niushuanan/xiaozhuang-dsh--plugins-runtime-pulse ↗★ 2

@deepseek-ai/dsh-runtime-pulse

A compact, progressively disclosed session runtime summary for Xiaozhuang's DeepSeek Harness profile.

AI 分析

核心用途是直观展示当前对话的性能指标。适合需要监控对话延迟、首字输出时间（TTFT）、生成速度、Token 消耗及缓存命中率的开发者或性能调优任务。

エージェント開発ツール生産性

パッケージ: @deepseek-ai/dsh-runtime-pulse
バージョン: 1.0.0
ライセンス: MIT
最終更新: 2026/09/05

インストール

npx -p @deepseek-ai/dsh dsh plugin --profile web add github:niushuanan/xiaozhuang-dsh#bb949c3d291ea55d378cc5fdb1b237b4f63127b6&path:plugins/runtime-pulse

ドキュメント

README 全文を読む ↗

Data and usage

15 · Model usage (standalone repository)

Check the DeepSeek balance and KIMI, GLM, and GPT quotas from the conversation header, refreshed every five minutes.

DeepSeek, KIMI, GLM, and GPT model usage cards

16 · Session runtime details

Expand the current session's turns, steps, latency, time to first token, output speed, and cache hits.

Current session steps, latency, speed, and token details

17 · Token overview (standalone repository)

Review tokens, calls, and cost trends across local clients for today, seven days, this month, or all time.

Cross-client token metrics and time-of-day usage trend