recovering-from-errors

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Recovering from errors

从错误中恢复

Failures use stable error codes and include an actionable
fix
. Preserve that evidence; do not replace it with a generic explanation.
失败会使用稳定的错误代码,并包含可执行的
fix
字段。请保留这些错误证据,不要用通用解释替代。

Diagnose first

先进行诊断

bash
watch-skill doctor --json
Read the failing checks and apply only their stated fixes.
doctor
can repair managed ffmpeg and yt-dlp binaries, stale locks, corrupt caches, missing frame directories, and known local-model health failures. Re-run it once after remediation.
bash
watch-skill doctor --json
查看失败的检查项,并仅应用其指定的修复方案。
doctor
命令可以修复托管的ffmpeg和yt-dlp二进制文件、过期锁、损坏的缓存、缺失的帧目录,以及已知的本地模型健康问题。修复完成后重新运行一次该命令。

Retry the original operation once

重试一次原操作

After doctor is green, repeat the command that failed. If it returns another structured error, report its code, message, and fix. Do not loop indefinitely, silently switch cloud providers, enable cloud STT, or reprocess an already indexed video.
Common routes:
  • acquisition or extractor failure:
    watch-skill doctor --json
    , then retry the watch;
  • provider authentication: verify the matching
    WATCHSKILL_*_API_KEY
    locally;
  • provider model not found: run
    watch-skill setup-vision
    with a valid vision model;
  • low memory or local server failure: reduce the local model/context or select a cloud provider the user already has;
  • unknown video ID:
    watch-skill list
    , then use the listed ID or original source.
Security and cost policy are invariants during recovery. Never upload the video file, enable a paid provider, or raise the cost ceiling merely to make an error disappear.
doctor
命令显示正常后,重复执行之前失败的命令。如果再次返回结构化错误,请报告其错误代码、消息和修复方案。不要无限循环、静默切换云服务提供商、启用云端STT,或重新处理已索引的视频。
常见处理路径:
  • 获取或提取器失败:执行
    watch-skill doctor --json
    ,然后重试观看操作;
  • 提供商认证:在本地验证对应的
    WATCHSKILL_*_API_KEY
  • 提供商模型未找到:使用有效的视觉模型运行
    watch-skill setup-vision
  • 内存不足或本地服务器故障:减小本地模型/上下文规模,或选择用户已有的云服务提供商;
  • 未知视频ID:执行
    watch-skill list
    ,然后使用列出的ID或原始来源。
恢复过程中需严格遵守安全和成本策略。切勿仅为消除错误而上传视频文件、启用付费提供商或提高成本上限。