mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-28 01:21:43 +00:00
The analytics dashboard had three accuracy issues: 1. TOTAL TOKENS excluded cache_read and cache_write tokens — only counted the non-cached input portion. With 90%+ cache hit rates typical in Hermes, this dramatically undercounted actual token usage (e.g. showing 9.1M when the real total was 169M+). 2. The 'API Calls' card displayed session count (COUNT(*) from sessions table), not actual LLM API requests. A single session makes 10-90 API calls through the tool loop, so this was ~30x lower than reality. 3. cache_write_tokens was stored in the DB but never exposed through the analytics API endpoint or frontend. Changes: - Add api_call_count column to sessions table (schema v7 migration) - Persist api_call_count=1 per LLM API call in run_agent.py - Analytics SQL queries now include cache_write_tokens and api_call_count in daily, by_model, and totals aggregations - Frontend TOTAL TOKENS card now shows input + cache_read + cache_write + output (the full prompt total + output) - API CALLS card now uses real api_call_count from DB - New Cache Hit Rate card shows cache efficiency percentage - Bar chart, tooltips, daily table, model table all use prompt totals (input + cache_read + cache_write) instead of just input - Labels changed from 'Input' to 'Prompt' to reflect the full prompt total - TypeScript interfaces and i18n strings updated (en + zh) |
||
|---|---|---|
| .. | ||
| public | ||
| src | ||
| eslint.config.js | ||
| index.html | ||
| package-lock.json | ||
| package.json | ||
| README.md | ||
| tsconfig.app.json | ||
| tsconfig.json | ||
| tsconfig.node.json | ||
| vite.config.ts | ||
Hermes Agent — Web UI
Browser-based dashboard for managing Hermes Agent configuration, API keys, and monitoring active sessions.
Stack
- Vite + React 19 + TypeScript
- Tailwind CSS v4 with custom dark theme
- shadcn/ui-style components (hand-rolled, no CLI dependency)
Development
# Start the backend API server
cd ../
python -m hermes_cli.main web --no-open
# In another terminal, start the Vite dev server (with HMR + API proxy)
cd web/
npm run dev
The Vite dev server proxies /api requests to http://127.0.0.1:9119 (the FastAPI backend).
Build
npm run build
This outputs to ../hermes_cli/web_dist/, which the FastAPI server serves as a static SPA. The built assets are included in the Python package via pyproject.toml package-data.
Structure
src/
├── components/ui/ # Reusable UI primitives (Card, Badge, Button, Input, etc.)
├── lib/
│ ├── api.ts # API client — typed fetch wrappers for all backend endpoints
│ └── utils.ts # cn() helper for Tailwind class merging
├── pages/
│ ├── StatusPage # Agent status, active/recent sessions
│ ├── ConfigPage # Dynamic config editor (reads schema from backend)
│ └── EnvPage # API key management with save/clear
├── App.tsx # Main layout and navigation
├── main.tsx # React entry point
└── index.css # Tailwind imports and theme variables