Use shared assets instead of prompt prefix change detectors

docs/roadmap/dnd.md

@@ -56,34 +56,28 @@ module-specific message:
   wording differs by lane. Factor the common bytes into one message and leave
   the differences in later messages instead.
 
-Tests inspect the fully rendered Scriptorium request boundary. Source-level
-message identity alone is not treated as proof of cache identity.
+Shared messages are embedded once and referenced by every applicable prompt.
+This makes reuse of the canonical asset the easiest way to preserve cache
+identity and avoids parallel module-specific copies that can drift.
 
-### Exact Prompt And Input Identity Is Protected
+### Shared Prompt Ownership And Input Behavior Are Protected
 
-Focused tests at the narrowest stable boundary expose the fully prepared
-provider-neutral request.
+Focused tests protect shared asset composition and input behavior without
+snapshotting the length or exact boundary of the common message prefix.
 
-- Render each extractor prompt with the same transcript and campaign
-  references and assert that the intended common message prefix has identical
-  roles, content bytes, ordering, and cache-control metadata.
-- Assert that spells and combat turns render identical NPC-registry messages
-  for the same bound or unbound registry.
+- Verify that each applicable prompt mounts and renders the canonical shared
+  assets rather than module-specific copies.
 - Verify common input material identity, including name, media type, content,
   digest, origin URI, size, empty-value representation, reference ordering,
   and `roster` fallback behavior.
-- Test both identical and intentionally different chunks and reference sets so
-  the test proves the cache boundary rather than merely snapshotting one
-  request.
-- Add an explicit assertion for the length of the common prefix. A new
-  module-specific message inserted inside that prefix should require deliberate
-  review.
 - Test that every prompt fingerprint includes exactly the assets actually
   rendered by that prompt. The current grouped reference hash helper should be
   replaced or refined so a module does not fingerprint an unused shared asset,
   while no used asset is omitted.
-- Prefer semantic assertions over complete prompt snapshots, except for the
-  common rendered prefix whose exact bytes are the behavior under protection.
+- Document the expected shared message ordering and cache-control policy so
+  later changes are reviewed against the caching intent.
+- Prefer behavioral and ownership assertions over message-count, prefix-length,
+  or full-prompt snapshots.
 
 ### Stable Extraction Preparation Is Centralized
 
@@ -175,10 +169,10 @@ This roadmap is complete when:
 
 - the three lanes expose the same stable structural conventions while keeping
   documented domain differences local;
-- shared provider-visible messages and inputs are produced from one source and
-  verified byte-for-byte at the rendered-request boundary;
-- the common prompt prefix is deliberate, tested, and as long as extraction
-  quality permits;
+- shared provider-visible messages are produced from canonical shared assets,
+  and shared inputs have one deterministic implementation;
+- the common prompt ordering is deliberate, documented, and as cache-friendly
+  as extraction quality permits;
 - every validator policy that affects reusable results participates in
   checkpoint identity;
 - source-reference traversal and diagnostics no longer drift between lanes;