eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Document D&D prompt cache ordering

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-27 20:16:11 +00:00
parent d1eaec4dad
commit de8ed41b34
2 changed files with 40 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
docs/internal/dnd.md
View File

@@ -39,9 +39,31 @@ D&D extractors assemble prompts from an ordered manifest of shared and
module-owned assets. Reuse the shared D&D system, evidence, identity,
reference, and transcript assets instead of copying their text into individual
modules. A manifest’s declared sequence, including cache-control placement, is
part of the prompt behavior, and the chunk transcript is the final message.
Preserve that order when changing an extractor or its assets so prompt-cache
behavior remains stable.
part of the prompt behavior.
All extraction prompts share this four-message rendered prefix: the system
message without cache control, the identity message without cache control, the
campaign-reference message with ephemeral cache control, and the chunk
transcript message with ephemeral cache control. This gives equivalent
extraction requests the same reusable prefix through their source material.
Extraction-evidence policy, generated NPC registries, spell catalogs, module
tasks, and instructions follow the transcript because they are not universal
across all extraction lanes. The final instructions message carries ephemeral
cache control; evidence, registry, catalog, and task messages do not. Preserve
this division when changing an extractor or its assets so prompt-cache behavior
remains stable.
The other D&D LLM prompts intentionally follow different patterns. Scene
chunking has no sibling extraction lane with which to share its full transcript,
so it renders campaign references before its task and instructions, then places
the cacheable full transcript last. NPC normalization keeps its task and
cacheable instructions before the candidate collection, followed by the
cacheable transcript windows: candidates must be available before their
supporting evidence is evaluated, and those windows are not a cross-lane
prefix. Mounted assets and their declared message order determine the prompt
fingerprint, so intentional prompt edits continue to invalidate stale
checkpoints.
All extractors use the shared prompt-input preparation rules. The current chunk
is copied into transcript material; player, party, glossary, and compatible