Implement Semantic Consolidator V0

- add deterministic canonicalization support for extraction items
- add facts-only semantic consolidation using local Ollama
- preserve source evidence and validate complete fact coverage
- add conservative merge rules and non-LLM tests
- record the first validated real-life consolidation benchmark
- document current scope, limitations and next evaluation step
This commit is contained in:
2026-07-31 11:25:46 +02:00
parent 6e34334506
commit 90aa34d5d0
20 changed files with 5517 additions and 93 deletions
+11
View File
@@ -19,6 +19,14 @@
Verteilerprotokoll and Knowledge Objects / Wissensdatenbankeintrag.
- Working Protocol Synthesizer V0 benchmark artifact for future
canonicalizer/consolidator comparisons.
- Canonicalizer V1 deterministic CLI for canonicalizing chunk extraction JSON.
- Non-LLM Canonicalizer V1 tests covering ordering, validation, IDs, parsing,
source references, exact duplicates, invalid JSON and empty categories.
- Semantic Consolidator V0 CLI for conservative facts-only semantic duplicate
detection using local Ollama.
- Consolidation prompt and non-LLM tests for payload construction, grouping
validation and source fact coverage.
- Semantic Consolidator V0 benchmark report and consolidated extraction JSON.
### Changed
@@ -28,6 +36,9 @@
are parallel renderings, not derived from one another.
- Documented the planned Deterministic Canonicalizer and Semantic Consolidator
stages before Canonical Meeting Knowledge.
- Clarified that Semantic Consolidator V0 is implemented only for fact
duplicate detection; broader semantic synthesis and Canonical Meeting
Knowledge remain planned.
- Documented that rendered protocol language should normally match the source
transcript or consolidated meeting knowledge unless explicitly requested
otherwise.