Reconcile remediation documentation

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,
+transcript JSON and can produce NPC, location, and item registries; their
-NPC identities, combat turns, NPC interactions, and spell casts.
+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
+    content_file: ./sharedassets/common-dnd-npc-registry.md
-  - role: user
-    content_file: ./task.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"},
+                "start_unit_id": {"type": "integer"},
-                "end_segment": {"type": "integer"}
+                "end_unit_id": {"type": "integer"}
               }
             }
           }

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

@@ -0,0 +1,47 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.dnd.entity_reconcile.llm",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["duplicate_groups"],
+  "properties": {
+    "duplicate_groups": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["members", "canonical"],
+        "properties": {
+          "members": {
+            "type": "array",
+            "items": {"$ref": "#/$defs/selector"}
+          },
+          "canonical": {"$ref": "#/$defs/selector"}
+        }
+      }
+    }
+  },
+  "$defs": {
+    "selector": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["name", "source_refs"],
+      "properties": {
+        "name": {"type": "string", "minLength": 1},
+        "source_refs": {
+          "type": "array",
+          "minItems": 1,
+          "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}
+            }
+          }
+        }
+      }
+    }
+  }
+}

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
+    content_file: ./item-registry.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:
@@ -43,5 +41,5 @@ messages:
 output:
   format: json
   validation_mode: json_schema
-  schema_path: dnd_npc_interactions_llm.v1.json
+  schema_path: dnd_item_occurrences_llm.v1.json
   repair_attempts: 0

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

@@ -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/candidates.md

@@ -0,0 +1,2 @@
+Item candidates:
+{{ input "candidates" }}

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

@@ -0,0 +1,8 @@
+Use candidate names and cited transcript windows only to determine whether
+candidates identify the same item type or unique designation. Do not treat
+nearby evidence, similar objects, or a shared owner as sufficient. Keep
+currency denominations, materially different item types, and 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: ./instructions.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-entity-reconciliation.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./candidates.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-transcript-windows.md
+    cache_control:
+      type: ephemeral
+output:
+  format: json
+  validation_mode: json_schema
+  schema_path: dnd_entity_reconcile_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/candidates.md

@@ -0,0 +1,2 @@
+Location candidates:
+{{ input "candidates" }}

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

@@ -0,0 +1,6 @@
+Use candidate names and their cited transcript windows to determine whether
+candidates identify the same physical place. Do not treat matching names,
+nearby evidence, nested places, or generic labels as sufficient. Keep parent
+and child places, similarly named places, and uncertain aliases separate.
+
+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: ./instructions.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-entity-reconciliation.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./candidates.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-transcript-windows.md
+    cache_control:
+      type: ephemeral
+output:
+  format: json
+  validation_mode: json_schema
+  schema_path: dnd_entity_reconcile_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
+Extract Dungeons & Dragons NPC occurrences from the supplied
-record must contain name, kind, and source_refs. Cite transcript ranges that
+transcript. Include an occurrence only when the transcript establishes one
-support both the NPC identity and the interaction kind.
+supplied NPC, one occurrence kind, and a coherent passage supporting both.
+Use the supplied canonical NPC `name`; never invent or substitute a similar
+name. Cite current-transcript evidence for every occurrence.
+
+Do not summarize, infer relationships, sentiment, factions, motives, aliases,
+or persistent state. Do not identify player characters, anonymous groups, or
+invented NPCs. Split records when an NPC's occurrence kind changes, when
+combat alignment changes, or when an NPC is first mentioned and later becomes
+present.
 
 Use exactly one kind per occurrence:
 

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

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

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

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

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

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

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

@@ -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/candidates.md

@@ -0,0 +1,3 @@
+NPC candidates for identity comparison:
+
+{{ input "candidates" }}

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

@@ -0,0 +1,10 @@
+Use candidate aliases and their cited transcript windows to determine whether
+candidates refer to the same individual. Preserve distinct individuals even
+when their names are similar.
+
+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:
@@ -11,20 +11,20 @@ inputs:
 messages:
   - role: system
     content_file: ./sharedassets/common-dnd-system.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-entity-reconciliation.md
     cache_control:
       type: ephemeral
   - role: user
     content_file: ./candidates.md
   - role: user
-    content_file: ./sharedassets/common-dnd-transcript.md
+    content_file: ./sharedassets/common-dnd-transcript-windows.md
     cache_control:
       type: ephemeral
 output:
   format: json
   validation_mode: json_schema
-  schema_path: dnd_npcs_normalize_llm.v1.json
+  schema_path: dnd_entity_reconcile_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
+outside the chunk.
-events or lore.
-
-Do not return identifiers, source identifiers, source ranges, unit identifiers,
-participants, confidence, or any fields besides kind, title, and summary.

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

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

assets/dnd/scenes/prompts/instructions.md

@@ -1,5 +1,5 @@
-Divide the provided transcript into coherent Dungeons & Dragons scenes for the
+Divide the complete provided transcript into coherent Dungeons & Dragons scenes
-`dnd/scenes` chunk module.
+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
+Cover the complete transcript from its first source unit to its last. Return
-scene. Do not return titles, modes, participants, summaries, boundary notes,
+scenes in source-unit order with no gaps or overlaps. Use only positive integer
-confidence, caveats, final chunk IDs, or chunk indexes.
+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-entity-reconciliation.md

@@ -0,0 +1,7 @@
+Identify only well-supported duplicate groups among the supplied candidates.
+
+Return each selected candidate's supplied contextual descriptor exactly: its
+`name` and complete ordered `source_refs`. A group must contain at least two
+supplied descriptors, and its `canonical` descriptor must be one of its
+members. Do not invent names, ranges, records, evidence, or replacement values.
+Omit any uncertain or unsafe group.

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

@@ -1,14 +1,7 @@
 Transcript units are the only evidence for extracted events and factual claims.
-Campaign and registry references may disambiguate names, aliases, speakers, or
-other identities, but they do not establish events, participation, effects, or
-source evidence.
-
 Every reported factual claim must be supported by cited transcript units. Use
 integer `start_unit_id` and `end_unit_id` values from the transcript. Omit
 `source_id`; Notarius assigns the current source identity.
 
 When supporting evidence is non-contiguous, use multiple narrow ranges rather
 than a broad range that bridges unrelated conversation.
-
-Return exactly one JSON object and no explanatory text. Output only the
-configured JSON object and fields defined by its response schema.

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

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

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

@@ -0,0 +1,7 @@
+You process Dungeons & Dragons gameplay transcripts.
+
+Rely only on the supplied inputs. They 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 +1,5 @@
+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 +1,4 @@
+The complete ordered transcript of this Dungeons & Dragons gameplay session is
+provided below. It may contain multiple scenes.
+
+{{ input "transcript" }}

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

@@ -0,0 +1,6 @@
+Selected Dungeons & Dragons gameplay transcript evidence windows are provided
+below. They may be incomplete, non-contiguous, or overlapping. Use them to
+evaluate candidate identity, but do not treat absence outside these windows as
+evidence.
+
+{{ 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
+    content_file: ./spell-catalog.md
-  - role: user
-    content_file: ./task.md
   - role: user
     content_file: ./instructions.md
     cache_control:

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

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

assets/dnd/spells/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/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/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
 ~~~
 
@@ -332,15 +332,15 @@ step:
 steps:
   - id: describe-session
     artifacts:
-      npcs:
+      npc-registry:
-        extract: dnd/npcs
+        extract: dnd/npc-registry
-        normalize: dnd/npcs
+        normalize: dnd/npc-registry
   - id: extract-events
     references:
-      npcs:
+      npc_registry:
         artifact:
           step: describe-session
-          lane: npcs
+          lane: npc-registry
     artifacts:
       spells:
         extract: dnd/spells
@@ -370,14 +370,38 @@ 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. |
+| **location_registry** | Required normalized location registry for location-occurrence extraction and normalization. |
-| **scene_descriptions** | Required normalized scene-description artifact for combat-turn extraction. |
+| **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
+normalized combat-turn module may use optional **npc_registry**. Location occurrences
-shows generated **npcs** and **scene_descriptions** bindings.
+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 +409,29 @@ 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 registry](integrations/dnd-npc-registry-artifacts.md),
-[NPC interactions](integrations/dnd-npc-interaction-artifacts.md),
+[NPC occurrences](integrations/dnd-npc-occurrence-artifacts.md),
 [combat turns](integrations/dnd-combat-turn-artifacts.md),
-[item events](integrations/dnd-item-event-artifacts.md), and
+[item registry](integrations/dnd-item-registry-artifacts.md),
-[scene descriptions](integrations/dnd-scene-description-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 +441,15 @@ 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** |
+| Item occurrences | **extract/dnd/item-occurrences/shape**, **extract/dnd/item-occurrences/registry**, **extract/dnd/item-occurrences/source_refs**, **extract/dnd/item-occurrences/source_relatedness**, **normalize/dnd/item-occurrences/invariants** |
-| NPC interactions | **extract/dnd/npc-interactions/shape**, **extract/dnd/npc-interactions/registry**, **extract/dnd/npc-interactions/source_refs**, **extract/dnd/npc-interactions/source_relatedness**, **normalize/dnd/npc-interactions/invariants** |
+| Item registry | **extract/dnd/item-registry/shape**, **extract/dnd/item-registry/source_refs**, **extract/dnd/item-registry/source_relatedness**, **normalize/dnd/item-registry/identity** |
+| NPC occurrences | **extract/dnd/npc-occurrences/shape**, **extract/dnd/npc-occurrences/registry**, **extract/dnd/npc-occurrences/source_refs**, **extract/dnd/npc-occurrences/source_relatedness**, **normalize/dnd/npc-occurrences/invariants** |
 | Scene descriptions | **extract/dnd/scene-descriptions/shape**, **extract/dnd/scene-descriptions/source_refs**, **extract/dnd/scene-descriptions/source_relatedness**, **normalize/dnd/scene-descriptions/invariants** |
+| Enemy events | **extract/dnd/enemy-events/shape**, **extract/dnd/enemy-events/engagements**, **extract/dnd/enemy-events/source_refs**, **extract/dnd/enemy-events/source_relatedness**, **normalize/dnd/enemy-events/invariants** |
+| 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 +458,15 @@ 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 |
+| Item occurrences | generic/valid_json, extract/dnd/item-occurrences/shape, extract/dnd/item-occurrences/registry, extract/dnd/item-occurrences/source_refs, generic/valid_json_schema, extract/dnd/item-occurrences/source_relatedness | generic/valid_json, extract/dnd/item-occurrences/shape, extract/dnd/item-occurrences/registry, normalize/dnd/item-occurrences/invariants, extract/dnd/item-occurrences/source_refs, generic/valid_json_schema, extract/dnd/item-occurrences/source_relatedness |
-| NPC interactions | generic/valid_json, extract/dnd/npc-interactions/shape, extract/dnd/npc-interactions/registry, extract/dnd/npc-interactions/source_refs, generic/valid_json_schema, extract/dnd/npc-interactions/source_relatedness | generic/valid_json, extract/dnd/npc-interactions/shape, extract/dnd/npc-interactions/registry, normalize/dnd/npc-interactions/invariants, extract/dnd/npc-interactions/source_refs, generic/valid_json_schema, extract/dnd/npc-interactions/source_relatedness |
+| Item registry | generic/valid_json, extract/dnd/item-registry/shape, extract/dnd/item-registry/source_refs, generic/valid_json_schema, extract/dnd/item-registry/source_relatedness | generic/valid_json, extract/dnd/item-registry/shape, normalize/dnd/item-registry/identity, extract/dnd/item-registry/source_refs, generic/valid_json_schema, extract/dnd/item-registry/source_relatedness |
+| NPC occurrences | generic/valid_json, extract/dnd/npc-occurrences/shape, extract/dnd/npc-occurrences/registry, extract/dnd/npc-occurrences/source_refs, generic/valid_json_schema, extract/dnd/npc-occurrences/source_relatedness | generic/valid_json, extract/dnd/npc-occurrences/shape, extract/dnd/npc-occurrences/registry, normalize/dnd/npc-occurrences/invariants, extract/dnd/npc-occurrences/source_refs, generic/valid_json_schema, extract/dnd/npc-occurrences/source_relatedness |
 | Scene descriptions | generic/valid_json, extract/dnd/scene-descriptions/shape, extract/dnd/scene-descriptions/source_refs, generic/valid_json_schema, extract/dnd/scene-descriptions/source_relatedness | generic/valid_json, extract/dnd/scene-descriptions/shape, normalize/dnd/scene-descriptions/invariants, extract/dnd/scene-descriptions/source_refs, generic/valid_json_schema, extract/dnd/scene-descriptions/source_relatedness |
+| Enemy events | generic/valid_json, extract/dnd/enemy-events/shape, extract/dnd/enemy-events/engagements, extract/dnd/enemy-events/source_refs, generic/valid_json_schema, extract/dnd/enemy-events/source_relatedness | generic/valid_json, extract/dnd/enemy-events/shape, normalize/dnd/enemy-events/invariants, extract/dnd/enemy-events/source_refs, generic/valid_json_schema, extract/dnd/enemy-events/source_relatedness |
+| 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
+reference files. Notarius generates a stable prompt session for the resolved
-needed, pass the supported CLI flags. Supply credentials through Notarius's
+input module and exact input bytes. Pass **--session-id** only when intentionally
-documented configuration and environment mechanisms, never as command-line
+grouping different invocations under a different session. Supply credentials
-arguments or generated secret-bearing configuration.
+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

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
+The [NPC-occurrence artifact](dnd-npc-occurrence-artifacts.md) records
-broader NPC occurrences. The [JSON output contract](json-output.md) defines
+broader NPC occurrences. The [enemy-event artifact](dnd-enemy-event-artifacts.md)
-publication, and [D&D module internals](../internal/dnd.md) describes routing
+uses combat turns as grounding only; turns do not establish an enemy event or
-and validation mechanics.
+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` |
+| Artifact kind | `dnd/npc-occurrence-list` |
-| Schema ID | `notarius.dnd.npc_interactions` |
+| Schema ID | `notarius.dnd.npc_occurrences` |
-| Schema name | `notarius_dnd_npc_interactions_v1` |
+| Schema name | `notarius_dnd_npc_occurrences_v1` |
 | Schema version | `v1` |
 | Media type | `application/json` |
 
-`v1` is a strict JSON object with required `interactions`; the array may be
+`v1` is a strict JSON object with required `occurrences`; the array may be
-empty. Interaction and source-reference objects reject unknown fields. An
+empty. Occurrence and source-reference objects reject unknown fields. An
 incompatible shape change requires a new schema version.
 
 ## Wire shape
 
-Each interaction has these required fields:
+Each occurrence has these required fields:
 
 | Field | Contract |
 | --- | --- |
+| `npc_id` | Exact durable ID from the required NPC registry. |
 | `name` | Non-empty canonical display name from the required NPC registry. |
-| `kind` | One of the interaction categories below. |
+| `kind` | One of the occurrence categories below. |
 | `source_refs` | One or more transcript evidence ranges. |
 
 Each source reference has exactly `source_id`, `start_unit_id`, and
 `end_unit_id`. It identifies an inclusive range in the current transcript;
 unit IDs are positive and the start may not follow the end. Extraction evidence
-for an interaction is confined to its accepted chunk.
+for an occurrence is confined to its accepted chunk.
 
 ```json
 {
-  "interactions": [
+  "occurrences": [
     {
+      "npc_id": "npc:sha256:example",
       "name": "Mira Thorn",
       "kind": "dialogue",
       "source_refs": [
@@ -48,7 +50,7 @@ for an interaction is confined to its accepted chunk.
 }
 ```
 
-## Interaction categories
+## Occurrence categories
 
 | Kind | Meaning |
 | --- | --- |
@@ -65,14 +67,24 @@ for uncertain classification.
 
 ## Identity, evidence, and order
 
-The required normalized [NPC artifact](dnd-npc-artifacts.md) resolves `name`.
+The required normalized [NPC registry artifact](dnd-npc-registry-artifacts.md)
-Registry references are provenance only and never replace an interaction's own
+supplies names-only contextual grounding to the model. Notarius resolves the
-evidence. Normalization canonicalizes recognized registry names, orders and
+selected name and writes the exact `{npc_id, name}` pair. An unknown or
-deduplicates exact source references, then orders interactions by valid source
+ambiguous selection rejects the complete model result; normalization does not
+repair names by similarity. Registry references are provenance only and never
+replace an occurrence's own evidence.
+The registry may include an identity established by a factual third-party
+mention; that provenance alone does not create a `mentioned` occurrence. Each
+occurrence remains a separately cited fact in the current transcript.
+Normalization validates the exact pair, orders and
+deduplicates exact source references, then orders occurrences by valid source
 chronology, NPC comparison identity, display name, kind, and reference sequence.
-Only entries with the same canonical name, kind, and complete valid evidence
+Only entries with the same NPC ID, canonical name, kind, and complete valid evidence
 sequence are collapsed; distinct categories or evidence remain separate.
 
 See the [combat-turn artifact](dnd-combat-turn-artifacts.md) for combat-action
-occurrences and the [JSON output contract](json-output.md) for publication.
+occurrences. The [enemy-event artifact](dnd-enemy-event-artifacts.md) consumes
-Pipeline mechanics are described in [D&D module internals](../internal/dnd.md).
+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

@@ -36,7 +36,7 @@ evidence publishes `contexts: []`.
   "source_id": "session-alpha",
   "source_digest": "sha256:0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef",
   "window_units": 1,
-  "selected_lanes": ["npcs", "spells"],
+  "selected_lanes": ["npc_registry", "spells"],
   "contexts": [
     {
       "context_ref": {

docs/integrations/json-output.md

@@ -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),
+[spells](dnd-spell-artifacts.md), [NPC registry](dnd-npc-registry-artifacts.md),
-[NPC interactions](dnd-npc-interaction-artifacts.md),
+[NPC occurrences](dnd-npc-occurrence-artifacts.md),
 [combat turns](dnd-combat-turn-artifacts.md),
-[item events](dnd-item-event-artifacts.md), and
+[item registry](dnd-item-registry-artifacts.md),
-[scene descriptions](dnd-scene-description-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
+compatibility. The generated identifier is 76 ASCII characters, within
-may be exposed to providers and provider observability.
+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
+5. construct registries, the scheduled LLM client, and prepared modules;
-   requested cache/checkpoint collaborators;
+6. read the source input once, resolve its effective session from the explicit
-6. read the source input and invoke the framework runner; and
+   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) |
+| Item occurrences | [item-occurrence artifacts](../integrations/dnd-item-occurrence-artifacts.md) |
-| NPC interactions | [NPC-interaction artifacts](../integrations/dnd-npc-interaction-artifacts.md) |
+| Item registry | [item-registry artifacts](../integrations/dnd-item-registry-artifacts.md) |
+| NPC occurrences | [NPC-occurrence artifacts](../integrations/dnd-npc-occurrence-artifacts.md) |
 | Scene descriptions | [scene-description artifacts](../integrations/dnd-scene-description-artifacts.md) |
+| Enemy events | [enemy-event artifacts](../integrations/dnd-enemy-event-artifacts.md) |
+| 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
+typed builder. Scene chunking, every extractor, and NPC, location, and item-registry
-registered as `llm_backed`; the remaining current D&D mergers and normalizers
+normalization are registered as `llm_backed`; the remaining current D&D mergers
-are `deterministic`. The metadata is available to catalog inspection and
+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 +44,67 @@ the contracts above define durable data.
 
 ## Prompt Construction
 
-D&D extractors assemble prompts from an ordered manifest of shared and
+D&D LLM-facing content lives beneath `assets/dnd/`. Each module contributes a
-module-owned assets. Reuse the shared D&D system, evidence, identity,
+local `prompt.yaml` declaration and `instructions.md`; input-specific files
-reference, and transcript assets instead of copying their text into individual
+such as a catalog, registry, grounding projection, or candidate collection are
-modules. A manifest’s declared sequence, including cache-control placement, is
+local only when that module needs them. New extractor content uses its feature
-part of the prompt behavior.
+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
+profile. The D&D registrar registers the fallback, while an operator can
-OpenRouter model, timeout, and service-tier policy. An operator may provide a
+replace it with a complete profile of the same ID from the configured PromptKit
-complete profile with the same ID through the configured PromptKit source; that
+source. Deployment profile selection is documented in
-definition replaces the fallback rather than merging with it. The fallback
-leaves reasoning and optional sampling controls unspecified. Deployment profile
-selection and the maintained operator example are documented in
 [Configuration](../config.md#promptkit-profiles).
 
-All extraction prompts share this four-message rendered prefix: the system
+The transcript assets have distinct consumers. Scene chunking consumes the
-message without cache control, the identity message without cache control, the
+complete-session `common-dnd-transcript-full.md`; extraction prompts consume
-campaign-reference message with ephemeral cache control, and the chunk
+the current-chunk `common-dnd-transcript-chunk.md`; and NPC, location, and item
-transcript message with ephemeral cache control. This gives equivalent
+normalization consume `common-dnd-transcript-windows.md` alongside their
-extraction requests the same reusable prefix through their source material.
+candidate collections. Player, party, glossary, and compatible campaign
+references provide disambiguating context only when declared by the active
+prompt; they never establish evidence. Reference material is canonically
+ordered before rendering so equivalent inputs remain stable.
 
-Extraction-evidence policy, generated NPC registries, spell catalogs, module
+Extraction prompts render the common system and identity messages first, then
-tasks, and instructions follow the transcript because they are not universal
+cached campaign references and the cached chunk transcript. Evidence policy and
-across all extraction lanes. The final instructions message carries ephemeral
+any lane-specific registry, catalog, or grounding projection follow that
-cache control; evidence, registry, catalog, and task messages do not. Preserve
+prefix. The final module instructions message is ephemeral. This keeps the
-this division when changing an extractor or its assets so prompt-cache behavior
+reusable extraction prefix identical while preserving the lane-specific suffix.
-remains stable.
 
-The other D&D LLM prompts intentionally follow different patterns. Scene
+Scene chunking intentionally uses a different order: system, cached campaign
-chunking has no sibling extraction lane with which to share its full transcript,
+references, uncached module instructions, then the final ephemeral full
-so it renders campaign references before its task and instructions, then places
+transcript. Entity normalization also has its own order: system, uncached
-the cacheable full transcript last. NPC normalization keeps its task and
+module instructions, ephemeral reconciliation policy, uncached candidates, and
-cacheable instructions before the candidate collection, followed by the
+final ephemeral transcript windows. These orders and cache controls are prompt
-cacheable transcript windows: candidates must be available before their
+behavior; change them only through the owning manifest and prompt declaration.
-supporting evidence is evaluated, and those windows are not a cross-lane
-prefix. Mounted assets and their declared message order determine the prompt
-fingerprint, so intentional prompt edits continue to invalidate stale
-checkpoints.
-
-All extractors use the shared prompt-input preparation rules. The current chunk
-is copied into transcript material; player, party, glossary, and compatible
-campaign references are context for disambiguation, not source evidence.
-Reference prompt material is canonically ordered before it is rendered, which
-keeps equivalent inputs stable across runs.
 
 ## Evidence, Candidates, And Normalization
 
@@ -96,18 +117,28 @@ 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
+Enemy-event extraction additionally rejects a second `engaged` observation for
-interactions, and scene descriptions. They canonicalize display values and
+the same comparison identity within one scene-scoped result. Normalization may
-evidence, use source-document order for stable output, and issue bounded
+combine results from distinct scenes, so it intentionally does not apply that
-warnings for changes or collapsed duplicates. The NPC normalizer is the
+rule. Configuration owns the exact validator key and chain position.
-intentional exception: it first produces a deterministic candidate set, then
+
-uses a bounded structured-LLM proposal to reconcile identity groups. Invalid
+Normalizers are deterministic for spells, combat turns, item occurrences, NPC
-or unusable proposals retain the deterministic result and surface retry or
+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. The proposal selects supplied
+descriptors—names with their candidate source references—not durable IDs.
+Request-local candidate keys may support resolution internally, but are never
+included in model input or output. Colliding descriptors are ineligible, and
+invalid or unusable proposals retain the deterministic result with retry or
 fallback diagnostics; the model does not directly replace durable records.
 
 ## Generated References And Grounding
@@ -118,30 +149,55 @@ 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
+NPC and item registry consumers receive names-only grounding. Location
-actors for spells and combat turns and are required for NPC interactions, but
+consumers receive a contextual selector containing the canonical name and the
-they do not supply evidence. Scene-description registries are eligibility-only
+registry references needed to distinguish same-name places. The calling module
-projections: they retain the current chunk’s classification data, not scene
+resolves those supplied selections locally and maps them into the unchanged
-prose or evidence, and exist to route combat extraction.
+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. |
+| Item occurrences | Requires the normalized item registry for exact deterministic grounding at extraction and normalization. Campaign context may disambiguate, but the registry never becomes occurrence evidence. |
-| NPC interactions | Requires the normalized NPC registry at extraction and normalization, using it for canonical actor grounding only. |
+| Item registry | Produces source-grounded item types and unique designations. Its LLM-assisted reconciliation is proposal-only, preserves distinct currency denominations and item types, and does not create per-instance identities. |
+| NPC occurrences | Requires the normalized NPC registry at extraction and normalization, using it for canonical actor grounding only. It separately emits cited current-transcript occurrence facts, including `mentioned`, rather than deriving them from registry provenance. |
 | Scene descriptions | Produces the classifications consumed by combat routing; it does not consume an NPC registry or provide evidence for combat artifacts. |
+| Enemy events | Requires NPC, scene-description, combat-turn, and NPC-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,
+passes the supplied request session through to PromptKit's direct per-run
-retains the same value as the `session_id` prompt variable for maintained
+session field, retains the same value as the `session_id` prompt variable for
-prompt compatibility, and forwards profile selection. It then creates one
+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 +129,24 @@ 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,
+LLM-facing content is embedded once by the root `assets` package. Each consumer
-and private response schema. Shared D&D wording is owned by the D&D shared
+uses only its scoped subtree, while the module retains ownership of its prompt
-asset package; the detailed D&D conventions are in
+declaration, ordered manifest, private response-schema identity, and
-[D&D Module Internals](dnd.md). The mounted prompt assets used by a module also
+registration. Shared D&D fragments are selected by D&D's shared implementation;
-determine its prompt fingerprint. Schema loaders validate JSON, attach identity
+the detailed convention is in [D&D Module Internals](dnd.md). This physical
-and digest metadata, make defensive copies, and expose diagnostics without raw
+arrangement and its data-only boundary are defined by
-schema bytes.
+[Architecture](../policy/architecture.md) and
+[ADR-0011](../adr/0011-centralize-llm-assets.md), rather than by this runtime
+guide.
+
+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.
 
 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 +180,9 @@ 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/overview.md

@@ -29,6 +29,7 @@ physical state roots.
 | Generic models | **internal/core/source**, **internal/core/artifacts**, **internal/framework/contracts** | Source documents and chunks, manifests and provenance, plus typed artifact, reference, validation, output, and structured-completion contracts. |
 | Pipeline framework | **internal/framework/pipeline** | Registries, profile and reference resolution, typed preparation, validation, retry coordination, ordered execution, handoff, and result assembly. |
 | LLM and prompt runtime | **internal/framework/llm**, **internal/framework/promptfs** | Provider-neutral structured completions, scheduling, profile recording, prompt assets, schema registration, and credential-shaped-value redaction. |
+| 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. |
 

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
+dependencies, input bytes, a supplied prompt session, and state/debug
-output files, normalized artifacts, recorded rejections and warnings, manifest
+collaborators. It returns logical output files, normalized artifacts, recorded
-provenance, and checkpoint decisions. The CLI owns process arguments,
+rejections and warnings, manifest provenance, and checkpoint decisions. The
-configuration discovery, physical roots, and placement of returned output
+CLI owns process arguments, configuration discovery, session resolution,
-files.
+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
+provenance. For a positive slot limit, it reads at most the limit plus one byte
-until its producing step completes.
+and rejects overflow before retaining content. A generated-artifact selector
+remains declared but has no bytes until its producing step completes.
 
 Preparation is the construction boundary. It validates the resolved shape and
 registry set, clones the resolved data, then constructs the input adapter,
-chunker, stage-local validators, every typed lane, and output encoder with
+chunker, stage-local validators, every typed lane, and output encoder. Each
-cloned options, references, and shared dependencies. It also collects stable
+registered builder receives its own cloned build request immediately before its
-checkpoint fingerprints. Missing registrations, incompatible typed entries,
+module-owned code runs. Preparation also collects stable checkpoint
-nil implementations, and constructor failures are reported before source
+fingerprints. Missing registrations, incompatible typed entries, nil
-parsing or any stage operation begins.
+implementations, and constructor failures are reported before source parsing
+or any stage operation begins.
 
 An output encoder can opt into source-evidence publication through its output
 policy. Preparation keeps the configured lane allowlist and active lanes
@@ -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
+their target: chunks, codec-decoded typed candidates, or serialized codec
-approve, approve with warnings, reject, or fail. A rejection is an ordinary
+bytes. Each typed validator receives a newly decoded value from the one
-pipeline result; a validator error is a framework error.
+candidate serialization for that attempt, while serialized validators receive
+separately owned representation bytes and schema metadata. They may approve,
+approve with warnings, reject, or fail. A rejection is an ordinary pipeline
+result; a validator error is a framework error.
 
 The runner applies the binding's retry policy around a stage operation and its
 complete validation chain. It preserves warnings only from the final accepted

docs/internal/state.md

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

docs/operations.md

@@ -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
+Concurrency has two independent layers. Notarius **total_llm** defaults to 16
-application-wide provider-call limit shared by all backends, modules, retries,
+and is the application-wide provider-call limit shared by all backends,
-and validators. PromptKit may impose a narrower admission limit for the
+modules, retries, and validators. PromptKit may impose a narrower admission
-selected backend. The effective active-generation bound is the intersection of
+limit for the selected backend. The effective active-generation bound is the
-both limits and can therefore be lower than **total_llm**. Built-in OpenRouter
+intersection of the Notarius limit, any PromptKit backend limit, and work made
-profiles use PromptKit's upstream backend limit; endpoint-only profiles have no
+available by the pipeline. Built-in OpenRouter profiles use PromptKit's
-PromptKit backend limit and remain bounded by Notarius. For the configured
+upstream backend limit; endpoint-only profiles have no PromptKit backend limit
-local backend, a zero **concurrency_limit** leaves only the Notarius scheduler
+and remain bounded by Notarius. For the configured local backend, a zero
-as a call limit. A positive value makes the effective active local-generation
+**concurrency_limit** leaves only the Notarius scheduler as a call limit. A
-bound the smaller of **total_llm** and that local limit.
+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

@@ -44,6 +44,13 @@ 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 +80,12 @@ 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 +183,12 @@ 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; [ADR-0012](../adr/0012-resolve-opaque-entity-identifiers-deterministically.md)
+records the rationale and limited request-local-label exception.
+
 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/audit-plan.md

@@ -0,0 +1,516 @@
+# Codebase Audit Plan
+
+## Purpose
+
+This document defines a repository-wide audit of Notarius for correctness,
+efficiency, maintainability, and clarity. The audit should identify concrete
+improvements without treating abstraction, fewer lines, or higher test coverage
+as goals in themselves.
+
+The audit is intentionally separate from implementation. Its findings should
+be evidence-backed and sufficiently specific to support a later remediation
+roadmap, but the audit should not modify production code, tests, assets, or
+current-behavior documentation.
+
+## Governing Principles
+
+The audit must preserve the architecture and testing policies in
+`docs/policy/architecture.md` and `docs/policy/testing.md`.
+
+In particular:
+
+- Notarius remains a fixed, staged pipeline rather than a general workflow
+  engine.
+- Generic framework packages must remain domain-neutral, and production
+  modules must not acquire CLI or physical-state responsibilities.
+- Typed artifact boundaries, exact codec compatibility, deterministic ordering,
+  whole-output validation, and generated-reference provenance are correctness
+  properties, not incidental complexity to be optimized away.
+- The root `assets` package remains a content-only dependency leaf.
+- Shared helpers should protect demonstrated common semantics. Similar-looking
+  code with different ownership, error policy, identity rules, or type contracts
+  should remain separate.
+- Tests should protect durable behavior and meaningful risks. The audit should
+  not recommend tests merely to increase coverage or freeze implementation
+  details.
+- Efficiency claims must distinguish measured or structurally credible costs
+  from cosmetic line-count reductions. Optimizing local CPU work that is
+  insignificant beside an LLM call is low priority unless it also simplifies
+  correctness or applies to large inputs.
+
+## Audit Questions
+
+Every audited area should be examined through the following questions.
+
+### Correctness
+
+- Are documented architecture invariants enforced at the correct boundary?
+- Can invalid configuration, incompatible artifact types, malformed references,
+  or unavailable dependencies reach execution when they could be rejected
+  during resolution or preparation?
+- Are nil, empty, absent, rejected, failed, and canceled states distinguished
+  consistently?
+- Are stored or returned slices, maps, byte slices, options, metadata, source
+  documents, references, and artifacts defensively owned where required?
+- Are public ordering, selected errors, warnings, and checkpoint decisions
+  deterministic regardless of map or goroutine completion order?
+- Do cancellation, retry, validation, and partial-work semantics match their
+  documented ownership?
+- Do checkpoint and chunk-plan identities include every semantic dependency and
+  exclude scheduling-only or diagnostic state?
+- Can auxiliary references accidentally become source evidence, or can
+  generated references bypass codec, schema, provenance, or step-order checks?
+- Can provider-specific values, credentials, or source content escape through
+  errors, manifests, debug summaries, cache state, or logs?
+- Do schemas, codecs, candidate decoders, normalizers, and validators agree on
+  the exact durable contract without silently accepting incompatible shapes?
+
+### Duplication And Shared Mechanics
+
+- Which exact or near-duplicate implementations express the same invariant and
+  failure policy?
+- Has duplicated code already drifted in naming, nil handling, canonicalization,
+  metadata, fingerprints, validation, or diagnostics?
+- Would a helper have a natural owner and a smaller, clearer contract than the
+  duplicated callers?
+- Can an extraction preserve static typing and package ownership, or would it
+  require reflection, `any`, callbacks with many policy parameters, or a
+  domain-neutral package importing domain concepts?
+- Is repeated code required by a small interface adapter or typed registration
+  boundary and therefore clearer when left explicit?
+
+As a default heuristic, prioritize a shared helper when identical semantics
+appear in three or more production sites, or in two sites where divergence
+would create a meaningful correctness risk. Do not use that heuristic as a
+quota: one substantial duplicate may warrant extraction, while widespread
+one-line interface methods may not.
+
+### Simplicity And Idiomatic Go
+
+- Does a function combine orchestration, policy, transformation, persistence,
+  and reporting that could be separated along existing ownership boundaries?
+- Are repeated scans, sorts, conversions, clones, encodes, or decodes doing work
+  that can safely occur once?
+- Are intermediate representations necessary, or can a value be validated,
+  canonicalized, and mapped in one comprehensible pass?
+- Are maps, sets, stable sorts, generics, standard-library helpers, and error
+  wrapping used idiomatically?
+- Are abstractions earning their complexity, or are interfaces, option layers,
+  wrappers, aliases, compatibility paths, and private types left over after a
+  completed migration?
+- Are there unreachable error branches, redundant fingerprints or digests,
+  duplicated sources of truth, or accessors used only by tests?
+- Can a smaller implementation preserve exact observable behavior and safety
+  properties?
+
+### Explanatory Comments
+
+Comments should be recommended where the code is necessarily complex because
+it preserves a non-obvious invariant. Good candidates include:
+
+- concurrency coordination, cancellation, and stable error selection;
+- checkpoint identity, reuse, forced recomputation, and dependency invalidation;
+- typed erasure and restoration at framework boundaries;
+- generated-reference ordering and provenance;
+- canonicalization and identity resolution where registry evidence differs
+  from occurrence evidence;
+- prompt ordering or input identity required for backend caching; and
+- path confinement, atomic publication, redaction, or terminal error precedence.
+
+Recommend comments that explain *why* a step or ordering constraint exists and
+what would break if it changed. Do not recommend comments that narrate syntax,
+repeat a function name, duplicate current-behavior documentation, or preserve
+implementation history.
+
+### Tests
+
+- Is each consequential invariant protected at the narrowest stable boundary?
+- Are concurrency, cancellation, retries, recovery, compatibility, path safety,
+  and data-integrity behavior credibly exercised?
+- Do higher-level contract tests duplicate lower-level cases without adding
+  integration confidence?
+- Are tests coupled to private constants, helper shape, exact prose, full error
+  strings, or collaborator choreography rather than behavior?
+- Can repetitive fixtures or fakes be simplified without creating a test
+  framework more complex than the tests?
+- Would a focused fuzz test, race test, or package-level invariant test protect
+  a realistic risk better than several example tests?
+
+## Evidence And Finding Standards
+
+Static metrics and textual similarity are discovery aids, not findings. A long
+function may be a clear linear coordinator; identical methods may be useful
+typed adapters. Every reported finding must include:
+
+1. a concise title and severity;
+2. exact files and symbols;
+3. the observed behavior or structural evidence;
+4. the correctness, efficiency, maintenance, or comprehension impact;
+5. a concrete recommended direction;
+6. important invariants the remediation must preserve;
+7. focused validation that would demonstrate success; and
+8. whether the recommendation is independent or should be grouped with another
+   finding.
+
+Use these severities:
+
+- **High:** a credible risk of corrupt output, unsafe state handling, secret
+  exposure, stale reuse, deadlock, nondeterminism, or violated external
+  contract.
+- **Medium:** a plausible behavioral defect, meaningful wasted work on common
+  paths, or complexity/duplication likely to cause future correctness drift.
+- **Low:** a contained simplification, small efficiency improvement, dead code,
+  naming issue, or missing explanation with no current behavioral failure.
+
+The audit should explicitly record examined areas with no findings. This makes
+coverage visible and prevents later agents from repeatedly rediscovering the
+same safe design.
+
+## Repository Areas
+
+### 1. Architecture And Dependency Boundaries
+
+Inspect `docs/policy/architecture.md`, `docs/adr/`, `docs/internal/overview.md`,
+package imports, module registrars, and the CLI composition root.
+
+Look for:
+
+- framework or core code depending on production modules;
+- modules depending on CLI, physical roots, or provider-specific types;
+- domain knowledge placed in generic helpers;
+- duplicated registries or composition policy outside the owning registrar;
+- abstractions that turn the fixed pipeline into an implicit general graph; and
+- current code that no longer matches an accepted ADR or documented invariant.
+
+Graph-reported cross-layer calls must be traced before being classified because
+tests and interface implementations can resemble dependency inversions without
+creating a production import violation.
+
+### 2. Configuration And CLI Composition
+
+Inspect `internal/core/config`, `internal/cli`, configuration parsing and
+redaction tests, profile construction, session derivation, catalog assembly,
+reference overrides, run-result handling, terminal reporting, and maintained
+example contract tests.
+
+Pay particular attention to the currently dense paths around
+`runPipelineCommand`, configuration profile validation, selected reference
+targets, recomputation policy, and option normalization. Determine whether
+their complexity reflects necessary composition or mixed responsibilities that
+can be separated without moving policy into the framework.
+
+Verify:
+
+- file, environment, CLI, pipeline, binding, and prompt-default precedence;
+- consistent strict option and unknown-field handling;
+- session identity independence from references and pipeline-local changes;
+- effective profile and runtime fingerprint consistency;
+- redaction before errors or debug/manifest boundaries;
+- output publication only after framework success; and
+- one guarded terminalization path that preserves the primary failure.
+
+### 3. Pipeline Resolution, Preparation, And Typed Registries
+
+Inspect `internal/framework/pipeline/profile.go`, `prepare.go`, registry files,
+`options.go`, `references.go`, `handoff.go`, `construction.go`, typed contracts,
+and their focused tests.
+
+This area deserves a dedicated pass because the current graph identifies
+`ResolvePipeline`, generated-binding validation, reference-target resolution,
+and generated-reference construction as high-complexity or high-fan-in code.
+
+Verify:
+
+- static failures occur before source parsing;
+- selected and unselected lanes do not contaminate each other's requirements;
+- stage defaults and overrides have one canonical resolution path;
+- typed registration and private erasure cannot panic or accept near-matching
+  artifact types;
+- generated bindings reject cycles, forward references, ambiguity, wrong kinds,
+  and missing accepted normalized producers;
+- materialized reference bytes and options are cloned and bounded; and
+- resolved composition and prepared fingerprints include the complete semantic
+  policy exactly once.
+
+Compare input, chunker, extractor, merger, normalizer, output, validator, codec,
+evidence-projector, and validator-chain registries for shared mechanics and
+intentional differences. Repeated typed registration code is a candidate only
+if a helper can retain useful compile-time guarantees and stage-specific
+diagnostics.
+
+### 4. Pipeline Execution, Validation, Retry, And Concurrency
+
+Inspect `runner*.go`, `typed_execution.go`, `runner_typed.go`,
+`runner_concurrent.go`, validation-chain execution, normalize retry behavior,
+synchronized collaborators, and the concurrency, cancellation, retry, debug,
+and checkpoint tests.
+
+Trace complete paths rather than reviewing helper files in isolation:
+
+- source and chunk-plan selection through chunk validation;
+- deterministic chunk-first/lane-second dispatch;
+- lane extraction through merge and normalize continuations;
+- rejection versus framework-error propagation;
+- cancellation before dispatch, while queued, and while running;
+- retry attempts and warning retention;
+- stable error selection after concurrent completion;
+- checkpoint hydration back into typed execution; and
+- output suppression after a framework error.
+
+Look for goroutine leaks, unbounded work, lock-order risks, double release or
+double recording, races on shared result state, unnecessary serialization,
+and repeated canonicalization. Comments are especially valuable here when they
+explain ordering or cancellation invariants that are not apparent from local
+control flow.
+
+### 5. State, Checkpoints, Chunk Plans, Debugging, And File Safety
+
+Inspect `internal/framework/checkpoint`, `chunkplan`, `chunkmap`, `debug`,
+`evidencecontext`, `internal/core/fileio`, `debugbundle`, and their CLI
+composition.
+
+Verify:
+
+- narrow path validation and symlink-resistant confinement;
+- atomic writes and recoverable explicit cleanup;
+- separation of checkpoint recording, resume loading, chunk-plan caching, and
+  debug capture;
+- canonical encoding before content identity is trusted;
+- complete but non-secret checkpoint fingerprints;
+- correct ordinary-resume and selective-recompute behavior;
+- producer dependency invalidation across ordered steps;
+- immutable hydration and no aliasing with stored bytes;
+- debug data never influencing execution or reuse; and
+- terminal persistence failures never obscuring the primary error.
+
+Review the repeated extract/merge/normalize recorder and loader methods, path
+component validators in multiple state packages, and clone/encode/decode paths.
+Determine which repetition is a clear stage adapter and which can share a
+private primitive without weakening reason-code ownership or diagnostics.
+
+### 6. LLM Runtime, Prompt Filesystems, And Assets
+
+Inspect `internal/framework/llm`, `promptfs`, the PromptKit integration,
+scheduler, profile-source construction, prompt/schema registries, root
+`assets`, module prompt manifests, and relevant D&D shared assets.
+
+Verify:
+
+- every provider call passes through the shared scheduler and cancellation
+  removes queued calls safely;
+- PromptKit and Notarius concurrency limits compose as documented;
+- profile inspection and runtime use identical source precedence;
+- session IDs, profile-source fingerprints, prompt fingerprints, and schema
+  fingerprints reflect the intended semantic inputs;
+- secrets and provider-specific error types do not cross the boundary;
+- prompt inputs and private outputs do not expose opaque entity IDs;
+- prompt ordering, stable prefixes, and cache controls remain intentional;
+- schema loaders and filesystem adapters validate once and return defensive
+  data; and
+- the root assets package contains no business logic.
+
+Compare the LLM asset registry and prompt-filesystem adapters for duplicated
+filesystem behavior. Review repeated prompt/schema loader and metadata code in
+module packages, but reject an extraction that would centralize domain prompt
+ownership or make unrelated assets share one invalidation boundary.
+
+### 7. Generic And Seriatim Modules
+
+Inspect `internal/modules/generic` and `internal/modules/seriatim`, including
+module specs, option decoding, chunk planning, input translation, validators,
+output encoding, evidence-context publication, registration, and tests.
+
+Verify that:
+
+- external Seriatim details end at the input boundary;
+- generic chunking and output remain domain-neutral;
+- chunk plans and source units preserve source-addressed invariants;
+- output logical names are safe and deterministic;
+- output options do not bypass preparation-time compatibility checks; and
+- option decoding is strict, small, and consistent with configuration
+  validation.
+
+The graph flags generic integer option parsing and JSON output policy decoding
+as relatively complex. Examine whether that is inherent strict decoding or an
+opportunity for a smaller typed parser with equally precise diagnostics.
+
+### 8. D&D Domain Model, Codecs, And Shared Helpers
+
+Inspect `internal/modules/dnd` domain types, codecs, candidate decoders,
+identity packages, registries, shared source-reference helpers, diagnostics,
+registry resolution, entity reconciliation, mergers, registrar, and assets.
+
+Compare all ten current artifact families. Build a convention matrix covering:
+
+- module specs and execution classes;
+- constructor and option behavior;
+- manifest metadata and checkpoint fingerprints;
+- response-schema loading and private-versus-durable types;
+- source-reference conversion, canonicalization, ordering, and deduplication;
+- nil versus present-empty output;
+- codecs and strict JSON behavior;
+- registry lookup, identity derivation, immutable projections, and resolution;
+- normalizer retry/fallback behavior;
+- validators and default chains; and
+- registration, prompt assets, and documentation ownership.
+
+The graph reports many exact similarities among codec `Decode` methods,
+fingerprint/metadata methods, registry extractors, identity helpers, occurrence
+normalizers, and validators. Treat these as a prioritized review list, not an
+instruction to create one generic D&D engine. A worthwhile helper must preserve
+domain-specific identity, evidence, kind ordering, validation, diagnostics,
+and artifact typing.
+
+### 9. D&D Extraction And Normalization Flows
+
+Trace each lane end to end rather than auditing only similarly named files:
+
+- spells;
+- NPC registry and NPC occurrences;
+- combat turns and enemy events;
+- item registry and item occurrences;
+- scene descriptions; and
+- location registry and location occurrences.
+
+For registry/occurrence pairs, verify the complete semantic boundary: the model
+uses contextual evidence, deterministic code attaches opaque identity, registry
+evidence does not become occurrence evidence, and unresolved or ambiguous
+selections fail according to lane policy.
+
+Review whether any lane resolves or canonicalizes the same entity, source
+reference, or response twice; constructs unnecessary intermediate response
+forms; performs repeated sorts or scans; or retains transitional paths. Compare
+registry normalizers and occurrence normalizers for genuinely identical
+mechanics, while keeping currency, same-name location, NPC ambiguity, spell
+catalog, scene eligibility, and combat-specific policy with their owners.
+
+### 10. Test Suite And Comment Coverage
+
+Review the tests associated with every preceding area after understanding the
+production contracts. This should be a cross-cutting pass, not a request to add
+tests for every flagged function.
+
+Identify:
+
+- consequential unprotected invariants;
+- duplicated policy assertions across layers;
+- brittle tests coupled to internal constants, prompt prose, or private helper
+  shape;
+- oversized test harnesses and repeated fixtures that obscure intent;
+- race-sensitive code not exercised under `-race`;
+- parsers, canonicalizers, and path handlers where fuzzing would address a real
+  input-space risk; and
+- complex production code whose tests reveal an unclear ownership boundary.
+
+Also identify necessarily complex symbols that lack a concise invariant-level
+comment. Comment recommendations should name the exact symbol and the fact the
+comment should explain; “add more comments” is not an actionable finding.
+
+## Efficiency Evaluation
+
+The audit should consider both runtime and maintenance efficiency.
+
+For runtime efficiency, examine algorithmic behavior relative to realistic
+input dimensions: source units, chunks, lanes, references, artifacts, registry
+records, checkpoint files, and prompt assets. Prioritize repeated full-input
+passes, nested linear lookup, unnecessary JSON round trips, repeated hashing,
+large defensive copies at adjacent ownership boundaries, and serialization on
+concurrent hot paths. Preserve a defensive copy when it establishes ownership;
+removing it solely to reduce allocation is not an improvement.
+
+For maintenance efficiency, prioritize repeated policy, parallel type systems,
+duplicated error classification, scattered defaults, and migrations that left
+two ways to perform the same operation. Boilerplate is costly only when it can
+drift or obscures the semantic core. Small explicit typed adapters can be more
+maintainable than a generic abstraction.
+
+Do not recommend caching, pooling, concurrency, or a benchmark without naming
+the workload and risk it addresses. Add a benchmark only when a proposed
+optimization concerns a repeatable local path and the result would influence
+the decision.
+
+## Audit Method
+
+Each area should use the same method:
+
+1. Read its architecture/internal documentation and focused tests.
+2. Map public/package contracts and trace the main call paths.
+3. Inspect high-fan-in, high-cognitive-complexity, nested-loop, and repeated-
+   conversion symbols.
+4. Review exact and near-duplicate code side by side, including callers and
+   failure semantics.
+5. Check dependency direction, ownership, aliasing, deterministic order,
+   cancellation, and error classification.
+6. Compare tests with the risks owned at that layer.
+7. Record findings and inspected-with-no-finding areas before moving on.
+8. Run focused read-only validation when it can confirm or refute a suspected
+   problem.
+
+Prefer the repository knowledge graph for symbol discovery, call tracing, and
+similarity candidates. Use textual search for literals, diagnostics, config
+keys, asset content, and stale names. Read complete implementations and tests
+before reporting a metric-derived candidate.
+
+## Execution Sequence
+
+This document owns audit scope, questions, evidence standards, and the quality
+bar. [Staged Codebase Audit Sequence](audit-sequence.md) is the sole canonical
+owner of prompt order, stage boundaries, per-stage reading, validation commands,
+and acceptance criteria. Do not derive or maintain a second sequence here.
+
+The audit is executed as bounded prompts and writes its accumulated findings to
+`docs/roadmap/audit.md`. Later stages must build on and reconcile earlier
+evidence rather than concatenate independent reports. Implementation and
+roadmap retirement remain separate work after maintainers review the completed
+audit.
+
+## Baseline And Validation
+
+Before the first audit stage, record the commit under review and require a clean
+worktree. Refresh the code knowledge graph so renamed or deleted code does not
+produce false findings. Run the normal offline baseline:
+
+```sh
+go test ./...
+go vet ./...
+go build ./cmd/notarius
+git diff --check
+```
+
+Run `go test -race` for packages with concurrency or mutable shared state,
+especially `internal/framework/pipeline`, `internal/framework/llm`, state
+packages, and D&D registries. A repository-wide race run is appropriate for
+final verification if its cost remains reasonable.
+
+Optional diagnostic commands should be used only when relevant:
+
+- `go test -count=1` to rule out cache-masked failures;
+- `go test -shuffle=on` to detect order coupling;
+- focused fuzzing for existing or newly justified fuzz targets; and
+- focused benchmarks or profiles for a specific efficiency finding.
+
+The audit itself should not change tests to make the baseline pass. Record any
+pre-existing failure and distinguish it from an audit finding.
+
+## Deliverable Quality Bar
+
+The completed audit should:
+
+- cover every repository area listed above;
+- distinguish defects from refactoring opportunities and comment requests;
+- distinguish credible performance costs from aesthetic simplification;
+- identify intentional duplication that should remain explicit;
+- avoid recommendations that violate dependency direction or weaken typing;
+- cite exact evidence and preserve named invariants for every finding;
+- consolidate root causes rather than report many symptoms;
+- rank independent work so a later implementation plan can stage it safely;
+- recommend no code change whose expected benefit is smaller than its added
+  abstraction or test-maintenance cost; and
+- leave implementation and roadmap retirement to later work.
+
+## Open Questions
+
+None are required to begin the audit. If a later stage cannot determine whether
+behavior is intentional from code, tests, policies, ADRs, or current
+documentation, it should record the uncertainty and a recommended resolution
+rather than silently treating preference as a defect.

docs/roadmap/contextual-entity-grounding.md

@@ -0,0 +1,350 @@
+# Contextual Entity Grounding
+
+## Purpose
+
+Notarius should use an LLM for semantic interpretation of source evidence, not
+for referential-integrity work that deterministic code can perform more
+reliably. D&D prompts must therefore stop requiring models to reproduce opaque
+machine identifiers such as hash-derived entity IDs. Models should identify
+entities through human-readable, evidence-grounded context, after which
+Notarius resolves the selection and attaches the canonical durable identity.
+
+This roadmap defines the policy, affected D&D prompt families, and intended
+end state. The ordered work needed to reach that state is maintained in
+[Implementation Plan](implementation.md).
+
+## User Intent
+
+The change has two goals:
+
+- prevent otherwise useful model responses from failing because a long,
+  non-semantic string was copied incorrectly; and
+- avoid spending prompt space and model effort on exact-copy work that provides
+  no semantic value.
+
+The policy is not a ban on identifiers. Durable artifacts may continue to use
+application-owned IDs, and prompts may continue to request source-unit ranges
+that locate evidence. The policy governs which identity work is assigned to
+the model.
+
+## Policy
+
+An LLM-facing prompt input or private response schema must not require a model
+to reproduce an opaque machine identifier when Notarius can establish the same
+association deterministically.
+
+Opaque machine identifiers include cryptographic hashes, UUIDs, digests,
+database keys, durable entity IDs, and other tokens whose characters do not
+carry source-grounded meaning for the model. These values may remain in
+application state, provenance, diagnostics, checkpoints, and durable artifact
+contracts, but should be omitted from model-visible material when they do not
+help the model make a semantic decision.
+
+The intended responsibility boundary is:
+
+- the model decides which contextual entity is supported by the supplied
+  evidence and returns the bounded semantic facts requested by the module;
+- the calling module validates that the contextual selection resolves to
+  exactly one supplied candidate;
+- deterministic code supplies the canonical display value and durable entity
+  ID; and
+- existing validators continue to enforce referential integrity at later
+  artifact boundaries.
+
+Transcript `start_unit_id` and `end_unit_id` values are permitted. They are
+contextual source coordinates and form part of the evidence contract rather
+than arbitrary identity tokens. Prompt IDs, schema IDs, fingerprints, session
+IDs, and digests may also remain in runtime metadata that the model is not
+asked to reproduce.
+
+Short request-local labels are a narrowly permitted fallback only when a
+contextual selector cannot uniquely represent the available choices without
+unreasonable prompt cost. Such a label must be compact, scoped to one request,
+validated against the supplied candidate set, and never reused as a durable
+identity. Current D&D occurrence and reconciliation prompts should be designed
+without this exception; adopting it later requires a concrete demonstrated
+need and documented rationale.
+
+## Current State
+
+The initial NPC, item, and location registry extractors already follow the
+desired pattern: the model returns contextual names and evidence, and Notarius
+derives durable IDs afterward. Spells, combat turns, and enemy events use
+contextual actor names rather than requiring hash-derived NPC IDs.
+
+Two current prompt families diverge from that pattern:
+
+1. `dnd/npc-occurrences`, `dnd/item-occurrences`, and
+   `dnd/location-occurrences` place durable registry IDs in model-visible
+   projections and require the private LLM response to repeat those IDs.
+2. NPC-, item-, and location-registry normalization use the shared entity
+   reconciliation prompt, which labels candidates with opaque
+   `candidate-000001`-style keys and requires the model to copy those keys into
+   duplicate-group proposals.
+
+The durable occurrence artifacts correctly retain canonical entity IDs. The
+problem is the private model transport contract, not the published artifact
+contract.
+
+## Target Architecture
+
+### Model proposals and durable artifacts
+
+Private LLM response types must express contextual semantic proposals rather
+than reuse the durable artifact type when that type contains an opaque entity
+ID. The extractor maps a validated private response into the existing durable
+artifact only after identity resolution succeeds.
+
+No affected durable artifact kind, media type, schema ID, schema version, or
+JSON field changes as part of this work. NPC, item, and location occurrence
+artifacts continue to publish their exact canonical ID/name pair. Registry
+artifacts likewise retain their IDs and evidence.
+
+The private schemas and prompt declarations may remain at their current `v1`
+identities because Notarius is pre-release and these are not external
+contracts. Their content hashes, mapping-policy fingerprints, and affected
+prompt fingerprints must change so incompatible checkpoints are not reused.
+
+### NPC occurrence grounding
+
+The NPC occurrence prompt receives an ordered names-only projection of the
+normalized NPC registry. Its private response contains the canonical NPC name,
+occurrence kind, and current-transcript source ranges, but no `npc_id`.
+
+The extractor resolves the returned name under the existing NPC comparison
+policy. Resolution must produce exactly one registry entry. It then writes that
+entry's canonical display name and durable ID into the `dnd.NPCOccurrence`.
+An unknown or ambiguous selection invalidates the extraction operation; the
+extractor must not guess, use fuzzy matching, silently omit the record, or
+accept a partial response.
+
+### Item occurrence grounding
+
+The item occurrence prompt receives an ordered names-only projection of the
+normalized item registry. Its private response contains the canonical item
+name, occurrence kind, kind-specific fields, and current-transcript source
+ranges, but no `item_id`.
+
+The extractor resolves the returned name under the existing item comparison
+and identity policies. Resolution must produce exactly one registry entry,
+whose canonical name and durable ID are attached deterministically. Unknown or
+ambiguous selections invalidate the complete extraction operation rather than
+being guessed, repaired by similarity, or dropped.
+
+### Location occurrence grounding
+
+Location identity cannot always be resolved from a display name alone: the
+current registry intentionally permits same-name locations with distinct
+source anchors. The location occurrence prompt must therefore receive a
+contextual registry descriptor that contains the canonical display name plus
+the minimum source-grounded registry evidence needed to distinguish same-name
+records. It must not contain the durable `location:sha256:...` value.
+
+The private response uses two required selector fields: `name` and
+`registry_refs`. For a comparison-unique canonical name, `registry_refs` is an
+empty array and Notarius resolves the name under the location comparison
+policy. For a name shared by multiple registry records, `registry_refs`
+contains that record's complete canonically ordered registry ranges as
+`start_unit_id` and `end_unit_id` pairs, without `source_id`.
+
+Every model-facing registry entry uses one fixed shape with required `name`,
+`registry_refs`, and `context` fields. `context` is an array of strict objects
+containing only `unit_id` and `text`. Comparison-unique entries use empty
+`registry_refs` and `context` arrays. Same-name entries use the complete
+registry-range selector and the bounded context described below. The model
+returns only `name` and `registry_refs`; it does not reproduce `context`.
+
+For same-name groups, the projection also supplies bounded transcript units
+covered by each record's registry ranges so the model receives meaningful
+identity context rather than coordinates alone. Those ranges must resolve
+against the current source document, and the resulting contextual selectors
+must be unique. An invalid range or selector collision prevents the LLM call
+and fails the operation. Unique-name entries do not repeat registry ranges or
+context in the selector, preserving compatibility with a valid registry from
+another source when the name alone is unambiguous.
+
+The private response separately supplies current-transcript `source_refs` that
+prove the occurrence. Registry identity evidence and occurrence evidence must
+remain different fields and must never be merged. The model should omit an
+occurrence when the transcript does not support choosing among same-name
+locations. If a returned selector does not resolve to exactly one supplied
+registry record, the extractor invalidates the complete operation rather than
+guessing.
+
+### Registry reconciliation
+
+The shared entity-reconciliation input replaces opaque candidate keys with
+contextual candidate descriptors. At minimum, a descriptor contains the
+candidate's display name and its canonically ordered source-reference ranges;
+the existing transcript windows remain available for semantic judgment.
+
+Duplicate-group members and the canonical member in the private response use
+the same contextual descriptor shape. The shared reconciliation helper maps
+each descriptor back to exactly one internal candidate before assessing the
+proposal. Exact deterministic duplicates should already be removed before the
+LLM call; any remaining descriptor collision makes the affected candidate
+ineligible for model-assisted reconciliation rather than authorizing an
+arbitrary choice.
+
+Existing safety behavior remains in force: groups must contain at least two
+supplied candidates, the canonical candidate must be a member, groups must not
+overlap, and domain-specific eligibility rules remain authoritative. Invalid,
+ambiguous, or unsafe groups are discarded through the existing bounded
+fallback and diagnostic behavior. The model never directly mutates the
+durable registry.
+
+The shared private reconciliation schema and helper must remain domain-neutral
+within the D&D family. NPC-, item-, and location-specific duplicate policy
+continues to live in the owning normalizer.
+
+## Prompt And Asset Changes
+
+The following LLM-facing assets are in scope:
+
+- the prompt instructions, registry input fragments, and private response
+  schemas for NPC, item, and location occurrences;
+- the prompt manifests where input shape or selected fragments change;
+- the shared D&D entity-reconciliation fragment and private response schema;
+  and
+- the NPC-, item-, and location-registry normalization prompt inputs that use
+  the shared reconciliation contract.
+
+Affected projections must exclude durable entity IDs rather than merely stop
+mentioning them in prose. Prompt instructions should describe the contextual
+selection rule once at the narrowest owning asset and must preserve the current
+distinction between registry grounding and transcript evidence.
+
+Prompt ordering and cache controls should remain unchanged unless the new
+contextual input requires an intentional manifest change. Unrelated shared
+prompt bytes should not be edited. Prompt and schema fingerprints should
+invalidate only the operations whose selected assets or mapping semantics
+changed.
+
+## Code And Validation Changes
+
+The occurrence extractors need private response types and deterministic
+registry-resolution paths appropriate to their domain. Shared code is
+appropriate only for demonstrated mechanics that have identical semantics;
+NPC, item, and location ambiguity policies must not be forced behind a generic
+resolver merely to reduce line count.
+
+Registry projections should expose explicit model-facing methods whose names
+describe whether they are names-only or contextual identity projections. The
+existing ID/name projections may remain only for deterministic consumers that
+genuinely require them; they must no longer be wired to an LLM input.
+
+Mapping-policy and normalization-policy identifiers must be reviewed and
+advanced wherever their semantics change. Checkpoint fingerprints must cover
+the new projection content, private schema, prompt assets, and mapping policy,
+while continuing to exclude irrelevant internal implementation details.
+
+Durable occurrence normalizers and registry validators remain defense in
+depth. They continue to validate exact ID/name pairs on artifacts entering
+through checkpoints, codecs, or other boundaries even though the LLM no longer
+produces the ID directly.
+
+## Testing And Evaluation
+
+Tests should protect the behavioral boundary rather than prompt prose or
+private helper structure. The completed work should demonstrate that:
+
+- affected model-facing registry projections do not contain durable entity
+  IDs;
+- private occurrence schemas reject opaque ID fields and accept the intended
+  contextual shape;
+- valid contextual selections map to the exact canonical durable ID/name pair;
+- unknown, mismatched, and ambiguous selections fail without fuzzy matching,
+  partial acceptance, or arbitrary reassignment;
+- same-name locations remain distinguishable through contextual evidence;
+- reconciliation preserves equal-name candidates, resolves valid contextual
+  groups, and discards ambiguous or unsafe proposals;
+- registry evidence never becomes occurrence evidence;
+- durable codec, normalization, and validator behavior remains compatible; and
+- representative assembled D&D pipelines still prepare and execute with fake
+  structured-LLM responses.
+
+Do not add repository-wide prompt-prose snapshots, exact-message-count tests,
+or a change-detector test that merely scans for today's field names. Focused
+projection, schema, mapping, fallback, and integration tests are the stable
+owners of these risks. Model-quality evaluation with representative
+transcripts remains a manual development aid rather than an offline test gate.
+
+## Documentation And Architectural Record
+
+This policy is durable and applies to future modules, so it warrants
+`docs/adr/0012-resolve-opaque-entity-identifiers-deterministically.md`, which
+records:
+
+- the semantic-proposal versus referential-integrity boundary;
+- why durable opaque IDs are excluded from model response contracts;
+- why contextual evidence coordinates remain permitted;
+- the narrowly scoped request-local-label exception;
+- alternatives including durable IDs, names-only matching, and short opaque
+  handles; and
+- the consequences for private schemas, deterministic resolution, debugging,
+  and ambiguous identities.
+
+`docs/policy/architecture.md` states the general LLM boundary invariant and
+links to the ADR. `docs/internal/dnd.md` describes the concrete occurrence
+projections, contextual reconciliation selectors, resolution and failure
+behavior, and the continued separation of registry grounding from occurrence
+evidence. `docs/internal/llm.md` contains only a short clarification that
+caller-owned modules, not PromptKit or the transport adapter, resolve
+contextual model selections into application identities.
+
+The NPC, item, and location occurrence and registry integration documents must
+continue to own their durable wire contracts, while removing current claims
+that the model-facing consumer projection contains `{id,name}` or that the raw
+LLM response supplies the durable ID. They should instead explain that
+Notarius resolves contextual model output and publishes the same exact durable
+ID/name pair. No public schema examples need to remove those IDs.
+
+The generic LLM-assisted deduplication entry in `docs/roadmap/future.md` must be
+reconciled with this policy: stable IDs may exist inside deterministic state,
+but a future model-facing proposal should use contextual selectors or a
+documented request-local-label exception rather than durable IDs.
+
+## Compatibility And Operational Effects
+
+This work intentionally changes private prompt inputs, private structured
+responses, and mapping semantics. It will invalidate affected checkpoints
+through existing prompt, schema, projection, and policy fingerprints. No
+manual checkpoint migration is required.
+
+Durable D&D artifacts and generated-reference compatibility remain unchanged.
+Operators do not receive new configuration fields or CLI controls. The feature
+does not change PromptKit, provider routing, profile selection, retries,
+concurrency, or public output placement.
+
+## Non-Goals
+
+This work does not:
+
+- remove canonical IDs from durable registries or occurrence artifacts;
+- change occurrence categories, evidence rules, or registry identity policy;
+- add fuzzy, probabilistic, or embedding-based entity resolution;
+- allow registry provenance to substitute for occurrence evidence;
+- introduce a general entity graph or cross-artifact identity framework;
+- redesign unrelated D&D prompts or their schemas;
+- implement the future generic deduplication normalizer; or
+- add provider-specific prompt behavior.
+
+## Acceptance Criteria
+
+The target state is complete when:
+
+- no maintained D&D prompt requires a model to reproduce a durable opaque
+  entity ID;
+- current D&D reconciliation prompts no longer require opaque candidate keys;
+- NPC, item, and location occurrence LLM outputs are resolved
+  deterministically into their unchanged durable artifacts;
+- same-name location and reconciliation cases remain safe and unambiguous;
+- invalid contextual selections preserve the existing extraction-failure or
+  normalization-fallback semantics appropriate to their stage;
+- affected checkpoint identities change without altering public schema
+  versions;
+- focused and repository-wide tests pass offline;
+- the ADR, architecture invariant, D&D internal guide, LLM internal guide,
+  relevant integration contracts, and future roadmap accurately describe
+  their canonical portions of the implemented policy; and
+- no unrelated code, prompt behavior, or public contract changes are included.

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
@@ -53,71 +22,6 @@ 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
@@ -125,13 +29,15 @@ not as committed release dates.
 - 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
+  whose elements retain stable unique IDs as internal deterministic state.
-  adapters may expose that structure without moving domain rules into the
+  Model proposals use contextual descriptors, or a specifically justified
-  generic package.
+  request-local short label, rather than durable 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,
+  resolve every supplied descriptor or local label exactly, reject overlapping
-  prevent unrelated insertion or deletion, and apply only approved replacement
+  or malformed groups, prevent unrelated insertion or deletion, and apply only
-  operations in code.
+  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

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
+            - item-occurrences
-            - npcs
+            - 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
+            normalize: dnd/item-registry
-          npcs:
+          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
+        # Accepted registry artifacts and scene-description eligibility artifacts
-        # supplied in memory to their compatible consumers in this step.
+        # 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
+}