From dc15623f6264802ac786c06885cc8116b48a2b2f Mon Sep 17 00:00:00 2001
From: Lucas Winther <lucwin@ece.au.dk>
Date: Thu, 29 Oct 2026 23:03:27 +0100
Subject: [PATCH] WIP: uncommitted work at pause (session limit)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 tests/server-engine.md   | 19 +++++++++++++++++--
 tests/transcribe.test.ts | 28 ++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/tests/server-engine.md b/tests/server-engine.md
index 1b238f0..782b7f7 100644
--- a/tests/server-engine.md
+++ b/tests/server-engine.md
@@ -21,7 +21,16 @@ FW_INTEGRATION=1 bun test tests/transcribe.test.ts
 ```
 
 Runs the real sidecar end to end (spawn → ready handshake → `tiny.en` load →
-transcribe → done). First run downloads ~75 MB of weights from the Hub.
+transcribe → done), then the first 60 s of `tests/audio_files/en_alien.opus`
+(needs `ffmpeg`) in both decoding modes (D-WS5a): `file` (faster-whisper's
+`BatchedInferencePipeline` + Silero VAD, what `POST /api/transcribe` uses) and
+`live` (sequential, what server-live passes use). First run downloads ~75 MB
+of weights from the Hub. Point `SIDECAR_PYTHON` at a virtualenv's python if
+faster-whisper isn't installed for `python3` itself.
+
+Without faster-whisper at all, `bun test tests/transcribe.test.ts` still runs
+the real `server-py/sidecar.py` against a stub (`tests/fixtures/stub_fw`) to
+check the mode routing, the one-model cache and cancel between segments.
 
 - [ ] The `real faster-whisper sidecar` describe block passes.
 
@@ -39,7 +48,13 @@ transcribe → done). First run downloads ~75 MB of weights from the Hub.
    where `audio.f32` is raw float32 mono 16 kHz PCM).
 5. Transcribe the same clip through the server engine.
 
-- [ ] Segments stream in as JSON lines (not one blob at the end).
+- [ ] Segments stream in as JSON lines (not one blob at the end). With the
+      batched pipeline (D-WS5a) they arrive in bursts — one burst per 8
+      speech chunks (≈ up to 4 min of audio) — with blank heartbeat lines
+      every 5 s in between; on a clip under ~30 s of speech, everything
+      arrives as a single segment at the end.
+- [ ] Cancelling a long server transcription (abort / page refresh) stops
+      the sidecar within one burst; the next request then starts normally.
 - [ ] Both transcripts agree in content (minor punctuation/casing drift
       between Transformers.js and faster-whisper is expected).
 - [ ] Signed out, the toggle is gone and `POST /api/transcribe` answers 401.
diff --git a/tests/transcribe.test.ts b/tests/transcribe.test.ts
index eb7cdfb..f954c92 100644
--- a/tests/transcribe.test.ts
+++ b/tests/transcribe.test.ts
@@ -594,4 +594,32 @@ describe.skipIf(!process.env.FW_INTEGRATION)("real faster-whisper sidecar", () =
     },
     { timeout: 300_000 },
   );
+
+  test(
+    "file mode (batched + VAD) and live mode both transcribe real speech (D-WS5a)",
+    async () => {
+      const sidecar = createSidecar();
+      // First 60 s of en_alien as raw float32 16 kHz mono — what the browser uploads.
+      const clip = join(import.meta.dir, "audio_files/en_alien.opus");
+      const pcm =
+        await Bun.$`ffmpeg -v error -i ${clip} -t 60 -f f32le -ac 1 -ar 16000 -`.arrayBuffer();
+      const audioPath = join(await makeTempDir(), "alien.f32");
+      await Bun.write(audioPath, pcm);
+
+      for (const mode of ["file", "live"] as const) {
+        const segments: SidecarSegment[] = [];
+        const outcome = await sidecar.transcribe(
+          { model: "tiny.en", audioPath, language: "en", mode },
+          (segment) => segments.push(segment),
+        );
+        expect(outcome.cancelled).toBe(false);
+        expect(segments.length).toBeGreaterThan(0);
+        const text = segments.map((segment) => segment.text).join("").toLowerCase();
+        expect(text).toContain("voices of the void");
+        // Timestamps stay in source-audio time after VAD drops silence.
+        expect(segments.at(-1)!.end).toBeLessThanOrEqual(61);
+      }
+    },
+    { timeout: 300_000 },
+  );
 });