Commit Graph
9 Commits
Author SHA1 Message Date
admin 6fc07690d9 Make protocol language follow meeting language 2026-09-11 10:25:45 +02:00
admin 8a0f38fce4 feat: add post-diarization speaker mapping workflow 2026-08-25 15:30:16 +02:00
admin df89a38829 feat: configure 32k context for protocol generation 2026-08-25 15:29:40 +02:00
admin d77bfedb6e Guard protocol generation against context truncation 2026-08-24 16:48:06 +02:00
admin 8dab928763 Add diarization and reusable MVP meeting pipeline 2026-08-23 19:29:47 +02:00
admin a9dab7c81a Add direct protocol MVP core 2026-08-20 21:42:36 +02:00
admin 950284e236 Stabilize Meeting Lab pipeline for RC1 evaluation
This commit significantly improves the robustness and determinism of the Meeting Lab processing pipeline and establishes the first Release Candidate baseline for end-to-end evaluation.

Highlights

- BUG-009
  - Implement deterministic responsible-party validation
  - Normalize participant aliases using Meeting Context
  - Reject invalid responsible values (dates, locations, technical terms, projects, products, unknown entities)
  - Record structured responsibility validation metadata
  - Add focused regression tests

- BUG-010
  - Implement adaptive num_predict estimation for Semantic Consolidator
  - Eliminate JSON truncation caused by fixed output limits
  - Add deterministic source coverage repair
  - Preserve strict post-repair validation
  - Add regression tests

- BUG-011
  - Implement Working Protocol V2 renderer contract enforcement
  - Preserve raw renderer responses
  - Reject invalid protocol output instead of accepting malformed documents
  - Add deterministic cleanup for harmless formatting deviations
  - Add focused renderer regression tests

- Meeting Context
  - Validate Meeting Context V1
  - Integrate authoritative participant alias normalization

- Documentation
  - Update architecture documentation
  - Update output documentation
  - Update regression bug tracker

The pipeline now fails safely instead of silently accepting invalid intermediate or final artifacts.

Remaining work focuses primarily on extraction quality and semantic classification (decisions, action items, protocol faithfulness), rather than pipeline robustness.
2026-08-04 13:11:54 +02:00
admin 07b0d80113 Implement first end-to-end meeting analysis pipeline 2026-07-30 09:15:38 +02:00
admin b2c195c365 Initial project structure 2026-07-21 16:32:49 +02:00