Update

devplacepy/services/openai_gateway/service.py

@@ -3,18 +3,32 @@
 import json
 import logging
 import os
+import re
+import time
 
 from fastapi import HTTPException, Request
+from fastapi.responses import JSONResponse
 
 from devplacepy.database import get_int_setting
 from devplacepy.services.base import BaseService, ConfigField
 from devplacepy.services.openai_gateway import config
 from devplacepy.services.openai_gateway.analytics import summary_metrics
 from devplacepy.services.openai_gateway.gateway import GatewayRuntime
+from devplacepy.services.openai_gateway.routing import model_store
 from devplacepy.utils import get_current_user
 
 logger = logging.getLogger(__name__)
 
+APP_REFERENCE_PATTERN = re.compile(r"^[a-zA-Z0-9_.-]{1,30}$")
+DEFAULT_APP_REFERENCE = "default"
+
+
+def _validate_app_reference(value: str) -> str:
+    stripped = (value or "").strip()
+    if not stripped or not APP_REFERENCE_PATTERN.match(stripped):
+        return DEFAULT_APP_REFERENCE
+    return stripped
+
 
 def _presented_key(request: Request) -> str:
     key = request.headers.get("X-API-KEY")
@@ -449,6 +463,29 @@ class GatewayService(BaseService):
             return (kind, user.get("uid") or "unknown")
         return ("anonymous", "anonymous")
 
+    def _models_response(self) -> JSONResponse:
+        created = int(time.time())
+        seen: set = set()
+        data = []
+        for row in model_store.list():
+            if str(row.get("kind") or "chat") != "chat":
+                continue
+            if not row.get("is_active", True):
+                continue
+            source = str(row.get("source_model") or "").strip()
+            if not source or source in seen:
+                continue
+            seen.add(source)
+            data.append(
+                {
+                    "id": source,
+                    "object": "model",
+                    "created": created,
+                    "owned_by": "molodetz",
+                }
+            )
+        return JSONResponse({"object": "list", "data": data})
+
     async def handle(self, request: Request, subpath: str):
         if not self.is_enabled():
             raise HTTPException(status_code=503, detail="Gateway is disabled")
@@ -459,6 +496,11 @@ class GatewayService(BaseService):
         runtime = self.runtime()
         owner = self.resolve_owner(request)
         user_agent = request.headers.get("user-agent", "")
+        app_reference = _validate_app_reference(
+            request.headers.get("X-App-Reference", DEFAULT_APP_REFERENCE)
+        )
+        if subpath == "models" and request.method == "GET":
+            return self._models_response()
         if subpath == "chat/completions" and request.method == "POST":
             try:
                 body = await request.json()
@@ -468,7 +510,7 @@ class GatewayService(BaseService):
             if not isinstance(body, dict):
                 self.log("Rejected chat request: JSON body was not an object")
                 raise HTTPException(status_code=400, detail="Invalid JSON body")
-            return await runtime.handle_chat(body, cfg, owner, user_agent, self.log)
+            return await runtime.handle_chat(body, cfg, owner, user_agent, app_reference, self.log)
         if subpath == "embeddings" and request.method == "POST":
             try:
                 body = await request.json()
@@ -479,7 +521,7 @@ class GatewayService(BaseService):
                 self.log("Rejected embeddings request: JSON body was not an object")
                 raise HTTPException(status_code=400, detail="Invalid JSON body")
             return await runtime.handle_embeddings(
-                body, cfg, owner, user_agent, self.log
+                body, cfg, owner, user_agent, app_reference, self.log
             )
         if subpath == "images/generations" and request.method == "POST":
             try:
@@ -491,7 +533,7 @@ class GatewayService(BaseService):
                 self.log("Rejected images request: JSON body was not an object")
                 raise HTTPException(status_code=400, detail="Invalid JSON body")
             return await runtime.handle_images(
-                body, cfg, owner, user_agent, self.log
+                body, cfg, owner, user_agent, app_reference, self.log
             )
         body = await request.body()
         content_type = request.headers.get("content-type", "")
@@ -503,6 +545,7 @@ class GatewayService(BaseService):
             cfg,
             owner,
             user_agent,
+            app_reference,
             self.log,
         )