Validate complete speech decode windows and retain rejected ASR output

tools/speech-eval/test_contract.py

@@ -4,11 +4,53 @@ from pathlib import Path
 import unittest
 import tempfile
 import sys
-from run import segments, run_owned
+import os
+import wave
+from run import segments, run_owned, recognized_window, decode_command, decoded_frames
 from score import score
 
 
 class ContractTests(unittest.TestCase):
+    @unittest.skipUnless(os.environ.get("SEARCHI_TEST_FFMPEG"), "Requires verified CPU FFmpeg")
+    def test_actual_ffmpeg_full_window_and_partial_tail_sample_coverage(self):
+        ffmpeg = Path(os.environ["SEARCHI_TEST_FFMPEG"])
+        with tempfile.TemporaryDirectory() as parent:
+            scratch = Path(parent)
+            for rate in [44100, 48000]:
+                with self.subTest(rate=rate):
+                    source = scratch / f"source-{rate}.wav"
+                    with wave.open(str(source), "wb") as audio:
+                        audio.setnchannels(1)
+                        audio.setsampwidth(2)
+                        audio.setframerate(rate)
+                        audio.writeframes(b"\x00\x00" * (rate * 31))
+                    for offset, length, expected in [(0, 30000, 480000), (30000, 1000, 16000)]:
+                        output = scratch / "decoded.wav"
+                        run_owned(decode_command(ffmpeg, source, offset, length, output), scratch,
+                                  "samplecoverage", [(output, 970000)], 30)
+                        self.assertEqual(decoded_frames(output, length), expected)
+
+    def test_threefold_truncation_rejected(self):
+        with tempfile.TemporaryDirectory() as parent:
+            path = Path(parent) / "truncated.wav"
+            with wave.open(str(path), "wb") as audio:
+                audio.setnchannels(1)
+                audio.setsampwidth(2)
+                audio.setframerate(16000)
+                audio.writeframes(b"\x00\x00" * 160000)
+            with self.assertRaises(ValueError):
+                decoded_frames(path, 30000)
+
+    def test_invalid_actual_json_is_retained_and_next_window_parses(self):
+        invalid = {"transcription": [{"offsets": {"from": 0, "to": 30010}, "text": "synthetic test"}]}
+        valid = {"transcription": [{"offsets": {"from": 0, "to": 10}, "text": "synthetic test"}]}
+        rows = [recognized_window(raw, offset, 30000, 1, 2) for raw, offset in [(invalid, 0), (valid, 30000)]]
+        self.assertEqual(rows[0]["actual_whisper_json"], invalid)
+        self.assertEqual(rows[0]["segments"], [])
+        self.assertIn("validation_error", rows[0])
+        self.assertNotIn("validation_error", rows[1])
+        self.assertEqual(rows[1]["segments"][0]["start_ms"], 30000)
+
     def test_timeout_and_output_overflow_terminate_owned_child(self):
         for name, code, error, timeout in [
             ("timeout", "import time; time.sleep(10)", TimeoutError, 0.1),