Simplify references and output instructions in LLM prompts

docs/internal/modules.md

@@ -42,7 +42,13 @@ transcript section, and trimmed description once for all four modules. PromptKit
 renders their embedded definitions from those variables and validates the
 correction-set schema before Audita maps proposals. Domain validators still
 check confidence, applicability, protected glossary terms, and replacement
-policy. Shared context encoding lives in `internal/framework/promptcontext`.
+policy. Model-facing segment IDs are one-based positions within the proposal
+request. Generation maps returned references back to the current chunk's actual
+segment IDs, preserving response order and multiple proposals per segment.
+Unknown references become invalid-target candidates for the existing domain
+checks; they are never interpreted as actual transcript IDs. Debug request
+metadata records `segment_ids` in local-reference order (reference 1 is the
+first entry). Shared context encoding lives in `internal/framework/promptcontext`.
 An empty `corrected_text` deletes the identified span when the resulting segment
 remains nonblank. Whitespace-only original spans can express spacing corrections;
 matching stays literal under each module's replacement policy. No automatic