Tighten evidence context source excerpts

README.md

@@ -2,9 +2,9 @@
 
 Notarius is a Go CLI for turning source material into structured artifacts with
 configured extraction pipelines. The implemented D&D workflow reads Seriatim
-transcript JSON and can produce location registries and occurrences, scene
+transcript JSON and can produce NPC, location, and item registries; their
-descriptions, item and currency events, NPC identities, combat turns, NPC
+source-grounded occurrences; scene descriptions, combat turns, enemy events,
-interactions, enemy events, and spell casts.
+and spell casts.
 
 ## Quickstart
 

assets/dnd/combat-turns/prompts/instructions.md

@@ -1,6 +1,18 @@
-Return the combat_turns array even when no combat turn is established. Return
+Extract Dungeons & Dragons combat-turn artifacts from the supplied transcript.
-actor, turn_kind, and source_refs for every record. For turn_kind, use exactly
+Include a record only when the transcript establishes that an in-world
-one of: turn, reaction, legendary_action, lair_action, or other. Cite the
+participant takes a combat turn or performs a discrete interrupting combat
-transcript ranges that establish both the actor and the combat event. Use the
+event. Keep events in transcript chronology; place an interrupting event where
-players, party, and transcript context to map speakers to in-world actors. NPC
+it occurs.
-names may help disambiguate identity but do not replace transcript evidence.
+
+Exclude initiative setup without a turn or combat event, tactical planning,
+table talk, rules lookup, hypothetical events, abandoned intentions, recaps
+outside the current passage, and downstream consequences. Do not infer combat
+events from Dungeons & Dragons rules knowledge. Preserve the session as played
+and attribute relevant nonstandard rulings to the GM or table. Unmatched actors
+remain permitted.
+
+Treat each record as one turn-level event and keep its supporting transcript
+evidence together. Use `turn` for a regular combat turn, `reaction` for an
+off-turn reaction, `legendary_action` for a legendary action,
+`lair_action` for a lair action, and `other` for another discrete combat
+event that does not fit those categories.

assets/dnd/combat-turns/prompts/prompt.yaml

@@ -14,7 +14,7 @@ inputs:
   - name: glossary
     required: false
     content_type: text/plain
-  - name: npcs
+  - name: npc_registry
     required: false
     content_type: application/json
 messages:
@@ -27,15 +27,13 @@ messages:
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
   - role: user
     content_file: ./sharedassets/common-dnd-extraction-evidence.md
   - role: user
-    content_file: ./sharedassets/common-dnd-npcs.md
+    content_file: ./sharedassets/common-dnd-npc-registry.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:

assets/dnd/combat-turns/prompts/task.md

@@ -1,18 +0,0 @@
-Extract Dungeons & Dragons combat-turn artifacts from the supplied transcript.
-
-Include a record only when the transcript establishes that an in-world
-participant takes a combat turn or performs a discrete interrupting combat
-event. Interrupting events belong at the point where they occur in transcript
-chronology.
-
-Exclude initiative setup without a turn or combat event, tactical planning,
-table talk, rules lookup, hypothetical events, abandoned intentions, recaps
-outside the current passage, and downstream consequences.
-
-Do not infer combat events from D&D rules knowledge. Preserve the session as
-played and attribute relevant nonstandard rulings to the GM or table.
-
-Unmatched actors remain permitted.
-
-Place all supporting transcript ranges for a turn in its turn-level source_refs
-collection.

assets/dnd/enemy-events/prompts/combat-grounding.md

@@ -9,4 +9,4 @@ Combat-turn grounding:
 
 Named combat-opponent grounding:
 
-{{ input "npc_interactions" }}
+{{ input "npc_occurrences" }}

assets/dnd/enemy-events/prompts/instructions.md

@@ -1,14 +1,25 @@
+Extract Dungeons & Dragons enemy events from the supplied combat transcript.
+An `engaged` event requires direct establishment that a subject is actively
+opposing the party in combat. A `killed`, `fled`, `captured`, or
+`incapacitated` event requires explicit establishment of that outcome. An
+outcome may share evidence with an engagement, and a later engagement or
+outcome for the same subject remains a separate observation. Emit at most one
+`engaged` observation for the same subject in this combat scene.
+
+For `killed`, direct death or killing is required. For `fled`, the subject
+must explicitly escape, retreat, or leave combat to avoid continued engagement.
+For `captured`, the subject must be explicitly taken prisoner or secured
+under the party's control. For `incapacitated`, the subject must be explicitly
+unable to continue acting without being established as killed or captured.
+
+When the transcript identifies a named NPC, use its normalized registry
+spelling. A hostile creature without a registry entry is allowed. For unnamed
+individuals or groups, use only the narrowest transcript-grounded label, such
+as `Orcs`, `One orc`, or `Remaining orcs`; never invent member names, IDs,
+or quantities.
+
 Exclude party members, allies, neutral observers, mentioned-but-absent enemies,
 hazards, traps, environmental effects, uncertain allegiance, table talk,
 planning, hypotheses, recaps outside this passage, and downstream inference.
-
 Do not infer an engagement or outcome from initiative, turn absence, damage,
-defeat, movement, a scene ending, combat-opponent grounding, or any auxiliary
+defeat, movement, or a scene ending.
-artifact. Auxiliary inputs can guide attention but cannot prove or supply an
-event. Cite only narrow current-transcript ranges that establish each event.
-
-Return the `events` array even when no enemy event is established. Every event
-must contain only `name`, `kind`, and `source_refs`. Use exactly one kind:
-`engaged`, `killed`, `fled`, `captured`, or `incapacitated`. Each source range
-uses integer `start_unit_id` and `end_unit_id`; omit `source_id` because
-Notarius assigns the current source identity.

assets/dnd/enemy-events/prompts/prompt.yaml

@@ -14,13 +14,13 @@ inputs:
   - name: glossary
     required: false
     content_type: text/plain
-  - name: npcs
+  - name: npc_registry
     required: true
     content_type: application/json
   - name: combat_turns
     required: true
     content_type: application/json
-  - name: npc_interactions
+  - name: npc_occurrences
     required: true
     content_type: application/json
 messages:
@@ -33,17 +33,15 @@ messages:
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
   - role: user
     content_file: ./sharedassets/common-dnd-extraction-evidence.md
   - role: user
-    content_file: ./sharedassets/common-dnd-npcs.md
+    content_file: ./sharedassets/common-dnd-npc-registry.md
   - role: user
-    content_file: ./grounding.md
+    content_file: ./combat-grounding.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:

assets/dnd/enemy-events/prompts/task.md

@@ -1,20 +0,0 @@
-Extract Dungeons & Dragons enemy events from the supplied combat transcript.
-
-Return an `engaged` event only when the transcript directly establishes that a
-subject is actively opposing the party in combat. Return `killed`, `fled`,
-`captured`, or `incapacitated` only when the transcript explicitly establishes
-that outcome. An outcome may share evidence with an engagement, and a later
-engagement or outcome for the same subject remains a separate observation.
-Emit at most one engagement for the same subject in this combat scene.
-
-For `killed`, direct death or killing is required. For `fled`, the subject must
-explicitly escape, retreat, or leave combat to avoid continued engagement. For
-`captured`, the subject must be explicitly taken prisoner or secured under the
-party's control. For `incapacitated`, the subject must be explicitly unable to
-continue acting without being established as killed or captured.
-
-Use a normalized NPC registry spelling when the transcript identifies that
-named NPC. A hostile creature without a registry entry is allowed. For unnamed
-individuals or groups, use only the narrowest transcript-grounded label, such
-as `Orcs`, `One orc`, or `Remaining orcs`; never invent member names, IDs, or
-quantities.

assets/dnd/entity-reconciliation/schemas/dnd_entity_reconcile_llm.v1.json

@@ -1,24 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "notarius.dnd.entity_reconcile.llm",
-  "type": "object",
-  "additionalProperties": false,
-  "required": ["duplicate_groups"],
-  "properties": {
-    "duplicate_groups": {
-      "type": "array",
-      "items": {
-        "type": "object",
-        "additionalProperties": false,
-        "required": ["members", "canonical"],
-        "properties": {
-          "members": {
-            "type": "array",
-            "items": {"type": "string"}
-          },
-          "canonical": {"type": "string"}
-        }
-      }
-    }
-  }
-}

assets/dnd/item-events/prompts/task.md

@@ -1,7 +0,0 @@
-Extract meaningful Dungeons & Dragons item and currency events established by
-the transcript. Record only discoveries and changes in party possession, with
-the transcript ranges that support each event.
-
-This is an event history, not an inventory or ledger. Do not calculate balances,
-resolve item identity across records, or infer ownership that the transcript
-does not establish.

assets/dnd/item-occurrences/prompts/instructions.md

@@ -1,7 +1,12 @@
-Return one event only when the transcript establishes a meaningful item or
+Extract meaningful Dungeons & Dragons item and currency occurrences: discoveries and changes
-currency occurrence. Use a concise observed item name and preserve the stated
+in party possession established by the transcript. This is an occurrence history,
-currency denomination. Set `quantity` to the explicitly stated integer, or to
+not an inventory or ledger: do not calculate balances, resolve item identity
-`null` when the transcript does not state one.
+across records, or infer ownership that the transcript does not establish.
+
+For every occurrence, use the supplied canonical item `name`. Record a stated
+quantity as an integer and leave it null when the transcript does not state
+one. Preserve the stated currency denomination through the selected canonical
+registry name.
 
 Use `discovered` when the party learns of or encounters an item without
 establishing possession. Use `acquired` when the party or a party member gains
@@ -13,14 +18,13 @@ when the transcript explicitly describes it being physically destroyed or
 expended as a non-payment component. Use `transferred` only when possession
 moves between two distinct named party members.
 
-Return both `from` and `to` for every event, using `null` when a holder does not
+Return both `from` and `to` for every occurrence, using `null` when a holder does not
 apply. For `discovered`, set both holders to `null`. For `acquired`, set `from`
 to `null` and provide `to`; for `lost` and `consumed`, provide `from` and set
 `to` to `null`; and for `transferred`, provide both holders. Use `party` only
 for collective or unresolved party possession, never for either side of a
 transfer. Do not emit a transfer for a gift, sale, or payment outside the party.
 
-Ordinary non-depleting use is not an event. Do not infer acquisition from a
+Ordinary non-depleting use is not an occurrence. Do not infer acquisition from a
 discovery, or discovery from an acquisition: emit both only when each is
-independently established. Every event needs at least one narrow transcript
+independently established.
-range. Return no lore, inventory totals, aliases, or unstated holder details.

assets/dnd/item-occurrences/prompts/item-registry.md

@@ -0,0 +1,6 @@
+Use the supplied item registry only to ground each occurrence. Every record
+must use one registry item's canonical `name`; do not invent, rename, merge,
+or infer registry items. The registry is not transcript evidence: cite only the
+current transcript chunk in `source_refs`.
+
+{{ input "item_registry" }}

assets/dnd/item-occurrences/prompts/prompt.yaml

@@ -1,4 +1,4 @@
-id: dnd.npc_interactions
+id: dnd.item_occurrences
 version: "v1"
 default_profile: dnd-extraction
 inputs:
@@ -14,7 +14,7 @@ inputs:
   - name: glossary
     required: false
     content_type: text/plain
-  - name: npcs
+  - name: item_registry
     required: true
     content_type: application/json
 messages:
@@ -27,15 +27,13 @@ messages:
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
   - role: user
     content_file: ./sharedassets/common-dnd-extraction-evidence.md
   - role: user
-    content_file: ./sharedassets/common-dnd-npcs.md
+    content_file: ./item-registry.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:
@@ -43,5 +41,5 @@ messages:
 output:
   format: json
   validation_mode: json_schema
-  schema_path: dnd_npc_interactions_llm.v1.json
+  schema_path: dnd_item_occurrences_llm.v1.json
   repair_attempts: 0

assets/dnd/item-occurrences/schemas/dnd_item_occurrences_llm.v1.json

@@ -1,11 +1,11 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "notarius.dnd.item_events.llm",
+  "$id": "notarius.dnd.item_occurrences.llm",
   "type": "object",
   "additionalProperties": false,
-  "required": ["events"],
+  "required": ["occurrences"],
   "properties": {
-    "events": {
+    "occurrences": {
       "type": "array",
       "items": {
         "type": "object",
@@ -22,10 +22,10 @@
             "items": {
               "type": "object",
               "additionalProperties": false,
-              "required": ["start_segment", "end_segment"],
+              "required": ["start_unit_id", "end_unit_id"],
               "properties": {
-                "start_segment": {"type": "integer"},
+                "start_unit_id": {"type": "integer"},
-                "end_segment": {"type": "integer"}
+                "end_unit_id": {"type": "integer"}
               }
             }
           }

assets/dnd/item-registry/extract/prompts/instructions.md

@@ -0,0 +1,12 @@
+Extract only items established by the provided Dungeons & Dragons transcript.
+
+Include named unique items, concrete reusable item types, and stable unique
+designations. Record each currency denomination separately when it is
+established, such as copper pieces, silver pieces, gold pieces, or platinum
+pieces. Do not use capitalization as an eligibility test. Keep distinct names
+and designations as separate candidates; do not merge aliases or invent
+qualifiers.
+
+Do not record vague categories such as "loot", "treasure", or "some gear";
+generic weapons; inferred properties; quantities; or inferred uniqueness. Omit
+uncertain or unsupported items.

assets/dnd/item-registry/extract/prompts/prompt.yaml

@@ -1,4 +1,4 @@
-id: dnd.npcs
+id: dnd.item_registry
 version: "v1"
 default_profile: dnd-extraction
 inputs:
@@ -24,13 +24,11 @@ messages:
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
   - role: user
     content_file: ./sharedassets/common-dnd-extraction-evidence.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:
@@ -38,5 +36,5 @@ messages:
 output:
   format: json
   validation_mode: json_schema
-  schema_path: dnd_npcs_llm.v1.json
+  schema_path: dnd_item_registry_llm.v1.json
   repair_attempts: 0

assets/dnd/item-registry/extract/schemas/dnd_item_registry_llm.v1.json

@@ -0,0 +1,32 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.dnd.item_registry.llm",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["items"],
+  "properties": {
+    "items": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["name", "source_refs"],
+        "properties": {
+          "name": {"type": "string"},
+          "source_refs": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "additionalProperties": false,
+              "required": ["start_unit_id", "end_unit_id"],
+              "properties": {
+                "start_unit_id": {"type": "integer"},
+                "end_unit_id": {"type": "integer"}
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}

assets/dnd/item-registry/normalize/prompts/instructions.md

@@ -0,0 +1,9 @@
+Determine whether candidates identify the same item type or unique designation
+using their contextual labels and cited transcript windows. Do not treat nearby
+evidence, similar objects, or a shared owner as sufficient.
+
+Keep currency denominations and materially different item types separate. Keep
+uncertain aliases separate. Do not infer an item property or uniqueness.
+
+When selecting a canonical display name, choose one supplied candidate name
+that is the clearest established designation.

assets/dnd/item-registry/normalize/prompts/prompt.yaml

@@ -1,4 +1,4 @@
-id: dnd.npcs.normalize
+id: dnd.item_registry.normalize
 version: "v1"
 default_profile: dnd-extraction
 inputs:
@@ -12,19 +12,19 @@ messages:
   - role: system
     content_file: ./sharedassets/common-dnd-system.md
   - role: user
-    content_file: ./task.md
+    content_file: ./sharedassets/protocol.md
   - role: user
-    content_file: ./sharedassets/common-dnd-entity-reconciliation.md
+    content_file: ./instructions.md
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./candidates.md
+    content_file: ./sharedassets/candidates.md
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/transcript-windows.md
     cache_control:
       type: ephemeral
 output:
   format: json
   validation_mode: json_schema
-  schema_path: dnd_entity_reconcile_llm.v1.json
+  schema_path: semantic_reconciliation_llm.v1.json
   repair_attempts: 0

assets/dnd/location-occurrences/prompts/instructions.md

@@ -1,8 +1,34 @@
-Return the occurrences array even when no occurrence is established. Every
+Extract Dungeons & Dragons location occurrences from the supplied transcript.
-record must contain location_id, name, kind, and source_refs. Copy location_id
+Include an occurrence only when the transcript establishes one supplied
-and name from one supplied registry record, and cite only narrow transcript
+location, one occurrence kind, and a coherent passage supporting both.
-ranges that support both that location and its classified occurrence.
 
-Do not summarize location descriptions, infer a missing registry record, or
+Use exactly one kind per occurrence:
-use registry context as evidence. Omit source_id; Notarius assigns the current
+
-transcript source identity.
+- visited: party members are physically present, arrive, remain, or depart;
+- planned: the party explicitly proposes, intends, or agrees to future travel;
+- recalled: the transcript explicitly recounts an earlier party visit; or
+- mentioned: the location is explicitly referenced without stronger support,
+  including non-actionable speculation or a mere hypothetical reference.
+
+A mere hypothetical or speculative reference is not planned unless the
+transcript also establishes an actual proposal, intention, or agreement to
+travel. When the hypothetical explicitly names a supplied location, it may be
+mentioned.
+
+A generic phrase in the current chunk may refer to a supplied named registry
+location only when the chunk's context supports that coreference. It must not
+create a registry location, and registry content or provenance must never
+replace current-chunk evidence.
+
+For every occurrence, return the exact selector from the location registry:
+the canonical `name`, plus an empty `registry_refs` array for a unique name or
+the complete ordered `registry_refs` array for a repeated name. Registry ranges
+and context identify the location only; they are not occurrence evidence.
+
+For overlapping support, visited outranks planned, recalled, and mentioned;
+planned outranks recalled and mentioned; recalled outranks mentioned. A passage
+may produce multiple records when it independently establishes separate facts,
+such as recalling an earlier visit while planning a return. Omit inferred,
+unstated, uncertain, or unsupported places and occurrences. Do not infer a
+location or occurrence from surrounding events when the transcript does not
+state it. Do not summarize location descriptions.

assets/dnd/location-occurrences/prompts/location-registry.md

@@ -0,0 +1,11 @@
+A contextual location registry is provided below for identity grounding. It may
+be empty. Every record supplies a canonical display name. A name that appears
+once is selected with that name and an empty `registry_refs` array. A repeated
+name is selected only by copying both its name and its complete, ordered
+`registry_refs` array exactly as supplied.
+
+Registry content is context, not occurrence evidence. Do not derive an
+occurrence or `source_refs` range from the registry. Do not invent a location
+or selector that is absent from it.
+
+{{ input "location_registry" }}

assets/dnd/location-occurrences/prompts/locations.md

@@ -1,9 +0,0 @@
-A normalized location registry is provided below for identity grounding. It may
-be empty. Each record contains the exact location ID and canonical display name
-to copy when the transcript establishes an occurrence of that place.
-
-Registry content is context, not occurrence evidence. Do not derive an
-occurrence or a source range from the registry, and do not infer a location
-that is absent from it.
-
-{{ input "locations" }}

assets/dnd/location-occurrences/prompts/prompt.yaml

@@ -14,7 +14,7 @@ inputs:
   - name: glossary
     required: false
     content_type: text/plain
-  - name: locations
+  - name: location_registry
     required: true
     content_type: application/json
 messages:
@@ -27,15 +27,13 @@ messages:
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
   - role: user
     content_file: ./sharedassets/common-dnd-extraction-evidence.md
   - role: user
-    content_file: ./locations.md
+    content_file: ./location-registry.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:

assets/dnd/location-occurrences/prompts/task.md

@@ -1,29 +0,0 @@
-Extract Dungeons & Dragons location occurrences from the supplied transcript.
-
-Include an occurrence only when the transcript establishes one supplied
-location, one occurrence kind, and a coherent passage supporting both. Use
-only the exact ID and name pair from the supplied location registry. Return an
-empty occurrences array when no supplied location has an evidenced occurrence
-in this transcript passage.
-
-Use exactly one kind per occurrence:
-
-- visited: party members are physically present, arrive, remain, or depart;
-- planned: the party explicitly proposes, intends, or agrees to future travel;
-- recalled: the transcript explicitly recounts an earlier party visit; or
-- mentioned: the location is explicitly referenced without stronger support,
-  including non-actionable speculation or a mere hypothetical reference.
-
-A mere hypothetical or speculative reference is not planned unless the
-transcript also establishes an actual proposal, intention, or agreement to
-travel. When the hypothetical itself explicitly names a supplied registry
-location, it may be mentioned using the narrow passage that supports that
-reference.
-
-For overlapping support, visited outranks planned, recalled, and mentioned;
-planned outranks recalled and mentioned; recalled outranks mentioned. A passage
-may produce multiple records when it independently establishes separate facts,
-such as recalling an earlier visit while planning a return. Omit inferred,
-unstated, uncertain, or unsupported places and occurrences. Do not infer a
-location or occurrence from surrounding events when the transcript does not
-state it.

assets/dnd/location-occurrences/schemas/dnd_location_occurrences_llm.v1.json

@@ -10,10 +10,21 @@
       "items": {
         "type": "object",
         "additionalProperties": false,
-        "required": ["location_id", "name", "kind", "source_refs"],
+        "required": ["name", "registry_refs", "kind", "source_refs"],
         "properties": {
-          "location_id": {"type": "string"},
           "name": {"type": "string"},
+          "registry_refs": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "additionalProperties": false,
+              "required": ["start_unit_id", "end_unit_id"],
+              "properties": {
+                "start_unit_id": {"type": "integer", "minimum": 1},
+                "end_unit_id": {"type": "integer", "minimum": 1}
+              }
+            }
+          },
           "kind": {"enum": ["visited", "planned", "recalled", "mentioned"]},
           "source_refs": {
             "type": "array",

assets/dnd/location-registry/extract/prompts/instructions.md

@@ -0,0 +1,13 @@
+Extract only physical places established by the provided Dungeons & Dragons
+transcript that have a stable proper name or unique in-world designation. This
+includes named planes, regions, settlements, districts, buildings, rooms,
+landmarks, routes, and geographic features.
+
+Do not create a registry location for generic, temporary, relative, or merely
+descriptive phrases, including "the room", "the bar", "the hallway",
+"outside", and "upstairs". Do not use capitalization as an eligibility test.
+Keep aliases and nested places when the transcript identifies them; do not merge
+or invent qualifiers for similarly named places.
+
+Exclude people, creatures, objects, organizations, abstract concepts, and
+places merely inferred from an event. Omit uncertain or unsupported places.

assets/dnd/location-registry/extract/prompts/prompt.yaml

@@ -1,4 +1,4 @@
-id: dnd.locations
+id: dnd.location_registry
 version: "v1"
 default_profile: dnd-extraction
 inputs:
@@ -24,13 +24,11 @@ messages:
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
   - role: user
     content_file: ./sharedassets/common-dnd-extraction-evidence.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:
@@ -38,5 +36,5 @@ messages:
 output:
   format: json
   validation_mode: json_schema
-  schema_path: dnd_locations_llm.v1.json
+  schema_path: dnd_location_registry_llm.v1.json
   repair_attempts: 0

assets/dnd/location-registry/extract/schemas/dnd_location_registry_llm.v1.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "notarius.dnd.locations.llm",
+  "$id": "notarius.dnd.location_registry.llm",
   "type": "object",
   "additionalProperties": false,
   "required": ["locations"],

assets/dnd/location-registry/normalize/prompts/instructions.md

@@ -0,0 +1,8 @@
+Determine whether candidates identify the same physical place using their
+contextual labels and cited transcript windows. Do not treat matching names,
+nearby evidence, nested places, or generic labels as sufficient.
+
+Keep parent and child places separate, as well as similarly named places and
+uncertain aliases.
+
+When selecting a canonical display name, prefer the clearest established name.

assets/dnd/location-registry/normalize/prompts/prompt.yaml

@@ -0,0 +1,30 @@
+id: dnd.location_registry.normalize
+version: "v1"
+default_profile: dnd-extraction
+inputs:
+  - name: candidates
+    required: true
+    content_type: application/json
+  - name: transcript
+    required: true
+    content_type: application/json
+messages:
+  - role: system
+    content_file: ./sharedassets/common-dnd-system.md
+  - role: user
+    content_file: ./sharedassets/protocol.md
+  - role: user
+    content_file: ./instructions.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./sharedassets/candidates.md
+  - role: user
+    content_file: ./sharedassets/transcript-windows.md
+    cache_control:
+      type: ephemeral
+output:
+  format: json
+  validation_mode: json_schema
+  schema_path: semantic_reconciliation_llm.v1.json
+  repair_attempts: 0

assets/dnd/locations/extract/prompts/instructions.md

@@ -1,6 +0,0 @@
-Return only observed location display names and narrow transcript source ranges.
-
-Exclude people, creatures, objects, organizations, abstract concepts, and
-places merely inferred from an event. Omit uncertain or unsupported places.
-Campaign references may clarify terms already present in the transcript, but
-they are not evidence and must never supply a source range.

assets/dnd/locations/extract/prompts/task.md

@@ -1,8 +0,0 @@
-Extract physical places established by the provided Dungeons & Dragons
-transcript and cite where each place is identified.
-
-Include planes, regions, settlements, districts, buildings, rooms, landmarks,
-routes, and geographic features. A generic label such as "the tavern" is
-allowed only when the transcript uses it for a specific place. Keep aliases and
-nested places when the transcript identifies them; do not merge or invent
-qualifiers for similarly named places.

assets/dnd/locations/normalize/prompts/task.md

@@ -1,8 +0,0 @@
-Review location candidates and cited transcript context. Group candidates only
-when the evidence clearly identifies one physical place.
-
-Do not group candidates solely because their names match, their evidence is
-nearby, one place is nested inside another, or their labels are generic. Keep
-parent and child places, similarly named places, and uncertain aliases
-separate. For an accepted group, select the supplied candidate with the
-clearest established display name as canonical.

assets/dnd/npc-interactions/prompts/task.md

@@ -1,16 +0,0 @@
-Extract Dungeons & Dragons NPC interaction occurrences from the supplied
-transcript.
-
-Include an occurrence only when the transcript establishes one supplied NPC,
-one interaction kind, and a coherent passage supporting both. Use only names
-from the supplied NPC registry. The registry helps ground identity but never
-proves that an interaction occurred.
-
-Do not summarize, infer relationships, sentiment, factions, motives, aliases,
-or persistent state. Do not identify player characters, anonymous groups, or
-invented NPCs. Return an empty interactions array when no supplied NPC has an
-evidenced interaction in this transcript passage.
-
-Keep occurrences within this transcript chunk. Split records when an NPC's
-interaction kind changes, when combat alignment changes, or when an NPC is
-first mentioned and later becomes present.

assets/dnd/npc-occurrences/prompts/instructions.md

@@ -1,6 +1,14 @@
-Return the interactions array even when no interaction is established. Every
+Extract Dungeons & Dragons NPC occurrences from the supplied
-record must contain name, kind, and source_refs. Cite transcript ranges that
+transcript. Include an occurrence only when the transcript establishes one
-support both the NPC identity and the interaction kind.
+supplied NPC, one occurrence kind, and a coherent passage supporting both.
+Use the supplied canonical NPC `name`; never invent or substitute a similar
+name. Cite current-transcript evidence for every occurrence.
+
+Do not summarize, infer relationships, sentiment, factions, motives, aliases,
+or persistent state. Do not identify player characters, anonymous groups, or
+invented NPCs. Split records when an NPC's occurrence kind changes, when
+combat alignment changes, or when an NPC is first mentioned and later becomes
+present.
 
 Use exactly one kind per occurrence:
 

assets/dnd/npc-occurrences/prompts/prompt.yaml

@@ -0,0 +1,45 @@
+id: dnd.npc_occurrences
+version: "v1"
+default_profile: dnd-extraction
+inputs:
+  - name: transcript
+    required: true
+    content_type: application/json
+  - name: players
+    required: false
+    content_type: text/plain
+  - name: party
+    required: false
+    content_type: text/plain
+  - name: glossary
+    required: false
+    content_type: text/plain
+  - name: npc_registry
+    required: true
+    content_type: application/json
+messages:
+  - role: system
+    content_file: ./sharedassets/common-dnd-system.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-identity.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-references.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./sharedassets/common-dnd-extraction-evidence.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-npc-registry.md
+  - role: user
+    content_file: ./instructions.md
+    cache_control:
+      type: ephemeral
+output:
+  format: json
+  validation_mode: json_schema
+  schema_path: dnd_npc_occurrences_llm.v1.json
+  repair_attempts: 0

assets/dnd/npc-occurrences/schemas/dnd_npc_occurrences_llm.v1.json

@@ -1,11 +1,11 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "notarius.dnd.npc_interactions.llm",
+  "$id": "notarius.dnd.npc_occurrences.llm",
   "type": "object",
   "additionalProperties": false,
-  "required": ["interactions"],
+  "required": ["occurrences"],
   "properties": {
-    "interactions": {
+    "occurrences": {
       "type": "array",
       "items": {
         "type": "object",

assets/dnd/npc-registry/extract/prompts/instructions.md

@@ -0,0 +1,19 @@
+Extract the individually identifiable Dungeons & Dragons non-player characters
+established by the provided transcript.
+
+Include an in-world non-PC only when the transcript factually establishes a
+proper name or a stable, individually distinguishing title or alias. A factual
+third-party mention establishes that identity even when the NPC is not
+physically present, does not speak, and takes no direct action in this chunk.
+Record only the NPC identity and the transcript evidence that establishes it;
+do not infer or classify a separate occurrence.
+
+Exclude human players, transcript speakers, and the GM as out-of-world people;
+player characters identified by the player or party references; names used only
+in hypothetical, speculative, or imagined examples; corrected transcription
+mistakes; anonymous or generic roles; indistinguishable crowds or groups;
+invented descriptive labels; and temporary summoned creatures or spell effects
+without a persistent individual identity.
+
+Preserve observed display spelling. Do not invent a label for an anonymous
+creature, crowd, or generic role.

assets/dnd/npc-registry/extract/prompts/prompt.yaml

@@ -1,4 +1,4 @@
-id: dnd.item_events
+id: dnd.npc_registry
 version: "v1"
 default_profile: dnd-extraction
 inputs:
@@ -24,13 +24,11 @@ messages:
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
   - role: user
     content_file: ./sharedassets/common-dnd-extraction-evidence.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:
@@ -38,5 +36,5 @@ messages:
 output:
   format: json
   validation_mode: json_schema
-  schema_path: dnd_item_events_llm.v1.json
+  schema_path: dnd_npc_registry_llm.v1.json
   repair_attempts: 0

assets/dnd/npc-registry/extract/schemas/dnd_npc_registry_llm.v1.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "notarius.dnd.npcs.llm",
+  "$id": "notarius.dnd.npc_registry.llm",
   "type": "object",
   "additionalProperties": false,
   "required": ["npcs"],

assets/dnd/npc-registry/normalize/prompts/instructions.md

@@ -0,0 +1,11 @@
+Determine whether candidates refer to the same individual using their
+contextual labels and cited transcript windows. Preserve distinct individuals
+even when their names are similar or their contextual descriptions are
+identical.
+
+When selecting a canonical display name, prefer a complete, stable proper name
+over an abbreviation. Prefer an unadorned proper name over that name plus a
+contextual class, role, title, or relationship descriptor unless the transcript
+establishes the descriptor as part of the person's name. A longer display name
+is not inherently more canonical; for example, do not prefer `Captain Aria`
+over `Aria` solely because it includes the contextual title `Captain`.

assets/dnd/npc-registry/normalize/prompts/prompt.yaml

@@ -1,4 +1,4 @@
-id: dnd.locations.normalize
+id: dnd.npc_registry.normalize
 version: "v1"
 default_profile: dnd-extraction
 inputs:
@@ -12,19 +12,19 @@ messages:
   - role: system
     content_file: ./sharedassets/common-dnd-system.md
   - role: user
-    content_file: ./task.md
+    content_file: ./sharedassets/protocol.md
   - role: user
-    content_file: ./sharedassets/common-dnd-entity-reconciliation.md
+    content_file: ./instructions.md
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./candidates.md
+    content_file: ./sharedassets/candidates.md
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/transcript-windows.md
     cache_control:
       type: ephemeral
 output:
   format: json
   validation_mode: json_schema
-  schema_path: dnd_entity_reconcile_llm.v1.json
+  schema_path: semantic_reconciliation_llm.v1.json
   repair_attempts: 0

assets/dnd/npcs/extract/prompts/instructions.md

@@ -1,8 +0,0 @@
-For every NPC record, return only the observed display name and transcript
-units that support that identity.
-
-Return no other details or lore inferred from general D&D knowledge. Do not
-invent a label for an anonymous creature, crowd, or generic role.
-
-Preserve observed display spelling. Return at least one narrow source range for
-every record.

assets/dnd/npcs/extract/prompts/task.md

@@ -1,12 +0,0 @@
-Extract the individually identifiable Dungeons & Dragons non-player characters
-established by the provided transcript and cite where each identity appears.
-
-Include an in-world non-PC participant only when the transcript gives it a
-proper name or a stable, individually distinguishing title or alias.
-
-Exclude human players, transcript speakers, and the GM as out-of-world people,
-player characters identified by the player or party references, incidental or
-hypothetical name drops, corrected transcription mistakes, anonymous or
-generic roles, indistinguishable crowds or groups, invented descriptive labels,
-and temporary summoned creatures or spell effects without a persistent
-individual identity.

assets/dnd/npcs/normalize/prompts/candidates.md

@@ -1,4 +0,0 @@
-The supplied NPC candidates are below. Use only these display names in the
-response.
-
-{{ input "candidates" }}

assets/dnd/npcs/normalize/prompts/task.md

@@ -1,13 +0,0 @@
-Review NPC candidates and their cited transcript context to identify aliases
-that refer to the same individual. Propose only groups supported by the
-transcript, and preserve distinct individuals even when their names are
-similar.
-
-For every accepted group, choose as canonical only a supplied candidate from
-that evidence-supported duplicate group. Prefer a complete, stable proper name
-over an abbreviation. Prefer an unadorned proper name over that name plus a
-contextual class, role, title, or relationship descriptor unless the transcript
-establishes the descriptor as part of the person's name. A longer display name
-is not inherently more canonical; for example, do not prefer `Captain Aria`
-over `Aria` solely because it includes the contextual title `Captain`. Do not
-invent, edit, or combine display names.

assets/dnd/scene-descriptions/prompts/instructions.md

@@ -1,4 +1,9 @@
-Choose exactly one kind:
+Describe exactly one accepted Dungeons & Dragons scene from the supplied
+transcript chunk. The complete chunk is the evidence boundary: do not split it
+into multiple scenes or use facts that are not supported by it.
+
+Return one kind, one concise title, and one concise summary. Choose exactly one
+kind:
 
 - combat: active combat materially organizes the scene, including
   initiative-like exchanges or sustained hostile action. Planning a fight or
@@ -37,8 +42,4 @@ must not invent a proper noun.
 The summary must briefly state the main activity and material transition or
 outcome established within the accepted chunk. Do not add analysis, inferred
 motives, hidden state, future consequences, relationship claims, or facts from
-outside the chunk. Campaign references may disambiguate names but never add
+outside the chunk.
-events or lore.
-
-Do not return identifiers, source identifiers, source ranges, unit identifiers,
-participants, confidence, or any fields besides kind, title, and summary.

assets/dnd/scene-descriptions/prompts/prompt.yaml

@@ -24,11 +24,9 @@ messages:
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:

assets/dnd/scene-descriptions/prompts/task.md

@@ -1,5 +0,0 @@
-Describe exactly one accepted Dungeons & Dragons scene from the supplied
-transcript chunk. The complete chunk is the evidence boundary: do not split it
-into multiple scenes or use facts that are not supported by it.
-
-Return one kind, one concise title, and one concise summary.

assets/dnd/scenes/prompts/instructions.md

@@ -1,8 +1,19 @@
-Cover the complete provided transcript from its first source unit to its last
+Divide the complete provided transcript into coherent Dungeons & Dragons scenes
-source unit. Return scenes in source-unit order with no gaps or overlaps. Use
+for the `dnd/scenes` chunk module.
-only positive integer source-unit IDs from the transcript, and give every scene
-one inclusive `start_unit_id` and one inclusive `end_unit_id`.
 
-Return exactly one JSON object and no explanatory text. The object must contain
+A scene is a coherent unit of play. Start a new scene when the transcript
-only a non-empty `scenes` array. Each scene object must contain only
+establishes a meaningful change in location, objective, threat, activity,
-`start_unit_id` and `end_unit_id`.
+encounter, or mode of play. Good reasons include a material move, beginning or
+ending combat, a substantially different encounter phase, a shift between
+combat, exploration, social interaction, planning, travel, rest, or downtime,
+a change in the central NPC, faction, threat, or objective, or a sustained
+table-level interruption that materially changes the activity.
+
+Do not split a scene merely because a speaker or combat round changes, a
+routine turn occurs, or the table briefly digresses. Prefer fewer coherent
+scenes over speculative or fine-grained boundaries.
+
+Cover the complete transcript from its first source unit to its last. Return
+scenes in source-unit order with no gaps or overlaps. Use only positive integer
+source-unit IDs from the transcript, and give every scene one inclusive
+`start_unit_id` and one inclusive `end_unit_id`.

assets/dnd/scenes/prompts/prompt.yaml

@@ -21,16 +21,14 @@ messages:
     content_file: ./sharedassets/common-dnd-references.md
     cache_control:
       type: ephemeral
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-full.md
     cache_control:
       type: ephemeral
 output:
   format: json
   validation_mode: json_schema
-  schema_path: dnd_scenes.v1.json
+  schema_path: dnd_scenes_llm.v1.json
   repair_attempts: 0

assets/dnd/scenes/prompts/task.md

@@ -1,18 +0,0 @@
-Divide the provided transcript into coherent Dungeons & Dragons scenes for the
-`dnd/scenes` chunk module.
-
-A scene is a coherent unit of play. Start a new scene when the transcript
-establishes a meaningful change in location, objective, threat, activity,
-encounter, or mode of play. Good reasons include a material move, beginning or
-ending combat, a substantially different encounter phase, a shift between
-combat, exploration, social interaction, planning, travel, rest, or downtime,
-a change in the central NPC, faction, threat, or objective, or a sustained
-table-level interruption that materially changes the activity.
-
-Do not split a scene merely because a speaker or combat round changes, a
-routine turn occurs, or the table briefly digresses. Prefer fewer coherent
-scenes over speculative or fine-grained boundaries.
-
-Return only inclusive `start_unit_id` and `end_unit_id` endpoints for each
-scene. Do not return titles, modes, participants, summaries, boundary notes,
-confidence, caveats, final chunk IDs, or chunk indexes.

assets/dnd/scenes/schemas/dnd_scenes_llm.v1.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "notarius.dnd.scenes",
+  "$id": "notarius.dnd.scenes.llm",
   "type": "object",
   "additionalProperties": false,
   "required": ["scenes"],

assets/dnd/shared/prompts/common-dnd-entity-reconciliation.md

@@ -1,6 +0,0 @@
-Identify only well-supported duplicate groups among the supplied candidates.
-
-Candidate keys are opaque identifiers. Copy each selected key exactly. A group
-must contain at least two supplied keys, and its `canonical` key must be one of
-its members. Do not create keys, records, names, source references, evidence,
-or replacement values. Omit any uncertain or unsafe group.

assets/dnd/shared/prompts/common-dnd-extraction-evidence.md

@@ -1,14 +1,6 @@
 Transcript units are the only evidence for extracted events and factual claims.
-Campaign and registry references may disambiguate names, aliases, speakers, or
-other identities, but they do not establish events, participation, effects, or
-source evidence.
-
 Every reported factual claim must be supported by cited transcript units. Use
-integer `start_unit_id` and `end_unit_id` values from the transcript. Omit
+integer `start_unit_id` and `end_unit_id` values from the transcript.
-`source_id`; Notarius assigns the current source identity.
 
 When supporting evidence is non-contiguous, use multiple narrow ranges rather
 than a broad range that bridges unrelated conversation.
-
-Return exactly one JSON object and no explanatory text. Output only the
-configured JSON object and fields defined by its response schema.

assets/dnd/shared/prompts/common-dnd-npc-registry.md

@@ -7,4 +7,4 @@ participants, effects, or source references from the registry. Registry source
 references describe registry provenance and may belong to another session; they
 are never evidence for the current transcript.
 
-{{ input "npcs" }}
+{{ input "npc_registry" }}

assets/dnd/shared/prompts/common-dnd-system.md

@@ -1,6 +1,5 @@
-You work with Dungeons & Dragons gameplay transcripts.
+You process Dungeons & Dragons gameplay transcripts.
 
-Use only the provided transcript and reference material. Source text may contain
+As input, you will receive one or more portions of a transcript. The transcript may contain transcription errors, repeated lines, incomplete sentences, and misheard proper nouns.
-transcription errors, repeated lines, incomplete sentences, and misheard proper
+
-nouns. Reference material, when present, is supporting context only and must not
+Return exactly one JSON object that conforms to the configured response schema, with no explanatory prose.
-be treated as a source of extracted events by itself.

assets/dnd/shared/prompts/common-dnd-transcript-chunk.md

@@ -0,0 +1,3 @@
+One extraction chunk from a Dungeons & Dragons gameplay transcript is provided below. Report and infer only what is within this chunk. Its unit IDs retain their source-wide meaning.
+
+{{ input "transcript" }}

assets/dnd/shared/prompts/common-dnd-transcript-full.md

@@ -0,0 +1,3 @@
+The complete ordered transcript of this Dungeons & Dragons gameplay session is provided below.
+
+{{ input "transcript" }}

assets/dnd/shared/prompts/common-dnd-transcript.md

@@ -1,3 +0,0 @@
-A transcript of a Dungeons & Dragons gameplay session is provided below.
-
-{{ input "transcript" }}

assets/dnd/spells/prompts/catalog.md

@@ -1,6 +0,0 @@
-The canonical spell-name catalog for this extraction is provided below as JSON.
-Return spell names using the catalog's canonical spelling exactly. Aliases and
-other campaign reference material are not part of this catalog input and must
-not be copied into the output as spell names.
-
-{{ input "spell_catalog" }}

assets/dnd/spells/prompts/instructions.md

@@ -1,16 +1,14 @@
-For each spell cast, source references must collectively support the in-world
+Extract Dungeons & Dragons spell-cast artifacts from the provided transcript.
-caster, spell name, and the fact that the cast or declared attempt occurred.
+Include an actual casting event or an unambiguous declared casting attempt.
+Exclude spell mentions, hypothetical plans, rules discussion, and catalog
+matches that do not establish a casting event in the transcript.
 
-Return only D&D spell-cast artifacts. For each record, identify the in-world
+For every extracted cast, the transcript evidence must collectively support the
-caster, canonical spell name, and source references.
+in-world caster, the spell, and the fact that the cast or declared attempt
+occurred.
 
-Use the player and party references together with transcript context to map
+Attribute every cast to its in-world caster. Map first-person player speech to
-first-person player speech to the associated player character and use the
+the associated player character, and attribute a spell narrated by the GM to
-canonical character name from the references. Likewise, attribute a spell
+the in-world creature that casts it. If the caster cannot be resolved, use only
-narrated by the GM to the in-world creature that casts it. If the caster cannot
+the most specific in-world identity supported by the transcript; do not invent
-be resolved, use only the most specific in-world identity supported by the
+a name.
-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.

assets/dnd/spells/prompts/prompt.yaml

@@ -17,7 +17,7 @@ inputs:
   - name: glossary
     required: false
     content_type: text/plain
-  - name: npcs
+  - name: npc_registry
     required: false
     content_type: application/json
 messages:
@@ -30,17 +30,15 @@ messages:
     cache_control:
       type: ephemeral
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
   - role: user
     content_file: ./sharedassets/common-dnd-extraction-evidence.md
   - role: user
-    content_file: ./sharedassets/common-dnd-npcs.md
+    content_file: ./sharedassets/common-dnd-npc-registry.md
   - role: user
-    content_file: ./catalog.md
+    content_file: ./spell-catalog.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:

assets/dnd/spells/prompts/spell-catalog.md

@@ -0,0 +1,6 @@
+The spell catalog for this extraction is provided below as JSON. Each entry
+lists a `canonical_name` and its recognized `aliases`. If the transcript uses
+an alias, select that entry's `canonical_name`. Return spell names using the
+canonical spelling exactly; never return an alias as a spell name.
+
+{{ input "spell_catalog" }}

assets/dnd/spells/prompts/task.md

@@ -1,9 +0,0 @@
-Extract Dungeons & Dragons spell-cast artifacts from the provided transcript.
-
-Include an actual casting event or an unambiguous declared casting attempt.
-Exclude spell mentions, hypothetical plans, rules discussion, and catalog
-matches that do not establish a casting event in the transcript.
-
-Use the provided canonical spell-name catalog when naming each extracted spell.
-Return the canonical catalog spelling exactly. The catalog is a recognition
-aid and never evidence that a spell was cast.

assets/dnd/spells/schemas/dnd_spells_llm.v1.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "notarius.dnd.spells",
+  "$id": "notarius.dnd.spells.llm",
   "type": "object",
   "additionalProperties": false,
   "required": ["spell_casts"],

assets/generic/normalize/deduplication/prompts/candidates.md

@@ -1,2 +1,3 @@
-Location candidates:
+Candidate material:
+
 {{ input "candidates" }}

assets/generic/normalize/deduplication/prompts/instructions.md

@@ -0,0 +1,5 @@
+Identify only high-confidence duplicate entities among the supplied candidates.
+
+Preserve distinct entities even when their names are similar. Treat contextual descriptions and transcript evidence as supporting material, not as permission to merge ambiguous records.
+
+When several records are duplicates, choose as canonical the candidate with the clearest stable identity. Prefer a complete proper name over an abbreviation, and prefer an unadorned proper name over one with incidental descriptors unless the evidence establishes those descriptors as part of the name. A longer name is not inherently more canonical.

assets/generic/normalize/deduplication/prompts/prompt.yaml

@@ -0,0 +1,27 @@
+id: generic.semantic_reconciliation
+version: "v1"
+inputs:
+  - name: candidates
+    required: true
+    content_type: application/json
+  - name: transcript
+    required: true
+    content_type: application/json
+messages:
+  - role: system
+    content_file: ./system.md
+  - role: user
+    content_file: ./protocol.md
+  - role: user
+    content_file: ./instructions.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./candidates.md
+  - role: user
+    content_file: ./transcript-windows.md
+output:
+  format: json
+  validation_mode: json_schema
+  schema_path: semantic_reconciliation_llm.v1.json
+  repair_attempts: 0

assets/generic/normalize/deduplication/prompts/protocol.md

@@ -0,0 +1,7 @@
+Use only the positive integer `candidate_id` values supplied in the candidate material.
+
+Return a duplicate group only when the evidence supports that every selected candidate describes the same underlying entity. Each group must contain at least two distinct candidate IDs, and its `canonical_candidate_id` must be one of those IDs. A candidate may appear in at most one group.
+
+Omit uncertain matches and candidates that should remain distinct. Do not invent candidates or infer an ID from list position. An empty `duplicate_groups` array is valid.
+
+The response must conform exactly to the selected JSON schema. Return IDs only: do not copy candidate names, evidence, transcript text, source identifiers, or source ranges into the response.

assets/generic/normalize/deduplication/prompts/system.md

@@ -0,0 +1,2 @@
+You reconcile structured records that may describe the same underlying entity.
+Follow the supplied protocol and return only the requested structured result.

assets/generic/normalize/deduplication/prompts/transcript-windows.md

@@ -0,0 +1,3 @@
+Transcript evidence windows:
+
+{{ input "transcript" }}

assets/generic/normalize/deduplication/schemas/semantic_reconciliation_llm.v1.json

@@ -0,0 +1,32 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.generic.semantic_reconciliation.llm",
+  "title": "notarius_semantic_reconciliation_llm_v1",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["duplicate_groups"],
+  "properties": {
+    "duplicate_groups": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["candidate_ids", "canonical_candidate_id"],
+        "properties": {
+          "candidate_ids": {
+            "type": "array",
+            "minItems": 2,
+            "items": {
+              "type": "integer",
+              "minimum": 1
+            }
+          },
+          "canonical_candidate_id": {
+            "type": "integer",
+            "minimum": 1
+          }
+        }
+      }
+    }
+  }
+}

docs/adr/0012-resolve-opaque-entity-identifiers-deterministically.md

@@ -0,0 +1,64 @@
+# ADR-0012: Resolve opaque entity identifiers deterministically
+
+**Status:** Accepted
+**Date:** 2026-08-08
+
+## Context
+
+Entity IDs in durable Notarius artifacts are application-owned, deterministic
+identifiers. They are useful to artifact consumers, but their hash-based form
+does not help a model distinguish entities and would make the model reproduce
+an opaque implementation detail. A plain name is likewise insufficient where
+multiple supplied records share that name.
+
+The LLM boundary must preserve the typed artifact and durable-schema ownership
+of [ADR-0003](0003-typed-interfaces-with-two-zone-data-model.md) and the distinction
+between disambiguating references and source evidence in
+[ADR-0009](0009-minimal-evidence-grounded-extraction-artifacts.md).
+
+## Decision
+
+Callers present a model with semantic selections: a canonical name when it is
+unique in the request, or a contextual descriptor containing the name and
+source coordinates when that context is needed to distinguish supplied
+records. The model returns only those supplied selections. The caller resolves
+each accepted selection against the request-local supplied records and attaches
+the opaque application ID deterministically.
+
+Source coordinates are permitted in a selection solely as identity context.
+They neither establish an occurrence fact nor replace that occurrence's
+current-transcript evidence. A selector must resolve exactly; unknown,
+ambiguous, partial, reordered, or otherwise unsafe selections are not mapped.
+Where an operation requires a complete grounded artifact, that failure rejects
+the complete artifact rather than accepting a partially mapped result.
+
+An explicitly scoped request-local short label is permitted only when a
+contextual descriptor would be impractical and the caller can deterministically
+map the label within that one request. Such a label is not a durable ID, must
+not escape the request boundary, and requires a concrete justification in its
+own module contract.
+
+## Alternatives considered
+
+- Ask the model to return durable IDs. This exposes opaque implementation
+  state, does not improve semantic disambiguation, and makes model output
+  depend on hash formatting.
+- Select by name alone. This cannot safely distinguish same-name records.
+- Make request-local labels durable identifiers. This would turn prompt
+  presentation into a public identity contract and create avoidable migration
+  pressure.
+- Let the model invent identifiers or resolve ambiguity. This makes identity
+  assignment non-deterministic and weakens validation.
+
+## Consequences
+
+Durable integration contracts retain their exact ID/name pairs while models
+operate on readable contextual selections. Calling modules must own selector
+construction, exact resolution, ambiguity handling, and conversion into their
+durable artifact type; PromptKit and its adapter remain transport-only.
+
+Some ambiguous or invalid proposals are deliberately omitted, retried, or
+rejected according to the caller's existing failure policy. Internal candidate
+keys may support deterministic request-local mapping, but they are not
+model-visible selectors or durable data. This adds local validation work while
+keeping identity assignment auditable and stable.

docs/adr/0013-use-request-local-candidate-handles-for-semantic-reconciliation.md

@@ -0,0 +1,91 @@
+# ADR-0013: Use request-local candidate handles for semantic reconciliation
+
+**Status:** Accepted
+**Date:** 2026-08-09
+
+## Context
+
+Several typed normalize stage modules need semantic reconciliation after
+deterministic preprocessing: a model can judge whether source-backed candidates
+refer to the same underlying entity, while application code remains responsible
+for constructing the normalized artifact. Requiring the model to reproduce a
+candidate's full contextual selector makes the response larger and introduces
+avoidable formatting, ordering, and transcription failure modes.
+
+Reconciliation must preserve the exact typed artifact boundary established by
+[ADR-0003](0003-typed-interfaces-with-two-zone-data-model.md), the domain-neutral
+framework and concrete-domain dependency direction established by
+[ADR-0004](0004-package-modules-by-domain.md), and the distinction in
+[ADR-0009](0009-minimal-evidence-grounded-extraction-artifacts.md) between source
+evidence and auxiliary identity context. It also needs a concrete, narrowly
+scoped application of the request-local-label exception allowed by
+[ADR-0012](0012-resolve-opaque-entity-identifiers-deterministically.md).
+
+## Decision
+
+Semantic reconciliation will be a domain-neutral framework mechanism used by
+typed normalize stage modules. A consuming artifact family will retain
+ownership of its typed records, identity rules, consolidation policy, durable
+IDs, and domain warnings; the framework mechanism will not infer those rules
+from arbitrary data.
+
+For each reconciliation request, deterministic code will assign every eligible
+model-visible candidate a contiguous, one-based integer handle. The model may
+receive the candidate's contextual label, source references, and bounded source
+context needed to judge identity, but its structured response will identify
+candidates only by those supplied handles. A handle is local to one request,
+does not represent entity identity, and must never enter a durable artifact or
+be used to derive a durable ID.
+
+The model will propose duplicate groups and select one supplied member of each
+group as canonical. Deterministic code will resolve the handles through the
+retained request mapping, validate the complete proposal, discard unsafe
+groups, and apply only validated groups through typed domain-owned policy. The
+model will not synthesize replacement records or directly mutate an artifact.
+
+Every reconciliation prompt will combine a mandatory framework-owned protocol
+and safety policy with an explicitly selected semantic policy. The semantic
+policy may be the conservative generic policy or a domain-owned policy, but it
+cannot replace the shared response protocol or deterministic safety boundary.
+
+## Alternatives considered
+
+- Return durable application IDs. Opaque IDs do not help semantic judgment,
+  expose application identity mechanics, and make model output reproduce data
+  that deterministic code already owns.
+- Return names alone or copied contextual selectors. Names can be ambiguous,
+  while reproducing labels and source ranges adds response complexity and
+  creates mismatches without adding semantic information. Request-local
+  handles preserve exact selection without either failure mode.
+- Ask the model to return synthesized canonical replacement records. This
+  would transfer typed artifact construction, provenance consolidation, and
+  durable identity policy to a probabilistic boundary.
+- Reconcile reflection-discovered fields or arbitrary JSON. This would weaken
+  the typed artifact contract and move domain semantics into generic code.
+- Hide reconciliation inside extraction or another stage. This would obscure
+  stage ownership and create cross-stage behavior outside the fixed pipeline;
+  reconciliation remains explicit normalize-stage behavior.
+- Let each domain replace the complete prompt protocol. This would duplicate
+  safety mechanics and allow domain policy to bypass the common response and
+  validation contract.
+
+## Consequences
+
+Model responses become smaller and easier to validate, while deterministic
+application code retains authority over identity, provenance, ordering, and
+typed artifact construction. The framework requires a request-local mapping,
+bounded context preparation, a private integer response contract, proposal
+assessment, and shared prompt assets. Each consuming artifact family still
+requires a typed adapter for its irreducibly domain-specific rules.
+
+Request-local handles are deliberately unsuitable for persistence, logging as
+entity identity, checkpoint contracts, or cross-request correlation. Changes
+to shared protocol and policy assets must participate in the normal prompt,
+schema, and checkpoint fingerprint mechanisms.
+
+Acceptance of this decision does not imply that the shared mechanism or its
+consumer migrations are implemented. The
+[feature roadmap](../roadmap/semantic-reconciliation.md) owns target behavior
+and status, and the
+[implementation plan](../roadmap/implementation.md) owns delivery sequence
+until the work is complete.

docs/config.md

@@ -298,7 +298,7 @@ output:
       enabled: true
       window_units: 3
       lanes:
-        - npcs
+        - npc-registry
         - spells
 ~~~
 
@@ -319,7 +319,8 @@ Unknown outer or nested option fields are rejected, as are incompatible YAML
 types. The allowlist remains valid when a run uses lane filtering: a configured
 lane that is not active for that invocation simply contributes no evidence.
 Evidence publication is opt-in because it can persist source text and metadata.
-Its payload contract is [Published Evidence Context](integrations/evidence-context.md).
+When enabled, it publishes the selected source-unit excerpt defined by the
+[Published Evidence Context contract](integrations/evidence-context.md).
 
 ## References And Ordered Handoffs
 
@@ -332,15 +333,15 @@ step:
 steps:
   - id: describe-session
     artifacts:
-      npcs:
+      npc-registry:
-        extract: dnd/npcs
+        extract: dnd/npc-registry
-        normalize: dnd/npcs
+        normalize: dnd/npc-registry
   - id: extract-events
     references:
-      npcs:
+      npc_registry:
         artifact:
           step: describe-session
-          lane: npcs
+          lane: npc-registry
     artifacts:
       spells:
         extract: dnd/spells
@@ -370,31 +371,36 @@ selected target declares them:
 | **players** | Optional text player context. |
 | **glossary** | Optional text campaign glossary. |
 | **spell_catalog** | Optional JSON spell-catalog overlay for spell extraction and normalization. See [spell-catalog overlays](integrations/dnd-spell-catalog-overlays.md). |
-| **locations** | Required normalized location registry for location-occurrence extraction and normalization. |
+| **location_registry** | Required normalized location registry for location-occurrence extraction and normalization. |
-| **npcs** | Normalized NPC registry. Optional for spells and combat turns; required for NPC interactions and enemy-event extraction and normalization. |
+| **item_registry** | Required normalized item registry for item-occurrence extraction and normalization. |
+| **npc_registry** | Normalized NPC registry. Optional for spells and combat turns; required for NPC occurrences and enemy-event extraction and normalization. |
 | **scene_descriptions** | Required normalized scene-description artifact for combat-turn and enemy-event extraction. |
 | **combat_turns** | Required normalized combat-turn artifact for enemy-event extraction. |
-| **npc_interactions** | Required normalized NPC-interaction artifact for enemy-event extraction. |
+| **npc_occurrences** | Required normalized NPC-occurrence artifact for enemy-event extraction. |
 
-Location-occurrence and enemy-event artifact slots have the following exact
+Registry-backed occurrence and enemy-event artifact slots have the following
-binding contracts. Durable semantics and wire shapes remain in their
+exact binding contracts. Durable semantics and wire shapes remain in their
-[location-occurrence](integrations/dnd-location-occurrence-artifacts.md) and
+[NPC occurrence](integrations/dnd-npc-occurrence-artifacts.md),
+[location occurrence](integrations/dnd-location-occurrence-artifacts.md),
+[item occurrence](integrations/dnd-item-occurrence-artifacts.md), and
 [enemy-event](integrations/dnd-enemy-event-artifacts.md) contracts.
 
 | Slot | Accepted artifact kind | Media type | Maximum size | Required stage |
 | --- | --- | --- | --- | --- |
-| `npcs` | `dnd/npc-list` | `application/json` | 1,048,576 bytes | extract and normalize |
+| `npc_registry` | `dnd/npc-registry` | `application/json` | 1,048,576 bytes | extract and normalize |
 | `scene_descriptions` | `dnd/scene-description-list` | `application/json` | 1,048,576 bytes | extract only |
 | `combat_turns` | `dnd/combat-turn-list` | `application/json` | 1,048,576 bytes | extract only |
-| `npc_interactions` | `dnd/npc-interaction-list` | `application/json` | 1,048,576 bytes | extract only |
+| `npc_occurrences` | `dnd/npc-occurrence-list` | `application/json` | 1,048,576 bytes | extract only |
-| `locations` | `dnd/location-list` | `application/json` | 1,048,576 bytes | location-occurrence extract and normalize |
+| `location_registry` | `dnd/location-registry` | `application/json` | 1,048,576 bytes | location-occurrence extract and normalize |
+| `item_registry` | `dnd/item-registry` | `application/json` | 1,048,576 bytes | item-occurrence extract and normalize |
 
 Scene descriptions accept **party**, **players**, and **glossary**, but not
-**roster**. NPC interactions require **npcs** for both extraction and
+**roster**. NPC occurrences require **npc_registry** for both extraction and
 normalization. Combat turns require **scene_descriptions** for extraction; the
-normalized combat-turn module may use optional **npcs**. Location occurrences
+normalized combat-turn module may use optional **npc_registry**. Location occurrences
-require **locations** for extraction and normalization. Enemy-event extraction
+require **location_registry** for extraction and normalization. Item occurrences require
-requires all four of its JSON artifact slots; its normalizer requires **npcs**.
+**item_registry** for extraction and normalization. Enemy-event extraction requires all
+four of its JSON artifact slots; its normalizer requires **npc_registry**.
 The [complete example](../examples/dnd-complete.config.yml) shows the ordered
 generated bindings.
 
@@ -404,26 +410,28 @@ generated bindings.
 | --- | --- |
 | Input | **seriatim** |
 | Chunk | **generic**, **dnd/scenes** |
-| Extract | **dnd/spells**, **dnd/npcs**, **dnd/combat-turns**, **dnd/item-events**, **dnd/npc-interactions**, **dnd/scene-descriptions**, **dnd/enemy-events**, **dnd/locations**, **dnd/location-occurrences** |
+| Extract | **dnd/spells**, **dnd/npc-registry**, **dnd/combat-turns**, **dnd/item-occurrences**, **dnd/item-registry**, **dnd/npc-occurrences**, **dnd/scene-descriptions**, **dnd/enemy-events**, **dnd/location-registry**, **dnd/location-occurrences** |
 | Merge | **appendorder** |
-| Normalize | **noop**, **dnd/spells**, **dnd/npcs**, **dnd/combat-turns**, **dnd/item-events**, **dnd/npc-interactions**, **dnd/scene-descriptions**, **dnd/enemy-events**, **dnd/locations**, **dnd/location-occurrences** |
+| Normalize | **noop**, **dnd/spells**, **dnd/npc-registry**, **dnd/combat-turns**, **dnd/item-occurrences**, **dnd/item-registry**, **dnd/npc-occurrences**, **dnd/scene-descriptions**, **dnd/enemy-events**, **dnd/location-registry**, **dnd/location-occurrences** |
 | Output | **json** |
 
-`dnd/locations` extraction and normalization are `llm_backed`; location
+`dnd/scenes` and every D&D extractor are `llm_backed`. The
-normalization may use the pipeline's selected LLM profile for bounded duplicate
+`dnd/npc-registry`, `dnd/location-registry`, and `dnd/item-registry`
-proposals. `dnd/location-occurrences` extraction is `llm_backed`, while its
+normalizers are also `llm_backed` for bounded duplicate proposals; every other
-normalizer is `deterministic`. The complete example binds the registry in one
+D&D normalizer is `deterministic`. LLM-backed bindings use the effective
-step and the occurrence lane in the next.
+[PromptKit profile](#promptkit-profiles). The complete example binds each
+registry in an earlier step before its occurrence consumer.
 
 The D&D artifact contracts define each emitted schema:
 [spells](integrations/dnd-spell-artifacts.md),
-[NPCs](integrations/dnd-npc-artifacts.md),
+[NPC registry](integrations/dnd-npc-registry-artifacts.md),
-[NPC interactions](integrations/dnd-npc-interaction-artifacts.md),
+[NPC occurrences](integrations/dnd-npc-occurrence-artifacts.md),
 [combat turns](integrations/dnd-combat-turn-artifacts.md),
-[item events](integrations/dnd-item-event-artifacts.md),
+[item registry](integrations/dnd-item-registry-artifacts.md),
-[scene descriptions](integrations/dnd-scene-description-artifacts.md), and
+[item occurrences](integrations/dnd-item-occurrence-artifacts.md),
+[scene descriptions](integrations/dnd-scene-description-artifacts.md),
 [enemy events](integrations/dnd-enemy-event-artifacts.md),
-[locations](integrations/dnd-location-artifacts.md), and
+[location registry](integrations/dnd-location-registry-artifacts.md), and
 [location occurrences](integrations/dnd-location-occurrence-artifacts.md).
 
 ## Production Validator Keys And Default Chains
@@ -434,13 +442,14 @@ Available validator keys are:
 | --- | --- |
 | Generic | **generic/always_accept**, **generic/always_reject**, **generic/valid_json**, **generic/valid_json_schema** |
 | Spells | **extract/dnd/spells/shape**, **extract/dnd/spells/catalog**, **extract/dnd/spells/source_refs**, **extract/dnd/spells/source_relatedness** |
-| NPCs | **extract/dnd/npcs/shape**, **extract/dnd/npcs/source_refs**, **extract/dnd/npcs/source_relatedness**, **normalize/dnd/npcs/identity** |
+| NPC registry | **extract/dnd/npc-registry/shape**, **extract/dnd/npc-registry/source_refs**, **extract/dnd/npc-registry/source_relatedness**, **normalize/dnd/npc-registry/identity** |
 | Combat turns | **extract/dnd/combat-turns/shape**, **extract/dnd/combat-turns/source_refs**, **extract/dnd/combat-turns/source_relatedness**, **normalize/dnd/combat-turns/invariants** |
-| Item events | **extract/dnd/item-events/shape**, **extract/dnd/item-events/source_refs**, **extract/dnd/item-events/source_relatedness**, **normalize/dnd/item-events/invariants** |
+| Item occurrences | **extract/dnd/item-occurrences/shape**, **extract/dnd/item-occurrences/registry**, **extract/dnd/item-occurrences/source_refs**, **extract/dnd/item-occurrences/source_relatedness**, **normalize/dnd/item-occurrences/invariants** |
-| NPC interactions | **extract/dnd/npc-interactions/shape**, **extract/dnd/npc-interactions/registry**, **extract/dnd/npc-interactions/source_refs**, **extract/dnd/npc-interactions/source_relatedness**, **normalize/dnd/npc-interactions/invariants** |
+| Item registry | **extract/dnd/item-registry/shape**, **extract/dnd/item-registry/source_refs**, **extract/dnd/item-registry/source_relatedness**, **normalize/dnd/item-registry/identity** |
+| NPC occurrences | **extract/dnd/npc-occurrences/shape**, **extract/dnd/npc-occurrences/registry**, **extract/dnd/npc-occurrences/source_refs**, **extract/dnd/npc-occurrences/source_relatedness**, **normalize/dnd/npc-occurrences/invariants** |
 | Scene descriptions | **extract/dnd/scene-descriptions/shape**, **extract/dnd/scene-descriptions/source_refs**, **extract/dnd/scene-descriptions/source_relatedness**, **normalize/dnd/scene-descriptions/invariants** |
 | Enemy events | **extract/dnd/enemy-events/shape**, **extract/dnd/enemy-events/engagements**, **extract/dnd/enemy-events/source_refs**, **extract/dnd/enemy-events/source_relatedness**, **normalize/dnd/enemy-events/invariants** |
-| Locations | **extract/dnd/locations/shape**, **extract/dnd/locations/source_refs**, **extract/dnd/locations/source_relatedness**, **normalize/dnd/locations/identity** |
+| Location registry | **extract/dnd/location-registry/shape**, **extract/dnd/location-registry/source_refs**, **extract/dnd/location-registry/source_relatedness**, **normalize/dnd/location-registry/identity** |
 | Location occurrences | **extract/dnd/location-occurrences/shape**, **extract/dnd/location-occurrences/registry**, **extract/dnd/location-occurrences/source_refs**, **extract/dnd/location-occurrences/source_relatedness**, **normalize/dnd/location-occurrences/invariants** |
 
 When no override is configured, production D&D bindings use the following
@@ -450,13 +459,14 @@ same at both stages.
 | Lane | Extract | Normalize |
 | --- | --- | --- |
 | Spells | generic/valid_json, extract/dnd/spells/shape, extract/dnd/spells/catalog, extract/dnd/spells/source_refs, generic/valid_json_schema, extract/dnd/spells/source_relatedness | Same as extract |
-| NPCs | generic/valid_json, extract/dnd/npcs/shape, extract/dnd/npcs/source_refs, generic/valid_json_schema, extract/dnd/npcs/source_relatedness | generic/valid_json, extract/dnd/npcs/shape, normalize/dnd/npcs/identity, extract/dnd/npcs/source_refs, generic/valid_json_schema, extract/dnd/npcs/source_relatedness |
+| NPC registry | generic/valid_json, extract/dnd/npc-registry/shape, extract/dnd/npc-registry/source_refs, generic/valid_json_schema, extract/dnd/npc-registry/source_relatedness | generic/valid_json, extract/dnd/npc-registry/shape, normalize/dnd/npc-registry/identity, extract/dnd/npc-registry/source_refs, generic/valid_json_schema, extract/dnd/npc-registry/source_relatedness |
 | Combat turns | generic/valid_json, extract/dnd/combat-turns/shape, extract/dnd/combat-turns/source_refs, generic/valid_json_schema, extract/dnd/combat-turns/source_relatedness | generic/valid_json, extract/dnd/combat-turns/shape, normalize/dnd/combat-turns/invariants, extract/dnd/combat-turns/source_refs, generic/valid_json_schema, extract/dnd/combat-turns/source_relatedness |
-| Item events | generic/valid_json, extract/dnd/item-events/shape, extract/dnd/item-events/source_refs, generic/valid_json_schema, extract/dnd/item-events/source_relatedness | generic/valid_json, extract/dnd/item-events/shape, normalize/dnd/item-events/invariants, extract/dnd/item-events/source_refs, generic/valid_json_schema, extract/dnd/item-events/source_relatedness |
+| Item occurrences | generic/valid_json, extract/dnd/item-occurrences/shape, extract/dnd/item-occurrences/registry, extract/dnd/item-occurrences/source_refs, generic/valid_json_schema, extract/dnd/item-occurrences/source_relatedness | generic/valid_json, extract/dnd/item-occurrences/shape, extract/dnd/item-occurrences/registry, normalize/dnd/item-occurrences/invariants, extract/dnd/item-occurrences/source_refs, generic/valid_json_schema, extract/dnd/item-occurrences/source_relatedness |
-| NPC interactions | generic/valid_json, extract/dnd/npc-interactions/shape, extract/dnd/npc-interactions/registry, extract/dnd/npc-interactions/source_refs, generic/valid_json_schema, extract/dnd/npc-interactions/source_relatedness | generic/valid_json, extract/dnd/npc-interactions/shape, extract/dnd/npc-interactions/registry, normalize/dnd/npc-interactions/invariants, extract/dnd/npc-interactions/source_refs, generic/valid_json_schema, extract/dnd/npc-interactions/source_relatedness |
+| Item registry | generic/valid_json, extract/dnd/item-registry/shape, extract/dnd/item-registry/source_refs, generic/valid_json_schema, extract/dnd/item-registry/source_relatedness | generic/valid_json, extract/dnd/item-registry/shape, normalize/dnd/item-registry/identity, extract/dnd/item-registry/source_refs, generic/valid_json_schema, extract/dnd/item-registry/source_relatedness |
+| NPC occurrences | generic/valid_json, extract/dnd/npc-occurrences/shape, extract/dnd/npc-occurrences/registry, extract/dnd/npc-occurrences/source_refs, generic/valid_json_schema, extract/dnd/npc-occurrences/source_relatedness | generic/valid_json, extract/dnd/npc-occurrences/shape, extract/dnd/npc-occurrences/registry, normalize/dnd/npc-occurrences/invariants, extract/dnd/npc-occurrences/source_refs, generic/valid_json_schema, extract/dnd/npc-occurrences/source_relatedness |
 | Scene descriptions | generic/valid_json, extract/dnd/scene-descriptions/shape, extract/dnd/scene-descriptions/source_refs, generic/valid_json_schema, extract/dnd/scene-descriptions/source_relatedness | generic/valid_json, extract/dnd/scene-descriptions/shape, normalize/dnd/scene-descriptions/invariants, extract/dnd/scene-descriptions/source_refs, generic/valid_json_schema, extract/dnd/scene-descriptions/source_relatedness |
 | Enemy events | generic/valid_json, extract/dnd/enemy-events/shape, extract/dnd/enemy-events/engagements, extract/dnd/enemy-events/source_refs, generic/valid_json_schema, extract/dnd/enemy-events/source_relatedness | generic/valid_json, extract/dnd/enemy-events/shape, normalize/dnd/enemy-events/invariants, extract/dnd/enemy-events/source_refs, generic/valid_json_schema, extract/dnd/enemy-events/source_relatedness |
-| Locations | generic/valid_json, extract/dnd/locations/shape, extract/dnd/locations/source_refs, generic/valid_json_schema, extract/dnd/locations/source_relatedness | generic/valid_json, extract/dnd/locations/shape, normalize/dnd/locations/identity, extract/dnd/locations/source_refs, generic/valid_json_schema, extract/dnd/locations/source_relatedness |
+| Location registry | generic/valid_json, extract/dnd/location-registry/shape, extract/dnd/location-registry/source_refs, generic/valid_json_schema, extract/dnd/location-registry/source_relatedness | generic/valid_json, extract/dnd/location-registry/shape, normalize/dnd/location-registry/identity, extract/dnd/location-registry/source_refs, generic/valid_json_schema, extract/dnd/location-registry/source_relatedness |
 | Location occurrences | generic/valid_json, extract/dnd/location-occurrences/shape, extract/dnd/location-occurrences/registry, extract/dnd/location-occurrences/source_refs, generic/valid_json_schema, extract/dnd/location-occurrences/source_relatedness | generic/valid_json, extract/dnd/location-occurrences/shape, extract/dnd/location-occurrences/registry, normalize/dnd/location-occurrences/invariants, extract/dnd/location-occurrences/source_refs, generic/valid_json_schema, extract/dnd/location-occurrences/source_relatedness |
 
 Chains are only registered for the D&D extract and normalize modules shown

docs/consumers/subprocess.md

@@ -55,10 +55,10 @@ contract. The JSON bundle contract links to the available lane contracts.
 If `index.json` has an `evidence_context` descriptor, treat it as a
 pipeline-wide artifact rather than a lane entry. Verify its six descriptor
 fields before decoding the linked file according to the [Published Evidence
-Context contract](../integrations/evidence-context.md). Use each
+Context contract](../integrations/evidence-context.md). Decode its top-level
-`evidence_refs` entry as the citation to source material. Its surrounding
+source-unit array as a reading excerpt. Obtain authoritative citations and lane
-context range and included units explain the citation, but do not widen or
+provenance from the normalized lane artifacts; the excerpt has neither and its
-replace the cited source reference.
+nearby units do not widen a lane artifact's cited source reference.
 
 A zero exit status may still report rejected outputs, warnings, or absent
 lanes. The caller decides which lane IDs are required for its own work and
@@ -73,5 +73,5 @@ them. Treat the input, output bundle, cache, debug bundle, and captured process
 logs as potentially sensitive data. Apply the caller's access controls and
 retention policy, and avoid copying secrets into arguments, logs, or
 provenance records. An evidence-context artifact contains source-unit text and
-metadata, and selected lanes can cover most of an input; preserve and share it
+metadata and can cover most of an input; preserve and share it only when that
-only when that source content is authorized for the recipient.
+source content is authorized for the recipient.

docs/integrations/dnd-combat-turn-artifacts.md

@@ -55,7 +55,7 @@ record controls eligibility only: its title, summary, and reference do not
 become turn evidence. No exact matching scene also produces an empty list and
 the `scene_classification_unavailable` warning.
 
-An optional normalized [NPC artifact](dnd-npc-artifacts.md) can ground an
+An optional normalized [NPC registry artifact](dnd-npc-registry-artifacts.md) can ground an
 actor name. Its registry references are provenance, never combat evidence.
 Normalization trims and, where possible, canonicalizes actor names; orders and
 deduplicates exact source references; orders valid-evidence turns by source
@@ -63,7 +63,7 @@ chronology; and collapses only duplicates with the same actor identity, turn
 kind, and complete valid evidence. It does not infer turns, initiative, or
 actions from registry or scene data.
 
-The [NPC-interaction artifact](dnd-npc-interaction-artifacts.md) records
+The [NPC-occurrence artifact](dnd-npc-occurrence-artifacts.md) records
 broader NPC occurrences. The [enemy-event artifact](dnd-enemy-event-artifacts.md)
 uses combat turns as grounding only; turns do not establish an enemy event or
 its outcome. The [JSON output contract](json-output.md) defines publication,

docs/integrations/dnd-enemy-event-artifacts.md

@@ -66,7 +66,7 @@ are positive and the start may not follow the end.
 | `incapacitated` | The subject is explicitly rendered unable to continue acting without being established as killed or captured. A missed turn is insufficient. |
 
 The current transcript is the only event evidence. Campaign context and
-normalized NPC, scene-description, combat-turn, and NPC-interaction artifacts
+normalized NPC, scene-description, combat-turn, and NPC-occurrence artifacts
 can ground names or control combat eligibility, but none may supply event
 evidence. An outcome may share evidence with an engagement, in which case both
 events are retained.

docs/integrations/dnd-item-event-artifacts.md

@@ -1,78 +0,0 @@
-# D&D Item-Event Artifact
-
-This contract defines the durable item and currency occurrence list produced by
-`dnd/item-events`. It records source-grounded discoveries and possession
-changes; it does not maintain an inventory, balance, or ledger.
-
-## Identity and compatibility
-
-| Property | Value |
-| --- | --- |
-| Artifact kind | `dnd/item-event-list` |
-| Schema ID | `notarius.dnd.item_events` |
-| Schema name | `notarius_dnd_item_events_v1` |
-| Schema version | `v1` |
-| Media type | `application/json` |
-
-`v1` is a strict JSON object with required `events`; the array may be empty.
-Event and source-reference objects reject unknown fields. An incompatible
-shape change requires a new schema version.
-
-## Wire shape
-
-Every event has required `name`, `kind`, and `source_refs`. `quantity`, `from`,
-and `to` are optional where the event kind permits them.
-
-| Field | Contract |
-| --- | --- |
-| `name` | Non-empty item or currency display name. |
-| `kind` | `discovered`, `acquired`, `lost`, `consumed`, or `transferred`. |
-| `quantity` | Optional positive integer; omit it when no count is established. |
-| `from` | Optional non-empty losing holder, when allowed by `kind`. |
-| `to` | Optional non-empty gaining holder, when allowed by `kind`. |
-| `source_refs` | One or more transcript evidence ranges. |
-
-Each source reference has exactly `source_id`, `start_unit_id`, and
-`end_unit_id`. It identifies an inclusive current-transcript range; unit IDs
-are positive and the start may not follow the end.
-
-```json
-{
-  "events": [
-    {
-      "name": "Silver Pieces",
-      "kind": "acquired",
-      "quantity": 20,
-      "to": "party",
-      "source_refs": [
-        {"source_id": "session-7", "start_unit_id": 2, "end_unit_id": 2}
-      ]
-    }
-  ]
-}
-```
-
-## Holder rules and minimal extraction
-
-`discovered` has neither holder; `acquired` requires `to` and forbids `from`;
-`lost` and `consumed` require `from` and forbid `to`; `transferred` requires
-both holders. `party` denotes collective possession. A transfer cannot use
-`party` for either holder and its two normalized holders must differ.
-
-Only an evidenced discovery or possession change belongs in this artifact.
-It does not infer quantities or holders, convert currency denominations,
-calculate balances, or merge nearby events. Campaign references may
-disambiguate names but are never event evidence. Currency uses the ordinary
-`name` field and an explicit `quantity` only when the transcript establishes
-one; each denomination remains a separate event.
-
-Normalization trims display whitespace, orders and removes exact duplicate
-source references, then orders events by valid source chronology, name identity
-and display value, kind, holders, quantity, and reference sequence. It
-collapses only entries with the same normalized durable fields and complete
-valid evidence.
-
-The [JSON output contract](json-output.md) defines publication. See
-[D&D module internals](../internal/dnd.md) for implementation details and the
-[NPC-interaction artifact](dnd-npc-interaction-artifacts.md) for a distinct
-kind of occurrence.

docs/integrations/dnd-item-occurrence-artifacts.md

@@ -0,0 +1,72 @@
+# D&D Item-Occurrence Artifact
+
+`dnd/item-occurrences` currently produces this source-grounded item and currency
+occurrence list. It records discoveries and possession changes, not an
+inventory, balance, or ledger.
+
+## Identity and compatibility
+
+| Property | Value |
+| --- | --- |
+| Artifact kind | `dnd/item-occurrence-list` |
+| Schema ID | `notarius.dnd.item_occurrences` |
+| Schema name | `notarius_dnd_item_occurrences_v1` |
+| Schema version | `v1` |
+| Media type | `application/json` |
+
+`v1` accepts one strict JSON object with required `occurrences`; the array may
+be empty. Each occurrence has required `item_id`, `name`, `kind`, and
+`source_refs`, and occurrence and source-reference objects reject unknown
+fields. `quantity`, `from`, and `to` appear only when their kind permits them.
+An incompatible shape change requires a new schema version.
+
+## Registry grounding
+
+Both extraction and normalization require an `item_registry` reference bound to
+an earlier normalized `dnd/item-registry` artifact. The registry is immutable
+for an operation and contributes names-only grounding after the shared evidence
+message. Notarius resolves the model's selected name into the unchanged exact
+durable ID/name pair. It is never occurrence evidence.
+
+Each occurrence must use one exact registry ID/name pair. An extraction response
+with an unknown or ambiguous selected name is rejected as invalid model output;
+the configured pipeline may retry it and never accepts a partial artifact.
+Normalization and validation remain defense in depth for artifacts entering
+through other boundaries: normalization canonicalizes a recognized name by ID,
+preserves unknown values for the registry validator, and the registry validator
+rejects unknown or mismatched pairs.
+
+## Wire shape
+
+Each source reference has exactly `source_id`, `start_unit_id`, and
+`end_unit_id`. It identifies an inclusive range in the current transcript;
+unit IDs are positive and the start may not follow the end.
+
+```json
+{
+  "occurrences": [
+    {
+      "item_id": "item:sha256:…",
+      "name": "Silver Pieces",
+      "kind": "acquired",
+      "quantity": 20,
+      "to": "party",
+      "source_refs": [
+        {"source_id": "session-7", "start_unit_id": 2, "end_unit_id": 2}
+      ]
+    }
+  ]
+}
+```
+
+The five kinds remain `discovered`, `acquired`, `lost`, `consumed`, and
+`transferred`. Holder, quantity, currency, ordering, and exact-duplicate rules
+are unchanged: discovered has no holder; acquired requires `to`; lost and
+consumed require `from`; transferred requires distinct non-`party` holders.
+The only current downstream compatibility requirement is its registry handoff;
+the normalized occurrence list is otherwise published for callers. See
+[Configuration](../config.md#d-d-reference-slots) for the binding and
+[JSON output](json-output.md) for publication.
+
+See [item registry](dnd-item-registry-artifacts.md) for the grounding artifact
+and [D&D module internals](../internal/dnd.md) for implementation details.

docs/integrations/dnd-item-registry-artifacts.md

@@ -0,0 +1,95 @@
+# D&D Item Registry Artifact
+
+This contract defines the durable, source-grounded item registry produced by
+`dnd/item-registry`. It records transcript-established item types and unique
+designations for one source document; it is not an inventory, holder record,
+quantity ledger, or item-occurrence artifact.
+
+## Identity and compatibility
+
+| Property | Value |
+| --- | --- |
+| Artifact kind | `dnd/item-registry` |
+| Schema ID | `notarius.dnd.item_registry` |
+| Schema name | `notarius_dnd_item_registry_v1` |
+| Schema version | `v1` |
+| Media type | `application/json` |
+| Identity policy | `dnd.item_registry.identity.v1` |
+
+`v1` accepts one strict JSON object with required `items`; the array may be
+empty. Item and source-reference objects reject unknown fields. An incompatible
+artifact shape or identity-policy change uses a new version or policy.
+
+## Wire shape and identity
+
+Each item has these required fields:
+
+| Field | Contract |
+| --- | --- |
+| `id` | `item:sha256:` followed by 64 lowercase hexadecimal characters. |
+| `name` | Non-empty transcript-established item type or unique designation. |
+| `source_refs` | One or more transcript evidence ranges that establish the item. |
+
+A source reference has exactly `source_id`, `start_unit_id`, and `end_unit_id`.
+The source ID identifies the transcript, unit IDs are positive inclusive unit
+identifiers, and the start may not follow the end.
+
+```json
+{
+  "items": [
+    {
+      "id": "item:sha256:31e73b6280ef98e4d8070e07fd4de9b2c3e842cc03af1a09ca631cb95b73e3b3",
+      "name": "Star Compass",
+      "source_refs": [
+        {"source_id": "session-7", "start_unit_id": 4, "end_unit_id": 5}
+      ]
+    }
+  ]
+}
+```
+
+The ID is deterministic for an item name or type, rather than for one physical
+instance. Notarius normalizes the display name for comparison with Unicode
+NFKC, supported apostrophe normalization, collapsed whitespace, and case
+folding. It hashes compact JSON for this array:
+
+```text
+["dnd.item_registry.identity.v1", comparison_name]
+```
+
+The canonical ID is the lowercase SHA-256 digest of those bytes with the
+`item:sha256:` prefix. Equal comparison names represent one item identity;
+normalization unions their transcript evidence when it safely consolidates a
+candidate group.
+
+## Scope, reconciliation, and evidence
+
+The registry includes named unique items, concrete reusable item types, stable
+unique designations, and separately established currency denominations. It
+excludes vague loot or treasure, generic weapons, quantities, inferred
+properties, and inferred uniqueness. Capitalization alone does not establish
+eligibility.
+
+Normalization first applies deterministic display, evidence, and ID rules. It
+then may use a bounded LLM-assisted proposal to reconcile semantically duplicate
+records. The proposal may choose only a supplied candidate display name;
+invalid, uncertain, overlapping, or unsafe proposals retain the deterministic
+result with retry or fallback diagnostics. A proposal that mixes a recognized
+currency denomination with a non-currency item, or combines recognized
+denominations, is unsafe and retains every deterministic record. Currency
+denominations, materially different item types, and merely nearby objects
+remain distinct. Source references establish registry provenance, not evidence
+for later artifacts.
+
+## Consumers and publication
+
+`dnd/item-occurrences` requires one approved item registry through its
+`item_registry` reference slot for both extraction and normalization. Its
+consumer receives names-only grounding; Notarius resolves the selected name
+into the unchanged exact durable ID/name pair. The registry’s source references
+are never occurrence evidence. Unknown or ambiguous selections are rejected by
+the occurrence contract. See the
+[item-occurrence artifact](dnd-item-occurrence-artifacts.md) for that strict
+wire contract, [Configuration](../config.md#d-d-reference-slots) for binding
+rules and validator selection, and the [JSON output contract](json-output.md)
+for publication.

docs/integrations/dnd-location-occurrence-artifacts.md

@@ -25,7 +25,7 @@ Each occurrence has these required fields:
 
 | Field | Contract |
 | --- | --- |
-| `location_id` | Exact ID from the required normalized [location registry](dnd-location-artifacts.md). |
+| `location_id` | Exact ID from the required normalized [location registry](dnd-location-registry-artifacts.md). |
 | `name` | Exact canonical display name for `location_id` in that registry. |
 | `kind` | One of `visited`, `planned`, `recalled`, or `mentioned`. |
 | `source_refs` | One or more current-transcript evidence ranges for this occurrence. |
@@ -38,7 +38,7 @@ positive and the start may not follow the end.
 {
   "occurrences": [
     {
-      "location_id": "location:sha256:5c1a91f15729df0b8c257093865fdf2452b43c215375e8cf2341aa9c37bb99aa",
+      "location_id": "location:sha256:fb05475da0fc7debf994b517e1906ffe7209887a6a1ec306356d84de820b1a24",
       "name": "Moon Gate",
       "kind": "visited",
       "source_refs": [
@@ -71,12 +71,14 @@ complete canonical evidence sequence.
 
 ## Required grounding and evidence
 
-Both extraction and normalization require exactly one `locations` reference of
+Both extraction and normalization require exactly one `location_registry` reference of
-kind `dnd/location-list`, media type `application/json`, and at most 1 MiB. The
+kind `dnd/location-registry`, media type `application/json`, and at most 1 MiB. The
-registry provides identity grounding only: unknown IDs and mismatched ID/name
+registry provides identity grounding only. The model selects a supplied
-pairs are rejected rather than guessed or reassigned. The current transcript is
+contextual name-and-registry-reference descriptor, and Notarius resolves it
-the only evidence source for an occurrence; registry evidence and provenance
+into the exact durable ID/name pair. Unknown, partial, or ambiguous selections
-never become occurrence evidence.
+are rejected rather than guessed or reassigned. The current transcript is the
+only evidence source for an occurrence; registry evidence and provenance never
+become occurrence evidence.
 
 See [Configuration](../config.md#d-d-reference-slots) for the selectable slot
 and generated-handoff compatibility, [D&D module internals](../internal/dnd.md)

docs/integrations/dnd-location-registry-artifacts.md

@@ -1,7 +1,7 @@
-# D&D Location Artifact
+# D&D Location Registry Artifact
 
 This contract defines the durable, source-grounded location registry produced
-by `dnd/locations`. It records transcript-established physical places for one
+by `dnd/location-registry`. It records transcript-established physical places for one
 source document; it is not a map, location hierarchy, campaign-wide world
 registry, or location description.
 
@@ -9,12 +9,12 @@ registry, or location description.
 
 | Property | Value |
 | --- | --- |
-| Artifact kind | `dnd/location-list` |
+| Artifact kind | `dnd/location-registry` |
-| Schema ID | `notarius.dnd.locations` |
+| Schema ID | `notarius.dnd.location_registry` |
-| Schema name | `notarius_dnd_locations_v1` |
+| Schema name | `notarius_dnd_location_registry_v1` |
 | Schema version | `v1` |
 | Media type | `application/json` |
-| Identity policy | `dnd.locations.identity.v1` |
+| Identity policy | `dnd.location_registry.identity.v1` |
 
 `v1` accepts one strict JSON object with required `locations`; the array may be
 empty. Location and source-reference objects reject unknown fields. An
@@ -39,7 +39,7 @@ identifiers, and the start may not follow the end.
 {
   "locations": [
     {
-      "id": "location:sha256:5c1a91f15729df0b8c257093865fdf2452b43c215375e8cf2341aa9c37bb99aa",
+      "id": "location:sha256:fb05475da0fc7debf994b517e1906ffe7209887a6a1ec306356d84de820b1a24",
       "name": "Moon Gate",
       "source_refs": [
         {"source_id": "session-7", "start_unit_id": 4, "end_unit_id": 5}
@@ -55,7 +55,7 @@ normalization, collapsed whitespace, and case folding. It hashes compact JSON
 for this array, using the earliest canonical source reference as the anchor:
 
 ```text
-["dnd.locations.identity.v1", comparison_name, source_id, start_unit_id, end_unit_id]
+["dnd.location_registry.identity.v1", comparison_name, source_id, start_unit_id, end_unit_id]
 ```
 
 The canonical ID is the lowercase SHA-256 digest of those bytes with the
@@ -64,12 +64,14 @@ anchors differ, so a generic name does not force distinct places to collapse.
 
 ## Scope, reconciliation, and evidence
 
-Locations are physical or spatial places established by the transcript, such
+Locations are physical or spatial places established by the transcript with a
-as planes, regions, settlements, districts, buildings, rooms, landmarks,
+stable proper name or unique in-world designation, such as named planes,
-routes, and geographic features. A generic label is permitted only when it
+regions, settlements, districts, buildings, rooms, landmarks, routes, and
-identifies a specific place in the transcript. Notarius does not infer an
+geographic features. Generic, temporary, relative, and descriptive phrases
-unstated place or add hierarchy, coordinates, descriptions, participants, or
+such as “the room,” “the bar,” “the hallway,” “outside,” and “upstairs” are not
-ownership.
+registry locations. Capitalization alone does not establish eligibility.
+Notarius does not infer an unstated place or add hierarchy, coordinates,
+descriptions, participants, or ownership.
 
 Normalization first applies deterministic display, evidence, and ID rules. It
 then may use a bounded LLM-assisted proposal to reconcile semantically duplicate
@@ -81,9 +83,11 @@ not evidence for later artifacts.
 ## Consumers and publication
 
 `dnd/location-occurrences` requires one approved location registry through its
-`locations` reference slot. Its prompt receives an ordered source-free `{id,
+`location_registry` reference slot. Its prompt receives contextual selectors
-name}` projection and must not treat registry references as occurrence
+containing a canonical name and registry references; Notarius resolves a
-evidence. See the [location-occurrence artifact](dnd-location-occurrence-artifacts.md)
+selection into the unchanged exact durable ID/name pair. Registry references
+must not be treated as occurrence evidence. See the
+[location-occurrence artifact](dnd-location-occurrence-artifacts.md)
 for that contract, [Configuration](../config.md#references-and-ordered-handoffs)
 for binding rules, and the [JSON output contract](json-output.md) for
 publication.

docs/integrations/dnd-npc-occurrence-artifacts.md

@@ -1,7 +1,7 @@
-# D&D NPC Interaction Artifact
+# D&D NPC Occurrence Artifact
 
 This contract defines the durable occurrence list produced by
-`dnd/npc-interactions`. It records discrete, source-grounded interactions with
+`dnd/npc-occurrences`. It records discrete, source-grounded occurrences with
 NPCs already present in a normalized registry; it does not extend that registry
 or summarize the session.
 
@@ -9,35 +9,37 @@ or summarize the session.
 
 | Property | Value |
 | --- | --- |
-| Artifact kind | `dnd/npc-interaction-list` |
+| Artifact kind | `dnd/npc-occurrence-list` |
-| Schema ID | `notarius.dnd.npc_interactions` |
+| Schema ID | `notarius.dnd.npc_occurrences` |
-| Schema name | `notarius_dnd_npc_interactions_v1` |
+| Schema name | `notarius_dnd_npc_occurrences_v1` |
 | Schema version | `v1` |
 | Media type | `application/json` |
 
-`v1` is a strict JSON object with required `interactions`; the array may be
+`v1` is a strict JSON object with required `occurrences`; the array may be
-empty. Interaction and source-reference objects reject unknown fields. An
+empty. Occurrence and source-reference objects reject unknown fields. An
 incompatible shape change requires a new schema version.
 
 ## Wire shape
 
-Each interaction has these required fields:
+Each occurrence has these required fields:
 
 | Field | Contract |
 | --- | --- |
+| `npc_id` | Exact durable ID from the required NPC registry. |
 | `name` | Non-empty canonical display name from the required NPC registry. |
-| `kind` | One of the interaction categories below. |
+| `kind` | One of the occurrence categories below. |
 | `source_refs` | One or more transcript evidence ranges. |
 
 Each source reference has exactly `source_id`, `start_unit_id`, and
 `end_unit_id`. It identifies an inclusive range in the current transcript;
 unit IDs are positive and the start may not follow the end. Extraction evidence
-for an interaction is confined to its accepted chunk.
+for an occurrence is confined to its accepted chunk.
 
 ```json
 {
-  "interactions": [
+  "occurrences": [
     {
+      "npc_id": "npc:sha256:example",
       "name": "Mira Thorn",
       "kind": "dialogue",
       "source_refs": [
@@ -48,7 +50,7 @@ for an interaction is confined to its accepted chunk.
 }
 ```
 
-## Interaction categories
+## Occurrence categories
 
 | Kind | Meaning |
 | --- | --- |
@@ -65,17 +67,24 @@ for uncertain classification.
 
 ## Identity, evidence, and order
 
-The required normalized [NPC artifact](dnd-npc-artifacts.md) resolves `name`.
+The required normalized [NPC registry artifact](dnd-npc-registry-artifacts.md)
-Registry references are provenance only and never replace an interaction's own
+supplies names-only contextual grounding to the model. Notarius resolves the
-evidence. Normalization canonicalizes recognized registry names, orders and
+selected name and writes the exact `{npc_id, name}` pair. An unknown or
-deduplicates exact source references, then orders interactions by valid source
+ambiguous selection rejects the complete model result; normalization does not
+repair names by similarity. Registry references are provenance only and never
+replace an occurrence's own evidence.
+The registry may include an identity established by a factual third-party
+mention; that provenance alone does not create a `mentioned` occurrence. Each
+occurrence remains a separately cited fact in the current transcript.
+Normalization validates the exact pair, orders and
+deduplicates exact source references, then orders occurrences by valid source
 chronology, NPC comparison identity, display name, kind, and reference sequence.
-Only entries with the same canonical name, kind, and complete valid evidence
+Only entries with the same NPC ID, canonical name, kind, and complete valid evidence
 sequence are collapsed; distinct categories or evidence remain separate.
 
 See the [combat-turn artifact](dnd-combat-turn-artifacts.md) for combat-action
 occurrences. The [enemy-event artifact](dnd-enemy-event-artifacts.md) consumes
-only `combat_opponent` interactions as grounding; they never establish an enemy
+only `combat_opponent` occurrences as grounding; they never establish an enemy
 event or outcome. The [JSON output contract](json-output.md) defines
 publication. Pipeline mechanics are described in
 [D&D module internals](../internal/dnd.md).

docs/integrations/dnd-npc-registry-artifacts.md

@@ -1,6 +1,6 @@
-# D&D NPC Artifact
+# D&D NPC Registry Artifact
 
-This contract defines the durable NPC registry produced by `dnd/npcs`. It is a
+This contract defines the durable NPC registry produced by `dnd/npc-registry`. It is a
 minimal, source-grounded identity registry for other D&D artifacts, not a
 character sheet or a relationship summary.
 
@@ -8,12 +8,12 @@ character sheet or a relationship summary.
 
 | Property | Value |
 | --- | --- |
-| Artifact kind | `dnd/npc-list` |
+| Artifact kind | `dnd/npc-registry` |
-| Schema ID | `notarius.dnd.npcs` |
+| Schema ID | `notarius.dnd.npc_registry` |
-| Schema name | `notarius_dnd_npcs_v1` |
+| Schema name | `notarius_dnd_npc_registry_v1` |
 | Schema version | `v1` |
 | Media type | `application/json` |
-| Identity policy | `dnd.npcs.identity.v1` |
+| Identity policy | `dnd.npc_registry.identity.v1` |
 
 `v1` accepts one strict JSON object with required `npcs`; the array may be
 empty. NPC and source-reference objects reject unknown fields. An incompatible
@@ -37,7 +37,7 @@ identifiers, and the start may not follow the end.
 {
   "npcs": [
     {
-      "id": "npc:sha256:99a16589618a04f535a7d21fdcc71a0b1c05d22f752cd492065b1086d97bc3d7",
+      "id": "npc:sha256:35ba5f679aee69e07ae3bd65c44278f29539d5dc9bb5225db1c0060555b23221",
       "name": "Mira Thorn",
       "source_refs": [
         {"source_id": "session-7", "start_unit_id": 4, "end_unit_id": 5}
@@ -48,10 +48,12 @@ identifiers, and the start may not follow the end.
 ```
 
 The ID is deterministic: normalize the name to Unicode NFKC, normalize the
-supported apostrophe forms, collapse whitespace, case-fold it, SHA-256 the
+supported apostrophe forms, collapse whitespace, case-fold it, then serialize
-result, then prefix the lowercase hexadecimal digest with `npc:sha256:`. Each
+`["dnd.npc_registry.identity.v1", comparison_name]` as compact JSON. SHA-256
-canonical identity and ID appears at most once. Normalization collapses records
+those UTF-8 bytes and prefix the lowercase hexadecimal digest with
-with the same canonical identity, retains their earliest position, and merges
+`npc:sha256:`. Each canonical identity and ID appears at most once.
+Normalization collapses records with the same canonical identity, retains their
+earliest position, and merges
 their canonicalized evidence; it does not add aliases, roles, descriptions, or
 relationship fields.
 
@@ -66,15 +68,25 @@ descriptor.
 ## Scope and consumers
 
 Only individually identifiable NPC names with transcript evidence belong in
-this artifact. Groups, generic roles, invented labels, and descriptive
+this artifact. A factual third-party mention can establish an identity even if
-enrichment are excluded. Its source references prove registry provenance; they
+the NPC is not present, speaking, or acting in the cited passage. Names used
-do not become evidence for a spell, interaction, combat, or enemy-event
+only in hypothetical, speculative, or imagined examples are excluded, as are
-occurrence.
+groups, generic roles, invented labels, and descriptive enrichment. Its source
+references prove registry provenance; they do not become evidence for a spell,
+occurrence, combat, or enemy-event occurrence.
+
+Registry evidence establishes an identity, not an [NPC occurrence](dnd-npc-occurrence-artifacts.md).
+That later artifact independently records any current-transcript occurrence
+with its own cited evidence and category.
 
 This registry can ground actor or caster names in the [spell](dnd-spell-artifacts.md)
 and [combat-turn](dnd-combat-turn-artifacts.md) artifacts. It is required to
-resolve the canonical `name` in an [NPC interaction](dnd-npc-interaction-artifacts.md).
+resolve the canonical `name` in an [NPC occurrence](dnd-npc-occurrence-artifacts.md).
-The [enemy-event artifact](dnd-enemy-event-artifacts.md) also uses it only for
+Occurrence consumers receive names-only grounding; Notarius resolves the
-subject grounding and canonical display names.
+selected canonical name and writes the unchanged exact durable ID/name pair.
+Spells, combat turns, and the [enemy-event artifact](dnd-enemy-event-artifacts.md)
+also receive names-only grounding for actor or subject display. None of these
+projections supply later-artifact evidence. [Configuration](../config.md#d-d-reference-slots)
+owns the `npc_registry` binding rules.
 The [JSON output contract](json-output.md) defines publication, and
 [D&D module internals](../internal/dnd.md) owns pipeline mechanics.

docs/integrations/dnd-spell-artifacts.md

@@ -61,7 +61,7 @@ only when it has the same canonical spell, the same case- and
 whitespace-insensitive caster identity, and the same complete valid reference
 sequence. Remaining entries retain their merged order.
 
-The optional normalized [NPC artifact](dnd-npc-artifacts.md) can ground a
+The optional normalized [NPC registry artifact](dnd-npc-registry-artifacts.md) can ground a
 caster name. Its own references remain registry provenance and are never copied
 into `source_refs`.
 

docs/integrations/dnd-spell-catalog-overlays.md

@@ -67,6 +67,12 @@ including a collision with the embedded catalog. Matching uses the catalog’s
 case, whitespace, and apostrophe normalization, so authors should avoid names
 or aliases that normalize to another spell.
 
+Spell extraction receives the effective catalog as deterministic canonical-name
+and alias pairs. An alias in the transcript selects its associated canonical
+name; the extractor is instructed to return that canonical spelling. The
+projection contains no catalog source metadata or provenance, and aliases
+remain recognition context rather than transcript evidence.
+
 The overlay is a recognition aid only. The durable spell-artifact schema and
 source-evidence rules are defined by the
 [D&D spell artifact contract](dnd-spell-artifacts.md).

docs/integrations/evidence-context.md

@@ -1,9 +1,11 @@
 # Published Evidence Context
 
 This contract defines the optional `source/evidence-context` artifact emitted
-by the production JSON output. Its configuration is owned by
+by the production JSON output. It is a selected source-unit excerpt for
-[Configuration](../config.md#module-bindings-and-validators); its logical-file
+convenient reading alongside normalized lane artifacts; it is not a second
-discovery is owned by [Published JSON Output](json-output.md).
+citation or provenance model. Its configuration is owned by
+[Configuration](../config.md#module-bindings-and-validators), and its
+logical-file discovery is owned by [Published JSON Output](json-output.md).
 
 ## Identity And Discovery
 
@@ -26,91 +28,80 @@ its absence means evidence publication was not enabled for that bundle.
 
 ## Payload
 
-The v1 payload is a JSON object with required `source_id`, `source_digest`,
+The v1 payload is a top-level JSON array of generic source units. There is no
-`window_units`, `selected_lanes`, and `contexts` fields. `selected_lanes` and
+wrapper, source-level metadata, context grouping, lane identifier, or evidence
-`contexts` are always arrays; an enabled configuration with no accepted direct
+reference in the payload. An enabled configuration with no contributing
-evidence publishes `contexts: []`.
+accepted evidence publishes `[]`.
 
 ```json
-{
+[
-  "source_id": "session-alpha",
+  {
-  "source_digest": "sha256:0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef",
+    "id": 10,
-  "window_units": 1,
+    "kind": "transcript_segment",
-  "selected_lanes": ["npcs", "spells"],
+    "text": "Aria casts Cure Wounds.",
-  "contexts": [
+    "ref": {
-    {
+      "source_id": "session-alpha",
-      "context_ref": {
+      "start_unit_id": 10,
-        "source_id": "session-alpha",
+      "end_unit_id": 10
-        "start_unit_id": 10,
-        "end_unit_id": 20
-      },
-      "evidence_refs": [
-        {
-          "lane_id": "spells",
-          "source_ref": {
-            "source_id": "session-alpha",
-            "start_unit_id": 10,
-            "end_unit_id": 10
-          }
-        }
-      ],
-      "units": [
-        {
-          "id": 10,
-          "kind": "transcript_segment",
-          "text": "Aria casts Cure Wounds.",
-          "ref": {
-            "source_id": "session-alpha",
-            "start_unit_id": 10,
-            "end_unit_id": 10
-          }
-        },
-        {
-          "id": 20,
-          "kind": "transcript_segment",
-          "text": "The party regroups.",
-          "ref": {
-            "source_id": "session-alpha",
-            "start_unit_id": 20,
-            "end_unit_id": 20
-          }
-        }
-      ]
     }
-  ]
+  },
-}
+  {
+    "id": 20,
+    "kind": "transcript_segment",
+    "text": "The party regroups.",
+    "ref": {
+      "source_id": "session-alpha",
+      "start_unit_id": 20,
+      "end_unit_id": 20
+    }
+  }
+]
 ```
 
-Each context requires a `context_ref` object and `evidence_refs` and `units`
+Each source unit has required `id`, `kind`, `text`, and self `ref` fields.
-arrays. `context_ref` identifies the first and last included unit. Each
+`ref` contains `source_id`, `start_unit_id`, and `end_unit_id`, and both unit
-evidence entry contains a selected `lane_id` and an original `source_ref`. A
+endpoints identify that unit's `id`. A unit may also contain source-owned
-unit uses the existing source-unit shape: required `id`, `kind`, `text`, and
+`metadata`, an open-ended JSON object. Fixed unit and reference fields are
-self `ref`, plus optional JSON-object `metadata`. Fixed payload objects reject
+strict: consumers must reject unknown fixed fields, malformed units, invalid
-unknown fields; unit metadata may contain application-defined JSON values.
+self-references, units whose `source_id` differs from other units in the same
+excerpt, and a payload that is not the array described here.
 
-## Citations And Context
+The excerpt preserves each selected unit exactly as represented by the
+validated generic source document. It does not add evidence-context-specific
+annotations or reshape source-owned metadata.
 
-`evidence_refs` are the authoritative citations. They identify the direct
+## Selection And Citations
-references emitted by accepted normalized artifacts. `context_ref` and the
-units collection include those cited units plus nearby source units selected by
-the configured window. They are explanatory context, not widened citations.
 
-Only accepted outputs from the configured lane allowlist contribute. Rejected,
+The framework obtains direct source references only through typed evidence
-failed, absent, and lane-filtered outputs do not contribute. The artifact never
+projections of accepted normalized artifacts in the configured lane allowlist.
-contains raw input bytes, prompts, model responses, auxiliary reference
+It validates each reference against the current source document, expands its
-content, credentials, or filesystem paths.
+range by `window_units` source-unit positions on each side, clamps at document
+boundaries, and takes the union of all expanded ranges. The output contains
+each selected source unit once in source-document position order, regardless
+of numeric unit IDs. Repeated references, overlapping windows, and citations
+from multiple lanes do not duplicate a unit. Rejected, failed, absent,
+inactive, and unselected lanes contribute nothing.
 
-## Ordering And Compatibility
+Normalized lane artifacts remain authoritative for citations and for which lane
+cited a range. The excerpt has no lane attribution and must not be used to
+reconstruct it. Its included nearby units provide reading context only; they
+do not widen any citation in a lane artifact.
 
-The selected lane allowlist is lexical. Contexts and units are in source
+The excerpt contains at most every generic source unit once. It can therefore
-document position order, not numeric unit-ID order. Direct evidence entries
+equal the complete generic source document when coverage is broad or the
-are deterministically ordered by lane and source reference. Overlapping or
+window is large. No byte-, token-, or compression-size guarantee is made, and
-contiguous windows merge, and each source unit appears at most once in the
+the framework does not truncate the excerpt to meet an arbitrary size limit.
-resulting contexts.
+
+## Consumer Responsibilities And Data Handling
 
 The artifact is additive to the JSON bundle and is not a lane payload,
 normalized-output count, checkpoint, or generated reference. Consumers that
-do not need it must tolerate the absent optional descriptor. Consumers that do
+do not need it must tolerate an absent descriptor. Consumers that do use it
-use it should preserve the artifact and its schema identity with the run
+should validate the descriptor and payload before use, retain the artifact with
-provenance, and should treat its source text and metadata as sensitive durable
+its schema identity when needed for a run record, and read citations from the
-content.
+corresponding normalized lane artifacts.
+
+The excerpt contains source-unit text and source-owned metadata and is durable
+output. Treat it as sensitive source content, apply appropriate access controls
+and retention, and do not assume its selected form is materially smaller or
+less sensitive than the original input.

docs/integrations/json-output.md

@@ -24,7 +24,7 @@ root for the logical discovery described here.
 | `warnings.json` | Accepted-output and run warnings. |
 | `lanes/<safe-lane-id>.json` | One normalized artifact payload for each lane. |
 | `chunk-map.json` | Optional accepted chunk map, when its export is enabled and available. |
-| `evidence-context.json` | Optional source-context artifact, when evidence publication is enabled. |
+| `evidence-context.json` | Optional selected source-unit excerpt, when evidence publication is enabled. |
 
 JSON files are pretty-printed with a trailing newline. Lane payloads are
 accepted only when their media type is `application/json`.
@@ -71,13 +71,14 @@ output encoding fail.
 Each `lanes/<safe-lane-id>.json` file is the codec-owned normalized JSON for
 that lane. Consumers should use the index descriptor’s schema identity rather
 than infer a lane schema from its name. The current D&D payload contracts are
-[spells](dnd-spell-artifacts.md), [NPCs](dnd-npc-artifacts.md),
+[spells](dnd-spell-artifacts.md), [NPC registry](dnd-npc-registry-artifacts.md),
-[NPC interactions](dnd-npc-interaction-artifacts.md),
+[NPC occurrences](dnd-npc-occurrence-artifacts.md),
 [combat turns](dnd-combat-turn-artifacts.md),
-[item events](dnd-item-event-artifacts.md),
+[item registry](dnd-item-registry-artifacts.md),
-[scene descriptions](dnd-scene-description-artifacts.md), and
+[item occurrences](dnd-item-occurrence-artifacts.md),
+[scene descriptions](dnd-scene-description-artifacts.md),
 [enemy events](dnd-enemy-event-artifacts.md),
-[locations](dnd-location-artifacts.md), and
+[location registry](dnd-location-registry-artifacts.md), and
 [location occurrences](dnd-location-occurrence-artifacts.md).
 
 ## `manifest.json`

docs/internal/dnd.md

@@ -7,19 +7,20 @@ selectable keys, bindings, reference syntax, and default validator chains.
 
 ## Durable Artifact Contracts
 
-The nine lanes have separate durable wire contracts. This guide deliberately
+The ten lanes have separate durable wire contracts. This guide deliberately
 does not repeat their JSON shapes or schemas.
 
 | Lane | Durable contract |
 | --- | --- |
 | Spells | [spell artifacts](../integrations/dnd-spell-artifacts.md) |
-| NPCs | [NPC artifacts](../integrations/dnd-npc-artifacts.md) |
+| NPC registry | [NPC registry artifacts](../integrations/dnd-npc-registry-artifacts.md) |
 | Combat turns | [combat-turn artifacts](../integrations/dnd-combat-turn-artifacts.md) |
-| Item events | [item-event artifacts](../integrations/dnd-item-event-artifacts.md) |
+| Item occurrences | [item-occurrence artifacts](../integrations/dnd-item-occurrence-artifacts.md) |
-| NPC interactions | [NPC-interaction artifacts](../integrations/dnd-npc-interaction-artifacts.md) |
+| Item registry | [item-registry artifacts](../integrations/dnd-item-registry-artifacts.md) |
+| NPC occurrences | [NPC-occurrence artifacts](../integrations/dnd-npc-occurrence-artifacts.md) |
 | Scene descriptions | [scene-description artifacts](../integrations/dnd-scene-description-artifacts.md) |
 | Enemy events | [enemy-event artifacts](../integrations/dnd-enemy-event-artifacts.md) |
-| Locations | [location artifacts](../integrations/dnd-location-artifacts.md) |
+| Location registry | [location-registry artifacts](../integrations/dnd-location-registry-artifacts.md) |
 | Location occurrences | [location-occurrence artifacts](../integrations/dnd-location-occurrence-artifacts.md) |
 
 ## Family Composition
@@ -28,7 +29,7 @@ The D&D registrar registers the family’s artifact codecs, extractors, typed
 append-order mergers, normalizers, validators, prompt assets, fallback LLM
 profile asset, and default validator chains. Each extractor and normalizer has
 a stable module spec, explicit execution class, strict option decoding, and a
-typed builder. Scene chunking, every extractor, NPC normalization, and location
+typed builder. Scene chunking, every extractor, and NPC, location, and item-registry
 normalization are registered as `llm_backed`; the remaining current D&D mergers
 and normalizers are `deterministic`. The metadata is available to catalog inspection and
 resolved-pipeline debug data and determines which selected bindings inherit the
@@ -43,59 +44,69 @@ the contracts above define durable data.
 
 ## Prompt Construction
 
-D&D LLM-facing content lives beneath `assets/dnd/`. New extractor content uses
+D&D LLM-facing content lives beneath `assets/dnd/`. Each module contributes a
-its feature subtree; when a family has both extraction and normalization
+local `prompt.yaml` declaration and `instructions.md`; input-specific files
-content, keep those in its `extract` and `normalize` subtrees. The owning module
+such as a catalog, registry, grounding projection, or candidate collection are
-still defines the ordered manifest and registers the resulting scoped filesystem.
+local only when that module needs them. New extractor content uses its feature
-Shared fragments belong to the D&D shared implementation and are selected by
+subtree, while families with both extraction and normalization content use their
-name, never copied into individual module subtrees.
+`extract` and `normalize` subtrees. Shared visual-provenance fragments use
+the `common-dnd-` prefix. Production lane code belongs with its D&D codec,
+extractor, normalizer, and validator packages; registry projections and
+identity helpers remain in their owning entity packages rather than in a
+consumer lane.
 
-D&D extractors assemble prompts from an ordered manifest of shared and
+The owning module’s manifest is the source of truth for which local and shared
-module-selected assets. The location extractor and occurrence extractor reuse
+assets are selected, their mount paths, their message order, cache controls,
-the shared D&D system, evidence, identity, reference, and transcript assets
+and the files included in its prompt fingerprint. Shared fragments belong to
-instead of copying their text into individual modules. A manifest’s declared
+the D&D shared implementation and are selected by name rather than copied into
-sequence, including cache-control placement, is part of the prompt behavior.
+module directories. The root `assets` package is a content-only boundary; its
+physical ownership and rationale are defined by
+[ADR-0011](../adr/0011-centralize-llm-assets.md).
+
+Put each rule at its narrowest owner:
+
+- universal behavior belongs in the shared system asset;
+- D&D-family behavior belongs in a selected `common-dnd-` asset;
+- rules for an input projection belong with that input asset;
+- lane-specific policy belongs in the module’s `instructions.md`; and
+- transport-envelope shape belongs in the private response schema.
+
+A rule is eligible for the system prompt only when every D&D LLM prompt needs
+it regardless of lane, inputs, or response shape. Module instructions must not
+repeat rules selected from shared assets or schemas. Reintroduce such repetition
+only after observational evaluation with representative transcripts shows that
+it improves results at the intended target models and cost; structural prompt
+tests alone are not that evidence.
 
 Every maintained D&D LLM prompt selects `dnd-extraction` as its default
-profile. The D&D registrar registers that fallback profile with the maintained
+profile. The D&D registrar registers the fallback, while an operator can
-OpenRouter model, timeout, and service-tier policy. An operator may provide a
+replace it with a complete profile of the same ID from the configured PromptKit
-complete profile with the same ID through the configured PromptKit source; that
+source. Deployment profile selection is documented in
-definition replaces the fallback rather than merging with it. The fallback
-leaves reasoning and optional sampling controls unspecified. Deployment profile
-selection and the maintained operator example are documented in
 [Configuration](../config.md#promptkit-profiles).
 
-All extraction prompts share this four-message rendered prefix: the system
+The D&D transcript assets have distinct consumers. Scene chunking consumes the
-message without cache control, the identity message without cache control, the
+complete-session `common-dnd-transcript-full.md`, while extraction prompts
-campaign-reference message with ephemeral cache control, and the chunk
+consume the current-chunk `common-dnd-transcript-chunk.md`. NPC, location, and
-transcript message with ephemeral cache control. This gives equivalent
+item normalization instead mount the generic semantic-reconciliation
-extraction requests the same reusable prefix through their source material.
+candidate and transcript-window presentation assets. Player, party, glossary,
+and compatible campaign references provide disambiguating context only when
+declared by the active prompt; they never establish evidence. Reference
+material is canonically ordered before rendering so equivalent inputs remain
+stable.
 
-Extraction-evidence policy, generated NPC registries, spell catalogs, module
+Extraction prompts render the common system and identity messages first, then
-tasks, and instructions follow the transcript because they are not universal
+cached campaign references and the cached chunk transcript. Evidence policy and
-across all extraction lanes. The final instructions message carries ephemeral
+any lane-specific registry, catalog, or grounding projection follow that
-cache control; evidence, registry, catalog, and task messages do not. Preserve
+prefix. The final module instructions message is ephemeral. This keeps the
-this division when changing an extractor or its assets so prompt-cache behavior
+reusable extraction prefix identical while preserving the lane-specific suffix.
-remains stable.
 
-The other D&D LLM prompts intentionally follow different patterns. Scene
+Scene chunking intentionally uses a different order: system, cached campaign
-chunking has no sibling extraction lane with which to share its full transcript,
+references, uncached module instructions, then the final ephemeral full
-so it renders campaign references before its task and instructions, then places
+transcript. Entity normalization also has its own order: D&D system, mandatory
-the cacheable full transcript last. NPC and location normalization share the
+generic protocol, ephemeral domain semantic instructions, generic candidate
-entity-reconciliation response schema and safety boundary while retaining their
+presentation, and final ephemeral generic transcript windows. These orders and
-own task and identity rules. NPC normalization keeps its task and
+cache controls are prompt behavior; change them only through the owning
-cacheable instructions before the candidate collection, followed by the
+manifest and prompt declaration.
-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
-campaign references are context for disambiguation, not source evidence.
-Reference prompt material is canonically ordered before it is rendered, which
-keeps equivalent inputs stable across runs.
 
 ## Evidence, Candidates, And Normalization
 
@@ -108,7 +119,8 @@ result.
 
 Default chains keep responsibilities separate: structural validators assess the
 candidate, source-reference validators resolve cited ranges against the current
-source, durable-schema validation checks an approved representation, and
+source and require extraction evidence to stay within the current chunk,
+durable-schema validation checks an approved representation, and
 relatedness validators report advisory evidence concerns. The configured order
 is documented in
 [Configuration](../config.md#production-validator-keys-and-default-chains).
@@ -118,15 +130,52 @@ the same comparison identity within one scene-scoped result. Normalization may
 combine results from distinct scenes, so it intentionally does not apply that
 rule. Configuration owns the exact validator key and chain position.
 
-Normalizers are deterministic for spells, combat turns, item events, NPC
+Normalizers are deterministic for spells, combat turns, item occurrences, NPC
-interactions, scene descriptions, enemy events, and location occurrences. They canonicalize display
+occurrences, scene descriptions, enemy events, and location occurrences. They
-values and evidence, use source-document order for stable output, and issue
+canonicalize display values and evidence, use source-document order for stable
-bounded warnings for changes or collapsed duplicates. The NPC and location
+output, and issue bounded warnings for changes or collapsed duplicates. NPC,
-normalizers are intentional exceptions: each first produces a deterministic
+item, and location registry normalizers are intentional exceptions: each first
-candidate set, then may use a bounded structured-LLM proposal to reconcile
+produces a deterministic candidate set, then may use a bounded structured-LLM
-identity groups. Invalid or unusable proposals retain the deterministic result
+proposal to reconcile identity groups.
-and surface retry or fallback diagnostics; the model does not directly replace
+
-durable records.
+## Semantic Registry Reconciliation
+
+The three registry normalizers instantiate the domain-neutral
+`internal/framework/semanticreconcile` engine with default bounds. Each
+eligible candidate receives a contiguous, one-based `candidate_id` for that
+request. The model sees that handle, the candidate label and source-free
+evidence ranges, plus bounded transcript windows; it returns only duplicate
+groups of supplied handles and one supplied canonical handle per group. It
+never returns names, evidence, durable IDs, or replacement records. Identical
+labels and evidence remain independently selectable because their handles are
+distinct.
+
+The generic core owns the mandatory handle protocol, candidate and transcript
+presentation, the private response schema, source-reference validation,
+candidate and combined-material limits, structured completion, proposal
+assessment, stable group ordering, and typed plan-application mechanics. The
+D&D prompt contributes its system message and registry-specific semantic
+instructions. The generic registrar registers the shared prompt and schema;
+the D&D registrar registers each consuming prompt and the fallback profile.
+
+Fewer than two eligible candidates skips the LLM without a semantic warning.
+An exceeded bound also skips the call and preserves the deterministic
+preprocessed registry, adding the registry's bounded fallback warning. Invalid
+structured output or discarded proposal groups use the normalizer's existing
+retry contract; retry exhaustion preserves the safe deterministic or
+partially applied result and emits its bounded fallback warning. Provider,
+transport, cancellation, and context-material failures remain execution
+errors.
+
+Application remains typed and registry-owned. All three policies select the
+canonical member's normalized display name, union member evidence in source
+order, preserve ungrouped records, and derive durable identity only after
+consolidation. NPC IDs derive from the final name. Item IDs also derive from
+the final name, and a typed guard prevents currency aliases from crossing
+denominations or mixing currency with non-currency records. Location IDs
+derive from the final name and final evidence, preserving same-name,
+parent/child, and distinct physical-place identities. Registry warning scopes,
+reason codes, and postconditions remain outside the generic core.
 
 ## Generated References And Grounding
 
@@ -136,33 +185,46 @@ producer provenance; consumers resolve the handed-off artifact into an
 immutable, validated projection for each operation. External files are checked
 during preparation, while generated artifacts are resolved at the handoff.
 
-NPC registries are names-only grounding projections: they may canonicalize
+NPC and item registry consumers receive names-only grounding. Location
-actors for spells and combat turns and are required for NPC interactions, but
+consumers receive a contextual selector containing the canonical name and the
-they do not supply evidence. Scene-description registries are eligibility-only
+registry references needed to distinguish same-name places. The calling module
-projections: they retain the current chunk’s classification data, not scene
+resolves those supplied selections locally and maps them into the unchanged
-prose or evidence, and exist to route combat extraction. Enemy-event extraction
+durable ID/name pair; an unknown or ambiguous selection rejects the complete
-also projects combat turns to `actor` and `turn_kind` and filters NPC
+occurrence result rather than accepting a partial mapping. The NPC registry
-interactions to `combat_opponent` names and kinds. Location registries project
+additionally supplies names-only actor grounding to spells, combat turns, and
-ordered `{id, name}` pairs to location-occurrence extraction and normalization;
+enemy events.
-exact ID/name matching keeps same-name locations distinguishable. These compact
+
-projections, like NPC grounding, are source-free guidance and never event
+Registry references establish a registry identity and may disambiguate a
-evidence.
+selection, but never become occurrence evidence. Each occurrence keeps its own
+current-transcript source references, even when it was grounded through the
+same registry record.
+Scene descriptions are eligibility-only projections: they retain current-chunk
+classification data, not scene prose or evidence, and exist to route combat
+extraction. Enemy-event extraction also projects combat turns to `actor` and
+`turn_kind` and filters NPC occurrences to `combat_opponent` names and kinds.
+These projections are guidance only and never event evidence.
 
 ## Lane-Specific Rules
 
 The following differences are intentional and should remain explicit when a
 shared helper changes.
 
+Shared D&D text comparison is identified by `dnd.text_comparison.v1`. Any
+semantic change requires an explicit policy-version review for every affected
+identity, mapping, normalization, and validator policy; helper source is not a
+checkpoint fingerprint.
+
 | Lane | Intentional behavior |
 | --- | --- |
 | Spells | May use a spell-catalog overlay and optional NPC grounding; the catalog validator supplies domain-specific semantic checks. |
-| NPCs | Does not consume an NPC registry. Its normalizer is the LLM-assisted reconciliation exception described above. |
+| NPC registry | Establishes transcript-grounded NPC identities, including factual third-party mentions, without assigning occurrence categories. It does not consume an NPC registry, and its normalizer is the LLM-assisted reconciliation exception described above. |
 | Combat turns | Requires a scene-description artifact. It calls the LLM only for an exact `combat` classification; exact non-combat classifications return an accepted empty result, while missing or mismatched classifications return an empty result with a bounded warning. Optional NPC grounding never becomes evidence. |
-| Item events | Uses campaign context for disambiguation but has no NPC-registry or scene-description dependency. |
+| Item occurrences | Requires the normalized item registry for exact deterministic grounding at extraction and normalization. Campaign context may disambiguate, but the registry never becomes occurrence evidence. |
-| NPC interactions | Requires the normalized NPC registry at extraction and normalization, using it for canonical actor grounding only. |
+| Item registry | Produces source-grounded item types and unique designations. Its LLM-assisted reconciliation is proposal-only, preserves distinct currency denominations and item types, and does not create per-instance identities. |
+| NPC occurrences | Requires the normalized NPC registry at extraction and normalization, using it for canonical actor grounding only. It separately emits cited current-transcript occurrence facts, including `mentioned`, rather than deriving them from registry provenance. |
 | Scene descriptions | Produces the classifications consumed by combat routing; it does not consume an NPC registry or provide evidence for combat artifacts. |
-| Enemy events | Requires NPC, scene-description, combat-turn, and NPC-interaction artifacts. It calls the LLM only for an exact `combat` classification, records ordered observations rather than terminal state, and normalizes recognized names through the NPC registry while preserving grounded collective labels. |
+| Enemy events | Requires NPC, scene-description, combat-turn, and NPC-occurrence artifacts. It calls the LLM only for an exact `combat` classification, records ordered observations rather than terminal state, and normalizes recognized names through the NPC registry while preserving grounded collective labels. |
-| Locations | Produces a source-anchored, session-scoped registry. Its LLM-assisted reconciliation is proposal-only and never collapses same-name places without validated identity and evidence rules. |
+| Location registry | Produces a source-anchored, session-scoped registry from stable proper names or unique in-world designations. Its LLM-assisted reconciliation is proposal-only and never collapses same-name places without validated identity and evidence rules. |
 | Location occurrences | Requires the normalized location registry for both extraction and normalization. Its [durable occurrence categories](../integrations/dnd-location-occurrence-artifacts.md#occurrence-categories) distinguish explicit speculation from unsupported inference; the deterministic normalizer enforces exact registry grounding and never turns registry provenance into occurrence evidence. |
 
 The combat and scene-description contracts describe their exact handoff and

docs/internal/llm.md

@@ -24,6 +24,9 @@ adapter does not own source evidence, artifact conversion, normalization, or
 durable schemas. Those responsibilities remain with the module and its
 [integration contract](../integrations/).
 
+The calling module also resolves contextual entity selections and attaches any
+application identity; PromptKit and this adapter do not own entity identity.
+
 `PromptKitClient` validates the request target and prompt identity, maps each
 named material to a PromptKit inline artifact while preserving its origin URI,
 passes the supplied request session through to PromptKit's direct per-run
@@ -99,7 +102,8 @@ because it changes scheduling rather than execution semantics.
 Production construction creates one PromptKit client and wraps it in one
 scheduled client. The scheduler has a fixed, positive permit limit, serves
 queued calls in FIFO order, and removes a queued call when its context is
-cancelled. A granted permit is released exactly once on every completion path.
+cancelled. It rechecks the caller context after admission and before dispatch.
+A granted permit is released exactly once on every completion path.
 
 The scheduled wrapper surrounds every `CompleteStructured` call, so concurrent
 lanes, pipeline retries, and LLM-backed validators share the same provider-call
@@ -138,12 +142,28 @@ arrangement and its data-only boundary are defined by
 [ADR-0011](../adr/0011-centralize-llm-assets.md), rather than by this runtime
 guide.
 
+The generic registrar is the sole production registration owner for the
+semantic-reconciliation default prompt and private response schema. The
+domain-neutral reconciliation package also exposes only its mandatory protocol
+and candidate/transcript presentation files for domain prompt manifests. D&D
+registry normalizers mount those files while retaining ownership and hashing
+of their D&D system message, semantic instructions, and complete prompt
+declaration. The response schema is therefore registered once even though
+several typed normalizers select it.
+
 Mounted prompt assets determine a module's fingerprint. The fingerprint hashes
 only the module and shared files explicitly selected by its manifest, so an
 unrelated asset does not invalidate a checkpoint. Schema loaders validate JSON,
 attach identity and digest metadata, make defensive copies, and expose
 diagnostics without raw schema bytes.
 
+Semantic-reconciliation normalizers extend this identity with the shared
+response-schema digest, framework policy version, and complete limit-policy
+digest. Their manifest metadata records the same content-free prompt, schema,
+policy, and limit identities together with domain identity and normalization
+policies. Request-local handles, source material, proposal content, and raw
+asset bytes are not checkpoint metadata.
+
 Private response schemas validate a model transport envelope. They are not the
 durable artifact schema and should not be documented as an external wire
 contract. Durable formats and compatibility rules remain in the
@@ -176,7 +196,9 @@ structured-output validation. The adapter reports an empty result, validation
 failure, empty structured body, or decode failure as
 `ErrInvalidStructuredOutput`, while retaining the returned raw bytes and debug
 material when they exist. Provider failures remain operational errors rather
-than output-validation failures.
+than output-validation failures. Apart from documented context, capacity, and
+invalid-output categories, provider error values and types do not cross the
+adapter error chain; callers receive only a credential-redacted diagnostic.
 
 When PromptKit rejects backend admission before generation, the adapter maps
 `promptkit.ErrCapacityExceeded` to

docs/internal/modules.md

@@ -42,14 +42,23 @@ generic source references and must use the codec's exact Go type. It does not
 interpret surrounding context or publish files; the pipeline validates the
 capability during preparation and the output boundary owns publication. See
 the [Published Evidence Context contract](../integrations/evidence-context.md)
-for the durable result.
+for the durable source-unit excerpt. Lane artifacts retain citation and lane
+provenance; the framework does not add either to that published excerpt.
+
+An artifact family is broader than a module: it owns the cohesive domain
+feature across its artifact type, codec, stage modules, validators, prompt
+policy, schemas, identity helpers, and reference projections. An extractor and
+normalizer in one artifact family remain independently registered modules in
+their respective pipeline stages. This ownership vocabulary does not create a
+new registry or change the fixed pipeline.
 
 ## Production Composition
 
 Production composition is intentionally split by family:
 
 - The generic registrar provides the unit chunker, generic JSON validators,
-  and JSON output encoder.
+  JSON output encoder, and shared semantic-reconciliation prompt and response
+  schema assets.
 - The Seriatim registrar provides the transcript input adapter. Its external
   input behavior is defined by the [Seriatim contract](../integrations/seriatim.md).
 - The D&D registrar provides its codecs, extractors, mergers, normalizers,
@@ -60,6 +69,36 @@ The CLI owns the composition that invokes these registrars. A module package
 may register its own family but must not assemble the CLI or make framework
 packages depend on production extensions.
 
+## Semantic Reconciliation
+
+`internal/framework/semanticreconcile` is a domain-neutral strategy used by a
+typed normalize module; it is not itself a selectable stage module. A
+source-backed artifact-family normalizer projects its deterministic records
+into contextual candidates and owned typed record envelopes, supplies its
+chosen prompt identity and resolved LLM profile, and constructs an engine with
+explicit limits. The core filters invalid evidence, assigns contiguous
+request-local integer handles, renders bounded candidate and transcript
+materials, invokes the structured-completion boundary, and assesses the
+returned duplicate groups into a stable non-overlapping plan.
+
+The normalizer then applies that plan through a typed `ApplicationPolicy`. The
+core preserves ungrouped records, contribution order, and provenance while the
+artifact family owns group guards, field and evidence consolidation, durable
+ID derivation, retry and fallback presentation, warnings, and postconditions.
+Request-local handles do not enter the typed value or durable artifact. Fewer
+than two eligible candidates skips model invocation; exceeding a candidate or
+combined-material bound preserves the deterministic result under the family's
+fallback policy. Provider, transport, cancellation, and context-construction
+failures remain execution errors.
+
+The core supplies a conservative generic prompt and the single private
+response schema. A domain prompt may substitute its semantic instructions but
+mounts the core-owned protocol and candidate/transcript presentation assets.
+Prompt, schema, policy, and limit identities participate in manifest metadata
+and checkpoint fingerprints. The generic registrar owns production
+registration of those shared assets; a consuming domain registrar owns only
+its domain prompt.
+
 ## Adding Or Changing A Module
 
 1. Choose the pipeline stage and the typed artifact boundary. Put external

docs/internal/overview.md

@@ -29,6 +29,7 @@ physical state roots.
 | Generic models | **internal/core/source**, **internal/core/artifacts**, **internal/framework/contracts** | Source documents and chunks, manifests and provenance, plus typed artifact, reference, validation, output, and structured-completion contracts. |
 | Pipeline framework | **internal/framework/pipeline** | Registries, profile and reference resolution, typed preparation, validation, retry coordination, ordered execution, handoff, and result assembly. |
 | LLM and prompt runtime | **internal/framework/llm**, **internal/framework/promptfs** | Provider-neutral structured completions, scheduling, profile recording, prompt assets, schema registration, and credential-shaped-value redaction. |
+| Semantic reconciliation | **internal/framework/semanticreconcile** | Bounded source-backed candidate preparation, request-local handle proposals, deterministic assessment, typed plan application, and reconciliation identity metadata; see [Module Internals](modules.md#semantic-reconciliation) and [D&D Module Internals](dnd.md#semantic-registry-reconciliation). |
 | Embedded LLM content | **assets** | Read-only centralized LLM-facing content, scoped by its consuming package; see [LLM Runtime](llm.md#prompt-and-schema-assets) and [D&D Module Internals](dnd.md#prompt-construction). |
 | Runtime state | **internal/core/fileio**, **internal/core/debugbundle**, **internal/framework/checkpoint**, **internal/framework/chunkplan**, **internal/framework/chunkmap**, **internal/framework/debug** | Confined atomic files, debug bundles, checkpoint and chunk-plan state, accepted chunk maps, and pipeline-facing debug recording. |
 | Production extensions | **internal/modules/generic**, **internal/modules/seriatim**, **internal/modules/dnd** | Domain-neutral extensions, Seriatim input support, and D&D extraction families registered into the production catalog. |
@@ -49,8 +50,9 @@ the CLI composition boundary.
   composition, and path safety.
 - [LLM Runtime](llm.md): structured completion, scheduling, prompt assets,
   profiles, and secret handling.
-- [Module Internals](modules.md): generic extension registration, module
+- [Module Internals](modules.md): generic extension registration, artifact
-  construction, validation, and reference mechanics.
+  families, module construction, semantic reconciliation, validation, and
+  reference mechanics.
 - [D&D Module Internals](dnd.md): shared D&D extractor conventions, generated
   reference projections, and lane-specific exceptions. Durable D&D and
   Seriatim data shapes remain in the [integration contracts](../integrations/).

docs/internal/pipeline.md

@@ -46,16 +46,18 @@ External reference materialization happens before preparation. The materializer
 checks that each slot is declared by the selected module, resolves a file path
 relative to the correct configuration or working-directory origin, reads
 UTF-8 text, verifies media type and size limits, and retains bounded
-provenance. A generated-artifact selector remains declared but has no bytes
+provenance. For a positive slot limit, it reads at most the limit plus one byte
-until its producing step completes.
+and rejects overflow before retaining content. A generated-artifact selector
+remains declared but has no bytes until its producing step completes.
 
 Preparation is the construction boundary. It validates the resolved shape and
 registry set, clones the resolved data, then constructs the input adapter,
-chunker, stage-local validators, every typed lane, and output encoder with
+chunker, stage-local validators, every typed lane, and output encoder. Each
-cloned options, references, and shared dependencies. It also collects stable
+registered builder receives its own cloned build request immediately before its
-checkpoint fingerprints. Missing registrations, incompatible typed entries,
+module-owned code runs. Preparation also collects stable checkpoint
-nil implementations, and constructor failures are reported before source
+fingerprints. Missing registrations, incompatible typed entries, nil
-parsing or any stage operation begins.
+implementations, and constructor failures are reported before source parsing
+or any stage operation begins.
 
 An output encoder can opt into source-evidence publication through its output
 policy. Preparation keeps the configured lane allowlist and active lanes
@@ -115,9 +117,12 @@ for started workers, and prevents output encoding.
 
 Every chunk, extract, merge, and normalize candidate passes its resolved
 validator chain. Validators receive immutable canonical input appropriate to
-their target: chunks, typed values, or serialized codec bytes. They may
+their target: chunks, codec-decoded typed candidates, or serialized codec
-approve, approve with warnings, reject, or fail. A rejection is an ordinary
+bytes. Each typed validator receives a newly decoded value from the one
-pipeline result; a validator error is a framework error.
+candidate serialization for that attempt, while serialized validators receive
+separately owned representation bytes and schema metadata. They may approve,
+approve with warnings, reject, or fail. A rejection is an ordinary pipeline
+result; a validator error is a framework error.
 
 The runner applies the binding's retry policy around a stage operation and its
 complete validation chain. It preserves warnings only from the final accepted

docs/internal/state.md

@@ -47,6 +47,9 @@ The serialized
 they do not describe a current public state surface.
 
 Ordered-step lane checkpoints include the step identity in their storage scope.
+Accepted step and lane identities are encoded injectively before becoming
+filesystem path components, while ordinary safe identifiers retain their
+readable paths.
 When a later lane consumes a generated artifact, its dependency fingerprints
 include the producer's artifact kind, complete schema identity, media type,
 canonical content digest, and size. Ordinary resume compares those fingerprints

docs/operations.md

@@ -110,9 +110,9 @@ are defined in [Accepted Chunk Map](integrations/chunk-map.md). An optional
 [evidence context](integrations/evidence-context.md) contains source-unit text
 and metadata. It is not a cache or debug artifact: retain it with the output
 bundle only for as long as consumers need it, and apply source-content access
-controls to the entire bundle. Selected lanes may collectively cite most of a
+controls to the entire bundle. Its selected source-unit excerpt may include
-transcript, so a broad allowlist can make the evidence artifact nearly as
+every source unit once when coverage is broad or its configured window is
-sensitive and large as the source itself.
+large, so do not assume a byte or token reduction or reduced sensitivity.
 
 ## Chunk-Plan Cache
 

docs/policy/architecture.md

@@ -24,6 +24,12 @@ DAGs or a general workflow language. Every stage remains explicit; general
 chunking, merging, or normalization behavior must not be hidden inside an
 extractor.
 
+A stage module is one configured implementation of one pipeline stage. An
+artifact family is the cohesive domain feature that owns an artifact across
+the explicit stages and supporting codecs, validators, prompts, identity
+rules, and reference projections. Artifact-family ownership does not combine
+stages or alter the fixed pipeline.
+
 Input and chunking are pipeline-wide. Each selected artifact lane owns its
 extract, merge, and normalize stages, and the output stage aggregates the run's
 lane outcomes.
@@ -39,6 +45,12 @@ implementations. Domain-neutral model and framework layers provide reusable
 policy, contracts, and orchestration. Concrete input, pipeline, output, and
 validation extensions depend inward on those generic layers.
 
+Semantic reconciliation is one such domain-neutral framework mechanism. It
+prepares bounded source context, invokes a shared model-judgment protocol,
+validates proposals, and applies safe plans through typed policies supplied by
+the consuming artifact family. It does not own domain identity, durable IDs,
+warning semantics, or artifact construction rules.
+
 Generic layers must not depend on production extensions. Concrete extensions
 must not compose the application or take ownership of process behavior. The
 current packages implementing these layers are inventoried in
@@ -183,6 +195,17 @@ The caller of the LLM owns prompt selection, prompt inputs, response schema,
 and interpretation of structured output. Provider adapters do not own source-
 or domain-specific prompt logic.
 
+When a model selects an application entity, callers must supply a contextual
+selection and deterministically attach the opaque application identity whenever
+the selection resolves exactly. Models do not receive or reproduce opaque
+application identifiers. Semantic reconciliation may instead expose
+contiguous, one-based candidate handles that exist only for one request;
+deterministic code resolves them before typed application, and they never
+become durable identity. This is the approved request-local-label application
+of [ADR-0012](../adr/0012-resolve-opaque-entity-identifiers-deterministically.md)
+recorded by
+[ADR-0013](../adr/0013-use-request-local-candidate-handles-for-semantic-reconciliation.md).
+
 LLM calls and other external operations accept cancellation and respect
 timeouts. Concurrency control belongs in shared runtime plumbing rather than in
 individual modules.

docs/roadmap/future.md

@@ -24,26 +24,52 @@ not as committed release dates.
 
 ## Shared Normalization And Quality Work
 
-### Generic LLM-Assisted Deduplication
+The implemented source-backed core and initial D&D registry adoption are
+described by [Module Internals](../internal/modules.md#semantic-reconciliation)
+and
+[D&D Module Internals](../internal/dnd.md#semantic-registry-reconciliation).
+The [Semantic Reconciliation Roadmap](semantic-reconciliation.md) retains the
+original feature scope; the sections below keep broader extensions deferred.
 
-- Add a reusable normalizer that asks an LLM to identify duplicate sets in a
+### Large-Collection Semantic Reconciliation
-  list and propose one replacement element for each set.
-- Define the minimum domain-neutral input contract, initially an ordered list
-  whose elements have stable unique IDs. Artifact-kind registrations or
-  adapters may expose that structure without moving domain rules into the
-  generic package.
-- Keep mutation deterministic: parse and validate the model's duplicate groups,
-  require every referenced ID to exist, reject overlapping or malformed groups,
-  prevent unrelated insertion or deletion, and apply only approved replacement
-  operations in code.
-- Preserve provenance needed for audit and downstream validation, and emit
-  warnings describing every collapsed group.
-- Evaluate batching and context-window limits before applying the normalizer to
-  large artifact collections.
 
-The model may use its own domain knowledge to judge semantic duplication; the
+- Evaluate deterministic candidate blocking only after representative registry
-generic implementation is responsible only for the common proposal contract,
+  inputs exceed the active roadmap's bounded single-request limits. Blocking
-safety checks, and deterministic application of accepted changes.
+  should use cheap, explainable signals to form plausible comparison sets while
+  preserving the possibility that a duplicate appears outside a lexical name
+  match.
+- Define correctness for candidates that appear in more than one block,
+  conflicting canonical selections, transitive identity across blocks, retry
+  isolation, and deterministic final ordering before implementation.
+- Prefer a reconciliation graph or union plan with explicit conflict checks
+  over arbitrary fixed-size slices. Never silently treat a batch boundary as
+  evidence that two candidates are distinct.
+- Record per-request bounds, block provenance, model calls, discarded
+  proposals, and final group derivation well enough to audit a collapse.
+
+### Operator-Selected Semantic Policies
+
+- Consider allowing an operator to select an approved semantic-policy prompt
+  for a typed reconciliation module without replacing the shared protocol,
+  response schema, or deterministic safety rules.
+- Define the trusted asset source, configuration syntax, compatibility checks,
+  startup validation, provenance, prompt fingerprinting, checkpoint effects,
+  and support boundary before exposing the option.
+- Prefer selection among registered, typed-policy-compatible prompt assets over
+  arbitrary filesystem prompt paths. Do not add this flexibility until an
+  operator workflow requires it; artifact-family-owned policy remains simpler
+  and safer for the initial implementation.
+
+### Broader Reconciliation Inputs And Module Selection
+
+- Revisit alternate context providers when a concrete non-source-backed entity
+  collection needs semantic reconciliation. Any extension must preserve the
+  same request-local identity, deterministic proposal validation, provenance,
+  and typed application guarantees.
+- Consider a selectable generic normalizer only if Notarius gains a real
+  domain-neutral typed artifact contract that can safely support it. Do not
+  weaken exact artifact registration or introduce reflection-based arbitrary
+  JSON mutation merely to expose a universal module key.
 
 ### Validation And Review
 
@@ -100,6 +126,18 @@ checkpoint reuse, when an older artifact may be decoded or adapted, and when a
 producer or all dependents must be recomputed. Do not add a general migration
 framework until an actual contract change requires one.
 
+### Artifact-family-oriented physical packaging
+
+[ADR-0004](../adr/0004-package-modules-by-domain.md) currently groups production
+extensions by domain and then by pipeline stage. After artifact-family
+ownership terminology is established and more families span extraction,
+normalization, validation, codecs, references, and assets, reassess whether a
+feature-first physical layout would improve navigation and reduce scattered
+changes enough to justify a repository-wide package migration. Any change must
+address Go dependency cycles, registrar ownership, stable public module keys,
+and supersession of the affected ADR-0004 decision. Conceptual artifact-family
+ownership does not by itself require this move.
+
 ## Blue-Sky Platform And Operations
 
 These ideas are intentionally less specified. Promote one into an earlier