44 KiB
Configuration
This is the canonical reference for Notarius configuration. Configuration files are YAML; the main file must declare version 5. They select pipelines and their modules; the CLI reference owns invocation syntax, and Operations owns run-state procedures.
Configuration Discovery And Precedence
Commands that load configuration choose a file in this order:
- a non-empty --config CLI value;
- a non-empty NOTARIUS_CONFIG environment value;
notarius.yml, thennotarius.yamlin the working directory;- the user configuration directory; then
- the Unix system configuration directories.
The user search checks <user-config>/notarius/ for notarius.yml,
notarius.yaml, config.yml, config.yaml, main.yml, and main.yaml, in
that order, then <user-config>/notarius.yml and notarius.yaml. The system
search uses the same groups under /usr/local/etc/notarius/ and /etc/notarius/,
then /etc/notarius.yml and /etc/notarius.yaml. Generic filenames in the
working directory are not candidates. Home-directory search is not enabled.
Discovery selects one main file; it does not layer all candidates. A missing
candidate advances the search, but an explicitly selected missing file, access
error, or invalid selected file fails without fallback. An exhausted search
fails. Use an explicit --config for services and subprocesses that need a
fixed selection independent of their working directory.
For configuration values, precedence is:
- built-in defaults;
- composed YAML sources, including imports;
- the selected ConfigKit overlay and inheritance;
- typed decoding and explicitly supplied configuration-valued run flags; and
- Notarius resolution and validation.
--config-overlay selects a ConfigKit overlay from overlays/<name>.yml
beneath the selected configuration root. Empty and default select no overlay.
profiles/<name>.yml is not a fallback location, and --config-profile is no
longer accepted. Configuration overlays are distinct from PromptKit LLM profiles selected by
llm_profile or --llm-profile. The retired operational environment variables
have no effect; NOTARIUS_CONFIG remains a source-discovery input.
Maintained Examples
- Minimal D&D configuration is a single-lane Seriatim-to-spell pipeline.
- Complete D&D configuration uses ordered steps, all implemented D&D lanes, generated references, state settings, bounded LLM concurrency, and the maintained LLM profile and imports its pipeline from a fragment, which imports its first step.
The complete fragment also defines dnd-session-development, which inherits
the complete pipeline and profile while setting
structured_output_repair_attempts: 0. Select it with:
notarius run dnd-session-development \
--config /path/to/dnd-complete.config.yml \
--input /path/to/transcript.json
See the CLI reference for the full invocation contract. This
variant disables PromptKit structural repairs without changing configured producer
retry budgets. When using another profile, operators can instead select
dnd-session and set its llm_profile to that profile.
Use these complete files as starting points rather than combining the illustrative fragments in this reference.
File Shape And Defaults
Unknown fields, duplicate mapping keys, empty identifiers, and identifiers that become duplicates after trimming whitespace are rejected. Every top-level field other than version is optional.
| Field | Type | Default | Rules |
|---|---|---|---|
| version | integer or quoted string | none | Required; must be 5. Maintained files use version: 5. |
| promptkit | object | none | Profile source and optional local-backend 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. |
| cache | object | see below | Chunk-plan and checkpoint settings. |
| debug | object | see below | Debug-bundle root only; it does not enable capture. |
Built-in defaults are:
| Field | Default |
|---|---|
| concurrency.total_llm | 16 |
| concurrency.stage_workers.extract | Effective total_llm |
| output.directory | ./notarius-output |
| cache.chunk_plans.mode | auto |
| cache.chunk_plans.directory | Empty, selecting the per-user chunk-plan root |
| cache.checkpoints.enabled | false |
| cache.checkpoints.directory | Empty, selecting the per-user checkpoint root |
| debug.directory | ./notarius-debug |
An empty cache directory in YAML deliberately selects the corresponding per-user root. An explicit empty output or debug directory is invalid. Selecting a chunk-plan or checkpoint directory does not configure filesystem access policy. Cache permissions come from deployment provisioning, process umask, setgid inheritance, and default ACLs; see Operations.
Every nonempty relative configured destination or reference path resolves from
the canonical directory of the file that supplies its surviving declaration.
This includes imported fragments, selected configuration overlays, and values
copied through inheritance: the copied value keeps its original declaring
file. A child-supplied replacement resolves from the child's declaring file.
Built-in relative destinations use the selected main configuration file's
directory; explicit --output-dir and --debug-dir values use the invocation
working directory. Absolute values remain unchanged.
Use source-root config controls for imports and collection declarations. For
example, an essential fragment should explicitly be required:
config:
imports:
- path: pipelines/session.yml
required: true
Imports are optional by default. ConfigKit supports paths, lists, directories,
globs, exclusions, recursive selection, destinations, and sequence-item placement;
its native input-root rules apply. Imported fragments need not declare a version.
The complete example places a mapping fragment at a step-list destination. Nested
application data named config is ordinary data, not a control block.
When migrating application files, rename genuine root configkit control
blocks to config in the main file and fragments. This is not a compatibility
alias: configkit is ordinary data under the new reader. PromptKit profile
documents still use their separate older engine and retain configkit controls;
see PromptKit Profiles.
Sibling Inheritance
ConfigKit supports native extends composition in mappings and identified
sequence records. A directive
names exactly one immediate sibling in the same mapping; it is not a path or a
cross-scope lookup. Imports and the selected overlay are composed before
inheritance and typed decoding. Explicit CLI assignments follow decoding and
inheritance, before Notarius resolution and validation; they cannot repair an
earlier structural or decoding error. Every definition, including a parent and definitions not
selected for a run, remains subject to ordinary validation.
Child mappings recursively overlay parent mappings. Scalars and null replace
inherited values. Unidentified sequences replace as whole values; pipeline
steps are identified by id and use native upsert by default:
pipelines:
production:
input: {module: seriatim}
llm_profile: dnd-extraction
# Other complete pipeline settings and ordered steps...
development:
extends: production
structured_output_repair_attempts: 0
Pipeline names are siblings within pipelines; nested mappings such as named
artifact lanes also have their own sibling namespace. Distinct imported step IDs
combine in source order; duplicate peer IDs conflict. Across an overlay or
inheritance, upsert replaces a matching step as a complete record in place and
appends new IDs. It does not merge individual fields of a matching step. An
identified record can itself use native extends. Authors may select replace
or append with a config.sequences declaration at the relevant destination;
an explicit replacement with [] clears the list, while empty append or upsert
does not. Notarius then validates the resulting pipeline, including its nonempty
step requirement. Validator chains are not automatically identified. Authors
may declare identities for other lists when needed. CLI list assignment replaces
the complete decoded list.
For example, an overlay can opt into replacing a pipeline's steps:
config:
sequences:
- destination: [pipelines, production, steps]
mode: replace
pipelines:
production:
steps:
- id: extract
artifacts: {spells: {extract: {module: dnd/spells}}}
Inherited values count as explicit input for Notarius's existing
presence-sensitive rules: zero, false, and empty-list overrides stay explicit
instead of restoring a default. Null also replaces the inherited value, but
each field's ordinary type and validation rules still apply; null is not
universally valid. Omitting extends preserves a relationship supplied by a
lower-priority source, while extends: null cancels that relationship. It
does not independently clear other inherited fields.
extends is now a reserved key in every input mapping, including dynamic
module options and named maps. Existing ordinary data or entry names using that
key must be renamed along with any consumer that reads them. Configuration
overlays, pipeline inheritance, and PromptKit's native profile extends
inheritance are separate mechanisms.
PromptKit Profiles
The optional promptkit object selects one source of profile definitions and may register one conventional local OpenAI-compatible backend:
version: 5
promptkit:
profile_dir: ./profiles
# profile_file: ./profiles.yml
transient_retries: 2
local_backend:
endpoint: http://localhost:8000/v1
concurrency_limit: 2
| Field | Type | Rules |
|---|---|---|
| profile_dir | string | Non-empty directory containing profile files. |
| profile_file | string | Non-empty profile file. |
| transient_retries | integer | Non-negative additional built-in HTTP attempts for eligible transient provider failures; defaults to 2. Set 0 to disable these retries. |
| local_backend | object | Optional registration for the conventional PromptKit backend ID local. |
| local_backend.endpoint | string | Required when local_backend is present; absolute HTTP or HTTPS URL with a host. |
| local_backend.concurrency_limit | integer | Optional non-negative limit; defaults to 0. |
Set at most one of profile_dir and profile_file. Every nonempty relative
configured filesystem path is resolved from the canonical directory of the
file that supplies it. The complete example's
./llm-profiles/dnd-extraction.yml value therefore resolves beside that example.
Use absolute paths for services and containers when their deployment layout is
not configuration-relative.
An operator source is optional. PromptKit's maintained catalog, Notarius's
registered prompt and fallback assets, and the selected operator source are
assembled in that order; a configured local_backend contributes its backend
last. Later source groups recursively overlay earlier groups. Within one group,
inputs compose strictly; directory filenames do not provide priority. For a
requested profile ID, an operator definition can partially override the
embedded fallback while retaining unspecified fields. The maintained
dnd-extraction LLM profile
is a secret-free deployment artifact. It also demonstrates a derived
development profile that is not selected by the normal pipeline.
Operations 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 PromptKit file uses keyed mappings for profiles, backends, and prompts. A profile selects a backend by its exact ID:
profiles:
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. api_key_required is supported in profile files;
inspection reports PromptKit's effective metadata but does not check whether
the named environment variable is set. PromptKit owns the
pinned v0.12.0 format,
including native extends inheritance and field-presence rules. Notarius
selects source groups and passes definitions through PromptKit.
The PromptKit upstream boundary identifies the
supported package API, and Operations
describes the effective concurrency layers.
Native PromptKit Sources And Migration
The configured profile_file or profile_dir is a PromptKit configuration
source. It can contain profiles and backends, as well as prompt overlays.
PromptKit's catalog is followed by registered application prompt/fallback
assets and the selected operator source; Notarius's optional programmatic
local backend is applied last. Composition, recursion, exact-key inheritance,
and final-value validation are owned by PromptKit and ConfigKit. Explicit
null, zero, false, blank, and omission may have different meanings; an empty
map does not clear an inherited map.
When migrating external files from PromptKit before v0.12, place backend and
profile entries beneath their backends and profiles mappings, and place
prompt versions beneath prompts.<prompt-id>.v1. Remove embedded prompt
id/version fields. Replace base_profile with native extends. There is
no legacy-format parser or alias layer. Keep Notarius's version: 5 and
promptkit.profile_file/profile_dir settings unchanged.
Imports use native ConfigKit declarations relative to the file that declares them. A file-root layout keeps imported fragments outside a recursively selected profile directory, avoiding selection of the same definition both by directory discovery and by import:
# notarius.yml
version: 5
promptkit:
profile_file: ./promptkit/entry.yml
# promptkit/entry.yml
configkit:
imports:
- path: fragments/profiles.yml
profiles:
dnd-extraction-development:
extends: dnd-extraction
temperature: 0.2
PromptKit recursively discovers YAML files in a selected directory, and its inputs compose strictly; there is no filename-priority merger. Imports retain their declaring source roots, so relative message/content files resolve from the file that declares them. Use a separate file root for related imports when directory selection would otherwise load those files a second time.
The same unified document can declare a custom backend or select a catalog backend without redeclaring it:
backends:
private-compatible:
endpoint: https://llm.example.invalid/v1
api_key_env: PRIVATE_LLM_API_KEY
profiles:
private-summary:
backend: private-compatible
model: summary-model
catalog-summary:
backend: openrouter
model: openai/gpt-5.6-luna
To override the embedded D&D fallback for a configured local backend, supply only the changed fields. Explicitly clear inherited settings that do not apply to the local target:
profiles:
dnd-extraction:
backend: local
model: local-model
service_tier: null
The backend can be declared as backends.local in the operator source or
registered through the optional promptkit.local_backend convenience object.
The source precedence applies when
both contribute. Prompt overlays use the same recursive source composition; for
example, this changes one output setting while retaining the other embedded
definition fields:
prompts:
dnd.spells:
v1:
output:
repair_attempts: 0
Sequences such as prompt messages are replaced as a whole when overridden. Engine construction validates final effective prompt definitions and captures message files and static templates. Request preparation loads response schemas and resolves request variables and input artifacts. Profile preflight needs no transcript, credential value, or provider call, but can read prompt-content files.
notarius config validate --pipeline <id> resolves the selected pipeline and
inspects every explicit effective profile without contacting a provider or
requiring credential values. It rejects absent, malformed, or incompatible
profiles before a run prepares modules. Credential availability is checked only
when a generation is prepared.
Version 5 Migration
Version 3 and version 4 files are rejected and are not rewritten at load time.
Use version: 5, rename the former scriptorium section to promptkit, and
convert every module binding to an object containing module. Convert every
external reference to {path: ...} and move any lane-level references to the
corresponding extraction binding. Put durable operational values in YAML or
use the documented explicit run flags; the former field-level environment
variables are not read.
Concurrency, Output, Cache, And Debug
concurrency:
total_llm: 2
stage_workers:
extract: 2
output:
directory: ./notarius-output
cache:
chunk_plans:
mode: auto
directory: ./notarius-cache/chunk-plans
checkpoints:
enabled: true
directory: ./notarius-cache/checkpoints
debug:
directory: ./notarius-debug
concurrency.total_llm must be greater than zero. The only supported concurrency.stage_workers key is extract; its value must be from 1 through total_llm. When omitted, it is recalculated from the effective total_llm after imports, overlay selection, and explicit ConfigKit overrides.
cache.chunk_plans.mode accepts auto, bypass, or refresh. cache.checkpoints.enabled is a boolean. The CLI can override the output directory and chunk-plan mode for one run; see CLI reference. Cache directory fields select only locations; Notarius has no cache permission field or operational environment override.
Pipelines
Each pipelines entry has a unique, non-empty ID and the following shape:
pipelines:
dnd-session:
llm_profile: dnd-extraction
input:
module: seriatim
chunk:
module: generic
output:
module: json
artifacts:
spells:
extract:
module: dnd/spells
merge:
module: appendorder
normalize:
module: dnd/spells
| Field | Type | Default | Rules |
|---|---|---|---|
| llm_profile | string | none | Optional non-empty default PromptKit profile ID for selected LLM-backed bindings and validators. An explicitly present blank value is invalid. |
| structured_output_repair_attempts | integer | prompt-owned (1 in maintained production prompts) | Optional structural-repair limit from 0 through 3 for selected LLM-backed bindings and validators. Omission leaves the prompt's declared policy in control; explicit 0 disables structural repair at that scope. |
| validation_policy | object | see below | Optional terminal policy defaults for producer validation. Its fields inherit independently into chunk, extract, merge, and normalize bindings. |
| input | module binding | none | Required. |
| chunk | module binding | generic | Optional. |
| output | module binding | json | Optional. |
| artifacts | map | none | Compact single-step lane map. |
| steps | list | none | Ordered lane definitions. Mutually exclusive with artifacts. |
| references | map | none | External reference defaults for eligible targets. |
Use either artifacts or steps. The compact artifacts form is an implicit single step. An explicit steps list must be non-empty; every step needs a unique non-empty id, an artifacts map, and may have references. A lane ID must not appear more than once in a pipeline, including across explicit steps.
For each selected LLM-backed binding or validator, profile selection occurs
after module, validator, and --only lane selection. It uses the
run-level --llm-profile value first, then the binding's llm_profile,
then the pipeline's llm_profile, and finally the PromptKit default.
Deterministic bindings do not receive these defaults or run overrides.
Structural output repair is resolved after module, validator, and --only lane
selection. An object's structured_output_repair_attempts value takes
precedence over the pipeline value; otherwise, an LLM-backed binding or
validator inherits the pipeline value. If both are omitted, PromptKit uses the
prompt's declared repair policy. The value must be an integer from 0 through 3;
explicit null and non-integer values are invalid. An explicit value on a
deterministic binding or validator is invalid, while a pipeline value simply
does not apply to deterministic selections.
validation_policy controls terminal disposition for one complete producer
attempt and validator chain. It may appear on a pipeline or a chunk,
extract, merge, or normalize module binding; input, output, and
validator bindings reject it. Every field is optional and resolves in binding,
pipeline, then application-default order:
| Field | Values | Default |
|---|---|---|
| producer_structural_failure | fail_run, reject_output | fail_run |
| semantic_rejection | fail_run, reject_output | fail_run |
| validator_failure | warn_continue, fail_run | warn_continue |
The policy object and its fields must be non-null, and unknown fields are rejected. A deterministic producer may not explicitly set producer_structural_failure on its binding, although a pipeline-level default remains valid for pipelines that include LLM-backed producers.
After the producer binding's retry budget is exhausted, an invalid structured
response uses producer_structural_failure. One or more semantic validator
rejections use semantic_rejection; rejection takes precedence over an
exhausted validator failure or skip. With no rejection, an exhausted validator
failure or skip uses validator_failure. reject_output records the
terminal rejection without advancing that candidate. warn_continue is valid
only for validator execution failure: it advances a structurally valid,
otherwise unrejected result with incomplete-validation provenance and without
making it reusable checkpoint state.
A lane has these fields:
| Field | Type | Default | Rules |
|---|---|---|---|
| extract | module binding | none | Required. |
| merge | module binding | appendorder | Optional. |
| normalize | module binding | noop | Optional. |
| references | map | none | Not supported at lane scope; place references on the eligible binding. |
| validators | list | none | Non-empty lane-level lists are rejected. Set validator overrides on a binding instead. |
Lane-level references are not supported. Put a lane extraction reference under extract.references.
Module Bindings And Validators
Every module and validator binding uses an object, even when it has no fields beyond its module key:
input:
module: seriatim
Use an object for fields:
extract:
module: dnd/spells
llm_profile: dnd-extraction
retries: 2
references:
spell_catalog:
path: ./dnd-spell-catalog.json
| Binding field | Type | Default | Rules |
|---|---|---|---|
| module | string | none | Required for an object binding. Must be a registered compatible key. |
| llm_profile | string | none | Optional non-empty PromptKit profile ID for an LLM-backed binding. It overrides the pipeline default unless the run supplies --llm-profile. |
| structured_output_repair_attempts | integer | pipeline or prompt-owned (1 in maintained production prompts) | Optional structural-repair limit from 0 through 3 for an LLM-backed binding. It overrides the pipeline value; explicit 0 disables structural repair. |
| validation_policy | object | pipeline or application defaults | Optional field-by-field terminal-policy override for a chunk, extract, merge, or normalize binding. |
| retries | integer | 0 | Non-negative additional complete producer attempts for chunk, extract, merge, and normalize bindings. This single budget covers operational errors, invalid structured output, module-requested normalization retry, and semantic correction. |
| options | object | none | Must satisfy the selected module. |
| references | map | none | Valid only on chunk, extract, merge, and normalize bindings. |
| validators | list | production chain | Valid only on chunk, extract, merge, and normalize bindings. |
Omitting validators uses the registered chain. validators: [] selects an empty chain; a non-empty list replaces the chain in the listed order. Validator bindings accept only module, llm_profile, structured_output_repair_attempts, retries, and options. Their retries value is a non-negative additional validator-execution budget and is valid only when the selected validator is LLM-backed. A validator retry rechecks the same immutable candidate; it never regenerates the producer. They reject validation_policy, references, and nested validators. Deterministic validators reject explicit llm_profile and structured_output_repair_attempts. Deterministic module bindings also reject those explicit fields.
An LLM-backed chunk, extract, merge, or normalize producer with both a non-empty validator chain and positive retries must declare the supported single-response correction capability. Preparation rejects a configuration that could require semantic correction from a producer that cannot provide an exact prior response. A deterministic producer, or an LLM attempt that did not make a model call, cannot consume a semantic retry after rejection.
The json output module accepts optional include_chunk_map and evidence_context settings:
output:
module: json
options:
include_chunk_map: true
evidence_context:
enabled: true
window_units: 3
lanes:
- npc-registry
- spells
include_chunk_map is a boolean and defaults to false. It adds the accepted chunk map when one exists; its wire format is defined in the chunk-map contract.
Omitting evidence_context disables evidence publication. When present, it is an object with these strict fields:
| Field | Type | Rules |
|---|---|---|
| enabled | boolean | Required. false permits no other evidence fields. |
| lanes | array of strings | Required and non-empty when enabled. Each value is trimmed and must be unique; every value must name a configured pipeline lane. |
| window_units | non-negative integer | Optional when enabled; defaults to 3. Zero retains only directly cited units. |
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.
References And Ordered Handoffs
Reference maps bind named slots that the selected target declares. An external
reference is an object with path. Pipeline-level maps accept only external
paths; step-local and binding-local maps may also select a normalized artifact
from an earlier step:
steps:
- id: describe-session
artifacts:
npc-registry:
extract:
module: dnd/npc-registry
normalize:
module: dnd/npc-registry
- id: extract-events
references:
npc_registry:
artifact:
step: describe-session
lane: npc-registry
artifacts:
spells:
extract:
module: dnd/spells
normalize:
module: dnd/spells
An artifact selector contains only step and lane. The producer must be an earlier step and the selected artifact must be compatible with the consumer slot. A generated binding supplies one accepted normalized artifact; it does not name a file. A configured generated dependency remains required even when that consumer slot is otherwise optional.
Pipeline references are configuration defaults. A matching step-local or binding-local external path overrides a pipeline default. CLI reference bindings are then operational overrides of configured external paths; their pipeline, lane, and binding scopes and precedence are defined by the CLI reference. A CLI file reference cannot replace a configured generated artifact handoff. Required slots must be bound after configuration and CLI reference actions are applied. A YAML reference path resolves from the file that supplies its surviving declaration, including an imported fragment or selected overlay. CLI reference paths resolve relative to the process working directory.
D&D Reference Slots
The following slot names are accepted by the implemented D&D modules when the selected target declares them:
| Slot | Source and use |
|---|---|
| party | Optional text campaign context. This is the canonical party-roster spelling. |
| roster | Accepted compatibility alias for party. |
| 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. |
| 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, location occurrence, item occurrence, and enemy-event contracts.
| Slot | Accepted artifact kind | Media type | Maximum size | Required stage |
|---|---|---|---|---|
npc_registry |
dnd/npc-registry |
application/json |
1,048,576 bytes | extract and normalize |
scene_descriptions |
dnd/scene-description-list |
application/json |
1,048,576 bytes | extract only |
combat_turns |
dnd/combat-turn-list |
application/json |
1,048,576 bytes | extract only |
npc_occurrences |
dnd/npc-occurrence-list |
application/json |
1,048,576 bytes | extract only |
location_registry |
dnd/location-registry |
application/json |
1,048,576 bytes | location-occurrence extract and normalize |
item_registry |
dnd/item-registry |
application/json |
1,048,576 bytes | item-occurrence extract and normalize |
Scene descriptions accept party, players, and glossary, but not roster. NPC occurrences require npc_registry for both extraction and 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 shows the ordered generated bindings.
Production Module Keys
| Kind | Keys |
|---|---|
| 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 |
| 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 |
| 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. The complete example binds each
registry in an earlier step before its occurrence consumer.
The D&D artifact contracts define each emitted schema: spells, NPC registry, NPC occurrences, combat turns, item registry, item occurrences, scene descriptions, enemy events, location registry, and location occurrences.
Production Validator Keys And Default Chains
Available validator keys are:
| Family | Keys |
|---|---|
| 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 |
| 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 |
| Scene descriptions | extract/dnd/scene-descriptions/shape, extract/dnd/scene-descriptions/source_refs, extract/dnd/scene-descriptions/source_relatedness, extract/dnd/scene-descriptions/combat_semantics (LLM-backed, opt-in), normalize/dnd/scene-descriptions/invariants |
| Enemy events | extract/dnd/enemy-events/shape, extract/dnd/enemy-events/engagements, extract/dnd/enemy-events/source_refs, extract/dnd/enemy-events/source_relatedness, normalize/dnd/enemy-events/invariants |
| Location registry | extract/dnd/location-registry/shape, extract/dnd/location-registry/source_refs, extract/dnd/location-registry/source_relatedness, normalize/dnd/location-registry/identity |
| Location occurrences | extract/dnd/location-occurrences/shape, extract/dnd/location-occurrences/registry, extract/dnd/location-occurrences/source_refs, extract/dnd/location-occurrences/source_relatedness, normalize/dnd/location-occurrences/invariants |
extract/dnd/scene-descriptions/combat_semantics is not in a production default chain. To opt in, replace the scene extractor validator chain with the current ordered chain plus the semantic validator last, and set a positive producer retry budget if a rejection should request a corrected scene:
extract:
module: dnd/scene-descriptions
retries: 1
validators:
- module: generic/valid_json
- module: extract/dnd/scene-descriptions/shape
- module: extract/dnd/scene-descriptions/source_refs
- module: generic/valid_json_schema
- module: extract/dnd/scene-descriptions/source_relatedness
- module: extract/dnd/scene-descriptions/combat_semantics
retries: 1
An override replaces, rather than extends, the default chain. See Module Bindings And Validators for binding, profile, repair, retry, and failure-policy rules.
The validator retry shown above permits one additional execution against the same scene candidate when the LLM-backed validator itself fails; it is separate from both the extractor's producer retry and PromptKit structural repair.
When no override is configured, production D&D bindings use the following ordered chains. Each row lists extract then normalize; spell chains are the 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 |
| 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 |
| 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 required.
Validation
Validate a file and one pipeline before running it:
go run ./cmd/notarius config validate \
--config examples/dnd-minimal.config.yml \
--pipeline dnd-session
Configuration validation rejects invalid YAML, unsupported fields, invalid defaults or explicit CLI overrides, incompatible module keys, unknown options, invalid reference bindings, missing required reference slots, invalid validator overrides, and incompatible generated artifact handoffs. Use pipelines list to inspect configured IDs.
Inspection
Use config effective to write the selected composed configuration as deterministic, redacted YAML. Use config explain with a canonical JSON Pointer to inspect the effective or historical provenance for one path, including a value displaced by a selected overlay. Neither command resolves a pipeline, prepares modules, materializes references, or requires provider credentials.