github-featured / yvgude--lean-ctx

发布

0 发布 257 Git 标签

RSS 订阅源
  • v2.9.0 a45f5e9523
    比较

    release: v2.9.0 — Intelligence Layer rebranding + Pro Adaptive Intelligence + critical fixes
    Release / Build aarch64-apple-darwin (push) Has been cancelled
    详情
    Release / Build x86_64-apple-darwin (push) Has been cancelled
    详情
    Release / Build x86_64-unknown-linux-musl (push) Has been cancelled
    详情
    Release / Build aarch64-unknown-linux-gnu (push) Has been cancelled
    详情
    Release / Build x86_64-unknown-linux-gnu (push) Has been cancelled
    详情
    Release / Build x86_64-pc-windows-msvc (push) Has been cancelled
    详情
    Release / Create Release (push) Has been cancelled
    详情

    frostbyte_neo 发布于 2026-03-29 19:05:26 +00:00

    • Rebrand: "Cognitive Filter" → "Intelligence Layer for AI Coding", "MCP tools" → "intelligent tools" / "Context Server"
    • Pro: lean-ctx upgrade command, adaptive compression models, auto-sync, cloud dashboard, Stripe checkout
    • Fix: setup no longer overwrites editor configs on parse failure (#29)
    • Fix: lossy UTF-8 file reading for non-UTF-8 files (#28)
    • Fix: Windows deferred binary update when MCP server locks executable
    • Fix: compression regression with static rule-based fallback for all users
    • Fix: cost constants unified to $2.50/M input + $10/M output
    • New: BM25 semantic code search, Information Bottleneck filter, MCP Unified Mode
    • New: mypy pattern, pytest direct routing, cloud backend with 12 API endpoints

    Made-with: Cursor

    下载附件