Merge pull request #2841 from heygen-com/07-27-feat_engine_open_drawelement_fast_capture_to_win32_hardware_gpu

feat(engine): open drawElement fast capture to Windows hardware GPU

packages/producer/src/services/render/observability.ts

@@ -72,6 +72,13 @@ export interface RenderCaptureObservability {
   dePreInversionWorkers?: number;
   /** DE parallel-router outcome: "routed" (fired, held) | "reverted" (fired, self-verify retry rolled back). */
   deParallelRouter?: "routed" | "reverted";
+  /**
+   * Low-cardinality GPU bucket (`<backend>/<vendor>`) from the DE probe
+   * session. Lives on capture observability (not just perfSummary) so a hard
+   * failure — crash / OOM / timeout — still reports which GPU backend it hit:
+   * that is precisely the cohort the win32 D3D11 rollout must attribute.
+   */
+  deGpuRenderer?: string;
   /** Worker count the resolver would have used absent the router; undefined if it never fired. */
   dePreRouterWorkers?: number;
   /**

packages/producer/src/services/render/perfSummary.ts

@@ -111,6 +111,9 @@ function aggregateDrawElement(
   const gateReasons = [
     ...new Set(perfs.map((p) => p.deGateReason).filter((r): r is string => !!r)),
   ].sort();
+  const gpuRenderers = [
+    ...new Set(perfs.map((p) => p.gpuRenderer).filter((r): r is string => !!r)),
+  ].sort();
   const drain = de.drainStats;
   return {
     mode: modes.join("|") || "unknown",
@@ -121,6 +124,7 @@ function aggregateDrawElement(
     parallelRouter: de.parallelRouter ?? "none",
     preRouterWorkers: de.preRouterWorkers,
     gateReason: gateReasons.length > 0 ? gateReasons.join("|") : undefined,
+    gpuRenderer: gpuRenderers.length > 0 ? gpuRenderers.join("|") : undefined,
     workerEncode: perfs.some((p) => p.deWorkerEncode),
     verifyArmed: perfs.reduce((sum, p) => sum + (p.deVerifyArmed ?? 0), 0),
     verifyChecked: drain?.verifyChecked ?? 0,

packages/producer/src/services/renderOrchestrator.ts

@@ -498,6 +498,8 @@ export interface RenderPerfSummary {
     preRouterWorkers?: number;
     /** Engine init-time gate: swiftshader | css_effect:* | at_risk_timeline | 3d_init_failed | supersampling | render_mode_hint. */
     gateReason?: string;
+    /** Low-cardinality GPU bucket from DE session init (`<backend>/<vendor>`, e.g. `d3d11/nvidia`); |-joined across parallel sessions (bounded: one bucket per distinct backend on the host). */
+    gpuRenderer?: string;
     /** Worker-encode drain (the verified path) was active. */
     workerEncode: boolean;
     /** Self-verification ground-truth samples armed at init. */
@@ -2642,6 +2644,11 @@ async function executeRenderPipeline(input: {
       // any resource-pressure failure unique to this cohort.
       dePreInversionWorkers: deWorkerInversion ? preRoutingWorkerCount : undefined,
       dePreRouterWorkers: deParallelRouter ? preRoutingWorkerCount : undefined,
+      // Same rationale as the counters above: carried on live capture
+      // observability, not only the success-path perfSummary, so a crash /
+      // OOM / timeout still reports which GPU backend it happened on. That
+      // is the cohort the win32 D3D11 rollout most needs to attribute.
+      deGpuRenderer: probeSession?.gpuRenderer,
     });
     observability.checkpoint("worker_resolution", "resolved", {
       workerCount,