Preflight Checklist
What's Wrong?
I'm on the Max (5x) plan and use Claude Code with Opus 5 as the main model (effort: max). The advisor is turned off. Even so, my weekly Fable limit keeps getting used up. In my understanding the Fable limit should not be touched.
What Should Happen?
Usage from Opus 5 sessions should only count toward the all-models limit. The weekly Fable meter should only go up when a Fable model actually runs (as the main model, advisor or subagent). If Claude Code calls Fable in the background for any reason, that should be visible in /usage.
Error Messages/Logs
Steps to Reproduce
- Use Claude Code on a Max (5x) subscription.
- Set the main model to Opus 5 with /model and turn the advisor off (/advisor off).
- Work normally with Opus 5 (in my case one long session with about 835k of 1M tokens of context, effort: max).
- Open the plan usage panel or run /usage.
- The "Weekly · Fable" meter has gone up even though no Fable model was used.
Claude Model
Opus
Is this a regression?
I don't know
Last Working Version
No response
Claude Code Version
2.1.251 (Claude Code)
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
PowerShell
Additional Information
No response
Preflight Checklist
What's Wrong?
I'm on the Max (5x) plan and use Claude Code with Opus 5 as the main model (effort: max). The advisor is turned off. Even so, my weekly Fable limit keeps getting used up. In my understanding the Fable limit should not be touched.
What Should Happen?
Usage from Opus 5 sessions should only count toward the all-models limit. The weekly Fable meter should only go up when a Fable model actually runs (as the main model, advisor or subagent). If Claude Code calls Fable in the background for any reason, that should be visible in /usage.
Error Messages/Logs
Steps to Reproduce
Claude Model
Opus
Is this a regression?
I don't know
Last Working Version
No response
Claude Code Version
2.1.251 (Claude Code)
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
PowerShell
Additional Information
No response