发布

  • fix: version bump to 0.5.5, SSRF allowlist, Ollama context, embedding detection
    Release / Desktop / macOS ARM64 (push) Has been cancelled
    Release / Desktop / Windows ARM64 (push) Has been cancelled
    Release / Desktop / macOS x86_64 (push) Has been cancelled
    Release / Desktop / Windows x86_64 (push) Has been cancelled
    Release / Desktop / Linux x86_64 (push) Has been cancelled
    Release / CLI / aarch64-apple-darwin (push) Has been cancelled
    Release / CLI / x86_64-apple-darwin (push) Has been cancelled
    Release / CLI / aarch64-unknown-linux-gnu (push) Has been cancelled
    Release / CLI / x86_64-unknown-linux-gnu (push) Has been cancelled
    Release / CLI / aarch64-pc-windows-msvc (push) Has been cancelled
    Release / CLI / x86_64-pc-windows-msvc (push) Has been cancelled
    Release / Docker Image (push) Has been cancelled

    frostbyte_neo 发布于 2026-03-30 18:30:48 +00:00

    • Bump workspace version and Tauri config to 0.5.5 (fixes users stuck on 0.5.1)
    • Add ssrf_allowed_hosts config for self-hosted K8s environments (Jerry Jaz)
    • Raise Ollama discovered model defaults to 128K context / 16K output (Cureator)
    • Expand embedding auto-detection: OpenAI, Groq, Mistral, Together, Fireworks, Cohere, then local providers (Thunder Guardian)

    All tests passing. 9 files changed, 272 insertions.

    下载附件