I really like this, however, there are two main flaws.
还没有人认领这个 Issue。
评估
调研方向
Start with the /chat path and the reported skill-invocation and session-context behavior. Reproduce on Windows 10.0.26200 with app version 1.1.22, especially when disable invocation is true; done means skill use is reliable and session context is always visible.
由索引模型根据 Issue 内容生成。
描述
I really like this, however, there are two main flaws.
- Luna tends to fail skills when trying to use them. Especially if disable invocation is true.
- I don't have an easy way to always view the context. I WANT to see session context ALWAYS so I can better choose when to compact. This is the biggest gripe I have thus far.
| Field | Value |
|---|---|
| App version | 1.1.22 |
| OS | Windows 10.0.26200 |
| Theme | GitHub |
| Path | /chat |
| Tenure | Week 6 |
- 主要语言
- 没有语言数据
- 星标
- 2.1k
- 派生
- 157
- PR 合并指标
- 30 天内没有已合并 PR
贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
github/app 的其他 Issue
-
triage
难度 2/5 1-3 小时 新手友好度 70/100
-
难度 2/5 1-3 小时 新手友好度 65/100
-
难度 2/5 1-3 小时 新手友好度 70/100
-
难度 2/5 1-3 小时 新手友好度 70/100
-
难度 2/5 1-3 小时 新手友好度 70/100
相似的 Issue
-
bug follow-up-work-in-progress from-review-extraction llm-providers python severity:should-fix
难度 2/5 1-3 小时 新手友好度 88/100
-
area/evaluation bug
难度 2/5 1-3 小时 新手友好度 75/100
-
[Bug]: OLLAMA_KEEP_ALIVE="5m" / "24h" crashes Ollama embedding and vision models with ValueError 未关闭
难度 2/5 1-3 小时 新手友好度 75/100
infiniflow/ragflow#20223 · 1 个 reaction ·
-
[Bug]: llms-anthropic 0.12.0 rejects claude-opus-5-5 during metadata lookup and agent initialization 未关闭
难度 2/5 1-3 小时 新手友好度 78/100
run-llama/llama_index#23222 ·
-
Bedrock adapter reports a context-window-truncated tool-call completion as a normal stop, not length 未关闭
难度 2/5 1-3 小时 新手友好度 88/100