separate "add to current turn" vs "new prompt" input while a turn is running
Preflight Checklist
- [x] I have searched existing requests and this feature hasn't been requested yet
- [x] This is a single feature request (not multiple features)
Problem Statement
When Claude Code is executing, provide two input affordances:
- Add context to the running turn — appended to the in-flight task's context.
- Queue a new, unrelated prompt — held until the current turn finishes; explicitly not part of the running context.
Why: Real usage is conversational — users often add info mid-turn rather than pre-writing perfect prompts. But a single input stream forces the model to guess intent. The common failure: the model pauses to ask a clarifying question, the user's unrelated mid-turn message arrives, and the model misinterprets it as the answer. Distinguishing the two at the input layer removes the ambiguity entirely (and would pair well with a visible "queued prompt" indicator).
Proposed Solution
While Claude Code is executing, provide two input affordances:
Alternative Solutions
_No response_
Priority
High - Significant impact on productivity
Feature Category
Interactive mode (TUI)
Use Case Example
_No response_
Additional Context
_No response_
This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗