Log actual tokens and elapsed time for all endpoints incl. streaming

For streaming /v1/chat/completions: inject stream_options.include_usage,
parse usage from SSE chunks, log actual ↑↓ tokens and wall time in the
generator's finally block. Add elapsed time to all second log entries.

Dockerfile

@@ -6,6 +6,8 @@ COPY frontend/ frontend/
 RUN npm run build --prefix frontend
 
 FROM python:3.12-slim
+ARG APP_VERSION=dev
+ENV APP_VERSION=$APP_VERSION
 WORKDIR /app
 
 COPY backend/requirements.txt .

KURZANLEITUNG.md

@@ -14,7 +14,7 @@ Typische Anwendungsfälle:
 
 ## Zugang
 
-Der Dienst ist **nur im Intranet** erreichbar.
+Der Dienst ist **nur im Intranet (VPN)** erreichbar.
 
 | | |
 |---|---|
@@ -86,6 +86,24 @@ for m in models.data:
 
 ---
 
+## Aktuell geladenes Modell abfragen
+
+Da immer nur ein Modell gleichzeitig im Speicher sein kann, lässt sich mit folgendem Aufruf prüfen, welches Modell gerade aktiv ist:
+
+```python
+import httpx
+
+r = httpx.get(
+    "http://141.75.33.244:8000/api/ps",
+    headers={"Authorization": "Bearer sk-..."}
+)
+print(r.json())
+```
+
+Die Antwort enthält Modellname, Größe und wie lange das Modell noch im Speicher bleibt.
+
+---
+
 ## Empfehlungen zur Nutzung
 
 - **Kleines Modell zuerst** (`gemma4:31b` oder `gpt-oss:20b`) – viel schneller, für viele Aufgaben ausreichend.

backend/admin.py

@@ -131,7 +131,10 @@ async def get_proxy_info(_ = Depends(require_admin_auth)):
     host = os.getenv("PROXY_HOST", "0.0.0.0")
     port = os.getenv("PROXY_PORT", "8000")
     display_host = "localhost" if host in ("0.0.0.0", "::") else host
-    return {"endpoint": f"http://{display_host}:{port}"}
+    return {
+        "endpoint": f"http://{display_host}:{port}",
+        "version": os.getenv("APP_VERSION", "dev"),
+    }
 
 @app.get("/api/settings", response_model=schemas.Settings)
 async def read_settings(db: Session = Depends(get_db), _ = Depends(require_admin_auth)):

backend/main.py

@@ -1,5 +1,7 @@
+import json
 import logging
 import os
+import time
 from logging.handlers import RotatingFileHandler
 from pathlib import Path
 
@@ -102,12 +104,14 @@ async def generate(request: Request, db: Session = Depends(get_db)):
     prompt_preview = (body.get("prompt", "").replace("\n", " ").strip())[:120]
     usage_log.info('%s | /api/generate | %s | ~%d tokens | "%s"',
                    request.state.api_key_name, body.get("model", "?"), prompt_tokens, prompt_preview)
+    start = time.monotonic()
     try:
         response = await proxy_request(f"{ollama_url}/api/generate", method="POST", json_data=body)
         resp_json = response.json()
-        usage_log.info('%s | /api/generate | %s | actual ↑%d ↓%d tokens',
+        usage_log.info('%s | /api/generate | %s | actual ↑%d ↓%d tokens | %.1fs',
                        request.state.api_key_name, body.get("model", "?"),
-                       resp_json.get("prompt_eval_count", 0), resp_json.get("eval_count", 0))
+                       resp_json.get("prompt_eval_count", 0), resp_json.get("eval_count", 0),
+                       time.monotonic() - start)
         return JSONResponse(content=resp_json, status_code=response.status_code)
     except Exception as exc:
         error_log.error("Proxy error | %s | /api/generate | %s | %s: %s",
@@ -131,12 +135,14 @@ async def chat(request: Request, db: Session = Depends(get_db)):
 
     usage_log.info('%s | /api/chat | %s | ~%d tokens | "%s"',
                    request.state.api_key_name, body.get("model", "?"), prompt_tokens, _last_user_msg(messages))
+    start = time.monotonic()
     try:
         response = await proxy_request(f"{ollama_url}/api/chat", method="POST", json_data=body)
         resp_json = response.json()
-        usage_log.info('%s | /api/chat | %s | actual ↑%d ↓%d tokens',
+        usage_log.info('%s | /api/chat | %s | actual ↑%d ↓%d tokens | %.1fs',
                        request.state.api_key_name, body.get("model", "?"),
-                       resp_json.get("prompt_eval_count", 0), resp_json.get("eval_count", 0))
+                       resp_json.get("prompt_eval_count", 0), resp_json.get("eval_count", 0),
+                       time.monotonic() - start)
         return JSONResponse(content=resp_json, status_code=response.status_code)
     except Exception as exc:
         error_log.error("Proxy error | %s | /api/chat | %s | %s: %s",
@@ -149,6 +155,16 @@ async def list_models(db: Session = Depends(get_db)):
     response = await proxy_request(f"{ollama_url}/api/tags", method="GET")
     return JSONResponse(content=response.json(), status_code=response.status_code)
 
+@app.get("/version")
+async def version():
+    return {"version": os.getenv("APP_VERSION", "dev")}
+
+@app.get("/api/ps")
+async def running_models(db: Session = Depends(get_db)):
+    ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
+    response = await proxy_request(f"{ollama_url}/api/ps", method="GET")
+    return JSONResponse(content=response.json(), status_code=response.status_code)
+
 @app.get("/api/versions")
 async def versions(db: Session = Depends(get_db)):
     ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
@@ -185,29 +201,51 @@ async def openai_chat_completions(request: Request, db: Session = Depends(get_db
     target = f"{ollama_url}/v1/chat/completions"
 
     if body.get("stream"):
+        existing_opts = body.get("stream_options") or {}
+        stream_body = {**body, "stream_options": {**existing_opts, "include_usage": True}}
+        start = time.monotonic()
+        usage_tokens = {"prompt": 0, "completion": 0}
+
         async def generate():
             try:
                 async with httpx.AsyncClient(timeout=300.0) as client:
-                    async with client.stream("POST", target, json=body) as resp:
+                    async with client.stream("POST", target, json=stream_body) as resp:
                         async for chunk in resp.aiter_bytes():
+                            try:
+                                for line in chunk.decode("utf-8", errors="ignore").splitlines():
+                                    if line.startswith("data: ") and "[DONE]" not in line:
+                                        data = json.loads(line[6:])
+                                        if u := data.get("usage"):
+                                            usage_tokens["prompt"] = u.get("prompt_tokens", 0)
+                                            usage_tokens["completion"] = u.get("completion_tokens", 0)
+                            except Exception:
+                                pass
                             yield chunk
             except Exception as exc:
                 error_log.error("Stream error | %s | /v1/chat/completions | %s | %s: %s",
                                 request.state.api_key_name, model_name, type(exc).__name__, exc, exc_info=exc)
                 raise
+            finally:
+                usage_log.info('%s | /v1/chat/completions | %s | actual ↑%d ↓%d tokens | %.1fs',
+                               request.state.api_key_name, model_name,
+                               usage_tokens["prompt"], usage_tokens["completion"],
+                               time.monotonic() - start)
+
         return StreamingResponse(
             generate(),
             media_type="text/event-stream",
             headers={"Cache-Control": "no-cache", "X-Accel-Buffering": "no"},
         )
 
+    start = time.monotonic()
     try:
         response = await proxy_request(target, method="POST", json_data=body)
         resp_json = response.json()
         usage = resp_json.get("usage", {})
-        usage_log.info('%s | /v1/chat/completions | %s | actual ↑%d ↓%d tokens',
+        usage_log.info('%s | /v1/chat/completions | %s | actual ↑%d ↓%d tokens | %.1fs',
                        request.state.api_key_name, model_name,
-                       usage.get("prompt_tokens", 0), usage.get("completion_tokens", 0))
+                       usage.get("prompt_tokens", 0), usage.get("completion_tokens", 0),
+                       time.monotonic() - start)
         return JSONResponse(content=resp_json, status_code=response.status_code)
     except Exception as exc:
         error_log.error("Proxy error | %s | /v1/chat/completions | %s | %s: %s",

build_push.sh

@@ -37,6 +37,7 @@ echo ""
 docker buildx build \
     --platform "$PLATFORM" \
     --push \
+    --build-arg APP_VERSION="$VERSION" \
     -t "$IMAGE:$VERSION" \
     -t "$IMAGE:latest" \
     .

frontend/src/main.jsx

@@ -82,6 +82,7 @@ function SettingsSection({ password }) {
   const [modelsLoading, setModelsLoading] = useState(false);
   const [ollamaReachable, setOllamaReachable] = useState(true);
   const [proxyEndpoint, setProxyEndpoint] = useState(null);
+  const [appVersion, setAppVersion] = useState(null);
   const [saved, setSaved] = useState(false);
   const [error, setError] = useState(null);
 
@@ -115,6 +116,7 @@ function SettingsSection({ password }) {
       const s = settingsRes.data;
       setSettings(s);
       setProxyEndpoint(proxyRes.data.endpoint);
+      setAppVersion(proxyRes.data.version);
       fetchModels(s.ollama_url, s.force_model);
     }).catch(() => setError('Einstellungen konnten nicht geladen werden.'));
   }, []);
@@ -145,6 +147,10 @@ function SettingsSection({ password }) {
             <small> (Änderung erfordert Neustart)</small>
           </span>
         </div>
+        <div className="settings-row">
+          <label>Version</label>
+          <span className="settings-value">{appVersion ?? '…'}</span>
+        </div>
         <div className="settings-row">
           <label>Ollama-Endpunkt</label>
           <div className="settings-input-wrap">