v1.0.1

Changes

• Added configurable auto-refresh intervals: 1, 3, 5, and 10 minutes, with 5 minutes as the default.
• Prevented hidden, blurred, or stale dashboard tabs from launching provider CLI collection during auto-refresh.
• Kept live collection available for manual refresh and active foreground auto-refresh.
• Updated Antigravity collection to use plain agy for /usage.
• Updated README, architecture notes, and the fix checklist to document the new refresh behavior.

Validation

• pnpm check
• pnpm exec prettier --check README.md docs/architecture.md docs/fix_check.md src/lib/usage.ts src/routes/+page.svelte src/routes/api/usage/refresh/+server.ts
• git diff --check

v1.0.0 — Initial Release

AI Usage Dashboard v1.0.0

Monitor Claude, Codex, and Gemini CLI usage in one local dashboard.
Runs entirely on your machine — no cloud, no telemetry, no API keys.

Features

• Multi-provider collection — runs /usage, /status, /model\ via
  ode-pty\ virtual terminals
• Smart retry — up to 5 attempts per provider with phase diagnostics and slash-command recovery
• Weekly Pace card — actual usage bar vs. 20 % minimum threshold marker
• Reset countdown — live per-provider countdown to next usage reset
• Live server logs — SSE-based real-time panel streaming directly to the browser
• Dual cache — server-side JSON history (10-min buckets) + browser \localStorage\ fallback

Quick Start

\\powershell
irm https://raw.githubusercontent.com/savvy773/ai_usage/main/scripts/install.ps1 | iex
\\

Or manually:

\\powershell
git clone https://github.com/savvy773/ai_usage.git
cd ai_usage
pnpm install
.\scripts\start-server.ps1 -Open
\\

Requirements

• Windows (PowerShell)
• Node.js + pnpm
• Claude CLI, Codex CLI, and/or Gemini CLI installed

Docs

• Architecture
• Fix Checklist
• Landing Page