anthropics / anthropics/claude-code
[Bug] Anthropic API Error: Opus 5 safeguards triggered on benign input
- 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