SecurityInsight settings · Settings > AI
AI summary answer length
| Key | OpenAI_MaxTokensPerRequest |
|---|---|
| Where | Settings > AI |
| Type | int |
| Default | 16384 tokens, unless the older AI_MaxTokensPerRequest is set |
| Edition | Community |
What it does
The largest answer, in tokens, the AI may return for each risk-analysis summary request.
When set
Higher allows longer AI summaries but costs more per call and may exceed what your model deployment allows; lower gives shorter, cheaper summaries that may be cut off.
When blank or default
Left blank, the default applies: 16384 tokens, unless the older AI_MaxTokensPerRequest is set
Risk and how to reverse it
Affects whether and how AI is used: when AI is used, asset data is sent to YOUR Azure OpenAI deployment, and it costs per call. Reversible at once; results already produced stay.
Requires
Read by: risk-analysis.
Recommended
Keep the default. Change it when: Rarely; lower it if your model has a smaller limit, raise it if summaries are cut short.
Documented for SecurityInsight 3.0.79. Written by the SecurityInsight team; Invardia publishes it. · All settings · Security review pack