#OpenTelemetry

Native OTel export removes the need for custom exporters when wiring Claude applications into existing observability pipelines. Teams building agents on the Messages API or Claude SDKs can now debug latency, tool calls and failures directly inside LangSmith alongside traces from other providers, consolidating monitoring into one tool. The public beta status means behaviour may change before general availability.

#Claude #LangSmith #OpenTelemetry #agents

Event

Official accountLangChain@LangChainAISource

Products BuildersSelected12:46

Claude adds OpenTelemetry observability for Claude Code and subagents

Detailed traces are gated behind a Beta flag, so teams that want full subagent call chains need to opt in explicitly. The setup works with Grafana or a local receiver, and subscription-logged Claude Code users can use it too — no API key required. Engineering teams running long agent workflows in production get billing and latency attribution they previously had to reconstruct manually.

#Claude #Claude Code #OpenTelemetry #observability

Event

岚叔@lufzzlizSource

Products BuildersMulti-sourceSelected05:05

Claude Managed Agents and Messages API Add OpenTelemetry Tracing

OpenTelemetry support means agent telemetry can flow into existing observability stacks like Grafana and Splunk instead of Anthropic-only dashboards, which matters for teams running Claude agents in production. Developers and platform engineers can use the token counts, durations and tool names in each trace to debug failures, measure costs and test agent behaviour with their standard monitoring setup.

#Claude #Anthropic #OpenTelemetry #agents

Event

TestingCatalog@testingcatalogSource

Products BuildersOfficialSelected04:42

Claude Code v2.1.300 adds mod hooks and OpenTelemetry detail

The finer cache-write telemetry matters for anyone cost-optimising long agent sessions, since 5-minute and 1-hour cache writes can differ sharply in price. The new mod hooks and $.ui.view make it practical to build richer prompt and agent-UI extensions inside Claude Code. Developers running MCP-heavy setups should also update for the fix to automatic tool search dropping mid-session.

#Claude Code #Anthropic #OpenTelemetry #agents

Event

Primary sourceClaude Code: GitHub Releases@ashwin-antSource

Oct 13

How-to Builders17:31

Chinese contentGoogle 发布《Site Reliability Engineering》第二版

十年前那本 SRE 圣经出第二版了，讲清了 AI 时代运维怎么变：GPU 集群怎么管、生成式 AI 怎么写复盘，还给了六大领域的 2016 对比 2026 对照表。

#SRE #Google #OpenTelemetry #FinOps

shao__meng@shao__mengSource

Oct 1

Products Builders02:11

Chinese contentCoreWeave发布Agent Lens调试工具

CoreWeave新工具帮你批量调试AI代理错误，不用再逐条查看追踪数据了

#CoreWeave #Agent Lens #OpenTelemetry #MCP

CoreWeave@CoreWeaveSource

Sep 1

ProductsSelected08:23

Wrapture Python testing library

Wrapture offers Python developers an alternative to unittest.mock with built-in tracing capabilities, useful for testing third-party code without modifying it.

#Wrapture #Python #unittest.mock #testing

Official accountSimon Willison’s WeblogSource

Aug 27

ProductsOfficialSelected03:18

Amazon Bedrock AgentCore Evaluations

Developers across ASEAN can now evaluate any agent framework using Amazon's standardized service, reducing vendor lock-in and improving development flexibility.

#Amazon Bedrock #AgentCore Evaluations #OpenTelemetry #LangGraph