Clarify that Ollama can run remotely, not just on Docker host

Split host-Ollama compose into SQLite and PostgreSQL variants
Add host-Ollama compose variant, fix leftover port 8001 exposure
2026-04-29 08:51:23 +02:00 · 2026-04-29 08:47:40 +02:00 · 2026-04-29 08:43:54 +02:00 · 2026-04-29 08:38:38 +02:00 · 2026-04-29 08:36:59 +02:00 · 2026-04-29 08:31:25 +02:00
15 changed files with 3048 additions and 171 deletions
@@ -14,7 +14,11 @@ __pycache__/
 *.sqlite3

 # IDE
-.idea/
+.idea/*
+!.idea/runConfigurations/
+.idea/runConfigurations/*
+!.idea/runConfigurations/Dev.xml
+!.idea/runConfigurations/Docker_Push.xml
 .vscode/

 # Frontend build
@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<component name="ProjectRunConfigurationManager">
+  <configuration default="false" name="Dev" type="PythonConfigurationType" factoryName="Python">
+    <module name="llm_quota" />
+    <option name="INTERPRETER_OPTIONS" value="" />
+    <option name="PARENT_ENVS" value="true" />
+    <option name="SDK_HOME" value="" />
+    <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+    <option name="IS_MODULE_SDK" value="false" />
+    <option name="ADD_CONTENT_ROOTS" value="true" />
+    <option name="ADD_SOURCE_ROOTS" value="true" />
+    <option name="SCRIPT_NAME" value="$PROJECT_DIR$/run_dev.py" />
+    <option name="PARAMETERS" value="" />
+    <method v="2" />
+  </configuration>
+</component>
@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<component name="ProjectRunConfigurationManager">
+  <configuration default="false" name="Docker Push" type="ShConfigurationType">
+    <option name="SCRIPT_PATH" value="$PROJECT_DIR$/build_push.sh" />
+    <option name="INDEPENDENT_SCRIPT_PATH" value="true" />
+    <option name="INTERPRETER_PATH" value="/bin/bash" />
+    <option name="INTERPRETER_OPTIONS" value="" />
+    <option name="INDEPENDENT_SCRIPT_WORKING_DIRECTORY" value="true" />
+    <option name="SCRIPT_WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+    <method v="2" />
+  </configuration>
+</component>
@@ -0,0 +1,206 @@
+# mediaeng/llmproxy
+
+Ein schlanker Reverse-Proxy für [Ollama](https://ollama.com), der API-Keys mit konfigurierbaren Token- und Request-Quoten verwaltet. Eingehende Anfragen im OpenAI-kompatiblen Format werden authentifiziert, auf Quota geprüft und an den konfigurierten Ollama-Server weitergeleitet.
+
+Ollama muss dabei nicht auf demselben Host laufen — `OLLAMA_URL` kann auf jeden erreichbaren Server zeigen, also auf den Docker-Host selbst, einen anderen Rechner im Netzwerk oder einen Remote-Server.
+
+## Funktionen
+
+- OpenAI-kompatibler Endpunkt (`/v1/chat/completions`, `/v1/models`)
+- API-Key-Verwaltung mit tages- und monatlichen Token-/Request-Limits
+- Web-basierte Admin-Oberfläche (Port 8001)
+- Streaming-Support (Server-Sent Events)
+- Tool-Use / Function Calling wird durchgereicht
+- Rotierende Nutzungs-Logs
+- SQLite (Standard) oder PostgreSQL
+
+## Ports
+
+| Port | Dienst |
+|------|--------|
+| `8000` | Proxy-Endpunkt (OpenAI-API) |
+| `8001` | Admin-API + Web-Oberfläche (nicht exponieren) |
+
+## Umgebungsvariablen
+
+| Variable | Standard | Beschreibung |
+|----------|----------|--------------|
+| `ADMIN_PASSWORD` | – | **Pflicht.** Passwort für die Admin-Oberfläche |
+| `OLLAMA_URL` | `http://localhost:11434` | URL des Ollama-Servers (ohne `/v1`-Suffix) |
+| `DEFAULT_MODEL` | `llama3` | Modell, das verwendet wird wenn der Client keines angibt |
+| `DATABASE_URL` | `sqlite:///./test.db` | Datenbank-Verbindungsstring (SQLite oder PostgreSQL) |
+| `PROXY_HOST` | `0.0.0.0` | Bind-Adresse des Proxy |
+| `PROXY_PORT` | `8000` | Port des Proxy |
+| `ADMIN_PORT` | `8001` | Port der Admin-API |
+| `APP_TZ` | `Europe/Berlin` | Zeitzone für Tages-/Monats-Reset der Quoten |
+| `LOG_FILE` | `logs/usage.log` | Pfad der rotierenden Nutzungs-Logdatei |
+
+## Docker Compose – Ollama extern, SQLite
+
+Wenn Ollama außerhalb von Docker läuft — auf dem Docker-Host oder einem anderen erreichbaren Server. `OLLAMA_URL` entsprechend anpassen.
+
+```yaml
+services:
+  llmproxy:
+    image: mediaeng/llmproxy:latest
+    restart: unless-stopped
+    ports:
+      - "8000:8000"
+    environment:
+      ADMIN_PASSWORD: changeme
+      OLLAMA_URL: http://host.docker.internal:11434  # oder http://<ip>:11434
+      DEFAULT_MODEL: llama3
+      APP_TZ: Europe/Berlin
+    volumes:
+      - llmproxy-data:/app/backend
+    # Auf Linux extra_hosts ergänzen, da host.docker.internal dort
+    # nicht automatisch verfügbar ist:
+    # extra_hosts:
+    #   - "host.docker.internal:host-gateway"
+
+volumes:
+  llmproxy-data:
+```
+
+## Docker Compose – Ollama extern, PostgreSQL
+
+```yaml
+services:
+  llmproxy:
+    image: mediaeng/llmproxy:latest
+    restart: unless-stopped
+    ports:
+      - "8000:8000"
+    environment:
+      ADMIN_PASSWORD: changeme
+      OLLAMA_URL: http://host.docker.internal:11434  # oder http://<ip>:11434
+      DEFAULT_MODEL: llama3
+      APP_TZ: Europe/Berlin
+      DATABASE_URL: postgresql://llmproxy:secret@db:5432/llmproxy
+    volumes:
+      - llmproxy-data:/app/backend
+    depends_on:
+      db:
+        condition: service_healthy
+    # extra_hosts:
+    #   - "host.docker.internal:host-gateway"
+
+  db:
+    image: postgres:16-alpine
+    restart: unless-stopped
+    environment:
+      POSTGRES_DB: llmproxy
+      POSTGRES_USER: llmproxy
+      POSTGRES_PASSWORD: secret
+    volumes:
+      - pg-data:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U llmproxy"]
+      interval: 5s
+      timeout: 5s
+      retries: 5
+
+volumes:
+  pg-data:
+```
+
+## Docker Compose – Ollama als Container, SQLite
+
+Ollama und llmproxy laufen gemeinsam in Docker, Daten in einem Volume.
+
+```yaml
+services:
+  llmproxy:
+    image: mediaeng/llmproxy:latest
+    restart: unless-stopped
+    ports:
+      - "8000:8000"
+    environment:
+      ADMIN_PASSWORD: changeme
+      OLLAMA_URL: http://ollama:11434
+      DEFAULT_MODEL: llama3
+      APP_TZ: Europe/Berlin
+    volumes:
+      - llmproxy-data:/app/backend
+    depends_on:
+      - ollama
+
+  ollama:
+    image: ollama/ollama:latest
+    restart: unless-stopped
+    volumes:
+      - ollama-data:/root/.ollama
+
+volumes:
+  llmproxy-data:
+  ollama-data:
+```
+
+## Docker Compose – Ollama als Container, PostgreSQL
+
+Für Produktionsumgebungen mit externer Datenbank.
+
+```yaml
+services:
+  llmproxy:
+    image: mediaeng/llmproxy:latest
+    restart: unless-stopped
+    ports:
+      - "8000:8000"
+    environment:
+      ADMIN_PASSWORD: changeme
+      OLLAMA_URL: http://ollama:11434
+      DEFAULT_MODEL: llama3
+      APP_TZ: Europe/Berlin
+      DATABASE_URL: postgresql://llmproxy:secret@db:5432/llmproxy
+    depends_on:
+      db:
+        condition: service_healthy
+      ollama:
+        condition: service_started
+
+  db:
+    image: postgres:16-alpine
+    restart: unless-stopped
+    environment:
+      POSTGRES_DB: llmproxy
+      POSTGRES_USER: llmproxy
+      POSTGRES_PASSWORD: secret
+    volumes:
+      - pg-data:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U llmproxy"]
+      interval: 5s
+      timeout: 5s
+      retries: 5
+
+  ollama:
+    image: ollama/ollama:latest
+    restart: unless-stopped
+    volumes:
+      - ollama-data:/root/.ollama
+
+volumes:
+  pg-data:
+  ollama-data:
+```
+
+## Schnellstart
+
+```bash
+docker run -d \
+  -p 8000:8000 \
+  -e ADMIN_PASSWORD=changeme \
+  -e OLLAMA_URL=http://host.docker.internal:11434 \
+  -v llmproxy-data:/app/backend \
+  mediaeng/llmproxy:latest
+```
+
+## Client-Konfiguration
+
+Den Proxy als OpenAI-kompatibler Endpunkt konfigurieren:
+
+```
+Base URL:  http://<host>:8000/v1
+API Key:   <angelegter API-Key aus der Admin-Oberfläche>
+```
@@ -9,7 +9,7 @@ FROM python:3.12-slim
 WORKDIR /app

 COPY backend/requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt psycopg2-binary

 COPY backend/ backend/
 COPY --from=frontend-builder /app/frontend/dist frontend/dist
@@ -8,7 +8,7 @@ from fastapi.staticfiles import StaticFiles
 from sqlalchemy.orm import Session
 from database import get_db
 import crud, schemas
-from models import APIKey as APIKeyModel
+from models import APIKey as APIKeyModel, Usage as UsageModel

 app = FastAPI(title="Ollama Proxy Admin API")

@@ -31,13 +31,24 @@ def require_admin_auth(request: Request):
    if not secrets.compare_digest(token, ADMIN_PASSWORD):
        raise HTTPException(status_code=401, detail="Invalid admin password")

-@app.get("/api/api-keys", response_model=list[schemas.APIKey])
+@app.get("/api/api-keys", response_model=list[schemas.APIKeyWithUsage])
 async def read_api_keys(
    skip: int = 0, limit: int = 100,
    db: Session = Depends(get_db),
    _ = Depends(require_admin_auth),
 ):
-    return db.query(APIKeyModel).offset(skip).limit(limit).all()
+    keys = db.query(APIKeyModel).offset(skip).limit(limit).all()
+    result = []
+    for key in keys:
+        item = schemas.APIKeyWithUsage.model_validate(key)
+        usage = db.query(UsageModel).filter(UsageModel.api_key_id == key.id).first()
+        if usage:
+            item.tokens_used_today = usage.tokens_used_today or 0
+            item.tokens_used_month = usage.tokens_used_month or 0
+            item.requests_today = usage.requests_today or 0
+            item.requests_month = usage.requests_month or 0
+        result.append(item)
+    return result

@app.post("/api/api-keys", response_model=schemas.APIKeyCreated)
 async def create_api_key(
@@ -87,6 +98,32 @@ async def deactivate_api_key(
    db.commit()
    return {"message": "API key deactivated"}

+@app.put("/api/api-keys/{api_key_id}/activate")
+async def activate_api_key(
+    api_key_id: int,
+    db: Session = Depends(get_db),
+    _ = Depends(require_admin_auth),
+):
+    db_key = db.query(APIKeyModel).filter(APIKeyModel.id == api_key_id).first()
+    if not db_key:
+        raise HTTPException(status_code=404, detail="API key not found")
+    db_key.is_active = True
+    db.commit()
+    return {"message": "API key activated"}
+
+@app.delete("/api/api-keys/{api_key_id}")
+async def delete_api_key(
+    api_key_id: int,
+    db: Session = Depends(get_db),
+    _ = Depends(require_admin_auth),
+):
+    db_key = db.query(APIKeyModel).filter(APIKeyModel.id == api_key_id).first()
+    if not db_key:
+        raise HTTPException(status_code=404, detail="API key not found")
+    db.delete(db_key)
+    db.commit()
+    return {"message": "API key deleted"}
+
@app.get("/api/proxy-info")
 async def get_proxy_info(_ = Depends(require_admin_auth)):
    host = os.getenv("PROXY_HOST", "0.0.0.0")
@@ -107,9 +144,10 @@ async def update_settings(
    db: Session = Depends(get_db),
    _ = Depends(require_admin_auth),
 ):
-    crud.set_setting(db, "ollama_url", settings.ollama_url)
+    ollama_url = settings.ollama_url.rstrip('/').removesuffix('/v1')
+    crud.set_setting(db, "ollama_url", ollama_url)
    crud.set_setting(db, "default_model", settings.default_model)
-    return settings
+    return schemas.Settings(ollama_url=ollama_url, default_model=settings.default_model)

@app.get("/api/ollama-models")
 async def get_ollama_models(
@@ -40,6 +40,7 @@ def create_api_key(
    db_key = APIKey(
        name=name,
        key=_hash_api_key(raw_key),
+        key_prefix=raw_key[:12],
        expires_at=expires_at,
        daily_tokens=daily_tokens,
        monthly_tokens=monthly_tokens,
@@ -1,135 +1,133 @@
-import time
-import uuid
+import logging
+import os
+from logging.handlers import RotatingFileHandler
+from pathlib import Path
+
 from fastapi import FastAPI, HTTPException, Depends, Request
-from fastapi.responses import JSONResponse
+from fastapi.responses import JSONResponse, StreamingResponse
 from sqlalchemy.orm import Session
-from database import get_db, SessionLocal
+from database import get_db
 import crud
 import httpx
-import os

-app = FastAPI(title="Ollama Proxy")
+# Rotating usage log (8 KB per file, 3 backups)
+_log_path = Path(os.getenv("LOG_FILE", "logs/usage.log"))
+_log_path.parent.mkdir(parents=True, exist_ok=True)
+_handler = RotatingFileHandler(str(_log_path), maxBytes=8192, backupCount=3, encoding="utf-8")
+_handler.setFormatter(logging.Formatter("%(asctime)s | %(message)s", datefmt="%Y-%m-%d %H:%M:%S"))
+usage_log = logging.getLogger("proxy.usage")
+usage_log.setLevel(logging.INFO)
+usage_log.addHandler(_handler)
+usage_log.propagate = False

-async def proxy_request(url: str, method: str = "GET", json_data: dict = None, headers: dict = None):
-    async with httpx.AsyncClient() as client:
-        response = await client.request(method=method, url=url, json=json_data, headers=headers)
-        return response
+def _last_user_msg(messages: list, max_len: int = 120) -> str:
+    for msg in reversed(messages):
+        if msg.get("role") == "user":
+            text = (msg.get("content") or "").replace("\n", " ").strip()
+            return text[:max_len] + ("…" if len(text) > max_len else "")
+    return ""

-@app.middleware("http")
-async def authenticate_and_quota(request: Request, call_next):
+async def require_api_key(request: Request, db: Session = Depends(get_db)):
    auth_header = request.headers.get("Authorization", "")
    if auth_header.startswith("Bearer "):
-        api_key = auth_header.replace("Bearer ", "")
+        api_key = auth_header[7:]
    elif auth_header.startswith("sk-"):
        api_key = auth_header
    else:
-        return JSONResponse(status_code=401, content={"detail": "Invalid or missing API key"})
+        raise HTTPException(status_code=401, detail="Invalid or missing API key")
+    db_key = crud.verify_api_key(db, api_key)
+    if not db_key:
+        raise HTTPException(status_code=401, detail="Invalid API key")
+    request.state.api_key_id = db_key.id
+    request.state.api_key_name = db_key.name

-    # Uses its own session since middleware cannot use Depends
-    db = SessionLocal()
-    try:
-        db_key = crud.verify_api_key(db, api_key)
-        if not db_key:
-            return JSONResponse(status_code=401, content={"detail": "Invalid API key"})
-        request.state.api_key_id = db_key.id
-    finally:
-        db.close()
+app = FastAPI(title="Ollama Proxy", dependencies=[Depends(require_api_key)])

-    response = await call_next(request)
-    return response
+async def proxy_request(url: str, method: str = "GET", json_data: dict = None):
+    async with httpx.AsyncClient(timeout=300.0) as client:
+        response = await client.request(method=method, url=url, json=json_data)
+        return response

@app.post("/api/generate")
 async def generate(request: Request, db: Session = Depends(get_db)):
-    api_key_id = request.state.api_key_id
    ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
-
    body = await request.json()
-
    prompt_tokens = crud.count_tokens(body.get("prompt", ""))
-    if not crud.check_and_increment_quota(db, api_key_id, tokens=prompt_tokens, requests=1):
+
+    if not crud.check_and_increment_quota(db, request.state.api_key_id, tokens=prompt_tokens, requests=1):
        raise HTTPException(status_code=429, detail="Quota exceeded")

-    response = await proxy_request(f"{ollama_url}/api/generate", method="POST", json_data=body, headers=dict(request.headers))
-    return JSONResponse(content=response.json(), status_code=response.status_code, headers=dict(response.headers))
+    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)
+    response = await proxy_request(f"{ollama_url}/api/generate", method="POST", json_data=body)
+    return JSONResponse(content=response.json(), status_code=response.status_code)

@app.post("/api/chat")
 async def chat(request: Request, db: Session = Depends(get_db)):
-    api_key_id = request.state.api_key_id
    ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
-
    body = await request.json()
+    messages = body.get("messages", [])
+    prompt_tokens = sum(crud.count_tokens(msg.get("content") or "") for msg in messages)

-    prompt_tokens = sum(crud.count_tokens(msg.get("content", "")) for msg in body.get("messages", []))
-    if not crud.check_and_increment_quota(db, api_key_id, tokens=prompt_tokens, requests=1):
+    if not crud.check_and_increment_quota(db, request.state.api_key_id, tokens=prompt_tokens, requests=1):
        raise HTTPException(status_code=429, detail="Quota exceeded")

-    response = await proxy_request(f"{ollama_url}/api/chat", method="POST", json_data=body, headers=dict(request.headers))
-    return JSONResponse(content=response.json(), status_code=response.status_code, headers=dict(response.headers))
+    usage_log.info('%s | /api/chat | %s | ~%d tokens | "%s"',
+                   request.state.api_key_name, body.get("model", "?"), prompt_tokens, _last_user_msg(messages))
+    response = await proxy_request(f"{ollama_url}/api/chat", method="POST", json_data=body)
+    return JSONResponse(content=response.json(), status_code=response.status_code)

@app.get("/api/tags")
-async def list_models(request: Request, db: Session = Depends(get_db)):
+async def list_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/tags", method="GET", headers=dict(request.headers))
-    return JSONResponse(content=response.json(), status_code=response.status_code, headers=dict(response.headers))
+    response = await proxy_request(f"{ollama_url}/api/tags", method="GET")
+    return JSONResponse(content=response.json(), status_code=response.status_code)

@app.get("/api/versions")
-async def versions(request: Request, db: Session = Depends(get_db)):
+async def versions(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/versions", method="GET", headers=dict(request.headers))
-    return JSONResponse(content=response.json(), status_code=response.status_code, headers=dict(response.headers))
+    response = await proxy_request(f"{ollama_url}/api/versions", method="GET")
+    return JSONResponse(content=response.json(), status_code=response.status_code)

@app.get("/v1/models")
-async def list_openai_models(request: Request, db: Session = Depends(get_db)):
+async def list_openai_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/tags", method="GET", headers=dict(request.headers))
-    ollama_models = response.json()
-    openai_models = {
-        "object": "list",
-        "data": [
-            {
-                "id": model["name"],
-                "object": "model",
-                "created": int(model["modified_at"][:10].replace("-", "")) * 1000 if "modified_at" in model else 0,
-                "owned_by": "ollama"
-            }
-            for model in ollama_models.get("models", [])
-        ]
-    }
-    return JSONResponse(content=openai_models, status_code=200, headers=dict(response.headers))
+    response = await proxy_request(f"{ollama_url}/v1/models", method="GET")
+    return JSONResponse(content=response.json(), status_code=response.status_code)

@app.post("/v1/chat/completions")
 async def openai_chat_completions(request: Request, db: Session = Depends(get_db)):
-    api_key_id = request.state.api_key_id
    ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
    default_model = crud.get_setting(db, "default_model", os.getenv("DEFAULT_MODEL", "llama3"))

    body = await request.json()
    messages = body.get("messages", [])
-    prompt_tokens = sum(crud.count_tokens(msg.get("content", "")) for msg in messages)
+    prompt_tokens = sum(crud.count_tokens(msg.get("content") or "") for msg in messages)

-    if not crud.check_and_increment_quota(db, api_key_id, tokens=prompt_tokens, requests=1):
+    if not crud.check_and_increment_quota(db, request.state.api_key_id, tokens=prompt_tokens, requests=1):
        raise HTTPException(status_code=429, detail="Quota exceeded")

-    ollama_body = {
-        "model": body.get("model", default_model),
-        "messages": messages,
-        "stream": body.get("stream", False)
-    }
+    if "model" not in body:
+        body = {**body, "model": default_model}

-    response = await proxy_request(f"{ollama_url}/api/chat", method="POST", json_data=ollama_body, headers=dict(request.headers))
-    response_content = response.json().get("message", {}).get("content", "")
-    completion_tokens = crud.count_tokens(response_content)
+    model_name = body["model"]
+    usage_log.info('%s | /v1/chat/completions | %s | ~%d tokens | "%s"',
+                   request.state.api_key_name, model_name, prompt_tokens, _last_user_msg(messages))

-    openai_response = {
-        "id": f"chatcmpl-{uuid.uuid4().hex}",
-        "object": "chat.completion",
-        "created": int(time.time()),
-        "model": body.get("model", default_model),
-        "choices": [{"index": 0, "message": {"role": "assistant", "content": response_content}, "finish_reason": "stop"}],
-        "usage": {
-            "prompt_tokens": prompt_tokens,
-            "completion_tokens": completion_tokens,
-            "total_tokens": prompt_tokens + completion_tokens,
-        },
-    }
-    return JSONResponse(content=openai_response, status_code=200, headers={"Content-Type": "application/json"})
+    target = f"{ollama_url}/v1/chat/completions"
+
+    if body.get("stream"):
+        async def generate():
+            async with httpx.AsyncClient(timeout=300.0) as client:
+                async with client.stream("POST", target, json=body) as resp:
+                    async for chunk in resp.aiter_bytes():
+                        yield chunk
+        return StreamingResponse(
+            generate(),
+            media_type="text/event-stream",
+            headers={"Cache-Control": "no-cache", "X-Accel-Buffering": "no"},
+        )
+
+    response = await proxy_request(target, method="POST", json_data=body)
+    return JSONResponse(content=response.json(), status_code=response.status_code)
@@ -10,6 +10,7 @@ class APIKey(Base):
    id = Column(Integer, primary_key=True, index=True)
    name = Column(String)
    key = Column(String, unique=True, index=True)
+    key_prefix = Column(String)
    is_active = Column(Boolean, default=True)
    created_at = Column(DateTime(timezone=True), default=_now)
    expires_at = Column(DateTime(timezone=True), nullable=True)
@@ -14,6 +14,7 @@ class APIKey(BaseModel):
    id: int
    name: str
    key: str
+    key_prefix: Optional[str] = None
    is_active: bool
    created_at: datetime
    expires_at: Optional[datetime] = None
@@ -49,5 +50,14 @@ class UsageStats(BaseModel):
    daily_reset_at: Optional[datetime] = None
    monthly_reset_at: Optional[datetime] = None

+    class Config:
+        from_attributes = True
+
+class APIKeyWithUsage(APIKey):
+    tokens_used_today: int = 0
+    tokens_used_month: int = 0
+    requests_today: int = 0
+    requests_month: int = 0
+
    class Config:
        from_attributes = True
@@ -0,0 +1,30 @@
+#!/bin/bash
+set -e
+cd "$(dirname "$0")"
+
+IMAGE=mediaeng/llmproxy
+PLATFORM=linux/arm64
+
+VERSION=$(git describe --tags --always)
+if [ -z "$VERSION" ]; then
+    echo "Fehler: git describe liefert kein Ergebnis"
+    exit 1
+fi
+
+echo "Version : $VERSION"
+echo "Image   : $IMAGE"
+echo "Platform: $PLATFORM"
+echo "Tags    : $IMAGE:$VERSION  $IMAGE:latest"
+echo ""
+
+docker buildx build \
+    --platform "$PLATFORM" \
+    --push \
+    -t "$IMAGE:$VERSION" \
+    -t "$IMAGE:latest" \
+    .
+
+echo ""
+echo "Fertig. Gepusht:"
+echo "  docker pull $IMAGE:$VERSION"
+echo "  docker pull $IMAGE:latest"
@@ -3,12 +3,29 @@ import ReactDOM from 'react-dom/client';
 import axios from 'axios';
 import './styles.css';

-const maskKey = (key) => `••••••••${key.slice(-4)}`;
+const displayKey = (prefix) => prefix ? `${prefix}••••••••` : '••••••••••••';

 function authHeaders(token) {
  return { Authorization: `Bearer ${token}` };
 }

+const fmtK = (n) => { const k = n / 1000; return k % 1 === 0 ? `${k}k` : `${k.toFixed(1)}k`; };
+
+function QuotaBar({ used, limit, isToken = false }) {
+  if (limit == null) return <span className="quota-unlimited">∞</span>;
+  const pct = Math.min(100, (used / limit) * 100);
+  const color = pct >= 90 ? '#e74c3c' : pct >= 70 ? '#e67e22' : '#27ae60';
+  const fmt = isToken ? fmtK : (n) => n.toLocaleString('de-DE');
+  return (
+    <div className="quota-cell">
+      <span className="quota-label">{fmt(used)} / {fmt(limit)}</span>
+      <div className="progress-bar">
+        <div className="progress-fill" style={{ width: `${pct}%`, backgroundColor: color }} />
+      </div>
+    </div>
+  );
+}
+
 function Login({ onLogin }) {
  const [password, setPassword] = useState('');
  const [error, setError] = useState(null);
@@ -162,6 +179,8 @@ function App() {
  const [newKey, setNewKey] = useState(null);
  const [form, setForm] = useState(EMPTY_KEY_FORM);
  const [creating, setCreating] = useState(false);
+  const [editKey, setEditKey] = useState(null);
+  const [editForm, setEditForm] = useState({});

  useEffect(() => {
    if (!password) { setLoading(false); return; }
@@ -183,8 +202,8 @@ function App() {
    try {
      const payload = { name: form.name };
      if (form.expires_at)       payload.expires_at       = new Date(form.expires_at).toISOString();
-      if (form.daily_tokens)     payload.daily_tokens     = Number(form.daily_tokens);
-      if (form.monthly_tokens)   payload.monthly_tokens   = Number(form.monthly_tokens);
+      if (form.daily_tokens)     payload.daily_tokens     = Number(form.daily_tokens) * 1000;
+      if (form.monthly_tokens)   payload.monthly_tokens   = Number(form.monthly_tokens) * 1000;
      if (form.daily_requests)   payload.daily_requests   = Number(form.daily_requests);
      if (form.monthly_requests) payload.monthly_requests = Number(form.monthly_requests);

@@ -208,6 +227,53 @@ function App() {
    }
  };

+  const handleActivate = async (id) => {
+    try {
+      await axios.put(`/api/api-keys/${id}/activate`, {}, { headers: authHeaders(password) });
+      await fetchApiKeys();
+    } catch {
+      setError('Fehler beim Aktivieren.');
+    }
+  };
+
+  const handleDelete = async (id, name) => {
+    if (!window.confirm(`API-Key "${name}" wirklich löschen?`)) return;
+    try {
+      await axios.delete(`/api/api-keys/${id}`, { headers: authHeaders(password) });
+      if (editKey?.id === id) setEditKey(null);
+      await fetchApiKeys();
+    } catch {
+      setError('Fehler beim Löschen.');
+    }
+  };
+
+  const handleEdit = (key) => {
+    setEditKey(key);
+    setEditForm({
+      daily_tokens:     key.daily_tokens    != null ? key.daily_tokens / 1000    : '',
+      monthly_tokens:   key.monthly_tokens  != null ? key.monthly_tokens / 1000  : '',
+      daily_requests:   key.daily_requests  ?? '',
+      monthly_requests: key.monthly_requests ?? '',
+    });
+  };
+
+  const handleSaveEdit = async (e) => {
+    e.preventDefault();
+    try {
+      const payload = {
+        daily_tokens:     editForm.daily_tokens     !== '' ? Number(editForm.daily_tokens) * 1000     : null,
+        monthly_tokens:   editForm.monthly_tokens   !== '' ? Number(editForm.monthly_tokens) * 1000   : null,
+        daily_requests:   editForm.daily_requests   !== '' ? Number(editForm.daily_requests)   : null,
+        monthly_requests: editForm.monthly_requests !== '' ? Number(editForm.monthly_requests) : null,
+      };
+      await axios.patch(`/api/api-keys/${editKey.id}/quota`, payload, { headers: authHeaders(password) });
+      setEditKey(null);
+      await fetchApiKeys();
+    } catch {
+      setError('Fehler beim Speichern der Limits.');
+    }
+  };
+
  const logout = () => {
    sessionStorage.removeItem('admin_password');
    setPassword(null);
@@ -229,43 +295,76 @@ function App() {
      <section>
        <h2>Neuer API-Key</h2>
        <form onSubmit={handleCreate} className="create-form">
-          <input
-            placeholder="Name"
-            value={form.name}
-            onChange={(e) => setForm({ ...form, name: e.target.value })}
-            required
-          />
-          <input
-            type="date"
-            placeholder="Ablaufdatum (leer = unbegrenzt)"
-            value={form.expires_at}
-            onChange={(e) => setForm({ ...form, expires_at: e.target.value })}
-          />
-          <input
-            type="number"
-            placeholder="Tokens/Tag (leer = unbegrenzt)"
-            value={form.daily_tokens}
-            onChange={(e) => setForm({ ...form, daily_tokens: e.target.value })}
-          />
-          <input
-            type="number"
-            placeholder="Tokens/Monat"
-            value={form.monthly_tokens}
-            onChange={(e) => setForm({ ...form, monthly_tokens: e.target.value })}
-          />
-          <input
-            type="number"
-            placeholder="Requests/Tag"
-            value={form.daily_requests}
-            onChange={(e) => setForm({ ...form, daily_requests: e.target.value })}
-          />
-          <input
-            type="number"
-            placeholder="Requests/Monat"
-            value={form.monthly_requests}
-            onChange={(e) => setForm({ ...form, monthly_requests: e.target.value })}
-          />
-          <button type="submit" disabled={creating}>Erstellen</button>
+          <div className="edit-form">
+            <label className="create-name">
+              Name
+              <small>&nbsp;</small>
+              <input
+                value={form.name}
+                onChange={(e) => setForm({ ...form, name: e.target.value })}
+                required
+                placeholder="z. B. alice"
+              />
+            </label>
+            <label className="create-date">
+              Ablaufdatum
+              <small>leer = unbegrenzt</small>
+              <input
+                type="date"
+                value={form.expires_at}
+                onChange={(e) => setForm({ ...form, expires_at: e.target.value })}
+              />
+            </label>
+            <div className="create-btn-wrap">
+              <button type="submit" disabled={creating} className="btn-save">Erstellen</button>
+            </div>
+          </div>
+          <div className="edit-form">
+            <label>
+              Tokens/Tag (k)
+              <small>leer = unbegrenzt</small>
+              <input
+                type="number"
+                min="0"
+                placeholder="∞"
+                value={form.daily_tokens}
+                onChange={(e) => setForm({ ...form, daily_tokens: e.target.value })}
+              />
+            </label>
+            <label>
+              Tokens/Monat (k)
+              <small>leer = unbegrenzt</small>
+              <input
+                type="number"
+                min="0"
+                placeholder="∞"
+                value={form.monthly_tokens}
+                onChange={(e) => setForm({ ...form, monthly_tokens: e.target.value })}
+              />
+            </label>
+            <label>
+              Requests/Tag
+              <small>leer = unbegrenzt</small>
+              <input
+                type="number"
+                min="0"
+                placeholder="∞"
+                value={form.daily_requests}
+                onChange={(e) => setForm({ ...form, daily_requests: e.target.value })}
+              />
+            </label>
+            <label>
+              Requests/Monat
+              <small>leer = unbegrenzt</small>
+              <input
+                type="number"
+                min="0"
+                placeholder="∞"
+                value={form.monthly_requests}
+                onChange={(e) => setForm({ ...form, monthly_requests: e.target.value })}
+              />
+            </label>
+          </div>
        </form>
        {newKey && (
          <div className="new-key-box">
@@ -281,41 +380,99 @@ function App() {
        <table>
          <thead>
            <tr>
-              <th>ID</th>
+              <th></th>
              <th>Name</th>
              <th>Key</th>
-              <th>Status</th>
              <th>Läuft ab</th>
-              <th>Tokens/Tag</th>
-              <th>Tokens/Monat</th>
-              <th>Req/Tag</th>
-              <th>Req/Monat</th>
+              <th className="th-quota">Tokens/Tag</th>
+              <th className="th-quota">Tokens/Monat</th>
+              <th className="th-quota">Req/Tag</th>
+              <th className="th-quota">Req/Monat</th>
              <th></th>
            </tr>
          </thead>
          <tbody>
            {apiKeys.map(key => (
-              <tr key={key.id}>
-                <td>{key.id}</td>
+              <tr key={key.id} className={editKey?.id === key.id ? 'row-editing' : ''}>
+                <td className="td-status">
+                  <span className={key.is_active ? 'status-active' : 'status-inactive'} title={key.is_active ? 'Aktiv' : 'Inaktiv'}>●</span>
+                </td>
                <td>{key.name}</td>
-                <td>{maskKey(key.key)}</td>
-                <td>{key.is_active ? 'Aktiv' : 'Inaktiv'}</td>
+                <td>{displayKey(key.key_prefix)}</td>
                <td>{key.expires_at ? new Date(key.expires_at).toLocaleDateString('de-DE', { timeZone: 'Europe/Berlin' }) : '∞'}</td>
-                <td>{key.daily_tokens ?? '∞'}</td>
-                <td>{key.monthly_tokens ?? '∞'}</td>
-                <td>{key.daily_requests ?? '∞'}</td>
-                <td>{key.monthly_requests ?? '∞'}</td>
-                <td>
-                  {key.is_active && (
-                    <button className="btn-danger" onClick={() => handleDeactivate(key.id)}>
-                      Deaktivieren
-                    </button>
+                <td><QuotaBar used={key.tokens_used_today} limit={key.daily_tokens} isToken /></td>
+                <td><QuotaBar used={key.tokens_used_month} limit={key.monthly_tokens} isToken /></td>
+                <td><QuotaBar used={key.requests_today} limit={key.daily_requests} /></td>
+                <td><QuotaBar used={key.requests_month} limit={key.monthly_requests} /></td>
+                <td className="action-cell">
+                  <button className="btn-icon btn-icon-edit" data-tooltip="Bearbeiten" onClick={() => handleEdit(key)}>✏</button>
+                  {key.is_active ? (
+                    <button className="btn-icon btn-icon-warn" data-tooltip="Deaktivieren" onClick={() => handleDeactivate(key.id)}>⏸</button>
+                  ) : (
+                    <button className="btn-icon btn-icon-ok" data-tooltip="Aktivieren" onClick={() => handleActivate(key.id)}>▶</button>
                  )}
+                  <button className="btn-icon btn-icon-danger" data-tooltip="Löschen" onClick={() => handleDelete(key.id, key.name)}>✕</button>
                </td>
              </tr>
            ))}
          </tbody>
        </table>
+
+        {editKey && (
+          <div className="edit-section">
+            <h3>Limits bearbeiten: <em>{editKey.name}</em></h3>
+            <form onSubmit={handleSaveEdit} className="edit-form">
+              <label>
+                Tokens/Tag (k)
+                <small>leer = unbegrenzt</small>
+                <input
+                  type="number"
+                  min="0"
+                  value={editForm.daily_tokens}
+                  onChange={(e) => setEditForm({ ...editForm, daily_tokens: e.target.value })}
+                  placeholder="∞"
+                />
+              </label>
+              <label>
+                Tokens/Monat (k)
+                <small>leer = unbegrenzt</small>
+                <input
+                  type="number"
+                  min="0"
+                  value={editForm.monthly_tokens}
+                  onChange={(e) => setEditForm({ ...editForm, monthly_tokens: e.target.value })}
+                  placeholder="∞"
+                />
+              </label>
+              <label>
+                Requests/Tag
+                <small>leer = unbegrenzt</small>
+                <input
+                  type="number"
+                  min="0"
+                  value={editForm.daily_requests}
+                  onChange={(e) => setEditForm({ ...editForm, daily_requests: e.target.value })}
+                  placeholder="∞"
+                />
+              </label>
+              <label>
+                Requests/Monat
+                <small>leer = unbegrenzt</small>
+                <input
+                  type="number"
+                  min="0"
+                  value={editForm.monthly_requests}
+                  onChange={(e) => setEditForm({ ...editForm, monthly_requests: e.target.value })}
+                  placeholder="∞"
+                />
+              </label>
+              <div className="edit-actions">
+                <button type="submit" className="btn-save">Speichern</button>
+                <button type="button" className="btn-cancel" onClick={() => setEditKey(null)}>Abbrechen</button>
+              </div>
+            </form>
+          </div>
+        )}
      </section>
    </div>
  );
@@ -325,4 +482,4 @@ ReactDOM.createRoot(document.getElementById('root')).render(
  <React.StrictMode>
    <App />
  </React.StrictMode>
-);
+);
@@ -92,30 +92,37 @@ tr:hover {

 .create-form {
  display: flex;
-  flex-wrap: wrap;
-  gap: 10px;
+  flex-direction: column;
+  gap: 12px;
+}
+
+.create-form .edit-form {
+  margin-bottom: 0;
+}
+
+.create-name {
+  flex: 0 0 auto !important;
+}
+
+.create-name input {
+  width: 200px;
+}
+
+.create-date {
+  flex: 0 0 auto !important;
+}
+
+.create-date input[type="date"] {
+  width: 150px;
+}
+
+.create-btn-wrap {
+  flex: 0 0 auto;
+  display: flex;
  align-items: flex-end;
 }

-.create-form input {
-  padding: 8px 10px;
-  border: 1px solid #ccc;
-  border-radius: 4px;
-  font-size: 14px;
-  flex: 1 1 160px;
-}
-
-.create-form button {
-  padding: 8px 20px;
-  background: #27ae60;
-  color: white;
-  border: none;
-  border-radius: 4px;
-  cursor: pointer;
-  font-size: 14px;
-}
-
-.create-form button:disabled {
+.create-form .btn-save:disabled {
  opacity: 0.6;
  cursor: not-allowed;
 }
@@ -218,3 +225,198 @@ tr:hover {
  color: #999;
  font-size: 12px;
 }
+
+/* Quota progress bars */
+.th-quota {
+  width: 90px;
+}
+
+.quota-cell {
+  width: 100%;
+}
+
+.quota-label {
+  font-size: 12px;
+  color: #555;
+  white-space: nowrap;
+}
+
+.quota-unlimited {
+  color: #aaa;
+  font-size: 14px;
+}
+
+.progress-bar {
+  height: 4px;
+  background: #e2e8f0;
+  border-radius: 2px;
+  margin-top: 4px;
+}
+
+.progress-fill {
+  height: 100%;
+  border-radius: 2px;
+  transition: width 0.3s ease;
+}
+
+/* Edit form */
+.td-status {
+  width: 20px;
+  text-align: center;
+}
+
+.status-active  { color: #27ae60; font-size: 12px; }
+.status-inactive { color: #bdc3c7; font-size: 12px; }
+
+.btn-icon {
+  background: none;
+  border: none;
+  cursor: pointer;
+  font-size: 16px;
+  padding: 2px 4px;
+  margin-right: 2px;
+  border-radius: 3px;
+  line-height: 1;
+  position: relative;
+}
+
+.btn-icon:hover {
+  background: rgba(0, 0, 0, 0.06);
+}
+
+.btn-icon-edit   { color: #2980b9; }
+.btn-icon-warn   { color: #e67e22; }
+.btn-icon-ok     { color: #27ae60; }
+.btn-icon-danger { color: #e74c3c; }
+
+.btn-icon::after {
+  content: attr(data-tooltip);
+  position: absolute;
+  bottom: calc(100% + 8px);
+  left: 50%;
+  transform: translateX(-50%);
+  background: #2c3e50;
+  color: white;
+  padding: 5px 10px;
+  border-radius: 5px;
+  font-size: 12px;
+  font-weight: 400;
+  white-space: nowrap;
+  opacity: 0;
+  pointer-events: none;
+  transition: opacity 0.15s;
+  z-index: 1000;
+}
+
+.btn-icon::before {
+  content: '';
+  position: absolute;
+  bottom: calc(100% + 2px);
+  left: 50%;
+  transform: translateX(-50%);
+  border: 5px solid transparent;
+  border-top-color: #2c3e50;
+  opacity: 0;
+  pointer-events: none;
+  transition: opacity 0.15s;
+  z-index: 1000;
+}
+
+.btn-icon:hover::after,
+.btn-icon:hover::before {
+  opacity: 1;
+}
+
+.action-cell {
+  white-space: nowrap;
+  position: relative;
+  overflow: visible;
+}
+
+.row-editing {
+  background: #eaf4fb !important;
+}
+
+.edit-section {
+  margin-top: 20px;
+  padding: 16px 20px;
+  background: #f0f7ff;
+  border: 1px solid #3498db;
+  border-radius: 6px;
+}
+
+.edit-section h3 {
+  margin: 0 0 14px;
+  font-size: 15px;
+  color: #2c3e50;
+  font-weight: 600;
+}
+
+.edit-section h3 em {
+  font-style: normal;
+  color: #2980b9;
+}
+
+.edit-form {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 14px;
+  align-items: flex-end;
+}
+
+.edit-form label {
+  display: flex;
+  flex-direction: column;
+  gap: 3px;
+  font-size: 13px;
+  font-weight: 500;
+  color: #34495e;
+}
+
+.edit-form label small {
+  font-weight: 400;
+  color: #999;
+  font-size: 11px;
+}
+
+.edit-form input {
+  padding: 6px 8px;
+  border: 1px solid #bdc3c7;
+  border-radius: 4px;
+  font-size: 14px;
+  width: 130px;
+}
+
+.edit-actions {
+  display: flex;
+  gap: 8px;
+  padding-bottom: 2px;
+}
+
+.btn-save {
+  padding: 6px 18px;
+  background: #27ae60;
+  color: white;
+  border: none;
+  border-radius: 4px;
+  cursor: pointer;
+  font-size: 13px;
+}
+
+.btn-save:hover {
+  background: #219a52;
+}
+
+.btn-cancel {
+  padding: 6px 18px;
+  background: #95a5a6;
+  color: white;
+  border: none;
+  border-radius: 4px;
+  cursor: pointer;
+  font-size: 13px;
+}
+
+.btn-cancel:hover {
+  background: #7f8c8d;
+}
@@ -0,0 +1,86 @@
+#!/usr/bin/env python3
+"""Dev runner: startet Proxy, Admin-API und Frontend gemeinsam."""
+import os
+import sys
+import signal
+import subprocess
+import threading
+from pathlib import Path
+
+
+def load_env(path: Path):
+    if not path.exists():
+        return
+    for line in path.read_text(encoding='utf-8').splitlines():
+        line = line.strip()
+        if line and not line.startswith('#') and '=' in line:
+            key, _, val = line.partition('=')
+            os.environ.setdefault(key.strip(), val.strip().strip('"\''))
+
+
+def pipe_output(proc: subprocess.Popen, label: str, color: str):
+    reset = '\033[0m'
+    prefix = f'\033[{color}m[{label}]{reset} '
+    for raw in iter(proc.stdout.readline, b''):
+        sys.stdout.write(prefix + raw.decode(errors='replace'))
+        sys.stdout.flush()
+
+
+def main():
+    root = Path(__file__).parent
+    load_env(root / '.env')
+
+    if not os.environ.get('ADMIN_PASSWORD'):
+        print('Fehler: ADMIN_PASSWORD nicht gesetzt (siehe .env)')
+        sys.exit(1)
+
+    python  = root / '.venv' / 'bin' / 'python'
+    backend = root / 'backend'
+    frontend = root / 'frontend'
+
+    proxy_host = os.environ.get('PROXY_HOST', '0.0.0.0')
+    proxy_port = os.environ.get('PROXY_PORT', '8000')
+    admin_port = os.environ.get('ADMIN_PORT', '8001')
+
+    print('Initialisiere Datenbank...')
+    subprocess.run([str(python), 'init_db.py'], cwd=backend, check=True)
+
+    print(f'Starte Proxy      → http://{proxy_host}:{proxy_port}')
+    print(f'Starte Admin-API  → http://127.0.0.1:{admin_port}')
+    print('Starte Frontend   → http://localhost:5173')
+
+    env = {**os.environ, 'PYTHONUNBUFFERED': '1'}
+
+    procs = [
+        (subprocess.Popen(
+            [str(python), '-m', 'uvicorn', 'main:app', '--reload',
+             '--host', proxy_host, '--port', proxy_port],
+            cwd=backend, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, env=env,
+        ), 'Proxy   ', '34'),  # blau
+        (subprocess.Popen(
+            [str(python), '-m', 'uvicorn', 'admin:app', '--reload',
+             '--host', '127.0.0.1', '--port', admin_port],
+            cwd=backend, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, env=env,
+        ), 'Admin   ', '33'),  # gelb
+        (subprocess.Popen(
+            ['npm', 'run', 'dev'],
+            cwd=frontend, stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
+        ), 'Frontend', '32'),  # grün
+    ]
+
+    for proc, label, color in procs:
+        threading.Thread(target=pipe_output, args=(proc, label, color), daemon=True).start()
+
+    def stop(*_):
+        for p, _, _ in procs:
+            p.terminate()
+
+    signal.signal(signal.SIGINT, stop)
+    signal.signal(signal.SIGTERM, stop)
+
+    for p, _, _ in procs:
+        p.wait()
+
+
+if __name__ == '__main__':
+    main()
Author	SHA1	Message	Date
Oliver Hofmann	c46c1c2b12	Clarify that Ollama can run remotely, not just on Docker host	2026-04-29 08:51:23 +02:00
Oliver Hofmann	d243523906	Split host-Ollama compose into SQLite and PostgreSQL variants	2026-04-29 08:47:40 +02:00
Oliver Hofmann	2319434b0f	Add host-Ollama compose variant, fix leftover port 8001 exposure	2026-04-29 08:43:54 +02:00
Oliver Hofmann	7912431ffb	Remove ALLOWED_ORIGINS from DockerHub docs (dev-only setting)	2026-04-29 08:38:38 +02:00
Oliver Hofmann	114c45dc7e	Remove port 8001 exposure from all Docker examples	2026-04-29 08:36:59 +02:00
Oliver Hofmann	6f67f29f68	Fix depends_on syntax in PostgreSQL compose example	2026-04-29 08:31:25 +02:00
Oliver Hofmann	3b7c88bf2c	Install psycopg2-binary in Dockerfile only, not in dev requirements	2026-04-29 08:30:16 +02:00
Oliver Hofmann	03712fe401	Add DockerHub README with usage, env vars and compose examples	2026-04-29 08:26:47 +02:00
Oliver Hofmann	a0512b3b2b	Replace build_push.py with build_push.sh, use shell script run config	2026-04-29 08:23:07 +02:00
Oliver Hofmann	511e85ea79	Add Docker build/push run config for arm64	2026-04-29 08:20:15 +02:00
Oliver Hofmann	cdaec894d8	Add PyCharm Dev run config and dev runner script - run_dev.py: starts proxy, admin and frontend together with colored output per process; handles SIGTERM from PyCharm Stop button - .idea/runConfigurations/Dev.xml: PyCharm Python run config - .gitignore: allow Dev.xml via layered negation pattern - vite.config.js: open browser automatically on dev server start	2026-04-29 08:14:33 +02:00
Oliver HofmannandClaude Sonnet 4.6	dd8f69ecb6	Proxy fixes, streaming support, Admin-UI overhaul Backend: - Fix Content-Length mismatch by not forwarding client headers to Ollama - Proxy /v1/chat/completions directly to Ollama's OpenAI-compatible endpoint (eliminates manual Ollama↔OpenAI format conversion, fixes tool use) - Add streaming support via SSE passthrough - Fix ollama_url /v1 suffix stripped on save - Replace BaseHTTPMiddleware with FastAPI global dependency (fixes double logging) - Add rotating usage log (8 KB, logs key name + model + token estimate + prompt preview) - Add httpx timeout 300s - Add activate and delete endpoints for API keys - Return usage data (tokens/requests) in GET /api/api-keys Frontend: - Admin table: remove ID column, status as icon, icon-only action buttons with CSS tooltips - Add activate + delete buttons; edit available for inactive keys too - Quota columns: fixed equal width, progress bars with k-unit formatting - Create form: structured layout matching edit form style - Edit form: token inputs in k units (÷1000 display, ×1000 on save) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-04-29 07:48:10 +02:00
Oliver Hofmann	c62cafc202	Store key_prefix for readable key display instead of masked hash The last-4 of the SHA-256 hash was meaningless for identification. Now storing the first 12 chars of the plaintext key as key_prefix, displayed as 'sk-aBcDeFgH••••••••' — consistent with what the user sees at creation time and how GitHub/OpenAI handle it.	2026-04-28 10:23:37 +02:00