Document published evidence context

.codebase-memory/.gitattributes

@@ -0,0 +1,3 @@
+# Auto-generated by codebase-memory-mcp
+# Prevent merge conflicts on compressed artifact
+graph.db.zst merge=ours binary

.codebase-memory/artifact.json

@@ -0,0 +1,11 @@
+{
+    "schema_version": 2,
+    "commit": "9e4b989e53d65efa614b5eedd8530caed12f60b5",
+    "indexed_at": "2026-07-27T18:27:55Z",
+    "project": "home-eric-Workspace-notarius",
+    "nodes": 6356,
+    "edges": 35132,
+    "original_size": 26017792,
+    "compressed_size": 4386397,
+    "compression_level": 3
+}

.gitignore

@@ -2,7 +2,6 @@
 notarius
 notarius-output
 workspace/
-.codebase-memory/
 
 # ---> Go
 # If you prefer the allow list template instead of the deny list, see community template:
@@ -74,3 +73,4 @@ Icon
 Network Trash Folder
 Temporary Items
 .apdisk
+

.woodpecker/release.yml

@@ -1,9 +0,0 @@
-# Advisory validation after source publication, never a release-completion gate.
-when:
-  - event: tag
-
-steps:
-  - name: validate-release
-    image: golang:1.25.5
-    commands:
-      - ./scripts/check-release-source.sh "$CI_COMMIT_TAG"

AGENTS.md

@@ -1,5 +1,2 @@
 Please review `docs/development.md` for initial orientation in this repository
 and follow its task-specific reading guide.
-
-Review and follow `docs/policy/agents.md` before recommending, planning, or
-implementing any changes to this repository.

README.md

@@ -2,9 +2,8 @@
 
 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 NPC, location, and item registries; their
+transcript JSON and can produce scene descriptions, item and currency events,
-source-grounded occurrences; scene descriptions, combat turns, enemy events,
+NPC identities, combat turns, NPC interactions, and spell casts.
-and spell casts.
 
 ## Quickstart
 
@@ -28,20 +27,6 @@ For the complete ordered D&D workflow, use
 [its synthetic transcript](examples/dnd-complete-transcript.json). It
 demonstrates all implemented D&D lanes and the supporting campaign references.
 
-## Install A Source Release
-
-Install a pinned source release with Go:
-
-~~~
-GOWORK=off go install \
-  gitea.maximumdirect.net/eric/notarius/cmd/notarius@<tag>
-~~~
-
-Replace `<tag>` with a stable release tag such as `vMAJOR.MINOR.PATCH`. The
-installed command's diagnostic version is described in the [CLI
-reference](docs/cli.md); maintainers preparing a release should follow [Source
-Releases](docs/release.md).
-
 ## Documentation
 
 - [CLI reference](docs/cli.md) — commands, flags, output streams, and exits.
@@ -53,8 +38,6 @@ Releases](docs/release.md).
   artifact formats.
 - [Subprocess consumer guide](docs/consumers/subprocess.md) — invoke Notarius
   from an orchestrator and consume a published result.
-- [Complete D&D consumer guide](docs/consumers/dnd-pipeline.md) — run the full
-  D&D pipeline as a subprocess and discover its structured artifacts.
 - [Internal overview](docs/internal/overview.md) — implemented component map
   for maintainers.
 - [Developer guide](docs/development.md) — contributor orientation and

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

@@ -1,18 +0,0 @@
-Extract Dungeons & Dragons combat-turn artifacts from the supplied transcript.
-Include a record only when the transcript establishes that an in-world
-participant takes a combat turn or performs a discrete interrupting combat
-event. 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/enemy-events/prompts/combat-grounding.md

@@ -1,12 +0,0 @@
-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

@@ -1,25 +0,0 @@
-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

@@ -1,53 +0,0 @@
-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: 1

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

@@ -1,38 +0,0 @@
-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. Use JSON `null`, not an empty
-string, whenever a holder does not apply. Follow this holder matrix exactly:
-
-| `kind` | required `from` | required `to` |
-| --- | --- | --- |
-| `discovered` | `null` | `null` |
-| `acquired` | `null` | `party` or the named party member gaining possession |
-| `lost` | `party` or the named party member losing possession | `null` |
-| `consumed` | `party` or the named party member consuming the item | `null` |
-| `transferred` | one named party member | a different named party member |
-
-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

@@ -1,6 +0,0 @@
-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

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

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

@@ -1,39 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$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",
-            "enum": ["discovered", "acquired", "lost", "consumed", "transferred"]
-          },
-          "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

@@ -1,12 +0,0 @@
-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

@@ -1,40 +0,0 @@
-id: dnd.item_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_item_registry_llm.v1.json
-  repair_attempts: 1

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

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

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

@@ -1,9 +0,0 @@
-Determine whether candidates identify the same item type or unique designation
-using their contextual labels and cited transcript windows. Do not treat nearby
-evidence, similar objects, or a shared owner as sufficient.
-
-Keep currency denominations and materially different item types separate. Keep
-uncertain aliases separate. Do not infer an item property or uniqueness.
-
-Set `canonical_candidate_number` to the supplied candidate number whose label
-is the clearest established designation.

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

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

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

@@ -1,34 +0,0 @@
-Extract Dungeons & Dragons location occurrences from the supplied transcript.
-Include an occurrence only when the transcript establishes one supplied
-location, one occurrence kind, and a coherent passage supporting both.
-
-Use 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

@@ -1,11 +0,0 @@
-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/schemas/dnd_location_occurrences_llm.v1.json

@@ -1,45 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$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

@@ -1,13 +0,0 @@
-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/schemas/dnd_location_registry_llm.v1.json

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

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

@@ -1,9 +0,0 @@
-Determine whether candidates identify the same physical place using their
-contextual labels and cited transcript windows. Do not treat matching names,
-nearby evidence, nested places, or generic labels as sufficient.
-
-Keep parent and child places separate, as well as similarly named places and
-uncertain aliases.
-
-Set `canonical_candidate_number` to the supplied candidate number whose label
-is the clearest established name.

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

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

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

@@ -1,45 +0,0 @@
-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: 1

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

@@ -1,19 +0,0 @@
-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/normalize/prompts/instructions.md

@@ -1,12 +0,0 @@
-Determine whether candidates refer to the same individual using their
-contextual labels and cited transcript windows. Preserve distinct individuals
-even when their names are similar or their contextual descriptions are
-identical.
-
-Set `canonical_candidate_number` to the supplied candidate number whose label
-is the preferred 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/profiles/dnd-extraction.yaml

@@ -1,5 +0,0 @@
-id: dnd-extraction
-backend: openrouter
-model: openai/gpt-5.6-luna
-timeout_seconds: 240
-service_tier: flex

assets/dnd/scene-descriptions/validate/combat-semantics/prompts/instructions.md

@@ -1,8 +0,0 @@
-Classify only whether substantive active combat occurs in the supplied
-transcript chunk under the shared combat policy. Do not judge the scene title,
-summary, non-combat subtype, scene boundary, or any other aspect of a scene
-description.
-
-Return `combat` when the chunk contains substantive active combat and
-`non_combat` otherwise. Give a concise, transcript-grounded explanation for
-the classification.

assets/dnd/scene-descriptions/validate/combat-semantics/prompts/prompt.yaml

@@ -1,23 +0,0 @@
-id: dnd.scene_descriptions.validate_combat
-version: "v1"
-default_profile: dnd-extraction
-inputs:
-  - name: transcript
-    required: true
-    content_type: application/json
-messages:
-  - role: system
-    content_file: ./sharedassets/common-dnd-system.md
-  - role: user
-    content_file: ./sharedassets/common-dnd-scene-combat-policy.md
-  - role: user
-    content_file: ./instructions.md
-  - role: user
-    content_file: ./sharedassets/common-dnd-transcript-chunk.md
-    cache_control:
-      type: ephemeral
-output:
-  format: json
-  validation_mode: json_schema
-  schema_path: dnd_scene_combat_semantics_llm.v1.json
-  repair_attempts: 1

assets/dnd/scene-descriptions/validate/combat-semantics/schemas/dnd_scene_combat_semantics_llm.v1.json

@@ -1,18 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "notarius.dnd.scene_descriptions.combat_semantics.llm",
-  "type": "object",
-  "additionalProperties": false,
-  "required": ["classification", "explanation"],
-  "properties": {
-    "classification": {
-      "type": "string",
-      "enum": ["combat", "non_combat"]
-    },
-    "explanation": {
-      "type": "string",
-      "minLength": 1,
-      "maxLength": 512
-    }
-  }
-}

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

@@ -1,8 +0,0 @@
-Transcript units are the only evidence for extracted events and factual claims.
-Every reported factual claim must be supported by cited transcript units. Use
-integer `start_unit_id` and `end_unit_id` values from the transcript.
-Within each range, `start_unit_id` must identify the earlier transcript unit and
-`end_unit_id` the same or a later unit according to transcript order.
-
-When supporting evidence is non-contiguous, use multiple narrow ranges rather
-than a broad range that bridges unrelated conversation.

assets/dnd/shared/prompts/common-dnd-scene-combat-policy.md

@@ -1,13 +0,0 @@
-Use `combat` only when substantive active combat materially organizes the
-scene. Active combat includes initiative or turn exchanges, attacks, combat
-spells, damage, saves, movement, or similarly sustained hostile action.
-
-Do not use `combat` for planning or preparing for a possible fight; threats,
-hostile dialogue, or a tense confrontation; immediate aftermath, looting,
-healing, or discussion of a completed fight; a recap or in-world recollection
-of earlier combat; or out-of-character rules discussion without active
-encounter play.
-
-When a chunk contains substantive active combat alongside brief setup, rules
-clarification, interruption, phase transition, or immediate aftermath, classify
-it as `combat`.

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

@@ -1,5 +0,0 @@
-You process Dungeons & Dragons gameplay transcripts.
-
-As input, you will receive one or more portions of a transcript. The transcript may contain transcription errors, repeated lines, incomplete sentences, and misheard proper nouns.
-
-Return exactly one JSON object that conforms to the configured response schema, with no explanatory prose.

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

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

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

assets/dnd/spells/prompts/instructions.md

@@ -1,14 +0,0 @@
-Extract Dungeons & Dragons spell-cast artifacts from the provided transcript.
-Include an actual casting event or an unambiguous declared casting attempt.
-Exclude spell mentions, hypothetical plans, rules discussion, and catalog
-matches that do not establish a casting event in the transcript.
-
-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/spell-catalog.md

@@ -1,6 +0,0 @@
-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/generic/normalize/deduplication/prompts/candidates.md

@@ -1,3 +0,0 @@
-Candidate material, including the exact valid candidate-number range:
-
-{{ input "candidates" }}

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

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

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

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

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

@@ -1,9 +0,0 @@
-Use only the positive integer `candidate_number` values supplied in the candidate material. Valid candidate numbers are exactly the inclusive `first` through `last` values declared in `candidate_number_range`; use the explicit number attached to each candidate.
-
-Transcript unit `id` values and evidence `start_unit_id` and `end_unit_id` values identify source positions. They are not candidate numbers and must never be used in `candidate_numbers` or `canonical_candidate_number`.
-
-Return a duplicate group only when the evidence supports that every selected candidate describes the same underlying entity. Each group must contain at least two distinct candidate numbers, and its `canonical_candidate_number` must be one of those numbers. A candidate may appear in at most one group.
-
-Omit uncertain matches and candidates that should remain distinct. Do not invent candidates or infer a number that is not explicitly supplied. An empty `duplicate_groups` array is valid.
-
-The response must conform exactly to the selected JSON schema. Return candidate numbers only: do not copy candidate names, evidence, transcript text, source identifiers, or source ranges into the response.

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

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

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

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

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

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

assets/package.go

@@ -1,15 +0,0 @@
-// 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 — its asset-co-location rule is superseded by [ADR-0011](0011-centralize-llm-assets.md); its domain-first module packaging decision remains accepted.
+**Status:** Accepted
 **Date:** 2026-07-13
 
 ## Context

docs/adr/0010-workload-oriented-llm-profile-defaults.md

@@ -1,49 +0,0 @@
-# ADR-0010: Use workload-oriented LLM profile defaults
-
-**Status:** Accepted
-**Date:** 2026-08-03
-
-## Context
-
-LLM-backed D&D operations share an execution-policy choice, but repeating a
-provider or model-named profile on every module binding ties pipeline structure
-to a deployment decision. Different environments may require different model,
-backend, timeout, or reasoning settings while retaining the same workload.
-
-Notarius also needs a usable default for maintained D&D prompts without making
-an operator profile mandatory. That default must remain owned by the D&D
-family, while generic LLM infrastructure stays unaware of domain-specific
-policy.
-
-## Decision
-
-Pipelines may name one workload-oriented default profile, inherited only by
-selected LLM-backed bindings and validators. Binding-level profile IDs remain
-intentional exceptions, and the run-wide CLI profile override has highest
-precedence.
-
-The D&D family owns an embedded fallback profile named `dnd-extraction`.
-Operators may provide a complete profile with the same ID through a PromptKit
-filesystem source. PromptKit selects the higher-precedence matching definition;
-Notarius does not merge profile documents. Production, development, and local
-deployments can therefore use different execution policy behind one unchanged
-pipeline ID.
-
-## Alternatives considered
-
-- Repeat a model-named profile on every binding. This makes routine deployment
-  policy changes noisy and obscures the shared workload intent.
-- Require every deployment to install a profile file. This adds configuration
-  friction and leaves maintained D&D prompts without an application-owned
-  fallback.
-- Put D&D profile policy in generic LLM infrastructure. This breaks domain
-  ownership and makes generic code depend on one workload.
-
-## Consequences
-
-Pipeline configuration expresses workload intent rather than a specific
-provider or model. Operators can replace the complete execution policy without
-editing bindings, while binding-level and run-wide exceptions remain available.
-Profile changes affect resolved pipeline and checkpoint identity, so they may
-intentionally cause work to be recomputed. The D&D fallback becomes a
-maintained application execution-policy asset.

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

@@ -1,69 +0,0 @@
-# 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

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

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

@@ -1,89 +0,0 @@
-# ADR-0013: Use request-local candidate handles for semantic reconciliation
-
-**Status:** Accepted
-**Date:** 2026-08-09
-
-## Context
-
-Several typed normalize stage modules need semantic reconciliation after
-deterministic preprocessing: a model can judge whether source-backed candidates
-refer to the same underlying entity, while application code remains responsible
-for constructing the normalized artifact. Requiring the model to reproduce a
-candidate's full contextual selector makes the response larger and introduces
-avoidable formatting, ordering, and transcription failure modes.
-
-Reconciliation must preserve the exact typed artifact boundary established by
-[ADR-0003](0003-typed-interfaces-with-two-zone-data-model.md), the domain-neutral
-framework and concrete-domain dependency direction established by
-[ADR-0004](0004-package-modules-by-domain.md), and the distinction in
-[ADR-0009](0009-minimal-evidence-grounded-extraction-artifacts.md) between source
-evidence and auxiliary identity context. It also needs a concrete, narrowly
-scoped application of the request-local-label exception allowed by
-[ADR-0012](0012-resolve-opaque-entity-identifiers-deterministically.md).
-
-## Decision
-
-Semantic reconciliation will be a domain-neutral framework mechanism used by
-typed normalize stage modules. A consuming artifact family will retain
-ownership of its typed records, identity rules, consolidation policy, durable
-IDs, and domain warnings; the framework mechanism will not infer those rules
-from arbitrary data.
-
-For each reconciliation request, deterministic code will assign every eligible
-model-visible candidate a contiguous, one-based integer handle. The model may
-receive the candidate's contextual label, source references, and bounded source
-context needed to judge identity, but its structured response will identify
-candidates only by those supplied handles. A handle is local to one request,
-does not represent entity identity, and must never enter a durable artifact or
-be used to derive a durable ID.
-
-The model will propose duplicate groups and select one supplied member of each
-group as canonical. Deterministic code will resolve the handles through the
-retained request mapping, validate the complete proposal, discard unsafe
-groups, and apply only validated groups through typed domain-owned policy. The
-model will not synthesize replacement records or directly mutate an artifact.
-
-Every reconciliation prompt will combine a mandatory framework-owned protocol
-and safety policy with an explicitly selected semantic policy. The semantic
-policy may be the conservative generic policy or a domain-owned policy, but it
-cannot replace the shared response protocol or deterministic safety boundary.
-
-## Alternatives considered
-
-- Return durable application IDs. Opaque IDs do not help semantic judgment,
-  expose application identity mechanics, and make model output reproduce data
-  that deterministic code already owns.
-- Return names alone or copied contextual selectors. Names can be ambiguous,
-  while reproducing labels and source ranges adds response complexity and
-  creates mismatches without adding semantic information. Request-local
-  handles preserve exact selection without either failure mode.
-- Ask the model to return synthesized canonical replacement records. This
-  would transfer typed artifact construction, provenance consolidation, and
-  durable identity policy to a probabilistic boundary.
-- Reconcile reflection-discovered fields or arbitrary JSON. This would weaken
-  the typed artifact contract and move domain semantics into generic code.
-- Hide reconciliation inside extraction or another stage. This would obscure
-  stage ownership and create cross-stage behavior outside the fixed pipeline;
-  reconciliation remains explicit normalize-stage behavior.
-- Let each domain replace the complete prompt protocol. This would duplicate
-  safety mechanics and allow domain policy to bypass the common response and
-  validation contract.
-
-## Consequences
-
-Model responses become smaller and easier to validate, while deterministic
-application code retains authority over identity, provenance, ordering, and
-typed artifact construction. The framework requires a request-local mapping,
-bounded context preparation, a private integer response contract, proposal
-assessment, and shared prompt assets. Each consuming artifact family still
-requires a typed adapter for its irreducibly domain-specific rules.
-
-Request-local handles are deliberately unsuitable for persistence, logging as
-entity identity, checkpoint contracts, or cross-request correlation. Changes
-to shared protocol and policy assets must participate in the normal prompt,
-schema, and checkpoint fingerprint mechanisms.
-
-The shared mechanism and its initial D&D registry consumers are now
-implemented. Current behavior is documented in
-[Module Internals](../internal/modules.md#semantic-reconciliation) and
-[D&D Module Internals](../internal/dnd.md#semantic-registry-reconciliation).

docs/adr/0014-feedback-aware-validation-retries.md

@@ -1,59 +0,0 @@
-# ADR-0014: Use feedback-aware validation retries
-
-**Status:** Accepted
-**Date:** 2026-08-26
-
-## Context
-
-Validation can identify a candidate defect after a producer has returned an
-otherwise well-formed result. Retrying without the validator's deterministic,
-bounded feedback wastes the useful diagnosis, while treating validator
-execution failures as defects would ask a producer to repair conditions it
-cannot control. The mechanism must preserve typed producer ownership,
-checkpoint safety, and the repository's sensitive-data boundaries.
-
-## Decision
-
-The implementation will keep three independent budgets: the producer binding's
-outer `retries` budget, PromptKit's structured-output repair budget, and each
-validator's execution-retry budget. Validators will run sequentially in their
-configured order and aggregate both rejections and execution failures before a
-candidate disposition is selected.
-
-A correction-capable producer will provide the exact single LLM response that
-controlled its candidate using the `single_response_v1` protocol. A correction
-attempt will reconstruct the ordinary request and append exactly two fresh
-messages: that latest response as `assistant`, followed by one deterministic
-aggregate correction request as `user`. Earlier turns will not accumulate.
-
-Validator failures will not recurse into correction. Pipeline policy owns
-terminal disposition, with field-by-field producer overrides over pipeline
-defaults: structural failure and semantic rejection default to `fail_run`, and
-validator execution failure defaults to `warn_continue`. Validators can report
-facts and bounded corrective guidance, but never decide disposition.
-
-Rejected and structurally invalid candidates will not advance. A candidate
-allowed through after a validator execution failure will retain explicit
-incomplete-validation provenance and will not be checkpointed. Exact response
-and correction text remain attempt-local: they are excluded from ordinary
-errors, warnings, manifests, receipts, caches, checkpoints, and default debug
-summaries.
-
-## Alternatives considered
-
-- Retry every producer after any validation outcome. This conflates producer
-  defects with validator operational failures and wastes retry budget.
-- Let validators decide whether to continue. This would distribute pipeline
-  disposition policy across validators and undermine consistent defaults.
-- Reuse the full prior conversation. Accumulated turns introduce unbounded
-  prompt growth and make correction behavior depend on incidental history.
-- Persist raw responses to simplify diagnosis. Raw model output and correction
-  guidance may be sensitive and do not belong in durable pipeline records.
-
-## Consequences
-
-The framework gains transport-neutral correction and candidate contracts,
-producer capability checks, policy resolution, aggregated validation outcomes,
-and conservative checkpoint handling. Prompt construction remains inside the
-LLM adapter, while modules remain responsible for accurately exposing the
-single response that directly controlled a candidate.

docs/adr/0015-separate-process-warnings-from-quality-diagnostics.md

@@ -1,67 +0,0 @@
-# ADR-0015: Separate process warnings from quality diagnostics
-
-**Status:** Accepted
-**Date:** 2026-08-27
-
-## Context
-
-Notarius currently represents process degradation, incomplete validation,
-extraction-quality doubt, and routine normalization with one flat warning
-record. That makes ordinary successful runs noisy, loses the framework context
-needed to explain a finding, and gives `warning_count` no stable operational
-meaning. It also permits output encoders to add a warning after the durable
-warning file has already been written.
-
-The application needs one bounded diagnostic model that preserves exact
-occurrence counts while retaining only safe, representative samples. Fresh and
-resumed logical runs must present the same groups. The model must not alter
-validation decisions, retry budgets, rejected-output behavior, or process exit
-policy.
-
-## Decision
-
-Warnings are reserved for a completed run that advanced under an allowed
-process-level degradation or incomplete-work policy. Extraction-quality signals
-are advisories, and routine accepted transformations are observations. A
-non-degraded successful run therefore has zero actionable warnings.
-
-Modules and validators own a diagnostic's disposition, category, reason code,
-scope, and safe message. The framework adds pipeline origin, including stage,
-step, lane, module, validator, and chunk context where applicable. It then
-aggregates deterministically by disposition, category, reason code, and full
-origin. Chunk context remains on representative samples so equivalent findings
-across chunks aggregate together.
-
-Diagnostics carry exact occurrence counts, at most three distinct samples, and
-numeric omitted-sample metadata. Producers and validators are bounded to 64
-local groups. Final actionable warning groups are bounded without truncation;
-the non-warning collection may truncate represented groups while preserving an
-exact total occurrence count and explicit truncation metadata.
-
-The public contracts will be versioned: grouped actionable warnings use
-`notarius.warnings.v2`, grouped advisories and observations use
-`notarius.diagnostics.v1`, and the run receipt uses
-`notarius.run-result.v2`. Successful output encoders return logical files or
-an error; they do not add post-encoding warnings.
-
-## Alternatives considered
-
-- Keep one warning list and filter only CLI output. This would leave durable
-  consumers with the same semantically mixed, unbounded contract.
-- Map reason codes to severity in a central framework registry. This would
-  split module-owned meaning between synchronized policy tables and make new
-  diagnostic meaning implicit.
-- Preserve local omission warning records. They inflate visible group counts
-  and lose exact occurrence semantics.
-- Keep output-encoder warnings. A one-pass encoder cannot include those
-  records consistently in files it has already serialized; a two-phase encoder
-  protocol is deferred until a demonstrated need exists.
-
-## Consequences
-
-The framework gains validated diagnostic primitives, local collection,
-origin-aware aggregation, and versioned durable presentation. Existing warning
-transport remains temporarily while producers migrate. Current architecture,
-operator, integration, and internal documentation will describe the behavior
-only as each implementation step lands; this accepted decision does not claim
-that the migration is complete.

docs/adr/0016-feedback-aware-module-requested-retries.md

@@ -1,76 +0,0 @@
-# ADR-0016: Use feedback-aware module-requested retries
-
-**Status:** Accepted
-**Date:** 2026-08-28
-
-## Context
-
-An LLM-backed module can discover that a structurally valid model response is
-unsafe while translating it into a typed candidate, before the ordinary
-validator chain runs. Semantic registry reconciliation is the first such case:
-the shared core can identify invalid duplicate-group proposals, and typed
-application can reject a domain-incompatible group while preserving a safe
-partial result. Repeating the original request without the rejected response or
-corrective explanation gives the model no information with which to improve.
-
-The existing feedback-aware validation mechanism already establishes the safe
-correction protocol, but module-owned retry directives also carry internal
-reason codes, operator messages, and fallback diagnostics. Those values are not
-model instructions. Some module retry conditions, including exhausted
-structured-output repair, also have no valid exact response to append.
-
-## Decision
-
-An LLM-backed normalizer may attach optional, bounded model-facing correction
-guidance to a module-requested retry. Guidance is a separate contract field; the
-framework never derives it from a reason code, operator message, diagnostic, or
-error. A feedback-capable directive must include the exact model candidate that
-controlled the safe fallback and must use `single_response_v1`.
-
-The artifact-neutral producer-attempt state machine constructs the correction
-from that exact latest response and the supplied guidance. The producer rebuilds
-its complete ordinary request and appends the response as one assistant message
-and the guidance as one user message. Earlier attempts do not accumulate, and
-the attempt consumes the same configured stage retry budget as operational,
-structural, validation, and feedback-free module retries.
-
-A module retry without guidance remains valid and starts a fresh attempt. This
-is the required behavior when no valid model candidate exists, including after
-structured-output repair is exhausted. If feedback is supplied without a valid
-supported candidate, the framework fails the module contract rather than
-retrying blindly or inventing guidance.
-
-After retry exhaustion, the normalizer's safe fallback continues through its
-validator chain. Safe semantic groups may remain applied, unsafe groups remain
-separate, and bounded fallback diagnostics may explain the process degradation.
-Exact responses and correction text remain attempt-local and are excluded from
-ordinary errors, warnings, manifests, receipts, caches, and checkpoints.
-
-This decision extends, rather than supersedes,
-[ADR-0014](0014-feedback-aware-validation-retries.md): both correction sources
-use the same transport-neutral payload, replacement-request semantics, outer
-retry budget, and sensitive-data boundary.
-
-## Alternatives considered
-
-- Continue blind module retries. This preserves a smaller contract but wastes
-  the module's deterministic diagnosis and commonly repeats the same defect.
-- Convert module safety checks into validators. Typed reconciliation must apply
-  only safe proposal groups and retain a fallback before validation; moving
-  artifact-owned translation and application policy into validators would blur
-  stage ownership.
-- Copy the retry reason or operator message into the model request. Those values
-  are written for provenance and humans, can contain opaque internal labels,
-  and do not reliably describe a correct replacement.
-- Require feedback for every module retry. Structural failures may have no
-  valid exact candidate, so this would either prevent useful fresh retries or
-  fabricate prior-response material.
-
-## Consequences
-
-The normalize retry contract and generic producer-attempt directive gain an
-optional correction-guidance field and candidate-pairing validation. Modules
-that use it must provide semantically meaningful bounded prose and an exact
-candidate. Registry reconciliation maintains separate operator and model
-renderers, and policy fingerprints change so checkpoints created under blind
-retry behavior are not reused.

docs/adr/0017-defer-cache-access-policy-to-deployment.md

@@ -1,59 +0,0 @@
-# ADR-0017: Defer cache access policy to the deployment
-
-**Status:** Accepted
-**Date:** 2026-09-11
-
-## Context
-
-Canonical chunk plans and invocation checkpoints are reconstructible cache
-state. They may include source-derived content, so access and retention matter,
-but Notarius cannot determine whether a deployment needs a private cache or a
-cache shared by a trusted group. The current application-enforced `0700` and
-`0600` modes prevent ordinary Unix provisioning from making that choice.
-
-[ADR-0005](0005-cache-canonical-chunk-plans-by-source.md) governs canonical
-chunk-plan reuse, while [ADR-0006](0006-separate-output-cache-and-debug-state.md)
-established the output, cache, and debug separation refined by
-[ADR-0007](0007-separate-checkpoint-recording-from-reuse.md). None of those
-decisions requires Notarius to own exact cache access modes.
-
-## Decision
-
-Deployments own cache access policy through provisioned directories, process
-umask, setgid inheritance, and default ACLs. Notarius requests conventional
-maximum creation modes for cache entries and leaves the kernel to select their
-effective permissions.
-
-Notarius continues to own confined paths, symlink rejection, validation,
-atomic publication, cleanup, and recovery. Those correctness boundaries are
-independent from deciding which accounts may access cache state.
-
-Source-derived cache contents can be sensitive. Operators own their access and
-retention policy, while API credentials remain outside cache payloads under the
-existing secret boundary. Existing cache inode modes are not migrated
-automatically.
-
-This decision does not supersede ADR-0005, ADR-0006, or ADR-0007.
-
-## Alternatives considered
-
-- Continue enforcing private `0700` directory and `0600` file modes. This
-  makes one deployment choice for every operator and prevents trusted-group
-  provisioning.
-- Add configurable Notarius permission modes or a private/group cache setting.
-  This preserves application ownership of a deployment concern and expands the
-  public configuration surface without a durable policy reason.
-- Recursively converge existing cache ownership, modes, or ACLs. This would
-  make upgrades mutate operator-managed state and cannot safely infer an
-  intended policy.
-
-## Consequences
-
-Operators can use a restrictive umask for private cache state or provision a
-setgid/default-ACL cache root for trusted-group access. They must deliberately
-recreate or administratively migrate pre-existing cache trees when their
-existing modes do not match the desired deployment policy.
-
-Notarius does not add user or group management, ACL mutation, permission
-configuration, or recursive cache migration. Output and debug permission
-contracts remain separate from this decision.

docs/adr/0018-adopt-configkit.md

@@ -1,53 +0,0 @@
-# ADR-0018: Adopt ConfigKit for configuration loading
-
-**Status:** Accepted
-**Date:** 2026-09-13
-
-## Context
-
-Notarius's former configuration boundary owned strict YAML parsing, input
-presence bookkeeping, defaults, normalization, environment overlays, and
-configuration inspection. Those general-purpose responsibilities had grown
-alongside application-specific pipeline and module semantics.
-
-ConfigKit v0.3.0 provides strict typed YAML loading, imports, configuration
-profiles, explicit CLI overrides, recorded defaults and normalization, safe
-inspection rendering, and released source-origin APIs. The application needs
-those source records to resolve filesystem paths according to the file that
-supplied a surviving declaration.
-
-## Decision
-
-Notarius will adopt the root public `gitea.maximumdirect.net/eric/ConfigKit`
-package at v0.3.0 for its version 5 configuration contract. ConfigKit owns
-source composition, strict decoding, input presence, metadata, and safe
-effective/explanation rendering. Notarius retains its typed document schema,
-field semantics, runtime conversion, catalog-dependent pipeline resolution,
-PromptKit profile handling, and physical run preparation.
-
-Version 5 is a deliberate breaking file-contract change. It uses canonical
-object module bindings and reference sources, and enables ConfigKit imports
-and configuration profiles. The selected configuration file's canonical
-directory is the base for its declared application paths; ConfigKit's released
-`Resolution.InputInfo` and `Resolution.Source` APIs provide their origins.
-
-`NOTARIUS_CONFIG` remains file discovery, while field-level operational
-environment overlays are retired. Explicit configuration-valued CLI flags are
-represented as ConfigKit overrides; invocation actions remain outside that
-boundary.
-
-## Alternatives considered
-
-- Continue extending the custom YAML loader. This preserves duplicated
-  general-purpose parsing, presence, composition, and inspection machinery.
-- Retain version 4 alongside version 5. This would leave a supported dual
-  configuration boundary and delay removal of the machinery being replaced.
-- Wrap ConfigKit in a compatibility pre-parser. This weakens ConfigKit's
-  strict contract and recreates the application-owned parser complexity.
-
-## Consequences
-
-The released application has one ConfigKit-backed loader and one version 5
-contract. Operator documentation and maintained examples move with the cutover.
-ConfigKit metadata is retained only at the configuration publication boundary;
-its types do not become module or runtime pipeline interfaces.

docs/cli.md

@@ -10,26 +10,14 @@ defined in [Operations](operations.md).
 
 ~~~
 notarius help
-notarius --version
 notarius run <pipeline-id> --input path/to/source.json [--json] [flags]
-notarius config validate [--config path/to/config.yml] [--config-overlay name] [--pipeline pipeline-id] [--only lane-a,lane-b]
+notarius config validate [--config path/to/config.yml] [--pipeline pipeline-id] [--only lane-a,lane-b]
-notarius pipelines list [--config path/to/config.yml] [--config-overlay name] [--json]
+notarius pipelines list [--config path/to/config.yml] [--json]
 ~~~
 
 Running Notarius without arguments, or with **help**, **--help**, or **-h**,
 writes the command summary to standard output and exits with status 0.
 
-`notarius --version` is valid only as the sole root argument. It writes exactly
-`notarius <version>` followed by a newline to standard output and exits with
-status 0. A tagged `go install` build can report its main-module stable tag,
-and controlled builds can inject a stable tag at link time through
-`gitea.maximumdirect.net/eric/notarius/internal/buildinfo.Override`; an ordinary
-unversioned checkout reports `development`. Invalid injected version content is
-a runtime error with exit status 1, while extra `--version` arguments are a
-syntax error with exit status 2. This diagnostic does not replace the
-[run-result](integrations/run-result.md) or artifact contracts for downstream
-compatibility decisions.
-
 ## run
 
 ~~~
@@ -42,7 +30,6 @@ pipeline ID and **--input** are required.
 | Flag | Meaning |
 | --- | --- |
 | **--config path** | Use this configuration file. When omitted, configuration discovery applies; see [Configuration](config.md). |
-| **--config-overlay name** | Select a ConfigKit configuration overlay. Empty and **default** select the composed base configuration. |
 | **--input path** | Source input file to process. Required. |
 | **--output-dir path** | Override the configured output root for this run. |
 | **--json** | Write the successful run-result receipt as JSON to standard output. |
@@ -52,92 +39,46 @@ pipeline ID and **--input** are required.
 | **--debug** | Retain a debug bundle for this run. |
 | **--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. |
+| **--llm-profile id** | Override effective LLM-capable module bindings with one configured profile. |
-| **--session-id id** | Override the generated prompt session identifier with a non-empty value for LLM-backed module calls. |
+| **--session-id id** | Supply a non-empty prompt session identifier to 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. |
+| **--reference selector=path** | Add or replace a file reference binding. Repeatable. |
-| **--clear-reasoning-effort** | Clear reasoning effort inherited from the selected PromptKit profile for every LLM-backed call in this run. |
+| **--without-reference selector** | Remove a configured optional reference binding. Repeatable. |
-| **--reference selector=path** | Add or replace external file reference bindings at pipeline, lane, chunk, or binding scope. Repeatable. |
-| **--without-reference selector** | Remove matching configured external reference bindings. Repeatable. |
 
 **--chunk_cache** accepts only **auto**, **bypass**, or **refresh**.
 **--debug-dir**, **--output-dir**, **--session-id**, and
-**--reasoning-effort**, and **--recompute-step** reject explicit empty values.
+**--recompute-step** reject explicit empty values. **--recompute-step**
-**--reasoning-effort** and **--clear-reasoning-effort** are mutually exclusive.
+requires **--resume**; checkpoint requirements and reuse behavior are
-When neither is present, reasoning effort comes from the selected PromptKit
+documented in [Operations](operations.md).
-profile. These controls apply to the shared run client, including retries and
-LLM-backed validators, and do not modify configuration or profile files.
-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 reference slots declared by the selected
+Use **--reference** only for a reference slot declared by the selected
-configured targets. Qualification narrows the scope of an override:
+configured target. The accepted selector forms are:
 
 | Form | Target |
 | --- | --- |
-| slot=path | Every selected target that declares slot. |
+| slot=path | The unique selected target that declares slot. |
 | chunk.slot=path | The chunker. |
-| lane.slot=path | Every extractor, merger, or normalizer in lane that declares slot. |
+| merge.slot=path | The unique selected merger that declares slot. |
+| lane.slot=path | The unique extractor, merger, or normalizer in lane that declares slot. |
 | lane.extract.slot=path | The extractor in lane. |
 | lane.merge.slot=path | The merger in lane. |
 | lane.normalize.slot=path | The normalizer in lane. |
 
-Pipeline- and lane-scoped selectors are expected to match multiple targets and
+**--without-reference** uses the same selector forms without =path. Slot
-fail if they match none. A stage-specific selector fails when its lane is not
+names, requiredness, and configured bindings are part of the
-selected or its target does not declare the slot. There is no stage-wide
-`merge.slot` shorthand; name the lane when targeting a merger.
-
-CLI bindings override configured external paths. For overlapping CLI
-selectors, a binding-specific or chunk selector overrides a lane selector, and
-a lane selector overrides a pipeline selector. The last occurrence wins at
-equal scope. Binding and unbinding the same concrete target at equal scope is
-an error; a narrower bind or unbind may create an intentional exception to a
-broader action.
-
-**--without-reference** uses the same selector forms without `=path` and
-removes external bindings only. Neither flag replaces or removes a generated
-artifact handoff; an external/generated collision is a resolution error.
-Required slots are checked after all effective changes. CLI reference paths
-are resolved relative to the process working directory, so subprocess and
-service callers should use absolute paths. Slot names, accepted media types,
-size limits, requiredness, and configured generated bindings are part of the
 [configuration contract](config.md).
 
-For example, one shared campaign reference can reach every compatible target,
-with an optional lane-specific exception:
-
-~~~
-notarius run dnd-session \
-  --input /data/transcript.json \
-  --reference party=/data/references/party.txt \
-  --reference npc-registry.party=/data/references/npc-party-context.txt
-~~~
-
 ### Run output
 
 Without **--json**, standard output contains the completed pipeline ID, counts
 of normalized and rejected outputs, and the output directory. A debug-enabled
 run also prints its debug-bundle path to standard output. A successful run with
-actionable process warnings reports their group and occurrence counts to
+warnings reports the warning count to standard error. The published JSON bundle
-standard error. When the selected output module publishes `warnings.json`, the
-summary also reports that durable file's path. Advisory and observation findings
-do not produce a warning line. The published JSON bundle
 is defined by the [JSON output contract](integrations/json-output.md).
 
 With **--json**, successful standard output is exactly one
-`notarius.run-result.v2` JSON document followed by a newline, with no
+`notarius.run-result.v1` JSON document followed by a newline, with no
 human-oriented status or debug-path line. Its fields and compatibility policy
 are defined by the [run-result contract](integrations/run-result.md). A caller
 must check for exit status 0 before decoding this output; a failed write can
@@ -155,10 +96,10 @@ OPENROUTER_API_KEY=your-api-key \
 ## config validate
 
 ~~~
-notarius config validate [--config path/to/config.yml] [--config-overlay name] [--pipeline pipeline-id] [--only lane-a,lane-b]
+notarius config validate [--config path/to/config.yml] [--pipeline pipeline-id] [--only lane-a,lane-b]
 ~~~
 
-This command loads and validates the selected composed configuration. With **--pipeline**, it also
+This command loads and validates a configuration. With **--pipeline**, it also
 resolves that pipeline against the production module catalog. **--only** selects
 lanes during that resolution and requires **--pipeline**.
 
@@ -181,32 +122,10 @@ OPENROUTER_API_KEY=validation-placeholder \
 The placeholder in the second command is sufficient only for offline
 validation; it cannot run a provider-backed pipeline.
 
-## config effective
-
-~~~
-notarius config effective [--config path/to/config.yml] [--config-overlay name]
-~~~
-
-This command writes the selected composed configuration as deterministic,
-redacted YAML. Standard output contains only that YAML: it does not validate a
-pipeline, prepare modules, materialize references, or contact a provider.
-
-## config explain
-
-~~~
-notarius config explain [--config path/to/config.yml] [--config-overlay name] <json-pointer>
-~~~
-
-This command writes ConfigKit's redacted, human-readable explanation for one
-canonical JSON Pointer. Supply `""` explicitly to explain the root. A malformed
-pointer is a syntax error; a well-formed unknown path is a command failure.
-The explanation can describe a value displaced by a selected overlay. Standard
-output contains only the explanation.
-
 ## pipelines list
 
 ~~~
-notarius pipelines list [--config path/to/config.yml] [--config-overlay name] [--json]
+notarius pipelines list [--config path/to/config.yml] [--json]
 ~~~
 
 This command lists configured pipeline IDs in sorted order. By default, it
@@ -223,11 +142,7 @@ go run ./cmd/notarius pipelines list \
 Successful commands write their primary result to standard output. Warnings and
 errors are written to standard error.
 
-Configuration load errors include ConfigKit's field diagnostics and source
+For **run --json**, warnings remain on standard error and standard output is a
-coordinates, followed by a source-ID legend identifying the acquired files or
-source labels. This includes imported files and the selected configuration overlay.
-
-For **run --json**, actionable process warnings remain on standard error and standard output is a
 machine-readable success result only. Syntax and runtime diagnostics remain on
 standard error. Parse the result only after the process exits with status 0.
 
@@ -238,6 +153,6 @@ standard error. Parse the result only after the process exits with status 0.
 | 2 | The command or flag syntax was invalid, including unknown commands, missing required arguments, invalid flag values, or invalid flag combinations. |
 
 The root help spellings are the supported help path. Invoking **--help** on
-**run**, a **config** subcommand, or **pipelines list** is handled by the flag
+**run**, **config validate**, or **pipelines list** is handled by the flag
 parser as a usage error: it writes an error to standard error and exits with
 status 2.

docs/config.md

@@ -1,7 +1,7 @@
 # Configuration
 
 This is the canonical reference for Notarius configuration. Configuration files
-are YAML and must declare version 5. They select pipelines and their modules;
+are YAML and must declare version 3. They select pipelines and their modules;
 the [CLI reference](cli.md) owns invocation syntax, and
 [Operations](operations.md) owns run-state procedures.
 
@@ -19,16 +19,12 @@ The command fails if none of these paths provides a configuration file.
 For configuration values, precedence is:
 
 1. built-in defaults;
-2. composed YAML sources, including imports;
+2. the selected YAML file;
-3. the selected ConfigKit overlay; and
+3. supported operational environment variables; and
-4. explicitly supplied configuration-valued run flags.
+4. the CLI run overrides that apply to a command.
 
-`--config-overlay` selects a ConfigKit overlay from `overlays/<name>.yml`
+Environment variables do not provide a second configuration schema. They only
-beneath the selected configuration root. Empty and `default` select no overlay.
+override the fields listed below.
-`profiles/<name>.yml` is not a fallback location, and `--config-profile` is no
-longer accepted. Configuration overlays are distinct from PromptKit LLM profiles selected by
-`llm_profile` or `--llm-profile`. The retired operational environment variables
-have no effect; `NOTARIUS_CONFIG` remains a source-discovery input.
 
 ## Maintained Examples
 
@@ -36,9 +32,7 @@ have no effect; `NOTARIUS_CONFIG` remains a source-discovery input.
   single-lane Seriatim-to-spell pipeline.
 - [Complete D&D configuration](../examples/dnd-complete.config.yml) uses
   ordered steps, all implemented D&D lanes, generated references, state
-  settings, bounded LLM concurrency, and the maintained
+  settings, and bounded LLM concurrency.
-  [LLM profile](../examples/llm-profiles/dnd-extraction.yml) and imports its
-  pipeline from [a fragment](../examples/pipelines/dnd-session.yml).
 
 Use these complete files as starting points rather than combining the
 illustrative fragments in this reference.
@@ -51,8 +45,8 @@ other than **version** is optional.
 
 | Field | Type | Default | Rules |
 | --- | --- | --- | --- |
-| **version** | integer or quoted string | none | Required; must be 5. Maintained files use `version: 5`. |
+| **version** | integer | none | Required; must be 3. |
-| **promptkit** | object | none | Profile source and optional local-backend configuration. |
+| **scriptorium** | object | none | Profile source configuration. |
 | **pipelines** | map | empty | Maps pipeline IDs to pipeline definitions. |
 | **concurrency** | object | see below | Global LLM and extraction limits. |
 | **output** | object | see below | Published output settings. |
@@ -63,7 +57,7 @@ Built-in defaults are:
 
 | Field | Default |
 | --- | --- |
-| **concurrency.total_llm** | 16 |
+| **concurrency.total_llm** | 1 |
 | **concurrency.stage_workers.extract** | Effective **total_llm** |
 | **output.directory** | **./notarius-output** |
 | **cache.chunk_plans.mode** | **auto** |
@@ -74,112 +68,39 @@ Built-in defaults are:
 
 An empty cache directory in YAML deliberately selects the corresponding
 per-user root. An explicit empty output or debug directory is invalid.
-Selecting a chunk-plan or checkpoint directory does not configure filesystem
-access policy. Cache permissions come from deployment provisioning, process
-umask, setgid inheritance, and default ACLs; see [Operations](operations.md#cache-provisioning).
 
-Every nonempty relative configured destination or reference path resolves from
+## Scriptorium Profiles
-the canonical directory of the file that supplies its surviving declaration.
-This includes imported fragments and selected configuration overlays. Built-in
-relative destinations use the selected main configuration file's directory;
-explicit `--output-dir` and `--debug-dir` values use the invocation working
-directory. Absolute values remain unchanged.
 
-The root file can use ConfigKit imports to compose disjoint definitions. Imports
+The optional **scriptorium** object selects one source of profile definitions:
-and selected overlays remain under the configuration root; they do not merge or
-append a pipeline's `steps` sequence. An overlay replaces sequences as defined
-by ConfigKit, so changing an individual ordered binding requires supplying the
-whole replacement sequence.
-
-## PromptKit Profiles
-
-The optional **promptkit** object selects one source of profile definitions and
-may register one conventional local OpenAI-compatible backend:
-
-~~~yaml
-version: 5
-
-promptkit:
-  profile_dir: ./profiles
-  # profile_file: ./profiles.yml
-  transient_retries: 2
-  local_backend:
-    endpoint: http://localhost:8000/v1
-    concurrency_limit: 2
-~~~
 
 | Field | Type | Rules |
 | --- | --- | --- |
 | **profile_dir** | string | Non-empty directory containing profile files. |
 | **profile_file** | string | Non-empty profile file. |
-| **transient_retries** | integer | Non-negative additional built-in HTTP attempts for eligible transient provider failures; defaults to 2. Set 0 to disable these retries. |
-| **local_backend** | object | Optional registration for the conventional PromptKit backend ID **local**. |
-| **local_backend.endpoint** | string | Required when **local_backend** is present; absolute HTTP or HTTPS URL with a host. |
-| **local_backend.concurrency_limit** | integer | Optional non-negative limit; defaults to 0. |
 
-Set at most one of **profile_dir** and **profile_file**. Every nonempty relative
+Set at most one of these fields. Profile IDs used by a binding must be available
-configured filesystem path is resolved from the canonical directory of the
+from the selected Scriptorium profile source when the pipeline is resolved.
-file that supplies it. The complete example's
+Keep credentials out of this file: configure a profile to read its credential
-`./llm-profiles/dnd-extraction.yml` value therefore resolves beside that example.
+from an environment variable, then set that environment variable only in the
-Use absolute paths for services and containers when their deployment layout is
+run environment.
-not configuration-relative.
 
-An operator source is optional. For a requested ID, PromptKit checks the
+## Operational Environment Variables
-configured operator source first, then Notarius's embedded fallback profiles,
-then its own built-in catalog. A matching profile is complete: it replaces a
-lower-precedence definition rather than merging with it. The maintained
-[`dnd-extraction` LLM profile](../examples/llm-profiles/dnd-extraction.yml)
-is a secret-free deployment artifact; production, development, and local
-deployments can each provide a complete definition with that same workload ID.
-Use workload-oriented IDs for new profiles instead of model names.
-[Operations](operations.md#promptkit-profile-deployment) owns the deployment
-workflow and credential-handling guidance.
 
-When **local_backend** is present, its endpoint is trimmed and must use HTTP or
+These variables are applied after YAML values:
-HTTPS case-insensitively, be absolute, and have a non-empty host. URL paths are
-allowed. User information, queries, and fragments are rejected. A zero
-**concurrency_limit** leaves the local backend unrestricted inside PromptKit;
-a positive value limits simultaneous local generations. The application-wide
-**concurrency.total_llm** limit still applies in both cases. Neither local
-backend field has an environment override. Omitting **local_backend** registers
-nothing and preserves existing built-in and endpoint-only profile behavior.
 
-A file-backed PromptKit profile selects the registration by its case-sensitive
+| Variable | Overrides | Rules |
-backend ID:
+| --- | --- | --- |
+| **NOTARIUS_TOTAL_LLM_CONCURRENCY** | **concurrency.total_llm** | Integer. |
+| **NOTARIUS_STAGE_WORKERS_EXTRACT** | **concurrency.stage_workers.extract** | Integer. |
+| **NOTARIUS_OUTPUT_DIR** | **output.directory** | Non-empty path. |
+| **NOTARIUS_CACHE_CHUNK_PLANS_MODE** | **cache.chunk_plans.mode** | **auto**, **bypass**, or **refresh**. |
+| **NOTARIUS_CACHE_CHUNK_PLANS_DIR** | **cache.chunk_plans.directory** | Non-empty path. |
+| **NOTARIUS_CACHE_CHECKPOINTS_DIR** | **cache.checkpoints.directory** | Non-empty path. |
+| **NOTARIUS_DEBUG_DIR** | **debug.directory** | Non-empty path. |
 
-~~~yaml
+Integer values are trimmed then parsed as base-10 integers. Directory and
-id: local-summary
+output values reject NUL characters. **NOTARIUS_CONFIG** participates only in
-backend: local
+configuration discovery.
-model: example-model
-~~~
-
-Keep credentials out of the local-backend object. A PromptKit profile may name
-its credential environment variable through `api_key_env`; set that variable
-only in the run environment. PromptKit owns the
-[pinned profile-file format](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.9.0/docs/formats.md),
-including `base_profile` inheritance. Notarius passes profiles through without
-merging them. Filesystem profiles cannot express PromptKit's in-memory
-`APIKeyRequired` setting; an unset `api_key_env` is optional and may reach the
-provider without authorization.
-The [PromptKit upstream boundary](integrations/pkg-promptkit.md) identifies the
-supported package API, and [Operations](operations.md#operational-limits)
-describes the effective concurrency layers.
-
-`notarius config validate --pipeline <id>` resolves the selected pipeline and
-inspects every explicit effective profile without contacting a provider or
-requiring credential values. It rejects absent, malformed, or incompatible
-profiles before a run prepares modules. Credential availability is checked only
-when a generation is prepared.
-
-## Version 5 Migration
-
-Version 3 and version 4 files are rejected and are not rewritten at load time.
-Use `version: 5`, rename the former `scriptorium` section to `promptkit`, and
-convert every module binding to an object containing `module`. Convert every
-external reference to `{path: ...}` and move any lane-level references to the
-corresponding extraction binding. Put durable operational values in YAML or
-use the documented explicit run flags; the former field-level environment
-variables are not read.
 
 ## Concurrency, Output, Cache, And Debug
 
@@ -204,14 +125,11 @@ debug:
 **concurrency.total_llm** must be greater than zero. The only supported
 **concurrency.stage_workers** key is **extract**; its value must be from 1
 through **total_llm**. When omitted, it is recalculated from the effective
-**total_llm** after imports, overlay selection, and explicit ConfigKit
+**total_llm** after YAML and environment precedence.
-overrides.
 
 **cache.chunk_plans.mode** accepts **auto**, **bypass**, or **refresh**.
 **cache.checkpoints.enabled** is a boolean. The CLI can override the output
 directory and chunk-plan mode for one run; see [CLI reference](cli.md#run).
-Cache directory fields select only locations; Notarius has no cache permission
-field or operational environment override.
 
 ## Pipelines
 
@@ -220,28 +138,18 @@ Each **pipelines** entry has a unique, non-empty ID and the following shape:
 ~~~yaml
 pipelines:
   dnd-session:
-    llm_profile: dnd-extraction
+    input: seriatim
-    input:
+    chunk: generic
-      module: seriatim
+    output: json
-    chunk:
-      module: generic
-    output:
-      module: json
     artifacts:
       spells:
-        extract:
+        extract: dnd/spells
-          module: dnd/spells
+        merge: appendorder
-        merge:
+        normalize: dnd/spells
-          module: appendorder
-        normalize:
-          module: dnd/spells
 ~~~
 
 | Field | Type | Default | Rules |
 | --- | --- | --- | --- |
-| **llm_profile** | string | none | Optional non-empty default PromptKit profile ID for selected LLM-backed bindings and validators. An explicitly present blank value is invalid. |
-| **structured_output_repair_attempts** | integer | prompt-owned (1 in maintained production prompts) | Optional structural-repair limit from 0 through 3 for selected LLM-backed bindings and validators. Omission leaves the prompt's declared policy in control; explicit 0 disables structural repair at that scope. |
-| **validation_policy** | object | see below | Optional terminal policy defaults for producer validation. Its fields inherit independently into chunk, extract, merge, and normalize bindings. |
 | **input** | module binding | none | Required. |
 | **chunk** | module binding | **generic** | Optional. |
 | **output** | module binding | **json** | Optional. |
@@ -255,48 +163,6 @@ needs a unique non-empty **id**, an **artifacts** map, and may have
 **references**. A lane ID must not appear more than once in a pipeline,
 including across explicit steps.
 
-For each selected LLM-backed binding or validator, profile selection occurs
-after module, validator, and `--only` lane selection. It uses the
-run-level **--llm-profile** value first, then the binding's **llm_profile**,
-then the pipeline's **llm_profile**, and finally the PromptKit default.
-Deterministic bindings do not receive these defaults or run overrides.
-
-Structural output repair is resolved after module, validator, and `--only` lane
-selection. An object's **structured_output_repair_attempts** value takes
-precedence over the pipeline value; otherwise, an LLM-backed binding or
-validator inherits the pipeline value. If both are omitted, PromptKit uses the
-prompt's declared repair policy. The value must be an integer from 0 through 3;
-explicit `null` and non-integer values are invalid. An explicit value on a
-deterministic binding or validator is invalid, while a pipeline value simply
-does not apply to deterministic selections.
-
-`validation_policy` controls terminal disposition for one complete producer
-attempt and validator chain. It may appear on a pipeline or a **chunk**,
-**extract**, **merge**, or **normalize** module binding; input, output, and
-validator bindings reject it. Every field is optional and resolves in binding,
-pipeline, then application-default order:
-
-| Field | Values | Default |
-| --- | --- | --- |
-| **producer_structural_failure** | **fail_run**, **reject_output** | **fail_run** |
-| **semantic_rejection** | **fail_run**, **reject_output** | **fail_run** |
-| **validator_failure** | **warn_continue**, **fail_run** | **warn_continue** |
-
-The policy object and its fields must be non-null, and unknown fields are
-rejected. A deterministic producer may not explicitly set
-**producer_structural_failure** on its binding, although a pipeline-level
-default remains valid for pipelines that include LLM-backed producers.
-
-After the producer binding's retry budget is exhausted, an invalid structured
-response uses **producer_structural_failure**. One or more semantic validator
-rejections use **semantic_rejection**; rejection takes precedence over an
-exhausted validator failure or skip. With no rejection, an exhausted validator
-failure or skip uses **validator_failure**. `reject_output` records the
-terminal rejection without advancing that candidate. `warn_continue` is valid
-only for validator execution failure: it advances a structurally valid,
-otherwise unrejected result with incomplete-validation provenance and without
-making it reusable checkpoint state.
-
 A lane has these fields:
 
 | Field | Type | Default | Rules |
@@ -304,20 +170,19 @@ A lane has these fields:
 | **extract** | module binding | none | Required. |
 | **merge** | module binding | **appendorder** | Optional. |
 | **normalize** | module binding | **noop** | Optional. |
-| **references** | map | none | Not supported at lane scope; place references on the eligible binding. |
+| **references** | map | none | Supported compatibility alias for **extract.references**. |
 | **validators** | list | none | Non-empty lane-level lists are rejected. Set validator overrides on a binding instead. |
 
-Lane-level **references** are not supported. Put a lane extraction reference
+The lane-level **references** alias remains accepted. When the alias and
-under **extract.references**.
+**extract.references** bind the same slot, **extract.references** wins. Use
+the binding-local form in new configurations.
 
 ## Module Bindings And Validators
 
-Every module and validator binding uses an object, even when it has no fields
+Use a module key directly when no other binding fields are needed:
-beyond its module key:
 
 ~~~yaml
-input:
+input: seriatim
-  module: seriatim
 ~~~
 
 Use an object for fields:
@@ -325,43 +190,26 @@ Use an object for fields:
 ~~~yaml
 extract:
   module: dnd/spells
-  llm_profile: dnd-extraction
+  llm_profile: gemini-2-flash
   retries: 2
   references:
-    spell_catalog:
+    spell_catalog: ./dnd-spell-catalog.json
-      path: ./dnd-spell-catalog.json
 ~~~
 
 | Binding field | Type | Default | Rules |
 | --- | --- | --- | --- |
 | **module** | string | none | Required for an object binding. Must be a registered compatible key. |
-| **llm_profile** | string | none | Optional non-empty PromptKit profile ID for an LLM-backed binding. It overrides the pipeline default unless the run supplies **--llm-profile**. |
+| **llm_profile** | string | none | Optional non-empty Scriptorium profile ID. |
-| **structured_output_repair_attempts** | integer | pipeline or prompt-owned (1 in maintained production prompts) | Optional structural-repair limit from 0 through 3 for an LLM-backed binding. It overrides the pipeline value; explicit 0 disables structural repair. |
+| **retries** | integer | 0 | Non-negative additional attempts for chunk, extract, merge, and normalize bindings. |
-| **validation_policy** | object | pipeline or application defaults | Optional field-by-field terminal-policy override for a chunk, extract, merge, or normalize binding. |
-| **retries** | integer | 0 | Non-negative additional complete producer attempts for chunk, extract, merge, and normalize bindings. This single budget covers operational errors, invalid structured output, module-requested normalization retry, and semantic correction. |
 | **options** | object | none | Must satisfy the selected module. |
 | **references** | map | none | Valid only on chunk, extract, merge, and normalize bindings. |
 | **validators** | list | production chain | Valid only on chunk, extract, merge, and normalize bindings. |
 
 Omitting **validators** uses the registered chain. **validators: []** selects
 an empty chain; a non-empty list replaces the chain in the listed order.
-Validator bindings accept only **module**, **llm_profile**,
+Validator bindings accept only **module**, **llm_profile**, and **options**.
-**structured_output_repair_attempts**, **retries**, and **options**. Their
+They reject **references**, **retries**, and nested **validators**. Deterministic
-**retries** value is a non-negative additional validator-execution budget and
+validators reject an explicit **llm_profile**.
-is valid only when the selected validator is LLM-backed. A validator retry
-rechecks the same immutable candidate; it never regenerates the producer.
-They reject
-**validation_policy**, **references**, and nested **validators**. Deterministic
-validators reject explicit **llm_profile** and
-**structured_output_repair_attempts**.
-Deterministic module bindings also reject those explicit fields.
-
-An LLM-backed chunk, extract, merge, or normalize producer with both a
-non-empty validator chain and positive **retries** must declare the supported
-single-response correction capability. Preparation rejects a configuration
-that could require semantic correction from a producer that cannot provide an
-exact prior response. A deterministic producer, or an LLM attempt that did
-not make a model call, cannot consume a semantic retry after rejection.
 
 The **json** output module accepts optional **include_chunk_map** and
 **evidence_context** settings:
@@ -375,7 +223,7 @@ output:
       enabled: true
       window_units: 3
       lanes:
-        - npc-registry
+        - npcs
         - spells
 ~~~
 
@@ -396,37 +244,32 @@ Unknown outer or nested option fields are rejected, as are incompatible YAML
 types. The allowlist remains valid when a run uses lane filtering: a configured
 lane that is not active for that invocation simply contributes no evidence.
 Evidence publication is opt-in because it can persist source text and metadata.
-When enabled, it publishes the selected source-unit excerpt defined by the
+Its payload contract is [Published Evidence Context](integrations/evidence-context.md).
-[Published Evidence Context contract](integrations/evidence-context.md).
 
 ## References And Ordered Handoffs
 
-Reference maps bind named slots that the selected target declares. An external
+Reference maps bind named slots that the selected target declares. A scalar is
-reference is an object with `path`. Pipeline-level maps accept only external
+an external path. Pipeline-level maps accept only external paths; step-local
-paths; step-local and binding-local maps may also select a normalized artifact
+and binding-local maps may also select a normalized artifact from an earlier
-from an earlier step:
+step:
 
 ~~~yaml
 steps:
   - id: describe-session
     artifacts:
-      npc-registry:
+      npcs:
-        extract:
+        extract: dnd/npcs
-          module: dnd/npc-registry
+        normalize: dnd/npcs
-        normalize:
-          module: dnd/npc-registry
   - id: extract-events
     references:
-      npc_registry:
+      npcs:
         artifact:
           step: describe-session
-          lane: npc-registry
+          lane: npcs
     artifacts:
       spells:
-        extract:
+        extract: dnd/spells
-          module: dnd/spells
+        normalize: dnd/spells
-        normalize:
-          module: dnd/spells
 ~~~
 
 An artifact selector contains only **step** and **lane**. The producer must be
@@ -435,16 +278,10 @@ slot. A generated binding supplies one accepted normalized artifact; it does
 not name a file. A configured generated dependency remains required even when
 that consumer slot is otherwise optional.
 
-Pipeline references are configuration defaults. A matching step-local or
+Pipeline references are defaults. A matching step-local or binding-local
-binding-local external path overrides a pipeline default. CLI reference
+external path overrides a pipeline default. Required slots must be bound after
-bindings are then operational overrides of configured external paths; their
+these configuration values and any CLI reference overrides are applied.
-pipeline, lane, and binding scopes and precedence are defined by the
+Reference paths in YAML are resolved relative to the configuration file.
-[CLI reference](cli.md#reference-selectors). A CLI file reference cannot
-replace a configured generated artifact handoff. Required slots must be bound
-after configuration and CLI reference actions are applied. A YAML reference
-path resolves from the file that supplies its surviving declaration, including
-an imported fragment or selected overlay. CLI reference paths resolve relative
-to the process working directory.
 
 ### D&D Reference Slots
 
@@ -458,38 +295,14 @@ 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). |
-| **location_registry** | Required normalized location registry for location-occurrence extraction and normalization. |
+| **npcs** | Normalized NPC registry. Optional for spells and combat turns; required for NPC interactions. |
-| **item_registry** | Required normalized item registry for item-occurrence extraction and normalization. |
+| **scene_descriptions** | Required normalized scene-description artifact for combat-turn extraction. |
-| **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 occurrences require **npc_registry** for both extraction and
+**roster**. NPC interactions require **npcs** for both extraction and
 normalization. Combat turns require **scene_descriptions** for extraction; the
-normalized combat-turn module may use optional **npc_registry**. Location occurrences
+normalized combat-turn module may use optional **npcs**. The complete example
-require **location_registry** for extraction and normalization. Item occurrences require
+shows generated **npcs** and **scene_descriptions** bindings.
-**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
 
@@ -497,29 +310,18 @@ generated bindings.
 | --- | --- |
 | Input | **seriatim** |
 | Chunk | **generic**, **dnd/scenes** |
-| 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** |
+| Extract | **dnd/spells**, **dnd/npcs**, **dnd/combat-turns**, **dnd/item-events**, **dnd/npc-interactions**, **dnd/scene-descriptions** |
 | Merge | **appendorder** |
-| 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** |
+| Normalize | **noop**, **dnd/spells**, **dnd/npcs**, **dnd/combat-turns**, **dnd/item-events**, **dnd/npc-interactions**, **dnd/scene-descriptions** |
 | 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),
-[NPC registry](integrations/dnd-npc-registry-artifacts.md),
+[NPCs](integrations/dnd-npc-artifacts.md),
-[NPC occurrences](integrations/dnd-npc-occurrence-artifacts.md),
+[NPC interactions](integrations/dnd-npc-interaction-artifacts.md),
 [combat turns](integrations/dnd-combat-turn-artifacts.md),
-[item registry](integrations/dnd-item-registry-artifacts.md),
+[item events](integrations/dnd-item-event-artifacts.md), and
-[item occurrences](integrations/dnd-item-occurrence-artifacts.md),
+[scene descriptions](integrations/dnd-scene-description-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
 
@@ -529,37 +331,11 @@ 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** |
-| NPC registry | **extract/dnd/npc-registry/shape**, **extract/dnd/npc-registry/source_refs**, **extract/dnd/npc-registry/source_relatedness**, **normalize/dnd/npc-registry/identity** |
+| NPCs | **extract/dnd/npcs/shape**, **extract/dnd/npcs/source_refs**, **extract/dnd/npcs/source_relatedness**, **normalize/dnd/npcs/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 occurrences | **extract/dnd/item-occurrences/shape**, **extract/dnd/item-occurrences/registry**, **extract/dnd/item-occurrences/source_refs**, **extract/dnd/item-occurrences/source_relatedness**, **normalize/dnd/item-occurrences/invariants** |
+| Item events | **extract/dnd/item-events/shape**, **extract/dnd/item-events/source_refs**, **extract/dnd/item-events/source_relatedness**, **normalize/dnd/item-events/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 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** |
-| 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** |
-| Scene descriptions | **extract/dnd/scene-descriptions/shape**, **extract/dnd/scene-descriptions/source_refs**, **extract/dnd/scene-descriptions/source_relatedness**, **extract/dnd/scene-descriptions/combat_semantics** (LLM-backed, opt-in), **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** |
-
-`extract/dnd/scene-descriptions/combat_semantics` is not in a production default chain. To opt in, replace the scene extractor validator chain with the current ordered chain plus the semantic validator last, and set a positive producer retry budget if a rejection should request a corrected scene:
-
-~~~yaml
-extract:
-  module: dnd/scene-descriptions
-  retries: 1
-  validators:
-    - module: generic/valid_json
-    - module: extract/dnd/scene-descriptions/shape
-    - module: extract/dnd/scene-descriptions/source_refs
-    - module: generic/valid_json_schema
-    - module: extract/dnd/scene-descriptions/source_relatedness
-    - module: extract/dnd/scene-descriptions/combat_semantics
-      retries: 1
-~~~
-
-An override replaces, rather than extends, the default chain. See [Module Bindings And Validators](#module-bindings-and-validators) for binding, profile, repair, retry, and failure-policy rules.
-
-The validator retry shown above permits one additional execution against the
-same scene candidate when the LLM-backed validator itself fails; it is separate
-from both the extractor's producer retry and PromptKit structural repair.
 
 When no override is configured, production D&D bindings use the following
 ordered chains. Each row lists extract then normalize; spell chains are the
@@ -568,15 +344,11 @@ 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 |
-| 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 |
+| 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 |
 | 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 occurrences | generic/valid_json, extract/dnd/item-occurrences/shape, extract/dnd/item-occurrences/registry, extract/dnd/item-occurrences/source_refs, generic/valid_json_schema, extract/dnd/item-occurrences/source_relatedness | generic/valid_json, extract/dnd/item-occurrences/shape, extract/dnd/item-occurrences/registry, normalize/dnd/item-occurrences/invariants, extract/dnd/item-occurrences/source_refs, generic/valid_json_schema, extract/dnd/item-occurrences/source_relatedness |
+| Item 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 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 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 |
-| 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
@@ -593,16 +365,7 @@ go run ./cmd/notarius config validate \
 ~~~
 
 Configuration validation rejects invalid YAML, unsupported fields, invalid
-defaults or explicit CLI overrides, incompatible module keys, unknown options,
+defaults or environment overrides, incompatible module keys, unknown options,
 invalid reference bindings, missing required reference slots, invalid validator
 overrides, and incompatible generated artifact handoffs. Use
 [pipelines list](cli.md#pipelines-list) to inspect configured IDs.
-
-## Inspection
-
-Use [config effective](cli.md#config-effective) to write the selected composed
-configuration as deterministic, redacted YAML. Use
-[config explain](cli.md#config-explain) with a canonical JSON Pointer to inspect
-the effective or historical provenance for one path, including a value displaced
-by a selected overlay. Neither command resolves a pipeline, prepares modules,
-materializes references, or requires provider credentials.

docs/consumers/dnd-pipeline.md

@@ -1,221 +0,0 @@
-# Consuming The Complete D&D Pipeline
-
-Use this workflow when an orchestrator runs the maintained complete D&D
-pipeline and consumes its structured JSON artifacts. The generic
-[subprocess consumer guide](subprocess.md) owns process-level responsibilities;
-this guide connects that workflow to the complete D&D configuration, its
-Seriatim input, and its artifact inventory.
-
-The [CLI reference](../cli.md), [configuration reference](../config.md),
-[run-result receipt](../integrations/run-result.md), and
-[published JSON output contract](../integrations/json-output.md) remain the
-canonical definitions of those public interfaces.
-
-## Prepare And Validate The Deployment
-
-Start from the maintained
-[complete D&D configuration](../../examples/dnd-complete.config.yml). It uses
-the `dnd-session` pipeline and demonstrates every implemented D&D lane, ordered
-artifact handoffs, campaign references, chunk-map publication, and evidence
-context.
-
-A deployment must provide its own PromptKit profile and campaign reference
-files. Use absolute paths for service and subprocess deployments. In
-particular, observe these different resolution rules:
-
-- reference and PromptKit profile paths in YAML are resolved relative to the
-  file that supplies their surviving declaration;
-- reference paths passed with `--reference` are resolved relative to the
-  Notarius process working directory.
-
-Do not copy the repository example's relative profile path into a deployment
-without preserving its configuration-relative layout. The complete path and
-profile rules are defined in [Configuration](../config.md).
-
-Preflight the deployed configuration before processing sessions and whenever
-it changes:
-
-```sh
-notarius config validate \
-  --config /absolute/path/to/notarius.yml \
-  --pipeline dnd-session
-```
-
-Provide credentials through the environment or the documented configuration
-mechanism. Do not put credentials in command arguments, generated
-configuration, or logs.
-
-## Supply The Transcript
-
-The complete pipeline consumes a Seriatim JSON document. The
-[Seriatim input contract](../integrations/seriatim.md) defines its required
-metadata, segments, and validation rules. Preserve segment IDs: D&D artifact
-citations use those segment IDs as source-unit ranges.
-
-When the caller maintains several transcript tiers, use the final trimmed JSON
-transcript so extraction operates on the same session content presented to
-later consumers. For example, Narratio identifies this implemented artifact as
-`narratio.transcript.final_trimmed` and normally stores it at
-`transcripts/final.trimmed.json`.
-
-Notarius generates a stable prompt session from the resolved input module and
-the exact input bytes. An ordinary orchestrator should not pass `--session-id`.
-Use that override only when intentionally changing the routing relationship
-between invocations; it is not a credential or output identity.
-
-## Run Notarius
-
-Invoke the pipeline with explicit absolute paths and request its
-machine-readable receipt:
-
-```sh
-notarius run dnd-session \
-  --config /absolute/path/to/notarius.yml \
-  --input /absolute/path/to/transcripts/final.trimmed.json \
-  --output-dir /absolute/path/to/notarius-output \
-  --reference party=/absolute/path/to/references/party.txt \
-  --reference players=/absolute/path/to/references/players.txt \
-  --reference glossary=/absolute/path/to/references/glossary.txt \
-  --reference spell_catalog=/absolute/path/to/references/spells.json \
-  --json
-```
-
-Each unqualified reference is pipeline-scoped: Notarius supplies it to every
-selected D&D target that declares the slot. A deployment may omit an optional
-reference it does not maintain, and may use the lane- or binding-qualified
-forms from the [CLI reference](../cli.md#reference-selectors) for an exceptional
-override. The registry, scene-description, combat-turn, and NPC-occurrence
-references declared between ordered steps in the complete configuration are
-generated artifacts. Do not pass those handoffs on the CLI.
-
-The caller should:
-
-- capture stdout and stderr separately;
-- propagate cancellation and impose an operator-appropriate timeout;
-- wait for process completion before interpreting stdout; and
-- retain stderr for diagnosis without copying secrets or transcript content
-  into other logs.
-
-Only exit status 0 permits decoding stdout as a receipt. Ignore stdout after a
-nonzero exit because a failed receipt write can leave partial bytes. The
-[CLI reference](../cli.md#output-streams-and-exit-statuses) defines the complete
-stream and exit-status contract.
-
-## Discover The Published Bundle
-
-Decode the successful stdout document as a supported run-result schema. For
-the current contract, `schema_version` is `notarius.run-result.v2`. Tolerate
-unknown fields allowed by that version, but reject an unsupported schema
-version.
-
-Use the receipt's absolute `output_directory` as the exact run-specific bundle
-root. Do not scan the output root for its newest directory, guess a run ID, or
-construct a bundle path. Resolve `index_file` beneath `output_directory` and
-reject an absolute logical path or any result that escapes the bundle root.
-
-The complete configuration uses the application validation defaults. A caller
-that requires fully validated D&D artifacts must also require receipt
-`validation_status: approved`; a successful `incomplete` result reflects the
-configured validator-failure continuation policy and carries its bounded
-validator provenance in `validation_summaries`.
-
-Read `index.json` and locate each requested lane in `output_files` by its exact
-`lane_id`. Do not guess a lane filename. Before decoding a payload:
-
-1. resolve its descriptor's relative `file` beneath the bundle root with the
-   same confinement check;
-2. verify the descriptor's media type and schema identity against the linked
-   artifact contract; and
-3. decode the payload according to that contract.
-
-The [published JSON output contract](../integrations/json-output.md) defines
-the index and bundle layout. Treat all paths obtained from a decoded external
-document as untrusted until confined to their documented root.
-
-## Complete Artifact Inventory
-
-When every configured lane is accepted, the complete example publishes these
-lane artifacts:
-
-| Lane ID | Purpose | Canonical contract |
-| --- | --- | --- |
-| `item-registry` | Canonical registry of encountered items and currency. | [Item registry](../integrations/dnd-item-registry-artifacts.md) |
-| `npc-registry` | Canonical registry of named NPCs. | [NPC registry](../integrations/dnd-npc-registry-artifacts.md) |
-| `location-registry` | Canonical registry of named locations. | [Location registry](../integrations/dnd-location-registry-artifacts.md) |
-| `scene-descriptions` | Classification, title, and summary for each scene. | [Scene descriptions](../integrations/dnd-scene-description-artifacts.md) |
-| `item-occurrences` | Source-grounded item discovery, acquisition, use, transfer, and loss events. | [Item occurrences](../integrations/dnd-item-occurrence-artifacts.md) |
-| `spells` | Source-grounded spell casts and casters. | [Spell casts](../integrations/dnd-spell-artifacts.md) |
-| `combat-turns` | Source-grounded combat turn participation. | [Combat turns](../integrations/dnd-combat-turn-artifacts.md) |
-| `npc-occurrences` | Source-grounded NPC interaction occurrences. | [NPC occurrences](../integrations/dnd-npc-occurrence-artifacts.md) |
-| `location-occurrences` | Source-grounded location occurrences. | [Location occurrences](../integrations/dnd-location-occurrence-artifacts.md) |
-| `enemy-events` | Source-grounded enemy combat events. | [Enemy events](../integrations/dnd-enemy-event-artifacts.md) |
-
-The JSON encoder always publishes these bundle-management files:
-
-| File | Purpose |
-| --- | --- |
-| `index.json` | Discovery document for lane and pipeline-wide artifacts. |
-| `manifest.json` | Run provenance and result summaries. |
-| `rejected.json` | Rejected pipeline outputs. |
-| `warnings.json` | Actionable process-degradation warnings. |
-| `diagnostics.json` | Advisory and observation findings for accepted artifacts. |
-
-The complete configuration also requests two pipeline-wide artifacts:
-
-- [`chunk-map.json`](../integrations/chunk-map.md), the accepted chunk plan and
-  chunk metadata; and
-- [`evidence-context.json`](../integrations/evidence-context.md), a reading
-  excerpt containing the union of selected cited source units and the
-  configured surrounding window.
-
-Discover both from their top-level `index.json` descriptors rather than
-treating them as lanes. Evidence context is convenient reading material, not
-authoritative provenance; citations in the normalized lane payloads remain the
-evidence contract.
-
-Every optional or lane file is published only when its corresponding artifact
-is available. A successful process does not guarantee that all configured
-lanes were accepted.
-
-## Decide What Counts As Consumer Success
-
-Exit status 0 means Notarius completed the pipeline and published its result
-bundle. The receipt or bundle may still report warnings, rejected outputs, or
-missing lane descriptors. A downstream consumer must define its own required
-artifact set explicitly.
-
-A caller that claims to consume the complete D&D workflow should normally
-require all ten lane IDs in the table and verify each descriptor's expected
-contract. If any required lane is missing, rejected, or incompatible, fail the
-caller's extraction step while retaining the Notarius bundle for diagnosis. A
-consumer that needs only a subset may define and document a narrower policy.
-
-Keep the successful receipt with the complete published bundle. Retain
-`manifest.json`, `rejected.json`, `warnings.json`, and captured process logs as
-required by the caller's provenance, diagnosis, and retention policies. Avoid
-selectively copying payload files without also preserving enough index and
-manifest information to identify their originating run and contracts.
-
-The transcript, lane artifacts, evidence context, manifest, debug data, and
-logs can all contain private campaign information. Apply the same access,
-publication, and retention controls used for the source transcript.
-
-## Consumer Checklist
-
-- Validate the deployed Notarius configuration and `dnd-session` pipeline.
-- Pass the final trimmed Seriatim JSON transcript with stable segment IDs.
-- Use absolute configuration, input, output-root, profile, and reference paths
-  in service deployments.
-- Capture stdout and stderr separately and enforce cancellation and timeout.
-- Parse stdout only after exit status 0.
-- Accept only supported receipt, index, and artifact schema versions while
-  tolerating permitted unknown fields.
-- Use the receipt's `output_directory`; never guess the run directory.
-- Confine `index_file` and every descriptor path to the published bundle root.
-- Discover lanes by `lane_id` and verify descriptor compatibility before
-  decoding payloads.
-- Enforce an explicit required-lane policy and inspect rejections and warnings.
-- Preserve the receipt and sufficient bundle provenance for every retained
-  artifact.
-- Protect all transcript-derived files and diagnostic streams as sensitive
-  campaign data.

docs/consumers/subprocess.md

@@ -6,21 +6,14 @@ statuses, while the [run-result receipt](../integrations/run-result.md) and
 [Published JSON Output contract](../integrations/json-output.md) own the
 durable result formats.
 
-For the maintained complete D&D workflow, including its transcript input,
-configured lane inventory, and downstream acceptance checklist, see
-[Consuming The Complete D&D Pipeline](dnd-pipeline.md).
-
 ## Run And Check The Process
 
 Optionally preflight a selected configuration and pipeline before work starts:
 
 ```sh
-notarius config validate --config /path/to/notarius.yml --config-overlay production --pipeline pipeline-id
+notarius config validate --config /path/to/notarius.yml --pipeline pipeline-id
 ```
 
-Omit `--config-overlay` when the composed base configuration is the intended
-selection; it is independent from any `--llm-profile` run override.
-
 Invoke the run with explicit paths and machine-readable output. Capture
 standard output and standard error separately; do not combine them before
 processing the result.
@@ -28,43 +21,16 @@ processing the result.
 ```sh
 notarius run pipeline-id \
   --config /path/to/notarius.yml \
-  --config-overlay production \
   --input /path/to/source.json \
   --output-dir /path/to/output-root \
   --json
 ```
 
 Use absolute paths for supplied input, configuration, output-root, and
-reference files. Pass each external reference as its own argument-vector pair;
+reference files. When a stable prompt session identifier or references are
-do not construct and invoke a shell command. An unqualified reference selector
+needed, pass the supported CLI flags. Supply credentials through Notarius's
-supplies that file to every compatible selected target. Lane and stage
+documented configuration and environment mechanisms, never as command-line
-qualification are available for exceptional overrides, while generated
+arguments or generated secret-bearing configuration.
-same-run references remain part of configured pipeline composition. The
-[CLI reference](../cli.md#reference-selectors) owns the exact selector and
-precedence contract.
-
-The maintained D&D subprocess workflow uses this facility for campaign context:
-
-```sh
-notarius run dnd-session \
-  --config /absolute/path/to/notarius.yml \
-  --input /absolute/path/to/transcripts/final.trimmed.json \
-  --output-dir /absolute/path/to/notarius-output \
-  --reference party=/absolute/path/to/references/party.txt \
-  --reference players=/absolute/path/to/references/players.txt \
-  --reference glossary=/absolute/path/to/references/glossary.txt \
-  --reference spell_catalog=/absolute/path/to/references/spells.json \
-  --json
-```
-
-Only pass the external references available to and desired by the deployment.
-Notarius generates a stable prompt session for the resolved input module and
-exact input bytes; reference changes do not change it. Pass **--session-id**
-only when intentionally grouping different invocations under a different
-session. Supply credentials through Notarius's documented configuration and
-environment mechanisms, never as command-line arguments or generated
-secret-bearing configuration. In particular, a session identifier is
-provider-visible and is not a credential mechanism.
 
 Wait for the process before interpreting standard output. Only an exit status
 of 0 permits decoding the receipt. On a nonzero exit, retain standard error for
@@ -86,30 +52,23 @@ contract. The JSON bundle contract links to the available lane contracts.
 If `index.json` has an `evidence_context` descriptor, treat it as a
 pipeline-wide artifact rather than a lane entry. Verify its six descriptor
 fields before decoding the linked file according to the [Published Evidence
-Context contract](../integrations/evidence-context.md). Decode its top-level
+Context contract](../integrations/evidence-context.md). Use each
-source-unit array as a reading excerpt. Obtain authoritative citations and lane
+`evidence_refs` entry as the citation to source material. Its surrounding
-provenance from the normalized lane artifacts; the excerpt has neither and its
+context range and included units explain the citation, but do not widen or
-nearby units do not widen a lane artifact's cited source reference.
+replace the cited source reference.
 
 A zero exit status may still report rejected outputs, warnings, or absent
 lanes. The caller decides which lane IDs are required for its own work and
 which are optional; it should make that decision explicitly rather than infer
 failure from the receipt counts alone.
 
-When complete validation is required, also require receipt
-`validation_status: approved` and inspect `validation_summaries`. A successful
-run with `validation_status: incomplete` contains a structurally valid result
-that advanced after validator execution could not complete under the configured
-`warn_continue` policy. It is not reusable checkpoint state and should not be
-silently treated as fully reviewed by the caller.
-
 ## Preserve Provenance And Handle Data Carefully
 
 Keep the receipt with the published `manifest.json`, and retain
-`rejected.json`, `warnings.json`, and `diagnostics.json` when review or later provenance requires
+`rejected.json` and `warnings.json` when review or later provenance requires
 them. Treat the input, output bundle, cache, debug bundle, and captured process
 logs as potentially sensitive data. Apply the caller's access controls and
 retention policy, and avoid copying secrets into arguments, logs, or
 provenance records. An evidence-context artifact contains source-unit text and
-metadata and can cover most of an input; preserve and share it only when that
+metadata, and selected lanes can cover most of an input; preserve and share it
-source content is authorized for the recipient.
+only when that source content is authorized for the recipient.

docs/development.md

@@ -9,9 +9,6 @@ the [README](../README.md) for product context, [Architecture](policy/architectu
 for system boundaries, and [Internal Overview](internal/overview.md) for the
 implemented component map.
 
-Read [Agent Policy](policy/agents.md) before recommending, planning, or
-implementing changes. It owns implementation discipline and local commit rules.
-
 ## What To Read
 
 | When working on | Read | Why |
@@ -21,14 +18,13 @@ implementing changes. It owns implementation discipline and local commit rules.
 | Any documentation addition or revision | [Documentation Policy](policy/documentation.md) | It defines canonical homes, audiences, current-behavior rules, and maintenance requirements. |
 | Adding, changing, reviewing, or deleting tests | [Testing Policy](policy/testing.md) | It defines risk-based sufficiency, durable test boundaries, test-double guidance, and criteria for retaining tests. |
 | CLI composition or command behavior | [CLI Internals](internal/cli.md) and [CLI Reference](cli.md) | The internal guide owns composition and command flow; the reference owns public syntax. |
-| Building a subprocess caller or changing its result protocol | [Subprocess Consumer Guide](consumers/subprocess.md), [Complete D&D Consumer Guide](consumers/dnd-pipeline.md), [Run Result Receipt](integrations/run-result.md), and [CLI Internals](internal/cli.md) | These separate generic caller workflow, the complete D&D workflow, the durable receipt contract, and CLI implementation behavior. |
+| Building a subprocess caller or changing its result protocol | [Subprocess Consumer Guide](consumers/subprocess.md), [Run Result Receipt](integrations/run-result.md), and [CLI Internals](internal/cli.md) | These separate caller workflow, durable receipt contract, and CLI implementation behavior. |
 | Configuration loading, resolution, or user-visible configuration behavior | [Configuration Internals](internal/configuration.md) and [Configuration](config.md) | The internal guide owns loading and resolution mechanics; the reference owns the configuration contract. |
 | Pipeline resolution or execution | [Pipeline Internals](internal/pipeline.md) | It documents profiles, references, validation, retries, checkpoints, and runner behavior. |
 | Production modules or validators | [Module Internals](internal/modules.md), [D&D Module Internals](internal/dnd.md), and [D&D integration contracts](integrations/) | The generic guide owns extension mechanics, the D&D guide owns shared family conventions, and the contracts own durable output shapes. |
-| LLM clients, prompts, schemas, profiles, or scheduling | [LLM Runtime](internal/llm.md) | It documents the transport boundary and PromptKit integration. |
+| LLM clients, prompts, schemas, profiles, or scheduling | [LLM Runtime](internal/llm.md) | It documents the transport boundary and Scriptorium integration. |
 | Output, cache, resume, or debug artifacts | [Run State Internals](internal/state.md), [Operations](operations.md), and [Configuration](config.md) | These separate implementation details, operator behavior, and configuration contracts. |
 | External input formats, artifact schemas, or durable output files | [Integration Contracts](integrations/) | Integration documents define external and durable data contracts. |
-| Release preparation, tagging, publication, or optional diagnostics | [Release Policy](policy/release.md) and [Source Releases](release.md) | Policy owns release requirements and completion; the runbook supplies the publication command and recovery procedure. |
 | Proposed or unimplemented behavior | [Roadmap](roadmap/) | Future work belongs only in roadmap documentation until implemented. |
 
 For an existing subsystem, also inspect its focused tests and the package-local

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 registry artifact](dnd-npc-registry-artifacts.md) can ground an
+An optional normalized [NPC artifact](dnd-npc-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
@@ -63,9 +63,7 @@ chronology; and collapses only duplicates with the same actor identity, turn
 kind, and complete valid evidence. It does not infer turns, initiative, or
 actions from registry or scene data.
 
-The [NPC-occurrence artifact](dnd-npc-occurrence-artifacts.md) records
+The [NPC-interaction artifact](dnd-npc-interaction-artifacts.md) records
-broader NPC occurrences. The [enemy-event artifact](dnd-enemy-event-artifacts.md)
+broader NPC occurrences. The [JSON output contract](json-output.md) defines
-uses combat turns as grounding only; turns do not establish an enemy event or
+publication, and [D&D module internals](../internal/dnd.md) describes routing
-its outcome. The [JSON output contract](json-output.md) defines publication,
+and validation mechanics.
-and [D&D module internals](../internal/dnd.md) describes routing and validation
-mechanics.

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

@@ -1,114 +0,0 @@
-# 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

@@ -0,0 +1,78 @@
+# 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

@@ -1,72 +0,0 @@
-# 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

@@ -1,95 +0,0 @@
-# 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

@@ -1,86 +0,0 @@
-# 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

@@ -1,93 +0,0 @@
-# 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

@@ -0,0 +1,69 @@
+# 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-interaction-artifacts.md

@@ -1,7 +1,7 @@
-# D&D NPC Occurrence Artifact
+# D&D NPC Interaction Artifact
 
 This contract defines the durable occurrence list produced by
-`dnd/npc-occurrences`. It records discrete, source-grounded occurrences with
+`dnd/npc-interactions`. It records discrete, source-grounded interactions with
 NPCs already present in a normalized registry; it does not extend that registry
 or summarize the session.
 
@@ -9,37 +9,35 @@ or summarize the session.
 
 | Property | Value |
 | --- | --- |
-| Artifact kind | `dnd/npc-occurrence-list` |
+| Artifact kind | `dnd/npc-interaction-list` |
-| Schema ID | `notarius.dnd.npc_occurrences` |
+| Schema ID | `notarius.dnd.npc_interactions` |
-| Schema name | `notarius_dnd_npc_occurrences_v1` |
+| Schema name | `notarius_dnd_npc_interactions_v1` |
 | Schema version | `v1` |
 | Media type | `application/json` |
 
-`v1` is a strict JSON object with required `occurrences`; the array may be
+`v1` is a strict JSON object with required `interactions`; the array may be
-empty. Occurrence and source-reference objects reject unknown fields. An
+empty. Interaction and source-reference objects reject unknown fields. An
 incompatible shape change requires a new schema version.
 
 ## Wire shape
 
-Each occurrence has these required fields:
+Each interaction 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 occurrence categories below. |
+| `kind` | One of the interaction 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 occurrence is confined to its accepted chunk.
+for an interaction is confined to its accepted chunk.
 
 ```json
 {
-  "occurrences": [
+  "interactions": [
     {
-      "npc_id": "npc:sha256:example",
       "name": "Mira Thorn",
       "kind": "dialogue",
       "source_refs": [
@@ -50,7 +48,7 @@ for an occurrence is confined to its accepted chunk.
 }
 ```
 
-## Occurrence categories
+## Interaction categories
 
 | Kind | Meaning |
 | --- | --- |
@@ -67,24 +65,14 @@ for uncertain classification.
 
 ## Identity, evidence, and order
 
-The required normalized [NPC registry artifact](dnd-npc-registry-artifacts.md)
+The required normalized [NPC artifact](dnd-npc-artifacts.md) resolves `name`.
-supplies names-only contextual grounding to the model. Notarius resolves the
+Registry references are provenance only and never replace an interaction's own
-selected name and writes the exact `{npc_id, name}` pair. An unknown or
+evidence. Normalization canonicalizes recognized registry names, orders and
-ambiguous selection rejects the complete model result; normalization does not
+deduplicates exact source references, then orders interactions by valid source
-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 NPC ID, canonical name, kind, and complete valid evidence
+Only entries with the same canonical name, kind, and complete valid evidence
 sequence are collapsed; distinct categories or evidence remain separate.
 
 See the [combat-turn artifact](dnd-combat-turn-artifacts.md) for combat-action
-occurrences. The [enemy-event artifact](dnd-enemy-event-artifacts.md) consumes
+occurrences and the [JSON output contract](json-output.md) for publication.
-only `combat_opponent` occurrences as grounding; they never establish an enemy
+Pipeline mechanics are described in [D&D module internals](../internal/dnd.md).
-event or outcome. The [JSON output contract](json-output.md) defines
-publication. Pipeline mechanics are described in
-[D&D module internals](../internal/dnd.md).

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

@@ -1,92 +0,0 @@
-# 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

@@ -62,9 +62,8 @@ 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) and
+The [combat-turn artifact](dnd-combat-turn-artifacts.md) uses an exact matching
-[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 their evidence. Publication is defined by the
+reference never become combat 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 registry artifact](dnd-npc-registry-artifacts.md) can ground a
+The optional normalized [NPC artifact](dnd-npc-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

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

docs/integrations/evidence-context.md

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

docs/integrations/json-output.md

@@ -9,7 +9,7 @@ Output configuration, including chunk-map and evidence-context publication, belo
 ## Bundle Layout
 
 All paths below are logical, relative, slash-separated bundle paths. The
-encoder always emits the first five JSON files below and adds lane or
+encoder always emits the first four JSON files below and adds lane or
 pipeline-wide artifact files when their corresponding artifacts are available:
 
 A subprocess caller first obtains the physical bundle root from the
@@ -21,11 +21,10 @@ root for the logical discovery described here.
 | `index.json` | Entry point that names the other published files and lane payloads. |
 | `manifest.json` | Run provenance and result summaries. |
 | `rejected.json` | Rejected pipeline outputs. |
-| `warnings.json` | Actionable process-degradation warnings. |
+| `warnings.json` | Accepted-output and run warnings. |
-| `diagnostics.json` | Accepted-artifact quality advisories and normalization observations. |
 | `lanes/<safe-lane-id>.json` | One normalized artifact payload for each lane. |
 | `chunk-map.json` | Optional accepted chunk map, when its export is enabled and available. |
-| `evidence-context.json` | Optional selected source-unit excerpt, when evidence publication is enabled. |
+| `evidence-context.json` | Optional source-context artifact, when evidence publication is enabled. |
 
 JSON files are pretty-printed with a trailing newline. Lane payloads are
 accepted only when their media type is `application/json`.
@@ -40,8 +39,7 @@ normalized lanes has this valid minimal index:
   "manifest_file": "manifest.json",
   "output_files": [],
   "rejected_file": "rejected.json",
-  "warnings_file": "warnings.json",
+  "warnings_file": "warnings.json"
-  "diagnostics_file": "diagnostics.json"
 }
 ```
 
@@ -51,7 +49,6 @@ normalized lanes has this valid minimal index:
 | `output_files` | Yes | Lane descriptors sorted by `lane_id`. |
 | `rejected_file` | Yes | Always `rejected.json`. |
 | `warnings_file` | Yes | Always `warnings.json`. |
-| `diagnostics_file` | Yes | Always `diagnostics.json`. |
 | `chunk_map` | No | Descriptor for the pipeline-wide `chunk-map.json`; never a lane descriptor. |
 | `evidence_context` | No | Descriptor for the pipeline-wide `evidence-context.json`; never a lane descriptor. |
 
@@ -74,15 +71,11 @@ 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), [NPC registry](dnd-npc-registry-artifacts.md),
+[spells](dnd-spell-artifacts.md), [NPCs](dnd-npc-artifacts.md),
-[NPC occurrences](dnd-npc-occurrence-artifacts.md),
+[NPC interactions](dnd-npc-interaction-artifacts.md),
 [combat turns](dnd-combat-turn-artifacts.md),
-[item registry](dnd-item-registry-artifacts.md),
+[item events](dnd-item-event-artifacts.md), and
-[item occurrences](dnd-item-occurrence-artifacts.md),
+[scene descriptions](dnd-scene-description-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`
 
@@ -95,7 +88,7 @@ group into the following externally observable summaries:
 | Run identity and result | `run_id`, `pipeline_id`, `pipeline_digest`, `schema_version`, `validation_status`, `started_at`, `completed_at` |
 | Resolved components | `input_module`, `chunker`, `extractors`, `merger`, `normalizer`, `output_encoder`, `artifact_lanes`, `validator_chains`, `module_metadata` |
 | Source and references | `source_digests`, `references` |
-| Published result summaries | `normalized_outputs`, `rejected_outputs`, `validation_summaries` |
+| Published result summaries | `normalized_outputs`, `rejected_outputs` |
 | Execution summaries | `chunk_plan`, `checkpoint_decisions`, `llm_profiles`, `metadata` |
 
 `references` records provenance such as the target, slot, origin, digest,
@@ -105,87 +98,16 @@ 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.
 
-Each `validation_summaries` entry is a bounded outcome for one producer result.
+## Rejections And Warnings
-It has required `status`, `producer_attempt_count`, and `terminal_action`;
-the stage and affected step, lane, module, or chunk identity are present when
-applicable. `status` is `complete`, `rejected`, or `incomplete`.
-`rejecting_validators`, `reason_codes`, and `incomplete_validators` preserve
-configured validator order and omit later duplicates. Entries contain no raw
-candidate response, correction guidance, validator diagnostic message, or
-artifact payload. The same shape may appear as `validation` on an affected
-rejection entry.
-
-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:
-
-| Field | Required | Meaning |
-| --- | --- | --- |
-| `id` | Yes | Selected PromptKit profile identifier. |
-| `provider` | No | Notarius adapter provider identifier. |
-| `model` | No | Effective provider model identifier. |
-| `backend_id` | No | Effective PromptKit backend registration identifier. Endpoint-only profiles omit it. |
-| `reasoning_effort` | No | Effective opaque provider reasoning setting. An empty or explicitly cleared setting is omitted. |
-
-These values describe observed execution; they are not a backend-registration
-interface. Entries that differ by backend or effective reasoning remain
-distinct even when their profile, provider, and model are otherwise equal.
-
-## Rejections, Warnings, And Diagnostics
 
 `rejected.json` is always an object with a `rejected` array. Each entry has
 required `stage` and `message`; `step_id`, `lane_id`, `module_key`, `chunk_id`,
 `chunk_index`, `validator_name`, `reason_code`, `attempt_count`, and
-`diagnostic_artifact_path` are present only when applicable. An entry may also
+`diagnostic_artifact_path` are present only when applicable.
-contain the bounded `validation` summary described above; the existing singular
-validator and reason fields remain the first configured rejection for
-compatibility.
 
-`warnings.json` is always the `notarius.warnings.v2` envelope:
+`warnings.json` is always an object with a `warnings` array. Each warning has
-
+`reason_code` and `message`; `scope` is optional. Both arrays are empty when
-```json
+there is nothing to report.
-{
-  "schema_version": "notarius.warnings.v2",
-  "group_count": 0,
-  "occurrence_count": 0,
-  "groups": []
-}
-```
-
-It contains only process warnings. `group_count` is exact, and
-`occurrence_count` is the exact sum of its group occurrence counts.
-
-`diagnostics.json` is always the `notarius.diagnostics.v1` envelope:
-
-```json
-{
-  "schema_version": "notarius.diagnostics.v1",
-  "group_count": 0,
-  "occurrence_count": 0,
-  "truncated": false,
-  "unrepresented_occurrence_count": 0,
-  "groups": []
-}
-```
-
-It contains only advisory and observation groups. `group_count` counts groups
-represented in `groups`; `occurrence_count` includes both represented and
-unrepresented occurrences. When `truncated` is true,
-`unrepresented_occurrence_count` is the exact number omitted from group
-representation.
-
-Each group has `disposition`, `category`, `reason_code`, framework-owned
-`origin`, exact `occurrence_count`, bounded `samples`, and
-`omitted_sample_count`. Samples carry safe `scope` and `message`, plus a chunk
-ID and zero-based chunk index when applicable. A group retains at most three
-distinct samples. The framework fails rather than truncating actionable
-warnings beyond 128 groups; it represents at most 256 advisory/observation
-groups and records further occurrences through the diagnostic truncation
-fields above.
 
 ## Compatibility
 

docs/integrations/pkg-configkit.md

@@ -1,13 +0,0 @@
-# ConfigKit Integration
-
-Notarius uses the public root package
-[`gitea.maximumdirect.net/eric/ConfigKit`](https://gitea.maximumdirect.net/eric/ConfigKit)
-at v0.4.0 for version 5 configuration acquisition, imports, overlays, explicit
-overrides, diagnostics, and safe inspection rendering.
-
-Notarius owns the typed document, domain defaults and validation, runtime
-conversion, catalog-dependent pipeline resolution, source-aware configured
-paths, and command discovery. It uses only ConfigKit's public path, result,
-diagnostic, and resolution-source APIs. Upstream documentation owns general
-ConfigKit semantics; [Configuration](../config.md) owns Notarius's file and
-operator contract.

docs/integrations/pkg-promptkit.md

@@ -1,178 +0,0 @@
-# PromptKit Integration
-
-Notarius pins
-[`gitea.maximumdirect.net/eric/promptkit` v0.11.0](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.11.0)
-as its in-process prompt engine. The upstream
-[Go package consumer guide](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.11.0/docs/consumers/pkg-promptkit.md)
-owns the public engine API, and the upstream
-[format reference](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.11.0/docs/formats.md)
-owns prompt, profile, and schema file contracts.
-
-## Supported Boundary
-
-Notarius relies on the root `promptkit` package to:
-
-- construct an `Engine` with filesystem-backed prompt, schema, and optional
-  operator and application-fallback profile sources;
-- prepare one frozen execution from a `RunRequest` with named inline artifacts,
-  variables, a direct session ID, prompt identity, profile selection, and
-  optional appended rendered messages, then
-  record credential-redacted details and run that exact execution;
-- return rendered debug material, validated structured output, selected
-  profile, backend, effective model metadata, and token usage;
-- register the optional conventional `local` backend through `BackendLocal`,
-  `LocalBackend`, and `WithBackend`;
-- distinguish structured-output validation failure from execution failure; and
-- identify a missing explicit profile through `ErrProfileNotFound` and backend
-  admission exhaustion through `ErrCapacityExceeded`.
-
-The pinned
-[`BackendLocal`, `LocalBackend`, and `WithBackend` API](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.11.0/backends.go)
-owns the registration and backend-capacity contract.
-
-For one completion, the adapter calls `PrepareExecution`, takes a
-caller-owned `Details` snapshot, and calls `RunPrepared` for that same opaque
-prepared execution. It defers `Discard` for every unexecuted handle. Explicit
-profile preflight uses `Engine.InspectProfile`; it does not prepare a synthetic
-prompt. PromptKit's prepared handle, inspection result, and capacity-error
-types stay inside the Notarius LLM adapter.
-
-When a PromptKit profile and runtime override leave `temperature`, `max_tokens`,
-or `top_p` unset, Notarius leaves that control unset as well. Compatible
-providers therefore apply their own defaults; an operator that requires a
-specific sampling value must select it explicitly in the profile or runtime
-override.
-
-Notarius does not use PromptKit's optional `ArtifactReader`. It materializes
-source and reference content itself and supplies owned inline artifacts at the
-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 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. The generated identifier is 76 ASCII characters, within
-PromptKit'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
-backend ID. Debug prompt material also retains the selected backend ID and
-PromptKit's stable lower-case `effective_model_params` JSON, which may include
-`backend_id`. Notarius production configuration exposes one optional
-conventional `local` registration. It does not expose a general user-defined
-PromptKit backend registry. Endpoint-only profiles remain supported unchanged.
-
-Notarius retains its application-wide scheduled client around the PromptKit
-adapter. PromptKit may apply a narrower limit for the selected backend;
-endpoint-only profiles have no such backend limit. The adapter translates
-PromptKit capacity rejection into the provider-neutral Notarius
-`ErrLLMCapacityExceeded` contract. It may include the normalized selected
-backend ID in safe diagnostic context, without exposing PromptKit's capacity
-error type. PromptKit's built-in client retries eligible transient HTTP failures
-with its v0.11.0 default of two additional attempts per generation; Notarius
-keeps pipeline-stage retries outside that completion boundary.
-
-The adapter projects built-in generation failures as the application-owned
-`LLMGenerationError`, retaining a safe failure kind, HTTP status when present,
-and retry-exhaustion attempt count. Transport, malformed successful envelopes,
-provider statuses, and generic generation failures remain distinct without
-exposing PromptKit error values to Notarius callers.
-
-## Profile Sources And Compatibility
-
-Notarius gives PromptKit the configured operator profile source, registered
-application fallback profile assets, and optional backend registration through
-the same construction path for inspection and execution. PromptKit owns the
-resulting source precedence and strict profile parsing: a matching operator
-profile is a complete replacement for a fallback or built-in profile, while an
-invalid matching document fails instead of falling through. The operator
-configuration and deployment workflow are defined in
-[Configuration](../config.md#promptkit-profiles) and
-[Operations](../operations.md#promptkit-profile-deployment).
-
-PromptKit owns `base_profile` resolution under its
-[pinned format rules](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.11.0/docs/formats.md).
-Notarius records the selected leaf identity and resolved target without parsing
-or merging inheritance. An unset filesystem `api_key_env` is optional and may
-reach the provider without authorization, which can result in a 401 or 403.
-
-PromptKit accepts only the `developer`, `system`, `user`, and
-`assistant` text-chat roles after normalizing case and surrounding whitespace.
-Maintained Notarius prompt definitions use only `system` and `user`.
-
-For application-owned semantic correction, Notarius uses PromptKit's
-`RunRequest.AppendedMessages` after the ordinary rendered prompt. It supplies
-exactly two messages in order: the latest validated producer response with
-role `assistant`, then deterministic validation guidance with role `user`.
-It never exposes a general caller-selected role API, accumulates earlier
-correction turns, or changes the ordinary prompt prefix. Ordinary requests
-leave appended messages unset.
-
-PromptKit preserves supplied content but does not own Notarius's correction
-bounds. Notarius rejects invalid UTF-8, blank, or oversized assistant material
-(at most 1 MiB), guidance (at most 64 KiB), and combined content (at most
-1,114,112 bytes) before preparing the request. The transport-neutral
-application contract owns defensive copying and these limits. Default request
-and terminal summaries retain only safe counts, digests, identities, and usage;
-complete appended messages remain limited to the explicitly requested detailed
-debug trace.
-
-PromptKit obtains its maintained OpenRouter and Rakestrawhome backend and
-profile catalogs from independently versioned transitive modules. Notarius
-does not import or register either catalog; PromptKit retains catalog source,
-identity, precedence, credential, and capacity ownership.
-
-External catalog profile names and settings can change between dependency
-releases, including removal without aliases. Review directly selected IDs and
-inherited `base_profile` values when upgrading. An application-owned alias that
-inherits an external profile does not freeze that profile's settings.
-PromptKit's opt-in `promptkit-openrouter-standard` and
-`promptkit-openrouter-auto` names provide name continuity within its
-selected-and-tested dependency scope, not a fixed model or provider availability
-guarantee. See the upstream
-[catalog compatibility policy](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.11.0/docs/policy/release.md#catalog-profile-compatibility).
-
-Use a complete operator-owned profile with explicit backend or endpoint, model,
-and settings when those choices must remain operator-controlled. The embedded
-`dnd-extraction` fallback already follows this model and does not inherit an
-external catalog profile. An upgrade updates Notarius's compiled-in catalog
-checkpoint identity so prior profile-source checkpoints are not reused.
-
-Notarius supports this boundary against PromptKit v0.11.0. Its fallback source,
-prepared-execution, inspection, and typed capacity APIs are used as public
-upstream contracts; other PromptKit APIs or file-format behavior are not
-implicitly supported. A dependency upgrade requires reviewing the adapter,
-profile-source construction, and this compatibility statement against the
-pinned upstream documentation.
-
-## Notarius Ownership
-
-[LLM Runtime Internals](../internal/llm.md) describes how Notarius mounts
-module assets, maps its transport-neutral completion contract, prepares and
-executes requests, validates output, records provenance, captures debug
-material, redacts errors, and preserves timeout ownership.
-
-PromptKit provider error details do not cross the ordinary completion boundary.
-Notarius exposes a provider-neutral generation category and optional status;
-redacted provider details are retained only in requested debug material.
-[D&D Module Internals](../internal/dnd.md) owns the embedded
-`dnd-extraction` fallback profile and the maintained D&D prompt defaults.
-[Configuration](../config.md#promptkit-profiles) defines how a Notarius
-configuration selects one PromptKit profile source and optionally registers
-the conventional local backend.
-
-PromptKit API or format changes outside this boundary are not implicitly
-supported. Updating the pinned version requires reviewing the adapter and
-profile/configuration contracts against the upstream documentation. Maintained
-production prompts use PromptKit's bounded structural-repair contract; their
-current declaration is one additional repair attempt. Notarius retains the
-transport-neutral boundary and does not expose PromptKit types to modules.
-
-PromptKit v0.11.0 is licensed under
-[LGPL-3.0-or-later](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.11.0/LICENSE).
-Its accompanying [GPLv3 notice](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.11.0/COPYING)
-is incorporated by that license. This dependency change does not alter
-Notarius's source license or distribution workflow.

docs/integrations/run-result.md

@@ -9,58 +9,36 @@ Command syntax, streams, and exit statuses are defined in the
 
 ## Schema
 
-The current schema version is `notarius.run-result.v2`.
+The current schema version is `notarius.run-result.v1`.
 
 | Field | Required | Meaning |
 | --- | --- | --- |
-| `schema_version` | Yes | Exactly `notarius.run-result.v2`. |
+| `schema_version` | Yes | Exactly `notarius.run-result.v1`. |
 | `run_id` | Yes | The finalized Notarius run identifier. |
 | `pipeline_id` | Yes | The effective pipeline identifier. |
 | `output_directory` | Yes | Absolute path to the published, run-specific output bundle. |
 | `index_file` | For the production JSON output | Logical path `index.json`; omitted for other output modules. |
 | `normalized_output_count` | Yes | Number of final normalized outputs. |
 | `rejected_output_count` | Yes | Number of recorded rejected outputs. |
-| `warning_group_count` | Yes | Exact number of actionable warning groups. |
+| `warning_count` | Yes | Number of final run warnings. |
-| `warning_occurrence_count` | Yes | Exact occurrences represented by actionable warning groups. |
-| `diagnostic_group_count` | Yes | Number of represented advisory and observation groups. |
-| `diagnostic_occurrence_count` | Yes | Advisory and observation occurrences, including unrepresented occurrences. |
-| `diagnostics_truncated` | Yes | Whether advisory/observation group representation was truncated. |
 | `validation_status` | Yes | The final run manifest validation status. |
-| `validation_summaries` | No | Bounded per-producer validation outcomes; present when producer work ran. |
 | `debug_directory` | No | Absolute path to the run-specific debug bundle when requested debug capture completed. |
 
 For the production `json` output module, `index_file` is present only when the
 completed run returned exactly one logical output file named `index.json`.
 For another output module, its absence does not indicate a failed run.
-`validation_status` is `approved`, `rejected`, or `incomplete`; `incomplete`
-means one or more otherwise accepted results advanced under validator-failure
-`warn_continue`.
 
 ```json
 {
-  "schema_version": "notarius.run-result.v2",
+  "schema_version": "notarius.run-result.v1",
   "run_id": "run-1770000000000000000-0123456789abcdef0123456789abcdef",
   "pipeline_id": "dnd-session",
   "output_directory": "/work/results/run-1770000000000000000-0123456789abcdef0123456789abcdef",
   "index_file": "index.json",
   "normalized_output_count": 6,
   "rejected_output_count": 2,
-  "warning_group_count": 1,
+  "warning_count": 1,
-  "warning_occurrence_count": 2,
+  "validation_status": "rejected"
-  "diagnostic_group_count": 3,
-  "diagnostic_occurrence_count": 5,
-  "diagnostics_truncated": false,
-  "validation_status": "incomplete",
-  "validation_summaries": [
-    {
-      "stage": "extract",
-      "lane_id": "spells",
-      "status": "incomplete",
-      "incomplete_validators": ["dnd/spells/source_refs"],
-      "producer_attempt_count": 1,
-      "terminal_action": "warn_continue"
-    }
-  ]
 }
 ```
 
@@ -70,11 +48,8 @@ means one or more otherwise accepted results advanced under validator-failure
 paths. They identify the paths used by Notarius and do not resolve symlinks.
 `output_directory` is the run-specific bundle, not the configured output root.
 
-The receipt is a summary and discovery document. Its optional validation
+The receipt is a summary and discovery document. It does not contain lane
-summaries contain only stable status, identity, validator names, reason codes,
+descriptors, payloads, manifest data, rejections, warnings, or file contents.
-attempt counts, and terminal actions. It does not contain lane descriptors,
-payloads, manifest payloads, rejection messages, warnings, raw model responses,
-correction guidance, or file contents.
 For the production JSON output, resolve `index_file` beneath
 `output_directory`, reject path escapes, and use the
 [Published JSON Output contract](json-output.md) to discover logical files and

docs/internal/cli.md

@@ -24,34 +24,23 @@ preparation, and runner mechanics after their inputs are supplied.
 
 ## Dispatch And Configuration Handoff
 
-The root dispatcher handles help, version reporting, configuration validation,
+The root dispatcher handles help, configuration validation, pipeline listing,
-effective-configuration inspection, explanation inspection, pipeline listing,
+and a pipeline run. It normalizes injectable options before dispatch so that a
-and a pipeline run. Version reporting resolves build
+missing production dependency fails as a command error rather than reaching
-information through `internal/buildinfo` before production composition, so the
+execution.
-diagnostic remains available without configuration or runtime collaborators.
-The public syntax, streams, exit classes, and version semantics are defined by
-the [CLI reference](../cli.md). Other root commands normalize injectable
-options before dispatch so that a missing production dependency fails as a
-command error rather than reaching execution.
 
-Commands that need configuration use one shared ConfigKit-backed loader. The
+Commands that need configuration use one shared loader. The CLI discovers the
-CLI discovers the file, passes the requested overlay and only explicit
+file, parses it through **internal/core/config**, starts from defaults, applies
-configuration-valued run overrides, and receives a **LoadedConfig**. The
+the file and supported environment overrides, and then validates it for the
-configured discovery and precedence contract is in
+command. The configured discovery and precedence contract is in
 [Configuration](../config.md), while the loading and resolution mechanics are
 in [Configuration Internals](configuration.md).
 
-`config effective` and `config explain` only render the loaded ConfigKit view;
+Configuration validation without a selected pipeline checks structural
-they do not resolve pipelines or construct providers. Configuration validation without a selected pipeline checks structural
 configuration only. Validation with a selected pipeline also builds the
-effective catalog, resolves the pipeline, and verifies every explicit effective
+effective catalog, resolves the pipeline, and verifies explicitly selected
-PromptKit profile. Selected LLM-backed input, chunk, lane, output, and validator
+Scriptorium profiles. Pipeline listing validates configuration before returning
-profiles are inspected
+normalized, sorted identifiers.
-against the configured PromptKit source and backend registrations without
-loading a prompt or performing generation, so an unknown or invalid profile
-fails before pipeline preparation. Credential availability remains an
-execution-time concern. Pipeline listing validates configuration before
-returning normalized, sorted identifiers.
 
 ## Production Composition
 
@@ -62,43 +51,29 @@ catalog used for resolution and the concrete constructors used for preparation.
 Tests may provide a catalog or registries instead; production code must not
 silently merge an injected partial catalog with production registrations.
 
-The production LLM factory builds one PromptKit-backed client from the resolved
+The production LLM factory builds the Scriptorium-backed client from resolved
-**promptkit.profile_dir** or **promptkit.profile_file** source, attaches the
+configuration, creates one scheduler from the effective global LLM limit, and
-profile-provenance recorder, creates one scheduler from the effective global
+wraps the client before it reaches modules. Registration and LLM construction
-LLM limit, and wraps the client before it reaches modules. Registration and LLM
+errors are returned before a pipeline is prepared. Concrete module keys and
-construction errors are returned before a pipeline is prepared. Configuration
+validator chains are public configuration choices and remain documented in
-field definitions remain in [Configuration](../config.md#promptkit-profiles);
+[Configuration](../config.md).
-the D&D registrar's fallback profile assets and the adapter mechanics remain in
-[LLM Runtime](llm.md).
-
-The factory also accepts `LLMRuntimeOverrides`, whose reasoning pointer
-preserves inherit, replace, and clear states across the composition boundary.
-Run orchestration constructs this value from the mutually exclusive
-`--reasoning-effort` and `--clear-reasoning-effort` controls. Absence preserves
-a nil pointer, replacement is trimmed, and clear uses a non-nil empty string.
-The same override reaches the one shared production client, checkpoint
-identity, and debug invocation metadata. Persistent reasoning configuration
-remains owned by PromptKit profiles; Notarius configuration has no reasoning
-field.
 
 ## Run Orchestration
 
 After parsing and validating a run invocation, the CLI performs this ordered
 handoff:
 
-1. load and validate configuration with ConfigKit command overrides;
+1. load and validate configuration, then apply command-level operational
+   overrides;
 2. create and validate a safe run identity, then allocate a debug bundle only
    when requested;
 3. build the effective catalog, resolve requested reference changes, resolve
-   the effective pipeline, and inspect its explicit effective PromptKit
+   the effective pipeline, and verify explicit Scriptorium profiles;
-   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, and prepared modules;
+5. construct registries, the scheduled LLM client, prepared modules, and the
-6. read the source input once, resolve its effective session from the explicit
+   requested cache/checkpoint collaborators;
-   override or resolved input module and raw bytes, then construct requested
+6. read the source input and invoke the framework runner; and
-   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.
 
@@ -109,23 +84,6 @@ 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.
-
-The CLI also owns the scope grammar for reference flags. It enumerates the
-selected chunk and lane targets from registered module specifications, expands
-pipeline- and lane-scoped actions into exact stage-and-lane bindings, and
-resolves overlapping bind and unbind actions by specificity before calling
-configuration resolution. The generic pipeline therefore receives only exact
-`ReferenceBinding` and `ReferenceUnbind` values and has no knowledge of CLI
-selector syntax. Configuration resolution retains ownership of configured
-external/generated conflicts, required slots, and module compatibility; file
-materialization still occurs afterward.
-
 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
@@ -177,9 +135,8 @@ is discoverable.
 - **internal/cli/production_contract_test.go** covers registrar composition,
   production catalog contents, assets, and representative configuration
   validation.
-- **internal/cli/reference_contract_test.go** covers scoped CLI reference
+- **internal/cli/reference_contract_test.go** covers CLI reference overrides,
-  expansion, specificity, bind/unbind conflicts, generated-reference
+  origin separation, and materialization boundaries.
-  protection, origin separation, and materialization boundaries.
 - **internal/cli/state_hardening_test.go** covers safe run identity, state
   roots, and failure ordering.
 

docs/internal/configuration.md

@@ -8,17 +8,17 @@ either interface.
 
 ## Boundary
 
-The configuration package turns a selected ConfigKit-composed YAML document
+The configuration package turns a selected YAML file and supported environment
-into a validated, independently owned configuration. It then resolves a
+values into a validated, independently owned configuration. It then resolves a
 requested pipeline against a module catalog before the framework prepares or
 runs anything.
 
 | Boundary | Inputs | Outputs | Does not own |
 | --- | --- | --- | --- |
-| Loading | Selected file path, profile, overrides, and invocation directory | **LoadedConfig** with ConfigKit inspection metadata and a populated **Config** | Choosing the file path or reporting a command result. |
+| Loading | Selected file path and environment lookup | Parsed file model and a populated **Config** | Choosing the file path or reporting a command result. |
 | Validation | **Config** | Structural configuration errors with pipeline, lane, or binding context | Module availability, capabilities, or construction. |
 | Resolution | Valid **Config**, selected pipeline and lanes, runtime reference changes, LLM override, and module catalog | **EffectiveConfig** with a **ResolvedPipeline** | Materializing reference bytes, preparing modules, execution, or filesystem state. |
-| Inspection | **LoadedConfig** and an optional JSON Pointer | Redacted effective YAML or explanation text | Pipeline selection, module preparation, or provider work. |
+| Summary | **Config** or **EffectiveConfig** | Detached redacted payload suitable for debug summaries | Redacting arbitrary process state or provider traffic. |
 
 The CLI discovers a configuration file, invokes this package, and supplies the
 result to the framework. Configuration never reads an input file, constructs a
@@ -28,65 +28,50 @@ at their respective [CLI](cli.md), [pipeline](pipeline.md), and
 
 ## Loading And Validation
 
-ConfigKit acquires the selected root, imports, optional selected overlay, and
+The CLI loads configuration in this order:
-explicit CLI overrides in precedence order. Its document definition supplies
+
-typed defaults, source-aware path normalization, and structural validation
+1. parse the selected YAML file strictly into the file model;
-before conversion to the independently owned runtime **Config**. Only
+2. start from **Default**;
-`NOTARIUS_CONFIG` participates in discovery; retired field-level environment
+3. apply the file model; and
-variables do not participate in loading. Version 5 decoding rejects scalar
+4. apply the supported environment overrides.
-module bindings and scalar external references. ConfigKit retains redacted,
+
-historical inspection metadata while **LoadedConfig** keeps that implementation
+This establishes the public precedence order without giving environment input a
-detail private behind effective and explanation writers.
+second file schema. Loading and application reject malformed YAML, unsupported
+file versions, unknown fields, invalid values, and identifiers that are empty
+or collide after whitespace normalization. The file application also makes the
+effective extraction-worker default follow the effective LLM limit.
 
 **Config.Validate** checks configuration-only invariants before resolution. It
 rejects incompatible profile sources, invalid state-surface values, unsupported
 concurrency settings, malformed bindings and references, invalid retries, and
-invalid pipeline, step, or lane structure. PromptKit local-backend validation
+invalid pipeline, step, or lane structure. Its errors retain the closest known
-accepts only an absolute HTTP or HTTPS endpoint with a host and no user
+pipeline, lane, and binding context. It deliberately does not require modules
-information, query, or fragment, and rejects a negative local concurrency
+to be registered: that requires a catalog and belongs to resolution.
-limit. It also rejects a negative `promptkit.transient_retries` value; decoded
-omission resolves to two, while explicit zero remains a distinct opt-out. Its
-errors retain the closest known pipeline, lane, and binding context.
-It deliberately does not require modules to be registered: that requires a
-catalog and belongs to resolution.
 
 The exact user-selectable values and validation rules are defined in
-[Configuration](../config.md). Keep document schema, source-aware normalization,
+[Configuration](../config.md). Keep additions to the file model, an
-runtime conversion, and that reference aligned in the same change.
+environment override, its validation, and that reference in the same change.
 
 ## Effective Resolution
 
-**Config.Resolve** derives an absent extraction-worker value in an owned copy
+**Config.Resolve** first recomputes derived concurrency defaults and validates
-and validates the configuration. A programmatically supplied worker value is
+the configuration. It normalizes the requested pipeline ID, copies the selected
-always explicit. It normalizes the requested pipeline ID, copies the selected
+profile, applies a non-empty command-level LLM profile override to the
-profile, and passes the non-empty command-level LLM profile override, requested
+LLM-capable stage bindings, and calls the framework resolver with the requested
-lane selection, and reference changes to the framework resolver.
+lane selection and reference changes.
 
-After module and validator selection, the resolver applies the effective
+The command-level override does not replace an explicitly selected validator
-profile policy to LLM-backed bindings only: command override, binding profile,
+profile. Validator bindings remain part of the resolved validator chain and
-pipeline profile, then the prompt default. Deterministic bindings remain
+are resolved under their own declared configuration.
-profile-free, and no second inheritance decision occurs during execution. The
-public field definitions and precedence are owned by
-[Configuration](../config.md#pipelines).
-
-The resolver retains configured `validation_policy` overrides and derives one
-detached concrete terminal policy for the chunk producer and every lane's
-extract, merge, and normalize producers. That field-by-field inheritance is
-complete before preparation, and the effective values contribute to pipeline
-and checkpoint identity; execution does not interpret configuration defaults.
 
 The framework resolver supplies defaults, selects lanes, resolves validator
 chains, checks registered module and artifact compatibility, validates module
-options, and returns the fixed ordered pipeline shape. Positive validator retry
+options, and returns the fixed ordered pipeline shape. The resulting
-budgets require an LLM-backed selected validator; deterministic validators are
+**EffectiveConfig** retains the selected ID, requested selection and reference
-rejected during resolution. Eligible LLM-backed producer specifications also
-contribute their declared correction protocol to the resolved metadata. The
-resulting **EffectiveConfig** retains the selected ID, requested selection and reference
 changes, a clone of the input configuration, and the resolved pipeline.
 Callers may therefore retain or modify their input slices and maps without
 changing the resolved result, and later consumers cannot mutate the original
-configuration through the effective value. This ownership includes the nested
+configuration through the effective value.
-PromptKit local-backend value.
 
 Resolution failures stop before module construction and source parsing. They
 include an error path for an unconfigured pipeline, missing module, missing
@@ -98,46 +83,46 @@ runtime error class described in the [CLI reference](../cli.md#output-streams-an
 
 The framework assigns the resolved pipeline a deterministic SHA-256 digest
 after defaults, lane selection, module bindings, reference bindings, validator
-chains, selected correction protocols, effective LLM profiles, and artifact
+chains, and artifact schema identity have been resolved. The digest excludes
-schema identity have been resolved. The digest excludes
 its own stored value. It identifies resolved composition rather than raw YAML
 bytes, a debug payload, or all runtime state. The CLI records it as invocation
 provenance before execution; cache and checkpoint identity have additional
 owners in [Run State Internals](state.md).
 
-Configuration publication uses ConfigKit's redacted effective YAML. Resolved
+Configuration summaries must use **Redacted**, **RedactedSummaryPayload**, or
-pipeline publication uses **RedactedResolvedPipelinePayload**, which copies
+**RedactedResolvedPipelinePayload**, never a direct configuration marshal.
-bindings and nested option containers, replaces credential-shaped values with
+Those methods copy every binding and nested option container, replace values
-**[REDACTED]**, and omits materialized reference content while retaining safe
+whose key is credential-shaped with **[REDACTED]**, and omit materialized
-provenance. This redaction is deliberately narrow and does not authorize
+reference content while retaining safe binding and reference provenance. The
-recording arbitrary environment values or provider requests.
+payload must not alias the source configuration or resolved pipeline. This
+redaction is deliberately narrow: it protects configuration summaries and does
+not authorize recording arbitrary environment values or provider requests.
 
 ## Invariants To Preserve
 
-- ConfigKit composition applies defaults, imports, an optional overlay, and
+- Defaults, YAML values, and environment values are applied in one direction;
-  explicit overrides in one direction with retained origin metadata.
+  later sources may override only their supported operational settings.
 - A configuration is structurally valid before it is resolved, and a resolved
   pipeline is compatible with the supplied catalog before preparation begins.
 - Whitespace-normalized identifiers are unique wherever they identify a
   pipeline, step, lane, worker, or reference slot.
-- Runtime conversion and resolved-pipeline publication return detached data.
+- Resolution and summary generation return detached data. Redaction must cover
-- The resolved PromptKit transient-retry budget is always passed to the shared
+  every configured and resolved binding, including nested validator bindings.
-  built-in client; document presence preserves an explicit zero.
 - The resolved digest changes when resolved composition changes and never
   includes itself.
 
 ## Focused Tests
 
-- **internal/core/config/document_test.go** and
+- **internal/core/config/file_config_contract_test.go** covers strict file
-  **operational_document_test.go** cover ConfigKit document loading,
+  parsing, normalization, file application, and structural rejection.
-  normalization, imports, overlays, and overrides.
+- **internal/core/config/env_contract_test.go** covers supported operational
+  overrides and their precedence.
 - **internal/core/config/validation_contract_test.go** covers configuration
   invariants and contextual failures.
 - **internal/core/config/effective_config_contract_test.go** covers defaults,
   selections, overrides, resolution context, digest changes, and ownership.
-- **internal/core/config/loaded_config_test.go** covers safe effective and
+- **internal/core/config/redaction_test.go** covers recursive credential
-  explanation rendering; **redaction_test.go** covers resolved-pipeline
+  redaction, reference-content exclusion, and non-aliasing payloads.
-  redaction and reference-content exclusion.
 
 Run **go test ./internal/core/config** after changing this boundary. Changes to
 the handoff or resolved-composition semantics also need the focused framework

docs/internal/dnd.md

@@ -7,40 +7,25 @@ selectable keys, bindings, reference syntax, and default validator chains.
 
 ## Durable Artifact Contracts
 
-The ten lanes have separate durable wire contracts. This guide deliberately
+The six 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) |
-| NPC registry | [NPC registry artifacts](../integrations/dnd-npc-registry-artifacts.md) |
+| NPCs | [NPC artifacts](../integrations/dnd-npc-artifacts.md) |
 | Combat turns | [combat-turn artifacts](../integrations/dnd-combat-turn-artifacts.md) |
-| Item occurrences | [item-occurrence artifacts](../integrations/dnd-item-occurrence-artifacts.md) |
+| Item events | [item-event artifacts](../integrations/dnd-item-event-artifacts.md) |
-| Item registry | [item-registry artifacts](../integrations/dnd-item-registry-artifacts.md) |
+| NPC interactions | [NPC-interaction artifacts](../integrations/dnd-npc-interaction-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
 
 The D&D registrar registers the family’s artifact codecs, extractors, typed
-append-order mergers, normalizers, validators, prompt assets, fallback LLM
+append-order mergers, normalizers, validators, prompt assets, and default
-profile asset, and default validator chains. Each extractor and normalizer has
+validator chains. Each extractor and normalizer has a stable module spec,
-a stable module spec, explicit execution class, strict option decoding, and a
+strict option decoding, and a typed builder. Configuration remains the
-typed builder. Scene chunking, every extractor, and NPC, location, and
+canonical owner of the exact keys and validator order.
-item-registry normalization are registered as `llm_backed`; the remaining
-current D&D mergers and normalizers are `deterministic`. The metadata is
-available to catalog inspection and resolved-pipeline debug data and determines
-which selected bindings inherit the pipeline profile. The registry normalizers
-use `single_response_v1`, forwarding corrections to their reconciliation
-completion and retaining the accepted raw proposal only as an owned model
-candidate. When deterministic proposal safety or typed application rejects a
-group, they provide separate model-facing prose for a corrective module retry;
-internal issue categories, reason codes, and operator messages remain
-diagnostic-only. Configuration remains the canonical owner of the exact keys,
-profile precedence, and validator order.
 
 Private structured-LLM response schemas are deliberately minimal. They reject
 invalid JSON structure, missing required fields, incompatible types, and
@@ -48,267 +33,46 @@ unknown fields, while preserving semantic candidates for deterministic
 validation. Do not promote a private response envelope into a durable schema;
 the contracts above define durable data.
 
-A D&D producer that declares `single_response_v1` forwards any supplied
-semantic correction to its structured completion and returns an owned copy of
-that completion's exact validated raw response as its model candidate. It does
-not serialize normalized artifacts to create that candidate, so deterministic
-identity, evidence, warning, and durable-schema behavior remains separate from
-the model transport material.
-
 ## Prompt Construction
 
-D&D LLM-facing content lives beneath `assets/dnd/`. Each module contributes a
+D&D extractors assemble prompts from an ordered manifest of shared and
-local `prompt.yaml` declaration and `instructions.md`; input-specific files
+module-owned assets. Reuse the shared D&D system, evidence, identity,
-such as a catalog, registry, grounding projection, or candidate collection are
+reference, and transcript assets instead of copying their text into individual
-local only when that module needs them. New extractor content uses its feature
+modules. A manifest’s declared sequence, including cache-control placement, is
-subtree, while families with both extraction and normalization content use their
+part of the prompt behavior, and the chunk transcript is the final message.
-`extract` and `normalize` subtrees. Shared visual-provenance fragments use
+Preserve that order when changing an extractor or its assets so prompt-cache
-the `common-dnd-` prefix. Production lane code belongs with its D&D codec,
+behavior remains stable.
-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
+All extractors use the shared prompt-input preparation rules. The current chunk
-assets are selected, their mount paths, their message order, cache controls,
+is copied into transcript material; player, party, glossary, and compatible
-and the files included in its prompt fingerprint. Shared fragments belong to
+campaign references are context for disambiguation, not source evidence.
-the D&D shared implementation and are selected by name rather than copied into
+Reference prompt material is canonically ordered before it is rendered, which
-module directories. The root `assets` package is a content-only boundary; its
+keeps equivalent inputs stable across runs.
-physical ownership and rationale are defined by
-[ADR-0011](../adr/0011-centralize-llm-assets.md).
-
-Put each rule at its narrowest owner:
-
-- universal behavior belongs in the shared system asset;
-- D&D-family behavior belongs in a selected `common-dnd-` asset;
-- rules for an input projection belong with that input asset;
-- lane-specific policy belongs in the module’s `instructions.md`; and
-- transport-envelope shape belongs in the private response schema.
-
-A rule is eligible for the system prompt only when every D&D LLM prompt needs
-it regardless of lane, inputs, or response shape. Module instructions must not
-repeat rules selected from shared assets or schemas. Reintroduce such repetition
-only after observational evaluation with representative transcripts shows that
-it improves results at the intended target models and cost; structural prompt
-tests alone are not that evidence.
-
-Every maintained D&D LLM prompt selects `dnd-extraction` as its default
-profile. The D&D registrar registers the fallback, while an operator can
-replace it with a complete profile of the same ID from the configured PromptKit
-source. Deployment profile selection is documented in
-[Configuration](../config.md#promptkit-profiles).
-
-The D&D transcript assets have distinct consumers. Scene chunking consumes the
-complete-session `common-dnd-transcript-full.md`, while extraction prompts
-consume the current-chunk `common-dnd-transcript-chunk.md`. NPC, location, and
-item normalization instead mount the generic semantic-reconciliation
-candidate and transcript-window presentation assets. Player, party, glossary,
-and compatible campaign references provide disambiguating context only when
-declared by the active prompt; they never establish evidence. Reference
-material is canonically ordered before rendering so equivalent inputs remain
-stable.
-
-Extraction prompts render the common system and identity messages first, then
-cached campaign references and the cached chunk transcript. Evidence policy and
-any lane-specific registry, catalog, or grounding projection follow that
-prefix. The final module instructions message is ephemeral. This keeps the
-reusable extraction prefix identical while preserving the lane-specific suffix.
-
-Scene chunking intentionally uses a different order: system, cached campaign
-references, uncached module instructions, then the final ephemeral full
-transcript. Entity normalization also has its own order: D&D system, mandatory
-generic protocol, ephemeral domain semantic instructions, generic candidate
-presentation, and final ephemeral generic transcript windows. These orders and
-cache controls are prompt behavior; change them only through the owning
-manifest and prompt declaration.
-
-NPC, item, and location registry reconciliation translate shared proposal
-safety categories into bounded prose that references only the response-local
-duplicate-group ordinals and candidate handles. Item reconciliation appends its
-typed rule that currency may be consolidated only with aliases of the same
-denomination and never with non-currency items. The next normalize attempt
-receives that prose with the exact defective proposal under the shared
-replacement-request protocol. Structurally invalid output has no valid proposal
-candidate and receives a fresh feedback-free attempt instead. If the stage
-budget is exhausted, safe groups stay applied, unsafe groups stay separate, and
-one fallback warning summarizes the final defect without raw model content.
 
 ## Evidence, Candidates, And Normalization
 
 The current transcript is the only durable evidence source. Extractors assign
-the current source identity and losslessly order any reversed range whose two
+the current source identity, preserve candidate evidence ranges for validators,
-endpoints resolve in that source, using transcript position rather than numeric
+and canonically order or remove exact duplicate ranges without asking the
-unit-ID order. They then canonically order ranges and remove exact duplicates.
+model to repair semantic errors. Campaign context and generated artifacts may
-This routine canonicalization does not request a retry or emit a warning.
+ground names or control routing, but they never establish evidence for a D&D
-Unresolvable or wrong-source ranges remain unchanged for validators to reject.
+result.
-Campaign context and generated artifacts may ground names or control routing,
-but they never establish evidence for a D&D result.
 
 Default chains keep responsibilities separate: structural validators assess the
 candidate, source-reference validators resolve cited ranges against the current
-source and require extraction evidence to stay within the current chunk,
+source, durable-schema validation checks an approved representation, and
-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).
 
-The optional `extract/dnd/scene-descriptions/combat_semantics` validator is the
+Normalizers are deterministic for spells, combat turns, item events, NPC
-D&D family's LLM-backed review of only combat versus non-combat classification.
+interactions, and scene descriptions. They canonicalize display values and
-It selects the shared combat-policy prompt fragment and asks the model to
+evidence, use source-document order for stable output, and issue bounded
-classify the current chunk independently as `combat` or `non_combat` without
+warnings for changes or collapsed duplicates. The NPC normalizer is the
-receiving the proposed scene kind. Deterministic code compares that
+intentional exception: it first produces a deterministic candidate set, then
-classification with the proposed kind and either approves it or produces the
+uses a bounded structured-LLM proposal to reconcile identity groups. Invalid
-appropriate correction guidance. This keeps every schema-valid classification
+or unusable proposals retain the deterministic result and surface retry or
-interpretable and avoids anchoring the reviewer on the producer's answer. It
+fallback diagnostics; the model does not directly replace durable records.
-does not assess titles, summaries, non-combat subtype, or scene boundaries;
-deferred boundary-coherence review remains separate. It is opt-in;
-[Configuration](../config.md) owns selection and retry/failure behavior.
-
-### Combat-semantics provider evaluation
-
-The human-reviewed corpus at
-`internal/modules/dnd/validate/scenedescriptions/combat_semantics/testdata/evaluation_cases.json`
-owns the proposed kind, expected combat classification, and reviewer rationale
-for each synthetic case. Its package test validates the fixture contract only.
-Provider evaluation remains an explicit maintainer operation and must not be
-added to the default offline test suite.
-
-Use the following protocol before proposing default-chain inclusion:
-
-1. Record the Notarius commit, prompt and schema fingerprints, provider, model,
-   profile settings, reasoning effort, structural-repair setting, number of
-   repetitions, and evaluation date before collecting results. Do not revise
-   expected classifications merely to agree with provider output; a substantive
-   corpus correction requires independent human review.
-2. Exercise the production validator construction and prompt assets from an
-   explicitly invoked, disposable evaluation driver or test in the validator
-   package. For each corpus case, construct transcript source units from the
-   listed IDs and text, assign matching per-unit source references, and use
-   `source.MaterializeChunkPlan` with one range spanning those units. Construct
-   exactly one scene whose ID and source range match that chunk and whose kind
-   is the case's `proposed_kind`; title and summary may use fixed placeholders
-   because the validator neither receives nor evaluates them. Invoke the typed
-   validator at extract stage through the production registry and scheduled LLM
-   client. Do not commit provider credentials, generated source material, or an
-   always-on live test.
-3. Compare the model classification with `expected_classification`, then verify
-   that its deterministic comparison with `proposed_kind` yields the expected
-   approval or rejection direction.
-   Record an unexpected approval of an expected rejection as a false
-   acceptance, an unexpected rejection of an expected approval as a false
-   rejection, and any validator execution failure separately from semantic
-   accuracy. Retain per-case results so repeated trials and systematic failure
-   modes remain visible.
-4. Evaluate producer correction separately with representative complete
-   scene-description runs configured as shown in
-   [Configuration](../config.md#production-validator-keys-and-default-chains).
-   For every initial semantic rejection, record whether the next producer
-   attempt returns the requested combat status and is approved. Do not count a
-   PromptKit structural repair as a producer-correction attempt.
-5. Run the correction evaluation with debug capture enabled and without reused
-   extraction checkpoints. Record added validator and producer calls, elapsed
-   latency, and cumulative prompt, completion, cached, and total token usage
-   from the debug attempt records. Compare these values with an otherwise
-   identical run whose scene-description chain omits the semantic validator.
-
-The default-chain review must consider classification error, false acceptance,
-false rejection, execution failure, producer-correction success, added calls,
-latency, and token use together. A structurally successful provider run alone
-is not evidence that the validator should become a default.
-
-Every producer-correctable D&D rejection describes all currently detectable
-corrections in transcript-grounded domain terms, using contextual names,
-model-owned artifact fields, and source segment ranges when useful. Validators
-collect independent record defects in one pass so one retry does not merely
-reveal the next issue. Shared D&D diagnostic helpers keep repeated rules and
-record descriptions stable, de-duplicated, and bounded; each artifact family
-continues to own the semantic rule and its prose.
-
-Operator diagnostics and model guidance are separate products of the same
-assessment. Operator messages may use typed paths, reason details, and opaque
-application identities. Correction guidance must not copy those messages or
-ask the model to reproduce durable entity IDs, hashes, validator module keys,
-reason codes, or Go field paths. A registry-normalization rejection instead
-speaks in terms of the duplicate-group proposal response the normalizer can
-actually revise. Normalization-only deterministic invariants retain useful
-operator detail but do not imply that a model controls derived ordering or
-identity. Only bounded actionable semantic guidance is eligible for a
-correction prompt.
-
-Private LLM schemas use simple enums for closed categorical fields when the
-provider-compatible shape can express the rule directly. Deterministic typed
-validators retain the same checks as defense in depth and for non-LLM
-producers. Private schemas keep every property required and avoid optional
-properties, `uniqueItems`, and conditional cross-field logic.
-
-Item-occurrence shape validation groups repeated holder mistakes by occurrence
-kind and gives the producer the required JSON null/non-null relationship. It
-identifies affected records by contextual item name and cited transcript range,
-never by the deterministically attached durable item ID. Holder mistakes remain
-semantic rejections rather than silent rewrites because changing a holder can
-also change the meaning of the occurrence kind.
-
-Enemy-event extraction additionally rejects a second `engaged` observation for
-the same comparison identity within one scene-scoped result. Normalization may
-combine results from distinct scenes, so it intentionally does not apply that
-rule. Configuration owns the exact validator key and chain position.
-
-Extraction source-reference validators share one full-span chunk-containment
-policy. After ordinary reference validity succeeds, the policy resolves both
-endpoints through document order and requires every source unit in the
-inclusive range to be present in the current chunk. It does not assume numeric
-unit-ID ordering, mutate input, or weaken wrong-source and unresolved-reference
-validation. Scene descriptions remain separate because their validator owns an
-exact one-scene range contract rather than general extraction containment.
-
-Normalizers are deterministic for spells, combat turns, item occurrences, NPC
-occurrences, scene descriptions, enemy events, and location occurrences. They
-canonicalize display values and evidence, use source-document order for stable
-output, and emit bounded normalization observations for changes or collapsed duplicates. NPC,
-item, and location registry normalizers are intentional exceptions: each first
-produces a deterministic candidate set, then may use a bounded structured-LLM
-proposal to reconcile identity groups.
-
-## Semantic Registry Reconciliation
-
-The three registry normalizers instantiate the domain-neutral
-`internal/framework/semanticreconcile` engine with default bounds. Each
-eligible candidate receives a contiguous, one-based `candidate_number` for that
-request, and candidate material declares the exact inclusive range. The model
-sees that handle, the candidate label and source-free evidence ranges, plus
-bounded transcript windows; it returns only duplicate
-groups of supplied handles and one supplied canonical handle per group. It
-never returns names, evidence, durable IDs, or replacement records. Identical
-labels and evidence remain independently selectable because their handles are
-distinct. Transcript unit `id` values and evidence `start_unit_id` and
-`end_unit_id` values are source positions in a separate namespace and are
-never valid candidate numbers.
-
-The generic core owns the mandatory handle protocol, candidate and transcript
-presentation, the private response schema, source-reference validation,
-candidate and combined-material limits, structured completion, proposal
-assessment, stable group ordering, and typed plan-application mechanics. The
-D&D prompt contributes its system message and registry-specific semantic
-instructions. The generic registrar registers the shared prompt and schema;
-the D&D registrar registers each consuming prompt and the fallback profile.
-
-Fewer than two eligible candidates skips the LLM without a semantic warning.
-An exceeded bound also skips the call and preserves the deterministic
-preprocessed registry, adding the registry's bounded fallback warning. Invalid
-structured output or discarded proposal groups use the normalizer's existing
-retry contract; retry exhaustion preserves the safe deterministic or
-partially applied result and emits its bounded fallback warning. Provider,
-transport, cancellation, and context-material failures remain execution
-errors.
-
-Application remains typed and registry-owned. All three policies select the
-canonical member's normalized display name, union member evidence in source
-order, preserve ungrouped records, and derive durable identity only after
-consolidation. NPC IDs derive from the final name. Item IDs also derive from
-the final name, and a typed guard prevents currency aliases from crossing
-denominations or mixing currency with non-currency records. Location IDs
-derive from the final name and final evidence, preserving same-name,
-parent/child, and distinct physical-place identities. Registry warning scopes,
-reason codes, and postconditions remain outside the generic core.
 
 ## Generated References And Grounding
 
@@ -318,55 +82,30 @@ 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 and item registry consumers receive names-only grounding. Location
+NPC registries are names-only grounding projections: they may canonicalize
-consumers receive a contextual selector containing the canonical name and the
+actors for spells and combat turns and are required for NPC interactions, but
-registry references needed to distinguish same-name places. The calling module
+they do not supply evidence. Scene-description registries are eligibility-only
-resolves those supplied selections locally and maps them into the unchanged
+projections: they retain the current chunk’s classification data, not scene
-durable ID/name pair; an unknown or ambiguous selection rejects the complete
+prose or evidence, and exist to route combat extraction.
-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. |
-| 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. |
+| NPCs | Does not consume an NPC registry. 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 occurrences | Requires the normalized item registry for exact deterministic grounding at extraction and normalization. Campaign context may disambiguate, but the registry never becomes occurrence evidence. |
+| Item events | Uses campaign context for disambiguation but has no NPC-registry or scene-description dependency. |
-| 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 interactions | Requires the normalized NPC registry at extraction and normalization, using it for canonical actor grounding only. |
-| 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

@@ -1,12 +1,12 @@
 # LLM Runtime Internals
 
 `internal/framework/llm` is Notarius’s provider-independent structured
-completion boundary. It adapts framework requests to PromptKit, bounds
+completion boundary. It adapts framework requests to Scriptorium, bounds
 provider calls, assembles registered prompt and schema assets, records selected
 profiles, and redacts provider errors. The architectural boundary is defined in
 [Architecture](../policy/architecture.md#llm-boundary); profile sources,
 credentials, and concurrency settings belong in
-[Configuration](../config.md#promptkit-profiles) and
+[Configuration](../config.md#scriptorium-profiles) and
 [Configuration](../config.md#concurrency-output-cache-and-debug).
 
 ## Structured Completion Boundary
@@ -24,102 +24,25 @@ 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
+`ScriptoriumClient` validates the request target and prompt identity, maps each
-application identity; PromptKit and this adapter do not own entity identity.
+named material to a Scriptorium inline artifact while preserving its origin URI,
+forwards session and profile selection, then prepares and runs the prompt. It
+returns Scriptorium’s validated raw bytes rather than re-encoding the decoded
+target. An empty optional material is represented as one space so its named
+input is retained by Scriptorium.
 
-`PromptKitClient` validates the request target and prompt identity, maps each
+An empty request profile lets the prompt select its configured default. The CLI
-named material to a PromptKit inline artifact while preserving its origin URI,
+prepares every explicitly selected binding profile before a run begins, so a
-passes the supplied request session through to PromptKit's direct per-run
+missing explicit profile fails before stage execution. Calls record the profile
-session field, retains the same value as the `session_id` prompt variable for
+actually selected by Scriptorium; the recorder deduplicates non-secret profile
-maintained prompt compatibility, and forwards profile selection. It does not
+identity, provider, and model values for manifest use.
-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
-is authoritative for provider session behavior. A session ID is a stable,
-non-secret correlation identifier and may be exposed to providers and provider
-observability. The adapter returns PromptKit’s validated raw bytes rather than
-re-encoding the decoded target. An empty optional material is represented as
-one space so its named input is retained by PromptKit.
-
-When a request includes semantic correction material, the adapter validates and
-defensively copies it before preparation, then appends exactly two messages
-after the ordinarily rendered prompt: the prior response as an assistant
-message and the correction guidance as a user message. Requests without a
-correction do not add messages or introduce caller roles. Ordinary request
-summaries record correction byte counts and digests only; complete messages are
-available solely in an explicitly requested debug trace.
-
-The adapter leaves the ordinary rendered message prefix, named inputs,
-variables, session, profile, execution overrides, prepared-execution path, and
-PromptKit repair policy unchanged for a corrected request. It never imports a
-PromptKit message type into a module or pipeline contract. PromptKit reports
-actual structural repair count and cumulative token usage per completion; the
-pipeline's safe terminal debug record projects those values without copying
-message content.
-
-Client construction may also receive a run-wide reasoning-effort override from
-the CLI factory boundary. The adapter copies the caller-owned pointer and
-creates a fresh PromptKit execution override for each request: a nil pointer
-inherits the selected profile, a non-empty value replaces it, and an empty
-value clears inherited reasoning. The CLI's mutually exclusive
-`--reasoning-effort` and `--clear-reasoning-effort` controls select those
-states. With neither flag, profile behavior remains unchanged. Because
-production constructs one shared client, the selected state applies uniformly
-to module calls, retries, and LLM-backed validators for the whole run.
-
-An empty request profile lets the prompt select its configured default. Before a
-run begins, the CLI asks the adapter to inspect every explicit profile on the
-resolved selected LLM-backed bindings and validators, including inherited
-pipeline profiles. Inspection resolves the profile and its selected backend and
-target without loading a prompt, reading credentials, admitting capacity, or
-contacting a provider, so a missing or invalid explicit profile fails before
-stage execution while a valid `api_key_env` may remain unset. Calls record the
-profile actually selected by PromptKit. The recorder trims and deduplicates
-non-secret profile identity, provider, model, selected backend ID, and
-effective reasoning values for manifest use. Entries that differ in backend or
-reasoning remain distinct and deterministically ordered. Endpoint-only profiles
-retain an empty backend ID, which the published JSON omits. Successful
-completion responses and recorded profile manifests identify the adapter
-provider as `promptkit`.
-
-The CLI's profile-inspection engine and the production adapter use the same
-profile-source construction to apply the configured profile directory or file,
-the optional registered fallback profile assets, and the optional conventional
-`local` backend. Preflight therefore resolves the same profile sources and
-backend membership as runtime without performing generation. Fallback assets
-are mounted only when at least one source is registered. The production D&D
-registrar contributes its `dnd-extraction` fallback, and the maintained D&D
-prompts select that logical ID by default. PromptKit owns source precedence and
-profile parsing and inheritance: an operator-provided matching profile takes precedence over a
-fallback profile without Notarius merging either document.
-When the registration is absent, a profile selecting `backend: local` fails
-inspection instead of falling back to a built-in or endpoint-only target.
-
-Before execution, the adapter also contributes a non-secret checkpoint
-fingerprint for the effective PromptKit profile source. It combines the
-identity of PromptKit's compiled-in profile catalog with a deterministic digest
-of every YAML profile in the configured profile directory, or of the configured
-profile file, and a deterministic digest of the flattened fallback profile
-assets. The fingerprint contains neither profile content nor source paths. It
-covers inherited pipeline profiles, explicit binding profiles, and
-prompt-selected defaults, so changing a model or other profile setting cannot
-reuse checkpoints created under the
-prior profile source. This cache identity is independent of durable
-profile provenance: run manifests continue to list only profiles actually
-observed during LLM calls. When the local backend is registered, a second
-fingerprint hashes its trimmed endpoint behind a stable marker. Changing that
-semantic execution target invalidates checkpoint reuse. The raw endpoint is not
-stored in checkpoint identity, and the local concurrency limit is excluded
-because it changes scheduling rather than execution semantics.
 
 ## Shared Provider-Call Limit
 
-Production construction creates one PromptKit client and wraps it in one
+Production construction creates one Scriptorium 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. It rechecks the caller context after admission and before dispatch.
+cancelled. A granted permit is released exactly once on every completion path.
-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
@@ -128,57 +51,22 @@ worker counts cannot exceed the configured LLM limit. The configuration field
 and its effective default are owned by
 [Configuration](../config.md#concurrency-output-cache-and-debug).
 
-PromptKit applies a second, independent admission limit when the selected
-profile names a limited backend. It sits beneath the Notarius scheduled client,
-so it may narrow but cannot expand the application-wide limit. Built-in
-OpenRouter profiles select PromptKit's reserved backend and its upstream
-capacity policy. A positive configured local-backend limit bounds active local
-generations inside PromptKit; zero leaves that backend unlimited there.
-Endpoint-only profiles do not select a PromptKit backend and remain limited
-only by the Notarius scheduler.
-
 ## Prompt And Schema Assets
 
-An `AssetRegistry` collects prompt, schema, and optional fallback-profile
+An `AssetRegistry` collects prompt and schema filesystems from production module
-filesystems from production module families. It flattens registered roots into
+families. It flattens registered roots into the Scriptorium filesystems and
-the corresponding PromptKit filesystems and rejects invalid roots, unreadable
+rejects invalid roots, unreadable assets, duplicate paths, and missing prompt
-assets, duplicate paths, and missing prompt or schema files during preparation.
+or schema files during preparation. The framework’s `promptfs` helper combines
-Fallback assets receive a safe content digest for checkpoint identity; raw
+module-owned prompt files with reusable domain fragments without making the
-paths and bytes are never included. The framework’s `promptfs` helper combines
-module-selected prompt files with reusable domain fragments without making the
 framework depend on D&D content.
 
-LLM-facing content is embedded once by the root `assets` package. Each consumer
+Each LLM-backed module owns its prompt declaration, package-specific assets,
-uses only its scoped subtree, while the module retains ownership of its prompt
+and private response schema. Shared D&D wording is owned by the D&D shared
-declaration, ordered manifest, private response-schema identity, and
+asset package; the detailed D&D conventions are in
-registration. Shared D&D fragments are selected by D&D's shared implementation;
+[D&D Module Internals](dnd.md). The mounted prompt assets used by a module also
-the detailed convention is in [D&D Module Internals](dnd.md). This physical
+determine its prompt fingerprint. Schema loaders validate JSON, attach identity
-arrangement and its data-only boundary are defined by
+and digest metadata, make defensive copies, and expose diagnostics without raw
-[Architecture](../policy/architecture.md) and
+schema bytes.
-[ADR-0011](../adr/0011-centralize-llm-assets.md), rather than by this runtime
-guide.
-
-The generic registrar is the sole production registration owner for the
-semantic-reconciliation default prompt and private response schema. The
-domain-neutral reconciliation package also exposes only its mandatory protocol
-and candidate/transcript presentation files for domain prompt manifests. D&D
-registry normalizers mount those files while retaining ownership and hashing
-of their D&D system message, semantic instructions, and complete prompt
-declaration. The response schema is therefore registered once even though
-several typed normalizers select it.
-
-Mounted prompt assets determine a module's fingerprint. The fingerprint hashes
-only the module and shared files explicitly selected by its manifest, so an
-unrelated asset does not invalidate a checkpoint. Schema loaders validate JSON,
-attach identity and digest metadata, make defensive copies, and expose
-diagnostics without raw schema bytes.
-
-Semantic-reconciliation normalizers extend this identity with the shared
-response-schema digest, framework policy version, and complete limit-policy
-digest. Their manifest metadata records the same content-free prompt, schema,
-policy, and limit identities together with domain identity and normalization
-policies. Request-local handles, source material, proposal content, and raw
-asset bytes are not checkpoint metadata.
 
 Private response schemas validate a model transport envelope. They are not the
 durable artifact schema and should not be documented as an external wire
@@ -188,136 +76,54 @@ contract. Durable formats and compatibility rules remain in the
 ## Prompt Maintenance And Backend Caching
 
 Prompt message order and shared asset bytes are runtime behavior. Backend cache
-reuse depends on identical preceding roles, rendered bytes, and cache-control
+reuse depends on the same preceding messages and content, not merely equivalent
-metadata—not merely equivalent meaning. Keep reusable shared assets
+meaning. Keep reusable shared assets byte-identical and keep stable material
-byte-identical and preserve each prompt’s declared ordering and cache controls
+before the inputs that vary per request wherever a prompt’s declared sequence
-when editing it.
+supports caching. Preserve the existing manifest order and cache-control hints
+when editing a prompt.
 
-For sibling prompts that can reuse the same source material, order universal
+D&D extraction manifests place the changing chunk transcript at the end of the
-shared context first, request source material next, and module-specific
+prompt after their reusable context. Scene chunking and NPC normalization use
-suffixes last. Put a cache boundary at a reusable prefix that is useful to the
+their own declared message sequences because their inputs and work differ. The
-backend. Redundant intermediate cache boundaries do not extend that reusable
+family-specific asset and ordering rules belong in [D&D Module Internals](dnd.md).
-prefix and add no value.
+Do not add tests that enforce a fixed message-prefix length; prompt-asset tests
-
+should instead verify the meaningful asset sequence, inputs, and cache controls
-Prompt-family owners may choose a different sequence when their inputs and
+of the prompt being changed.
-reuse pattern differ. The D&D family’s extraction, scene-chunking, and NPC
-normalization policies are maintained in [D&D Module Internals](dnd.md#prompt-construction).
-Do not add tests that enforce prompt prose; prompt tests should verify the
-meaningful input placement and cache controls of the prompt being changed.
 
 ## Validation, Repair, And Retries
 
-PromptKit performs prompt rendering, provider execution, and the prompt’s
+Scriptorium performs prompt rendering, provider execution, and the prompt’s
 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. Apart from documented context, capacity, and
+than output-validation failures.
-invalid-output categories, provider error values and types do not cross the
-adapter error chain; callers receive only a credential-redacted diagnostic.
 
-`LLMGenerationError` preserves the provider-neutral failure kind (`transport`,
+Prompt-declared repair is executed within Scriptorium’s structured-output flow.
-`provider_status`, `malformed_response`, or generic `generation`) and any HTTP
+The current production D&D prompt manifests set repair attempts to zero. That
-status. When PromptKit exhausts an eligible transient-status retry budget, it
+setting does not replace pipeline retry behavior: a binding’s configured retry
-also records that exhaustion and the attempts in that generation. Those fields
+count reruns its stage attempt after an error or rejection, and an exhausted
-do not include repair generations, and zero attempts means unavailable rather
+rejection is a recorded output rather than a provider error. The pipeline owns
-than proof that no request was sent.
+attempt lifecycle, validation chains, and retry diagnostics; see
-
-Every execution that reaches PromptKit returns an optional request-local
-`execution` summary. It contains only terminal aggregate attempts, retry and
-repair counts, durations, outcome and failure classification, status, and
-presence-aware token usage. Preparation failures have no summary; later local
-decode failures retain the upstream terminal summary without changing it.
-
-When PromptKit rejects backend admission before generation, the adapter maps
-`promptkit.ErrCapacityExceeded` to
-`contracts.ErrLLMCapacityExceeded`, retaining prompt context and a redacted
-upstream diagnostic without exposing the PromptKit sentinel or capacity-error
-type as a framework contract. When supplied, the normalized selected backend
-ID appears only in that safe application-owned diagnostic context. A canceled
-caller context takes precedence. The adapter does not retry capacity failures;
-the pipeline's existing binding attempt policy sees the operational error and
-decides whether to rerun the complete operation.
-
-PromptKit executes structural repair within its structured-output flow. The
-maintained production prompt manifests declare one additional repair attempt.
-When a resolved binding supplies a repair value, the adapter inspects the
-prompt, copies its complete output contract, changes only the repair limit, and
-passes that complete replacement contract to PromptKit. This preserves the
-prompt's output format, validation mode, schema, and provider structured-output
-settings.
-
-A successful repair is an ordinary successful completion, not a warning. The
-adapter reports PromptKit's actual repair count and its cumulative usage
-directly, without adding the initial and corrective counts again. Debug prompt
-material records the configured complete contract; debug response material
-records the repaired response and actual validation result. If the repair
-budget is exhausted, the adapter retains the final raw bytes and debug material
-and reports `ErrInvalidStructuredOutput`. Generation failures during an initial
-or corrective call remain provider-neutral operational errors with the same
-redaction boundary.
-
-Structural repair does not replace pipeline retry behavior: a binding's
-configured retry count reruns its complete stage attempt after an operational
-or structural error, module-requested retry, or actionable semantic rejection.
-An actionable module-requested retry and a validator rejection both use the
-same correction payload when the producer exposes an exact latest response;
-feedback-free module retries reconstruct the ordinary request without appended
-messages. The pipeline owns attempt lifecycle, validation chains, and retry
-diagnostics; see
 [Pipeline Internals](pipeline.md#validation-retries-and-output) and the
 [binding reference](../config.md#module-bindings-and-validators).
 
-## Timeout Ownership
-
-The caller context remains the outer cancellation authority. PromptKit applies
-a positive effective generation timeout as an inner request deadline for each
-built-in generation attempt; an explicit zero disables only that generation
-deadline. The HTTP client timeout is a separate transport-wide cap. Notarius
-forwards the caller context and does not install another timeout wrapper around
-PromptKit.
-
-The selected PromptKit profile owns generation settings. The resolved global
-`promptkit.transient_retries` configuration is passed to the shared PromptKit
-engine and controls additional built-in attempts for eligible transient HTTP
-failures in one generation. It defaults to two; explicit zero disables those
-attempts. Notarius binding retries remain outside the adapter and repeat the
-complete module operation and validation chain.
-Operator-facing behavior is summarized in
-[Operations](../operations.md#operational-limits), and the pinned upstream
-contract is identified in
-[PromptKit Integration](../integrations/pkg-promptkit.md).
-
 ## Observability And Redaction
 
 When debug recording is enabled, the pipeline decorates the shared client. The
 wrapper records prepared prompt and response material, timing, selected profile
-and backend, effective model parameters, and call identifiers in the run’s
+and model, and call identifiers in the run’s debug bundle, including material
-debug bundle, including material available from a failed structured completion.
+available from a failed structured completion. For a successful completion, a
-Effective parameters use PromptKit's stable lower-case JSON field names and may
+debug-write failure is surfaced; when the completion already failed, its call
-include `backend_id`. For a successful completion, a debug-write failure is
+error remains the result. Debug-bundle location, retention, and handling are
-surfaced; when the completion already failed, its call error remains the
+operational concerns documented in [Operations](../operations.md#debug-bundles).
-result. Debug-bundle location, retention, and handling are operational concerns
-documented in [Operations](../operations.md#debug-bundles).
 
-The attempt-terminal summary is a separate safe trace record: it contains
+Run manifests receive selected profile summaries and component identities, not
-attempt kinds, validator outcome counts and reason codes, effective policy,
+prompt, schema, source, reference, or response content. Provider error text is
-terminal action, and repair/usage references. It excludes raw assistant
+wrapped with prompt context and bearer credentials are redacted before it
-responses and correction text. Those values can appear only in the explicitly
+crosses the runtime boundary. Known-secret redaction is available to other
-requested detailed prompt and response artifacts, which require sensitive-data
+runtime collaborators; it does not make prompt or response contents safe for
-handling.
+general logging.
-
-Run manifests receive selected profile summaries, including optional effective
-backend and reasoning provenance, and component identities—not prompt, schema,
-source, reference, or response content. The published field semantics belong
-to the [JSON output contract](../integrations/json-output.md#manifestjson).
-Provider error text is wrapped with prompt context and bearer credentials are
-redacted before it crosses the runtime boundary. Known-secret redaction is
-available to other runtime collaborators; it does not make prompt or response
-contents safe for general logging.
-
-Generation failures expose an application-owned category and optional HTTP
-status. Provider code, type, and message remain debug-only, after redaction.
 
 ## Failure Boundaries
 
@@ -325,8 +131,6 @@ status. Provider code, type, and message remain debug-only, after redaction.
   sources, invalid asset registration, or a non-positive scheduler limit.
 - Preparation failures, unavailable explicit profiles, provider failures, and
   context cancellation propagate to the calling stage with context.
-- Backend admission exhaustion is a provider-neutral operational error and is
-  not classified as invalid structured output or validator rejection.
 - Malformed or schema-invalid provider output is classified separately as
   invalid structured output so the module or pipeline can apply its own retry
   and rejection policy.

docs/internal/modules.md

@@ -12,24 +12,9 @@ exceptions. See [D&D Module Internals](dnd.md) rather than adding them here.
 
 A module is a typed implementation registered for one pipeline stage. Its
 `ModuleSpec` is the public-to-the-framework declaration of its stable key,
-stage, execution class, required and provided capabilities, artifact kind, and
+stage, required and provided capabilities, artifact kind, and accepted
-accepted reference slots. The execution class states whether a module is
+reference slots. The framework uses that declaration to resolve a configured
-`deterministic` or `llm_backed`; registries retain it for catalog inspection and
+binding before it builds the implementation.
-resolved-pipeline debug data without constructing the module. The framework
-uses the declaration to resolve a configured binding before it builds the
-implementation. After selection, the resolver applies profile inheritance only
-to bindings whose declared execution class is `llm_backed` and rejects a
-binding-specific profile on a deterministic module. The user-facing precedence
-contract belongs in [Configuration](../config.md#pipelines).
-
-An eligible LLM-backed chunk, extract, merge, or normalize producer may also
-declare correction protocol `single_response_v1`. That declaration is a
-promise that the implementation accepts one attempt-local semantic correction
-and returns an owned copy of the exact one model response that directly
-controlled the candidate. It must forward correction only to its structured
-completion request; it must not manufacture prior-response material by
-serializing a normalized artifact or expose opaque application IDs. Input,
-output, validator, and deterministic specs cannot declare the protocol.
 
 Implementations that accept options must provide both an option validator and
 a builder. The validator is used while resolving configuration; the builder
@@ -45,118 +30,45 @@ they need, register each leaf implementation, and add any family-owned assets
 or default validator chains. They return contextual errors so production
 composition fails at startup rather than at the first run.
 
-A validator that returns a completed rejection must supply two separate
-bounded values: a stable `ReasonCode` for provenance and actionable
-`CorrectionGuidance` for the producer. Guidance identifies the semantic defect
-and the constraints on one complete corrected replacement. It must not contain
-validator keys, diagnostic paths, opaque application IDs, or other internal
-identifiers. An operator-facing `Message` may explain the same event, but the
-framework never copies it into a model request. Missing or invalid guidance is
-a validator contract failure.
-
 An artifact family can register an optional typed evidence projector alongside
 its codec. The projector returns defensive copies of the artifact's direct
 generic source references and must use the codec's exact Go type. It does not
 interpret surrounding context or publish files; the pipeline validates the
 capability during preparation and the output boundary owns publication. See
 the [Published Evidence Context contract](../integrations/evidence-context.md)
-for the durable source-unit excerpt. Lane artifacts retain citation and lane
+for the durable result.
-provenance; the framework does not add either to that published excerpt.
-
-An artifact family is broader than a module: it owns the cohesive domain
-feature across its artifact type, codec, stage modules, validators, prompt
-policy, schemas, identity helpers, and reference projections. An extractor and
-normalizer in one artifact family remain independently registered modules in
-their respective pipeline stages. This ownership vocabulary does not create a
-new registry or change the fixed pipeline.
 
 ## Production Composition
 
 Production composition is intentionally split by family:
 
 - The generic registrar provides the unit chunker, generic JSON validators,
-  JSON output encoder, and shared semantic-reconciliation prompt and response
+  and JSON output encoder.
-  schema assets.
 - The Seriatim registrar provides the transcript input adapter. Its external
   input behavior is defined by the [Seriatim contract](../integrations/seriatim.md).
 - The D&D registrar provides its codecs, extractors, mergers, normalizers,
-  validators, prompt assets, fallback profile asset, and default chains. Its behavioral conventions
+  validators, prompt assets, and default chains. Its behavioral conventions
   are documented in [D&D Module Internals](dnd.md).
 
 The CLI owns the composition that invokes these registrars. A module package
 may register its own family but must not assemble the CLI or make framework
 packages depend on production extensions.
 
-## Semantic Reconciliation
-
-`internal/framework/semanticreconcile` is a domain-neutral strategy used by a
-typed normalize module; it is not itself a selectable stage module. A
-source-backed artifact-family normalizer projects its deterministic records
-into contextual candidates and owned typed record envelopes, supplies its
-chosen prompt identity and resolved LLM profile, and constructs an engine with
-explicit limits. The core filters invalid evidence, assigns contiguous
-one-based request-local candidate numbers, renders bounded candidate and
-transcript materials, invokes the structured-completion boundary, and assesses
-the returned duplicate groups into a stable non-overlapping plan. Candidate
-material declares the exact inclusive number range for the request. Transcript
-unit IDs and evidence range endpoints remain source positions in a separate
-namespace and are never valid candidate numbers.
-
-The normalizer then applies that plan through a typed `ApplicationPolicy`. The
-core preserves ungrouped records, contribution order, and provenance while the
-artifact family owns group guards, field and evidence consolidation, durable
-ID derivation, retry and fallback presentation, classified diagnostics, and
-postconditions.
-These candidate numbers are the concrete private representation of ADR-0013's
-request-local handles; they do not enter the typed value or durable artifact.
-Fewer than two eligible candidates skips model invocation; exceeding a
-candidate or combined-material bound preserves the deterministic result under
-the family's fallback policy. Provider, transport, cancellation, and
-context-construction failures remain execution errors.
-
-When the engine actually makes a proposal call, its typed result carries the
-owned exact proposal response under the same correction contract as other
-eligible producers. Deterministic skip, limit, and fallback outcomes carry no
-model candidate, so a later rejection applies terminal policy without spending
-an ineffective semantic retry.
-
-When proposal assessment or typed group application rejects a structurally
-valid group, the normalizer may return its safe partial value with a
-module-requested retry. A feedback-capable directive supplies bounded
-model-facing correction guidance separately from operator diagnostics and
-retains the exact proposal response as its candidate. The shared stage retry
-mechanism appends that response and guidance to a fresh complete request. A
-structurally invalid completion has no valid candidate and therefore requests a
-feedback-free fresh attempt. On exhaustion, only the final safe fallback and
-its bounded process diagnostic advance to validation.
-
-The core supplies a conservative generic prompt and the single private
-response schema. A domain prompt may substitute its semantic instructions but
-mounts the core-owned protocol and candidate/transcript presentation assets.
-Prompt, schema, policy, and limit identities participate in manifest metadata
-and checkpoint fingerprints. The generic registrar owns production
-registration of those shared assets; a consuming domain registrar owns only
-its domain prompt.
-
 ## Adding Or Changing A Module
 
 1. Choose the pipeline stage and the typed artifact boundary. Put external
    input or durable artifact formats in the relevant integration contract,
    not in this guide or in a private LLM response type.
-2. Define a stable `ModuleSpec` with an explicit execution class, the exact
+2. Define a stable `ModuleSpec` with the exact capabilities and reference
-   capabilities, and reference slots needed for the operation. Model a
+   slots needed for the operation. Model a producer/consumer handoff as an
-   producer/consumer handoff as an artifact-compatible slot; configuration
+   artifact-compatible slot; configuration then chooses an external file or a
-   then chooses an external file or a generated binding.
+   generated binding.
 3. Implement strict option decoding, construction, and the typed stage
    interface. Preserve caller ownership: do not retain mutable request data
    and return defensive copies where an implementation exposes stored data.
-   If declaring correction capability, forward the request correction and
-   retain only the exact validated response that controlled the result.
 4. Register the module through its typed registry helper and add it to the
    owning family registrar. Add a default validator chain only when that
    family owns the behavior; otherwise require an explicit compatible chain.
-   Every rejection path in a validator must provide actionable correction
-   guidance while retaining its stable internal reason code.
 5. Update the selectable-key and chain reference in
    [Configuration](../config.md#production-module-keys), the applicable
    integration contract, and focused tests. Keep the configuration document

docs/internal/overview.md

@@ -25,13 +25,10 @@ physical state roots.
 | Area | Implemented owners | Responsibility |
 | --- | --- | --- |
 | Executable and command boundary | **cmd/notarius**, **internal/cli** | Process entry, command dispatch, configuration discovery, production composition, runtime collaborator setup, durable file placement, and user-facing reporting. |
-| Build information | **internal/buildinfo** | Resolves a stable linked release tag or build metadata for the diagnostic root version command. |
+| Configuration | **internal/core/config** | Defaults, strict YAML parsing, environment overrides, structural validation, effective resolution, redaction, and resolved-composition summaries. |
-| Configuration | **internal/core/config** | ConfigKit document definition, source-aware normalization, runtime conversion, structural validation, safe inspection, effective resolution, and resolved-composition redaction. |
 | Generic models | **internal/core/source**, **internal/core/artifacts**, **internal/framework/contracts** | Source documents and chunks, manifests and provenance, plus typed artifact, reference, validation, output, and structured-completion contracts. |
 | Pipeline framework | **internal/framework/pipeline** | Registries, profile and reference resolution, typed preparation, validation, retry coordination, ordered execution, handoff, and result assembly. |
 | LLM and prompt runtime | **internal/framework/llm**, **internal/framework/promptfs** | Provider-neutral structured completions, scheduling, profile recording, prompt assets, schema registration, and credential-shaped-value redaction. |
-| Semantic reconciliation | **internal/framework/semanticreconcile** | Bounded source-backed candidate preparation, request-local handle proposals, deterministic assessment, typed plan application, and reconciliation identity metadata; see [Module Internals](modules.md#semantic-reconciliation) and [D&D Module Internals](dnd.md#semantic-registry-reconciliation). |
-| Embedded LLM content | **assets** | Read-only centralized LLM-facing content, scoped by its consuming package; see [LLM Runtime](llm.md#prompt-and-schema-assets) and [D&D Module Internals](dnd.md#prompt-construction). |
 | Runtime state | **internal/core/fileio**, **internal/core/debugbundle**, **internal/framework/checkpoint**, **internal/framework/chunkplan**, **internal/framework/chunkmap**, **internal/framework/debug** | Confined atomic files, debug bundles, checkpoint and chunk-plan state, accepted chunk maps, and pipeline-facing debug recording. |
 | Production extensions | **internal/modules/generic**, **internal/modules/seriatim**, **internal/modules/dnd** | Domain-neutral extensions, Seriatim input support, and D&D extraction families registered into the production catalog. |
 
@@ -51,9 +48,8 @@ the CLI composition boundary.
   composition, and path safety.
 - [LLM Runtime](llm.md): structured completion, scheduling, prompt assets,
   profiles, and secret handling.
-- [Module Internals](modules.md): generic extension registration, artifact
+- [Module Internals](modules.md): generic extension registration, module
-  families, module construction, semantic reconciliation, validation, and
+  construction, validation, and reference mechanics.
-  reference mechanics.
 - [D&D Module Internals](dnd.md): shared D&D extractor conventions, generated
   reference projections, and lane-specific exceptions. Durable D&D and
   Seriatim data shapes remain in the [integration contracts](../integrations/).

docs/internal/pipeline.md

@@ -10,11 +10,11 @@ own durable output shapes. Concrete production extensions are covered by
 ## Boundary
 
 The pipeline framework accepts a resolved composition, registries, shared
-dependencies, input bytes, a supplied prompt session, and state/debug
+dependencies, input bytes, and state/debug collaborators. It returns logical
-collaborators. It returns logical output files, normalized artifacts, recorded
+output files, normalized artifacts, recorded rejections and warnings, manifest
-rejections, grouped diagnostics, manifest provenance, and checkpoint decisions. The
+provenance, and checkpoint decisions. The CLI owns process arguments,
-CLI owns process arguments, configuration discovery, session resolution,
+configuration discovery, physical roots, and placement of returned output
-physical roots, and placement of returned output files.
+files.
 
 The framework has one fixed shape:
 
@@ -32,47 +32,25 @@ Resolution turns a configured pipeline profile into a **ResolvedPipeline**.
 It normalizes the pipeline and lane identities, applies stage defaults, selects
 requested lanes where that is supported, resolves validator chains, checks
 module capabilities and typed artifact compatibility, validates options, and
-assigns a deterministic resolved-composition digest. A correction protocol is
+assigns a deterministic resolved-composition digest. The resolved pipeline
-selected from each eligible LLM-backed producer specification and becomes part
+contains bindings and declared reference targets, not external reference bytes.
-of that resolved identity; only `single_response_v1` is currently supported.
+Configuration resolution supplies the selected profile and catalog; see
-Preparation rejects an LLM-backed producer that combines a non-empty validator
-chain with positive producer retries unless it declares that protocol. Producers
-without validators or without retries remain valid without correction support.
-The resolved pipeline contains bindings and declared reference targets, not
-external reference bytes.
-After selection, the resolver applies command, binding, and pipeline profile
-precedence to LLM-backed bindings and validators only; prompt defaults remain
-an empty resolved binding profile. It resolves structural output repair
-separately: a binding's `structured_output_repair_attempts` value wins, then a
-pipeline value applies to LLM-backed bindings and validators, and omission
-leaves the prompt-owned policy intact. An explicit repair value on a
-deterministic binding is rejected. Resolved bindings own copied repair values,
-and these effective values are part of the digest, so execution and checkpoint
-consumers do not repeat profile inheritance or configuration resolution.
-Each LLM request receives its own copy of that resolved value. PromptKit spends
-it only for structural correction inside one completion; the runner's binding
-retry policy remains the separate outer budget for complete stage attempts.
-Configuration resolution supplies the selected overlay and catalog; see
 [Configuration Internals](configuration.md).
 
 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. For a positive slot limit, it reads at most the limit plus one byte
+provenance. A generated-artifact selector remains declared but has no bytes
-and rejects overflow before retaining content. A generated-artifact selector
+until its producing step completes.
-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. The
+chunker, stage-local validators, every typed lane, and output encoder with
-prepared producer metadata preserves each selected correction protocol, and
+cloned options, references, and shared dependencies. It also collects stable
-the resolved digest carrying that metadata participates in checkpoint identity.
+checkpoint fingerprints. Missing registrations, incompatible typed entries,
-Each registered builder receives its own cloned build request immediately
+nil implementations, and constructor failures are reported before source
-before its module-owned code runs. Preparation also collects stable checkpoint
+parsing or any stage operation begins.
-fingerprints. Missing registrations, incompatible typed entries, nil
-implementations, and constructor failures are reported before source parsing
-or any stage operation begins.
 
 An output encoder can opt into source-evidence publication through its output
 policy. Preparation keeps the configured lane allowlist and active lanes
@@ -97,21 +75,10 @@ codec, checks its complete schema and media identity, and records a content
 digest plus bounded producer provenance. A missing, ambiguous, invalid, or
 incompatible producer prevents the consumer step from starting.
 
-Resolution receives only exact stage-and-lane operational reference overrides.
-The CLI may offer broader pipeline- or lane-scoped selectors, but expands and
-arbitrates those before entering the framework. External overrides are applied
-after configured external defaults and local bindings. They cannot coexist
-with a generated binding for the same target and slot, and external unbinds do
-not remove generated handoffs.
-
 ## Execution And Ordering
 
 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
@@ -139,59 +106,18 @@ 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, codec-decoded typed candidates, or serialized codec
+their target: chunks, typed values, or serialized codec bytes. They may
-bytes. Each typed validator receives a newly decoded value from the one
+approve, approve with warnings, reject, or fail. A rejection is an ordinary
-candidate serialization for that attempt, while serialized validators receive
+pipeline result; a validator error is a framework error.
-separately owned representation bytes and schema metadata. They may approve,
-approve with warnings, reject, fail, or be skipped when a runtime prerequisite
-is unavailable. The shared executor settles every configured validator in
-order. A failed LLM-backed validator retries only itself against the same
-immutable candidate; it does not regenerate the producer or alter the
-validator request. Rejections stop that validator, while other configured
-validators still run. The executor retains ordered results, bounded
-deduplicated correction guidance from rejections, and only the final exhausted
-failure outcome for each validator. The correction builder keeps first
-occurrence order, omits internal reason codes, validator names, and operator
-messages, and requests one complete replacement. Missing guidance or an
-oversized aggregate is a framework contract error; guidance is never inferred
-or truncated.
 
 The runner applies the binding's retry policy around a stage operation and its
-complete validation chain. It preserves terminal diagnostics only from the final accepted
+complete validation chain. It preserves warnings only from the final accepted
-or rejected attempt, plus one fixed validation-incomplete warning per validator whose execution
+or rejected attempt. Cancellation stops retries. Normalizer-specific retry
-budget was exhausted under `warn_continue`. Cancellation stops retries.
+directives consume this same budget and validate any final safe fallback through
-Normalizer-specific retry directives consume this same budget and validate any
+the normalizer chain.
-final safe fallback through the normalizer chain. A directive may carry bounded
-correction guidance only when it also exposes the exact latest
-`single_response_v1` candidate. The state machine then uses the same replacement
-request shape as validator correction. A directive without guidance clears any
-prior correction and starts a fresh attempt, which preserves structural retry
-behavior when no valid response exists.
-
-The artifact-neutral producer-attempt state machine owns that shared budget,
-attempt provenance, semantic-correction material, and terminal-policy
-selection. It accepts producer and complete-validation closures, so artifact
-materialization, cache handling, checkpoints, and debug output stay at the
-operation boundary. It distinguishes operational, structural, module-requested,
-and validator-semantic retries. Model feedback from either semantic source is
-available only for a valid latest `single_response_v1` candidate. A
-deterministic or no-model validator rejection instead settles the semantic
-policy immediately, while a feedback-free module directive remains an ordinary
-fresh retry. Structural-output errors alone use the structural policy, and
-validation failure without rejection settles the validator-failure policy
-without regenerating the producer.
-
-Chunk planning uses this state machine for generated plans. A rejected or
-validation-incomplete automatic cache hit is not model material and therefore
-falls through to a fresh initial generation at producer attempt one; it neither
-receives a correction, consumes retry budget, promotes cached-candidate
-diagnostics, nor overwrites the stored record. An incomplete cache validation
-under `fail_run` terminates instead. Only a newly generated, completely
-validated plan is published to the chunk-plan store. Rejected plans never
-advance, and validation-incomplete plans remain unpublishable.
 
 After terminal lane work, the runner assembles manifest provenance, normalized
-artifacts, rejections, final grouped diagnostics, and an optional accepted chunk map. When an
+artifacts, rejections, warnings, and an optional accepted chunk map. When an
 output policy selected evidence lanes, it decodes accepted serialized normalize
 outputs through their registered codecs and invokes the prepared typed
 projectors. Rejected or absent lanes contribute nothing. This reconstruction is
@@ -202,15 +128,6 @@ The CLI publishes those files only after the runner returns without a framework
 error. Logical file names and schemas are defined by the [output integration
 contracts](../integrations/).
 
-For every completed producer disposition, the runner projects one bounded
-validation summary to the manifest, the affected rejection when present, and
-the CLI result receipt. The summary records status, configured-order rejecting
-validators and reason codes, incomplete validators, producer-attempt count,
-and terminal action. It contains no operator message, correction guidance, or
-model response. `complete`, `rejected`, and `incomplete` describe the final
-candidate disposition; a run-level `incomplete` status indicates at least one
-current-run output advanced under `warn_continue`.
-
 ## Checkpoint And Debug Hooks
 
 The runner receives checkpoint and debug interfaces rather than roots. It
@@ -220,26 +137,10 @@ handoff. Generated-reference dependencies participate in checkpoint decisions.
 Selective recomputation can require a canonical accepted normalized predecessor
 before a dependent lane starts.
 
-The runner writes successful checkpoint artifacts only after complete accepted
-validation. Chunk plans follow the same rule for publication. A rejection,
-invalid structured response, or incomplete validation is never reusable state;
-the current run may still hand off an otherwise valid `warn_continue` result
-according to its terminal policy. The runner carries private reuse eligibility
-through extract, merge, normalize, and generated-reference handoff. Any stage
-derived from incomplete validation skips both checkpoint lookup and all
-checkpoint publication even when that stage's own validation completes.
-External references and fully validated generated references remain eligible.
-Attempt debug records retain safe kind,
-validator, repair-usage, policy, and terminal-decision provenance. Full
-assistant and correction content remains confined to the requested detailed
-LLM trace.
-
 Debug recording is attempt-scoped and application-owned. A failure to persist
 required debug data is a framework error. State roots, persistence, reason-code
 meanings, resume, and cleanup are intentionally owned by
 [Run State Internals](state.md) and [Operations](../operations.md).
-Extract-validator trace scopes include the current chunk ordinal so concurrent
-chunks cannot overwrite one another's validator attempts or LLM artifacts.
 
 ## Invariants To Preserve
 

docs/internal/state.md

@@ -1,9 +1,5 @@
 # Run State Internals
 
-LLM debug response artifacts and their safe per-call references retain an
-optional terminal execution summary when one is available. This metadata is
-diagnostic only and does not change receipts, checkpoints, or aggregate usage.
-
 This document describes the implementation collaborators behind output, cache,
 and debug state. User-visible fields belong in [Configuration](../config.md),
 and physical layout, retention, recovery, reason codes, and cleanup belong in
@@ -36,31 +32,19 @@ owned by the [Accepted Chunk Map contract](../integrations/chunk-map.md).
 
 `internal/framework/chunkplan` owns source-addressed plan storage, validation,
 and atomic publication. Its store is constructed only when the selected mode is
-not `bypass`. It preserves rooted entry checks while creating new cache roots
+not `bypass`.
-and source-digest directories with requested mode `0777`, then creates an
-atomic temporary file through rooted `O_CREATE|O_EXCL` with requested mode
-`0666` before sync and rename.
 
 `internal/framework/checkpoint` owns checkpoint identity, manifests, payload
 codecs, loader, and recorder. The CLI constructs a recorder whenever checkpoint
 recording is enabled and constructs a loader only for a `--resume` invocation.
-The recorder writes manifest and payload JSON through
-`fileio.WriteJSONWithProcessPermissions`, whose confined atomic writer creates
-new directories with requested mode `0777` and temporary files with requested
-mode `0666` before publication.
 Identity incorporates explicit stable semantic fingerprints collected from
 prepared modules and validators in addition to configuration, input,
-references, runtime overrides, observed LLM profiles, and the LLM runtime's
+references, runtime overrides, and LLM profiles.
-non-secret effective profile-source identity. A profile source change therefore
-causes a cold miss even when the configured profile ID remains unchanged.
 The serialized
 `workspace_schema_version` identifiers are frozen wire-compatibility fields;
 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
@@ -75,13 +59,12 @@ Ordinary resume loads extract, merge, and normalize checkpoints progressively
 and may execute later lane stages after an earlier cache miss. Selective
 recomputation instead asks the loader for the required producer's accepted
 normalize artifact. That lookup reuses the existing normalize files, requires
-workspace schema v4 plus an exact non-empty invocation identity, and deliberately
+workspace schema v3 plus an exact non-empty invocation identity, and deliberately
 does not require extract or merge checkpoint files or dependency fingerprints.
 The runner performs canonical codec and producer-provenance validation before
 cloning the artifact into normal step output. Success restores only stored
-normalize diagnostics and emits one normalize decision; failure retains the
+normalize warnings and emits one normalize decision; failure retains the files,
-files, records the decision, and stops without executing the producer or
+records the decision, and stops without executing the producer or consumer.
-consumer.
 
 The loader assigns a typed category and reason code at each validation site;
 diagnostic prose is not classified after the fact. The runner then applies
@@ -97,10 +80,7 @@ and debug-summary JSON.
 canonical operator-facing reason-code reference.
 
 `internal/core/fileio` provides confined atomic file writes used by state
-collaborators. Its exact-mode writer remains available to output and debug
+collaborators. The chunk-plan store retains its stronger entry validation.
-callers; its process-permission writer is used by checkpoints. The chunk-plan
-store retains its stronger rooted entry validation. [Operations](../operations.md#cache-provisioning)
-owns cache mode and provisioning guidance.
 
 The CLI constructs selective-recomputation policy from resolved generated
 artifact dependencies. It forces the selected step and transitive consumers,
@@ -112,7 +92,7 @@ owns the operator workflow and stable reason-code meanings.
 
 `internal/core/debugbundle` allocates an explicitly requested per-run bundle
 with `summary/` and `trace/` roots. `SummaryWriter` persists redacted command,
-resolution, run, final grouped diagnostic, and failure artifacts. `internal/framework/debug`
+resolution, run, warning, and failure artifacts. `internal/framework/debug`
 implements the pipeline-facing trace recorder under the trace root.
 
 The CLI allocates a bundle before pipeline resolution and treats requested

docs/operations.md

@@ -5,23 +5,6 @@ This is the canonical guide for operating Notarius runtime state. The
 [Configuration](config.md) owns fields, defaults, and precedence. Maintainers
 who need implementation mechanics should read [Run State Internals](internal/state.md).
 
-## Source Deployment
-
-Linux is the supported deployment platform. Install a pinned source release
-with the Go version declared in `go.mod` (currently Go 1.25.5):
-
-~~~sh
-GOWORK=off go install \
-  gitea.maximumdirect.net/eric/notarius/cmd/notarius@vMAJOR.MINOR.PATCH
-~~~
-
-Pin the exact tag in deployment automation rather than following a branch.
-Use [`notarius --version`](cli.md#command-summary) as a diagnostic after
-installation; its syntax and semantics are owned by the [CLI reference](cli.md).
-The maintainer publication process, including tag guards and verification,
-belongs to [Source Releases](release.md). macOS builds are best-effort for
-development, and Windows is unsupported.
-
 ## State Surfaces
 
 Each run can use independent roots with different retention and access-control
@@ -50,88 +33,15 @@ directory selects a per-user root:
 
 The field definitions and configuration examples are in [Configuration](config.md).
 On supported Unix systems, output directories and files are created with
-requested modes **0755** and **0644**; debug directories and files use
+requested modes **0755** and **0644**. Chunk-plan, checkpoint, and debug
-**0700** and **0600**. The operating system's umask may impose stricter output
+directories and files use **0700** and **0600**. The operating system's umask
-or debug modes. Chunk-plan and checkpoint caches instead request maximum modes
+may impose stricter output modes. Cache and debug roots may contain sensitive
-of **0777** for new directories and **0666** for new files, including atomic
+source-derived data, so provision them for one trusted account or service. An
-temporary files. The kernel applies the service's umask and applicable default
+output bundle can also contain source content when its JSON output enables
-ACLs when those entries are created.
-
-## Cache Provisioning
-
-Cache locations select where Notarius writes, not who can access them. A
-private service can use a restrictive umask:
-
-~~~sh
-umask 0077
-notarius run example --config /etc/notarius/config.yml --input /srv/input.txt
-~~~
-
-A trusted-group deployment can provision a setgid cache root and use a
-group-oriented umask (or an equivalent default ACL):
-
-~~~sh
-install -d -m 2770 -g notarius-operators /srv/notarius/chunk-plans /srv/notarius/checkpoints
-umask 0007
-notarius run example --config /etc/notarius/config.yml --input /srv/input.txt
-~~~
-
-Setgid and default ACLs control inherited group ownership and access policy;
-Notarius does not copy a parent directory's literal mode bits. Cache state is
-reconstructible but can contain source-derived data, so operators own its
-access and retention policy. Existing cache inodes retain their prior modes
-after an upgrade. Recreate a cache beneath correctly provisioned parents, or
-stop writers and perform a deliberate administrative migration when a
-whole-tree change is required.
-
-Cache publication remains atomic and stored records remain validated. Those
-guarantees do not add cross-process locking or transactional coordination for
-simultaneous writers to one checkpoint identity.
-
-Output bundles can also contain source content when JSON output enables
 evidence publication. Apply an appropriate umask and output-root access policy
 before enabling that option; the requested output modes alone may not be
 suitable for transcript-bearing bundles.
 
-## PromptKit Profile Deployment
-
-Profile deployment has four distinct layers:
-
-| Layer | Owner | Operational role |
-| --- | --- | --- |
-| Prompts and schemas | Notarius module families | Embedded request and structured-output definitions. They are not deployment profile files. |
-| Fallback profiles | Notarius module families | Embedded application defaults, including D&D's `dnd-extraction` profile. |
-| Built-in profiles | PromptKit | Upstream catalog entries available when no higher-precedence source defines an ID. |
-| Operator profiles | Deployment filesystem | Complete environment-specific definitions selected by `promptkit.profile_file` or `promptkit.profile_dir`. |
-
-The maintained D&D pipeline uses the workload ID `dnd-extraction`. The
-embedded fallback makes that ID usable without an operator file. Production,
-development, and local deployments can each install a different complete
-definition for the same ID, retaining the pipeline while choosing their own
-model, backend, timeout, or reasoning policy. An operator definition wins over
-the fallback; it is not merged with it. The configuration field and full
-precedence rules are owned by [Configuration](config.md#promptkit-profiles).
-
-Use a profile source owned by the service account, keep it readable only by
-the intended operator, and supply provider credentials through the service
-environment—not in the Notarius configuration or profile YAML. The maintained
-[LLM profile](../examples/llm-profiles/dnd-extraction.yml) is secret-free and
-can be copied as a format starting point. Validate a deployment without a
-provider call or credentials:
-
-~~~sh
-notarius config validate --config /etc/notarius/config.yml --pipeline dnd-session
-~~~
-
-An unset optional `api_key_env` reaches the provider without authorization and
-may receive a 401 or 403 response.
-
-Configured PromptKit profile paths resolve from the file that supplies their
-surviving declaration. The complete example's
-`./llm-profiles/dnd-extraction.yml` path is therefore relative to that example.
-Use absolute paths such as `/etc/notarius/profiles/dnd-extraction.yml` for
-services and containers when that is clearer for the deployment.
-
 ## Run Lifecycle
 
 Use the [run command](cli.md#run) to start a pipeline. A valid invocation loads
@@ -139,59 +49,10 @@ and resolves configuration before module preparation and source parsing. It
 then performs any permitted cache lookup, executes the pipeline, and publishes
 logical output files only after a successful runner result.
 
-On success, the command reports the output bundle path. A run with actionable
+On success, the command reports the output bundle path. A warning-bearing run
-process warnings still succeeds and reports warning-group and occurrence counts
+still succeeds and reports its warning count on standard error. Errors and
-on standard error; advisory and observation findings do not produce a warning
-line. Errors and
 their exit classes are defined in the [CLI reference](cli.md#output-streams-and-exit-statuses).
 
-## Validation Retries And Terminal Outcomes
-
-When debug recording is enabled, per-call response artifacts include the
-terminal execution summary for retry, repair, timing, and presence-aware usage
-diagnosis. Normal output, receipts, and warnings do not aggregate or publish
-this diagnostic metadata.
-
-Each producer binding has one outer **retries** budget. It covers complete
-producer attempts for operational failures, invalid structured output,
-normalizer fallback retry, and semantic correction. It is independent from
-PromptKit's structural-repair calls inside one completion, its configured
-`promptkit.transient_retries` built-in HTTP attempts, and an LLM-backed
-validator's own retry budget. The transient setting defaults to two additional
-attempts for eligible provider statuses; set it explicitly to zero when an
-operator needs one HTTP attempt per generation. A semantic correction rebuilds
-the ordinary producer request and supplies only the latest rejected model
-response plus aggregated validator guidance; it is not a conversation replay.
-
-These budgets multiply only by their declared scopes. With two outer producer
-retries, two transient retries, and one structural repair, a single producer
-can issue up to 18 HTTP attempts: three producer attempts, each with an initial
-generation and one repair generation, each allowing three HTTP attempts. This
-is an illustration, not a total-deadline or exactly-once guarantee. Every
-built-in HTTP attempt has its own generation timeout; caller cancellation
-remains the overall authority and interrupts Retry-After waiting. The shared
-Notarius scheduler keeps its permit through those waits, so retry budgets can
-increase latency and provider cost. Observed usage can remain incomplete when
-providers omit accounting fields.
-
-After the applicable budgets are exhausted, the resolved
-[`validation_policy`](config.md#pipelines) determines the result. Structural
-failure and semantic rejection normally fail the run; an explicit
-`reject_output` records a rejection and allows unrelated work to finish. A
-validator execution failure normally uses `warn_continue`, which keeps an
-otherwise accepted result in the current run with `incomplete` validation
-provenance. It emits one bounded warning for every validator whose execution
-budget was exhausted. A corrected result that later passes validation does not
-retain diagnostics from abandoned attempts.
-
-Treat a successful process exit as a completed run, not as proof that every
-candidate was fully validated. Inspect the receipt's `validation_status`,
-`validation_summaries`, rejection count, and warning group and occurrence
-counts when an orchestrator requires complete validation. The durable fields
-and their meanings are owned by the
-[run-result receipt](integrations/run-result.md) and
-[published JSON output contract](integrations/json-output.md).
-
 ## Output Bundles
 
 Each successful run receives a generated safe run identifier and writes beneath:
@@ -213,9 +74,9 @@ are defined in [Accepted Chunk Map](integrations/chunk-map.md). An optional
 [evidence context](integrations/evidence-context.md) contains source-unit text
 and metadata. It is not a cache or debug artifact: retain it with the output
 bundle only for as long as consumers need it, and apply source-content access
-controls to the entire bundle. Its selected source-unit excerpt may include
+controls to the entire bundle. Selected lanes may collectively cite most of a
-every source unit once when coverage is broad or its configured window is
+transcript, so a broad allowlist can make the evidence artifact nearly as
-large, so do not assume a byte or token reduction or reduced sensitivity.
+sensitive and large as the source itself.
 
 ## Chunk-Plan Cache
 
@@ -241,9 +102,7 @@ The configured cache mode controls one invocation:
 A reused plan is still materialized and validated against the current source.
 If a prior plan no longer gives acceptable results, use a refresh run rather
 than editing cache files. Deleting a plan is recoverable but can repeat costly
-chunking work. A plan accepted only under incomplete validation is not
+chunking work.
-published, and a rejected cache hit falls through to ordinary generation rather
-than becoming a correction candidate.
 
 ## Checkpoint Recording, Resume, And Recompute
 
@@ -258,21 +117,9 @@ compatible recorded work. A resume request fails when checkpoint recording is
 disabled. Without **--resume**, a recording-enabled run executes normally and
 does not load checkpoint state. Compatibility includes the resolved pipeline,
 input, selected lanes, runtime overrides, reference provenance, LLM-profile
-provenance, the effective PromptKit profile-source fingerprint, and
+provenance, and prepared-component fingerprints. A changed identity produces a
-prepared-component fingerprints. When a local PromptKit backend is configured,
+cold miss; Notarius does not migrate, rewrite, or delete older checkpoint
-compatibility also includes a non-secret fingerprint of its endpoint. Changing
+directories.
-profile content or the local endpoint causes a cold miss; changing only the
-local concurrency limit does not. A changed identity produces a cold miss;
-Notarius does not migrate, rewrite, or delete older checkpoint directories.
-Reasoning-effort inheritance, replacement, and explicit clearing are distinct
-runtime identities, so checkpoints created under one state are not reused by
-either of the others.
-
-Only accepted, completely validated chunk, extract, merge, and normalize
-results are checkpointed for reuse. Rejected, structurally invalid, and
-validation-incomplete producer results remain non-reusable, even when a
-`warn_continue` result advanced during its original run. A resumed invocation
-therefore reruns that producer rather than treating degraded state as accepted.
 
 Checkpoint state is confined below an identity-specific path:
 
@@ -327,19 +174,12 @@ Only a [debug-enabled run](cli.md#run) creates a bundle:
   trace/
 ~~~
 
-The summary contains redacted invocation and resolution information, including
+The summary contains redacted invocation and resolution information plus run,
-`effective-config.yml` and the separately redacted resolved pipeline, plus run,
+warning, checkpoint, chunk-plan, and terminal reporting artifacts. The trace
-final grouped diagnostic, checkpoint, chunk-plan, and terminal reporting artifacts. Attempt
+contains allowlisted application diagnostic records and can include source or
-terminal records contain bounded attempt kinds, validator outcomes, policy,
+derived application data. Neither surface is a cache input. Do not treat a
-decision, PromptKit repair count, and usage; they do not contain assistant
+debug bundle as safe to share merely because its configuration summary is
-responses or complete correction messages. The trace contains allowlisted
+redacted.
-application diagnostic records and can include source, model, and correction
-content. Neither surface is a cache input. Do not treat a debug bundle as safe
-to share merely because its configuration summary is redacted. Invocation
-metadata omits reasoning effort when it is inherited, records the replacement
-value when one is supplied, and records an empty value when inherited reasoning
-was explicitly cleared. It records `config_overlay` only when a non-base
-configuration overlay was selected.
 
 Notarius never creates debug state without an explicit request and never
 automatically deletes a requested bundle. If allocation succeeds, the command
@@ -367,74 +207,10 @@ or automatic cleanup command.
 
 ## Operational Limits
 
-Provider execution settings and the generation timeout come from the selected
+Provider retries and timeouts are supplied by the selected Scriptorium profile.
-PromptKit profile. The invocation-only **--reasoning-effort** and
+Module retry settings and concurrency limits are configuration contracts; see
-**--clear-reasoning-effort** controls may replace or clear that profile setting
+[module bindings](config.md#module-bindings-and-validators) and
-for all LLM-backed calls in one run without changing the profile. PromptKit
-v0.11.0 also retries eligible transient HTTP failures with its built-in default
-of two additional attempts per generation. This retry work is separate from
-structural output repair, which happens within one structured-completion call. Its
-effective `structured_output_repair_attempts` limit is resolved from the
-selected binding, then the pipeline, then the prompt declaration; see
-[module bindings](config.md#module-bindings-and-validators). This is distinct
-from Notarius binding **retries**, which rerun the complete module operation
-and validation chain and do not consume or replenish the structural-repair
-limit. The maintained production prompts declare one repair attempt, paid only
-after a structural failure. One structured completion with repair budget **R**
-contains at most **R + 1** serial generations. Each generation can now contain
-more than one provider call when PromptKit retries an eligible transient
-failure. LLM-backed validators have their own corresponding invocation and
-repair budgets. These are bounds on attempted work, not a promise that every
-call reaches a provider.
-
-Timeouts are layered. Caller cancellation is the outer authority. A positive
-effective generation timeout adds an inner request deadline to each built-in
-generation attempt, while zero disables only that generation deadline. The HTTP
-client timeout remains a transport-wide cap. Notarius does not add another
-timeout around PromptKit. Retries and repairs are serial within the same caller
-context, so their worst-case latency and cost can exceed the structural-repair
-bound above; provision run deadlines and provider budgets accordingly.
-Credentials remain optional unless the selected
-PromptKit profile requires one, in which case preparation fails before a
-provider call when its configured credential is unavailable.
-The pinned upstream boundary and profile-format links are in
-[PromptKit Integration](integrations/pkg-promptkit.md).
-
-Concurrency has two independent layers. Notarius **total_llm** defaults to 16
-and is the application-wide provider-call limit shared by all backends,
-modules, retries, and validators. PromptKit may impose a narrower admission
-limit for the selected backend. The effective active-generation bound is the
-intersection of the Notarius limit, any PromptKit backend limit, and work made
-available by the pipeline. Built-in OpenRouter profiles use PromptKit's
-upstream backend limit; endpoint-only profiles have no PromptKit backend limit
-and remain bounded by Notarius. For the configured local backend, a zero
-**concurrency_limit** leaves only the Notarius scheduler as a call limit. A
-positive value makes the effective active local-generation bound the smaller
-of **total_llm** and that local limit, so a local limit of four permits no more
-than four active local generations.
-
-The Notarius scheduler admits one logical structured completion and holds that
-permit while PromptKit performs its serial corrective calls. PromptKit applies
-its selected-backend admission to each provider call; Notarius does not
-reacquire a permit or add another scheduler for a repair.
-
-For a positive local limit, PromptKit owns its default waiting capacity and
-admission behavior. When a PromptKit backend has admitted all active and queued
-work, a new call fails as capacity exhaustion before generation. The adapter
-maps that failure to Notarius's existing provider-neutral capacity error and
-does not retry it. The calling stage's configured retry policy applies
-normally, and the run fails if those attempts are exhausted. Caller
-cancellation remains authoritative. Configuration contracts are documented
-under [PromptKit profiles](config.md#promptkit-profiles) and
 [concurrency](config.md#concurrency-output-cache-and-debug). Extract-worker
 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/agents.md

@@ -1,90 +0,0 @@
-# Agent Policy
-
-**Base Policy Version:** 1.1
-
-**Last Updated**: 2026-09-25
-
-**Upstream Source:** `policy` commit `45591a79004c6811950f14dca554f6ff69b7f58e`.
-
-Notarius adaptations preserve operator choice, existing explicit contracts, and
-the deployment-permissions example below.
-
-## Purpose
-
-Agents working in this repository must read and adhere to the following house rules.
-
-## Implementation Discipline
-
-Simplify the mechanism, not the user's choices.
-
-**KEY PRINCIPLES:** Write the simplest idiomatic code that satisfies the user's
-request. Do not implicitly strengthen requirements, restrictions, or guarantees
-beyond what the user actually requested.
-
-**Keep implementation machinery proportionate.** Use straightforward,
-idiomatic code and introduce only the machinery needed to support the requested
-behavior and flexibility. Optimize for conceptual simplicity and
-maintainability, not for the fewest lines, fewest options, or narrowest product
-surface.
-
-**Do not invent restrictions.** Do not reject, prohibit, constrain, cap,
-harden, or otherwise narrow behavior unless required by the user, an explicit
-repository contract, or an unavoidable correctness constraint. Preserve
-operator and caller choice where policy has not been established. If an
-additional restriction appears advisable, present it as a decision rather than
-silently implementing it.
-
-**Do not invent guarantees.** Do not strengthen public contracts, guarantees,
-or invariants beyond those expressly requested by the user.
-
-**Use the standard library.** For example: in almost every case, the best
-approach to copying files is to use the standard library. Writing custom code to
-implement power-loss protection at the application level, or to guard against
-bad actors with privileged and concurrent access to the host's filesystem,
-is wasteful, unnecessary, and not idiomatic. Stick to the simple, standard, and
-idiomatic approach unless another path is expressly requested by the user.
-
-**An implementation detail is not repository policy.** Tests and documentation
-must not elevate incidental behavior into a durable guarantee or restriction
-unless that behavior was expressly selected as part of the contract. Existing
-explicit contracts remain authoritative; changing or weakening one requires a
-deliberate decision rather than being inferred from these principles.
-
-[ADR-0017](../adr/0017-defer-cache-access-policy-to-deployment.md) illustrates
-why Unix deployments own cache access policy through permissions, umask, setgid,
-and default ACLs. Notarius retains its separately adopted correctness boundaries.
-
-## Git Commit Policy
-
-By default, create a commit after completing each coherent unit of work, using a
-concise, plain-English message describing what changed. This policy is standing
-authorization to create those local commits; a separate user request is not
-required. An explicit user instruction to leave work uncommitted takes precedence.
-
-A unit of work is a focused, reviewable outcome, including its relevant tests and
-documentation. Do not commit after every intermediate edit or create empty commits.
-Complete the appropriate validation before committing. If work is incomplete or
-validation is blocked, report that state rather than presenting it as completed.
-
-Before committing:
-
-1. Run `git status --short` and review the relevant diff, including any staged
-   changes. Identify changes that predate the current unit of work.
-2. Exclude secrets, local environment files, generated junk, and unrelated changes.
-3. Stage only the files or hunks belonging to the completed unit. Use `git add .`
-   only when every included change belongs to that unit. Do not disturb unrelated
-   staged or unstaged work.
-4. Review `git diff --staged` and run appropriate checks for the change. Do not
-   repeat checks already passed for unchanged content merely to create a commit.
-5. Review `git log --oneline -n 10` and use
-   `git commit -m "<concise plain-English commit message>"`.
-6. Report the commit identifier and any remaining uncommitted work.
-
-If the unit cannot be safely separated from pre-existing work, leave it uncommitted
-and explain the overlap rather than silently including that work. If a commit
-fails, preserve the changes and report the failure; do not bypass hooks.
-
-Default commit authorization does not authorize pushing, publishing, amending,
-resetting, reverting, or rewriting history. Those actions require a separate user
-instruction. Do not use `git commit -a` or `git commit --no-verify` to bypass the
-staging and validation discipline above.

docs/policy/architecture.md

@@ -1,25 +1,11 @@
 # Architecture
 
-**Base Policy Version:** 1.1
-
-**Last Updated**: 2026-09-25
-
-**Upstream Source:** `policy` commit `45591a79004c6811950f14dca554f6ff69b7f58e`.
-
-Notarius adapts the base template to its fixed pipeline, artifact families,
-external adapters, state boundaries, and source-only distribution.
-
 This document defines the intended high-level architecture of Notarius and the
 invariants that changes must preserve. Implemented component details belong in
 [Internal Overview](../internal/overview.md) and its linked documents. The
 reasoning behind significant architectural choices belongs in
 [ADRs](../adr/).
 
-An adopted constraint can govern future changes without implying that every
-component it could govern exists. Descriptions of implemented structure must
-remain accurate; proposals and transition status belong in roadmaps and ADRs.
-Constraints reflect selected requirements, not incidental implementation choices.
-
 ## System Shape
 
 Notarius is a small, dependency-light Go application for extracting structured
@@ -38,12 +24,6 @@ DAGs or a general workflow language. Every stage remains explicit; general
 chunking, merging, or normalization behavior must not be hidden inside an
 extractor.
 
-A stage module is one configured implementation of one pipeline stage. An
-artifact family is the cohesive domain feature that owns an artifact across
-the explicit stages and supporting codecs, validators, prompts, identity
-rules, and reference projections. Artifact-family ownership does not combine
-stages or alter the fixed pipeline.
-
 Input and chunking are pipeline-wide. Each selected artifact lane owns its
 extract, merge, and normalize stages, and the output stage aggregates the run's
 lane outcomes.
@@ -52,8 +32,6 @@ Notarius is contract-first without being abstraction-heavy. Interfaces and
 extension points should protect demonstrated boundaries. New abstraction is not
 itself an architectural goal.
 
-Implementation discipline is owned by [Agent Policy](agents.md).
-
 ## Layers And Dependency Direction
 
 The application boundary is the composition root and may depend on concrete
@@ -61,24 +39,11 @@ implementations. Domain-neutral model and framework layers provide reusable
 policy, contracts, and orchestration. Concrete input, pipeline, output, and
 validation extensions depend inward on those generic layers.
 
-Semantic reconciliation is one such domain-neutral framework mechanism. It
-prepares bounded source context, invokes a shared model-judgment protocol,
-validates proposals, and applies safe plans through typed policies supplied by
-the consuming artifact family. It does not own domain identity, durable IDs,
-warning semantics, or artifact construction rules.
-
 Generic layers must not depend on production extensions. Concrete extensions
 must not compose the application or take ownership of process behavior. The
 current packages implementing these layers are inventoried in
 [Internal Overview](../internal/overview.md).
 
-The root `assets` package is a content-only dependency leaf. It may expose a
-read-only embedded filesystem, but it must contain no business logic and must
-not depend on `internal` packages or PromptKit. Consumers scope that filesystem
-to the content they own; the root package is not a behavioral registry or a
-public extension contract. The rationale and compatibility consequence are
-recorded in [ADR-0011](../adr/0011-centralize-llm-assets.md).
-
 The following dependency boundaries are mandatory:
 
 - extractors and validators do not depend on concrete input adapters;
@@ -108,12 +73,6 @@ 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
@@ -162,9 +121,8 @@ lanes, validators, and LLM profile: the canonical source digest selects the
 plan, while the current run still applies its configured chunk validators to
 the materialized chunks.
 
-The framework owns orchestration, origin enrichment, aggregation, and handoff
+The framework owns orchestration and handoff provenance. Modules return logical
-provenance. Modules return logical results and classified diagnostics; they do
+results and warnings; they do not own CLI reporting, physical output, cache, or
-not own CLI reporting, physical output, cache, or
 debug roots, durable file placement, or checkpoint and debug lifecycle.
 
 After pipeline-wide chunking, extraction uses bounded framework concurrency.
@@ -176,53 +134,26 @@ may overlap. The framework must not create unbounded goroutines per lane or
 chunk.
 
 Completion timing does not choose public ordering or errors. The coordinator
-orders accepted artifacts, grouped diagnostics, rejections, checkpoint events, and
+orders accepted artifacts, warnings, rejections, checkpoint events, and
 framework errors by stable pipeline scope. Rejections do not cancel unrelated
 work. A framework error cancels derived work, prevents undispatched work from
 starting, waits for started work, and prevents output encoding.
 
-Warnings are process-only signals: configuration degradation, approved fallback,
-or incomplete configured validation. Quality uncertainty and grounding findings
-are advisories; successful canonicalization and cleanup are observations.
-Modules choose that semantic classification, while the framework attaches
-origin, aggregates groups, enforces bounds, and presents final collections.
-An ordinary successful run therefore has zero warnings. See
-[ADR-0015](../adr/0015-separate-process-warnings-from-quality-diagnostics.md)
-for the decision rationale.
-
 ## Validation
 
 Validation is a framework-managed boundary around outputs from chunk, extract,
-merge, and normalize stages. Validators receive immutable stage output and
+merge, and normalize stages. Validators receive immutable stage output
-make an explicit whole-output decision: approve, reject, fail, or skip when a
+and make an explicit whole-output decision: approve, approve with warnings, or
-runtime prerequisite is unavailable.
+reject.
 
 Typed artifact validators receive the domain value directly. Chunk validators
 receive source-zone chunks, while serialized validators receive immutable
 representation bytes and declared schema metadata. A validator registered for
 one target or artifact kind cannot satisfy an incompatible selection.
 
-The framework runs every applicable validator sequentially in configured order.
+Rejection is a recorded pipeline outcome, not a framework execution error.
-It aggregates rejections, exhausted validator failures, and skips before the
+Validator execution failures are framework errors. Rejected output does not
-producer policy chooses a disposition. A completed rejection never advances.
+advance to the next stage.
-With no rejection, an exhausted validator failure may fail the run or, under
-the configured `warn_continue` policy, advance a structurally valid candidate
-with explicit incomplete-validation provenance. Validators report findings;
-they do not choose candidate disposition.
-
-A completed rejection supplies a stable reason code for internal provenance
-and bounded actionable correction guidance for the candidate producer. Reason
-codes, validator keys, and operator-facing messages remain diagnostic data;
-they are not model instructions. The framework constructs model-facing retry
-text only from the semantic guidance and fails the contract rather than
-inventing or truncating missing guidance.
-
-An LLM-backed module may also request a feedback-aware retry when its own
-deterministic translation or typed safety policy rejects a structurally valid
-model response. It must supply model-facing guidance separately from its
-reason code, operator message, and fallback diagnostics, together with the
-exact `single_response_v1` candidate. A feedback-free module retry remains
-valid when no exact candidate exists.
 
 Default validator chains are production composition policy and are registered
 centrally by stage and module. Configuration may replace a stage-local default,
@@ -239,32 +170,6 @@ 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.
 
-PromptKit owns bounded structural correction within one structured completion.
-Notarius owns outer stage attempts, semantic validation, and acceptance policy;
-the two budgets must remain separate.
-
-An LLM-backed producer can participate in semantic correction only when it
-declares `single_response_v1` and returns the exact one response that directly
-controlled its candidate. On an actionable validator rejection or
-feedback-capable module retry, the framework rebuilds the ordinary request and
-appends only the latest defective response as an `assistant` message plus one
-aggregated `user` correction message. This is a fresh replacement request, not
-a growing conversation. The retry budgets, terminal policy, and sensitive-data
-rationale are recorded in
-[ADR-0014](../adr/0014-feedback-aware-validation-retries.md) and
-[ADR-0016](../adr/0016-feedback-aware-module-requested-retries.md).
-
-When a model selects an application entity, callers must supply a contextual
-selection and deterministically attach the opaque application identity whenever
-the selection resolves exactly. Models do not receive or reproduce opaque
-application identifiers. Semantic reconciliation may instead expose
-contiguous, one-based candidate handles that exist only for one request;
-deterministic code resolves them before typed application, and they never
-become durable identity. This is the approved request-local-label application
-of [ADR-0012](../adr/0012-resolve-opaque-entity-identifiers-deterministically.md)
-recorded by
-[ADR-0013](../adr/0013-use-request-local-candidate-handles-for-semantic-reconciliation.md).
-
 LLM calls and other external operations accept cancellation and respect
 timeouts. Concurrency control belongs in shared runtime plumbing rather than in
 individual modules.
@@ -272,16 +177,13 @@ individual modules.
 The application-wide LLM scheduler bounds actual provider calls independently
 of framework worker limits. Every LLM-backed module, retry, and validator uses
 the single injected scheduled client, including work performed by overlapping
-lanes. Provider runtime adapters may enforce a narrower backend-specific limit
+lanes.
-beneath this mandatory application-wide scheduler.
 
 ## Configuration And Provenance
 
-Configuration loading, precedence, defaults, redaction, and validation are
+Configuration loading, precedence, defaults, environment overrides, redaction,
-centralized through the ConfigKit-backed boundary. `NOTARIUS_CONFIG` is limited
+and validation are centralized. Named pipeline definitions make structural
-to discovery; field-level environment overlays are not configuration input.
+composition explicit and discoverable. Operational overrides are permitted
-Named pipeline definitions make structural composition explicit and discoverable.
-Explicit command overrides are permitted
 when they do not obscure the configured pipeline structure.
 
 Run preparation fails before stage execution when statically discoverable
@@ -290,18 +192,10 @@ invalid or incompatible.
 
 Run manifests record enough resolved pipeline, module, source, reference, and
 LLM provenance to make a run auditable after configuration changes. Manifests
-record identities and bounded validation summaries rather than secret, raw
+record identities and summaries rather than secret or large payload content.
-model, correction, or large payload content.
 
 ## State, Output, And Safety
 
-Source material and model responses cross application validation boundaries.
-Host access policy belongs to the deployment; hypothetical privileged actors
-concurrently changing the filesystem do not justify new application defenses
-without an explicit decision. This scope statement does not remove the adopted
-correctness boundaries below or claim excluded scenarios cannot occur. Follow
-[Agent Policy](agents.md) when a new threat or guarantee needs a decision.
-
 Notarius exposes three filesystem surfaces with independent roots and
 lifecycle:
 
@@ -318,49 +212,18 @@ an invocation that explicitly requests resume. Debug is never a cache input and
 is never created without an explicit request. Pipeline modules receive
 collaborator interfaces and never physical roots.
 
-Deployments own cache access policy. Cache writers request conventional maximum
-creation modes and let the process umask, setgid inheritance, and default ACLs
-determine effective access. Notarius owns the separate safety boundary:
-confined paths, symlink rejection, atomic publication, validation, and
-recovery. It does not chmod, chown, chgrp, or migrate cache entries to impose
-an application policy. This rule applies to chunk-plan and checkpoint cache
-only; output and debug retain their separate contracts. [Operations](../operations.md)
-owns deployment provisioning and retention guidance.
-
-Only accepted, completely validated producer output is reusable checkpoint or
-chunk-plan state. Rejected, structurally invalid, and validation-incomplete
-results cannot become cache or checkpoint inputs, even when a
-`warn_continue` result is allowed to advance in the current run. This
-ineligibility follows derived merge and normalize results and generated
-references for the remainder of the run: current-run handoff remains allowed,
-but no dependent cache or checkpoint may be loaded or published.
-
 Writes are atomic where practical. Paths for writes, moves, overwrites, and
 deletion must be narrow and explicit. Notarius never automatically deletes
 output or requested debug bundles; cache cleanup is explicit and recoverable.
 
 Secrets must not appear in errors, logs, output, cache, debug summaries,
-traces, manifests, documentation, examples, or redacted configuration. Raw
+traces, manifests, documentation, examples, or redacted configuration. Debug
-assistant responses and complete correction messages are attempt-local and are
-excluded from ordinary durable records and summaries; the requested detailed
-debug trace is the sole diagnostic surface allowed to retain them. Debug
 collection is allowlisted to application-owned payloads and must not capture
 unrelated process environment values or filesystem content. Trace data may
 contain application data and therefore inherits its sensitivity; operators own
 access controls and retention. Physical layout and operation are defined in
 [Operations](../operations.md).
 
-## Platform And Distribution
-
-Linux is the supported deployment platform. macOS is supported only as a
-best-effort development and compilation environment, while Windows is
-unsupported. Notarius distributes source releases only: an immutable source
-tag and its checked-in release note identify a release. The project does not
-publish executable binaries, archives, installers, container images,
-checksums, signatures, or package-manager entries. [Release Policy](release.md)
-owns publication requirements and completion; maintainer commands and guards
-belong to [Source Releases](../release.md).
-
 ## Architectural Non-Goals
 
 Notarius does not aim to provide:

docs/policy/documentation.md

@@ -1,14 +1,5 @@
 # Documentation Policy
 
-**Base Policy Version:** 1.3
-
-**Last Updated**: 2026-09-25
-
-**Upstream Source:** `policy` commit `45591a79004c6811950f14dca554f6ff69b7f58e`.
-
-Notarius retains subprocess-consumer ownership, the distinction between
-descriptive behavior and policy, and no placeholders for absent interfaces.
-
 ## Purpose
 
 This policy assigns each documentation topic to one canonical owner. Its goal is
@@ -33,28 +24,12 @@ contract, maintain it only in the owning document.
 Outside `docs/roadmap/`, documentation describes implemented behavior only.
 Partial features may be described only to their implemented boundary.
 
-Architectural constraints may govern future changes without implying that the
+ADRs are the narrow exception: an ADR may record an accepted architectural
-components or capabilities they would govern already exist. This does not permit
+decision before implementation, but acceptance must not be presented as proof
-describing a proposed system structure as implemented.
-
-ADRs may record an accepted architectural decision before implementation, but
-acceptance must not be presented as proof
 that the behavior exists. The roadmap owns implementation status and sequencing
 until the decision is implemented. Current architecture, user, operator,
 integration, and internal documentation are updated when the behavior lands.
 
-### Implementation Details And Policy
-
-Documentation must distinguish an explicit contract from an incidental
-implementation choice. Do not describe a restriction, guarantee, security
-policy, default, or limit as authoritative merely because the current code
-implements it. Documentation may accurately describe current behavior without
-making it a permanent requirement; distinguish descriptive behavior from
-normative policy. The
-[implementation-discipline rules](agents.md#implementation-discipline)
-own the criteria for adopting product restrictions and for elevating behavior
-into repository policy.
-
 ### Audience And Detail
 
 Write for the document's stated audience and include only the detail needed for
@@ -84,18 +59,14 @@ secret values.
 | --- | --- | --- | --- |
 | Product orientation and minimal end-to-end quickstart | `README.md` | What Notarius is, why it is useful, one shortest successful invocation, and links onward. | Complete command reference, configuration reference, operational procedures, implementation detail. |
 | Contributor entry point | `docs/development.md` | Task-oriented reading guide, minimal contributor orientation, baseline validation commands, and links to canonical docs. | Package inventory, architecture rules, subsystem behavior, detailed change recipes. |
-| Application architecture policy | `docs/policy/architecture.md` | System shape, normative ownership, dependency direction, architectural boundaries, invariants, safety properties, and non-goals. | Concrete package inventory, implementation mechanics, contributor procedures, decision history, future work. |
+| Current application architecture | `docs/policy/architecture.md` | System shape, normative ownership, dependency direction, architectural boundaries, invariants, safety properties, and non-goals. | Concrete package inventory, implementation mechanics, contributor procedures, decision history, future work. |
-| Agent policy | `docs/policy/agents.md` | Implementation discipline, rules against invented restrictions or guarantees, and local commit authorization. | Application contracts, architecture, testing policy, and contributor procedures. |
 | Documentation organization | `docs/policy/documentation.md` | Documentation ownership, audience boundaries, maintenance rules, and ADR/document lifecycle. | Application architecture or product behavior. |
 | Testing policy | `docs/policy/testing.md` | Test philosophy, risk-based sufficiency, test boundaries, doubles, coverage guidance, regression-test policy, and criteria for adding, rewriting, or deleting tests. | Subsystem behavior, application contracts, subsystem-specific test inventories, and implementation plans. |
 | CLI contract | `docs/cli.md` | Commands, arguments, flags, invocation semantics, and exit codes. | End-to-end operating procedures, configuration field definitions, runtime filesystem layout, module implementation details. |
 | Configuration contract | `docs/config.md` | Discovery and precedence, file schema, fields, defaults, environment overrides, validation rules, and user-selectable module or validator keys. | Complete example files, CLI syntax, runtime state lifecycle, module implementation details. |
 | Operations | `docs/operations.md` | Runtime workflows, physical filesystem and state layout, output, cache, and debug handling, resume, cleanup, permissions, recovery, and operational limits. | CLI flag syntax, configuration field definitions, logical output schemas, implementation mechanics. |
-| Release policy | `docs/policy/release.md` | Versioning, compatibility, integrity, immutability, proportionate gate selection, publication controls, and release completion. | Concrete commands, product installation, historical notes, and CI implementation detail. |
-| Repository-specific release procedure | `docs/release.md` | Prerequisites, candidate preparation, publication command, automated guards, optional diagnostics, and failure recovery. | General release requirements, product installation guidance, historical summaries, and current compatibility contracts. |
-| Release-note history | `docs/releases/` | One checked-in historical summary for each source release made under the procedure. The note at the immutable tag is that release's record. | Current commands, behavior, contracts, and compatibility definitions. |
 | Public HTTP contract, if introduced | `docs/api.md` | Routes, authentication, media types, request and response schemas, status codes, pagination, caching, idempotency, rate limits, and HTTP retry semantics. | Client walkthroughs, upstream or downstream integration internals, implementation detail. |
-| Consumer guidance | `docs/consumers/` | Task-oriented subprocess use, minimal client examples, consumer responsibilities, and guidance for any future public package or API. | Wire semantics, external protocol contracts, internal implementation detail. |
+| Consumer guidance, if a public package or API is introduced | `docs/consumers/` | Task-oriented use of the public interface, minimal client examples, and consumer responsibilities. | HTTP wire semantics, external protocol contracts, internal implementation detail. |
 | External and durable integration contracts | `docs/integrations/` | External file formats and protocols, upstream and downstream contracts, logical output bundle paths and schemas, media types, and compatibility behavior. | Physical runtime placement and lifecycle, internal transformations, CLI syntax, configuration defaults. |
 | Implemented component inventory | `docs/internal/overview.md` | Current packages and components, their implemented responsibilities, and links to focused internal docs. | Normative architecture, contributor reading policy, external contracts. |
 | Internal component behavior | Other files under `docs/internal/` | Implementation flow, internal collaborators and state transitions, package-local guarantees and failures, and relevant tests. | Global architecture invariants, configuration definitions and defaults, external schemas, operator procedures. |
@@ -124,16 +95,6 @@ runtime state and how to operate or recover the application. When a workflow
 crosses these topics, choose the document that owns the task and link to the
 other contracts.
 
-### Releases
-
-The [release policy](release.md) owns requirements and invariants; the
-[repository procedure](../release.md) owns the commands that satisfy them.
-Release notes are
-historical summaries, not current-state contract owners: the checked-in note at
-an immutable tag records that release, while current canonical documentation
-must change with the behavior it describes. Do not use a release procedure or
-note to weaken policy, redefine current contracts, or defer documentation updates.
-
 ### Contracts And Implementation
 
 Integration and API documents define externally observable shapes and

docs/policy/release.md

@@ -1,204 +0,0 @@
-# Release Policy
-
-**Base Policy Version:** 1.1
-
-**Last Updated**: 2026-09-25
-
-**Upstream Source:** `policy` commit `45591a79004c6811950f14dca554f6ff69b7f58e`.
-
-Notarius adaptations: source-only delivery, lightweight tags, branch-before-tag
-publication, no prereleases, and the justified native command check below.
-
-## Purpose
-
-This policy defines a proportionate workflow for validating and publishing an
-intended source revision under a fresh version. Releases should require little
-routine intervention, avoid repeated work, and preserve published contents.
-
-The repository-specific commands belong in `docs/release.md`. Historical release
-summaries belong in `docs/releases/`. The procedure must agree with the adopted
-policy and link to it rather than introduce additional release requirements.
-
-## Release Model And Completion
-
-A source release identifies one exact committed source revision through an
-immutable version tag and a version-matched, checked-in release note. The
-primary release branch is `main` and the authoritative remote is `origin`.
-Tags are lightweight. Publish the candidate to `main` before pushing its tag.
-
-A successful push of the intended tag, with its source commit available on the
-authoritative primary branch, completes the release. Notarius uses
-branch-before-tag publication; it does not require an atomic push.
-
-Release commands must finish at successful publication. They must not wait for
-or poll CI, require successful CI status, inspect downloadable artifacts, or
-check consumer installation or Go module availability as completion gates.
-A failed or ambiguous push requires resolving the authoritative remote state
-before declaring success or retrying; successful pushes do not require a
-separate remote read-back gate.
-
-Notarius publishes source only: no binaries, archives, images, packages,
-checksums, signatures, or Gitea release objects. Tag CI may provide advisory
-validation but publishes no deliverables and is not a completion gate.
-
-## Versioning And Compatibility
-
-Stable releases use Semantic Versioning in the form `vMAJOR.MINOR.PATCH`, with
-no leading zeroes. Notarius does not support prereleases.
-
-The selected version must be unused locally and on the authoritative remote.
-Do not require queries to every configured remote or publication service.
-A version known to have already been published must not be reused, even if the
-normal guards do not inspect that channel. Adding a distribution channel
-requires a deliberate update to the policy and procedure where needed.
-
-For releases at or after `v1.0.0`:
-
-- a major release may make intentional incompatible changes;
-- a minor release may add backward-compatible behavior; and
-- a patch release may make backward-compatible fixes.
-
-Before `v1.0.0`, a minor release may change a documented public, operational,
-configuration, data, integration, or compatibility contract when the release
-note explains the impact and required consumer action. A patch release must
-not intentionally break those contracts within its minor line.
-
-Additional compatibility promises and deliberate exceptions belong in the
-adopted policy or canonical contract documentation. Release notes explain
-changes; they do not redefine current compatibility contracts.
-
-## Release Documentation And Preparation
-
-Every new release must include `docs/releases/<version>.md` in the tagged
-source tree. Use the complete version tag as the filename and begin with a
-title containing the product name and that exact version.
-
-Include a short summary and any relevant compatibility impact or upgrade
-instructions. Keep the note proportionate to the change. Fixed sections and
-explicit no-action boilerplate are not required. Existing historical notes
-need not be rewritten to adopt this format.
-
-Keep exact current contracts in their canonical documents and update affected
-documentation with the behavior change. Link to those documents from the note
-where useful. A release note must not substitute for current documentation.
-Do not create retrospective notes for the pre-procedure v0.1.0, v0.2.0, or
-v0.3.0 tags.
-
-Version selection, release-note content, and retirement of completed roadmaps
-are preparation responsibilities, not separate human approval gates. Preserve
-planned and deferred work and repair affected links when retiring roadmaps.
-Ordinary change review covers unintended files, credentials, and private data;
-do not repeat it as a release-specific sign-off. Ignored local files are not
-prohibited merely because they exist: they are not included in the tagged source.
-
-## Candidate Validation
-
-Provide one publication command that validates the final committed candidate,
-checks publication state, and publishes the intended refs. A validation-only
-mode or command may be provided for diagnosis, but must not be a required step
-before publication repeats the same checks.
-
-Run the complete deterministic, offline default test suite once for the final
-candidate, following the [testing policy](testing.md). For repositories that
-publish builds, verify the required build targets. Select those targets for
-the application's actual support commitments; native testing on each platform
-and access to particular hardware are not default release prerequisites.
-
-Additional gates must address a concrete risk that the existing checks do not
-adequately cover. Do not automatically require linting, race testing, module
-hygiene audits, documentation audits, credential scans, example validation, or
-expanded platform matrices solely because they are possible. Retain such
-checks when their distinct protection justifies their cost. A one-time migration
-check must not silently become a permanent release requirement.
-
-Release tests must not require real credentials, mutable application services,
-paid APIs, provider probes, or inference calls. The procedure may describe dependency
-preparation separately from offline validation.
-
-Avoid duplicate validation across release phases. Successful checks for the
-same final candidate need not be repeated solely to satisfy another phase;
-any reuse must clearly apply to that exact candidate. Persistent validation
-caches are not required. If the candidate changes, validate the new candidate.
-Cheap publication-state checks may be repeated immediately before pushing
-because local or remote state may have changed during validation.
-
-Automate mechanical guards. Human review gates are strongly disfavored: add one
-only through an explicit project-specific policy decision explaining the
-concrete risk and why ordinary change review or automation is insufficient.
-Do not add routine confirmations for checks the command can perform itself.
-
-### Notarius Gate Selection
-
-Run the default offline Go suite once and build the native `cmd/notarius` with
-release version injection, checking its `--version` output. The command check
-protects the actual executable entry point and linker-supplied version, which
-package tests alone do not verify. Build products are temporary, not published.
-Use `GOWORK=off` so a sibling checkout cannot substitute for declared dependencies.
-
-Race tests, standalone vet, formatting/whitespace checks, module tidy audits,
-standalone example validation, and Linux/Darwin cross-builds remain useful
-change-specific development checks, not mandatory release gates. Default tests
-already cover maintained examples. Source-only publication does not require a
-binary distribution matrix. No new platform or hardware prerequisites are added.
-
-## Publication Guards
-
-Automate the checks needed to publish the intended source under a fresh version:
-
-- the version has the adopted format and is unused locally and on the
-  authoritative remote;
-- the worktree and index are clean on the primary release branch;
-- the source being published is the exact candidate that passed validation,
-  including its matching release note;
-- the branch push advances authoritative `main` to the candidate without
-  discarding remote history, before the tag is published; and
-- the tag identifies the validated candidate and only the intended refs are
-  published.
-
-Fetch the authoritative branch and tag state as needed for these checks.
-Do not force branch or tag updates to bypass a failed guard. Publish explicit
-refs rather than all local tags. Do not require CI success, publication-service
-availability checks, or a separate manual confirmation for each guard.
-
-## Immutability And Failure Recovery
-
-Published version tags and published contents are immutable. Do not move,
-overwrite, recreate, or delete a published tag, or replace a published artifact,
-checksum, signature, provenance statement, or release note under that version.
-The checked-in note at the immutable tag is that release's historical record.
-
-If validation fails before publication, correct and commit the candidate and
-rerun the publication command. If a push fails or its outcome is ambiguous,
-inspect the authoritative remote before retrying. Remove an unpublished local
-tag only after confirming it was never published or used by a release channel.
-An unavailable remote leaves publication status unknown; do not overwrite a tag
-to resolve uncertainty.
-
-Transient network, authentication, CI, or consumer-availability failures do not
-by themselves require a new version. Advisory CI or optional installation checks
-may be retried against the same immutable tag. Notarius has no asynchronous
-artifact delivery to recover.
-
-A defect requiring changes to published source or contents requires a corrected
-commit, a new semantically appropriate version, a matching release note, and
-the release procedure again. Leave the original release intact. A channel's
-yank, deprecation, or advisory mechanism may warn consumers away from a defective
-release without replacing its contents or reusing its version.
-
-## Repository Release Procedure
-
-Maintain `docs/release.md` as a short, executable maintainer runbook. It must
-identify:
-
-1. prerequisites, primary branch, and authoritative remote;
-2. version and release-note preparation;
-3. one publication command with its selected local checks and automated guards;
-4. declared deliverables, required build targets, and automation responsibilities;
-5. the successful-push completion point and separately reported delivery status;
-   and
-6. failure handling and ambiguous-push recovery.
-
-Use copyable commands where practical. Keep optional diagnostics and consumer
-verification clearly optional. The procedure must not turn preparation work,
-ordinary change review, or post-publication investigation into additional
-release gates.

docs/policy/testing.md

@@ -1,14 +1,5 @@
 # Testing Policy
 
-**Base Policy Version:** 1.1
-
-**Last Updated**: 2026-09-25
-
-**Upstream Source:** `policy` commit `45591a79004c6811950f14dca554f6ff69b7f58e`.
-
-Adopted without substantive deviations; Notarius's established contracts remain
-subject to [Agent Policy](agents.md).
-
 ## Purpose
 
 Our tests exist to make **incorrect changes expensive and correct changes cheap**.
@@ -17,16 +8,29 @@ We do not optimize for test count, line coverage, exhaustive isolation, or the f
 
 ## Every test has a cost
 
-Every test has an immediate and continuing cost: writing, review, execution,
+Testing is not an unqualified good. Every test imposes both an immediate cost and a continuing lifetime cost.
-diagnosis, fixture maintenance, and updates when legitimate behavior changes.
+
-Tests can also constrain refactoring, duplicate policy, and add failure noise.
+A test must be:
+
+- written and reviewed;
+- understood by future maintainers and coding agents;
+- executed in local and CI workflows;
+- diagnosed when it fails;
+- updated when legitimate behavior changes;
+- maintained as fixtures, APIs, and dependencies evolve; and
+- removed or rewritten when it becomes redundant, brittle, misleading, or obsolete.
+
+Tests also create cognitive and architectural friction. They can constrain refactoring, duplicate policy, slow feedback loops, add noise to failures, and cause harmless implementation changes to require unrelated edits across the suite.
 
 A test is warranted only when the confidence it provides justifies these costs.
-Evaluate that tradeoff at two levels:
+
+Apply this cost-benefit analysis at two levels:
 
 1. **Per test:** What realistic defect does this test detect, how consequential would that defect be, and is that protection worth the test's lifetime cost?
 2. **Across the suite:** Does this collection provide materially more confidence than a smaller, simpler suite would?
 
+The preferred test suite is a **lean suite that provides sufficient confidence in the risks that matter, without redundant or low-value tests**. We seek sufficient confidence with the least unnecessary testing friction, not the fewest possible tests.
+
 Some friction is intentional. Tests should make dangerous changes—such as breaking compatibility, corrupting data, violating security boundaries, or reintroducing subtle bugs—require deliberate review. They should not make ordinary internal changes needlessly expensive.
 
 The cost of a test is not a reason to omit testing by default. Do not cite maintenance cost abstractly. When omitting a plausible test, be able to state why the protected failure is low-risk, already covered, obvious, reversible, or cheaper to detect elsewhere. For consequential, subtle, or difficult-to-observe behavior, the presumption should favor testing.
@@ -51,7 +55,7 @@ Control clocks, randomness, environment variables, and other process-global or m
 
 ## What deserves tests
 
-To the extent the following features are present in the application, prioritize tests for:
+Prioritize tests for:
 
 1. Public and package-level contracts.
 2. Domain rules and important invariants.
@@ -63,18 +67,7 @@ To the extent the following features are present in the application, prioritize
 
 A package-level contract is behavior relied upon by another package or major collaborator, not every observable detail of a package implementation.
 
-Choose tests for requested behavior and established contracts. Tests must not
+For behavior involving **data integrity, destructive operations, compatibility, security, concurrency, idempotency, or recovery**, presume that durable tests are required unless the behavior is already credibly protected at another layer.
-introduce new restrictions, guarantees, or threat scenarios merely because they
-could be asserted. Follow the [agent policy](agents.md) when deciding whether a
-behavior belongs to the contract; current implementation behavior alone is not
-sufficient authority.
-
-For established behavior involving **data integrity, destructive operations,
-compatibility, security, concurrency, idempotency, or recovery**, favor durable
-tests for realistic failures whose consequences warrant protection. Identify
-the failure and the existing contract it would violate. These categories call
-for attention, not an automatic test inventory or permission to strengthen the
-application's guarantees. Account for protection already provided at other layers.
 
 Do not add tests merely because a function, branch, or line exists. Do not add a test when the same meaningful risk is already adequately protected elsewhere.
 
@@ -92,7 +85,11 @@ Do not force all behavior through oversized end-to-end tests. Do not test every
 
 ## Test behavior, not implementation
 
-A test should protect a decision, contract, or invariant. A test must not memorialize the current implementation.
+A test should protect a decision, contract, or invariant—not memorialize the current implementation.
+
+Before adding or retaining a test, ask:
+
+> What realistic defect would this test catch?
 
 A test is suspect when its main purpose is to detect that someone:
 
@@ -105,6 +102,8 @@ A test is suspect when its main purpose is to detect that someone:
 
 Refactoring should normally require no test edits unless the refactored structure is itself part of the contract.
 
+A test can be factually correct and still have negative value. Accurately describing current behavior is not enough; the protected behavior must be important enough to justify the future friction.
+
 ## Expected effects of different changes
 
 Use the following expectations when evaluating test failures and test maintenance:
@@ -122,11 +121,10 @@ A test failing is not the same as a test needing to be edited. Many tests may co
 
 Configurable thresholds and defaults must not be duplicated throughout the test suite.
 
-For this example, assume the selected contract rejects a request to start more
+For example, do not encode an internal concurrency limit indirectly:
-processes than a configured limit. Do not encode its production default indirectly:
 
 ```go
-// Production default:
+// Production policy:
 const maxConcurrency = 4
 
 // Brittle test:
@@ -144,30 +142,25 @@ require.NoError(t, runner.Start(limit))
 require.ErrorIs(t, runner.Start(limit+1), ErrTooMuchConcurrency)
 ```
 
-For this selected contract, the test should prove:
+The test should prove:
 
 - the configured limit is accepted; and
 - one beyond the configured limit is rejected.
 
-Rejection is not a general requirement for concurrency control. If the selected
-contract queues excess work or limits active workers while accepting larger
-batches, test that behavior instead. Do not add rejection or a configurable
-limit solely to reproduce this example.
-
 The production default should be tested exactly only when its literal value is itself a public, operational, safety, protocol, or compatibility requirement.
 
 Apply the same rule to limits, timeouts, capacities, retry counts, and ranges: test relationships and behavior, not duplicated literals.
 
-For established concurrency limits, distinguish these behaviors where the contract requires them:
+For concurrency limits, test both kinds of behavior when relevant:
 
-1. **Configuration handling:** values are accepted or rejected according to the selected contract.
+1. **Configuration enforcement:** invalid or excessive requested values are handled correctly.
 2. **Runtime enforcement:** observed peak concurrency never exceeds the configured limit.
 
 Use a test-controlled limit and measure the behavior relative to that limit. Do not merely assert today's default value.
 
 ## Avoid semantic duplication across layers
 
-Each behavior should have a clear test owner. Where these layers exist:
+Each behavior should have a clear test owner.
 
 - Parser tests own parsing cases.
 - Validator tests own validation rules.
@@ -179,6 +172,8 @@ Each behavior should have a clear test owner. Where these layers exist:
 
 Higher-level tests should not repeat every lower-level case. A single intentional policy change should not require unrelated edits across many test files.
 
+Tests that are individually reasonable may still be collectively redundant. Evaluate the marginal value of each additional test in light of the protection already provided by the rest of the suite.
+
 ## Use test doubles deliberately
 
 Choose the least elaborate test double that provides the required control or observation.
@@ -202,16 +197,15 @@ Do not use mocks merely to isolate every object or reproduce the implementation'
 
 ## Go-specific guidance
 
-Select techniques according to the behavior and risk being tested. The following
+Use:
-are options, not a checklist that every package or application must satisfy:
 
 - table-driven tests for meaningful behavioral categories and boundaries;
 - `t.TempDir()` for real filesystem behavior;
 - `httptest.Server` for realistic HTTP interactions;
-- fuzz tests when exploring broad input spaces, such as parsers or path handling, adds useful protection beyond representative cases;
+- fuzz tests for parsers, normalization, path handling, and broad input spaces;
 - golden files only when the complete output is intentionally stable;
 - integration tests where correctness depends on component interaction; and
-- a small number of representative end-to-end tests when assembled workflows expose meaningful risks not adequately covered at narrower boundaries.
+- a small number of representative end-to-end tests.
 
 Avoid exact error-string assertions unless the wording is itself contractual. Prefer `errors.Is`, `errors.As`, typed errors, or structured error fields.
 
@@ -229,6 +223,8 @@ Use it to find untested critical branches and unexpectedly weak packages. Do not
 
 Pure domain logic will often warrant higher coverage than CLI wiring or external adapters. Uneven coverage is acceptable when it reflects risk.
 
+Increasing coverage is valuable only when the newly covered behavior protects a meaningful risk at an acceptable cost.
+
 ## Regression tests
 
 A bug fix should normally include a regression test that fails before the fix and passes afterward.
@@ -257,26 +253,44 @@ Strong candidates include tests that:
 
 Several brittle tests may encode one genuine requirement. Replace them with one durable behavior-level or invariant test rather than preserving all of them.
 
+Deleting a low-value test can improve the quality of the suite by reducing noise, maintenance burden, and friction around legitimate change.
+
 ## Reviewing a proposed test
 
 Use the following questions when the value, boundary, or durability of a proposed test is not self-evident. Significant test additions should be reviewable against them, but written answers are not required for every routine test.
 
-1. Which requested behavior or established contract does it protect, and what realistic defect would violate it?
+1. What realistic defect would it catch?
-2. How likely and consequential is that defect, and is it already protected elsewhere?
+2. How likely is that defect?
-3. What is the narrowest stable boundary that can test it clearly?
+3. How consequential would it be?
-4. Would a correct internal refactor or a change to an incidental default require test edits?
+4. Is the behavior already protected elsewhere?
-5. Does its confidence justify its maintenance, execution, and diagnostic cost, or would a smaller test suffice?
+5. At which layer should this behavior be owned?
+6. Does the test assert a durable contract or an incidental implementation detail?
+7. Could the implementation be refactored without changing the behavior and without editing this test?
+8. What should cause this test to fail?
+9. What legitimate changes should not cause this test to fail?
+10. What ongoing maintenance, execution, and diagnostic cost will the test impose?
+11. Is there a smaller or more direct test that protects the same risk?
+
+Do not add the test when its expected lifetime cost exceeds its expected protective value.
+
+When deciding not to test plausible behavior, record or be able to explain why the risk is low, already protected, obvious, reversible, or cheaper to detect elsewhere.
 
 ## Definition of sufficient
 
 A test suite is sufficient when:
 
-- important requested behavior and established contracts are protected against realistic, consequential failures;
+- important contracts and invariants are protected;
-- boundaries and component interactions have coverage where they introduce meaningful risks not protected elsewhere;
+- meaningful boundaries and failure modes are exercised;
+- realistic and consequential regressions are credibly protected against silent recurrence;
+- behavior involving data integrity, destructive operations, compatibility, security, concurrency, idempotency, and recovery is credibly protected;
+- important external boundaries have realistic integration coverage;
+- representative complete workflows are tested;
 - failures provide useful signal rather than redundant noise;
 - legitimate internal changes usually do not require test edits; and
 - additional tests would mostly repeat existing protection or preserve inconsequential implementation details.
 
-Sufficiency is a risk judgment, not a coverage percentage, test count, or required
+Sufficiency is a risk judgment, not a coverage percentage or test count. Reassess it as the application, its users, and the consequences of failure evolve.
-mix of testing techniques. Reassess it as the application, its users, and the
+
-consequences of failure evolve.
+The governing rule is:
+
+> Test heavily where failure is consequential, subtle, or difficult to detect after the fact. Test lightly where failure is obvious, reversible, and inexpensive—and retain no test whose lifetime cost exceeds the confidence it provides.

docs/release.md

@@ -1,84 +0,0 @@
-# Source Releases
-
-This is the executable runbook for [Release Policy](policy/release.md).
-Notarius publishes an immutable lightweight tag and its checked-in release note,
-not binaries or Gitea release objects. Linux is supported; macOS is best-effort
-for development, and Windows is unsupported. `main` on `origin` is authoritative.
-
-## Prepare
-
-Use Git, a POSIX shell, and Go 1.25.5 or newer. Configure ordinary Git credentials
-for `origin` and private-module access without putting secrets in the repository.
-Prepare dependencies before offline validation where necessary:
-
-```sh
-GOWORK=off GOPRIVATE=gitea.maximumdirect.net go mod download
-```
-
-Choose an unused stable version under the policy's compatibility rules. Add
-`docs/releases/<version>.md`, starting with `# Notarius <version>`, with a concise
-summary and relevant compatibility/upgrade information. No fixed section list is
-required. Update current documentation with behavior changes; retire only
-completed roadmaps and preserve planned/deferred work. Commit the candidate on
-`main` after ordinary change review. There is no separate release sign-off.
-
-## Publish
-
-Run one command from the repository with the actual selected version:
-
-```sh
-./scripts/release.sh vMAJOR.MINOR.PATCH
-```
-
-The command checks version availability on `origin`, branch and worktree state,
-and the matching note. It runs the complete offline default test suite once and
-a native CLI build/version check with `GOWORK=off`. The
-[gate rationale](policy/release.md#notarius-gate-selection) explains the selected
-checks. It then rechecks candidate and publication state, pushes the exact
-candidate to `main` without force, creates a lightweight tag, and pushes only
-that tag. It neither rewrites history nor publishes other local tags.
-
-A successful tag push completes the source release. The command does not wait
-for CI or verify consumer installation/module availability. Tag CI is advisory
-validation only; there are no asynchronous deliverables to await.
-
-## Failure And Recovery
-
-Before publication, correct failed checks, commit any changes, and rerun the
-command. If the candidate changes during validation, validation must run again
-on the new candidate. A failed branch push publishes no tag.
-
-On a failed or ambiguous push, the command queries the affected remote ref. If
-a tag push reports failure but the intended lightweight tag is confirmed on the
-remote, publication succeeded. Otherwise it stops and reports failure or unknown
-status, leaving any local tag intact for inspection. Do not blindly rerun, force
-push, or delete a possibly published tag.
-
-Inspect authoritative state before retrying:
-
-```sh
-git ls-remote origin refs/heads/main refs/tags/vMAJOR.MINOR.PATCH
-git rev-parse vMAJOR.MINOR.PATCH
-```
-
-If the intended tag exists remotely, leave it immutable. If it is absent and
-you have confirmed that the local tag was never published or used by a release
-channel, remove only that unpublished local tag, then rerun the command. A
-failed remote query is not proof of absence. Network/authentication failures
-alone do not require a new version. A defect requiring changes to published
-source requires a new semantically appropriate version and matching note.
-
-## Optional Diagnostics
-
-`./scripts/check-release-source.sh <version>` runs validation without publication.
-It is useful for diagnosis, but is not a required preliminary step that must
-repeat the publication command's checks.
-
-Race tests, vet, module hygiene, formatting, example checks, and cross-builds may
-be run when relevant to a change; they are not additional release gates. The
-development guide and testing policy govern change-specific verification.
-
-A fresh source install or exact-tag checkout/build may be used to investigate
-consumer availability after release. Such checks are optional and do not delay
-or reverse release completion. `notarius --version` is diagnostic; subprocess
-compatibility is defined by the receipt and artifact contracts.

docs/releases/v0.4.0.md

@@ -1,83 +0,0 @@
-# Notarius v0.4.0
-
-This release strengthens LLM reliability and validation throughout the
-configured pipeline, upgrades the PromptKit integration, and establishes the
-source-release and downstream-consumer workflows needed for broader D&D
-pipeline integration.
-
-## Summary
-
-Notarius now distinguishes PromptKit structural-output repair from
-application-owned semantic validation retries. Producer candidates can run
-through complete deterministic validator chains, receive bounded semantic
-correction guidance, and retry under explicit stage policies. Final run
-receipts and manifests preserve bounded validation provenance, while outputs
-that advance with incomplete validation remain available to the current run
-without entering reusable checkpoint state.
-
-The release also adds a maintained complete D&D subprocess-consumer workflow,
-diagnostic build versions, and the source-only release procedure used to
-publish this version.
-
-## Compatibility
-
-- Configuration files must use schema version 4. Version 3 is not decoded or
-  rewritten; rename the top-level `scriptorium` section to `promptkit` when
-  migrating. See [Configuration](../config.md#migrating-version-3-configuration).
-- PromptKit is pinned to v0.9.0. Operator profile files use PromptKit's v0.9.0
-  format and may use its profile-inheritance support. Notarius continues to
-  resolve operator profiles before embedded fallbacks.
-- Structural-output repair and semantic stage retries are separate bounded
-  mechanisms. Maintained production prompts request one structural repair by
-  default; explicit configuration can override the supported repair count.
-- Validation policy can now fail a run, reject an output, or permit an
-  otherwise valid candidate to advance with incomplete-validation provenance.
-  The application defaults are documented in
-  [Configuration](../config.md#pipelines).
-- The `notarius.run-result.v1` receipt remains at schema version 1 and adds
-  optional validation summaries plus a required validation-status field.
-  Consumers of this pre-release contract should follow the current
-  [run-result receipt](../integrations/run-result.md).
-- Existing D&D artifact schema identities remain unchanged. Validation and
-  producer-policy changes can nevertheless cause previously accepted weak
-  candidates to retry, reject, or fail instead.
-
-## Upgrade
-
-1. Migrate every Notarius configuration to version 4 and rename `scriptorium`
-   to `promptkit`.
-2. Review deployed PromptKit profiles against the pinned v0.9.0 profile format
-   and ensure their credential environment variables are available at run
-   time.
-3. Run `notarius config validate --config <path> --pipeline <id>` before the
-   first production invocation.
-4. Review `structured_output_repair_attempts`, producer retry counts, and
-   `validation_policy` wherever the deployment needs behavior different from
-   the documented defaults.
-5. Update subprocess consumers to inspect receipt `validation_status` and to
-   tolerate the optional bounded `validation_summaries` field. A consumer that
-   requires fully validated artifacts should require `approved`.
-
-## Changes
-
-- Upgraded PromptKit from v0.5.0 through v0.9.0 and adopted profile
-  inheritance, structured-output repair, typed error classification, and the
-  correction-aware completion protocol.
-- Added pipeline and binding configuration for structural repair and terminal
-  validation policy, with strict startup validation and effective-setting
-  provenance.
-- Added feedback-aware retries for chunking, extraction, merge, normalize, and
-  semantic reconciliation producers. Retry prompts contain the exact defective
-  response and actionable semantic correction guidance without exposing
-  internal reason codes or opaque entity identifiers.
-- Added complete validator-chain execution, validator retry handling, bounded
-  warnings, terminal dispositions, and durable validation summaries.
-- Prevented validation-incomplete artifacts and all derived lineage from
-  loading or publishing reusable checkpoints while preserving same-run
-  generated-reference handoff.
-- Tightened cached chunk-plan validation so only completely validated plans are
-  reused or replace stored plans.
-- Added a machine-readable subprocess receipt workflow and complete D&D
-  consumer documentation covering all maintained artifacts.
-- Added source-release checks, immutable lightweight-tag guidance, Linux and
-  Darwin build verification, and diagnostic `notarius --version` output.

docs/releases/v0.5.0.md

@@ -1,85 +0,0 @@
-# Notarius v0.5.0
-
-This release separates actionable process warnings from extraction-quality
-advisories and routine normalization observations, giving operators a quiet
-warning channel without discarding durable diagnostic detail.
-
-## Summary
-
-Notarius now carries one validated, origin-aware diagnostic contract from
-producers and validators through retries, reusable state, output publication,
-debug summaries, run receipts, and CLI presentation. Warnings are reserved for
-process degradation or incomplete configured work. Data-quality findings are
-advisories, and successful deterministic cleanup is recorded as observations.
-An ordinary successful run therefore reports zero warnings while retaining
-bounded diagnostic provenance for later review.
-
-The framework aggregates findings deterministically by their stable identity
-and complete pipeline origin, preserves exact occurrence counts, and retains
-bounded representative samples. Warning groups fail rather than truncate;
-advisory and observation representation is bounded with explicit truncation
-metadata and exact unrepresented-occurrence counts.
-
-## Compatibility
-
-- `warnings.json` now uses the incompatible grouped
-  `notarius.warnings.v2` envelope and contains process warnings only. Consumers
-  of the former flat warning payload must migrate to the current
-  [JSON output contract](../integrations/json-output.md).
-- The new `diagnostics.json` file uses `notarius.diagnostics.v1` and contains
-  advisory and observation groups. Production `index.json` files always expose
-  both `warnings_file` and `diagnostics_file`.
-- The machine-readable run receipt is now `notarius.run-result.v2`. It replaces
-  `warning_count` with exact warning group and occurrence counts and adds
-  advisory/observation group, occurrence, and truncation fields. See the
-  current [run-result receipt](../integrations/run-result.md).
-- Custom output modules must return their complete logical file set or an
-  error. The former `OutputResult.Warnings` field has been removed; an output
-  module cannot report a warning after serializing its output.
-- Reusable state now uses `notarius.workspace.v4` and chunk-plan records use
-  `notarius.chunk-plan.v3` so they can preserve structured diagnostics. Older
-  pre-release reusable state is not reused under these contracts; start with
-  clean state when deterministic continuity with an older workspace is not
-  required.
-- Validation acceptance, semantic retry budgets, rejection policy, and D&D
-  artifact schema identities are unchanged by this release.
-
-## Upgrade
-
-1. Update subprocess consumers to require `notarius.run-result.v2` and read
-   `warning_group_count`, `warning_occurrence_count`,
-   `diagnostic_group_count`, `diagnostic_occurrence_count`, and
-   `diagnostics_truncated`.
-2. Update output-bundle consumers to decode `notarius.warnings.v2`, discover
-   `diagnostics.json` through `index.json`, and treat diagnostics as review
-   information rather than process warnings.
-3. Update any custom output module for the removal of
-   `OutputResult.Warnings`; return an error when encoding cannot complete.
-4. Clear pre-release reusable state before the first upgraded production run
-   when deterministic continuity with an older workspace is not required.
-5. Run `notarius config validate --config <path> --pipeline <id>` and perform
-   one representative run before promoting the release in an automated
-   pipeline.
-
-## Changes
-
-- Added validated diagnostic dispositions, categories, origins, stable reason
-  codes, exact occurrence counts, and bounded representative samples.
-- Added deterministic run-level aggregation with separate limits for
-  actionable warning groups and advisory/observation groups.
-- Reclassified D&D source-relatedness and unresolved-identity findings as
-  data-quality advisories and routine normalization changes as observations.
-- Preserved structured diagnostics across producer retries, validation,
-  generated-reference handoff, checkpoints, chunk-plan reuse, and debug
-  summaries while discarding superseded-attempt findings.
-- Added grouped `warnings.json`, a new grouped `diagnostics.json`, and the
-  corresponding production index entries.
-- Upgraded the machine-readable run receipt and human CLI summary to report
-  exact warning and diagnostic counts without allowing advisory volume to
-  create warning output.
-- Removed post-encoding output warnings and hardened diagnostic validation,
-  overflow handling, aggregate memory bounds, and warning-file path
-  presentation.
-- Documented diagnostic ownership, classification, operator interpretation,
-  durable contracts, and architectural invariants in ADR-0015 and the
-  canonical CLI, operations, integration, and internal documentation.

docs/releases/v0.6.0.md

@@ -1,84 +0,0 @@
-# Notarius v0.6.0
-
-This release improves the reliability and ergonomics of unattended,
-subprocess-driven D&D extraction pipelines.
-
-## Summary
-
-Notarius now gives models more precise, semantically useful correction guidance
-when deterministic or model-backed validation rejects an otherwise structured
-candidate. Semantic reconciliation retries identify candidates with compact,
-request-local numbers, preserve valid candidates when a proposal cannot be
-repaired, and report bounded process warnings when reconciliation is
-incomplete. D&D extraction also canonicalizes safely resolvable reversed source
-ranges and applies more consistent schema, prompt, and validator constraints,
-improving successful operation with smaller models without weakening evidence
-validation.
-
-An optional LLM-backed combat-semantics validator can review whether scene
-descriptions correctly consolidate combat and apply the `combat` kind. For
-subprocess callers, command-line references now follow the pipeline-scoped
-configuration model: a shared reference can be supplied once and automatically
-reach every compatible selected target, while lane- and binding-specific forms
-remain available for exceptions.
-
-## Compatibility
-
-- The meaning of an unqualified `--reference slot=path` or
-  `--without-reference slot` selector has changed. It now applies to every
-  selected pipeline target that declares the slot instead of requiring exactly
-  one matching target. Review callers that relied on ambiguity rejection or a
-  unique implicit target; the current selector contract is documented in the
-  [CLI reference](../cli.md).
-- The stage-wide `merge.slot` CLI reference shorthand has been removed. Use
-  `lane.merge.slot` for an exact merge binding, `lane.slot` for all compatible
-  bindings in one lane, or an unqualified `slot` for pipeline scope.
-- Command-line file references cannot replace, remove, or coexist with a
-  generated artifact handoff for the same concrete target and slot. Resolution
-  reports the conflict so the caller can narrow or remove the selector.
-- The private LLM-facing semantic-reconciliation contract now uses contiguous
-  `candidate_number` values rather than application identities. This is not a
-  durable or operator-configurable contract and requires no operator action.
-- Durable D&D artifact schemas, the `notarius.run-result.v2` receipt,
-  `notarius.warnings.v2`, and `notarius.diagnostics.v1` are unchanged from
-  `v0.5.0`.
-
-## Upgrade
-
-1. Update subprocess commands to provide shared inputs once with
-   `--reference slot=path`, and convert any stage-wide `merge.slot` selector to
-   an explicit supported scope. The [subprocess consumer guide](../consumers/subprocess.md)
-   and [complete D&D consumer guide](../consumers/dnd-pipeline.md) show the
-   current invocation pattern.
-2. Review CLI reference overrides that overlap generated same-run references;
-   narrow or remove an external selector rather than attempting to replace the
-   generated handoff.
-3. Run `notarius config validate --config <path> --pipeline <id>` for every
-   deployed pipeline configuration.
-4. Optionally add
-   `extract/dnd/scene-descriptions/combat_semantics` to the scene-description
-   validator chain where the deployment wants LLM-backed combat-scene review;
-   see the [configuration reference](../config.md).
-5. Perform a representative run with the deployed model profile and inspect
-   the machine-readable receipt, warnings, and diagnostics before promotion.
-
-## Changes
-
-- Added feedback-aware, module-requested retry support for normalizers while
-  keeping retry budgets bounded and preserving attempt diagnostics.
-- Reworked semantic reconciliation around compact, contiguous candidate
-  numbers, explicit namespace guidance, complete proposal validation, and
-  model-facing retry feedback that omits opaque internal identities.
-- Preserved candidates separately when an exhausted semantic proposal cannot
-  be safely applied, with a bounded process warning describing the fallback.
-- Canonicalized safely resolvable reversed D&D source-reference endpoints
-  before deterministic coverage validation and clarified the shared evidence
-  prompt.
-- Improved D&D schemas, prompts, and validators with closed-value constraints,
-  contextual correction guidance, shared source-range coverage logic, and
-  clearer item-holder transition rules.
-- Added the optional D&D scene-description combat-semantics validator, shared
-  combat policy assets, evaluation fixtures, and retry-path coverage.
-- Made unqualified CLI references pipeline-scoped, added hierarchical lane and
-  exact-binding selectors, defined deterministic override precedence, and
-  documented first-class subprocess use.