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.
Bug 10 fix(MeetingModePage 인라인 가드)를 isImeComposingEvent helper로 추출하고,
한글 위험도 있는 나머지 7개 Enter 핸들러에 일괄 적용. 총 8곳이 이제 동일 helper 경유.
신규:
- apps/desktop/src/renderer/utils/keyboard.ts — isImeComposingEvent(e)
JSDoc에 Bug 10 원리(Chromium이 IME 조합 중 Enter를 2번 발화) + 권장 사용 패턴 포함
적용 8곳:
- pages/MeetingModePage.tsx:164 회의 메모 (기존 인라인 가드 4줄 교체)
- pages/KnowledgeBasePage.tsx:84 RAG 쿼리
- pages/VoiceConversationPage.tsx:113 텍스트 채팅
- pages/CommandsPage.tsx:336 키워드 추가 (Enter+Esc)
- components/meeting/MeetingChatPanel.tsx:111 미팅 챗
- components/meeting/EditableSegment.tsx:70 전사 세그먼트 편집 (Enter+Esc)
- components/meeting/MeetingDetailTabs.tsx:242 미팅 타이틀 (인라인 arrow → 블록)
- components/shared/HistoryEntryCard.tsx:64 태그 추가 (Enter+Esc)
/simplify 패스 품질 리뷰:
- Phase 3.3 CloudSyncService.pushOne 훅 8곳은 이미 fire-and-forget 1줄로 일관.
내부 try-catch가 에러 삼켜 로컬 write 차단 금지 철학 준수 → 수정 없음, 현 상태가 최적.
검증:
- desktop tsc --noEmit EXIT=0
- Vite HMR로 dev 프로세스 자동 반영 (재기동 없음)
- 한글 Enter 시연은 사용자 실측 대기 (VoiceConversationPage / MeetingDetailTabs 대표 2곳)
- npm workspaces 루트 (apps/*, packages/*) 세팅
- V1 전체를 apps/desktop/으로 git mv (src, resources, tests, sidecar,
scripts, electron.vite.config.ts, electron-builder.yml, vitest.config.ts,
tsconfig.node.json, tsconfig.web.json)
- apps/desktop/package.json 신규 (name=@d3ro/desktop)
- productName: 'd3ro-voice' 명시 — app.getName()을 고정하여 userData 경로
%APPDATA%\d3ro-voice\ 그대로 유지 (기존 DB/설정 연속성 보장)
- 루트 package.json을 workspace 루트로 재구성, 공통 devDep만 유지
(typescript, eslint, prettier)
- turbo.json, tsconfig.base.json 추가 (Turborepo 자체 설치는 별도 sub-phase)
- memory/project_status.md 생성 (규칙 13)
검증:
- npm run typecheck 통과
- npm run build 통과 (electron-vite main+preload+renderer)
- npm run dev 실제 실행 → DB/핫키/Ollama 자동 실행 모두 정상
2026-04-08 14:04:41 +09:00
Renamed from src/renderer/pages/CommandsPage.tsx (Browse further)
