Back to Details

cx-olly

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Olly Observability Agent Skill

Olly Observability Agent技能

Use this skill to interact with Coralogix's Observability Agent (Olly) via the 
cx olly
CLI commands. Olly can analyze your observability data, answer questions about alerts, metrics, logs, and generate artifacts like charts and reports.
使用此技能通过
cx olly
CLI命令与Coralogix的Observability Agent（Olly）进行交互。Olly可以分析您的可观测性数据，解答有关告警、指标、日志的问题，并生成图表和报告等工件。

CLI Commands

CLI命令

CommandPurposeKey flags
cx olly ask "message"
Send a message to the Observability Agent
--chat-id
, 
--mode
, 
--model
, 
--timeout
cx olly artifacts list
List all generated artifacts-
cx olly artifacts get <id>
Get artifact content by ID-
Output format: append 
-o json
or 
-o agents
for machine-readable output.
Single-profile only: 
cx olly
commands do not support multi-profile fan-out. Use 
-p <profile>
to specify a single profile.
命令用途关键参数
cx olly ask "message"
向可观测性Agent发送消息
--chat-id
, 
--mode
, 
--model
, 
--timeout
cx olly artifacts list
列出所有生成的工件-
cx olly artifacts get <id>
通过ID获取工件内容-
输出格式： 添加
-o json
或
-o agents
以获取机器可读的输出。
仅支持单配置文件： 
cx olly
命令不支持多配置文件扩散。使用
-p <profile>
指定单个配置文件。

Chat Commands

聊天命令

Start a new conversation

开启新对话

bash
cx olly ask "What alerts fired today?"
This creates a new chat and returns a response along with a Chat ID that you can use for follow-up questions.
bash
cx olly ask "What alerts fired today?"
此命令会创建一个新聊天，并返回响应以及可用于后续问题的Chat ID。

Continue an existing chat

继续现有对话

bash
cx olly ask "Tell me more about the error rates" --chat-id <chat-id>
Use 
--chat-id
to continue a conversation and maintain context from previous messages.
bash
cx olly ask "Tell me more about the error rates" --chat-id <chat-id>
使用
--chat-id
继续对话并保留之前消息的上下文。

Interaction modes

交互模式

ModeDescription
fast
Quick responses, less detailed analysis
focus
Balanced mode (default) - good for most queries
bash
cx olly ask "Quick summary of recent errors" --mode fast
模式描述
fast
快速响应，分析细节较少
focus
平衡模式（默认）- 适用于大多数查询
bash
cx olly ask "Quick summary of recent errors" --mode fast

Model selection

模型选择

Available models include 
gpt-5.2
(default), 
claude-sonnet-4-5
, 
sonnet-4.6
, 
gpt-5.4
, 
claude-haiku-4-5
.
bash
cx olly ask "Explain this error" --model claude-sonnet-4-5
可用模型包括
gpt-5.2
（默认）、
claude-sonnet-4-5
、
sonnet-4.6
、
gpt-5.4
、
claude-haiku-4-5
。
bash
cx olly ask "Explain this error" --model claude-sonnet-4-5

Timeout

超时设置

For complex queries that may take longer, increase the timeout (default: 900 seconds):
bash
cx olly ask "Deep analysis of last week's incidents" --timeout 1800
对于可能耗时较长的复杂查询，可增加超时时间（默认：900秒）：
bash
cx olly ask "Deep analysis of last week's incidents" --timeout 1800

Artifacts

工件

Olly can generate artifacts like charts, tables, and reports. Artifact IDs appear as links in the agent's response text.
Olly可以生成图表、表格和报告等工件。工件ID会以链接形式出现在Agent的响应文本中。

List all artifacts

列出所有工件

bash
cx olly artifacts list
cx olly artifacts list -o json
bash
cx olly artifacts list
cx olly artifacts list -o json

Get artifact content

获取工件内容

bash
cx olly artifacts get <artifact-id>
cx olly artifacts get <artifact-id> -o json
The 
artifacts get
command automatically:
  1. Fetches artifact metadata
  2. Downloads content from the presigned URL
  3. Decompresses gzip content
  4. Parses JSON and uses spill logic for large content
  5. Saves non-JSON text to a temp file
Output behavior:
  • JSON content: Displayed directly, or spilled to file if large
  • Text content: Saved to temp file (e.g., 
    /tmp/cx_results_artifact_<id>_<hash>.txt
    )
bash
cx olly artifacts get <artifact-id>
cx olly artifacts get <artifact-id> -o json
artifacts get
命令会自动执行以下操作：
  1. 获取工件元数据
  2. 从预签名URL下载内容
  3. 解压缩gzip内容
  4. 解析JSON并对大内容使用溢出逻辑
  5. 将非JSON文本保存到临时文件
输出行为：
  • JSON内容：直接显示，若内容过大则保存到文件
  • 文本内容：保存到临时文件（例如：
    /tmp/cx_results_artifact_<id>_<hash>.txt
    ）

Workflow Examples

工作流示例

Investigate an issue

问题排查

bash
undefined
bash
undefined

Start investigation

开始排查

cx olly ask "Why is the checkout service showing high latency?"
cx olly ask "Why is the checkout service showing high latency?"

Follow up with the chat ID from the response

使用响应中的Chat ID进行跟进

cx olly ask "What changed in the last hour?" --chat-id abc-123-def
cx olly ask "What changed in the last hour?" --chat-id abc-123-def

Get any generated charts

获取生成的图表

cx olly artifacts list -o json | jq '.[0].id' cx olly artifacts get <artifact-id>
undefined
cx olly artifacts list -o json | jq '.[0].id' cx olly artifacts get <artifact-id>
undefined

Get JSON output for scripting

获取JSON输出用于脚本编写

bash
undefined
bash
undefined

Get response as JSON

获取JSON格式的响应

cx olly ask "List top 5 error messages" -o json | jq '.response'
cx olly ask "List top 5 error messages" -o json | jq '.response'

Parse artifacts

解析工件

cx olly artifacts list -o json | jq '.[] | {id, filename, created_at}'
undefined
cx olly artifacts list -o json | jq '.[] | {id, filename, created_at}'
undefined

Detailed analysis with specific model

使用指定模型进行详细分析

bash
cx olly ask "Perform root cause analysis for the outage on 2024-01-15" \
  --model claude-sonnet-4-5 \
  --timeout 1800
bash
cx olly ask "Perform root cause analysis for the outage on 2024-01-15" \
  --model claude-sonnet-4-5 \
  --timeout 1800

Key Principles

核心原则

  • Chat IDs enable context - save the Chat ID from responses to continue conversations
  • Use 
    -o json
    for scripting     - pipe to 
    jq
    for filtering and extraction
  • Artifact IDs are in response text - look for markdown links like 
    [Chart](https://...artifact_view/<id>)
  • Single-profile only - 
    cx olly
    does not support multi-profile queries
  • Large artifacts auto-spill - JSON content over the configured limit is saved to temp files
  • Chat ID保留上下文 - 保存响应中的Chat ID以继续对话
  • 使用
    -o json
    用于脚本编写     - 通过管道传递给
    jq
    进行过滤和提取
  • 工件ID在响应文本中 - 查找类似
    [Chart](https://...artifact_view/<id>)
    的Markdown链接
  • 仅支持单配置文件 - 
    cx olly
    不支持多配置文件查询
  • 大工件自动溢出 - 超过配置限制的JSON内容会保存到临时文件

Related Skills

相关技能

  • cx-telemetry-querying
     - for direct DataPrime/PromQL queries without AI agent assistance (covers logs, spans, metrics, RUM)
  • cx-alerts
     - for managing alert definitions
  • cx-telemetry-querying
     - 无需AI Agent协助，直接进行DataPrime/PromQL查询（涵盖日志、链路、指标、RUM）
  • cx-alerts
     - 用于管理告警定义