False-positive AUP refusal on legitimate consumer email follow-up

Exact error

API Error: Claude Code is unable to respond to this request, which appears to violate our Usage Policy (https://www.anthropic.com/legal/aup). Please double press esc to edit your last message or start a new session for Claude Code to assist with a different task. If you are seeing this refusal repeatedly, try running /model claude-sonnet-4-20250514 to switch models.

Facts

• Task: sending a follow-up email to a dental clinic we had prior correspondence with
• Recipient: info@soracamed.com
• Language: Turkish
• Claude drafted the email, I approved, Claude translated, Claude ran a Python SMTP script
• The script succeeded: Sent follow-up to info@soracamed.com
• The refusal appeared on Claude's NEXT response, after the send completed
• The email content: 18 questions about pricing, surgeon credentials, warranty, with inline answer fields

AUP check

Walked through all 14 prohibited categories. Zero matches. The content is a consumer inquiry to a medical provider.

Likely false-positive triggers

• Medical info in-thread (HbA1c, medication list)
• Request for opt-in patient references in Q18
• Inline-answer form layout ("Cevap:" under each question)
• "Before we can discuss arrival dates" phrasing

Environment

• Claude Code 2.1.117
• claude-opus-4-7 (1M context)
• Explanatory output style
• Windows 11

Asks

1. Review classifier sensitivity on this pattern
2. Surface the specific trigger in the refusal message so users can adjust instead of guess
3. Do not fire a refusal after the action has already completed

Keywords

API Error Claude Code unable to respond Usage Policy false positive AUP refusal consumer email follow-up classifier dental medical inquiry