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

Minor additional improvements to the D&D spell extraction prompt.

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-20 20:34:59 -05:00
parent c4c907d421
commit 5186e061a8
4 changed files with 41 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
docs/integrations/dnd-spell-artifacts.md
View File

@@ -58,13 +58,16 @@ occurred. The `spell` value must resolve through the effective SRD-plus-overlay
catalog as either a canonical name or alias. Catalog validation accepts aliases
but does not rewrite them; unknown fields are rejected.
`effect` and `narrative_description` record what the transcript establishes
about the session as played. They do not correct the table from published D&D
rules or supplement the transcript with model knowledge. When the transcript
contains a nonstandard or disputed ruling, the artifact may preserve the
observed resolution and attribute relevant reasoning to the GM or table; it
must not present that reasoning as a universal game rule. The spell catalog is
name-recognition policy, not evidence for spell mechanics or outcomes.
`effect` and `narrative_description` record the casting declaration and its
immediate resolution as established by the transcript. They do not follow
summoned creatures, persistent spell effects, or other downstream consequences
through the rest of the scene. They also do not correct the table from
published D&D rules or supplement the transcript with model knowledge. When the
transcript contains a nonstandard or disputed ruling, the artifact may preserve
the immediate observed resolution and attribute relevant reasoning to the GM or
table; it must not present that reasoning as a universal game rule. The spell
catalog is name-recognition policy, not evidence for spell mechanics or
outcomes.
## Source References
@@ -75,14 +78,16 @@ must not appear after the end unit. Unknown fields are rejected.
For each cast, the complete `source_refs` collection identifies the transcript
evidence for every factual claim in `caster`, `spell`, `effect`, and
`narrative_description`. A cast declaration and a later resolution may be
`narrative_description`. A cast declaration and its immediate resolution may be
cited with separate narrow ranges when intervening units are unrelated. A
reported target, roll, amount, condition, interruption, or outcome must be
supported by the cited units; otherwise the artifact describes only the
supported attempt or declaration. The deterministic validators establish that
ranges are structurally valid and that the spell name is related to cited
text. Semantic claim completeness is an extraction policy and remains subject
to evaluation rather than deterministic proof.
reported target, roll, amount, condition, interruption, or immediate outcome
must be supported by the cited units; otherwise the artifact describes only the
supported attempt or declaration. Later behavior by summoned creatures,
recurring effects, and other downstream consequences are outside the cast
artifact's evidence scope. The deterministic validators establish that ranges
are structurally valid and that the spell name is related to cited text.
Semantic claim completeness is an extraction policy and remains subject to
evaluation rather than deterministic proof.
Reference slot keys and accepted file types are defined in
[Configuration](../config.md#implemented-production-modules). References are

10
docs/internal/modules.md
View File

@@ -160,10 +160,12 @@ failures therefore stop construction before source parsing or an LLM call;
campaign references remain separate disambiguation inputs and never become
source evidence.
The prompt requires each cast's source references collectively to support all
reported facts, using separate narrow ranges when a declaration and resolution
are non-contiguous. It grounds caster names in in-world identities, using the
player and party references to disambiguate transcript speakers without
The prompt limits each cast to its declaration and immediate resolution; it
does not follow summoned creatures, persistent effects, or other downstream
consequences through the scene. Source references must collectively support all
reported facts, using separate narrow ranges when immediate evidence is
non-contiguous. The prompt grounds caster names in in-world identities, using
the player and party references to disambiguate transcript speakers without
treating those references as event evidence. Effects describe the session as
played: model rules knowledge cannot supplement or correct the transcript, and
nonstandard adjudication is attributed to the GM or table rather than stated as