Finish the references implementation for the extraction module and update roadmap documentation

docs/roadmap/future.md

@@ -8,6 +8,21 @@ future work only.
 
 - Additional input adapters, such as Markdown or note-export formats.
 - Additional D&D extractors beyond spell casts.
+- First-class LLM access for all LLM-eligible pipeline stages: `chunk`,
+  `extract`, and `normalize`.
+- Expand reference support beyond extractors to `chunk` and `normalize`
+  modules, using the same declared-slot model and preserving stage-specific
+  ownership boundaries.
+- Add non-file reference producers, such as prior-run artifacts, derived
+  summaries, or entity registries, without changing module-facing reference
+  item contracts.
+- Add token budgeting and model context-window management for reference content.
+- Add per-slot or per-chunk inclusion policies so modules can avoid repeating
+  large reference content in every prompt when that becomes important.
+- Add structured or parsed references, such as typed roster schemas, when a
+  module has a clear need for more than opaque UTF-8 text.
+- Add reference caching, preprocessing, summarization, embedding, or retrieval
+  if references become large enough to require preprocessing.
 - Cross-lane entity normalization.
 - Cross-chunk semantic deduplication.
 - Configurable validator chains with production validator modules.
@@ -15,6 +30,13 @@ future work only.
 - Parallel execution where it preserves deterministic manifests and diagnostics.
 - Additional output encoders.
 
+## Candidate Architecture Work
+
+- Evaluate replacing the local LLM adapter with an import from
+  `gitea.maximumdirect.net/eric/scriptorium`, provided it preserves Notarius
+  boundaries around provider plumbing, prompt ownership, diagnostics, and secret
+  handling.
+
 ## Candidate Operational Work
 
 - Packaged release artifacts for alpha distribution.