dsh-token-monitor: DeepSeek Harness Real-Time Usage and Balance Monitoring Plugin
The `dsh-token-monitor` plugin provides real-time token usage statistics and balance queries for DeepSeek Harness (DSH). It listens to event streams to persistently store usage data and securely queries the official balance using a Node child process and OpenSSL. The plugin displays a fixed floating widget, supports light and dark themes, and offers collapsible styling. It can be installed via CLI or manual configuration, provides a local API endpoint for data retrieval, and keeps the API key from passing through the browser, with access limited to the local machine.
Read Moredsh-token-monitor: DSH Web Large Model Quota and Usage Monitor Plugin
It is standard for DSH users to connect to multiple model providers simultaneously: Kimi For Coding utilizes subscription quotas, DeepSeek Official deducts balance based on usage, and OpenRouter tracks credits. To check "how much is remaining" or "how much has been spent this month," users typically have to log in to each provider's console separately, toggling back and forth. By the time the round of checks is complete, work at hand is often interrupted. dsh-token-monitor integrates this functionality directly into DSH Web: it features a persistent balance badge in the session header, an additional "Usage" tab in the main area, and local SQLite records tracking token usage and estimated costs for each API call. Below, we introduce its features, installation, and configuration. # What is this? dsh-token-monitor is a component of DeepSeek Harness (
Read Moredsh-token-monitor: DSH Sidebar Token Usage Plugin
`zhangzheng25/dsh-token-monitor` is a DeepSeek Harness (DSH) plugin designed to provide intuitive token usage monitoring. It adheres to the DSH "everything is a plugin" philosophy, displaying a "Today's Usage" card at the bottom of the sidebar. Clicking it opens a statistics window showing token totals for today, the last 7 days, and the last 30 days, along with stacked usage charts by model, model rankings, and session statistics. The plugin auto-refreshes every 30 seconds, supports idempotent historical backfill to include pre-installation usage in statistics, and persists data bucketed by day for 181 days. Installation requires Node.js >=20 and can be done via the `dsh plugin add` command from GitHub or a local directory, with the plugin taking effect after restarting DSH. The project采
Read More