Tighten evidence context source excerpts

README.md

@@ -2,8 +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 scene descriptions, item and currency events,
-NPC identities, combat turns, NPC interactions, and spell casts.
+transcript JSON and can produce NPC, location, and item registries; their
+source-grounded occurrences; scene descriptions, combat turns, enemy events,
+and spell casts.
 
 ## Quickstart
 

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

@@ -0,0 +1,18 @@
+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. Keep events in transcript chronology; place an interrupting event where
+it occurs.
+
+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
-  - role: user
-    content_file: ./task.md
+    content_file: ./sharedassets/common-dnd-npc-registry.md
   - role: user
     content_file: ./instructions.md
     cache_control:

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

@@ -0,0 +1,12 @@
+Compact combat grounding is supplied below. It can guide attention and
+disambiguation, but it is not evidence. Do not derive an event, subject,
+outcome, or source range from either list. The current transcript alone must
+directly establish every returned event.
+
+Combat-turn grounding:
+
+{{ input "combat_turns" }}
+
+Named combat-opponent grounding:
+
+{{ input "npc_occurrences" }}

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

@@ -0,0 +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, or a scene ending.

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

@@ -0,0 +1,53 @@
+id: dnd.enemy_events
+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
+  - name: combat_turns
+    required: true
+    content_type: application/json
+  - name: npc_occurrences
+    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: ./combat-grounding.md
+  - role: user
+    content_file: ./instructions.md
+    cache_control:
+      type: ephemeral
+output:
+  format: json
+  validation_mode: json_schema
+  schema_path: dnd_enemy_events_llm.v1.json
+  repair_attempts: 0

assets/dnd/enemy-events/schemas/dnd_enemy_events_llm.v1.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "notarius.dnd.item_events.llm",
+  "$id": "notarius.dnd.enemy_events.llm",
   "type": "object",
   "additionalProperties": false,
   "required": ["events"],
@@ -14,18 +14,15 @@
         "properties": {
           "name": {"type": "string"},
           "kind": {"type": "string"},
-          "quantity": {"type": "integer"},
-          "from": {"type": "string"},
-          "to": {"type": "string"},
           "source_refs": {
             "type": "array",
             "items": {
               "type": "object",
               "additionalProperties": false,
-              "required": ["start_segment", "end_segment"],
+              "required": ["start_unit_id", "end_unit_id"],
               "properties": {
-                "start_segment": {"type": "integer"},
-                "end_segment": {"type": "integer"}
+                "start_unit_id": {"type": "integer"},
+                "end_unit_id": {"type": "integer"}
               }
             }
           }

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

@@ -0,0 +1,30 @@
+Extract meaningful Dungeons & Dragons item and currency occurrences: discoveries and changes
+in party possession established by the transcript. This is an occurrence history,
+not an inventory or ledger: do not calculate balances, resolve item identity
+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
+possession. Use `lost` when party possession ends through a gift, sale, payment,
+theft, abandonment, or destruction not caused by intended use. Use `consumed`
+when intended use depletes an expendable item. Monetary spending, purchases, and
+payments are always `lost`, not `consumed`. Classify currency as `consumed` only
+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 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 occurrence. Do not infer acquisition from a
+discovery, or discovery from an acquisition: emit both only when each is
+independently established.

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
-  - role: user
-    content_file: ./task.md
+    content_file: ./item-registry.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

@@ -0,0 +1,36 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.dnd.item_occurrences.llm",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["occurrences"],
+  "properties": {
+    "occurrences": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["name", "kind", "quantity", "from", "to", "source_refs"],
+        "properties": {
+          "name": {"type": "string"},
+          "kind": {"type": "string"},
+          "quantity": {"type": ["integer", "null"]},
+          "from": {"type": ["string", "null"]},
+          "to": {"type": ["string", "null"]},
+          "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/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

@@ -0,0 +1,30 @@
+id: dnd.item_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/location-occurrences/prompts/instructions.md

@@ -0,0 +1,34 @@
+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 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 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/prompt.yaml

@@ -0,0 +1,45 @@
+id: dnd.location_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: location_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: ./location-registry.md
+  - role: user
+    content_file: ./instructions.md
+    cache_control:
+      type: ephemeral
+output:
+  format: json
+  validation_mode: json_schema
+  schema_path: dnd_location_occurrences_llm.v1.json
+  repair_attempts: 0

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

@@ -0,0 +1,45 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.dnd.location_occurrences.llm",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["occurrences"],
+  "properties": {
+    "occurrences": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["name", "registry_refs", "kind", "source_refs"],
+        "properties": {
+          "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",
+            "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/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.item_events
+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_item_events_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

@@ -0,0 +1,32 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.dnd.location_registry.llm",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["locations"],
+  "properties": {
+    "locations": {
+      "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/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/npc-occurrences/prompts/instructions.md

@@ -1,6 +1,14 @@
-Return the interactions array even when no interaction is established. Every
-record must contain name, kind, and source_refs. Cite transcript ranges that
-support both the NPC identity and the interaction kind.
+Extract Dungeons & Dragons NPC occurrences from the supplied
+transcript. Include an occurrence only when the transcript establishes one
+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

@@ -0,0 +1,40 @@
+id: dnd.npc_registry
+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
+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: ./instructions.md
+    cache_control:
+      type: ephemeral
+output:
+  format: json
+  validation_mode: json_schema
+  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.npcs.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: ./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_npcs_normalize_llm.v1.json
+  schema_path: semantic_reconciliation_llm.v1.json
   repair_attempts: 0

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
-events or lore.
-
-Do not return identifiers, source identifiers, source ranges, unit identifiers,
-participants, confidence, or any fields besides kind, title, and summary.
+outside the chunk.

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/scenes/prompts/instructions.md

@@ -1,5 +1,5 @@
-Divide the provided transcript into coherent Dungeons & Dragons scenes for the
-`dnd/scenes` chunk module.
+Divide the complete 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,
@@ -13,6 +13,7 @@ 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.
+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/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-extraction-evidence.md

@@ -0,0 +1,6 @@
+Transcript units are the only evidence for extracted events and factual claims.
+Every reported factual claim must be supported by cited transcript units. Use
+integer `start_unit_id` and `end_unit_id` values from the transcript.
+
+When supporting evidence is non-contiguous, use multiple narrow ranges rather
+than a broad range that bridges unrelated conversation.

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

@@ -0,0 +1,5 @@
+You process Dungeons & Dragons gameplay transcripts.
+
+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.
+
+Return exactly one JSON object that conforms to the configured response schema, with no explanatory prose.

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/spells/prompts/instructions.md

@@ -0,0 +1,14 @@
+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.
+
+For every extracted cast, the transcript evidence must collectively support the
+in-world caster, the spell, and the fact that the cast or declared attempt
+occurred.
+
+Attribute every cast to its in-world caster. Map first-person player speech to
+the associated player character, and attribute a spell narrated by the GM to
+the in-world creature that casts it. If the caster cannot be resolved, use only
+the most specific in-world identity supported by the transcript; do not invent
+a name.

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
-  - role: user
-    content_file: ./task.md
+    content_file: ./spell-catalog.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/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

@@ -0,0 +1,3 @@
+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
+          }
+        }
+      }
+    }
+  }
+}

assets/package.go

@@ -0,0 +1,15 @@
+// Package assets exposes embedded LLM-facing content.
+package assets
+
+import (
+	"embed"
+	"io/fs"
+)
+
+//go:embed dnd generic
+var embedded embed.FS
+
+// FS returns the embedded read-only asset filesystem.
+func FS() fs.FS {
+	return embedded
+}

docs/adr/0004-package-modules-by-domain.md

@@ -1,6 +1,6 @@
 # ADR-0004: Package modules by domain, not by stage
 
-**Status:** Accepted
+**Status:** Accepted — its asset-co-location rule is superseded by [ADR-0011](0011-centralize-llm-assets.md); its domain-first module packaging decision remains accepted.
 **Date:** 2026-07-13
 
 ## Context

docs/adr/0011-centralize-llm-assets.md

@@ -0,0 +1,69 @@
+# ADR-0011: Centralize LLM-facing assets in a content-only package
+
+**Status:** Accepted
+**Date:** 2026-08-05
+
+## Context
+
+LLM prompts, private response schemas, generic schemas, and fallback profiles
+are authored and reviewed as content, but package-local embedding scattered that
+content across implementation trees. Finding all of the assets that contribute
+to a prompt family required navigating code ownership boundaries rather than a
+single discoverable content boundary.
+
+The repository must retain module ownership of prompt semantics, schema
+identities, registration, and prompt-cache behavior. Durable artifact schemas
+and non-LLM domain data have different compatibility and ownership rules, so
+they must not move merely because they are embedded files.
+
+## Decision
+
+LLM-facing content is embedded by the root `assets` package. It is a data-only
+dependency leaf: its single `FS() fs.FS` API returns the read-only embedded
+filesystem, and the package contains no business logic or internal or PromptKit
+dependencies. The accepted import path is
+`gitea.maximumdirect.net/eric/notarius/assets`; it makes repository-owned
+content available to its consumers, not a public extension contract.
+
+Consumers scope that filesystem to the subtree they own before reading or
+registering content. Modules continue to own their manifests, prompt ordering,
+private response-schema identity, and registration. Centralizing physical files
+does not centralize domain semantics or transfer those responsibilities to the
+root package.
+
+The root package contains prompt content, private LLM response schemas, generic
+LLM schemas, shared fragments, and fallback profiles. Durable artifact schemas
+and non-LLM domain data remain with their current owners. A module fingerprint
+is derived from its manifest-selected module and shared files, rather than from
+an entire asset tree. The relocation is accepted to cause a one-time checkpoint
+invalidation.
+
+This decision supersedes only the physical asset-co-location portion of
+ADR-0004's decision that places domain-specific prompt fragments and schemas
+within the domain tree. ADR-0004's domain-first packaging and registrar
+ownership decisions remain accepted.
+
+## Alternatives Considered
+
+- Keep package-local assets. This preserves physical co-location with code but
+  makes prompt-author discovery and cross-family review unnecessarily costly.
+- Use `internal/llmassets`. This would hide content from legitimate owners
+  outside the `internal` subtree and would make the root asset boundary depend
+  on implementation-layer placement.
+- Build a behavioral central registry. This would mix content discovery with
+  prompt selection and registration behavior, moving module semantics into a
+  shared registry.
+- Use runtime filesystem overlays. This would add runtime configuration and
+  failure modes where compile-time embedded content is sufficient.
+
+## Consequences
+
+Prompt authors can find in-scope LLM content in one top-level tree while module
+packages continue to define its meaning and registration. Consumers have an
+explicit, narrow dependency on only the content they need. The root package is
+intentionally importable but must remain a stable, content-only leaf rather
+than becoming a general extension API.
+
+The initial relocation invalidates existing checkpoints once. Later checkpoint
+identity changes remain limited to the manifest-selected prompt and shared
+content, so unrelated files do not trigger recomputation.

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/cli.md

@@ -40,7 +40,7 @@ pipeline ID and **--input** are required.
 | **--debug-dir path** | Override the debug-bundle root. Requires **--debug**. |
 | **--only lane-a,lane-b** | Run only the selected comma-separated artifact lanes when that selection is valid for the configured pipeline. |
 | **--llm-profile id** | Highest-precedence configured profile for selected LLM-backed bindings and validators; it replaces binding and [pipeline](config.md#pipelines) defaults. |
-| **--session-id id** | Supply a non-empty prompt session identifier to LLM-backed module calls. |
+| **--session-id id** | Override the generated prompt session identifier with a non-empty value for LLM-backed module calls. |
 | **--reasoning-effort value** | Replace the selected PromptKit profile's reasoning effort for every LLM-backed call in this run. The value must be non-empty and the flag may be specified only once. |
 | **--clear-reasoning-effort** | Clear reasoning effort inherited from the selected PromptKit profile for every LLM-backed call in this run. |
 | **--reference selector=path** | Add or replace a file reference binding. Repeatable. |
@@ -57,6 +57,16 @@ Persistent reasoning settings remain a PromptKit profile concern.
 **--recompute-step** requires **--resume**; checkpoint requirements and reuse
 behavior are documented in [Operations](operations.md).
 
+Every run uses one effective prompt session. Without **--session-id**, Notarius
+generates a stable `notarius:v1:` identifier from the trimmed resolved input
+module key and the input file's exact raw bytes. The same module and bytes
+therefore produce the same identifier, regardless of pipeline, references,
+profile, retries, or run settings. An explicit non-empty value replaces that
+default. Session identifiers are visible to providers; they are non-secret
+correlation identifiers, not credential storage. See
+[Operations](operations.md#operational-limits) for privacy and workflow
+guidance.
+
 ### Reference selectors
 
 Use **--reference** only for a reference slot declared by the selected

docs/config.md

@@ -58,7 +58,7 @@ Built-in defaults are:
 
 | Field | Default |
 | --- | --- |
-| **concurrency.total_llm** | 1 |
+| **concurrency.total_llm** | 16 |
 | **concurrency.stage_workers.extract** | Effective **total_llm** |
 | **output.directory** | **./notarius-output** |
 | **cache.chunk_plans.mode** | **auto** |
@@ -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:
-        extract: dnd/npcs
-        normalize: dnd/npcs
+      npc-registry:
+        extract: dnd/npc-registry
+        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
@@ -370,14 +371,38 @@ 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). |
-| **npcs** | Normalized NPC registry. Optional for spells and combat turns; required for NPC interactions. |
-| **scene_descriptions** | Required normalized scene-description artifact for combat-turn extraction. |
+| **location_registry** | Required normalized location registry for location-occurrence 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_occurrences** | Required normalized NPC-occurrence artifact for enemy-event extraction. |
+
+Registry-backed occurrence and enemy-event artifact slots have the following
+exact binding contracts. Durable semantics and wire shapes remain in their
+[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 |
+| --- | --- | --- | --- | --- |
+| `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_occurrences` | `dnd/npc-occurrence-list` | `application/json` | 1,048,576 bytes | extract only |
+| `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**. The complete example
-shows generated **npcs** and **scene_descriptions** bindings.
+normalized combat-turn module may use optional **npc_registry**. Location occurrences
+require **location_registry** for extraction and normalization. Item occurrences require
+**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.
 
 ## Production Module Keys
 
@@ -385,18 +410,29 @@ shows generated **npcs** and **scene_descriptions** bindings.
 | --- | --- |
 | Input | **seriatim** |
 | Chunk | **generic**, **dnd/scenes** |
-| Extract | **dnd/spells**, **dnd/npcs**, **dnd/combat-turns**, **dnd/item-events**, **dnd/npc-interactions**, **dnd/scene-descriptions** |
+| 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** |
+| 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/scenes` and every D&D extractor are `llm_backed`. The
+`dnd/npc-registry`, `dnd/location-registry`, and `dnd/item-registry`
+normalizers are also `llm_backed` for bounded duplicate proposals; every other
+D&D normalizer is `deterministic`. LLM-backed bindings use the effective
+[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 interactions](integrations/dnd-npc-interaction-artifacts.md),
+[NPC registry](integrations/dnd-npc-registry-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), and
-[scene descriptions](integrations/dnd-scene-description-artifacts.md).
+[item registry](integrations/dnd-item-registry-artifacts.md),
+[item occurrences](integrations/dnd-item-occurrence-artifacts.md),
+[scene descriptions](integrations/dnd-scene-description-artifacts.md),
+[enemy events](integrations/dnd-enemy-event-artifacts.md),
+[location registry](integrations/dnd-location-registry-artifacts.md), and
+[location occurrences](integrations/dnd-location-occurrence-artifacts.md).
 
 ## Production Validator Keys And Default Chains
 
@@ -406,11 +442,15 @@ 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** |
-| 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 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** |
+| 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** |
+| 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
 ordered chains. Each row lists extract then normalize; spell chains are the
@@ -419,11 +459,15 @@ 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 |
-| 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 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 |
+| 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 |
+| 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
 above; select an explicit override when a different compatible chain is

docs/consumers/subprocess.md

@@ -27,10 +27,13 @@ notarius run pipeline-id \
 ```
 
 Use absolute paths for supplied input, configuration, output-root, and
-reference files. When a stable prompt session identifier or references are
-needed, pass the supported CLI flags. Supply credentials through Notarius's
-documented configuration and environment mechanisms, never as command-line
-arguments or generated secret-bearing configuration.
+reference files. Notarius generates a stable prompt session for the resolved
+input module and exact input bytes. Pass **--session-id** only when intentionally
+grouping different invocations under a different session. Supply credentials
+through Notarius's documented configuration and environment mechanisms, never
+as command-line arguments or generated secret-bearing configuration. In
+particular, a session identifier is provider-visible and is not a credential
+mechanism.
 
 Wait for the process before interpreting standard output. Only an exit status
 of 0 permits decoding the receipt. On a nonzero exit, retain standard error for
@@ -52,10 +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
-`evidence_refs` entry as the citation to source material. Its surrounding
-context range and included units explain the citation, but do not widen or
-replace the cited source reference.
+Context contract](../integrations/evidence-context.md). Decode its top-level
+source-unit array as a reading excerpt. Obtain authoritative citations and lane
+provenance from the normalized lane artifacts; the excerpt has neither and its
+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
@@ -70,5 +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
-only when that source content is authorized for the recipient.
+metadata and can cover most of an input; preserve and share it only when that
+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 +63,9 @@ 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
-broader NPC occurrences. The [JSON output contract](json-output.md) defines
-publication, and [D&D module internals](../internal/dnd.md) describes routing
-and validation mechanics.
+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,
+and [D&D module internals](../internal/dnd.md) describes routing and validation
+mechanics.

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

@@ -0,0 +1,114 @@
+# D&D Enemy-Event Artifact
+
+This contract defines the durable, source-grounded enemy-event occurrence list.
+It records enemies directly established as opposing the party and explicitly
+observed combat outcomes. It is an ordered observation artifact from which a
+consumer may derive a ledger; it is not a ledger, encounter roster, or terminal
+state model.
+
+## Identity and compatibility
+
+| Property | Value |
+| --- | --- |
+| Artifact kind | `dnd/enemy-event-list` |
+| Schema ID | `notarius.dnd.enemy_events` |
+| Schema name | `notarius_dnd_enemy_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 these required fields:
+
+| Field | Contract |
+| --- | --- |
+| `name` | Non-empty display name or directly grounded collective subject label. |
+| `kind` | `engaged`, `killed`, `fled`, `captured`, or `incapacitated`. |
+| `source_refs` | One or more current-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": "Ashfang",
+      "kind": "engaged",
+      "source_refs": [
+        {"source_id": "session-7", "start_unit_id": 41, "end_unit_id": 42}
+      ]
+    },
+    {
+      "name": "Ashfang",
+      "kind": "fled",
+      "source_refs": [
+        {"source_id": "session-7", "start_unit_id": 57, "end_unit_id": 58}
+      ]
+    }
+  ]
+}
+```
+
+## Event semantics and evidence
+
+| Kind | Required evidence |
+| --- | --- |
+| `engaged` | The subject is directly established as actively opposing the party in combat. At most one engagement is emitted for one subject in one combat scene. |
+| `killed` | The transcript explicitly establishes that the subject died or was killed. Damage, defeat, disappearance, or combat ending is insufficient. |
+| `fled` | The subject explicitly escapes, retreats, or otherwise leaves combat to avoid continued engagement. Movement or absence from later turns is insufficient. |
+| `captured` | The subject is explicitly taken prisoner or secured under the party's control. A grapple or temporary restraint alone is insufficient. |
+| `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-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.
+
+Extraction is limited to chunks with an exact combat-scene classification. An
+exact non-combat classification produces an accepted empty list. Missing or
+mismatched classification also produces an accepted empty list and a
+`scene_classification_unavailable` warning.
+
+## Subjects, normalization, and order
+
+A subject matching the normalized NPC registry uses that registry's canonical
+display name. Unmatched hostile creatures, summoned entities, and directly
+grounded groups remain valid subjects. An unnamed homogeneous group uses the
+narrowest transcript-grounded label, such as `Orcs`, `One orc`, or `Remaining
+orcs`; the artifact never invents synthetic member identities or quantities.
+Party members, allies, neutral observers, mentioned-but-absent enemies, hazards,
+traps, and environmental effects are excluded.
+
+Normalization collapses surrounding and repeated internal whitespace in subject
+display values, canonicalizes recognized registry names, canonicalizes and
+deduplicates exact source ranges, then orders events by valid evidence
+chronology, normalized subject identity, display name, kind, and reference
+sequence. The deterministic kind tie order is `engaged`,
+`incapacitated`, `captured`, `fled`, then `killed`. Only entries with the same
+normalized name, kind, and complete canonical evidence sequence are collapsed.
+Different kinds, evidence, repeated engagement in separate scenes, and later
+outcomes remain separate. A later engagement for the same named subject is
+preserved after an earlier outcome because the artifact does not assert an
+irreversible state transition.
+
+## Non-goals
+
+The artifact has no NPC or scene ID, quantity, confidence, description,
+rationale, summary, current state, or inferred terminal outcome. It does not
+emit `active` or `unresolved`; consumers may derive an unresolved ledger view
+only when an engagement has no later explicit outcome. It never infers an
+outcome from turn absence, scene termination, initiative order, hit-point
+guesses, or other artifacts.
+
+The [JSON output contract](json-output.md) defines publication. Configuration
+keys, required generated-reference slots, and validator-chain selection are
+defined in the [configuration reference](../config.md). Implementation and
+prompt-grounding mechanics are described in the
+[D&D module internals](../internal/dnd.md).

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

@@ -0,0 +1,86 @@
+# D&D Location-Occurrence Artifact
+
+This contract defines the durable occurrence list produced by
+`dnd/location-occurrences`. It records source-grounded ways the party relates
+to locations in a required normalized location registry; it does not extend
+that registry or infer a place absent from it.
+
+## Identity and compatibility
+
+| Property | Value |
+| --- | --- |
+| Artifact kind | `dnd/location-occurrence-list` |
+| Schema ID | `notarius.dnd.location_occurrences` |
+| Schema name | `notarius_dnd_location_occurrences_v1` |
+| Schema version | `v1` |
+| Media type | `application/json` |
+
+`v1` accepts one strict JSON object with required `occurrences`; the array may
+be empty. Occurrence and source-reference objects reject unknown fields. An
+incompatible shape change requires a new schema version.
+
+## Wire shape
+
+Each occurrence has these required fields:
+
+| Field | Contract |
+| --- | --- |
+| `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. |
+
+A 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": [
+    {
+      "location_id": "location:sha256:fb05475da0fc7debf994b517e1906ffe7209887a6a1ec306356d84de820b1a24",
+      "name": "Moon Gate",
+      "kind": "visited",
+      "source_refs": [
+        {"source_id": "session-7", "start_unit_id": 12, "end_unit_id": 13}
+      ]
+    }
+  ]
+}
+```
+
+## Occurrence categories
+
+| Kind | Meaning |
+| --- | --- |
+| `visited` | The transcript establishes physical party presence, including arrival, continuing presence, or departure. |
+| `planned` | The party explicitly proposes, intends, or agrees to future travel; speculation alone is not enough. |
+| `recalled` | The transcript explicitly recounts prior party presence before the current live events. |
+| `mentioned` | The location is explicit but no stronger category applies, including lore, directions, third-party activity, non-actionable speculation, a mere hypothetical reference, or out-of-character discussion. |
+
+For overlapping evidence, precedence is `visited`, then `planned`, then
+`recalled`, then `mentioned`. For example, “What if we went to Moon Gate?” is
+eligible as `mentioned` when its narrow evidence explicitly references that
+registry location, but it is not `planned` without an actual proposal,
+intention, or agreement to travel. Inferred, unstated, uncertain, and
+unsupported places or occurrences are omitted. Normalization
+canonicalizes the registry name, orders and deduplicates source references, and
+orders occurrences by source chronology, location ID, name, kind, and reference
+sequence. It collapses only exact duplicates with the same ID, kind, and
+complete canonical evidence sequence.
+
+## Required grounding and evidence
+
+Both extraction and normalization require exactly one `location_registry` reference of
+kind `dnd/location-registry`, media type `application/json`, and at most 1 MiB. The
+registry provides identity grounding only. The model selects a supplied
+contextual name-and-registry-reference descriptor, and Notarius resolves it
+into the exact durable ID/name pair. Unknown, partial, or ambiguous selections
+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)
+for implementation behavior, and the [JSON output contract](json-output.md)
+for publication.

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

@@ -0,0 +1,93 @@
+# D&D Location Registry Artifact
+
+This contract defines the durable, source-grounded location registry produced
+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.
+
+## Identity and compatibility
+
+| Property | Value |
+| --- | --- |
+| Artifact kind | `dnd/location-registry` |
+| Schema ID | `notarius.dnd.location_registry` |
+| Schema name | `notarius_dnd_location_registry_v1` |
+| Schema version | `v1` |
+| Media type | `application/json` |
+| 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
+incompatible artifact shape or identity-policy change uses a new version or
+policy.
+
+## Wire shape and identity
+
+Each location has these required fields:
+
+| Field | Contract |
+| --- | --- |
+| `id` | `location:sha256:` followed by 64 lowercase hexadecimal characters. |
+| `name` | Non-empty transcript-established display name. |
+| `source_refs` | One or more transcript evidence ranges that identify the place. |
+
+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
+{
+  "locations": [
+    {
+      "id": "location:sha256:fb05475da0fc7debf994b517e1906ffe7209887a6a1ec306356d84de820b1a24",
+      "name": "Moon Gate",
+      "source_refs": [
+        {"source_id": "session-7", "start_unit_id": 4, "end_unit_id": 5}
+      ]
+    }
+  ]
+}
+```
+
+The ID is deterministic and scoped to the source document. 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, using the earliest canonical source reference as the anchor:
+
+```text
+["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
+`location:sha256:` prefix. Equal display names are allowed when their evidence
+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 with a
+stable proper name or unique in-world designation, such as named planes,
+regions, settlements, districts, buildings, rooms, landmarks, routes, and
+geographic features. Generic, temporary, relative, and descriptive phrases
+such as “the room,” “the bar,” “the hallway,” “outside,” and “upstairs” are not
+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
+records. The proposal is validated and applied conservatively; invalid or
+unusable proposals retain the deterministic result with retry or fallback
+diagnostics. The registry's source references establish registry provenance,
+not evidence for later artifacts.
+
+## Consumers and publication
+
+`dnd/location-occurrences` requires one approved location registry through its
+`location_registry` reference slot. Its prompt receives contextual selectors
+containing a canonical name and registry references; Notarius resolves a
+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-artifacts.md

@@ -1,69 +0,0 @@
-# D&D NPC Artifact
-
-This contract defines the durable NPC registry produced by `dnd/npcs`. It is a
-minimal, source-grounded identity registry for other D&D artifacts, not a
-character sheet or a relationship summary.
-
-## Identity and compatibility
-
-| Property | Value |
-| --- | --- |
-| Artifact kind | `dnd/npc-list` |
-| Schema ID | `notarius.dnd.npcs` |
-| Schema name | `notarius_dnd_npcs_v1` |
-| Schema version | `v1` |
-| Media type | `application/json` |
-| Identity policy | `dnd.npcs.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
-artifact shape or identity-policy change uses a new version or policy.
-
-## Wire shape and identity
-
-Each NPC has these required fields:
-
-| Field | Contract |
-| --- | --- |
-| `id` | `npc:sha256:` followed by 64 lowercase hexadecimal characters. |
-| `name` | Non-empty canonical display name. |
-| `source_refs` | One or more transcript evidence ranges for the identity. |
-
-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
-{
-  "npcs": [
-    {
-      "id": "npc:sha256:99a16589618a04f535a7d21fdcc71a0b1c05d22f752cd492065b1086d97bc3d7",
-      "name": "Mira Thorn",
-      "source_refs": [
-        {"source_id": "session-7", "start_unit_id": 4, "end_unit_id": 5}
-      ]
-    }
-  ]
-}
-```
-
-The ID is deterministic: normalize the name to Unicode NFKC, normalize the
-supported apostrophe forms, collapse whitespace, case-fold it, SHA-256 the
-result, then prefix the lowercase hexadecimal digest with `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.
-
-## Scope and consumers
-
-Only individually identifiable NPC names with transcript evidence belong in
-this artifact. Groups, generic roles, invented labels, and descriptive
-enrichment are excluded. Its source references prove registry provenance; they
-do not become evidence for a spell, interaction, or combat occurrence.
-
-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).
-The [JSON output contract](json-output.md) defines publication, and
-[D&D module internals](../internal/dnd.md) owns pipeline mechanics.

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` |
-| Schema ID | `notarius.dnd.npc_interactions` |
-| Schema name | `notarius_dnd_npc_interactions_v1` |
+| Artifact kind | `dnd/npc-occurrence-list` |
+| Schema ID | `notarius.dnd.npc_occurrences` |
+| 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
-empty. Interaction and source-reference objects reject unknown fields. An
+`v1` is a strict JSON object with required `occurrences`; the array may be
+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 |
 | --- | --- |
@@ -65,14 +67,24 @@ for uncertain classification.
 
 ## Identity, evidence, and order
 
-The required normalized [NPC artifact](dnd-npc-artifacts.md) resolves `name`.
-Registry references are provenance only and never replace an interaction's own
-evidence. Normalization canonicalizes recognized registry names, orders and
-deduplicates exact source references, then orders interactions by valid source
+The required normalized [NPC registry artifact](dnd-npc-registry-artifacts.md)
+supplies names-only contextual grounding to the model. Notarius resolves the
+selected name and writes the exact `{npc_id, name}` pair. An unknown or
+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 and the [JSON output contract](json-output.md) for publication.
-Pipeline mechanics are described in [D&D module internals](../internal/dnd.md).
+occurrences. The [enemy-event artifact](dnd-enemy-event-artifacts.md) consumes
+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

@@ -0,0 +1,92 @@
+# D&D NPC Registry Artifact
+
+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.
+
+## Identity and compatibility
+
+| Property | Value |
+| --- | --- |
+| Artifact kind | `dnd/npc-registry` |
+| Schema ID | `notarius.dnd.npc_registry` |
+| Schema name | `notarius_dnd_npc_registry_v1` |
+| Schema version | `v1` |
+| Media type | `application/json` |
+| 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
+artifact shape or identity-policy change uses a new version or policy.
+
+## Wire shape and identity
+
+Each NPC has these required fields:
+
+| Field | Contract |
+| --- | --- |
+| `id` | `npc:sha256:` followed by 64 lowercase hexadecimal characters. |
+| `name` | Non-empty canonical display name. |
+| `source_refs` | One or more transcript evidence ranges for the identity. |
+
+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
+{
+  "npcs": [
+    {
+      "id": "npc:sha256:35ba5f679aee69e07ae3bd65c44278f29539d5dc9bb5225db1c0060555b23221",
+      "name": "Mira Thorn",
+      "source_refs": [
+        {"source_id": "session-7", "start_unit_id": 4, "end_unit_id": 5}
+      ]
+    }
+  ]
+}
+```
+
+The ID is deterministic: normalize the name to Unicode NFKC, normalize the
+supported apostrophe forms, collapse whitespace, case-fold it, then serialize
+`["dnd.npc_registry.identity.v1", comparison_name]` as compact JSON. SHA-256
+those UTF-8 bytes and prefix the lowercase hexadecimal digest with
+`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.
+
+When evidence supports a semantically duplicate group, the canonical display
+name is one of that group's supplied candidates. A complete, stable proper name
+is preferred over an abbreviation. An unadorned proper name is preferred over
+the same name plus a contextual class, role, title, or relationship descriptor
+unless the transcript establishes that descriptor as part of the person's
+name. A longer candidate is not preferred solely because it includes such a
+descriptor.
+
+## Scope and consumers
+
+Only individually identifiable NPC names with transcript evidence belong in
+this artifact. A factual third-party mention can establish an identity even if
+the NPC is not present, speaking, or acting in the cited passage. Names used
+only in hypothetical, speculative, or imagined examples are excluded, as are
+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 occurrence](dnd-npc-occurrence-artifacts.md).
+Occurrence consumers receive names-only grounding; Notarius resolves the
+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-scene-description-artifacts.md

@@ -62,8 +62,9 @@ durable fields, or the same source range with different kind, title, or
 summary, is invalid. It does not merge adjacent ranges, alter prose, or infer
 missing scenes.
 
-The [combat-turn artifact](dnd-combat-turn-artifacts.md) uses an exact matching
+The [combat-turn artifact](dnd-combat-turn-artifacts.md) and
+[enemy-event artifact](dnd-enemy-event-artifacts.md) use an exact matching
 `combat` scene only as eligibility control; scene title, summary, and source
-reference never become combat evidence. Publication is defined by the
+reference never become their evidence. Publication is defined by the
 [JSON output contract](json-output.md); implementation details live in
 [D&D module internals](../internal/dnd.md).

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
-[Configuration](../config.md#module-bindings-and-validators); its logical-file
-discovery is owned by [Published JSON Output](json-output.md).
+by the production JSON output. It is a selected source-unit excerpt for
+convenient reading alongside normalized lane artifacts; it is not a second
+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`,
-`window_units`, `selected_lanes`, and `contexts` fields. `selected_lanes` and
-`contexts` are always arrays; an enabled configuration with no accepted direct
-evidence publishes `contexts: []`.
+The v1 payload is a top-level JSON array of generic source units. There is no
+wrapper, source-level metadata, context grouping, lane identifier, or evidence
+reference in the payload. An enabled configuration with no contributing
+accepted evidence publishes `[]`.
 
 ```json
-{
-  "source_id": "session-alpha",
-  "source_digest": "sha256:0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef",
-  "window_units": 1,
-  "selected_lanes": ["npcs", "spells"],
-  "contexts": [
-    {
-      "context_ref": {
-        "source_id": "session-alpha",
-        "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": 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
+    }
+  }
+]
 ```
 
-Each context requires a `context_ref` object and `evidence_refs` and `units`
-arrays. `context_ref` identifies the first and last included unit. Each
-evidence entry contains a selected `lane_id` and an original `source_ref`. A
-unit uses the existing source-unit shape: required `id`, `kind`, `text`, and
-self `ref`, plus optional JSON-object `metadata`. Fixed payload objects reject
-unknown fields; unit metadata may contain application-defined JSON values.
+Each source unit has required `id`, `kind`, `text`, and self `ref` fields.
+`ref` contains `source_id`, `start_unit_id`, and `end_unit_id`, and both unit
+endpoints identify that unit's `id`. A unit may also contain source-owned
+`metadata`, an open-ended JSON object. Fixed unit and reference fields are
+strict: consumers must reject unknown fixed fields, malformed units, invalid
+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
-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.
+## Selection And Citations
 
-Only accepted outputs from the configured lane allowlist contribute. Rejected,
-failed, absent, and lane-filtered outputs do not contribute. The artifact never
-contains raw input bytes, prompts, model responses, auxiliary reference
-content, credentials, or filesystem paths.
+The framework obtains direct source references only through typed evidence
+projections of accepted normalized artifacts in the configured lane allowlist.
+It validates each reference against the current source document, expands its
+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
-document position order, not numeric unit-ID order. Direct evidence entries
-are deterministically ordered by lane and source reference. Overlapping or
-contiguous windows merge, and each source unit appears at most once in the
-resulting contexts.
+The excerpt contains at most every generic source unit once. It can therefore
+equal the complete generic source document when coverage is broad or the
+window is large. No byte-, token-, or compression-size guarantee is made, and
+the framework does not truncate the excerpt to meet an arbitrary size limit.
+
+## 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
-use it should preserve the artifact and its schema identity with the run
-provenance, and should treat its source text and metadata as sensitive durable
-content.
+do not need it must tolerate an absent descriptor. Consumers that do use it
+should validate the descriptor and payload before use, retain the artifact with
+its schema identity when needed for a run record, and read citations from the
+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`.
@@ -71,11 +71,15 @@ 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),
-[NPC interactions](dnd-npc-interaction-artifacts.md),
+[spells](dnd-spell-artifacts.md), [NPC registry](dnd-npc-registry-artifacts.md),
+[NPC occurrences](dnd-npc-occurrence-artifacts.md),
 [combat turns](dnd-combat-turn-artifacts.md),
-[item events](dnd-item-event-artifacts.md), and
-[scene descriptions](dnd-scene-description-artifacts.md).
+[item registry](dnd-item-registry-artifacts.md),
+[item occurrences](dnd-item-occurrence-artifacts.md),
+[scene descriptions](dnd-scene-description-artifacts.md),
+[enemy events](dnd-enemy-event-artifacts.md),
+[location registry](dnd-location-registry-artifacts.md), and
+[location occurrences](dnd-location-occurrence-artifacts.md).
 
 ## `manifest.json`
 
@@ -98,6 +102,11 @@ summarize results without embedding lane payload bytes. A chunk-plan summary is
 provenance for the plan used by this run; cache records, debug artifacts, and
 other operational state are not published as bundle files.
 
+When present, `metadata.session_id` is the effective non-secret routing
+correlation identifier used for the run. It can be visible to providers and is
+not a substitute for a cache or checkpoint identity. Its generation and
+override behavior are defined by the [CLI reference](../cli.md#run).
+
 Each `llm_profiles` entry identifies effective, non-secret LLM execution
 provenance:
 

docs/integrations/pkg-promptkit.md

@@ -48,11 +48,13 @@ adapter boundary. It also retains responsibility for pipeline retries,
 scheduling, debug persistence, redaction, profile provenance, and conversion
 from private model responses into durable domain artifacts.
 
-Notarius sends its trimmed run session through PromptKit's direct session
+Notarius sends one stable effective session through PromptKit's direct session
 field, which is authoritative for provider session behavior. It also retains
 the same value as the `session_id` prompt variable for maintained prompt
-compatibility. Session IDs are stable, non-secret correlation identifiers and
-may be exposed to providers and provider observability.
+compatibility. The generated identifier is 76 ASCII characters, within
+PromptKit v0.5.0's 256-code-point session limit. Session IDs are non-secret
+correlation identifiers and may be exposed to providers and provider
+observability. The CLI contract owns generation and override behavior.
 
 Notarius records PromptKit's selected backend ID and effective reasoning
 setting as optional run-manifest provenance. Endpoint-only profiles have no

docs/internal/cli.md

@@ -89,9 +89,11 @@ handoff:
    profiles;
 4. materialize external or generated references and record redacted invocation
    and resolution provenance when debug capture is enabled;
-5. construct registries, the scheduled LLM client, prepared modules, and the
-   requested cache/checkpoint collaborators;
-6. read the source input and invoke the framework runner; and
+5. construct registries, the scheduled LLM client, and prepared modules;
+6. read the source input once, resolve its effective session from the explicit
+   override or resolved input module and raw bytes, then construct requested
+   checkpoint collaborators and invoke the framework runner with that same
+   value; and
 7. write the runner's logical output files only after a successful run, then
    complete the command report and user-facing result.
 
@@ -102,6 +104,13 @@ final command result. Detailed state lifecycle, resume handling, and physical
 path confinement are maintained in [Run State Internals](state.md) and
 [Operations](../operations.md).
 
+The CLI owns the versioned generated-session policy and resolves the sole
+effective value before checkpoint construction. It records that value in the
+final debug invocation summary when capture is enabled and passes it unchanged
+to checkpoint identity and `pipeline.RunInput`. The public flag and stability
+contract are defined by the [CLI reference](../cli.md#run); framework and LLM
+packages only transport the supplied value.
+
 For `run --json`, the CLI constructs and encodes its private run-result receipt
 after a successful runner result is available, before it publishes logical
 output files. It writes the prepared receipt to standard output only after

docs/internal/dnd.md

@@ -7,17 +7,21 @@ selectable keys, bindings, reference syntax, and default validator chains.
 
 ## Durable Artifact Contracts
 
-The six 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) |
-| NPC interactions | [NPC-interaction artifacts](../integrations/dnd-npc-interaction-artifacts.md) |
+| Item occurrences | [item-occurrence artifacts](../integrations/dnd-item-occurrence-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) |
+| Location registry | [location-registry artifacts](../integrations/dnd-location-registry-artifacts.md) |
+| Location occurrences | [location-occurrence artifacts](../integrations/dnd-location-occurrence-artifacts.md) |
 
 ## Family Composition
 
@@ -25,9 +29,9 @@ 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, and NPC normalization are
-registered as `llm_backed`; the remaining current D&D mergers and normalizers
-are `deterministic`. The metadata is available to catalog inspection and
+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
 pipeline profile. Configuration remains the canonical owner of the exact keys,
 profile precedence, and validator order.
@@ -40,50 +44,69 @@ the contracts above define durable data.
 
 ## Prompt Construction
 
-D&D extractors assemble prompts from an ordered manifest of shared and
-module-owned assets. Reuse the shared D&D system, evidence, identity,
-reference, and transcript assets instead of copying their text into individual
-modules. A manifest’s declared sequence, including cache-control placement, is
-part of the prompt behavior.
+D&D LLM-facing content lives beneath `assets/dnd/`. Each module contributes a
+local `prompt.yaml` declaration and `instructions.md`; input-specific files
+such as a catalog, registry, grounding projection, or candidate collection are
+local only when that module needs them. New extractor content uses its feature
+subtree, while families with both extraction and normalization content use their
+`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.
+
+The owning module’s manifest is the source of truth for which local and shared
+assets are selected, their mount paths, their message order, cache controls,
+and the files included in its prompt fingerprint. Shared fragments belong to
+the D&D shared implementation and are selected by name rather than copied into
+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 embeds that fallback profile with the maintained
-OpenRouter model, timeout, and service-tier policy. An operator may provide a
-complete profile with the same ID through the configured PromptKit source; that
-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
+profile. The D&D registrar registers the fallback, while an operator can
+replace it with a complete profile of the same ID from the configured PromptKit
+source. Deployment profile selection is documented in
 [Configuration](../config.md#promptkit-profiles).
 
-All extraction prompts share this four-message rendered prefix: the system
-message without cache control, the identity message without cache control, the
-campaign-reference message with ephemeral cache control, and the chunk
-transcript message with ephemeral cache control. This gives equivalent
-extraction requests the same reusable prefix through their source material.
+The D&D transcript assets have distinct consumers. Scene chunking consumes the
+complete-session `common-dnd-transcript-full.md`, while extraction prompts
+consume the current-chunk `common-dnd-transcript-chunk.md`. NPC, location, and
+item normalization instead mount the generic semantic-reconciliation
+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
-tasks, and instructions follow the transcript because they are not universal
-across all extraction lanes. The final instructions message carries ephemeral
-cache control; evidence, registry, catalog, and task messages do not. Preserve
-this division when changing an extractor or its assets so prompt-cache behavior
-remains stable.
+Extraction prompts render the common system and identity messages first, then
+cached campaign references and the cached chunk transcript. Evidence policy and
+any lane-specific registry, catalog, or grounding projection follow that
+prefix. The final module instructions message is ephemeral. This keeps the
+reusable extraction prefix identical while preserving the lane-specific suffix.
 
-The other D&D LLM prompts intentionally follow different patterns. Scene
-chunking has no sibling extraction lane with which to share its full transcript,
-so it renders campaign references before its task and instructions, then places
-the cacheable full transcript last. NPC normalization keeps its task and
-cacheable instructions before the candidate collection, followed by the
-cacheable transcript windows: candidates must be available before their
-supporting evidence is evaluated, and those windows are not a cross-lane
-prefix. Mounted assets and their declared message order determine the prompt
-fingerprint, so intentional prompt edits continue to invalidate stale
-checkpoints.
-
-All extractors use the shared prompt-input preparation rules. The current chunk
-is copied into transcript material; player, party, glossary, and compatible
-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.
+Scene chunking intentionally uses a different order: system, cached campaign
+references, uncached module instructions, then the final ephemeral full
+transcript. Entity normalization also has its own order: D&D system, mandatory
+generic protocol, ephemeral domain semantic instructions, generic candidate
+presentation, and final ephemeral generic transcript windows. These orders and
+cache controls are prompt behavior; change them only through the owning
+manifest and prompt declaration.
 
 ## Evidence, Candidates, And Normalization
 
@@ -96,19 +119,63 @@ 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).
 
-Normalizers are deterministic for spells, combat turns, item events, NPC
-interactions, and scene descriptions. They canonicalize display values and
-evidence, use source-document order for stable output, and issue bounded
-warnings for changes or collapsed duplicates. The NPC normalizer is the
-intentional exception: it first produces a deterministic candidate set, then
-uses a bounded structured-LLM proposal to reconcile identity groups. Invalid
-or unusable proposals retain the deterministic result and surface retry or
-fallback diagnostics; the model does not directly replace durable records.
+Enemy-event extraction additionally rejects a second `engaged` observation for
+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 occurrences, NPC
+occurrences, scene descriptions, enemy events, and location occurrences. They
+canonicalize display values and evidence, use source-document order for stable
+output, and issue bounded warnings for changes or collapsed duplicates. NPC,
+item, and location registry normalizers are intentional exceptions: each first
+produces a deterministic candidate set, then may use a bounded structured-LLM
+proposal to reconcile identity groups.
+
+## 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
 
@@ -118,30 +185,55 @@ 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
-actors for spells and combat turns and are required for NPC interactions, but
-they do not supply evidence. Scene-description registries are eligibility-only
-projections: they retain the current chunk’s classification data, not scene
-prose or evidence, and exist to route combat extraction.
+NPC and item registry consumers receive names-only grounding. Location
+consumers receive a contextual selector containing the canonical name and the
+registry references needed to distinguish same-name places. The calling module
+resolves those supplied selections locally and maps them into the unchanged
+durable ID/name pair; an unknown or ambiguous selection rejects the complete
+occurrence result rather than accepting a partial mapping. The NPC registry
+additionally supplies names-only actor grounding to spells, combat turns, and
+enemy events.
+
+Registry references establish a registry identity and may disambiguate a
+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. |
-| NPC interactions | Requires the normalized NPC registry at extraction and normalization, using it for canonical actor grounding only. |
+| 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. |
+| 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-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. |
+| 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
 empty-result behavior in more detail:
 [combat turns](../integrations/dnd-combat-turn-artifacts.md) and
 [scene descriptions](../integrations/dnd-scene-description-artifacts.md).
+The [enemy-event contract](../integrations/dnd-enemy-event-artifacts.md)
+defines its durable semantics; [Configuration](../config.md) owns its
+selectable bindings and validation chains.
 
 ## Focused Verification
 

docs/internal/llm.md

@@ -24,11 +24,15 @@ 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,
-maps the trimmed request session to PromptKit's direct per-run session field,
-retains the same value as the `session_id` prompt variable for maintained
-prompt compatibility, and forwards profile selection. It then creates one
+passes the supplied request session through to PromptKit's direct per-run
+session field, retains the same value as the `session_id` prompt variable for
+maintained prompt compatibility, and forwards profile selection. It does not
+derive or replace session values; the CLI owns that policy. It then creates one
 frozen prepared execution, captures its caller-owned credential-redacted
 details for debug material, and executes that exact snapshot through
 PromptKit's prepared-execution boundary. The direct field
@@ -98,7 +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
@@ -124,16 +129,40 @@ the corresponding PromptKit filesystems and rejects invalid roots, unreadable
 assets, duplicate paths, and missing prompt or schema files during preparation.
 Fallback assets receive a safe content digest for checkpoint identity; raw
 paths and bytes are never included. The framework’s `promptfs` helper combines
-module-owned prompt files with reusable domain fragments without making the
+module-selected prompt files with reusable domain fragments without making the
 framework depend on D&D content.
 
-Each LLM-backed module owns its prompt declaration, package-specific assets,
-and private response schema. Shared D&D wording is owned by the D&D shared
-asset package; the detailed D&D conventions are in
-[D&D Module Internals](dnd.md). The mounted prompt assets used by a module also
-determine its prompt fingerprint. Schema loaders validate JSON, attach identity
-and digest metadata, make defensive copies, and expose diagnostics without raw
-schema bytes.
+LLM-facing content is embedded once by the root `assets` package. Each consumer
+uses only its scoped subtree, while the module retains ownership of its prompt
+declaration, ordered manifest, private response-schema identity, and
+registration. Shared D&D fragments are selected by D&D's shared implementation;
+the detailed convention is in [D&D Module Internals](dnd.md). This physical
+arrangement and its data-only boundary are defined by
+[Architecture](../policy/architecture.md) and
+[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
@@ -167,7 +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 +29,8 @@ 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. |
 
@@ -48,8 +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
-  construction, validation, and reference mechanics.
+- [Module Internals](modules.md): generic extension registration, artifact
+  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

@@ -10,11 +10,11 @@ own durable output shapes. Concrete production extensions are covered by
 ## Boundary
 
 The pipeline framework accepts a resolved composition, registries, shared
-dependencies, input bytes, and state/debug collaborators. It returns logical
-output files, normalized artifacts, recorded rejections and warnings, manifest
-provenance, and checkpoint decisions. The CLI owns process arguments,
-configuration discovery, physical roots, and placement of returned output
-files.
+dependencies, input bytes, a supplied prompt session, and state/debug
+collaborators. It returns logical output files, normalized artifacts, recorded
+rejections and warnings, manifest provenance, and checkpoint decisions. The
+CLI owns process arguments, configuration discovery, session resolution,
+physical roots, and placement of returned output files.
 
 The framework has one fixed shape:
 
@@ -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
-until its producing step completes.
+provenance. For a positive slot limit, it reads at most the limit plus one byte
+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
-cloned options, references, and shared dependencies. It also collects stable
-checkpoint fingerprints. Missing registrations, incompatible typed entries,
-nil implementations, and constructor failures are reported before source
-parsing or any stage operation begins.
+chunker, stage-local validators, every typed lane, and output encoder. Each
+registered builder receives its own cloned build request immediately before its
+module-owned code runs. Preparation also collects stable checkpoint
+fingerprints. Missing registrations, incompatible typed entries, nil
+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
@@ -84,6 +86,10 @@ incompatible producer prevents the consumer step from starting.
 
 The runner validates its input, installs no-op state collaborators when none
 were supplied, and serially performs source parsing and chunk-plan selection.
+It transports the supplied session unchanged to prompt-facing operations and
+run-manifest metadata; it neither derives a session nor substitutes a parsed
+source document identifier. The public session contract is owned by the
+[CLI reference](../cli.md#run).
 An accepted plan is materialized into source-addressed chunks and passes the
 configured chunk validators before any lane runs. A chunk rejection is a
 recorded pipeline outcome: lanes do not start, but the output stage can encode
@@ -111,9 +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
-approve, approve with warnings, reject, or fail. A rejection is an ordinary
-pipeline result; a validator error is a framework error.
+their target: chunks, codec-decoded typed candidates, or serialized codec
+bytes. Each typed validator receives a newly decoded value from the one
+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
-transcript, so a broad allowlist can make the evidence artifact nearly as
-sensitive and large as the source itself.
+controls to the entire bundle. Its selected source-unit excerpt may include
+every source unit once when coverage is broad or its configured window is
+large, so do not assume a byte or token reduction or reduced sensitivity.
 
 ## Chunk-Plan Cache
 
@@ -266,16 +266,18 @@ transport-wide cap. Notarius does not add another timeout around PromptKit.
 The pinned upstream boundary and profile-format links are in
 [PromptKit Integration](integrations/pkg-promptkit.md).
 
-Concurrency has two independent layers. Notarius **total_llm** is the
-application-wide provider-call limit shared by all backends, modules, retries,
-and validators. PromptKit may impose a narrower admission limit for the
-selected backend. The effective active-generation bound is the intersection of
-both limits and can therefore be lower than **total_llm**. Built-in OpenRouter
-profiles use PromptKit's upstream backend limit; endpoint-only profiles have no
-PromptKit backend limit and remain bounded by Notarius. For the configured
-local backend, a zero **concurrency_limit** leaves only the Notarius scheduler
-as a call limit. A positive value makes the effective active local-generation
-bound the smaller of **total_llm** and that local limit.
+Concurrency has two independent layers. Notarius **total_llm** defaults to 16
+and is the application-wide provider-call limit shared by all backends,
+modules, retries, and validators. PromptKit may impose a narrower admission
+limit for the selected backend. The effective active-generation bound is the
+intersection of the Notarius limit, any PromptKit backend limit, and work made
+available by the pipeline. Built-in OpenRouter profiles use PromptKit's
+upstream backend limit; endpoint-only profiles have no PromptKit backend limit
+and remain bounded by Notarius. For the configured local backend, a zero
+**concurrency_limit** leaves only the Notarius scheduler as a call limit. A
+positive value makes the effective active local-generation bound the smaller
+of **total_llm** and that local limit, so a local limit of four permits no more
+than four active local generations.
 
 For a positive local limit, PromptKit owns its default waiting capacity and
 admission behavior. When a PromptKit backend has admitted all active and queued
@@ -289,3 +291,11 @@ under [PromptKit profiles](config.md#promptkit-profiles) and
 limits and actual provider-call limits are independent. Notarius writes local
 filesystem state only; remote storage, archival, and retention automation are
 outside the implemented CLI.
+
+Every run has an effective prompt session used for provider routing and run
+provenance. The generated default is stable for the same input module and raw
+input bytes; use [**--session-id**](cli.md#run) only when intentionally grouping
+different invocations. Both generated and explicit values can be visible to
+providers, manifests, checkpoints, and requested debug bundles. Do not put
+credentials or other secrets in an explicit session identifier; command-line
+values are not a credential mechanism.

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.
@@ -39,11 +45,24 @@ 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
 [Internal Overview](../internal/overview.md).
 
+The root `assets` package is a content-only dependency leaf. It may expose a
+read-only embedded filesystem, but it must contain no business logic and must
+not depend on `internal` packages or PromptKit. Consumers scope that filesystem
+to the content they own; the root package is not a behavioral registry or a
+public extension contract. The rationale and compatibility consequence are
+recorded in [ADR-0011](../adr/0011-centralize-llm-assets.md).
+
 The following dependency boundaries are mandatory:
 
 - extractors and validators do not depend on concrete input adapters;
@@ -73,6 +92,12 @@ Extract modules own artifact semantics, prompt use, response schemas, and
 domain interpretation. Domain-specific concepts remain in the relevant module,
 validator, shared domain helper, and artifact contract.
 
+Physical centralization of LLM-facing content does not transfer semantic
+ownership from those modules. Modules retain their manifests, response-schema
+identities, prompt ordering, and registration, while reading only their scoped
+content subtree. Generic framework code remains domain-neutral when it reads
+its own scoped generic assets from the shared content container.
+
 Typed artifact registrations declare one stable artifact kind and exact Go
 type from extraction through merge, normalization, and semantic validation.
 Pipeline resolution requires a compatible codec and matching kind-specific
@@ -170,6 +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

@@ -7,37 +7,6 @@ not as committed release dates.
 
 ## Near-Term D&D Pipeline
 
-### Combat Enemy Ledger
-
-- Add a D&D artifact that identifies enemies faced during combat and supports
-  an end-of-session encounter ledger.
-- Track each enemy's observed state using a small controlled vocabulary such as
-  `active`, `killed`, `fled`, `captured`, or `incapacitated`, while preserving
-  an explicit unresolved state when the transcript does not establish an
-  outcome.
-- Preserve the evidence for enemy participation and state changes rather than
-  inferring a terminal outcome from combat ending or an enemy disappearing
-  from the conversation.
-- Define how repeated mentions, groups of unnamed enemies, summoned or allied
-  creatures, and the same enemy appearing in multiple combats affect identity
-  and ledger entries.
-- Evaluate whether the ledger should be extracted directly, derived from
-  combat-turn artifacts, or use a sequential pipeline that consumes combat
-  turns and the normalized NPC registry as grounding references.
-
-### Location Extraction
-
-- Add a D&D artifact for locations visited by the party or otherwise mentioned
-  in the transcript.
-- Distinguish observed visits from references, plans, recalled places, and
-  uncertain or inferred locations so a mention alone is not reported as a
-  visit.
-- Preserve transcript evidence for each visit or mention and reconcile aliases,
-  nested places, and repeated appearances without collapsing distinct
-  locations that share a generic name.
-- Define how the location artifact should ground later narrative reports and
-  whether future event artifacts should retain canonical location identities.
-
 ### Evaluate Spell Extraction And Normalization
 
 - Evaluate ordinary extraction retries and the completed normalization path
@@ -53,93 +22,54 @@ not as committed release dates.
   spell, combat, interaction, and scene-description lanes after real-world use.
   Add more complex chunking only in response to demonstrated failures.
 
-## Cross-Cutting LLM Runtime
-
-### Deterministic Prompt Session Identity
-
-- Replace the source-document-ID default for prompt sessions with one
-  predictable, procedurally generated session ID for the complete
-  source-processing workload.
-- Preserve an explicit non-empty `--session-id` as the highest-precedence
-  override. Otherwise, derive the default only from the effective input module
-  identity and the exact raw input bytes.
-- Use a versioned, bounded representation such as
-  `notarius:v1:<sha256(input-module + NUL + raw-input)>`. The exact encoding
-  must fit PromptKit's session length contract and must not embed source
-  content.
-- Keep the derived session stable across runs, pipelines, selected lanes,
-  ordered steps, retries, resume, recomputation, LLM profiles, reasoning
-  overrides, and output, debug, or cache settings.
-- Do not include file-backed references, generated references, reference
-  contents, or the composition of a reference bundle in session derivation.
-  References may change between prompt calls within one pipeline without
-  changing routing affinity.
-- Resolve the authoritative session before checkpoint construction and use the
-  same value for checkpoint runtime identity, every prompt-facing module,
-  PromptKit's direct session field, the compatibility `session_id` prompt
-  variable, run-manifest metadata, and debug metadata.
-- Keep routing identity separate from cache and checkpoint content identity.
-  Exact prompt prefixes, reference contents, model settings, and other
-  generation-affecting inputs must continue to participate in their existing
-  hashes and checkpoint fingerprints even though they do not change the
-  session.
-- Treat the generated value as a provider-visible, stable pseudonymous
-  correlation identifier. Do not introduce an installation-specific HMAC or
-  secret unless a concrete multi-tenant or privacy requirement justifies
-  sacrificing deterministic identity across installations.
-
-### Raise The Default Application-Wide LLM Limit
-
-- Raise the default `concurrency.total_llm` value from 1 to 16 so ordinary
-  single-backend runs can use PromptKit's expected OpenRouter capacity and
-  lower-capacity local backends without an unnecessarily narrower Notarius
-  limit.
-- Keep the Notarius application-wide scheduler mandatory and require
-  `total_llm` to remain a positive integer. Do not make the default unlimited:
-  endpoint-only profiles, an unrestricted local backend, injected clients, and
-  aggregate work across several backends may have no narrower PromptKit limit.
-- Continue defaulting `concurrency.stage_workers.extract` to the effective
-  `total_llm`, making its default 16 as part of the same change. Preserve an
-  explicit lower extract-worker setting when an operator wants less queued or
-  concurrent extraction work.
-- Define effective provider concurrency as the intersection of the Notarius
-  application-wide limit, the selected PromptKit backend limit when present,
-  and the work made available by stage execution. A Notarius limit of 16 does
-  not narrow a backend already limited to 16, while a local backend limited to
-  4 remains bounded at 4.
-- Treat the default as an application-wide safety ceiling across profiles,
-  backends, modules, retries, and validators. A run that intentionally needs
-  the combined capacity of several backends may configure a higher
-  `total_llm` and an appropriate extract-worker count explicitly.
-- Retain the existing configuration and environment override surfaces. Update
-  canonical configuration, operations, and internal documentation together
-  when the default changes.
-- Reconsider decoupling the extract-worker default from `total_llm` only after
-  mixed-backend workloads demonstrate a need for a high global emergency
-  ceiling with a lower default work-production rate.
-
 ## 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
-  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.
+### Large-Collection Semantic Reconciliation
 
-The model may use its own domain knowledge to judge semantic duplication; the
-generic implementation is responsible only for the common proposal contract,
-safety checks, and deterministic application of accepted changes.
+- Evaluate deterministic candidate blocking only after representative registry
+  inputs exceed the active roadmap's bounded single-request limits. Blocking
+  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
 
@@ -196,6 +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

docs/roadmap/implementation.md

@@ -1,586 +0,0 @@
-# PromptKit v0.5 Implementation Plan
-
-## Objective
-
-Implement the target state in
-[PromptKit v0.5 Integration And LLM Profile Policy](promptkit.md). Each numbered
-stage is intended to be one implementation prompt for a GPT-5.6-Terra coding
-agent. Complete stages in order and leave the repository buildable, tested, and
-internally coherent after every stage.
-
-Follow [Architecture](../policy/architecture.md),
-[Testing Policy](../policy/testing.md), and
-[Documentation Policy](../policy/documentation.md) throughout. Preserve
-unrelated user changes. Use `apply_patch` for source and documentation edits,
-run `gofmt` on changed Go files, and add only tests that protect the behaviors
-and risks assigned to that stage.
-
-Do not implement the separate deterministic session-ID or default-concurrency
-roadmap items as part of this plan. Do not perform paid or credentialed LLM
-calls.
-
-## Background Summary
-
-Notarius currently pins PromptKit v0.3.0, calls `Prepare` and then `Run` for one
-completion, validates profiles through a synthetic prompt, has no application
-fallback profile source, and accepts LLM profiles only at individual bindings
-or through the run-wide CLI override. PromptKit v0.5.0 is source-compatible
-with the current tree; a temporary v0.5.0 module override has already passed
-`go test ./...`.
-
-The implementation must nevertheless treat the upstream optional-parameter
-change as intentional: unset `temperature`, `max_tokens`, and `top_p` remain
-unset and are omitted from compatible provider requests. Do not restore the old
-implicit `top_p: 1` default.
-
-## Stage 1: Upgrade The PromptKit Dependency
-
-### Goal
-
-Establish a clean PromptKit v0.5.0 baseline before adopting its new APIs.
-
-### Work
-
-- Update `go.mod` and `go.sum` from PromptKit v0.3.0 to v0.5.0 and run
-  `go mod tidy`.
-- Change the PromptKit built-in profile-catalog marker in
-  `internal/framework/llm/promptkit_profile_fingerprint.go` to identify
-  v0.5.0. This deliberately invalidates LLM checkpoints tied to the prior
-  catalog identity.
-- Review PromptKit-facing compile errors or test failures against the v0.4.0
-  and v0.5.0 release guides. Do not adopt prepared execution, inspection, or
-  fallback profiles in this stage.
-- Replace the existing test assertion for one exact built-in fingerprint hash
-  with durable assertions that the fingerprint is deterministic, non-empty,
-  non-secret, and changes when a semantic profile source changes. Do not add a
-  new version-constant or exact-hash change detector.
-- Update `docs/integrations/pkg-promptkit.md` to pin and link v0.5.0 and state
-  the implemented dependency-level behavior: unset optional sampling controls
-  are provider defaults. Do not document later stages as implemented.
-- Update any other canonical text that explicitly claims the dependency is
-  v0.3.0, but defer descriptions of unimplemented v0.5 APIs.
-
-### Tests And Validation
-
-- `go test ./internal/framework/llm ./internal/cli`
-- `go test ./...`
-- `go vet ./...`
-- `go build ./cmd/notarius`
-- `rg -n 'promptkit v0\.3\.0|promptkit@v0\.3\.0|PromptKit v0\.3\.0' .`
-- `git diff --check`
-
-### Completion Criteria
-
-- The repository directly pins v0.5.0 and all default offline checks pass.
-- The profile-source fingerprint identifies the new upstream catalog without a
-  brittle literal-hash test.
-- Current documentation no longer identifies v0.3.0 as the supported version.
-
-## Stage 2: Execute One Frozen Prepared Snapshot
-
-### Goal
-
-Make Notarius debug details and generation use one exact PromptKit preparation.
-
-### Work
-
-- Refactor `PromptKitClient.CompleteStructured` to call
-  `PrepareExecution`, immediately defer `Discard`, obtain a caller-owned
-  `Details` value, and execute with `RunPrepared`.
-- Preserve the existing Notarius request mapping, cancellation precedence,
-  validation classification, raw structured bytes, response decoding,
-  profile recording, usage reporting, and credential redaction.
-- Ensure every preparation, execution, validation, empty-result, and decode
-  error retains useful Notarius prompt context without exposing prepared handle
-  state or secrets.
-- Use `errors.As` to obtain `*promptkit.CapacityError` on admission rejection.
-  Preserve `contracts.ErrLLMCapacityExceeded` as the stable classification and
-  add a nonblank backend ID only to safe application-owned diagnostic context.
-  Do not expose `promptkit.CapacityError` outside the LLM adapter.
-- Update `docs/internal/llm.md` and the implemented-mechanics portion of
-  `docs/integrations/pkg-promptkit.md` to describe the single frozen execution
-  snapshot and structured capacity adaptation.
-
-### Tests And Validation
-
-- Adapt existing PromptKit client tests to the prepared-execution path.
-- Retain or add one behavioral test proving that the debug prompt details match
-  the request actually passed to generation when a backing prompt source could
-  otherwise change between independent preparations. Test the resulting
-  snapshot consistency, not a private helper call count.
-- Retain capacity tests proving `errors.Is` reaches
-  `contracts.ErrLLMCapacityExceeded`, the selected backend can appear in safe
-  diagnostic context, and provider calls are not made after rejected
-  admission.
-- Run `go test ./internal/framework/llm` and
-  `go test -race ./internal/framework/llm`.
-- Run `go test ./...` and `git diff --check`.
-
-### Completion Criteria
-
-- `CompleteStructured` no longer calls independent `Prepare` and `Run`
-  operations for one request.
-- Debug prompt material and generation result originate from the same frozen
-  PromptKit snapshot.
-- Capacity remains a provider-neutral Notarius error classification.
-
-## Stage 3: Replace Synthetic Profile Validation With Inspection
-
-### Goal
-
-Validate profiles through PromptKit's exact profile-inspection boundary and
-centralize engine profile-source construction.
-
-### Work
-
-- Introduce a small provider-adapter-owned profile inspection or validation
-  function in `internal/framework/llm`. Its public internal signature must use
-  Notarius-owned configuration and result/error types rather than returning
-  PromptKit types to the CLI.
-- Share the code that applies `profile_dir`, `profile_file`, and registered
-  backend options between the production PromptKit engine and the inspection
-  engine. Preserve the mutual-exclusion and local-backend rules.
-- Change CLI explicit-profile preflight to use `Engine.InspectProfile` through
-  that LLM boundary.
-- Remove `profileCheckPromptID`, `profileCheckPromptFS`, the `testing/fstest`
-  production dependency, and the synthetic `Prepare` request.
-- Preserve distinct, useful errors for an absent profile, invalid profile,
-  unknown backend registration, cancellation, and invalid profile source.
-- Do not require `api_key_env` to be populated during configuration validation.
-  Inspection may report credential requirements internally, but actual
-  preparation remains responsible for credential availability before a model
-  call.
-- Update current-behavior sections in `docs/internal/cli.md` and
-  `docs/internal/llm.md`. Keep field definitions in `docs/config.md`.
-
-### Tests And Validation
-
-- Replace synthetic-prompt tests with profile inspection tests covering:
-  configured local backend success; missing local backend failure; absent
-  profile; malformed profile; and an otherwise valid profile whose credential
-  environment variable is intentionally unset.
-- Prove validation performs no provider HTTP call and remains offline.
-- Run `go test ./internal/framework/llm ./internal/cli` and `go test ./...`.
-- Run `git diff --check`.
-
-### Completion Criteria
-
-- No production synthetic profile-check prompt remains.
-- Profile validation uses the same ordinary profile source and backend
-  registrations as execution.
-- Configuration validation succeeds for structurally valid profiles without
-  reading credential values.
-
-## Stage 4: Add Application Fallback Profile Asset Plumbing
-
-### Goal
-
-Allow module families to register application-owned fallback profile YAML
-without placing domain policy in generic LLM code.
-
-### Work
-
-- Extend `internal/framework/llm.AssetRegistry` with a separate fallback
-  profile source collection, registration method, flattened filesystem, and
-  safe content digest.
-- Reuse the existing asset-source path validation and flattening behavior where
-  appropriate. Reject invalid roots, unreadable assets, and duplicate flattened
-  paths. Do not parse PromptKit profile YAML in Notarius.
-- Add `promptkit.WithFallbackProfileFS` to production engine options only when
-  at least one fallback profile source is registered.
-- Supply the identical assembled fallback source to the profile-inspection
-  engine. Adjust CLI composition so pipeline-aware profile validation can use
-  the production LLM asset registry without exposing PromptKit types.
-- Extend profile-source checkpoint identity to include the exact fallback
-  profile asset digest in addition to the PromptKit catalog marker and operator
-  source. Keep the resulting fingerprint hash-only and path/content/credential
-  free.
-- Keep operator source precedence owned by PromptKit. Do not implement profile
-  merging or duplicate PromptKit source resolution in Notarius.
-- Update `docs/internal/llm.md` only for the new implemented generic asset and
-  fingerprint mechanics. No domain fallback exists until Stage 5.
-
-### Tests And Validation
-
-- Add focused AssetRegistry tests for successful flattening, invalid roots,
-  duplicate paths, and hash changes when fallback bytes change.
-- Add adapter-level tests showing that the fallback filesystem reaches both
-  execution construction and inspection construction.
-- Extend checkpoint tests to prove fallback content changes profile-source
-  identity without exposing raw YAML or paths. Use relational comparisons, not
-  a fixed hash literal.
-- Run `go test ./internal/framework/llm ./internal/cli` and `go test ./...`.
-- Run `git diff --check`.
-
-### Completion Criteria
-
-- Generic plumbing can carry application fallback profiles while remaining
-  unaware of D&D IDs or model settings.
-- Inspection, execution, and checkpoint identity use the same fallback asset
-  source.
-
-## Stage 5: Adopt The D&D `dnd-extraction` Fallback
-
-### Goal
-
-Give the D&D module family one stable embedded workload profile that operators
-can replace.
-
-### Work
-
-- Add a D&D-owned embedded PromptKit profile asset with ID `dnd-extraction`
-  under `internal/modules/dnd`. Use the exact baseline defined in
-  `promptkit.md`: OpenRouter, `openai/gpt-5.6-luna`, no explicit reasoning
-  effort, a 240-second timeout, flex service tier, and no selected temperature,
-  token limit, or `top_p`. The omitted reasoning value intentionally allows
-  OpenAI's backend to apply its `medium` default.
-- Register the profile filesystem from the D&D registrar through the generic
-  fallback profile asset boundary. Keep D&D policy out of
-  `internal/framework/llm` and the CLI composition root.
-- Change every maintained D&D LLM prompt definition—including scene chunking,
-  all D&D extractors, and NPC normalization—from the model-named default to
-  `default_profile: dnd-extraction`.
-- Add an integration-level profile-resolution test proving that:
-  - the fallback resolves when no operator source defines the ID;
-  - a valid operator profile with the same ID wins completely; and
-  - an invalid matching operator profile fails rather than falling through.
-- Test through Notarius's assembled production assets and PromptKit boundary;
-  do not duplicate every upstream source-precedence case.
-- Update the implemented profile ownership and prompt-default behavior in
-  `docs/internal/dnd.md`, `docs/internal/llm.md`, and
-  `docs/integrations/pkg-promptkit.md`. Defer the complete operator walkthrough
-  and examples to Stage 10.
-
-### Tests And Validation
-
-- Run focused D&D prompt preparation tests and the production composition
-  tests.
-- Run `go test ./internal/modules/dnd/... ./internal/framework/llm
-  ./internal/cli`.
-- Run `go test ./...`.
-- Verify `rg -n 'default_profile: gemini-2-flash' internal/modules/dnd`
-  returns no matches.
-- Run `git diff --check`.
-
-### Completion Criteria
-
-- All maintained D&D prompts use the application-owned logical profile ID.
-- The fallback works without an operator profile and remains authoritatively
-  overridable by a matching valid operator definition.
-
-## Stage 6: Introduce Module Execution-Class Metadata
-
-### Goal
-
-Make each production module's ability to use an LLM statically discoverable
-without yet changing profile inheritance.
-
-### Work
-
-- Add `ExecutionClass contracts.ExecutionClass` to `pipeline.ModuleSpec` and
-  preserve it through normalization, cloning, catalogs, registries, JSON/debug
-  views, and lookup helpers.
-- In this transitional stage only, allow an omitted execution class to
-  normalize to deterministic so existing test-only fixtures can be migrated in
-  Stage 7 without breaking the repository midway.
-- Explicitly classify every production module:
-  - D&D scene chunking, every D&D extractor, and D&D NPC normalization as
-    `llm_backed`;
-  - all other current production input, chunk, merge, normalize, and output
-    modules as `deterministic`.
-- Update production module specification tests and production catalog tests to
-  assert the semantic class alongside stage, artifact kind, and capabilities.
-- Add catalog lookup support needed by later resolution to retrieve a selected
-  module's execution class by stage and key without constructing it.
-- Do not implement pipeline-level profile inheritance or reject deterministic
-  profiles yet.
-- Update `docs/internal/modules.md` and `docs/internal/dnd.md` to identify
-  execution class as registered module metadata, while noting only implemented
-  uses.
-
-### Tests And Validation
-
-- Run module registration/spec tests across generic, Seriatim, and D&D
-  families.
-- Run `go test ./internal/framework/pipeline ./internal/modules/...`.
-- Run `go test ./...` and `git diff --check`.
-
-### Completion Criteria
-
-- Every production module has an explicit correct execution class.
-- Catalog consumers can retrieve that class without a concrete module
-  instance.
-- Test-only omitted classes remain the only temporary compatibility behavior.
-
-## Stage 7: Enforce Execution Metadata And Remove Runtime Probing
-
-### Goal
-
-Finish the execution-class contract so missing metadata cannot cause future
-profile drift.
-
-### Work
-
-- Update every framework, CLI, and integration test module specification to
-  declare an explicit execution class appropriate to the fake behavior.
-- Change module-spec validation so an empty or unsupported execution class is a
-  registration error. Remove the transitional deterministic default from
-  Stage 6.
-- Replace the chunk runner's special `ChunkExecutionClassProvider` probe with
-  specification-derived behavior. Remove the now-redundant provider interface,
-  implementation methods, and tests when they have no remaining consumer.
-- Ensure chunk producer provenance remains unchanged: it records a non-empty
-  effective binding profile for an LLM-backed chunker, while a deterministic
-  chunker records no profile. A profile selected only through the prompt
-  default remains represented by PromptKit's actual-profile manifest rather
-  than being invented as an explicit chunk binding.
-- Review helper constructors and fixtures for opportunities to set execution
-  class once without obscuring the class under test. Do not introduce an
-  elaborate test-spec framework.
-- Update internal documentation if the removal changes any described runtime
-  mechanics.
-
-### Tests And Validation
-
-- Add or retain focused registration tests for missing and invalid execution
-  classes.
-- Retain chunk-plan provenance tests for LLM-backed and deterministic
-  chunkers.
-- Run `go test ./internal/framework/pipeline ./internal/modules/...`.
-- Run `go test ./...`, `go vet ./...`, and `git diff --check`.
-
-### Completion Criteria
-
-- No registered module specification relies on an implicit execution class.
-- Pipeline metadata, not a concrete runtime type assertion, owns module
-  execution classification.
-
-## Stage 8: Resolve Programmatic Pipeline Profile Defaults
-
-### Goal
-
-Implement profile inheritance and precedence inside the pipeline resolver
-before exposing the field through YAML configuration.
-
-### Work
-
-- Add an optional trimmed `LLMProfile` field to
-  `pipeline.PipelineProfile`. Add a non-empty runtime override field to
-  `pipeline.ResolveOptions` so all precedence decisions occur in the resolver
-  rather than through pre-resolution mutation.
-- After module selection, `--only` filtering, default validator-chain
-  selection, and validator compatibility resolution, apply effective profiles
-  to every selected input, chunk, extract, merge, normalize, output, and
-  validator binding according to the precedence in `promptkit.md`.
-- Apply profiles only when the selected module or validator execution class is
-  `llm_backed`.
-- Reject a binding-specific `llm_profile` on any deterministic module or
-  validator. Do not reject or inspect an unused pipeline default when no
-  selected LLM-backed binding consumes it.
-- Leave an LLM-backed binding empty when no CLI, binding, or pipeline profile is
-  selected so PromptKit can use the prompt's `default_profile`.
-- Store the effective values on resolved bindings before digest construction.
-  Do not add a second inheritance decision to execution.
-- Ensure semantically equivalent repeated binding profiles and one inherited
-  default produce the same resolved pipeline digest. Ensure any changed
-  effective profile changes the digest.
-- Do not modify file configuration or CLI parsing in this stage.
-
-### Tests And Validation
-
-- Add pipeline package tests for the complete precedence matrix:
-  runtime override; binding-specific exception; pipeline default; prompt
-  fallback; and deterministic bindings.
-- Cover default and explicitly configured validator chains, all relevant stage
-  categories, `--only` lane selection, unused defaults, deterministic-profile
-  rejection, and semantic digest equivalence.
-- Prefer table-driven package-level tests over assertions on private traversal
-  helpers.
-- Run `go test ./internal/framework/pipeline` and `go test ./...`.
-- Run `git diff --check`.
-
-### Completion Criteria
-
-- Programmatic pipelines resolve one canonical effective profile policy.
-- Only LLM-backed resolved bindings can contain a profile.
-- Runtime override, binding, pipeline, and prompt precedence is unambiguous and
-  digest-stable.
-
-## Stage 9: Expose Pipeline Defaults Through Configuration And CLI
-
-### Goal
-
-Make the profile-default workflow available to operators while preserving
-validation and override behavior.
-
-### Work
-
-- Add optional `pipelines.<id>.llm_profile` support to the version 4 file
-  configuration model. Use presence-aware decoding so an explicitly set blank
-  value is rejected, while omission remains valid.
-- Preserve the field through file application, configuration cloning,
-  effective configuration, and programmatic profile copies without aliasing or
-  trimming drift.
-- Remove `applyLLMProfileOverride`. Pass the CLI override through the resolver's
-  runtime-override input so deterministic bindings are never populated.
-- Update effective profile-ID collection to cover every selected LLM-backed
-  module stage and LLM-backed validator, including future LLM-backed input and
-  output modules. Do not inspect deterministic or unselected profiles.
-- Ensure `run`, `config validate --pipeline`, resume/checkpoint identity, and
-  relevant dry preflight paths all use the same resolved effective profiles.
-- Preserve `--llm-profile` as the highest-precedence non-empty run-wide
-  override and preserve binding-specific profiles as exceptions when no CLI
-  override is present.
-- Do not increment the configuration version.
-- Update current configuration and CLI contracts in `docs/config.md` and
-  `docs/cli.md` in the same stage. Link to operations for the deployment
-  workflow rather than duplicating it prematurely.
-
-### Tests And Validation
-
-- Add file-config tests for omission, trimming, explicit blank rejection,
-  unknown-key behavior, cloning, and round-trip application.
-- Add effective-config and CLI contract tests for precedence, LLM-only
-  application, inherited-profile inspection failure before factory execution,
-  `--only`, and digest changes.
-- Retain offline operation and do not require credentials for
-  `config validate --pipeline`.
-- Run `go test ./internal/core/config ./internal/framework/pipeline
-  ./internal/cli`.
-- Run `go test ./...`, `go vet ./...`, and `git diff --check`.
-
-### Completion Criteria
-
-- Operators can select `dnd-extraction` once per pipeline.
-- Configuration and CLI paths share the resolver's precedence policy.
-- Unknown effective profiles fail preflight, while deterministic and unused
-  profiles do not cause spurious inspection.
-
-## Stage 10: Complete Operator Documentation, Examples, And Decision Record
-
-### Goal
-
-Make the implemented workflow understandable, copyable, and maintainable
-without duplicating canonical facts.
-
-### Work
-
-- Create an ADR using the next sequential number for the durable decision to
-  use workload-oriented pipeline defaults with operator-overridable application
-  fallback profiles. Record context, decision, alternatives, and consequences;
-  do not turn the ADR into a field reference or implementation log.
-- Complete `docs/config.md` as the canonical owner of profile-source fields,
-  `pipelines.<id>.llm_profile`, validation, and precedence.
-- Complete `docs/operations.md` with an operator workflow that distinguishes
-  Notarius embedded prompts, Notarius fallback profiles, PromptKit built-ins,
-  and deployment filesystem profiles. Include production/development/local use
-  of the same `dnd-extraction` ID, credential handling, absolute-path guidance,
-  and the fact that current relative profile paths use the process working
-  directory rather than the configuration file's directory.
-- Complete `docs/integrations/pkg-promptkit.md` with the v0.5.0 boundary,
-  prepared execution, inspection, fallback and ordinary source precedence,
-  optional provider controls, capacity adaptation, and compatibility policy.
-- Update `docs/internal/configuration.md`, `docs/internal/pipeline.md`,
-  `docs/internal/cli.md`, `docs/internal/llm.md`, `docs/internal/modules.md`, and
-  `docs/internal/dnd.md` only for their owned implementation details. Link to
-  canonical configuration, operations, and upstream format contracts rather
-  than restating them.
-- Keep exactly the existing two D&D configuration examples. Add
-  `llm_profile: dnd-extraction` to the minimal and complete pipelines and remove
-  the now-redundant model-named binding override from the complete example.
-- Add one secret-free maintained operator profile at
-  `examples/profiles/dnd-extraction.yml`. It should be a complete valid profile
-  for the same logical ID and may mirror the embedded baseline; its purpose is
-  to demonstrate file ownership and format, not claim automatic environment
-  detection. Link it from the configuration and operations documentation.
-- If the complete example selects the external profile file, use a path that
-  is valid for the documented repository-root invocation and explicitly note
-  the working-directory rule. Keep the minimal example dependent only on the
-  embedded fallback.
-- Add or extend maintained-example validation so both configuration examples
-  and the profile YAML are checked without generation or credentials.
-- Remove the now-implemented `Pipeline-Level LLM Profile Defaults` section from
-  `docs/roadmap/future.md`. Preserve the unrelated deterministic session and
-  concurrency items.
-- Do not delete `promptkit.md` or this implementation plan during the feature
-  implementation; retire them only after post-implementation review.
-
-### Tests And Validation
-
-- Run maintained example/configuration tests and relevant CLI help/parser
-  tests.
-- Run `go test ./...`.
-- Run `rg -n 'gemini-2-flash' examples docs` and review every remaining match
-  for intentional model-policy or historical context.
-- Run `rg -n 'v0\.3\.0|profileCheckPrompt|applyLLMProfileOverride' .` and resolve
-  stale production or current-documentation matches.
-- Verify all new links and `git diff --check`.
-
-### Completion Criteria
-
-- Every current fact has one canonical documentation owner.
-- Operators can distinguish and deploy all profile layers without reading Go
-  source.
-- Both maintained configurations and the maintained external profile are valid,
-  secret-free, and tested offline.
-- Implemented profile work no longer remains in `future.md`.
-
-## Stage 11: Final Verification And Quality Review
-
-### Goal
-
-Verify the complete migration as one integrated change and correct only defects
-or omissions found during that review.
-
-### Work
-
-- Review the final diff against every acceptance criterion in `promptkit.md`.
-- Confirm provider-specific PromptKit types remain inside the LLM integration
-  boundary and D&D policy remains inside the D&D module family.
-- Confirm execution and inspection receive identical ordinary, fallback, and
-  backend configuration.
-- Confirm no paths, profile YAML, endpoints, credentials, or prepared handle
-  state leak into fingerprints or ordinary diagnostics.
-- Confirm all production module specs have explicit correct execution classes
-  and every resolved deterministic binding is profile-free.
-- Confirm prompt default, pipeline default, binding override, and CLI override
-  behavior through representative assembled configurations.
-- Review tests for redundancy and remove obsolete synthetic-prompt,
-  runtime-probe, exact-hash, or duplicated upstream-behavior tests superseded by
-  stronger contract tests.
-- Perform an optional manual D&D quality comparison if credentials and an
-  evaluation transcript are deliberately supplied. Record no private input or
-  credential material, and do not make this comparison a completion gate.
-
-### Validation Commands
-
-```sh
-gofmt -w <changed-go-files>
-go test ./...
-go test -race ./internal/framework/llm ./internal/core/config ./internal/framework/pipeline ./internal/cli
-go vet ./...
-go build ./cmd/notarius
-git diff --check
-```
-
-Also run focused stale-contract searches:
-
-```sh
-rg -n 'gitea.maximumdirect.net/eric/promptkit v0\.3\.0|PromptKit v0\.3\.0' .
-rg -n 'default_profile: gemini-2-flash|profileCheckPrompt|applyLLMProfileOverride' internal docs examples
-```
-
-Review any matches rather than deleting intentional historical references
-blindly.
-
-### Completion Criteria
-
-- All automated checks pass offline and without real credentials.
-- The implemented behavior matches `promptkit.md` with no known architecture,
-  provenance, checkpoint, profile-precedence, or documentation gap.
-- Any optional live evaluation is clearly separate from correctness testing.
-
-## Open Questions
-
-None. The roadmap decisions are sufficient to implement every stage without an
-additional product or architecture choice.

docs/roadmap/promptkit.md

@@ -1,318 +0,0 @@
-# PromptKit v0.5 Integration And LLM Profile Policy
-
-## Purpose
-
-This roadmap defines the target state for upgrading Notarius from PromptKit
-v0.3.0 to v0.5.0 and adopting the upstream runtime and profile facilities that
-directly improve Notarius. It also defines the application policy for stable,
-domain-oriented LLM profile names, operator overrides, pipeline inheritance,
-profile validation, provider defaults, checkpoint identity, and documentation.
-
-The ordered work needed to reach this state belongs in
-[the implementation plan](implementation.md). Current behavior remains defined
-by the canonical documentation outside `docs/roadmap/` until the corresponding
-work is implemented.
-
-## Background
-
-Notarius currently pins PromptKit v0.3.0. Its adapter prepares a request once
-for debug material and then independently runs the original request, causing
-PromptKit to prepare the same logical call a second time. The CLI validates an
-explicit profile by preparing a synthetic prompt. PromptKit profile selection
-can be repeated on individual module bindings or replaced for one invocation
-with `--llm-profile`, but a configured pipeline cannot yet declare one inherited
-profile policy.
-
-PromptKit v0.4.0 and v0.5.0 add the upstream boundaries needed to improve these
-areas:
-
-- [v0.4.0](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.5.0/docs/releases/v0.4.0.md)
-  adds opaque prepared executions, exact profile and prompt inspection, and a
-  typed backend-capacity error;
-- [v0.5.0](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.5.0/docs/releases/v0.5.0.md)
-  adds application fallback profile filesystems and stops sending unset
-  optional sampling controls as framework-selected provider values; and
-- the [v0.5.0 format contract](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.5.0/docs/formats.md)
-  defines the resulting profile-source and execution-setting precedence.
-
-A source-compatibility test of the current Notarius repository against
-PromptKit v0.5.0 completed successfully. The work is therefore primarily an
-intentional runtime and configuration migration rather than a repair for a
-breaking Go API change.
-
-## Goals
-
-- Pin and document PromptKit v0.5.0 as Notarius's supported upstream contract.
-- Execute the exact prepared request snapshot whose safe details are recorded
-  in Notarius debug material.
-- Validate configured PromptKit profiles through the upstream inspection API
-  without synthetic prompts, provider calls, or credential-value access.
-- Give Notarius an application-owned, operator-overridable
-  `dnd-extraction` profile fallback.
-- Let a pipeline choose one default LLM profile without repeating that ID on
-  every LLM-backed binding.
-- Apply profile inheritance and run-wide overrides only where the resolved
-  module or validator can use an LLM.
-- Preserve accurate checkpoint invalidation, effective profile provenance,
-  redaction, cancellation, concurrency, and provider-neutral module contracts.
-- Provide operators with one clear deployment pattern for production,
-  development, and local profile definitions.
-
-## Target End State
-
-### PromptKit Runtime Boundary
-
-Notarius depends on PromptKit v0.5.0 and uses its public APIs rather than
-reimplementing source or execution resolution.
-
-For each structured completion, the adapter:
-
-1. builds one PromptKit run request from the provider-neutral Notarius request;
-2. calls `PrepareExecution` once;
-3. immediately arranges an idempotent `Discard` for every unexecuted handle;
-4. obtains credential-redacted `Details` for debug and response metadata; and
-5. calls `RunPrepared` so generation uses that exact frozen snapshot.
-
-The debug prompt and successful result therefore describe the same selected
-profile, rendered messages, input bytes, session, output contract, and effective
-settings even when a filesystem-backed source changes concurrently. PromptKit
-handle types remain private to `internal/framework/llm`.
-
-PromptKit admission failures continue to match Notarius's provider-neutral
-`ErrLLMCapacityExceeded` contract. When PromptKit supplies a `CapacityError`,
-the adapter obtains the normalized backend ID through `errors.As` and may add it
-to safe application-owned diagnostics without parsing upstream error wording.
-The backend ID does not become a provider-specific module contract.
-
-### Optional Provider Controls
-
-Notarius accepts PromptKit v0.5.0's new behavior for `temperature`,
-`max_tokens`, and `top_p`: an unset setting is omitted from compatible provider
-requests and the provider chooses its own default. Notarius does not restore
-PromptKit's former implicit `top_p: 1` value globally.
-
-An operator who requires a particular value specifies it in the selected
-PromptKit profile. The application fallback described below intentionally
-leaves these controls unset. A human-reviewed D&D extraction comparison should
-be performed after the upgrade, but paid or nondeterministic model output is
-not part of the default automated test suite.
-
-### Profile Inspection
-
-Pipeline-aware configuration validation uses `Engine.InspectProfile` for every
-effective explicit profile ID. It verifies that the profile exists, parses and
-validates, resolves its backend and target, and is compatible with the engine's
-registered backends. It does not create a synthetic prompt, load prompt inputs,
-contact a provider, or require credential values to exist in the validation
-process environment.
-
-Credential availability is execution-time state. PromptKit preparation still
-enforces the selected profile's credential contract before generation. This
-keeps `notarius config validate` useful in build and deployment validation
-environments where secrets are deliberately absent.
-
-PromptKit construction for inspection and execution uses one shared internal
-profile-source and backend-option path. The CLI does not expose PromptKit public
-types across the Notarius LLM boundary merely to perform inspection.
-
-`InspectPrompt` is not adopted merely because it exists. It remains available
-for a later, separately defined module-to-prompt interface preflight if a
-concrete validation requirement justifies that additional contract.
-
-### Application And Operator Profile Sources
-
-Notarius embeds one ordinary PromptKit YAML profile with the stable ID
-`dnd-extraction`. It is an application fallback registered through
-`WithFallbackProfileFS`, is owned by the D&D module family, and initially
-preserves the current effective D&D baseline:
-
-- backend: PromptKit's built-in `openrouter` backend;
-- model: `openai/gpt-5.6-luna`;
-- reasoning effort: unset, allowing OpenAI's backend to apply its default of
-  `medium`;
-- generation timeout: 240 seconds;
-- service tier: `flex`; and
-- no application-selected `temperature`, `max_tokens`, or `top_p`.
-
-All maintained D&D LLM prompt definitions use `dnd-extraction` as their
-`default_profile`. The ID communicates workload intent rather than a provider,
-model, or environment. Changing the embedded fallback is an intentional
-Notarius execution-policy change and participates in checkpoint identity.
-
-Effective profile definitions resolve in PromptKit's order:
-
-1. programmatic in-memory profiles used by tests or explicit consumers;
-2. the operator source configured by `promptkit.profile_file` or
-   `promptkit.profile_dir`;
-3. the Notarius application fallback source; and
-4. PromptKit's embedded built-in catalog.
-
-Only an absent ID falls through to the next source. A matching profile is a
-complete definition: fields are not merged with a lower-precedence definition,
-and a malformed matching operator profile fails rather than silently selecting
-the application fallback.
-
-Production, development, and local deployments should normally provide
-different complete definitions for the same `dnd-extraction` ID. An operator
-source is optional because the application fallback keeps the maintained D&D
-workflow usable, but a deployment that needs an intentional model or backend
-policy should configure its own definition.
-
-### Domain Ownership And Asset Assembly
-
-The D&D fallback profile remains under `internal/modules/dnd` and is registered
-by the D&D registrar, consistent with ADR-0004. Generic LLM plumbing knows how
-to collect and flatten application fallback profile filesystems but contains no
-D&D model or policy knowledge.
-
-The shared asset registry detects invalid roots, unreadable sources, and
-duplicate flattened paths. PromptKit remains responsible for strict profile
-YAML parsing, duplicate profile-ID detection, source precedence, and effective
-target resolution. The same assembled fallback source is supplied to runtime
-execution and CLI profile inspection.
-
-### Explicit Module Execution Metadata
-
-Every registered input, chunk, extract, merge, normalize, and output module
-declares one required execution class: `deterministic` or `llm_backed`.
-Validator registrations continue to declare the same distinction through their
-validator specifications.
-
-The registered specification is authoritative for configuration resolution.
-Current production classifications are:
-
-- the D&D scene chunker, all D&D extractors, and the D&D NPC normalizer are
-  LLM-backed;
-- the Seriatim input adapter, generic chunker, all current mergers, all other
-  current normalizers, and the JSON output encoder are deterministic; and
-- current validators retain their declared classifications.
-
-Missing or unsupported execution metadata is a registration error. Explicitly
-assigning `llm_profile` to a deterministic module or validator is a pipeline
-resolution error. The framework does not infer execution class by inspecting
-domain package names or concrete implementation types at runtime.
-
-The module specification replaces the chunk runner's special runtime
-execution-class probe. Effective resolved bindings already express the result:
-only LLM-backed bindings may retain a non-empty profile.
-
-### Pipeline-Level Profile Default
-
-Configuration version 4 gains one optional non-empty pipeline field:
-
-```yaml
-pipelines:
-  dnd-session:
-    llm_profile: dnd-extraction
-```
-
-No configuration-version increment is required because the field is additive
-and existing files remain valid. An explicitly present blank value is invalid.
-
-For every selected LLM-backed module and validator, the effective profile uses
-this precedence:
-
-1. non-empty run-wide `--llm-profile` override;
-2. binding-specific `llm_profile`;
-3. pipeline-level `llm_profile`; and
-4. the prompt definition's `default_profile`, represented by an empty effective
-   Notarius binding profile.
-
-The run-wide override and inherited pipeline default never attach to a
-deterministic binding. Binding-specific exceptions remain available when one
-operation needs a different cost, latency, quality, backend, or reasoning
-policy.
-
-Inheritance is resolved after module and validator selection, including
-`--only` lane filtering, but before effective-pipeline validation, digest
-construction, explicit-profile inspection, checkpoint construction,
-preparation, execution, or provenance capture. Only profiles used by selected
-LLM-backed bindings are inspected. An unused pipeline default in a pipeline
-with no selected LLM-backed work does not require an otherwise unused profile
-to exist.
-
-The resolved pipeline contains effective binding profiles rather than a second
-runtime inheritance mechanism. Two pipelines that differ only by spelling the
-same effective policy once as a pipeline default and once on every LLM-backed
-binding have the same semantic resolved digest. Changing an effective profile
-changes the digest and applicable checkpoint identity.
-
-### Provenance And Checkpoints
-
-The PromptKit profile-source checkpoint fingerprint covers:
-
-- the PromptKit v0.5.0 built-in profile catalog identity;
-- exact application fallback profile asset content; and
-- exact configured operator profile YAML content, when present.
-
-The existing local-backend target fingerprint remains separate and continues
-to exclude scheduling-only concurrency limits. Fingerprints contain hashes and
-stable markers, not profile contents, filesystem paths, endpoints, credentials,
-or other secrets.
-
-Changing the PromptKit version, application fallback, operator profile, or
-effective pipeline profile makes incompatible LLM checkpoints ineligible for
-reuse. The dependency upgrade is expected to invalidate checkpoints produced
-under v0.3.0.
-
-Successful run manifests continue to record only profiles actually selected by
-PromptKit, including their effective model, backend, and reasoning metadata.
-Debug output reports the same effective execution snapshot used for generation.
-
-### Operator Documentation And Examples
-
-Canonical documentation clearly distinguishes:
-
-- Notarius prompt and schema assets embedded in the application;
-- Notarius application fallback profiles embedded in the application;
-- PromptKit's own embedded built-in profiles; and
-- operator profile files on the deployment filesystem.
-
-The configuration reference owns the pipeline field, profile-source fields,
-validation rules, and precedence. Operations owns deployment layout, working
-directory behavior, credentials, and environment-specific profile management.
-The PromptKit integration document owns the pinned upstream contract and
-source-precedence boundary. Internal documents describe asset registration,
-resolution, inspection, prepared execution, fingerprinting, and tests without
-duplicating user-facing field definitions.
-
-The maintained examples continue to include only the minimal and complete D&D
-configurations. They use the stable `dnd-extraction` policy, and one maintained
-PromptKit profile file under `examples/` demonstrates an operator override.
-Examples remain secret-free and are validated without live provider calls.
-
-## Out Of Scope
-
-- Implementing the separate deterministic prompt-session identity roadmap
-  item.
-- Changing the default `concurrency.total_llm` value; PromptKit's retained
-  OpenRouter capacity of 16 remains relevant to that separate item.
-- Adding model evaluation as a deterministic or CI correctness gate.
-- Automatically selecting production, development, or local environments.
-  Deployment configuration chooses the operator profile source.
-- Profile inheritance, partial profile merging, or cross-profile aliases.
-- Exposing PromptKit types to modules, validators, durable output contracts, or
-  public configuration structures.
-- Adopting `InspectPrompt` without a separately justified prompt-interface
-  validation contract.
-
-## Acceptance Criteria
-
-- Notarius builds and its offline test suite passes with PromptKit v0.5.0.
-- Every structured completion executes the exact snapshot used for safe debug
-  prompt details.
-- Profile preflight uses profile inspection and no synthetic prompt.
-- The embedded `dnd-extraction` fallback resolves without an operator source,
-  and a matching valid operator profile replaces it completely.
-- Every production module has explicit, correct execution metadata.
-- Pipeline, binding, CLI, and prompt-default precedence behaves as defined for
-  modules and validators, while deterministic bindings remain profile-free.
-- Effective profiles participate in pipeline digests, profile inspection,
-  checkpoint identity, debug records, and run provenance at the appropriate
-  boundaries.
-- The dependency and application fallback changes invalidate incompatible old
-  checkpoints without exposing profile or credential content.
-- Canonical documentation and maintained examples accurately describe and
-  exercise the implemented operator workflow.
-- Default tests remain deterministic, offline, credential-free, and focused on
-  Notarius-owned behavior rather than duplicating PromptKit's upstream suite.

examples/dnd-complete.config.yml

@@ -35,28 +35,40 @@ pipelines:
           enabled: true
           window_units: 3
           lanes:
-            - item-events
-            - npcs
+            - item-occurrences
+            - item-registry
+            - location-registry
+            - location-occurrences
+            - npc-registry
             - spells
             - combat-turns
-            - npc-interactions
+            - npc-occurrences
+            - enemy-events
     steps:
-      # Establish session-wide reference artifacts alongside independent item events.
+      # Establish session-wide reference artifacts before their consumers.
       - id: describe-session
         artifacts:
-          item-events:
+          item-registry:
             extract:
-              module: dnd/item-events
+              module: dnd/item-registry
               retries: 2
             merge: appendorder
-            normalize: dnd/item-events
-          npcs:
+            normalize: dnd/item-registry
+          npc-registry:
             extract:
-              module: dnd/npcs
+              module: dnd/npc-registry
               retries: 2
             merge: appendorder
             normalize:
-              module: dnd/npcs
+              module: dnd/npc-registry
+              retries: 2
+          location-registry:
+            extract:
+              module: dnd/location-registry
+              retries: 2
+            merge: appendorder
+            normalize:
+              module: dnd/location-registry
               retries: 2
           scene-descriptions:
             extract:
@@ -65,18 +77,32 @@ pipelines:
             merge: appendorder
             normalize: dnd/scene-descriptions
       - id: extract-events
-        # Accepted NPC grounding and scene-description eligibility artifacts are
-        # supplied in memory to their compatible consumers in this step.
+        # Accepted registry artifacts and scene-description eligibility artifacts
+        # are supplied in memory to their compatible consumers in this step.
         references:
-          npcs:
+          location_registry:
             artifact:
               step: describe-session
-              lane: npcs
+              lane: location-registry
+          npc_registry:
+            artifact:
+              step: describe-session
+              lane: npc-registry
           scene_descriptions:
             artifact:
               step: describe-session
               lane: scene-descriptions
+          item_registry:
+            artifact:
+              step: describe-session
+              lane: item-registry
         artifacts:
+          item-occurrences:
+            extract:
+              module: dnd/item-occurrences
+              retries: 2
+            merge: appendorder
+            normalize: dnd/item-occurrences
           spells:
             extract:
               module: dnd/spells
@@ -95,9 +121,40 @@ pipelines:
               retries: 2
             merge: appendorder
             normalize: dnd/combat-turns
-          npc-interactions:
+          npc-occurrences:
             extract:
-              module: dnd/npc-interactions
+              module: dnd/npc-occurrences
               retries: 2
             merge: appendorder
-            normalize: dnd/npc-interactions
+            normalize: dnd/npc-occurrences
+          location-occurrences:
+            extract:
+              module: dnd/location-occurrences
+              retries: 2
+            merge: appendorder
+            normalize: dnd/location-occurrences
+      - id: track-enemies
+        references:
+          npc_registry:
+            artifact:
+              step: describe-session
+              lane: npc-registry
+          scene_descriptions:
+            artifact:
+              step: describe-session
+              lane: scene-descriptions
+          combat_turns:
+            artifact:
+              step: extract-events
+              lane: combat-turns
+          npc_occurrences:
+            artifact:
+              step: extract-events
+              lane: npc-occurrences
+        artifacts:
+          enemy-events:
+            extract:
+              module: dnd/enemy-events
+              retries: 2
+            merge: appendorder
+            normalize: dnd/enemy-events

internal/cli/assembled_enemy_event_codec_contract_test.go

@@ -0,0 +1,81 @@
+package cli
+
+import (
+	"context"
+	"errors"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+)
+
+const invalidEnemyEventExtractorKey = "test/dnd/invalid-enemy-events"
+
+func TestAssembledEnemyEventLaneRejectsInvalidFinalArtifactDespiteValidatorOverrides(t *testing.T) {
+	components := productionTestComponents(t)
+	if err := pipeline.RegisterExtractor[dnd.EnemyEventList](components.registries.Extractors, pipeline.ModuleSpec{
+		Key:            invalidEnemyEventExtractorKey,
+		Stage:          pipeline.StageExtract,
+		ExecutionClass: contracts.ExecutionClassDeterministic,
+		Requires:       []string{"chunks", "source.transcript"},
+		Provides:       []string{"dnd.enemy_events"},
+		ArtifactKind:   dnd.EnemyEventListKind,
+	}, func() (contracts.Extractor[dnd.EnemyEventList], error) {
+		return invalidEnemyEventExtractor{}, nil
+	}); err != nil {
+		t.Fatalf("register extractor: %v", err)
+	}
+
+	accept := pipeline.ValidatorOverride{Set: true, Validators: []pipeline.ModuleBinding{pipeline.Binding("generic/always_accept")}}
+	resolved, err := pipeline.ResolvePipeline(pipeline.PipelineProfile{
+		ID:    "assembled-invalid-enemy-events",
+		Input: pipeline.Binding("seriatim"),
+		Chunk: pipeline.ModuleBinding{Module: "generic", Options: map[string]any{"max_units": 1}},
+		Artifacts: map[string]pipeline.ArtifactLaneProfile{
+			"enemy-events": {
+				Extract:   pipeline.ModuleBinding{Module: invalidEnemyEventExtractorKey, Validators: accept},
+				Normalize: pipeline.ModuleBinding{Module: pipeline.DefaultNormalizeModule, Validators: accept},
+			},
+		},
+		Output: pipeline.Binding("json"),
+	}, pipeline.ResolveOptions{}, catalogFromRegistries(components.registries))
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v", err)
+	}
+
+	prepared, err := pipeline.Prepare(resolved, components.registries, pipeline.ModuleDependencies{})
+	if err != nil {
+		t.Fatalf("Prepare() error = %v", err)
+	}
+	_, err = pipeline.New().Run(context.Background(), pipeline.RunInput{
+		Prepared:       prepared,
+		RawInput:       readRepositoryFile(t, "examples", "seriatim-minimal-transcript.json"),
+		ChunkCacheMode: pipeline.ChunkCacheBypass,
+	})
+	if err == nil || !strings.Contains(err.Error(), "serialize accepted extract output") || !strings.Contains(err.Error(), "must not exceed") {
+		t.Fatalf("Run() error = %v, want final durable range rejection", err)
+	}
+}
+
+type invalidEnemyEventExtractor struct{}
+
+func (invalidEnemyEventExtractor) Key() string { return invalidEnemyEventExtractorKey }
+
+func (invalidEnemyEventExtractor) ReferenceSlots() []contracts.ReferenceSlot { return nil }
+
+func (invalidEnemyEventExtractor) Extract(ctx context.Context, req contracts.TypedExtractionRequest) (contracts.TypedExtractionResult[dnd.EnemyEventList], error) {
+	if err := ctx.Err(); err != nil {
+		return contracts.TypedExtractionResult[dnd.EnemyEventList]{}, err
+	}
+	if req.Source == nil {
+		return contracts.TypedExtractionResult[dnd.EnemyEventList]{}, errors.New("assembled extractor requires source")
+	}
+	return contracts.TypedExtractionResult[dnd.EnemyEventList]{Value: dnd.EnemyEventList{Events: []dnd.EnemyEvent{{
+		Name:       "Ashfang",
+		Kind:       dnd.EnemyEventKindEngaged,
+		SourceRefs: []source.SourceRef{{SourceID: req.Source.ID, StartUnitID: 2, EndUnitID: 1}},
+	}}}}, nil
+}