- Replace ZSH_AUTOSUGGEST_ALLOW_EMPTY_BUFFER with AI_MIN_INPUT
- Add ZSH_AUTOSUGGEST_AI_DEBUG environment variable
- Add debug logging function to diagnose failures
- Update history lines default from 20 to 5
- Update pwd history preference default to no
Min input provides clearer semantics: set to 0 for empty-buffer
suggestions or higher to require minimum input. Debug logging helps
diagnose missing suggestions by showing API request flow.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
Enable AI suggestions on empty prompts with enhanced
environmental context.
- Update AI_MIN_INPUT default from 3 to 0
- Add ALLOW_EMPTY_BUFFER opt-in config variable
- Remove empty-buffer guards in modify, suggest, enable
- Add zle-line-init hook for prompt-time suggestions
- Enhance history gathering with PWD-aware priority
- Add env context for dir listing, git branch, status
- Implement dual prompts: predict vs complete modes
- Add prompt artifact stripping for $ and > prefixes
- Update README with empty buffer configuration
- Add tests for empty buffer and artifact stripping
Empty buffer suggestions require zsh 5.3+ and work best with
AI strategy, leveraging directory context, git state, and
command history to predict likely next actions.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Based on https://github.com/Valodim/zsh-capture-completion
`zpty -r` with a pattern seems to have some funky behavior on older
versions, giving unpredictable results
Don't use `-s` option to `zmodload`. It is not available in zsh versions
older than 5.3
If running in sync mode and a completion takes a long time, the user can
^C out of it. We need to use `always` in the strategy function or the
pty will not be destroyed in this case and the next time we go to create
it, it will fail, making the shell unusable.
User can have many different completion styles set that will modify what
they've already typed. These styles will result in suggestions that
don't match what the user has already typed. We try our best to unset
some of the more problematic ones, but add some code to fetch to
invalidate suggestions that don't match what the user's already typed.
See technique used in `fast-syntax-highlighting`:
- ca2e18bbc9
- http://www.zsh.org/mla/users/2018/msg00424.html
Also see http://www.zsh.org/mla/users/2018/msg00432.html
In async response handler:
- We only want to read data in case of POLLIN or POLLHUP. Not POLLNVAL
or select error.
- We always want to remove the handler, so it doesn't get called in an
infinite loop when error is nval or err.
There is an upstream bug that prevents ctrl-c from resetting the prompt
immediately after a suggestion has been fetched asynchronously. A patch
has been submitted, but a workaround for now is to add `command true`
after the exec.
See https://github.com/zsh-users/zsh-autosuggestions/issues/364
This fixes a small issue in src/widgets.zsh which makes it so if you
alias [ to g[ (as is done in prezto if the gnu-utility module is loaded)
autosuggestions would fail.
The documentation for GNU test mentions that -o and -a should be avoided
if possible because it's not very clear. Also, with zsh and [[ -o
actually tests if an option is set, which makes this option even more
confusing.
Frad LEE
Eric Freese
Kaleb Elwert