Document validation architecture and renderer faithfulness findings

- document Entity Registry and Meeting Context V2 architecture
- preserve meeting_context.yaml as the authoritative meeting-specific input
- define immutable authoritative metadata across all pipeline stages
- restrict Constraint Repair to deterministic structured-data operations
- record BUG-003 root cause and deferred entity-verification resolution
- document BUG-005 attendance-consistency design
- add BUG-006 renderer faithfulness root-cause analysis
- distinguish Engineering Readiness from Practical Usability
- update the persistent regression bug tracker
This commit is contained in:
2026-08-03 16:05:47 +02:00
parent 06f0e7e651
commit 9446c6e0be
13 changed files with 2208 additions and 0 deletions
+61
View File
@@ -126,6 +126,67 @@ Out of scope:
- Export formats beyond those needed to validate the model.
- Knowledge-system storage design.
## Phase 4A - Meeting Context V2 and Entity Registry
Goal:
- Replace primarily manual Meeting Context authoring with an interactive
entity confirmation workflow backed by a persistent Entity Registry.
Accepted architecture:
```text
Whisper
↓
Entity Detection
↓
User Confirmation
↓
Entity Registry Update
↓
Meeting Context Builder
↓
meeting_context.yaml
↓
Extraction Pipeline
```
Deliverables:
- Persistent Entity Registry independent from individual meetings as the
cross-meeting knowledge source for confirmed entities, aliases and
organizational metadata.
- Stable internal entity IDs for people, organizations, departments, products,
projects, locations and abbreviations.
- First-class aliases, including spelling and transcription variants.
- User confirmation UI/workflow for unknown names.
- Meeting Context Builder that produces meeting-specific `meeting_context.yaml`
from registry entries, user confirmations and meeting metadata.
- Generated `meeting_context.yaml` as the authoritative meeting-specific Point
of Truth and reproducible input artifact for each meeting run.
- Similarity suggestions for spelling variants, Whisper variants, umlaut
handling and OCR-like mistakes.
Prerequisites:
- Agreement on the Entity Registry data model.
- Review workflow for confirming unknown entities after Whisper transcription.
- Meeting Context V1 remains the extraction interface until V2 is implemented.
Current status:
- Accepted Architecture.
- Implementation deferred.
Out of scope:
- Autonomous learning.
- Silent registry updates.
- Registry overrides of explicit meeting-specific confirmations.
- Silent changes to historical Meeting Context after Registry updates.
- Inferring responsibility, decisions, ownership or attendance from registry
metadata.
## Phase 5 - Output Views
Goal: