feat(desktop): typo auto-correct and context-aware sentence prediction
Some checks failed
ci / 정본·보안·린트·타입·테스트 (push) Has been cancelled
deploy-site / deploy (push) Has been cancelled
ci / 워크스페이스 빌드 검증 (push) Has been cancelled
ci / 모바일 린트·타입·Jest (push) Has been cancelled
ci / Supabase Edge Functions + Cloudflare Worker (push) Has been cancelled
ci / .NET API 서버 테스트 (push) Has been cancelled

Typo auto-correct (INPUT-19)
- TypoCorrectionService + core typo-correction: 2-set Korean layout
  mistypes both ways, always-wrong spellings, near-misses of the user's
  frequent words, optional model check re-validated in core; applied by
  backspace N + paste and cancelled on new keys or window change.

Prediction quality (INPUT-20/21)
- gemma models are sent raw with the user's unfinished sentence pre-filled
  into the model turn, so the model truly continues the text (mid-word
  joins and spacing exact). Other models keep the instruction prompt.
- Context: text before the caret (opening lines and a fact list of names,
  dates, amounts outside the 400-char window), messages just sent in the
  same chat window (memory only, 30 min), personal-graph follow-ups and
  IDF-ranked related sentences with Korean stemming.
- Guards: first sentence only, restated-prefix stripping (also fixes the
  instruction path), repeat drop, no invented dates/names/numbers
  (one retry), plain -다 register, no emoji unless the user uses them,
  search-box keywords. Fill loop mixes instruction prompts for variety.
- Opt-in real-model probe: tests/integration/suggestion-quality.ollama.test.ts

Suggestions now actually show up
- Terminal (Claude Code): caret trust from the input line, not the whole
  screen (status line below the box blocked every keystroke); Korean
  composition counts as typing at the end; a grey placeholder filling the
  empty box at once is not user text.
- Chrome: UIA focus flicker while typing no longer resets "edited".
- KakaoTalk/RichEdit: trailing paragraph mark ignored for edit position
  and stripped so accepted text keeps its separating space.
- While the overlay is visible the suggestion shortcuts are captured so
  Ctrl+Alt+Enter no longer also types a newline; released when hidden.
- nut-js preloaded after boot (first accept waited 4.8 s).
This commit is contained in:
Yun Chan 2026-10-03 21:48:28 +09:00
parent 5ca3709b32
commit 3cac14f668
56 changed files with 4700 additions and 258 deletions

View file

@ -160,6 +160,36 @@ describe('KeyBindingService — globalShortcut 예약 · 마우스 release', ()
expect(registeredAccelerators()).toEqual(['Control+Shift+V', 'Control+Shift+C'])
})
it('Windows 에서 제안 창이 떠 있는 동안만 제안 단축키를 잡고, 사라지면 푼다 (Ctrl+Alt+Enter 개행 방지)', () => {
setPlatform('win32')
configSet('suggestionEnabled', true)
const service = getKeyBindingService()
service.loadFromConfig()
service.start()
expect(globalShortcut.register).not.toHaveBeenCalled()
service.setSuggestionCaptureActive(true)
expect(registeredAccelerators()).toEqual(
expect.arrayContaining(['Control+Alt+Return', 'Control+Alt+Down', 'Control+Alt+Up', 'Control+Alt+Backspace'])
)
expect(registeredAccelerators()).not.toContain('Control+Shift+V')
service.setSuggestionCaptureActive(false)
const released = vi.mocked(globalShortcut.unregister).mock.calls.map((call) => String(call[0]))
expect(released).toEqual(expect.arrayContaining(['Control+Alt+Return', 'Control+Alt+Down']))
})
it('제안 기능이 꺼져 있으면 제안 창 상태와 무관하게 아무것도 잡지 않는다', () => {
setPlatform('win32')
configSet('suggestionEnabled', false)
const service = getKeyBindingService()
service.loadFromConfig()
service.start()
service.setSuggestionCaptureActive(true)
expect(globalShortcut.register).not.toHaveBeenCalled()
service.setSuggestionCaptureActive(false)
})
it('X1 hold 중 Alt 를 더 누른 채 버튼을 놓아도 dictation 이 released 된다', () => {
setPlatform('win32')
const map = createDefaultBindingMap()