anthropics / anthropics/claude-code
[BUG] Claude Code Pro: Daily limit exhausted after ~10 simple questions despite 50% weekly boost
- Langage dominant
- Python
- Étoiles
- 145k
- Forks
- 23.1k
- Métriques de merge des PR
- Métriques de PR en attente
Description
### Preflight Checklist
- [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
### What's Wrong?
I renewed my Claude Code Pro subscription. After ~10 simple questions
(no coding, just Q&A), my 5 hour session limit was full in 40 minutes.
I still have 19% weekly limit remaining (50% boost is active till Sept 13),
but the 5 hour limit keeps running out far too quickly. I've been using claude code for a while now but this is really weird.
This doesn't seem normal. Can you check if there's a token usage issue?
### What Should Happen?
If there is any issue with the token usage, please resolve it.
### Error Messages/Logs
```shell
```
### Steps to Reproduce
1. Open Claude Code Pro with renewed subscription
2. Ask simple questions (no coding)
3. Token limits should be used up too quickly.
### Claude Model
Sonnet (default)
### Is this a regression?
No, this never worked
### Last Working Version
_No response_
### Claude Code Version
2.1.247.
### Platform
Anthropic API
### Operating System
Windows
### Terminal/Shell
PowerShell
### Additional Information
Guide de contribution
Aucun guide de contribution indexé pour ce dépôt
Piste de recherche
No source file, test, or diagnostic log is named. Start by reproducing the reported usage with Claude Code Pro, Sonnet, version 2.1.247 on Windows PowerShell, then compare the five-hour and weekly limit accounting against the reported questions. Done means identifying whether token usage is being miscounted and documenting a verified correction or a clear non-bug explanation.
Rédigé par le modèle d'indexation à partir du texte de l'issue.
Évaluation
- Stack technique
- powershell
- Domaine
- api, cloud
- Type d'issue
- Bug
- Difficulté
- 4/5
- Temps estimé
- 3-5 jours
- Activité
- Active
- Clarté
- À clarifier
- Accessibilité débutants
- 25/100