feat: reconcile speaker identities through OpenRouter audio

Short chunk overlaps often contain only one participant, so returning
speakers receive new transcript IDs. MAI can also split one voice into
several IDs within a single request, which overlap stitching cannot fix.

Add an opt-in audio comparison pass: --speakers N selects Gemini 3.8 Flash
with a known count, and --speaker-model allows another compatible model.
Keep request-local identities separate, select up to three clean excerpts
per ID, and compare all excerpts in one OpenRouter request. Gemini uses
Google AI Studio because the Vertex backend limits prompts to one audio
file. No local model or extra Python dependency is required.

Only reconcile identities whose sample assignments agree. Preserve
uncertain identities separately, reject incomplete or malformed replies,
and retain the original words and timestamps. Bound sample count and
request size, clip sampling to the real audio duration, and extend worker
cleanup and buffered output to the comparison step. Document the sampled
method's limitations and additional provider request.

Test Plan:
- python3 -B -m unittest -v: all 82 tests passed, including real MP3
  encoding with fake transcription/comparison responses and cancellation.
- bash -n transcribe: passed.
- git diff --cached --check: passed.
- Live API and voice accuracy unverified: this workspace could not access
  the configured 1Password credential. Mocked responses prove pipeline
  behavior, not model accuracy on the supplied recording.

tests/fake_provider.py

@@ -18,21 +18,82 @@ args = sys.argv[1:]
 request_path = Path(args[args.index("--data-binary") + 1][1:])
 request = json.loads(request_path.read_text())
 output = Path(args[args.index("-o") + 1])
-index = int(output.stem.split("-")[1])
-manifest = json.loads((output.parent / "chunks.json").read_text())
-chunk = manifest[index]
 mode = os.environ.get("TRANSCRIBE_TEST_MODE", "ok")
 events_path = Path(os.environ["TRANSCRIBE_TEST_LOG"]).with_suffix(".events.jsonl")
+is_comparison = "https://openrouter.ai/api/v1/chat/completions" in args
+index = -1 if is_comparison else int(output.stem.split("-")[1])
+staging = output.parent.parent if is_comparison else output.parent
 
 
 def event(kind, **extra):
     record = dict(event=kind, index=index, pid=os.getpid(), group=os.getpgrp(),
-                  time=time.monotonic(), staging=str(output.parent), **extra)
+                  time=time.monotonic(), staging=str(staging), **extra)
     with events_path.open("a") as log:
         log.write(json.dumps(record) + "\n")
 
 
 event("start")
+if is_comparison:
+    samples = json.loads((output.parent / "samples.json").read_text())
+    content = request["messages"][-1]["content"]
+    audio_parts = [part["input_audio"] for part in content if part["type"] == "input_audio"]
+    assert len(content) == 2 * len(samples) == 2 * len(audio_parts)
+    for number, sample in enumerate(samples):
+        assert content[number * 2] == {"type": "text", "text": f"Sample ID {sample['id']}"}
+        assert content[number * 2 + 1]["type"] == "input_audio"
+    assert request["response_format"]["type"] == "json_schema"
+    assert request["response_format"]["json_schema"]["strict"] is True
+    prompt = "\n".join(part["text"] for message in request["messages"]
+                       for part in (message["content"] if isinstance(message["content"], list)
+                                    else [{"type": "text", "text": message["content"]}])
+                       if part["type"] == "text")
+    assert not any(word in prompt for word in ("Alpha.", "Again.", "Beta.", "AlphaLate.", "BetaLate."))
+    durations = []
+    for number, part in enumerate(audio_parts):
+        assert part["format"] == "mp3"
+        audio = output.parent / f"checked-{number}.mp3"
+        audio.write_bytes(base64.b64decode(part["data"], validate=True))
+        info = json.loads(subprocess.check_output([
+            "ffprobe", "-v", "error", "-show_entries",
+            "format=duration:stream=codec_name,sample_rate,channels", "-of", "json", str(audio),
+        ], text=True))
+        assert info["streams"][0] == {"codec_name": "mp3", "sample_rate": "16000", "channels": 1}
+        durations.append(float(info["format"]["duration"]))
+        assert 1.5 <= durations[-1] <= 8.1
+    Path(os.environ["TRANSCRIBE_TEST_LOG"]).with_suffix(".speakers.json").write_text(json.dumps({
+        "request": request, "samples": samples, "durations": durations, "staging": str(staging),
+    }))
+    if mode == "reconcile-blocked":
+        child = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(30)"])
+        event("child", child_pid=child.pid)
+        time.sleep(30)
+    if mode == "reconcile-http-error":
+        output.write_text('{"error":{"message":"simulated comparison failure"}}')
+        sys.exit(22)
+    if mode == "reconcile-bad-json":
+        output.write_text("not json")
+        sys.exit(0)
+    assignments = [{"sample": sample["id"], "speaker": 0 if round(sample["start"]) in (1, 6, 60) else 1}
+                   for sample in samples]
+    if mode == "reconcile-missing":
+        assignments.pop()
+    elif mode == "reconcile-duplicate":
+        assignments.append(assignments[0])
+    elif mode == "reconcile-unknown-sample":
+        assignments[0]["sample"] = "not-a-sample"
+    elif mode == "reconcile-invalid-speaker":
+        assignments[0]["speaker"] = -1
+    elif mode == "reconcile-null":
+        assignments[0]["speaker"] = None
+    output.write_text(json.dumps({"choices": [{
+        "finish_reason": "length" if mode == "reconcile-truncated" else "stop",
+        "message": {"content": json.dumps({"assignments": assignments})},
+    }]}))
+    event("finish")
+    sys.exit(0)
+
+manifest = json.loads((output.parent / "chunks.json").read_text())
+chunk = manifest[index]
 if mode in ("parallel-error", "blocked") and index == 0:
     child = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(30)"])
     event("child", child_pid=child.pid)
@@ -118,6 +179,17 @@ else:
     if mode == "parallel":
         middle = (chunk["end"] - chunk["start"]) / 2
         words = [{"word": f"Part{index}.", "start": middle, "end": middle + 0.4}]
+    if mode.startswith("reconcile"):
+        # Two labels already describe voice A inside the first request; later
+        # chunks reuse the same local numbers for different request identities.
+        words = [
+            {"word": text, "start": start - chunk["start"], "end": start + 2 - chunk["start"],
+             "speaker": speaker}
+            for text, start, speaker in [
+                ("Alpha.", 1, 7), ("Again.", 6, 8), ("Beta.", 12, 9),
+                ("AlphaLate.", 60, 9), ("BetaLate.", 65, 7),
+            ] if start >= chunk["start"] and start + 2 <= chunk["end"]
+        ]
     response = {"text": " ".join(w["word"] for w in words), "words": words}
 output.write_text(json.dumps(response))
 event("finish")