Feat: Add Token Stats and Cost Savings dashboard card and backend tracking

backend/routers/gateway_proxy.py

@@ -1,18 +1,11 @@
-"""
-Eingebauter Routing-Gateway (OpenAI-kompatibel) — EIN Endpunkt für Hermes + IDEs.
-
-`model: auto` → Komplexitäts-Routing fast↔heavy; jeder andere Name geht als
-llama-swap-Alias durch (das lädt das Modell bei Bedarf). Streaming wird
-durchgereicht. Ersetzt LiteLLM (das auf Python 3.14 nicht baut) — gleicher
-Vertrag, später austauschbar.
-"""
-
+import json
 import httpx
 from fastapi import APIRouter, Request
 from fastapi.responses import JSONResponse, StreamingResponse
 
 from config import LLAMA_SWAP_URL
 from services.router_logic import FAST, FAST_NO_THINK, choose_model
+from services.token_stats import increment_tokens
 
 router = APIRouter(prefix="/v1")
 
@@ -44,12 +37,42 @@ async def _proxy(path: str, request: Request):
             async with httpx.AsyncClient(timeout=None) as c:
                 async with c.stream("POST", url, json=body) as r:
                     async for chunk in r.aiter_raw():
+                        try:
+                            chunk_str = chunk.decode("utf-8", errors="ignore")
+                            if '"usage":' in chunk_str:
+                                for line in chunk_str.splitlines():
+                                    if line.startswith("data:"):
+                                        data_str = line[5:].strip()
+                                        if data_str == "[DONE]":
+                                            continue
+                                        try:
+                                            data_json = json.loads(data_str)
+                                            usage = data_json.get("usage")
+                                            if usage:
+                                                prompt = usage.get("prompt_tokens", 0)
+                                                completion = usage.get("completion_tokens", 0)
+                                                if prompt or completion:
+                                                    increment_tokens(prompt, completion)
+                                        except Exception:
+                                            pass
+                        except Exception:
+                            pass
                         yield chunk
         return StreamingResponse(gen(), media_type="text/event-stream", headers=routed)
 
     async with httpx.AsyncClient(timeout=600) as c:
         r = await c.post(url, json=body)
-        return JSONResponse(r.json(), status_code=r.status_code, headers=routed)
+        resp_json = r.json()
+        try:
+            usage = resp_json.get("usage")
+            if usage:
+                prompt = usage.get("prompt_tokens", 0)
+                completion = usage.get("completion_tokens", 0)
+                if prompt or completion:
+                    increment_tokens(prompt, completion)
+        except Exception:
+            pass
+        return JSONResponse(resp_json, status_code=r.status_code, headers=routed)
 
 
 @router.post("/chat/completions")