feat: add post-diarization speaker mapping workflow

PROJECT_KNOWLEDGE.md

@@ -39,6 +39,14 @@ Implemented:
   configurable safe input budget, falls back to complete plain transcript text
   when necessary, and fails before any Ollama request if even that input is too
   large. Silent head/tail truncation is prohibited.
+- The `qwen3.8:27b` direct-protocol stage explicitly requests `num_ctx=32768`
+  and `think=false`; the practical prompt target is approximately 29,000 tokens.
+  A 31,038-token synthetic prompt passed, but larger prompts are not assumed safe
+  from the model's advertised 262,144-token native context alone.
+- `regenerate_mvp_protocol` updates the run's validated Meeting Context and
+  regenerates protocol artifacts from the existing diarized transcript when
+  available. It never reruns audio preparation, Whisper or Pyannote, and it
+  preserves anonymous speaker labels in the source transcript.
 - Non-LLM unit tests for chunking, extraction helpers, protocol rendering and
   gold-test runner validation.
 - Meeting Context V1 scaffold and documentation for manually maintained

docs/diarization.md

@@ -48,9 +48,9 @@ derived representation sent to prompt construction.
 
 Before contacting Ollama, Meeting Lab conservatively estimates prompt tokens
 from UTF-8 byte count without adding a model tokenizer dependency. The default safe
-budget is 16,200 estimated tokens, below the observed 16,386-token effective
+budget is 29,000 estimated tokens within the explicitly configured 32,768-token
-boundary even when a larger `num_ctx` was requested. The estimate is calibrated
+Ollama context. The estimate is calibrated against the currently validated
-against the currently validated German BPD input and is configurable through
+German BPD input and is configurable through
 `MvpMeetingConfig.protocol_safe_input_token_budget` or
 `--protocol-safe-input-token-budget`.
 

src/meeting_lab/orchestration/mvp.py

@@ -30,6 +30,7 @@ from src.meeting_lab.models.meeting_context import (
 from src.meeting_lab.progress import ProgressEvent, ProgressSink, ProgressStatus
 from src.meeting_lab.protocol.generate_direct_protocol import (
     DEFAULT_MODEL,
+    DEFAULT_NUM_CTX,
     DEFAULT_SAFE_INPUT_TOKEN_BUDGET,
     DirectProtocolResult,
     generate_direct_protocol,
@@ -55,6 +56,7 @@ class MvpMeetingConfig:
     threads: str | int = "auto"
     model: str = DEFAULT_MODEL
     ollama_endpoint: str = DEFAULT_ENDPOINT
+    protocol_num_ctx: int = DEFAULT_NUM_CTX
     protocol_safe_input_token_budget: int = DEFAULT_SAFE_INPUT_TOKEN_BUDGET
     diarization: str = "off"
     diarization_runtime: str = "native"
@@ -69,6 +71,64 @@ class MvpRunResult:
     protocol_path: Path | None
 
 
+def regenerate_mvp_protocol(
+    run_dir: Path,
+    *,
+    meeting_context: ContextInput,
+    model: str = DEFAULT_MODEL,
+    ollama_endpoint: str = DEFAULT_ENDPOINT,
+    protocol_num_ctx: int = DEFAULT_NUM_CTX,
+    protocol_safe_input_token_budget: int = DEFAULT_SAFE_INPUT_TOKEN_BUDGET,
+    progress_sink: ProgressSink | None = None,
+) -> MvpRunResult:
+    """Regenerate only protocol artifacts from an existing completed run."""
+    started = time.perf_counter()
+    run_dir = Path(run_dir)
+    context = _effective_context(meeting_context)
+    if context is None:
+        raise ValueError("Meeting Context is required for protocol regeneration.")
+    if protocol_num_ctx <= 0:
+        raise ValueError("Protocol Ollama context size must be positive.")
+    if protocol_safe_input_token_budget <= 0:
+        raise ValueError("Protocol safe input token budget must be positive.")
+
+    diarized_transcript = run_dir / "diarization" / "transcript_diarized.json"
+    plain_transcript = run_dir / "transcript" / "transcript.json"
+    transcript_path = (
+        diarized_transcript if diarized_transcript.is_file() else plain_transcript
+    )
+    if not transcript_path.is_file():
+        raise FileNotFoundError(
+            f"Existing run has no protocol transcript artifact: {run_dir}"
+        )
+
+    context_path = run_dir / "context" / "meeting_context.yaml"
+    write_meeting_context(context, context_path)
+    _emit(progress_sink, "protocol_generation", "started", started)
+    try:
+        result = generate_direct_protocol(
+            transcript_path,
+            context_path,
+            model=model,
+            endpoint=ollama_endpoint,
+            num_ctx=protocol_num_ctx,
+            safe_input_token_budget=protocol_safe_input_token_budget,
+        )
+        protocol_path = _persist_protocol(run_dir, result)
+    except Exception as exc:
+        _emit(
+            progress_sink,
+            "failed",
+            "failed",
+            started,
+            message=f"protocol_generation: {type(exc).__name__}: {exc}",
+        )
+        raise
+    _emit(progress_sink, "protocol_generation", "completed", started)
+    _emit(progress_sink, "completed", "completed", started)
+    return MvpRunResult(0, run_dir, protocol_path)
+
+
 def create_unique_run_dir(
     output_root: Path,
     meeting_name: str,
@@ -131,6 +191,8 @@ def _validate_inputs(
         raise ValueError("A diarization container image is required.")
     if config.protocol_safe_input_token_budget <= 0:
         raise ValueError("Protocol safe input token budget must be positive.")
+    if config.protocol_num_ctx <= 0:
+        raise ValueError("Protocol Ollama context size must be positive.")
 
 
 def _emit(
@@ -363,6 +425,7 @@ def run_mvp_meeting(
             preserved_context,
             model=config.model,
             endpoint=config.ollama_endpoint,
+            num_ctx=config.protocol_num_ctx,
             safe_input_token_budget=config.protocol_safe_input_token_budget,
         )
         stage_runtimes["protocol"] = round(time.perf_counter() - stage_started, 3)

src/meeting_lab/protocol/direct_protocol_prompt.py

@@ -15,6 +15,8 @@ Beginne mit # Meeting Protocol. Gliedere themenorientiert mit ## <Thema> und syn
 
 Entferne nur Wiederholungen, Füllwörter und Gesprächsrauschen. Erfinde keine Fakten oder Identitäten. Gib kein JSON, keine Sprecherlabels und kein Denkprotokoll aus. Eine belegte themenübergreifende Maßnahmenliste am Ende ist optional."""
 
+MAPPED_SPEAKER_ATTRIBUTION_INSTRUCTION = """Nutze die autoritativen SPEAKER_XX-zu-Teilnehmer-Zuordnungen im Meeting-Kontext, um ausdrücklich belegte Aussagen, Positionen, Entscheidungen, Zuweisungen und angenommene persönliche Verpflichtungen namentlich zuzuordnen. Eine ausdrückliche Ich-Zusage eines zugeordneten Sprechers belegt persönliche Verantwortung. Unterscheide stets den Sprecher einer Aussage von darin nur erwähnten Personen. Leite für nicht zugeordnete Sprecher keine Identität ab und erfinde keine persönliche Verantwortung. Gib die technischen SPEAKER_XX-Bezeichnungen nicht im nutzerseitigen Protokoll aus."""
+
 
 def build_direct_protocol_prompt(
     transcript: str,

src/meeting_lab/protocol/generate_direct_protocol.py

@@ -20,6 +20,7 @@ from src.meeting_lab.models.meeting_context import (
 )
 from src.meeting_lab.protocol.direct_protocol_prompt import (
     COMPACT_DIARIZED_PROTOCOL_INSTRUCTION,
+    MAPPED_SPEAKER_ATTRIBUTION_INSTRUCTION,
     build_direct_protocol_prompt,
 )
 from src.meeting_lab.protocol.transcript_input import (
@@ -33,7 +34,7 @@ DEFAULT_MODEL = "qwen3.6:35B-A3B"
 DEFAULT_NUM_CTX = 32768
 DEFAULT_NUM_PREDICT = 8192
 DEFAULT_TIMEOUT = 1800
-DEFAULT_SAFE_INPUT_TOKEN_BUDGET = 16_200
+DEFAULT_SAFE_INPUT_TOKEN_BUDGET = 29_000
 ESTIMATED_UTF8_BYTES_PER_TOKEN = 4.4
 
 
@@ -106,10 +107,16 @@ def select_transcript_input(
             plain_text = plain_segment_transcript(transcript.get("segments"))
         except TranscriptInputError as exc:
             raise DirectProtocolError(str(exc)) from exc
+        instruction = COMPACT_DIARIZED_PROTOCOL_INSTRUCTION
+        if (
+            rendered_context
+            and "Confirmed diarization speaker mappings" in rendered_context
+        ):
+            instruction = f"{instruction}\n\n{MAPPED_SPEAKER_ATTRIBUTION_INSTRUCTION}"
         compact_prompt = build_direct_protocol_prompt(
             compact.text,
             rendered_context,
-            instruction=COMPACT_DIARIZED_PROTOCOL_INSTRUCTION,
+            instruction=instruction,
         )
         compact_estimate = estimate_input_tokens(compact_prompt)
         if compact_estimate <= safe_input_token_budget:
@@ -205,6 +212,19 @@ def generate_direct_protocol(
         "input_token_estimation_method": "utf8_bytes_divided_by_4.4",
         "fallback_used": selected.fallback_used,
         "diarization_enabled": selected.diarization_enabled,
+        "speaker_attribution_available": (
+            True
+            if selected.representation == "diarized_compact"
+            else False
+            if selected.representation == "plain_transcript_fallback"
+            else None
+        ),
+        "speaker_attribution_loss_reason": (
+            "plain_transcript_fallback"
+            if selected.representation == "plain_transcript_fallback"
+            else None
+        ),
+        "speaker_mapping_count": len(context.speaker_mappings) if context else 0,
     }
     return DirectProtocolResult(
         protocol_text=generation.text,

tests/test_direct_protocol.py

@@ -116,6 +116,7 @@ class GeneratorTests(unittest.TestCase):
         self.assertEqual(check.call_count, 1)
         self.assertEqual(call.call_count, 1)
         self.assertEqual(call.call_args.args[1], "qwen3.6:35B-A3B")
+        self.assertEqual(call.call_args.kwargs["num_ctx"], 32768)
         self.assertEqual(result.runtime_metadata["request_count"], 1)
         self.assertEqual(result.runtime_metadata["prompt_token_count"], 123)
         self.assertFalse(result.runtime_metadata["think"])
@@ -181,7 +182,7 @@ class OllamaTests(unittest.TestCase):
         with patch.object(ollama.requests, "post", return_value=response) as post:
             result = ollama.generate_once(
                 "http://localhost:11434",
-                "chosen:model",
+                "qwen3.8:27b",
                 "prompt",
                 timeout=30,
                 num_ctx=32768,
@@ -190,8 +191,9 @@ class OllamaTests(unittest.TestCase):
 
         self.assertEqual(post.call_count, 1)
         payload = post.call_args.kwargs["json"]
-        self.assertEqual(payload["model"], "chosen:model")
+        self.assertEqual(payload["model"], "qwen3.8:27b")
         self.assertEqual(payload["options"]["temperature"], 0.0)
+        self.assertEqual(payload["options"]["num_ctx"], 32768)
         self.assertFalse(payload["think"])
         self.assertFalse(payload["stream"])
         self.assertEqual(result.raw_response, raw)

tests/test_mvp_api.py

@@ -115,7 +115,7 @@ class MvpApiTests(unittest.TestCase):
                 patch.object(mvp_api, "prepare_audio", side_effect=fake_prepare),
                 patch.object(
                     mvp_api, "generate_direct_protocol", side_effect=fake_protocol
-                ),
+                ) as protocol_generator,
                 patch.object(subprocess, "run") as subprocess_run,
             ):
                 result = mvp_api.run_mvp_meeting(
@@ -142,6 +142,65 @@ class MvpApiTests(unittest.TestCase):
                 ],
             )
             self.assertTrue(all(event.progress is None for event in events))
+            self.assertEqual(protocol_generator.call_args.kwargs["num_ctx"], 32_768)
+            self.assertEqual(
+                protocol_generator.call_args.kwargs["safe_input_token_budget"],
+                29_000,
+            )
+
+    def test_protocol_only_regeneration_reuses_diarized_artifacts(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            run_dir = root / "existing-run"
+            diarization_dir = run_dir / "diarization"
+            diarization_dir.mkdir(parents=True)
+            source = diarization_dir / "transcript_diarized.json"
+            source.write_text(
+                json.dumps(
+                    {
+                        "text": "SPEAKER_00: Existing statement.\n",
+                        "segments": [
+                            {
+                                "start": 0.0,
+                                "end": 1.0,
+                                "speaker_id": "SPEAKER_00",
+                                "text": "Existing statement.",
+                            }
+                        ],
+                        "speaker_labels_anonymous": True,
+                    }
+                ),
+                encoding="utf-8",
+            )
+            source_before = source.read_bytes()
+            mapped_context = context_data()
+            mapped_context["speaker_mappings"] = {"SPEAKER_00": "person-1"}
+            with (
+                patch.object(mvp_api, "prepare_audio") as preparation,
+                patch.object(mvp_api, "transcribe_audio") as transcription,
+                patch.object(mvp_api, "diarize_audio") as diarization,
+                patch.object(
+                    mvp_api, "generate_direct_protocol", side_effect=fake_protocol
+                ) as protocol,
+            ):
+                result = mvp_api.regenerate_mvp_protocol(
+                    run_dir,
+                    meeting_context=mapped_context,
+                    model="qwen3.8:27b",
+                    protocol_num_ctx=32_768,
+                    protocol_safe_input_token_budget=29_000,
+                )
+
+            self.assertEqual(result.exit_code, 0)
+            self.assertEqual(result.protocol_path, run_dir / "protocol.md")
+            preparation.assert_not_called()
+            transcription.assert_not_called()
+            diarization.assert_not_called()
+            self.assertEqual(protocol.call_args.args[0], source)
+            self.assertEqual(protocol.call_args.kwargs["num_ctx"], 32_768)
+            self.assertEqual(source.read_bytes(), source_before)
+            persisted = load_meeting_context(run_dir / "context/meeting_context.yaml")
+            self.assertEqual(persisted.speaker_mappings, {"SPEAKER_00": "person-1"})
 
     def test_failure_emits_terminal_failure_event(self):
         with tempfile.TemporaryDirectory() as directory:
@@ -180,7 +239,8 @@ class MvpApiTests(unittest.TestCase):
             self.assertEqual(delegated.whisper_executable, "whisper-cli")
             self.assertEqual(delegated.ffmpeg_executable, "ffmpeg")
             self.assertTrue(delegated.audio_normalization)
-            self.assertEqual(delegated.protocol_safe_input_token_budget, 16_200)
+            self.assertEqual(delegated.protocol_num_ctx, 32_768)
+            self.assertEqual(delegated.protocol_safe_input_token_budget, 29_000)
             self.assertEqual(api.call_args.kwargs["meeting_context"], context_data())
 
     def test_cli_explicit_audio_normalization_values_are_propagated(self):

tests/test_protocol_transcript_input.py

@@ -2,9 +2,10 @@ import json
 import tempfile
 import unittest
 from pathlib import Path
-from unittest.mock import Mock
+from unittest.mock import Mock, patch
 
 from src.meeting_lab.diarization.alignment import diarized_transcript_text
+from src.meeting_lab.llm import ollama
 from src.meeting_lab.llm.ollama import OllamaGeneration
 from src.meeting_lab.protocol.direct_protocol_prompt import (
     COMPACT_DIARIZED_PROTOCOL_INSTRUCTION,
@@ -136,6 +137,81 @@ class ProtocolInputBudgetTests(unittest.TestCase):
         self.assertEqual(result.transcript_input, compact)
         self.assertEqual(call.call_count, 1)
 
+    def test_mapped_speakers_and_statements_reach_final_ollama_payload(self) -> None:
+        diarized = {
+            "text": "",
+            "segments": [
+                {
+                    "start": 0.0,
+                    "end": 1.0,
+                    "speaker_id": "SPEAKER_00",
+                    "text": "We will run the trial on Wednesday.",
+                },
+                {
+                    "start": 1.0,
+                    "end": 2.0,
+                    "speaker_id": "SPEAKER_01",
+                    "text": "I will prepare the raw materials before then.",
+                },
+                {
+                    "start": 2.0,
+                    "end": 3.0,
+                    "speaker_id": "SPEAKER_00",
+                    "text": "Good. Anna owns the material preparation.",
+                },
+            ],
+            "speaker_labels_anonymous": True,
+            "alignment_source": "exclusive_diarization",
+        }
+        context = {
+            "schema_version": "1",
+            "meeting": {
+                "meeting_id": "speaker-test",
+                "title": "Speaker test",
+                "language": "en",
+            },
+            "participants": [
+                {"participant_id": "martin", "display_name": "Martin"},
+                {"participant_id": "anna", "display_name": "Anna"},
+            ],
+            "speaker_mappings": {"SPEAKER_00": "martin", "SPEAKER_01": "anna"},
+            "mentioned_people": [],
+            "organization": {"departments": []},
+            "known_entities": {},
+        }
+        response = Mock()
+        response.raise_for_status.return_value = None
+        response.json.return_value = {"response": "# Meeting Protocol\n", "done": True}
+
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            transcript = self._write(root, diarized)
+            context_path = root / "context.yaml"
+            context_path.write_text(json.dumps(context), encoding="utf-8")
+            with patch.object(ollama.requests, "post", return_value=response) as post:
+                result = generate_direct_protocol(
+                    transcript,
+                    context_path,
+                    model="qwen3.8:27b",
+                    model_check=Mock(return_value={}),
+                )
+
+        prompt = post.call_args.kwargs["json"]["prompt"]
+        self.assertEqual(result.exact_prompt, prompt)
+        self.assertIn("- SPEAKER_00: Martin (participant_id: martin)", prompt)
+        self.assertIn("- SPEAKER_01: Anna (participant_id: anna)", prompt)
+        self.assertIn("SPEAKER_00: We will run the trial on Wednesday.", prompt)
+        self.assertIn(
+            "SPEAKER_01: I will prepare the raw materials before then.", prompt
+        )
+        self.assertIn("SPEAKER_00: Good. Anna owns the material preparation.", prompt)
+        self.assertNotIn("Martin: We will run the trial on Wednesday.", prompt)
+        self.assertNotIn("Anna: I will prepare the raw materials before then.", prompt)
+        self.assertIn("autoritativen SPEAKER_XX-zu-Teilnehmer-Zuordnungen", prompt)
+        self.assertIn("Ich-Zusage", prompt)
+        self.assertIn("nur erwähnten Personen", prompt)
+        self.assertIn("keine persönliche Verantwortung", prompt)
+
     def test_plain_fallback_selected_when_diarized_compact_exceeds_budget(self) -> None:
         with tempfile.TemporaryDirectory() as directory:
             root = Path(directory)
@@ -180,6 +256,13 @@ class ProtocolInputBudgetTests(unittest.TestCase):
         )
         self.assertTrue(result.runtime_metadata["fallback_used"])
         self.assertEqual(result.transcript_input, plain)
+        self.assertNotIn("SPEAKER_00", result.exact_prompt)
+        self.assertNotIn("SPEAKER_01", result.exact_prompt)
+        self.assertFalse(result.runtime_metadata["speaker_attribution_available"])
+        self.assertEqual(
+            result.runtime_metadata["speaker_attribution_loss_reason"],
+            "plain_transcript_fallback",
+        )
 
     def test_oversized_plain_transcript_fails_before_any_network_call(self) -> None:
         with tempfile.TemporaryDirectory() as directory:
@@ -225,6 +308,7 @@ class ProtocolInputBudgetTests(unittest.TestCase):
         )
         self.assertFalse(result.runtime_metadata["fallback_used"])
         self.assertFalse(result.runtime_metadata["diarization_enabled"])
+        self.assertIsNone(result.runtime_metadata["speaker_attribution_available"])
 
 
 if __name__ == "__main__":