feat: add post-diarization speaker mapping workflow

2026-08-25 15:30:16 +02:00
parent df89a38829
commit 8a0f38fce4
6 changed files with 233 additions and 2 deletions
@@ -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