Minimize D&D spell extraction contracts

docs/integrations/dnd-spell-artifacts.md

@@ -47,12 +47,10 @@ Each spell cast contains exactly these required fields:
 
 - `caster`: in-world character or creature casting the spell;
 - `spell`: spell name;
-- `effect`: concise spell effect in the scene;
-- `narrative_description`: short description of the spell cast in context;
 - `source_refs`: transcript source references with extractor-assigned source
   IDs and evidence unit ranges. It must contain at least one entry.
 
-All four string fields must be non-empty. `caster` is the canonical in-world
+Both string fields must be non-empty. `caster` is the canonical in-world
 caster, not the human player, transcript speaker, or GM when the associated
 character or creature can be identified. Player and party references may
 disambiguate that identity, but do not independently establish that a cast
@@ -60,16 +58,10 @@ 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 the casting declaration and its
+The artifact includes an actual casting event or an unambiguous declared
-immediate resolution as established by the transcript. They do not follow
+casting attempt. Spell mentions, hypothetical plans, rules discussion, and
-summoned creatures, persistent spell effects, or other downstream consequences
+catalog matches without a casting event are excluded. The spell catalog is a
-through the rest of the scene. They also do not correct the table from
+name-recognition policy and never evidence that a cast occurred.
-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
 
@@ -79,17 +71,11 @@ The unit IDs must be positive integers present in the input, and the start unit
 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
+evidence for the caster, spell name, and occurrence of the cast or declared
-`narrative_description`. A cast declaration and its immediate resolution may be
+attempt. The deterministic validators establish that ranges are structurally
-cited with separate narrow ranges when intervening units are unrelated. A
+valid and that the spell name is related to cited text. Semantic evidence
-reported target, roll, amount, condition, interruption, or immediate outcome
+sufficiency is an extraction policy and remains subject to evaluation rather
-must be supported by the cited units; otherwise the artifact describes only the
+than deterministic proof.
-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
@@ -103,8 +89,9 @@ normalized NPC artifact as `application/json`, up to 1 MiB. An external file is
 validated during preparation; an ordered generated binding is validated at the
 step handoff. Both paths use the approved NPC codec and identity policy,
 re-encode canonical durable JSON for registry provenance, and supply only the
-registry's ordered names as the operation-time spell prompt input. It helps the model prefer canonical
+registry's ordered names as the operation-time spell prompt input. It helps the
-caster names; it does not establish that a spell was cast.
+model prefer canonical caster names; it does not establish that a spell was
+cast.
 
 NPC source references may identify the run that produced the registry or any
 other session. They remain registry provenance and are never copied into a
@@ -130,10 +117,9 @@ does not synthesize references or change their boundaries.
 After those per-cast changes, duplicate identity requires the same canonical
 spell name, the same caster after case folding and whitespace normalization,
 and the same complete, non-empty set of source references valid for the source
-document. Only the first occurrence is retained, in stable order. Its caster,
+document. Only the first occurrence is retained, in stable order. Its caster
-effect, narrative description, and canonical references are preserved without
+and canonical references are preserved. Unknown names, empty or invalid
-prose merging or source union. Unknown names, empty or invalid evidence, and
+evidence, and casts with different evidence remain separate.
-casts with different evidence remain separate.
 
 Mutation and duplicate decisions are returned through the normal warnings
 surface. Warning scopes use the merged input index, such as `spell_casts[0]`,

docs/internal/llm.md

@@ -134,8 +134,8 @@ reusable content follows it.
 
 Accordingly, the common prefix of all three extraction prompts is system,
 extraction evidence, identity, and campaign references. The NPC prompt then
-renders task, instructions, and transcript. Spell renders immediate resolution,
+renders task, instructions, and transcript. Spell renders the NPC registry,
-NPC registry, catalog, task, instructions, and transcript. Combat renders
+catalog, task, instructions, and transcript. Combat renders
 immediate resolution, NPC registry, task, instructions, and transcript. The
 scene chunker is not an extraction lane: it retains its separate system,
 transcript, campaign-reference, task, and instruction order and marks its

docs/internal/modules.md

@@ -207,16 +207,13 @@ failures therefore stop construction before source parsing or an LLM call;
 campaign references remain separate disambiguation inputs and never become
 source evidence.
 
-The prompt limits each cast to its declaration and immediate resolution; it
+The prompt includes only actual casting events and unambiguous declared casting
-does not follow summoned creatures, persistent effects, or other downstream
+attempts. Spell mentions, plans, rules discussion, and catalog matches without
-consequences through the scene. Shared extraction-evidence and identity rules
+a casting event are excluded. Shared extraction-evidence and identity rules
-require transcript-supported factual claims and the most specific in-world
+require transcript-supported caster and spell facts, while the catalog,
-caster identity, while campaign references only disambiguate source text.
+campaign references, and NPC names only disambiguate source text. Structural
-Effects describe the session as played: model rules knowledge cannot supplement
+source validation remains deterministic; semantic evidence sufficiency is
-or correct the transcript, and nonstandard adjudication is attributed to the GM
+enforced through extraction policy and evaluation.
-or table rather than stated as a universal rule. Structural source validation
-remains deterministic; semantic claim completeness is enforced through
-extraction policy and evaluation.
 
 Both the extractor and deterministic catalog validator expose
 the effective base-plus-overlay semantic digest as scoped prepared-component
@@ -224,23 +221,23 @@ checkpoint identity. Raw overlay provenance independently covers file-byte
 changes, while the semantic digest also invalidates reuse when the embedded
 catalog or catalog composition changes. The extractor additionally fingerprints
 its complete prompt assets and private response schema, so either semantic
-contract changing invalidates previously recorded extraction checkpoints. The separate
+contract changing invalidates previously recorded extraction checkpoints. The
-`internal/modules/dnd/codec/spells` package
+separate `internal/modules/dnd/codec/spells` package
 owns the durable schema and stable JSON representation for artifact kind
 `dnd/spell-list`. The runner keeps the result typed through validators and later
 stages, using the codec only for checkpoint, debug, and output boundaries.
-Shared D&D helpers keep prompt input
+Shared D&D helpers keep prompt input names and source-unit reference conversion
-names and source-unit reference conversion consistent with the scene chunker.
+consistent with the scene chunker.
 
 The extractor also declares the optional `npcs` registry slot and consumes the
 immutable registry boundary from `internal/modules/dnd/npcs/registry`. An
 external registry is prepared before execution; a generated registry is
-validated and supplied at operation time. External bindings may add only
+validated and supplied at operation time. Bound external registries add only
-`npc_registry_digest` and `npc_count` to module metadata and an
+the full `npc_registry_digest` and `npc_count` to module metadata. The local
-`npc_registry` checkpoint fingerprint. Generated bindings are represented by
+`npc_registry` checkpoint fingerprint always covers the names-only projection,
+including its exact unbound value. Generated bindings are represented by
 framework handoff provenance and dependency fingerprints. The unbound prompt
-input is exactly `{"npcs":[]}`, has a projection fingerprint, and has no
+input is exactly `{"npcs":[]}` and has no registry provenance.
-registry provenance.
 The shared NPC grounding fragment is placed immediately after the common
 campaign reference message and is included in the spell prompt fingerprint.
 
@@ -321,9 +318,9 @@ scoped warnings for each mutation or unresolved name.
 After those per-cast changes, it collapses only casts with the same canonical
 spell, case-folded and whitespace-normalized caster, and complete non-empty
 valid source-reference set. It retains the first occurrence and its caster,
-effect, narrative description, and stable order. Unknown names, empty or
+source references, and stable order. Unknown names, empty or invalid evidence,
-invalid evidence, and adjacent or overlapping but different ranges remain
+and adjacent or overlapping but different ranges remain unchanged for
-unchanged for validation.
+validation.
 
 The normalizer exposes the effective catalog digest as its independently scoped
 `effective_catalog` checkpoint fingerprint and reports catalog base ID, digest,
@@ -378,11 +375,11 @@ codec bytes according to its target context. Neither validator calls the LLM.
 ## D&D Spell Validators
 
 All four validators receive `dnd.SpellList` directly. The shape validator
-rejects missing or empty spell fields and empty reference lists. The catalog
+rejects a missing list, blank caster or spell names, and empty reference lists.
-validator defers when shape is invalid, then checks every non-empty spell name
+The catalog validator defers when shape is invalid, then checks every non-empty
-against the immutable effective SRD and overlay catalog. It accepts normalized
+spell name against the immutable effective SRD and overlay catalog. It accepts
-canonical names and aliases without rewriting the artifact; unknown names
+normalized canonical names and aliases without rewriting the artifact; unknown
-reject the complete result with bounded, stable index/name diagnostics. The
+names reject the complete result with bounded, stable index/name diagnostics. The
 source-reference validator defers malformed shapes, validates every cited
 range, and reports all range defects through a bounded aggregate while
 preserving `invalid_source_refs`. The relatedness validator resolves all cited

docs/internal/overview.md

@@ -115,11 +115,13 @@ this package. Domain-neutral prompt filesystem composition lives in
 The `dnd/npcs/registry` package owns the optional `npcs` registry boundary.
 External references are strictly decoded and identity-validated during
 preparation; generated references are decoded and identity-validated at the
-ordered step handoff. Both paths emit canonical registry JSON to operation-time
+ordered step handoff. Both paths retain canonical registry JSON for provenance
-spell and combat prompt or normalization requests. The framework records
+and emit a names-only projection to operation-time spell and combat prompts.
-generated identity and bounded producer provenance, while the raw external
+Combat normalization uses the canonical registry for exact actor lookup. The
-reference remains independently tracked by pipeline provenance. An absent
+framework records generated identity and bounded producer provenance, while
-registry is represented only by the empty prompt value `{"npcs":[]}`. Spell
+the raw external reference remains independently tracked by pipeline
+provenance. An absent registry is represented only by the empty prompt value
+`{"npcs":[]}`. Spell
 and combat consumers use this shared boundary without changing their public
 module contracts.
 

internal/cli/assembled_spell_pipeline_contract_test.go

@@ -57,8 +57,8 @@ func TestAssembledSpellPipelineNormalizesMergedCasts(t *testing.T) {
 		t.Fatalf("normalized casts = %#v, want collapsed duplicate plus distinct evidence", normalized.SpellCasts)
 	}
 	first, distinct := normalized.SpellCasts[0], normalized.SpellCasts[1]
-	if first.Spell != "Cure Wounds" || first.Caster != "  Aria \t" || first.Effect != "first occurrence" || first.NarrativeDescription != "first narrative" {
+	if first.Spell != "Cure Wounds" || first.Caster != "  Aria \t" {
-		t.Fatalf("retained cast = %#v, want canonical spell with first occurrence fields", first)
+		t.Fatalf("retained cast = %#v, want canonical spell with first occurrence caster", first)
 	}
 	if !reflect.DeepEqual(first.SourceRefs, []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 1}, {SourceID: "session-alpha", StartUnitID: 2, EndUnitID: 2}}) {
 		t.Fatalf("retained refs = %#v, want sorted complete evidence", first.SourceRefs)
@@ -271,7 +271,7 @@ func (e *assembledSpellExtractor) Extract(ctx context.Context, req contracts.Typ
 	if e.unknownSpell {
 		if req.Chunk.Index == 0 {
 			return contracts.TypedExtractionResult[dnd.SpellList]{Value: dnd.SpellList{SpellCasts: []dnd.SpellCast{{
-				Caster: "Aria", Spell: "Mysterious Burst", Effect: "an unknown magical effect", NarrativeDescription: "Aria produces a mysterious burst.", SourceRefs: []source.SourceRef{refOne},
+				Caster: "Aria", Spell: "Mysterious Burst", SourceRefs: []source.SourceRef{refOne},
 			}}}}, nil
 		}
 		return contracts.TypedExtractionResult[dnd.SpellList]{Value: dnd.SpellList{SpellCasts: []dnd.SpellCast{}}}, nil
@@ -279,12 +279,12 @@ func (e *assembledSpellExtractor) Extract(ctx context.Context, req contracts.Typ
 	switch req.Chunk.Index {
 	case 0:
 		return contracts.TypedExtractionResult[dnd.SpellList]{Value: dnd.SpellList{SpellCasts: []dnd.SpellCast{{
-			Caster: "  Aria \t", Spell: " cure   wounds ", Effect: "first occurrence", NarrativeDescription: "first narrative", SourceRefs: []source.SourceRef{refTwo, refOne},
+			Caster: "  Aria \t", Spell: " cure   wounds ", SourceRefs: []source.SourceRef{refTwo, refOne},
 		}}}}, nil
 	case 1:
 		return contracts.TypedExtractionResult[dnd.SpellList]{Value: dnd.SpellList{SpellCasts: []dnd.SpellCast{
-			{Caster: "aria", Spell: "Cure Wounds", Effect: "removed occurrence", NarrativeDescription: "removed narrative", SourceRefs: []source.SourceRef{refOne, refTwo}},
+			{Caster: "aria", Spell: "Cure Wounds", SourceRefs: []source.SourceRef{refOne, refTwo}},
-			{Caster: "aria", Spell: "Cure Wounds", Effect: "different evidence", NarrativeDescription: "different narrative", SourceRefs: []source.SourceRef{refTwo}},
+			{Caster: "aria", Spell: "Cure Wounds", SourceRefs: []source.SourceRef{refTwo}},
 		}}}, nil
 	default:
 		return contracts.TypedExtractionResult[dnd.SpellList]{}, fmt.Errorf("unexpected assembled chunk index %d", req.Chunk.Index)

internal/cli/production_contract_test.go

@@ -672,7 +672,7 @@ func (client *productionFakeLLMClient) CompleteStructured(ctx context.Context, r
 		if client.spellResponse != "" {
 			content = []byte(client.spellResponse)
 		} else {
-			content = []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","effect":"Heals an injured ally.","narrative_description":"Aria restores the fighter after the fight.","source_refs":[{"source_id":"session-alpha","start_unit_id":1,"end_unit_id":1}]}]}`)
+			content = []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[{"start_unit_id":1,"end_unit_id":1}]}]}`)
 		}
 	default:
 		return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected prompt %q", req.PromptID)

internal/cli/spell_catalog_retry_contract_test.go

@@ -148,11 +148,9 @@ func (client *catalogRetryLLMClient) CallCount() int {
 
 func productionSpellResponse(name string) string {
 	content, err := json.Marshal(dnd.SpellList{SpellCasts: []dnd.SpellCast{{
-		Caster:               "Aria",
+		Caster:     "Aria",
-		Spell:                name,
+		Spell:      name,
-		Effect:               "The spell takes effect.",
+		SourceRefs: []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 1}},
-		NarrativeDescription: "Aria casts the spell.",
-		SourceRefs:           []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 1}},
 	}}})
 	if err != nil {
 		panic(err)

internal/modules/dnd/codec/spells/assets/schemas/dnd_spells.v1.json

@@ -13,8 +13,6 @@
         "required": [
           "caster",
           "spell",
-          "effect",
-          "narrative_description",
           "source_refs"
         ],
         "properties": {
@@ -26,14 +24,6 @@
             "type": "string",
             "minLength": 1
           },
-          "effect": {
-            "type": "string",
-            "minLength": 1
-          },
-          "narrative_description": {
-            "type": "string",
-            "minLength": 1
-          },
           "source_refs": {
             "type": "array",
             "minItems": 1,

internal/modules/dnd/codec/spells/codec.go

@@ -99,12 +99,6 @@ func validate(value dnd.SpellList) error {
 		if strings.TrimSpace(spell.Spell) == "" {
 			return fmt.Errorf("spell_casts[%d].spell must not be empty", index)
 		}
-		if strings.TrimSpace(spell.Effect) == "" {
-			return fmt.Errorf("spell_casts[%d].effect must not be empty", index)
-		}
-		if strings.TrimSpace(spell.NarrativeDescription) == "" {
-			return fmt.Errorf("spell_casts[%d].narrative_description must not be empty", index)
-		}
 		if len(spell.SourceRefs) == 0 {
 			return fmt.Errorf("spell_casts[%d].source_refs must not be empty", index)
 		}

internal/modules/dnd/codec/spells/codec_test.go

@@ -27,8 +27,8 @@ func TestCodecMatchesMaintainedDurableFixture(t *testing.T) {
 		t.Fatalf("Decode() error = %v, want nil", err)
 	}
 	want := dnd.SpellList{SpellCasts: []dnd.SpellCast{
-		{Caster: "Aria", Spell: "Cure Wounds", Effect: "Heals an injured ally.", NarrativeDescription: "Aria restores the fighter after the fight.", SourceRefs: []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 2}}},
+		{Caster: "Aria", Spell: "Cure Wounds", SourceRefs: []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 2}}},
-		{Caster: "Borin", Spell: "Fire Bolt", Effect: "Scorches the wight.", NarrativeDescription: "Borin hurls fire at the wight.", SourceRefs: []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 3, EndUnitID: 3}}},
+		{Caster: "Borin", Spell: "Fire Bolt", SourceRefs: []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 3, EndUnitID: 3}}},
 	}}
 	if !reflect.DeepEqual(value, want) {
 		t.Fatalf("Decode() = %#v, want %#v", value, want)
@@ -82,9 +82,10 @@ func TestCodecStrictlyRejectsInvalidRepresentations(t *testing.T) {
 		want string
 	}{
 		{name: "unknown", raw: `{"spell_casts":[],"unexpected":true}`, want: "unknown field"},
+		{name: "unknown record field", raw: `{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[],"unexpected":true}]}`, want: "unknown field"},
 		{name: "trailing", raw: `{"spell_casts":[]} {}`, want: "multiple JSON values"},
 		{name: "missing", raw: `{}`, want: "spell_casts must be present"},
-		{name: "invalid evidence", raw: `{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","effect":"Heals","narrative_description":"Aria heals","source_refs":[{"source_id":"session","start_unit_id":0,"end_unit_id":1}]}]}`, want: "start_unit_id"},
+		{name: "invalid evidence", raw: `{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[{"source_id":"session","start_unit_id":0,"end_unit_id":1}]}]}`, want: "start_unit_id"},
 	}
 	for _, test := range tests {
 		t.Run(test.name, func(t *testing.T) {

internal/modules/dnd/codec/spells/testdata/dnd_spells.v1.json

@@ -3,8 +3,6 @@
     {
       "caster": "Aria",
       "spell": "Cure Wounds",
-      "effect": "Heals an injured ally.",
-      "narrative_description": "Aria restores the fighter after the fight.",
       "source_refs": [
         {
           "source_id": "session-alpha",
@@ -16,8 +14,6 @@
     {
       "caster": "Borin",
       "spell": "Fire Bolt",
-      "effect": "Scorches the wight.",
-      "narrative_description": "Borin hurls fire at the wight.",
       "source_refs": [
         {
           "source_id": "session-alpha",

internal/modules/dnd/extract/spells/assets/prompts/dnd.spells.yaml

@@ -33,8 +33,6 @@ messages:
     content_file: ./sharedassets/common-dnd-references.md
     cache_control:
       type: ephemeral
-  - role: user
-    content_file: ./sharedassets/common-dnd-immediate-resolution.md
   - role: user
     content_file: ./sharedassets/common-dnd-npcs.md
     cache_control:

internal/modules/dnd/extract/spells/assets/prompts/instructions.md

@@ -1,14 +1,8 @@
-For each spell cast, source references must collectively support the caster,
+For each spell cast, source references must collectively support the in-world
-spell, effect, and narrative_description. If a detail is not supported by the
+caster, spell name, and the fact that the cast or declared attempt occurred.
-cited transcript units, omit that detail or describe only the supported attempt
-or declaration.
 
-For spells, do not follow summoned creatures, persistent effects, or other
+Return only D&D spell-cast artifacts. For each record, identify the in-world
-downstream consequences through the rest of the scene.
+caster, canonical spell name, and source references.
-
-Return only D&D spell-cast artifacts. For each spell cast, identify the
-in-world caster, spell name, effect, narrative description, and source
-references.
 
 Use the player and party references together with transcript context to map
 first-person player speech to the associated player character and use the
@@ -20,10 +14,3 @@ transcript; do not invent a name.
 Use the canonical spell-name catalog to select spell names. Do not return a
 spell name absent from that catalog, even when it is suggested by general D&D
 knowledge or reference material.
-
-Effects and narrative descriptions are session records, not rules summaries.
-Report only mechanics, explanations, and outcomes established by the cited
-transcript units. Preserve the table's observed resolution without silently
-correcting it from general D&D knowledge. If the transcript gives a possibly
-nonstandard rationale, use wording such as "the GM rules" or "the table
-resolves" rather than asserting that rationale as a universal rule.

internal/modules/dnd/extract/spells/assets/prompts/task.md

@@ -1,15 +1,9 @@
 Extract Dungeons & Dragons spell-cast artifacts from the provided transcript.
 
-Do not infer a spell cast from general D&D knowledge or from table chatter that
+Include an actual casting event or an unambiguous declared casting attempt.
-does not identify a spell being cast.
+Exclude spell mentions, hypothetical plans, rules discussion, and catalog
-
+matches that do not establish a casting event in the transcript.
-Describe the session as it was played and adjudicated. The transcript is
-authoritative for what happened in this session, even when a table ruling may
-differ from published D&D rules. Do not correct the transcript or fill in
-unstated mechanics from general D&D knowledge. When a ruling or mechanical
-explanation matters, attribute it to the GM or table instead of presenting it
-as a universal game rule.
 
 Use the provided canonical spell-name catalog when naming each extracted spell.
 Return the canonical catalog spelling exactly. The catalog is a recognition
-aid; it does not establish that a spell was cast or how the spell works.
+aid and never evidence that a spell was cast.

internal/modules/dnd/extract/spells/assets/schemas/dnd_spells_llm.v1.json

@@ -13,8 +13,6 @@
         "required": [
           "caster",
           "spell",
-          "effect",
-          "narrative_description",
           "source_refs"
         ],
         "properties": {
@@ -26,17 +24,9 @@
             "type": "string",
             "description": "Canonical spell name from the provided spell-name catalog."
           },
-          "effect": {
-            "type": "string",
-            "description": "Concise immediate effect or resolution established by the cited transcript units; do not infer mechanics from general D&D rules knowledge or follow persistent downstream consequences."
-          },
-          "narrative_description": {
-            "type": "string",
-            "description": "Short session-grounded description of the casting declaration and immediate resolution, containing only details established by the cited transcript units."
-          },
           "source_refs": {
             "type": "array",
-            "description": "Transcript ranges offered as evidence for factual claims about the casting declaration and immediate resolution in this spell-cast object.",
+            "description": "Transcript ranges offered as evidence for the caster, spell name, and casting event in this spell-cast object.",
             "items": {
               "type": "object",
               "additionalProperties": false,

internal/modules/dnd/extract/spells/canonicalize.go

@@ -88,11 +88,9 @@ func canonicalSpellList(response extractionResponse, sourceID string) dnd.SpellL
 			}
 		}
 		spellCasts[index] = dnd.SpellCast{
-			Caster:               spell.Caster,
+			Caster:     spell.Caster,
-			Spell:                spell.Spell,
+			Spell:      spell.Spell,
-			Effect:               spell.Effect,
+			SourceRefs: refs,
-			NarrativeDescription: spell.NarrativeDescription,
-			SourceRefs:           refs,
 		}
 	}
 	if response.SpellCasts == nil {

internal/modules/dnd/extract/spells/extractor_test.go

@@ -19,11 +19,9 @@ import (
 func TestExtractReturnsCanonicalSpellListFromPrivateResponse(t *testing.T) {
 	client := &fakeSpellsLLMClient{response: extractionResponse{SpellCasts: []spellCastResponse{
 		{
-			Caster:               " Aria ",
+			Caster:     " Aria ",
-			Spell:                " Cure Wounds ",
+			Spell:      " Cure Wounds ",
-			Effect:               " Heals an injured ally. ",
+			SourceRefs: responseSourceRefs(1, 2),
-			NarrativeDescription: " Aria restores the fighter after the fight. ",
-			SourceRefs:           responseSourceRefs(1, 2),
 		},
 	}}}
 	req := extractionRequest()
@@ -34,11 +32,9 @@ func TestExtractReturnsCanonicalSpellListFromPrivateResponse(t *testing.T) {
 	}
 	want := dnd.SpellList{SpellCasts: []dnd.SpellCast{
 		{
-			Caster:               " Aria ",
+			Caster:     " Aria ",
-			Spell:                " Cure Wounds ",
+			Spell:      " Cure Wounds ",
-			Effect:               " Heals an injured ally. ",
+			SourceRefs: []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 2}},
-			NarrativeDescription: " Aria restores the fighter after the fight. ",
-			SourceRefs:           []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 2}},
 		},
 	}}
 	if !reflect.DeepEqual(result.Value, want) {
@@ -268,9 +264,9 @@ func TestExtractRejectsInvalidRequests(t *testing.T) {
 
 func TestExtractOrdersAndDeduplicatesEvidence(t *testing.T) {
 	client := &fakeSpellsLLMClient{response: extractionResponse{SpellCasts: []spellCastResponse{
-		{Caster: "Borin", Spell: "Fire Bolt", Effect: "Burns.", NarrativeDescription: "Second.", SourceRefs: responseSourceRefs(2, 2)},
+		{Caster: "Borin", Spell: "Fire Bolt", SourceRefs: responseSourceRefs(2, 2)},
-		{Caster: "Aria", Spell: "Cure Wounds", Effect: "Heals.", NarrativeDescription: "First.", SourceRefs: []spellSourceRefResponse{{StartUnitID: 1, EndUnitID: 2}, {StartUnitID: 1, EndUnitID: 2}}},
+		{Caster: "Aria", Spell: "Cure Wounds", SourceRefs: []spellSourceRefResponse{{StartUnitID: 1, EndUnitID: 2}, {StartUnitID: 1, EndUnitID: 2}}},
-		{Caster: "Narrator", Spell: "Unknown", Effect: "Unknown.", NarrativeDescription: "Uncited."},
+		{Caster: "Narrator", Spell: "Unknown"},
 	}}}
 	result, err := newExtractor(t, client).Extract(context.Background(), extractionRequest())
 	if err != nil {
@@ -286,7 +282,7 @@ func TestExtractOrdersAndDeduplicatesEvidence(t *testing.T) {
 
 func TestExtractPreservesInvalidEvidenceForValidators(t *testing.T) {
 	client := &fakeSpellsLLMClient{response: extractionResponse{SpellCasts: []spellCastResponse{{
-		Caster: "Aria", Spell: "Cure Wounds", Effect: "Heals.", NarrativeDescription: "Aria heals.",
+		Caster: "Aria", Spell: "Cure Wounds",
 		SourceRefs: []spellSourceRefResponse{{StartUnitID: 99, EndUnitID: 0}},
 	}}}}
 	result, err := newExtractor(t, client).Extract(context.Background(), extractionRequest())
@@ -300,13 +296,13 @@ func TestExtractPreservesInvalidEvidenceForValidators(t *testing.T) {
 }
 
 func TestExtractMapsRawSemanticCandidatesWithoutRepair(t *testing.T) {
-	client := &fakeSpellsLLMClient{content: []byte(`{"spell_casts":[{"caster":"","spell":"Cure Wounds","effect":"","narrative_description":"","source_refs":[{"start_unit_id":0,"end_unit_id":-1}]}]}`)}
+	client := &fakeSpellsLLMClient{content: []byte(`{"spell_casts":[{"caster":"","spell":"Cure Wounds","source_refs":[{"start_unit_id":0,"end_unit_id":-1}]}]}`)}
 	result, err := newExtractor(t, client).Extract(context.Background(), extractionRequest())
 	if err != nil {
 		t.Fatalf("Extract() error = %v, want nil", err)
 	}
 	spell := result.Value.SpellCasts[0]
-	if spell.Caster != "" || spell.Effect != "" || spell.NarrativeDescription != "" {
+	if spell.Caster != "" {
 		t.Fatalf("spell = %#v, want blank semantic values preserved", spell)
 	}
 	if refs := spell.SourceRefs; len(refs) != 1 || refs[0] != (source.SourceRef{SourceID: "session-alpha", StartUnitID: 0, EndUnitID: -1}) {

internal/modules/dnd/extract/spells/model.go

@@ -5,11 +5,9 @@ type extractionResponse struct {
 }
 
 type spellCastResponse struct {
-	Caster               string                   `json:"caster"`
+	Caster     string                   `json:"caster"`
-	Spell                string                   `json:"spell"`
+	Spell      string                   `json:"spell"`
-	Effect               string                   `json:"effect"`
+	SourceRefs []spellSourceRefResponse `json:"source_refs"`
-	NarrativeDescription string                   `json:"narrative_description"`
-	SourceRefs           []spellSourceRefResponse `json:"source_refs"`
 }
 
 type spellSourceRefResponse struct {

internal/modules/dnd/extract/spells/schema_test.go

@@ -37,14 +37,14 @@ func TestLoadResponseSchemaUsesExtractorOwnedLLMSchema(t *testing.T) {
 		{
 			name: "semantic blanks and empty evidence",
 			response: map[string]any{"spell_casts": []any{map[string]any{
-				"caster": "", "spell": "", "effect": "", "narrative_description": "", "source_refs": []any{},
+				"caster": "", "spell": "", "source_refs": []any{},
 			}}},
 			valid: true,
 		},
 		{
 			name: "nonpositive unit candidates",
 			response: map[string]any{"spell_casts": []any{map[string]any{
-				"caster": "Aria", "spell": "Cure Wounds", "effect": "Heals.", "narrative_description": "Aria heals.",
+				"caster": "Aria", "spell": "Cure Wounds",
 				"source_refs": []any{map[string]any{"start_unit_id": 0, "end_unit_id": -1}},
 			}}},
 			valid: true,
@@ -52,25 +52,25 @@ func TestLoadResponseSchemaUsesExtractorOwnedLLMSchema(t *testing.T) {
 		{
 			name: "missing required field",
 			response: map[string]any{"spell_casts": []any{map[string]any{
-				"spell": "Cure Wounds", "effect": "Heals.", "narrative_description": "Aria heals.", "source_refs": []any{},
+				"spell": "Cure Wounds", "source_refs": []any{},
 			}}},
 		},
 		{
 			name: "unknown field",
 			response: map[string]any{"spell_casts": []any{map[string]any{
-				"caster": "Aria", "spell": "Cure Wounds", "effect": "Heals.", "narrative_description": "Aria heals.", "source_refs": []any{}, "id": "assigned later",
+				"caster": "Aria", "spell": "Cure Wounds", "source_refs": []any{}, "id": "assigned later",
 			}}},
 		},
 		{
 			name: "wrong field type",
 			response: map[string]any{"spell_casts": []any{map[string]any{
-				"caster": 7, "spell": "Cure Wounds", "effect": "Heals.", "narrative_description": "Aria heals.", "source_refs": []any{},
+				"caster": 7, "spell": "Cure Wounds", "source_refs": []any{},
 			}}},
 		},
 		{
 			name: "noninteger source identifier",
 			response: map[string]any{"spell_casts": []any{map[string]any{
-				"caster": "Aria", "spell": "Cure Wounds", "effect": "Heals.", "narrative_description": "Aria heals.",
+				"caster": "Aria", "spell": "Cure Wounds",
 				"source_refs": []any{map[string]any{"start_unit_id": 1.5, "end_unit_id": 2}},
 			}}},
 		},
@@ -131,10 +131,8 @@ func validSpellsResponse() map[string]any {
 	return map[string]any{
 		"spell_casts": []any{
 			map[string]any{
-				"caster":                "Aria",
+				"caster": "Aria",
-				"spell":                 "Cure Wounds",
+				"spell":  "Cure Wounds",
-				"effect":                "The wounds close.",
-				"narrative_description": "Aria casts Cure Wounds.",
 				"source_refs": []any{
 					map[string]any{"start_unit_id": 1, "end_unit_id": 2},
 				},

internal/modules/dnd/extract/spells/scriptorium_assets.go

@@ -25,7 +25,6 @@ var promptAssetManifest = shared.PromptAssetManifest{
 		"common-dnd-identity.md",
 		"common-dnd-transcript.md",
 		"common-dnd-references.md",
-		"common-dnd-immediate-resolution.md",
 		"common-dnd-npcs.md",
 	},
 }

internal/modules/dnd/normalize/spells/normalizer_test.go

@@ -266,12 +266,12 @@ func TestNormalizeCollapsesDuplicateGroupsAfterCanonicalization(t *testing.T) {
 	firstEvidence := source.SourceRef{SourceID: "source", StartUnitID: 1, EndUnitID: 2}
 	secondEvidence := source.SourceRef{SourceID: "source", StartUnitID: 3, EndUnitID: 4}
 	input := dnd.SpellList{SpellCasts: []dnd.SpellCast{
-		{Caster: "  Aria \t", Spell: " cure   wounds ", Effect: "first effect", NarrativeDescription: "first narrative", SourceRefs: []source.SourceRef{secondEvidence, firstEvidence, firstEvidence}},
+		{Caster: "  Aria \t", Spell: " cure   wounds ", SourceRefs: []source.SourceRef{secondEvidence, firstEvidence, firstEvidence}},
-		{Caster: "Borin", Spell: "Healing Word", Effect: "distinct effect", NarrativeDescription: "distinct narrative", SourceRefs: []source.SourceRef{firstEvidence}},
+		{Caster: "Borin", Spell: "Healing Word", SourceRefs: []source.SourceRef{firstEvidence}},
-		{Caster: " Kyle ", Spell: "Cure Wounds", Effect: "kept effect", NarrativeDescription: "kept narrative", SourceRefs: []source.SourceRef{firstEvidence}},
+		{Caster: " Kyle ", Spell: "Cure Wounds", SourceRefs: []source.SourceRef{firstEvidence}},
-		{Caster: "aria", Spell: " cure wounds ", Effect: "removed effect", NarrativeDescription: "removed narrative", SourceRefs: []source.SourceRef{firstEvidence, secondEvidence}},
+		{Caster: "aria", Spell: " cure wounds ", SourceRefs: []source.SourceRef{firstEvidence, secondEvidence}},
-		{Caster: "KYLE", Spell: " cure wounds ", Effect: "removed effect two", NarrativeDescription: "removed narrative two", SourceRefs: []source.SourceRef{firstEvidence}},
+		{Caster: "KYLE", Spell: " cure wounds ", SourceRefs: []source.SourceRef{firstEvidence}},
-		{Caster: " kyle ", Spell: "Cure Wounds", Effect: "removed effect three", NarrativeDescription: "removed narrative three", SourceRefs: []source.SourceRef{firstEvidence}},
+		{Caster: " kyle ", Spell: "Cure Wounds", SourceRefs: []source.SourceRef{firstEvidence}},
 	}}
 
 	result, err := normalizer.Normalize(context.Background(), normalizeRequestWithSource(input, doc))
@@ -281,8 +281,8 @@ func TestNormalizeCollapsesDuplicateGroupsAfterCanonicalization(t *testing.T) {
 	if len(result.Value.SpellCasts) != 3 {
 		t.Fatalf("normalized casts = %#v, want first occurrences plus distinct cast", result.Value.SpellCasts)
 	}
-	if got := result.Value.SpellCasts[0]; got.Caster != "  Aria \t" || got.Effect != "first effect" || got.NarrativeDescription != "first narrative" {
+	if got := result.Value.SpellCasts[0]; got.Caster != "  Aria \t" {
-		t.Fatalf("retained first cast = %#v, want first occurrence fields unchanged", got)
+		t.Fatalf("retained first cast = %#v, want first occurrence caster unchanged", got)
 	}
 	if got := result.Value.SpellCasts[0].SourceRefs; !reflect.DeepEqual(got, []source.SourceRef{firstEvidence, secondEvidence}) {
 		t.Fatalf("retained first evidence = %#v, want canonical first evidence only", got)
@@ -393,11 +393,9 @@ func TestNormalizeBoundsDuplicateWarningIndices(t *testing.T) {
 func TestNormalizeIsIdempotentForAlreadyNormalizedInput(t *testing.T) {
 	doc := sourceDocument(3)
 	input := dnd.SpellList{SpellCasts: []dnd.SpellCast{{
-		Spell:                "Cure Wounds",
+		Spell:      "Cure Wounds",
-		Caster:               "Aria",
+		Caster:     "Aria",
-		Effect:               "effect",
+		SourceRefs: []source.SourceRef{{SourceID: "source", StartUnitID: 1, EndUnitID: 2}},
-		NarrativeDescription: "narrative",
-		SourceRefs:           []source.SourceRef{{SourceID: "source", StartUnitID: 1, EndUnitID: 2}},
 	}}}
 	normalizer := newNormalizer(t)
 	first, err := normalizer.Normalize(context.Background(), normalizeRequestWithSource(input, doc))

internal/modules/dnd/normalize/spells/testdata/normalizer_accepted_cases.json

@@ -7,8 +7,6 @@
           {
             "caster": "  Aria ",
             "spell": " cure   wounds ",
-            "effect": "first effect",
-            "narrative_description": "first narrative",
             "source_refs": [
               {"source_id": "source", "start_unit_id": 2, "end_unit_id": 2},
               {"source_id": "source", "start_unit_id": 1, "end_unit_id": 1},
@@ -18,8 +16,6 @@
           {
             "caster": "aria",
             "spell": "Cure Wounds",
-            "effect": "duplicate effect",
-            "narrative_description": "duplicate narrative",
             "source_refs": [
               {"source_id": "source", "start_unit_id": 1, "end_unit_id": 1},
               {"source_id": "source", "start_unit_id": 2, "end_unit_id": 2}
@@ -28,8 +24,6 @@
           {
             "caster": "aria",
             "spell": "Cure Wounds",
-            "effect": "distinct effect",
-            "narrative_description": "distinct narrative",
             "source_refs": [
               {"source_id": "source", "start_unit_id": 2, "end_unit_id": 2}
             ]
@@ -41,8 +35,6 @@
           {
             "caster": "  Aria ",
             "spell": "Cure Wounds",
-            "effect": "first effect",
-            "narrative_description": "first narrative",
             "source_refs": [
               {"source_id": "source", "start_unit_id": 1, "end_unit_id": 1},
               {"source_id": "source", "start_unit_id": 2, "end_unit_id": 2}
@@ -51,8 +43,6 @@
           {
             "caster": "aria",
             "spell": "Cure Wounds",
-            "effect": "distinct effect",
-            "narrative_description": "distinct narrative",
             "source_refs": [
               {"source_id": "source", "start_unit_id": 2, "end_unit_id": 2}
             ]
@@ -72,8 +62,6 @@
           {
             "caster": "Aria",
             "spell": "Cure Wounds",
-            "effect": "heals an ally",
-            "narrative_description": "Aria restores an ally's wounds.",
             "source_refs": [
               {"source_id": "source", "start_unit_id": 1, "end_unit_id": 1}
             ]
@@ -85,8 +73,6 @@
           {
             "caster": "Aria",
             "spell": "Cure Wounds",
-            "effect": "heals an ally",
-            "narrative_description": "Aria restores an ally's wounds.",
             "source_refs": [
               {"source_id": "source", "start_unit_id": 1, "end_unit_id": 1}
             ]

internal/modules/dnd/types.go

@@ -17,11 +17,9 @@ type SpellList struct {
 }
 
 type SpellCast struct {
-	Caster               string             `json:"caster"`
+	Caster     string             `json:"caster"`
-	Spell                string             `json:"spell"`
+	Spell      string             `json:"spell"`
-	Effect               string             `json:"effect"`
+	SourceRefs []source.SourceRef `json:"source_refs"`
-	NarrativeDescription string             `json:"narrative_description"`
-	SourceRefs           []source.SourceRef `json:"source_refs"`
 }
 
 type NPCList struct {

internal/modules/dnd/validate/spells/catalog/validator_test.go

@@ -201,11 +201,9 @@ func spellList(names ...string) dnd.SpellList {
 
 func validCast(name string) dnd.SpellCast {
 	return dnd.SpellCast{
-		Caster:               "Aria",
+		Caster:     "Aria",
-		Spell:                name,
+		Spell:      name,
-		Effect:               "heals an ally",
+		SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}},
-		NarrativeDescription: "Aria restores Borin.",
-		SourceRefs:           []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}},
 	}
 }
 

internal/modules/dnd/validate/spells/shape/validator.go

@@ -48,12 +48,6 @@ func Validate(value dnd.SpellList) error {
 		if strings.TrimSpace(spell.Spell) == "" {
 			return fmt.Errorf("spell_casts[%d].spell must not be empty", index)
 		}
-		if strings.TrimSpace(spell.Effect) == "" {
-			return fmt.Errorf("spell_casts[%d].effect must not be empty", index)
-		}
-		if strings.TrimSpace(spell.NarrativeDescription) == "" {
-			return fmt.Errorf("spell_casts[%d].narrative_description must not be empty", index)
-		}
 		if len(spell.SourceRefs) == 0 {
 			return fmt.Errorf("spell_casts[%d].source_refs must not be empty", index)
 		}

internal/modules/dnd/validate/spells/shape/validator_test.go

@@ -34,17 +34,23 @@ func TestValidatorRejectsMissingSpellList(t *testing.T) {
 }
 
 func TestValidatorRejectsMissingRequiredSpellFields(t *testing.T) {
-	value := validSpellList()
+	tests := []struct {
-	value.SpellCasts[0].Spell = ""
+		name   string
-	result, err := New(Options{}).Validate(context.Background(), requestWithValue(value))
+		mutate func(*dnd.SpellCast)
-	if err != nil {
+	}{
-		t.Fatalf("Validate() error = %v, want nil", err)
+		{name: "blank caster", mutate: func(cast *dnd.SpellCast) { cast.Caster = " " }},
+		{name: "blank spell", mutate: func(cast *dnd.SpellCast) { cast.Spell = "" }},
+		{name: "empty evidence", mutate: func(cast *dnd.SpellCast) { cast.SourceRefs = nil }},
 	}
-	if result.Approved {
+	for _, test := range tests {
-		t.Fatalf("Approved = true, want false")
+		t.Run(test.name, func(t *testing.T) {
-	}
+			value := validSpellList()
-	if result.ReasonCode != ReasonCode {
+			test.mutate(&value.SpellCasts[0])
-		t.Fatalf("ReasonCode = %q, want %q", result.ReasonCode, ReasonCode)
+			result, err := New(Options{}).Validate(context.Background(), requestWithValue(value))
+			if err != nil || result.Approved || result.ReasonCode != ReasonCode {
+				t.Fatalf("Validate() = %#v, %v; want shape rejection", result, err)
+			}
+		})
 	}
 }
 
@@ -69,5 +75,5 @@ func requestWithValue(value dnd.SpellList) contracts.TypedValidationRequest[dnd.
 }
 
 func validSpellList() dnd.SpellList {
-	return dnd.SpellList{SpellCasts: []dnd.SpellCast{{Caster: "Aria", Spell: "Cure Wounds", Effect: "heals", NarrativeDescription: "Aria heals Borin.", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}}}
+	return dnd.SpellList{SpellCasts: []dnd.SpellCast{{Caster: "Aria", Spell: "Cure Wounds", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}}}
 }

internal/modules/dnd/validate/spells/source_refs/validator_test.go

@@ -90,7 +90,7 @@ func TestValidatorSpecCheckpointAndRegistration(t *testing.T) {
 
 func requestWithValue(doc *source.SourceDocument, ref source.SourceRef) contracts.TypedValidationRequest[dnd.SpellList] {
 	return contracts.TypedValidationRequest[dnd.SpellList]{Source: doc, Value: dnd.SpellList{SpellCasts: []dnd.SpellCast{{
-		Caster: "Aria", Spell: "Cure Wounds", Effect: "heals", NarrativeDescription: "Aria casts Cure Wounds.", SourceRefs: []source.SourceRef{ref},
+		Caster: "Aria", Spell: "Cure Wounds", SourceRefs: []source.SourceRef{ref},
 	}}}}
 }
 

internal/modules/dnd/validate/spells/source_relatedness/validator_test.go

@@ -41,7 +41,7 @@ func TestValidatorWarnsWhenSpellDoesNotAppearInCitedText(t *testing.T) {
 
 func TestValidatorMatchesCaseInsensitiveUnicodeMultiwordSpellAcrossCitations(t *testing.T) {
 	value := dnd.SpellList{SpellCasts: []dnd.SpellCast{{
-		Caster: "Aria", Spell: "Tasha's Hideous Laughter", Effect: "effect", NarrativeDescription: "description",
+		Caster: "Aria", Spell: "Tasha's Hideous Laughter",
 		SourceRefs: []source.SourceRef{
 			{SourceID: "session", StartUnitID: 2, EndUnitID: 2},
 			{SourceID: "session", StartUnitID: 1, EndUnitID: 2},
@@ -108,7 +108,7 @@ func TestValidatorSpecCheckpointAndRegistration(t *testing.T) {
 
 func requestWithSpell(doc *source.SourceDocument, name string, unitID int) contracts.TypedValidationRequest[dnd.SpellList] {
 	return contracts.TypedValidationRequest[dnd.SpellList]{Source: doc, Value: dnd.SpellList{SpellCasts: []dnd.SpellCast{{
-		Caster: "Aria", Spell: name, Effect: "effect", NarrativeDescription: "description",
+		Caster: "Aria", Spell: name,
 		SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: unitID, EndUnitID: unitID}},
 	}}}}
 }

internal/modules/integration/dnd_npc_grounded_test.go

@@ -18,7 +18,6 @@ import (
 	combatextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/combatturns"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcs"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/spells"
-	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
 )
 
 func TestNPCOutputGroundsSpellAndCombatConsumersThroughOneOperation(t *testing.T) {
@@ -112,7 +111,7 @@ func TestNPCOutputGroundsSpellAndCombatConsumersThroughOneOperation(t *testing.T
 			if len(spellValue.SpellCasts) != 1 || spellValue.SpellCasts[0].Caster != "Mira Thorn" {
 				t.Fatalf("spell output = %#v, want one registry-grounded-context spell", spellValue)
 			}
-			assertSpellEvidence(t, spellValue.SpellCasts[0].SourceRefs)
+			assertCurrentEvidence(t, spellValue.SpellCasts[0].SourceRefs)
 		case "combat":
 			decoded, decodeErr := combatcodec.New().Decode(serialized.Artifact.Content)
 			if decodeErr != nil {
@@ -127,15 +126,6 @@ func TestNPCOutputGroundsSpellAndCombatConsumersThroughOneOperation(t *testing.T
 	assertCurrentEvidence(t, combatValue.CombatTurns[0].SourceRefs)
 }
 
-func assertSpellEvidence(t *testing.T, references []shared.SourceRefResponse) {
-	t.Helper()
-	for _, reference := range references {
-		if reference.SourceID != "npc-session" {
-			t.Fatalf("spell evidence reference = %#v, want current source only", reference)
-		}
-	}
-}
-
 func assertCurrentEvidence(t *testing.T, references []source.SourceRef) {
 	t.Helper()
 	for _, reference := range references {
@@ -184,9 +174,8 @@ func (client *groundedDNDLLMClient) CompleteStructured(ctx context.Context, requ
 		}}
 	case spells.PromptID:
 		payload = map[string]any{"spell_casts": []any{map[string]any{
-			"caster": "Mira Thorn", "spell": "Cure Wounds", "effect": "Restores an ally.",
+			"caster": "Mira Thorn", "spell": "Cure Wounds",
-			"narrative_description": "Mira Thorn restores an ally.",
+			"source_refs": []any{map[string]int{"start_unit_id": 1, "end_unit_id": 1}},
-			"source_refs":           []any{map[string]int{"start_unit_id": 1, "end_unit_id": 1}},
 		}}}
 	case combatextract.PromptID:
 		payload = map[string]any{"combat_turns": []any{map[string]any{

internal/modules/integration/dnd_spells_helpers_test.go

@@ -6,7 +6,6 @@ import (
 	"fmt"
 
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
-	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
 )
 
 type extractionResponse struct {
@@ -14,11 +13,14 @@ type extractionResponse struct {
 }
 
 type spellCastResponse struct {
-	Caster               string                     `json:"caster"`
+	Caster     string                   `json:"caster"`
-	Spell                string                     `json:"spell"`
+	Spell      string                   `json:"spell"`
-	Effect               string                     `json:"effect"`
+	SourceRefs []spellSourceRefResponse `json:"source_refs"`
-	NarrativeDescription string                     `json:"narrative_description"`
+}
-	SourceRefs           []shared.SourceRefResponse `json:"source_refs"`
+
+type spellSourceRefResponse struct {
+	StartUnitID int `json:"start_unit_id"`
+	EndUnitID   int `json:"end_unit_id"`
 }
 
 type fakeSpellsLLMClient struct {
@@ -58,12 +60,11 @@ func (client *fakeSpellsLLMClient) CompleteStructured(_ context.Context, req con
 	return contracts.StructuredCompletionResponse{Content: content}, nil
 }
 
-func responseSourceRefs(sourceID string, startUnitID int, endUnitID int) []shared.SourceRefResponse {
+func responseSourceRefs(startUnitID int, endUnitID int) []spellSourceRefResponse {
-	return []shared.SourceRefResponse{
+	return []spellSourceRefResponse{
 		{
-			SourceID:    sourceID,
+			StartUnitID: startUnitID,
-			StartUnitID: shared.UnitRefFromInt(startUnitID),
+			EndUnitID:   endUnitID,
-			EndUnitID:   shared.UnitRefFromInt(endUnitID),
 		},
 	}
 }

internal/modules/integration/dnd_spells_runner_test.go

@@ -2,7 +2,6 @@ package integration_test
 
 import (
 	"context"
-	"encoding/json"
 	"os"
 	"strings"
 	"testing"
@@ -11,6 +10,8 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	spellcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/spells"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/spells"
 	spellnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/spells"
 	spellshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/spells/shape"
@@ -36,18 +37,14 @@ func TestRunnerProcessesSeriatimInputWithDNDSpellsExtractor(t *testing.T) {
 		response: extractionResponse{
 			SpellCasts: []spellCastResponse{
 				{
-					Caster:               "Aria",
+					Caster:     "Aria",
-					Spell:                "Cure Wounds",
+					Spell:      "Cure Wounds",
-					Effect:               "Heals an injured ally.",
+					SourceRefs: responseSourceRefs(1, 1),
-					NarrativeDescription: "Aria restores the fighter after the fight.",
-					SourceRefs:           responseSourceRefs(expectedDoc.ID, 1, 1),
 				},
 				{
-					Caster:               "Borin",
+					Caster:     "Borin",
-					Spell:                "Fire Bolt",
+					Spell:      "Fire Bolt",
-					Effect:               "Scorches the wight.",
+					SourceRefs: responseSourceRefs(3, 3),
-					NarrativeDescription: "Borin hurls fire at the wight.",
-					SourceRefs:           responseSourceRefs(expectedDoc.ID, 3, 3),
 				},
 			},
 		},
@@ -119,7 +116,6 @@ func TestRunnerProcessesSeriatimInputWithDNDSpellsExtractor(t *testing.T) {
 
 func TestRunnerPassesPartyAndGlossaryReferencesToDNDSpellsPrompt(t *testing.T) {
 	raw := readDNDSpellsFixture(t)
-	expectedDoc := parseDNDSpellsFixture(t, raw)
 	resolved := resolveDNDSpellsPipeline(t)
 	resolved.ResolvedPipeline.Steps[0].ArtifactLanes[0].ExtractReferences.ReferenceSet = dndSpellsReferenceSet(
 		"Aria: party cleric\nBorin: fighter",
@@ -129,11 +125,9 @@ func TestRunnerPassesPartyAndGlossaryReferencesToDNDSpellsPrompt(t *testing.T) {
 		response: extractionResponse{
 			SpellCasts: []spellCastResponse{
 				{
-					Caster:               "Borin",
+					Caster:     "Borin",
-					Spell:                "Fire Bolt",
+					Spell:      "Fire Bolt",
-					Effect:               "Scorches the wight.",
+					SourceRefs: responseSourceRefs(3, 3),
-					NarrativeDescription: "Borin hurls fire at the wight.",
-					SourceRefs:           responseSourceRefs(expectedDoc.ID, 3, 3),
 				},
 			},
 		},
@@ -195,25 +189,25 @@ func TestProductionSpellPipelineRoutesSemanticCandidatesToDeterministicValidator
 	}{
 		{
 			name:          "blank string",
-			response:      []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","effect":"","narrative_description":"Aria casts the spell.","source_refs":[{"start_unit_id":1,"end_unit_id":1}]}]}`),
+			response:      []byte(`{"spell_casts":[{"caster":"","spell":"Cure Wounds","source_refs":[{"start_unit_id":1,"end_unit_id":1}]}]}`),
 			reasonCode:    spellshape.ReasonCode,
 			validatorName: spellshape.Key,
 		},
 		{
 			name:          "empty evidence",
-			response:      []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","effect":"Heals.","narrative_description":"Aria casts the spell.","source_refs":[]}]}`),
+			response:      []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[]}]}`),
 			reasonCode:    spellshape.ReasonCode,
 			validatorName: spellshape.Key,
 		},
 		{
 			name:          "nonpositive unit candidate",
-			response:      []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","effect":"Heals.","narrative_description":"Aria casts the spell.","source_refs":[{"start_unit_id":0,"end_unit_id":1}]}]}`),
+			response:      []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[{"start_unit_id":0,"end_unit_id":1}]}]}`),
 			reasonCode:    spellsourcerefs.ReasonCode,
 			validatorName: spellsourcerefs.Key,
 		},
 		{
 			name:          "unknown unit candidate",
-			response:      []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","effect":"Heals.","narrative_description":"Aria casts the spell.","source_refs":[{"start_unit_id":99,"end_unit_id":99}]}]}`),
+			response:      []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[{"start_unit_id":99,"end_unit_id":99}]}]}`),
 			reasonCode:    spellsourcerefs.ReasonCode,
 			validatorName: spellsourcerefs.Key,
 		},
@@ -320,12 +314,12 @@ func parseDNDSpellsFixture(t *testing.T, raw []byte) *source.SourceDocument {
 	return doc
 }
 
-func decodeRunnerSpellResponse(t *testing.T, raw []byte) extractionResponse {
+func decodeRunnerSpellResponse(t *testing.T, raw []byte) dnd.SpellList {
 	t.Helper()
 
-	var response extractionResponse
+	response, err := spellcodec.New().Decode(raw)
-	if err := json.Unmarshal(raw, &response); err != nil {
+	if err != nil {
-		t.Fatalf("Unmarshal(raw output) error = %v, want nil", err)
+		t.Fatalf("decode durable spell output: %v", err)
 	}
 	return response
 }