claude-code - 💡(How to fix) Fix False-positive AUP refusal on legitimate consumer email follow-up [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#51974Fetched 2026-04-23 07:39:56
View on GitHub
Comments
0
Participants
1
Timeline
4
Reactions
0
Author
Participants
Timeline (top)
labeled ×3cross-referenced ×1

Error Message

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

RAW_BUFFERClick to expand / collapse

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: [email protected]
  • Language: Turkish
  • Claude drafted the email, I approved, Claude translated, Claude ran a Python SMTP script
  • The script succeeded: Sent follow-up to [email protected]
  • 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

extent analysis

TL;DR

The issue can be mitigated by adjusting the email content to avoid potential false-positive triggers, such as removing medical information, rephrasing sensitive questions, and altering the inline-answer form layout.

Guidance

  • Review the email content for any medical information or sensitive questions that may be triggering the Usage Policy refusal, and consider rephrasing or removing them.
  • Consider using a different format for the questions, such as a numbered list instead of an inline-answer form layout, to avoid triggering the classifier.
  • Test the email content with a different model, such as claude-sonnet-4-20250514, to see if the issue persists.
  • Provide feedback to the developers to surface the specific trigger in the refusal message, allowing users to adjust their content accordingly.

Example

No code snippet is provided as it is not explicitly supported by the issue.

Notes

The issue may be specific to the claude-opus-4-7 model or the Explanatory output style, and further testing may be needed to determine the root cause.

Recommendation

Apply workaround: Adjust the email content to avoid potential false-positive triggers, as the issue is likely due to the classifier's sensitivity to certain patterns in the email content.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING