dsh-token-usage
Token usage and cache efficiency analytics dashboard for DeepSeek Harness.
Install
No clear install command was found in the current repository evidence.
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.
Key Capabilities
- Captures token consumption (input, output, reasoning, cache read/write) from session logs and LLM streams
- Provides interactive sidebar UI with trend lines, donut breakdown charts, and filtering by model and timeframe
- Calculates cache hit efficiency ratios to monitor prompt caching effectiveness
- Aggregates metrics by model name, provider, project directory, caller source, account, and date
- Performs automatic startup backfills by scanning existing session logs without losing historical data
- Includes built-in self-updater and zero-restart hot reloading via internal Cordis fibers
- Exposes local HTTP API endpoints for metric summaries, data flushing, manual rebuilding, and updates
Useful For
- Monitoring token usage patterns and prompt cache hit rates across workflows and subagents
- Auditing LLM usage and expenditure breakdown across multiple providers and projects
- Investigating context compaction and session title generation token overhead
Who It Fits
- DeepSeek Harness users tracking daily and project-specific token consumption
- Developers optimizing prompt structures and evaluating cache efficiency
- Teams managing multiple LLM providers and account allocations
Documented Limitations
- Historical token usage cannot be attributed to specific user accounts because session logs lack account identifiers
- Failed model request attempts typically report zero token usage upstream, capturing call frequency rather than consumed tokens
- Hot reload relies on Cordis internal loader APIs and may necessitate a complete DSH restart if host module internals diverge
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 1 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- hugoyee75-cmyk/dsh-token-usage
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 72cf5f2 · 2026-10-19
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
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-19
- Last release
- 2026-10-19
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Skill manager UI for DeepSeek Harness to discover, toggle, import, and update agent skills.
View plugin →Session lifecycle manager for DeepSeek Harness with search, restore, idle cleanup, and diagnosis.
View plugin →Theme, wallpaper, and styling plugin for DeepSeek Harness with 8 preset themes, glassmorphism, accent colors, and custom theme packs.
View plugin →Cost and token tracking plugin for DeepSeek Harness featuring session budgets, provider balances, and coding plan quotas.
View plugin →