zai-org / zai-org/feedback

[建议 / Feature] Anti overload suggestion(Web mostly)

Open
#170 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

priority: P2 status: 待评估 type: 功能建议
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,确认这不是重复提议 / 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

稳定性 / 崩溃 · Stability / Crash

涉及的 Agent 框架 · Agent framework

ZCode Agent(自研)

使用场景 · Use case

not sure what to type there

建议方案 · Proposal

add something similar to rate limits but prompts on web
example - 1 prompt per 3 minuts lim - maybe the timer starts after response done
5 hour limit - 15-30 prompts
week limit - 150 prompts
SUGGESTING OTHER WAY
agent + chatbot limited usage
free plan agent - 25 prompts per day/
free plan chatbot - 50 messages per day/
web pro plan (10-20 dollars/month) - x4 more limits ,
web extra plan (50 dollars/month) - x5 more usage than pro
u may change numbers but it shouldnt be either too limiting like i guess on free plan 10 prompts per 5 hours on agent is acceptable or just like 5 minutes cooldown per prompt
if u would think making it too limiting id say best way is like making cooldown per prompt
3RD IDEA WITH SETTINGS
so i will bring this in percentage usage limits
1% - 1 prompt chatbot
5% - 1 prompt agent (likely per 5 hour)
Also might add dynamic limits where like 500 lines coded/edited = 3-5% usage

  • for basic settings around 3 minutes min message cooldown
    so i can say we may able to off min message cooldown but it will consume usage limit faster but shouldnt be able to put something like 1 prompt per hour like maximum 15 minutes
    no min message cooldown - x1.5 usage
    15 minutes message cooldown - x0.5-0.75 usage
    since id say that if we limit ourself to 15 minutes for 1 prompt it will gradually reduce overload because i guess overload is coming mostly from web
预期价值 · Expected value

this should decrease overloads and make it much reliable to use so you dont get hit with infinite "model is currently at capacity" or "doctypeh is not valid JSON:

你认为的优先级 · Your perceived priority

中 · Medium

你使用的 ZCode 版本 / 环境 · ZCode version / environment

No response

补充材料 · Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are named. First clarify whether the proposal targets web prompts, chatbot messages, agent prompts, or all three, then define the limits, cooldown behavior, plan tiers, and usage calculation that would count as done.

Written by the indexing model from the issue text.

Assessment

Domain
backend, web-dev
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.