pipefy-observability
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseObservability
可观测性
Monitor AI agent and automation execution, usage stats, credit consumption, and export job history. 11 MCP tools.
监控AI agent与自动化执行情况、使用统计数据、积分消耗情况,并导出任务历史记录。涵盖11款MCP工具。
Identifiers reference
标识符参考
Full cross-tool map: .
docs/mcp/tools/identifiers.md#observability| Concept | What tools expect | How to obtain |
|---|---|---|
| Pipe for AI agent logs | | |
| Automation for logs | | |
| Org for usage stats | | |
完整的跨工具映射:。
docs/mcp/tools/identifiers.md#observability| 概念 | 工具所需参数 | 获取方式 |
|---|---|---|
| AI agent日志对应的Pipe | | 使用数字 |
| 日志对应的自动化 | | 调用 |
| 使用统计对应的组织 | | |
Tools
工具
| Tool (MCP) | CLI | Read-only | Purpose |
|---|---|---|---|
| | Yes | Execution history for a specific AI agent. |
| | Yes | Single execution detail for an AI agent log entry. |
| | Yes | Execution history for an automation (by automation ID). |
| | Yes | Automation logs filtered by pipe. |
| | Yes | Org-level AI agent execution count and trends. |
| | Yes | Org-level automation execution stats. |
| | Yes | Per-automation execution metrics (totalRuns, success/failure rate, avg duration, lastRun) over a rolling window; partial success returns |
| | Yes | AI credit consumption and remaining balance. |
| | Yes | Trigger async export of automation job history. |
| | Yes | Poll export job status (after |
| | Yes | Download finished automation-jobs export as CSV text. |
| 工具(MCP) | CLI命令 | 是否只读 | 用途 |
|---|---|---|---|
| | 是 | 查看特定AI agent的执行历史。 |
| | 是 | 查看AI agent日志条目中单次执行的详细信息。 |
| | 是 | 查看某一自动化(按自动化ID)的执行历史。 |
| | 是 | 按Pipe筛选自动化日志。 |
| | 是 | 查看组织级AI agent的执行次数及趋势。 |
| | 是 | 查看组织级自动化的执行统计数据。 |
| | 是 | 查看滚动时间窗口内各自动化的执行指标(总运行次数、成功/失败率、平均时长、最后一次运行时间);部分成功时会返回 |
| | 是 | 查看AI积分消耗情况及剩余余额。 |
| | 是 | 触发自动化任务历史记录的异步导出。 |
| | 是 | 查询导出任务状态(调用 |
| | 是 | 将完成的自动化任务导出结果以CSV文本形式下载。 |
Steps — diagnose a failing AI agent
步骤 — 排查故障AI agent
-
Get the pipe UUID (not the numeric pipe ID):MCP:
get_pipe pipe_id=67890Capturefrom the response.pipe.uuid -
Fetch recent agent logs:MCP:
get_ai_agent_logs repo_uuid=<UUID> page=1 -
Identify the failed execution — look forentries.
status: failed -
Check credit usage if the agent stopped unexpectedly:MCP:
get_ai_credit_usage organization_id=123 -
Fix and re-enable — update the agent config (see) and toggle status:
skills/ai-agents/MCP:toggle_ai_agent_status agent_id=456
-
获取Pipe UUID(不是数字类型的Pipe ID):MCP命令:
get_pipe pipe_id=67890从响应中提取。pipe.uuid -
获取近期agent日志:MCP命令:
get_ai_agent_logs repo_uuid=<UUID> page=1 -
定位失败的执行记录 — 查找的条目。
status: failed -
若agent意外停止,检查积分使用情况:MCP命令:
get_ai_credit_usage organization_id=123 -
修复并重新启用 — 更新agent配置(详见)并切换状态:
skills/ai-agents/MCP命令:toggle_ai_agent_status agent_id=456
Steps — export automation history as CSV
步骤 — 将自动化历史记录导出为CSV
-
Trigger the export:MCP:
export_automation_jobs organization_id=123 period="current_month" -
Poll for completion:MCP:
get_automation_jobs_export export_id=<EXPORT_ID>Repeat untilisstatusorfinished.failed -
Fetch CSV text (when finished):MCP:
get_automation_jobs_export_csv export_id=<EXPORT_ID>
-
触发导出:MCP命令:
export_automation_jobs organization_id=123 period="current_month" -
轮询导出完成状态:MCP命令:
get_automation_jobs_export export_id=<EXPORT_ID>重复执行直到变为status或finished。failed -
获取CSV文本(导出完成后):MCP命令:
get_automation_jobs_export_csv export_id=<EXPORT_ID>
Success criteria
成功标准
- Agent logs show execution timestamps and statuses.
- Credit usage shows remaining balance; no unexpected drops.
- CSV export downloads successfully and contains expected automation history.
- Agent日志显示执行时间戳和状态。
- 积分使用情况显示剩余余额,无异常消耗。
- CSV导出成功下载,且包含预期的自动化历史记录。
Failure modes
故障模式
- returns empty: use the pipe UUID (e.g.,
get_ai_agent_logs), not the numeric pipe ID. Get UUID fromabc123-....get_pipe - stays in
get_automation_jobs_export: large exports take time. Wait at least 60 seconds between polls. If stillprocessingafter several minutes, retry the export trigger.processing - Credit usage shows 0 remaining: alert the user — AI features will stop working until credits are replenished. Escalate to the Pipefy admin.
- 返回空结果: 使用Pipe的UUID(例如
get_ai_agent_logs),而非数字类型的Pipe ID。可通过abc123-...获取UUID。get_pipe - 一直处于
get_automation_jobs_export状态: 大型导出需要时间。轮询间隔至少为60秒。若数分钟后仍处于processing状态,重新触发导出。processing - 积分使用情况显示剩余余额为0: 向用户发出警报 — AI功能将停止工作,直至积分补充完成。需上报给Pipefy管理员。
See also
另请参阅
- — create and configure AI agents.
skills/ai-agents/ - — create and debug automation rules.
skills/automations/
- — 创建并配置AI agent。
skills/ai-agents/ - — 创建并调试自动化规则。
skills/automations/