Replace default_model with force_model (model lock)

Removes DEFAULT_MODEL in favour of a force_model setting configurable
via the admin UI. When set, every proxy request's model field is
overridden, preventing uncoordinated model switches during lab sessions.
Updates schemas, admin API, all three proxy endpoints, frontend,
init_db, and docs (README, DOCKERHUB, KURZANLEITUNG).

backend/admin.py

@@ -137,7 +137,7 @@ async def get_proxy_info(_ = Depends(require_admin_auth)):
 async def read_settings(db: Session = Depends(get_db), _ = Depends(require_admin_auth)):
     return schemas.Settings(
         ollama_url=crud.get_setting(db, "ollama_url", "http://localhost:11434"),
-        default_model=crud.get_setting(db, "default_model", "llama3"),
+        force_model=crud.get_setting(db, "force_model") or None,
     )
 
 @app.put("/api/settings", response_model=schemas.Settings)
@@ -148,8 +148,8 @@ async def update_settings(
 ):
     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 schemas.Settings(ollama_url=ollama_url, default_model=settings.default_model)
+    crud.set_setting(db, "force_model", settings.force_model or "")
+    return schemas.Settings(ollama_url=ollama_url, force_model=settings.force_model or None)
 
 @app.get("/api/ollama-models")
 async def get_ollama_models(

backend/init_db.py

@@ -13,8 +13,6 @@ def init_db():
     db = SessionLocal()
     if not get_setting(db, "ollama_url"):
         set_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
-    if not get_setting(db, "default_model"):
-        set_setting(db, "default_model", os.getenv("DEFAULT_MODEL", "llama3"))
     db.close()
 
     print("Database initialized.")

backend/main.py

@@ -70,8 +70,6 @@ def apply_env_settings():
     try:
         if url := os.getenv("OLLAMA_URL"):
             crud.set_setting(db, "ollama_url", url)
-        if model := os.getenv("DEFAULT_MODEL"):
-            crud.set_setting(db, "default_model", model)
         db.commit()
     finally:
         db.close()
@@ -91,6 +89,9 @@ async def proxy_request(url: str, method: str = "GET", json_data: dict = None):
 async def generate(request: Request, db: Session = Depends(get_db)):
     ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
     body = await request.json()
+    force_model = crud.get_setting(db, "force_model") or None
+    if force_model:
+        body = {**body, "model": force_model}
     prompt_tokens = crud.count_tokens(body.get("prompt", ""))
 
     if not crud.check_and_increment_quota(db, request.state.api_key_id, tokens=prompt_tokens, requests=1):
@@ -115,6 +116,9 @@ async def generate(request: Request, db: Session = Depends(get_db)):
 async def chat(request: Request, db: Session = Depends(get_db)):
     ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
     body = await request.json()
+    force_model = crud.get_setting(db, "force_model") or None
+    if force_model:
+        body = {**body, "model": force_model}
     messages = body.get("messages", [])
     prompt_tokens = sum(crud.count_tokens(_content_to_str(msg.get("content"))) for msg in messages)
 
@@ -156,19 +160,19 @@ async def list_openai_models(db: Session = Depends(get_db)):
 @app.post("/v1/chat/completions")
 async def openai_chat_completions(request: Request, db: Session = Depends(get_db)):
     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()
+    force_model = crud.get_setting(db, "force_model") or None
+    if force_model:
+        body = {**body, "model": force_model}
     messages = body.get("messages", [])
     prompt_tokens = sum(crud.count_tokens(_content_to_str(msg.get("content"))) for msg in messages)
 
     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")
 
-    if "model" not in body:
-        body = {**body, "model": default_model}
+    model_name = body.get("model", "?")
 
-    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))
 

backend/schemas.py

@@ -40,7 +40,7 @@ class QuotaUpdate(BaseModel):
 
 class Settings(BaseModel):
     ollama_url: str
-    default_model: str
+    force_model: Optional[str] = None
 
 class UsageStats(BaseModel):
     tokens_used_today: int = 0