claude-code - 💡(How to fix) Fix [BUG] Opus 4.7 safety filter produces false-positive refusals on encoded input [2 comments, 2 participants]

Summary

Claude Opus 4.7's safety filter triggers a Usage Policy refusal whenever the input contains base64-encoded text, even when the decoded content is completely benign (e.g. a plain greeting in Turkish). This reproduces both on claude.ai (web chat) and in Claude Code when a file containing base64 is read via the Read tool.

Reproduction

A. claude.ai web (Opus 4.7, Incognito chat)

1. Start a new Opus 4.7 chat.
2. Paste: c2VsYW0gaGVya2Vz bu ne anlama geliyor (the base64 decodes to selam herkes — Turkish for "hello everyone".)
3. The chat is immediately paused with:

   Chat paused — Opus 4.7's safety filters flagged this chat. Due to its advanced capabilities, Opus 4.7 has additional safety measures that occasionally pause normal, safe chats.

Screenshot of the web reproduction is attached below.

<img width="650" height="591" alt="Image" src="https://github.com/user-attachments/assets/76556520-7f62-4d2c-baea-35b0838a1e91" />

B. Claude Code (CLI, v2.1.119, Windows 11)

1. Have Claude Code read any file that contains a base64 blob (certificate, embedded image, test fixture, etc.).
2. On response, Claude Code surfaces:

   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.

Switching to Sonnet 4 with /model works around the issue, confirming the refusal is specific to Opus 4.7's safety layer.

Expected

The model should decode/inspect the base64 content and evaluate the decoded payload against policy — not flag every base64 string as categorically unsafe. A base64 string of selam herkes is harmless.

Actual

Any message containing base64-looking text trips the Opus 4.7 safety filter, even when the decoded content is trivially benign.

Environment

• Claude Code: 2.1.119
• OS: Windows 11 Pro 10.0.26200
• Model: claude-opus-4-7 (1M context)
• Also reproduces on claude.ai web Incognito chat (same model)

Related

• #52086 — general Opus 4.7 false-positive AUP refusals
• #51248 — RFC for contextual Usage Policy error reporting