steel-session-debugging

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Steel Session Debugging

Steel会话调试

Skill Boundary

Skill边界

Use this skill to explain what happened in a failed Steel session and what to change next. Start from evidence, not guesses.
Do not use this skill as the primary place for bot-detection mitigation, proxy strategy, CAPTCHA strategy, login reputation, or retry policy. If the evidence points there, collect enough proof and hand off to
steel-reliability
.
使用此Skill来解释失败的Steel会话中发生了什么以及下一步需要做出哪些更改。从证据出发,而非猜测。
请勿将此Skill作为机器人检测缓解、代理策略、CAPTCHA策略、登录信誉或重试策略的主要处理工具。如果证据指向这些方向,请收集足够的证明后转交给
steel-reliability

Setup Check

设置检查

  1. Confirm the user provided a Steel session ID or enough context to identify one.
  2. Run
    steel doctor --preflight
    if CLI auth or API access is uncertain.
  3. Prefer Steel CLI diagnostics before raw API calls.
  4. Create local artifacts under
    .steel-debug/
    ; do not paste raw logs into chat unless the user asks.
  1. 确认用户已提供Steel会话ID或足够的上下文信息以定位会话。
  2. 如果不确定CLI身份验证或API访问权限是否正常,运行
    steel doctor --preflight
  3. 优先使用Steel CLI诊断工具,而非直接调用原始API。
  4. .steel-debug/
    目录下创建本地工件;除非用户要求,否则不要在聊天中粘贴原始日志。

Investigation Workflow

调查流程

  1. Collect session metadata, browser logs, raw agent logs, semantic agent traces, and viewer/replay links.
  2. Redact cookies, bearer tokens, API keys, passwords, form values, and obvious PII before summarizing.
  3. Build a timeline: session creation, navigations, actions, waits, console errors, failed requests, CAPTCHA/proxy signals, and final state.
  4. Classify the failure using the taxonomy in
    references/failure-taxonomy.md
    .
  5. Produce an evidence-backed diagnosis with a smallest useful verification step.
  6. If the fix involves bot detection, proxy, CAPTCHA, identity, pacing, or login persistence, route to
    steel-reliability
    .
  1. 收集会话元数据、浏览器日志、原始Agent日志、语义Agent跟踪以及查看器/重放链接。
  2. 在总结前,编辑掉Cookie、Bearer令牌、API密钥、密码、表单值和明显的个人身份信息(PII)。
  3. 构建时间线:会话创建、导航、操作、等待、控制台错误、失败请求、CAPTCHA/代理信号以及最终状态。
  4. 使用
    references/failure-taxonomy.md
    中的分类法对故障进行分类。
  5. 生成基于证据的诊断,并提供最简化的验证步骤。
  6. 如果修复涉及机器人检测、代理、CAPTCHA、身份验证、节奏控制或登录持久性,请转交给
    steel-reliability
    处理。

Output Format

输出格式

text
Diagnosis:
- What happened:
- Most likely cause:
- Evidence:
- What to change:
- Verification step:
- Confidence:
text
诊断结果:
- 发生了什么:
- 最可能的原因:
- 证据:
- 需要更改的内容:
- 验证步骤:
- 置信度:

Useful Commands

实用命令

bash
steel --json sessions get <session-id>
steel --json sessions logs <session-id>
steel --json sessions agent-logs <session-id>
steel --json sessions traces <session-id>
node scripts/collect-session-debug.mjs <session-id>
node scripts/redact-session-debug.mjs .steel-debug/<session-id>/bundle.json
node scripts/summarize-session-debug.mjs .steel-debug/<session-id>/redacted-bundle.json
bash
steel --json sessions get <session-id>
steel --json sessions logs <session-id>
steel --json sessions agent-logs <session-id>
steel --json sessions traces <session-id>
node scripts/collect-session-debug.mjs <session-id>
node scripts/redact-session-debug.mjs .steel-debug/<session-id>/bundle.json
node scripts/summarize-session-debug.mjs .steel-debug/<session-id>/redacted-bundle.json

References

参考资料

  • references/investigation-workflow.md
    : detailed collection and timeline process.
  • references/log-event-types.md
    : how to separate metadata, browser logs, raw agent logs, and traces.
  • references/agent-traces.md
    : how to read semantic agent trace events.
  • references/network-forensics.md
    : request failures, redirects, and blocked-page evidence.
  • references/replay-and-screenshots.md
    : viewer, player, HLS, and screenshot usage.
  • references/failure-taxonomy.md
    : standard failure classes.
  • references/reliability-handoff.md
    : when to load
    steel-reliability
    .
  • references/investigation-workflow.md
    :详细的收集和时间线处理流程。
  • references/log-event-types.md
    :如何区分元数据、浏览器日志、原始Agent日志和跟踪信息。
  • references/agent-traces.md
    :如何解读语义Agent跟踪事件。
  • references/network-forensics.md
    :请求失败、重定向和页面被阻止的相关证据。
  • references/replay-and-screenshots.md
    :查看器、播放器、HLS和截图的使用方法。
  • references/failure-taxonomy.md
    :标准故障分类。
  • references/reliability-handoff.md
    :何时转交至
    steel-reliability
    的说明。