← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-usage-vendor-stats

DeepSeek Harness API usage analytics by vendor and KPI, featuring a 53-week heatmap, trend charts, and model drilldown.

VisionUI & ProductivityTerminal & TUIDeveloper ToolsBrowser & Web
1GitHub Stars1ForksUpdated2026-10-02

Install

$ dsh plugin --profile web add "github:kirigayakazima/dsh-usage-vendor-stats"

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-usage-vendor-stats is an analytics and visualization plugin for DeepSeek Harness that aggregates token usage and model invocations across API vendors and providers. It delivers a GitHub-style 53-week activity heatmap, daily and hourly trend charts, model drilldowns, cost estimation, health performance metrics, and CSV export functionality via settings and full-screen overlays.

Key Capabilities

  • Auto-discovers and aggregates usage metrics by vendor and model provenance from durable session logs
  • Displays a GitHub-style 53-week activity heatmap and dual-axis token/calls trend charts
  • Provides token composition breakdown including input, cache hits, output, and reasoning tokens
  • Supports vendor management with custom aliases, subscription/official API categorization, and cost estimations
  • Tracks performance and health metrics including TTFT, generation speed (tokens/sec), peak context, and error rates
  • Exports daily, monthly, and vendor aggregated statistics to CSV

Useful For

  • Analyzing token consumption and cache hit efficiency across multiple AI providers and models
  • Estimating API spending and subscription costs across DeepSeek Harness sessions
  • Monitoring model performance metrics like time-to-first-token and throughput over time
  • Exporting aggregated usage and session statistics for external reporting or auditing

Who It Fits

  • DeepSeek Harness developers and power users managing multiple model providers
  • Engineering leads optimizing token spend and cache hit ratios across teams
  • Users monitoring API latency, context sizes, and model generation throughput

Documented Limitations

  • Relies on DSH durable session logs and assistant/message event metadata for usage telemetry
  • Cost calculations are approximations based on manually configured per-million-token rates

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 0 development, 5 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
kirigayakazima/dsh-usage-vendor-stats
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
74cab29 · 2026-10-15

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
1GitHub stars
Forks
1
Open issues
1
Last commit
2026-10-02
Last release
2026-08-16
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app