anthropics / anthropics/claude-code

[Bug] Anthropic API Error: Opus 5 safeguards triggered on benign input

Open
#93,149 0 comments 1 reaction 0 assignees View on GitHub
area:model bug duplicate platform:windows
Dominant language
Python
Stars
145k
Forks
23.1k
PR merge metrics
PR metrics pending

Description

**Bug Description**
▐▛███▛█ Claude Code v2.1.247
▝▜██████▀ Opus 4.8 with max effort · Claude Pro
▝▝ ▝▝ C:\Users\minzhan

❯ /status
⎿ Set Fast mode to ON

❯ HI

● Opus 5'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. Switched to Opus 4.8. Send feedback with /feedback or learn more

Details: `[cyber]`
⎿ Tip: You can configure model switch behavior in /config

Hey! What are you working on today?

✻ Cooked for 7s · done 1:00 AM

**Environment Info**
- Platform: win32
- Terminal: windows-terminal
- Version: 2.1.247
- Feedback ID: 3fccd952-61b6-4a9e-b190-2bef72ce6545

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

Contributor guide

No contributing guide indexed for this repository

Research direction

Reproduce the report in Claude Code v2.1.247 on Windows by sending “HI” after enabling Fast mode and observe the Opus 5 safeguard response and fallback to Opus 4.8. No source files or tests are identified in the issue, so the work is complete only when this benign input no longer triggers the safeguard unexpectedly.

Written by the indexing model from the issue text.

Assessment

Domain
api, cli
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.