DeepSeek Harness web plugin: a live activity line under the composer that says what the turn is actually doing (tool running / waiting on you / retrying / model thinking).
기타 확장
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:NeoWangKing/dsh-activity-line
DSH plugin: auto-select reasoning_effort (low/high/max) per user turn via a MiniMax complexity scorer with heuristic fallback, an effort-router-style token ledger, and a per-reply metadata label (model · effort · tokens · steps, click to jump back). Manual picker in the model popup; scorer triggers ONLY on Auto. GLM-5.3 safe: never picks off/medium, clamps manual off on forced-thinking models.
기타 확장
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:imkingjh999/dsh-adaptive-effort
Adaptive output-token budgeting for DeepSeek Harness: shrink maxTokens as context fills, restore it after compaction, and retry recognized output-budget overflows once.
기타 확장
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:3289192-bot/dsh-adaptive-max-tokens
Android Studio-style ADB logcat viewer for the DSH Web GUI: device list, live logcat streaming, level/tag/text filtering, level colors, floating and docked layouts, draggable height.
기타 확장
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:dxsdyhm/dsh-adb-logcat