• v1.15.0 f18cebaa24

    D3RO Voice v1.15.0
    Some checks failed
    ci / 정본·보안·린트·타입·테스트 (push) Failing after 21s
    ci / 모바일 린트·타입·Jest (push) Successful in 40s
    ci / Supabase Edge Functions + Cloudflare Worker (push) Successful in 33s
    ci / .NET API 서버 테스트 (push) Successful in 12s
    ci / 워크스페이스 빌드 검증 (push) Has been skipped
    deploy-site / deploy (push) Successful in 33s
    release / release-windows (push) Failing after 14m1s
    portable-unsigned / portable-windows (push) Failing after 14m6s
    Stable

    yunchan released this 2026-10-30 17:55:55 +00:00 | 45 commits to main since this release

    [1.15.0] - 2026-10-31

    Published from an annotated tag. Installer and update metadata are served by the
    canonical Forgejo feed; no binaries are committed to this repository.

    Added

    • Multi-command ordered pipeline selection & reordering in Commands (CommandsPage.tsx, @d3ro/core/instruction-template, VoiceModeService).
      • Replaces single-select radio buttons in the Commands screen with an ordered multi-select pipeline: check multiple commands in sequence (e.g., 1단계: 구어·추임새·중복 정리 → 2단계: 격식체 변환 or 1단계: 구어·추임새·중복 정리 → 2단계: 텍스트 요약 → 3단계: 번역) and reorder steps anytime with ↑ / ↓ controls.
      • Synthesizes selected pipeline steps into a single ordered pipeline prompt (composeInstructionPipelinePrompt) where later steps determine the final output tone/format/language without adding multi-roundtrip LLM latency, and supports testing the full multi-step pipeline directly in the Commands test runner.

    SHA-256

    • D3RO-Voice-Setup-1.15.0-x64.exe: f6b557acbf003ee392791b14dd4ddc3b8b8c81d843d3e873b310e86e1f652171
    • D3RO-Voice-Setup-1.15.0-x64.exe.blockmap: 759ac7f2ae8a0885cbcc1d9d46c58167c03b48be34830d208f9f2940113c4851
    • latest.yml: 3e14a07d4e8c87b32b7152872adbc6dd5c3c1b532a1e73ec60c196b0ddffacb8
    • latest.yml.sig: 532b23e3aeae0f68811090ea95f07ed7f06056cbff85571d9ed57f42b2573565
    Downloads