Enable correction-aware semantic reconciliation

docs/internal/dnd.md

@@ -33,7 +33,9 @@ typed builder. Scene chunking, every extractor, and NPC, location, and item-regi
 normalization are registered as `llm_backed`; the remaining current D&D mergers
 and normalizers are `deterministic`. The metadata is available to catalog inspection and
 resolved-pipeline debug data and determines which selected bindings inherit the
-pipeline profile. Configuration remains the canonical owner of the exact keys,
+pipeline profile. The registry normalizers use `single_response_v1`, forwarding
+corrections to their reconciliation completion and retaining the accepted raw
+proposal only as an owned model candidate. Configuration remains the canonical owner of the exact keys,
 profile precedence, and validator order.
 
 Private structured-LLM response schemas are deliberately minimal. They reject

docs/internal/pipeline.md

@@ -35,6 +35,9 @@ module capabilities and typed artifact compatibility, validates options, and
 assigns a deterministic resolved-composition digest. A correction protocol is
 selected from each eligible LLM-backed producer specification and becomes part
 of that resolved identity; only `single_response_v1` is currently supported.
+Preparation rejects an LLM-backed producer that combines a non-empty validator
+chain with positive producer retries unless it declares that protocol. Producers
+without validators or without retries remain valid without correction support.
 The resolved pipeline contains bindings and declared reference targets, not
 external reference bytes.
 After selection, the resolver applies command, binding, and pipeline profile

docs/roadmap/implementation.md

@@ -379,7 +379,7 @@ producers.
 Every direct production D&D LLM extractor implements the same correction
 protocol without changing artifact semantics. This stage is one Terra prompt.
 
-## Stage 8 — Migrate Semantic Reconciliation Normalizers
+## Stage 8 — Migrate Semantic Reconciliation Normalizers ✅
 
 ### Goal