GenAI conventions2026-07-31

31 Jul 2026since 2026-07-28

0 breaking0 notable14 editorial

From the upstream commit

gen-ai: add fetch_response operation and span

Read the commit

Editorial14

enumattributegen_ai.operation.nameEnum members changed (17 to 18).
usageattributegen_ai.operation.nameNow referenced by gen_ai.fetch_response.client (required).
usageattributegen_ai.output.messagesNow referenced by gen_ai.fetch_response.client (opt in).
usageattributegen_ai.provider.nameNow referenced by gen_ai.fetch_response.client (required).
usageattributegen_ai.response.finish_reasonsNow referenced by gen_ai.fetch_response.client (recommended).
usageattributegen_ai.response.idNow referenced by gen_ai.fetch_response.client (required).
usageattributegen_ai.response.modelNow referenced by gen_ai.fetch_response.client (recommended).
usageattributegen_ai.system_instructionsNow referenced by gen_ai.fetch_response.client (opt in).
usageattributegen_ai.tool.definitionsNow referenced by gen_ai.fetch_response.client (opt in).
usageattributeopenai.api.typeNow referenced by gen_ai.fetch_response.client (recommended).
usageattributeopenai.response.service_tierNow referenced by gen_ai.fetch_response.client (conditionally required).
addedsignalgen_ai.fetch_response.clientDescribes a request to a Generative AI provider that fetches a previously generated model response by its identifier.
addedattributegen_ai.request.stream_cursorThe cursor identifying the last streamed event already received, used to resume a streamed response from that position.
addedattributegen_ai.response.statusThe lifecycle status of a generated response, as reported by the provider when the response is fetched or polled.