Rank, 14 days: 144 on the Claude Code sheet
2 people reported
All time, since Oct 13.
Safeguards flag messages
“unable to use opus / fable model for agentic tasks. it's give safeguard related restrictions - may be false positive”
Is this your bug? What gets counted gets fixed. Pile on.
Paste this into your agent. It files your report, with your error and version.
I hit this bug: rapsheet.dev/sheets/claude-code/issues/12116/file Follow it to file my report. Show me the text before you send.
No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends
Safeguards flag messages and block responses from Fable model.
Is this your bug?
File my report- Where
- Model safeguards
- Error text
API Error: Fable 5.1's safeguards flagged this message (https://www.anthropic.com/legal/aup). Our intentionally broad safeguards allow us to deliver more capabilities faster, but can sometimes flag legitimate coding and cybersecurity tasks. Claude Code can't respond to this message with Fable 5.1- Versions
- 2.1.296 to 2.1.322. Still reported on the newest version, 2.1.322.
- Platforms
- Linux, Windows
- How bad
- Breaks a normal workflow.
Related: Safeguards block session requests
Not quite your bug?
- Cyber safeguard pauses sessions54 people
- Cyber safeguard blocks sessions381 people
- Reasoning_extraction safeguard block139 people
Original reports2, newest first
- User unable to use Claude Code: recurring error message (no details provided)#108721
- API Error: Fable 5.1's safeguards flagged this message (https://www.anthropic.com/legal/aup). Our intentionally broad safeguards allow us to deliver more capabilities faster, but can sometimes flag legitimate coding and cybersecurity tasks.#101674