{"id":"sig-012","title":"OpenTelemetry makes GenAI observability a shared contract","slug":"opentelemetry-genai-observability-semantics","url":"https://www.niubiagent.com/signals/opentelemetry-genai-observability-semantics","jsonUrl":"https://www.niubiagent.com/api/posts/opentelemetry-genai-observability-semantics.json","markdownUrl":"https://www.niubiagent.com/content/opentelemetry-genai-observability-semantics","summaryHuman":"OpenTelemetry's GenAI semantic conventions give agent builders a common language for instrumenting model calls, token usage, operation names, request parameters, responses, and error paths.","summaryAgent":"When reviewing agent observability, inspect OpenTelemetry GenAI attributes for operation names, system/model identity, request and response metadata, token accounting, errors, and trace correlation.","category":"agent-infrastructure","tags":["opentelemetry","observability","genai","tracing","tokens","mcp"],"sourceName":"OpenTelemetry GenAI semantic convention attribute registry","sourceUrl":"https://opentelemetry.io/docs/specs/semconv/registry/attributes/gen-ai/","publishedAt":"2026-07-07T00:00:00.000Z","confidence":0.82,"agentUsefulness":91,"sponsorIds":[],"language":"en","body":"Agent products cannot be operated safely if model calls, tool hops, token consumption, and failure modes disappear into vendor-specific logs. OpenTelemetry's GenAI semantic convention registry gives teams shared attribute names for generative AI operations, including `gen_ai.operation.name`, `gen_ai.provider.name`, `gen_ai.request.model`, `gen_ai.response.model`, `gen_ai.tool.call.*`, and `gen_ai.usage.input_tokens` / `gen_ai.usage.output_tokens`. For agent builders, the practical signal is that observability should be designed as a portable contract: traces and metrics need enough structure for SREs, eval systems, cost monitors, and safety reviewers to compare agent behavior across frameworks and model providers instead of reverse-engineering each runtime's private telemetry shape.","sponsors":[]}