Reuse prepared glossary data across stage sections

docs/internal/modules.md

@@ -37,9 +37,9 @@ Shared proposal-generation plumbing is centralized in:
 Module packages own:
 - prompt selection (`internal/prompts` prompt IDs).
 
-`proposal_generation.BuildProposalVariables` encodes the glossary, selected
-transcript section, and trimmed description once for all four modules. PromptKit
-renders their embedded definitions from those variables and validates the
+Each stage prepares the encoded glossary context and protected spellings once.
+Proposal generation adds the selected transcript section and trimmed description
+for each request. PromptKit renders the selected definition and validates the
 correction-set schema before Audita maps proposals. Domain validators still
 check confidence, applicability, protected glossary terms, and replacement
 policy. Model-facing segment IDs are one-based positions within the proposal

docs/internal/validators.md

@@ -120,10 +120,11 @@ is covered by [report assembly](diagnostics-reporting.md).
 
 ## Supplemental Validation Context
 
-Request construction prepares one segment-position lookup and a matcher from the
-selected context entries for all candidates. Context selection remains candidate-specific,
-including the proposed replacement text. The independent protection view is used
-by the deterministic guard and application check.
+Each stage prepares a context matcher and indexes its selected glossary entries
+by identity. Request construction uses a segment-position lookup and returns
+matched entries in selection order for each candidate, including matches in the
+replacement text. The deterministic guard and application check share the
+stage's separate protection matcher.
 
 Each candidate includes the immediately preceding and following source segments
 available within its fixed chunk, labeled `preceding` or `following` with speaker,