D3RO Voice — 멀티플랫폼 AI 음성 어시스턴트 (Monorepo & CI/CD)
99f06c253c
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.
|
||
|---|---|---|
| .agents | ||
| .claude | ||
| .codex | ||
| .forgejo/workflows | ||
| .github/workflows | ||
| apps | ||
| bucket | ||
| docs | ||
| memory | ||
| packages | ||
| release | ||
| scripts | ||
| server | ||
| site | ||
| tests/e2e | ||
| .dockerignore | ||
| .editorconfig | ||
| .env.example | ||
| .eslintignore | ||
| .eslintrc.cjs | ||
| .gitattributes | ||
| .gitignore | ||
| .gitlab-ci.yml | ||
| .nvmrc | ||
| .prettierrc | ||
| AGENTS.md | ||
| CHANGELOG.md | ||
| CLAUDE.md | ||
| CONTRIBUTING.md | ||
| design.md | ||
| docker-compose.nas.yml | ||
| docker-compose.yml | ||
| Dockerfile.admin | ||
| global.json | ||
| LICENSE | ||
| package-lock.json | ||
| package.json | ||
| pnpm-workspace.yaml | ||
| README-NAS.md | ||
| run-desktop.bat | ||
| SECURITY.md | ||
| skills-lock.json | ||
| tsconfig.base.json | ||
| tsconfig.json | ||
| turbo.json | ||