[Bug] Free Tier account getting 100m daily tokens after new update
Nobody has claimed this yet.
- Dominant language
- No language data
- Stars
- 22
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
提交前确认 · Pre-submission checklist
- 我已搜索过现有 issue,确认这不是重复 / I searched existing issues and confirmed this isn't a duplicate.
- 我已阅读 CONTRIBUTING.md / I've read CONTRIBUTING.md.
问题类别 · Category
计费 / 配额 · Billing / Quota
涉及的 Agent 框架 · Agent framework
ZCode Agent(自研)
严重程度 · Severity
影响体验 · Major (功能可用但体验受损 / works but degraded)
复现频率 · Reproducibility
必现 · Always
问题描述 · Description
I don't have any paid account and only one Free Tier account, which today in ZCode got 100m tokens daly usage in the new update. The UI is duplicated and it seems to be a bug, because there's no documentation of this new usage anywhere.
I noticed I had more usage but I didn't know it was this much until I opened the model settings. Now that I searched it, it seems clear that is a bug, followed by the other visual bug.
I know some folks won't like this post, but it's the correct thing to do, we shouldn't abuse broken limits, specially at Zai which is struggling with hardware.
复现步骤 · Steps to reproduce
Open Zcode
Enter in a Free Account
See usage in the context window
Expand that menu of today's balance in Model Settings
期望表现 · Expected behavior
It should have only two models there
实际表现 · Actual behavior
Thera are three models there, one being the primary that is the GLM 5.3 duplicated, but with insane tokens to use.
ZCode 版本 · ZCode version
3.8.1
设备 / 系统 / 浏览器 · Device / OS / Browser
Windows 11
截图 / 录屏 / 日志 · Screenshots / Recordings / Logs
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the issue in ZCode 3.8.1 on Windows 11 with a Free Tier account, then inspect the Model Settings usage display and the context-window balance. Done means the duplicate GLM 5.3 entry and incorrect 100m-token allowance no longer appear, leaving the intended two models and quota.
Written by the indexing model from the issue text.
Assessment
- Domain
- backend, frontend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 42/100