datadog-analyser

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Datadog Analyser

Datadog 分析工具

Investigate and analyse Datadog observability data using the

pup

CLI.

使用

pup

CLI调查和分析Datadog可观测性数据。

Arguments

参数

```
$ARGUMENTS[0]
```
— (optional) What to analyse (e.g.
```
"error rate last 1h"
```
,
```
"triggered monitors"
```
,
```
"incidents today"
```
,
```
"service:api logs"
```
). If not provided, perform a general health overview.

```
$ARGUMENTS[0]
```
—（可选）要分析的内容（例如
```
"error rate last 1h"
```
、
```
"triggered monitors"
```
、
```
"incidents today"
```
、
```
"service:api logs"
```
）。如果未提供，则执行常规健康概览。

System Requirements

系统要求

```
pup
```
CLI installed — see https://github.com/datadog-labs/pup/blob/main/README.md
```
DD_API_KEY
```
and
```
DD_APP_KEY
```
environment variables set
```
DD_SITE
```
set if not using
```
datadoghq.com
```
(optional)

已安装
```
pup
```
CLI — 详见https://github.com/datadog-labs/pup/blob/main/README.md
已设置
```
DD_API_KEY
```
和
```
DD_APP_KEY
```
环境变量
若未使用
```
datadoghq.com
```
，需设置
```
DD_SITE
```
（可选）

Output Directory

输出目录

.datadog-analyser-tmp/
└── report.md    # Final analysis report

.datadog-analyser-tmp/
└── report.md    # 最终分析报告

Execution

执行步骤

1. Verify Connection

1. 验证连接

Run

pup test

to confirm the CLI is configured and connected:

bash

pup test

If this fails, use

AskUserQuestion

to inform the user that

pup

is not configured or

DD_API_KEY

DD_APP_KEY

are not set, and link to the setup guide: https://github.com/datadog-labs/pup/blob/main/README.md

Do NOT continue until

pup test

succeeds.

运行

pup test

确认CLI已配置并连接：

bash

pup test

如果验证失败，使用AskUserQuestion告知用户

pup

未配置或

DD_API_KEY

DD_APP_KEY

未设置，并链接到设置指南：https://github.com/datadog-labs/pup/blob/main/README.md

在

pup test

成功前，请勿继续执行。

2. Discover Available Commands

2. 查看可用命令

Run

pup agent guide

to get the full list of available commands and usage patterns for this session:

bash

pup agent guide

pup agent guide

is not available (command not found), use the known command reference below and continue.

运行

pup agent guide

获取本次会话的完整可用命令列表和使用模式：

bash

pup agent guide

如果

pup agent guide

不可用（命令未找到），请使用下方已知命令参考继续操作。

3. Analyse

3. 执行分析

Based on

$ARGUMENTS[0]

, determine which

pup

commands are most relevant. Use

--output=json

(default) for all commands to get structured output. Run commands sequentially.

Common analysis patterns:

Goal	Commands
Triggered/alerting monitors	`pup monitors list` , `pup monitors search --query="status:alert"`
Error logs	`pup logs search --query="status:error" --from="1h"`
Metric trend	`pup metrics query --query="<metric>" --from="<window>"`
Active incidents	`pup incidents list`
SLO health	`pup slos list` , `pup slos status <id>`
APM service health	`pup apm services` , `pup apm dependencies`
Security signals	`pup security signals list` , `pup security findings search`
Error tracking	`pup error-tracking issues search --query="<service>"`
Synthetics failures	`pup synthetics tests list`
CI failures	`pup cicd pipelines list` , `pup cicd events list`

All commands default to JSON output. Use flags like

--from

--to

--query

--tags

to narrow scope. Refer to

pup <command> --help

for available flags.

根据

$ARGUMENTS[0]

确定最相关的

pup

命令。所有命令默认使用

--output=json

以获取结构化输出。按顺序执行命令。

常见分析模式：

目标	命令
已触发/告警的监控器	`pup monitors list` , `pup monitors search --query="status:alert"`
错误日志	`pup logs search --query="status:error" --from="1h"`
指标趋势	`pup metrics query --query="<metric>" --from="<window>"`
活跃事件	`pup incidents list`
SLO健康状况	`pup slos list` , `pup slos status <id>`
APM服务健康	`pup apm services` , `pup apm dependencies`
安全信号	`pup security signals list` , `pup security findings search`
错误追踪	`pup error-tracking issues search --query="<service>"`
合成监控失败情况	`pup synthetics tests list`
CI失败情况	`pup cicd pipelines list` , `pup cicd events list`

所有命令默认输出JSON格式。可使用

--from

、

--to

、

--query

、

--tags

等参数缩小范围。请参考

pup <command> --help

查看可用参数。

4. Report

4. 生成报告

All timestamps in the report must use user's local time, not UTC.

Write a structured analysis to

.datadog-analyser-tmp/report.md

using the Write tool:

Summary — Overall health status and key findings
Details — Breakdown of findings per domain (monitors, logs, metrics, etc.)
Anomalies — Anything alerting, degraded, or unusual
Recommendations — Suggested follow-up actions

Inform the user of the report location:

.datadog-analyser-tmp/report.md

<tags> <mode>think</mode> <custom>yes</custom> </tags>

报告中的所有时间戳必须使用用户的本地时间，而非UTC时间。

使用Write工具将结构化分析内容写入

.datadog-analyser-tmp/report.md

：

摘要 — 整体健康状态和关键发现
详情 — 按领域（监控器、日志、指标等）细分的发现内容
异常情况 — 所有告警、性能下降或异常内容
建议 — 建议的后续操作

告知用户报告位置：

.datadog-analyser-tmp/report.md

<tags> <mode>think</mode> <custom>yes</custom> </tags>