anthropics / anthropics/claude-code

[Bug] Anthropic API Error: Opus 5 Safeguards Flagged Legitimate Request

Open
#87,907 0 comments 0 reactions 0 assignees View on GitHub
area:model bug platform:vscode platform:windows stale
Dominant language
Python
Stars
145k
Forks
23.1k
PR merge metrics
PR metrics pending

Description

**Bug Description**
❯ bonjour

─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Session paused

Opus 5 (1M context)'s safeguards flagged this message. Our intentionally broad safeguards allow us to deliver more capabilities faster, but can sometimes flag legitimate coding, cybersecurity, and biology tasks. Send feedback with /feedback or learn more: https://support.claude.com/en/articles/16049681

Details: `[cyber]`

❯ 1. Switch to Opus 4.8
2. Edit prompt and retry with Opus 5 (1M context)

**Environment Info**
- Platform: win32
- Terminal: vscode
- Version: 2.1.235
- Feedback ID: df19c124-77cf-42f2-be3c-a80239803ca8

**Errors**
```json
[]
```

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the reported prompt in Claude Code 2.1.235 on win32 through the VS Code terminal with Opus 5 (1M context), then compare the result with Opus 4.8. Use feedback ID df19c124-77cf-42f2-be3c-a80239803ca8 to investigate; done requires identifying a reproducible cause or a confirmed fix for the false-positive safeguard response.

Written by the indexing model from the issue text.

Assessment

Tech stack
vscode
Domain
security
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.