Add Streamlit meeting assistant MVP

PROJECT_KNOWLEDGE.md

@@ -15,7 +15,7 @@ are derived, reproducible artifacts and require human review.
 
 Meeting Lab owns reusable and experimental processing:
 
-- FFmpeg audio preparation
+- FFmpeg audio preparation, with optional normalization enabled by default
 - `whisper.cpp` transcription
 - optional `pyannote.audio` diarization
 - protocol generation
@@ -47,7 +47,8 @@ Processing logic must not be duplicated in the application.
 
 ```text
 Imported audio
-    -> prepare as mono, 16 kHz PCM WAV with FFmpeg
+    -> always prepare as mono, 16 kHz PCM WAV with FFmpeg
+       (optionally normalize loudness; default on)
     -> transcribe with whisper.cpp and large-v3-turbo
     -> optionally diarize with pyannote.audio Community-1
     -> generate a protocol directly from the full transcript
@@ -66,11 +67,14 @@ requirements. CPU execution remains supported and may be substantially slower.
 
 ## Meeting Context and Speakers
 
-`MeetingContext` is a structured domain object containing meeting metadata and
-participants. It can also contain optional explicit mappings from
+`MeetingContext` is a structured domain object containing meeting metadata,
+present participants, and people who were mentioned without attending. The GUI
+records exactly `present` or `mentioned_only`; missing legacy participant status
+defaults to `present` in Meeting Lab. It can also contain optional explicit mappings from
 `SPEAKER_XX` labels to `participant_id` values.
 
-A speaker mapping is authoritative only when a user explicitly confirms it.
+A speaker mapping is authoritative only when a user explicitly confirms it and
+may reference only a present participant.
 Speakers otherwise remain anonymous. Automatic speaker-name inference is not
 allowed. The GUI must create and edit Meeting Context; hand-written YAML is not
 a product requirement.
@@ -101,6 +105,11 @@ The product should ultimately offer both a detailed contextual protocol and a
 shorter participant/distribution version. The short version remains follow-up
 work if it is not available for the first GUI milestone.
 
+Confirmed meeting-specific corrections should ultimately be reusable by both
+protocol views. The detailed correction and selective-regeneration decision is
+recorded in [ADR 0012](docs/adr/0012-post-run-corrections.md); it is later
+product work, not a current MVP requirement.
+
 ## Design Principles
 
 - offline-first where practical