mirror of
https://github.com/wu736139669/hapi.git
synced 2026-08-05 06:24:37 +00:00
Haoqing WangandGitHub
eaf5ac49bd
* fix(web): exclude subagent usage from the parent context indicator The status bar's `ctx N/M` and `cache N` come from latestUsage, which scans the normalized messages backwards for the most recent usage. That scan includes sidechain messages, so while a Task subagent runs its usage — describing the subagent's own, much smaller context — becomes the parent's numerator, then snaps back when the parent resumes. The existing `scope_role !== 'child'` guard never fired on any path. Claude never stamps scope_role (sdkToLogConverter.ts says so outright), and Codex drops child token_count events in the CLI before they can reach the web layer, so no producer ever emits 'child'. isSidechain is the signal that actually survives. sdkToLogConverter.ts:308-313 already documents this exact reducer behaviour, but works around only the denominator by forcing the main session's context_window onto sidechain messages. The numerator was left unguarded. * fix(cli): stop stripping context_window from local-session usage UsageSchema is a plain z.object, so Zod's default strip mode drops every undeclared key. sessionScanner forwards parsed.data rather than the raw line, so on the local-JSONL path usage is truncated to the five declared fields and context_window — injected on the SDK path by sdkToLogConverter — never survives. The web status bar then falls back to getContextBudgetTokens, which subtracts a 10k headroom, so the same model reports a 1.0M denominator on a remote session and 990k on a local one. RawMessageSchema right below already carries .passthrough() with a comment about losing message.model and messageId the same way; the nested usage object just never got the same treatment.
HAPI
Run official Claude Code / Codex / Cursor Agent / Grok Build / OpenCode sessions locally and control them remotely through a Web / PWA / Telegram Mini App.
Why HAPI? HAPI is a local-first alternative to Happy. See Why Not Happy? for the key differences.
Features
- Seamless Handoff - Work locally, switch to remote when needed, switch back anytime. No context loss, no session restart.
- Native First - HAPI wraps your AI agent instead of replacing it. Same terminal, same experience, same muscle memory.
- AFK Without Stopping - Step away from your desk? Approve AI requests from your phone with one tap.
- Your AI, Your Choice - Claude Code, Codex, Cursor Agent, Grok Build, OpenCode—different agents, one unified workflow.
- Terminal Anywhere - Run commands from your phone or browser, directly connected to the working machine.
- Voice Control - Talk to your AI agent hands-free using the built-in voice assistant.
- Workspace Browser - Opt-in via one or more
hapi runner start --workspace-root <path>flags: browse scoped file trees from the web and start sessions in allowed subdirectories.
Demo
https://github.com/user-attachments/assets/38230353-94c6-4dbe-9c29-b2a2cc457546
Getting Started
npx @twsxtd/hapi hub --relay # start hub with E2E encrypted relay
npx @twsxtd/hapi # run claude code
hapi server remains supported as an alias.
The terminal will display a URL and QR code. Scan the QR code with your phone or open the URL to access.
The relay uses WireGuard + TLS for end-to-end encryption. Your data is encrypted from your device to your machine.
For self-hosted options (Cloudflare Tunnel, Tailscale), see Installation
Docs
Build from source
bun install
bun run build:single-exe
Credits
HAPI means "哈皮" a Chinese transliteration of Happy. Great credit to the original project.