github-featured / rightnow-ai--openfang

发布

0 发布 100 Git 标签

RSS 订阅源
  • v0.6.3 948117d5de
    比较

    v0.6.3 — Reasoning Models, Slack Dedup, Hot-Reload
    Release / Desktop / macOS ARM64 (push) Has been cancelled
    详情
    Release / Desktop / Windows ARM64 (push) Has been cancelled
    详情
    Release / Desktop / macOS x86_64 (push) Has been cancelled
    详情
    Release / Desktop / Windows x86_64 (push) Has been cancelled
    详情
    Release / Desktop / Linux x86_64 (push) Has been cancelled
    详情
    Release / CLI / aarch64-apple-darwin (push) Has been cancelled
    详情
    Release / CLI / x86_64-apple-darwin (push) Has been cancelled
    详情
    Release / CLI / aarch64-unknown-linux-gnu (push) Has been cancelled
    详情
    Release / CLI / armv7-unknown-linux-gnueabihf (push) Has been cancelled
    详情
    Release / CLI / x86_64-unknown-linux-gnu (push) Has been cancelled
    详情
    Release / CLI / aarch64-pc-windows-msvc (push) Has been cancelled
    详情
    Release / CLI / x86_64-pc-windows-msvc (push) Has been cancelled
    详情
    Release / Docker Image (push) Has been cancelled
    详情

    frostbyte_neo 发布于 2026-05-01 10:12:42 +00:00

    This release resolves 4 bugs across LLM drivers, channels, and kernel hot-reload, plus a CI tooling bump. 2540 tests passing, zero clippy warnings, zero regressions.

    LLM Drivers:

    • #1098 Reasoning models retain state across turns. Thinking blocks are now parsed, persisted, and replayed across all three drivers (Anthropic with thinking_signature, Gemini reasoning, OpenAI o1/o3). Round-trip tests added. Models like Claude Sonnet extended thinking, Gemini 2.5 Flash, DeepSeek R1, Qwen, GPT o1 no longer lose reasoning state between turns.

    Channels:

    • #1103 Slack envelope_id deduplication. Socket Mode events now dedup against a 60s TTL cache (10000-entry soft cap). Connection rotation no longer causes double-processing of the same event.
    • #1133 Telegram REACTION_TOO_MANY removed from terminal-error list. The transient rate-limit reaction error is no longer cached as permanent rejection. Future reactions land once the cap clears.

    Kernel:

    • #1129 Subprocess timeout hot-reload. Edits to subprocess_timeout_secs in default_model and fallback_providers now propagate without restart. Follow-up to #1128 in v0.6.1.

    CI:

    • #1061 softprops/action-gh-release bumped from v2 to v3 (Node 24 runtime).

    Stats:

    • 2540 tests passing (+23 from v0.6.2)
    • Zero clippy warnings (workspace, all targets)
    • Zero regressions

    Full Changelog: https://github.com/RightNow-AI/openfang/compare/v0.6.2...v0.6.3

    下载附件