@@ -165,6 +165,10 @@ When any subkey is enabled, model and tool spans get bounded, redacted
165165- `openclaw.context.tokens` (histogram, attrs: `openclaw.context`, `openclaw.channel`, `openclaw.provider`, `openclaw.model`)
166166- `gen_ai.client.token.usage` (histogram, GenAI semantic-conventions metric, attrs: `gen_ai.token.type` = `input`/`output`, `gen_ai.provider.name`, `gen_ai.operation.name`, `gen_ai.request.model`)
167167- `gen_ai.client.operation.duration` (histogram, seconds, GenAI semantic-conventions metric, attrs: `gen_ai.provider.name`, `gen_ai.operation.name`, `gen_ai.request.model`, optional `error.type`)
168+- `openclaw.model_call.duration_ms` (histogram, attrs: `openclaw.provider`, `openclaw.model`, `openclaw.api`, `openclaw.transport`)
169+- `openclaw.model_call.request_bytes` (histogram, UTF-8 byte size of the final model request payload; no raw payload content)
170+- `openclaw.model_call.response_bytes` (histogram, UTF-8 byte size of streamed model response events; no raw response content)
171+- `openclaw.model_call.time_to_first_byte_ms` (histogram, elapsed time before the first streamed response event)
168172169173### Message flow
170174@@ -216,6 +220,7 @@ When any subkey is enabled, model and tool spans get bounded, redacted
216220- `openclaw.model.call`
217221- `gen_ai.system` by default, or `gen_ai.provider.name` when the latest GenAI semantic conventions are opted in
218222- `gen_ai.request.model`, `gen_ai.operation.name`, `openclaw.provider`, `openclaw.model`, `openclaw.api`, `openclaw.transport`
223+- `openclaw.model_call.request_bytes`, `openclaw.model_call.response_bytes`, `openclaw.model_call.time_to_first_byte_ms`
219224- `openclaw.provider.request_id_hash` (bounded SHA-based hash of the upstream provider request id; raw ids are not exported)
220225- `openclaw.harness.run`
221226- `openclaw.harness.id`, `openclaw.harness.plugin`, `openclaw.outcome`, `openclaw.provider`, `openclaw.model`, `openclaw.channel`
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。