hofmannol/llmproxy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Return 422 when model field is missing and no force_model is set

Browse Source 
Prevents an opaque Ollama error from reaching the client by failing fast
with a clear message before the request is forwarded.
This commit is contained in:
Oliver Hofmann 2026-05-08 08:04:52 +02:00
parent 34b108f4df
commit f823e7d314
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
backend/main.py
View File

@ -92,6 +92,8 @@ async def generate(request: Request, db: Session = Depends(get_db)):
force_model = crud.get_setting(db, "force_model") or None force_model = crud.get_setting(db, "force_model") or None
if force_model: if force_model:
body = {**body, "model": force_model} body = {**body, "model": force_model}
if not body.get("model"):
raise HTTPException(status_code=422, detail="Field 'model' is required")
prompt_tokens = crud.count_tokens(body.get("prompt", "")) 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): if not crud.check_and_increment_quota(db, request.state.api_key_id, tokens=prompt_tokens, requests=1):
@ -119,6 +121,8 @@ async def chat(request: Request, db: Session = Depends(get_db)):
force_model = crud.get_setting(db, "force_model") or None force_model = crud.get_setting(db, "force_model") or None
if force_model: if force_model:
body = {**body, "model": force_model} body = {**body, "model": force_model}
if not body.get("model"):
raise HTTPException(status_code=422, detail="Field 'model' is required")
messages = body.get("messages", []) messages = body.get("messages", [])
prompt_tokens = sum(crud.count_tokens(_content_to_str(msg.get("content"))) for msg in messages) prompt_tokens = sum(crud.count_tokens(_content_to_str(msg.get("content"))) for msg in messages)
@ -165,13 +169,15 @@ async def openai_chat_completions(request: Request, db: Session = Depends(get_db
force_model = crud.get_setting(db, "force_model") or None force_model = crud.get_setting(db, "force_model") or None
if force_model: if force_model:
body = {**body, "model": force_model} body = {**body, "model": force_model}
if not body.get("model"):
raise HTTPException(status_code=422, detail="Field 'model' is required")
messages = body.get("messages", []) messages = body.get("messages", [])
prompt_tokens = sum(crud.count_tokens(_content_to_str(msg.get("content"))) for msg in 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): 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") raise HTTPException(status_code=429, detail="Quota exceeded")
model_name = body.get("model", "?") model_name = body["model"]
usage_log.info('%s | /v1/chat/completions | %s | ~%d tokens | "%s"', usage_log.info('%s | /v1/chat/completions | %s | ~%d tokens | "%s"',
request.state.api_key_name, model_name, prompt_tokens, _last_user_msg(messages)) request.state.api_key_name, model_name, prompt_tokens, _last_user_msg(messages))