@fenzhenhua123/dsh-balance-meter: DeepSeek Harness Balance and Cost Statistics
`@fenzhenhua123/dsh-balance-meter` is a DeepSeek Harness plugin designed to address the lack of intuitive API balance monitoring and cost statistics. It displays the balance and current session cost in the session statistics bar, supports billing segmented by model, cache hit rate, and peak/off-peak periods, and automatically fetches official prices. Users can configure fallback prices. The plugin runs on the host side and enables real-time cost monitoring after installation.
Read Moredsh-cache-cost-monitor: Add cache hit rate and cost monitoring for DSH
`dsh-cache-cost-monitor` is an MIT-licensed plugin for DSH v0.1.x designed to monitor the prefix cache hit rate and API costs during Agent calls. By extracting fields such as `prompt_cache_hit_tokens`, `prompt_cache_miss_tokens`, and `completion_tokens`, it calculates the cache hit rate in real-time and estimates costs based on official pricing (including peak and off-peak hours). The plugin provides a `cache_report` tool for Agents to query detailed reports, supporting trend sparklines and per-round details. Additionally, it displays a persistent status bar on the browser side and the consumption of the current round at the end of each reply. Furthermore, it supports threshold and budget alerts and automatically degrades in case of exceptions to ensure the stability of the main program.
Read MoreDeepSeek Harness Plugin: dsh-plugin-usage-meter (API Usage/Cost/Balance Dashboard)
`dsh-plugin-usage-meter` is a community plugin designed specifically for the DeepSeek Harness (dsh) web interface, aiming to solve the problems of cost accounting and budget monitoring after API usage. The plugin is approximately 0.6MB in size, requires no Electron or separate process, and is mounted through the official profile mechanism—without modifying source code and can be easily uninstalled. Core features include displaying real-time token usage below the input box, cost estimation based on official listed prices, and account balance queries (API Key configuration required). It provides bar charts showing model cost distribution for the current day and the past 7 days, supports peak/off-peak pricing, and offers dual-currency display in CNY/USD. Users can connect to the official billing from `platform.deepseek.com` to verify actual charges, and historical costs automatically...
Read Moredsh-status-bar: DSH Configurable Status Bar Management Plugin
dsh-status-bar is an MIT-licensed DSH client plugin maintained by Starlight-bananice, designed to address issues with the native bottom status bar, such as information truncation and display limitations in narrow windows. The plugin replaces the built-in stats line, offering a highly configurable status bar that supports toggling and rearranging 17 information segments, including model, context pressure, tokens, task queue, and more, with multi-line wrapping to prevent truncation. Its core features include real-time TPS updates based on assistant/chunk events, fee estimation supporting peak/valley pricing and CNY/USD selection, zero-configuration default activation of 13 information segments, and a Usage & cost dialog box that includes cost trend graphs and usage history. The plugin is compatible with DSH 0.
Read Moredsh-spend: DSH Token Usage and Cost Monitoring Plugin
dsh-spend is a web plugin for DeepSeek Harness (DSH), maintained by nonewind under the MIT license. It is designed to address the fragmented monitoring of Token usage, latency, costs, and quotas across multiple providers and models. By replaying session logs from `$DSH_HOME/sessions`, it provides a floating window and detailed panel in the Web UI. Core features include: multi-dimensional statistics by provider, model, time, and session; time-series charts for today, 24 hours, 7 days, and a 52-week activity heatmap; a built-in price database covering 17 providers and 131 models with automatic recognition of Code or Token billing plans, and support for DeepSeek's peak-valley pricing. It also reads real-time data from DeepSeek, M...
Read More