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

AGENTS.md

@@ -30,10 +30,11 @@ Audio
 Status:
 
 - Implemented: Whisper JSON cleanup script, normalization, technical chunking,
-  local chunk extraction, interim Markdown protocol builder.
+  local chunk extraction, Canonicalizer V1, Semantic Consolidator V0
+  facts-only duplicate detection, interim Markdown protocol builder.
 - Experimental/prototype: topic segmentation and review tooling.
-- Planned: Deterministic Canonicalizer, Semantic Consolidator, Canonical
-  Meeting Knowledge implementation, final Output Views.
+- Planned: broader semantic consolidation, Canonical Meeting Knowledge
+  implementation, final Output Views.
 
 ## Architectural Principles
 
@@ -46,16 +47,20 @@ Status:
 - Extraction, consolidation, synthesis and rendering are separate concerns.
 - Deterministic canonicalization and semantic consolidation are separate
   concerns.
-- The Deterministic Canonicalizer is planned Python code. It validates and
-  normalizes extraction objects, assigns stable source references and IDs,
-  normalizes category names and basic field structure, performs only safe
-  deterministic cleanup, may group exact duplicates, and must preserve all
-  source evidence. It must not perform uncertain semantic merging.
-- The Semantic Consolidator is planned local-LLM work. It merges semantically
-  equivalent statements, groups content by topic, preserves evidence from all
-  contributing chunks, marks contradictions and uncertainty, separates durable
-  information from transient discussion, and produces Canonical Meeting
-  Knowledge. It does not directly write a protocol.
+- Canonicalizer V1 is implemented Python code. It validates and normalizes
+  extraction objects, assigns stable source references and IDs, normalizes
+  category names and basic field structure, performs only safe deterministic
+  cleanup, may group exact duplicates, and must preserve all source evidence.
+  It must not perform uncertain semantic merging.
+- Semantic Consolidator V0 is implemented as local-LLM facts-only duplicate
+  detection. It merges semantically equivalent fact items conservatively,
+  preserves source references and evidence, and validates complete source fact
+  coverage. It is not a summarizer, topic grouper, protocol renderer or
+  complete Canonical Meeting Knowledge stage.
+- Broader semantic consolidation remains planned. It should group content by
+  topic, mark contradictions and uncertainty, separate durable information from
+  transient discussion, and prepare Canonical Meeting Knowledge. It does not
+  directly write a protocol.
 - Prefer small, testable processing stages over one monolithic LLM prompt.
 - Current extraction strategy is one normalized chunk per LLM call.
 - Do not expand context windows or redesign the extraction strategy without an
@@ -132,8 +137,8 @@ Current documented Prompt Version 2 decision baseline:
 - `src/meeting_lab/segmentation/`: experimental topic segmentation tooling.
 - `src/meeting_lab/extraction/`: local LLM extraction flow and category
   extractor modules.
-- `src/meeting_lab/consolidation/`: planned deterministic canonicalization and
-  semantic consolidation area.
+- `src/meeting_lab/consolidation/`: Canonicalizer V1 and Semantic
+  Consolidator V0.
 - `src/meeting_lab/protocol/`: interim protocol rendering.
 - `src/meeting_lab/models/`: current lightweight data models.
 - `samples/`: sample inputs and generated/experimental artifacts; do not treat