You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe.
Yes. I have poor spelling skills, which makes drafting complex prompts in the terminal difficult. My current workaround is to type my prompts into the Gemini web interface (to catch typos) and then cut and paste them into the CLI. This workflow is inefficient and breaks the immersive experience of the tool. This feature would also be a significant accessibility improvement for developers who do not speak English as a primary language.
Describe the solution you'd like
I propose adding a lightweight spell-check functionality directly to the input loop.
Architecture: We could utilize nspell and dictionary-en as dependencies.
Logic: The tokenizer in src/ui/utils/highlight.ts could be updated to identify words within default tokens and check them against the dictionary, assigning a new 'misspelled' token type.
UI: Update src/ui/components/InputPrompt.tsx to render these tokens with a visual cue (e.g., red underline) and handle interactions (like a mouse click) to display suggestions.
Toggle: A configuration option in config.yaml to enable/disable this behavior.
Describe alternatives you've considered
Current Workaround: Drafting in the Gemini Web App to verify spelling, then pasting into the terminal.
External Editors: Using VS Code or Notepad, which creates context switching.
Additional context
I have an implementation plan drafted that involves hooking into parseInputForHighlighting for the logic and InputPrompt for the UI rendering. I am happy to share that or submit a PR if this approach sounds acceptable to the maintainers.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Is your feature request related to a problem? Please describe.
Yes. I have poor spelling skills, which makes drafting complex prompts in the terminal difficult. My current workaround is to type my prompts into the Gemini web interface (to catch typos) and then cut and paste them into the CLI. This workflow is inefficient and breaks the immersive experience of the tool. This feature would also be a significant accessibility improvement for developers who do not speak English as a primary language.
Describe the solution you'd like
I propose adding a lightweight spell-check functionality directly to the input loop.
nspellanddictionary-enas dependencies.src/ui/utils/highlight.tscould be updated to identify words within default tokens and check them against the dictionary, assigning a new'misspelled'token type.src/ui/components/InputPrompt.tsxto render these tokens with a visual cue (e.g., red underline) and handle interactions (like a mouse click) to display suggestions.config.yamlto enable/disable this behavior.Describe alternatives you've considered
Additional context
I have an implementation plan drafted that involves hooking into
parseInputForHighlightingfor the logic andInputPromptfor the UI rendering. I am happy to share that or submit a PR if this approach sounds acceptable to the maintainers.Beta Was this translation helpful? Give feedback.
All reactions