196 lines
8.9 KiB
Markdown
196 lines
8.9 KiB
Markdown
# D&D Spell Normalization
|
|
|
|
## Status
|
|
|
|
<<<<<<< HEAD
|
|
Proposed as the next D&D pipeline milestone. This feature completes the first
|
|
domain-specific normalize stage for the spell pipeline before work begins on
|
|
NPC and combat-turn artifacts.
|
|
=======
|
|
Accepted target state. Implementation details are maintained separately in
|
|
`docs/roadmap/implementation.md`.
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
|
|
## Objective
|
|
|
|
Replace the spell lane's no-op normalizer with a deterministic D&D normalizer
|
|
that emits canonical catalog names, removes only clearly identical duplicate
|
|
casts, preserves source provenance, and makes every mutation visible through
|
|
scoped warnings.
|
|
|
|
<<<<<<< HEAD
|
|
The milestone should improve the consistency of durable spell output without
|
|
adding another LLM call or introducing fuzzy repair policy.
|
|
=======
|
|
The normalizer improves the consistency of durable spell output without adding
|
|
another LLM call or introducing fuzzy repair policy.
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
|
|
## Target Behavior
|
|
|
|
### Effective catalog construction
|
|
|
|
The normalizer constructs the same immutable SRD-plus-overlay effective
|
|
catalog used by spell extraction and catalog validation. It declares the
|
|
optional `spell_catalog` normalize-stage reference slot and resolves it during
|
|
pipeline preparation, before source parsing or module execution.
|
|
|
|
An overlay-capable pipeline binds the same catalog file independently at the
|
|
extract and normalize stages. This repetition is intentional: references are
|
|
stage-local, and the normalizer must not reach into a constructed extractor or
|
|
depend on extractor-private state.
|
|
|
|
The normalizer contributes its effective catalog digest through
|
|
`pipeline.CheckpointFingerprintProvider`. Changing the embedded catalog,
|
|
composition policy, or normalize-stage overlay therefore invalidates reusable
|
|
<<<<<<< HEAD
|
|
normalize checkpoints.
|
|
=======
|
|
normalize checkpoints. It also records catalog base ID, digest, and overlay IDs
|
|
as manifest metadata. Neither identity surface includes catalog contents or
|
|
reference paths.
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
|
|
### Canonical spell names
|
|
|
|
For every spell cast, look up the extracted name using the effective catalog's
|
|
existing case, whitespace, apostrophe, and alias rules. Replace a recognized
|
|
value with its canonical display name. This is the only spell-name repair in
|
|
<<<<<<< HEAD
|
|
the initial feature.
|
|
=======
|
|
this feature.
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
|
|
Do not use edit distance, phonetic matching, model judgment, or another fuzzy
|
|
heuristic. If a value does not resolve, retain it unchanged and emit a scoped
|
|
warning; the configured normalize validator chain remains responsible for
|
|
acceptance or rejection.
|
|
|
|
Emit a warning for each changed spell name. Diagnostics should identify the
|
|
artifact index and the original and canonical values without modifying other
|
|
<<<<<<< HEAD
|
|
fields.
|
|
=======
|
|
fields. Diagnostics are deterministic and bounded: user-controlled spell names
|
|
are truncated to 128 Unicode code points before display.
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
|
|
### Source-reference normalization
|
|
|
|
Sort each cast's source references by source identity, start unit, and end
|
|
unit, then remove exact duplicate references. Do not merge adjacent or merely
|
|
overlapping ranges, because doing so could broaden the evidence attributed to
|
|
an event.
|
|
|
|
The normalizer must not synthesize source references, alter source-unit
|
|
<<<<<<< HEAD
|
|
boundaries, or use auxiliary references as evidence.
|
|
=======
|
|
boundaries, or use auxiliary references as evidence. Reordering references or
|
|
removing exact duplicates emits a scoped warning for the affected input cast.
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
|
|
### Conservative duplicate collapse
|
|
|
|
After name and source-reference canonicalization, treat two casts as the same
|
|
event only when all of the following match:
|
|
|
|
- canonical spell name;
|
|
- caster after case folding and whitespace normalization; and
|
|
<<<<<<< HEAD
|
|
- the complete canonical source-reference set.
|
|
=======
|
|
- the complete canonical source-reference set, which must be non-empty and
|
|
valid against the source document.
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
|
|
Collapse each such group into its first occurrence, preserving stable pipeline
|
|
order. Retain the first cast's caster, effect, and narrative description. Do
|
|
not combine prose fields or select a winner based on length, confidence, or
|
|
model-like semantic judgment. The retained cast receives the group's already
|
|
canonical source-reference set.
|
|
|
|
Emit one scoped warning per collapsed group, including the retained index and
|
|
the removed indices. Casts with different evidence remain distinct even when
|
|
their spell and caster match. In particular, adjacency at a chunk or scene
|
|
boundary is not sufficient evidence of duplication.
|
|
|
|
<<<<<<< HEAD
|
|
=======
|
|
Unknown spell names, empty evidence sets, and invalid source references cannot
|
|
establish duplicate identity. They remain in the artifact for the configured
|
|
normalize validators to accept or reject. A duplicate warning displays at most
|
|
20 removed input indices and reports the exact omitted count.
|
|
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
### Production composition and validation
|
|
|
|
Register the typed spell normalizer in the D&D family and make it the default
|
|
normalizer for the maintained production spell pipeline. Keep the artifact
|
|
kind and durable spell-list schema unchanged.
|
|
|
|
Add a normalize-stage production validator chain using the existing generic
|
|
JSON and JSON Schema validators followed by the existing spell shape, catalog,
|
|
source-reference, and source-relatedness validators in their current order.
|
|
Explicit validator overrides remain authoritative.
|
|
|
|
The maintained overlay-capable example should bind `spell_catalog` at both the
|
|
extract and normalize stages. The base-only example should continue to work
|
|
without a catalog reference.
|
|
|
|
## Acceptance Criteria
|
|
|
|
- Base and overlay aliases are written using canonical catalog display names.
|
|
- Unknown names are never guessed, deleted, or silently changed.
|
|
- Source references are deterministically sorted and exactly deduplicated.
|
|
- Only casts with matching canonical spell, normalized caster, and identical
|
|
<<<<<<< HEAD
|
|
evidence sets collapse; near or adjacent events remain separate.
|
|
- Normalization preserves the first cast's non-name fields and stable order.
|
|
- Every name change and duplicate collapse emits a scoped warning.
|
|
=======
|
|
non-empty valid evidence sets collapse; near, invalid, unknown, or adjacent
|
|
events remain separate.
|
|
- Normalization preserves the first cast's non-name fields and stable order.
|
|
- Every name change, unresolved name, source-reference mutation, and duplicate
|
|
collapse emits a scoped warning.
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
- Extract, normalize, and catalog-validation catalog identities agree for the
|
|
same bound references, and catalog changes invalidate normalize checkpoints.
|
|
- The maintained production pipeline and current-behavior documentation use
|
|
the D&D normalizer without changing the durable artifact schema.
|
|
|
|
## Evaluation
|
|
|
|
Maintain a small human-reviewed set of representative spell outputs covering
|
|
canonical names, aliases, repeated casts, duplicate model output, and scene
|
|
boundaries. Use it to review normalization behavior and warnings, not as a
|
|
claim that LLM extraction is deterministically correct.
|
|
|
|
Record cases where likely duplicates remain because their evidence differs.
|
|
Those examples should inform later LLM-assisted deduplication work rather than
|
|
<<<<<<< HEAD
|
|
causing this deterministic milestone to adopt broader heuristics.
|
|
=======
|
|
causing this deterministic feature to adopt broader heuristics.
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
|
|
## Deferred Work
|
|
|
|
- Fuzzy correction of unknown spell names.
|
|
- Collapsing casts based only on overlapping, adjacent, or semantically similar
|
|
evidence.
|
|
- LLM-assisted duplicate proposals or prose reconciliation.
|
|
- A generic deduplication contract based on stable artifact-element IDs.
|
|
- Repair-aware extraction retries or LLM-backed semantic validation.
|
|
- Changes to the spell artifact schema, including stable cast IDs.
|
|
|
|
<<<<<<< HEAD
|
|
An LLM-backed normalizer is explicitly outside this milestone. If later
|
|
=======
|
|
An LLM-backed normalizer is explicitly outside this feature. If later
|
|
>>>>>>> 6fbdf6b (Add feature roadmap and implementation plan for D&D spell normalization module)
|
|
evaluation justifies one, shared spell-catalog prompt material should be
|
|
designed at that time around the actual normalization or repair request.
|