[AutoComplete] UX requests for AutoComplete tool

## Type of Issue

Select the type of issue:
- [ ] Bug report (to report a bug)
- [ ] Feature request (to request an additional feature)
- [x] Tracker (I am just using this as a tracker)
- [ ] Refactor request
- [ ] Documentation Ask

## Checklist

Use this checklist if you are using this issue as a tracker:

- [x] I think it'd be great if Action dict text box could be resizable (especially for bigger dictionaries)
- [ ] Once I reach the end of annotations, it says "congrats" but still keeps showing the last text I annotated with empty dict which confuses me whether I should that empty dict for the same command ? Is it possible to just wipe out the text box + action dict (not even show {} , just empty it) when we reach end of annotations ?
- [x] README: instructions on what to do after save - probably point at running the upload to s3 script ? Should we just upload as is or rename the files ?
- [x] I double checked but the annotations I wrote (for commands coming from annotated.txt) do not get substituted in place in file annotated.txt but I see the changes in autocomplete_timestamp.txt file
- [x] Allow "OTHER" sub dictionaries for situations where a sub-logical form is not possible with our current grammar, but could be clearly isolated in the logical form
- [ ] proper re-focusing/re-centering cursor after [enter] jsonification