB before rotation
+        type: integer
       logs_dir:
         description: Logs directory override (relative to data_dir if not absolute)
         type: string
@@ -955,6 +958,102 @@ paths:
       summary: Stop a running instance
       tags:
       - Instances
+  /api/v1/llama-cpp/{name}/models:
+    get:
+      description: Returns a list of models available in the specified llama.cpp instance
+      parameters:
+      - description: Instance Name
+        in: path
+        name: name
+        required: true
+        type: string
+      responses:
+        "200":
+          description: Models list response
+          schema:
+            additionalProperties: true
+            type: object
+        "400":
+          description: Invalid instance
+          schema:
+            type: string
+        "500":
+          description: Internal Server Error
+          schema:
+            type: string
+      security:
+      - ApiKeyAuth: []
+      summary: List models in a llama.cpp instance
+      tags:
+      - Llama.cpp
+  /api/v1/llama-cpp/{name}/models/{model}/load:
+    post:
+      description: Loads the specified model in the given llama.cpp instance
+      parameters:
+      - description: Instance Name
+        in: path
+        name: name
+        required: true
+        type: string
+      - description: Model Name
+        in: path
+        name: model
+        required: true
+        type: string
+      responses:
+        "200":
+          description: Success message
+          schema:
+            additionalProperties:
+              type: string
+            type: object
+        "400":
+          description: Invalid request
+          schema:
+            type: string
+        "500":
+          description: Internal Server Error
+          schema:
+            type: string
+      security:
+      - ApiKeyAuth: []
+      summary: Load a model in a llama.cpp instance
+      tags:
+      - Llama.cpp
+  /api/v1/llama-cpp/{name}/models/{model}/unload:
+    post:
+      description: Unloads the specified model in the given llama.cpp instance
+      parameters:
+      - description: Instance Name
+        in: path
+        name: name
+        required: true
+        type: string
+      - description: Model Name
+        in: path
+        name: model
+        required: true
+        type: string
+      responses:
+        "200":
+          description: Success message
+          schema:
+            additionalProperties:
+              type: string
+            type: object
+        "400":
+          description: Invalid request
+          schema:
+            type: string
+        "500":
+          description: Internal Server Error
+          schema:
+            type: string
+      security:
+      - ApiKeyAuth: []
+      summary: Unload a model in a llama.cpp instance
+      tags:
+      - Llama.cpp
   /api/v1/nodes:
     get:
       description: Returns a map of all nodes configured in the server (node name