anvil-serving-release-readiness
Gate an Anvil Serving package release and coordinated live deployment across Windows, Primary Node, Companion Node, the controller, router, Hermes, Pi, and OpenClaw. Use when a change will be merged, tagged, published, or deployed and exact manifest dependencies, version parity, recovery policy, and outage-free client smokes must be proven.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- anvil-serving-release-readiness
- description
- Gate an Anvil Serving package release and coordinated live deployment across Windows, Primary Node, Companion Node, the controller, router, Hermes, Pi, and OpenClaw. Use when a change will be merged, tagged, published, or deployed and exact manifest dependencies, version parity, recovery policy, and outage-free client smokes must be proven.
02 资源文件 1
- 参考文档agents/openai.yaml388 B
03 SKILL.md 正文
Anvil Serving Release Readiness
Use the canonical repository skill:
skills/anvil-serving-release-readiness/SKILL.md
Follow all four stages. A published package, healthy container, or passing route probe is not enough by itself. Do not close the release while any declared endpoint is version-skewed or any in-scope client path is unavailable. The canonical skill also covers router-derived Hermes/Pi/OpenClaw catalog sync and explicitly authorized fix-forward recovery.
04 同仓库更多 Skills
voice
暂无简介
workbench
暂无简介
workbench
暂无简介
workbench
暂无简介
anvil-serving-voice-ops
Operate topology-owned anvil-serving voice audio and Realtime proxy lifecycle, Mini-to-Dark loopback forwarding, profiles, sidecars, and bounded voice benchmarks. Use for voice status, logs, start/stop/restart, OpenClaw Talk topology checks, and voice evidence that must remain separate from LLM serve qualification evidence.
anvil-serving-stt-benchmark
Prepare, validate, execute, compare, and publish reproducible multi-sample speech-to-text qualifications in anvil-serving. Use for STT model bakeoffs, corpus-based WER/CER and latency testing, candidate overlays, concurrency tests, restoration checks, and fail-closed stt-benchmark-evidence/v1 artifacts. Do not use for a single voice-pipeline turn or LLM qualification.