| Setting | Default | What it does |
| Min confidence | 0.80 | Answers the AI is less sure about are dropped. Lower it to about 0.60 if it never answers. Raise it if it types wrong answers. |
| Max answer length | 48 | Longer answers are discarded instead of typed. |
| Lowercase answers | Off | Types everything in lowercase. Many quiz servers ignore capitals. |
| Delay (min and max) | 250 to 900 ms | A random wait before typing, measured from when the round was detected. |
| Give up after | 10 s | Answers older than this are discarded. |
| Max solve tokens | 600 | Output budget for the solving call. Reasoning models need more (1500 to 3000). If the log says "truncated by the token cap", raise it. |
| AI requests per hour | No limit | Protects free-tier quotas and costs. When the limit is hit, rounds are skipped and the Activity log says why. The menu shows how many were used in the last hour. |