[建议 / Feature] delete or edit or own messages; change models but keep the same chat
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
对话 / Agent 交互 · Agent chat / interaction
涉及的 Agent 框架 · Agent framework
多个 / 通用 · Multiple / General
使用场景 · Use case
It's annoying not being able to delete or edit messages, because if you made a mistake you only have the option to clarify it in another message afterwards, so the messages increase and the memory decreases. It's also a basic necessity that any ai chat would need. On another topic, i dont get why when choosing another model because others are down leads you to a new chat. It seems like you're stuck on only one model on each chat
建议方案 · Proposal
Add delete and edit functions for your own messages, as well as staying on the current chat after changing model. There should be a more evident way of changing models on web version.
预期价值 · Expected value
Less messages to clarify mistakes, persistent work even when other models are down so you can keep working on something residing in a chat
你认为的优先级 · Your perceived priority
中 · Medium
你使用的 ZCode 版本 / 环境 · ZCode version / environment
Web
补充材料 · Additional context
No response
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
This feedback issue identifies no source files, tests, or entry points. Start by locating the web chat message controls and model-selection flow; done should include editing and deleting the user's own messages, retaining the current chat when changing models, and making model switching more evident.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, frontend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100