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

ROADMAP.md

@@ -36,7 +36,7 @@ Goal:
 
 Deliverables:
 
-- Deterministic Canonicalizer implemented in Python.
+- Canonicalizer V1 implemented in Python.
 - Stable source references and IDs.
 - Normalized category names and basic field structure.
 - Safe deterministic cleanup.
@@ -48,6 +48,10 @@ Prerequisites:
 - Stable local extraction baseline.
 - Agreement on the extraction object shape that should be canonicalized.
 
+Current status:
+
+- Implemented as `meeting_lab.consolidation.canonicalize`.
+
 Out of scope:
 
 - Uncertain semantic merging.
@@ -64,22 +68,34 @@ Goal:
 
 Deliverables:
 
-- Semantic Consolidator using the local LLM.
-- Semantically equivalent statement merging.
-- Topic grouping.
+- Semantic Consolidator V0 using the local LLM for facts-only duplicate
+  detection.
+- Semantically equivalent fact statement merging.
 - Evidence preserved from all contributing chunks.
-- Contradiction and uncertainty markers.
-- Separation of durable information from transient discussion.
-- Canonical Meeting Knowledge output.
+- Complete source fact coverage validation.
+- Later broader semantic consolidation with topic grouping, contradiction and
+  uncertainty markers, durable/transient separation and Canonical Meeting
+  Knowledge preparation.
 
 Prerequisites:
 
-- Deterministic Canonicalizer output with stable IDs and source references.
+- Canonicalizer V1 output with stable IDs and source references.
 - Gold or benchmark cases that expose duplication and category shifts.
 
+Current status:
+
+- Semantic Consolidator V0 is implemented and experimentally validated for
+  facts-only conservative merging.
+- The first accepted benchmark merged one correct pair among 33 facts and left
+  31 singleton groups.
+
 Out of scope:
 
 - Direct protocol writing.
+- Topic synthesis in V0.
+- Processing decisions, action items, questions, positions or technical details
+  in V0.
+- Canonical Meeting Knowledge generation in V0.
 - Deriving output views from one another.
 - Retrieval or RAG integration.