Entity · protocol
OpenTelemetry
protocolactive
opentelemetry-90095182·7 events·first seen Aliases: OpenTelemetry
Co-occurring entities
More like this (12)
Recent events (7)
ORCA-bench evaluates LLM agents on production oncall root cause analysis tasks
ORCA-bench is a new benchmark that tests general-purpose coding agents on oncall root cause analysis (RCA) in a production-fidelity environment, using a live OpenTelemetry-instrumented microservice system with 1,079 tasks spanning metrics, logs, traces, and source code. Across five frontier agents, the best RCA accuracy is 25.3% on medium-difficulty tasks and 10.0% on hard tasks, with even Claude Fable 5 failing to close the gap significantly. The benchmark is notable for its expert-curated ground truth (Cohen's κ_w=0.90 human-LLM agreement) and its argument that reported performance is a lower bound on real-world difficulty, since production systems are far larger and more dynamic than the testbed.
SigNoz: OpenTelemetry-native observability platform with MCP integration and AI agent support
SigNoz is an open-source observability platform (30k+ GitHub stars, +343 today) that provides logs, metrics, and traces with APM and distributed tracing capabilities. It has added an MCP server integration and a native AI teammate feature in its cloud offering, positioning it for AI agent observability use cases. The trending activity suggests growing adoption in the AI/ML infrastructure space.
Claude Code 2.1.214 release: security fixes, EndConversation tool, and extensive bug fixes
Anthropic released Claude Code version 2.1.214, a substantial patch addressing multiple permission-check security vulnerabilities including a Windows PowerShell 5.1 bypass, file-descriptor redirect bypass, and path-traversal issues in allow rules. The release adds the EndConversation tool enabling Claude to terminate sessions with abusive users or jailbreak attempts, improved OpenTelemetry observability attributes, and docker/Podman permission prompts. Dozens of bug fixes address Windows-specific issues, background session lifecycle problems, memory management, and streaming reliability.
Claude Code 2.1.202 release: dynamic workflow sizing, OTel attributes, and numerous bug fixes
Claude Code version 2.1.202 ships a new 'Dynamic workflow size' configuration setting that advises how large Claude makes dynamic workflows (small/medium/large agent counts). The release adds OpenTelemetry attributes (workflow.run_id and workflow.name) to telemetry from workflow-spawned agents, enabling full reconstruction of workflow runs from OTel data. A large set of bug fixes addresses crashes in history search, mTLS rotation failures, Remote Control command failures, unicode corruption in workflow scripts, and memory/performance issues with git worktrees. The /review command reverts to single-pass mode, with multi-agent review now available via /code-review.
Claude Code 2.1.193 adds shell classifier routing, OTel response logging, and background agent fixes
Claude Code version 2.1.193 ships several notable additions: a new autoMode.classifyAllShell setting to route all shell commands through the auto-mode classifier, an OpenTelemetry log event for assistant responses (redacted by default, with opt-in via environment variable), and live file path autocomplete in bash mode. The release also fixes multiple background agent bugs including phantom subagent spawning, spurious cancellation on backgrounding, and agent panel display issues, while improving MCP authentication reconnection on 401/403 errors.
Langfuse: Open Source LLM Engineering Platform Trending on GitHub
Langfuse is an open-source LLM engineering platform providing observability, metrics, evaluations, prompt management, and dataset tooling. It integrates with OpenTelemetry, LangChain, OpenAI SDK, and LiteLLM. The project has accumulated 28,075 GitHub stars with 89 new stars today, indicating sustained community traction. Backed by Y Combinator (W23), it represents a notable entry in the LLM ops/tooling ecosystem.
Mistral AI Launches Workflows: Enterprise AI Orchestration Layer in Public Preview
Mistral AI has released Workflows in public preview, an enterprise-grade orchestration layer integrated into its Studio platform that enables durable, observable, fault-tolerant AI pipeline execution in production. The system supports human-in-the-loop approvals via a single API call, full execution tracing with OpenTelemetry, and Python-based workflow authoring that publishes to Le Chat for non-developer triggering. Early enterprise customers including ASML, ABANCA, CMA-CGM, and La Banque Postale are already using it for cargo release automation, KYC compliance, and customer support triage. The product targets the gap between proof-of-concept AI pipelines and reliable production deployment.