check_text
Decide whether a text should be allowed: profanity, slurs, threats and sexual language, including disguised spellings. Returns the action (allow, review, block), the evidence, a one-sentence reason and a censored version. Use context "username" for names shown publicly.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mask | No | ||
| mode | No | ||
| text | Yes | ||
| policy | No | ||
| context | No |