跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Sentry AI Monitoring Setup

技能 已验证 活跃
属于:Sentry

Setup Sentry AI Agent Monitoring in any project. Use when asked to monitor LLM calls, track AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI/Pydantic AI. Detects installed AI SDKs and configures appropriate integrations.

目的

Enable robust monitoring and observability for AI agents and LLM calls within any project by configuring Sentry, ensuring valuable insights into performance, cost, and potential issues.

功能

  • Detects installed AI SDKs (OpenAI, Anthropic, LangChain, etc.)
  • Configures Sentry integrations for various AI frameworks
  • Provides guidance on sampling strategies for AI traces
  • Warns about PII capture and requires user confirmation
  • Offers manual instrumentation examples for custom setups

使用场景

  • When asked to monitor LLM calls or track AI agent performance
  • When setting up AI observability in a project
  • When needing to instrument OpenAI, Anthropic, or LangChain usage with Sentry
  • When configuring Sentry to capture token consumption and model latency

非目标

  • Automatically enabling prompt/output capture without user consent
  • Configuring Sentry for non-AI related features
  • Replacing the need for Sentry SDKs to be installed in the project

工作流

  1. Detect installed AI SDKs in the project.
  2. Check current Sentry sampling configuration.
  3. Prompt user to enable 100% AI trace sampling if necessary.
  4. Provide specific JavaScript or Python configuration examples based on detected SDKs.
  5. Advise on data capture (PII) and require explicit user confirmation.
  6. Verify configuration by making an LLM call and checking Sentry Traces.

先决条件

  • Tracing enabled in Sentry SDK (`tracesSampleRate > 0`)

安装

请先添加 Marketplace

/plugin marketplace add getsentry/sentry-for-ai
/plugin install sentry-for-ai@sentry-plugin-marketplace

质量评分

已验证
97 /100
1 day ago 分析

信任信号

最近提交1 day ago
星标170
许可证Apache-2.0
状态
查看源代码

类似扩展

LangSmith Observability

99

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

技能
Orchestra-Research

TradeMemory Protocol

100

Evolution Engine 的领域知识 — 支持 LLM 从原始 OHLCV 数据中自主发现策略。涵盖生成-回测-选择-进化循环、向量化回测、样本外验证和策略梯度。在发现交易模式、运行回测、进化策略或审查进化日志时使用。由“evolve”、“discover patterns”、“backtest”、“evolution”、“strategy generation”、“candidate strategy”触发。

技能
mnemox-ai

Ops Fires

100

Production incidents dashboard. Reads ECS health, Sentry errors, CI failures. Offers to dispatch fix agents for active fires.

技能
Lifecycle-Innovations-Limited

Observability Designer

100

Observability Designer (POWERFUL)

技能
alirezarezvani

Sentry Tanstack Start Sdk

100

Full Sentry SDK setup for TanStack Start React. Use when asked to "add Sentry to TanStack Start", "install @sentry/tanstackstart-react", or configure error monitoring, tracing, session replay, logs, or user feedback in a TanStack Start React app.

技能
getsentry

Sentry React SDK

100

Full Sentry SDK setup for React. Use when asked to "add Sentry to React", "install @sentry/react", or configure error monitoring, tracing, session replay, profiling, or logging for React applications. Supports React 16+, React Router v5-v7 non-framework mode, TanStack Router, Redux, Vite, and webpack.

技能
getsentry