eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: eric:v0.3.0
Branches Tags
eric:main
eric:v0.5.0 eric:v0.4.0 eric:v0.3.0 eric:v0.2.0 eric:v0.1.0
..
compare: eric:987c9691c6dd1ea82a17f8de1b4bb94e4981d936
Branches Tags
eric:main
eric:v0.5.0 eric:v0.4.0 eric:v0.3.0 eric:v0.2.0 eric:v0.1.0

5 Commits
v0.3.0 ... 987c9691c6

Author SHA1 Message Date
Eric Rakestraw
987c9691c6 Document published evidence context 2026-07-27 18:28:02 +00:00
Eric Rakestraw
9e4b989e53 Publish evidence context in JSON output bundles 2026-07-27 18:23:48 +00:00
Eric Rakestraw
6bdebcb5e2 Build evidence context for output encoders 2026-07-27 18:17:54 +00:00
Eric Rakestraw
ad36d534a4 Add evidence context artifact builder 2026-07-27 18:11:49 +00:00
Eric Rakestraw
73d6e184ab Add evidence context policy preparation 2026-07-27 18:04:12 +00:00
604 changed files with 10908 additions and 38990 deletions
Expand all files Collapse all files

3
.codebase-memory/.gitattributes vendored Normal file
View File

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

11
.codebase-memory/artifact.json Normal file
View File

@@ -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
}

BIN
.codebase-memory/graph.db.zst Normal file
View File

Binary file not shown.

2
.gitignore vendored
View File

@@ -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

5
README.md
View File

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

18
assets/dnd/combat-turns/prompts/instructions.md
View File

@@ -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.

12
assets/dnd/enemy-events/prompts/combat-grounding.md
View File

@@ -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" }}

25
assets/dnd/enemy-events/prompts/instructions.md
View File

@@ -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.

53
assets/dnd/enemy-events/prompts/prompt.yaml
View File

@@ -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: 0

30
assets/dnd/item-occurrences/prompts/instructions.md
View File

@@ -1,30 +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, using `null` when a holder does not
apply. For `discovered`, set both holders to `null`. For `acquired`, set `from`
to `null` and provide `to`; for `lost` and `consumed`, provide `from` and set
`to` to `null`; and for `transferred`, provide both holders. Use `party` only
for collective or unresolved party possession, never for either side of a
transfer. Do not emit a transfer for a gift, sale, or payment outside the party.
Ordinary non-depleting use is not an occurrence. Do not infer acquisition from a
discovery, or discovery from an acquisition: emit both only when each is
independently established.

6
assets/dnd/item-occurrences/prompts/item-registry.md
View File

@@ -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" }}

45
assets/dnd/item-occurrences/prompts/prompt.yaml
View File

@@ -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: 0

36
assets/dnd/item-occurrences/schemas/dnd_item_occurrences_llm.v1.json
View File

@@ -1,36 +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"},
"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"}
}
}
}
}
}
}
}
}

12
assets/dnd/item-registry/extract/prompts/instructions.md
View File

@@ -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.

40
assets/dnd/item-registry/extract/prompts/prompt.yaml
View File

@@ -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: 0

32
assets/dnd/item-registry/extract/schemas/dnd_item_registry_llm.v1.json
View File

@@ -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"}
}
}
}
}
}
}
}
}

9
assets/dnd/item-registry/normalize/prompts/instructions.md
View File

@@ -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.
When selecting a canonical display name, choose one supplied candidate name
that is the clearest established designation.

30
assets/dnd/item-registry/normalize/prompts/prompt.yaml
View File

@@ -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: 0

34
assets/dnd/location-occurrences/prompts/instructions.md
View File

@@ -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.

11
assets/dnd/location-occurrences/prompts/location-registry.md
View File

@@ -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" }}

45
assets/dnd/location-occurrences/schemas/dnd_location_occurrences_llm.v1.json
View File

@@ -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"}
}
}
}
}
}
}
}
}

13
assets/dnd/location-registry/extract/prompts/instructions.md
View File

@@ -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.

32
assets/dnd/location-registry/extract/schemas/dnd_location_registry_llm.v1.json
View File

@@ -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"}
}
}
}
}
}
}
}
}

8
assets/dnd/location-registry/normalize/prompts/instructions.md
View File

@@ -1,8 +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.
When selecting a canonical display name, prefer the clearest established name.

30
assets/dnd/location-registry/normalize/prompts/prompt.yaml
View File

@@ -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: 0

45
assets/dnd/npc-occurrences/prompts/prompt.yaml
View File

@@ -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: 0

19
assets/dnd/npc-registry/extract/prompts/instructions.md
View File

@@ -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.

11
assets/dnd/npc-registry/normalize/prompts/instructions.md
View File

@@ -1,11 +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.
When selecting a canonical display name, prefer a complete, stable proper name
over an abbreviation. Prefer an unadorned proper name over that name plus a
contextual class, role, title, or relationship descriptor unless the transcript
establishes the descriptor as part of the person's name. A longer display name
is not inherently more canonical; for example, do not prefer `Captain Aria`
over `Aria` solely because it includes the contextual title `Captain`.

5
assets/dnd/profiles/dnd-extraction.yaml
View File

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

6
assets/dnd/shared/prompts/common-dnd-extraction-evidence.md
View File

@@ -1,6 +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.
When supporting evidence is non-contiguous, use multiple narrow ranges rather
than a broad range that bridges unrelated conversation.

5
assets/dnd/shared/prompts/common-dnd-system.md
View File

@@ -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.

3
assets/dnd/shared/prompts/common-dnd-transcript-chunk.md
View File

@@ -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" }}

3
assets/dnd/shared/prompts/common-dnd-transcript-full.md
View File

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

14
assets/dnd/spells/prompts/instructions.md
View File

@@ -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.

6
assets/dnd/spells/prompts/spell-catalog.md
View File

@@ -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" }}

3
assets/generic/normalize/deduplication/prompts/candidates.md
View File

@@ -1,3 +0,0 @@
Candidate material:
{{ input "candidates" }}

5
assets/generic/normalize/deduplication/prompts/instructions.md
View File

@@ -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.

27
assets/generic/normalize/deduplication/prompts/prompt.yaml
View File

@@ -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: 0

7
assets/generic/normalize/deduplication/prompts/protocol.md
View File

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

2
assets/generic/normalize/deduplication/prompts/system.md
View File

@@ -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.

3
assets/generic/normalize/deduplication/prompts/transcript-windows.md
View File

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

32
assets/generic/normalize/deduplication/schemas/semantic_reconciliation_llm.v1.json
View File

@@ -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_ids", "canonical_candidate_id"],
"properties": {
"candidate_ids": {
"type": "array",
"minItems": 2,
"items": {
"type": "integer",
"minimum": 1
}
},
"canonical_candidate_id": {
"type": "integer",
"minimum": 1
}
}
}
}
}
}

15
assets/package.go
View File

@@ -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
}

2
docs/adr/0004-package-modules-by-domain.md
View File

@@ -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

49
docs/adr/0010-workload-oriented-llm-profile-defaults.md
View File

@@ -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.

69
docs/adr/0011-centralize-llm-assets.md
View File

@@ -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.

64
docs/adr/0012-resolve-opaque-entity-identifiers-deterministically.md
View File

@@ -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.

91
docs/adr/0013-use-request-local-candidate-handles-for-semantic-reconciliation.md
View File

@@ -1,91 +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.
Acceptance of this decision does not imply that the shared mechanism or its
consumer migrations are implemented. The
[feature roadmap](../roadmap/semantic-reconciliation.md) owns target behavior
and status, and the
[implementation plan](../roadmap/implementation.md) owns delivery sequence
until the work is complete.

27
docs/cli.md
View File

@@ -39,33 +39,16 @@ 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. |
| **--session-id id** | Override the generated prompt session identifier with a non-empty value for LLM-backed module calls. |
| **--reasoning-effort value** | Replace the selected PromptKit profile's reasoning effort for every LLM-backed call in this run. The value must be non-empty and the flag may be specified only once. |
| **--clear-reasoning-effort** | Clear reasoning effort inherited from the selected PromptKit profile for every LLM-backed call in this run. |
| **--llm-profile id** | Override effective LLM-capable module bindings with one configured profile. |
| **--session-id id** | Supply a non-empty prompt session identifier to LLM-backed module calls. |
| **--reference selector=path** | Add or replace a file reference binding. Repeatable. |
| **--without-reference selector** | Remove a configured optional reference binding. 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.
**--reasoning-effort** and **--clear-reasoning-effort** are mutually exclusive.
When neither is present, reasoning effort comes from the selected PromptKit
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.
**--recompute-step** reject explicit empty values. **--recompute-step**
requires **--resume**; checkpoint requirements and reuse behavior are
documented in [Operations](operations.md).
### Reference selectors

197
docs/config.md
View File

@@ -1,7 +1,7 @@
# Configuration
This is the canonical reference for Notarius configuration. Configuration files
are YAML and must declare version 4. 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.
@@ -32,8 +32,7 @@ override the fields listed below.
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
[operator profile](../examples/profiles/dnd-extraction.yml).
settings, and bounded LLM concurrency.
Use these complete files as starting points rather than combining the
illustrative fragments in this reference.
@@ -46,8 +45,8 @@ other than **version** is optional.
| Field | Type | Default | Rules |
| --- | --- | --- | --- |
| **version** | integer | none | Required; must be 4. |
| **promptkit** | object | none | Profile source and optional local-backend configuration. |
| **version** | integer | none | Required; must be 3. |
| **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. |
@@ -58,7 +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** |
@@ -70,85 +69,20 @@ 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.
## PromptKit Profiles
## Scriptorium Profiles
The optional **promptkit** object selects one source of profile definitions and
may register one conventional local OpenAI-compatible backend:
~~~yaml
version: 4
promptkit:
profile_dir: ./profiles
# profile_file: ./profiles.yml
local_backend:
endpoint: http://localhost:8000/v1
concurrency_limit: 2
~~~
The optional **scriptorium** object selects one source of profile definitions:
| Field | Type | Rules |
| --- | --- | --- |
| **profile_dir** | string | Non-empty directory containing profile files. |
| **profile_file** | string | Non-empty profile file. |
| **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**. Relative values use
the process working directory, not the configuration file's directory. The
complete example's `./examples/profiles/dnd-extraction.yml` value is therefore
valid when Notarius is launched from the repository root; use an absolute path
for services and containers.
An operator source is optional. For a requested ID, PromptKit checks the
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` operator profile](../examples/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
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
backend ID:
~~~yaml
id: local-summary
backend: local
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/v0.5.0/docs/formats.md).
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.
## Migrating Version 3 Configuration
Version 3 files are not decoded or rewritten. Change **version: 3** to
**version: 4** and rename the top-level **scriptorium:** section to
**promptkit:**. Version 4 decoding is strict, so a remaining **scriptorium**
field is rejected as unknown.
Set at most one of these fields. Profile IDs used by a binding must be available
from the selected Scriptorium profile source when the pipeline is resolved.
Keep credentials out of this file: configure a profile to read its credential
from an environment variable, then set that environment variable only in the
run environment.
## Operational Environment Variables
@@ -204,7 +138,6 @@ Each **pipelines** entry has a unique, non-empty ID and the following shape:
~~~yaml
pipelines:
dnd-session:
llm_profile: dnd-extraction
input: seriatim
chunk: generic
output: json
@@ -217,7 +150,6 @@ pipelines:
| 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. |
| **input** | module binding | none | Required. |
| **chunk** | module binding | **generic** | Optional. |
| **output** | module binding | **json** | Optional. |
@@ -231,12 +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.
A lane has these fields:
| Field | Type | Default | Rules |
@@ -264,7 +190,7 @@ Use an object for fields:
~~~yaml
extract:
module: dnd/spells
llm_profile: dnd-extraction
llm_profile: gemini-2-flash
retries: 2
references:
spell_catalog: ./dnd-spell-catalog.json
@@ -273,7 +199,7 @@ extract:
| 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. |
| **retries** | integer | 0 | Non-negative additional attempts for chunk, extract, merge, and normalize bindings. |
| **options** | object | none | Must satisfy the selected module. |
| **references** | map | none | Valid only on chunk, extract, merge, and normalize bindings. |
@@ -283,8 +209,7 @@ 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**, and **options**.
They reject **references**, **retries**, and nested **validators**. Deterministic
validators reject an explicit **llm_profile**. Deterministic module bindings
also reject an explicit **llm_profile**.
validators reject an explicit **llm_profile**.
The **json** output module accepts optional **include_chunk_map** and
**evidence_context** settings:
@@ -298,7 +223,7 @@ output:
enabled: true
window_units: 3
lanes:
- npc-registry
- npcs
- spells
~~~
@@ -319,8 +244,7 @@ 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
[Published Evidence Context contract](integrations/evidence-context.md).
Its payload contract is [Published Evidence Context](integrations/evidence-context.md).
## References And Ordered Handoffs
@@ -333,15 +257,15 @@ step:
steps:
- id: describe-session
artifacts:
npc-registry:
extract: dnd/npc-registry
normalize: dnd/npc-registry
npcs:
extract: dnd/npcs
normalize: dnd/npcs
- id: extract-events
references:
npc_registry:
npcs:
artifact:
step: describe-session
lane: npc-registry
lane: npcs
artifacts:
spells:
extract: dnd/spells
@@ -371,38 +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. |
| **item_registry** | Required normalized item registry for item-occurrence extraction and normalization. |
| **npc_registry** | Normalized NPC registry. Optional for spells and combat turns; required for NPC occurrences and enemy-event extraction and normalization. |
| **scene_descriptions** | Required normalized scene-description artifact for combat-turn and enemy-event extraction. |
| **combat_turns** | Required normalized combat-turn artifact for enemy-event extraction. |
| **npc_occurrences** | Required normalized NPC-occurrence artifact for enemy-event extraction. |
Registry-backed occurrence and enemy-event artifact slots have the following
exact binding contracts. Durable semantics and wire shapes remain in their
[NPC occurrence](integrations/dnd-npc-occurrence-artifacts.md),
[location occurrence](integrations/dnd-location-occurrence-artifacts.md),
[item occurrence](integrations/dnd-item-occurrence-artifacts.md), and
[enemy-event](integrations/dnd-enemy-event-artifacts.md) contracts.
| Slot | Accepted artifact kind | Media type | Maximum size | Required stage |
| --- | --- | --- | --- | --- |
| `npc_registry` | `dnd/npc-registry` | `application/json` | 1,048,576 bytes | extract and normalize |
| `scene_descriptions` | `dnd/scene-description-list` | `application/json` | 1,048,576 bytes | extract only |
| `combat_turns` | `dnd/combat-turn-list` | `application/json` | 1,048,576 bytes | extract only |
| `npc_occurrences` | `dnd/npc-occurrence-list` | `application/json` | 1,048,576 bytes | extract only |
| `location_registry` | `dnd/location-registry` | `application/json` | 1,048,576 bytes | location-occurrence extract and normalize |
| `item_registry` | `dnd/item-registry` | `application/json` | 1,048,576 bytes | item-occurrence extract and normalize |
| **npcs** | Normalized NPC registry. Optional for spells and combat turns; required for NPC interactions. |
| **scene_descriptions** | Required normalized scene-description artifact for combat-turn extraction. |
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
require **location_registry** for extraction and normalization. Item occurrences require
**item_registry** for extraction and normalization. Enemy-event extraction requires all
four of its JSON artifact slots; its normalizer requires **npc_registry**.
The [complete example](../examples/dnd-complete.config.yml) shows the ordered
generated bindings.
normalized combat-turn module may use optional **npcs**. The complete example
shows generated **npcs** and **scene_descriptions** bindings.
## Production Module Keys
@@ -410,29 +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),
[NPC occurrences](integrations/dnd-npc-occurrence-artifacts.md),
[NPCs](integrations/dnd-npc-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 occurrences](integrations/dnd-item-occurrence-artifacts.md),
[scene descriptions](integrations/dnd-scene-description-artifacts.md),
[enemy events](integrations/dnd-enemy-event-artifacts.md),
[location registry](integrations/dnd-location-registry-artifacts.md), and
[location occurrences](integrations/dnd-location-occurrence-artifacts.md).
[item events](integrations/dnd-item-event-artifacts.md), and
[scene descriptions](integrations/dnd-scene-description-artifacts.md).
## Production Validator Keys And Default Chains
@@ -442,15 +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 registry | **extract/dnd/item-registry/shape**, **extract/dnd/item-registry/source_refs**, **extract/dnd/item-registry/source_relatedness**, **normalize/dnd/item-registry/identity** |
| NPC occurrences | **extract/dnd/npc-occurrences/shape**, **extract/dnd/npc-occurrences/registry**, **extract/dnd/npc-occurrences/source_refs**, **extract/dnd/npc-occurrences/source_relatedness**, **normalize/dnd/npc-occurrences/invariants** |
| Item events | **extract/dnd/item-events/shape**, **extract/dnd/item-events/source_refs**, **extract/dnd/item-events/source_relatedness**, **normalize/dnd/item-events/invariants** |
| NPC interactions | **extract/dnd/npc-interactions/shape**, **extract/dnd/npc-interactions/registry**, **extract/dnd/npc-interactions/source_refs**, **extract/dnd/npc-interactions/source_relatedness**, **normalize/dnd/npc-interactions/invariants** |
| Scene descriptions | **extract/dnd/scene-descriptions/shape**, **extract/dnd/scene-descriptions/source_refs**, **extract/dnd/scene-descriptions/source_relatedness**, **normalize/dnd/scene-descriptions/invariants** |
| Enemy events | **extract/dnd/enemy-events/shape**, **extract/dnd/enemy-events/engagements**, **extract/dnd/enemy-events/source_refs**, **extract/dnd/enemy-events/source_relatedness**, **normalize/dnd/enemy-events/invariants** |
| Location registry | **extract/dnd/location-registry/shape**, **extract/dnd/location-registry/source_refs**, **extract/dnd/location-registry/source_relatedness**, **normalize/dnd/location-registry/identity** |
| Location occurrences | **extract/dnd/location-occurrences/shape**, **extract/dnd/location-occurrences/registry**, **extract/dnd/location-occurrences/source_refs**, **extract/dnd/location-occurrences/source_relatedness**, **normalize/dnd/location-occurrences/invariants** |
When no override is configured, production D&D bindings use the following
ordered chains. Each row lists extract then normalize; spell chains are the
@@ -459,15 +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 registry | generic/valid_json, extract/dnd/item-registry/shape, extract/dnd/item-registry/source_refs, generic/valid_json_schema, extract/dnd/item-registry/source_relatedness | generic/valid_json, extract/dnd/item-registry/shape, normalize/dnd/item-registry/identity, extract/dnd/item-registry/source_refs, generic/valid_json_schema, extract/dnd/item-registry/source_relatedness |
| NPC occurrences | generic/valid_json, extract/dnd/npc-occurrences/shape, extract/dnd/npc-occurrences/registry, extract/dnd/npc-occurrences/source_refs, generic/valid_json_schema, extract/dnd/npc-occurrences/source_relatedness | generic/valid_json, extract/dnd/npc-occurrences/shape, extract/dnd/npc-occurrences/registry, normalize/dnd/npc-occurrences/invariants, extract/dnd/npc-occurrences/source_refs, generic/valid_json_schema, extract/dnd/npc-occurrences/source_relatedness |
| Item events | generic/valid_json, extract/dnd/item-events/shape, extract/dnd/item-events/source_refs, generic/valid_json_schema, extract/dnd/item-events/source_relatedness | generic/valid_json, extract/dnd/item-events/shape, normalize/dnd/item-events/invariants, extract/dnd/item-events/source_refs, generic/valid_json_schema, extract/dnd/item-events/source_relatedness |
| NPC interactions | generic/valid_json, extract/dnd/npc-interactions/shape, extract/dnd/npc-interactions/registry, extract/dnd/npc-interactions/source_refs, generic/valid_json_schema, extract/dnd/npc-interactions/source_relatedness | generic/valid_json, extract/dnd/npc-interactions/shape, extract/dnd/npc-interactions/registry, normalize/dnd/npc-interactions/invariants, extract/dnd/npc-interactions/source_refs, generic/valid_json_schema, extract/dnd/npc-interactions/source_relatedness |
| 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

23
docs/consumers/subprocess.md
View File

@@ -27,13 +27,10 @@ notarius run pipeline-id \
```
Use absolute paths for supplied input, configuration, output-root, and
reference files. Notarius generates a stable prompt session for the resolved
input module and exact input bytes. Pass **--session-id** only when intentionally
grouping different invocations under a different session. Supply credentials
through Notarius's documented configuration and environment mechanisms, never
as command-line arguments or generated secret-bearing configuration. In
particular, a session identifier is provider-visible and is not a credential
mechanism.
reference files. When a stable prompt session identifier or references are
needed, pass the supported CLI flags. Supply credentials through Notarius's
documented configuration and environment mechanisms, never as command-line
arguments or generated secret-bearing configuration.
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
@@ -55,10 +52,10 @@ contract. The JSON bundle contract links to the available lane contracts.
If `index.json` has an `evidence_context` descriptor, treat it as a
pipeline-wide artifact rather than a lane entry. Verify its six descriptor
fields before decoding the linked file according to the [Published Evidence
Context contract](../integrations/evidence-context.md). Decode its top-level
source-unit array as a reading excerpt. Obtain authoritative citations and lane
provenance from the normalized lane artifacts; the excerpt has neither and its
nearby units do not widen a lane artifact's cited source reference.
Context contract](../integrations/evidence-context.md). Use each
`evidence_refs` entry as the citation to source material. Its surrounding
context range and included units explain the citation, but do not widen or
replace the cited source reference.
A zero exit status may still report rejected outputs, warnings, or absent
lanes. The caller decides which lane IDs are required for its own work and
@@ -73,5 +70,5 @@ them. Treat the input, output bundle, cache, debug bundle, and captured process
logs as potentially sensitive data. Apply the caller's access controls and
retention policy, and avoid copying secrets into arguments, logs, or
provenance records. An evidence-context artifact contains source-unit text and
metadata and can cover most of an input; preserve and share it only when that
source content is authorized for the recipient.
metadata, and selected lanes can cover most of an input; preserve and share it
only when that source content is authorized for the recipient.

2
docs/development.md
View File

@@ -22,7 +22,7 @@ implemented component map.
| 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. |
| Proposed or unimplemented behavior | [Roadmap](roadmap/) | Future work belongs only in roadmap documentation until implemented. |

12
docs/integrations/dnd-combat-turn-artifacts.md
View File

@@ -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
broader NPC occurrences. The [enemy-event artifact](dnd-enemy-event-artifacts.md)
uses combat turns as grounding only; turns do not establish an enemy event or
its outcome. The [JSON output contract](json-output.md) defines publication,
and [D&D module internals](../internal/dnd.md) describes routing and validation
mechanics.
The [NPC-interaction artifact](dnd-npc-interaction-artifacts.md) records
broader NPC occurrences. The [JSON output contract](json-output.md) defines
publication, and [D&D module internals](../internal/dnd.md) describes routing
and validation mechanics.

114
docs/integrations/dnd-enemy-event-artifacts.md
View File

@@ -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).

78
docs/integrations/dnd-item-event-artifacts.md Normal file
View File

@@ -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.

72
docs/integrations/dnd-item-occurrence-artifacts.md
View File

@@ -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.

95
docs/integrations/dnd-item-registry-artifacts.md
View File

@@ -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.

86
docs/integrations/dnd-location-occurrence-artifacts.md
View File

@@ -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.

93
docs/integrations/dnd-location-registry-artifacts.md
View File

@@ -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.

69
docs/integrations/dnd-npc-artifacts.md Normal file
View File

@@ -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.

50
docs/integrations/dnd-npc-occurrence-artifacts.md → docs/integrations/dnd-npc-interaction-artifacts.md
View File

@@ -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` |
| Schema ID | `notarius.dnd.npc_occurrences` |
| Schema name | `notarius_dnd_npc_occurrences_v1` |
| Artifact kind | `dnd/npc-interaction-list` |
| Schema ID | `notarius.dnd.npc_interactions` |
| 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
empty. Occurrence and source-reference objects reject unknown fields. An
`v1` is a strict JSON object with required `interactions`; the array may be
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)
supplies names-only contextual grounding to the model. Notarius resolves the
selected name and writes the exact `{npc_id, name}` pair. An unknown or
ambiguous selection rejects the complete model result; normalization does not
repair names by similarity. Registry references are provenance only and never
replace an occurrence's own evidence.
The registry may include an identity established by a factual third-party
mention; that provenance alone does not create a `mentioned` occurrence. Each
occurrence remains a separately cited fact in the current transcript.
Normalization validates the exact pair, orders and
deduplicates exact source references, then orders occurrences by valid source
The required normalized [NPC artifact](dnd-npc-artifacts.md) resolves `name`.
Registry references are provenance only and never replace an interaction's own
evidence. Normalization canonicalizes recognized registry names, orders and
deduplicates exact source references, then orders interactions by valid source
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
only `combat_opponent` occurrences as grounding; they never establish an enemy
event or outcome. The [JSON output contract](json-output.md) defines
publication. Pipeline mechanics are described in
[D&D module internals](../internal/dnd.md).
occurrences and the [JSON output contract](json-output.md) for publication.
Pipeline mechanics are described in [D&D module internals](../internal/dnd.md).

92
docs/integrations/dnd-npc-registry-artifacts.md
View File

@@ -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.

5
docs/integrations/dnd-scene-description-artifacts.md
View File

@@ -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
[enemy-event artifact](dnd-enemy-event-artifacts.md) use an exact matching
The [combat-turn artifact](dnd-combat-turn-artifacts.md) uses 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).

2
docs/integrations/dnd-spell-artifacts.md
View File

@@ -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`.

6
docs/integrations/dnd-spell-catalog-overlays.md
View File

@@ -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).

109
docs/integrations/evidence-context.md
View File

@@ -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
convenient reading alongside normalized lane artifacts; it is not a second
citation or provenance model. Its configuration is owned by
[Configuration](../config.md#module-bindings-and-validators), and its
logical-file discovery is owned by [Published JSON Output](json-output.md).
by the production JSON output. Its configuration is owned by
[Configuration](../config.md#module-bindings-and-validators); its logical-file
discovery is owned by [Published JSON Output](json-output.md).
## Identity And Discovery
@@ -28,13 +26,35 @@ 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
wrapper, source-level metadata, context grouping, lane identifier, or evidence
reference in the payload. An enabled configuration with no contributing
accepted evidence publishes `[]`.
The v1 payload is a JSON object with required `source_id`, `source_digest`,
`window_units`, `selected_lanes`, and `contexts` fields. `selected_lanes` and
`contexts` are always arrays; an enabled configuration with no accepted direct
evidence publishes `contexts: []`.
```json
[
{
"source_id": "session-alpha",
"source_digest": "sha256:0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef",
"window_units": 1,
"selected_lanes": ["npcs", "spells"],
"contexts": [
{
"context_ref": {
"source_id": "session-alpha",
"start_unit_id": 10,
"end_unit_id": 20
},
"evidence_refs": [
{
"lane_id": "spells",
"source_ref": {
"source_id": "session-alpha",
"start_unit_id": 10,
"end_unit_id": 10
}
}
],
"units": [
{
"id": 10,
"kind": "transcript_segment",
@@ -55,53 +75,42 @@ accepted evidence publishes `[]`.
"end_unit_id": 20
}
}
]
]
}
]
}
```
Each source unit has required `id`, `kind`, `text`, and self `ref` fields.
`ref` contains `source_id`, `start_unit_id`, and `end_unit_id`, and both unit
endpoints identify that unit's `id`. A unit may also contain source-owned
`metadata`, an open-ended JSON object. Fixed unit and reference fields are
strict: consumers must reject unknown fixed fields, malformed units, invalid
self-references, units whose `source_id` differs from other units in the same
excerpt, and a payload that is not the array described here.
Each context requires `context_ref`, `evidence_refs`, and `units` arrays.
`context_ref` identifies the first and last included unit. Each evidence entry
contains a selected `lane_id` and an original `source_ref`. A unit uses the
existing source-unit shape: required `id`, `kind`, `text`, and self `ref`, plus
optional JSON-object `metadata`. Fixed payload objects reject unknown fields;
unit metadata may contain application-defined JSON values.
The excerpt preserves each selected unit exactly as represented by the
validated generic source document. It does not add evidence-context-specific
annotations or reshape source-owned metadata.
## Citations And Context
## 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
projections of accepted normalized artifacts in the configured lane allowlist.
It validates each reference against the current source document, expands its
range by `window_units` source-unit positions on each side, clamps at document
boundaries, and takes the union of all expanded ranges. The output contains
each selected source unit once in source-document position order, regardless
of numeric unit IDs. Repeated references, overlapping windows, and citations
from multiple lanes do not duplicate a unit. Rejected, failed, absent,
inactive, and unselected lanes contribute nothing.
Only accepted outputs from the configured lane allowlist contribute. Rejected,
failed, absent, and lane-filtered outputs do not contribute. The artifact never
contains raw input bytes, prompts, model responses, auxiliary reference
content, credentials, or filesystem paths.
Normalized lane artifacts remain authoritative for citations and for which lane
cited a range. The excerpt has no lane attribution and must not be used to
reconstruct it. Its included nearby units provide reading context only; they
do not widen any citation in a lane artifact.
## Ordering And Compatibility
The excerpt contains at most every generic source unit once. It can therefore
equal the complete generic source document when coverage is broad or the
window is large. No byte-, token-, or compression-size guarantee is made, and
the framework does not truncate the excerpt to meet an arbitrary size limit.
## Consumer Responsibilities And Data Handling
The selected lane allowlist is lexical. Contexts and units are in source
document position order, not numeric unit-ID order. Direct evidence entries
are deterministically ordered by lane and source reference. Overlapping or
contiguous windows merge, and each source unit appears at most once in the
resulting contexts.
The 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
should validate the descriptor and payload before use, retain the artifact with
its schema identity when needed for a run record, and read citations from the
corresponding normalized lane artifacts.
The excerpt contains source-unit text and source-owned metadata and is durable
output. Treat it as sensitive source content, apply appropriate access controls
and retention, and do not assume its selected form is materially smaller or
less sensitive than the original input.
do not need it must tolerate the absent optional descriptor. Consumers that do
use it should preserve the artifact and its schema identity with the run
provenance, and should treat its source text and metadata as sensitive durable
content.

34
docs/integrations/json-output.md
View File

@@ -24,7 +24,7 @@ root for the logical discovery described here.
| `warnings.json` | Accepted-output and run warnings. |
| `lanes/<safe-lane-id>.json` | One normalized artifact payload for each lane. |
| `chunk-map.json` | Optional accepted chunk map, when its export is enabled and available. |
| `evidence-context.json` | Optional 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`.
@@ -71,15 +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),
[NPC occurrences](dnd-npc-occurrence-artifacts.md),
[spells](dnd-spell-artifacts.md), [NPCs](dnd-npc-artifacts.md),
[NPC interactions](dnd-npc-interaction-artifacts.md),
[combat turns](dnd-combat-turn-artifacts.md),
[item registry](dnd-item-registry-artifacts.md),
[item occurrences](dnd-item-occurrence-artifacts.md),
[scene descriptions](dnd-scene-description-artifacts.md),
[enemy events](dnd-enemy-event-artifacts.md),
[location registry](dnd-location-registry-artifacts.md), and
[location occurrences](dnd-location-occurrence-artifacts.md).
[item events](dnd-item-event-artifacts.md), and
[scene descriptions](dnd-scene-description-artifacts.md).
## `manifest.json`
@@ -102,26 +98,6 @@ summarize results without embedding lane payload bytes. A chunk-plan summary is
provenance for the plan used by this run; cache records, debug artifacts, and
other operational state are not published as bundle files.
When present, `metadata.session_id` is the effective non-secret routing
correlation identifier used for the run. It can be visible to providers and is
not a substitute for a cache or checkpoint identity. Its generation and
override behavior are defined by the [CLI reference](../cli.md#run).
Each `llm_profiles` entry identifies effective, non-secret LLM execution
provenance:
| 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 And Warnings
`rejected.json` is always an object with a `rejected` array. Each entry has

108
docs/integrations/pkg-promptkit.md
View File

@@ -1,108 +0,0 @@
# PromptKit Integration
Notarius pins
[`gitea.maximumdirect.net/eric/promptkit` v0.5.0](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.5.0)
as its in-process prompt engine. The upstream
[Go package consumer guide](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.5.0/docs/consumers/pkg-promptkit.md)
owns the public engine API, and the upstream
[format reference](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.5.0/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, and profile selection, 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/v0.5.0/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 v0.5.0's 256-code-point session limit. Session IDs are non-secret
correlation identifiers and may be exposed to providers and provider
observability. The CLI contract owns generation and override behavior.
Notarius records PromptKit's selected backend ID and effective reasoning
setting as optional run-manifest provenance. Endpoint-only profiles have no
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, and leaves retries to the calling pipeline stage.
## 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).
Notarius supports this boundary against PromptKit v0.5.0. 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.
[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.

53
docs/internal/cli.md
View File

@@ -38,14 +38,9 @@ in [Configuration Internals](configuration.md).
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
PromptKit profile. Selected LLM-backed input, chunk, lane, output, and validator
profiles are inspected
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.
effective catalog, resolves the pipeline, and verifies explicitly selected
Scriptorium profiles. Pipeline listing validates configuration before returning
normalized, sorted identifiers.
## Production Composition
@@ -56,24 +51,12 @@ 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
**promptkit.profile_dir** or **promptkit.profile_file** source, attaches the
profile-provenance recorder, creates one scheduler from the effective global
LLM limit, and wraps the client before it reaches modules. Registration and LLM
construction errors are returned before a pipeline is prepared. Configuration
field definitions remain in [Configuration](../config.md#promptkit-profiles);
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.
The production LLM factory builds the Scriptorium-backed client from resolved
configuration, creates one scheduler from the effective global LLM limit, and
wraps the client before it reaches modules. Registration and LLM construction
errors are returned before a pipeline is prepared. Concrete module keys and
validator chains are public configuration choices and remain documented in
[Configuration](../config.md).
## Run Orchestration
@@ -85,15 +68,12 @@ handoff:
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
profiles;
the effective pipeline, and verify explicit Scriptorium 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;
6. read the source input once, resolve its effective session from the explicit
override or resolved input module and raw bytes, then construct requested
checkpoint collaborators and invoke the framework runner with that same
value; and
5. construct registries, the scheduled LLM client, prepared modules, and the
requested cache/checkpoint collaborators;
6. read the source input and invoke the framework runner; and
7. write the runner's logical output files only after a successful run, then
complete the command report and user-facing result.
@@ -104,13 +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.
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

45
docs/internal/configuration.md
View File

@@ -39,22 +39,14 @@ This establishes the public precedence order without giving environment input a
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. A present
PromptKit local-backend object requires and trims its endpoint, defaults its
omitted concurrency limit to zero, and is copied so the parsed file model
cannot alias the populated **Config**. A pipeline `llm_profile` is
presence-aware: omission remains empty, while a present blank value is
rejected and a non-empty file value is trimmed before it reaches **Config**.
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
accepts only an absolute HTTP or HTTPS endpoint with a host and no user
information, query, or fragment, and rejects a negative local concurrency
limit. 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.
invalid pipeline, step, or lane structure. 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 additions to the file model, an
@@ -64,15 +56,13 @@ environment override, its validation, and that reference in the same change.
**Config.Resolve** first recomputes derived concurrency defaults and validates
the configuration. It normalizes the requested pipeline ID, copies the selected
profile, and passes the non-empty command-level LLM profile override, requested
lane selection, and reference changes to the framework resolver.
profile, applies a non-empty command-level LLM profile override to the
LLM-capable stage bindings, and calls the framework resolver with the requested
lane selection and reference changes.
After module and validator selection, the resolver applies the effective
profile policy to LLM-backed bindings only: command override, binding profile,
pipeline profile, then the prompt default. Deterministic bindings remain
profile-free, and no second inheritance decision occurs during execution. The
public field definitions and precedence are owned by
[Configuration](../config.md#pipelines).
The command-level override does not replace an explicitly selected validator
profile. Validator bindings remain part of the resolved validator chain and
are resolved under their own declared configuration.
The framework resolver supplies defaults, selects lanes, resolves validator
chains, checks registered module and artifact compatibility, validates module
@@ -81,8 +71,7 @@ options, and returns the fixed ordered pipeline shape. The resulting
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
PromptKit local-backend value.
configuration through the effective value.
Resolution failures stop before module construction and source parsing. They
include an error path for an unconfigured pipeline, missing module, missing
@@ -94,8 +83,7 @@ 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, effective LLM profiles, and artifact schema identity have been
resolved. The digest excludes
chains, and artifact 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
@@ -106,12 +94,9 @@ Configuration summaries must use **Redacted**, **RedactedSummaryPayload**, or
Those methods copy every binding and nested option container, replace values
whose key is credential-shaped with **[REDACTED]**, and omit materialized
reference content while retaining safe binding and reference provenance. The
payload must not alias the source configuration or resolved pipeline.
PromptKit's local endpoint and concurrency limit are preserved as non-secret
configuration metadata in the independently owned summary; the object contains
no credential value. This redaction is deliberately narrow: it protects
configuration summaries and does not authorize 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

202
docs/internal/dnd.md
View File

@@ -7,34 +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 registry | [item-registry artifacts](../integrations/dnd-item-registry-artifacts.md) |
| NPC occurrences | [NPC-occurrence artifacts](../integrations/dnd-npc-occurrence-artifacts.md) |
| Item events | [item-event artifacts](../integrations/dnd-item-event-artifacts.md) |
| NPC interactions | [NPC-interaction artifacts](../integrations/dnd-npc-interaction-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
profile asset, and default validator chains. Each extractor and normalizer has
a stable module spec, explicit execution class, strict option decoding, and a
typed builder. Scene chunking, every extractor, and NPC, location, and item-registry
normalization are registered as `llm_backed`; the remaining current D&D mergers
and normalizers are `deterministic`. The metadata is available to catalog inspection and
resolved-pipeline debug data and determines which selected bindings inherit the
pipeline profile. Configuration remains the canonical owner of the exact keys,
profile precedence, and validator order.
append-order mergers, normalizers, validators, prompt assets, and default
validator chains. Each extractor and normalizer has a stable module spec,
strict option decoding, and a typed builder. Configuration remains the
canonical owner of the exact keys and validator order.
Private structured-LLM response schemas are deliberately minimal. They reject
invalid JSON structure, missing required fields, incompatible types, and
@@ -44,69 +35,19 @@ the contracts above define durable data.
## Prompt Construction
D&D LLM-facing content lives beneath `assets/dnd/`. Each module contributes a
local `prompt.yaml` declaration and `instructions.md`; input-specific files
such as a catalog, registry, grounding projection, or candidate collection are
local only when that module needs them. New extractor content uses its feature
subtree, while families with both extraction and normalization content use their
`extract` and `normalize` subtrees. Shared visual-provenance fragments use
the `common-dnd-` prefix. Production lane code belongs with its D&D codec,
extractor, normalizer, and validator packages; registry projections and
identity helpers remain in their owning entity packages rather than in a
consumer lane.
D&D extractors assemble prompts from an ordered manifest of shared and
module-owned assets. Reuse the shared D&D system, evidence, identity,
reference, and transcript assets instead of copying their text into individual
modules. A manifest’s declared sequence, including cache-control placement, is
part of the prompt behavior, and the chunk transcript is the final message.
Preserve that order when changing an extractor or its assets so prompt-cache
behavior remains stable.
The owning module’s manifest is the source of truth for which local and shared
assets are selected, their mount paths, their message order, cache controls,
and the files included in its prompt fingerprint. Shared fragments belong to
the D&D shared implementation and are selected by name rather than copied into
module directories. The root `assets` package is a content-only boundary; its
physical ownership and rationale are defined by
[ADR-0011](../adr/0011-centralize-llm-assets.md).
Put each rule at its narrowest owner:
- universal behavior belongs in the shared system asset;
- D&D-family behavior belongs in a selected `common-dnd-` asset;
- rules for an input projection belong with that input asset;
- lane-specific policy belongs in the module’s `instructions.md`; and
- transport-envelope shape belongs in the private response schema.
A rule is eligible for the system prompt only when every D&D LLM prompt needs
it regardless of lane, inputs, or response shape. Module instructions must not
repeat rules selected from shared assets or schemas. Reintroduce such repetition
only after observational evaluation with representative transcripts shows that
it improves results at the intended target models and cost; structural prompt
tests alone are not that evidence.
Every maintained D&D LLM prompt selects `dnd-extraction` as its default
profile. The D&D registrar 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.
All extractors use the shared prompt-input preparation rules. The current chunk
is copied into transcript material; player, party, glossary, and compatible
campaign references are context for disambiguation, not source evidence.
Reference prompt material is canonically ordered before it is rendered, which
keeps equivalent inputs stable across runs.
## Evidence, Candidates, And Normalization
@@ -119,63 +60,19 @@ 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,
durable-schema validation checks an approved representation, and
source, 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).
Enemy-event extraction additionally rejects a second `engaged` observation for
the same comparison identity within one scene-scoped result. Normalization may
combine results from distinct scenes, so it intentionally does not apply that
rule. Configuration owns the exact validator key and chain position.
Normalizers are deterministic for spells, combat turns, item occurrences, NPC
occurrences, scene descriptions, enemy events, and location occurrences. They
canonicalize display values and evidence, use source-document order for stable
output, and issue bounded warnings for changes or collapsed duplicates. NPC,
item, and location registry normalizers are intentional exceptions: each first
produces a deterministic candidate set, then may use a bounded structured-LLM
proposal to reconcile identity groups.
## Semantic Registry Reconciliation
The three registry normalizers instantiate the domain-neutral
`internal/framework/semanticreconcile` engine with default bounds. Each
eligible candidate receives a contiguous, one-based `candidate_id` for that
request. The model sees that handle, the candidate label and source-free
evidence ranges, plus bounded transcript windows; it returns only duplicate
groups of supplied handles and one supplied canonical handle per group. It
never returns names, evidence, durable IDs, or replacement records. Identical
labels and evidence remain independently selectable because their handles are
distinct.
The generic core owns the mandatory handle protocol, candidate and transcript
presentation, the private response schema, source-reference validation,
candidate and combined-material limits, structured completion, proposal
assessment, stable group ordering, and typed plan-application mechanics. The
D&D prompt contributes its system message and registry-specific semantic
instructions. The generic registrar registers the shared prompt and schema;
the D&D registrar registers each consuming prompt and the fallback profile.
Fewer than two eligible candidates skips the LLM without a semantic warning.
An exceeded bound also skips the call and preserves the deterministic
preprocessed registry, adding the registry's bounded fallback warning. Invalid
structured output or discarded proposal groups use the normalizer's existing
retry contract; retry exhaustion preserves the safe deterministic or
partially applied result and emits its bounded fallback warning. Provider,
transport, cancellation, and context-material failures remain execution
errors.
Application remains typed and registry-owned. All three policies select the
canonical member's normalized display name, union member evidence in source
order, preserve ungrouped records, and derive durable identity only after
consolidation. NPC IDs derive from the final name. Item IDs also derive from
the final name, and a typed guard prevents currency aliases from crossing
denominations or mixing currency with non-currency records. Location IDs
derive from the final name and final evidence, preserving same-name,
parent/child, and distinct physical-place identities. Registry warning scopes,
reason codes, and postconditions remain outside the generic core.
Normalizers are deterministic for spells, combat turns, item events, NPC
interactions, and scene descriptions. They canonicalize display values and
evidence, use source-document order for stable output, and issue bounded
warnings for changes or collapsed duplicates. The NPC normalizer is the
intentional exception: it first produces a deterministic candidate set, then
uses a bounded structured-LLM proposal to reconcile identity groups. Invalid
or unusable proposals retain the deterministic result and surface retry or
fallback diagnostics; the model does not directly replace durable records.
## Generated References And Grounding
@@ -185,55 +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
consumers receive a contextual selector containing the canonical name and the
registry references needed to distinguish same-name places. The calling module
resolves those supplied selections locally and maps them into the unchanged
durable ID/name pair; an unknown or ambiguous selection rejects the complete
occurrence result rather than accepting a partial mapping. The NPC registry
additionally supplies names-only actor grounding to spells, combat turns, and
enemy events.
Registry references establish a registry identity and may disambiguate a
selection, but never become occurrence evidence. Each occurrence keeps its own
current-transcript source references, even when it was grounded through the
same registry record.
Scene descriptions are eligibility-only projections: they retain current-chunk
classification data, not scene prose or evidence, and exist to route combat
extraction. Enemy-event extraction also projects combat turns to `actor` and
`turn_kind` and filters NPC occurrences to `combat_opponent` names and kinds.
These projections are guidance only and never event evidence.
NPC registries are names-only grounding projections: they may canonicalize
actors for spells and combat turns and are required for NPC interactions, but
they do not supply evidence. Scene-description registries are eligibility-only
projections: they retain the current chunk’s classification data, not scene
prose or evidence, and exist to route combat extraction.
## 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 registry | Produces source-grounded item types and unique designations. Its LLM-assisted reconciliation is proposal-only, preserves distinct currency denominations and item types, and does not create per-instance identities. |
| NPC occurrences | Requires the normalized NPC registry at extraction and normalization, using it for canonical actor grounding only. It separately emits cited current-transcript occurrence facts, including `mentioned`, rather than deriving them from registry provenance. |
| Item events | Uses campaign context for disambiguation but has no NPC-registry or scene-description dependency. |
| NPC interactions | Requires the normalized NPC registry at extraction and normalization, using it for canonical actor grounding only. |
| 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

239
docs/internal/llm.md
View File

@@ -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
@@ -24,86 +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
application identity; PromptKit and this adapter do not own entity identity.
`ScriptoriumClient` validates the request target and prompt identity, maps each
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
named material to a PromptKit inline artifact while preserving its origin URI,
passes the supplied request session through to PromptKit's direct per-run
session field, retains the same value as the `session_id` prompt variable for
maintained prompt compatibility, and forwards profile selection. It does not
derive or replace session values; the CLI owns that policy. It then creates one
frozen prepared execution, captures its caller-owned credential-redacted
details for debug material, and executes that exact snapshot through
PromptKit's prepared-execution boundary. The direct field
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.
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: 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.
An empty request profile lets the prompt select its configured default. The CLI
prepares every explicitly selected binding profile before a run begins, so a
missing explicit profile fails before stage execution. Calls record the profile
actually selected by Scriptorium; the recorder deduplicates non-secret profile
identity, provider, and model values for manifest use.
## 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.
A granted permit is released exactly once on every completion path.
cancelled. 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
@@ -112,57 +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
filesystems from production module families. It flattens registered roots into
the corresponding PromptKit filesystems and rejects invalid roots, unreadable
assets, duplicate paths, and missing prompt or schema files during preparation.
Fallback assets receive a safe content digest for checkpoint identity; raw
paths and bytes are never included. The framework’s `promptfs` helper combines
module-selected prompt files with reusable domain fragments without making the
An `AssetRegistry` collects prompt and schema filesystems from production module
families. It flattens registered roots into the Scriptorium filesystems and
rejects invalid roots, unreadable assets, duplicate paths, and missing prompt
or schema files during preparation. The framework’s `promptfs` helper combines
module-owned 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
uses only its scoped subtree, while the module retains ownership of its prompt
declaration, ordered manifest, private response-schema identity, and
registration. Shared D&D fragments are selected by D&D's shared implementation;
the detailed convention is in [D&D Module Internals](dnd.md). This physical
arrangement and its data-only boundary are defined by
[Architecture](../policy/architecture.md) and
[ADR-0011](../adr/0011-centralize-llm-assets.md), rather than by this runtime
guide.
The generic registrar is the sole production registration owner for the
semantic-reconciliation default prompt and private response schema. The
domain-neutral reconciliation package also exposes only its mandatory protocol
and candidate/transcript presentation files for domain prompt manifests. D&D
registry normalizers mount those files while retaining ownership and hashing
of their D&D system message, semantic instructions, and complete prompt
declaration. The response schema is therefore registered once even though
several typed normalizers select it.
Mounted prompt assets determine a module's fingerprint. The fingerprint hashes
only the module and shared files explicitly selected by its manifest, so an
unrelated asset does not invalidate a checkpoint. Schema loaders validate JSON,
attach identity and digest metadata, make defensive copies, and expose
diagnostics without raw schema bytes.
Semantic-reconciliation normalizers extend this identity with the shared
response-schema digest, framework policy version, and complete limit-policy
digest. Their manifest metadata records the same content-free prompt, schema,
policy, and limit identities together with domain identity and normalization
policies. Request-local handles, source material, proposal content, and raw
asset bytes are not checkpoint metadata.
Each LLM-backed module owns its prompt declaration, package-specific assets,
and private response schema. Shared D&D wording is owned by the D&D shared
asset package; the detailed D&D conventions are in
[D&D Module Internals](dnd.md). The mounted prompt assets used by a module also
determine its prompt fingerprint. Schema loaders validate JSON, attach identity
and digest metadata, make defensive copies, and expose diagnostics without raw
schema bytes.
Private response schemas validate a model transport envelope. They are not the
durable artifact schema and should not be documented as an external wire
@@ -172,45 +76,30 @@ 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
metadata—not merely equivalent meaning. Keep reusable shared assets
byte-identical and preserve each prompt’s declared ordering and cache controls
when editing it.
reuse depends on the same preceding messages and content, not merely equivalent
meaning. Keep reusable shared assets byte-identical and keep stable material
before the inputs that vary per request wherever a prompt’s declared sequence
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
shared context first, request source material next, and module-specific
suffixes last. Put a cache boundary at a reusable prefix that is useful to the
backend. Redundant intermediate cache boundaries do not extend that reusable
prefix and add no value.
Prompt-family owners may choose a different sequence when their inputs and
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.
D&D extraction manifests place the changing chunk transcript at the end of the
prompt after their reusable context. Scene chunking and NPC normalization use
their own declared message sequences because their inputs and work differ. The
family-specific asset and ordering rules belong in [D&D Module Internals](dnd.md).
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
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
invalid-output categories, provider error values and types do not cross the
adapter error chain; callers receive only a credential-redacted diagnostic.
than output-validation failures.
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.
Prompt-declared repair is executed within PromptKit’s structured-output flow.
Prompt-declared repair is executed within Scriptorium’s structured-output flow.
The current production D&D prompt manifests set repair attempts to zero. That
setting does not replace pipeline retry behavior: a binding’s configured retry
count reruns its stage attempt after an error or rejection, and an exhausted
@@ -219,42 +108,22 @@ 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; 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. Notarius binding
retries remain outside the adapter and repeat the complete module operation
and validation chain. PromptKit does not add a provider retry loop.
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
debug bundle, including material available from a failed structured completion.
Effective parameters use PromptKit's stable lower-case JSON field names and may
include `backend_id`. For a successful completion, a debug-write failure is
surfaced; when the completion already failed, its call error remains the
result. Debug-bundle location, retention, and handling are operational concerns
documented in [Operations](../operations.md#debug-bundles).
and model, and call identifiers in the run’s debug bundle, including material
available from a failed structured completion. For a successful completion, a
debug-write failure is surfaced; when the completion already failed, its call
error remains the result. Debug-bundle location, retention, and handling are
operational concerns documented in [Operations](../operations.md#debug-bundles).
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.
Run manifests receive selected profile summaries and component identities, not
prompt, schema, source, reference, or response content. 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.
## Failure Boundaries
@@ -262,8 +131,6 @@ contents safe for general logging.
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.

65
docs/internal/modules.md
View File

@@ -12,15 +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
accepted reference slots. The execution class states whether a module is
`deterministic` or `llm_backed`; registries retain it for catalog inspection and
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).
stage, required and provided capabilities, artifact kind, and accepted
reference slots. The framework uses that declaration to resolve a configured
binding before it builds the implementation.
Implementations that accept options must provide both an option validator and
a builder. The validator is used while resolving configuration; the builder
@@ -42,72 +36,33 @@ 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
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.
for the durable result.
## 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
schema assets.
and JSON output encoder.
- 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
request-local integer handles, renders bounded candidate and transcript
materials, invokes the structured-completion boundary, and assesses the
returned duplicate groups into a stable non-overlapping plan.
The normalizer then applies that plan through a typed `ApplicationPolicy`. The
core preserves ungrouped records, contribution order, and provenance while the
artifact family owns group guards, field and evidence consolidation, durable
ID derivation, retry and fallback presentation, warnings, and postconditions.
Request-local handles do not enter the typed value or durable artifact. Fewer
than two eligible candidates skips model invocation; exceeding a candidate or
combined-material bound preserves the deterministic result under the family's
fallback policy. Provider, transport, cancellation, and context-construction
failures remain execution errors.
The core supplies a conservative generic prompt and the single private
response schema. A domain prompt may substitute its semantic instructions but
mounts the core-owned protocol and candidate/transcript presentation assets.
Prompt, schema, policy, and limit identities participate in manifest metadata
and checkpoint fingerprints. The generic registrar owns production
registration of those shared assets; a consuming domain registrar owns only
its domain prompt.
## Adding Or Changing A Module
1. Choose the pipeline stage and the typed artifact boundary. Put external
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
capabilities, and reference slots needed for the operation. Model a
producer/consumer handoff as an artifact-compatible slot; configuration
then chooses an external file or a generated binding.
2. Define a stable `ModuleSpec` with the exact capabilities and reference
slots needed for the operation. Model a producer/consumer handoff as an
artifact-compatible slot; configuration then chooses an external file or a
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.

7
docs/internal/overview.md
View File

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

44
docs/internal/pipeline.md
View File

@@ -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
collaborators. It returns logical output files, normalized artifacts, recorded
rejections and warnings, manifest provenance, and checkpoint decisions. The
CLI owns process arguments, configuration discovery, session resolution,
physical roots, and placement of returned output files.
dependencies, input bytes, and state/debug collaborators. It returns logical
output files, normalized artifacts, recorded rejections and warnings, manifest
provenance, and checkpoint decisions. The CLI owns process arguments,
configuration discovery, physical roots, and placement of returned output
files.
The framework has one fixed shape:
@@ -34,11 +34,6 @@ 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. 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. Deterministic bindings remain profile-free.
These effective values are part of the digest, so execution and checkpoint
consumers do not repeat profile inheritance.
Configuration resolution supplies the selected profile and catalog; see
[Configuration Internals](configuration.md).
@@ -46,18 +41,16 @@ 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
and rejects overflow before retaining content. A generated-artifact selector
remains declared but has no bytes until its producing step completes.
provenance. A generated-artifact selector remains declared but has no bytes
until its producing step completes.
Preparation is the construction boundary. It validates the resolved shape and
registry set, clones the resolved data, then constructs the input adapter,
chunker, stage-local validators, every typed lane, and output encoder. Each
registered builder receives its own cloned build request immediately before its
module-owned code runs. Preparation also collects stable checkpoint
fingerprints. Missing registrations, incompatible typed entries, nil
implementations, and constructor failures are reported before source parsing
or any stage operation begins.
chunker, stage-local validators, every typed lane, and output encoder with
cloned options, references, and shared dependencies. It also collects stable
checkpoint fingerprints. Missing registrations, incompatible typed entries,
nil implementations, and constructor failures are reported before source
parsing or any stage operation begins.
An output encoder can opt into source-evidence publication through its output
policy. Preparation keeps the configured lane allowlist and active lanes
@@ -86,10 +79,6 @@ incompatible producer prevents the consumer step from starting.
The runner validates its input, installs no-op state collaborators when none
were supplied, and serially performs source parsing and chunk-plan selection.
It transports the supplied session unchanged to prompt-facing operations and
run-manifest metadata; it neither derives a session nor substitutes a parsed
source document identifier. The public session contract is owned by the
[CLI reference](../cli.md#run).
An accepted plan is materialized into source-addressed chunks and passes the
configured chunk validators before any lane runs. A chunk rejection is a
recorded pipeline outcome: lanes do not start, but the output stage can encode
@@ -117,12 +106,9 @@ 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
bytes. Each typed validator receives a newly decoded value from the one
candidate serialization for that attempt, while serialized validators receive
separately owned representation bytes and schema metadata. They may approve,
approve with warnings, reject, or fail. A rejection is an ordinary pipeline
result; a validator error is a framework error.
their target: chunks, typed values, or serialized codec bytes. They may
approve, approve with warnings, reject, or fail. A rejection is an ordinary
pipeline result; a validator error is a framework error.
The runner applies the binding's retry policy around a stage operation and its
complete validation chain. It preserves warnings only from the final accepted

7
docs/internal/state.md
View File

@@ -39,17 +39,12 @@ codecs, loader, and recorder. The CLI constructs a recorder whenever checkpoint
recording is enabled and constructs a loader only for a `--resume` invocation.
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
non-secret effective profile-source identity. A profile source change therefore
causes a cold miss even when the configured profile ID remains unchanged.
references, runtime overrides, and LLM profiles.
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

105
docs/operations.md
View File

@@ -42,42 +42,6 @@ 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
[operator profile](../examples/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
~~~
Profile paths are currently resolved from the process working directory, not
from the configuration file. The complete example's
`./examples/profiles/dnd-extraction.yml` path is valid for a repository-root
invocation only. Use absolute paths such as
`/etc/notarius/profiles/dnd-extraction.yml` for services and containers.
## Run Lifecycle
Use the [run command](cli.md#run) to start a pipeline. A valid invocation loads
@@ -110,9 +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
every source unit once when coverage is broad or its configured window is
large, so do not assume a byte or token reduction or reduced sensitivity.
controls to the entire bundle. Selected lanes may collectively cite most of a
transcript, so a broad allowlist can make the evidence artifact nearly as
sensitive and large as the source itself.
## Chunk-Plan Cache
@@ -153,15 +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
prepared-component fingerprints. When a local PromptKit backend is configured,
compatibility also includes a non-secret fingerprint of its endpoint. Changing
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.
provenance, and prepared-component fingerprints. A changed identity produces a
cold miss; Notarius does not migrate, rewrite, or delete older checkpoint
directories.
Checkpoint state is confined below an identity-specific path:
@@ -221,9 +179,7 @@ warning, checkpoint, chunk-plan, and terminal reporting artifacts. The trace
contains allowlisted application diagnostic records and can include source or
derived application data. 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.
redacted.
Notarius never creates debug state without an explicit request and never
automatically deletes a requested bundle. If allocation succeeds, the command
@@ -251,51 +207,10 @@ or automatic cleanup command.
## Operational Limits
Provider execution settings and the generation timeout come from the selected
PromptKit profile. The invocation-only **--reasoning-effort** and
**--clear-reasoning-effort** controls may replace or clear that profile setting
for all LLM-backed calls in one run without changing the profile. PromptKit
v0.5.0 does not add a provider retry loop. Notarius binding retries rerun the
complete module operation and validation chain as defined by
[module bindings](config.md#module-bindings-and-validators).
Timeouts are layered. Caller cancellation is the outer authority. A positive
effective generation timeout adds an inner request deadline, while zero
disables only that generation deadline. The HTTP client timeout remains a
transport-wide cap. Notarius does not add another timeout around PromptKit.
The pinned upstream boundary and profile-format links are in
[PromptKit Integration](integrations/pkg-promptkit.md).
Concurrency has two independent layers. Notarius **total_llm** defaults to 16
and is the application-wide provider-call limit shared by all backends,
modules, retries, and validators. PromptKit may impose a narrower admission
limit for the selected backend. The effective active-generation bound is the
intersection of the Notarius limit, any PromptKit backend limit, and work made
available by the pipeline. Built-in OpenRouter profiles use PromptKit's
upstream backend limit; endpoint-only profiles have no PromptKit backend limit
and remain bounded by Notarius. For the configured local backend, a zero
**concurrency_limit** leaves only the Notarius scheduler as a call limit. A
positive value makes the effective active local-generation bound the smaller
of **total_llm** and that local limit, so a local limit of four permits no more
than four active local generations.
For a positive local limit, PromptKit owns its default waiting capacity and
admission behavior. When a PromptKit backend has admitted all active and queued
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
Provider retries and timeouts are supplied by the selected Scriptorium profile.
Module retry settings and concurrency limits are configuration contracts; see
[module bindings](config.md#module-bindings-and-validators) 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.

39
docs/policy/architecture.md
View File

@@ -24,12 +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.
@@ -45,24 +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;
@@ -92,12 +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
@@ -195,17 +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.
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.
@@ -213,8 +177,7 @@ 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
beneath this mandatory application-wide scheduler.
lanes.
## Configuration And Provenance

2474
docs/roadmap/archive/audit.md
View File

File diff suppressed because it is too large Load Diff

226
docs/roadmap/evidence.md Normal file
View File

@@ -0,0 +1,226 @@
# Published Evidence Context
## Status
Implemented.
## Purpose
Let downstream consumers build narrative reports from normalized artifacts
without separately parsing the original transcript or resolving source-unit
references themselves.
The production JSON output optionally publishes one deterministic, deduplicated
evidence-context artifact containing the transcript units relevant to explicitly
selected normalized lanes. Existing lane payloads remain the canonical semantic
results and retain their precise source references.
## Desired End State
When evidence-context publication is enabled, a consumer can:
1. discover one versioned evidence-context document through `index.json`;
2. obtain the union of source units needed to understand evidence cited by the
selected normalized lanes;
3. distinguish each artifact's direct evidence references from surrounding
units included only for narrative context;
4. retain speaker, timestamp, and other accepted source-unit metadata needed to
interpret the transcript; and
5. produce a narrative report without receiving duplicated transcript text in
every lane payload.
This is deterministic output projection. It does not invoke an LLM, change
normalization, or make surrounding context part of an artifact's evidence.
## Configuration Policy
Evidence publication is configured on the production JSON output module. The
intended configuration shape is:
```yaml
output:
module: json
options:
evidence_context:
enabled: true
window_units: 3
lanes:
- combat-turns
- item-events
- npc-interactions
- npcs
- spells
```
- Omitting `evidence_context` disables publication. When the object is present,
`enabled` is required.
- `enabled: false` accepts no `lanes` or `window_units` fields, preventing
silently ignored configuration.
- `lanes` is a required, non-empty allowlist of configured final lane IDs when
evidence publication is enabled. Values are trimmed, unique, and normalized
to lexical order.
- `window_units` is a non-negative integer and defaults to `3`. Zero publishes
only directly referenced units.
- Unknown lanes, duplicate lane IDs, and selected lanes whose artifact kind
cannot expose source evidence fail configuration resolution or pipeline
preparation.
- A selected lane that completes without a normalized output contributes no
evidence and does not make an otherwise successful run fail.
- Invocation-level lane filtering does not invalidate the configured allowlist.
Allowlisted lanes excluded from the effective run contribute nothing, while
the evidence document still records the configured allowlist.
The allowlist is intentional safety and stability policy. Scene descriptions
and other broad-range lanes are excluded unless named expressly. Adding a new
pipeline lane never silently increases output size or publishes more transcript
content.
## Evidence Collection Boundary
Evidence collection applies to accepted final normalized artifacts from the
selected lanes. It must not inspect arbitrary serialized JSON for fields named
`source_ref` or `source_refs`, and the generic JSON output module must not
depend on D&D artifact types.
Artifact-kind registrations expose their source references through an explicit
typed projection contract. The framework uses that contract to assemble a
domain-neutral evidence request containing:
- the accepted generic source document;
- the selected lane and artifact identities; and
- defensive copies of their direct source references.
The output stage owns publication of the resulting logical artifact. Generic
framework code owns range validation, position-based expansion, and union
logic. Domain-specific adapters own only the extraction of evidence references
from their typed artifacts.
Both plural-reference artifacts and singular-reference artifacts, such as
scene descriptions, can participate through the same projection contract.
They do so only when their configured lane is allowlisted.
## Range Expansion And Deduplication
For every valid direct source reference:
1. resolve its endpoints through source-document positions, not numeric
unit-ID arithmetic;
2. expand the range by `window_units` positions on each side;
3. clip the expanded range at document boundaries; and
4. union overlapping or contiguous expanded ranges.
Published contexts and units remain in source-document order. Each source unit
appears at most once in a merged context. Original direct references remain
unchanged and are associated with their contributing lane IDs so consumers can
tell why a context was included.
The projector must not silently omit or repair an invalid reference that
reaches this boundary. Such a value violates the accepted normalized-artifact
contract and causes output projection to fail with a content-safe error.
No implicit coverage limit truncates selected evidence. If the allowlisted
lanes collectively cite most or all of a transcript, the evidence document may
contain most or all of it. The explicit lane allowlist is the control that
prevents a broad lane such as scene descriptions from doing so accidentally.
## Durable Evidence Artifact
The JSON bundle gains one optional, non-lane artifact with these durable
identities:
| Property | Value |
| --- | --- |
| Logical file | `evidence-context.json` |
| Index descriptor | `evidence_context` |
| Artifact kind | `source/evidence-context` |
| Media type | `application/json` |
| Schema ID | `notarius.source.evidence_context` |
| Schema name | `notarius_source_evidence_context_v1` |
| Schema version | `v1` |
The descriptor in `index.json` carries the artifact and schema identities,
analogous to the existing chunk-map descriptor. The artifact is present
whenever evidence publication is enabled, including when its context collection
is empty.
The document contains:
- the source document ID and semantic digest;
- the effective window size;
- the sorted configured lane allowlist;
- an ordered context collection;
- each context's expanded start and end unit IDs;
- the original direct references and contributing lane IDs covered by that
context; and
- the ordered accepted source units, including unit ID, kind, text,
self-reference, and metadata.
Expanded context bounds are navigation aids, not citations. The original
references embedded in each context remain the authoritative direct evidence.
The evidence artifact is discovered separately from lane payloads and does not
increase the normalized-lane count reported by the runner or subprocess
receipt.
## Failure And Publication Semantics
- Evidence projection occurs only after selected normalized outputs are known
and before the output encoder returns its logical files.
- Projection or encoding failure is an output-stage framework error; the CLI
does not publish a partially assembled output bundle.
- Rejected or absent lane outputs contribute nothing. Their attempted values
and source references must not be published through this artifact.
- Context generation is deterministic for the same source document, selected
normalized outputs, lane allowlist, and window size.
- Existing output, checkpoint, warning, rejection, debug, and subprocess
success semantics remain unchanged.
## Sensitivity And Size
Unlike the current chunk map, the evidence artifact contains transcript text
and source-unit metadata. Enabling it therefore creates additional durable
sensitive data and may materially increase bundle size.
The implemented configuration, operations, integration, and consumer documents
state that:
- evidence publication is opt-in;
- output permissions and retention must be appropriate for source content;
- selecting broad or numerous lanes can publish most of the transcript; and
- the artifact must not contain raw input bytes, LLM prompts or responses,
auxiliary reference content, credentials, debug-only data, or filesystem
paths.
## Acceptance Criteria
- Evidence publication is disabled by default and leaves existing bundles
unchanged.
- Enabling it requires an explicit non-empty lane allowlist.
- References from all selected successful lanes contribute to one deduplicated
document.
- Non-monotonic unit IDs are expanded and ordered correctly by document
position.
- Overlapping windows share one ordered copy of each included source unit.
- Direct references remain distinguishable from added context.
- Scene descriptions cannot contribute unless their lane is explicitly
allowlisted.
- Invalid selected lanes and unsupported artifact kinds fail before execution;
invalid accepted references fail output projection rather than being ignored.
- Empty selected-lane results produce a valid empty evidence artifact.
- Existing D&D lane schemas, normalized-output counts, and source-reference
semantics do not change.
- Generic framework and output packages do not depend on D&D types or parse
artifact JSON heuristically.
- The published contract and operational documentation clearly describe source
sensitivity, discovery, compatibility, and retention.
## Out Of Scope
- Embedding transcript units directly into each D&D record or lane payload.
- Replacing precise source references with expanded context ranges.
- Automatically including every configured lane.
- An explicit full-transcript publication mode.
- LLM summarization, retrieval, ranking, or narrative generation.
- Per-record window sizes or lane-specific window sizes.
- CLI overrides for evidence configuration.
- Reading rejected attempts, debug artifacts, auxiliary references, or prior
output bundles as evidence sources.

74
docs/roadmap/future.md
View File

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

486
docs/roadmap/implementation.md Normal file
View File

@@ -0,0 +1,486 @@
# Published Evidence Context Implementation Plan
## Status
Completed.
## Objective
Implement the accepted [Published Evidence Context](evidence.md) roadmap as an
optional, deterministic extension of the production JSON output. The completed
work must publish one deduplicated source-context artifact for an explicit set
of successful normalized lanes while leaving existing lane payloads,
normalization, checkpointing, subprocess results, and disabled output bundles
unchanged.
Complete the stages below in order. Each stage must leave its affected packages
passing before the next begins. Do not implement per-record hydration, implicit
all-lane collection, a full-transcript mode, LLM processing, or any other
roadmap item marked out of scope.
## Decisions And Invariants
- Evidence publication is output policy. Normalizers continue to return
semantic artifacts with precise source references and do not receive
hydration responsibilities.
- The framework operates on the accepted generic `source.SourceDocument` and
typed artifact projections. It must not inspect serialized JSON for
`source_ref` or `source_refs`, and generic packages must not depend on D&D
types.
- The selected lane allowlist is explicit, non-empty, and globally addressed by
resolved lane ID. Pipeline resolution already guarantees lane IDs are unique
across ordered steps.
- The framework decodes accepted serialized normalize outputs through their
registered artifact codecs before invoking typed evidence projectors. This
supports both fresh and checkpoint-reused normalize outputs without retaining
a second typed result channel.
- Expansion uses source-document positions. Numeric unit IDs are identities,
not sequence numbers.
- Direct source references are never widened or rewritten. Expanded ranges are
context bounds only.
- Rejected, failed, and absent normalized lane outputs contribute no evidence.
- Evidence output is sensitive durable source content, not cache or debug
state. It contains accepted source units only and never raw input bytes,
prompts, model responses, auxiliary references, paths, or credentials.
- The optional `evidence_context` index field is an additive v1 JSON-bundle
change. Existing D&D artifact schemas and the subprocess receipt do not
change.
## Stage 1: Add Typed Evidence Capability And Resolve Output Policy
Add a dedicated artifact-evidence registry under the pipeline framework:
- `pipeline.ArtifactEvidenceRegistry` stores one typed projector per artifact
kind.
- `pipeline.ArtifactEvidenceProjector[T]` is
`func(T) []source.SourceRef`.
- `pipeline.RegisterArtifactEvidence[T](registry, kind, projector)` accepts a
non-empty kind and non-nil projector, records the exact Go type for `T`, and
rejects duplicate kinds.
- The erased projection boundary checks the exact registered type, invokes the
projector, and returns a defensive copy of its references.
- The registry exposes only the discovery and projection operations required by
resolution, preparation, and execution; do not expose its mutable entries.
Add the registry to `pipeline.Registries` and `pipeline.ModuleCatalog`, including
CLI catalog conversion, production construction, empty-set detection, and
test registry helpers. A nil evidence registry remains valid when evidence
publication is disabled. Production construction and the D&D registrar require
and populate it.
Define these framework-level output-policy contracts:
```go
type EvidenceContextPolicy struct {
Enabled bool
WindowUnits int
LaneIDs []string
}
type EvidenceContextPolicyProvider interface {
EvidenceContextPolicy() EvidenceContextPolicy
}
```
Provider and prepared-pipeline boundaries defensively copy `LaneIDs`.
Add an optional output-profile option-validation callback to
`OutputEncoderRegistry`:
```go
type OutputProfileOptionContext struct {
LaneIDs []string
}
type OutputProfileOptionValidator func(
OutputProfileOptionContext,
map[string]any,
) error
```
Add `RegisterBuilderWithProfileValidation(spec, validateOptions,
validateProfile, builder)` and make existing output registration methods
delegate to it with no profile callback. The registry passes defensive copies
to validation. The callback receives the complete configured lane-ID set before
invocation-level `--only` filtering. The production JSON output uses it only to
prove that every configured evidence lane exists. Keep the extension generic:
the pipeline supplies lane identities, while the output module interprets its
own options. Build that lane set from the normalized legacy-or-steps profile
before selection and reject duplicate configured lane IDs through the existing
pipeline identity rules.
Extend the production JSON output options with the nested
`evidence_context` object:
- omission disables the feature;
- `enabled` is required when the object is present;
- `enabled: false` permits no `lanes` or `window_units` fields;
- `enabled: true` requires a non-empty `lanes` array;
- lane values are strings, trimmed, non-empty, unique after trimming, and
normalized to lexical order;
- `window_units` is an optional non-negative integer with default `3`; and
- outer and nested unknown fields and incompatible YAML value types remain
strict configuration errors.
The JSON encoder implements the policy provider from its decoded immutable
options. Pipeline resolution invokes its profile validator against all
configured steps, so an unknown evidence lane fails even when another lane is
selected with `--only`.
During `pipeline.Prepare`, after constructing the output encoder:
1. obtain and defensively normalize an enabled policy;
2. intersect its configured IDs with the effective prepared lanes, treating
allowlisted lanes removed by invocation-level filtering as inactive;
3. require an artifact-evidence registration for each active lane kind;
4. prove that its projector Go type exactly matches the active lane's registered
artifact codec type; and
5. retain an immutable private evidence plan on `PreparedPipeline`.
Duplicate or empty provider values, a missing evidence registry for an active
lane, unsupported active artifact kinds, and type mismatches fail preparation
with pipeline/output/lane context. A disabled or non-participating output
encoder creates no evidence plan and preserves existing preparation behavior.
The private plan retains both the full configured allowlist for publication and
the active lane/projector intersection for execution.
Register D&D evidence projectors for all six current artifact kinds. Each
projector returns copies of the artifact's direct references in record order:
spells, NPCs, combat turns, item events, NPC interactions, and the singular
reference from each scene description. Scene descriptions gain capability but
remain excluded unless their configured lane ID is allowlisted.
Stage tests:
- Registry tests cover nil, blank, duplicate, exact-type, defensive-copy, and
deterministic discovery behavior.
- JSON option tests cover disabled, enabled/default-window, explicit zero
window, normalization, duplicates, unknown fields, and invalid types.
- Preparation tests cover selected lanes across steps, unknown lanes,
unsupported kinds, projector/codec type mismatch, disabled behavior, and
defensive policy ownership.
- Resolution/preparation tests prove a valid allowlist survives `--only`, an
excluded lane contributes no active projector, and a genuinely unknown
configured lane still fails profile resolution.
- D&D registration tests prove every production D&D artifact kind has the
expected evidence capability without testing individual field loops
redundantly.
- One table-driven D&D projector test supplies representative values for all
six artifact kinds and proves plural and singular references are copied
without aliasing or semantic rewriting.
Stage completion:
- `go test ./internal/framework/pipeline`
- `go test ./internal/modules/generic/output/json`
- `go test ./internal/modules/dnd/register`
- `go test ./internal/cli`
## Stage 2: Define And Build The Evidence-Context Artifact
Add a domain-neutral `internal/framework/evidencecontext` package that owns the
durable model, JSON Schema, strict codec, projection algorithm, and these exact
identities:
- artifact kind `source/evidence-context`;
- media type `application/json`;
- schema ID `notarius.source.evidence_context`;
- schema name `notarius_source_evidence_context_v1`; and
- schema version `v1`.
Use these package-level model and build contracts:
```go
type Document struct {
SourceID string
SourceDigest string
WindowUnits int
SelectedLanes []string
Contexts []Context
}
type Context struct {
ContextRef source.SourceRef
EvidenceRefs []EvidenceRef
Units []source.SourceUnit
}
type EvidenceRef struct {
LaneID string
SourceRef source.SourceRef
}
type LaneEvidence struct {
LaneID string
SourceRefs []source.SourceRef
}
type BuildRequest struct {
Source *source.SourceDocument
WindowUnits int
SelectedLanes []string
LaneEvidence []LaneEvidence
}
```
Apply the JSON field names shown below. Provide `Build(BuildRequest)`,
`Serialize(BuildRequest)`, and a `Codec` with the same identity/encode/decode
responsibilities as the chunk-map codec.
The v1 payload has this exact shape:
```json
{
"source_id": "session-alpha",
"source_digest": "sha256:0000000000000000000000000000000000000000000000000000000000000000",
"window_units": 0,
"selected_lanes": ["npcs"],
"contexts": [
{
"context_ref": {
"source_id": "session-alpha",
"start_unit_id": 13,
"end_unit_id": 13
},
"evidence_refs": [
{
"lane_id": "npcs",
"source_ref": {
"source_id": "session-alpha",
"start_unit_id": 13,
"end_unit_id": 13
}
}
],
"units": [
{
"id": 13,
"kind": "transcript_segment",
"text": "The party meets Rowan.",
"ref": {
"source_id": "session-alpha",
"start_unit_id": 13,
"end_unit_id": 13
}
}
]
}
]
}
```
All displayed fields are required. `selected_lanes`, `contexts`,
`evidence_refs`, and `units` encode as arrays rather than `null`; `contexts`
may be empty. Each unit uses the existing `source.SourceUnit` JSON shape with
required `id`, `kind`, `text`, and `ref`, plus optional JSON-shaped `metadata`.
Fixed objects reject unknown fields; metadata remains an arbitrary JSON object.
The builder accepts the validated source document, selected lane IDs, effective
window, and lane-attributed direct references, then:
1. requires a non-negative window and a non-empty, trimmed, unique selected
lane set, then stores that set in lexical order;
2. requires every `LaneEvidence.LaneID` to belong to the selected set;
3. validates the source document, recomputes its semantic digest, and requires
it to equal `SourceDocument.Digest`;
4. validates every direct reference against one `source.DocumentIndex`;
5. deduplicates exact `(lane_id, source_ref)` contributions;
6. resolves endpoints to document positions;
7. expands each side without integer overflow and clips at document bounds;
8. sorts by expanded document position with deterministic lane/reference
tie-breakers;
9. merges overlapping or position-contiguous expanded intervals;
10. unions and deterministically sorts each merged context's direct
contributions; and
11. deep-clones the corresponding source units and JSON-shaped metadata.
Contexts are disjoint and ordered by document position, so a source unit occurs
at most once in the document. `context_ref` identifies the first and last
included units; `evidence_refs` retains only original citations. An empty
reference collection produces the same source identity, window, sorted
allowlist, and an explicit empty contexts array.
Projection failures identify only structural scope such as lane and reference
position. They must not include source text, metadata values, raw serialized
artifacts, or unrelated paths.
The codec must validate its model before encoding, produce deterministic JSON,
strictly decode the checked-in schema, and return independently owned values.
The JSON output encoder remains responsible for pretty-printing the logical
file with its standard trailing newline. Follow the existing chunk-map
package's separation between model, builder, codec, schema asset, and contract
tests where useful, without coupling the two artifact formats.
Stage tests:
- A table-driven builder suite covers zero and nonzero windows, boundary
clipping, non-monotonic unit IDs, separate gaps, overlapping and contiguous
windows, duplicate contributions, multiple lanes, stable ordering, empty
contexts, invalid selected/contributing lanes, source-digest mismatch, and
invalid references.
- Ownership tests prove output mutation cannot affect the source document or
projector inputs, including nested metadata.
- Codec tests cover round trip, required arrays, schema identity, malformed and
trailing JSON, unknown fixed fields, invalid ordering/ranges, mismatched
source identities, and independently owned decoded metadata.
- Use structured assertions and a compact valid fixture; do not add a large
transcript golden file.
Stage completion:
- `go test ./internal/framework/evidencecontext`
## Stage 3: Integrate Projection With Runner Output
Extend `contracts.OutputRequest` with an optional
`EvidenceContext *SerializedArtifact` field and clone it at every ownership
handoff, following the existing chunk-map pointer pattern.
After lane execution and final manifest population, but before invoking the
output encoder, the runner must:
1. skip all work when the prepared evidence plan is absent;
2. index accepted `NormalizeOutputs` by their globally unique lane IDs and fail
on an internal duplicate rather than silently overwrite it;
3. for each selected lane with an output, verify its source and artifact kind,
decode it through the prepared artifact codec registry, and invoke the
prepared typed projector;
4. build and serialize the evidence document through the evidence-context
package; and
5. pass a defensive serialized-artifact copy to the output encoder.
Selected lanes without normalized output contribute nothing. Normalize
rejections remain successful pipeline outcomes; evidence projection does not
inspect rejected candidates. An invalid accepted reference, incompatible
serialized artifact, projection type failure, or evidence serialization failure
is an output-stage framework error before logical files are returned or
physically published.
At this external-content consumption boundary, do not propagate artifact-codec
or metadata-cloning errors with `%w` when their text could contain artifact
fields or source metadata. Return fixed, actionable categories scoped by lane
and operation; detailed codec errors remain available to direct trusted
callers and their focused tests.
Add an allowlisted debug summary containing only evidence artifact identity,
selected lanes, window, context count, unit count, and source digest. Do not
duplicate transcript text or source-unit metadata into a new evidence-specific
debug envelope. Existing normalized-output debug behavior remains unchanged.
The output artifact is not a normalized lane, generated reference, checkpoint,
or manifest normalized-output entry. It does not alter normalized-output,
rejection, or warning counts. Resume continues to reuse normalized checkpoints;
evidence is deterministically rebuilt during the always-executed output stage.
Stage tests:
- Runner tests use a real codec, evidence projector, and small capturing output
encoder to prove selected-lane union, absent/rejected lane omission, invalid
accepted-reference failure, output-request defensive ownership, and no work
when disabled.
- Include one checkpoint-reused normalized-output case to prove evidence is
reconstructed identically without retaining typed normalize values.
- Confirm projection failures prevent output encoding and return a failed
manifest without changing rejection semantics.
Stage completion:
- `go test ./internal/framework/pipeline`
## Stage 4: Publish Through The JSON Bundle
Teach the production JSON encoder to recognize the optional evidence-context
artifact, verify its exact kind, media type, schema identity, schema digest, and
payload validity through the evidence-context codec, and emit:
- logical file `evidence-context.json`; and
- optional `index.json` descriptor field `evidence_context`.
The descriptor uses the same six fields as `chunk_map`:
`artifact_kind`, `file`, `media_type`, `schema_id`, `schema_name`, and
`schema_version`. Refactor the encoder's private descriptor representation only
as needed to share that shape; do not change the existing `chunk_map` wire
contract. Evidence output is ordered with the encoder's other fixed logical
files, remains a non-lane artifact, and is present with an empty contexts array
when enabled but no selected lane produces references.
The JSON encoder's validation boundary returns a fixed content-safe evidence
artifact error rather than propagating decoder or schema diagnostics that could
echo transcript text or metadata. Direct evidence-context codec tests retain
detailed structural errors.
Update the maintained complete D&D configuration to enable evidence context
with window `3` for `item-events`, `npcs`, `spells`, `combat-turns`, and
`npc-interactions`. Deliberately omit `scene-descriptions`. Keep the minimal
configuration disabled by omission.
Stage tests:
- JSON encoder tests own descriptor shape, exact logical filename, identity
checking, empty evidence publication, and disabled bundle stability.
- One assembled production D&D test uses multiple selected lanes with
overlapping references and non-monotonic unit IDs, decodes the published
artifact through its production codec, and proves union/deduplication and
scene-description exclusion.
- A second narrow case explicitly allowlists a scene-description lane to prove
capability is opt-in rather than hard-coded exclusion.
- Existing index, chunk-map, lane, manifest, warning, and rejection tests remain
the owners of their current formats; do not repeat their full matrices.
Stage completion:
- `go test ./internal/modules/generic/output/json`
- `go test ./internal/modules/dnd/...`
- `go test ./internal/modules/integration`
- `go test ./internal/cli`
## Stage 5: Publish Current-Behavior Documentation
After implementation and behavioral tests pass, update canonical documentation:
- `docs/config.md` owns the nested JSON output options, defaults, strict
validation, required lane allowlist, and a small configuration snippet.
- A new `docs/integrations/evidence-context.md` owns the complete v1 payload,
identities, direct-evidence versus context semantics, ordering,
compatibility, and a compact valid example.
- `docs/integrations/json-output.md` owns the optional logical file and
`index.json` descriptor; link to the evidence contract rather than repeating
its payload.
- `docs/operations.md` owns durable source-content sensitivity, permissions,
retention, and the possibility that selected lanes cover most of a
transcript.
- `docs/consumers/subprocess.md` explains discovery through the optional index
descriptor and requires consumers to treat `evidence_refs`, not expanded
context bounds, as citations.
- `docs/policy/architecture.md` records the generic typed evidence-projection
boundary and output ownership without adding D&D or wire-format detail.
- `docs/internal/pipeline.md` and `docs/internal/modules.md` describe the typed
evidence registry, preparation checks, reconstruction from serialized
normalize outputs, and output-stage ownership without restating public wire
fields.
Update only the smallest orientation links needed for discoverability. Do not
add a CLI flag, configuration environment override, or duplicate the complete
configuration outside `examples/`.
After all current-behavior documentation is accurate:
- set [the feature roadmap](evidence.md) status to `Implemented`;
- set this plan's status to `Completed`; and
- leave the integration and configuration documents, not either roadmap, as
the canonical implemented contract.
Final verification:
- `git diff --check`
- `go test ./...`
- `go vet ./...`
- `go build ./cmd/notarius`
- `go test -race ./internal/framework/evidencecontext ./internal/framework/pipeline ./internal/modules/generic/output/json ./internal/modules/dnd/... ./internal/modules/integration ./internal/cli`
## Open Questions
None. The plan fixes the configuration shape and defaults, typed projection
boundary, preparation timing, durable schema and identities, range-union
algorithm, failure semantics, JSON discovery, D&D coverage, documentation
ownership, and test boundaries.

208
docs/roadmap/subprocess.md Normal file
View File

@@ -0,0 +1,208 @@
# Subprocess Integration Contract
## Status
Implemented.
## Purpose
Make Notarius straightforward to invoke as a subprocess from an orchestrator
such as Narratio. A caller should be able to run a configured pipeline, discover
the published output bundle without parsing human prose or scanning a
directory, and hand selected structured artifacts to a later stage.
This work strengthens the public CLI boundary. It does not turn Notarius into a
Go library, embed Narratio-specific behavior, or change pipeline execution and
artifact semantics.
## Desired End State
A subprocess caller can:
1. validate a Notarius configuration and selected pipeline before execution;
2. invoke `notarius run` with explicit input, output-root, session, and
reference arguments;
3. request one versioned, machine-readable success result on standard output;
4. use that result to locate the published output bundle;
5. discover normalized lane payloads through the bundle's authoritative
`index.json`;
6. distinguish process failure from successful partial pipeline outcomes; and
7. record Notarius run provenance in its own manifest without depending on
internal packages, cache formats, debug formats, or human-readable messages.
The existing human-oriented command output remains the default for interactive
use.
## Machine-Readable Run Result
`notarius run` supports `--json`. On success, the flag makes standard output
contain exactly one JSON object followed by a newline. No human-oriented status
line is mixed into that stream.
The result uses the schema identity `notarius.run-result.v1` and contains:
| Field | Presence | Meaning |
| --- | --- | --- |
| `schema_version` | Required | Exactly `notarius.run-result.v1`. |
| `run_id` | Required | The Notarius run identifier. |
| `pipeline_id` | Required | The effective pipeline identifier. |
| `output_directory` | Required | Absolute path to the successfully published output bundle. |
| `index_file` | Required for the production JSON output | Logical bundle path `index.json`. |
| `normalized_output_count` | Required | Number of final normalized lane outputs returned by the pipeline. |
| `rejected_output_count` | Required | Number of recorded rejected outputs. |
| `warning_count` | Required | Number of final run warnings returned by the pipeline. |
| `validation_status` | Required | The run manifest's final validation status without reinterpretation. |
| `debug_directory` | Optional | Absolute debug-bundle path when debug capture was requested and completed. |
An illustrative successful result is:
```json
{
"schema_version": "notarius.run-result.v1",
"run_id": "run-1770000000000000000-0123456789abcdef0123456789abcdef",
"pipeline_id": "dnd-session",
"output_directory": "/srv/narratio/runs/session-7/notarius/run-1770000000000000000-0123456789abcdef0123456789abcdef",
"index_file": "index.json",
"normalized_output_count": 6,
"rejected_output_count": 2,
"warning_count": 1,
"validation_status": "approved"
}
```
The receipt is a discovery and summary document, not a duplicate output
envelope. It does not embed lane payloads, rejection entries, warnings, the run
manifest, or output-file contents. Consumers use `index_file` and the existing
published JSON output contract for those records.
The result contract must tolerate future additive optional fields. Any
incompatible field or semantic change requires a new run-result schema version.
## Stream, Publication, And Failure Semantics
Machine-readable output is emitted only after:
- the pipeline has completed without a framework error;
- all logical output files have been successfully published;
- requested debug terminal reporting has completed; and
- all result fields are known.
Writing or encoding the machine-readable result is part of successful command
completion. Failure to write it produces the existing runtime-failure exit
class.
With `--json`:
- successful stdout is exclusively the run-result JSON document;
- successful warnings remain on stderr under the existing CLI contract;
- syntax and runtime errors retain their existing exit statuses and stderr
diagnostics;
- consumers treat stdout as a valid result only when the process exits with
status 0; failures before result writing emit no result, while a failure
during the stdout write may leave incomplete bytes that must be ignored; and
- human-readable diagnostic wording is not promoted into a machine contract.
Without `--json`, current interactive stdout and stderr behavior remains
unchanged.
Successful runs may contain rejected outputs or omit some normalized lanes.
That remains a valid pipeline outcome. The run result reports counts, while
`index.json`, `rejected.json`, and `warnings.json` remain authoritative for
details. Notarius will not add a generic `--fail-on-rejection` policy as part
of this work.
## Output Discovery And Consumer Responsibilities
The production JSON encoder's `index.json` remains the authoritative mapping
from lane IDs to published payloads. A subprocess consumer should:
- resolve `index_file` beneath `output_directory` and reject path escape;
- locate expected outputs by `lane_id`, not by guessing filenames;
- check each selected descriptor's media type and schema identity;
- decode payloads according to their published integration contracts;
- decide which lanes are required or optional for its own later stages; and
- retain rejection, warning, and manifest files when they are needed for
provenance or review.
For Narratio, required report inputs and partial-success policy remain Narratio
stage configuration and orchestration concerns. Notarius does not acquire
knowledge of Narratio stages, manifests, workspace layout, publication policy,
or report formats.
## Invocation Guidance
The consumer documentation recommends that subprocess callers:
- use `notarius config validate --pipeline` as an optional preflight;
- pass explicit absolute paths for the input, configuration, output root, and
CLI-supplied references;
- use a stable, non-secret prompt session identifier when useful for provider
routing or caching;
- capture stdout and stderr separately;
- supply credentials through the configured environment mechanism rather than
command arguments or generated configuration containing secret values;
- place output, cache, debug, and subprocess logs under intentional
sensitivity and retention policies; and
- treat the Notarius manifest and run-result receipt as provenance while
leaving the caller's own manifest authoritative for its stage lifecycle.
Notarius configuration remains owned by Notarius. An orchestrator may select a
configuration and pass supported operational overrides, but should not
duplicate the complete Notarius configuration schema.
## Documentation End State
- `docs/cli.md` owns `run --json`, stream behavior, and exit semantics;
- a new `docs/integrations/run-result.md` owns the versioned run-result wire
contract and compatibility policy;
- `docs/integrations/json-output.md` remains the sole owner of output-bundle
discovery and lane publication;
- a new `docs/consumers/subprocess.md` provides the task-oriented invocation and
consumption workflow; and
- `docs/internal/cli.md` describes how the CLI constructs and emits the result
only after successful publication.
Other documents should link to these owners instead of repeating volatile
fields or command details.
## Acceptance Criteria
- An ordinary successful `run` retains its existing human-readable output.
- A successful `run --json` emits one valid `notarius.run-result.v1` document
and no human prose on stdout.
- Relative configured or overridden output and debug roots are reported as
absolute bundle paths.
- The receipt identifies the production JSON bundle entry point without
copying its lane descriptors or payloads.
- Warning-bearing and rejection-bearing runs remain successful and report
accurate counts.
- Syntax, configuration, provider, pipeline, publication, debug, and result
writing failures retain the correct nonzero exit class. Consumers are
explicitly required to ignore stdout from a nonzero invocation.
- The implementation does not expose internal Go types or couple generic CLI
code to D&D or Narratio concepts.
- Public and internal documentation assigns each new contract to one canonical
owner.
- Offline behavioral tests protect the structured-output contract, default
human behavior, absolute path reporting, stream separation, and failure to
serialize or write the success result without duplicating lower-level output
encoder tests.
## Out Of Scope
The following may be useful later but are not prerequisites for the Narratio
integration:
- a result-file flag in addition to machine-readable stdout;
- a JSON failure envelope or stable machine-readable error taxonomy;
- caller-supplied Notarius run IDs or exact output-bundle paths;
- a generic `--fail-on-rejection` or required-lane CLI policy;
- a public Go client package or importable Narratio adapter;
- Narratio stage, configuration, manifest, or report-generation changes;
- `notarius version --json`;
- installable or queryable artifact JSON Schemas;
- signal-aware CLI contexts and graceful SIGINT or SIGTERM handling;
- packaged release artifacts and a broader application-versioning policy.
These items should be promoted only in response to a demonstrated integration
need rather than bundled into the initial subprocess contract.

97
examples/dnd-complete.config.yml
View File

@@ -1,6 +1,4 @@
version: 4
promptkit:
profile_file: ./examples/profiles/dnd-extraction.yml
version: 3
concurrency:
total_llm: 2
stage_workers:
@@ -18,7 +16,6 @@ debug:
directory: ./notarius-debug
pipelines:
dnd-session:
llm_profile: dnd-extraction
input: seriatim
# Stable campaign context is shared by every module that accepts these slots.
references:
@@ -35,40 +32,29 @@ pipelines:
enabled: true
window_units: 3
lanes:
- item-occurrences
- item-registry
- location-registry
- location-occurrences
- npc-registry
- item-events
- npcs
- spells
- combat-turns
- npc-occurrences
- enemy-events
- npc-interactions
steps:
# Establish session-wide reference artifacts before their consumers.
# Establish session-wide reference artifacts alongside independent item events.
- id: describe-session
artifacts:
item-registry:
item-events:
extract:
module: dnd/item-registry
module: dnd/item-events
retries: 2
merge: appendorder
normalize: dnd/item-registry
npc-registry:
normalize: dnd/item-events
npcs:
extract:
module: dnd/npc-registry
module: dnd/npcs
retries: 2
merge: appendorder
normalize:
module: dnd/npc-registry
retries: 2
location-registry:
extract:
module: dnd/location-registry
retries: 2
merge: appendorder
normalize:
module: dnd/location-registry
module: dnd/npcs
llm_profile: gemini-2-flash
retries: 2
scene-descriptions:
extract:
@@ -77,32 +63,18 @@ pipelines:
merge: appendorder
normalize: dnd/scene-descriptions
- id: extract-events
# Accepted registry artifacts and scene-description eligibility artifacts
# are supplied in memory to their compatible consumers in this step.
# Accepted NPC grounding and scene-description eligibility artifacts are
# supplied in memory to their compatible consumers in this step.
references:
location_registry:
npcs:
artifact:
step: describe-session
lane: location-registry
npc_registry:
artifact:
step: describe-session
lane: npc-registry
lane: npcs
scene_descriptions:
artifact:
step: describe-session
lane: scene-descriptions
item_registry:
artifact:
step: describe-session
lane: item-registry
artifacts:
item-occurrences:
extract:
module: dnd/item-occurrences
retries: 2
merge: appendorder
normalize: dnd/item-occurrences
spells:
extract:
module: dnd/spells
@@ -121,40 +93,9 @@ pipelines:
retries: 2
merge: appendorder
normalize: dnd/combat-turns
npc-occurrences:
npc-interactions:
extract:
module: dnd/npc-occurrences
module: dnd/npc-interactions
retries: 2
merge: appendorder
normalize: dnd/npc-occurrences
location-occurrences:
extract:
module: dnd/location-occurrences
retries: 2
merge: appendorder
normalize: dnd/location-occurrences
- id: track-enemies
references:
npc_registry:
artifact:
step: describe-session
lane: npc-registry
scene_descriptions:
artifact:
step: describe-session
lane: scene-descriptions
combat_turns:
artifact:
step: extract-events
lane: combat-turns
npc_occurrences:
artifact:
step: extract-events
lane: npc-occurrences
artifacts:
enemy-events:
extract:
module: dnd/enemy-events
retries: 2
merge: appendorder
normalize: dnd/enemy-events
normalize: dnd/npc-interactions

3
examples/dnd-minimal.config.yml
View File

@@ -1,7 +1,6 @@
version: 4
version: 3
pipelines:
dnd-session:
llm_profile: dnd-extraction
input: seriatim
artifacts:
spells:

5
examples/profiles/dnd-extraction.yml
View File

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

2
go.mod
View File

@@ -3,7 +3,7 @@ module gitea.maximumdirect.net/eric/notarius
go 1.25.5
require (
gitea.maximumdirect.net/eric/promptkit v0.5.0
gitea.maximumdirect.net/eric/scriptorium v0.11.1
github.com/santhosh-tekuri/jsonschema/v6 v6.0.2
gopkg.in/yaml.v3 v3.0.1
)

8
go.sum
View File

@@ -1,9 +1,13 @@
gitea.maximumdirect.net/eric/promptkit v0.5.0 h1:jnpazLyyNhWrB2xzwwtUkNUfktkTdkENTwuSPnKiYrc=
gitea.maximumdirect.net/eric/promptkit v0.5.0/go.mod h1:R95NM6fbMDGDC0/UomgnSBP6ui2ns+8SZb8bESNvrDQ=
gitea.maximumdirect.net/eric/scriptorium v0.11.0 h1:rjvbt9FTaWHxYlHq7QlUzmMVUt3QdbTmeCkmH81N//o=
gitea.maximumdirect.net/eric/scriptorium v0.11.0/go.mod h1:FQ5lEuNxmrQyNgIomkpZdxvfTC0jWjbXYuq3tbJWF64=
gitea.maximumdirect.net/eric/scriptorium v0.11.1 h1:zBKtB3+fP8FcHGI8DJD99CiTL6crAGitBhWtE+xYJHc=
gitea.maximumdirect.net/eric/scriptorium v0.11.1/go.mod h1:FQ5lEuNxmrQyNgIomkpZdxvfTC0jWjbXYuq3tbJWF64=
github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
github.com/santhosh-tekuri/jsonschema/v6 v6.0.2 h1:KRzFb2m7YtdldCEkzs6KqmJw4nqEVZGK7IN2kJkjTuQ=
github.com/santhosh-tekuri/jsonschema/v6 v6.0.2/go.mod h1:JXeL+ps8p7/KNMjDQk3TCwPpBy0wYklyWTfbkIzdIFU=
golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/text v0.40.0 h1:Ub2Z6/xjgF1WrYQz2nuITOEegKFtiIy+rieRJ5lHZKs=
golang.org/x/text v0.40.0/go.mod h1:hpnzDAfGV753zIKo+wk3u1bVKCGPbrnF7+7LBF/UHVY=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=

81
internal/cli/assembled_enemy_event_codec_contract_test.go
View File

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

9
internal/cli/assembled_spell_pipeline_contract_test.go
View File

@@ -134,7 +134,7 @@ func TestAssembledSpellPipelineHonorsNormalizeValidatorOverride(t *testing.T) {
}
}
func TestAssembledSpellPipelinePromotesTerminalUnknownSpellWarning(t *testing.T) {
func TestAssembledSpellPipelineRejectsUnknownSpellWithoutPromotingAttemptWarning(t *testing.T) {
registries, resolved, _ := assembledSpellPipeline(t, assembledSpellPipelineOptions{unknownSpell: true})
prepared, err := pipeline.Prepare(resolved, registries, pipeline.ModuleDependencies{})
if err != nil {
@@ -161,8 +161,10 @@ func TestAssembledSpellPipelinePromotesTerminalUnknownSpellWarning(t *testing.T)
if !reflect.DeepEqual(rejectedFile.Rejected, output.Rejected) {
t.Fatalf("rejected file = %#v, run rejections = %#v, want durable rejection diagnostic", rejectedFile.Rejected, output.Rejected)
}
if len(output.Warnings) != 1 || output.Warnings[0].ReasonCode != spellnormalize.ReasonCodeSpellNameUnresolved || output.Warnings[0].Scope != "spell_casts[0]" {
t.Fatalf("warnings = %#v, want terminal normalize catalog warning", output.Warnings)
for _, warning := range output.Warnings {
if warning.ReasonCode == spellnormalize.ReasonCodeSpellNameUnresolved {
t.Fatalf("warnings = %#v, want rejected-attempt warning to remain non-durable", output.Warnings)
}
}
}
@@ -213,7 +215,6 @@ func assembledSpellPipeline(t *testing.T, options assembledSpellPipelineOptions)
if err := pipeline.RegisterExtractor[dnd.SpellList](components.registries.Extractors, pipeline.ModuleSpec{
Key: assembledSpellExtractorKey,
Stage: pipeline.StageExtract,
ExecutionClass: contracts.ExecutionClassDeterministic,
Requires: []string{"chunks", "source.transcript"},
Provides: []string{"dnd.spell_casts"},
ArtifactKind: dnd.SpellListKind,

14
internal/cli/cache_contract_test.go
View File

@@ -249,24 +249,10 @@ func TestRunAutoReusesPlanWhenRunInputsChange(t *testing.T) {
}
harness.mu.Lock()
chunkCalls := harness.chunkCalls
sessions := append([]string(nil), harness.sessionIDs...)
harness.mu.Unlock()
if chunkCalls != 1 {
t.Fatalf("chunk calls across changed run inputs = %d, want 1", chunkCalls)
}
rawInput, err := os.ReadFile(roots.input)
if err != nil {
t.Fatal(err)
}
wantSessionID, err := resolvePromptSessionID("", "test/input", rawInput)
if err != nil {
t.Fatal(err)
}
for _, sessionID := range sessions {
if sessionID != wantSessionID {
t.Fatalf("session IDs across reference changes = %#v, want %q", sessions, wantSessionID)
}
}
assertFile(t, filepath.Join(roots.plans, strings.TrimPrefix(stateTestDigest, "sha256:"), "plan.json"))
assertAnyFile(t, roots.output)
}

27
internal/cli/catalog.go
View File

@@ -143,13 +143,24 @@ func isEmptyRegistries(registries pipeline.Registries) bool {
registries.Outputs == nil
}
func productionLLMClientFactory(ctx context.Context, cfg config.Config, profileID string) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
if err := ctx.Err(); err != nil {
return nil, nil, err
}
assets, err := productionPromptAssets()
if err != nil {
return nil, nil, err
}
return buildProductionLLMClient(ctx, cfg, profileID, assets)
}
func productionLLMClientFactoryWithAssets(assets *llm.AssetRegistry) LLMClientFactory {
return func(ctx context.Context, cfg config.Config, profileID string, overrides LLMRuntimeOverrides) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
return buildProductionLLMClient(ctx, cfg, profileID, overrides, assets)
return func(ctx context.Context, cfg config.Config, profileID string) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
return buildProductionLLMClient(ctx, cfg, profileID, assets)
}
}
func buildProductionLLMClient(ctx context.Context, cfg config.Config, profileID string, overrides LLMRuntimeOverrides, assets *llm.AssetRegistry) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
func buildProductionLLMClient(ctx context.Context, cfg config.Config, profileID string, assets *llm.AssetRegistry) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
if err := ctx.Err(); err != nil {
return nil, nil, err
}
@@ -157,16 +168,14 @@ func buildProductionLLMClient(ctx context.Context, cfg config.Config, profileID
return nil, nil, fmt.Errorf("production asset registry must not be nil")
}
recorder := llm.NewLLMProfileRecorder()
client, err := llm.NewPromptKitClient(llm.PromptKitClientConfig{
ProfileDir: cfg.PromptKit.ProfileDir,
ProfileFile: cfg.PromptKit.ProfileFile,
LocalBackend: mapPromptKitLocalBackend(cfg.PromptKit.LocalBackend),
client, err := llm.NewScriptoriumClient(llm.ScriptoriumClientConfig{
ProfileDir: cfg.Scriptorium.ProfileDir,
ProfileFile: cfg.Scriptorium.ProfileFile,
Assets: assets,
Recorder: recorder,
ReasoningEffort: overrides.ReasoningEffort,
})
if err != nil {
return nil, nil, fmt.Errorf("create PromptKit-backed LLM client: %w", err)
return nil, nil, fmt.Errorf("create Scriptorium-backed LLM client: %w", err)
}
scheduler, err := llm.NewScheduler(cfg.Concurrency.TotalLLM)
if err != nil {

21
internal/cli/command_contract_test.go
View File

@@ -154,23 +154,6 @@ func TestConfigValidateResolvesPipelineAndChecksSelection(t *testing.T) {
}
}
func TestConfigValidatePipelineDefaultProfileIsOffline(t *testing.T) {
configPath := writeCommandConfigContent(t, `version: 4
pipelines:
demo:
llm_profile: dnd-extraction
input: seriatim
artifacts:
spells:
extract: dnd/spells
`)
var stdout, stderr bytes.Buffer
code := RunWithOptions([]string{"config", "validate", "--config", configPath, "--pipeline", "demo"}, &stdout, &stderr, Options{})
if code != 0 || !strings.Contains(stdout.String(), "valid for pipeline \"demo\"") || stderr.Len() != 0 {
t.Fatalf("code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
}
}
func TestPipelinesListSortsNormalizedIDsInTextAndJSON(t *testing.T) {
configPath := writeCommandConfig(t, " zeta ", "alpha")
options := commandContractOptions(t)
@@ -231,13 +214,13 @@ func commandContractOptionsWithLookup(t *testing.T, lookup func(string) (string,
func writeCommandConfig(t *testing.T, firstID, secondID string) string {
t.Helper()
content := fmt.Sprintf("version: 4\npipelines:\n %q:\n input: seriatim\n %q:\n input: seriatim\n", firstID, secondID)
content := fmt.Sprintf("version: 3\npipelines:\n %q:\n input: seriatim\n %q:\n input: seriatim\n", firstID, secondID)
return writeCommandConfigContent(t, content)
}
func writeResolvableCommandConfig(t *testing.T) string {
t.Helper()
return writeCommandConfigContent(t, `version: 4
return writeCommandConfigContent(t, `version: 3
pipelines:
demo:
input: seriatim

8
internal/cli/dnd_combat_contract_test.go
View File

@@ -48,7 +48,7 @@ func TestProductionCombatConfigurationResolvesTypedLane(t *testing.T) {
if !ok || codecSpec.Schema.ID != "notarius.dnd.combat_turns" || codecSpec.Schema.Version != "v1" {
t.Fatalf("combat codec spec = %#v, want compatible durable schema", codecSpec)
}
if !hasReferenceSlot(extractSpec.ReferenceSlots, "npc_registry") || !hasReferenceSlot(extractSpec.ReferenceSlots, "scene_descriptions") || !hasReferenceSlot(normalizeSpec.ReferenceSlots, "npc_registry") {
if !hasReferenceSlot(extractSpec.ReferenceSlots, "npcs") || !hasReferenceSlot(extractSpec.ReferenceSlots, "scene_descriptions") || !hasReferenceSlot(normalizeSpec.ReferenceSlots, "npcs") {
t.Fatalf("combat reference slots = %#v / %#v, want extraction scene and NPC slots plus normalization NPC slot", extractSpec.ReferenceSlots, normalizeSpec.ReferenceSlots)
}
sceneSlot := referenceSlot(extractSpec.ReferenceSlots, "scene_descriptions")
@@ -85,15 +85,15 @@ func TestProductionCombatConfigurationResolvesTypedLane(t *testing.T) {
PipelineID: "dnd-combat",
Catalog: catalog,
ReferenceOverrides: []pipeline.ReferenceBinding{
{Stage: pipeline.StageExtract, LaneID: "combat", SlotName: "npc_registry", Source: "npc-run/lanes/npc_registry.json", BindingSource: contracts.ReferenceBindingSourceCLI},
{Stage: pipeline.StageNormalize, LaneID: "combat", SlotName: "npc_registry", Source: "npc-run/lanes/npc_registry.json", BindingSource: contracts.ReferenceBindingSourceCLI},
{Stage: pipeline.StageExtract, LaneID: "combat", SlotName: "npcs", Source: "npc-run/lanes/npcs.json", BindingSource: contracts.ReferenceBindingSourceCLI},
{Stage: pipeline.StageNormalize, LaneID: "combat", SlotName: "npcs", Source: "npc-run/lanes/npcs.json", BindingSource: contracts.ReferenceBindingSourceCLI},
},
})
if err != nil {
t.Fatalf("Resolve(bound references) error = %v, want nil", err)
}
boundLane := bound.ResolvedPipeline.Steps[0].ArtifactLanes[0]
if len(boundLane.ExtractReferences.Bindings) != 2 || len(boundLane.NormalizeReferences.Bindings) != 1 || !hasReferenceBinding(boundLane.ExtractReferences.Bindings, "npc_registry") || !hasReferenceBinding(boundLane.ExtractReferences.Bindings, "scene_descriptions") || !hasReferenceBinding(boundLane.NormalizeReferences.Bindings, "npc_registry") {
if len(boundLane.ExtractReferences.Bindings) != 2 || len(boundLane.NormalizeReferences.Bindings) != 1 || !hasReferenceBinding(boundLane.ExtractReferences.Bindings, "npcs") || !hasReferenceBinding(boundLane.ExtractReferences.Bindings, "scene_descriptions") || !hasReferenceBinding(boundLane.NormalizeReferences.Bindings, "npcs") {
t.Fatalf("bound combat references = %#v / %#v, want extraction scene and NPC bindings plus normalization NPC binding", boundLane.ExtractReferences, boundLane.NormalizeReferences)
}
}

433
internal/cli/dnd_enemy_events_contract_test.go
View File

@@ -1,433 +0,0 @@
package cli
import (
"context"
"encoding/json"
"errors"
"fmt"
"os"
"path/filepath"
"reflect"
"strings"
"sync"
"testing"
"time"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/evidencecontext"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/chunk/scenes"
itemoccurrencecodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/itemoccurrences"
itemregistrycodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/itemregistry"
locationoccurrencecodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/locationoccurrences"
locationcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/locationregistry"
npcoccurrencecodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcoccurrences"
npccodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcregistry"
combat "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/combatturns"
enemyevents "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/enemyevents"
itemoccurrences "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemoccurrences"
itemregistry "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemregistry"
locationoccurrences "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationoccurrences"
locations "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationregistry"
npcoccurrences "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcoccurrences"
npcregistry "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcregistry"
scenedescriptions "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/scenedescriptions"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/spells"
enemyeventnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/enemyevents"
itemregistrynormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemregistry"
locationnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationregistry"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcregistry"
)
func TestProductionEnemyEventConfigurationResolvesGeneratedHandoffs(t *testing.T) {
components := productionTestComponents(t)
cfg := loadMaintainedExample(t, repositoryPath("examples", "dnd-complete.config.yml"))
effective, err := cfg.Resolve(resolveInputForMaintainedExample(components, "dnd-session"))
if err != nil {
t.Fatalf("Resolve() error = %v, want nil", err)
}
materialized, _, err := pipeline.MaterializeReferences(effective.ResolvedPipeline, catalogFromRegistries(components.registries), pipeline.ReferenceMaterializationOptions{
ConfigPath: repositoryPath("examples", "dnd-complete.config.yml"),
WorkingDir: repositoryPath("examples"),
})
if err != nil {
t.Fatalf("MaterializeReferences() error = %v, want nil", err)
}
lane := referenceContractLane(t, materialized, "enemy-events")
if lane.ArtifactKind != dnd.EnemyEventListKind || lane.Extract.Module != enemyevents.Key || lane.Extract.Retries != 2 || lane.Merge.Module != pipeline.DefaultMergeModule || lane.Normalize.Module != enemyeventnormalize.Key {
t.Fatalf("enemy event lane = %#v, want typed production composition", lane)
}
for slot, want := range map[string]struct{ step, lane string }{
"npc_registry": {step: "describe-session", lane: "npc-registry"},
"scene_descriptions": {step: "describe-session", lane: "scene-descriptions"},
"combat_turns": {step: "extract-events", lane: "combat-turns"},
"npc_occurrences": {step: "extract-events", lane: "npc-occurrences"},
} {
binding, found := generatedReferenceBinding(lane.ExtractReferences.Bindings, slot)
if !found || binding.Artifact.Step != want.step || binding.Artifact.Lane != want.lane {
t.Fatalf("enemy event %s reference = %#v, want generated %s/%s artifact", slot, binding, want.step, want.lane)
}
}
if binding, found := generatedReferenceBinding(lane.NormalizeReferences.Bindings, "npc_registry"); !found || binding.Artifact.Step != "describe-session" || binding.Artifact.Lane != "npc-registry" {
t.Fatalf("enemy event normalizer NPC reference = %#v, want generated NPC artifact", binding)
}
catalog := catalogFromRegistries(components.registries)
extractSpec, ok := catalog.Extractors.Spec(enemyevents.Key)
if !ok || !reflect.DeepEqual(extractSpec.Requires, []string{"chunks", "source.transcript"}) || !reflect.DeepEqual(extractSpec.Provides, []string{"dnd.enemy_events"}) {
t.Fatalf("enemy event extractor spec = %#v, want source and artifact capabilities", extractSpec)
}
normalizeSpec, ok := catalog.Normalizers.SpecForArtifact(enemyeventnormalize.Key, dnd.EnemyEventListKind)
if !ok || !reflect.DeepEqual(normalizeSpec.Requires, []string{"merged"}) || !reflect.DeepEqual(normalizeSpec.Provides, []string{"normalized"}) {
t.Fatalf("enemy event normalizer spec = %#v, want merged/normalized capabilities", normalizeSpec)
}
for _, slot := range []string{"npc_registry", "scene_descriptions", "combat_turns", "npc_occurrences"} {
if !hasReferenceSlot(extractSpec.ReferenceSlots, slot) {
t.Fatalf("enemy event extractor slots = %#v, want %q", extractSpec.ReferenceSlots, slot)
}
}
if !hasReferenceSlot(normalizeSpec.ReferenceSlots, "npc_registry") {
t.Fatalf("enemy event normalizer slots = %#v, want NPC registry", normalizeSpec.ReferenceSlots)
}
profile := cfg.Pipelines["dnd-session"]
profile.Steps[2].References["npc_registry"] = pipeline.GeneratedReference("track-enemies", "enemy-events")
cfg.Pipelines["dnd-session"] = profile
if _, err := cfg.Resolve(resolveInputForMaintainedExample(components, "dnd-session")); err == nil || !strings.Contains(err.Error(), "earlier step") {
t.Fatalf("Resolve() error = %v, want future generated-reference rejection", err)
}
}
func TestMaintainedCompleteExamplePublishesRegistryBackedEntityOccurrences(t *testing.T) {
t.Chdir(repositoryPath())
outputRoot := filepath.Join(t.TempDir(), "output")
configPath := completeExampleConfigWithTemporaryCache(t)
client := &enemyEventLLMClient{}
options := productionCLIOptions(t)
options.Now = func() time.Time { return time.Unix(1700000000, 0).UTC() }
options.RunIDGenerator = func(time.Time) (string, error) { return productionRunID, nil }
options.UserCacheDir = func() (string, error) { return "", errors.New("user cache must not be used") }
options.LLMClientFactory = func(context.Context, config.Config, string, LLMRuntimeOverrides) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
return client, nil, nil
}
var stdout, stderr strings.Builder
code := RunWithOptions([]string{
"run", "dnd-session",
"--config", configPath,
"--input", repositoryPath("examples", "dnd-complete-transcript.json"),
"--chunk_cache", "bypass", "--output-dir", outputRoot, "--session-id", "enemy-event-session",
}, &stdout, &stderr, options)
if code != 0 {
t.Fatalf("code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
}
runRoot := filepath.Join(outputRoot, productionRunID)
index := readProductionJSON[exampleOutputIndex](t, filepath.Join(runRoot, "index.json"))
outputs := make(map[string]exampleOutputIndexEntry)
for _, entry := range index.OutputFiles {
outputs[entry.LaneID] = entry
}
enemyOutput := outputs["enemy-events"]
locationOutput := outputs["location-registry"]
locationOccurrenceOutput := outputs["location-occurrences"]
npcRegistryOutput := outputs["npc-registry"]
npcOccurrenceOutput := outputs["npc-occurrences"]
itemRegistryOutput := outputs["item-registry"]
itemOccurrenceOutput := outputs["item-occurrences"]
if enemyOutput.File != "lanes/enemy-events.json" || enemyOutput.SchemaID != "notarius.dnd.enemy_events" || enemyOutput.SchemaVersion != "v1" {
t.Fatalf("enemy event output = %#v, want typed enemy-event JSON", enemyOutput)
}
value := readProductionJSON[dnd.EnemyEventList](t, filepath.Join(runRoot, enemyOutput.File))
if len(value.Events) != 1 || value.Events[0].Name != "Kesh" || value.Events[0].Kind != dnd.EnemyEventKindFled || len(value.Events[0].SourceRefs) != 1 || value.Events[0].SourceRefs[0].SourceID != "session-ravenfall" || value.Events[0].SourceRefs[0].StartUnitID != 10 {
t.Fatalf("enemy event artifact = %#v, want source-linked Kesh fleeing event", value)
}
if locationOutput.File != "lanes/location-registry.json" || locationOutput.SchemaID != locationcodec.SchemaID || locationOutput.SchemaVersion != locationcodec.SchemaVersion {
t.Fatalf("location output = %#v, want typed location registry JSON", locationOutput)
}
locationsValue := readProductionJSON[dnd.LocationRegistry](t, filepath.Join(runRoot, locationOutput.File))
if len(locationsValue.Locations) != 2 || locationsValue.Locations[0].Name != "Moon Gate" || locationsValue.Locations[1].Name != "Moon Gate" || locationsValue.Locations[0].ID == locationsValue.Locations[1].ID {
t.Fatalf("location registry = %#v, want distinct source-grounded identities for same-name locations", locationsValue)
}
if locationOccurrenceOutput.File != "lanes/location-occurrences.json" || locationOccurrenceOutput.SchemaID != locationoccurrencecodec.SchemaID || locationOccurrenceOutput.SchemaVersion != locationoccurrencecodec.SchemaVersion {
t.Fatalf("location occurrence output = %#v, want typed occurrence JSON", locationOccurrenceOutput)
}
occurrencesValue := readProductionJSON[dnd.LocationOccurrenceList](t, filepath.Join(runRoot, locationOccurrenceOutput.File))
if len(occurrencesValue.Occurrences) != 2 || occurrencesValue.Occurrences[0].LocationID == occurrencesValue.Occurrences[1].LocationID || occurrencesValue.Occurrences[0].Name != "Moon Gate" || occurrencesValue.Occurrences[1].Name != "Moon Gate" {
t.Fatalf("location occurrences = %#v, want source-grounded references to distinct registry identities", occurrencesValue)
}
if npcRegistryOutput.File != "lanes/npc-registry.json" || npcRegistryOutput.SchemaID != npccodec.SchemaID || npcRegistryOutput.SchemaVersion != npccodec.SchemaVersion {
t.Fatalf("NPC registry output = %#v, want typed registry JSON", npcRegistryOutput)
}
npcRegistry := readProductionJSON[dnd.NPCRegistry](t, filepath.Join(runRoot, npcRegistryOutput.File))
if len(npcRegistry.NPCs) != 1 || npcRegistry.NPCs[0].Name != "Kesh" {
t.Fatalf("NPC registry = %#v, want Kesh identity", npcRegistry)
}
if npcOccurrenceOutput.File != "lanes/npc-occurrences.json" || npcOccurrenceOutput.SchemaID != npcoccurrencecodec.SchemaID || npcOccurrenceOutput.SchemaVersion != npcoccurrencecodec.SchemaVersion {
t.Fatalf("NPC occurrence output = %#v, want typed occurrence JSON", npcOccurrenceOutput)
}
npcOccurrences := readProductionJSON[dnd.NPCOccurrenceList](t, filepath.Join(runRoot, npcOccurrenceOutput.File))
if len(npcOccurrences.Occurrences) != 1 || npcOccurrences.Occurrences[0].NPCID != npcRegistry.NPCs[0].ID || npcOccurrences.Occurrences[0].Name != "Kesh" || len(npcOccurrences.Occurrences[0].SourceRefs) != 1 || npcOccurrences.Occurrences[0].SourceRefs[0].StartUnitID != 7 {
t.Fatalf("NPC occurrences = %#v, want independently evidenced Kesh registry grounding", npcOccurrences)
}
if itemRegistryOutput.File != "lanes/item-registry.json" || itemRegistryOutput.SchemaID != itemregistrycodec.SchemaID || itemRegistryOutput.SchemaVersion != itemregistrycodec.SchemaVersion {
t.Fatalf("item registry output = %#v, want typed registry JSON", itemRegistryOutput)
}
itemRegistry := readProductionJSON[dnd.ItemRegistry](t, filepath.Join(runRoot, itemRegistryOutput.File))
if len(itemRegistry.Items) != 1 || itemRegistry.Items[0].Name != "Moonblade" {
t.Fatalf("item registry = %#v, want Moonblade identity", itemRegistry)
}
if itemOccurrenceOutput.File != "lanes/item-occurrences.json" || itemOccurrenceOutput.SchemaID != itemoccurrencecodec.SchemaID || itemOccurrenceOutput.SchemaVersion != itemoccurrencecodec.SchemaVersion {
t.Fatalf("item occurrence output = %#v, want typed occurrence JSON", itemOccurrenceOutput)
}
itemOccurrences := readProductionJSON[dnd.ItemOccurrenceList](t, filepath.Join(runRoot, itemOccurrenceOutput.File))
if len(itemOccurrences.Occurrences) != 1 || itemOccurrences.Occurrences[0].ItemID != itemRegistry.Items[0].ID || itemOccurrences.Occurrences[0].Name != "Moonblade" || len(itemOccurrences.Occurrences[0].SourceRefs) != 1 || itemOccurrences.Occurrences[0].SourceRefs[0].StartUnitID != 5 {
t.Fatalf("item occurrences = %#v, want independently evidenced Moonblade registry grounding", itemOccurrences)
}
evidence := readProductionJSON[evidencecontext.Document](t, filepath.Join(runRoot, "evidence-context.json"))
if len(evidence) == 0 {
t.Fatalf("evidence context = %#v, want selected source-unit evidence", evidence)
}
seenEvidenceUnits := make(map[int]struct{}, len(evidence))
for _, unit := range evidence {
if unit.Ref.SourceID != "session-ravenfall" || unit.Ref.StartUnitID != unit.ID || unit.Ref.EndUnitID != unit.ID {
t.Fatalf("evidence unit = %#v, want unchanged source-unit self-reference", unit)
}
if _, exists := seenEvidenceUnits[unit.ID]; exists {
t.Fatalf("evidence context = %#v, want each source unit once", evidence)
}
seenEvidenceUnits[unit.ID] = struct{}{}
}
requests := client.requestsFor(enemyevents.PromptID)
if len(requests) != 1 {
t.Fatalf("enemy event requests = %#v, want only the combat scene request", requests)
}
request := requests[0]
if request.SessionID != "enemy-event-session" {
t.Fatalf("enemy event session = %q, want shared session", request.SessionID)
}
for slot, required := range map[string]string{
"npc_registry": "Kesh",
"combat_turns": "Kesh",
"npc_occurrences": "Kesh",
} {
input, ok := request.Inputs[slot]
if !ok || !strings.Contains(string(input.Content), required) || strings.Contains(string(input.Content), "source_refs") || strings.Contains(string(input.Content), "start_unit_id") {
t.Fatalf("enemy event %s prompt input = %q, want compact source-free grounding", slot, input.Content)
}
}
locationRequests := client.requestsFor(locationoccurrences.PromptID)
if len(locationRequests) != 2 {
t.Fatalf("location occurrence requests = %#v, want one request per scene", locationRequests)
}
for _, request := range locationRequests {
registryInput := request.Inputs["location_registry"]
if !strings.Contains(string(registryInput.Content), "Moon Gate") || !strings.Contains(string(registryInput.Content), "registry_refs") || strings.Contains(string(registryInput.Content), `"id"`) || strings.Contains(string(registryInput.Content), "source_refs") {
t.Fatalf("location occurrence registry input = %q, want contextual selector grounding", registryInput.Content)
}
}
for _, test := range []struct {
promptID string
slot string
name string
requiresIDs bool
}{
{promptID: npcoccurrences.PromptID, slot: "npc_registry", name: "Kesh"},
{promptID: itemoccurrences.PromptID, slot: "item_registry", name: "Moonblade"},
} {
requests := client.requestsFor(test.promptID)
if len(requests) != 2 {
t.Fatalf("%s requests = %#v, want one request per scene", test.promptID, requests)
}
for _, request := range requests {
registryInput := request.Inputs[test.slot]
hasID := strings.Contains(string(registryInput.Content), `"id"`)
if !strings.Contains(string(registryInput.Content), test.name) || hasID != test.requiresIDs || strings.Contains(string(registryInput.Content), "source_refs") {
t.Fatalf("%s registry input = %q, want source-free configured grounding", test.promptID, registryInput.Content)
}
}
}
}
func completeExampleConfigWithTemporaryCache(t *testing.T) string {
t.Helper()
content, err := os.ReadFile(repositoryPath("examples", "dnd-complete.config.yml"))
if err != nil {
t.Fatal(err)
}
cacheRoot := t.TempDir()
updated := strings.Replace(string(content), "directory: ./notarius-cache/chunk-plans", fmt.Sprintf("directory: %q", filepath.Join(cacheRoot, "chunk-plans")), 1)
updated = strings.Replace(updated, "directory: ./notarius-cache/checkpoints", fmt.Sprintf("directory: %q", filepath.Join(cacheRoot, "checkpoints")), 1)
for relative, absolute := range map[string]string{
"./dnd-party.txt": repositoryPath("examples", "dnd-party.txt"),
"./dnd-glossary.txt": repositoryPath("examples", "dnd-glossary.txt"),
"./dnd-spell-catalog.json": repositoryPath("examples", "dnd-spell-catalog.json"),
} {
updated = strings.ReplaceAll(updated, relative, fmt.Sprintf("%q", absolute))
}
path := filepath.Join(t.TempDir(), "dnd-complete.config.yml")
if err := os.WriteFile(path, []byte(updated), 0o600); err != nil {
t.Fatal(err)
}
return path
}
type enemyEventLLMClient struct {
mu sync.Mutex
requests []contracts.StructuredCompletionRequest
}
func (client *enemyEventLLMClient) CompleteStructured(ctx context.Context, request contracts.StructuredCompletionRequest, output any) (contracts.StructuredCompletionResponse, error) {
if err := ctx.Err(); err != nil {
return contracts.StructuredCompletionResponse{}, err
}
combatScene := strings.Contains(string(request.Inputs["transcript"].Content), "Roll initiative")
var content []byte
switch request.PromptID {
case scenes.PromptID:
content = []byte(`{"scenes":[{"start_unit_id":1,"end_unit_id":6},{"start_unit_id":7,"end_unit_id":11}]}`)
case npcregistry.PromptID:
if combatScene {
content = []byte(`{"npcs":[{"name":"Kesh","source_refs":[{"start_unit_id":7,"end_unit_id":7}]}]}`)
} else {
content = []byte(`{"npcs":[]}`)
}
case npcnormalize.PromptID:
content = []byte(`{"duplicate_groups":[]}`)
case scenedescriptions.PromptID:
kind, title := "narrative", "Arrival"
if combatScene {
kind, title = "combat", "Raiders attack"
}
content = []byte(fmt.Sprintf(`{"kind":%q,"title":%q,"summary":"session scene"}`, kind, title))
case locations.PromptID:
unitID := 1
if combatScene {
unitID = 7
}
content = []byte(fmt.Sprintf(`{"locations":[{"name":"Moon Gate","source_refs":[{"start_unit_id":%d,"end_unit_id":%d}]}]}`, unitID, unitID))
case locationnormalize.PromptID:
content = []byte(`{"duplicate_groups":[]}`)
case spells.PromptID:
content = []byte(`{"spell_casts":[]}`)
case itemregistry.PromptID:
if combatScene {
content = []byte(`{"items":[]}`)
} else {
content = []byte(`{"items":[{"name":"Moonblade","source_refs":[{"start_unit_id":5,"end_unit_id":5}]}]}`)
}
case itemregistrynormalize.PromptID:
content = []byte(`{"duplicate_groups":[]}`)
case itemoccurrences.PromptID:
if combatScene {
content = []byte(`{"occurrences":[]}`)
} else {
var registry struct {
Items []struct {
Name string `json:"name"`
} `json:"items"`
}
if err := json.Unmarshal(request.Inputs["item_registry"].Content, &registry); err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("decode generated item registry: %w", err)
}
if len(registry.Items) != 1 || registry.Items[0].Name != "Moonblade" {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("generated item registry has %d items, want 1", len(registry.Items))
}
content = []byte(`{"occurrences":[{"name":"Moonblade","kind":"discovered","quantity":null,"from":null,"to":null,"source_refs":[{"start_unit_id":5,"end_unit_id":5}]}]}`)
}
case combat.PromptID:
content = []byte(`{"combat_turns":[{"actor":"Kesh","turn_kind":"turn","source_refs":[{"start_unit_id":8,"end_unit_id":8}]}]}`)
case npcoccurrences.PromptID:
if combatScene {
var registry struct {
NPCs []struct {
Name string `json:"name"`
} `json:"npcs"`
}
if err := json.Unmarshal(request.Inputs["npc_registry"].Content, &registry); err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("decode generated NPC registry: %w", err)
}
if len(registry.NPCs) == 0 || registry.NPCs[0].Name != "Kesh" {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("generated NPC registry has no NPCs")
}
content = []byte(`{"occurrences":[{"name":"Kesh","kind":"combat_opponent","source_refs":[{"start_unit_id":7,"end_unit_id":7}]}]}`)
} else {
content = []byte(`{"occurrences":[]}`)
}
case locationoccurrences.PromptID:
var registry struct {
Locations []struct {
Name string `json:"name"`
RegistryRefs []struct {
StartUnitID int `json:"start_unit_id"`
EndUnitID int `json:"end_unit_id"`
} `json:"registry_refs"`
} `json:"locations"`
}
if err := json.Unmarshal(request.Inputs["location_registry"].Content, &registry); err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("decode generated location registry: %w", err)
}
if len(registry.Locations) == 0 {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("generated location registry has no locations")
}
unitID := 1
location := registry.Locations[0]
if combatScene {
unitID = 7
if len(registry.Locations) > 1 {
location = registry.Locations[1]
}
}
registryRefs, err := json.Marshal(location.RegistryRefs)
if err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("encode location selector: %w", err)
}
content = []byte(fmt.Sprintf(`{"occurrences":[{"name":%q,"registry_refs":%s,"kind":"visited","source_refs":[{"start_unit_id":%d,"end_unit_id":%d}]}]}`, location.Name, registryRefs, unitID, unitID))
case enemyevents.PromptID:
content = []byte(`{"events":[{"name":"Kesh","kind":"fled","source_refs":[{"start_unit_id":10,"end_unit_id":10}]}]}`)
default:
return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected prompt %q", request.PromptID)
}
if err := json.Unmarshal(content, output); err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("populate fake structured target: %w", err)
}
client.mu.Lock()
client.requests = append(client.requests, request)
client.mu.Unlock()
return contracts.StructuredCompletionResponse{Content: content, Provider: "test", Model: "deterministic", ProfileID: request.ProfileID}, nil
}
func (client *enemyEventLLMClient) requestsFor(promptID string) []contracts.StructuredCompletionRequest {
client.mu.Lock()
defer client.mu.Unlock()
var requests []contracts.StructuredCompletionRequest
for _, request := range client.requests {
if request.PromptID == promptID {
requests = append(requests, request)
}
}
return requests
}
func containsString(values []string, want string) bool {
for _, value := range values {
if value == want {
return true
}
}
return false
}
func generatedReferenceBinding(bindings []pipeline.ReferenceBinding, slotName string) (pipeline.ReferenceBinding, bool) {
for _, binding := range bindings {
if binding.SlotName == slotName && binding.Artifact != nil {
return binding, true
}
}
return pipeline.ReferenceBinding{}, false
}

135
internal/cli/dnd_interactions_contract_test.go Normal file
View File

@@ -0,0 +1,135 @@
package cli
import (
"os"
"path/filepath"
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
interactioncodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcinteractions"
interactionextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcinteractions"
npcextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcs"
interactionnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcinteractions"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcs"
)
func TestProductionNPCInteractionPipelineResolvesAndPrepares(t *testing.T) {
components := productionTestComponents(t)
resolved, err := pipeline.ResolvePipeline(npcInteractionProfile(pipeline.GeneratedReference("npcs", "npcs")), pipeline.ResolveOptions{}, catalogFromRegistries(components.registries))
if err != nil {
t.Fatalf("ResolvePipeline() error = %v", err)
}
if len(resolved.Steps) != 2 || len(resolved.Steps[1].ArtifactLanes) != 1 {
t.Fatalf("resolved pipeline = %#v", resolved)
}
lane := resolved.Steps[1].ArtifactLanes[0]
if lane.ArtifactKind != dnd.NPCInteractionListKind || lane.Extract.Module != interactionextract.Key || lane.Normalize.Module != interactionnormalize.Key {
t.Fatalf("interaction lane = %#v", lane)
}
for _, bindings := range [][]pipeline.ReferenceBinding{lane.ExtractReferences.Bindings, lane.NormalizeReferences.Bindings} {
if len(bindings) != 1 || bindings[0].SlotName != "npcs" || bindings[0].Artifact == nil || bindings[0].Artifact.Step != "npcs" || bindings[0].Artifact.Lane != "npcs" {
t.Fatalf("generated bindings = %#v", bindings)
}
}
if _, err := pipeline.Prepare(resolved, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}}); err != nil {
t.Fatalf("Prepare() error = %v", err)
}
catalog := catalogFromRegistries(components.registries)
codecSpec, ok := catalog.ArtifactCodecs.Spec(dnd.NPCInteractionListKind)
if !ok || codecSpec.Schema.ID != interactioncodec.SchemaID || codecSpec.Schema.Version != interactioncodec.SchemaVersion {
t.Fatalf("NPC interaction codec spec = %#v", codecSpec)
}
}
func TestProductionNPCInteractionReferencesRequireEarlierCompatibleProducer(t *testing.T) {
components := productionTestComponents(t)
catalog := catalogFromRegistries(components.registries)
laterProfile := npcInteractionProfile(pipeline.GeneratedReference("npcs", "npcs"))
laterProfile.Steps[0].ID = "seed"
laterProfile.Steps[0].Artifacts["seed"] = laterProfile.Steps[0].Artifacts["npcs"]
delete(laterProfile.Steps[0].Artifacts, "npcs")
laterProfile.Steps = append(laterProfile.Steps, pipeline.PipelineStepProfile{ID: "future", Artifacts: map[string]pipeline.ArtifactLaneProfile{
"npcs": {Extract: pipeline.Binding(npcextract.Key), Normalize: pipeline.Binding(npcnormalize.Key)},
}})
laterProfile.Steps[1].References["npcs"] = pipeline.GeneratedReference("future", "npcs")
tests := []struct {
name string
profile pipeline.PipelineProfile
want string
}{
{name: "missing", profile: npcInteractionProfile(pipeline.ReferenceSource{}), want: "source must not be empty"},
{name: "same step", profile: npcInteractionProfile(pipeline.GeneratedReference("interactions", "interactions")), want: "earlier step"},
{name: "later step", profile: laterProfile, want: "earlier step"},
{name: "wrong artifact kind", profile: npcInteractionProfile(pipeline.GeneratedReference("npcs", "npcs")), want: "does not accept artifact kind"},
}
tests[3].profile.Steps[0].Artifacts["npcs"] = pipeline.ArtifactLaneProfile{Extract: pipeline.Binding("dnd/spells")}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
_, err := pipeline.ResolvePipeline(test.profile, pipeline.ResolveOptions{}, catalog)
if err == nil || !strings.Contains(err.Error(), test.want) {
t.Fatalf("ResolvePipeline() error = %v, want %q", err, test.want)
}
})
}
}
func TestProductionNPCInteractionReferencesRejectIncompatibleExternalRegistries(t *testing.T) {
components := productionTestComponents(t)
catalog := catalogFromRegistries(components.registries)
root := t.TempDir()
for _, test := range []struct {
name string
file string
content string
prepare bool
want string
}{
{name: "media type", file: "registry.txt", content: "not JSON", want: "media type"},
{name: "artifact schema", file: "registry.json", content: `{"npcs":[{"name":"missing required fields"}]}`, prepare: true, want: "NPC registry"},
} {
t.Run(test.name, func(t *testing.T) {
path := filepath.Join(root, test.file)
if err := os.WriteFile(path, []byte(test.content), 0o600); err != nil {
t.Fatal(err)
}
resolved, err := pipeline.ResolvePipeline(npcInteractionProfile(pipeline.ExternalReference(path)), pipeline.ResolveOptions{}, catalog)
if err != nil {
t.Fatalf("ResolvePipeline() error = %v", err)
}
materialized, _, err := pipeline.MaterializeReferences(resolved, catalog, pipeline.ReferenceMaterializationOptions{})
if !test.prepare {
if err == nil || !strings.Contains(err.Error(), test.want) {
t.Fatalf("MaterializeReferences() error = %v, want %q", err, test.want)
}
return
}
if err != nil {
t.Fatalf("MaterializeReferences() error = %v", err)
}
if _, err := pipeline.Prepare(materialized, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}}); err == nil || !strings.Contains(err.Error(), test.want) {
t.Fatalf("Prepare() error = %v, want %q", err, test.want)
}
})
}
}
func npcInteractionProfile(reference pipeline.ReferenceSource) pipeline.PipelineProfile {
profile := pipeline.PipelineProfile{
ID: "dnd-npc-interactions",
Input: pipeline.Binding("seriatim"),
Chunk: pipeline.ModuleBinding{Module: "generic", Options: map[string]any{"max_units": 1}},
Output: pipeline.Binding("json"),
Steps: []pipeline.PipelineStepProfile{
{ID: "npcs", Artifacts: map[string]pipeline.ArtifactLaneProfile{
"npcs": {Extract: pipeline.Binding(npcextract.Key), Normalize: pipeline.Binding(npcnormalize.Key)},
}},
{ID: "interactions", References: map[string]pipeline.ReferenceSource{"npcs": reference}, Artifacts: map[string]pipeline.ArtifactLaneProfile{
"interactions": {Extract: pipeline.Binding(interactionextract.Key), Normalize: pipeline.Binding(interactionnormalize.Key)},
}},
},
}
return profile
}

48
internal/cli/dnd_npc_contract_test.go
View File

@@ -8,9 +8,9 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
npccodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcregistry"
npcextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcregistry"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcregistry"
npccodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcs"
npcextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcs"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcs"
)
func TestProductionNPCConfigurationResolvesTypedLane(t *testing.T) {
@@ -28,7 +28,7 @@ func TestProductionNPCConfigurationResolvesTypedLane(t *testing.T) {
t.Fatalf("artifact lanes = %#v, want one NPC lane", effective.ResolvedPipeline.Steps[0].ArtifactLanes)
}
lane := effective.ResolvedPipeline.Steps[0].ArtifactLanes[0]
if lane.ID != "npc_registry" || lane.ArtifactKind != dnd.NPCRegistryKind || lane.Extract.Module != npcextract.Key || lane.Extract.Retries != 2 || lane.Merge.Module != pipeline.DefaultMergeModule || lane.Normalize.Module != npcnormalize.Key {
if lane.ID != "npcs" || lane.ArtifactKind != dnd.NPCListKind || lane.Extract.Module != npcextract.Key || lane.Extract.Retries != 2 || lane.Merge.Module != pipeline.DefaultMergeModule || lane.Normalize.Module != npcnormalize.Key {
t.Fatalf("resolved NPC lane = %#v, want typed production composition", lane)
}
if len(lane.ExtractReferences.Bindings) != 0 || len(lane.NormalizeReferences.Bindings) != 0 {
@@ -36,36 +36,36 @@ func TestProductionNPCConfigurationResolvesTypedLane(t *testing.T) {
}
extractSpec, ok := catalog.Extractors.Spec(npcextract.Key)
if !ok || !reflect.DeepEqual(extractSpec.Requires, []string{"chunks", "source.transcript"}) || !reflect.DeepEqual(extractSpec.Provides, []string{"dnd.npc_registry"}) {
if !ok || !reflect.DeepEqual(extractSpec.Requires, []string{"chunks", "source.transcript"}) || !reflect.DeepEqual(extractSpec.Provides, []string{"dnd.npcs"}) {
t.Fatalf("NPC extractor spec = %#v, want source and artifact capabilities", extractSpec)
}
mergeSpec, ok := catalog.Mergers.SpecForArtifact(pipeline.DefaultMergeModule, dnd.NPCRegistryKind)
mergeSpec, ok := catalog.Mergers.SpecForArtifact(pipeline.DefaultMergeModule, dnd.NPCListKind)
if !ok || !reflect.DeepEqual(mergeSpec.Provides, []string{"merged"}) {
t.Fatalf("NPC merger spec = %#v, want merged capability", mergeSpec)
}
normalizeSpec, ok := catalog.Normalizers.SpecForArtifact(npcnormalize.Key, dnd.NPCRegistryKind)
normalizeSpec, ok := catalog.Normalizers.SpecForArtifact(npcnormalize.Key, dnd.NPCListKind)
if !ok || !reflect.DeepEqual(normalizeSpec.Requires, []string{"merged"}) || !reflect.DeepEqual(normalizeSpec.Provides, []string{"normalized"}) {
t.Fatalf("NPC normalizer spec = %#v, want merged/normalized capabilities", normalizeSpec)
}
codecSpec, ok := catalog.ArtifactCodecs.Spec(dnd.NPCRegistryKind)
if !ok || codecSpec.Kind != dnd.NPCRegistryKind || codecSpec.Schema.ID != npccodec.SchemaID || codecSpec.Schema.Version != npccodec.SchemaVersion {
codecSpec, ok := catalog.ArtifactCodecs.Spec(dnd.NPCListKind)
if !ok || codecSpec.Kind != dnd.NPCListKind || codecSpec.Schema.ID != npccodec.SchemaID || codecSpec.Schema.Version != npccodec.SchemaVersion {
t.Fatalf("NPC codec spec = %#v, want typed v1 durable schema", codecSpec)
}
wantExtractChain := []pipeline.ModuleBinding{
pipeline.Binding("generic/valid_json"),
pipeline.Binding("extract/dnd/npc-registry/shape"),
pipeline.Binding("extract/dnd/npc-registry/source_refs"),
pipeline.Binding("extract/dnd/npcs/shape"),
pipeline.Binding("extract/dnd/npcs/source_refs"),
pipeline.Binding("generic/valid_json_schema"),
pipeline.Binding("extract/dnd/npc-registry/source_relatedness"),
pipeline.Binding("extract/dnd/npcs/source_relatedness"),
}
wantNormalizeChain := []pipeline.ModuleBinding{
pipeline.Binding("generic/valid_json"),
pipeline.Binding("extract/dnd/npc-registry/shape"),
pipeline.Binding("normalize/dnd/npc-registry/identity"),
pipeline.Binding("extract/dnd/npc-registry/source_refs"),
pipeline.Binding("extract/dnd/npcs/shape"),
pipeline.Binding("normalize/dnd/npcs/identity"),
pipeline.Binding("extract/dnd/npcs/source_refs"),
pipeline.Binding("generic/valid_json_schema"),
pipeline.Binding("extract/dnd/npc-registry/source_relatedness"),
pipeline.Binding("extract/dnd/npcs/source_relatedness"),
}
if got := validatorChain(effective.ResolvedPipeline, pipeline.StageExtract, npcextract.Key); !reflect.DeepEqual(got, wantExtractChain) {
t.Fatalf("NPC extract chain = %#v, want %#v", got, wantExtractChain)
@@ -90,16 +90,16 @@ func TestProductionNPCConfigurationValidatesOptionsReferencesAndPlacement(t *tes
}
if err := resolve(func(profile *pipeline.PipelineProfile) {
lane := profile.Artifacts["npc_registry"]
lane := profile.Artifacts["npcs"]
lane.Extract.Options = map[string]any{"unexpected": true}
profile.Artifacts["npc_registry"] = lane
profile.Artifacts["npcs"] = lane
}); err == nil || !strings.Contains(err.Error(), "unknown option") {
t.Fatalf("unknown extractor option error = %v, want strict option rejection", err)
}
if err := resolve(func(profile *pipeline.PipelineProfile) {
lane := profile.Artifacts["npc_registry"]
lane := profile.Artifacts["npcs"]
lane.Normalize.Options = map[string]any{"unexpected": true}
profile.Artifacts["npc_registry"] = lane
profile.Artifacts["npcs"] = lane
}); err == nil || !strings.Contains(err.Error(), "unknown option") {
t.Fatalf("unknown normalizer option error = %v, want strict option rejection", err)
}
@@ -113,9 +113,9 @@ func TestProductionNPCConfigurationValidatesOptionsReferencesAndPlacement(t *tes
t.Fatalf("optional NPC references error = %v, want resolution success", err)
}
if err := resolve(func(profile *pipeline.PipelineProfile) {
lane := profile.Artifacts["npc_registry"]
lane.Validators = []pipeline.ModuleBinding{pipeline.Binding("normalize/dnd/npc-registry/identity")}
profile.Artifacts["npc_registry"] = lane
lane := profile.Artifacts["npcs"]
lane.Validators = []pipeline.ModuleBinding{pipeline.Binding("normalize/dnd/npcs/identity")}
profile.Artifacts["npcs"] = lane
}); err == nil || !strings.Contains(err.Error(), "artifact lane level") {
t.Fatalf("lane-level validator error = %v, want invalid placement rejection", err)
}
@@ -128,7 +128,7 @@ func productionNPCContractConfig() config.Config {
Input: pipeline.Binding("seriatim"),
Chunk: pipeline.Binding(pipeline.DefaultChunkModule),
Artifacts: map[string]pipeline.ArtifactLaneProfile{
"npc_registry": {
"npcs": {
Extract: pipeline.ModuleBinding{Module: npcextract.Key, Retries: 2},
Normalize: pipeline.Binding(npcnormalize.Key),
},

217
internal/cli/dnd_occurrences_contract_test.go
View File

@@ -1,217 +0,0 @@
package cli
import (
"os"
"path/filepath"
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
itemregistrycodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/itemregistry"
locationregistrycodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/locationregistry"
occurrencecodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcoccurrences"
npcregistrycodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcregistry"
itemoccurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemoccurrences"
locationoccurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationoccurrences"
occurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcoccurrences"
npcextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcregistry"
itemidentity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/items/identity"
locationidentity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/locations/identity"
itemoccurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemoccurrences"
locationoccurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationoccurrences"
occurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcoccurrences"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcregistry"
npcidentity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
)
func TestProductionNPCOccurrencePipelineResolvesAndPrepares(t *testing.T) {
components := productionTestComponents(t)
resolved, err := pipeline.ResolvePipeline(npcOccurrenceProfile(pipeline.GeneratedReference("npc-registry", "npc_registry")), pipeline.ResolveOptions{}, catalogFromRegistries(components.registries))
if err != nil {
t.Fatalf("ResolvePipeline() error = %v", err)
}
if len(resolved.Steps) != 2 || len(resolved.Steps[1].ArtifactLanes) != 1 {
t.Fatalf("resolved pipeline = %#v", resolved)
}
lane := resolved.Steps[1].ArtifactLanes[0]
if lane.ArtifactKind != dnd.NPCOccurrenceListKind || lane.Extract.Module != occurrenceextract.Key || lane.Normalize.Module != occurrencenormalize.Key {
t.Fatalf("occurrence lane = %#v", lane)
}
for _, bindings := range [][]pipeline.ReferenceBinding{lane.ExtractReferences.Bindings, lane.NormalizeReferences.Bindings} {
if len(bindings) != 1 || bindings[0].SlotName != "npc_registry" || bindings[0].Artifact == nil || bindings[0].Artifact.Step != "npc-registry" || bindings[0].Artifact.Lane != "npc_registry" {
t.Fatalf("generated bindings = %#v", bindings)
}
}
if _, err := pipeline.Prepare(resolved, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}}); err != nil {
t.Fatalf("Prepare() error = %v", err)
}
catalog := catalogFromRegistries(components.registries)
codecSpec, ok := catalog.ArtifactCodecs.Spec(dnd.NPCOccurrenceListKind)
if !ok || codecSpec.Schema.ID != occurrencecodec.SchemaID || codecSpec.Schema.Version != occurrencecodec.SchemaVersion {
t.Fatalf("NPC occurrence codec spec = %#v", codecSpec)
}
}
func TestProductionNPCOccurrenceReferencesRequireEarlierCompatibleProducer(t *testing.T) {
components := productionTestComponents(t)
catalog := catalogFromRegistries(components.registries)
laterProfile := npcOccurrenceProfile(pipeline.GeneratedReference("npc-registry", "npc_registry"))
laterProfile.Steps[0].ID = "seed"
laterProfile.Steps[0].Artifacts["seed"] = laterProfile.Steps[0].Artifacts["npc_registry"]
delete(laterProfile.Steps[0].Artifacts, "npc_registry")
laterProfile.Steps = append(laterProfile.Steps, pipeline.PipelineStepProfile{ID: "future", Artifacts: map[string]pipeline.ArtifactLaneProfile{
"npc_registry": {Extract: pipeline.Binding(npcextract.Key), Normalize: pipeline.Binding(npcnormalize.Key)},
}})
laterProfile.Steps[1].References["npc_registry"] = pipeline.GeneratedReference("future", "npc_registry")
tests := []struct {
name string
profile pipeline.PipelineProfile
want string
}{
{name: "missing", profile: npcOccurrenceProfile(pipeline.ReferenceSource{}), want: "source must not be empty"},
{name: "same step", profile: npcOccurrenceProfile(pipeline.GeneratedReference("occurrences", "occurrences")), want: "earlier step"},
{name: "later step", profile: laterProfile, want: "earlier step"},
{name: "wrong artifact kind", profile: npcOccurrenceProfile(pipeline.GeneratedReference("npc-registry", "npc_registry")), want: "does not accept artifact kind"},
}
tests[3].profile.Steps[0].Artifacts["npc_registry"] = pipeline.ArtifactLaneProfile{Extract: pipeline.Binding("dnd/spells")}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
_, err := pipeline.ResolvePipeline(test.profile, pipeline.ResolveOptions{}, catalog)
if err == nil || !strings.Contains(err.Error(), test.want) {
t.Fatalf("ResolvePipeline() error = %v, want %q", err, test.want)
}
})
}
}
func TestProductionNPCOccurrenceReferencesRejectIncompatibleExternalRegistries(t *testing.T) {
components := productionTestComponents(t)
catalog := catalogFromRegistries(components.registries)
root := t.TempDir()
for _, test := range []struct {
name string
file string
content string
prepare bool
want string
}{
{name: "media type", file: "registry.txt", content: "not JSON", want: "media type"},
{name: "artifact schema", file: "registry.json", content: `{"npcs":[{"name":"missing required fields"}]}`, prepare: true, want: "NPC registry"},
} {
t.Run(test.name, func(t *testing.T) {
path := filepath.Join(root, test.file)
if err := os.WriteFile(path, []byte(test.content), 0o600); err != nil {
t.Fatal(err)
}
resolved, err := pipeline.ResolvePipeline(npcOccurrenceProfile(pipeline.ExternalReference(path)), pipeline.ResolveOptions{}, catalog)
if err != nil {
t.Fatalf("ResolvePipeline() error = %v", err)
}
materialized, _, err := pipeline.MaterializeReferences(resolved, catalog, pipeline.ReferenceMaterializationOptions{})
if !test.prepare {
if err == nil || !strings.Contains(err.Error(), test.want) {
t.Fatalf("MaterializeReferences() error = %v, want %q", err, test.want)
}
return
}
if err != nil {
t.Fatalf("MaterializeReferences() error = %v", err)
}
if _, err := pipeline.Prepare(materialized, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}}); err == nil || !strings.Contains(err.Error(), test.want) {
t.Fatalf("Prepare() error = %v, want %q", err, test.want)
}
})
}
}
func TestProductionOccurrencePipelinesAcceptCompatibleExternalRegistries(t *testing.T) {
components := productionTestComponents(t)
catalog := catalogFromRegistries(components.registries)
reference := source.SourceRef{SourceID: "external-registry", StartUnitID: 1, EndUnitID: 1}
npcContent, err := npcregistrycodec.New().Encode(dnd.NPCRegistry{NPCs: []dnd.NPC{{
ID: npcidentity.DeriveID("Mira Thorn"), Name: "Mira Thorn", SourceRefs: []source.SourceRef{reference},
}}})
if err != nil {
t.Fatal(err)
}
locationContent, err := locationregistrycodec.New().Encode(dnd.LocationRegistry{Locations: []dnd.Location{{
ID: locationidentity.DeriveID("Moon Gate", []source.SourceRef{reference}), Name: "Moon Gate", SourceRefs: []source.SourceRef{reference},
}}})
if err != nil {
t.Fatal(err)
}
itemContent, err := itemregistrycodec.New().Encode(dnd.ItemRegistry{Items: []dnd.Item{{
ID: itemidentity.DeriveID("Moonblade"), Name: "Moonblade", SourceRefs: []source.SourceRef{reference},
}}})
if err != nil {
t.Fatal(err)
}
root := t.TempDir()
for _, test := range []struct {
name string
slot string
extractor string
normalizer string
content []byte
}{
{name: "NPC", slot: "npc_registry", extractor: occurrenceextract.Key, normalizer: occurrencenormalize.Key, content: npcContent},
{name: "location", slot: "location_registry", extractor: locationoccurrenceextract.Key, normalizer: locationoccurrencenormalize.Key, content: locationContent},
{name: "item", slot: "item_registry", extractor: itemoccurrenceextract.Key, normalizer: itemoccurrencenormalize.Key, content: itemContent},
} {
t.Run(test.name, func(t *testing.T) {
path := filepath.Join(root, strings.ToLower(test.name)+"-registry.json")
if err := os.WriteFile(path, test.content, 0o600); err != nil {
t.Fatal(err)
}
resolved, err := pipeline.ResolvePipeline(externalOccurrenceProfile(test.slot, test.extractor, test.normalizer, pipeline.ExternalReference(path)), pipeline.ResolveOptions{}, catalog)
if err != nil {
t.Fatalf("ResolvePipeline() error = %v", err)
}
materialized, warnings, err := pipeline.MaterializeReferences(resolved, catalog, pipeline.ReferenceMaterializationOptions{})
if err != nil || len(warnings) != 0 {
t.Fatalf("MaterializeReferences() error = %v warnings = %#v", err, warnings)
}
if _, err := pipeline.Prepare(materialized, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}}); err != nil {
t.Fatalf("Prepare() error = %v", err)
}
})
}
}
func externalOccurrenceProfile(slot, extractor, normalizer string, reference pipeline.ReferenceSource) pipeline.PipelineProfile {
return pipeline.PipelineProfile{
ID: "external-registry-occurrences",
Input: pipeline.Binding("seriatim"),
Chunk: pipeline.ModuleBinding{Module: "generic", Options: map[string]any{"max_units": 1}},
Output: pipeline.Binding("json"),
Steps: []pipeline.PipelineStepProfile{{
ID: "occurrences",
References: map[string]pipeline.ReferenceSource{slot: reference},
Artifacts: map[string]pipeline.ArtifactLaneProfile{
"occurrences": {Extract: pipeline.Binding(extractor), Normalize: pipeline.Binding(normalizer)},
},
}},
}
}
func npcOccurrenceProfile(reference pipeline.ReferenceSource) pipeline.PipelineProfile {
profile := pipeline.PipelineProfile{
ID: "dnd-npc-occurrences",
Input: pipeline.Binding("seriatim"),
Chunk: pipeline.ModuleBinding{Module: "generic", Options: map[string]any{"max_units": 1}},
Output: pipeline.Binding("json"),
Steps: []pipeline.PipelineStepProfile{
{ID: "npc-registry", Artifacts: map[string]pipeline.ArtifactLaneProfile{
"npc_registry": {Extract: pipeline.Binding(npcextract.Key), Normalize: pipeline.Binding(npcnormalize.Key)},
}},
{ID: "occurrences", References: map[string]pipeline.ReferenceSource{"npc_registry": reference}, Artifacts: map[string]pipeline.ArtifactLaneProfile{
"occurrences": {Extract: pipeline.Binding(occurrenceextract.Key), Normalize: pipeline.Binding(occurrencenormalize.Key)},
}},
},
}
return profile
}

46
internal/cli/dnd_scene_descriptions_contract_test.go
View File

@@ -6,10 +6,8 @@ import (
"fmt"
"reflect"
"strings"
"sync"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
@@ -30,7 +28,7 @@ func TestProductionSceneDescriptionWorkflow(t *testing.T) {
Output: pipeline.Binding("json"),
Artifacts: map[string]pipeline.ArtifactLaneProfile{
"scene-descriptions": {
Extract: pipeline.ModuleBinding{Module: sceneextract.Key, LLMProfile: "scene-description-profile"},
Extract: pipeline.Binding(sceneextract.Key),
Normalize: pipeline.Binding(scenenormalize.Key),
},
},
@@ -47,8 +45,7 @@ func TestProductionSceneDescriptionWorkflow(t *testing.T) {
t.Fatalf("resolved references = %#v / %#v, want no generated or required references", lane.ExtractReferences, lane.NormalizeReferences)
}
llmClient := &sceneDescriptionLLM{}
prepared, err := pipeline.Prepare(effective.ResolvedPipeline, components.registries, pipeline.ModuleDependencies{LLM: llmClient})
prepared, err := pipeline.Prepare(effective.ResolvedPipeline, components.registries, pipeline.ModuleDependencies{LLM: sceneDescriptionLLM{}})
if err != nil {
t.Fatalf("Prepare() error = %v", err)
}
@@ -63,14 +60,6 @@ func TestProductionSceneDescriptionWorkflow(t *testing.T) {
if output.Manifest.ValidationStatus != "approved" || len(output.Rejected) != 0 || len(output.NormalizeOutputs) != 1 {
t.Fatalf("run output = %#v, want one approved normalized artifact", output)
}
wantProfiles := []artifacts.LLMProfileManifest{{
ID: "scene-description-profile",
Provider: "promptkit",
Model: "deterministic",
}}
if !reflect.DeepEqual(output.Manifest.LLMProfiles, wantProfiles) {
t.Fatalf("manifest LLM profiles = %#v, want %#v", output.Manifest.LLMProfiles, wantProfiles)
}
normalizedOutput := output.NormalizeOutputs[0]
if normalizedOutput.NormalizerKey != scenenormalize.Key || normalizedOutput.Artifact.Kind != dnd.SceneDescriptionListKind || normalizedOutput.Artifact.Schema.ID != scenecodec.SchemaID || normalizedOutput.Artifact.Schema.Name != scenecodec.SchemaName || normalizedOutput.Artifact.Schema.Version != scenecodec.SchemaVersion {
t.Fatalf("normalized output = %#v, want registered durable scene-description schema", normalizedOutput)
@@ -96,12 +85,9 @@ func TestProductionSceneDescriptionWorkflow(t *testing.T) {
}
}
type sceneDescriptionLLM struct {
mu sync.Mutex
profile *artifacts.LLMProfileManifest
}
type sceneDescriptionLLM struct{}
func (client *sceneDescriptionLLM) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
func (sceneDescriptionLLM) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
if err := ctx.Err(); err != nil {
return contracts.StructuredCompletionResponse{}, err
}
@@ -121,27 +107,5 @@ func (client *sceneDescriptionLLM) CompleteStructured(ctx context.Context, req c
if err := json.Unmarshal([]byte(content), out); err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("populate structured response: %w", err)
}
profile := artifacts.LLMProfileManifest{
ID: req.ProfileID,
Provider: "promptkit",
Model: "deterministic",
}
client.mu.Lock()
client.profile = &profile
client.mu.Unlock()
return contracts.StructuredCompletionResponse{
Content: []byte(content),
Provider: profile.Provider,
Model: profile.Model,
ProfileID: profile.ID,
}, nil
}
func (client *sceneDescriptionLLM) LLMProfileManifests() []artifacts.LLMProfileManifest {
client.mu.Lock()
defer client.mu.Unlock()
if client.profile == nil {
return nil
}
return []artifacts.LLMProfileManifest{*client.profile}
return contracts.StructuredCompletionResponse{Content: []byte(content), Provider: "test", Model: "deterministic", ProfileID: req.ProfileID}, nil
}

92
internal/cli/example_contract_test.go
View File

@@ -15,10 +15,6 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
locationoccurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationoccurrences"
locationextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationregistry"
locationoccurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationoccurrences"
locationnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationregistry"
spellnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/spells"
"gitea.maximumdirect.net/eric/notarius/internal/modules/seriatim/input/transcript"
)
@@ -28,9 +24,6 @@ func TestMaintainedExamplesLoadResolveAndList(t *testing.T) {
for _, example := range maintainedExampleFiles(t) {
t.Run(example.name, func(t *testing.T) {
cfg := loadMaintainedExample(t, example.path)
if example.name == "complete" && (cfg.Concurrency.TotalLLM != 2 || cfg.Concurrency.StageWorkers["extract"] != 2) {
t.Fatalf("complete example concurrency = %#v, want explicit limits of 2", cfg.Concurrency)
}
raw, err := os.ReadFile(example.transcriptPath)
if err != nil {
t.Fatalf("read maintained transcript %q: %v", example.transcriptPath, err)
@@ -58,55 +51,21 @@ func TestMaintainedExamplesLoadResolveAndList(t *testing.T) {
t.Fatalf("materialize maintained example references for %q: %v", pipelineID, err)
}
if example.name == "complete" {
if got := exampleStepLaneIDs(materialized); strings.Join(got, "|") != "describe-session:item-registry,location-registry,npc-registry,scene-descriptions|extract-events:combat-turns,item-occurrences,location-occurrences,npc-occurrences,spells|track-enemies:enemy-events" {
t.Fatalf("complete example steps and lanes = %v, want the documented D&D extractor composition", got)
}
locationLane := referenceContractLane(t, materialized, "location-registry")
if locationLane.ArtifactKind != dnd.LocationRegistryKind || locationLane.Extract.Module != locationextract.Key || locationLane.Extract.Retries != 2 || locationLane.Merge.Module != pipeline.DefaultMergeModule || locationLane.Normalize.Module != locationnormalize.Key || locationLane.Normalize.Retries != 2 {
t.Fatalf("location lane = %#v, want typed registry composition", locationLane)
}
occurrenceLane := referenceContractLane(t, materialized, "location-occurrences")
if occurrenceLane.ArtifactKind != dnd.LocationOccurrenceListKind || occurrenceLane.Extract.Module != locationoccurrenceextract.Key || occurrenceLane.Extract.Retries != 2 || occurrenceLane.Merge.Module != pipeline.DefaultMergeModule || occurrenceLane.Normalize.Module != locationoccurrencenormalize.Key {
t.Fatalf("location occurrence lane = %#v, want typed occurrence composition", occurrenceLane)
}
for _, target := range []pipeline.ResolvedReferenceTarget{occurrenceLane.ExtractReferences, occurrenceLane.NormalizeReferences} {
binding, found := generatedReferenceBinding(target.Bindings, "location_registry")
if !found || binding.Artifact.Step != "describe-session" || binding.Artifact.Lane != "location-registry" {
t.Fatalf("location occurrence %s reference = %#v, want generated location registry", target.Stage, binding)
}
}
for _, slot := range []string{"party", "glossary"} {
if len(occurrenceLane.ExtractReferences.ReferenceSet.Slots[slot].Items) != 1 {
t.Fatalf("location occurrence extractor %s reference was not materialized: %#v", slot, occurrenceLane.ExtractReferences)
}
if _, found := occurrenceLane.NormalizeReferences.ReferenceSet.Slots[slot]; found {
t.Fatalf("location occurrence normalizer unexpectedly consumes %s: %#v", slot, occurrenceLane.NormalizeReferences)
}
if got := exampleStepLaneIDs(materialized); strings.Join(got, "|") != "describe-session:item-events,npcs,scene-descriptions|extract-events:combat-turns,npc-interactions,spells" {
t.Fatalf("complete example steps and lanes = %v, want every D&D extractor in the documented two-step composition", got)
}
spellLane := referenceContractLane(t, materialized, "spells")
if len(spellLane.ExtractReferences.ReferenceSet.Slots["spell_catalog"].Items) != 1 ||
len(spellLane.NormalizeReferences.ReferenceSet.Slots["spell_catalog"].Items) != 1 {
t.Fatalf("complete example spell catalog reference was not materialized: %#v", spellLane)
}
itemOccurrenceLane := referenceContractLane(t, materialized, "item-occurrences")
for _, references := range []pipeline.ResolvedReferenceTarget{itemOccurrenceLane.ExtractReferences, itemOccurrenceLane.NormalizeReferences} {
if _, found := references.ReferenceSet.Slots["npc_registry"]; found {
t.Fatalf("item occurrence lane unexpectedly depends on generated NPCs: %#v", itemOccurrenceLane)
itemEventLane := referenceContractLane(t, materialized, "item-events")
for _, references := range []pipeline.ResolvedReferenceTarget{itemEventLane.ExtractReferences, itemEventLane.NormalizeReferences} {
if _, found := references.ReferenceSet.Slots["npcs"]; found {
t.Fatalf("item event lane unexpectedly depends on generated NPCs: %#v", itemEventLane)
}
if _, found := references.ReferenceSet.Slots["scene_descriptions"]; found {
t.Fatalf("item occurrence lane unexpectedly depends on generated scene descriptions: %#v", itemOccurrenceLane)
}
}
enemyEventLane := referenceContractLane(t, materialized, "enemy-events")
for slot, want := range map[string]struct{ step, lane string }{
"npc_registry": {step: "describe-session", lane: "npc-registry"},
"scene_descriptions": {step: "describe-session", lane: "scene-descriptions"},
"combat_turns": {step: "extract-events", lane: "combat-turns"},
"npc_occurrences": {step: "extract-events", lane: "npc-occurrences"},
} {
binding, found := generatedReferenceBinding(enemyEventLane.ExtractReferences.Bindings, slot)
if !found || binding.Artifact.Step != want.step || binding.Artifact.Lane != want.lane {
t.Fatalf("enemy event %s reference = %#v, want generated %s/%s artifact", slot, binding, want.step, want.lane)
t.Fatalf("item event lane unexpectedly depends on generated scene descriptions: %#v", itemEventLane)
}
}
}
@@ -135,37 +94,6 @@ func TestMaintainedConfigurationExampleSet(t *testing.T) {
if got := strings.Join(names, ","); got != "dnd-complete.config.yml,dnd-minimal.config.yml" {
t.Fatalf("maintained configuration examples = %q, want only the minimal and complete D&D examples", got)
}
profileEntries, err := os.ReadDir(repositoryPath("examples", "profiles"))
if err != nil {
t.Fatal(err)
}
names = names[:0]
for _, entry := range profileEntries {
if !entry.IsDir() && strings.HasSuffix(entry.Name(), ".yml") {
names = append(names, entry.Name())
}
}
sort.Strings(names)
if got := strings.Join(names, ","); got != "dnd-extraction.yml" {
t.Fatalf("maintained operator profiles = %q, want dnd-extraction.yml", got)
}
}
func TestMaintainedExamplesValidateEffectiveProfilesOffline(t *testing.T) {
t.Chdir(repositoryPath())
t.Setenv("OPENROUTER_API_KEY", "")
for _, example := range maintainedExampleFiles(t) {
t.Run(example.name, func(t *testing.T) {
var stdout, stderr strings.Builder
code := RunWithOptions([]string{
"config", "validate", "--config", example.path, "--pipeline", "dnd-session",
}, &stdout, &stderr, Options{})
if code != 0 || stderr.Len() != 0 || !strings.Contains(stdout.String(), `valid for pipeline "dnd-session"`) {
t.Fatalf("code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
}
})
}
}
func exampleStepLaneIDs(resolved pipeline.ResolvedPipeline) []string {
@@ -283,12 +211,6 @@ func TestMaintainedMalformedInputOnlyRecordsDebugFailureWhenRequested(t *testing
if report.Succeeded || report.PipelineID != "dnd-session" {
t.Fatalf("failure report = %#v, want failed dnd-session report", report)
}
invocation := readProductionJSON[debugbundle.Invocation](t, filepath.Join(bundle, "summary", "invocation.json"))
manifest := readProductionJSON[artifacts.RunManifest](t, filepath.Join(bundle, "summary", "run-manifest.json"))
manifestSession, found := manifest.Metadata["session_id"]
if invocation.SessionID == "" || !found || manifestSession != invocation.SessionID {
t.Fatalf("failed run sessions: invocation=%q manifest=%#v metadata=%#v", invocation.SessionID, manifestSession, manifest.Metadata)
}
})
}
}

Some files were not shown because too many files have changed in this diff Show More