Because I don't want to lose context, I frequently input tasks into the AI ...
- Dominant language
- No language data
- Stars
- 2.1k
- Forks
- 153
- PR merge metrics
- No merged PRs in 30d
Description
Because I don't want to lose context, I frequently input tasks into the AI within a session, constantly interrupting it. I prefer the design pattern of Codex, where my input is automatically turned into the next task and temporarily placed in the task queue. If I want it to become a guide, I can quickly click to send it directly. I sincerely hope you can take a look at it.
---
| Field | Value |
| --- | --- |
| App version | 1.1.6 |
| OS | macOS 26.2.0 |
| Theme | GitHub |
| Path | /chat |
| Tenure | Week 10 |
Contributor guide
Research direction
Start at the /chat entry point and review how input is handled while an AI task is running. Compare the requested Codex-style behavior: new input should become a queued next task, with an option to send it directly as guidance; done means both paths work without losing context.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, desktop
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100