Add Peer Model Support (#438)

This PR allows a single llama-swap to be the central proxy for models served by other inference servers. The peer servers can be another llama-swap or any API that supports the /v1/* inference endpoint.

Updates: #433, #299
Closes: #296

config-schema.json

@@ -273,6 +273,58 @@
             },
             "additionalProperties": false,
             "description": "A dictionary of event triggers and actions. Only supported hook is on_startup."
+        },
+        "logToStdout": {
+            "type": "string",
+            "enum": [
+                "proxy",
+                "upstream",
+                "both",
+                "none"
+            ],
+            "default": "proxy",
+            "description": "Controls what is logged to stdout. 'proxy': logs generated by llama-swap, 'upstream': copy of upstream process stdout logs, 'both': both interleaved together, 'none': no logs written to stdout."
+        },
+        "apiKeys": {
+            "type": "array",
+            "items": {
+                "type": "string",
+                "minLength": 1
+            },
+            "default": [],
+            "description": "Require an API key when making requests to inference endpoints. When empty, authorization will not be checked. Each key is a non-empty string."
+        },
+        "peers": {
+            "type": "object",
+            "additionalProperties": {
+                "type": "object",
+                "required": [
+                    "proxy",
+                    "models"
+                ],
+                "properties": {
+                    "proxy": {
+                        "type": "string",
+                        "format": "uri",
+                        "description": "A valid base URL to proxy requests to. Requested path to llama-swap will be appended to the end of the proxy value."
+                    },
+                    "apiKey": {
+                        "type": "string",
+                        "default": "",
+                        "description": "A string key to be injected into the request. If blank, no key will be added. Key will be injected into headers: Authorization: Bearer <key> and x-api-key: <key>."
+                    },
+                    "models": {
+                        "type": "array",
+                        "items": {
+                            "type": "string",
+                            "minLength": 1
+                        },
+                        "description": "A list of models served by the peer."
+                    }
+                }
+            },
+            "default": {},
+            "description": "A dictionary of remote peers and models they provide. Peers can be another llama-swap or any server that provides the /v1/ generative API endpoints supported by llama-swap."
         }
     }
 }