feat(engine): preflight psnr filter availability and force-fallback to screenshot on missing

packages/engine/src/services/frameCapture.ts

@@ -46,6 +46,7 @@ import {
   produceDrawElementFrameBatch,
 } from "./drawElementService.js";
 import { initThreeDProjection, detectCssEffectRisk } from "./threeDProjection.js";
+import { isPsnrFilterAvailable } from "../utils/psnrFilterAvailability.js";
 import { DEFAULT_CONFIG, applyConcreteGpuScreenshotClamp, type EngineConfig } from "../config.js";
 import type {
   CaptureOptions,
@@ -902,6 +903,28 @@ async function initDrawElementOrTransparentBackground(
       await routeToFallback();
       return;
     }
+    // ffmpeg-psnr preflight: the disk-sample self-verify path
+    // (parallelCoordinator's psnrForDiskSample → psnrDb) shells to
+    // `ffmpeg -lavfi psnr`. When the resident ffmpeg is missing or was built
+    // without libpostproc, every per-sample compare throws and
+    // psnrForDiskSample swallows the error — the safety net silently fails
+    // open. Force-fallback to the reliable capture path so the safety net
+    // for drawElement isn't the one thing standing between a compositor bug
+    // and a shipped video. Skipped under HF_FORCE_DRAWELEMENT (matches the
+    // policy of every other gate below).
+    if (!forceDE && !(await isPsnrFilterAvailable())) {
+      session.deGateReason = "ffmpeg_no_psnr_filter";
+      session.deFallbackTrigger = "ffmpeg_no_psnr_filter";
+      console.warn(
+        `[engine] fast capture: falling back to ${session.launchCaptureMode} capture — ` +
+          "host ffmpeg is missing or was built without the `psnr` filter " +
+          "(libpostproc), so drawElement self-verification cannot run. Install " +
+          "an ffmpeg build that includes libpostproc (or set HYPERFRAMES_FFMPEG_PATH " +
+          "to one) to re-enable fast capture.",
+      );
+      await routeToFallback();
+      return;
+    }
     // SwiftShader gate: drawElement's only advantage is skipping the GPU→CPU
     // screenshot-readback IPC. On a software rasterizer (Docker/CI, no GPU) both
     // paths block on identical software raster, so drawElement is parity-or-slower

packages/engine/src/services/parallelCoordinator.test.ts

@@ -6,6 +6,7 @@ import {
   expectedFramesForTask,
   flagSilentWorkerExits,
   formatWorkerFailure,
+  isFfmpegInfrastructureFailure,
   selectVerifySampleIndicesForTask,
   selectWorkerDiagnostics,
   shouldDisableBrowserPoolForParallelWorker,
@@ -425,3 +426,60 @@ describe("resolveParallelDeVerifySamples", () => {
     expect(resolveParallelDeVerifySamples(2, 3)).toBe(2);
   });
 });
+
+describe("isFfmpegInfrastructureFailure", () => {
+  it("matches an execFile ENOENT (missing ffmpeg binary)", () => {
+    const err = Object.assign(new Error("spawn ffmpeg ENOENT"), { code: "ENOENT" });
+    expect(isFfmpegInfrastructureFailure(err)).toBe(true);
+  });
+
+  it('matches ffmpeg\'s "No such filter" stderr (libpostproc-less build)', () => {
+    const err = Object.assign(new Error("Command failed"), {
+      stderr:
+        "Error initializing filter 'psnr' with args ''\n" +
+        "  No such filter: 'psnr'\n" +
+        "Error opening filters!",
+    });
+    expect(isFfmpegInfrastructureFailure(err)).toBe(true);
+  });
+
+  it("matches the older `Unknown filter 'psnr'` wording (ffmpeg <=5)", () => {
+    const err = Object.assign(new Error("Command failed"), {
+      stderr: "Unknown filter 'psnr'",
+    });
+    expect(isFfmpegInfrastructureFailure(err)).toBe(true);
+  });
+
+  it("does not match per-sample noise (readFile race, transient EPERM)", () => {
+    const eperm = Object.assign(new Error("EACCES: permission denied, open '/tmp/…'"), {
+      code: "EACCES",
+    });
+    expect(isFfmpegInfrastructureFailure(eperm)).toBe(false);
+
+    const parseErr = new Error("psnr parse failed: average=<truncated>");
+    expect(isFfmpegInfrastructureFailure(parseErr)).toBe(false);
+
+    const enoentFile = Object.assign(
+      new Error("ENOENT: no such file or directory, open '/tmp/frame_000042.jpg'"),
+      {
+        code: "ENOENT",
+      },
+    );
+    // ⚠ known aliasing edge: an execFile ENOENT and an fs ENOENT reading the
+    // sample frame share the same code. The discriminator errs toward the
+    // infrastructure classification — a spurious per-sample fs ENOENT
+    // (impossible for a frame that was just written by the worker before this
+    // verify call) would abort the render, which is acceptable given how
+    // rarely that shape appears vs. how important the infra-fail signal is.
+    // Documented here so a future maintainer sees why the assertion below
+    // reads "true": this is the deliberate false-positive on collision.
+    expect(isFfmpegInfrastructureFailure(enoentFile)).toBe(true);
+  });
+
+  it("returns false for null / non-object errors", () => {
+    expect(isFfmpegInfrastructureFailure(null)).toBe(false);
+    expect(isFfmpegInfrastructureFailure(undefined)).toBe(false);
+    expect(isFfmpegInfrastructureFailure("psnr broken")).toBe(false);
+    expect(isFfmpegInfrastructureFailure(42)).toBe(false);
+  });
+});

packages/engine/src/services/parallelCoordinator.ts

@@ -619,11 +619,37 @@ function assertDiskSampleAboveFloor(
   );
 }
 
+/**
+ * Distinguishes infrastructure-class ffmpeg failures (spawn ENOENT, missing
+ * `psnr` filter) from per-sample noise (readFile races, transient tmpdir
+ * EPERM). Only the infrastructure class should terminate the render — the
+ * ffmpeg preflight in `initDrawElementOrTransparentBackground` catches these
+ * at bootstrap, so surfacing them here means the preflight was bypassed or
+ * the host ffmpeg changed mid-render.
+ *
+ * Exported for testing; the discriminator is a pure error-shape read.
+ */
+export function isFfmpegInfrastructureFailure(err: unknown): boolean {
+  if (!err || typeof err !== "object") return false;
+  const record = err as { code?: unknown; message?: unknown; stderr?: unknown };
+  if (record.code === "ENOENT") return true;
+  const message = typeof record.message === "string" ? record.message : "";
+  const stderr = typeof record.stderr === "string" ? record.stderr : "";
+  const text = `${message}\n${stderr}`;
+  // Spawn-side failures ("spawn ffmpeg ENOENT") and filter-side failures
+  // ("No such filter: 'psnr'", ffmpeg <=5 emits "Unknown filter 'psnr'").
+  return /\bENOENT\b|No such filter|Unknown filter/i.test(text);
+}
+
 /**
  * Compare one captured frame file against its ground truth. Returns the
- * PSNR, or null on infrastructure failure (missing file already surfaces
- * via the frame completeness check; ffmpeg spawn/tmpdir here) — a skipped
- * sample is not damage evidence and must not fail the capture.
+ * PSNR, or null on per-sample noise (readFile races, transient EPERM,
+ * unparseable ffmpeg output on a single sample) — a skipped sample is not
+ * damage evidence and must not fail the capture. Re-throws when the error
+ * shape indicates the ffmpeg install itself is broken (missing binary or
+ * missing `psnr` filter): the drawElement self-verify safety net cannot
+ * possibly run in that state, and continuing would silently ship every
+ * remaining frame unverified.
  */
 async function psnrForDiskSample(
   framePath: string,
@@ -634,6 +660,17 @@ async function psnrForDiskSample(
   try {
     return await psnrDb(await readFile(framePath), truth);
   } catch (err) {
+    if (isFfmpegInfrastructureFailure(err)) {
+      const detail = err instanceof Error ? err.message : String(err);
+      throw new Error(
+        `[Parallel] drawElement disk self-verify aborted (worker ${workerId}, frame ${idx}): ` +
+          `ffmpeg or the \`psnr\` filter is unavailable — ${detail}. The preflight in ` +
+          "initDrawElementOrTransparentBackground normally catches this at bootstrap; if you " +
+          "hit this after a successful preflight, ffmpeg was replaced mid-render or " +
+          "HYPERFRAMES_FFMPEG_PATH now points at a different binary.",
+        { cause: err },
+      );
+    }
     console.warn(
       `[Parallel] drawElement disk self-verify sample skipped (worker ${workerId}, ` +
         `frame ${idx}): ${err instanceof Error ? err.message : String(err)}`,

packages/engine/src/utils/psnrFilterAvailability.test.ts

@@ -0,0 +1,172 @@
+import { promisify } from "node:util";
+import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
+
+interface ExecFileCall {
+  file: string;
+  args: readonly string[];
+}
+
+type ExecFileOutcome =
+  | { kind: "ok"; stdout: string; stderr?: string }
+  | { kind: "exit_nonzero"; code: number; stdout?: string; stderr?: string }
+  | { kind: "enoent" };
+
+// Node's built-in `child_process.execFile` carries a `util.promisify.custom`
+// implementation that resolves to `{stdout, stderr}`. A plain-callback mock
+// without that Symbol would be promisified as a single-result function, so
+// `{stdout} = await execFileP(...)` would silently destructure to `undefined`
+// — the exact hazard psnr.ts documents. Stamp the custom impl on the mock so
+// promisify keeps the `{stdout, stderr}` shape.
+function createExecFileSpy(outcome: ExecFileOutcome): {
+  execFile: (
+    file: string,
+    args: readonly string[],
+    options: unknown,
+    callback: (err: Error | null, stdout?: string, stderr?: string) => void,
+  ) => void;
+  calls: ExecFileCall[];
+} {
+  const calls: ExecFileCall[] = [];
+
+  async function run(
+    file: string,
+    args: readonly string[],
+  ): Promise<{ stdout: string; stderr: string }> {
+    calls.push({ file, args });
+    if (outcome.kind === "enoent") {
+      const err = new Error("spawn ffmpeg ENOENT") as NodeJS.ErrnoException;
+      err.code = "ENOENT";
+      throw err;
+    }
+    if (outcome.kind === "exit_nonzero") {
+      const err = new Error(`Command failed: ffmpeg (exit ${outcome.code})`) as Error & {
+        code: number;
+        stdout?: string;
+        stderr?: string;
+      };
+      err.code = outcome.code;
+      err.stdout = outcome.stdout ?? "";
+      err.stderr = outcome.stderr ?? "";
+      throw err;
+    }
+    return { stdout: outcome.stdout, stderr: outcome.stderr ?? "" };
+  }
+
+  const execFile = ((
+    file: string,
+    args: readonly string[],
+    _options: unknown,
+    callback: (err: Error | null, stdout?: string, stderr?: string) => void,
+  ) => {
+    run(file, args).then(
+      ({ stdout, stderr }) => process.nextTick(() => callback(null, stdout, stderr)),
+      (err: Error) => process.nextTick(() => callback(err)),
+    );
+  }) as ((
+    file: string,
+    args: readonly string[],
+    options: unknown,
+    callback: (err: Error | null, stdout?: string, stderr?: string) => void,
+  ) => void) & { [key: symbol]: unknown };
+  (execFile as { [k: symbol]: unknown })[promisify.custom] = (
+    file: string,
+    args: readonly string[],
+  ) => run(file, args);
+
+  return { execFile, calls };
+}
+
+beforeEach(() => {
+  vi.resetModules();
+});
+
+afterEach(() => {
+  vi.doUnmock("node:child_process");
+});
+
+describe("isPsnrFilterAvailable", () => {
+  it("returns true when `ffmpeg -filters` output lists the psnr filter", async () => {
+    const { execFile } = createExecFileSpy({
+      kind: "ok",
+      stdout: [
+        "Filters:",
+        "  T.. overlay          VV->V      Overlay a video source on top of the input.",
+        "  T.. psnr             VV->V      Calculate the PSNR between two video streams.",
+        "  ... yadif            V->V       Deinterlace the input image.",
+      ].join("\n"),
+    });
+    vi.doMock("node:child_process", () => ({ execFile }));
+
+    const { isPsnrFilterAvailable } = await import("./psnrFilterAvailability.js");
+    await expect(isPsnrFilterAvailable()).resolves.toBe(true);
+  });
+
+  it("returns false when `ffmpeg -filters` output omits the psnr filter", async () => {
+    const { execFile } = createExecFileSpy({
+      kind: "ok",
+      stdout: [
+        "Filters:",
+        "  T.. overlay          VV->V      Overlay a video source on top of the input.",
+        "  ... yadif            V->V       Deinterlace the input image.",
+      ].join("\n"),
+    });
+    vi.doMock("node:child_process", () => ({ execFile }));
+
+    const { isPsnrFilterAvailable } = await import("./psnrFilterAvailability.js");
+    await expect(isPsnrFilterAvailable()).resolves.toBe(false);
+  });
+
+  it("returns false when the ffmpeg binary is missing (ENOENT from execFile)", async () => {
+    const { execFile } = createExecFileSpy({ kind: "enoent" });
+    vi.doMock("node:child_process", () => ({ execFile }));
+
+    const { isPsnrFilterAvailable } = await import("./psnrFilterAvailability.js");
+    await expect(isPsnrFilterAvailable()).resolves.toBe(false);
+  });
+
+  it("returns false on a non-zero exit from `ffmpeg -filters`", async () => {
+    const { execFile } = createExecFileSpy({
+      kind: "exit_nonzero",
+      code: 1,
+      stderr: "Unrecognized option '-filters'.",
+    });
+    vi.doMock("node:child_process", () => ({ execFile }));
+
+    const { isPsnrFilterAvailable } = await import("./psnrFilterAvailability.js");
+    await expect(isPsnrFilterAvailable()).resolves.toBe(false);
+  });
+
+  it("memoizes the probe across calls and re-probes after resetPsnrFilterAvailabilityCache", async () => {
+    const { execFile, calls } = createExecFileSpy({
+      kind: "ok",
+      stdout: "  T.. psnr             VV->V      Calculate the PSNR",
+    });
+    vi.doMock("node:child_process", () => ({ execFile }));
+
+    const { isPsnrFilterAvailable, resetPsnrFilterAvailabilityCache } =
+      await import("./psnrFilterAvailability.js");
+
+    await isPsnrFilterAvailable();
+    await isPsnrFilterAvailable();
+    await isPsnrFilterAvailable();
+    expect(calls.length).toBe(1);
+
+    resetPsnrFilterAvailabilityCache();
+    await isPsnrFilterAvailable();
+    expect(calls.length).toBe(2);
+  });
+
+  it("does not treat a whole-string 'psnr' inside another word as the filter", async () => {
+    const { execFile } = createExecFileSpy({
+      kind: "ok",
+      stdout: [
+        "Filters:",
+        "  T.. bpsnrx            V->V       (hypothetical extended filter, not the real psnr)",
+      ].join("\n"),
+    });
+    vi.doMock("node:child_process", () => ({ execFile }));
+
+    const { isPsnrFilterAvailable } = await import("./psnrFilterAvailability.js");
+    await expect(isPsnrFilterAvailable()).resolves.toBe(false);
+  });
+});

packages/engine/src/utils/psnrFilterAvailability.ts

@@ -0,0 +1,58 @@
+import { execFile } from "node:child_process";
+import { promisify } from "node:util";
+import { getFfmpegBinary } from "./ffmpegBinaries.js";
+
+/**
+ * Preflight for the ffmpeg `psnr` filter used by drawElement self-verify
+ * (see `psnr.ts`). Some host ffmpeg builds ship without `libpostproc` and
+ * silently omit the filter — every downstream `psnrDb()` call then throws
+ * mid-render and the disk-sample verifier swallows it (fail-open safety net).
+ * A cached one-shot probe surfaces the shape once, at bootstrap, so the
+ * capture-session router can force-fallback to the reliable screenshot path
+ * instead of arming a drawElement render whose safety net cannot run.
+ *
+ * Cache lifetime is the current process: an operator's ffmpeg install does
+ * not change across renders within the same CLI invocation, and re-probing
+ * per session would burn ~50-100ms of subprocess spawn per capture worker.
+ */
+let cached: Promise<boolean> | null = null;
+
+/**
+ * Returns true when the resident ffmpeg exposes the `psnr` filter. False on
+ * any probe failure — missing binary (ENOENT), non-zero exit, timeout,
+ * unparseable output — because in every case the drawElement self-verify
+ * path cannot function. Never rejects.
+ *
+ * Result is memoized per process; call {@link resetPsnrFilterAvailabilityCache}
+ * from tests that need to re-probe.
+ */
+export function isPsnrFilterAvailable(): Promise<boolean> {
+  if (cached === null) cached = probe();
+  return cached;
+}
+
+/** Test-only: drop the memoized probe result. */
+export function resetPsnrFilterAvailabilityCache(): void {
+  cached = null;
+}
+
+async function probe(): Promise<boolean> {
+  // Match `psnr.ts`: promisify lazily so a partial `node:child_process` mock
+  // (test that omits `execFile`) doesn't crash at module load — it fails at
+  // call time instead, and the try/catch below converts that to `false`.
+  const execFileP = promisify(execFile);
+  try {
+    const { stdout } = await execFileP(getFfmpegBinary(), ["-hide_banner", "-filters"], {
+      maxBuffer: 4 * 1024 * 1024,
+      timeout: 5_000,
+    });
+    // ffmpeg's `-filters` output lists one filter per line, e.g.
+    //   " T.. psnr             VV->V      Calculate the PSNR between two video streams."
+    // A whole-word match keeps `multi-psnr` (hypothetical) from masquerading
+    // as the real filter, and dodges the banner text that mentions PSNR in
+    // prose on some builds.
+    return /(^|\s)psnr(\s|$)/m.test(stdout);
+  } catch {
+    return false;
+  }
+}