Commit graph

7 commits

Author SHA1 Message Date
Yun Chan
10af20a0ad feat(commands): multi-select ordered command pipeline with step reordering and single-pass composition (AI-05, AI-07) 2026-10-31 02:54:54 +09:00
Yun Chan
3cac14f668 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).
2026-10-03 21:48:28 +09:00
Yun Chan
ba0dbbd813 refactor(instructions): share instruction template rendering via @d3ro/core 2026-09-28 00:53:44 +09:00
Yun Chan
39b8e7448e feat(caption): stream live captions and polish finished lines in context
Replaces the fixed six-second batches with a streaming track per audio
source: the uncommitted audio is re-recognised every second and sent as a
partial with its agreed (stable) prefix, a short pause finalises the line,
and long unbroken speech is committed at Whisper segment boundaries. Idle
audio is trimmed so silence cannot produce invented sentences.

Finished lines are corrected by the local model against the previous lines
and replaced in place; edits that change too much are rejected. The
behaviour can be switched off in Settings.
2026-09-24 20:22:21 +09:00
Yun Chan
2fe20fa7b5 release: ship v1.6.0 with paged suggestions and a cleaner phrase memory
Some checks failed
deploy-site / deploy (push) Failing after 39s
release / release-windows (push) Failing after 3m41s
portable-unsigned / portable-windows (push) Failing after 12m23s
Next-sentence suggestions now arrive one at a time up to twelve, shown three
per page with Ctrl+Alt+Up/Down to move, Left/Right to page, Enter to accept
and Esc to close; old default bindings migrate and the panel guide follows the
live bindings. The overlay is redesigned, stays put while candidates stream
and sits outside the input box when no caret is reported.

The personal phrase memory stops learning from terminals, code editors and
the coding-agent hub, ignores symbol-heavy lines and empty-field placeholders,
and prunes existing entries that break those rules.

Fixes suggestion keys starting dictation, installs stuck on a pre-1.5.0
speech engine without the focus endpoint, Ollama runner windows flashing
while typing, the speech engine starting twice, and cold-model timeouts.
Live captions can be dragged to a remembered position and show a waiting
notice until the first line arrives.

Bumps the product version to 1.6.0 (Android/iOS build 1060000).
2026-09-24 19:56:28 +09:00
Yun Chan
5c11ee2fde release: ship v1.5.0 with on-device writing suggestions
Some checks failed
deploy-site / deploy (push) Failing after 33s
portable-unsigned / portable-windows (push) Failing after 4m7s
release / release-windows (push) Failing after 3m16s
Adds next-sentence suggestions while typing, weekly input insights and a
personal phrase memory to the desktop app, and fixes custom instructions so
they process the text instead of inserting the instruction's own wording.
Local model requests are now bounded and individually cancellable.

Bumps the product version to 1.5.0 (Android/iOS build 1050000), refreshes the
landing and web download links, and records the new INPUT feature rows and the
open verification gaps in the infrastructure map.
2026-09-23 16:04:27 +09:00
Yun Chan
99f06c253c fix(llm): stop leaking instruction prompts instead of processed text
Running a custom instruction (translate, summarise, rewrite, explain code,
free prompt) inserted the instruction's own wording instead of the result.
Two faults stacked:

The instruction was passed as the text to process, leaving the system-prompt
argument empty. `BASE_SYSTEM_PROMPTS` has no `custom` key, so resolution fell
back to `refine` without saying so, and the model dutifully polished the
instruction it had been handed. The transcript never reached it.

And only `{{text}}` was substituted, which none of the five built-in
instructions use — they carry `{{targetLanguage}}`, `{{userPrompt}}`, or no
placeholder at all. The substitution was a no-op from the day it was written:
the presets landed ten hours before the code that expected them.

- Instruction prompts now go to the system-prompt argument and the transcript
  to the text argument. Instructions that spell out `{{text}}` keep their old
  meaning, so hand-written ones still work.
- `renderInstructionPrompt` resolves `{{text}}`, `{{userPrompt}}` and
  `{{targetLanguage}}` in one place, and warns by name when a placeholder is
  left standing rather than letting it reach the model.
- `resolveSystemPrompt` no longer drops silently to `refine` for `custom`.
- Voice shortcuts no longer die at the `defaultLLMAction === 'none'` gate; an
  explicitly named instruction outranks the default. Without one, `none` still
  passes the transcript through untouched.
- `translate` receives its target language instead of relying on a default two
  call frames away. It is still always English — `AppConfig` has no key for it,
  and neither `language` (UI locale) nor `sttLanguage` (source language) can
  stand in. Choosing a target language needs a setting and is not in this fix.
- Chains ran instructions with placeholders intact; they share the same
  resolution now.
- The command screen's pipeline bench called `llm.generate`, which preload does
  not expose, so every run threw and the catch showed the input back as if it
  had succeeded. It uses `llm.process` now, over the same path production
  takes, and a failure reads as a failure.

Present since the feature shipped: the custom-instruction path has never
worked. Plain actions (refine, summarise, grammar, expand) were unaffected and
are now covered by tests so they stay that way.
2026-09-21 14:39:26 +09:00