fix(diagnostics): align response byte metric description

vincentkoc · vincentkoc · commit 347f5430ac5c · 2026-06-06T16:01:01.000+02:00
diff --git a/docs/gateway/opentelemetry.md b/docs/gateway/opentelemetry.md
@@ -190,7 +190,7 @@ message bodies are also approved for export.
 - `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`)
 - `openclaw.model_call.duration_ms` (histogram, attrs: `openclaw.provider`, `openclaw.model`, `openclaw.api`, `openclaw.transport`, plus `openclaw.errorCategory` and `openclaw.failureKind` on classified errors)
 - `openclaw.model_call.request_bytes` (histogram, UTF-8 byte size of the final model request payload; no raw payload content)
-- `openclaw.model_call.response_bytes` (histogram, UTF-8 byte size of streamed model response events excluding accumulated `partial` snapshots on delta events; no raw response content)
+- `openclaw.model_call.response_bytes` (histogram, UTF-8 byte size of streamed response chunk payloads; high-frequency text, thinking, and tool-call deltas count only incremental `delta` bytes; no raw response content)
 - `openclaw.model_call.time_to_first_byte_ms` (histogram, elapsed time before the first streamed response event)
 - `openclaw.model.failover` (counter, attrs: `openclaw.provider`, `openclaw.model`, `openclaw.failover.to_provider`, `openclaw.failover.to_model`, `openclaw.failover.reason`, `openclaw.failover.suspended`, `openclaw.lane`)
 - `openclaw.skill.used` (counter, attrs: `openclaw.skill.name`, `openclaw.skill.source`, `openclaw.skill.activation`, optional `openclaw.agent`, optional `openclaw.toolName`)
diff --git a/extensions/diagnostics-otel/src/service.ts b/extensions/diagnostics-otel/src/service.ts
@@ -1464,8 +1464,7 @@ export function createDiagnosticsOtelService(): OpenClawPluginService {
         "openclaw.model_call.response_bytes",
         {
           unit: "By",
-          description:
-            "UTF-8 byte size of streamed model response events excluding accumulated partial snapshots",
+          description: "UTF-8 byte size of bounded streamed model response payloads",
         },
       );
       const modelCallTimeToFirstByteHistogram = meter.createHistogram(
