dsh-sound
DeepSeek Harness 插件:为对话结束、审批、提问、计划审查、目标受阻、任务失败等事件提供独立的提示音及音量控制。
AI 分析
为 DSH 的各种运行状态(如任务完成、等待审批、报错等)配置个性化声音提醒。适合在后台挂机运行智能体、需要通过听觉反馈及时介入或获知任务进度的用户。
安裝
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AI-Galaxy-GPU/dsh-sound說明文件
閱讀完整 README ↗Configuration storage
- The browser half persists its configuration in localStorage (key
dsh-sound:config), sanitizing every read and filling defaults. Uploaded local music files are stored in IndexedDB (dsh-sound-audio) instead — no localStorage quota limits. - Config keys:
enabled,quietCurrent, and six sound + six volume fields —completionSound/approvalSound/questionSound/planReviewSound/goalBlockedSound/failureSound(builtin key,none,local,data:URL, oraudio:) andcompletionVolume…failureVolume(0–1).localFileskeeps the last chosen local file per event so switching to a built-in sound and back does not drop it. - 0.2.0 migration: older configs are upgraded automatically —
defaultSoundbecomescompletionSound, voice/TTS values degrade to the per-event default, andworkspaces/debounceMs/ globalvolume/ voice settings are dropped. - Export / import: the settings panel downloads the full config as JSON (IndexedDB audio references are inlined as data URLs) and restores it from a JSON file — moving browsers or machines does not require reconfiguration.
- The host half also registers the
dsh-soundsettings namespace: on rc.6 the settings API allowlist (WEB_SETTINGS_NAMESPACESindsh-host-apiproxy) does not expose third-party namespaces to browsers, so the client does not depend onsettingsScopetoday; the registration keeps the migration path open for future releases.