# Troubleshooting

> What you see, why, and what to do: the failures the documentation describes, in one place.

Source: https://opendecisio.com/docs/troubleshooting/

Most failures announce themselves with a status code or a line in the server’s log. This page collects the ones the documentation explains.

 

[Figure: What you see, why, and what to do: ten things the documentation says. Symptoms and fixes: Connection refused right after the start; 422 on a request; 400 on a request; 503 on every request, and /health answers 503; The server will not start and mentions VLLM_USE_DEEP_GEMM; The server refuses a model repository; WARNING: tasks fitted under another model or rendering are not applied at the start; No x-decisio-tasks header on a question you registered; Answers that differ between runs; The first request after a start is slow.]

 

## TL;DR

 

Start with what the server says about itself:

 

```
curl -s -o /dev/null -w '%{http_code}\n' http://127.0.0.1:8000/health
curl -s http://127.0.0.1:8000/v1/tasks
# 200 when the engine is up, 503 when it has died, and 000 while nothing answers yet (the server is still starting)
# the registered tasks, whether tasks are applied, and the server's fingerprint
```

 

Run against the CPU stand-in at v0.11.1 on 2026-10-14.

  

| Word | Meaning |
| --- | --- |
| 422 | the request is malformed or the prompt is too long; the `detail` says what |
| 400 | the engine cannot answer the request |
| 503 | the engine has died |
| fingerprint | the model and rendering a task is fitted under; a task is applied only by a server with the same one |

 

## 1. Is it up?

 

A connection refused right after a start means the server is still starting: the first start downloads the checkpoint and warms the engine. `/health` answers once it is ready (7 min 54 s for the 31B’s first start, with its download, on the measured machine). A 503 means the engine died; the server exits with code 70 and a restart policy brings a new one ([Health and monitoring](https://opendecisio.com/docs/health/)).

 

## 2. Is it the request?

 

A 422 or a 400 comes with a `detail` that names what is wrong; read it first. A prompt over 32,768 tokens is a 422 that says the rendered prompt is longer than the context, and a choice with more than 255 options is a 400. The `model` field does not choose a model, and fields the server does not know are ignored, not rejected.

 

## 3. Is it the tasks?

 

No `x-decisio-tasks` header on a question you registered means it matched no task: ask it exactly as registered. A server that prints `WARNING: tasks fitted under another model or rendering are not applied` at start was given tasks fitted under something else; register them again from their examples ([Teach it your question](https://opendecisio.com/docs/tasks/)).

 

## 4. Is it the answer?

 

Answers can differ between runs on the Gemma bases, which do not repeat bit for bit, and between sessions on the 31B for near-tied options. That is stated per base in [the evaluation card](https://opendecisio.com/docs/evaluation-card/); it is not a fault.

 

## What next

 

- [Health and monitoring](https://opendecisio.com/docs/health/): what `/health` and the headers report.
- [Flags and options](https://opendecisio.com/docs/flags/): every flag, including the ones a start can refuse on.
- [The HTTP API](https://opendecisio.com/docs/api/): every status and field.