fix(diagnostics-otel): stabilize genai token metric model attr

CHANGELOG.md

@@ -42,6 +42,7 @@ Docs: https://docs.openclaw.ai
 - Diagnostics/OTEL: add GenAI usage token attributes to model-usage spans, including cache read/write input token counts without session identifiers or prompt/response content. Thanks @vincentkoc.
 - Diagnostics/OTEL: include bounded GenAI operation, provider, and request-model attributes on model-usage spans so token usage remains self-describing without diagnostic identifiers. Thanks @vincentkoc.
 - Diagnostics/OTEL: keep model-usage span GenAI provider attributes aligned with the existing semantic-convention opt-in policy, using legacy `gen_ai.system` unless latest experimental GenAI conventions are enabled. Thanks @vincentkoc.
+- Diagnostics/OTEL: keep `gen_ai.request.model` present on GenAI token usage metrics with a bounded `unknown` fallback when model usage events do not include a model. Thanks @vincentkoc.
 - Diagnostics/OTEL: add bounded outbound message delivery lifecycle diagnostics and export them as low-cardinality delivery spans/metrics without message body, recipient, room, or media-path data. (#71471) Thanks @vincentkoc and @jlapenna.
 - Diagnostics/OTEL: emit bounded exec-process diagnostics and export them as `openclaw.exec` spans without exposing command text, working directories, or container identifiers. (#71451) Thanks @vincentkoc and @jlapenna.
 - Diagnostics/OTEL: support `OPENCLAW_OTEL_PRELOADED=1` so the plugin can reuse an already-registered OpenTelemetry SDK while keeping OpenClaw diagnostic listeners wired. (#71450) Thanks @vincentkoc and @jlapenna.

extensions/diagnostics-otel/src/service.test.ts

@@ -740,6 +740,30 @@ describe("diagnostics-otel service", () => {
     await service.stop?.(ctx);
   });
 
+  test("keeps GenAI token usage metric model attribute present when model is unavailable", async () => {
+    const service = createDiagnosticsOtelService();
+    const ctx = createOtelContext(OTEL_TEST_ENDPOINT, { metrics: true });
+    await service.start(ctx);
+
+    emitDiagnosticEvent({
+      type: "model.usage",
+      provider: "openai",
+      usage: { input: 2 },
+    });
+    await flushDiagnosticEvents();
+
+    expect(telemetryState.histograms.get("gen_ai.client.token.usage")?.record).toHaveBeenCalledWith(
+      2,
+      {
+        "gen_ai.operation.name": "chat",
+        "gen_ai.provider.name": "openai",
+        "gen_ai.request.model": "unknown",
+        "gen_ai.token.type": "input",
+      },
+    );
+    await service.stop?.(ctx);
+  });
+
   test("exports GenAI usage attributes on model usage spans without diagnostic identifiers", async () => {
     const service = createDiagnosticsOtelService();
     const ctx = createOtelContext(OTEL_TEST_ENDPOINT, { traces: true });

extensions/diagnostics-otel/src/service.ts

@@ -904,7 +904,7 @@ export function createDiagnosticsOtelService(): OpenClawPluginService {
         const genAiAttrs: Record<string, string> = {
           "gen_ai.operation.name": "chat",
           "gen_ai.provider.name": lowCardinalityAttr(evt.provider),
-          ...(evt.model ? { "gen_ai.request.model": lowCardinalityAttr(evt.model) } : {}),
+          "gen_ai.request.model": lowCardinalityAttr(evt.model),
         };
 
         const usage = evt.usage;