Upgrade PromptKit and prepare version 0.7.1

AGENTS.md

@@ -1,2 +1,7 @@
 Please review `docs/development.md` for initial orientation in this repository
 and follow its task-specific reading guide.
+
+For every planning and implementation task, follow the
+[`Implementation Discipline`](docs/policy/architecture.md#implementation-discipline):
+keep machinery proportionate, do not invent restrictions, and do not elevate
+incidental implementation details into repository policy.

assets/dnd/combat-turns/schemas/dnd_combat_turns_llm.v1.json

@@ -16,7 +16,8 @@
             "type": "string"
           },
           "turn_kind": {
-            "type": "string"
+            "type": "string",
+            "enum": ["turn", "reaction", "legendary_action", "lair_action", "other"]
           },
           "source_refs": {
             "type": "array",

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

@@ -13,7 +13,10 @@
         "required": ["name", "kind", "source_refs"],
         "properties": {
           "name": {"type": "string"},
-          "kind": {"type": "string"},
+          "kind": {
+            "type": "string",
+            "enum": ["engaged", "killed", "fled", "captured", "incapacitated"]
+          },
           "source_refs": {
             "type": "array",
             "items": {

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

@@ -18,12 +18,20 @@ 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.
+Return both `from` and `to` for every occurrence. Use JSON `null`, not an empty
+string, whenever a holder does not apply. Follow this holder matrix exactly:
+
+| `kind` | required `from` | required `to` |
+| --- | --- | --- |
+| `discovered` | `null` | `null` |
+| `acquired` | `null` | `party` or the named party member gaining possession |
+| `lost` | `party` or the named party member losing possession | `null` |
+| `consumed` | `party` or the named party member consuming the item | `null` |
+| `transferred` | one named party member | a different named party member |
+
+Use `party` only for collective or unresolved party possession, never for
+either side of a transfer. Do not emit a transfer for a gift, sale, or payment
+outside the party.
 
 Ordinary non-depleting use is not an occurrence. Do not infer acquisition from a
 discovery, or discovery from an acquisition: emit both only when each is

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

@@ -13,7 +13,10 @@
         "required": ["name", "kind", "quantity", "from", "to", "source_refs"],
         "properties": {
           "name": {"type": "string"},
-          "kind": {"type": "string"},
+          "kind": {
+            "type": "string",
+            "enum": ["discovered", "acquired", "lost", "consumed", "transferred"]
+          },
           "quantity": {"type": ["integer", "null"]},
           "from": {"type": ["string", "null"]},
           "to": {"type": ["string", "null"]},

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

@@ -5,5 +5,5 @@ 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.
+Set `canonical_candidate_number` to the supplied candidate number whose label
+is the clearest established designation.

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

@@ -5,4 +5,5 @@ 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.
+Set `canonical_candidate_number` to the supplied candidate number whose label
+is the clearest established name.

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

@@ -16,7 +16,8 @@
             "type": "string"
           },
           "kind": {
-            "type": "string"
+            "type": "string",
+            "enum": ["mentioned", "noncombat_presence", "dialogue", "combat_ally", "combat_opponent", "other"]
           },
           "source_refs": {
             "type": "array",

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

@@ -3,7 +3,8 @@ 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
+Set `canonical_candidate_number` to the supplied candidate number whose label
+is the preferred canonical display name. Prefer a complete, stable proper name
 over an abbreviation. Prefer an unadorned proper name over that name plus a
 contextual class, role, title, or relationship descriptor unless the transcript
 establishes the descriptor as part of the person's name. A longer display name

assets/dnd/scene-descriptions/prompts/instructions.md

@@ -5,9 +5,7 @@ into multiple scenes or use facts that are not supported by it.
 Return one kind, one concise title, and one concise summary. Choose exactly one
 kind:
 
-- combat: active combat materially organizes the scene, including
-  initiative-like exchanges or sustained hostile action. Planning a fight or
-  discussing a completed fight is not combat by itself.
+- combat: a scene classified as combat under the shared combat policy.
 - narrative: current-session in-world play that is not principally active
   combat, a prior-session recap, or sustained out-of-character session
   discussion. This includes exploration, travel, dialogue, investigation,
@@ -20,15 +18,13 @@ kind:
   play.
 
 Narrative is the default for actual current-session gameplay that does not meet
-another definition. When the accepted chunk is mixed:
+another definition. When the accepted chunk has no substantive active combat:
 
-1. use combat when active combat is a substantive central activity, even with
-   brief setup, rules clarification, or immediate aftermath;
-2. otherwise use recap when recounting a previous session is the chunk's
+1. use recap when recounting a previous session is the chunk's
    primary table purpose;
-3. otherwise use meta when sustained out-of-character session discussion is
+2. otherwise use meta when sustained out-of-character session discussion is
    primary and in-world progression is no more than incidental; and
-4. use narrative for all remaining current-session in-world play.
+3. use narrative for all remaining current-session in-world play.
 
 Brief table talk, dice resolution, rules clarification, jokes, or
 administrative comments do not make a gameplay scene meta. A short recollection

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

@@ -27,6 +27,8 @@ messages:
     content_file: ./sharedassets/common-dnd-transcript-chunk.md
     cache_control:
       type: ephemeral
+  - role: user
+    content_file: ./sharedassets/common-dnd-scene-combat-policy.md
   - role: user
     content_file: ./instructions.md
     cache_control:

assets/dnd/scene-descriptions/schemas/dnd_scene_descriptions_llm.v1.json

@@ -6,7 +6,8 @@
   "required": ["kind", "title", "summary"],
   "properties": {
     "kind": {
-      "type": "string"
+      "type": "string",
+      "enum": ["combat", "narrative", "recap", "meta"]
     },
     "title": {
       "type": "string"

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

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

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

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

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

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

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

@@ -1,6 +1,8 @@
 Transcript units are the only evidence for extracted events and factual claims.
 Every reported factual claim must be supported by cited transcript units. Use
 integer `start_unit_id` and `end_unit_id` values from the transcript.
+Within each range, `start_unit_id` must identify the earlier transcript unit and
+`end_unit_id` the same or a later unit according to transcript order.
 
 When supporting evidence is non-contiguous, use multiple narrow ranges rather
 than a broad range that bridges unrelated conversation.

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

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

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

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

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

@@ -1,7 +1,9 @@
-Use only the positive integer `candidate_id` values supplied in the candidate material.
+Use only the positive integer `candidate_number` values supplied in the candidate material. Valid candidate numbers are exactly the inclusive `first` through `last` values declared in `candidate_number_range`; use the explicit number attached to each candidate.
 
-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.
+Transcript unit `id` values and evidence `start_unit_id` and `end_unit_id` values identify source positions. They are not candidate numbers and must never be used in `candidate_numbers` or `canonical_candidate_number`.
 
-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.
+Return a duplicate group only when the evidence supports that every selected candidate describes the same underlying entity. Each group must contain at least two distinct candidate numbers, and its `canonical_candidate_number` must be one of those numbers. A candidate may appear in at most one group.
 
-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.
+Omit uncertain matches and candidates that should remain distinct. Do not invent candidates or infer a number that is not explicitly supplied. An empty `duplicate_groups` array is valid.
+
+The response must conform exactly to the selected JSON schema. Return candidate numbers only: do not copy candidate names, evidence, transcript text, source identifiers, or source ranges into the response.

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

@@ -11,9 +11,9 @@
       "items": {
         "type": "object",
         "additionalProperties": false,
-        "required": ["candidate_ids", "canonical_candidate_id"],
+        "required": ["candidate_numbers", "canonical_candidate_number"],
         "properties": {
-          "candidate_ids": {
+          "candidate_numbers": {
             "type": "array",
             "minItems": 2,
             "items": {
@@ -21,7 +21,7 @@
               "minimum": 1
             }
           },
-          "canonical_candidate_id": {
+          "canonical_candidate_number": {
             "type": "integer",
             "minimum": 1
           }

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

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

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

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

docs/adr/0018-adopt-configkit.md

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

docs/cli.md

@@ -12,8 +12,8 @@ defined in [Operations](operations.md).
 notarius help
 notarius --version
 notarius run <pipeline-id> --input path/to/source.json [--json] [flags]
-notarius config validate [--config path/to/config.yml] [--pipeline pipeline-id] [--only lane-a,lane-b]
-notarius pipelines list [--config path/to/config.yml] [--json]
+notarius config validate [--config path/to/config.yml] [--config-profile name] [--pipeline pipeline-id] [--only lane-a,lane-b]
+notarius pipelines list [--config path/to/config.yml] [--config-profile name] [--json]
 ~~~
 
 Running Notarius without arguments, or with **help**, **--help**, or **-h**,
@@ -42,6 +42,7 @@ pipeline ID and **--input** are required.
 | Flag | Meaning |
 | --- | --- |
 | **--config path** | Use this configuration file. When omitted, configuration discovery applies; see [Configuration](config.md). |
+| **--config-profile name** | Select a ConfigKit configuration overlay. Empty and **default** select the composed base configuration. |
 | **--input path** | Source input file to process. Required. |
 | **--output-dir path** | Override the configured output root for this run. |
 | **--json** | Write the successful run-result receipt as JSON to standard output. |
@@ -55,8 +56,8 @@ pipeline ID and **--input** are required.
 | **--session-id id** | Override the generated prompt session identifier with a non-empty value for LLM-backed module calls. |
 | **--reasoning-effort value** | Replace the selected PromptKit profile's reasoning effort for every LLM-backed call in this run. The value must be non-empty and the flag may be specified only once. |
 | **--clear-reasoning-effort** | Clear reasoning effort inherited from the selected PromptKit profile for every LLM-backed call in this run. |
-| **--reference selector=path** | Add or replace a file reference binding. Repeatable. |
-| **--without-reference selector** | Remove a configured optional reference binding. Repeatable. |
+| **--reference selector=path** | Add or replace external file reference bindings at pipeline, lane, chunk, or binding scope. Repeatable. |
+| **--without-reference selector** | Remove matching configured external reference bindings. Repeatable. |
 
 **--chunk_cache** accepts only **auto**, **bypass**, or **refresh**.
 **--debug-dir**, **--output-dir**, **--session-id**, and
@@ -81,23 +82,49 @@ guidance.
 
 ### Reference selectors
 
-Use **--reference** only for a reference slot declared by the selected
-configured target. The accepted selector forms are:
+Use **--reference** only for reference slots declared by the selected
+configured targets. Qualification narrows the scope of an override:
 
 | Form | Target |
 | --- | --- |
-| slot=path | The unique selected target that declares slot. |
+| slot=path | Every selected target that declares slot. |
 | chunk.slot=path | The chunker. |
-| merge.slot=path | The unique selected merger that declares slot. |
-| lane.slot=path | The unique extractor, merger, or normalizer in lane that declares slot. |
+| lane.slot=path | Every extractor, merger, or normalizer in lane that declares slot. |
 | lane.extract.slot=path | The extractor in lane. |
 | lane.merge.slot=path | The merger in lane. |
 | lane.normalize.slot=path | The normalizer in lane. |
 
-**--without-reference** uses the same selector forms without =path. Slot
-names, requiredness, and configured bindings are part of the
+Pipeline- and lane-scoped selectors are expected to match multiple targets and
+fail if they match none. A stage-specific selector fails when its lane is not
+selected or its target does not declare the slot. There is no stage-wide
+`merge.slot` shorthand; name the lane when targeting a merger.
+
+CLI bindings override configured external paths. For overlapping CLI
+selectors, a binding-specific or chunk selector overrides a lane selector, and
+a lane selector overrides a pipeline selector. The last occurrence wins at
+equal scope. Binding and unbinding the same concrete target at equal scope is
+an error; a narrower bind or unbind may create an intentional exception to a
+broader action.
+
+**--without-reference** uses the same selector forms without `=path` and
+removes external bindings only. Neither flag replaces or removes a generated
+artifact handoff; an external/generated collision is a resolution error.
+Required slots are checked after all effective changes. CLI reference paths
+are resolved relative to the process working directory, so subprocess and
+service callers should use absolute paths. Slot names, accepted media types,
+size limits, requiredness, and configured generated bindings are part of the
 [configuration contract](config.md).
 
+For example, one shared campaign reference can reach every compatible target,
+with an optional lane-specific exception:
+
+~~~
+notarius run dnd-session \
+  --input /data/transcript.json \
+  --reference party=/data/references/party.txt \
+  --reference npc-registry.party=/data/references/npc-party-context.txt
+~~~
+
 ### Run output
 
 Without **--json**, standard output contains the completed pipeline ID, counts
@@ -128,10 +155,10 @@ OPENROUTER_API_KEY=your-api-key \
 ## config validate
 
 ~~~
-notarius config validate [--config path/to/config.yml] [--pipeline pipeline-id] [--only lane-a,lane-b]
+notarius config validate [--config path/to/config.yml] [--config-profile name] [--pipeline pipeline-id] [--only lane-a,lane-b]
 ~~~
 
-This command loads and validates a configuration. With **--pipeline**, it also
+This command loads and validates the selected composed configuration. With **--pipeline**, it also
 resolves that pipeline against the production module catalog. **--only** selects
 lanes during that resolution and requires **--pipeline**.
 
@@ -154,10 +181,32 @@ OPENROUTER_API_KEY=validation-placeholder \
 The placeholder in the second command is sufficient only for offline
 validation; it cannot run a provider-backed pipeline.
 
+## config effective
+
+~~~
+notarius config effective [--config path/to/config.yml] [--config-profile name]
+~~~
+
+This command writes the selected composed configuration as deterministic,
+redacted YAML. Standard output contains only that YAML: it does not validate a
+pipeline, prepare modules, materialize references, or contact a provider.
+
+## config explain
+
+~~~
+notarius config explain [--config path/to/config.yml] [--config-profile name] <json-pointer>
+~~~
+
+This command writes ConfigKit's redacted, human-readable explanation for one
+canonical JSON Pointer. Supply `""` explicitly to explain the root. A malformed
+pointer is a syntax error; a well-formed unknown path is a command failure.
+The explanation can describe a value displaced by a selected profile. Standard
+output contains only the explanation.
+
 ## pipelines list
 
 ~~~
-notarius pipelines list [--config path/to/config.yml] [--json]
+notarius pipelines list [--config path/to/config.yml] [--config-profile name] [--json]
 ~~~
 
 This command lists configured pipeline IDs in sorted order. By default, it
@@ -174,6 +223,10 @@ go run ./cmd/notarius pipelines list \
 Successful commands write their primary result to standard output. Warnings and
 errors are written to standard error.
 
+Configuration load errors include ConfigKit's field diagnostics and source
+coordinates, followed by a source-ID legend identifying the acquired files or
+source labels. This includes imported files and the selected configuration profile.
+
 For **run --json**, actionable process warnings remain on standard error and standard output is a
 machine-readable success result only. Syntax and runtime diagnostics remain on
 standard error. Parse the result only after the process exits with status 0.
@@ -185,6 +238,6 @@ standard error. Parse the result only after the process exits with status 0.
 | 2 | The command or flag syntax was invalid, including unknown commands, missing required arguments, invalid flag values, or invalid flag combinations. |
 
 The root help spellings are the supported help path. Invoking **--help** on
-**run**, **config validate**, or **pipelines list** is handled by the flag
+**run**, a **config** subcommand, or **pipelines list** is handled by the flag
 parser as a usage error: it writes an error to standard error and exits with
 status 2.

docs/config.md

@@ -1,7 +1,7 @@
 # Configuration
 
 This is the canonical reference for Notarius configuration. Configuration files
-are YAML and must declare version 4. They select pipelines and their modules;
+are YAML and must declare version 5. They select pipelines and their modules;
 the [CLI reference](cli.md) owns invocation syntax, and
 [Operations](operations.md) owns run-state procedures.
 
@@ -19,12 +19,15 @@ The command fails if none of these paths provides a configuration file.
 For configuration values, precedence is:
 
 1. built-in defaults;
-2. the selected YAML file;
-3. supported operational environment variables; and
-4. the CLI run overrides that apply to a command.
+2. composed YAML sources, including imports;
+3. the selected ConfigKit profile; and
+4. explicitly supplied configuration-valued run flags.
 
-Environment variables do not provide a second configuration schema. They only
-override the fields listed below.
+`--config-profile` selects a ConfigKit overlay from `profiles/<name>.yml`
+beneath the selected configuration root. Empty and `default` select no overlay.
+Configuration profiles 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
 
@@ -33,7 +36,8 @@ override the fields listed below.
 - [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).
+  [LLM profile](../examples/llm-profiles/dnd-extraction.yml) and imports its
+  pipeline from [a fragment](../examples/pipelines/dnd-session.yml).
 
 Use these complete files as starting points rather than combining the
 illustrative fragments in this reference.
@@ -46,7 +50,7 @@ other than **version** is optional.
 
 | Field | Type | Default | Rules |
 | --- | --- | --- | --- |
-| **version** | integer | none | Required; must be 4. |
+| **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. |
@@ -69,6 +73,22 @@ Built-in defaults are:
 
 An empty cache directory in YAML deliberately selects the corresponding
 per-user root. An explicit empty output or debug directory is invalid.
+Selecting a chunk-plan or checkpoint directory does not configure filesystem
+access policy. Cache permissions come from deployment provisioning, process
+umask, setgid inheritance, and default ACLs; see [Operations](operations.md#cache-provisioning).
+
+Every nonempty relative configured destination or reference path resolves from
+the canonical directory of the file that supplies its surviving declaration.
+This includes imported fragments and selected configuration profiles. Built-in
+relative destinations use the selected main configuration file's directory;
+explicit `--output-dir` and `--debug-dir` values use the invocation working
+directory. Absolute values remain unchanged.
+
+The root file can use ConfigKit imports to compose disjoint definitions. Imports
+and selected profiles remain under the configuration root; they do not merge or
+append a pipeline's `steps` sequence. A profile replaces sequences as defined
+by ConfigKit, so changing an individual ordered binding requires supplying the
+whole replacement sequence.
 
 ## PromptKit Profiles
 
@@ -76,7 +96,7 @@ The optional **promptkit** object selects one source of profile definitions and
 may register one conventional local OpenAI-compatible backend:
 
 ~~~yaml
-version: 4
+version: 5
 
 promptkit:
   profile_dir: ./profiles
@@ -94,17 +114,18 @@ promptkit:
 | **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.
+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. 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)
+[`dnd-extraction` LLM profile](../examples/llm-profiles/dnd-extraction.yml)
 is a secret-free deployment artifact; production, development, and local
 deployments can each provide a complete definition with that same workload ID.
 Use workload-oriented IDs for new profiles instead of model names.
@@ -147,30 +168,15 @@ 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 5 Migration
 
-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.
-
-## Operational Environment Variables
-
-These variables are applied after YAML values:
-
-| Variable | Overrides | Rules |
-| --- | --- | --- |
-| **NOTARIUS_TOTAL_LLM_CONCURRENCY** | **concurrency.total_llm** | Integer. |
-| **NOTARIUS_STAGE_WORKERS_EXTRACT** | **concurrency.stage_workers.extract** | Integer. |
-| **NOTARIUS_OUTPUT_DIR** | **output.directory** | Non-empty path. |
-| **NOTARIUS_CACHE_CHUNK_PLANS_MODE** | **cache.chunk_plans.mode** | **auto**, **bypass**, or **refresh**. |
-| **NOTARIUS_CACHE_CHUNK_PLANS_DIR** | **cache.chunk_plans.directory** | Non-empty path. |
-| **NOTARIUS_CACHE_CHECKPOINTS_DIR** | **cache.checkpoints.directory** | Non-empty path. |
-| **NOTARIUS_DEBUG_DIR** | **debug.directory** | Non-empty path. |
-
-Integer values are trimmed then parsed as base-10 integers. Directory and
-output values reject NUL characters. **NOTARIUS_CONFIG** participates only in
-configuration discovery.
+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
 
@@ -195,11 +201,14 @@ 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 YAML and environment precedence.
+**total_llm** after imports, profile 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](cli.md#run).
+Cache directory fields select only locations; Notarius has no cache permission
+field or operational environment override.
 
 ## Pipelines
 
@@ -209,14 +218,20 @@ Each **pipelines** entry has a unique, non-empty ID and the following shape:
 pipelines:
   dnd-session:
     llm_profile: dnd-extraction
-    input: seriatim
-    chunk: generic
-    output: json
+    input:
+      module: seriatim
+    chunk:
+      module: generic
+    output:
+      module: json
     artifacts:
       spells:
-        extract: dnd/spells
-        merge: appendorder
-        normalize: dnd/spells
+        extract:
+          module: dnd/spells
+        merge:
+          module: appendorder
+        normalize:
+          module: dnd/spells
 ~~~
 
 | Field | Type | Default | Rules |
@@ -286,19 +301,20 @@ A lane has these fields:
 | **extract** | module binding | none | Required. |
 | **merge** | module binding | **appendorder** | Optional. |
 | **normalize** | module binding | **noop** | Optional. |
-| **references** | map | none | Supported compatibility alias for **extract.references**. |
+| **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. |
 
-The lane-level **references** alias remains accepted. When the alias and
-**extract.references** bind the same slot, **extract.references** wins. Use
-the binding-local form in new configurations.
+Lane-level **references** are not supported. Put a lane extraction reference
+under **extract.references**.
 
 ## Module Bindings And Validators
 
-Use a module key directly when no other binding fields are needed:
+Every module and validator binding uses an object, even when it has no fields
+beyond its module key:
 
 ~~~yaml
-input: seriatim
+input:
+  module: seriatim
 ~~~
 
 Use an object for fields:
@@ -309,7 +325,8 @@ extract:
   llm_profile: dnd-extraction
   retries: 2
   references:
-    spell_catalog: ./dnd-spell-catalog.json
+    spell_catalog:
+      path: ./dnd-spell-catalog.json
 ~~~
 
 | Binding field | Type | Default | Rules |
@@ -381,18 +398,20 @@ When enabled, it publishes the selected source-unit excerpt defined by the
 
 ## References And Ordered Handoffs
 
-Reference maps bind named slots that the selected target declares. A scalar is
-an external path. Pipeline-level maps accept only external paths; step-local
-and binding-local maps may also select a normalized artifact from an earlier
-step:
+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:
 
 ~~~yaml
 steps:
   - id: describe-session
     artifacts:
       npc-registry:
-        extract: dnd/npc-registry
-        normalize: dnd/npc-registry
+        extract:
+          module: dnd/npc-registry
+        normalize:
+          module: dnd/npc-registry
   - id: extract-events
     references:
       npc_registry:
@@ -401,8 +420,10 @@ steps:
           lane: npc-registry
     artifacts:
       spells:
-        extract: dnd/spells
-        normalize: dnd/spells
+        extract:
+          module: dnd/spells
+        normalize:
+          module: dnd/spells
 ~~~
 
 An artifact selector contains only **step** and **lane**. The producer must be
@@ -411,10 +432,16 @@ 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 defaults. A matching step-local or binding-local
-external path overrides a pipeline default. Required slots must be bound after
-these configuration values and any CLI reference overrides are applied.
-Reference paths in YAML are resolved relative to the configuration file.
+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](cli.md#reference-selectors). A CLI file reference cannot
+replace a configured generated artifact handoff. Required slots must be bound
+after configuration and CLI reference actions are applied. A YAML reference
+path resolves from the file that supplies its surviving declaration, including
+an imported fragment or selected profile. CLI reference paths resolve relative
+to the process working directory.
 
 ### D&D Reference Slots
 
@@ -504,11 +531,33 @@ Available validator keys are:
 | Item occurrences | **extract/dnd/item-occurrences/shape**, **extract/dnd/item-occurrences/registry**, **extract/dnd/item-occurrences/source_refs**, **extract/dnd/item-occurrences/source_relatedness**, **normalize/dnd/item-occurrences/invariants** |
 | Item registry | **extract/dnd/item-registry/shape**, **extract/dnd/item-registry/source_refs**, **extract/dnd/item-registry/source_relatedness**, **normalize/dnd/item-registry/identity** |
 | NPC occurrences | **extract/dnd/npc-occurrences/shape**, **extract/dnd/npc-occurrences/registry**, **extract/dnd/npc-occurrences/source_refs**, **extract/dnd/npc-occurrences/source_relatedness**, **normalize/dnd/npc-occurrences/invariants** |
-| Scene descriptions | **extract/dnd/scene-descriptions/shape**, **extract/dnd/scene-descriptions/source_refs**, **extract/dnd/scene-descriptions/source_relatedness**, **normalize/dnd/scene-descriptions/invariants** |
+| Scene descriptions | **extract/dnd/scene-descriptions/shape**, **extract/dnd/scene-descriptions/source_refs**, **extract/dnd/scene-descriptions/source_relatedness**, **extract/dnd/scene-descriptions/combat_semantics** (LLM-backed, opt-in), **normalize/dnd/scene-descriptions/invariants** |
 | Enemy events | **extract/dnd/enemy-events/shape**, **extract/dnd/enemy-events/engagements**, **extract/dnd/enemy-events/source_refs**, **extract/dnd/enemy-events/source_relatedness**, **normalize/dnd/enemy-events/invariants** |
 | Location registry | **extract/dnd/location-registry/shape**, **extract/dnd/location-registry/source_refs**, **extract/dnd/location-registry/source_relatedness**, **normalize/dnd/location-registry/identity** |
 | Location occurrences | **extract/dnd/location-occurrences/shape**, **extract/dnd/location-occurrences/registry**, **extract/dnd/location-occurrences/source_refs**, **extract/dnd/location-occurrences/source_relatedness**, **normalize/dnd/location-occurrences/invariants** |
 
+`extract/dnd/scene-descriptions/combat_semantics` is not in a production default chain. To opt in, replace the scene extractor validator chain with the current ordered chain plus the semantic validator last, and set a positive producer retry budget if a rejection should request a corrected scene:
+
+~~~yaml
+extract:
+  module: dnd/scene-descriptions
+  retries: 1
+  validators:
+    - module: generic/valid_json
+    - module: extract/dnd/scene-descriptions/shape
+    - module: extract/dnd/scene-descriptions/source_refs
+    - module: generic/valid_json_schema
+    - module: extract/dnd/scene-descriptions/source_relatedness
+    - module: extract/dnd/scene-descriptions/combat_semantics
+      retries: 1
+~~~
+
+An override replaces, rather than extends, the default chain. See [Module Bindings And Validators](#module-bindings-and-validators) for binding, profile, repair, retry, and failure-policy rules.
+
+The validator retry shown above permits one additional execution against the
+same scene candidate when the LLM-backed validator itself fails; it is separate
+from both the extractor's producer retry and PromptKit structural repair.
+
 When no override is configured, production D&D bindings use the following
 ordered chains. Each row lists extract then normalize; spell chains are the
 same at both stages.
@@ -541,7 +590,16 @@ go run ./cmd/notarius config validate \
 ~~~
 
 Configuration validation rejects invalid YAML, unsupported fields, invalid
-defaults or environment overrides, incompatible module keys, unknown options,
+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](cli.md#pipelines-list) to inspect configured IDs.
+
+## Inspection
+
+Use [config effective](cli.md#config-effective) to write the selected composed
+configuration as deterministic, redacted YAML. Use
+[config explain](cli.md#config-explain) with a canonical JSON Pointer to inspect
+the effective or historical provenance for one path, including a value displaced
+by a selected profile. Neither command resolves a pipeline, prepares modules,
+materializes references, or requires provider credentials.

docs/consumers/dnd-pipeline.md

@@ -23,14 +23,14 @@ A deployment must provide its own PromptKit profile and campaign reference
 files. Use absolute paths for service and subprocess deployments. In
 particular, observe these different resolution rules:
 
-- reference paths in YAML are resolved relative to the Notarius configuration
-  file; and
-- `promptkit.profile_file` is resolved relative to the Notarius process working
-  directory.
+- reference and PromptKit profile paths in YAML are resolved relative to the
+  file that supplies their surviving declaration;
+- reference paths passed with `--reference` are resolved relative to the
+  Notarius process working directory.
 
 Do not copy the repository example's relative profile path into a deployment
-without also controlling that working directory. The complete path and profile
-rules are defined in [Configuration](../config.md).
+without preserving its configuration-relative layout. The complete path and
+profile rules are defined in [Configuration](../config.md).
 
 Preflight the deployed configuration before processing sessions and whenever
 it changes:
@@ -73,9 +73,21 @@ notarius run dnd-session \
   --config /absolute/path/to/notarius.yml \
   --input /absolute/path/to/transcripts/final.trimmed.json \
   --output-dir /absolute/path/to/notarius-output \
+  --reference party=/absolute/path/to/references/party.txt \
+  --reference players=/absolute/path/to/references/players.txt \
+  --reference glossary=/absolute/path/to/references/glossary.txt \
+  --reference spell_catalog=/absolute/path/to/references/spells.json \
   --json
 ```
 
+Each unqualified reference is pipeline-scoped: Notarius supplies it to every
+selected D&D target that declares the slot. A deployment may omit an optional
+reference it does not maintain, and may use the lane- or binding-qualified
+forms from the [CLI reference](../cli.md#reference-selectors) for an exceptional
+override. The registry, scene-description, combat-turn, and NPC-occurrence
+references declared between ordered steps in the complete configuration are
+generated artifacts. Do not pass those handoffs on the CLI.
+
 The caller should:
 
 - capture stdout and stderr separately;

docs/consumers/subprocess.md

@@ -15,9 +15,12 @@ configured lane inventory, and downstream acceptance checklist, see
 Optionally preflight a selected configuration and pipeline before work starts:
 
 ```sh
-notarius config validate --config /path/to/notarius.yml --pipeline pipeline-id
+notarius config validate --config /path/to/notarius.yml --config-profile production --pipeline pipeline-id
 ```
 
+Omit `--config-profile` when the composed base configuration is the intended
+selection; it is independent from any `--llm-profile` run override.
+
 Invoke the run with explicit paths and machine-readable output. Capture
 standard output and standard error separately; do not combine them before
 processing the result.
@@ -25,19 +28,43 @@ processing the result.
 ```sh
 notarius run pipeline-id \
   --config /path/to/notarius.yml \
+  --config-profile production \
   --input /path/to/source.json \
   --output-dir /path/to/output-root \
   --json
 ```
 
 Use absolute paths for supplied input, configuration, output-root, and
-reference files. 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. Pass each external reference as its own argument-vector pair;
+do not construct and invoke a shell command. An unqualified reference selector
+supplies that file to every compatible selected target. Lane and stage
+qualification are available for exceptional overrides, while generated
+same-run references remain part of configured pipeline composition. The
+[CLI reference](../cli.md#reference-selectors) owns the exact selector and
+precedence contract.
+
+The maintained D&D subprocess workflow uses this facility for campaign context:
+
+```sh
+notarius run dnd-session \
+  --config /absolute/path/to/notarius.yml \
+  --input /absolute/path/to/transcripts/final.trimmed.json \
+  --output-dir /absolute/path/to/notarius-output \
+  --reference party=/absolute/path/to/references/party.txt \
+  --reference players=/absolute/path/to/references/players.txt \
+  --reference glossary=/absolute/path/to/references/glossary.txt \
+  --reference spell_catalog=/absolute/path/to/references/spells.json \
+  --json
+```
+
+Only pass the external references available to and desired by the deployment.
+Notarius generates a stable prompt session for the resolved input module and
+exact input bytes; reference changes do not change it. Pass **--session-id**
+only when intentionally grouping different invocations under a different
+session. Supply credentials through Notarius's documented configuration and
+environment mechanisms, never as command-line arguments or generated
+secret-bearing configuration. In particular, a session identifier is
+provider-visible and is not a credential mechanism.
 
 Wait for the process before interpreting standard output. Only an exit status
 of 0 permits decoding the receipt. On a nonzero exit, retain standard error for

docs/integrations/pkg-configkit.md

@@ -0,0 +1,13 @@
+# ConfigKit Integration
+
+Notarius uses the public root package
+[`gitea.maximumdirect.net/eric/ConfigKit`](https://gitea.maximumdirect.net/eric/ConfigKit)
+at v0.3.0 for version 5 configuration acquisition, imports, profiles, explicit
+overrides, diagnostics, and safe inspection rendering.
+
+Notarius owns the typed document, domain defaults and validation, runtime
+conversion, catalog-dependent pipeline resolution, source-aware configured
+paths, and command discovery. It uses only ConfigKit's public path, result,
+diagnostic, and resolution-source APIs. Upstream documentation owns general
+ConfigKit semantics; [Configuration](../config.md) owns Notarius's file and
+operator contract.

docs/integrations/pkg-promptkit.md

@@ -1,11 +1,11 @@
 # PromptKit Integration
 
 Notarius pins
-[`gitea.maximumdirect.net/eric/promptkit` v0.9.0](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.9.0)
+[`gitea.maximumdirect.net/eric/promptkit` v0.10.0](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.10.0)
 as its in-process prompt engine. The upstream
-[Go package consumer guide](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.9.0/docs/consumers/pkg-promptkit.md)
+[Go package consumer guide](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.10.0/docs/consumers/pkg-promptkit.md)
 owns the public engine API, and the upstream
-[format reference](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.9.0/docs/formats.md)
+[format reference](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.10.0/docs/formats.md)
 owns prompt, profile, and schema file contracts.
 
 ## Supported Boundary
@@ -27,7 +27,7 @@ Notarius relies on the root `promptkit` package to:
   admission exhaustion through `ErrCapacityExceeded`.
 
 The pinned
-[`BackendLocal`, `LocalBackend`, and `WithBackend` API](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.9.0/backends.go)
+[`BackendLocal`, `LocalBackend`, and `WithBackend` API](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.10.0/backends.go)
 owns the registration and backend-capacity contract.
 
 For one completion, the adapter calls `PrepareExecution`, takes a
@@ -53,7 +53,7 @@ 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 v0.9.0's 256-code-point session limit. Session IDs are non-secret
+PromptKit's 256-code-point session limit. Session IDs are non-secret
 correlation identifiers and may be exposed to providers and provider
 observability. The CLI contract owns generation and override behavior.
 
@@ -86,16 +86,16 @@ configuration and deployment workflow are defined in
 [Operations](../operations.md#promptkit-profile-deployment).
 
 PromptKit owns `base_profile` resolution under its
-[pinned format rules](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.9.0/docs/formats.md).
+[pinned format rules](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.10.0/docs/formats.md).
 Notarius records the selected leaf identity and resolved target without parsing
 or merging inheritance. An unset filesystem `api_key_env` is optional and may
 reach the provider without authorization, which can result in a 401 or 403.
 
-PromptKit v0.9.0 accepts only the `developer`, `system`, `user`, and
+PromptKit accepts only the `developer`, `system`, `user`, and
 `assistant` text-chat roles after normalizing case and surrounding whitespace.
 Maintained Notarius prompt definitions use only `system` and `user`.
 
-For application-owned semantic correction, Notarius uses PromptKit v0.9.0's
+For application-owned semantic correction, Notarius uses PromptKit's
 `RunRequest.AppendedMessages` after the ordinary rendered prompt. It supplies
 exactly two messages in order: the latest validated producer response with
 role `assistant`, then deterministic validation guidance with role `user`.
@@ -112,12 +112,28 @@ and terminal summaries retain only safe counts, digests, identities, and usage;
 complete appended messages remain limited to the explicitly requested detailed
 debug trace.
 
-PromptKit now obtains its maintained OpenRouter and Rakestrawhome backend and
+PromptKit obtains its maintained OpenRouter and Rakestrawhome backend and
 profile catalogs from independently versioned transitive modules. Notarius
 does not import or register either catalog; PromptKit retains catalog source,
 identity, precedence, credential, and capacity ownership.
 
-Notarius supports this boundary against PromptKit v0.9.0. Its fallback source,
+External catalog profile names and settings can change between dependency
+releases, including removal without aliases. Review directly selected IDs and
+inherited `base_profile` values when upgrading. An application-owned alias that
+inherits an external profile does not freeze that profile's settings.
+PromptKit's opt-in `promptkit-openrouter-standard` and
+`promptkit-openrouter-auto` names provide name continuity within its
+selected-and-tested dependency scope, not a fixed model or provider availability
+guarantee. See the upstream
+[catalog compatibility policy](https://gitea.maximumdirect.net/eric/promptkit/src/tag/v0.10.0/docs/release.md#catalog-profile-compatibility).
+
+Use a complete operator-owned profile with explicit backend or endpoint, model,
+and settings when those choices must remain operator-controlled. The embedded
+`dnd-extraction` fallback already follows this model and does not inherit an
+external catalog profile. An upgrade updates Notarius's compiled-in catalog
+checkpoint identity so prior profile-source checkpoints are not reused.
+
+Notarius supports this boundary against PromptKit v0.10.0. 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,

docs/internal/cli.md

@@ -25,7 +25,8 @@ preparation, and runner mechanics after their inputs are supplied.
 ## Dispatch And Configuration Handoff
 
 The root dispatcher handles help, version reporting, configuration validation,
-pipeline listing, and a pipeline run. Version reporting resolves build
+effective-configuration inspection, explanation inspection, pipeline listing,
+and a pipeline run. Version reporting resolves build
 information through `internal/buildinfo` before production composition, so the
 diagnostic remains available without configuration or runtime collaborators.
 The public syntax, streams, exit classes, and version semantics are defined by
@@ -33,14 +34,15 @@ the [CLI reference](../cli.md). Other root commands normalize injectable
 options before dispatch so that a missing production dependency fails as a
 command error rather than reaching execution.
 
-Commands that need configuration use one shared loader. The CLI discovers the
-file, parses it through **internal/core/config**, starts from defaults, applies
-the file and supported environment overrides, and then validates it for the
-command. The configured discovery and precedence contract is in
+Commands that need configuration use one shared ConfigKit-backed loader. The
+CLI discovers the file, passes the requested profile and only explicit
+configuration-valued run overrides, and receives a **LoadedConfig**. The
+configured discovery and precedence contract is in
 [Configuration](../config.md), while the loading and resolution mechanics are
 in [Configuration Internals](configuration.md).
 
-Configuration validation without a selected pipeline checks structural
+`config effective` and `config explain` only render the loaded ConfigKit view;
+they do not resolve pipelines or construct providers. Configuration validation without a selected pipeline checks structural
 configuration only. Validation with a selected pipeline also builds the
 effective catalog, resolves the pipeline, and verifies every explicit effective
 PromptKit profile. Selected LLM-backed input, chunk, lane, output, and validator
@@ -84,8 +86,7 @@ field.
 After parsing and validating a run invocation, the CLI performs this ordered
 handoff:
 
-1. load and validate configuration, then apply command-level operational
-   overrides;
+1. load and validate configuration with ConfigKit command overrides;
 2. create and validate a safe run identity, then allocate a debug bundle only
    when requested;
 3. build the effective catalog, resolve requested reference changes, resolve
@@ -115,6 +116,16 @@ to checkpoint identity and `pipeline.RunInput`. The public flag and stability
 contract are defined by the [CLI reference](../cli.md#run); framework and LLM
 packages only transport the supplied value.
 
+The CLI also owns the scope grammar for reference flags. It enumerates the
+selected chunk and lane targets from registered module specifications, expands
+pipeline- and lane-scoped actions into exact stage-and-lane bindings, and
+resolves overlapping bind and unbind actions by specificity before calling
+configuration resolution. The generic pipeline therefore receives only exact
+`ReferenceBinding` and `ReferenceUnbind` values and has no knowledge of CLI
+selector syntax. Configuration resolution retains ownership of configured
+external/generated conflicts, required slots, and module compatibility; file
+materialization still occurs afterward.
+
 For `run --json`, the CLI constructs and encodes its private run-result receipt
 after a successful runner result is available, before it publishes logical
 output files. It writes the prepared receipt to standard output only after
@@ -166,8 +177,9 @@ is discoverable.
 - **internal/cli/production_contract_test.go** covers registrar composition,
   production catalog contents, assets, and representative configuration
   validation.
-- **internal/cli/reference_contract_test.go** covers CLI reference overrides,
-  origin separation, and materialization boundaries.
+- **internal/cli/reference_contract_test.go** covers scoped CLI reference
+  expansion, specificity, bind/unbind conflicts, generated-reference
+  protection, origin separation, and materialization boundaries.
 - **internal/cli/state_hardening_test.go** covers safe run identity, state
   roots, and failure ordering.
 

docs/internal/configuration.md

@@ -8,17 +8,17 @@ either interface.
 
 ## Boundary
 
-The configuration package turns a selected YAML file and supported environment
-values into a validated, independently owned configuration. It then resolves a
+The configuration package turns a selected ConfigKit-composed YAML document
+into a validated, independently owned configuration. It then resolves a
 requested pipeline against a module catalog before the framework prepares or
 runs anything.
 
 | Boundary | Inputs | Outputs | Does not own |
 | --- | --- | --- | --- |
-| Loading | Selected file path and environment lookup | Parsed file model and a populated **Config** | Choosing the file path or reporting a command result. |
+| Loading | Selected file path, profile, overrides, and invocation directory | **LoadedConfig** with ConfigKit inspection metadata and a populated **Config** | Choosing the file path or reporting a command result. |
 | Validation | **Config** | Structural configuration errors with pipeline, lane, or binding context | Module availability, capabilities, or construction. |
 | Resolution | Valid **Config**, selected pipeline and lanes, runtime reference changes, LLM override, and module catalog | **EffectiveConfig** with a **ResolvedPipeline** | Materializing reference bytes, preparing modules, execution, or filesystem state. |
-| Summary | **Config** or **EffectiveConfig** | Detached redacted payload suitable for debug summaries | Redacting arbitrary process state or provider traffic. |
+| Inspection | **LoadedConfig** and an optional JSON Pointer | Redacted effective YAML or explanation text | Pipeline selection, module preparation, or provider work. |
 
 The CLI discovers a configuration file, invokes this package, and supplies the
 result to the framework. Configuration never reads an input file, constructs a
@@ -28,23 +28,15 @@ at their respective [CLI](cli.md), [pipeline](pipeline.md), and
 
 ## Loading And Validation
 
-The CLI loads configuration in this order:
-
-1. parse the selected YAML file strictly into the file model;
-2. start from **Default**;
-3. apply the file model; and
-4. apply the supported environment overrides.
-
-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**.
+ConfigKit acquires the selected root, imports, optional selected profile, and
+explicit CLI overrides in precedence order. Its document definition supplies
+typed defaults, source-aware path normalization, and structural validation
+before conversion to the independently owned runtime **Config**. Only
+`NOTARIUS_CONFIG` participates in discovery; retired field-level environment
+variables do not participate in loading. Version 5 decoding rejects scalar
+module bindings and scalar external references. ConfigKit retains redacted,
+historical inspection metadata while **LoadedConfig** keeps that implementation
+detail private behind effective and explanation writers.
 
 **Config.Validate** checks configuration-only invariants before resolution. It
 rejects incompatible profile sources, invalid state-surface values, unsupported
@@ -57,13 +49,14 @@ 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
-environment override, its validation, and that reference in the same change.
+[Configuration](../config.md). Keep document schema, source-aware normalization,
+runtime conversion, and that reference aligned in the same change.
 
 ## Effective Resolution
 
-**Config.Resolve** first recomputes derived concurrency defaults and validates
-the configuration. It normalizes the requested pipeline ID, copies the selected
+**Config.Resolve** derives an absent extraction-worker value in an owned copy
+and validates the configuration. A programmatically supplied worker value is
+always explicit. 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.
 
@@ -110,43 +103,37 @@ bytes, a debug payload, or all runtime state. The CLI records it as invocation
 provenance before execution; cache and checkpoint identity have additional
 owners in [Run State Internals](state.md).
 
-Configuration summaries must use **Redacted**, **RedactedSummaryPayload**, or
-**RedactedResolvedPipelinePayload**, never a direct configuration marshal.
-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.
+Configuration publication uses ConfigKit's redacted effective YAML. Resolved
+pipeline publication uses **RedactedResolvedPipelinePayload**, which copies
+bindings and nested option containers, replaces credential-shaped values with
+**[REDACTED]**, and omits materialized reference content while retaining safe
+provenance. This redaction is deliberately narrow and does not authorize
+recording arbitrary environment values or provider requests.
 
 ## Invariants To Preserve
 
-- Defaults, YAML values, and environment values are applied in one direction;
-  later sources may override only their supported operational settings.
+- ConfigKit composition applies defaults, imports, an optional profile, and
+  explicit overrides in one direction with retained origin metadata.
 - A configuration is structurally valid before it is resolved, and a resolved
   pipeline is compatible with the supplied catalog before preparation begins.
 - Whitespace-normalized identifiers are unique wherever they identify a
   pipeline, step, lane, worker, or reference slot.
-- Resolution and summary generation return detached data. Redaction must cover
-  every configured and resolved binding, including nested validator bindings.
+- Runtime conversion and resolved-pipeline publication return detached data.
 - The resolved digest changes when resolved composition changes and never
   includes itself.
 
 ## Focused Tests
 
-- **internal/core/config/file_config_contract_test.go** covers strict file
-  parsing, normalization, file application, and structural rejection.
-- **internal/core/config/env_contract_test.go** covers supported operational
-  overrides and their precedence.
+- **internal/core/config/document_test.go** and
+  **operational_document_test.go** cover ConfigKit document loading,
+  normalization, imports, profiles, and overrides.
 - **internal/core/config/validation_contract_test.go** covers configuration
   invariants and contextual failures.
 - **internal/core/config/effective_config_contract_test.go** covers defaults,
   selections, overrides, resolution context, digest changes, and ownership.
-- **internal/core/config/redaction_test.go** covers recursive credential
-  redaction, reference-content exclusion, and non-aliasing payloads.
+- **internal/core/config/loaded_config_test.go** covers safe effective and
+  explanation rendering; **redaction_test.go** covers resolved-pipeline
+  redaction and reference-content exclusion.
 
 Run **go test ./internal/core/config** after changing this boundary. Changes to
 the handoff or resolved-composition semantics also need the focused framework

docs/internal/dnd.md

@@ -29,13 +29,17 @@ 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. The registry normalizers use `single_response_v1`, forwarding
-corrections to their reconciliation completion and retaining the accepted raw
-proposal only as an owned model candidate. Configuration remains the canonical owner of the exact keys,
+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. The registry normalizers
+use `single_response_v1`, forwarding corrections to their reconciliation
+completion and retaining the accepted raw proposal only as an owned model
+candidate. When deterministic proposal safety or typed application rejects a
+group, they provide separate model-facing prose for a corrective module retry;
+internal issue categories, reason codes, and operator messages remain
+diagnostic-only. Configuration remains the canonical owner of the exact keys,
 profile precedence, and validator order.
 
 Private structured-LLM response schemas are deliberately minimal. They reject
@@ -117,14 +121,27 @@ presentation, and final ephemeral generic transcript windows. These orders and
 cache controls are prompt behavior; change them only through the owning
 manifest and prompt declaration.
 
+NPC, item, and location registry reconciliation translate shared proposal
+safety categories into bounded prose that references only the response-local
+duplicate-group ordinals and candidate handles. Item reconciliation appends its
+typed rule that currency may be consolidated only with aliases of the same
+denomination and never with non-currency items. The next normalize attempt
+receives that prose with the exact defective proposal under the shared
+replacement-request protocol. Structurally invalid output has no valid proposal
+candidate and receives a fresh feedback-free attempt instead. If the stage
+budget is exhausted, safe groups stay applied, unsafe groups stay separate, and
+one fallback warning summarizes the final defect without raw model content.
+
 ## Evidence, Candidates, And Normalization
 
 The current transcript is the only durable evidence source. Extractors assign
-the current source identity, preserve candidate evidence ranges for validators,
-and canonically order or remove exact duplicate ranges without asking the
-model to repair semantic errors. Campaign context and generated artifacts may
-ground names or control routing, but they never establish evidence for a D&D
-result.
+the current source identity and losslessly order any reversed range whose two
+endpoints resolve in that source, using transcript position rather than numeric
+unit-ID order. They then canonically order ranges and remove exact duplicates.
+This routine canonicalization does not request a retry or emit a warning.
+Unresolvable or wrong-source ranges remain unchanged for validators to reject.
+Campaign context and generated artifacts may ground names or control routing,
+but they never establish evidence for a D&D result.
 
 Default chains keep responsibilities separate: structural validators assess the
 candidate, source-reference validators resolve cited ranges against the current
@@ -134,18 +151,115 @@ relatedness validators report advisory evidence concerns. The configured order
 is documented in
 [Configuration](../config.md#production-validator-keys-and-default-chains).
 
-Every D&D rejection describes the correction in transcript-grounded domain
-terms, using contextual names, artifact fields, and source segment ranges when
-useful. The guidance must not ask the model to reproduce durable entity IDs,
-hashes, validator module keys, or reason codes. Those identifiers remain in
-ordinary validation provenance; only the actionable semantic guidance is
-eligible for the correction prompt.
+The optional `extract/dnd/scene-descriptions/combat_semantics` validator is the
+D&D family's LLM-backed review of only combat versus non-combat classification.
+It selects the shared combat-policy prompt fragment and asks the model to
+classify the current chunk independently as `combat` or `non_combat` without
+receiving the proposed scene kind. Deterministic code compares that
+classification with the proposed kind and either approves it or produces the
+appropriate correction guidance. This keeps every schema-valid classification
+interpretable and avoids anchoring the reviewer on the producer's answer. It
+does not assess titles, summaries, non-combat subtype, or scene boundaries;
+deferred boundary-coherence review remains separate. It is opt-in;
+[Configuration](../config.md) owns selection and retry/failure behavior.
+
+### Combat-semantics provider evaluation
+
+The human-reviewed corpus at
+`internal/modules/dnd/validate/scenedescriptions/combat_semantics/testdata/evaluation_cases.json`
+owns the proposed kind, expected combat classification, and reviewer rationale
+for each synthetic case. Its package test validates the fixture contract only.
+Provider evaluation remains an explicit maintainer operation and must not be
+added to the default offline test suite.
+
+Use the following protocol before proposing default-chain inclusion:
+
+1. Record the Notarius commit, prompt and schema fingerprints, provider, model,
+   profile settings, reasoning effort, structural-repair setting, number of
+   repetitions, and evaluation date before collecting results. Do not revise
+   expected classifications merely to agree with provider output; a substantive
+   corpus correction requires independent human review.
+2. Exercise the production validator construction and prompt assets from an
+   explicitly invoked, disposable evaluation driver or test in the validator
+   package. For each corpus case, construct transcript source units from the
+   listed IDs and text, assign matching per-unit source references, and use
+   `source.MaterializeChunkPlan` with one range spanning those units. Construct
+   exactly one scene whose ID and source range match that chunk and whose kind
+   is the case's `proposed_kind`; title and summary may use fixed placeholders
+   because the validator neither receives nor evaluates them. Invoke the typed
+   validator at extract stage through the production registry and scheduled LLM
+   client. Do not commit provider credentials, generated source material, or an
+   always-on live test.
+3. Compare the model classification with `expected_classification`, then verify
+   that its deterministic comparison with `proposed_kind` yields the expected
+   approval or rejection direction.
+   Record an unexpected approval of an expected rejection as a false
+   acceptance, an unexpected rejection of an expected approval as a false
+   rejection, and any validator execution failure separately from semantic
+   accuracy. Retain per-case results so repeated trials and systematic failure
+   modes remain visible.
+4. Evaluate producer correction separately with representative complete
+   scene-description runs configured as shown in
+   [Configuration](../config.md#production-validator-keys-and-default-chains).
+   For every initial semantic rejection, record whether the next producer
+   attempt returns the requested combat status and is approved. Do not count a
+   PromptKit structural repair as a producer-correction attempt.
+5. Run the correction evaluation with debug capture enabled and without reused
+   extraction checkpoints. Record added validator and producer calls, elapsed
+   latency, and cumulative prompt, completion, cached, and total token usage
+   from the debug attempt records. Compare these values with an otherwise
+   identical run whose scene-description chain omits the semantic validator.
+
+The default-chain review must consider classification error, false acceptance,
+false rejection, execution failure, producer-correction success, added calls,
+latency, and token use together. A structurally successful provider run alone
+is not evidence that the validator should become a default.
+
+Every producer-correctable D&D rejection describes all currently detectable
+corrections in transcript-grounded domain terms, using contextual names,
+model-owned artifact fields, and source segment ranges when useful. Validators
+collect independent record defects in one pass so one retry does not merely
+reveal the next issue. Shared D&D diagnostic helpers keep repeated rules and
+record descriptions stable, de-duplicated, and bounded; each artifact family
+continues to own the semantic rule and its prose.
+
+Operator diagnostics and model guidance are separate products of the same
+assessment. Operator messages may use typed paths, reason details, and opaque
+application identities. Correction guidance must not copy those messages or
+ask the model to reproduce durable entity IDs, hashes, validator module keys,
+reason codes, or Go field paths. A registry-normalization rejection instead
+speaks in terms of the duplicate-group proposal response the normalizer can
+actually revise. Normalization-only deterministic invariants retain useful
+operator detail but do not imply that a model controls derived ordering or
+identity. Only bounded actionable semantic guidance is eligible for a
+correction prompt.
+
+Private LLM schemas use simple enums for closed categorical fields when the
+provider-compatible shape can express the rule directly. Deterministic typed
+validators retain the same checks as defense in depth and for non-LLM
+producers. Private schemas keep every property required and avoid optional
+properties, `uniqueItems`, and conditional cross-field logic.
+
+Item-occurrence shape validation groups repeated holder mistakes by occurrence
+kind and gives the producer the required JSON null/non-null relationship. It
+identifies affected records by contextual item name and cited transcript range,
+never by the deterministically attached durable item ID. Holder mistakes remain
+semantic rejections rather than silent rewrites because changing a holder can
+also change the meaning of the occurrence kind.
 
 Enemy-event extraction additionally rejects a second `engaged` observation for
 the same comparison identity within one scene-scoped result. Normalization may
 combine results from distinct scenes, so it intentionally does not apply that
 rule. Configuration owns the exact validator key and chain position.
 
+Extraction source-reference validators share one full-span chunk-containment
+policy. After ordinary reference validity succeeds, the policy resolves both
+endpoints through document order and requires every source unit in the
+inclusive range to be present in the current chunk. It does not assume numeric
+unit-ID ordering, mutate input, or weaken wrong-source and unresolved-reference
+validation. Scene descriptions remain separate because their validator owns an
+exact one-scene range contract rather than general extraction containment.
+
 Normalizers are deterministic for spells, combat turns, item occurrences, NPC
 occurrences, scene descriptions, enemy events, and location occurrences. They
 canonicalize display values and evidence, use source-document order for stable
@@ -158,13 +272,16 @@ proposal to reconcile identity groups.
 
 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
+eligible candidate receives a contiguous, one-based `candidate_number` for that
+request, and candidate material declares the exact inclusive range. The model
+sees that handle, the candidate label and source-free evidence ranges, plus
+bounded transcript windows; it returns only duplicate
 groups of supplied handles and one supplied canonical handle per group. It
 never returns names, evidence, durable IDs, or replacement records. Identical
 labels and evidence remain independently selectable because their handles are
-distinct.
+distinct. Transcript unit `id` values and evidence `start_unit_id` and
+`end_unit_id` values are source positions in a separate namespace and are
+never valid candidate numbers.
 
 The generic core owns the mandatory handle protocol, candidate and transcript
 presentation, the private response schema, source-reference validation,

docs/internal/llm.md

@@ -247,8 +247,12 @@ redaction boundary.
 Structural repair does not replace pipeline retry behavior: a binding's
 configured retry count reruns its complete stage attempt after an operational
 or structural error, module-requested retry, or actionable semantic rejection.
-The pipeline owns attempt lifecycle, validation chains, and retry diagnostics;
-see [Pipeline Internals](pipeline.md#validation-retries-and-output) and the
+An actionable module-requested retry and a validator rejection both use the
+same correction payload when the producer exposes an exact latest response;
+feedback-free module retries reconstruct the ordinary request without appended
+messages. The pipeline owns attempt lifecycle, validation chains, and retry
+diagnostics; see
+[Pipeline Internals](pipeline.md#validation-retries-and-output) and the
 [binding reference](../config.md#module-bindings-and-validators).
 
 ## Timeout Ownership

docs/internal/modules.md

@@ -95,19 +95,24 @@ 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.
+one-based request-local candidate numbers, renders bounded candidate and
+transcript materials, invokes the structured-completion boundary, and assesses
+the returned duplicate groups into a stable non-overlapping plan. Candidate
+material declares the exact inclusive number range for the request. Transcript
+unit IDs and evidence range endpoints remain source positions in a separate
+namespace and are never valid candidate numbers.
 
 The normalizer then applies that plan through a typed `ApplicationPolicy`. The
 core preserves ungrouped records, contribution order, and provenance while the
 artifact family owns group guards, field and evidence consolidation, durable
-ID derivation, retry and fallback presentation, classified diagnostics, and postconditions.
-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.
+ID derivation, retry and fallback presentation, classified diagnostics, and
+postconditions.
+These candidate numbers are the concrete private representation of ADR-0013's
+request-local handles; they do not enter the typed value or durable artifact.
+Fewer than two eligible candidates skips model invocation; exceeding a
+candidate or combined-material bound preserves the deterministic result under
+the family's fallback policy. Provider, transport, cancellation, and
+context-construction failures remain execution errors.
 
 When the engine actually makes a proposal call, its typed result carries the
 owned exact proposal response under the same correction contract as other
@@ -115,6 +120,16 @@ eligible producers. Deterministic skip, limit, and fallback outcomes carry no
 model candidate, so a later rejection applies terminal policy without spending
 an ineffective semantic retry.
 
+When proposal assessment or typed group application rejects a structurally
+valid group, the normalizer may return its safe partial value with a
+module-requested retry. A feedback-capable directive supplies bounded
+model-facing correction guidance separately from operator diagnostics and
+retains the exact proposal response as its candidate. The shared stage retry
+mechanism appends that response and guidance to a fresh complete request. A
+structurally invalid completion has no valid candidate and therefore requests a
+feedback-free fresh attempt. On exhaustion, only the final safe fallback and
+its bounded process diagnostic advance to validation.
+
 The core supplies a conservative generic prompt and the single private
 response schema. A domain prompt may substitute its semantic instructions but
 mounts the core-owned protocol and candidate/transcript presentation assets.

docs/internal/overview.md

@@ -26,7 +26,7 @@ physical state roots.
 | --- | --- | --- |
 | Executable and command boundary | **cmd/notarius**, **internal/cli** | Process entry, command dispatch, configuration discovery, production composition, runtime collaborator setup, durable file placement, and user-facing reporting. |
 | Build information | **internal/buildinfo** | Resolves a stable linked release tag or build metadata for the diagnostic root version command. |
-| Configuration | **internal/core/config** | Defaults, strict YAML parsing, environment overrides, structural validation, effective resolution, redaction, and resolved-composition summaries. |
+| Configuration | **internal/core/config** | ConfigKit document definition, source-aware normalization, runtime conversion, structural validation, safe inspection, effective resolution, and resolved-composition redaction. |
 | Generic models | **internal/core/source**, **internal/core/artifacts**, **internal/framework/contracts** | Source documents and chunks, manifests and provenance, plus typed artifact, reference, validation, output, and structured-completion contracts. |
 | Pipeline framework | **internal/framework/pipeline** | Registries, profile and reference resolution, typed preparation, validation, retry coordination, ordered execution, handoff, and result assembly. |
 | LLM and prompt runtime | **internal/framework/llm**, **internal/framework/promptfs** | Provider-neutral structured completions, scheduling, profile recording, prompt assets, schema registration, and credential-shaped-value redaction. |

docs/internal/pipeline.md

@@ -97,6 +97,13 @@ codec, checks its complete schema and media identity, and records a content
 digest plus bounded producer provenance. A missing, ambiguous, invalid, or
 incompatible producer prevents the consumer step from starting.
 
+Resolution receives only exact stage-and-lane operational reference overrides.
+The CLI may offer broader pipeline- or lane-scoped selectors, but expands and
+arbitrates those before entering the framework. External overrides are applied
+after configured external defaults and local bindings. They cannot coexist
+with a generated binding for the same target and slot, and external unbinds do
+not remove generated handoffs.
+
 ## Execution And Ordering
 
 The runner validates its input, installs no-op state collaborators when none
@@ -154,18 +161,25 @@ complete validation chain. It preserves terminal diagnostics only from the final
 or rejected attempt, plus one fixed validation-incomplete warning per validator whose execution
 budget was exhausted under `warn_continue`. Cancellation stops retries.
 Normalizer-specific retry directives consume this same budget and validate any
-final safe fallback through the normalizer chain.
+final safe fallback through the normalizer chain. A directive may carry bounded
+correction guidance only when it also exposes the exact latest
+`single_response_v1` candidate. The state machine then uses the same replacement
+request shape as validator correction. A directive without guidance clears any
+prior correction and starts a fresh attempt, which preserves structural retry
+behavior when no valid response exists.
 
 The artifact-neutral producer-attempt state machine owns that shared budget,
 attempt provenance, semantic-correction material, and terminal-policy
 selection. It accepts producer and complete-validation closures, so artifact
 materialization, cache handling, checkpoints, and debug output stay at the
 operation boundary. It distinguishes operational, structural, module-requested,
-and semantic retries. A semantic retry is available only for a valid latest
-`single_response_v1` candidate; a deterministic or no-model rejection instead
-settles the semantic policy immediately. Structural-output errors alone use the
-structural policy, and validation failure without rejection settles the
-validator-failure policy without regenerating the producer.
+and validator-semantic retries. Model feedback from either semantic source is
+available only for a valid latest `single_response_v1` candidate. A
+deterministic or no-model validator rejection instead settles the semantic
+policy immediately, while a feedback-free module directive remains an ordinary
+fresh retry. Structural-output errors alone use the structural policy, and
+validation failure without rejection settles the validator-failure policy
+without regenerating the producer.
 
 Chunk planning uses this state machine for generated plans. A rejected or
 validation-incomplete automatic cache hit is not model material and therefore
@@ -224,6 +238,8 @@ Debug recording is attempt-scoped and application-owned. A failure to persist
 required debug data is a framework error. State roots, persistence, reason-code
 meanings, resume, and cleanup are intentionally owned by
 [Run State Internals](state.md) and [Operations](../operations.md).
+Extract-validator trace scopes include the current chunk ordinal so concurrent
+chunks cannot overwrite one another's validator attempts or LLM artifacts.
 
 ## Invariants To Preserve
 

docs/internal/state.md

@@ -32,11 +32,18 @@ owned by the [Accepted Chunk Map contract](../integrations/chunk-map.md).
 
 `internal/framework/chunkplan` owns source-addressed plan storage, validation,
 and atomic publication. Its store is constructed only when the selected mode is
-not `bypass`.
+not `bypass`. It preserves rooted entry checks while creating new cache roots
+and source-digest directories with requested mode `0777`, then creates an
+atomic temporary file through rooted `O_CREATE|O_EXCL` with requested mode
+`0666` before sync and rename.
 
 `internal/framework/checkpoint` owns checkpoint identity, manifests, payload
 codecs, loader, and recorder. The CLI constructs a recorder whenever checkpoint
 recording is enabled and constructs a loader only for a `--resume` invocation.
+The recorder writes manifest and payload JSON through
+`fileio.WriteJSONWithProcessPermissions`, whose confined atomic writer creates
+new directories with requested mode `0777` and temporary files with requested
+mode `0666` before publication.
 Identity incorporates explicit stable semantic fingerprints collected from
 prepared modules and validators in addition to configuration, input,
 references, runtime overrides, observed LLM profiles, and the LLM runtime's
@@ -86,7 +93,10 @@ and debug-summary JSON.
 canonical operator-facing reason-code reference.
 
 `internal/core/fileio` provides confined atomic file writes used by state
-collaborators. The chunk-plan store retains its stronger entry validation.
+collaborators. Its exact-mode writer remains available to output and debug
+callers; its process-permission writer is used by checkpoints. The chunk-plan
+store retains its stronger rooted entry validation. [Operations](../operations.md#cache-provisioning)
+owns cache mode and provisioning guidance.
 
 The CLI constructs selective-recomputation policy from resolved generated
 artifact dependencies. It forces the selected step and transitive consumers,

docs/operations.md

@@ -50,11 +50,45 @@ directory selects a per-user root:
 
 The field definitions and configuration examples are in [Configuration](config.md).
 On supported Unix systems, output directories and files are created with
-requested modes **0755** and **0644**. Chunk-plan, checkpoint, and debug
-directories and files use **0700** and **0600**. The operating system's umask
-may impose stricter output modes. Cache and debug roots may contain sensitive
-source-derived data, so provision them for one trusted account or service. An
-output bundle can also contain source content when its JSON output enables
+requested modes **0755** and **0644**; debug directories and files use
+**0700** and **0600**. The operating system's umask may impose stricter output
+or debug modes. Chunk-plan and checkpoint caches instead request maximum modes
+of **0777** for new directories and **0666** for new files, including atomic
+temporary files. The kernel applies the service's umask and applicable default
+ACLs when those entries are created.
+
+## Cache Provisioning
+
+Cache locations select where Notarius writes, not who can access them. A
+private service can use a restrictive umask:
+
+~~~sh
+umask 0077
+notarius run example --config /etc/notarius/config.yml --input /srv/input.txt
+~~~
+
+A trusted-group deployment can provision a setgid cache root and use a
+group-oriented umask (or an equivalent default ACL):
+
+~~~sh
+install -d -m 2770 -g notarius-operators /srv/notarius/chunk-plans /srv/notarius/checkpoints
+umask 0007
+notarius run example --config /etc/notarius/config.yml --input /srv/input.txt
+~~~
+
+Setgid and default ACLs control inherited group ownership and access policy;
+Notarius does not copy a parent directory's literal mode bits. Cache state is
+reconstructible but can contain source-derived data, so operators own its
+access and retention policy. Existing cache inodes retain their prior modes
+after an upgrade. Recreate a cache beneath correctly provisioned parents, or
+stop writers and perform a deliberate administrative migration when a
+whole-tree change is required.
+
+Cache publication remains atomic and stored records remain validated. Those
+guarantees do not add cross-process locking or transactional coordination for
+simultaneous writers to one checkpoint identity.
+
+Output bundles can also contain source content when JSON output enables
 evidence publication. Apply an appropriate umask and output-root access policy
 before enabling that option; the requested output modes alone may not be
 suitable for transcript-bearing bundles.
@@ -81,7 +115,7 @@ 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
+[LLM profile](../examples/llm-profiles/dnd-extraction.yml) is secret-free and
 can be copied as a format starting point. Validate a deployment without a
 provider call or credentials:
 
@@ -92,11 +126,11 @@ notarius config validate --config /etc/notarius/config.yml --pipeline dnd-sessio
 An unset optional `api_key_env` reaches the provider without authorization and
 may receive a 401 or 403 response.
 
-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.
+Configured PromptKit profile paths resolve from the file that supplies their
+surviving declaration. The complete example's
+`./llm-profiles/dnd-extraction.yml` path is therefore relative to that example.
+Use absolute paths such as `/etc/notarius/profiles/dnd-extraction.yml` for
+services and containers when that is clearer for the deployment.
 
 ## Run Lifecycle
 
@@ -274,7 +308,8 @@ Only a [debug-enabled run](cli.md#run) creates a bundle:
   trace/
 ~~~
 
-The summary contains redacted invocation and resolution information plus run,
+The summary contains redacted invocation and resolution information, including
+`effective-config.yml` and the separately redacted resolved pipeline, plus run,
 final grouped diagnostic, checkpoint, chunk-plan, and terminal reporting artifacts. Attempt
 terminal records contain bounded attempt kinds, validator outcomes, policy,
 decision, PromptKit repair count, and usage; they do not contain assistant
@@ -284,7 +319,8 @@ content. Neither surface is a cache input. Do not treat a debug bundle as safe
 to share merely because its configuration summary is redacted. Invocation
 metadata omits reasoning effort when it is inherited, records the replacement
 value when one is supplied, and records an empty value when inherited reasoning
-was explicitly cleared.
+was explicitly cleared. It records `config_profile` only when a non-base
+configuration overlay was selected.
 
 Notarius never creates debug state without an explicit request and never
 automatically deletes a requested bundle. If allocation succeeds, the command

docs/policy/architecture.md

@@ -38,6 +38,36 @@ Notarius is contract-first without being abstraction-heavy. Interfaces and
 extension points should protect demonstrated boundaries. New abstraction is not
 itself an architectural goal.
 
+## Implementation Discipline
+
+Simplify the mechanism, not the user's choices.
+
+**Keep implementation machinery proportionate.** Use straightforward,
+idiomatic code and introduce only the machinery needed to support the requested
+behavior and flexibility. Optimize for conceptual simplicity and
+maintainability, not for the fewest lines, fewest options, or narrowest product
+surface.
+
+**Do not invent restrictions.** Do not reject, prohibit, constrain, cap,
+harden, or otherwise narrow behavior unless required by the user, an explicit
+repository contract, or an unavoidable correctness constraint. Preserve
+operator and caller choice where policy has not been established. If an
+additional restriction appears advisable, present it as a decision rather than
+silently implementing it.
+
+**An implementation detail is not repository policy.** Tests and documentation
+must not elevate incidental behavior into a durable guarantee or restriction
+unless that behavior was expressly selected as part of the contract. Existing
+explicit contracts remain authoritative; changing or weakening one requires a
+deliberate decision rather than being inferred from this principle.
+
+[ADR-0017](../adr/0017-defer-cache-access-policy-to-deployment.md) illustrates
+these principles. Notarius previously elevated private cache creation modes
+into application policy even though Unix deployments already express access
+policy through directory permissions, process umask, setgid inheritance, and
+default ACLs. The revised design retains application-owned correctness
+boundaries while leaving deployment security policy to the operator.
+
 ## Layers And Dependency Direction
 
 The application boundary is the composition root and may depend on concrete
@@ -201,6 +231,13 @@ they are not model instructions. The framework constructs model-facing retry
 text only from the semantic guidance and fails the contract rather than
 inventing or truncating missing guidance.
 
+An LLM-backed module may also request a feedback-aware retry when its own
+deterministic translation or typed safety policy rejects a structurally valid
+model response. It must supply model-facing guidance separately from its
+reason code, operator message, and fallback diagnostics, together with the
+exact `single_response_v1` candidate. A feedback-free module retry remains
+valid when no exact candidate exists.
+
 Default validator chains are production composition policy and are registered
 centrally by stage and module. Configuration may replace a stage-local default,
 including with an explicitly empty chain. Configured validator order is
@@ -222,12 +259,14 @@ the two budgets must remain separate.
 
 An LLM-backed producer can participate in semantic correction only when it
 declares `single_response_v1` and returns the exact one response that directly
-controlled its candidate. On an actionable rejection, the framework rebuilds
-the ordinary request and appends only the latest defective response as an
-`assistant` message plus one aggregated `user` correction message. This is a
-fresh replacement request, not a growing conversation. The retry budgets,
-terminal policy, and sensitive-data rationale are recorded in
-[ADR-0014](../adr/0014-feedback-aware-validation-retries.md).
+controlled its candidate. On an actionable validator rejection or
+feedback-capable module retry, the framework rebuilds the ordinary request and
+appends only the latest defective response as an `assistant` message plus one
+aggregated `user` correction message. This is a fresh replacement request, not
+a growing conversation. The retry budgets, terminal policy, and sensitive-data
+rationale are recorded in
+[ADR-0014](../adr/0014-feedback-aware-validation-retries.md) and
+[ADR-0016](../adr/0016-feedback-aware-module-requested-retries.md).
 
 When a model selects an application entity, callers must supply a contextual
 selection and deterministically attach the opaque application identity whenever
@@ -252,9 +291,11 @@ beneath this mandatory application-wide scheduler.
 
 ## Configuration And Provenance
 
-Configuration loading, precedence, defaults, environment overrides, redaction,
-and validation are centralized. Named pipeline definitions make structural
-composition explicit and discoverable. Operational overrides are permitted
+Configuration loading, precedence, defaults, redaction, and validation are
+centralized through the ConfigKit-backed boundary. `NOTARIUS_CONFIG` is limited
+to discovery; field-level environment overlays are not configuration input.
+Named pipeline definitions make structural composition explicit and discoverable.
+Explicit command overrides are permitted
 when they do not obscure the configured pipeline structure.
 
 Run preparation fails before stage execution when statically discoverable
@@ -284,6 +325,15 @@ an invocation that explicitly requests resume. Debug is never a cache input and
 is never created without an explicit request. Pipeline modules receive
 collaborator interfaces and never physical roots.
 
+Deployments own cache access policy. Cache writers request conventional maximum
+creation modes and let the process umask, setgid inheritance, and default ACLs
+determine effective access. Notarius owns the separate safety boundary:
+confined paths, symlink rejection, atomic publication, validation, and
+recovery. It does not chmod, chown, chgrp, or migrate cache entries to impose
+an application policy. This rule applies to chunk-plan and checkpoint cache
+only; output and debug retain their separate contracts. [Operations](../operations.md)
+owns deployment provisioning and retention guidance.
+
 Only accepted, completely validated producer output is reusable checkpoint or
 chunk-plan state. Rejected, structurally invalid, and validation-incomplete
 results cannot become cache or checkpoint inputs, even when a

docs/policy/documentation.md

@@ -30,6 +30,18 @@ that the behavior exists. The roadmap owns implementation status and sequencing
 until the decision is implemented. Current architecture, user, operator,
 integration, and internal documentation are updated when the behavior lands.
 
+### Implementation Details And Policy
+
+Documentation must distinguish an explicit contract from an incidental
+implementation choice. Do not describe a restriction, guarantee, security
+policy, default, or limit as authoritative merely because the current code
+implements it. Documentation may accurately describe current behavior without
+making it a permanent requirement; distinguish descriptive behavior from
+normative policy. The
+[implementation-discipline rules](architecture.md#implementation-discipline)
+own the criteria for adopting product restrictions and for elevating behavior
+into repository policy.
+
 ### Audience And Detail
 
 Write for the document's stated audience and include only the detail needed for

docs/policy/testing.md

@@ -87,6 +87,13 @@ Do not force all behavior through oversized end-to-end tests. Do not test every
 
 A test should protect a decision, contract, or invariant—not memorialize the current implementation.
 
+Tests must not create a stronger product contract than the requirement they
+protect. In particular, do not turn an incidental limit, restriction,
+permission choice, validation rule, or implementation default into policy by
+asserting it without an expressly selected contract. Follow the
+[implementation-discipline rules](architecture.md#implementation-discipline)
+when deciding what behavior deserves durable protection.
+
 Before adding or retaining a test, ask:
 
 > What realistic defect would this test catch?

docs/releases/v0.6.0.md

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

docs/releases/v0.7.0.md

@@ -0,0 +1,88 @@
+# Notarius v0.7.0
+
+This release simplifies configuration management with ConfigKit and makes
+cache access permissions a deployment responsibility.
+
+## Summary
+
+Notarius adopts ConfigKit v0.3.0 for strict configuration loading, imports,
+configuration profiles, provenance, and redacted inspection. Operators can
+compose whole pipeline definitions from separate files and select development
+overlays without duplicating the base configuration.
+
+Configured relative filesystem paths now resolve against their declaring
+files, including imported definitions and profile replacements. The effective
+configuration and its explanation reflect the paths used at runtime.
+
+## Compatibility
+
+- Configuration version 5 replaces version 4; there is no compatibility loader.
+  Numeric `version: 5` is the canonical spelling; quoted `"5"` also works.
+- Module and validator bindings require objects with `module:`; external
+  references require objects with `path:`. Lane-level reference aliases are
+  removed; use binding-local references instead.
+- Strict ConfigKit YAML parsing rejects aliases, merge keys, and unsupported
+  scalar forms. See the [configuration reference](../config.md) for the
+  complete contract and migration guidance.
+- The seven operational environment overrides are removed:
+  `NOTARIUS_TOTAL_LLM_CONCURRENCY`, `NOTARIUS_STAGE_WORKERS_EXTRACT`,
+  `NOTARIUS_OUTPUT_DIR`, `NOTARIUS_CACHE_CHUNK_PLANS_MODE`,
+  `NOTARIUS_CACHE_CHUNK_PLANS_DIR`, `NOTARIUS_CACHE_CHECKPOINTS_DIR`, and
+  `NOTARIUS_DEBUG_DIR`. `NOTARIUS_CONFIG` still selects the configuration
+  file; PromptKit credential environment variables remain supported.
+- Configured relative reference, PromptKit profile, output, cache, and debug
+  paths use the canonical declaring file's directory. Built-in relative
+  defaults use the main configuration directory. CLI-relative paths still use
+  the invocation directory; absolute paths are unchanged.
+- Requested debug bundles now contain `effective-config.yml` instead of
+  `effective-config.json`. Inspection output is redacted and is not promised
+  to be reloadable configuration.
+- Chunk-plan and checkpoint cache writers respect deployment permissions
+  through ordinary creation modes, umask, setgid inheritance, and default ACLs;
+  they no longer impose private permissions. Existing entries are not chmodded
+  or migrated. Output and debug access contracts are unchanged.
+- Durable extraction artifact schemas and subprocess receipt formats are
+  unchanged by this release.
+
+## Upgrade
+
+1. Migrate deployed configurations to version 5 using the
+   [configuration migration guide](../config.md#version-5-migration). Expand
+   shorthand bindings and references, and move retired environment settings
+   into YAML or supported CLI overrides.
+2. Review relative paths, particularly output/cache/debug directories and
+   PromptKit profile sources. Use absolute paths when preserving an existing
+   deployment location is important.
+3. Review deployment access settings for cache directories. Provision umask,
+   groups, and ACLs as appropriate; Notarius does not choose the installation's
+   access policy. See [Operations](../operations.md).
+4. Use `config validate --config <path> --pipeline <id>` for each pipeline,
+   including selected configuration profiles. Inspect resolved settings with
+   `config effective` and their provenance with `config explain`; see the
+   [CLI reference](../cli.md).
+5. Update any debug-bundle tooling that consumes the former effective JSON
+   file. Subprocess callers may optionally select an overlay through
+   `--config-profile`; this is separate from PromptKit's `--llm-profile`.
+
+The maintained [minimal](../../examples/dnd-minimal.config.yml) and
+[complete](../../examples/dnd-complete.config.yml) D&D examples demonstrate
+self-contained configuration and composed pipelines with a development profile.
+Build from the source tag using the [source-release procedure](../release.md).
+
+## Changes
+
+- Replaced custom YAML parsing and environment-overlay machinery with a
+  ConfigKit-backed typed document boundary and detached runtime conversion.
+- Added imports, configuration profiles, source-aware normalization, safe
+  effective/explanation commands, and source-file legends for load errors.
+- Preserved explicit zeroes and empty validator overrides at supported stages,
+  rejected invalid reference branches before conversion, and retained
+  whitespace normalization for worker identifiers.
+- Corrected normalization recording for ordered steps and validator sequences,
+  with regression coverage for runtime values and provenance.
+- Accepted ConfigKit's integer representation at module-option boundaries
+  through checked shared conversion.
+- Updated examples, configuration and subprocess guidance, and debug rendering.
+- Reworked cache creation to respect deployment-selected permissions while
+  retaining confined paths, symlink rejection, atomic publication, validation,
+  and recovery.

docs/releases/v0.7.1.md

@@ -0,0 +1,44 @@
+# Notarius v0.7.1
+
+This release updates the prompt engine and its provider catalogs while retaining
+Notarius's application-owned D&D defaults and subprocess contracts.
+
+## Summary
+
+- Upgrade PromptKit from v0.9.0 to v0.10.0 and adopt its selected provider catalogs.
+- Refresh the profile-source checkpoint identity for the updated catalog.
+- Document profile ownership and upstream catalog compatibility.
+
+## Compatibility
+
+Notarius's CLI, configuration schema, durable artifact formats, and subprocess
+receipt are unchanged. The `dnd-extraction` fallback retains its explicit model
+and settings; the upgrade does not switch it to an upstream default profile.
+
+Upstream catalog selections require review: `deepseek-3-2`, `deepseek-4-flash`,
+and `deepseek-4-pro` are no longer present. Operators selecting or inheriting
+those profiles must supply a complete operator-owned definition or select an
+available profile. `deepseek-flash-latest` and `deepseek-pro-latest` are not
+equivalent aliases and need not preserve previous settings. See the
+[PromptKit integration contract](../integrations/pkg-promptkit.md#profile-sources-and-compatibility).
+
+Existing checkpoints with the previous profile-source identity are not reused.
+Source-keyed chunk plans and existing output artifacts are unaffected.
+
+## Upgrade
+
+Review selected LLM profile IDs and inherited bases before rebuilding from this
+tag. No Notarius configuration migration is required for the maintained examples
+or application-owned D&D defaults. For controlled model settings, use a complete
+[operator profile](../config.md#promptkit-profiles), rather than inheriting a
+volatile catalog entry. Follow the [source release procedure](../release.md)
+for source installation and verification.
+
+## Changes
+
+- PromptKit v0.10.0 preserves the public engine API and adds two opt-in maintained
+  profile names; Notarius continues using its existing adapter and defaults.
+- The dependency graph selects OpenRouter catalog v2.20260922.1 and Rakestrawhome
+  catalog v2.20260922.0.
+- Profile checkpoint fingerprinting and current integration documentation now
+  identify the updated engine.

docs/roadmap/future.md

@@ -14,47 +14,9 @@ eligibility, and the separation of actionable process warnings from quality
 diagnostics. The remaining near-term work applies those completed foundations
 to domain review and empirical evaluation.
 
-### D&D Combat Scene Semantic Validation
-
-- Add an optional production LLM-backed D&D validator that determines whether
-  proposed scene boundaries and classifications represent substantive active
-  combat correctly. Its central quality goal is that active combat is kept in
-  coherent scenes classified as `combat`, rather than split incorrectly or
-  hidden inside scenes classified as `narrative`, `recap`, or `meta`.
-- Resolve the validator's exact target before implementation. The current
-  `dnd/scenes` chunker owns only complete, gap-free source ranges, while the
-  per-chunk `dnd/scene-descriptions` extractor owns the `combat`, `narrative`,
-  `recap`, and `meta` classification. The preferred initial placement is
-  therefore an extract-stage validator for `dnd/scene-descriptions`, where it
-  can compare one proposed kind with the corresponding transcript chunk.
-- Consider a chunk-stage LLM validator only for a distinct boundary-coherence
-  question that can be answered from the complete transcript and proposed
-  range map, such as whether one continuous combat was fragmented across
-  inappropriate scene boundaries. Do not duplicate the same classification
-  judgment at both stages. Moving classification into chunk-plan annotations
-  would change the deliberately minimal, annotation-free chunk contract and
-  requires an explicit architecture review before it is selected.
-- Validate both false negatives and false positives: a non-combat kind must not
-  omit substantive active combat, and a combat kind must be supported by such
-  combat. Keep the existing deterministic downstream rule that combat-turn
-  extraction runs only for an exact `combat` scene classification; semantic
-  review improves the upstream classification but does not replace that gate.
-- Run the semantic validator through PromptKit, use a minimal required-field
-  structured response schema, and let PromptKit repair structural validator
-  output within its bounded budget. A contract-invalid final validator response
-  is a validator execution failure, not a semantic rejection and not a reason
-  to recursively validate the validator.
-- Evaluate the prompt and decision policy against a small human-reviewed set
-  containing combat setup, active turns, interruptions, multi-phase encounters,
-  brief rules discussion, aftermath, recalled combat, and false-positive
-  hostile dialogue. Measure false acceptance, false rejection, retry success,
-  added calls, latency, and token cost before placing it in the production
-  default chain.
-- An ADR is not required if classification remains owned by
-  `dnd/scene-descriptions` and the validator follows the generic validation ADR.
-  Create or supersede an ADR if the work transfers scene classification into
-  the chunker or otherwise changes stage ownership or the durable chunk-plan
-  contract.
+Near-term reliability work should now be selected from the concrete evaluation
+and extension opportunities below. The retry, validation, and subprocess
+foundations described above are implemented current behavior.
 
 ## Near-Term D&D Pipeline
 

examples/dnd-complete.config.yml

@@ -1,6 +1,9 @@
-version: 4
+version: 5
+configkit:
+  imports:
+    - path: pipelines/dnd-session.yml
 promptkit:
-  profile_file: ./examples/profiles/dnd-extraction.yml
+  profile_file: ./llm-profiles/dnd-extraction.yml
 concurrency:
   total_llm: 2
   stage_workers:
@@ -16,145 +19,3 @@ cache:
     directory: ./notarius-cache/checkpoints
 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:
-      party: ./dnd-party.txt
-      glossary: ./dnd-glossary.txt
-    chunk:
-      module: dnd/scenes
-      retries: 2
-    output:
-      module: json
-      options:
-        include_chunk_map: true
-        evidence_context:
-          enabled: true
-          window_units: 3
-          lanes:
-            - item-occurrences
-            - item-registry
-            - location-registry
-            - location-occurrences
-            - npc-registry
-            - spells
-            - combat-turns
-            - npc-occurrences
-            - enemy-events
-    steps:
-      # Establish session-wide reference artifacts before their consumers.
-      - id: describe-session
-        artifacts:
-          item-registry:
-            extract:
-              module: dnd/item-registry
-              retries: 2
-            merge: appendorder
-            normalize: dnd/item-registry
-          npc-registry:
-            extract:
-              module: dnd/npc-registry
-              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
-              retries: 2
-          scene-descriptions:
-            extract:
-              module: dnd/scene-descriptions
-              retries: 2
-            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.
-        references:
-          location_registry:
-            artifact:
-              step: describe-session
-              lane: location-registry
-          npc_registry:
-            artifact:
-              step: describe-session
-              lane: npc-registry
-          scene_descriptions:
-            artifact:
-              step: describe-session
-              lane: scene-descriptions
-          item_registry:
-            artifact:
-              step: describe-session
-              lane: item-registry
-        artifacts:
-          item-occurrences:
-            extract:
-              module: dnd/item-occurrences
-              retries: 2
-            merge: appendorder
-            normalize: dnd/item-occurrences
-          spells:
-            extract:
-              module: dnd/spells
-              retries: 2
-              references:
-                spell_catalog: ./dnd-spell-catalog.json
-            merge: appendorder
-            # Stage-local file references are intentionally bound at each stage.
-            normalize:
-              module: dnd/spells
-              references:
-                spell_catalog: ./dnd-spell-catalog.json
-          combat-turns:
-            extract:
-              module: dnd/combat-turns
-              retries: 2
-            merge: appendorder
-            normalize: dnd/combat-turns
-          npc-occurrences:
-            extract:
-              module: dnd/npc-occurrences
-              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

examples/dnd-minimal.config.yml

@@ -1,9 +1,12 @@
-version: 4
+version: 5
 pipelines:
   dnd-session:
     llm_profile: dnd-extraction
-    input: seriatim
+    input:
+      module: seriatim
     artifacts:
       spells:
-        extract: dnd/spells
-        normalize: dnd/spells
+        extract:
+          module: dnd/spells
+        normalize:
+          module: dnd/spells

examples/pipelines/dnd-session.yml

@@ -0,0 +1,164 @@
+pipelines:
+  dnd-session:
+    llm_profile: dnd-extraction
+    input:
+      module: seriatim
+    # Stable campaign context is shared by every module that accepts these slots.
+    references:
+      party:
+        path: ../dnd-party.txt
+      glossary:
+        path: ../dnd-glossary.txt
+    chunk:
+      module: dnd/scenes
+      retries: 2
+    output:
+      module: json
+      options:
+        include_chunk_map: true
+        evidence_context:
+          enabled: true
+          window_units: 3
+          lanes:
+            - item-occurrences
+            - item-registry
+            - location-registry
+            - location-occurrences
+            - npc-registry
+            - spells
+            - combat-turns
+            - npc-occurrences
+            - enemy-events
+    steps:
+      # Establish session-wide reference artifacts before their consumers.
+      - id: describe-session
+        artifacts:
+          item-registry:
+            extract:
+              module: dnd/item-registry
+              retries: 2
+            merge:
+              module: appendorder
+            normalize:
+              module: dnd/item-registry
+          npc-registry:
+            extract:
+              module: dnd/npc-registry
+              retries: 2
+            merge:
+              module: appendorder
+            normalize:
+              module: dnd/npc-registry
+              retries: 2
+          location-registry:
+            extract:
+              module: dnd/location-registry
+              retries: 2
+            merge:
+              module: appendorder
+            normalize:
+              module: dnd/location-registry
+              retries: 2
+          scene-descriptions:
+            extract:
+              module: dnd/scene-descriptions
+              retries: 2
+            merge:
+              module: appendorder
+            normalize:
+              module: 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.
+        references:
+          location_registry:
+            artifact:
+              step: describe-session
+              lane: location-registry
+          npc_registry:
+            artifact:
+              step: describe-session
+              lane: npc-registry
+          scene_descriptions:
+            artifact:
+              step: describe-session
+              lane: scene-descriptions
+          item_registry:
+            artifact:
+              step: describe-session
+              lane: item-registry
+        artifacts:
+          item-occurrences:
+            extract:
+              module: dnd/item-occurrences
+              retries: 2
+            merge:
+              module: appendorder
+            normalize:
+              module: dnd/item-occurrences
+          spells:
+            extract:
+              module: dnd/spells
+              retries: 2
+              references:
+                spell_catalog:
+                  path: ../dnd-spell-catalog.json
+            merge:
+              module: appendorder
+            # Stage-local file references are intentionally bound at each stage.
+            normalize:
+              module: dnd/spells
+              references:
+                spell_catalog:
+                  path: ../dnd-spell-catalog.json
+          combat-turns:
+            extract:
+              module: dnd/combat-turns
+              retries: 2
+            merge:
+              module: appendorder
+            normalize:
+              module: dnd/combat-turns
+          npc-occurrences:
+            extract:
+              module: dnd/npc-occurrences
+              retries: 2
+            merge:
+              module: appendorder
+            normalize:
+              module: dnd/npc-occurrences
+          location-occurrences:
+            extract:
+              module: dnd/location-occurrences
+              retries: 2
+            merge:
+              module: appendorder
+            normalize:
+              module: 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:
+              module: appendorder
+            normalize:
+              module: dnd/enemy-events

examples/profiles/development.yml

@@ -0,0 +1,8 @@
+# This selects operational settings only; choose a different LLM profile with
+# the pipeline's llm_profile field or the run command's --llm-profile flag.
+concurrency:
+  total_llm: 1
+  stage_workers:
+    extract: 1
+output:
+  directory: ./notarius-output-development

go.mod

@@ -3,14 +3,16 @@ module gitea.maximumdirect.net/eric/notarius
 go 1.25.5
 
 require (
-	gitea.maximumdirect.net/eric/promptkit v0.9.0
+	gitea.maximumdirect.net/eric/ConfigKit v0.3.0
+	gitea.maximumdirect.net/eric/promptkit v0.10.0
 	github.com/santhosh-tekuri/jsonschema/v6 v6.0.2
-	gopkg.in/yaml.v3 v3.0.1
+	gopkg.in/yaml.v3 v3.0.1 // indirect
 )
 
 require golang.org/x/text v0.40.0
 
 require (
-	gitea.maximumdirect.net/eric/promptkit-backend-openrouter v1.0.0 // indirect
-	gitea.maximumdirect.net/eric/promptkit-backend-rakestrawhome v1.0.0 // indirect
+	gitea.maximumdirect.net/eric/promptkit-backend-openrouter/v2 v2.20260922.1 // indirect
+	gitea.maximumdirect.net/eric/promptkit-backend-rakestrawhome/v2 v2.20260922.0 // indirect
+	go.yaml.in/yaml/v4 v4.0.0-rc.6 // indirect
 )

go.sum

@@ -1,13 +1,17 @@
-gitea.maximumdirect.net/eric/promptkit v0.9.0 h1:IpvDRC8L6xRxQ9hpuyKOmMc5b6MeLTKYyx+h1YAjy08=
-gitea.maximumdirect.net/eric/promptkit v0.9.0/go.mod h1:oMJ/WUJImUtwJ5e+6MAGECPYAErAkOaKel0G+3T/b4E=
-gitea.maximumdirect.net/eric/promptkit-backend-openrouter v1.0.0 h1:lc062euk2qseO//D762i3JaFyulDNML3eQQX7DkYTho=
-gitea.maximumdirect.net/eric/promptkit-backend-openrouter v1.0.0/go.mod h1:AIa7kAu2mfrRQgcspe4L+DW51WqgnALQT60lqkEywJI=
-gitea.maximumdirect.net/eric/promptkit-backend-rakestrawhome v1.0.0 h1:j9YY7wsTVjzke2kHH4YAzpU0oUpM+x+nXwl1IeS+2eg=
-gitea.maximumdirect.net/eric/promptkit-backend-rakestrawhome v1.0.0/go.mod h1:4RNS+LILDg4JbS4Ts9Lwy1C92wauXJIbeQaalps4Koo=
+gitea.maximumdirect.net/eric/ConfigKit v0.3.0 h1:LgXEUjR0KsgwGBznOWa8FJTQ+iElctHtI1via5vKdu4=
+gitea.maximumdirect.net/eric/ConfigKit v0.3.0/go.mod h1:tYWpsrbLyu05r8+1MapWp5fN6ZrX9I8hU2xEPedYmYk=
+gitea.maximumdirect.net/eric/promptkit v0.10.0 h1:Nyi+YbqvO7tkRjen+Opc79wuzuKIIwcSfkriixPPwrE=
+gitea.maximumdirect.net/eric/promptkit v0.10.0/go.mod h1:0zEBVlJJC+ldDdXazAgybYBXNSe74vwFx5dyOuSos/w=
+gitea.maximumdirect.net/eric/promptkit-backend-openrouter/v2 v2.20260922.1 h1:S2/Q/JDE+m8Ca3pDhAjVbfYrdlEhs9blj0STgNopHo0=
+gitea.maximumdirect.net/eric/promptkit-backend-openrouter/v2 v2.20260922.1/go.mod h1:a3VBbh9oaGXD6ruxhtwHj+AWW6DY/SSyby1QtMmYSUo=
+gitea.maximumdirect.net/eric/promptkit-backend-rakestrawhome/v2 v2.20260922.0 h1:Y0EXc3eh12eKW2NrOviVqdk3oBo6UUjopt1YAa1B3Oc=
+gitea.maximumdirect.net/eric/promptkit-backend-rakestrawhome/v2 v2.20260922.0/go.mod h1:mtgD1E0SGm0e/I8Ffhz+AYX7GN7RKUWJXehNFIKHs4Y=
 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=
+go.yaml.in/yaml/v4 v4.0.0-rc.6 h1:1h7H1ohdUh93/FyE4YaDa1Zh64K6VVbjF4K6WUxMtH4=
+go.yaml.in/yaml/v4 v4.0.0-rc.6/go.mod h1:aZqd9kCMsGL7AuUv/m/PvWLdg5sjJsZ4oHDEnfPPfY0=
 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=

internal/cli/cache_contract_test.go

@@ -23,7 +23,7 @@ func TestRunChunkPlanModePrecedenceAndValidation(t *testing.T) {
 	}{
 		{name: "default", wantStores: 1},
 		{name: "file", fileMode: "bypass"},
-		{name: "environment", envMode: "bypass"},
+		{name: "retired environment has no effect", envMode: "bypass", wantStores: 1},
 		{name: "cli", envMode: "refresh", cliMode: "bypass"},
 	}
 	for _, tt := range tests {
@@ -80,25 +80,14 @@ func TestRunChunkPlanModePrecedenceAndValidation(t *testing.T) {
 	})
 
 	for _, tt := range []struct {
-		name       string
-		fileConfig bool
+		name string
 	}{
-		{name: "invalid environment mode"},
-		{name: "invalid file mode", fileConfig: true},
+		{name: "invalid file mode"},
 	} {
 		t.Run(tt.name, func(t *testing.T) {
 			roots := newStateTestRoots(t)
 			opts := newStateTestHarness().options()
-			if tt.fileConfig {
-				replaceStateTestConfigLine(t, roots.config, "    mode: auto\n", "    mode: invalid\n")
-			} else {
-				opts.LookupEnv = func(name string) (string, bool) {
-					if name == "NOTARIUS_CACHE_CHUNK_PLANS_MODE" {
-						return "invalid", true
-					}
-					return "", false
-				}
-			}
+			replaceStateTestConfigLine(t, roots.config, "    mode: auto\n", "    mode: invalid\n")
 			var stdout, stderr bytes.Buffer
 			code := RunWithOptions([]string{"run", "sample", "--config", roots.config, "--input", roots.input}, &stdout, &stderr, opts)
 			if code != 1 || stdout.Len() != 0 || stderr.Len() == 0 {
@@ -207,16 +196,20 @@ func TestRunAutoReusesPlanWhenRunInputsChange(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	configText := replaceRequiredOnce(t, string(data), "    chunk: test/chunk\n", `    chunk:
+	configText := replaceRequiredOnce(t, string(data), "    chunk:\n      module: test/chunk\n", `    chunk:
       module: test/chunk
       options:
         strategy: first
 `)
-	configText = replaceRequiredOnce(t, configText, "    output: test/output\n", `      other:
-        extract: test/extract
-        merge: test/merge
-        normalize: test/normalize
-    output: test/output
+	configText = replaceRequiredOnce(t, configText, "    output:\n      module: test/output\n", `      other:
+        extract:
+          module: test/extract
+        merge:
+          module: test/merge
+        normalize:
+          module: test/normalize
+    output:
+      module: test/output
 `)
 	if err := os.WriteFile(roots.config, []byte(configText), 0o600); err != nil {
 		t.Fatal(err)

internal/cli/command_contract_test.go

@@ -140,7 +140,7 @@ func TestConfigLoadingFailuresReturnOneWithPathContext(t *testing.T) {
 	stdout.Reset()
 	stderr.Reset()
 	code = RunWithOptions([]string{"config", "validate", "--config", malformed}, &stdout, &stderr, commandContractOptions(t))
-	if code != 1 || !strings.Contains(stderr.String(), malformed) || !strings.Contains(stderr.String(), "parse config file") || stdout.Len() != 0 {
+	if code != 1 || !strings.Contains(stderr.String(), "configuration contains invalid YAML") || stdout.Len() != 0 {
 		t.Fatalf("malformed config: code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
 	}
 }
@@ -185,14 +185,16 @@ func TestConfigValidateResolvesPipelineAndChecksSelection(t *testing.T) {
 }
 
 func TestConfigValidatePipelineDefaultProfileIsOffline(t *testing.T) {
-	configPath := writeCommandConfigContent(t, `version: 4
+	configPath := writeCommandConfigContent(t, `version: 5
 pipelines:
   demo:
     llm_profile: dnd-extraction
-    input: seriatim
+    input:
+      module: seriatim
     artifacts:
       spells:
-        extract: dnd/spells
+        extract:
+          module: dnd/spells
 `)
 	var stdout, stderr bytes.Buffer
 	code := RunWithOptions([]string{"config", "validate", "--config", configPath, "--pipeline", "demo"}, &stdout, &stderr, Options{})
@@ -261,19 +263,21 @@ 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: 5\npipelines:\n  %q:\n    input:\n      module: seriatim\n  %q:\n    input:\n      module: 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: 5
 pipelines:
   demo:
-    input: seriatim
+    input:
+      module: seriatim
     artifacts:
       spells:
-        extract: dnd/spells
+        extract:
+          module: dnd/spells
 `)
 }
 

internal/cli/configkit_commands.go

@@ -0,0 +1,157 @@
+package cli
+
+import (
+	"context"
+	"encoding/json"
+	"flag"
+	"fmt"
+	"io"
+	"strings"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+	"gitea.maximumdirect.net/eric/notarius/internal/core/config"
+)
+
+func runConfigEffective(args []string, stdout, stderr io.Writer, opts Options) int {
+	fs := flag.NewFlagSet("config effective", flag.ContinueOnError)
+	fs.SetOutput(io.Discard)
+	configPath := fs.String("config", "", "config file path")
+	profile := fs.String("config-profile", "", "configuration profile")
+	if err := fs.Parse(args); err != nil {
+		fmt.Fprintf(stderr, "notarius: %v\n", err)
+		return 2
+	}
+	if fs.NArg() != 0 {
+		fmt.Fprintf(stderr, "notarius: unexpected argument %q\n", fs.Arg(0))
+		return 2
+	}
+	loaded, _, err := loadConfigKit(*configPath, *profile, nil, opts)
+	if err != nil {
+		writeConfigLoadError(stderr, err)
+		return 1
+	}
+	if err := loaded.WriteEffective(stdout); err != nil {
+		fmt.Fprintf(stderr, "notarius: write effective configuration: %v\n", err)
+		return 1
+	}
+	return 0
+}
+
+func runConfigExplain(args []string, stdout, stderr io.Writer, opts Options) int {
+	fs := flag.NewFlagSet("config explain", flag.ContinueOnError)
+	fs.SetOutput(io.Discard)
+	configPath := fs.String("config", "", "config file path")
+	profile := fs.String("config-profile", "", "configuration profile")
+	if err := fs.Parse(args); err != nil {
+		fmt.Fprintf(stderr, "notarius: %v\n", err)
+		return 2
+	}
+	if fs.NArg() != 1 {
+		fmt.Fprintln(stderr, "notarius: config explain requires exactly one JSON Pointer")
+		return 2
+	}
+	pointer := fs.Arg(0)
+	parsed, err := configkit.ParsePath(pointer)
+	if err != nil || parsed.String() != pointer {
+		fmt.Fprintf(stderr, "notarius: %q is not a canonical JSON Pointer\n", pointer)
+		return 2
+	}
+	loaded, _, err := loadConfigKit(*configPath, *profile, nil, opts)
+	if err != nil {
+		writeConfigLoadError(stderr, err)
+		return 1
+	}
+	if err := loaded.WriteExplanation(stdout, pointer); err != nil {
+		fmt.Fprintf(stderr, "notarius: write configuration explanation: %v\n", err)
+		return 1
+	}
+	return 0
+}
+
+func runConfigValidate(args []string, stdout, stderr io.Writer, opts Options) int {
+	fs := flag.NewFlagSet("config validate", flag.ContinueOnError)
+	fs.SetOutput(io.Discard)
+	configPath := fs.String("config", "", "config file path")
+	profile := fs.String("config-profile", "", "configuration profile")
+	pipelineID := fs.String("pipeline", "", "pipeline ID")
+	onlyRaw := fs.String("only", "", "comma-separated artifact lanes")
+	if err := fs.Parse(args); err != nil {
+		fmt.Fprintf(stderr, "notarius: %v\n", err)
+		return 2
+	}
+	if fs.NArg() != 0 {
+		fmt.Fprintf(stderr, "notarius: unexpected argument %q\n", fs.Arg(0))
+		return 2
+	}
+	if strings.TrimSpace(*onlyRaw) != "" && strings.TrimSpace(*pipelineID) == "" {
+		fmt.Fprintln(stderr, "notarius: --only requires --pipeline")
+		return 2
+	}
+	only, err := parseOnly(*onlyRaw)
+	if err != nil {
+		fmt.Fprintf(stderr, "notarius: %v\n", err)
+		return 2
+	}
+	loaded, path, err := loadConfigKit(*configPath, *profile, nil, opts)
+	if err != nil {
+		writeConfigLoadError(stderr, err)
+		return 1
+	}
+	if strings.TrimSpace(*pipelineID) == "" {
+		fmt.Fprintf(stdout, "config %q is valid\n", path)
+		return 0
+	}
+	catalog, err := effectiveCatalog(opts)
+	if err != nil {
+		fmt.Fprintf(stderr, "notarius: %v\n", err)
+		return 1
+	}
+	effective, err := loaded.Config.Resolve(config.ResolveInput{PipelineID: *pipelineID, Only: only, Catalog: catalog})
+	if err != nil {
+		fmt.Fprintf(stderr, "notarius: %v\n", err)
+		return 1
+	}
+	if err := validateExplicitPromptKitProfiles(context.Background(), effective.Config, effectiveLLMProfileIDs(effective.ResolvedPipeline), opts.promptKitAssets); err != nil {
+		fmt.Fprintf(stderr, "notarius: %v\n", err)
+		return 1
+	}
+	fmt.Fprintf(stdout, "config %q is valid for pipeline %q\n", path, strings.TrimSpace(*pipelineID))
+	return 0
+}
+
+func runPipelinesList(args []string, stdout, stderr io.Writer, opts Options) int {
+	fs := flag.NewFlagSet("pipelines list", flag.ContinueOnError)
+	fs.SetOutput(io.Discard)
+	configPath := fs.String("config", "", "config file path")
+	profile := fs.String("config-profile", "", "configuration profile")
+	jsonOutput := fs.Bool("json", false, "write JSON output")
+	if err := fs.Parse(args); err != nil {
+		fmt.Fprintf(stderr, "notarius: %v\n", err)
+		return 2
+	}
+	if fs.NArg() != 0 {
+		fmt.Fprintf(stderr, "notarius: unexpected argument %q\n", fs.Arg(0))
+		return 2
+	}
+	loaded, _, err := loadConfigKit(*configPath, *profile, nil, opts)
+	if err != nil {
+		writeConfigLoadError(stderr, err)
+		return 1
+	}
+	ids := sortedPipelineIDs(loaded.Config)
+	if *jsonOutput {
+		payload, err := json.Marshal(struct {
+			Pipelines []string `json:"pipelines"`
+		}{Pipelines: ids})
+		if err != nil {
+			fmt.Fprintf(stderr, "notarius: marshal pipeline list: %v\n", err)
+			return 1
+		}
+		fmt.Fprintf(stdout, "%s\n", payload)
+		return 0
+	}
+	for _, id := range ids {
+		fmt.Fprintln(stdout, id)
+	}
+	return 0
+}

internal/cli/configkit_commands_test.go

@@ -0,0 +1,132 @@
+package cli
+
+import (
+	"bytes"
+	"context"
+	"errors"
+	"io"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
+	"gitea.maximumdirect.net/eric/notarius/internal/core/config"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func TestConfigKitReadOnlyCommandsLoadImportsAndProfiles(t *testing.T) {
+	t.Parallel()
+	root := t.TempDir()
+	path := filepath.Join(root, "notarius.yml")
+	writeConfigKitFile(t, filepath.Join(root, "fragment.yml"), "pipelines:\n  imported:\n    input: {module: input}\n")
+	writeConfigKitFile(t, filepath.Join(root, "profiles", "development.yml"), "pipelines:\n  profiled:\n    input: {module: input}\n")
+	writeConfigKitFile(t, path, "version: 5\nconfigkit:\n  imports:\n    - path: fragment.yml\npipelines:\n  base:\n    input: {module: input}\n")
+	var stdout, stderr bytes.Buffer
+	if code := RunWithOptions([]string{"pipelines", "list", "--config", path, "--config-profile", "development"}, &stdout, &stderr, commandContractOptions(t)); code != 0 || stdout.String() != "base\nimported\nprofiled\n" {
+		t.Fatalf("list = %d, %q, %q", code, stdout.String(), stderr.String())
+	}
+	stdout.Reset()
+	stderr.Reset()
+	if code := RunWithOptions([]string{"config", "validate", "--config", path, "--config-profile", "development"}, &stdout, &stderr, commandContractOptions(t)); code != 0 || !strings.Contains(stdout.String(), "is valid") {
+		t.Fatalf("validate = %d, %q, %q", code, stdout.String(), stderr.String())
+	}
+}
+
+func TestConfigKitReadOnlyCommandsRejectVersionFour(t *testing.T) {
+	t.Parallel()
+	path := filepath.Join(t.TempDir(), "notarius.yml")
+	writeConfigKitFile(t, path, "version: 4\n")
+	var stdout, stderr bytes.Buffer
+	if code := runPipelinesList([]string{"--config", path}, &stdout, &stderr, commandContractOptions(t)); code != 1 || !strings.Contains(stderr.String(), "version") {
+		t.Fatalf("list = %d, %q", code, stderr.String())
+	}
+}
+
+func TestConfigurationInspectionCommandsRenderSafeConfigKitViews(t *testing.T) {
+	t.Parallel()
+	root := t.TempDir()
+	path := filepath.Join(root, "notarius.yml")
+	writeConfigKitFile(t, path, `version: 5
+concurrency:
+  total_llm: 4
+pipelines:
+  "0":
+    input: {module: input}
+`)
+	writeConfigKitFile(t, filepath.Join(root, "profiles", "development.yml"), "concurrency:\n  total_llm: 3\n")
+	writeConfigKitFile(t, filepath.Join(root, "profiles", "retired.yml"), "pipelines: null\n")
+
+	providerCalled := false
+	opts := commandContractOptions(t)
+	opts.LLMClientFactory = func(context.Context, config.Config, string, LLMRuntimeOverrides) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
+		providerCalled = true
+		return nil, nil, errors.New("LLM client must not be constructed")
+	}
+
+	var stdout, stderr bytes.Buffer
+	if code := RunWithOptions([]string{"config", "effective", "--config", path, "--config-profile", "development"}, &stdout, &stderr, opts); code != 0 || !strings.Contains(stdout.String(), "total_llm: 3") || stderr.Len() != 0 {
+		t.Fatalf("effective = %d, %q, %q", code, stdout.String(), stderr.String())
+	}
+	if providerCalled {
+		t.Fatal("config effective constructed an LLM client")
+	}
+
+	stdout.Reset()
+	stderr.Reset()
+	if code := RunWithOptions([]string{"config", "explain", "--config", path, "--config-profile", "development", "/concurrency/total_llm"}, &stdout, &stderr, opts); code != 0 || !strings.Contains(stdout.String(), `path: "/concurrency/total_llm"`) || stderr.Len() != 0 {
+		t.Fatalf("explain effective = %d, %q, %q", code, stdout.String(), stderr.String())
+	}
+
+	stdout.Reset()
+	stderr.Reset()
+	if code := RunWithOptions([]string{"config", "explain", "--config", path, ""}, &stdout, &stderr, opts); code != 0 || !strings.Contains(stdout.String(), `path: ""`) || stderr.Len() != 0 {
+		t.Fatalf("explain root = %d, %q, %q", code, stdout.String(), stderr.String())
+	}
+
+	stdout.Reset()
+	stderr.Reset()
+	if code := RunWithOptions([]string{"config", "explain", "--config", path, "--config-profile", "retired", "/pipelines/0"}, &stdout, &stderr, opts); code != 0 || !strings.Contains(stdout.String(), `path: "/pipelines/0"`) || stderr.Len() != 0 {
+		t.Fatalf("explain removed mapping key = %d, %q, %q", code, stdout.String(), stderr.String())
+	}
+}
+
+func TestConfigExplainRejectsInvalidAndUnknownPointers(t *testing.T) {
+	t.Parallel()
+	path := writeCommandConfig(t, "session", "other")
+	for _, test := range []struct {
+		name     string
+		pointer  string
+		wantCode int
+	}{
+		{name: "missing", wantCode: 2},
+		{name: "malformed escape", pointer: "/pipelines~2session", wantCode: 2},
+		{name: "unknown", pointer: "/unknown", wantCode: 1},
+		{name: "invalid sequence index", pointer: "/pipelines/session/steps/+0", wantCode: 1},
+	} {
+		t.Run(test.name, func(t *testing.T) {
+			var stdout, stderr bytes.Buffer
+			args := []string{"config", "explain", "--config", path}
+			if test.name != "missing" {
+				args = append(args, test.pointer)
+			}
+			if code := RunWithOptions(args, &stdout, &stderr, commandContractOptions(t)); code != test.wantCode || stdout.Len() != 0 || stderr.Len() == 0 {
+				t.Fatalf("code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
+			}
+		})
+	}
+}
+
+func TestConfigInspectionCommandsReportWriterFailures(t *testing.T) {
+	t.Parallel()
+	path := writeCommandConfig(t, "session", "other")
+	var stderr bytes.Buffer
+	if code := RunWithOptions([]string{"config", "effective", "--config", path}, failingInspectionWriter{}, &stderr, commandContractOptions(t)); code != 1 || !strings.Contains(stderr.String(), "write effective configuration") {
+		t.Fatalf("effective writer failure = %d, %q", code, stderr.String())
+	}
+}
+
+type failingInspectionWriter struct{}
+
+func (failingInspectionWriter) Write([]byte) (int, error) {
+	return 0, io.ErrClosedPipe
+}

internal/cli/configkit_load.go

@@ -0,0 +1,49 @@
+package cli
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"os"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+	"gitea.maximumdirect.net/eric/notarius/internal/core/config"
+)
+
+func loadConfigKit(configPath, profile string, overrides []configkit.Override, opts Options) (*config.LoadedConfig, string, error) {
+	path, err := discoverConfigPath(configPath, opts)
+	if err != nil {
+		return nil, "", err
+	}
+	workingDirectory, err := os.Getwd()
+	if err != nil {
+		return nil, "", fmt.Errorf("determine invocation directory: %w", err)
+	}
+	loaded, err := config.Load(path, config.LoadOptions{Profile: profile, Overrides: overrides, InvocationDirectory: workingDirectory})
+	if err != nil {
+		return nil, "", err
+	}
+	return loaded, path, nil
+}
+
+func writeConfigLoadError(output io.Writer, err error) {
+	var loadError *configkit.LoadError
+	if errors.As(err, &loadError) {
+		if writeErr := configkit.WriteDiagnostics(output, loadError.Diagnostics()); writeErr == nil {
+			// ConfigKit's locations contain source IDs. Keep its renderer and
+			// supply the acquired-source legend so imported/profile errors can
+			// be traced to a file. Quoting also escapes terminal controls.
+			for _, source := range loadError.Sources() {
+				label := source.Path
+				if label == "" {
+					label = source.Label
+				}
+				if _, err := fmt.Fprintf(output, "source %q: %q\n", source.ID, label); err != nil {
+					return
+				}
+			}
+			return
+		}
+	}
+	fmt.Fprintf(output, "notarius: %v\n", err)
+}

internal/cli/configkit_load_test.go

@@ -0,0 +1,85 @@
+package cli
+
+import (
+	"bytes"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"testing"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+)
+
+func TestConfigLoadDiagnosticsIdentifyComposedSources(t *testing.T) {
+	t.Parallel()
+	for _, profile := range []bool{false, true} {
+		t.Run(strconv.FormatBool(profile), func(t *testing.T) {
+			root := t.TempDir()
+			main := filepath.Join(root, "config.yml")
+			fragment := filepath.Join(root, "pipeline\n\x1b.yml")
+			args := []string{"config", "validate", "--config", main}
+			if profile {
+				fragment = filepath.Join(root, "profiles", "development.yml")
+				writeConfigKitFile(t, main, "version: 5\n")
+				args = append(args, "--config-profile", "development")
+			} else {
+				writeConfigKitFile(t, main, "version: 5\nconfigkit:\n  imports:\n    - path: "+strconv.Quote(filepath.Base(fragment))+"\n")
+			}
+			writeConfigKitFile(t, fragment, "concurrency: {total_llm: invalid-private-value}\n")
+			var stdout, stderr bytes.Buffer
+			if code := RunWithOptions(args, &stdout, &stderr, commandContractOptions(t)); code != 1 {
+				t.Fatalf("status = %d; %s", code, stderr.String())
+			}
+			got := stderr.String()
+			if stdout.Len() != 0 || !strings.Contains(got, "decode.type") ||
+				!strings.Contains(got, "source-2:1:") ||
+				!strings.Contains(got, strconv.Quote(fragment)) ||
+				strings.Contains(got, "invalid-private-value") ||
+				strings.ContainsRune(got, '\x1b') {
+				t.Fatalf("stdout = %q; stderr = %q", stdout.String(), got)
+			}
+		})
+	}
+}
+
+func TestLoadConfigKitUsesDiscoveryProfileAndOverrides(t *testing.T) {
+	t.Parallel()
+	root := t.TempDir()
+	path := filepath.Join(root, "notarius.yml")
+	writeConfigKitFile(t, path, "version: 5\npipelines:\n  base:\n    input: {module: input}\n")
+	profiles := filepath.Join(root, "profiles")
+	writeConfigKitFile(t, filepath.Join(profiles, "development.yml"), "pipelines:\n  profiled:\n    input: {module: input}\n")
+	loaded, gotPath, err := loadConfigKit(path, "development", []configkit.Override{{Path: configkit.Keys("output", "directory"), Value: "generated", Flag: "--output"}}, commandContractOptions(t))
+	if err != nil {
+		t.Fatalf("loadConfigKit() error = %v", err)
+	}
+	if gotPath != path || loaded.Config.Pipelines["profiled"].Input.Module != "input" || loaded.Config.Output.Directory == "generated" {
+		t.Fatalf("loaded = %#v, path=%q", loaded.Config, gotPath)
+	}
+}
+
+func TestWriteConfigLoadErrorUsesSafeDiagnostics(t *testing.T) {
+	t.Parallel()
+	path := filepath.Join(t.TempDir(), "invalid.yml")
+	writeConfigKitFile(t, path, "version: 4\n")
+	_, _, err := loadConfigKit(path, "", nil, commandContractOptions(t))
+	if err == nil {
+		t.Fatal("loadConfigKit() error = nil")
+	}
+	var output bytes.Buffer
+	writeConfigLoadError(&output, err)
+	if !strings.Contains(output.String(), "version") || strings.Contains(output.String(), "notarius: configkit") {
+		t.Fatalf("diagnostics = %q", output.String())
+	}
+}
+
+func writeConfigKitFile(t *testing.T, path, contents string) {
+	t.Helper()
+	if err := os.MkdirAll(filepath.Dir(path), 0o700); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(path, []byte(contents), 0o600); err != nil {
+		t.Fatal(err)
+	}
+}

internal/cli/dnd_enemy_events_contract_test.go

@@ -264,13 +264,29 @@ func completeExampleConfigWithTemporaryCache(t *testing.T) string {
 	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"),
+		"./llm-profiles/dnd-extraction.yml": repositoryPath("examples", "llm-profiles", "dnd-extraction.yml"),
 	} {
 		updated = strings.ReplaceAll(updated, relative, fmt.Sprintf("%q", absolute))
 	}
-	path := filepath.Join(t.TempDir(), "dnd-complete.config.yml")
+	root := t.TempDir()
+	fragment, err := os.ReadFile(repositoryPath("examples", "pipelines", "dnd-session.yml"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	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"),
+	} {
+		fragment = []byte(strings.ReplaceAll(string(fragment), relative, fmt.Sprintf("%q", absolute)))
+	}
+	if err := os.MkdirAll(filepath.Join(root, "pipelines"), 0o700); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(root, "pipelines", "dnd-session.yml"), fragment, 0o600); err != nil {
+		t.Fatal(err)
+	}
+	path := filepath.Join(root, "dnd-complete.config.yml")
 	if err := os.WriteFile(path, []byte(updated), 0o600); err != nil {
 		t.Fatal(err)
 	}

internal/cli/example_contract_test.go

@@ -147,8 +147,15 @@ func TestMaintainedConfigurationExampleSet(t *testing.T) {
 		}
 	}
 	sort.Strings(names)
-	if got := strings.Join(names, ","); got != "dnd-extraction.yml" {
-		t.Fatalf("maintained operator profiles = %q, want dnd-extraction.yml", got)
+	if got := strings.Join(names, ","); got != "development.yml" {
+		t.Fatalf("maintained configuration profiles = %q, want development.yml", got)
+	}
+	llmProfiles, err := os.ReadDir(repositoryPath("examples", "llm-profiles"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(llmProfiles) != 1 || llmProfiles[0].Name() != "dnd-extraction.yml" {
+		t.Fatalf("maintained LLM profiles = %#v, want dnd-extraction.yml", llmProfiles)
 	}
 }
 

internal/cli/npc_registry_contract_test.go

@@ -23,7 +23,7 @@ func TestOversizedNPCRegistryFailsBeforeRuntimeAndCheckpointConstruction(t *test
 		t.Fatal(err)
 	}
 	checkpointRoot := filepath.Join(t.TempDir(), "checkpoints")
-	content := fmt.Sprintf(`version: 4
+	content := fmt.Sprintf(`version: 5
 cache:
   chunk_plans:
     mode: bypass
@@ -32,14 +32,17 @@ cache:
     directory: %q
 pipelines:
   dnd-session:
-    input: seriatim
+    input:
+      module: seriatim
     artifacts:
       spells:
         extract:
           module: dnd/spells
           references:
-            npc_registry: %q
-        normalize: dnd/spells
+            npc_registry:
+              path: %q
+        normalize:
+          module: dnd/spells
 `, checkpointRoot, npcPath)
 	configPath := filepath.Join(t.TempDir(), "config.yml")
 	if err := os.WriteFile(configPath, []byte(content), 0o600); err != nil {

internal/cli/production_contract_test.go

@@ -19,8 +19,6 @@ import (
 	"testing/fstest"
 	"time"
 
-	"gopkg.in/yaml.v3"
-
 	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
 	"gitea.maximumdirect.net/eric/notarius/internal/core/config"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/chunkmap"
@@ -333,61 +331,8 @@ func TestProductionPromptAssetsPrepareWithoutProviderCredentials(t *testing.T) {
 	if err != nil {
 		t.Fatalf("production prompt engine: %v", err)
 	}
-	promptFS, err := components.assets.PromptFS()
-	if err != nil {
-		t.Fatalf("production prompt assets: %v", err)
-	}
-	type manifest struct {
-		ID      string `yaml:"id"`
-		Version string `yaml:"version"`
-		Inputs  []struct {
-			Name string `yaml:"name"`
-		} `yaml:"inputs"`
-		Messages []struct {
-			Role string `yaml:"role"`
-		} `yaml:"messages"`
-	}
-	preparedPrompts := 0
-	if err := fs.WalkDir(promptFS, ".", func(path string, entry fs.DirEntry, walkErr error) error {
-		if walkErr != nil {
-			return walkErr
-		}
-		if entry.IsDir() || filepath.Base(path) != "prompt.yaml" {
-			return nil
-		}
-		data, err := fs.ReadFile(promptFS, path)
-		if err != nil {
-			return err
-		}
-		var prompt manifest
-		if err := yaml.Unmarshal(data, &prompt); err != nil {
-			return err
-		}
-		for _, message := range prompt.Messages {
-			if message.Role != promptkit.RoleSystem && message.Role != promptkit.RoleUser {
-				return fmt.Errorf("production prompt %q uses role %q, want system or user", prompt.ID, message.Role)
-			}
-		}
-		inputs := make(map[string]promptkit.ArtifactRef, len(prompt.Inputs))
-		for _, input := range prompt.Inputs {
-			inputs[input.Name] = promptkit.Inline(`{}`)
-		}
-		prepared, err := engine.Prepare(context.Background(), promptkit.RunRequest{
-			PromptID: prompt.ID, PromptVersion: prompt.Version, ProfileID: "assembled-prompt-test", Inputs: inputs,
-		})
-		if err != nil {
-			return fmt.Errorf("prepare production prompt %q: %w", prompt.ID, err)
-		}
-		if prepared.OutputContract.RepairAttempts != 1 {
-			return fmt.Errorf("prompt %q repair attempts = %d, want 1", prompt.ID, prepared.OutputContract.RepairAttempts)
-		}
-		preparedPrompts++
-		return nil
-	}); err != nil {
-		t.Fatal(err)
-	}
-	if preparedPrompts == 0 {
-		t.Fatal("prepared no production prompts")
+	if engine == nil {
+		t.Fatal("production PromptKit engine is nil")
 	}
 }
 
@@ -737,13 +682,13 @@ func TestProductionConfigValidationCoversModuleAndVariantFailures(t *testing.T)
 	}{
 		{
 			name:      "unknown module",
-			content:   replaceRequiredOnce(t, base, "    input: seriatim\n", "    input: missing/input\n"),
+			content:   replaceRequiredOnce(t, base, "    input:\n      module: seriatim\n", "    input:\n      module: missing/input\n"),
 			options:   productionCLIOptions(t),
 			fragments: []string{"pipeline \"dnd-session\"", "input", "missing/input"},
 		},
 		{
 			name:      "unknown validator",
-			content:   replaceRequiredOnce(t, base, "        extract: dnd/spells\n", "        extract:\n          module: dnd/spells\n          validators:\n            - module: missing/validator\n"),
+			content:   replaceRequiredOnce(t, base, "        extract:\n          module: dnd/spells\n", "        extract:\n          module: dnd/spells\n          validators:\n            - module: missing/validator\n"),
 			options:   productionCLIOptions(t),
 			fragments: []string{"validator", "missing/validator"},
 		},
@@ -755,7 +700,7 @@ func TestProductionConfigValidationCoversModuleAndVariantFailures(t *testing.T)
 		},
 		{
 			name:      "deterministic validator with profile",
-			content:   replaceRequiredOnce(t, base, "        extract: dnd/spells\n", "        extract:\n          module: dnd/spells\n          validators:\n            - module: generic/valid_json\n              llm_profile: forbidden-profile\n"),
+			content:   replaceRequiredOnce(t, base, "        extract:\n          module: dnd/spells\n", "        extract:\n          module: dnd/spells\n          validators:\n            - module: generic/valid_json\n              llm_profile: forbidden-profile\n"),
 			options:   productionCLIOptions(t),
 			fragments: []string{"deterministic validator", "llm_profile"},
 		},
@@ -779,7 +724,7 @@ func TestProductionConfigValidationCoversModuleAndVariantFailures(t *testing.T)
 
 func TestProductionNormalizeValidatorOverrideRemainsAuthoritative(t *testing.T) {
 	base := string(readRepositoryFile(t, "examples", "dnd-minimal.config.yml"))
-	content := replaceRequiredOnce(t, base, "        normalize: dnd/spells\n", "        normalize:\n          module: dnd/spells\n          validators:\n            - module: generic/always_accept\n            - module: generic/valid_json\n")
+	content := replaceRequiredOnce(t, base, "        normalize:\n          module: dnd/spells\n", "        normalize:\n          module: dnd/spells\n          validators:\n            - module: generic/always_accept\n            - module: generic/valid_json\n")
 	path := writeProductionContractConfig(t, content)
 	components := productionTestComponents(t)
 	effective, err := loadMaintainedExample(t, path).Resolve(resolveInputForMaintainedExample(components, "dnd-session"))
@@ -879,7 +824,7 @@ func maintainedExampleFiles(t *testing.T) []maintainedExample {
 
 func productionSpellCatalogContractConfig(t *testing.T) string {
 	t.Helper()
-	return fmt.Sprintf(`version: 4
+	return fmt.Sprintf(`version: 5
 cache:
   chunk_plans:
     mode: bypass
@@ -888,21 +833,26 @@ cache:
     directory: ""
 pipelines:
   dnd-session:
-    input: seriatim
+    input:
+      module: seriatim
     references:
-      party: %q
-      glossary: %q
+      party:
+        path: %q
+      glossary:
+        path: %q
     artifacts:
       spells:
         extract:
           module: dnd/spells
           retries: 2
           references:
-            spell_catalog: %q
+            spell_catalog:
+              path: %q
         normalize:
           module: dnd/spells
           references:
-            spell_catalog: %q
+            spell_catalog:
+              path: %q
 `, repositoryPath("examples", "dnd-party.txt"), repositoryPath("examples", "dnd-glossary.txt"), repositoryPath("examples", "dnd-spell-catalog.json"), repositoryPath("examples", "dnd-spell-catalog.json"))
 }
 
@@ -913,14 +863,11 @@ func writeProductionSpellCatalogContractConfig(t *testing.T) string {
 
 func loadMaintainedExample(t *testing.T, path string) config.Config {
 	t.Helper()
-	fileConfig, err := config.LoadFileConfig(path)
+	loaded, err := config.Load(path, config.LoadOptions{})
 	if err != nil {
 		t.Fatalf("load maintained config %q: %v", path, err)
 	}
-	cfg := config.Default()
-	if err := cfg.ApplyFileConfig(fileConfig); err != nil {
-		t.Fatalf("apply maintained config %q: %v", path, err)
-	}
+	cfg := loaded.RuntimeConfig()
 	if err := cfg.Validate(); err != nil {
 		t.Fatalf("validate maintained config %q: %v", path, err)
 	}
@@ -977,7 +924,7 @@ func productionRunOptions(t *testing.T, fake *productionFakeLLMClient) Options {
 }
 
 func productionRunConfig(outputRoot, chunkModule string) string {
-	return fmt.Sprintf(`version: 4
+	return fmt.Sprintf(`version: 5
 output:
   directory: %q
 cache:
@@ -988,8 +935,10 @@ debug:
   directory: %q
 pipelines:
   dnd-session:
-    input: seriatim
-    chunk: %s
+    input:
+      module: seriatim
+    chunk:
+      module: %s
     output:
       module: json
       options:
@@ -998,8 +947,10 @@ pipelines:
       - id: identify-items
         artifacts:
           item-registry:
-            extract: dnd/item-registry
-            normalize: dnd/item-registry
+            extract:
+              module: dnd/item-registry
+            normalize:
+              module: dnd/item-registry
       - id: extract-occurrences
         references:
           item_registry:
@@ -1008,9 +959,11 @@ pipelines:
               lane: item-registry
         artifacts:
           spells:
-            extract: dnd/spells
+            extract:
+              module: dnd/spells
           item-occurrences:
-            extract: dnd/item-occurrences
+            extract:
+              module: dnd/item-occurrences
 `, outputRoot, filepath.Join(filepath.Dir(outputRoot), "debug"), chunkModule)
 }
 

internal/cli/recompute_execution_contract_test.go

@@ -194,7 +194,7 @@ func (recomputeTestOutput) Encode(_ context.Context, req contracts.OutputRequest
 func newRecomputeTestRoots(t *testing.T) stateTestRoots {
 	t.Helper()
 	roots := newStateTestRoots(t)
-	config := fmt.Sprintf(`version: 4
+	config := fmt.Sprintf(`version: 5
 output:
   directory: %q
 cache:
@@ -208,19 +208,27 @@ debug:
   directory: %q
 pipelines:
   sample:
-    input: test/input
-    chunk: test/chunk
+    input:
+      module: test/input
+    chunk:
+      module: test/chunk
     steps:
       - id: first
         artifacts:
           producer:
-            extract: test/extract/producer
-            merge: test/merge
-            normalize: test/normalize
+            extract:
+              module: test/extract/producer
+            merge:
+              module: test/merge
+            normalize:
+              module: test/normalize
           unrelated:
-            extract: test/extract/unrelated
-            merge: test/merge
-            normalize: test/normalize
+            extract:
+              module: test/extract/unrelated
+            merge:
+              module: test/merge
+            normalize:
+              module: test/normalize
       - id: second
         references:
           upstream:
@@ -229,9 +237,12 @@ pipelines:
               lane: producer
         artifacts:
           middle:
-            extract: test/extract/middle
-            merge: test/merge
-            normalize: test/normalize
+            extract:
+              module: test/extract/middle
+            merge:
+              module: test/merge
+            normalize:
+              module: test/normalize
       - id: third
         references:
           upstream:
@@ -240,10 +251,14 @@ pipelines:
               lane: middle
         artifacts:
           dependent:
-            extract: test/extract/dependent
-            merge: test/merge
-            normalize: test/normalize
-    output: test/recompute-output
+            extract:
+              module: test/extract/dependent
+            merge:
+              module: test/merge
+            normalize:
+              module: test/normalize
+    output:
+      module: test/recompute-output
 `, roots.output, roots.plans, roots.checkpoints, roots.debug)
 	if err := os.WriteFile(roots.config, []byte(config), 0o600); err != nil {
 		t.Fatal(err)

internal/cli/reference_contract_test.go

@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"os"
 	"path/filepath"
+	"slices"
 	"strings"
 	"testing"
 
@@ -14,20 +15,16 @@ import (
 
 func TestReferenceSelectorsParseAndApplyAllDocumentedForms(t *testing.T) {
 	tests := []struct {
-		name      string
-		selector  string
-		only      []string
-		wantStage pipeline.ModuleStage
-		wantLane  string
-		wantSlot  string
+		name     string
+		selector string
+		want     []string
 	}{
-		{name: "flat", selector: "alpha-slot", wantStage: pipeline.StageExtract, wantLane: "alpha", wantSlot: "alpha-slot"},
-		{name: "chunk", selector: "chunk.chunk-slot", wantStage: pipeline.StageChunk, wantSlot: "chunk-slot"},
-		{name: "merge", selector: "merge.alpha-merge", only: []string{"alpha"}, wantStage: pipeline.StageMerge, wantLane: "alpha", wantSlot: "alpha-merge"},
-		{name: "lane", selector: "alpha.alpha-slot", wantStage: pipeline.StageExtract, wantLane: "alpha", wantSlot: "alpha-slot"},
-		{name: "lane extract", selector: "alpha.extract.alpha-slot", wantStage: pipeline.StageExtract, wantLane: "alpha", wantSlot: "alpha-slot"},
-		{name: "lane merge", selector: "alpha.merge.alpha-merge", wantStage: pipeline.StageMerge, wantLane: "alpha", wantSlot: "alpha-merge"},
-		{name: "lane normalize", selector: "alpha.normalize.alpha-normalize", wantStage: pipeline.StageNormalize, wantLane: "alpha", wantSlot: "alpha-normalize"},
+		{name: "pipeline", selector: "shared", want: []string{"alpha.extract.shared", "alpha.merge.shared", "alpha.normalize.shared", "beta.extract.shared", "beta.merge.shared", "beta.normalize.shared"}},
+		{name: "chunk", selector: "chunk.chunk-slot", want: []string{"chunk.chunk-slot"}},
+		{name: "lane", selector: "alpha.shared", want: []string{"alpha.extract.shared", "alpha.merge.shared", "alpha.normalize.shared"}},
+		{name: "lane extract", selector: "alpha.extract.alpha-slot", want: []string{"alpha.extract.alpha-slot"}},
+		{name: "lane merge", selector: "alpha.merge.alpha-merge", want: []string{"alpha.merge.alpha-merge"}},
+		{name: "lane normalize", selector: "alpha.normalize.alpha-normalize", want: []string{"alpha.normalize.alpha-normalize"}},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
@@ -37,70 +34,135 @@ func TestReferenceSelectorsParseAndApplyAllDocumentedForms(t *testing.T) {
 			if err != nil {
 				t.Fatal(err)
 			}
-			overrides, _, err := resolveCLIReferenceRequests(cfg, "demo", tt.only, catalog, []cliReferenceRequest{{Selector: selector, Source: "reference.txt"}}, nil)
+			overrides, _, err := resolveCLIReferenceRequests(cfg, "demo", nil, catalog, []cliReferenceRequest{{Selector: selector, Source: "reference.txt"}}, nil)
 			if err != nil {
 				t.Fatalf("resolve selector: %v", err)
 			}
-			if len(overrides) != 1 {
-				t.Fatalf("overrides = %#v, want one binding", overrides)
+			if got := referenceContractBindingLabels(overrides); !slices.Equal(got, tt.want) {
+				t.Fatalf("binding targets = %#v, want %#v", got, tt.want)
 			}
-			got := overrides[0]
-			if got.Stage != tt.wantStage || got.LaneID != tt.wantLane || got.SlotName != tt.wantSlot || got.BindingSource != contracts.ReferenceBindingSourceCLI {
-				t.Fatalf("binding = %#v, want %s/%s/%s from CLI", got, tt.wantStage, tt.wantLane, tt.wantSlot)
-			}
-		})
-	}
-}
-
-func TestReferenceSelectorsRejectAmbiguityWithSpecificSuggestions(t *testing.T) {
-	cfg := referenceContractConfig()
-	catalog := referenceContractCatalog(t, true, true)
-	for _, tt := range []struct {
-		name     string
-		selector string
-		want     []string
-	}{
-		{name: "flat shared slot", selector: "shared", want: []string{"alpha.extract.shared", "beta.extract.shared"}},
-		{name: "lane shared slot", selector: "alpha.shared", want: []string{"alpha.extract.shared", "alpha.merge.shared", "alpha.normalize.shared"}},
-		{name: "all mergers", selector: "merge.shared", want: []string{"alpha.merge.shared", "beta.merge.shared"}},
-	} {
-		t.Run(tt.name, func(t *testing.T) {
-			selector, err := parseReferenceSelector(tt.selector, "--reference")
-			if err != nil {
-				t.Fatal(err)
-			}
-			_, _, err = resolveCLIReferenceRequests(cfg, "demo", nil, catalog, []cliReferenceRequest{{Selector: selector, Source: "reference.txt"}}, nil)
-			if err == nil {
-				t.Fatal("resolve selector succeeded, want ambiguity error")
-			}
-			for _, fragment := range tt.want {
-				if !strings.Contains(err.Error(), fragment) {
-					t.Fatalf("error = %q, want suggestion %q", err, fragment)
+			for _, binding := range overrides {
+				if binding.Source != "reference.txt" || binding.BindingSource != contracts.ReferenceBindingSourceCLI {
+					t.Fatalf("binding = %#v, want CLI source", binding)
 				}
 			}
 		})
 	}
 }
 
-func TestReferenceSelectorsRespectSelectedLanesBeforeMaterialization(t *testing.T) {
+func TestReferenceSelectorSpecificityAndFinalOccurrenceChooseConcreteBindings(t *testing.T) {
+	cfg := referenceContractConfig()
+	catalog := referenceContractCatalog(t, true, true)
+	requests := []cliReferenceRequest{
+		{Selector: mustParseReferenceSelector(t, "shared", "--reference"), Source: "pipeline-first.txt"},
+		{Selector: mustParseReferenceSelector(t, "shared", "--reference"), Source: "pipeline-final.txt"},
+		{Selector: mustParseReferenceSelector(t, "alpha.shared", "--reference"), Source: "lane.txt"},
+		{Selector: mustParseReferenceSelector(t, "alpha.extract.shared", "--reference"), Source: "binding.txt"},
+	}
+	overrides, unbinds, err := resolveCLIReferenceRequests(cfg, "demo", nil, catalog, requests, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(unbinds) != 0 {
+		t.Fatalf("unbinds = %#v, want none", unbinds)
+	}
+	want := map[string]string{
+		"alpha.extract.shared":   "binding.txt",
+		"alpha.merge.shared":     "lane.txt",
+		"alpha.normalize.shared": "lane.txt",
+		"beta.extract.shared":    "pipeline-final.txt",
+		"beta.merge.shared":      "pipeline-final.txt",
+		"beta.normalize.shared":  "pipeline-final.txt",
+	}
+	for _, binding := range overrides {
+		label := referenceContractBindingLabel(binding)
+		if binding.Source != want[label] {
+			t.Fatalf("binding %s source = %q, want %q", label, binding.Source, want[label])
+		}
+		delete(want, label)
+	}
+	if len(want) != 0 {
+		t.Fatalf("missing bindings: %#v", want)
+	}
+}
+
+func TestCompleteDNDSharedCLIReferencesExpandAcrossCompatibleTargets(t *testing.T) {
+	cfg := loadMaintainedExample(t, repositoryPath("examples", "dnd-complete.config.yml"))
+	catalog := catalogFromRegistries(productionTestComponents(t).registries)
+	sources := map[string]string{
+		"party":         "/references/party.txt",
+		"players":       "/references/players.txt",
+		"glossary":      "/references/glossary.txt",
+		"spell_catalog": "/references/spells.json",
+	}
+	requests := make([]cliReferenceRequest, 0, len(sources))
+	for _, slot := range []string{"party", "players", "glossary", "spell_catalog"} {
+		requests = append(requests, cliReferenceRequest{
+			Selector: mustParseReferenceSelector(t, slot, "--reference"),
+			Source:   sources[slot],
+		})
+	}
+	overrides, unbinds, err := resolveCLIReferenceRequests(cfg, "dnd-session", nil, catalog, requests, nil)
+	if err != nil {
+		t.Fatalf("expand complete D&D references: %v", err)
+	}
+	if len(unbinds) != 0 {
+		t.Fatalf("unbinds = %#v, want none", unbinds)
+	}
+
+	actual := make(map[string]pipeline.ReferenceBinding, len(overrides))
+	for _, binding := range overrides {
+		actual[referenceContractBindingLabel(binding)] = binding
+	}
+	targets, err := selectedReferenceTargets(cfg, "dnd-session", nil, catalog)
+	if err != nil {
+		t.Fatal(err)
+	}
+	matched := make(map[string]int, len(sources))
+	for _, target := range targets {
+		for slot, sourcePath := range sources {
+			if _, ok := target.slots[slot]; !ok {
+				continue
+			}
+			matched[slot]++
+			label := targetLabel(target) + "." + slot
+			binding, ok := actual[label]
+			if !ok || binding.Source != sourcePath || binding.BindingSource != contracts.ReferenceBindingSourceCLI {
+				t.Fatalf("binding %q = %#v, want CLI source %q", label, binding, sourcePath)
+			}
+		}
+	}
+	for slot := range sources {
+		if matched[slot] < 2 {
+			t.Fatalf("reference %q matched %d target(s), want a shared D&D reference", slot, matched[slot])
+		}
+	}
+	if _, err := cfg.Resolve(config.ResolveInput{PipelineID: "dnd-session", Catalog: catalog, ReferenceOverrides: overrides}); err != nil {
+		t.Fatalf("resolve complete D&D CLI references: %v", err)
+	}
+}
+
+func TestReferenceSelectorsRejectInvalidOrUnselectedScopesBeforeMaterialization(t *testing.T) {
 	cfg := referenceContractConfig()
 	catalog := referenceContractCatalog(t, true, true)
 	for _, tt := range []struct {
 		name     string
 		selector string
+		only     []string
 		want     string
 	}{
-		{name: "unselected lane", selector: "beta.extract.beta-slot", want: `reference lane "beta" is not selected`},
+		{name: "pipeline slot", selector: "missing", want: `reference slot "missing" is not declared by any selected target`},
+		{name: "lane slot", selector: "alpha.missing", want: `reference slot "missing" is not declared by selected lane "alpha"`},
+		{name: "binding slot", selector: "alpha.extract.missing", want: `reference slot "missing" is not declared`},
+		{name: "former merge shorthand", selector: "merge.shared", want: `reference lane "merge" is not selected`},
+		{name: "unselected lane", selector: "beta.extract.beta-slot", only: []string{"alpha"}, want: `reference lane "beta" is not selected`},
 		{name: "unknown lane", selector: "missing.extract.beta-slot", want: `reference lane "missing" is not selected`},
 	} {
 		t.Run(tt.name, func(t *testing.T) {
-			selector, err := parseReferenceSelector(tt.selector, "--reference")
-			if err != nil {
-				t.Fatal(err)
-			}
-			_, _, err = resolveCLIReferenceRequests(cfg, "demo", []string{"alpha"}, catalog, []cliReferenceRequest{{Selector: selector, Source: filepath.Join(t.TempDir(), "missing.txt")}}, nil)
+			selector := mustParseReferenceSelector(t, tt.selector, "--reference")
+			_, _, err := resolveCLIReferenceRequests(cfg, "demo", tt.only, catalog, []cliReferenceRequest{{Selector: selector, Source: filepath.Join(t.TempDir(), "missing.txt")}}, nil)
 			if err == nil || !strings.Contains(err.Error(), tt.want) || strings.Contains(err.Error(), "missing.txt") {
-				t.Fatalf("error = %v, want selection failure before file access", err)
+				t.Fatalf("error = %v, want selection failure containing %q before file access", err, tt.want)
 			}
 		})
 	}
@@ -131,40 +193,50 @@ func TestReferenceSyntaxErrorsReturnTwo(t *testing.T) {
 	}
 }
 
-func TestReferenceOverridesUseFinalExactTargetBinding(t *testing.T) {
+func TestReferenceBindAndUnbindSpecificity(t *testing.T) {
 	cfg := referenceContractConfig()
 	catalog := referenceContractCatalog(t, true, true)
-	alphaShared, err := parseReferenceSelector("alpha.extract.shared", "--reference")
-	if err != nil {
-		t.Fatal(err)
-	}
-	betaShared, err := parseReferenceSelector("beta.extract.shared", "--reference")
-	if err != nil {
-		t.Fatal(err)
-	}
-	overrides, unbinds, err := resolveCLIReferenceRequests(cfg, "demo", nil, catalog, []cliReferenceRequest{
-		{Selector: alphaShared, Source: "alpha-first.txt"},
-		{Selector: alphaShared, Source: "alpha-final.txt"},
-		{Selector: betaShared, Source: "beta-only.txt"},
-	}, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if len(unbinds) != 0 {
-		t.Fatalf("unbinds = %#v, want none", unbinds)
-	}
-	effective, err := cfg.Resolve(config.ResolveInput{PipelineID: "demo", Catalog: catalog, ReferenceOverrides: overrides})
-	if err != nil {
-		t.Fatalf("resolve pipeline: %v", err)
-	}
-	alpha := referenceContractLane(t, effective.ResolvedPipeline, "alpha")
-	beta := referenceContractLane(t, effective.ResolvedPipeline, "beta")
-	if source := referenceContractBindingSource(alpha.ExtractReferences.Bindings, "shared"); source != "alpha-final.txt" {
-		t.Fatalf("alpha shared source = %q, want final exact-target override", source)
-	}
-	if source := referenceContractBindingSource(beta.ExtractReferences.Bindings, "shared"); source != "beta-only.txt" {
-		t.Fatalf("beta shared source = %q, want target-specific override", source)
-	}
+	t.Run("specific unbind carves out broad binding", func(t *testing.T) {
+		overrides, unbinds, err := resolveCLIReferenceRequests(cfg, "demo", nil, catalog,
+			[]cliReferenceRequest{{Selector: mustParseReferenceSelector(t, "shared", "--reference"), Source: "shared.txt"}},
+			[]cliReferenceUnbindRequest{{Selector: mustParseReferenceSelector(t, "alpha.extract.shared", "--without-reference")}},
+		)
+		if err != nil {
+			t.Fatal(err)
+		}
+		if got := referenceContractBindingLabels(overrides); slices.Contains(got, "alpha.extract.shared") || len(got) != 5 {
+			t.Fatalf("overrides = %#v, want all shared targets except alpha extract", got)
+		}
+		if got := referenceContractUnbindLabels(unbinds); !slices.Equal(got, []string{"alpha.extract.shared"}) {
+			t.Fatalf("unbinds = %#v, want alpha extract", got)
+		}
+	})
+
+	t.Run("specific binding restores broad unbind", func(t *testing.T) {
+		overrides, unbinds, err := resolveCLIReferenceRequests(cfg, "demo", nil, catalog,
+			[]cliReferenceRequest{{Selector: mustParseReferenceSelector(t, "alpha.extract.shared", "--reference"), Source: "alpha.txt"}},
+			[]cliReferenceUnbindRequest{{Selector: mustParseReferenceSelector(t, "shared", "--without-reference")}},
+		)
+		if err != nil {
+			t.Fatal(err)
+		}
+		if got := referenceContractBindingLabels(overrides); !slices.Equal(got, []string{"alpha.extract.shared"}) {
+			t.Fatalf("overrides = %#v, want alpha extract", got)
+		}
+		if got := referenceContractUnbindLabels(unbinds); slices.Contains(got, "alpha.extract.shared") || len(got) != 5 {
+			t.Fatalf("unbinds = %#v, want all shared targets except alpha extract", got)
+		}
+	})
+
+	t.Run("same specificity conflicts", func(t *testing.T) {
+		_, _, err := resolveCLIReferenceRequests(cfg, "demo", nil, catalog,
+			[]cliReferenceRequest{{Selector: mustParseReferenceSelector(t, "alpha.shared", "--reference"), Source: "alpha.txt"}},
+			[]cliReferenceUnbindRequest{{Selector: mustParseReferenceSelector(t, "alpha.shared", "--without-reference")}},
+		)
+		if err == nil || !strings.Contains(err.Error(), "same specificity") {
+			t.Fatalf("error = %v, want same-specificity conflict", err)
+		}
+	})
 }
 
 func TestReferenceUnbindsRemoveOptionalAndProtectRequiredSlots(t *testing.T) {
@@ -217,7 +289,7 @@ func TestReferenceMaterializationSeparatesCLIAndConfigPathOrigins(t *testing.T)
 	workingDir := t.TempDir()
 	cfg := referenceContractConfig()
 	configPath := filepath.Join(configDir, "config.yml")
-	if err := os.WriteFile(configPath, []byte("version: 4\n"), 0o600); err != nil {
+	if err := os.WriteFile(configPath, []byte("version: 5\n"), 0o600); err != nil {
 		t.Fatal(err)
 	}
 	if err := os.WriteFile(filepath.Join(configDir, "required.txt"), []byte("config reference"), 0o600); err != nil {
@@ -257,6 +329,52 @@ func TestReferenceMaterializationSeparatesCLIAndConfigPathOrigins(t *testing.T)
 	}
 }
 
+func TestPipelineScopedCLIReferenceProtectsGeneratedHandoff(t *testing.T) {
+	cfg := referenceContractConfig()
+	profile := cfg.Pipelines["demo"]
+	alpha := profile.Artifacts["alpha"]
+	beta := profile.Artifacts["beta"]
+	alpha.Extract.References["shared"] = pipeline.GeneratedReference("produce", "beta")
+	profile.Artifacts = nil
+	profile.Steps = []pipeline.PipelineStepProfile{
+		{ID: "produce", Artifacts: map[string]pipeline.ArtifactLaneProfile{"beta": beta}},
+		{ID: "consume", Artifacts: map[string]pipeline.ArtifactLaneProfile{"alpha": alpha}},
+	}
+	cfg.Pipelines["demo"] = profile
+	catalog := referenceContractCatalog(t, true, true)
+
+	t.Run("binding conflicts before file access", func(t *testing.T) {
+		overrides, _, err := resolveCLIReferenceRequests(cfg, "demo", nil, catalog, []cliReferenceRequest{{
+			Selector: mustParseReferenceSelector(t, "shared", "--reference"),
+			Source:   filepath.Join(t.TempDir(), "never-read.json"),
+		}}, nil)
+		if err != nil {
+			t.Fatalf("expand CLI reference: %v", err)
+		}
+		_, err = cfg.Resolve(config.ResolveInput{PipelineID: "demo", Catalog: catalog, ReferenceOverrides: overrides})
+		if err == nil || !strings.Contains(err.Error(), "conflicting generated and external bindings") || strings.Contains(err.Error(), "never-read.json") {
+			t.Fatalf("resolve error = %v, want generated/external conflict before file access", err)
+		}
+	})
+
+	t.Run("unbind leaves generated source intact", func(t *testing.T) {
+		_, unbinds, err := resolveCLIReferenceRequests(cfg, "demo", nil, catalog, nil, []cliReferenceUnbindRequest{{
+			Selector: mustParseReferenceSelector(t, "shared", "--without-reference"),
+		}})
+		if err != nil {
+			t.Fatalf("expand CLI unbind: %v", err)
+		}
+		effective, err := cfg.Resolve(config.ResolveInput{PipelineID: "demo", Catalog: catalog, ReferenceUnbinds: unbinds})
+		if err != nil {
+			t.Fatalf("resolve generated reference with CLI unbind: %v", err)
+		}
+		binding := referenceContractFindBinding(referenceContractLane(t, effective.ResolvedPipeline, "alpha").ExtractReferences.Bindings, "shared")
+		if binding == nil || binding.Artifact == nil || binding.Artifact.Step != "produce" || binding.Artifact.Lane != "beta" {
+			t.Fatalf("generated binding = %#v, want preserved produce/beta handoff", binding)
+		}
+	})
+}
+
 func TestReferenceTargetLookupUsesArtifactVariantsAndReportsMissingContext(t *testing.T) {
 	cfg := referenceContractConfig()
 	full := referenceContractCatalog(t, true, true)
@@ -368,7 +486,7 @@ func referenceContractCatalog(t *testing.T, includeBetaMerger, includeBetaNormal
 	register(registries.Chunkers.RegisterWithSpec(pipeline.ModuleSpec{Key: "reference/chunk", Stage: pipeline.StageChunk, ExecutionClass: contracts.ExecutionClassDeterministic, Requires: []string{"source"}, Provides: []string{"chunks"}, ReferenceSlots: []contracts.ReferenceSlot{{Name: "chunk-slot"}, {Name: "required-chunk", Required: true}}}, func() (contracts.Chunker, error) { return stateTestChunker{}, nil }))
 	register(pipeline.RegisterArtifactCodec(registries.ArtifactCodecs, referenceContractCodecA{}))
 	register(pipeline.RegisterArtifactCodec(registries.ArtifactCodecs, referenceContractCodecB{}))
-	register(pipeline.RegisterExtractor(registries.Extractors, pipeline.ModuleSpec{Key: "reference/extract-alpha", Stage: pipeline.StageExtract, ExecutionClass: contracts.ExecutionClassDeterministic, Requires: []string{"chunks"}, Provides: []string{"artifact"}, ArtifactKind: referenceContractKindAlpha, ReferenceSlots: []contracts.ReferenceSlot{{Name: "shared"}, {Name: "alpha-slot"}, {Name: "required-extract", Required: true}}}, func() (contracts.Extractor[stateTestArtifact], error) { return stateTestExtractor{}, nil }))
+	register(pipeline.RegisterExtractor(registries.Extractors, pipeline.ModuleSpec{Key: "reference/extract-alpha", Stage: pipeline.StageExtract, ExecutionClass: contracts.ExecutionClassDeterministic, Requires: []string{"chunks"}, Provides: []string{"artifact"}, ArtifactKind: referenceContractKindAlpha, ReferenceSlots: []contracts.ReferenceSlot{{Name: "shared", AcceptedArtifactKinds: []contracts.ArtifactKind{referenceContractKindBeta}, AcceptedMediaTypes: []string{"application/json"}}, {Name: "alpha-slot"}, {Name: "required-extract", Required: true}}}, func() (contracts.Extractor[stateTestArtifact], error) { return stateTestExtractor{}, nil }))
 	register(pipeline.RegisterExtractor(registries.Extractors, pipeline.ModuleSpec{Key: "reference/extract-beta", Stage: pipeline.StageExtract, ExecutionClass: contracts.ExecutionClassDeterministic, Requires: []string{"chunks"}, Provides: []string{"artifact"}, ArtifactKind: referenceContractKindBeta, ReferenceSlots: []contracts.ReferenceSlot{{Name: "shared"}, {Name: "beta-slot"}, {Name: "required-extract", Required: true}}}, func() (contracts.Extractor[stateTestArtifact], error) { return stateTestExtractor{}, nil }))
 	register(pipeline.RegisterMerger(registries.Mergers, pipeline.ModuleSpec{Key: "reference/shared-merge", Stage: pipeline.StageMerge, ExecutionClass: contracts.ExecutionClassDeterministic, Requires: []string{"artifact"}, Provides: []string{"merged"}, ArtifactKind: referenceContractKindAlpha, ReferenceSlots: []contracts.ReferenceSlot{{Name: "shared"}, {Name: "alpha-merge"}, {Name: "required-merge", Required: true}}}, func() (contracts.Merger[stateTestArtifact], error) { return stateTestMerger{}, nil }))
 	if includeBetaMerger {
@@ -444,6 +562,42 @@ func referenceContractBindingSource(bindings []pipeline.ReferenceBinding, slot s
 	return ""
 }
 
+func mustParseReferenceSelector(t *testing.T, value, flagName string) cliReferenceSelector {
+	t.Helper()
+	selector, err := parseReferenceSelector(value, flagName)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return selector
+}
+
+func referenceContractBindingLabels(bindings []pipeline.ReferenceBinding) []string {
+	labels := make([]string, 0, len(bindings))
+	for _, binding := range bindings {
+		labels = append(labels, referenceContractBindingLabel(binding))
+	}
+	return labels
+}
+
+func referenceContractBindingLabel(binding pipeline.ReferenceBinding) string {
+	if binding.Stage == pipeline.StageChunk {
+		return "chunk." + binding.SlotName
+	}
+	return binding.LaneID + "." + string(binding.Stage) + "." + binding.SlotName
+}
+
+func referenceContractUnbindLabels(unbinds []pipeline.ReferenceUnbind) []string {
+	labels := make([]string, 0, len(unbinds))
+	for _, unbind := range unbinds {
+		labels = append(labels, referenceContractBindingLabel(pipeline.ReferenceBinding{
+			Stage:    unbind.Stage,
+			LaneID:   unbind.LaneID,
+			SlotName: unbind.SlotName,
+		}))
+	}
+	return labels
+}
+
 func referenceContractFindBinding(bindings []pipeline.ReferenceBinding, slot string) *pipeline.ReferenceBinding {
 	for i := range bindings {
 		if bindings[i].SlotName == slot {

internal/cli/run.go

@@ -4,7 +4,6 @@ import (
 	"context"
 	"crypto/sha256"
 	"encoding/hex"
-	"encoding/json"
 	"errors"
 	"flag"
 	"fmt"
@@ -16,6 +15,7 @@ import (
 	"strings"
 	"time"
 
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
 	"gitea.maximumdirect.net/eric/notarius/internal/buildinfo"
 	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
 	"gitea.maximumdirect.net/eric/notarius/internal/core/config"
@@ -34,8 +34,10 @@ const usage = `Usage:
   notarius help
   notarius --version
   notarius run <pipeline-id> --input path/to/source.json [--json] [flags]
-  notarius config validate --config path/to/config.yml [--pipeline pipeline-id] [--only lane-a,lane-b]
-  notarius pipelines list --config path/to/config.yml [--json]
+  notarius config validate --config path/to/config.yml [--config-profile name] [--pipeline pipeline-id] [--only lane-a,lane-b]
+  notarius config effective --config path/to/config.yml [--config-profile name]
+  notarius config explain --config path/to/config.yml [--config-profile name] <json-pointer>
+  notarius pipelines list --config path/to/config.yml [--config-profile name] [--json]
 `
 
 type Options struct {
@@ -158,6 +160,7 @@ func runPipelineCommand(args []string, stdout, stderr io.Writer, opts Options) i
 	fs := flag.NewFlagSet("run", flag.ContinueOnError)
 	fs.SetOutput(io.Discard)
 	configPath := fs.String("config", "", "config file path")
+	configProfile := fs.String("config-profile", "", "configuration profile")
 	inputPath := fs.String("input", "", "source input file path")
 	onlyRaw := fs.String("only", "", "comma-separated artifact lanes")
 	outputDir := fs.String("output-dir", "", "output directory")
@@ -177,7 +180,7 @@ func runPipelineCommand(args []string, stdout, stderr io.Writer, opts Options) i
 	fs.Var(&llmProfile, "llm-profile", "LLM profile override")
 	fs.Var(&reasoningEffort, "reasoning-effort", "reasoning effort override")
 	fs.Var(&chunkCache, "chunk_cache", "chunk plan cache mode: auto, bypass, or refresh")
-	fs.Var(&referenceFlags, "reference", "reference binding, as slot=path, chunk.slot=path, merge.slot=path, lane.slot=path, lane.extract.slot=path, lane.merge.slot=path, or lane.normalize.slot=path")
+	fs.Var(&referenceFlags, "reference", "reference binding, as slot=path, chunk.slot=path, lane.slot=path, lane.extract.slot=path, lane.merge.slot=path, or lane.normalize.slot=path")
 	fs.Var(&withoutReferenceFlags, "without-reference", "unbind a reference, using the same selector forms as --reference")
 	fs.Var(&recomputeStep, "recompute-step", "recompute one ordered pipeline step and dependent lanes")
 	if err := validateRunFlagValues(args); err != nil {
@@ -265,20 +268,12 @@ func runPipelineCommand(args []string, stdout, stderr io.Writer, opts Options) i
 		return 2
 	}
 
-	cfg, loadedConfigPath, err := loadConfig(*configPath, opts)
+	loaded, loadedConfigPath, err := loadConfigKit(*configPath, *configProfile, runConfigurationOverrides(chunkCache, *outputDir, *debugDir), opts)
 	if err != nil {
-		fmt.Fprintf(stderr, "notarius: %v\n", err)
+		writeConfigLoadError(stderr, err)
 		return 1
 	}
-	if chunkCache.set {
-		cfg.Cache.ChunkPlans.Mode = chunkCache.value
-	}
-	if dir := strings.TrimSpace(*outputDir); dir != "" {
-		cfg.Output.Directory = dir
-	}
-	if dir := strings.TrimSpace(*debugDir); dir != "" {
-		cfg.Debug.Directory = dir
-	}
+	cfg := loaded.RuntimeConfig()
 	if err := cfg.Validate(); err != nil {
 		fmt.Fprintf(stderr, "notarius: %v\n", err)
 		return 1
@@ -336,6 +331,7 @@ func runPipelineCommand(args []string, stdout, stderr io.Writer, opts Options) i
 		InputPath:               strings.TrimSpace(*inputPath),
 		ConfigPath:              loadedConfigPath,
 		ConfigSource:            configSource(*configPath),
+		ConfigProfile:           effectiveConfigProfile(*configProfile),
 		OnlyLanes:               append([]string(nil), only...),
 		ChunkCacheOverride:      chunkCache.explicitValue(),
 		ReasoningEffortOverride: runtimeOverrides.ReasoningEffort,
@@ -394,7 +390,7 @@ func runPipelineCommand(args []string, stdout, stderr io.Writer, opts Options) i
 	if err := writeSummary(summary, func() error { return summary.WriteInvocation(invocation) }); err != nil {
 		return failPipelineCommand(stderr, commandState, terminalWriter, fmt.Errorf("write debug invocation metadata: %w", err))
 	}
-	if err := writeSummary(summary, func() error { return summary.WriteRedactedEffectiveConfig(effective) }); err != nil {
+	if err := writeSummary(summary, func() error { return summary.WriteEffectiveConfig(loaded) }); err != nil {
 		return failPipelineCommand(stderr, commandState, terminalWriter, fmt.Errorf("write debug effective config: %w", err))
 	}
 	if err := writeSummary(summary, func() error { return summary.WriteResolvedPipeline(effective) }); err != nil {
@@ -881,13 +877,39 @@ func reorderRunArgs(args []string) []string {
 
 func runFlagTakesValue(arg string) bool {
 	switch arg {
-	case "--config", "--input", "--only", "--output-dir", "--debug-dir", "--llm-profile", "--session-id", "--reasoning-effort", "--chunk_cache", "--reference", "--without-reference", "--recompute-step":
+	case "--config", "--config-profile", "--input", "--only", "--output-dir", "--debug-dir", "--llm-profile", "--session-id", "--reasoning-effort", "--chunk_cache", "--reference", "--without-reference", "--recompute-step":
 		return true
 	default:
 		return false
 	}
 }
 
+func runConfigurationOverrides(chunkCache chunkCacheFlag, outputDir, debugDir string) []configkit.Override {
+	overrides := make([]configkit.Override, 0, 3)
+	if chunkCache.set {
+		overrides = append(overrides, configkit.Override{
+			Path:  configkit.Keys("cache", "chunk_plans", "mode"),
+			Value: string(chunkCache.value),
+			Flag:  "--chunk_cache",
+		})
+	}
+	if outputDir = strings.TrimSpace(outputDir); outputDir != "" {
+		overrides = append(overrides, configkit.Override{
+			Path:  configkit.Keys("output", "directory"),
+			Value: outputDir,
+			Flag:  "--output-dir",
+		})
+	}
+	if debugDir = strings.TrimSpace(debugDir); debugDir != "" {
+		overrides = append(overrides, configkit.Override{
+			Path:  configkit.Keys("debug", "directory"),
+			Value: debugDir,
+			Flag:  "--debug-dir",
+		})
+	}
+	return overrides
+}
+
 type chunkCacheFlag struct {
 	value pipeline.ChunkCacheMode
 	set   bool
@@ -941,7 +963,7 @@ func chunkPlanStoreForRun(cfg config.ChunkPlanCacheConfig, opts Options) (pipeli
 
 func validateRunFlagValues(args []string) error {
 	for i, arg := range args {
-		if arg != "--session-id" && arg != "--reasoning-effort" {
+		if arg != "--config-profile" && arg != "--session-id" && arg != "--reasoning-effort" {
 			continue
 		}
 		if i+1 >= len(args) || strings.HasPrefix(args[i+1], "-") {
@@ -951,6 +973,13 @@ func validateRunFlagValues(args []string) error {
 	return nil
 }
 
+func effectiveConfigProfile(profile string) string {
+	if profile == "" || profile == "default" {
+		return ""
+	}
+	return profile
+}
+
 func flagWasProvided(args []string, name string) bool {
 	for _, arg := range args {
 		if arg == name || strings.HasPrefix(arg, name+"=") {
@@ -1026,6 +1055,10 @@ func runConfig(args []string, stdout, stderr io.Writer, opts Options) int {
 	switch args[0] {
 	case "validate":
 		return runConfigValidate(args[1:], stdout, stderr, opts)
+	case "effective":
+		return runConfigEffective(args[1:], stdout, stderr, opts)
+	case "explain":
+		return runConfigExplain(args[1:], stdout, stderr, opts)
 	default:
 		fmt.Fprintf(stderr, "notarius: unknown config subcommand %q\n", args[0])
 		writeUsage(stderr)
@@ -1033,67 +1066,6 @@ func runConfig(args []string, stdout, stderr io.Writer, opts Options) int {
 	}
 }
 
-func runConfigValidate(args []string, stdout, stderr io.Writer, opts Options) int {
-	fs := flag.NewFlagSet("config validate", flag.ContinueOnError)
-	fs.SetOutput(io.Discard)
-	configPath := fs.String("config", "", "config file path")
-	pipelineID := fs.String("pipeline", "", "pipeline ID")
-	onlyRaw := fs.String("only", "", "comma-separated artifact lanes")
-	if err := fs.Parse(args); err != nil {
-		fmt.Fprintf(stderr, "notarius: %v\n", err)
-		return 2
-	}
-	if fs.NArg() != 0 {
-		fmt.Fprintf(stderr, "notarius: unexpected argument %q\n", fs.Arg(0))
-		return 2
-	}
-	if strings.TrimSpace(*onlyRaw) != "" && strings.TrimSpace(*pipelineID) == "" {
-		fmt.Fprintln(stderr, "notarius: --only requires --pipeline")
-		return 2
-	}
-	only, err := parseOnly(*onlyRaw)
-	if err != nil {
-		fmt.Fprintf(stderr, "notarius: %v\n", err)
-		return 2
-	}
-
-	cfg, path, err := loadConfig(*configPath, opts)
-	if err != nil {
-		fmt.Fprintf(stderr, "notarius: %v\n", err)
-		return 1
-	}
-
-	if strings.TrimSpace(*pipelineID) != "" {
-		catalog, err := effectiveCatalog(opts)
-		if err != nil {
-			fmt.Fprintf(stderr, "notarius: %v\n", err)
-			return 1
-		}
-		effective, err := cfg.Resolve(config.ResolveInput{
-			PipelineID: *pipelineID,
-			Only:       only,
-			Catalog:    catalog,
-		})
-		if err != nil {
-			fmt.Fprintf(stderr, "notarius: %v\n", err)
-			return 1
-		}
-		if err := validateExplicitPromptKitProfiles(context.Background(), effective.Config, effectiveLLMProfileIDs(effective.ResolvedPipeline), opts.promptKitAssets); err != nil {
-			fmt.Fprintf(stderr, "notarius: %v\n", err)
-			return 1
-		}
-		fmt.Fprintf(stdout, "config %q is valid for pipeline %q\n", path, strings.TrimSpace(*pipelineID))
-		return 0
-	}
-
-	if err := cfg.Validate(); err != nil {
-		fmt.Fprintf(stderr, "notarius: %v\n", err)
-		return 1
-	}
-	fmt.Fprintf(stdout, "config %q is valid\n", path)
-	return 0
-}
-
 func runPipelines(args []string, stdout, stderr io.Writer, opts Options) int {
 	if len(args) == 0 {
 		fmt.Fprintln(stderr, "notarius: pipelines requires a subcommand")
@@ -1110,70 +1082,6 @@ func runPipelines(args []string, stdout, stderr io.Writer, opts Options) int {
 	}
 }
 
-func runPipelinesList(args []string, stdout, stderr io.Writer, opts Options) int {
-	fs := flag.NewFlagSet("pipelines list", flag.ContinueOnError)
-	fs.SetOutput(io.Discard)
-	configPath := fs.String("config", "", "config file path")
-	jsonOutput := fs.Bool("json", false, "write JSON output")
-	if err := fs.Parse(args); err != nil {
-		fmt.Fprintf(stderr, "notarius: %v\n", err)
-		return 2
-	}
-	if fs.NArg() != 0 {
-		fmt.Fprintf(stderr, "notarius: unexpected argument %q\n", fs.Arg(0))
-		return 2
-	}
-
-	cfg, _, err := loadConfig(*configPath, opts)
-	if err != nil {
-		fmt.Fprintf(stderr, "notarius: %v\n", err)
-		return 1
-	}
-	if err := cfg.Validate(); err != nil {
-		fmt.Fprintf(stderr, "notarius: %v\n", err)
-		return 1
-	}
-
-	ids := sortedPipelineIDs(cfg)
-	if *jsonOutput {
-		payload := struct {
-			Pipelines []string `json:"pipelines"`
-		}{Pipelines: ids}
-		encoded, err := json.Marshal(payload)
-		if err != nil {
-			fmt.Fprintf(stderr, "notarius: marshal pipeline list: %v\n", err)
-			return 1
-		}
-		fmt.Fprintf(stdout, "%s\n", encoded)
-		return 0
-	}
-
-	for _, id := range ids {
-		fmt.Fprintln(stdout, id)
-	}
-	return 0
-}
-
-func loadConfig(configPath string, opts Options) (config.Config, string, error) {
-	path, err := discoverConfigPath(configPath, opts)
-	if err != nil {
-		return config.Config{}, "", err
-	}
-
-	fileCfg, err := config.LoadFileConfig(path)
-	if err != nil {
-		return config.Config{}, "", err
-	}
-	cfg := config.Default()
-	if err := cfg.ApplyFileConfigWithLookup(fileCfg, opts.LookupEnv); err != nil {
-		return config.Config{}, "", err
-	}
-	if err := cfg.ApplyEnvOverridesWithLookup(opts.LookupEnv); err != nil {
-		return config.Config{}, "", err
-	}
-	return cfg, path, nil
-}
-
 func discoverConfigPath(configPath string, opts Options) (string, error) {
 	if path := strings.TrimSpace(configPath); path != "" {
 		if err := requireConfigFile(path); err != nil {
@@ -1287,11 +1195,21 @@ type cliReferenceUnbindRequest struct {
 }
 
 type cliReferenceSelector struct {
+	Scope    cliReferenceSelectorScope
 	LaneID   string
 	Stage    pipeline.ModuleStage
 	SlotName string
 }
 
+type cliReferenceSelectorScope uint8
+
+const (
+	cliReferenceScopePipeline cliReferenceSelectorScope = iota
+	cliReferenceScopeLane
+	cliReferenceScopeChunk
+	cliReferenceScopeBinding
+)
+
 func parseReferenceFlags(values []string) ([]cliReferenceRequest, error) {
 	if len(values) == 0 {
 		return nil, nil
@@ -1300,7 +1218,7 @@ func parseReferenceFlags(values []string) ([]cliReferenceRequest, error) {
 	for _, raw := range values {
 		name, source, ok := strings.Cut(raw, "=")
 		if !ok {
-			return nil, fmt.Errorf("--reference must use slot=path or lane.slot=path")
+			return nil, fmt.Errorf("--reference must use slot=path, lane.slot=path, or lane.stage.slot=path")
 		}
 		if strings.TrimSpace(source) == "" {
 			return nil, fmt.Errorf("--reference path must not be empty; use --without-reference to unbind")
@@ -1350,17 +1268,14 @@ func parseReferenceSelector(raw string, flagName string) (cliReferenceSelector,
 	}
 	switch len(parts) {
 	case 1:
-		return cliReferenceSelector{SlotName: strings.TrimSpace(parts[0])}, nil
+		return cliReferenceSelector{Scope: cliReferenceScopePipeline, SlotName: strings.TrimSpace(parts[0])}, nil
 	case 2:
 		first := strings.TrimSpace(parts[0])
 		slotName := strings.TrimSpace(parts[1])
 		if first == string(pipeline.StageChunk) {
-			return cliReferenceSelector{Stage: pipeline.StageChunk, SlotName: slotName}, nil
+			return cliReferenceSelector{Scope: cliReferenceScopeChunk, Stage: pipeline.StageChunk, SlotName: slotName}, nil
 		}
-		if first == string(pipeline.StageMerge) {
-			return cliReferenceSelector{Stage: pipeline.StageMerge, SlotName: slotName}, nil
-		}
-		return cliReferenceSelector{LaneID: first, SlotName: slotName}, nil
+		return cliReferenceSelector{Scope: cliReferenceScopeLane, LaneID: first, SlotName: slotName}, nil
 	case 3:
 		laneID := strings.TrimSpace(parts[0])
 		stage := pipeline.ModuleStage(strings.TrimSpace(parts[1]))
@@ -1368,9 +1283,9 @@ func parseReferenceSelector(raw string, flagName string) (cliReferenceSelector,
 		if stage != pipeline.StageExtract && stage != pipeline.StageMerge && stage != pipeline.StageNormalize {
 			return cliReferenceSelector{}, fmt.Errorf("%s lane-qualified selector must use lane.extract.slot, lane.merge.slot, or lane.normalize.slot", flagName)
 		}
-		return cliReferenceSelector{LaneID: laneID, Stage: stage, SlotName: slotName}, nil
+		return cliReferenceSelector{Scope: cliReferenceScopeBinding, LaneID: laneID, Stage: stage, SlotName: slotName}, nil
 	default:
-		return cliReferenceSelector{}, fmt.Errorf("%s must use slot, chunk.slot, merge.slot, lane.slot, lane.extract.slot, lane.merge.slot, or lane.normalize.slot", flagName)
+		return cliReferenceSelector{}, fmt.Errorf("%s must use slot, chunk.slot, lane.slot, lane.extract.slot, lane.merge.slot, or lane.normalize.slot", flagName)
 	}
 }
 
@@ -1391,37 +1306,153 @@ func resolveCLIReferenceRequests(
 		return nil, nil, err
 	}
 
-	overrides := make([]pipeline.ReferenceBinding, 0, len(referenceRequests))
+	// Broad CLI selectors are only presentation syntax. Collapse them into one
+	// highest-specificity action per concrete framework target before pipeline
+	// resolution so the generic reference contract stays stage-and-lane exact.
+	actions := make(map[cliReferenceTargetKey]resolvedCLIReferenceAction)
 	for _, request := range referenceRequests {
-		target, err := resolveCLIReferenceTarget(targets, request.Selector)
+		matches, err := resolveCLIReferenceTargets(targets, request.Selector)
 		if err != nil {
 			return nil, nil, err
 		}
-		overrides = append(overrides, pipeline.ReferenceBinding{
-			Stage:         target.stage,
-			LaneID:        target.laneID,
-			SlotName:      request.Selector.SlotName,
-			Source:        request.Source,
-			BindingSource: contracts.ReferenceBindingSourceCLI,
-		})
+		for _, target := range matches {
+			candidate := resolvedCLIReferenceAction{
+				kind:        cliReferenceActionBind,
+				selector:    request.Selector,
+				target:      target,
+				slotName:    request.Selector.SlotName,
+				source:      request.Source,
+				specificity: request.Selector.specificity(),
+			}
+			if err := mergeCLIReferenceAction(actions, candidate); err != nil {
+				return nil, nil, err
+			}
+		}
 	}
-
-	unbinds := make([]pipeline.ReferenceUnbind, 0, len(unbindRequests))
 	for _, request := range unbindRequests {
-		target, err := resolveCLIReferenceTarget(targets, request.Selector)
+		matches, err := resolveCLIReferenceTargets(targets, request.Selector)
 		if err != nil {
 			return nil, nil, err
 		}
-		unbinds = append(unbinds, pipeline.ReferenceUnbind{
-			Stage:    target.stage,
-			LaneID:   target.laneID,
-			SlotName: request.Selector.SlotName,
-		})
+		for _, target := range matches {
+			candidate := resolvedCLIReferenceAction{
+				kind:        cliReferenceActionUnbind,
+				selector:    request.Selector,
+				target:      target,
+				slotName:    request.Selector.SlotName,
+				specificity: request.Selector.specificity(),
+			}
+			if err := mergeCLIReferenceAction(actions, candidate); err != nil {
+				return nil, nil, err
+			}
+		}
 	}
 
+	resolved := make([]resolvedCLIReferenceAction, 0, len(actions))
+	for _, action := range actions {
+		resolved = append(resolved, action)
+	}
+	sort.Slice(resolved, func(i, j int) bool {
+		left, right := resolved[i], resolved[j]
+		if left.target.laneID != right.target.laneID {
+			return left.target.laneID < right.target.laneID
+		}
+		if left.target.stage != right.target.stage {
+			return referenceStageOrder(left.target.stage) < referenceStageOrder(right.target.stage)
+		}
+		return left.slotName < right.slotName
+	})
+
+	overrides := make([]pipeline.ReferenceBinding, 0, len(resolved))
+	unbinds := make([]pipeline.ReferenceUnbind, 0, len(resolved))
+	for _, action := range resolved {
+		switch action.kind {
+		case cliReferenceActionBind:
+			overrides = append(overrides, pipeline.ReferenceBinding{
+				Stage:         action.target.stage,
+				LaneID:        action.target.laneID,
+				SlotName:      action.slotName,
+				Source:        action.source,
+				BindingSource: contracts.ReferenceBindingSourceCLI,
+			})
+		case cliReferenceActionUnbind:
+			unbinds = append(unbinds, pipeline.ReferenceUnbind{
+				Stage:    action.target.stage,
+				LaneID:   action.target.laneID,
+				SlotName: action.slotName,
+			})
+		}
+	}
 	return overrides, unbinds, nil
 }
 
+type cliReferenceActionKind uint8
+
+const (
+	cliReferenceActionBind cliReferenceActionKind = iota
+	cliReferenceActionUnbind
+)
+
+type cliReferenceTargetKey struct {
+	stage    pipeline.ModuleStage
+	laneID   string
+	slotName string
+}
+
+type resolvedCLIReferenceAction struct {
+	kind        cliReferenceActionKind
+	selector    cliReferenceSelector
+	target      selectedReferenceTarget
+	slotName    string
+	source      string
+	specificity int
+}
+
+func mergeCLIReferenceAction(actions map[cliReferenceTargetKey]resolvedCLIReferenceAction, candidate resolvedCLIReferenceAction) error {
+	key := cliReferenceTargetKey{stage: candidate.target.stage, laneID: candidate.target.laneID, slotName: candidate.slotName}
+	current, ok := actions[key]
+	if !ok || candidate.specificity > current.specificity {
+		actions[key] = candidate
+		return nil
+	}
+	if candidate.specificity < current.specificity {
+		return nil
+	}
+	if candidate.kind != current.kind {
+		return fmt.Errorf("reference target %q slot %q is both bound by %q and unbound by %q at the same specificity", targetLabel(candidate.target), candidate.slotName, current.selector.String(), candidate.selector.String())
+	}
+	actions[key] = candidate
+	return nil
+}
+
+func (selector cliReferenceSelector) specificity() int {
+	switch selector.Scope {
+	case cliReferenceScopePipeline:
+		return 0
+	case cliReferenceScopeLane:
+		return 1
+	case cliReferenceScopeChunk, cliReferenceScopeBinding:
+		return 2
+	default:
+		return -1
+	}
+}
+
+func (selector cliReferenceSelector) String() string {
+	switch selector.Scope {
+	case cliReferenceScopePipeline:
+		return selector.SlotName
+	case cliReferenceScopeLane:
+		return selector.LaneID + "." + selector.SlotName
+	case cliReferenceScopeChunk:
+		return "chunk." + selector.SlotName
+	case cliReferenceScopeBinding:
+		return selector.LaneID + "." + string(selector.Stage) + "." + selector.SlotName
+	default:
+		return selector.SlotName
+	}
+}
+
 type selectedReferenceTarget struct {
 	laneID string
 	stage  pipeline.ModuleStage
@@ -1638,114 +1669,77 @@ func referenceSlotSet(slots []contracts.ReferenceSlot) map[string]struct{} {
 	return slotSet
 }
 
-func resolveCLIReferenceTarget(targets []selectedReferenceTarget, selector cliReferenceSelector) (selectedReferenceTarget, error) {
+func resolveCLIReferenceTargets(targets []selectedReferenceTarget, selector cliReferenceSelector) ([]selectedReferenceTarget, error) {
 	slotName := strings.TrimSpace(selector.SlotName)
 	if slotName == "" {
-		return selectedReferenceTarget{}, fmt.Errorf("reference slot must not be empty")
+		return nil, fmt.Errorf("reference slot must not be empty")
 	}
-	if selector.Stage == pipeline.StageChunk {
+	switch selector.Scope {
+	case cliReferenceScopePipeline:
+		matches := make([]selectedReferenceTarget, 0, len(targets))
+		for _, target := range targets {
+			if _, ok := target.slots[slotName]; ok {
+				matches = append(matches, target)
+			}
+		}
+		if len(matches) == 0 {
+			return nil, fmt.Errorf("reference slot %q is not declared by any selected target", slotName)
+		}
+		return matches, nil
+	case cliReferenceScopeChunk:
 		for _, target := range targets {
 			if target.stage != pipeline.StageChunk {
 				continue
 			}
 			if _, ok := target.slots[slotName]; !ok {
-				return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is not declared by chunk module %q", slotName, target.module)
+				return nil, fmt.Errorf("reference slot %q is not declared by chunk module %q", slotName, target.module)
 			}
-			return target, nil
-		}
-		return selectedReferenceTarget{}, fmt.Errorf("reference chunk target is not selected")
-	}
-	if selector.Stage == pipeline.StageExtract || selector.Stage == pipeline.StageMerge || selector.Stage == pipeline.StageNormalize {
-		if selector.LaneID == "" && selector.Stage == pipeline.StageMerge {
-			return resolveCLIReferenceStageTarget(targets, selector.Stage, slotName)
+			return []selectedReferenceTarget{target}, nil
 		}
+		return nil, fmt.Errorf("reference chunk target is not selected")
+	case cliReferenceScopeLane:
+		laneSelected := false
+		matches := make([]selectedReferenceTarget, 0, 3)
 		for _, target := range targets {
-			if target.laneID == selector.LaneID && target.stage == selector.Stage {
-				if _, ok := target.slots[slotName]; !ok {
-					return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is not declared by selected %s target %q", slotName, selector.Stage, targetLabel(target))
-				}
-				return target, nil
+			if target.laneID != selector.LaneID {
+				continue
+			}
+			laneSelected = true
+			if _, ok := target.slots[slotName]; ok {
+				matches = append(matches, target)
 			}
 		}
-		return selectedReferenceTarget{}, fmt.Errorf("reference lane %q is not selected", selector.LaneID)
-	}
-	if strings.TrimSpace(selector.LaneID) != "" {
-		return resolveCLIReferenceLaneTarget(targets, strings.TrimSpace(selector.LaneID), slotName)
-	}
-	return resolveCLIReferenceFlatTarget(targets, slotName)
-}
-
-func resolveCLIReferenceStageTarget(targets []selectedReferenceTarget, stage pipeline.ModuleStage, slotName string) (selectedReferenceTarget, error) {
-	matches := make([]selectedReferenceTarget, 0, 2)
-	for _, target := range targets {
-		if target.stage != stage {
-			continue
+		if !laneSelected {
+			return nil, fmt.Errorf("reference lane %q is not selected", selector.LaneID)
 		}
-		if _, ok := target.slots[slotName]; ok {
-			matches = append(matches, target)
+		if len(matches) == 0 {
+			return nil, fmt.Errorf("reference slot %q is not declared by selected lane %q", slotName, selector.LaneID)
 		}
-	}
-	switch len(matches) {
-	case 0:
-		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is not declared by any selected %s target", slotName, stage)
-	case 1:
-		return matches[0], nil
+		return matches, nil
+	case cliReferenceScopeBinding:
+		laneSelected := false
+		for _, target := range targets {
+			if target.laneID != selector.LaneID {
+				continue
+			}
+			laneSelected = true
+			if target.stage != selector.Stage {
+				continue
+			}
+			if _, ok := target.slots[slotName]; !ok {
+				return nil, fmt.Errorf("reference slot %q is not declared by selected %s target %q", slotName, selector.Stage, targetLabel(target))
+			}
+			return []selectedReferenceTarget{target}, nil
+		}
+		if !laneSelected {
+			return nil, fmt.Errorf("reference lane %q is not selected", selector.LaneID)
+		}
+		return nil, fmt.Errorf("reference %s target is not selected for lane %q", selector.Stage, selector.LaneID)
 	default:
-		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is declared by multiple selected %s targets (%s); use a more specific selector such as %s", slotName, stage, targetList(matches), selectorSuggestions(matches, slotName))
+		return nil, fmt.Errorf("reference selector has unknown scope")
 	}
 }
 
-func resolveCLIReferenceLaneTarget(targets []selectedReferenceTarget, laneID string, slotName string) (selectedReferenceTarget, error) {
-	laneSelected := false
-	matches := make([]selectedReferenceTarget, 0, 2)
-	for _, target := range targets {
-		if target.laneID != laneID {
-			continue
-		}
-		laneSelected = true
-		if _, ok := target.slots[slotName]; ok {
-			matches = append(matches, target)
-		}
-	}
-	if !laneSelected {
-		return selectedReferenceTarget{}, fmt.Errorf("reference lane %q is not selected", laneID)
-	}
-	switch len(matches) {
-	case 0:
-		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is not declared by selected lane %q", slotName, laneID)
-	case 1:
-		return matches[0], nil
-	default:
-		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is declared by multiple selected targets in lane %q (%s); use a more specific selector such as %s", slotName, laneID, targetList(matches), selectorSuggestions(matches, slotName))
-	}
-}
-
-func resolveCLIReferenceFlatTarget(targets []selectedReferenceTarget, slotName string) (selectedReferenceTarget, error) {
-	matches := make([]selectedReferenceTarget, 0, 2)
-	for _, target := range targets {
-		if _, ok := target.slots[slotName]; ok {
-			matches = append(matches, target)
-		}
-	}
-	switch len(matches) {
-	case 0:
-		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is not declared by any selected reference target", slotName)
-	case 1:
-		return matches[0], nil
-	default:
-		return selectedReferenceTarget{}, fmt.Errorf("reference slot %q is declared by multiple selected targets (%s); use a more specific selector such as %s", slotName, targetList(matches), selectorSuggestions(matches, slotName))
-	}
-}
-
-func targetList(targets []selectedReferenceTarget) string {
-	labels := make([]string, 0, len(targets))
-	for _, target := range targets {
-		labels = append(labels, targetLabel(target))
-	}
-	sort.Strings(labels)
-	return strings.Join(labels, ", ")
-}
-
 func targetLabel(target selectedReferenceTarget) string {
 	if target.stage == pipeline.StageChunk {
 		return "chunk"
@@ -1753,17 +1747,19 @@ func targetLabel(target selectedReferenceTarget) string {
 	return target.laneID + "." + string(target.stage)
 }
 
-func selectorSuggestions(targets []selectedReferenceTarget, slotName string) string {
-	suggestions := make([]string, 0, len(targets))
-	for _, target := range targets {
-		if target.stage == pipeline.StageChunk {
-			suggestions = append(suggestions, "chunk."+slotName)
-			continue
-		}
-		suggestions = append(suggestions, target.laneID+"."+string(target.stage)+"."+slotName)
+func referenceStageOrder(stage pipeline.ModuleStage) int {
+	switch stage {
+	case pipeline.StageChunk:
+		return 0
+	case pipeline.StageExtract:
+		return 1
+	case pipeline.StageMerge:
+		return 2
+	case pipeline.StageNormalize:
+		return 3
+	default:
+		return 4
 	}
-	sort.Strings(suggestions)
-	return strings.Join(suggestions, " or ")
 }
 
 func sortedPipelineIDs(cfg config.Config) []string {

internal/cli/run_contract_test.go

@@ -12,6 +12,7 @@ import (
 
 	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
 	"gitea.maximumdirect.net/eric/notarius/internal/core/config"
+	"gitea.maximumdirect.net/eric/notarius/internal/core/debugbundle"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/checkpoint"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
@@ -37,6 +38,9 @@ func TestRunControlsRejectSyntaxWithoutAllocatingState(t *testing.T) {
 		{name: "blank debug directory", args: func(roots stateTestRoots) []string {
 			return []string{"run", "sample", "--config", roots.config, "--input", roots.input, "--debug-dir", ""}
 		}},
+		{name: "missing configuration profile", args: func(roots stateTestRoots) []string {
+			return []string{"run", "sample", "--config", roots.config, "--input", roots.input, "--config-profile"}
+		}},
 		{name: "debug directory without debug", args: func(roots stateTestRoots) []string {
 			return []string{"run", "sample", "--config", roots.config, "--input", roots.input, "--debug-dir", filepath.Join(filepath.Dir(roots.debug), "requested-debug")}
 		}},
@@ -79,7 +83,7 @@ func TestRecomputeStepCLIContract(t *testing.T) {
 		{
 			name: "explicit step",
 			configure: func(t *testing.T, roots stateTestRoots) {
-				replaceStateTestConfigLine(t, roots.config, "    artifacts:\n      items:\n        extract: test/extract\n        merge: test/merge\n        normalize: test/normalize\n", "    steps:\n      - id: chosen\n        artifacts:\n          items:\n            extract: test/extract\n            merge: test/merge\n            normalize: test/normalize\n")
+				replaceStateTestConfigLine(t, roots.config, "    artifacts:\n      items:\n        extract:\n          module: test/extract\n        merge:\n          module: test/merge\n        normalize:\n          module: test/normalize\n", "    steps:\n      - id: chosen\n        artifacts:\n          items:\n            extract:\n              module: test/extract\n            merge:\n              module: test/merge\n            normalize:\n              module: test/normalize\n")
 			},
 			flags:      []string{"--resume", "--recompute-step", "chosen"},
 			wantCode:   0,
@@ -161,7 +165,7 @@ func TestRunOnlyExecutesSelectedLanes(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	data = []byte(replaceRequiredOnce(t, string(data), "    output: test/output\n", "      other:\n        extract: test/extract\n    output: test/output\n"))
+	data = []byte(replaceRequiredOnce(t, string(data), "    output:\n      module: test/output\n", "      other:\n        extract:\n          module: test/extract\n    output:\n      module: test/output\n"))
 	if err := os.WriteFile(roots.config, data, 0o600); err != nil {
 		t.Fatal(err)
 	}
@@ -180,7 +184,7 @@ func TestRunOnlyExecutesSelectedLanes(t *testing.T) {
 }
 
 func TestRunStateRootsHonorEnvironmentFlagsAndDefaults(t *testing.T) {
-	t.Run("environment roots", func(t *testing.T) {
+	t.Run("retired environment roots have no effect", func(t *testing.T) {
 		roots := newStateTestRoots(t)
 		environmentOutput := filepath.Join(t.TempDir(), "environment-output")
 		environmentDebug := filepath.Join(t.TempDir(), "environment-debug")
@@ -193,10 +197,10 @@ func TestRunStateRootsHonorEnvironmentFlagsAndDefaults(t *testing.T) {
 		if result.code != 0 {
 			t.Fatalf("code=%d stdout=%q stderr=%q", result.code, result.stdout, result.stderr)
 		}
-		assertFile(t, filepath.Join(environmentOutput, filepath.Base(onlyChildDir(t, environmentOutput)), "result.json"))
-		onlyChildDir(t, environmentDebug)
-		assertAbsent(t, roots.output)
-		assertAbsent(t, roots.debug)
+		assertFile(t, filepath.Join(roots.output, filepath.Base(onlyChildDir(t, roots.output)), "result.json"))
+		onlyChildDir(t, roots.debug)
+		assertAbsent(t, environmentOutput)
+		assertAbsent(t, environmentDebug)
 	})
 
 	t.Run("command flags override environment", func(t *testing.T) {
@@ -227,23 +231,57 @@ func TestRunStateRootsHonorEnvironmentFlagsAndDefaults(t *testing.T) {
 			t.Fatal(err)
 		}
 		text := string(data)
-		text = replaceRequiredOnce(t, text, fmt.Sprintf("  directory: %q\n", roots.output), "")
-		text = replaceRequiredOnce(t, text, fmt.Sprintf("  directory: %q\n", roots.debug), "")
+		text = replaceRequiredOnce(t, text, fmt.Sprintf("output:\n  directory: %q\n", roots.output), "")
+		text = replaceRequiredOnce(t, text, fmt.Sprintf("debug:\n  directory: %q\n", roots.debug), "")
 		if err := os.WriteFile(roots.config, []byte(text), 0o600); err != nil {
 			t.Fatal(err)
 		}
-		workDir := t.TempDir()
-		t.Chdir(workDir)
 		opts := newStateTestHarness().options()
 		result := runWithStateRoots(t, roots, opts, nil)
 		if result.code != 0 {
 			t.Fatalf("code=%d stdout=%q stderr=%q", result.code, result.stdout, result.stderr)
 		}
-		assertFile(t, filepath.Join(workDir, "notarius-output", filepath.Base(onlyChildDir(t, filepath.Join(workDir, "notarius-output"))), "result.json"))
-		onlyChildDir(t, filepath.Join(workDir, "notarius-debug"))
+		configDirectory := filepath.Dir(roots.config)
+		assertFile(t, filepath.Join(configDirectory, "notarius-output", filepath.Base(onlyChildDir(t, filepath.Join(configDirectory, "notarius-output"))), "result.json"))
+		onlyChildDir(t, filepath.Join(configDirectory, "notarius-debug"))
 	})
 }
 
+func TestRunAppliesConfigurationProfileAndRecordsSelection(t *testing.T) {
+	roots := newStateTestRoots(t)
+	profileDirectory := filepath.Join(filepath.Dir(roots.config), "profiles")
+	profileOutput := filepath.Join(profileDirectory, "profile-output")
+	profileDebug := filepath.Join(profileDirectory, "profile-debug")
+	writeConfigKitFile(t, filepath.Join(profileDirectory, "development.yml"), "output:\n  directory: ./profile-output\ndebug:\n  directory: ./profile-debug\n")
+
+	var stdout, stderr bytes.Buffer
+	code := RunWithOptions([]string{
+		"run", "sample", "--config", roots.config, "--config-profile", "development",
+		"--input", roots.input, "--chunk_cache", "bypass", "--debug",
+	}, &stdout, &stderr, newStateTestHarness().options())
+	if code != 0 || stderr.Len() != 0 {
+		t.Fatalf("code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
+	}
+	assertFile(t, filepath.Join(profileOutput, filepath.Base(onlyChildDir(t, profileOutput)), "result.json"))
+	bundle := onlyChildDir(t, profileDebug)
+	var invocation debugbundle.Invocation
+	readStateTestSummaryJSON(t, bundle, "invocation.json", &invocation)
+	if invocation.ConfigProfile != "development" {
+		t.Fatalf("config profile = %q, want development", invocation.ConfigProfile)
+	}
+}
+
+func TestEffectiveConfigProfileOmitsBaseSelection(t *testing.T) {
+	for _, profile := range []string{"", "default"} {
+		if got := effectiveConfigProfile(profile); got != "" {
+			t.Fatalf("effectiveConfigProfile(%q) = %q, want empty", profile, got)
+		}
+	}
+	if got := effectiveConfigProfile("development"); got != "development" {
+		t.Fatalf("effectiveConfigProfile(development) = %q", got)
+	}
+}
+
 func TestRunLLMProfileOverrideAndValidationUseInjectedBoundaries(t *testing.T) {
 	t.Run("one effective profile reaches the factory and modules", func(t *testing.T) {
 		roots := newStateTestRoots(t)
@@ -567,7 +605,7 @@ func TestRunFactoryAndPreparationFailuresAreProcessFailures(t *testing.T) {
 		if err != nil {
 			t.Fatal(err)
 		}
-		data = []byte(replaceRequiredOnce(t, string(data), "extract: test/extract", "extract: test/failing-extract"))
+		data = []byte(replaceRequiredOnce(t, string(data), "module: test/extract", "module: test/failing-extract"))
 		if err := os.WriteFile(roots.config, data, 0o600); err != nil {
 			t.Fatal(err)
 		}

internal/cli/run_result_command_test.go

@@ -92,7 +92,7 @@ func TestRunResultReportsSuccessfulRejection(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	configBytes = []byte(replaceRequiredOnce(t, string(configBytes), "        normalize: test/normalize\n", "        normalize:\n          module: test/normalize\n          validators:\n            - generic/always_reject\n          validation_policy:\n            semantic_rejection: reject_output\n"))
+	configBytes = []byte(replaceRequiredOnce(t, string(configBytes), "        normalize:\n          module: test/normalize\n", "        normalize:\n          module: test/normalize\n          validators:\n            - module: generic/always_reject\n          validation_policy:\n            semantic_rejection: reject_output\n"))
 	if err := os.WriteFile(roots.config, configBytes, 0o600); err != nil {
 		t.Fatal(err)
 	}

internal/cli/spell_catalog_identity_contract_test.go

@@ -264,7 +264,7 @@ func TestChangedSemanticSpellCatalogFingerprintCannotResumeRecordedCheckpoint(t
 	if _, decision := changedLoader.Normalize("spells", spellnormalize.Key, normalizeDependencies); decision.Reused {
 		t.Fatalf("changed normalize fingerprint decision = %#v, want normalize checkpoint cold miss", decision)
 	}
-	changedMapping := replaceCheckpointFingerprintValue(t, fingerprints, extractSpellMappingFingerprintName(), "dnd.spells.extract_mapping.v3")
+	changedMapping := replaceCheckpointFingerprintValue(t, fingerprints, extractSpellMappingFingerprintName(), "dnd.spells.extract_mapping.changed")
 	assertOnlyCheckpointFingerprintChanged(t, fingerprints, changedMapping, extractSpellMappingFingerprintName())
 	_, mappingLoader, err := checkpointHandlersForRun(settings, Options{}, materialized, changedMapping, llmFingerprints, []byte("same input"), nil, nil, "", "", LLMRuntimeOverrides{}, true)
 	if err != nil {

internal/cli/state_hardening_test.go

@@ -57,7 +57,6 @@ func TestRunStateSurfaceMatrix(t *testing.T) {
 						}
 					}
 					assertAnyFile(t, roots.checkpoints)
-					assertRestrictedTree(t, roots.checkpoints)
 					if debug {
 						bundle := onlyChildDir(t, roots.debug)
 						assertFile(t, filepath.Join(bundle, "summary", "invocation.json"))
@@ -259,7 +258,7 @@ func TestRunRedactsSensitiveModuleOptionsFromConfigAndPipelineSummaries(t *testi
 	if err != nil {
 		t.Fatal(err)
 	}
-	configText := replaceRequiredOnce(t, string(data), "    input: test/input\n", `    input:
+	configText := replaceRequiredOnce(t, string(data), "    input:\n      module: test/input\n", `    input:
       module: test/input
       options:
         api_key: CONFIG_SUMMARY_SECRET_SENTINEL
@@ -277,7 +276,7 @@ func TestRunRedactsSensitiveModuleOptionsFromConfigAndPipelineSummaries(t *testi
 		t.Fatalf("code=%d stderr=%q", result.code, result.stderr)
 	}
 	summaryRoot := filepath.Join(onlyChildDir(t, roots.debug), "summary")
-	for _, name := range []string{"effective-config.json", "resolved-pipeline.json"} {
+	for _, name := range []string{"effective-config.yml", "resolved-pipeline.json"} {
 		contents, err := os.ReadFile(filepath.Join(summaryRoot, name))
 		if err != nil {
 			t.Fatal(err)
@@ -688,7 +687,7 @@ func newStateTestRoots(t *testing.T) stateTestRoots {
 		t.Fatal(err)
 	}
 	roots.config = filepath.Join(base, "config.yml")
-	config := fmt.Sprintf("version: 4\noutput:\n  directory: %q\ncache:\n  chunk_plans:\n    directory: %q\n    mode: auto\n  checkpoints:\n    enabled: true\n    directory: %q\ndebug:\n  directory: %q\npipelines:\n  sample:\n    input: test/input\n    chunk: test/chunk\n    artifacts:\n      items:\n        extract: test/extract\n        merge: test/merge\n        normalize: test/normalize\n    output: test/output\n", roots.output, roots.plans, roots.checkpoints, roots.debug)
+	config := fmt.Sprintf("version: 5\noutput:\n  directory: %q\ncache:\n  chunk_plans:\n    directory: %q\n    mode: auto\n  checkpoints:\n    enabled: true\n    directory: %q\ndebug:\n  directory: %q\npipelines:\n  sample:\n    input:\n      module: test/input\n    chunk:\n      module: test/chunk\n    artifacts:\n      items:\n        extract:\n          module: test/extract\n        merge:\n          module: test/merge\n        normalize:\n          module: test/normalize\n    output:\n      module: test/output\n", roots.output, roots.plans, roots.checkpoints, roots.debug)
 	if err := os.WriteFile(roots.config, []byte(config), 0o600); err != nil {
 		t.Fatal(err)
 	}

internal/cli/state_permissions_unix_test.go

@@ -0,0 +1,53 @@
+//go:build linux || darwin
+
+package cli
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"syscall"
+	"testing"
+)
+
+func TestRunCreatesReusableGroupAccessibleCacheState(t *testing.T) {
+	previousUmask := syscall.Umask(0o007)
+	defer syscall.Umask(previousUmask)
+
+	roots := newStateTestRoots(t)
+	harness := newStateTestHarness()
+	result := runStateTest(t, roots, harness.options(), false, false, "auto")
+	if result.code != 0 {
+		t.Fatalf("initial run code=%d stderr=%q", result.code, result.stderr)
+	}
+	assertGroupAccessibleCacheTree(t, roots.plans)
+	assertGroupAccessibleCacheTree(t, roots.checkpoints)
+
+	extractCalls := harness.extractCalls
+	result = runStateTest(t, roots, harness.options(), false, true, "auto")
+	if result.code != 0 {
+		t.Fatalf("resume run code=%d stderr=%q", result.code, result.stderr)
+	}
+	if harness.extractCalls != extractCalls {
+		t.Fatalf("extract calls after reuse = %d, want %d", harness.extractCalls, extractCalls)
+	}
+}
+
+func assertGroupAccessibleCacheTree(t *testing.T, root string) {
+	t.Helper()
+	if err := filepath.Walk(root, func(path string, info os.FileInfo, err error) error {
+		if err != nil {
+			return err
+		}
+		want := os.FileMode(0o660)
+		if info.IsDir() {
+			want = 0o770
+		}
+		if got := info.Mode().Perm(); got != want {
+			return fmt.Errorf("%s mode = %#o, want %#o", path, got, want)
+		}
+		return nil
+	}); err != nil {
+		t.Fatal(err)
+	}
+}

internal/core/config/config.go

@@ -4,8 +4,6 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
 )
 
-const SupportedFileConfigVersion = 4
-
 type Config struct {
 	PromptKit   PromptKitConfig                     `json:"promptkit,omitempty"`
 	Pipelines   map[string]pipeline.PipelineProfile `json:"pipelines"`
@@ -29,9 +27,6 @@ type PromptKitLocalBackendConfig struct {
 type ConcurrencyConfig struct {
 	TotalLLM     int            `json:"total_llm"`
 	StageWorkers map[string]int `json:"stage_workers"`
-
-	extractWorkersConfigured bool
-	defaultedExtractWorkers  int
 }
 
 const defaultLLMConcurrency = 16
@@ -62,9 +57,8 @@ func Default() Config {
 	return Config{
 		Pipelines: map[string]pipeline.PipelineProfile{},
 		Concurrency: ConcurrencyConfig{
-			TotalLLM:                defaultLLMConcurrency,
-			StageWorkers:            map[string]int{"extract": defaultLLMConcurrency},
-			defaultedExtractWorkers: defaultLLMConcurrency,
+			TotalLLM:     defaultLLMConcurrency,
+			StageWorkers: map[string]int{"extract": defaultLLMConcurrency},
 		},
 		Output: OutputConfig{Directory: "./notarius-output"},
 		Cache:  CacheConfig{ChunkPlans: ChunkPlanCacheConfig{Mode: pipeline.ChunkCacheAuto}},
@@ -97,21 +91,15 @@ func cloneIntMap(in map[string]int) map[string]int {
 	return out
 }
 
-func (c *ConcurrencyConfig) recomputeStageWorkerDefaults() {
-	if c == nil {
-		return
-	}
-	if c.StageWorkers == nil {
-		c.StageWorkers = make(map[string]int)
-	}
-	if !c.extractWorkersConfigured {
-		if value, ok := c.StageWorkers["extract"]; ok && (c.defaultedExtractWorkers == 0 || value != c.defaultedExtractWorkers) {
-			c.extractWorkersConfigured = true
-			return
+func (c Config) withDerivedStageWorkers() Config {
+	c = cloneConfig(c)
+	if _, exists := c.Concurrency.StageWorkers["extract"]; !exists {
+		if c.Concurrency.StageWorkers == nil {
+			c.Concurrency.StageWorkers = make(map[string]int)
 		}
-		c.StageWorkers["extract"] = c.TotalLLM
-		c.defaultedExtractWorkers = c.TotalLLM
+		c.Concurrency.StageWorkers["extract"] = c.Concurrency.TotalLLM
 	}
+	return c
 }
 
 func clonePipelineProfile(in pipeline.PipelineProfile) pipeline.PipelineProfile {

internal/core/config/document.go

@@ -0,0 +1,122 @@
+package config
+
+import "gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+
+// Document is the version 5 configuration shape decoded by ConfigKit. It is
+// deliberately separate from Config so YAML presence and composition concerns
+// do not reach runtime pipeline types.
+type Document struct {
+	Version     string                      `yaml:"version"`
+	PromptKit   *PromptKitDocument          `yaml:"promptkit,omitempty"`
+	Pipelines   map[string]PipelineDocument `yaml:"pipelines,omitempty"`
+	Concurrency *ConcurrencyDocument        `yaml:"concurrency,omitempty"`
+	Output      *OutputDocument             `yaml:"output,omitempty"`
+	Cache       *CacheDocument              `yaml:"cache,omitempty"`
+	Debug       *DebugDocument              `yaml:"debug,omitempty"`
+}
+
+type PromptKitDocument struct {
+	ProfileDir   *string                        `yaml:"profile_dir,omitempty"`
+	ProfileFile  *string                        `yaml:"profile_file,omitempty"`
+	LocalBackend *PromptKitLocalBackendDocument `yaml:"local_backend,omitempty"`
+}
+
+type PromptKitLocalBackendDocument struct {
+	Endpoint         *string `yaml:"endpoint,omitempty"`
+	ConcurrencyLimit *int    `yaml:"concurrency_limit,omitempty"`
+}
+
+type PipelineDocument struct {
+	LLMProfile                     *string                         `yaml:"llm_profile,omitempty"`
+	StructuredOutputRepairAttempts *int                            `yaml:"structured_output_repair_attempts,omitempty"`
+	ValidationPolicy               *ValidationPolicyDocument       `yaml:"validation_policy,omitempty"`
+	Input                          BindingDocument                 `yaml:"input"`
+	Chunk                          *BindingDocument                `yaml:"chunk,omitempty"`
+	Artifacts                      map[string]ArtifactLaneDocument `yaml:"artifacts,omitempty"`
+	Steps                          []PipelineStepDocument          `yaml:"steps,omitempty"`
+	Output                         *BindingDocument                `yaml:"output,omitempty"`
+	References                     map[string]ReferenceDocument    `yaml:"references,omitempty"`
+}
+
+type PipelineStepDocument struct {
+	ID         string                          `yaml:"id"`
+	Artifacts  map[string]ArtifactLaneDocument `yaml:"artifacts"`
+	References map[string]ReferenceDocument    `yaml:"references,omitempty"`
+}
+
+type ArtifactLaneDocument struct {
+	Extract    BindingDocument              `yaml:"extract"`
+	Merge      *BindingDocument             `yaml:"merge,omitempty"`
+	Normalize  *BindingDocument             `yaml:"normalize,omitempty"`
+	Validators []ValidatorDocument          `yaml:"validators,omitempty"`
+	References map[string]ReferenceDocument `yaml:"references,omitempty"`
+}
+
+// BindingDocument represents a producer binding. ValidatorDocument is a
+// deliberately finite subset so nested validator-only fields are rejected by
+// ConfigKit's strict decoder.
+type BindingDocument struct {
+	Module                         string                       `yaml:"module"`
+	LLMProfile                     *string                      `yaml:"llm_profile,omitempty"`
+	StructuredOutputRepairAttempts *int                         `yaml:"structured_output_repair_attempts,omitempty"`
+	ValidationPolicy               *ValidationPolicyDocument    `yaml:"validation_policy,omitempty"`
+	Retries                        int                          `yaml:"retries,omitempty"`
+	Options                        map[string]any               `yaml:"options,omitempty"`
+	References                     map[string]ReferenceDocument `yaml:"references,omitempty"`
+	Validators                     []ValidatorDocument          `yaml:"validators,omitempty"`
+}
+
+type ValidatorDocument struct {
+	Module                         string         `yaml:"module"`
+	LLMProfile                     *string        `yaml:"llm_profile,omitempty"`
+	StructuredOutputRepairAttempts *int           `yaml:"structured_output_repair_attempts,omitempty"`
+	Retries                        int            `yaml:"retries,omitempty"`
+	Options                        map[string]any `yaml:"options,omitempty"`
+}
+
+// ReferenceDocument is the explicit version 5 union. Later document
+// validation establishes which locations permit generated references and
+// requires exactly one populated branch.
+type ReferenceDocument struct {
+	Path     *string                    `yaml:"path,omitempty"`
+	Artifact *ArtifactReferenceDocument `yaml:"artifact,omitempty"`
+}
+
+type ArtifactReferenceDocument struct {
+	Step string `yaml:"step"`
+	Lane string `yaml:"lane"`
+}
+
+type ValidationPolicyDocument struct {
+	ProducerStructuralFailure *pipeline.ProducerStructuralFailureAction `yaml:"producer_structural_failure,omitempty"`
+	SemanticRejection         *pipeline.SemanticRejectionAction         `yaml:"semantic_rejection,omitempty"`
+	ValidatorFailure          *pipeline.ValidatorFailureAction          `yaml:"validator_failure,omitempty"`
+}
+
+type ConcurrencyDocument struct {
+	TotalLLM     *int           `yaml:"total_llm,omitempty"`
+	StageWorkers map[string]int `yaml:"stage_workers,omitempty"`
+}
+
+type OutputDocument struct {
+	Directory *string `yaml:"directory,omitempty"`
+}
+
+type CacheDocument struct {
+	ChunkPlans  *ChunkPlanCacheDocument  `yaml:"chunk_plans,omitempty"`
+	Checkpoints *CheckpointCacheDocument `yaml:"checkpoints,omitempty"`
+}
+
+type ChunkPlanCacheDocument struct {
+	Directory *string `yaml:"directory,omitempty"`
+	Mode      *string `yaml:"mode,omitempty"`
+}
+
+type CheckpointCacheDocument struct {
+	Enabled   *bool   `yaml:"enabled,omitempty"`
+	Directory *string `yaml:"directory,omitempty"`
+}
+
+type DebugDocument struct {
+	Directory *string `yaml:"directory,omitempty"`
+}

internal/core/config/document_normalizer.go

@@ -0,0 +1,26 @@
+package config
+
+import configkit "gitea.maximumdirect.net/eric/ConfigKit"
+
+// documentNormalizer records leaf provenance and, while visiting a sequence,
+// covers its atomic mutation boundary. ConfigKit audits sequences as whole
+// values, so a record for only a descendant is insufficient. The outermost
+// sequence covers nested sequences as well; unchanged visits record nothing.
+type documentNormalizer struct {
+	*configkit.Resolution
+	sequence *configkit.Path
+}
+
+func (n documentNormalizer) inSequence(path configkit.Path) documentNormalizer {
+	if n.sequence == nil {
+		n.sequence = &path
+	}
+	return n
+}
+
+func (n documentNormalizer) Record(path configkit.Path, kind configkit.ChangeKind, reason string, dependencies ...configkit.Path) {
+	n.Resolution.Record(path, kind, reason, dependencies...)
+	if n.sequence != nil {
+		n.Resolution.Record(*n.sequence, kind, reason, append([]configkit.Path{path}, dependencies...)...)
+	}
+}

internal/core/config/document_paths.go

@@ -0,0 +1,167 @@
+package config
+
+import (
+	"path/filepath"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+)
+
+func normalizeDocumentPaths(document *Document, context *configkit.Resolution, state *documentLoadState) {
+	resolution := documentNormalizer{Resolution: context}
+	if document == nil {
+		return
+	}
+	initializeDocumentMainDirectory(resolution, state)
+	if document.PromptKit != nil {
+		normalizeDocumentPath(resolution, state, configkit.Keys("promptkit", "profile_dir"), &document.PromptKit.ProfileDir, false, "resolved PromptKit profile directory")
+		normalizeDocumentPath(resolution, state, configkit.Keys("promptkit", "profile_file"), &document.PromptKit.ProfileFile, false, "resolved PromptKit profile file")
+	}
+	if document.Output != nil {
+		normalizeDocumentPath(resolution, state, configkit.Keys("output", "directory"), &document.Output.Directory, false, "resolved output directory")
+	}
+	if document.Cache != nil {
+		if document.Cache.ChunkPlans != nil {
+			normalizeDocumentPath(resolution, state, configkit.Keys("cache", "chunk_plans", "directory"), &document.Cache.ChunkPlans.Directory, true, "resolved chunk-plan cache directory")
+		}
+		if document.Cache.Checkpoints != nil {
+			normalizeDocumentPath(resolution, state, configkit.Keys("cache", "checkpoints", "directory"), &document.Cache.Checkpoints.Directory, true, "resolved checkpoint cache directory")
+		}
+	}
+	if document.Debug != nil {
+		normalizeDocumentPath(resolution, state, configkit.Keys("debug", "directory"), &document.Debug.Directory, false, "resolved debug directory")
+	}
+	for _, id := range sortedPipelineDocumentKeys(document.Pipelines) {
+		profile := document.Pipelines[id]
+		path := configkit.Keys("pipelines").Key(id)
+		normalizeDocumentReferencePaths(profile.References, path.Key("references"), resolution, state)
+		normalizeDocumentBindingReferencePaths(&profile.Input, path.Key("input"), resolution, state)
+		if profile.Chunk != nil {
+			normalizeDocumentBindingReferencePaths(profile.Chunk, path.Key("chunk"), resolution, state)
+		}
+		if profile.Output != nil {
+			normalizeDocumentBindingReferencePaths(profile.Output, path.Key("output"), resolution, state)
+		}
+		for laneID, lane := range profile.Artifacts {
+			normalizeDocumentLaneReferencePaths(&lane, path.Key("artifacts").Key(laneID), resolution, state)
+			profile.Artifacts[laneID] = lane
+		}
+		stepResolution := resolution.inSequence(path.Key("steps"))
+		for index := range profile.Steps {
+			step := &profile.Steps[index]
+			stepPath := path.Key("steps").Index(index)
+			normalizeDocumentReferencePaths(step.References, stepPath.Key("references"), stepResolution, state)
+			for laneID, lane := range step.Artifacts {
+				normalizeDocumentLaneReferencePaths(&lane, stepPath.Key("artifacts").Key(laneID), stepResolution, state)
+				step.Artifacts[laneID] = lane
+			}
+		}
+		document.Pipelines[id] = profile
+	}
+}
+
+func initializeDocumentMainDirectory(resolution documentNormalizer, state *documentLoadState) {
+	if state == nil || state.mainDirectory != "" {
+		return
+	}
+	info, ok := resolution.InputInfo(configkit.Keys("version"))
+	if ok && len(info.Origin.Locations) == 1 {
+		if source, sourceOK := resolution.Source(info.Origin.Locations[0].SourceID); sourceOK && source.Path != "" {
+			state.mainDirectory = filepath.Dir(source.Path)
+			return
+		}
+	}
+	// Byte and reader sources are test-oriented private entry points. They have
+	// no declaring file, so preserve their established invocation-directory
+	// semantics without extending that fallback to file-backed production loads.
+	state.mainDirectory = cleanInvocationDirectory(".")
+}
+
+func normalizeDocumentBindingReferencePaths(binding *BindingDocument, path configkit.Path, resolution documentNormalizer, state *documentLoadState) {
+	if binding != nil {
+		normalizeDocumentReferencePaths(binding.References, path.Key("references"), resolution, state)
+	}
+}
+
+func normalizeDocumentLaneReferencePaths(lane *ArtifactLaneDocument, path configkit.Path, resolution documentNormalizer, state *documentLoadState) {
+	if lane == nil {
+		return
+	}
+	normalizeDocumentBindingReferencePaths(&lane.Extract, path.Key("extract"), resolution, state)
+	normalizeDocumentBindingReferencePaths(lane.Merge, path.Key("merge"), resolution, state)
+	normalizeDocumentBindingReferencePaths(lane.Normalize, path.Key("normalize"), resolution, state)
+}
+
+func normalizeDocumentReferencePaths(references map[string]ReferenceDocument, path configkit.Path, resolution documentNormalizer, state *documentLoadState) {
+	for _, name := range sortedReferenceDocumentKeys(references) {
+		source := references[name]
+		sourcePath := path.Key(name).Key("path")
+		if source.Path != nil && *source.Path != "" && !filepath.IsAbs(*source.Path) {
+			base, ok := documentPathBase(resolution, state, sourcePath)
+			if !ok {
+				resolution.Error(sourcePath, "relative path has no unambiguous source base")
+			} else {
+				value := filepath.Clean(filepath.Join(base, *source.Path))
+				if value != *source.Path {
+					resolution.Record(sourcePath, configkit.ChangeNormalization, "resolved external reference path")
+					source.Path = documentValue(value)
+				}
+			}
+			references[name] = source
+		}
+	}
+}
+
+func normalizeDocumentPath(resolution documentNormalizer, state *documentLoadState, path configkit.Path, target **string, optional bool, reason string) {
+	if target == nil || *target == nil || **target == "" || filepath.IsAbs(**target) {
+		return
+	}
+	base, ok := documentPathBase(resolution, state, path)
+	if !ok {
+		resolution.Error(path, "relative path has no unambiguous source base")
+		return
+	}
+	value := filepath.Clean(filepath.Join(base, **target))
+	if optional && **target == "" {
+		return
+	}
+	if *target != nil && **target != value {
+		configkit.Normalize(resolution.Resolution, path, target, documentValue(value), reason)
+	}
+}
+
+func documentPathBase(resolution documentNormalizer, state *documentLoadState, path configkit.Path) (string, bool) {
+	original := path
+	if state != nil {
+		original = state.originalPath(path)
+	}
+	info, ok := resolution.InputInfo(original)
+	if !ok {
+		if state != nil && state.mainDirectory != "" {
+			return state.mainDirectory, true
+		}
+		return "", false
+	}
+	switch info.Origin.Layer {
+	case configkit.LayerCLI:
+		if state != nil && state.invocationDirectory != "" {
+			return state.invocationDirectory, true
+		}
+	case configkit.LayerDefault:
+		if state != nil && state.mainDirectory != "" {
+			return state.mainDirectory, true
+		}
+	default:
+		if len(info.Origin.Locations) != 1 {
+			return "", false
+		}
+		source, ok := resolution.Source(info.Origin.Locations[0].SourceID)
+		if !ok || source.Path == "" {
+			if state != nil && state.mainDirectory != "" {
+				return state.mainDirectory, true
+			}
+			return "", false
+		}
+		return filepath.Dir(source.Path), true
+	}
+	return "", false
+}

internal/core/config/document_paths_test.go

@@ -0,0 +1,123 @@
+package config
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+)
+
+func TestDocumentPathsUseDeclaringFilesAcrossImports(t *testing.T) {
+	t.Parallel()
+
+	root := t.TempDir()
+	main := filepath.Join(root, "notarius.yml")
+	fragmentDirectory := filepath.Join(root, "fragments")
+	if err := os.MkdirAll(fragmentDirectory, 0o700); err != nil {
+		t.Fatal(err)
+	}
+	fragment := filepath.Join(fragmentDirectory, "pipelines.yml")
+	if err := os.WriteFile(fragment, []byte(`pipelines:
+  imported:
+    input: {module: input}
+    references:
+      source: {path: ./from-fragment.txt}
+`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(main, []byte(`version: 5
+configkit:
+  imports:
+    - path: fragments/pipelines.yml
+output: {directory: ./output}
+debug: {directory: ./debug}
+pipelines:
+  main:
+    input: {module: input}
+    references:
+      source: {path: ./from-main.txt}
+`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+
+	loaded, err := loadConfig(main, LoadOptions{})
+	if err != nil {
+		t.Fatalf("loadConfig() error = %v", err)
+	}
+	if got := loaded.Config.Pipelines["main"].References["source"].Path; got != filepath.Join(root, "from-main.txt") {
+		t.Fatalf("main reference = %q", got)
+	}
+	if got := loaded.Config.Pipelines["imported"].References["source"].Path; got != filepath.Join(fragmentDirectory, "from-fragment.txt") {
+		t.Fatalf("fragment reference = %q", got)
+	}
+	if loaded.Config.Output.Directory != filepath.Join(root, "output") || loaded.Config.Debug.Directory != filepath.Join(root, "debug") {
+		t.Fatalf("destinations = %#v %#v", loaded.Config.Output, loaded.Config.Debug)
+	}
+}
+
+func TestDocumentPathsUseInvocationDirectoryForOverrides(t *testing.T) {
+	t.Parallel()
+
+	root := t.TempDir()
+	configPath := filepath.Join(root, "notarius.yml")
+	if err := os.WriteFile(configPath, []byte("version: 5\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	invocation := t.TempDir()
+	loaded, err := loadConfig(configPath, LoadOptions{
+		InvocationDirectory: invocation,
+		Overrides:           []configkit.Override{{Path: configkit.Keys("output", "directory"), Value: "generated", Flag: "--output"}},
+	})
+	if err != nil {
+		t.Fatalf("loadConfig() error = %v", err)
+	}
+	if got := loaded.Config.Output.Directory; got != filepath.Join(invocation, "generated") {
+		t.Fatalf("override directory = %q", got)
+	}
+}
+
+func TestDocumentPathsUseProfileDeclarationDirectory(t *testing.T) {
+	t.Parallel()
+
+	root := t.TempDir()
+	profiles := filepath.Join(root, "profiles")
+	if err := os.MkdirAll(profiles, 0o700); err != nil {
+		t.Fatal(err)
+	}
+	main := filepath.Join(root, "notarius.yml")
+	if err := os.WriteFile(main, []byte("version: 5\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(profiles, "development.yml"), []byte("output: {directory: ./profile-output}\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	loaded, err := loadConfig(main, LoadOptions{Profile: "development"})
+	if err != nil {
+		t.Fatalf("loadConfig() error = %v", err)
+	}
+	if got := loaded.Config.Output.Directory; got != filepath.Join(profiles, "profile-output") {
+		t.Fatalf("profile directory = %q", got)
+	}
+}
+
+func TestDocumentPathsKeepEmptyCacheDirectoriesAndAbsolutePaths(t *testing.T) {
+	t.Parallel()
+
+	root := t.TempDir()
+	configPath := filepath.Join(root, "notarius.yml")
+	abs := filepath.Join(t.TempDir(), "outside.txt")
+	if err := os.WriteFile(configPath, []byte("version: 5\ncache:\n  chunk_plans: {directory: ''}\n  checkpoints: {directory: ''}\npipelines:\n  main:\n    input: {module: input}\n    references:\n      outside: {path: "+abs+"}\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	loaded, err := loadConfig(configPath, LoadOptions{})
+	if err != nil {
+		t.Fatalf("loadConfig() error = %v", err)
+	}
+	if loaded.Config.Cache.ChunkPlans.Directory != "" || loaded.Config.Cache.Checkpoints.Directory != "" {
+		t.Fatalf("cache directories = %#v", loaded.Config.Cache)
+	}
+	if got := loaded.Config.Pipelines["main"].References["outside"].Path; got != abs {
+		t.Fatalf("absolute reference = %q", got)
+	}
+}

internal/core/config/document_test.go

@@ -0,0 +1,154 @@
+package config
+
+import (
+	"errors"
+	"strings"
+	"testing"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+)
+
+func TestDocumentLoadAcceptsVersion5AndCanonicalShapes(t *testing.T) {
+	t.Parallel()
+
+	for _, source := range []string{
+		`version: 5
+pipelines:
+  session:
+    input:
+      module: seriatim
+    references:
+      party:
+        path: ./party.txt
+    steps:
+      - id: describe
+        artifacts:
+          spells:
+            extract:
+              module: dnd/spells
+              validators:
+                - module: generic/valid_json
+                  options:
+                    strict: true
+      - id: use-artifact
+        references:
+          spells:
+            artifact:
+              step: describe
+              lane: spells
+        artifacts:
+          locations:
+            extract:
+              module: dnd/locations
+`,
+		`version: "5"
+pipelines:
+  session:
+    input:
+      module: seriatim
+`,
+	} {
+		loaded, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(source)), LoadOptions{})
+		if err != nil {
+			t.Fatalf("loadDocumentSource() error = %v", err)
+		}
+		profile, ok := loaded.Config.Pipelines["session"]
+		if !ok || profile.Input.Module != "seriatim" {
+			t.Fatalf("pipeline = %#v", profile)
+		}
+	}
+}
+
+func TestDocumentLoadRejectsUnsupportedVersionsBeforeDocumentDecoding(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name   string
+		source string
+		code   configkit.Code
+	}{
+		{name: "missing", source: "unknown: value\n", code: configkit.CodeVersionError},
+		{name: "null", source: "version: null\nunknown: value\n", code: configkit.CodeVersionError},
+		{name: "version four", source: "version: 4\nunknown: value\n", code: configkit.CodeVersionError},
+		{name: "unsupported", source: "version: 6\nunknown: value\n", code: configkit.CodeVersionError},
+		{name: "noninteger", source: "version: 5.0\n", code: configkit.CodeVersionType},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			_, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(test.source)), LoadOptions{})
+			var loadError *configkit.LoadError
+			if !errors.As(err, &loadError) {
+				t.Fatalf("error = %v, want ConfigKit load error", err)
+			}
+			diagnostics := loadError.Diagnostics()
+			if len(diagnostics) != 1 || diagnostics[0].Code != test.code || diagnostics[0].Path.String() != "/version" {
+				t.Fatalf("diagnostics = %#v", diagnostics)
+			}
+			if strings.Contains(diagnostics[0].Message, "unknown") {
+				t.Fatalf("document decoding ran before version validation: %#v", diagnostics)
+			}
+		})
+	}
+}
+
+func TestDocumentLoadRejectsShorthandAndUnknownFields(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name   string
+		source string
+		code   configkit.Code
+		path   string
+	}{
+		{
+			name:   "binding shorthand",
+			source: "version: 5\npipelines:\n  session:\n    input: seriatim\n",
+			code:   configkit.CodeDecodeType,
+			path:   "/pipelines/session/input",
+		},
+		{
+			name:   "validator nested producer field",
+			source: "version: 5\npipelines:\n  session:\n    input:\n      module: seriatim\n      validators:\n        - module: generic/valid_json\n          validators: []\n",
+			code:   configkit.CodeDecodeUnknownField,
+			path:   "/pipelines/session/input/validators/0/validators",
+		},
+		{
+			name:   "unknown field",
+			source: "version: 5\npipelines:\n  session:\n    input:\n      module: seriatim\n      unknown: true\n",
+			code:   configkit.CodeDecodeUnknownField,
+			path:   "/pipelines/session/input/unknown",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			_, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(test.source)), LoadOptions{})
+			var loadError *configkit.LoadError
+			if !errors.As(err, &loadError) {
+				t.Fatalf("error = %v, want ConfigKit load error", err)
+			}
+			diagnostics := loadError.Diagnostics()
+			if len(diagnostics) != 1 || diagnostics[0].Code != test.code || diagnostics[0].Path.String() != test.path {
+				t.Fatalf("diagnostics = %#v", diagnostics)
+			}
+		})
+	}
+}
+
+func TestDocumentDefinitionReturnsIndependentDefaults(t *testing.T) {
+	t.Parallel()
+
+	first, err := loadDocumentSource(configkit.Bytes("first.yml", []byte("version: 5\n")), LoadOptions{})
+	if err != nil {
+		t.Fatal(err)
+	}
+	first.Config.Pipelines["changed"] = PipelineDocument{}
+	first.Config.Concurrency.StageWorkers["extract"] = 3
+
+	second, err := loadDocumentSource(configkit.Bytes("second.yml", []byte("version: 5\n")), LoadOptions{})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(second.Config.Pipelines) != 0 || second.Config.Concurrency.StageWorkers["extract"] != defaultLLMConcurrency || len(second.Config.Concurrency.StageWorkers) != 1 {
+		t.Fatalf("defaults aliased across loads: %#v", second.Config)
+	}
+}

internal/core/config/effective_config.go

@@ -26,7 +26,7 @@ type EffectiveConfig struct {
 }
 
 func (c Config) Resolve(input ResolveInput) (EffectiveConfig, error) {
-	c.Concurrency.recomputeStageWorkerDefaults()
+	c = c.withDerivedStageWorkers()
 	if err := c.Validate(); err != nil {
 		return EffectiveConfig{}, err
 	}

internal/core/config/env.go

@@ -1,103 +0,0 @@
-package config
-
-import (
-	"fmt"
-	"os"
-	"strconv"
-	"strings"
-
-	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
-)
-
-func LoadFromEnv() (Config, error) {
-	cfg := Default()
-	if err := cfg.applyEnvOverridesWithLookup(os.LookupEnv); err != nil {
-		return Config{}, err
-	}
-	return cfg, nil
-}
-
-func (c *Config) ApplyEnvOverrides() error {
-	return c.applyEnvOverridesWithLookup(os.LookupEnv)
-}
-
-func (c *Config) ApplyEnvOverridesWithLookup(lookup func(string) (string, bool)) error {
-	return c.applyEnvOverridesWithLookup(lookup)
-}
-
-func (c *Config) applyEnvOverridesWithLookup(lookup func(string) (string, bool)) error {
-	if c == nil {
-		return fmt.Errorf("config must not be nil")
-	}
-	if raw, ok := lookup("NOTARIUS_TOTAL_LLM_CONCURRENCY"); ok {
-		value, err := parseIntEnv("NOTARIUS_TOTAL_LLM_CONCURRENCY", raw)
-		if err != nil {
-			return err
-		}
-		c.Concurrency.TotalLLM = value
-	}
-	if raw, ok := lookup("NOTARIUS_STAGE_WORKERS_EXTRACT"); ok {
-		value, err := parseIntEnv("NOTARIUS_STAGE_WORKERS_EXTRACT", raw)
-		if err != nil {
-			return err
-		}
-		if c.Concurrency.StageWorkers == nil {
-			c.Concurrency.StageWorkers = make(map[string]int)
-		}
-		c.Concurrency.StageWorkers["extract"] = value
-		c.Concurrency.extractWorkersConfigured = true
-	}
-	c.Concurrency.recomputeStageWorkerDefaults()
-	if raw, ok := lookup("NOTARIUS_OUTPUT_DIR"); ok {
-		c.Output.Directory = strings.TrimSpace(raw)
-		if c.Output.Directory == "" {
-			return fmt.Errorf("NOTARIUS_OUTPUT_DIR: must not be empty")
-		}
-		if strings.ContainsRune(c.Output.Directory, '\x00') {
-			return fmt.Errorf("NOTARIUS_OUTPUT_DIR: must not contain NUL")
-		}
-	}
-	if raw, ok := lookup("NOTARIUS_CACHE_CHUNK_PLANS_MODE"); ok {
-		mode, err := pipeline.ParseChunkCacheMode(raw)
-		if err != nil {
-			return fmt.Errorf("NOTARIUS_CACHE_CHUNK_PLANS_MODE: %w", err)
-		}
-		c.Cache.ChunkPlans.Mode = mode
-	}
-	if raw, ok := lookup("NOTARIUS_CACHE_CHUNK_PLANS_DIR"); ok {
-		c.Cache.ChunkPlans.Directory = cleanOptionalPath(raw)
-		if c.Cache.ChunkPlans.Directory == "" {
-			return fmt.Errorf("NOTARIUS_CACHE_CHUNK_PLANS_DIR: must not be empty")
-		}
-		if strings.ContainsRune(c.Cache.ChunkPlans.Directory, '\x00') {
-			return fmt.Errorf("NOTARIUS_CACHE_CHUNK_PLANS_DIR: must not contain NUL")
-		}
-	}
-	if raw, ok := lookup("NOTARIUS_CACHE_CHECKPOINTS_DIR"); ok {
-		c.Cache.Checkpoints.Directory = cleanOptionalPath(raw)
-		if c.Cache.Checkpoints.Directory == "" {
-			return fmt.Errorf("NOTARIUS_CACHE_CHECKPOINTS_DIR: must not be empty")
-		}
-		if strings.ContainsRune(c.Cache.Checkpoints.Directory, '\x00') {
-			return fmt.Errorf("NOTARIUS_CACHE_CHECKPOINTS_DIR: must not contain NUL")
-		}
-	}
-	if raw, ok := lookup("NOTARIUS_DEBUG_DIR"); ok {
-		c.Debug.Directory = strings.TrimSpace(raw)
-		if c.Debug.Directory == "" {
-			return fmt.Errorf("NOTARIUS_DEBUG_DIR: must not be empty")
-		}
-		if strings.ContainsRune(c.Debug.Directory, '\x00') {
-			return fmt.Errorf("NOTARIUS_DEBUG_DIR: must not contain NUL")
-		}
-	}
-	return nil
-}
-
-func parseIntEnv(name string, raw string) (int, error) {
-	value, err := strconv.Atoi(strings.TrimSpace(raw))
-	if err != nil {
-		return 0, fmt.Errorf("%s: must be an integer", name)
-	}
-	return value, nil
-}

internal/core/config/env_contract_test.go

@@ -1,239 +0,0 @@
-package config
-
-import (
-	"errors"
-	"reflect"
-	"strings"
-	"testing"
-
-	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
-)
-
-func TestPrecedenceFileValuesOverrideBuiltInDefaults(t *testing.T) {
-	cfg := applyFileConfig(t, `version: 4
-concurrency:
-  total_llm: 4
-  stage_workers:
-    extract: 2
-output:
-  directory: ./file-output
-cache:
-  chunk_plans:
-    directory: ./file-plans
-    mode: refresh
-  checkpoints:
-    directory: ./file-checkpoints
-debug:
-  directory: ./file-debug
-`)
-	if cfg.Concurrency.TotalLLM != 4 || cfg.Concurrency.StageWorkers["extract"] != 2 ||
-		cfg.Output.Directory != "./file-output" || cfg.Cache.ChunkPlans.Directory != "file-plans" ||
-		cfg.Cache.ChunkPlans.Mode != pipeline.ChunkCacheRefresh || cfg.Cache.Checkpoints.Directory != "file-checkpoints" ||
-		cfg.Debug.Directory != "./file-debug" {
-		t.Fatalf("file values did not override defaults: %#v", cfg)
-	}
-}
-
-func TestPrecedenceOperationalEnvironmentOverridesFileValues(t *testing.T) {
-	cfg := applyFileConfig(t, `version: 4
-concurrency:
-  total_llm: 2
-  stage_workers:
-    extract: 1
-output:
-  directory: ./file-output
-cache:
-  chunk_plans:
-    directory: ./file-plans
-    mode: refresh
-  checkpoints:
-    directory: ./file-checkpoints
-debug:
-  directory: ./file-debug
-`)
-	env := map[string]string{
-		"NOTARIUS_TOTAL_LLM_CONCURRENCY":  "8",
-		"NOTARIUS_STAGE_WORKERS_EXTRACT":  "6",
-		"NOTARIUS_OUTPUT_DIR":             "/env/output",
-		"NOTARIUS_CACHE_CHUNK_PLANS_MODE": "bypass",
-		"NOTARIUS_CACHE_CHUNK_PLANS_DIR":  "/env/plans",
-		"NOTARIUS_CACHE_CHECKPOINTS_DIR":  "/env/checkpoints",
-		"NOTARIUS_DEBUG_DIR":              "/env/debug",
-	}
-	if err := cfg.ApplyEnvOverridesWithLookup(lookupValues(env)); err != nil {
-		t.Fatal(err)
-	}
-	if cfg.Concurrency.TotalLLM != 8 || cfg.Concurrency.StageWorkers["extract"] != 6 ||
-		cfg.Output.Directory != "/env/output" || cfg.Cache.ChunkPlans.Directory != "/env/plans" ||
-		cfg.Cache.ChunkPlans.Mode != pipeline.ChunkCacheBypass || cfg.Cache.Checkpoints.Directory != "/env/checkpoints" ||
-		cfg.Debug.Directory != "/env/debug" {
-		t.Fatalf("environment values did not override file values: %#v", cfg)
-	}
-}
-
-func TestPrecedenceExtractWorkersFollowEffectiveConcurrencyUnlessExplicit(t *testing.T) {
-	tests := []struct {
-		name       string
-		file       string
-		env        map[string]string
-		wantTotal  int
-		wantWorker int
-	}{
-		{
-			name:       "default follows environment total",
-			file:       "version: 4\n",
-			env:        map[string]string{"NOTARIUS_TOTAL_LLM_CONCURRENCY": "5"},
-			wantTotal:  5,
-			wantWorker: 5,
-		},
-		{
-			name:       "file worker is retained",
-			file:       "version: 4\nconcurrency:\n  total_llm: 3\n  stage_workers:\n    extract: 2\n",
-			env:        map[string]string{"NOTARIUS_TOTAL_LLM_CONCURRENCY": "6"},
-			wantTotal:  6,
-			wantWorker: 2,
-		},
-		{
-			name: "environment worker is retained",
-			file: "version: 4\nconcurrency:\n  total_llm: 2\n",
-			env: map[string]string{
-				"NOTARIUS_TOTAL_LLM_CONCURRENCY": "6",
-				"NOTARIUS_STAGE_WORKERS_EXTRACT": "4",
-			},
-			wantTotal:  6,
-			wantWorker: 4,
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			cfg := applyFileConfig(t, tt.file)
-			if err := cfg.ApplyEnvOverridesWithLookup(lookupValues(tt.env)); err != nil {
-				t.Fatal(err)
-			}
-			if cfg.Concurrency.TotalLLM != tt.wantTotal || cfg.Concurrency.StageWorkers["extract"] != tt.wantWorker {
-				t.Fatalf("concurrency = %#v, want total %d and extract %d", cfg.Concurrency, tt.wantTotal, tt.wantWorker)
-			}
-		})
-	}
-}
-
-func TestPrecedenceEmptyFileCacheDirectoriesDeferPerUserResolution(t *testing.T) {
-	cfg := applyFileConfig(t, `version: 4
-cache:
-  chunk_plans:
-    directory: ""
-  checkpoints:
-    directory: ""
-`)
-	if err := cfg.Validate(); err != nil {
-		t.Fatalf("empty file cache directories should be valid: %v", err)
-	}
-	if cfg.Cache.ChunkPlans.Directory != "" || cfg.Cache.Checkpoints.Directory != "" {
-		t.Fatalf("empty cache directories were not preserved for deferred resolution: %#v", cfg.Cache)
-	}
-	resolver := func() (string, error) { return "/user/cache", nil }
-	chunkPlans, err := DefaultChunkPlanRoot(resolver)
-	if err != nil {
-		t.Fatal(err)
-	}
-	checkpoints, err := DefaultCheckpointRoot(resolver)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if chunkPlans != "/user/cache/notarius/chunk-plans" || checkpoints != "/user/cache/notarius/checkpoints" {
-		t.Fatalf("deferred cache roots = %q, %q", chunkPlans, checkpoints)
-	}
-}
-
-func TestDefaultCacheRootsRejectInvalidUserCacheResolvers(t *testing.T) {
-	tests := []struct {
-		name     string
-		resolver func() (string, error)
-		want     string
-	}{
-		{name: "nil resolver", want: "must not be nil"},
-		{
-			name: "resolver failure",
-			resolver: func() (string, error) {
-				return "", errors.New("cache home unavailable")
-			},
-			want: "resolve user cache directory",
-		},
-		{name: "empty directory", resolver: func() (string, error) { return "  ", nil }, want: "must not be empty"},
-	}
-	families := []struct {
-		name string
-		root func(func() (string, error)) (string, error)
-	}{
-		{name: "chunk plans", root: DefaultChunkPlanRoot},
-		{name: "checkpoints", root: DefaultCheckpointRoot},
-	}
-
-	for _, family := range families {
-		for _, tt := range tests {
-			t.Run(family.name+"/"+tt.name, func(t *testing.T) {
-				_, err := family.root(tt.resolver)
-				if err == nil || !strings.Contains(err.Error(), tt.want) {
-					t.Fatalf("error = %v, want substring %q", err, tt.want)
-				}
-			})
-		}
-	}
-}
-
-func TestEnvEmptyDirectoryOverridesAreErrors(t *testing.T) {
-	tests := []string{
-		"NOTARIUS_OUTPUT_DIR",
-		"NOTARIUS_CACHE_CHUNK_PLANS_DIR",
-		"NOTARIUS_CACHE_CHECKPOINTS_DIR",
-		"NOTARIUS_DEBUG_DIR",
-	}
-	for _, name := range tests {
-		t.Run(name, func(t *testing.T) {
-			cfg := Default()
-			err := cfg.ApplyEnvOverridesWithLookup(lookupValues(map[string]string{name: " \t"}))
-			if err == nil || !strings.Contains(err.Error(), name) {
-				t.Fatalf("error = %v, want responsible environment variable", err)
-			}
-		})
-	}
-}
-
-func TestEnvInvalidIntegersAndChunkCacheModesReportTheirNames(t *testing.T) {
-	tests := map[string]string{
-		"NOTARIUS_TOTAL_LLM_CONCURRENCY":  "not-an-integer",
-		"NOTARIUS_STAGE_WORKERS_EXTRACT":  "not-an-integer",
-		"NOTARIUS_CACHE_CHUNK_PLANS_MODE": "not-a-cache-mode",
-	}
-	for name, value := range tests {
-		t.Run(name, func(t *testing.T) {
-			cfg := Default()
-			err := cfg.ApplyEnvOverridesWithLookup(lookupValues(map[string]string{name: value}))
-			if err == nil || !strings.Contains(err.Error(), name) {
-				t.Fatalf("error = %v, want responsible environment variable", err)
-			}
-		})
-	}
-}
-
-func TestEnvRemovedProviderVariablesAreIgnored(t *testing.T) {
-	before := Default()
-	cfg := Default()
-	removed := map[string]string{
-		"NOTARIUS_LLM_DEFAULT_ENDPOINT": "ignored-provider-setting",
-		"NOTARIUS_LLM_DEFAULT_MODEL":    "ignored-provider-setting",
-	}
-	if err := cfg.ApplyEnvOverridesWithLookup(lookupValues(removed)); err != nil {
-		t.Fatal(err)
-	}
-	if !reflect.DeepEqual(cfg, before) {
-		t.Fatalf("removed provider variables changed configuration: %#v", cfg)
-	}
-}
-
-func lookupValues(values map[string]string) func(string) (string, bool) {
-	return func(name string) (string, bool) {
-		value, ok := values[name]
-		return value, ok
-	}
-}

internal/core/config/file_config.go

@@ -1,902 +0,0 @@
-package config
-
-import (
-	"bytes"
-	"fmt"
-	"io"
-	"os"
-	"path/filepath"
-	"sort"
-	"strings"
-
-	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
-	"gopkg.in/yaml.v3"
-)
-
-type FileConfig struct {
-	Version     int                            `yaml:"version"`
-	PromptKit   *FilePromptKitConfig           `yaml:"promptkit,omitempty"`
-	Pipelines   map[string]FilePipelineProfile `yaml:"pipelines,omitempty"`
-	Concurrency *FileConcurrencyConfig         `yaml:"concurrency,omitempty"`
-	Output      *FileOutputConfig              `yaml:"output,omitempty"`
-	Cache       *FileCacheConfig               `yaml:"cache,omitempty"`
-	Debug       *FileDebugConfig               `yaml:"debug,omitempty"`
-}
-
-type FilePromptKitConfig struct {
-	ProfileDir   *string                          `yaml:"profile_dir,omitempty"`
-	ProfileFile  *string                          `yaml:"profile_file,omitempty"`
-	LocalBackend *FilePromptKitLocalBackendConfig `yaml:"local_backend,omitempty"`
-}
-
-type FilePromptKitLocalBackendConfig struct {
-	Endpoint         *string `yaml:"endpoint,omitempty"`
-	ConcurrencyLimit *int    `yaml:"concurrency_limit,omitempty"`
-}
-
-type FilePipelineProfile struct {
-	LLMProfile                     *string                            `yaml:"llm_profile,omitempty"`
-	StructuredOutputRepairAttempts *int                               `yaml:"structured_output_repair_attempts,omitempty"`
-	ValidationPolicy               *pipeline.ValidationPolicyOverride `yaml:"validation_policy,omitempty"`
-	Input                          fileModuleBinding                  `yaml:"input"`
-	Chunk                          *fileModuleBinding                 `yaml:"chunk,omitempty"`
-	Artifacts                      map[string]FileArtifactLaneProfile `yaml:"artifacts,omitempty"`
-	Steps                          []FilePipelineStepProfile          `yaml:"steps,omitempty"`
-	Output                         *fileModuleBinding                 `yaml:"output,omitempty"`
-	References                     map[string]fileReferenceSource     `yaml:"references,omitempty"`
-	artifactsSet                   bool                               `yaml:"-"`
-	stepsSet                       bool                               `yaml:"-"`
-	llmProfileSet                  bool                               `yaml:"-"`
-}
-
-func (p *FilePipelineProfile) UnmarshalYAML(node *yaml.Node) error {
-	if err := validateStructuredOutputRepairAttemptsNode(node, "pipeline profile"); err != nil {
-		return err
-	}
-	type plainFilePipelineProfile FilePipelineProfile
-	var decoded plainFilePipelineProfile
-	seen, err := decodeKnownMapping(node, &decoded, map[string]struct{}{
-		"llm_profile": {}, "structured_output_repair_attempts": {}, "validation_policy": {}, "input": {}, "chunk": {}, "artifacts": {}, "steps": {}, "output": {}, "references": {},
-	}, "pipeline profile")
-	if err != nil {
-		return err
-	}
-	*p = FilePipelineProfile(decoded)
-	if validationPolicyNode, ok := mappingValue(node, "validation_policy"); ok {
-		policy, err := parseValidationPolicy(validationPolicyNode, "pipeline profile")
-		if err != nil {
-			return err
-		}
-		p.ValidationPolicy = policy
-	}
-	_, p.artifactsSet = seen["artifacts"]
-	_, p.stepsSet = seen["steps"]
-	_, p.llmProfileSet = seen["llm_profile"]
-	return nil
-}
-
-func (s *FilePipelineStepProfile) UnmarshalYAML(node *yaml.Node) error {
-	type plainFilePipelineStepProfile FilePipelineStepProfile
-	var decoded plainFilePipelineStepProfile
-	if _, err := decodeKnownMapping(node, &decoded, map[string]struct{}{
-		"id": {}, "artifacts": {}, "references": {},
-	}, "pipeline step"); err != nil {
-		return err
-	}
-	*s = FilePipelineStepProfile(decoded)
-	return nil
-}
-
-func (l *FileArtifactLaneProfile) UnmarshalYAML(node *yaml.Node) error {
-	type plainFileArtifactLaneProfile FileArtifactLaneProfile
-	var decoded plainFileArtifactLaneProfile
-	if _, err := decodeKnownMapping(node, &decoded, map[string]struct{}{
-		"extract": {}, "merge": {}, "normalize": {}, "validators": {}, "references": {},
-	}, "artifact lane"); err != nil {
-		return err
-	}
-	*l = FileArtifactLaneProfile(decoded)
-	return nil
-}
-
-func decodeKnownMapping(node *yaml.Node, target any, allowed map[string]struct{}, context string) (map[string]struct{}, error) {
-	if node.Kind != yaml.MappingNode {
-		return nil, fmt.Errorf("%s must be an object", context)
-	}
-	if err := node.Decode(target); err != nil {
-		return nil, err
-	}
-	seen := make(map[string]struct{}, len(node.Content)/2)
-	for i := 0; i < len(node.Content); i += 2 {
-		key := node.Content[i].Value
-		if _, exists := seen[key]; exists {
-			return nil, fmt.Errorf("%s field %q is duplicated", context, key)
-		}
-		if _, ok := allowed[key]; !ok {
-			return nil, fmt.Errorf("field %s not found in %s", key, context)
-		}
-		seen[key] = struct{}{}
-	}
-	return seen, nil
-}
-
-type FilePipelineStepProfile struct {
-	ID         string                             `yaml:"id"`
-	Artifacts  map[string]FileArtifactLaneProfile `yaml:"artifacts"`
-	References map[string]fileReferenceSource     `yaml:"references,omitempty"`
-}
-
-type FileArtifactLaneProfile struct {
-	Extract    fileModuleBinding              `yaml:"extract"`
-	Merge      *fileModuleBinding             `yaml:"merge,omitempty"`
-	Normalize  *fileModuleBinding             `yaml:"normalize,omitempty"`
-	Validators []fileModuleBinding            `yaml:"validators,omitempty"`
-	References map[string]fileReferenceSource `yaml:"references,omitempty"`
-}
-
-type FileConcurrencyConfig struct {
-	TotalLLM     *int           `yaml:"total_llm,omitempty"`
-	StageWorkers map[string]int `yaml:"stage_workers,omitempty"`
-}
-
-type FileOutputConfig struct {
-	Directory *string `yaml:"directory,omitempty"`
-}
-type FileCacheConfig struct {
-	ChunkPlans  *FileChunkPlanCacheConfig  `yaml:"chunk_plans,omitempty"`
-	Checkpoints *FileCheckpointCacheConfig `yaml:"checkpoints,omitempty"`
-}
-type FileChunkPlanCacheConfig struct {
-	Directory *string `yaml:"directory,omitempty"`
-	Mode      *string `yaml:"mode,omitempty"`
-}
-type FileCheckpointCacheConfig struct {
-	Enabled   *bool   `yaml:"enabled,omitempty"`
-	Directory *string `yaml:"directory,omitempty"`
-}
-type FileDebugConfig struct {
-	Directory *string `yaml:"directory,omitempty"`
-}
-
-type fileModuleBinding struct {
-	Module                         string
-	LLMProfile                     string
-	StructuredOutputRepairAttempts *int
-	ValidationPolicy               *pipeline.ValidationPolicyOverride
-	Retries                        int
-	Options                        map[string]any
-	References                     map[string]fileReferenceSource
-	Validators                     pipeline.ValidatorOverride
-}
-
-type fileReferenceSource struct {
-	path     string
-	artifact *pipeline.ArtifactReference
-}
-
-func (source *fileReferenceSource) UnmarshalYAML(node *yaml.Node) error {
-	if source == nil {
-		return fmt.Errorf("reference source must not be nil")
-	}
-	switch node.Kind {
-	case yaml.ScalarNode:
-		if node.Tag != "!!str" {
-			return fmt.Errorf("external reference path must be a string")
-		}
-		path := strings.TrimSpace(node.Value)
-		if path == "" {
-			return fmt.Errorf("external reference path must not be empty")
-		}
-		source.path = path
-		source.artifact = nil
-		return nil
-	case yaml.MappingNode:
-		if len(node.Content) != 2 || node.Content[0].Value != "artifact" {
-			return fmt.Errorf("reference source mapping must contain only artifact")
-		}
-		artifactNode := node.Content[1]
-		if artifactNode.Kind != yaml.MappingNode {
-			return fmt.Errorf("artifact reference must be an object")
-		}
-		var step, lane string
-		seen := map[string]bool{}
-		for i := 0; i < len(artifactNode.Content); i += 2 {
-			key := artifactNode.Content[i].Value
-			value := artifactNode.Content[i+1]
-			if seen[key] {
-				return fmt.Errorf("artifact reference field %q is duplicated", key)
-			}
-			seen[key] = true
-			if value.Tag != "!!str" {
-				return fmt.Errorf("artifact reference field %q must be a string", key)
-			}
-			switch key {
-			case "step":
-				step = strings.TrimSpace(value.Value)
-			case "lane":
-				lane = strings.TrimSpace(value.Value)
-			default:
-				return fmt.Errorf("field %s not found in artifact reference", key)
-			}
-		}
-		if step == "" || lane == "" {
-			return fmt.Errorf("artifact reference step and lane must not be empty")
-		}
-		source.path = ""
-		source.artifact = &pipeline.ArtifactReference{Step: step, Lane: lane}
-		return nil
-	default:
-		return fmt.Errorf("reference source must be a string or object")
-	}
-}
-
-func (source fileReferenceSource) toPipelineSource() pipeline.ReferenceSource {
-	if source.artifact != nil {
-		artifact := *source.artifact
-		return pipeline.ReferenceSource{Artifact: &artifact}
-	}
-	return pipeline.ExternalReference(source.path)
-}
-
-func fileReferenceSourcesToPipeline(values map[string]fileReferenceSource) map[string]pipeline.ReferenceSource {
-	if len(values) == 0 {
-		return nil
-	}
-	out := make(map[string]pipeline.ReferenceSource, len(values))
-	for key, value := range values {
-		out[strings.TrimSpace(key)] = value.toPipelineSource()
-	}
-	return out
-}
-
-func (b *fileModuleBinding) UnmarshalYAML(node *yaml.Node) error {
-	switch node.Kind {
-	case yaml.ScalarNode:
-		var module string
-		if err := node.Decode(&module); err != nil {
-			return fmt.Errorf("module binding must be a string or object")
-		}
-		b.Module = strings.TrimSpace(module)
-		return nil
-	case yaml.MappingNode:
-		seen := make(map[string]struct{}, len(node.Content)/2)
-		for i := 0; i < len(node.Content); i += 2 {
-			keyNode := node.Content[i]
-			valueNode := node.Content[i+1]
-			if _, exists := seen[keyNode.Value]; exists {
-				return fmt.Errorf("module binding field %q is duplicated", keyNode.Value)
-			}
-			seen[keyNode.Value] = struct{}{}
-			switch keyNode.Value {
-			case "module":
-				var module string
-				if err := valueNode.Decode(&module); err != nil {
-					return err
-				}
-				b.Module = strings.TrimSpace(module)
-			case "llm_profile":
-				var llmProfile string
-				if err := valueNode.Decode(&llmProfile); err != nil {
-					return err
-				}
-				b.LLMProfile = strings.TrimSpace(llmProfile)
-				if b.LLMProfile == "" {
-					return fmt.Errorf("llm_profile must not be empty when set")
-				}
-			case "structured_output_repair_attempts":
-				attempts, err := parseStructuredOutputRepairAttempts(valueNode, "module binding")
-				if err != nil {
-					return err
-				}
-				b.StructuredOutputRepairAttempts = attempts
-			case "validation_policy":
-				policy, err := parseValidationPolicy(valueNode, "module binding")
-				if err != nil {
-					return err
-				}
-				b.ValidationPolicy = policy
-			case "retries":
-				var retries int
-				if err := valueNode.Decode(&retries); err != nil {
-					return err
-				}
-				b.Retries = retries
-			case "options":
-				var options map[string]any
-				if err := valueNode.Decode(&options); err != nil {
-					return err
-				}
-				b.Options = normalizeOptions(options)
-			case "references":
-				var references map[string]fileReferenceSource
-				if err := valueNode.Decode(&references); err != nil {
-					return err
-				}
-				b.References = references
-			case "validators":
-				b.Validators.Set = true
-				var validators []fileModuleBinding
-				if err := valueNode.Decode(&validators); err != nil {
-					return err
-				}
-				b.Validators.Validators = make([]pipeline.ModuleBinding, len(validators))
-				for i, validator := range validators {
-					b.Validators.Validators[i] = validator.toPipelineBinding()
-				}
-			default:
-				return fmt.Errorf("field %s not found in module binding", keyNode.Value)
-			}
-		}
-		return nil
-	default:
-		return fmt.Errorf("module binding must be a string or object")
-	}
-}
-
-func (b fileModuleBinding) toPipelineBinding() pipeline.ModuleBinding {
-	return pipeline.ModuleBinding{
-		Module:                         strings.TrimSpace(b.Module),
-		LLMProfile:                     strings.TrimSpace(b.LLMProfile),
-		StructuredOutputRepairAttempts: cloneStructuredOutputRepairAttempts(b.StructuredOutputRepairAttempts),
-		ValidationPolicy:               cloneValidationPolicyOverride(b.ValidationPolicy),
-		Retries:                        b.Retries,
-		Options:                        cloneOptions(b.Options),
-		References:                     fileReferenceSourcesToPipeline(b.References),
-		Validators:                     cloneValidatorOverride(b.Validators),
-	}
-}
-
-func mappingValue(node *yaml.Node, key string) (*yaml.Node, bool) {
-	for i := 0; i < len(node.Content); i += 2 {
-		if node.Content[i].Value == key {
-			return node.Content[i+1], true
-		}
-	}
-	return nil, false
-}
-
-func parseValidationPolicy(node *yaml.Node, context string) (*pipeline.ValidationPolicyOverride, error) {
-	if node == nil || node.Tag == "!!null" || node.Kind != yaml.MappingNode {
-		return nil, fmt.Errorf("%s validation_policy must be an object", context)
-	}
-	policy := &pipeline.ValidationPolicyOverride{}
-	seen := make(map[string]struct{}, len(node.Content)/2)
-	for i := 0; i < len(node.Content); i += 2 {
-		key := node.Content[i].Value
-		value := node.Content[i+1]
-		if _, exists := seen[key]; exists {
-			return nil, fmt.Errorf("%s validation_policy field %q is duplicated", context, key)
-		}
-		seen[key] = struct{}{}
-		if value.Tag == "!!null" || value.Kind != yaml.ScalarNode || value.Tag != "!!str" {
-			return nil, fmt.Errorf("%s validation_policy.%s must be a string", context, key)
-		}
-		switch key {
-		case "producer_structural_failure":
-			value := pipeline.ProducerStructuralFailureAction(value.Value)
-			policy.ProducerStructuralFailure = &value
-		case "semantic_rejection":
-			value := pipeline.SemanticRejectionAction(value.Value)
-			policy.SemanticRejection = &value
-		case "validator_failure":
-			value := pipeline.ValidatorFailureAction(value.Value)
-			policy.ValidatorFailure = &value
-		default:
-			return nil, fmt.Errorf("field %s not found in %s validation_policy", key, context)
-		}
-	}
-	if err := policy.Validate(); err != nil {
-		return nil, fmt.Errorf("%s validation_policy: %w", context, err)
-	}
-	return policy, nil
-}
-
-func validateStructuredOutputRepairAttemptsNode(node *yaml.Node, context string) error {
-	if node.Kind != yaml.MappingNode {
-		return fmt.Errorf("%s must be an object", context)
-	}
-	for i := 0; i < len(node.Content); i += 2 {
-		if node.Content[i].Value != "structured_output_repair_attempts" {
-			continue
-		}
-		if _, err := parseStructuredOutputRepairAttempts(node.Content[i+1], context); err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-func parseStructuredOutputRepairAttempts(node *yaml.Node, context string) (*int, error) {
-	if node.Tag == "!!null" {
-		return nil, fmt.Errorf("%s structured_output_repair_attempts must not be null", context)
-	}
-	if node.Kind != yaml.ScalarNode || node.Tag != "!!int" {
-		return nil, fmt.Errorf("%s structured_output_repair_attempts must be an integer", context)
-	}
-	var attempts int
-	if err := node.Decode(&attempts); err != nil {
-		return nil, fmt.Errorf("%s structured_output_repair_attempts must be an integer: %w", context, err)
-	}
-	if attempts < 0 || attempts > 3 {
-		return nil, fmt.Errorf("%s structured_output_repair_attempts must be between zero and three", context)
-	}
-	return &attempts, nil
-}
-
-func cloneStructuredOutputRepairAttempts(attempts *int) *int {
-	if attempts == nil {
-		return nil
-	}
-	value := *attempts
-	return &value
-}
-
-func LoadFileConfig(path string) (FileConfig, error) {
-	data, err := os.ReadFile(path)
-	if err != nil {
-		return FileConfig{}, fmt.Errorf("read config file %q: %w", path, err)
-	}
-	cfg, err := ParseFileConfigYAML(data)
-	if err != nil {
-		return FileConfig{}, fmt.Errorf("parse config file %q: %w", path, err)
-	}
-	return cfg, nil
-}
-
-func ParseFileConfigYAML(data []byte) (FileConfig, error) {
-	var header struct {
-		Version int `yaml:"version"`
-	}
-	if err := yaml.Unmarshal(data, &header); err != nil {
-		return FileConfig{}, fmt.Errorf("decode yaml version header: %w", err)
-	}
-	if header.Version == 0 {
-		return FileConfig{}, fmt.Errorf("config version is required")
-	}
-	if header.Version == 2 {
-		return FileConfig{}, fmt.Errorf("config version 2 is no longer supported; migrate the file using the version 2-to-3 migration in docs/config.md")
-	}
-	if header.Version == 3 {
-		return FileConfig{}, fmt.Errorf("config version 3 is no longer supported; change \"version: 3\" to \"version: 4\" and rename \"scriptorium:\" to \"promptkit:\"")
-	}
-	if header.Version != SupportedFileConfigVersion {
-		return FileConfig{}, fmt.Errorf("unsupported config version %d (supported version is %d)", header.Version, SupportedFileConfigVersion)
-	}
-	var fileCfg FileConfig
-	decoder := yaml.NewDecoder(bytes.NewReader(data))
-	decoder.KnownFields(true)
-	if err := decoder.Decode(&fileCfg); err != nil {
-		return FileConfig{}, fmt.Errorf("decode yaml: %w", err)
-	}
-	var trailing any
-	if err := decoder.Decode(&trailing); err == nil {
-		return FileConfig{}, fmt.Errorf("config must contain exactly one YAML document")
-	} else if err != io.EOF {
-		return FileConfig{}, fmt.Errorf("decode trailing yaml document: %w", err)
-	}
-	return fileCfg, nil
-}
-
-func (c *Config) ApplyFileConfig(fileCfg FileConfig) error {
-	return c.applyFileConfigWithLookup(fileCfg, os.LookupEnv)
-}
-
-func (c *Config) ApplyFileConfigWithLookup(fileCfg FileConfig, lookup func(string) (string, bool)) error {
-	return c.applyFileConfigWithLookup(fileCfg, lookup)
-}
-
-func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(string) (string, bool)) error {
-	_ = lookup
-	if c == nil {
-		return fmt.Errorf("config must not be nil")
-	}
-	if fileCfg.Version != SupportedFileConfigVersion {
-		return fmt.Errorf("unsupported config version %d", fileCfg.Version)
-	}
-	if c.Pipelines == nil {
-		c.Pipelines = map[string]pipeline.PipelineProfile{}
-	}
-
-	pipelineIDs, rawPipelineIDs, err := normalizedMapKeys(fileCfg.Pipelines, "pipeline id")
-	if err != nil {
-		return err
-	}
-	for _, pipelineID := range pipelineIDs {
-		filePipeline := fileCfg.Pipelines[rawPipelineIDs[pipelineID]]
-		hasArtifacts := filePipeline.artifactsSet || filePipeline.Artifacts != nil
-		hasSteps := filePipeline.stepsSet || filePipeline.Steps != nil
-		if hasArtifacts && hasSteps {
-			return fmt.Errorf("pipeline %q must not declare both artifacts and steps", pipelineID)
-		}
-		if hasSteps && len(filePipeline.Steps) == 0 {
-			return fmt.Errorf("pipeline %q must declare at least one ordered step", pipelineID)
-		}
-		if hasSteps {
-			seenSteps := make(map[string]struct{}, len(filePipeline.Steps))
-			seenLanes := make(map[string]struct{})
-			for index, step := range filePipeline.Steps {
-				stepID := strings.TrimSpace(step.ID)
-				if stepID == "" {
-					return fmt.Errorf("pipeline %q step[%d] id must not be empty", pipelineID, index)
-				}
-				if _, ok := seenSteps[stepID]; ok {
-					return fmt.Errorf("pipeline %q step id %q is duplicated after trimming", pipelineID, stepID)
-				}
-				seenSteps[stepID] = struct{}{}
-				laneIDs, rawLaneIDs, err := normalizedMapKeys(step.Artifacts, fmt.Sprintf("pipeline %q step %q artifact lane id", pipelineID, stepID))
-				if err != nil {
-					return err
-				}
-				for _, laneID := range laneIDs {
-					if _, ok := seenLanes[laneID]; ok {
-						return fmt.Errorf("pipeline %q artifact lane id %q is duplicated across steps", pipelineID, laneID)
-					}
-					seenLanes[laneID] = struct{}{}
-					fileLane := step.Artifacts[rawLaneIDs[laneID]]
-					if err := validateFileLaneReferences(pipelineID, stepID, laneID, fileLane); err != nil {
-						return err
-					}
-				}
-				if err := validateFileReferenceSources(step.References, fmt.Sprintf("pipeline %q step %q reference slot", pipelineID, stepID)); err != nil {
-					return err
-				}
-			}
-		}
-		if _, _, err := normalizedMapKeys(filePipeline.Artifacts, fmt.Sprintf("pipeline %q artifact lane id", pipelineID)); err != nil {
-			return err
-		}
-		if err := validateFileReferenceSources(filePipeline.References, fmt.Sprintf("pipeline %q reference slot", pipelineID)); err != nil {
-			return err
-		}
-		if filePipeline.Chunk != nil {
-			if _, _, err := normalizedMapKeys(filePipeline.Chunk.References, fmt.Sprintf("pipeline %q chunk reference slot", pipelineID)); err != nil {
-				return err
-			}
-		}
-		if _, _, err := normalizedMapKeys(filePipeline.Input.References, fmt.Sprintf("pipeline %q input reference slot", pipelineID)); err != nil {
-			return err
-		}
-		if filePipeline.Output != nil {
-			if _, _, err := normalizedMapKeys(filePipeline.Output.References, fmt.Sprintf("pipeline %q output reference slot", pipelineID)); err != nil {
-				return err
-			}
-		}
-		for rawLaneID, fileLane := range filePipeline.Artifacts {
-			laneID := strings.TrimSpace(rawLaneID)
-			if laneID == "" {
-				continue
-			}
-			if _, _, err := normalizedMapKeys(fileLane.References, fmt.Sprintf("pipeline %q lane %q reference slot", pipelineID, laneID)); err != nil {
-				return err
-			}
-			if _, _, err := normalizedMapKeys(fileLane.Extract.References, fmt.Sprintf("pipeline %q lane %q extract reference slot", pipelineID, laneID)); err != nil {
-				return err
-			}
-			if fileLane.Merge != nil {
-				if _, _, err := normalizedMapKeys(fileLane.Merge.References, fmt.Sprintf("pipeline %q lane %q merge reference slot", pipelineID, laneID)); err != nil {
-					return err
-				}
-			}
-			if fileLane.Normalize != nil {
-				if _, _, err := normalizedMapKeys(fileLane.Normalize.References, fmt.Sprintf("pipeline %q lane %q normalize reference slot", pipelineID, laneID)); err != nil {
-					return err
-				}
-			}
-			for i, validator := range fileLane.Validators {
-				if _, _, err := normalizedMapKeys(validator.References, fmt.Sprintf("pipeline %q lane %q validator[%d] reference slot", pipelineID, laneID, i)); err != nil {
-					return err
-				}
-			}
-		}
-	}
-
-	if fileCfg.PromptKit != nil {
-		if fileCfg.PromptKit.ProfileDir != nil {
-			value := strings.TrimSpace(*fileCfg.PromptKit.ProfileDir)
-			if value == "" {
-				return fmt.Errorf("promptkit.profile_dir must not be empty when set")
-			}
-			c.PromptKit.ProfileDir = value
-		}
-		if fileCfg.PromptKit.ProfileFile != nil {
-			value := strings.TrimSpace(*fileCfg.PromptKit.ProfileFile)
-			if value == "" {
-				return fmt.Errorf("promptkit.profile_file must not be empty when set")
-			}
-			c.PromptKit.ProfileFile = value
-		}
-		if fileCfg.PromptKit.LocalBackend != nil {
-			if fileCfg.PromptKit.LocalBackend.Endpoint == nil {
-				return fmt.Errorf("promptkit.local_backend.endpoint must not be empty when set")
-			}
-			endpoint := strings.TrimSpace(*fileCfg.PromptKit.LocalBackend.Endpoint)
-			if endpoint == "" {
-				return fmt.Errorf("promptkit.local_backend.endpoint must not be empty when set")
-			}
-			localBackend := PromptKitLocalBackendConfig{Endpoint: endpoint}
-			if fileCfg.PromptKit.LocalBackend.ConcurrencyLimit != nil {
-				localBackend.ConcurrencyLimit = *fileCfg.PromptKit.LocalBackend.ConcurrencyLimit
-			}
-			c.PromptKit.LocalBackend = &localBackend
-		}
-	}
-
-	for _, pipelineID := range pipelineIDs {
-		filePipeline := fileCfg.Pipelines[rawPipelineIDs[pipelineID]]
-		llmProfile := ""
-		if filePipeline.llmProfileSet || filePipeline.LLMProfile != nil {
-			if filePipeline.LLMProfile == nil || strings.TrimSpace(*filePipeline.LLMProfile) == "" {
-				return fmt.Errorf("pipeline %q llm_profile must not be empty when set", pipelineID)
-			}
-			llmProfile = strings.TrimSpace(*filePipeline.LLMProfile)
-		}
-		hasSteps := filePipeline.stepsSet || filePipeline.Steps != nil
-		laneIDs, rawLaneIDs, err := normalizedMapKeys(filePipeline.Artifacts, fmt.Sprintf("pipeline %q artifact lane id", pipelineID))
-		if err != nil {
-			return err
-		}
-		profile := pipeline.PipelineProfile{
-			ID:                             pipelineID,
-			LLMProfile:                     llmProfile,
-			StructuredOutputRepairAttempts: cloneStructuredOutputRepairAttempts(filePipeline.StructuredOutputRepairAttempts),
-			ValidationPolicy:               cloneValidationPolicyOverride(filePipeline.ValidationPolicy),
-			Input:                          filePipeline.Input.toPipelineBinding(),
-			Artifacts:                      make(map[string]pipeline.ArtifactLaneProfile, len(filePipeline.Artifacts)),
-			References:                     fileReferenceSourcesToPipeline(filePipeline.References),
-		}
-		if filePipeline.Chunk != nil {
-			profile.Chunk = filePipeline.Chunk.toPipelineBinding()
-		}
-		if filePipeline.Output != nil {
-			profile.Output = filePipeline.Output.toPipelineBinding()
-		}
-		for _, laneID := range laneIDs {
-			fileLane := filePipeline.Artifacts[rawLaneIDs[laneID]]
-			extract := fileLane.Extract.toPipelineBinding()
-			extract.References = mergeReferenceSources(fileReferenceSourcesToPipeline(fileLane.References), extract.References)
-			lane := pipeline.ArtifactLaneProfile{
-				Extract:    extract,
-				References: fileReferenceSourcesToPipeline(fileLane.References),
-			}
-			if fileLane.Merge != nil {
-				lane.Merge = fileLane.Merge.toPipelineBinding()
-			}
-			if fileLane.Normalize != nil {
-				lane.Normalize = fileLane.Normalize.toPipelineBinding()
-			}
-			if len(fileLane.Validators) > 0 {
-				lane.Validators = make([]pipeline.ModuleBinding, len(fileLane.Validators))
-				for i, validator := range fileLane.Validators {
-					lane.Validators[i] = validator.toPipelineBinding()
-				}
-			}
-			profile.Artifacts[laneID] = lane
-		}
-		if hasSteps {
-			profile.Artifacts = nil
-			profile.Steps = make([]pipeline.PipelineStepProfile, len(filePipeline.Steps))
-			for i, fileStep := range filePipeline.Steps {
-				stepID := strings.TrimSpace(fileStep.ID)
-				step := pipeline.PipelineStepProfile{
-					ID:         stepID,
-					Artifacts:  make(map[string]pipeline.ArtifactLaneProfile, len(fileStep.Artifacts)),
-					References: fileReferenceSourcesToPipeline(fileStep.References),
-				}
-				stepLaneIDs, stepRawLaneIDs, err := normalizedMapKeys(fileStep.Artifacts, fmt.Sprintf("pipeline %q step %q artifact lane id", pipelineID, stepID))
-				if err != nil {
-					return err
-				}
-				for _, laneID := range stepLaneIDs {
-					fileLane := fileStep.Artifacts[stepRawLaneIDs[laneID]]
-					extract := fileLane.Extract.toPipelineBinding()
-					extract.References = mergeReferenceSources(fileReferenceSourcesToPipeline(fileLane.References), extract.References)
-					lane := pipeline.ArtifactLaneProfile{Extract: extract, References: fileReferenceSourcesToPipeline(fileLane.References)}
-					if fileLane.Merge != nil {
-						lane.Merge = fileLane.Merge.toPipelineBinding()
-					}
-					if fileLane.Normalize != nil {
-						lane.Normalize = fileLane.Normalize.toPipelineBinding()
-					}
-					if len(fileLane.Validators) > 0 {
-						lane.Validators = make([]pipeline.ModuleBinding, len(fileLane.Validators))
-						for index, validator := range fileLane.Validators {
-							lane.Validators[index] = validator.toPipelineBinding()
-						}
-					}
-					step.Artifacts[laneID] = lane
-				}
-				profile.Steps[i] = step
-			}
-		}
-		c.Pipelines[pipelineID] = profile
-	}
-
-	if fileCfg.Concurrency != nil && fileCfg.Concurrency.TotalLLM != nil {
-		c.Concurrency.TotalLLM = *fileCfg.Concurrency.TotalLLM
-	}
-	if fileCfg.Concurrency != nil && fileCfg.Concurrency.StageWorkers != nil {
-		workers, configured, err := normalizeStageWorkers(fileCfg.Concurrency.StageWorkers)
-		if err != nil {
-			return err
-		}
-		c.Concurrency.StageWorkers = workers
-		c.Concurrency.extractWorkersConfigured = configured
-	}
-	c.Concurrency.recomputeStageWorkerDefaults()
-	if fileCfg.Output != nil && fileCfg.Output.Directory != nil {
-		c.Output.Directory = strings.TrimSpace(*fileCfg.Output.Directory)
-		if c.Output.Directory == "" {
-			return fmt.Errorf("output.directory must not be empty")
-		}
-		if strings.ContainsRune(c.Output.Directory, '\x00') {
-			return fmt.Errorf("output.directory must not contain NUL")
-		}
-	}
-	if fileCfg.Cache != nil {
-		if fileCfg.Cache.ChunkPlans != nil {
-			if fileCfg.Cache.ChunkPlans.Mode != nil {
-				mode, err := pipeline.ParseChunkCacheMode(*fileCfg.Cache.ChunkPlans.Mode)
-				if err != nil {
-					return fmt.Errorf("cache.chunk_plans.mode: %w", err)
-				}
-				c.Cache.ChunkPlans.Mode = mode
-			}
-			if fileCfg.Cache.ChunkPlans.Directory != nil {
-				c.Cache.ChunkPlans.Directory = cleanOptionalPath(*fileCfg.Cache.ChunkPlans.Directory)
-				if strings.ContainsRune(c.Cache.ChunkPlans.Directory, '\x00') {
-					return fmt.Errorf("cache.chunk_plans.directory must not contain NUL")
-				}
-			}
-		}
-		if fileCfg.Cache.Checkpoints != nil {
-			if fileCfg.Cache.Checkpoints.Enabled != nil {
-				c.Cache.Checkpoints.Enabled = *fileCfg.Cache.Checkpoints.Enabled
-			}
-			if fileCfg.Cache.Checkpoints.Directory != nil {
-				c.Cache.Checkpoints.Directory = cleanOptionalPath(*fileCfg.Cache.Checkpoints.Directory)
-				if strings.ContainsRune(c.Cache.Checkpoints.Directory, '\x00') {
-					return fmt.Errorf("cache.checkpoints.directory must not contain NUL")
-				}
-			}
-		}
-	}
-	if fileCfg.Debug != nil && fileCfg.Debug.Directory != nil {
-		c.Debug.Directory = strings.TrimSpace(*fileCfg.Debug.Directory)
-		if c.Debug.Directory == "" {
-			return fmt.Errorf("debug.directory must not be empty")
-		}
-		if strings.ContainsRune(c.Debug.Directory, '\x00') {
-			return fmt.Errorf("debug.directory must not contain NUL")
-		}
-	}
-
-	return nil
-}
-
-func cleanOptionalPath(value string) string {
-	value = strings.TrimSpace(value)
-	if value == "" {
-		return ""
-	}
-	return filepath.Clean(value)
-}
-
-func normalizeStageWorkers(values map[string]int) (map[string]int, bool, error) {
-	workers := make(map[string]int, len(values))
-	configured := false
-	for rawKey, value := range values {
-		key := strings.TrimSpace(rawKey)
-		if key == "" {
-			return nil, false, fmt.Errorf("concurrency.stage_workers key must not be empty")
-		}
-		if key != "extract" {
-			return nil, false, fmt.Errorf("concurrency.stage_workers key %q is not supported", rawKey)
-		}
-		if _, exists := workers[key]; exists {
-			return nil, false, fmt.Errorf("concurrency.stage_workers key %q is duplicated after trimming", key)
-		}
-		workers[key] = value
-		configured = true
-	}
-	return workers, configured, nil
-}
-
-func normalizedMapKeys[T any](values map[string]T, keyName string) ([]string, map[string]string, error) {
-	keys := make([]string, 0, len(values))
-	rawByNormalized := make(map[string]string, len(values))
-	for rawID := range values {
-		id := strings.TrimSpace(rawID)
-		if id == "" {
-			return nil, nil, fmt.Errorf("%s must not be empty", keyName)
-		}
-		if _, ok := rawByNormalized[id]; ok {
-			return nil, nil, fmt.Errorf("%s %q is duplicated after trimming", keyName, id)
-		}
-		rawByNormalized[id] = rawID
-		keys = append(keys, id)
-	}
-	sort.Strings(keys)
-	return keys, rawByNormalized, nil
-}
-
-func validateFileReferenceSources(values map[string]fileReferenceSource, context string) error {
-	seen := make(map[string]struct{}, len(values))
-	for rawSlot, source := range values {
-		slot := strings.TrimSpace(rawSlot)
-		if slot == "" {
-			return fmt.Errorf("%s must not be empty", context)
-		}
-		if _, ok := seen[slot]; ok {
-			return fmt.Errorf("%s %q is duplicated after trimming", context, slot)
-		}
-		seen[slot] = struct{}{}
-		if source.artifact != nil {
-			if strings.TrimSpace(source.artifact.Step) == "" || strings.TrimSpace(source.artifact.Lane) == "" {
-				return fmt.Errorf("%s %q artifact selector step and lane must not be empty", context, slot)
-			}
-			if strings.TrimSpace(source.path) != "" {
-				return fmt.Errorf("%s %q must contain either an external path or artifact selector", context, slot)
-			}
-			continue
-		}
-		if strings.TrimSpace(source.path) == "" {
-			return fmt.Errorf("%s %q source must not be empty", context, slot)
-		}
-	}
-	return nil
-}
-
-func validateFileLaneReferences(pipelineID, stepID, laneID string, lane FileArtifactLaneProfile) error {
-	prefix := fmt.Sprintf("pipeline %q step %q lane %q", pipelineID, stepID, laneID)
-	references := []struct {
-		label  string
-		values map[string]fileReferenceSource
-	}{
-		{label: "reference slot", values: lane.References},
-		{label: "extract reference slot", values: lane.Extract.References},
-	}
-	if lane.Merge != nil {
-		references = append(references, struct {
-			label  string
-			values map[string]fileReferenceSource
-		}{label: "merge reference slot", values: lane.Merge.References})
-	}
-	if lane.Normalize != nil {
-		references = append(references, struct {
-			label  string
-			values map[string]fileReferenceSource
-		}{label: "normalize reference slot", values: lane.Normalize.References})
-	}
-	for _, item := range references {
-		if err := validateFileReferenceSources(item.values, prefix+" "+item.label); err != nil {
-			return err
-		}
-	}
-	for index, validator := range lane.Validators {
-		if err := validateFileReferenceSources(validator.References, fmt.Sprintf("%s validator[%d] reference slot", prefix, index)); err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-func mergeReferenceSources(base map[string]pipeline.ReferenceSource, override map[string]pipeline.ReferenceSource) map[string]pipeline.ReferenceSource {
-	if len(base) == 0 && len(override) == 0 {
-		return nil
-	}
-	out := make(map[string]pipeline.ReferenceSource, len(base)+len(override))
-	for key, value := range base {
-		out[key] = value
-	}
-	for key, value := range override {
-		out[key] = value
-	}
-	return out
-}
-
-func normalizeOptions(options map[string]any) map[string]any {
-	if len(options) == 0 {
-		return nil
-	}
-	return cloneOptions(options)
-}

internal/core/config/file_config_contract_test.go

@@ -1,928 +0,0 @@
-package config
-
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"path/filepath"
-	"reflect"
-	"strings"
-	"testing"
-
-	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
-)
-
-func TestDefaultReturnsDocumentedValuesAndIndependentMaps(t *testing.T) {
-	first := Default()
-	if first.Concurrency.TotalLLM != 16 || first.Concurrency.StageWorkers["extract"] != 16 {
-		t.Fatalf("concurrency defaults = %#v", first.Concurrency)
-	}
-	if first.Output.Directory != "./notarius-output" || first.Debug.Directory != "./notarius-debug" {
-		t.Fatalf("output/debug defaults = %#v, %#v", first.Output, first.Debug)
-	}
-	if first.Cache.ChunkPlans.Mode != pipeline.ChunkCacheAuto || first.Cache.ChunkPlans.Directory != "" || first.Cache.Checkpoints.Enabled || first.Cache.Checkpoints.Directory != "" {
-		t.Fatalf("cache defaults = %#v", first.Cache)
-	}
-	if len(first.Pipelines) != 0 {
-		t.Fatalf("pipeline defaults = %#v", first.Pipelines)
-	}
-
-	first.Concurrency.StageWorkers["extract"] = 99
-	first.Concurrency.StageWorkers["other"] = 100
-	first.Pipelines["changed"] = pipeline.PipelineProfile{}
-	second := Default()
-	if second.Concurrency.StageWorkers["extract"] != 16 || len(second.Concurrency.StageWorkers) != 1 || len(second.Pipelines) != 0 {
-		t.Fatalf("Default() returned state shared with an earlier result: %#v", second)
-	}
-}
-
-func TestFileConfigMinimalVersion4AppliesOverDefaults(t *testing.T) {
-	file := parseFileConfig(t, "version: 4\n")
-	cfg := Default()
-	if err := cfg.ApplyFileConfig(file); err != nil {
-		t.Fatal(err)
-	}
-	if cfg.Output.Directory != "./notarius-output" || cfg.Debug.Directory != "./notarius-debug" || cfg.Cache.ChunkPlans.Mode != pipeline.ChunkCacheAuto {
-		t.Fatalf("minimal file changed unrelated defaults: %#v", cfg)
-	}
-	if cfg.Concurrency.TotalLLM != 16 || cfg.Concurrency.StageWorkers["extract"] != 16 || len(cfg.Pipelines) != 0 {
-		t.Fatalf("minimal file did not retain defaults: %#v", cfg)
-	}
-}
-
-func TestParseFileConfigYAMLRejectsAdditionalDocuments(t *testing.T) {
-	tests := []struct {
-		name    string
-		source  string
-		wantErr bool
-	}{
-		{name: "trailing whitespace", source: "version: 4\n\n  \t", wantErr: false},
-		{name: "trailing comment", source: "version: 4\n# trailing comment\n", wantErr: false},
-		{name: "second valid document", source: "version: 4\n---\nversion: 4\n", wantErr: true},
-		{name: "second empty document", source: "version: 4\n---\n", wantErr: true},
-		{name: "second malformed document", source: "version: 4\n---\nversion: [\n", wantErr: true},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			_, err := ParseFileConfigYAML([]byte(tt.source))
-			if (err != nil) != tt.wantErr {
-				t.Fatalf("ParseFileConfigYAML() error = %v, want error=%t", err, tt.wantErr)
-			}
-		})
-	}
-}
-
-func TestFilePipelineLLMProfileIsPresenceAwareAndDetached(t *testing.T) {
-	const pipelineYAML = `version: 4
-pipelines:
-  main:
-    %s
-    input: input
-    artifacts:
-      lane:
-        extract: extract
-`
-
-	t.Run("omitted", func(t *testing.T) {
-		file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, ""))
-		if file.Pipelines["main"].LLMProfile != nil || file.Pipelines["main"].llmProfileSet {
-			t.Fatalf("parsed pipeline profile = %#v, want omitted llm profile", file.Pipelines["main"])
-		}
-		cfg := Default()
-		if err := cfg.ApplyFileConfig(file); err != nil {
-			t.Fatal(err)
-		}
-		if got := cfg.Pipelines["main"].LLMProfile; got != "" {
-			t.Fatalf("pipeline llm profile = %q, want empty", got)
-		}
-	})
-
-	t.Run("trimmed and detached", func(t *testing.T) {
-		file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, "llm_profile: ' configured-profile '"))
-		cfg := Default()
-		if err := cfg.ApplyFileConfig(file); err != nil {
-			t.Fatal(err)
-		}
-		if got := cfg.Pipelines["main"].LLMProfile; got != "configured-profile" {
-			t.Fatalf("pipeline llm profile = %q, want trimmed value", got)
-		}
-		*file.Pipelines["main"].LLMProfile = "changed-profile"
-		if got := cfg.Pipelines["main"].LLMProfile; got != "configured-profile" {
-			t.Fatalf("effective config aliases parsed file: %q", got)
-		}
-		if got := cloneConfig(cfg).Pipelines["main"].LLMProfile; got != "configured-profile" {
-			t.Fatalf("cloned pipeline llm profile = %q", got)
-		}
-		data, err := json.Marshal(cfg)
-		if err != nil {
-			t.Fatal(err)
-		}
-		var roundTripped Config
-		if err := json.Unmarshal(data, &roundTripped); err != nil {
-			t.Fatal(err)
-		}
-		if got := roundTripped.Pipelines["main"].LLMProfile; got != "configured-profile" {
-			t.Fatalf("round-tripped pipeline llm profile = %q", got)
-		}
-	})
-
-	for _, value := range []string{"''", "'   '", "null"} {
-		t.Run("explicit empty "+value, func(t *testing.T) {
-			file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, "llm_profile: "+value))
-			cfg := Default()
-			err := cfg.ApplyFileConfig(file)
-			if err == nil || !strings.Contains(err.Error(), `pipeline "main" llm_profile must not be empty`) {
-				t.Fatalf("ApplyFileConfig() error = %v, want explicit-empty rejection", err)
-			}
-		})
-	}
-}
-
-func TestStructuredOutputRepairAttemptsFileConfigurationPreservesPresenceAndOwnership(t *testing.T) {
-	const pipelineYAML = `version: 4
-pipelines:
-  main:
-    %s
-    input: input
-    artifacts:
-      lane:
-        extract:
-          module: extract
-          structured_output_repair_attempts: 2
-          validators:
-            - module: validator
-              structured_output_repair_attempts: 3
-`
-
-	t.Run("omitted pipeline value remains absent", func(t *testing.T) {
-		file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, ""))
-		if got := file.Pipelines["main"].StructuredOutputRepairAttempts; got != nil {
-			t.Fatalf("file pipeline repair attempts = %v, want nil", *got)
-		}
-		cfg := Default()
-		if err := cfg.ApplyFileConfig(file); err != nil {
-			t.Fatal(err)
-		}
-		if got := cfg.Pipelines["main"].StructuredOutputRepairAttempts; got != nil {
-			t.Fatalf("pipeline repair attempts = %v, want nil", *got)
-		}
-		if got := cfg.Pipelines["main"].Input.StructuredOutputRepairAttempts; got != nil {
-			t.Fatalf("scalar input binding repair attempts = %v, want nil", *got)
-		}
-	})
-
-	t.Run("zero is explicit and survives configuration boundaries", func(t *testing.T) {
-		file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, "structured_output_repair_attempts: 0"))
-		cfg := Default()
-		if err := cfg.ApplyFileConfig(file); err != nil {
-			t.Fatal(err)
-		}
-		profile := cfg.Pipelines["main"]
-		if profile.StructuredOutputRepairAttempts == nil || *profile.StructuredOutputRepairAttempts != 0 {
-			t.Fatalf("pipeline repair attempts = %v, want explicit zero", profile.StructuredOutputRepairAttempts)
-		}
-		lane := profile.Artifacts["lane"]
-		if lane.Extract.StructuredOutputRepairAttempts == nil || *lane.Extract.StructuredOutputRepairAttempts != 2 {
-			t.Fatalf("extract repair attempts = %v, want 2", lane.Extract.StructuredOutputRepairAttempts)
-		}
-		if lane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts == nil || *lane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts != 3 {
-			t.Fatalf("validator repair attempts = %v, want 3", lane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts)
-		}
-
-		*file.Pipelines["main"].StructuredOutputRepairAttempts = 1
-		if got := *cfg.Pipelines["main"].StructuredOutputRepairAttempts; got != 0 {
-			t.Fatalf("applied config aliased file configuration: got %d, want 0", got)
-		}
-		fileProfile := file.Pipelines["main"]
-		fileLane := fileProfile.Artifacts["lane"]
-		*fileLane.Extract.StructuredOutputRepairAttempts = 1
-		*fileLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts = 1
-		fileProfile.Artifacts["lane"] = fileLane
-		file.Pipelines["main"] = fileProfile
-		configuredLane := cfg.Pipelines["main"].Artifacts["lane"]
-		if got := *configuredLane.Extract.StructuredOutputRepairAttempts; got != 2 {
-			t.Fatalf("configured extract aliased file configuration: got %d, want 2", got)
-		}
-		if got := *configuredLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts; got != 3 {
-			t.Fatalf("configured validator aliased file configuration: got %d, want 3", got)
-		}
-		cloned := cloneConfig(cfg)
-		*cloned.Pipelines["main"].StructuredOutputRepairAttempts = 1
-		if got := *cfg.Pipelines["main"].StructuredOutputRepairAttempts; got != 0 {
-			t.Fatalf("cloned config aliased source configuration: got %d, want 0", got)
-		}
-		redacted := cfg.Redacted()
-		*redacted.Pipelines["main"].StructuredOutputRepairAttempts = 1
-		if got := *cfg.Pipelines["main"].StructuredOutputRepairAttempts; got != 0 {
-			t.Fatalf("redacted config aliased source configuration: got %d, want 0", got)
-		}
-		summary := cfg.RedactedSummaryPayload().(Config)
-		if summary.Pipelines["main"].StructuredOutputRepairAttempts == nil || *summary.Pipelines["main"].StructuredOutputRepairAttempts != 0 {
-			t.Fatalf("redacted summary pipeline repair attempts = %v, want explicit zero", summary.Pipelines["main"].StructuredOutputRepairAttempts)
-		}
-
-		data, err := json.Marshal(cfg)
-		if err != nil {
-			t.Fatal(err)
-		}
-		var roundTripped Config
-		if err := json.Unmarshal(data, &roundTripped); err != nil {
-			t.Fatal(err)
-		}
-		roundTrippedProfile := roundTripped.Pipelines["main"]
-		if roundTrippedProfile.StructuredOutputRepairAttempts == nil || *roundTrippedProfile.StructuredOutputRepairAttempts != 0 {
-			t.Fatalf("round-tripped pipeline repair attempts = %v, want explicit zero", roundTrippedProfile.StructuredOutputRepairAttempts)
-		}
-		roundTrippedLane := roundTrippedProfile.Artifacts["lane"]
-		if roundTrippedLane.Extract.StructuredOutputRepairAttempts == nil || *roundTrippedLane.Extract.StructuredOutputRepairAttempts != 2 {
-			t.Fatalf("round-tripped extract repair attempts = %v, want 2", roundTrippedLane.Extract.StructuredOutputRepairAttempts)
-		}
-		if roundTrippedLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts == nil || *roundTrippedLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts != 3 {
-			t.Fatalf("round-tripped validator repair attempts = %v, want 3", roundTrippedLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts)
-		}
-	})
-}
-
-func TestStructuredOutputRepairAttemptsFileConfigurationRejectsInvalidValues(t *testing.T) {
-	const pipelineYAML = `version: 4
-pipelines:
-  main:
-    input: input
-    artifacts:
-      lane:
-        extract: extract
-    %s
-`
-	const bindingYAML = `version: 4
-pipelines:
-  main:
-    input:
-      module: input
-      %s
-    artifacts:
-      lane:
-        extract: extract
-`
-
-	for _, tt := range []struct {
-		name   string
-		source string
-		want   string
-	}{
-		{name: "null pipeline value", source: "structured_output_repair_attempts: null", want: "pipeline profile structured_output_repair_attempts must not be null"},
-		{name: "fractional pipeline value", source: "structured_output_repair_attempts: 1.5", want: "pipeline profile structured_output_repair_attempts must be an integer"},
-		{name: "quoted pipeline value", source: "structured_output_repair_attempts: '1'", want: "pipeline profile structured_output_repair_attempts must be an integer"},
-		{name: "out of range pipeline value", source: "structured_output_repair_attempts: 4", want: "pipeline profile structured_output_repair_attempts must be between zero and three"},
-	} {
-		t.Run(tt.name, func(t *testing.T) {
-			_, err := ParseFileConfigYAML([]byte(fmt.Sprintf(pipelineYAML, tt.source)))
-			if err == nil || !strings.Contains(err.Error(), tt.want) {
-				t.Fatalf("ParseFileConfigYAML() error = %v, want %q", err, tt.want)
-			}
-		})
-	}
-
-	for _, tt := range []struct {
-		name   string
-		source string
-		want   string
-	}{
-		{name: "null binding value", source: "structured_output_repair_attempts: null", want: "module binding structured_output_repair_attempts must not be null"},
-		{name: "noninteger binding value", source: "structured_output_repair_attempts: true", want: "module binding structured_output_repair_attempts must be an integer"},
-		{name: "out of range binding value", source: "structured_output_repair_attempts: -1", want: "module binding structured_output_repair_attempts must be between zero and three"},
-	} {
-		t.Run(tt.name, func(t *testing.T) {
-			_, err := ParseFileConfigYAML([]byte(fmt.Sprintf(bindingYAML, tt.source)))
-			if err == nil || !strings.Contains(err.Error(), tt.want) {
-				t.Fatalf("ParseFileConfigYAML() error = %v, want %q", err, tt.want)
-			}
-		})
-	}
-}
-
-func TestFileModuleBindingRejectsExplicitEmptyLLMProfile(t *testing.T) {
-	const configYAML = `version: 4
-pipelines:
-  main:
-    input:
-      module: input
-      llm_profile: %s
-    artifacts:
-      lane:
-        extract: extract
-`
-	for _, value := range []string{"''", "'   '", "null"} {
-		t.Run(value, func(t *testing.T) {
-			_, err := ParseFileConfigYAML([]byte(fmt.Sprintf(configYAML, value)))
-			if err == nil || !strings.Contains(err.Error(), "llm_profile must not be empty when set") {
-				t.Fatalf("ParseFileConfigYAML() error = %v, want explicit-empty binding profile rejection", err)
-			}
-		})
-	}
-}
-
-func TestFilePromptKitProfileSourcesSurviveConfigBoundaries(t *testing.T) {
-	tests := []struct {
-		name string
-		yaml string
-		want PromptKitConfig
-	}{
-		{
-			name: "profile directory",
-			yaml: "version: 4\npromptkit:\n  profile_dir: ' ./profiles '\n",
-			want: PromptKitConfig{ProfileDir: "./profiles"},
-		},
-		{
-			name: "profile file",
-			yaml: "version: 4\npromptkit:\n  profile_file: ' ./profiles.yml '\n",
-			want: PromptKitConfig{ProfileFile: "./profiles.yml"},
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			cfg := applyFileConfig(t, tt.yaml)
-			if cfg.PromptKit != tt.want {
-				t.Fatalf("PromptKit config = %#v, want %#v", cfg.PromptKit, tt.want)
-			}
-			if got := cloneConfig(cfg).PromptKit; got != tt.want {
-				t.Fatalf("cloned PromptKit config = %#v, want %#v", got, tt.want)
-			}
-			if got := cfg.Redacted().PromptKit; got != tt.want {
-				t.Fatalf("redacted PromptKit config = %#v, want %#v", got, tt.want)
-			}
-
-			data, err := json.Marshal(cfg)
-			if err != nil {
-				t.Fatalf("json.Marshal() error = %v", err)
-			}
-			var payload map[string]json.RawMessage
-			if err := json.Unmarshal(data, &payload); err != nil {
-				t.Fatalf("json.Unmarshal() error = %v", err)
-			}
-			if _, ok := payload["promptkit"]; !ok {
-				t.Fatalf("runtime JSON keys = %v, want promptkit", payload)
-			}
-			if _, ok := payload["scriptorium"]; ok {
-				t.Fatalf("runtime JSON keys = %v, must not contain removed section", payload)
-			}
-		})
-	}
-}
-
-func TestFilePromptKitLocalBackendSurvivesConfigBoundaries(t *testing.T) {
-	tests := []struct {
-		name            string
-		concurrencyYAML string
-		wantConcurrency int
-	}{
-		{name: "omitted concurrency defaults to zero"},
-		{name: "positive concurrency is preserved", concurrencyYAML: "    concurrency_limit: 2\n", wantConcurrency: 2},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			file := parseFileConfig(t, "version: 4\npromptkit:\n  local_backend:\n    endpoint: ' http://localhost:8000/v1 '\n"+tt.concurrencyYAML)
-			cfg := Default()
-			if err := cfg.ApplyFileConfig(file); err != nil {
-				t.Fatalf("ApplyFileConfig() error = %v", err)
-			}
-			want := PromptKitLocalBackendConfig{
-				Endpoint:         "http://localhost:8000/v1",
-				ConcurrencyLimit: tt.wantConcurrency,
-			}
-			if cfg.PromptKit.LocalBackend == nil || *cfg.PromptKit.LocalBackend != want {
-				t.Fatalf("local backend config = %#v, want %#v", cfg.PromptKit.LocalBackend, want)
-			}
-
-			*file.PromptKit.LocalBackend.Endpoint = "http://changed.example/v1"
-			if file.PromptKit.LocalBackend.ConcurrencyLimit != nil {
-				*file.PromptKit.LocalBackend.ConcurrencyLimit = 99
-			}
-			if *cfg.PromptKit.LocalBackend != want {
-				t.Fatalf("effective config aliases parsed file model: %#v", cfg.PromptKit.LocalBackend)
-			}
-
-			cloned := cloneConfig(cfg)
-			if cloned.PromptKit.LocalBackend == cfg.PromptKit.LocalBackend || *cloned.PromptKit.LocalBackend != want {
-				t.Fatalf("cloned local backend = %#v, want detached %#v", cloned.PromptKit.LocalBackend, want)
-			}
-			cloned.PromptKit.LocalBackend.Endpoint = "http://clone.example/v1"
-			if *cfg.PromptKit.LocalBackend != want {
-				t.Fatalf("mutating clone changed source config: %#v", cfg.PromptKit.LocalBackend)
-			}
-
-			redacted := cfg.Redacted()
-			if redacted.PromptKit.LocalBackend == cfg.PromptKit.LocalBackend || *redacted.PromptKit.LocalBackend != want {
-				t.Fatalf("redacted local backend = %#v, want detached %#v", redacted.PromptKit.LocalBackend, want)
-			}
-
-			data, err := json.Marshal(cfg)
-			if err != nil {
-				t.Fatalf("json.Marshal() error = %v", err)
-			}
-			var payload struct {
-				PromptKit map[string]json.RawMessage `json:"promptkit"`
-			}
-			if err := json.Unmarshal(data, &payload); err != nil {
-				t.Fatalf("json.Unmarshal() error = %v", err)
-			}
-			localJSON, ok := payload.PromptKit["local_backend"]
-			if !ok {
-				t.Fatalf("runtime PromptKit JSON keys = %v, want local_backend", payload.PromptKit)
-			}
-			var localPayload map[string]json.RawMessage
-			if err := json.Unmarshal(localJSON, &localPayload); err != nil {
-				t.Fatalf("unmarshal local_backend JSON: %v", err)
-			}
-			if _, ok := localPayload["endpoint"]; !ok {
-				t.Fatalf("runtime local_backend JSON keys = %v, want endpoint", localPayload)
-			}
-			if _, ok := localPayload["concurrency_limit"]; !ok {
-				t.Fatalf("runtime local_backend JSON keys = %v, want concurrency_limit", localPayload)
-			}
-		})
-	}
-}
-
-func TestFilePromptKitLocalBackendRequiresEndpoint(t *testing.T) {
-	for _, tt := range []struct {
-		name string
-		yaml string
-	}{
-		{name: "missing", yaml: "version: 4\npromptkit:\n  local_backend: {}\n"},
-		{name: "empty", yaml: "version: 4\npromptkit:\n  local_backend:\n    endpoint: ''\n"},
-		{name: "blank", yaml: "version: 4\npromptkit:\n  local_backend:\n    endpoint: '   '\n"},
-	} {
-		t.Run(tt.name, func(t *testing.T) {
-			file := parseFileConfig(t, tt.yaml)
-			cfg := Default()
-			err := cfg.ApplyFileConfig(file)
-			if err == nil || !strings.Contains(err.Error(), "promptkit.local_backend.endpoint") {
-				t.Fatalf("ApplyFileConfig() error = %v, want endpoint field context", err)
-			}
-		})
-	}
-}
-
-func TestFilePromptKitExplicitEmptyProfileSourcesAreRejected(t *testing.T) {
-	for _, field := range []string{"profile_dir", "profile_file"} {
-		t.Run(field, func(t *testing.T) {
-			file := parseFileConfig(t, "version: 4\npromptkit:\n  "+field+": ''\n")
-			cfg := Default()
-			err := cfg.ApplyFileConfig(file)
-			if err == nil || !strings.Contains(err.Error(), "promptkit."+field+" must not be empty") {
-				t.Fatalf("ApplyFileConfig() error = %v, want explicit-empty rejection", err)
-			}
-		})
-	}
-}
-
-func TestFilePromptKitProfileSourcesRemainMutuallyExclusive(t *testing.T) {
-	cfg := applyFileConfig(t, `version: 4
-promptkit:
-  profile_dir: ./profiles
-  profile_file: ./profiles.yml
-`)
-	if err := cfg.Validate(); err == nil || !strings.Contains(err.Error(), "promptkit profile_dir and profile_file are mutually exclusive") {
-		t.Fatalf("Validate() error = %v, want mutually exclusive profile sources", err)
-	}
-}
-
-func TestFileConfigMissingVersionIsReportedBeforeFieldDecoding(t *testing.T) {
-	_, err := ParseFileConfigYAML([]byte("workspace:\n  directory: /tmp/old\n"))
-	if err == nil || !strings.Contains(err.Error(), "config version is required") {
-		t.Fatalf("missing version error = %v", err)
-	}
-}
-
-func TestFileConfigVersion3ReportsPromptKitMigration(t *testing.T) {
-	_, err := ParseFileConfigYAML([]byte("version: 3\nscriptorium:\n  profile_dir: ./profiles\n"))
-	if err == nil ||
-		!strings.Contains(err.Error(), `change "version: 3" to "version: 4"`) ||
-		!strings.Contains(err.Error(), `rename "scriptorium:" to "promptkit:"`) {
-		t.Fatalf("version 3 error = %v, want actionable version and section migration", err)
-	}
-}
-
-func TestFileConfigRejectsUnknownCurrentAndRemovedFields(t *testing.T) {
-	tests := []struct {
-		name string
-		yaml string
-		want string
-	}{
-		{
-			name: "removed diagnostics",
-			yaml: "version: 4\ndiagnostics: {}\n",
-			want: "field diagnostics not found",
-		},
-		{
-			name: "removed llm profiles",
-			yaml: "version: 4\nllm_profiles: {}\n",
-			want: "field llm_profiles not found",
-		},
-		{
-			name: "removed scriptorium section",
-			yaml: "version: 4\nscriptorium: {}\n",
-			want: "field scriptorium not found",
-		},
-		{
-			name: "version 2 migration",
-			yaml: "version: 2\nworkspace:\n  directory: /tmp/old\n",
-			want: "version 2-to-3 migration",
-		},
-		{
-			name: "pipeline field",
-			yaml: "version: 4\npipelines:\n  main:\n    unknown: true\n",
-			want: "field unknown not found",
-		},
-		{
-			name: "lane field",
-			yaml: "version: 4\npipelines:\n  main:\n    artifacts:\n      spells:\n        unknown: true\n",
-			want: "field unknown not found",
-		},
-		{
-			name: "module binding field",
-			yaml: "version: 4\npipelines:\n  main:\n    input:\n      module: seriatim\n      unknown: true\n",
-			want: "field unknown not found in module binding",
-		},
-		{
-			name: "checkpoint field",
-			yaml: "version: 4\ncache:\n  checkpoints:\n    unknown: true\n",
-			want: "field unknown not found",
-		},
-		{
-			name: "checkpoint enabled type",
-			yaml: "version: 4\ncache:\n  checkpoints:\n    enabled: definitely\n",
-			want: "cannot unmarshal",
-		},
-		{
-			name: "local backend field",
-			yaml: "version: 4\npromptkit:\n  local_backend:\n    endpoint: http://localhost:8000/v1\n    unknown: true\n",
-			want: "field unknown not found",
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			_, err := ParseFileConfigYAML([]byte(tt.yaml))
-			if err == nil || !strings.Contains(err.Error(), tt.want) {
-				t.Fatalf("error = %v, want context %q", err, tt.want)
-			}
-		})
-	}
-}
-
-func TestFileConfigModuleBindingsPreserveFormsAndValidatorPresence(t *testing.T) {
-	cfg := applyFileConfig(t, `version: 4
-pipelines:
-  main:
-    input: seriatim
-    chunk:
-      module: generic
-      llm_profile: chunk-profile
-      retries: 2
-      options:
-        max_units: 25
-      references:
-        glossary: ./glossary.md
-      validators: []
-    artifacts:
-      spells:
-        extract:
-          module: dnd/spells
-          options:
-            nested:
-              enabled: true
-        merge: appendorder
-        normalize: noop
-`)
-	profile := cfg.Pipelines["main"]
-	if profile.Input.Module != "seriatim" || profile.Input.Validators.Set {
-		t.Fatalf("shorthand binding = %#v", profile.Input)
-	}
-	if profile.Chunk.Module != "generic" || profile.Chunk.LLMProfile != "chunk-profile" || profile.Chunk.Retries != 2 ||
-		!reflect.DeepEqual(profile.Chunk.Options, map[string]any{"max_units": 25}) ||
-		!reflect.DeepEqual(profile.Chunk.References, pipeline.ExternalReferenceMap(map[string]string{"glossary": "./glossary.md"})) {
-		t.Fatalf("object binding = %#v", profile.Chunk)
-	}
-	if !profile.Chunk.Validators.Set || len(profile.Chunk.Validators.Validators) != 0 {
-		t.Fatalf("explicit empty validators = %#v", profile.Chunk.Validators)
-	}
-	if profile.Artifacts["spells"].Extract.Module != "dnd/spells" ||
-		!reflect.DeepEqual(profile.Artifacts["spells"].Extract.Options, map[string]any{
-			"nested": map[string]any{"enabled": true},
-		}) {
-		t.Fatalf("extract binding = %#v", profile.Artifacts["spells"].Extract)
-	}
-	if profile.Artifacts["spells"].Merge.Module != "appendorder" || profile.Artifacts["spells"].Normalize.Module != "noop" {
-		t.Fatalf("stage shorthand bindings = %#v", profile.Artifacts["spells"])
-	}
-}
-
-func TestFileConfigReferencePrecedenceIsRetained(t *testing.T) {
-	cfg := applyFileConfig(t, `version: 4
-pipelines:
-  main:
-    input: seriatim
-    references:
-      pipeline-only: ./pipeline.txt
-      shared: ./pipeline-shared.txt
-    chunk:
-      module: generic
-      references:
-        chunk-only: ./chunk.txt
-    artifacts:
-      spells:
-        references:
-          lane-only: ./lane.txt
-          shared: ./lane-shared.txt
-          overridden: ./lane.txt
-        extract:
-          module: dnd/spells
-          references:
-            extract-only: ./extract.txt
-            overridden: ./extract-overridden.txt
-        merge:
-          module: appendorder
-          references:
-            merge-only: ./merge.txt
-        normalize:
-          module: noop
-          references:
-            normalize-only: ./normalize.txt
-`)
-	profile := cfg.Pipelines["main"]
-	if !reflect.DeepEqual(profile.References, pipeline.ExternalReferenceMap(map[string]string{
-		"pipeline-only": "./pipeline.txt",
-		"shared":        "./pipeline-shared.txt",
-	})) {
-		t.Fatalf("pipeline references = %#v", profile.References)
-	}
-	if !reflect.DeepEqual(profile.Chunk.References, pipeline.ExternalReferenceMap(map[string]string{"chunk-only": "./chunk.txt"})) {
-		t.Fatalf("chunk references = %#v", profile.Chunk.References)
-	}
-	lane := profile.Artifacts["spells"]
-	if !reflect.DeepEqual(lane.References, pipeline.ExternalReferenceMap(map[string]string{
-		"lane-only":  "./lane.txt",
-		"shared":     "./lane-shared.txt",
-		"overridden": "./lane.txt",
-	})) {
-		t.Fatalf("lane compatibility references = %#v", lane.References)
-	}
-	if !reflect.DeepEqual(lane.Extract.References, pipeline.ExternalReferenceMap(map[string]string{
-		"lane-only":    "./lane.txt",
-		"shared":       "./lane-shared.txt",
-		"overridden":   "./extract-overridden.txt",
-		"extract-only": "./extract.txt",
-	})) {
-		t.Fatalf("extract references = %#v", lane.Extract.References)
-	}
-	if !reflect.DeepEqual(lane.Merge.References, pipeline.ExternalReferenceMap(map[string]string{"merge-only": "./merge.txt"})) ||
-		!reflect.DeepEqual(lane.Normalize.References, pipeline.ExternalReferenceMap(map[string]string{"normalize-only": "./normalize.txt"})) {
-		t.Fatalf("merge/normalize references = %#v, %#v", lane.Merge.References, lane.Normalize.References)
-	}
-}
-
-func TestFileConfigStageLocalValidatorsPreserveOrderAndFields(t *testing.T) {
-	cfg := applyFileConfig(t, `version: 4
-pipelines:
-  main:
-    input: seriatim
-    chunk:
-      module: generic
-      validators:
-        - generic/always_accept
-        - module: generic/valid_json
-          llm_profile: validator-profile
-          options:
-            schema: compact
-    artifacts:
-      spells:
-        extract:
-          module: dnd/spells
-          validators:
-            - module: extract/dnd/spells/shape
-              options:
-                strict: true
-        merge:
-          module: appendorder
-          validators:
-            - generic/always_accept
-        normalize:
-          module: noop
-          validators:
-            - module: generic/valid_json
-              options:
-                mode: normalized
-`)
-	profile := cfg.Pipelines["main"]
-	chunkValidators := profile.Chunk.Validators.Validators
-	if !profile.Chunk.Validators.Set || len(chunkValidators) != 2 || chunkValidators[0].Module != "generic/always_accept" ||
-		chunkValidators[1].Module != "generic/valid_json" || chunkValidators[1].LLMProfile != "validator-profile" ||
-		!reflect.DeepEqual(chunkValidators[1].Options, map[string]any{"schema": "compact"}) {
-		t.Fatalf("chunk validators = %#v", profile.Chunk.Validators)
-	}
-	lane := profile.Artifacts["spells"]
-	if len(lane.Extract.Validators.Validators) != 1 || lane.Extract.Validators.Validators[0].Module != "extract/dnd/spells/shape" ||
-		!reflect.DeepEqual(lane.Extract.Validators.Validators[0].Options, map[string]any{"strict": true}) {
-		t.Fatalf("extract validators = %#v", lane.Extract.Validators)
-	}
-	if len(lane.Merge.Validators.Validators) != 1 || lane.Merge.Validators.Validators[0].Module != "generic/always_accept" {
-		t.Fatalf("merge validators = %#v", lane.Merge.Validators)
-	}
-	if len(lane.Normalize.Validators.Validators) != 1 || lane.Normalize.Validators.Validators[0].Module != "generic/valid_json" ||
-		!reflect.DeepEqual(lane.Normalize.Validators.Validators[0].Options, map[string]any{"mode": "normalized"}) {
-		t.Fatalf("normalize validators = %#v", lane.Normalize.Validators)
-	}
-}
-
-func TestFileConfigStateSectionsApplyIndependently(t *testing.T) {
-	cfg := applyFileConfig(t, `version: 4
-promptkit:
-  profile_dir: ./profiles
-concurrency:
-  total_llm: 7
-output:
-  directory: ./output
-cache:
-  chunk_plans:
-    directory: ./plans
-    mode: bypass
-  checkpoints:
-    enabled: true
-    directory: ./checkpoints
-debug:
-  directory: ./debug
-`)
-	if cfg.PromptKit.ProfileDir != "./profiles" || cfg.PromptKit.ProfileFile != "" {
-		t.Fatalf("promptkit = %#v", cfg.PromptKit)
-	}
-	if cfg.Concurrency.TotalLLM != 7 || cfg.Concurrency.StageWorkers["extract"] != 7 {
-		t.Fatalf("concurrency = %#v", cfg.Concurrency)
-	}
-	if cfg.Output.Directory != "./output" || cfg.Cache.ChunkPlans.Directory != "plans" || cfg.Cache.ChunkPlans.Mode != pipeline.ChunkCacheBypass ||
-		!cfg.Cache.Checkpoints.Enabled || cfg.Cache.Checkpoints.Directory != "checkpoints" || cfg.Debug.Directory != "./debug" {
-		t.Fatalf("state sections = %#v, %#v, %#v, %#v", cfg.Output, cfg.Cache, cfg.Debug, cfg.PromptKit)
-	}
-	if cfg.Output.Directory == cfg.Cache.ChunkPlans.Directory || cfg.Cache.ChunkPlans.Directory == cfg.Cache.Checkpoints.Directory || cfg.Cache.Checkpoints.Directory == cfg.Debug.Directory {
-		t.Fatal("state roots were coupled")
-	}
-}
-
-func TestFileConfigCheckpointEnabledCanBeExplicitlyDisabled(t *testing.T) {
-	cfg := applyFileConfig(t, "version: 4\ncache:\n  checkpoints:\n    enabled: true\n")
-	if !cfg.Cache.Checkpoints.Enabled || !cloneConfig(cfg).Cache.Checkpoints.Enabled {
-		t.Fatalf("enabled checkpoint config was not retained: %#v", cfg.Cache.Checkpoints)
-	}
-	file := parseFileConfig(t, "version: 4\ncache:\n  checkpoints:\n    enabled: false\n")
-	if err := cfg.ApplyFileConfig(file); err != nil {
-		t.Fatal(err)
-	}
-	if cfg.Cache.Checkpoints.Enabled {
-		t.Fatalf("explicit false checkpoint config was not applied: %#v", cfg.Cache.Checkpoints)
-	}
-}
-
-func TestFileConfigRejectsTrimmedKeyCollisions(t *testing.T) {
-	tests := []struct {
-		name string
-		yaml string
-		want string
-	}{
-		{
-			name: "pipeline ids",
-			yaml: "version: 4\npipelines:\n  main: {}\n  ' main ': {}\n",
-			want: "pipeline id \"main\" is duplicated after trimming",
-		},
-		{
-			name: "lane ids",
-			yaml: "version: 4\npipelines:\n  main:\n    artifacts:\n      spells: {}\n      ' spells ': {}\n",
-			want: "artifact lane id \"spells\" is duplicated after trimming",
-		},
-		{
-			name: "reference slots",
-			yaml: "version: 4\npipelines:\n  main:\n    references:\n      slot: ./one.txt\n      ' slot ': ./two.txt\n",
-			want: "reference slot \"slot\" is duplicated after trimming",
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			file := parseFileConfig(t, tt.yaml)
-			cfg := Default()
-			err := cfg.ApplyFileConfig(file)
-			if err == nil || !strings.Contains(err.Error(), tt.want) {
-				t.Fatalf("ApplyFileConfig() error = %v, want context %q", err, tt.want)
-			}
-		})
-	}
-}
-
-func TestFileConfigParsesOrderedStepsAndReferenceSources(t *testing.T) {
-	file := parseFileConfig(t, `version: 4
-pipelines:
-  session:
-    input: seriatim
-    steps:
-      - id: identify-npcs
-        artifacts:
-          npc_registry:
-            extract: dnd/npc-registry
-      - id: grounded-events
-        references:
-          npc_registry:
-            artifact:
-              step: identify-npcs
-              lane: npc_registry
-        artifacts:
-          spells:
-            extract: dnd/spells
-`)
-	cfg := Default()
-	if err := cfg.ApplyFileConfig(file); err != nil {
-		t.Fatal(err)
-	}
-	profile := cfg.Pipelines["session"]
-	if len(profile.Steps) != 2 || profile.Steps[0].ID != "identify-npcs" || profile.Steps[1].ID != "grounded-events" {
-		t.Fatalf("steps = %#v", profile.Steps)
-	}
-	source := profile.Steps[1].References["npc_registry"]
-	if source.Artifact == nil || source.Artifact.Step != "identify-npcs" || source.Artifact.Lane != "npc_registry" {
-		t.Fatalf("generated source = %#v", source)
-	}
-}
-
-func TestFileConfigRejectsAmbiguousReferenceSourceForms(t *testing.T) {
-	for _, source := range []string{
-		"artifact: {step: a, lane: b, extra: c}",
-		"artifact: {step: 1, lane: b}",
-		"1",
-	} {
-		_, err := ParseFileConfigYAML([]byte("version: 4\npipelines:\n  p:\n    input: text\n    references:\n      slot: " + source + "\n"))
-		if err == nil {
-			t.Fatalf("ParseFileConfigYAML(%q) error = nil", source)
-		}
-	}
-}
-
-func TestFileConfigRejectsEmptyAndAmbiguousPipelineShapes(t *testing.T) {
-	tests := []struct {
-		name string
-		yaml string
-		want string
-	}{
-		{
-			name: "empty steps",
-			yaml: "version: 4\npipelines:\n  p:\n    input: text\n    steps: []\n",
-			want: "at least one ordered step",
-		},
-		{
-			name: "both forms",
-			yaml: "version: 4\npipelines:\n  p:\n    input: text\n    artifacts: {}\n    steps: []\n",
-			want: "both artifacts and steps",
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			file := parseFileConfig(t, tt.yaml)
-			cfg := Default()
-			err := cfg.ApplyFileConfig(file)
-			if err == nil || !strings.Contains(err.Error(), tt.want) {
-				t.Fatalf("ApplyFileConfig() error = %v, want context %q", err, tt.want)
-			}
-		})
-	}
-}
-
-func TestLoadFileConfigReportsPathAndOperationContext(t *testing.T) {
-	dir := t.TempDir()
-	missing := filepath.Join(dir, "missing.yml")
-	_, err := LoadFileConfig(missing)
-	if err == nil || !strings.Contains(err.Error(), "read config file") || !strings.Contains(err.Error(), missing) {
-		t.Fatalf("missing-file error = %v", err)
-	}
-
-	malformed := filepath.Join(dir, "malformed.yml")
-	if err := os.WriteFile(malformed, []byte("version: [\n"), 0o600); err != nil {
-		t.Fatal(err)
-	}
-	_, err = LoadFileConfig(malformed)
-	if err == nil || !strings.Contains(err.Error(), "parse config file") || !strings.Contains(err.Error(), malformed) {
-		t.Fatalf("malformed-file error = %v", err)
-	}
-}
-
-func parseFileConfig(t *testing.T, source string) FileConfig {
-	t.Helper()
-	file, err := ParseFileConfigYAML([]byte(source))
-	if err != nil {
-		t.Fatalf("ParseFileConfigYAML() error = %v", err)
-	}
-	return file
-}
-
-func applyFileConfig(t *testing.T, source string) Config {
-	t.Helper()
-	cfg := Default()
-	if err := cfg.ApplyFileConfig(parseFileConfig(t, source)); err != nil {
-		t.Fatalf("ApplyFileConfig() error = %v", err)
-	}
-	return cfg
-}

internal/core/config/load.go

@@ -0,0 +1,101 @@
+package config
+
+import (
+	"path/filepath"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+)
+
+// LoadOptions contains configuration selections supplied by an application
+// boundary. It is intentionally narrow: configuration discovery and CLI flag
+// parsing remain outside this package.
+type LoadOptions struct {
+	Profile             string
+	Overrides           []configkit.Override
+	InvocationDirectory string
+}
+
+// loadDocument composes and validates a version 5 file with ConfigKit before
+// runtime conversion, retaining source provenance and frozen inspection output.
+func loadDocument(path string, options LoadOptions) (*configkit.Result[Document], error) {
+	return loadDocumentWithSource(configkit.File(path), options, true)
+}
+
+func loadDocumentSource(source configkit.Source, options LoadOptions) (*configkit.Result[Document], error) {
+	return loadDocumentWithSource(source, options, false)
+}
+
+func loadDocumentWithSource(source configkit.Source, options LoadOptions, imports bool) (*configkit.Result[Document], error) {
+	state := newDocumentLoadState(options.InvocationDirectory)
+	return configkit.Load(source, configkit.Options[Document]{
+		Definition: documentDefinition(state),
+		Imports:    imports,
+		Profile:    options.Profile,
+		Overrides:  options.Overrides,
+	})
+}
+
+func cleanInvocationDirectory(value string) string {
+	if value == "" {
+		return ""
+	}
+	absolute, err := filepath.Abs(value)
+	if err != nil {
+		return ""
+	}
+	return filepath.Clean(absolute)
+}
+
+func documentDefinition(state *documentLoadState) configkit.Definition[Document] {
+	return configkit.Definition[Document]{
+		Defaults: documentDefaults,
+		Resolve: func(document *Document, resolution *configkit.Resolution) error {
+			return resolveDocumentOperations(document, resolution, state)
+		},
+		Validate: validateDocumentOperations,
+		Version: &configkit.VersionRule{
+			Path:  configkit.Keys("version"),
+			Check: validateDocumentVersion,
+		},
+		Secret: sensitiveDocumentPath,
+	}
+}
+
+func documentDefaults() Document {
+	return Document{
+		Pipelines: map[string]PipelineDocument{},
+		Concurrency: &ConcurrencyDocument{
+			TotalLLM:     documentValue(defaultLLMConcurrency),
+			StageWorkers: map[string]int{},
+		},
+		Output: &OutputDocument{Directory: documentValue("./notarius-output")},
+		Cache: &CacheDocument{
+			ChunkPlans: &ChunkPlanCacheDocument{
+				Directory: documentValue(""),
+				Mode:      documentValue("auto"),
+			},
+			Checkpoints: &CheckpointCacheDocument{
+				Enabled:   documentValue(false),
+				Directory: documentValue(""),
+			},
+		},
+		Debug: &DebugDocument{Directory: documentValue("./notarius-debug")},
+	}
+}
+
+func documentValue[T any](value T) *T { return &value }
+
+func validateDocumentVersion(version configkit.Version, validation *configkit.Validation) error {
+	if !version.Present || version.Null {
+		validation.Error(configkit.Keys("version"), "configuration version is required")
+		return nil
+	}
+	if version.Text == "4" {
+		validation.Error(configkit.Keys("version"), "configuration version 4 is no longer supported; migrate to version 5")
+		return nil
+	}
+	if version.Text != "5" {
+		validation.Error(configkit.Keys("version"), "unsupported configuration version")
+	}
+	return nil
+}

internal/core/config/loaded_config.go

@@ -0,0 +1,323 @@
+package config
+
+import (
+	"fmt"
+	"io"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+)
+
+// LoadedConfig keeps the finalized runtime configuration together with the
+// private ConfigKit inspection snapshot that produced it.
+type LoadedConfig struct {
+	Config Config
+
+	result *configkit.Result[Document]
+}
+
+// RuntimeConfig returns an independently owned runtime configuration.
+func (loaded *LoadedConfig) RuntimeConfig() Config {
+	if loaded == nil {
+		return Config{}
+	}
+	return cloneConfig(loaded.Config)
+}
+
+// WriteEffective renders ConfigKit's frozen, redacted effective document.
+func (loaded *LoadedConfig) WriteEffective(output io.Writer) error {
+	if loaded == nil || loaded.result == nil {
+		return fmt.Errorf("loaded configuration is unavailable")
+	}
+	return loaded.result.WriteEffective(output)
+}
+
+// WriteExplanation renders ConfigKit's safe explanation for a JSON-pointer
+// path without exposing ConfigKit types at this package boundary.
+func (loaded *LoadedConfig) WriteExplanation(output io.Writer, pointer string) error {
+	if loaded == nil || loaded.result == nil {
+		return fmt.Errorf("loaded configuration is unavailable")
+	}
+	path, err := configkit.ParsePath(pointer)
+	if err != nil {
+		return fmt.Errorf("parse configuration explanation path: %w", err)
+	}
+	return loaded.result.WriteExplanation(output, path)
+}
+
+func loadConfig(path string, options LoadOptions) (*LoadedConfig, error) {
+	result, err := loadDocument(path, options)
+	if err != nil {
+		return nil, err
+	}
+	return newLoadedConfig(result)
+}
+
+// Load reads a version 5 configuration file into runtime configuration and a
+// private inspection snapshot.
+func Load(path string, options LoadOptions) (*LoadedConfig, error) {
+	return loadConfig(path, options)
+}
+
+func loadConfigSource(source configkit.Source, options LoadOptions) (*LoadedConfig, error) {
+	result, err := loadDocumentSource(source, options)
+	if err != nil {
+		return nil, err
+	}
+	return newLoadedConfig(result)
+}
+
+func newLoadedConfig(result *configkit.Result[Document]) (*LoadedConfig, error) {
+	if result == nil {
+		return nil, fmt.Errorf("configuration result is unavailable")
+	}
+	runtime, err := documentToConfig(result.Config)
+	if err != nil {
+		return nil, err
+	}
+	return &LoadedConfig{Config: runtime, result: result}, nil
+}
+
+func documentToConfig(document Document) (Config, error) {
+	config := Default()
+	config.Pipelines = documentPipelinesToRuntime(document.Pipelines)
+	if document.Concurrency != nil {
+		config.Concurrency.StageWorkers = documentIntMap(document.Concurrency.StageWorkers)
+		if document.Concurrency.TotalLLM != nil {
+			config.Concurrency.TotalLLM = *document.Concurrency.TotalLLM
+		}
+	}
+	if document.PromptKit != nil {
+		if document.PromptKit.ProfileDir != nil {
+			config.PromptKit.ProfileDir = *document.PromptKit.ProfileDir
+		}
+		if document.PromptKit.ProfileFile != nil {
+			config.PromptKit.ProfileFile = *document.PromptKit.ProfileFile
+		}
+		if document.PromptKit.LocalBackend != nil {
+			backend := PromptKitLocalBackendConfig{}
+			if document.PromptKit.LocalBackend.Endpoint != nil {
+				backend.Endpoint = *document.PromptKit.LocalBackend.Endpoint
+			}
+			if document.PromptKit.LocalBackend.ConcurrencyLimit != nil {
+				backend.ConcurrencyLimit = *document.PromptKit.LocalBackend.ConcurrencyLimit
+			}
+			config.PromptKit.LocalBackend = &backend
+		}
+	}
+	if document.Output != nil && document.Output.Directory != nil {
+		config.Output.Directory = *document.Output.Directory
+	}
+	if document.Cache != nil {
+		if document.Cache.ChunkPlans != nil {
+			if document.Cache.ChunkPlans.Directory != nil {
+				config.Cache.ChunkPlans.Directory = *document.Cache.ChunkPlans.Directory
+			}
+			if document.Cache.ChunkPlans.Mode != nil {
+				mode, err := pipeline.ParseChunkCacheMode(*document.Cache.ChunkPlans.Mode)
+				if err != nil {
+					return Config{}, fmt.Errorf("convert chunk-plan cache mode: %w", err)
+				}
+				config.Cache.ChunkPlans.Mode = mode
+			}
+		}
+		if document.Cache.Checkpoints != nil {
+			if document.Cache.Checkpoints.Enabled != nil {
+				config.Cache.Checkpoints.Enabled = *document.Cache.Checkpoints.Enabled
+			}
+			if document.Cache.Checkpoints.Directory != nil {
+				config.Cache.Checkpoints.Directory = *document.Cache.Checkpoints.Directory
+			}
+		}
+	}
+	if document.Debug != nil && document.Debug.Directory != nil {
+		config.Debug.Directory = *document.Debug.Directory
+	}
+	return config, nil
+}
+
+func documentPipelinesToRuntime(documents map[string]PipelineDocument) map[string]pipeline.PipelineProfile {
+	if documents == nil {
+		return nil
+	}
+	profiles := make(map[string]pipeline.PipelineProfile, len(documents))
+	for id, document := range documents {
+		profiles[id] = documentPipelineToRuntime(id, document)
+	}
+	return profiles
+}
+
+func documentPipelineToRuntime(id string, document PipelineDocument) pipeline.PipelineProfile {
+	profile := pipeline.PipelineProfile{
+		ID:                             id,
+		StructuredOutputRepairAttempts: cloneDocumentInt(document.StructuredOutputRepairAttempts),
+		ValidationPolicy:               documentPolicyToRuntime(document.ValidationPolicy),
+		Input:                          documentBindingToRuntime(document.Input),
+		Artifacts:                      documentLanesToRuntime(document.Artifacts),
+		References:                     documentReferencesToRuntime(document.References),
+	}
+	if document.LLMProfile != nil {
+		profile.LLMProfile = *document.LLMProfile
+	}
+	if document.Chunk != nil {
+		profile.Chunk = documentBindingToRuntime(*document.Chunk)
+	}
+	if document.Output != nil {
+		profile.Output = documentBindingToRuntime(*document.Output)
+	}
+	if document.Steps != nil {
+		profile.Steps = make([]pipeline.PipelineStepProfile, len(document.Steps))
+		for index, step := range document.Steps {
+			profile.Steps[index] = pipeline.PipelineStepProfile{
+				ID:         step.ID,
+				Artifacts:  documentLanesToRuntime(step.Artifacts),
+				References: documentReferencesToRuntime(step.References),
+			}
+		}
+	}
+	return profile
+}
+
+func documentLanesToRuntime(documents map[string]ArtifactLaneDocument) map[string]pipeline.ArtifactLaneProfile {
+	if documents == nil {
+		return nil
+	}
+	lanes := make(map[string]pipeline.ArtifactLaneProfile, len(documents))
+	for id, document := range documents {
+		lane := pipeline.ArtifactLaneProfile{
+			Extract:    documentBindingToRuntime(document.Extract),
+			References: documentReferencesToRuntime(document.References),
+		}
+		if document.Merge != nil {
+			lane.Merge = documentBindingToRuntime(*document.Merge)
+		}
+		if document.Normalize != nil {
+			lane.Normalize = documentBindingToRuntime(*document.Normalize)
+		}
+		if document.Validators != nil {
+			lane.Validators = make([]pipeline.ModuleBinding, len(document.Validators))
+			for index, validator := range document.Validators {
+				lane.Validators[index] = documentValidatorToRuntime(validator)
+			}
+		}
+		lanes[id] = lane
+	}
+	return lanes
+}
+
+func documentBindingToRuntime(document BindingDocument) pipeline.ModuleBinding {
+	binding := pipeline.ModuleBinding{
+		Module:                         document.Module,
+		StructuredOutputRepairAttempts: cloneDocumentInt(document.StructuredOutputRepairAttempts),
+		ValidationPolicy:               documentPolicyToRuntime(document.ValidationPolicy),
+		Retries:                        document.Retries,
+		Options:                        documentOptions(document.Options),
+		References:                     documentReferencesToRuntime(document.References),
+	}
+	if document.LLMProfile != nil {
+		binding.LLMProfile = *document.LLMProfile
+	}
+	if document.Validators != nil {
+		binding.Validators.Set = true
+		binding.Validators.Validators = make([]pipeline.ModuleBinding, len(document.Validators))
+		for index, validator := range document.Validators {
+			binding.Validators.Validators[index] = documentValidatorToRuntime(validator)
+		}
+	}
+	return binding
+}
+
+func documentValidatorToRuntime(document ValidatorDocument) pipeline.ModuleBinding {
+	binding := pipeline.ModuleBinding{
+		Module:                         document.Module,
+		StructuredOutputRepairAttempts: cloneDocumentInt(document.StructuredOutputRepairAttempts),
+		Retries:                        document.Retries,
+		Options:                        documentOptions(document.Options),
+	}
+	if document.LLMProfile != nil {
+		binding.LLMProfile = *document.LLMProfile
+	}
+	return binding
+}
+
+func documentReferencesToRuntime(documents map[string]ReferenceDocument) map[string]pipeline.ReferenceSource {
+	if documents == nil {
+		return nil
+	}
+	references := make(map[string]pipeline.ReferenceSource, len(documents))
+	for name, document := range documents {
+		if document.Artifact != nil {
+			references[name] = pipeline.GeneratedReference(document.Artifact.Step, document.Artifact.Lane)
+			continue
+		}
+		if document.Path != nil {
+			references[name] = pipeline.ExternalReference(*document.Path)
+		}
+	}
+	return references
+}
+
+func documentPolicyToRuntime(document *ValidationPolicyDocument) *pipeline.ValidationPolicyOverride {
+	if document == nil {
+		return nil
+	}
+	policy := pipeline.ValidationPolicyOverride{}
+	if document.ProducerStructuralFailure != nil {
+		value := *document.ProducerStructuralFailure
+		policy.ProducerStructuralFailure = &value
+	}
+	if document.SemanticRejection != nil {
+		value := *document.SemanticRejection
+		policy.SemanticRejection = &value
+	}
+	if document.ValidatorFailure != nil {
+		value := *document.ValidatorFailure
+		policy.ValidatorFailure = &value
+	}
+	return &policy
+}
+
+func documentIntMap(values map[string]int) map[string]int {
+	if values == nil {
+		return nil
+	}
+	result := make(map[string]int, len(values))
+	for key, value := range values {
+		result[key] = value
+	}
+	return result
+}
+
+func cloneDocumentInt(value *int) *int {
+	if value == nil {
+		return nil
+	}
+	result := *value
+	return &result
+}
+
+func documentOptions(values map[string]any) map[string]any {
+	if values == nil {
+		return nil
+	}
+	result := make(map[string]any, len(values))
+	for key, value := range values {
+		result[key] = cloneDocumentOption(value)
+	}
+	return result
+}
+
+func cloneDocumentOption(value any) any {
+	switch typed := value.(type) {
+	case map[string]any:
+		return documentOptions(typed)
+	case []any:
+		result := make([]any, len(typed))
+		for index, item := range typed {
+			result[index] = cloneDocumentOption(item)
+		}
+		return result
+	default:
+		return typed
+	}
+}

internal/core/config/loaded_config_test.go

@@ -0,0 +1,184 @@
+package config
+
+import (
+	"bytes"
+	"strings"
+	"testing"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	units "gitea.maximumdirect.net/eric/notarius/internal/modules/generic/chunk/units"
+	jsonoutput "gitea.maximumdirect.net/eric/notarius/internal/modules/generic/output/json"
+)
+
+func TestLoadedConfigConvertsDocumentsAndResolvesRuntimePipeline(t *testing.T) {
+	t.Parallel()
+
+	loaded, err := loadConfigSource(configkit.Bytes("document.yml", []byte(`version: 5
+pipelines:
+  session:
+    llm_profile: local
+    structured_output_repair_attempts: 0
+    input:
+      module: input
+    chunk:
+      module: generic
+      validators: []
+    artifacts:
+      score:
+        extract:
+          module: extract
+          validators:
+            - module: configured-a
+              options:
+                nested:
+                  level: 1
+`)), LoadOptions{})
+	if err != nil {
+		t.Fatalf("loadConfigSource() error = %v", err)
+	}
+	profile := loaded.Config.Pipelines["session"]
+	if profile.LLMProfile != "local" || profile.StructuredOutputRepairAttempts == nil || *profile.StructuredOutputRepairAttempts != 0 {
+		t.Fatalf("pipeline profile = %#v", profile)
+	}
+	if !profile.Chunk.Validators.Set || profile.Chunk.Validators.Validators == nil || len(profile.Chunk.Validators.Validators) != 0 {
+		t.Fatalf("empty validator chain was not preserved: %#v", profile.Chunk.Validators)
+	}
+	validator := profile.Artifacts["score"].Extract.Validators.Validators[0]
+	if validator.Module != "configured-a" || validator.Options["nested"].(map[string]any)["level"] == nil {
+		t.Fatalf("validator conversion = %#v", validator)
+	}
+
+	effective, err := loaded.Config.Resolve(ResolveInput{PipelineID: "session", Catalog: effectiveCatalog(t)})
+	if err != nil {
+		t.Fatalf("Resolve() error = %v", err)
+	}
+	if effective.ResolvedPipeline.ID != "session" || effective.ResolvedPipeline.Digest == "" {
+		t.Fatalf("resolved pipeline = %#v", effective.ResolvedPipeline)
+	}
+}
+
+func TestLoadedConfigOwnsRuntimeValuesAndKeepsFrozenInspection(t *testing.T) {
+	t.Parallel()
+
+	loaded, err := loadConfigSource(configkit.Bytes("document.yml", []byte(`version: 5
+pipelines:
+  session:
+    input: {module: input}
+    artifacts:
+      score:
+        extract:
+          module: extract
+          options:
+            nested: {value: original}
+`)), LoadOptions{})
+	if err != nil {
+		t.Fatalf("loadConfigSource() error = %v", err)
+	}
+
+	first := loaded.RuntimeConfig()
+	first.Pipelines["session"] = pipelineProfileWithChangedOption(first.Pipelines["session"])
+	second := loaded.RuntimeConfig()
+	if got := second.Pipelines["session"].Artifacts["score"].Extract.Options["nested"].(map[string]any)["value"]; got != "original" {
+		t.Fatalf("runtime configuration aliases caller mutation: %#v", got)
+	}
+
+	loaded.Config.Pipelines["session"] = pipelineProfileWithChangedOption(loaded.Config.Pipelines["session"])
+	var effective bytes.Buffer
+	if err := loaded.WriteEffective(&effective); err != nil {
+		t.Fatalf("WriteEffective() error = %v", err)
+	}
+	if !strings.Contains(effective.String(), "original") || strings.Contains(effective.String(), "changed") {
+		t.Fatalf("effective document changed with runtime mutation: %q", effective.String())
+	}
+}
+
+func TestLoadedConfigPreservesConfigKitIntegerOptionsForModules(t *testing.T) {
+	t.Parallel()
+
+	loaded, err := loadConfigSource(configkit.Bytes("document.yml", []byte(`version: 5
+pipelines:
+  session:
+    input: {module: input}
+    chunk:
+      module: generic
+      options:
+        max_units: 3
+        overlap_units: 1
+    output:
+      module: json
+      options:
+        evidence_context:
+          enabled: true
+          lanes: [score]
+          window_units: 2
+`)), LoadOptions{})
+	if err != nil {
+		t.Fatalf("loadConfigSource() error = %v", err)
+	}
+	profile := loaded.Config.Pipelines["session"]
+	chunkOptions, err := units.DecodeOptions(profile.Chunk.Options)
+	if err != nil || chunkOptions.MaxUnits != 3 || chunkOptions.OverlapUnits != 1 {
+		t.Fatalf("chunk options = %#v, %v", chunkOptions, err)
+	}
+	outputOptions, err := jsonoutput.DecodeOptions(profile.Output.Options)
+	if err != nil || !outputOptions.EvidenceContext.Enabled || outputOptions.EvidenceContext.WindowUnits != 2 {
+		t.Fatalf("output options = %#v, %v", outputOptions, err)
+	}
+}
+
+func TestLoadedConfigRedactsSensitiveNestedOptions(t *testing.T) {
+	t.Parallel()
+
+	loaded, err := loadConfigSource(configkit.Bytes("document.yml", []byte(`version: 5
+pipelines:
+  session:
+    input:
+      module: input
+      options:
+        nested:
+          api_key: input-secret
+    artifacts:
+      score:
+        extract:
+          module: extract
+          validators:
+            - module: configured-a
+              options:
+                credentials:
+                  token: validator-secret
+`)), LoadOptions{})
+	if err != nil {
+		t.Fatalf("loadConfigSource() error = %v", err)
+	}
+	var effective bytes.Buffer
+	if err := loaded.WriteEffective(&effective); err != nil {
+		t.Fatalf("WriteEffective() error = %v", err)
+	}
+	for _, secret := range []string{"input-secret", "validator-secret"} {
+		if strings.Contains(effective.String(), secret) {
+			t.Fatalf("effective configuration exposes %q: %q", secret, effective.String())
+		}
+	}
+	if !strings.Contains(effective.String(), "[REDACTED]") {
+		t.Fatalf("effective configuration did not mark sensitive values: %q", effective.String())
+	}
+
+	var explanation bytes.Buffer
+	if err := loaded.WriteExplanation(&explanation, "/pipelines/session/artifacts/score/extract/validators/0/options/credentials/token"); err != nil {
+		t.Fatalf("WriteExplanation() error = %v", err)
+	}
+	if strings.Contains(explanation.String(), "validator-secret") || !strings.Contains(explanation.String(), "[REDACTED]") {
+		t.Fatalf("explanation exposes sensitive value: %q", explanation.String())
+	}
+}
+
+func pipelineProfileWithChangedOption(profile pipeline.PipelineProfile) pipeline.PipelineProfile {
+	profile = clonePipelineProfile(profile)
+	nested := profile.Artifacts["score"].Extract.Options["nested"].(map[string]any)
+	nested["value"] = "changed"
+	lane := profile.Artifacts["score"]
+	lane.Extract.Options["nested"] = nested
+	profile.Artifacts["score"] = lane
+	return profile
+}

internal/core/config/operational_document.go

@@ -0,0 +1,305 @@
+package config
+
+import (
+	"fmt"
+	"net/url"
+	"sort"
+	"strings"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+)
+
+func resolveDocumentOperations(document *Document, resolution *configkit.Resolution, state *documentLoadState) error {
+	if document == nil {
+		return nil
+	}
+	normalizeDocumentPromptKit(document.PromptKit, resolution)
+	normalizeDocumentState(document, resolution)
+	normalizeDocumentPipelines(document, resolution, state)
+	normalizeDocumentPaths(document, resolution, state)
+	if document.Concurrency != nil {
+		document.Concurrency.StageWorkers = normalizeDocumentMap(document.Concurrency.StageWorkers,
+			configkit.Keys("concurrency", "stage_workers"), "stage worker identifier",
+			documentNormalizer{Resolution: resolution}, state)
+	}
+	deriveDocumentExtractWorkers(document, resolution, state)
+	return nil
+}
+
+func normalizeDocumentPromptKit(promptKit *PromptKitDocument, resolution *configkit.Resolution) {
+	if promptKit == nil {
+		return
+	}
+	profileDirPath := configkit.Keys("promptkit", "profile_dir")
+	profileFilePath := configkit.Keys("promptkit", "profile_file")
+	if promptKit.ProfileDir == nil && resolution.IsExplicit(profileDirPath) {
+		resolution.Error(profileDirPath, "must not be null")
+	}
+	if promptKit.ProfileFile == nil && resolution.IsExplicit(profileFilePath) {
+		resolution.Error(profileFilePath, "must not be null")
+	}
+	normalizeDocumentString(resolution, profileDirPath, &promptKit.ProfileDir, "trimmed PromptKit profile directory")
+	normalizeDocumentString(resolution, profileFilePath, &promptKit.ProfileFile, "trimmed PromptKit profile file")
+
+	if promptKit.LocalBackend == nil {
+		return
+	}
+	endpointPath := configkit.Keys("promptkit", "local_backend", "endpoint")
+	limitPath := configkit.Keys("promptkit", "local_backend", "concurrency_limit")
+	normalizeDocumentString(resolution, endpointPath, &promptKit.LocalBackend.Endpoint, "trimmed PromptKit local backend endpoint")
+	if promptKit.LocalBackend.ConcurrencyLimit == nil && !resolution.IsExplicit(limitPath) {
+		configkit.Default(resolution, limitPath, &promptKit.LocalBackend.ConcurrencyLimit,
+			documentValue(0), "defaulted PromptKit local backend concurrency limit")
+	}
+}
+
+func normalizeDocumentState(document *Document, resolution *configkit.Resolution) {
+	if document.Output != nil {
+		normalizeDocumentString(resolution, configkit.Keys("output", "directory"), &document.Output.Directory, "trimmed output directory")
+	}
+	if document.Cache != nil {
+		if document.Cache.ChunkPlans != nil {
+			normalizeDocumentString(resolution, configkit.Keys("cache", "chunk_plans", "directory"), &document.Cache.ChunkPlans.Directory, "trimmed chunk-plan cache directory")
+			normalizeDocumentString(resolution, configkit.Keys("cache", "chunk_plans", "mode"), &document.Cache.ChunkPlans.Mode, "trimmed chunk-plan cache mode")
+		}
+		if document.Cache.Checkpoints != nil {
+			normalizeDocumentString(resolution, configkit.Keys("cache", "checkpoints", "directory"), &document.Cache.Checkpoints.Directory, "trimmed checkpoint cache directory")
+		}
+	}
+	if document.Debug != nil {
+		normalizeDocumentString(resolution, configkit.Keys("debug", "directory"), &document.Debug.Directory, "trimmed debug directory")
+	}
+}
+
+func normalizeDocumentString(resolution *configkit.Resolution, path configkit.Path, target **string, reason string) {
+	if target == nil || *target == nil || !resolution.IsExplicit(path) {
+		return
+	}
+	configkit.Normalize(resolution, path, target, documentValue(strings.TrimSpace(**target)), reason)
+}
+
+func deriveDocumentExtractWorkers(document *Document, resolution *configkit.Resolution, state *documentLoadState) {
+	if document.Concurrency == nil || document.Concurrency.TotalLLM == nil {
+		return
+	}
+	if document.Concurrency.StageWorkers == nil {
+		document.Concurrency.StageWorkers = make(map[string]int)
+	}
+	path := configkit.Keys("concurrency", "stage_workers", "extract")
+	// Presence belongs to the input spelling, not the key produced by trimming.
+	// A moved explicit count must never be replaced by a derived default.
+	if resolution.IsExplicit(state.originalPath(path)) {
+		return
+	}
+	workers := document.Concurrency.StageWorkers
+	value := workers["extract"]
+	configkit.Default(resolution, path, &value, *document.Concurrency.TotalLLM,
+		"derived extraction workers from total LLM concurrency", configkit.Keys("concurrency", "total_llm"))
+	workers["extract"] = value
+}
+
+func validateDocumentOperations(document *Document, validation *configkit.Validation) {
+	if document == nil {
+		return
+	}
+	validateDocumentConcurrency(document.Concurrency, validation)
+	validateDocumentPromptKit(document.PromptKit, validation)
+	validateDocumentState(document, validation)
+	validateDocumentPipelines(document, validation)
+}
+
+func validateDocumentConcurrency(concurrency *ConcurrencyDocument, validation *configkit.Validation) {
+	if concurrency == nil {
+		validation.Error(configkit.Keys("concurrency"), "must not be null")
+		return
+	}
+	totalPath := configkit.Keys("concurrency", "total_llm")
+	if concurrency.TotalLLM == nil {
+		validation.Error(totalPath, "must not be null")
+		return
+	}
+	totalValid := true
+	if err := validateTotalLLMConcurrency(*concurrency.TotalLLM); err != nil {
+		validation.Error(totalPath, err.Error())
+		totalValid = false
+	}
+	keys := make([]string, 0, len(concurrency.StageWorkers))
+	for key := range concurrency.StageWorkers {
+		keys = append(keys, key)
+	}
+	sort.Strings(keys)
+	for _, key := range keys {
+		if err := validateStageWorkerKey(key); err != nil {
+			validation.Error(configkit.Keys("concurrency", "stage_workers").Key(key), err.Error())
+		}
+	}
+	if !totalValid {
+		return
+	}
+	if workers, ok := concurrency.StageWorkers["extract"]; ok {
+		if err := validateExtractWorkerCount(workers, *concurrency.TotalLLM); err != nil {
+			validation.Error(configkit.Keys("concurrency", "stage_workers", "extract"), err.Error())
+		}
+	}
+}
+
+func validateDocumentPromptKit(promptKit *PromptKitDocument, validation *configkit.Validation) {
+	if promptKit == nil {
+		return
+	}
+	profileDirPath := configkit.Keys("promptkit", "profile_dir")
+	profileFilePath := configkit.Keys("promptkit", "profile_file")
+	profileDir := ""
+	if promptKit.ProfileDir != nil {
+		profileDir = *promptKit.ProfileDir
+		if strings.TrimSpace(profileDir) == "" {
+			validation.Error(profileDirPath, "must not be empty when set")
+		}
+	}
+	profileFile := ""
+	if promptKit.ProfileFile != nil {
+		profileFile = *promptKit.ProfileFile
+		if strings.TrimSpace(profileFile) == "" {
+			validation.Error(profileFilePath, "must not be empty when set")
+		}
+	}
+	if err := validatePromptKitProfileSources(profileDir, profileFile); err != nil {
+		validation.Error(configkit.Keys("promptkit"), err.Error())
+	}
+	if promptKit.LocalBackend == nil {
+		return
+	}
+	endpointPath := configkit.Keys("promptkit", "local_backend", "endpoint")
+	limitPath := configkit.Keys("promptkit", "local_backend", "concurrency_limit")
+	if promptKit.LocalBackend.Endpoint == nil {
+		validation.Error(endpointPath, "must be nonempty when local backend is configured")
+	}
+	if promptKit.LocalBackend.ConcurrencyLimit == nil {
+		validation.Error(limitPath, "must be an integer when local backend is configured")
+	}
+	if promptKit.LocalBackend.Endpoint != nil {
+		if err := validatePromptKitLocalBackendEndpoint(*promptKit.LocalBackend.Endpoint); err != nil {
+			validation.Error(endpointPath, err.Error())
+		}
+	}
+	if promptKit.LocalBackend.ConcurrencyLimit != nil {
+		if err := validatePromptKitLocalBackendConcurrencyLimit(*promptKit.LocalBackend.ConcurrencyLimit); err != nil {
+			validation.Error(limitPath, err.Error())
+		}
+	}
+}
+
+func validateDocumentState(document *Document, validation *configkit.Validation) {
+	if document.Output == nil || document.Output.Directory == nil {
+		validation.Error(configkit.Keys("output", "directory"), "must not be empty")
+	} else if err := validateRequiredPath("output.directory", *document.Output.Directory); err != nil {
+		validation.Error(configkit.Keys("output", "directory"), err.Error())
+	}
+
+	if document.Cache == nil || document.Cache.ChunkPlans == nil || document.Cache.ChunkPlans.Mode == nil {
+		validation.Error(configkit.Keys("cache", "chunk_plans", "mode"), "must be a supported cache mode")
+	} else if err := validateChunkPlanCacheMode(*document.Cache.ChunkPlans.Mode); err != nil {
+		validation.Error(configkit.Keys("cache", "chunk_plans", "mode"), err.Error())
+	}
+	if document.Cache != nil && document.Cache.ChunkPlans != nil && document.Cache.ChunkPlans.Directory != nil {
+		if err := validateOptionalPath("cache.chunk_plans.directory", *document.Cache.ChunkPlans.Directory); err != nil {
+			validation.Error(configkit.Keys("cache", "chunk_plans", "directory"), err.Error())
+		}
+	}
+	if document.Cache != nil && document.Cache.Checkpoints != nil && document.Cache.Checkpoints.Directory != nil {
+		if err := validateOptionalPath("cache.checkpoints.directory", *document.Cache.Checkpoints.Directory); err != nil {
+			validation.Error(configkit.Keys("cache", "checkpoints", "directory"), err.Error())
+		}
+	}
+
+	if document.Debug == nil || document.Debug.Directory == nil {
+		validation.Error(configkit.Keys("debug", "directory"), "must not be empty")
+	} else if err := validateRequiredPath("debug.directory", *document.Debug.Directory); err != nil {
+		validation.Error(configkit.Keys("debug", "directory"), err.Error())
+	}
+}
+
+func validateTotalLLMConcurrency(total int) error {
+	if total <= 0 {
+		return fmt.Errorf("total LLM concurrency must be greater than zero")
+	}
+	return nil
+}
+
+func validateStageWorkerKey(key string) error {
+	if strings.TrimSpace(key) == "" {
+		return fmt.Errorf("concurrency.stage_workers key must not be empty")
+	}
+	if key != "extract" {
+		return fmt.Errorf("concurrency.stage_workers key %q is not supported", key)
+	}
+	return nil
+}
+
+func validateExtractWorkerCount(workers, total int) error {
+	if workers < 1 || workers > total {
+		return fmt.Errorf("concurrency.stage_workers.extract must be between 1 and concurrency.total_llm (%d)", total)
+	}
+	return nil
+}
+
+func validatePromptKitProfileSources(profileDir, profileFile string) error {
+	if strings.TrimSpace(profileDir) != "" && strings.TrimSpace(profileFile) != "" {
+		return fmt.Errorf("promptkit profile_dir and profile_file are mutually exclusive")
+	}
+	return nil
+}
+
+func validatePromptKitLocalBackend(endpoint string, concurrencyLimit int) error {
+	if err := validatePromptKitLocalBackendEndpoint(endpoint); err != nil {
+		return err
+	}
+	return validatePromptKitLocalBackendConcurrencyLimit(concurrencyLimit)
+}
+
+func validatePromptKitLocalBackendEndpoint(endpoint string) error {
+	if strings.TrimSpace(endpoint) == "" {
+		return fmt.Errorf("promptkit.local_backend.endpoint must not be empty when set")
+	}
+	parsed, err := url.Parse(strings.TrimSpace(endpoint))
+	if err != nil ||
+		(!strings.EqualFold(parsed.Scheme, "http") && !strings.EqualFold(parsed.Scheme, "https")) ||
+		!parsed.IsAbs() ||
+		parsed.Hostname() == "" ||
+		parsed.User != nil ||
+		parsed.RawQuery != "" ||
+		parsed.ForceQuery ||
+		strings.Contains(endpoint, "#") {
+		return fmt.Errorf("promptkit.local_backend.endpoint must be an absolute HTTP or HTTPS URL with a host and no user information, query, or fragment")
+	}
+	return nil
+}
+
+func validatePromptKitLocalBackendConcurrencyLimit(concurrencyLimit int) error {
+	if concurrencyLimit < 0 {
+		return fmt.Errorf("promptkit.local_backend.concurrency_limit must not be negative")
+	}
+	return nil
+}
+
+func validateRequiredPath(name, value string) error {
+	if strings.TrimSpace(value) == "" {
+		return fmt.Errorf("%s must not be empty", name)
+	}
+	return validateOptionalPath(name, value)
+}
+
+func validateOptionalPath(name, value string) error {
+	if strings.ContainsRune(value, '\x00') {
+		return fmt.Errorf("%s must not contain NUL", name)
+	}
+	return nil
+}
+
+func validateChunkPlanCacheMode(value string) error {
+	if _, err := pipeline.ParseChunkCacheMode(value); err != nil {
+		return fmt.Errorf("cache.chunk_plans.mode: %w", err)
+	}
+	return nil
+}

internal/core/config/operational_document_test.go

@@ -0,0 +1,228 @@
+package config
+
+import (
+	"bytes"
+	"errors"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+)
+
+func TestWorkerKeyNormalizationPreservesExplicitCount(t *testing.T) {
+	t.Parallel()
+	for _, test := range []struct {
+		name, workers string
+		want          int
+		errorPath     string
+	}{
+		{name: "omitted", workers: "{}", want: 4},
+		{name: "padded", workers: "{' extract ': 2}", want: 2},
+		{name: "explicit invalid", workers: "{' extract ': 0}", errorPath: "/concurrency/stage_workers/extract"},
+		{name: "collision", workers: "{' extract ': 2, extract: 3}", errorPath: "/concurrency/stage_workers/extract"},
+	} {
+		t.Run(test.name, func(t *testing.T) {
+			loaded, err := loadConfigSource(configkit.Bytes("workers.yml", []byte(
+				"version: 5\nconcurrency:\n  total_llm: 4\n  stage_workers: "+test.workers+"\n")), LoadOptions{})
+			if test.errorPath != "" {
+				assertDocumentDiagnosticAt(t, err, test.errorPath)
+				return
+			}
+			if err != nil {
+				t.Fatal(err)
+			}
+			if got := loaded.Config.Concurrency.StageWorkers["extract"]; got != test.want {
+				t.Fatalf("workers = %d, want %d", got, test.want)
+			}
+			var explanation bytes.Buffer
+			if err := loaded.WriteExplanation(&explanation, "/concurrency/stage_workers"); err != nil {
+				t.Fatal(err)
+			}
+			if test.name == "padded" && (!strings.Contains(explanation.String(), "normalization") ||
+				!strings.Contains(explanation.String(), " extract ") ||
+				strings.Contains(explanation.String(), "derived extraction workers")) {
+				t.Fatalf("explicit worker provenance = %s", explanation.String())
+			}
+		})
+	}
+}
+
+func TestDocumentLoadAppliesOperationalDefaultsAndNormalization(t *testing.T) {
+	t.Parallel()
+
+	loaded, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(`version: 5
+concurrency:
+  total_llm: 4
+promptkit:
+  profile_dir: " ./profiles "
+  local_backend:
+    endpoint: " https://localhost:8080/v1 "
+output:
+  directory: " ./output "
+cache:
+  chunk_plans:
+    mode: " refresh "
+    directory: " "
+  checkpoints:
+    directory: " "
+debug:
+  directory: " ./debug "
+`)), LoadOptions{})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if loaded.Config.Concurrency.TotalLLM == nil || *loaded.Config.Concurrency.TotalLLM != 4 || loaded.Config.Concurrency.StageWorkers["extract"] != 4 {
+		t.Fatalf("concurrency = %#v", loaded.Config.Concurrency)
+	}
+	workingDirectory, err := os.Getwd()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if loaded.Config.PromptKit.ProfileDir == nil || *loaded.Config.PromptKit.ProfileDir != filepath.Join(workingDirectory, "profiles") ||
+		loaded.Config.PromptKit.LocalBackend == nil || loaded.Config.PromptKit.LocalBackend.Endpoint == nil || *loaded.Config.PromptKit.LocalBackend.Endpoint != "https://localhost:8080/v1" ||
+		loaded.Config.PromptKit.LocalBackend.ConcurrencyLimit == nil || *loaded.Config.PromptKit.LocalBackend.ConcurrencyLimit != 0 {
+		t.Fatalf("promptkit = %#v", loaded.Config.PromptKit)
+	}
+	if loaded.Config.Output.Directory == nil || *loaded.Config.Output.Directory != filepath.Join(workingDirectory, "output") ||
+		loaded.Config.Cache.ChunkPlans.Mode == nil || *loaded.Config.Cache.ChunkPlans.Mode != "refresh" ||
+		loaded.Config.Cache.ChunkPlans.Directory == nil || *loaded.Config.Cache.ChunkPlans.Directory != "" ||
+		loaded.Config.Cache.Checkpoints.Directory == nil || *loaded.Config.Cache.Checkpoints.Directory != "" ||
+		loaded.Config.Debug.Directory == nil || *loaded.Config.Debug.Directory != filepath.Join(workingDirectory, "debug") {
+		t.Fatalf("state = %#v, %#v, %#v", loaded.Config.Output, loaded.Config.Cache, loaded.Config.Debug)
+	}
+	if diagnostics := loaded.Diagnostics(); len(diagnostics) != 0 {
+		t.Fatalf("diagnostics = %#v", diagnostics)
+	}
+	extractHistory := loaded.Metadata().History(configkit.Keys("concurrency", "stage_workers", "extract"))
+	if len(extractHistory) == 0 || extractHistory[len(extractHistory)-1].Origin.Operation != configkit.ChangeDerivedDefault {
+		t.Fatalf("extract history = %#v", extractHistory)
+	}
+	outputHistory := loaded.Metadata().History(configkit.Keys("output", "directory"))
+	if len(outputHistory) == 0 || outputHistory[len(outputHistory)-1].Origin.Operation != configkit.ChangeNormalization {
+		t.Fatalf("output history = %#v", outputHistory)
+	}
+}
+
+func TestDocumentLoadDerivesWorkersAfterProfileAndCLIOverrides(t *testing.T) {
+	t.Parallel()
+
+	directory := t.TempDir()
+	main := filepath.Join(directory, "config.yml")
+	profiles := filepath.Join(directory, "profiles")
+	if err := os.Mkdir(profiles, 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(main, []byte("version: 5\nconcurrency:\n  total_llm: 4\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(profiles, "development.yml"), []byte("concurrency:\n  total_llm: 3\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+
+	profiled, err := loadDocument(main, LoadOptions{Profile: "development"})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if profiled.Config.Concurrency.TotalLLM == nil || *profiled.Config.Concurrency.TotalLLM != 3 || profiled.Config.Concurrency.StageWorkers["extract"] != 3 {
+		t.Fatalf("profiled concurrency = %#v", profiled.Config.Concurrency)
+	}
+
+	overridden, err := loadDocument(main, LoadOptions{Overrides: []configkit.Override{{
+		Path: configkit.Keys("concurrency", "total_llm"), Value: 2, Flag: "--total-llm",
+	}}})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if overridden.Config.Concurrency.TotalLLM == nil || *overridden.Config.Concurrency.TotalLLM != 2 || overridden.Config.Concurrency.StageWorkers["extract"] != 2 {
+		t.Fatalf("overridden concurrency = %#v", overridden.Config.Concurrency)
+	}
+}
+
+func TestDocumentLoadRetainsExplicitWorkerAndRejectsInvalidOperationalValues(t *testing.T) {
+	t.Parallel()
+
+	loaded, err := loadDocumentSource(configkit.Bytes("explicit.yml", []byte(`version: 5
+concurrency:
+  total_llm: 4
+  stage_workers:
+    extract: 0
+`)), LoadOptions{})
+	if loaded != nil {
+		t.Fatalf("loaded = %#v, want validation failure", loaded.Config)
+	}
+	assertDocumentDiagnostic(t, err, configkit.CodeValidateError, "/concurrency/stage_workers/extract")
+
+	_, err = loadDocumentSource(configkit.Bytes("invalid.yml", []byte(`version: 5
+concurrency:
+  total_llm: 0
+output:
+  directory: ""
+promptkit:
+  local_backend:
+    endpoint: "ftp://localhost"
+    concurrency_limit: -1
+`)), LoadOptions{})
+	var loadError *configkit.LoadError
+	if !errors.As(err, &loadError) {
+		t.Fatalf("error = %v, want ConfigKit load error", err)
+	}
+	seen := make(map[string]bool)
+	for _, diagnostic := range loadError.Diagnostics() {
+		if diagnostic.Code != configkit.CodeValidateError || diagnostic.Primary == nil {
+			t.Fatalf("diagnostic = %#v", diagnostic)
+		}
+		seen[diagnostic.Path.String()] = true
+	}
+	for _, path := range []string{"/concurrency/total_llm", "/output/directory", "/promptkit/local_backend/endpoint", "/promptkit/local_backend/concurrency_limit"} {
+		if !seen[path] {
+			t.Fatalf("diagnostics missing %s: %#v", path, loadError.Diagnostics())
+		}
+	}
+}
+
+func TestDocumentLoadDistinguishesRequiredAndOptionalPathValues(t *testing.T) {
+	t.Parallel()
+
+	loaded, err := loadDocumentSource(configkit.Bytes("cache.yml", []byte(`version: 5
+cache:
+  chunk_plans:
+    directory: " "
+  checkpoints:
+    directory: " "
+`)), LoadOptions{})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if loaded.Config.Cache.ChunkPlans.Directory == nil || *loaded.Config.Cache.ChunkPlans.Directory != "" ||
+		loaded.Config.Cache.Checkpoints.Directory == nil || *loaded.Config.Cache.Checkpoints.Directory != "" {
+		t.Fatalf("cache directories = %#v", loaded.Config.Cache)
+	}
+
+	_, err = loadDocumentSource(configkit.Bytes("output.yml", []byte("version: 5\noutput:\n  directory: ' '\n")), LoadOptions{})
+	assertDocumentDiagnostic(t, err, configkit.CodeValidateError, "/output/directory")
+
+	_, err = loadDocumentSource(configkit.Bytes("promptkit.yml", []byte("version: 5\npromptkit:\n  profile_file: null\n  local_backend: {}\n")), LoadOptions{})
+	assertDocumentDiagnostic(t, err, configkit.CodeResolveError, "/promptkit/profile_file")
+
+	_, err = loadDocumentSource(configkit.Bytes("empty-source.yml", []byte("version: 5\npromptkit:\n  profile_dir: ' '\n")), LoadOptions{})
+	assertDocumentDiagnostic(t, err, configkit.CodeValidateError, "/promptkit/profile_dir")
+
+	_, err = loadDocumentSource(configkit.Bytes("missing-endpoint.yml", []byte("version: 5\npromptkit:\n  local_backend: {}\n")), LoadOptions{})
+	assertDocumentDiagnostic(t, err, configkit.CodeValidateError, "/promptkit/local_backend/endpoint")
+}
+
+func assertDocumentDiagnostic(t *testing.T, err error, code configkit.Code, path string) {
+	t.Helper()
+	var loadError *configkit.LoadError
+	if !errors.As(err, &loadError) {
+		t.Fatalf("error = %v, want ConfigKit load error", err)
+	}
+	for _, diagnostic := range loadError.Diagnostics() {
+		if diagnostic.Code == code && diagnostic.Path.String() == path {
+			return
+		}
+	}
+	t.Fatalf("diagnostics = %#v, want %s at %s", loadError.Diagnostics(), code, path)
+}

internal/core/config/pipeline_document.go

@@ -0,0 +1,513 @@
+package config
+
+import (
+	"sort"
+	"strings"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+)
+
+// documentLoadState keeps the spelling supplied by the user while resolver
+// operations move map entries to their canonical keys. It is intentionally
+// load-local: source-location handling consumes it during a later resolver
+// pass and it never becomes runtime configuration state.
+type documentLoadState struct {
+	originalPaths       map[string]configkit.Path
+	mainDirectory       string
+	invocationDirectory string
+}
+
+func newDocumentLoadState(invocationDirectory string) *documentLoadState {
+	return &documentLoadState{originalPaths: make(map[string]configkit.Path), invocationDirectory: cleanInvocationDirectory(invocationDirectory)}
+}
+
+func (state *documentLoadState) rememberPath(normalized, original configkit.Path) {
+	if state != nil {
+		state.originalPaths[normalized.String()] = original
+	}
+}
+
+// originalPath follows recorded map-key moves back to the spelling present in
+// the source. Resolver code that needs a source coordinate must use this
+// rather than reconstructing a path from a normalized identifier.
+func (state *documentLoadState) originalPath(path configkit.Path) configkit.Path {
+	if state == nil || len(state.originalPaths) == 0 {
+		return path
+	}
+	value := path.String()
+	for {
+		changed := false
+		segments := strings.Split(strings.TrimPrefix(value, "/"), "/")
+		for length := 1; length <= len(segments); length++ {
+			prefix := "/" + strings.Join(segments[:length], "/")
+			original, ok := state.originalPaths[prefix]
+			if !ok {
+				continue
+			}
+			value = original.String() + strings.TrimPrefix(value, prefix)
+			changed = true
+			break
+		}
+		if !changed {
+			break
+		}
+	}
+	if original, err := configkit.ParsePath(value); err == nil {
+		return original
+	}
+	return path
+}
+
+func normalizeDocumentPipelines(document *Document, resolution *configkit.Resolution, state *documentLoadState) {
+	if document == nil {
+		return
+	}
+	validateDocumentPipelinePresence(document, resolution)
+	normalizer := documentNormalizer{Resolution: resolution}
+
+	pipelinesPath := configkit.Keys("pipelines")
+	for _, id := range sortedPipelineDocumentKeys(document.Pipelines) {
+		profile := document.Pipelines[id]
+		normalizePipelineDocument(&profile, pipelinesPath.Key(id), normalizer, state)
+		document.Pipelines[id] = profile
+	}
+	document.Pipelines = normalizeDocumentMap(document.Pipelines, pipelinesPath, "pipeline identifier", normalizer, state)
+}
+
+func validateDocumentPipelinePresence(document *Document, resolution *configkit.Resolution) {
+	pipelinesPath := configkit.Keys("pipelines")
+	for _, id := range sortedPipelineDocumentKeys(document.Pipelines) {
+		profile := document.Pipelines[id]
+		path := pipelinesPath.Key(id)
+		validatePipelineDocumentPresence(profile, path, resolution)
+	}
+}
+
+func validatePipelineDocumentPresence(profile PipelineDocument, path configkit.Path, resolution *configkit.Resolution) {
+	rejectDocumentNull(resolution, path.Key("llm_profile"), profile.LLMProfile == nil)
+	rejectDocumentNull(resolution, path.Key("structured_output_repair_attempts"), profile.StructuredOutputRepairAttempts == nil)
+	rejectDocumentNull(resolution, path.Key("validation_policy"), profile.ValidationPolicy == nil)
+	validateDocumentPolicyPresence(profile.ValidationPolicy, path.Key("validation_policy"), resolution)
+
+	stepsPath := path.Key("steps")
+	if resolution.IsExplicit(stepsPath) && profile.Steps == nil {
+		resolution.Error(stepsPath, "must not be null")
+	}
+	if resolution.IsExplicit(stepsPath) && len(profile.Steps) == 0 {
+		resolution.Error(stepsPath, "must contain at least one ordered step")
+	}
+	if resolution.IsExplicit(stepsPath) && resolution.IsExplicit(path.Key("artifacts")) {
+		resolution.Error(stepsPath, "must not be declared with artifacts", path.Key("artifacts"))
+	}
+
+	validateBindingDocumentPresence(profile.Input, path.Key("input"), resolution)
+	validateOptionalBindingDocumentPresence(profile.Chunk, path.Key("chunk"), resolution)
+	validateOptionalBindingDocumentPresence(profile.Output, path.Key("output"), resolution)
+	validateReferenceDocumentMapPresence(profile.References, path.Key("references"), resolution)
+	for _, laneID := range sortedLaneDocumentKeys(profile.Artifacts) {
+		validateArtifactLaneDocumentPresence(profile.Artifacts[laneID], path.Key("artifacts").Key(laneID), resolution)
+	}
+	for index, step := range profile.Steps {
+		stepPath := stepsPath.Index(index)
+		validateReferenceDocumentMapPresence(step.References, stepPath.Key("references"), resolution)
+		for _, laneID := range sortedLaneDocumentKeys(step.Artifacts) {
+			validateArtifactLaneDocumentPresence(step.Artifacts[laneID], stepPath.Key("artifacts").Key(laneID), resolution)
+		}
+	}
+}
+
+func validateArtifactLaneDocumentPresence(lane ArtifactLaneDocument, path configkit.Path, resolution *configkit.Resolution) {
+	if resolution.IsExplicit(path.Key("references")) {
+		resolution.Error(path.Key("references"), "artifact-lane references are not supported; use binding references")
+	}
+	validateBindingDocumentPresence(lane.Extract, path.Key("extract"), resolution)
+	validateOptionalBindingDocumentPresence(lane.Merge, path.Key("merge"), resolution)
+	validateOptionalBindingDocumentPresence(lane.Normalize, path.Key("normalize"), resolution)
+}
+
+func validateOptionalBindingDocumentPresence(binding *BindingDocument, path configkit.Path, resolution *configkit.Resolution) {
+	if binding == nil {
+		if resolution.IsExplicit(path) {
+			resolution.Error(path, "must not be null when configured")
+		}
+		return
+	}
+	validateBindingDocumentPresence(*binding, path, resolution)
+}
+
+func validateBindingDocumentPresence(binding BindingDocument, path configkit.Path, resolution *configkit.Resolution) {
+	rejectDocumentNull(resolution, path.Key("llm_profile"), binding.LLMProfile == nil)
+	rejectDocumentNull(resolution, path.Key("structured_output_repair_attempts"), binding.StructuredOutputRepairAttempts == nil)
+	rejectDocumentNull(resolution, path.Key("validation_policy"), binding.ValidationPolicy == nil)
+	validateDocumentPolicyPresence(binding.ValidationPolicy, path.Key("validation_policy"), resolution)
+	if binding.Validators == nil && resolution.IsExplicit(path.Key("validators")) {
+		resolution.Error(path.Key("validators"), "must not be null")
+	}
+	validateReferenceDocumentMapPresence(binding.References, path.Key("references"), resolution)
+	for index, validator := range binding.Validators {
+		validatorPath := path.Key("validators").Index(index)
+		rejectDocumentNull(resolution, validatorPath.Key("llm_profile"), validator.LLMProfile == nil)
+		rejectDocumentNull(resolution, validatorPath.Key("structured_output_repair_attempts"), validator.StructuredOutputRepairAttempts == nil)
+	}
+}
+
+func validateReferenceDocumentMapPresence(references map[string]ReferenceDocument, path configkit.Path, resolution *configkit.Resolution) {
+	for _, name := range sortedReferenceDocumentKeys(references) {
+		source := references[name]
+		sourcePath := path.Key(name)
+		rejectDocumentNull(resolution, sourcePath.Key("path"), source.Path == nil)
+		rejectDocumentNull(resolution, sourcePath.Key("artifact"), source.Artifact == nil)
+	}
+}
+
+func rejectDocumentNull(resolution *configkit.Resolution, path configkit.Path, isNil bool) {
+	if isNil && resolution.IsExplicit(path) {
+		resolution.Error(path, "must not be null")
+	}
+}
+
+func validateDocumentPolicyPresence(policy *ValidationPolicyDocument, path configkit.Path, resolution *configkit.Resolution) {
+	if policy == nil {
+		return
+	}
+	rejectDocumentNull(resolution, path.Key("producer_structural_failure"), policy.ProducerStructuralFailure == nil)
+	rejectDocumentNull(resolution, path.Key("semantic_rejection"), policy.SemanticRejection == nil)
+	rejectDocumentNull(resolution, path.Key("validator_failure"), policy.ValidatorFailure == nil)
+}
+
+func normalizePipelineDocument(profile *PipelineDocument, path configkit.Path, resolution documentNormalizer, state *documentLoadState) {
+	normalizePipelineDocumentString(resolution, path.Key("llm_profile"), &profile.LLMProfile, "trimmed pipeline LLM profile")
+	normalizeDocumentBinding(&profile.Input, path.Key("input"), resolution, state)
+	if profile.Chunk != nil {
+		normalizeDocumentBinding(profile.Chunk, path.Key("chunk"), resolution, state)
+	}
+	if profile.Output != nil {
+		normalizeDocumentBinding(profile.Output, path.Key("output"), resolution, state)
+	}
+	profile.References = normalizeDocumentReferences(profile.References, path.Key("references"), resolution, state)
+	for _, laneID := range sortedLaneDocumentKeys(profile.Artifacts) {
+		lane := profile.Artifacts[laneID]
+		normalizeArtifactLaneDocument(&lane, path.Key("artifacts").Key(laneID), resolution, state)
+		profile.Artifacts[laneID] = lane
+	}
+	profile.Artifacts = normalizeDocumentMap(profile.Artifacts, path.Key("artifacts"), "artifact lane identifier", resolution, state)
+	resolution = resolution.inSequence(path.Key("steps"))
+	for index := range profile.Steps {
+		step := &profile.Steps[index]
+		stepPath := path.Key("steps").Index(index)
+		normalizeDocumentValue(resolution, stepPath.Key("id"), &step.ID, strings.TrimSpace(step.ID), "trimmed step identifier")
+		step.References = normalizeDocumentReferences(step.References, stepPath.Key("references"), resolution, state)
+		for _, laneID := range sortedLaneDocumentKeys(step.Artifacts) {
+			lane := step.Artifacts[laneID]
+			normalizeArtifactLaneDocument(&lane, stepPath.Key("artifacts").Key(laneID), resolution, state)
+			step.Artifacts[laneID] = lane
+		}
+		step.Artifacts = normalizeDocumentMap(step.Artifacts, stepPath.Key("artifacts"), "artifact lane identifier", resolution, state)
+	}
+}
+
+func normalizeArtifactLaneDocument(lane *ArtifactLaneDocument, path configkit.Path, resolution documentNormalizer, state *documentLoadState) {
+	normalizeDocumentBinding(&lane.Extract, path.Key("extract"), resolution, state)
+	if lane.Merge != nil {
+		normalizeDocumentBinding(lane.Merge, path.Key("merge"), resolution, state)
+	}
+	if lane.Normalize != nil {
+		normalizeDocumentBinding(lane.Normalize, path.Key("normalize"), resolution, state)
+	}
+	resolution = resolution.inSequence(path.Key("validators"))
+	for index := range lane.Validators {
+		normalizeValidatorDocument(&lane.Validators[index], path.Key("validators").Index(index), resolution)
+	}
+}
+
+func normalizeDocumentBinding(binding *BindingDocument, path configkit.Path, resolution documentNormalizer, state *documentLoadState) {
+	normalizeDocumentValue(resolution, path.Key("module"), &binding.Module, strings.TrimSpace(binding.Module), "trimmed module identifier")
+	normalizePipelineDocumentString(resolution, path.Key("llm_profile"), &binding.LLMProfile, "trimmed binding LLM profile")
+	binding.References = normalizeDocumentReferences(binding.References, path.Key("references"), resolution, state)
+	resolution = resolution.inSequence(path.Key("validators"))
+	for index := range binding.Validators {
+		normalizeValidatorDocument(&binding.Validators[index], path.Key("validators").Index(index), resolution)
+	}
+}
+
+func normalizeValidatorDocument(validator *ValidatorDocument, path configkit.Path, resolution documentNormalizer) {
+	normalizeDocumentValue(resolution, path.Key("module"), &validator.Module, strings.TrimSpace(validator.Module), "trimmed validator module identifier")
+	normalizePipelineDocumentString(resolution, path.Key("llm_profile"), &validator.LLMProfile, "trimmed validator LLM profile")
+}
+
+func normalizeDocumentReferences(references map[string]ReferenceDocument, path configkit.Path, resolution documentNormalizer, state *documentLoadState) map[string]ReferenceDocument {
+	for _, name := range sortedReferenceDocumentKeys(references) {
+		source := references[name]
+		sourcePath := path.Key(name)
+		normalizePipelineDocumentString(resolution, sourcePath.Key("path"), &source.Path, "trimmed reference path")
+		if source.Artifact != nil {
+			normalizeDocumentValue(resolution, sourcePath.Key("artifact").Key("step"), &source.Artifact.Step, strings.TrimSpace(source.Artifact.Step), "trimmed artifact step selector")
+			normalizeDocumentValue(resolution, sourcePath.Key("artifact").Key("lane"), &source.Artifact.Lane, strings.TrimSpace(source.Artifact.Lane), "trimmed artifact lane selector")
+		}
+		references[name] = source
+	}
+	return normalizeDocumentMap(references, path, "reference name", resolution, state)
+}
+
+func normalizeDocumentValue[T comparable](resolution documentNormalizer, path configkit.Path, target *T, value T, reason string) {
+	if target == nil || !resolution.IsExplicit(path) {
+		return
+	}
+	if *target != value {
+		resolution.Record(path, configkit.ChangeNormalization, reason)
+		*target = value
+	}
+}
+
+func normalizePipelineDocumentString(resolution documentNormalizer, path configkit.Path, target **string, reason string) {
+	if target == nil || *target == nil || !resolution.IsExplicit(path) {
+		return
+	}
+	value := strings.TrimSpace(**target)
+	if **target != value {
+		resolution.Record(path, configkit.ChangeNormalization, reason)
+		**target = value
+	}
+}
+
+func normalizeDocumentMap[T any](values map[string]T, path configkit.Path, kind string, resolution documentNormalizer, state *documentLoadState) map[string]T {
+	if len(values) == 0 {
+		return values
+	}
+	keys := make([]string, 0, len(values))
+	for key := range values {
+		keys = append(keys, key)
+	}
+	sort.Strings(keys)
+	canonical := make(map[string]string, len(values))
+	valid := true
+	for _, key := range keys {
+		trimmed := strings.TrimSpace(key)
+		if trimmed == "" {
+			resolution.Error(path.Key(key), kind+" must not be empty")
+			valid = false
+			continue
+		}
+		if first, exists := canonical[trimmed]; exists {
+			resolution.Error(path.Key(key), kind+" collides after whitespace normalization", path.Key(first))
+			valid = false
+			continue
+		}
+		canonical[trimmed] = key
+	}
+	if !valid {
+		return values
+	}
+	result := make(map[string]T, len(values))
+	changed := false
+	dependencies := make([]configkit.Path, 0, len(keys))
+	for _, key := range keys {
+		trimmed := strings.TrimSpace(key)
+		result[trimmed] = values[key]
+		dependencies = append(dependencies, path.Key(key))
+		if trimmed != key {
+			changed = true
+			state.rememberPath(path.Key(trimmed), path.Key(key))
+		}
+	}
+	if changed {
+		resolution.Record(path, configkit.ChangeNormalization, "normalized "+kind+" keys", dependencies...)
+		values = result
+	}
+	return values
+}
+
+func validateDocumentPipelines(document *Document, validation *configkit.Validation) {
+	if document == nil {
+		return
+	}
+	pipelinesPath := configkit.Keys("pipelines")
+	for _, id := range sortedPipelineDocumentKeys(document.Pipelines) {
+		profile := document.Pipelines[id]
+		path := pipelinesPath.Key(id)
+		validatePipelineDocument(profile, path, validation)
+	}
+}
+
+func validatePipelineDocument(profile PipelineDocument, path configkit.Path, validation *configkit.Validation) {
+	validateSelectedDocumentProfile(profile.LLMProfile, path.Key("llm_profile"), validation)
+	validateDocumentRepairAttempts(profile.StructuredOutputRepairAttempts, path.Key("structured_output_repair_attempts"), validation)
+	validateDocumentPolicy(profile.ValidationPolicy, path.Key("validation_policy"), validation)
+	validateDocumentBinding(profile.Input, path.Key("input"), "input", false, false, validation)
+	if profile.Chunk != nil {
+		validateDocumentBinding(*profile.Chunk, path.Key("chunk"), "chunk", true, true, validation)
+	}
+	if profile.Output != nil {
+		validateDocumentBinding(*profile.Output, path.Key("output"), "output", false, false, validation)
+	}
+	validateDocumentReferences(profile.References, path.Key("references"), false, validation)
+
+	seenLanes := make(map[string]configkit.Path)
+	if profile.Steps != nil {
+		seenSteps := make(map[string]configkit.Path)
+		for index, step := range profile.Steps {
+			stepPath := path.Key("steps").Index(index)
+			if strings.TrimSpace(step.ID) == "" {
+				validation.Error(stepPath.Key("id"), "must not be empty")
+			} else if first, exists := seenSteps[step.ID]; exists {
+				validation.Error(stepPath.Key("id"), "must be unique", first)
+			} else {
+				seenSteps[step.ID] = stepPath.Key("id")
+			}
+			validateDocumentReferences(step.References, stepPath.Key("references"), true, validation)
+			validateDocumentLanes(step.Artifacts, stepPath.Key("artifacts"), seenLanes, validation)
+		}
+		return
+	}
+	validateDocumentLanes(profile.Artifacts, path.Key("artifacts"), seenLanes, validation)
+}
+
+func validateDocumentLanes(lanes map[string]ArtifactLaneDocument, path configkit.Path, seen map[string]configkit.Path, validation *configkit.Validation) {
+	for _, id := range sortedLaneDocumentKeys(lanes) {
+		lanePath := path.Key(id)
+		if first, exists := seen[id]; exists {
+			validation.Error(lanePath, "artifact lane identifier must be unique across steps", first)
+		} else {
+			seen[id] = lanePath
+		}
+		lane := lanes[id]
+		validateDocumentBinding(lane.Extract, lanePath.Key("extract"), "extract", true, true, validation)
+		if lane.Merge != nil {
+			validateDocumentBinding(*lane.Merge, lanePath.Key("merge"), "merge", true, true, validation)
+		}
+		if lane.Normalize != nil {
+			validateDocumentBinding(*lane.Normalize, lanePath.Key("normalize"), "normalize", true, true, validation)
+		}
+		if len(lane.Validators) > 0 {
+			validation.Error(lanePath.Key("validators"), "artifact-lane validators are not supported; attach validators to a binding")
+		}
+	}
+}
+
+func validateDocumentBinding(binding BindingDocument, path configkit.Path, slot string, referencesAllowed, validatorsAllowed bool, validation *configkit.Validation) {
+	if strings.TrimSpace(binding.Module) == "" {
+		validation.Error(path.Key("module"), "must not be empty")
+	}
+	validateSelectedDocumentProfile(binding.LLMProfile, path.Key("llm_profile"), validation)
+	validateDocumentRepairAttempts(binding.StructuredOutputRepairAttempts, path.Key("structured_output_repair_attempts"), validation)
+	if binding.Retries < 0 {
+		validation.Error(path.Key("retries"), "must be greater than or equal to zero")
+	}
+	if binding.ValidationPolicy != nil {
+		if slot != "chunk" && slot != "extract" && slot != "merge" && slot != "normalize" {
+			validation.Error(path.Key("validation_policy"), "is not supported for this binding")
+		}
+		validateDocumentPolicy(binding.ValidationPolicy, path.Key("validation_policy"), validation)
+	}
+	if len(binding.References) > 0 && !referencesAllowed {
+		validation.Error(path.Key("references"), "are not supported for this binding")
+	}
+	if referencesAllowed {
+		validateDocumentReferences(binding.References, path.Key("references"), true, validation)
+	}
+	if binding.Validators != nil && !validatorsAllowed {
+		validation.Error(path.Key("validators"), "are not supported for this binding")
+	}
+	for index, validator := range binding.Validators {
+		validateValidatorDocument(validator, path.Key("validators").Index(index), validation)
+	}
+}
+
+func validateValidatorDocument(validator ValidatorDocument, path configkit.Path, validation *configkit.Validation) {
+	if strings.TrimSpace(validator.Module) == "" {
+		validation.Error(path.Key("module"), "must not be empty")
+	}
+	validateSelectedDocumentProfile(validator.LLMProfile, path.Key("llm_profile"), validation)
+	validateDocumentRepairAttempts(validator.StructuredOutputRepairAttempts, path.Key("structured_output_repair_attempts"), validation)
+	if validator.Retries < 0 {
+		validation.Error(path.Key("retries"), "must be greater than or equal to zero")
+	}
+}
+
+func validateDocumentReferences(references map[string]ReferenceDocument, path configkit.Path, generatedAllowed bool, validation *configkit.Validation) {
+	for _, name := range sortedReferenceDocumentKeys(references) {
+		source := references[name]
+		sourcePath := path.Key(name)
+		hasPath := source.Path != nil
+		hasArtifact := source.Artifact != nil
+		if hasPath == hasArtifact {
+			validation.Error(sourcePath, "must select exactly one reference source")
+			continue
+		}
+		if hasPath {
+			if strings.TrimSpace(*source.Path) == "" {
+				validation.Error(sourcePath.Key("path"), "must not be empty")
+			}
+			continue
+		}
+		if !generatedAllowed {
+			validation.Error(sourcePath.Key("artifact"), "is not supported here; use an external path")
+			continue
+		}
+		if strings.TrimSpace(source.Artifact.Step) == "" {
+			validation.Error(sourcePath.Key("artifact").Key("step"), "must not be empty")
+		}
+		if strings.TrimSpace(source.Artifact.Lane) == "" {
+			validation.Error(sourcePath.Key("artifact").Key("lane"), "must not be empty")
+		}
+	}
+}
+
+func validateSelectedDocumentProfile(value *string, path configkit.Path, validation *configkit.Validation) {
+	if value != nil && strings.TrimSpace(*value) == "" {
+		validation.Error(path, "must not be empty when set")
+	}
+}
+
+func validateDocumentRepairAttempts(value *int, path configkit.Path, validation *configkit.Validation) {
+	if value != nil && (*value < 0 || *value > 3) {
+		validation.Error(path, "must be between zero and three")
+	}
+}
+
+func validateDocumentPolicy(policy *ValidationPolicyDocument, path configkit.Path, validation *configkit.Validation) {
+	if policy == nil {
+		return
+	}
+	if policy.ProducerStructuralFailure != nil {
+		switch *policy.ProducerStructuralFailure {
+		case pipeline.ProducerStructuralFailureFailRun, pipeline.ProducerStructuralFailureRejectOutput:
+		default:
+			validation.Error(path.Key("producer_structural_failure"), "must be fail_run or reject_output")
+		}
+	}
+	if policy.SemanticRejection != nil {
+		switch *policy.SemanticRejection {
+		case pipeline.SemanticRejectionFailRun, pipeline.SemanticRejectionRejectOutput:
+		default:
+			validation.Error(path.Key("semantic_rejection"), "must be fail_run or reject_output")
+		}
+	}
+	if policy.ValidatorFailure != nil {
+		switch *policy.ValidatorFailure {
+		case pipeline.ValidatorFailureWarnContinue, pipeline.ValidatorFailureFailRun:
+		default:
+			validation.Error(path.Key("validator_failure"), "must be warn_continue or fail_run")
+		}
+	}
+}
+
+func sortedPipelineDocumentKeys(values map[string]PipelineDocument) []string {
+	return sortedDocumentKeys(values)
+}
+func sortedLaneDocumentKeys(values map[string]ArtifactLaneDocument) []string {
+	return sortedDocumentKeys(values)
+}
+func sortedReferenceDocumentKeys(values map[string]ReferenceDocument) []string {
+	return sortedDocumentKeys(values)
+}
+
+func sortedDocumentKeys[T any](values map[string]T) []string {
+	keys := make([]string, 0, len(values))
+	for key := range values {
+		keys = append(keys, key)
+	}
+	sort.Strings(keys)
+	return keys
+}

internal/core/config/pipeline_document_test.go

@@ -0,0 +1,263 @@
+package config
+
+import (
+	"errors"
+	"fmt"
+	"testing"
+
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
+)
+
+func TestDocumentRejectsExplicitInvalidBranches(t *testing.T) {
+	t.Parallel()
+	for _, slot := range []string{"input", "output"} {
+		t.Run(slot+" empty validators", func(t *testing.T) {
+			body := "input: {module: input, validators: []}"
+			if slot == "output" {
+				body = "input: {module: input}\n    output: {module: output, validators: []}"
+			}
+			_, err := loadConfigSource(configkit.Bytes("document.yml", []byte("version: 5\npipelines:\n  session:\n    "+body+"\n")), LoadOptions{})
+			assertDocumentDiagnosticAt(t, err, "/pipelines/session/"+slot+"/validators")
+		})
+	}
+	for _, value := range []string{
+		"{path: ''}", "{path: '   '}",
+		"{path: '', artifact: {step: previous, lane: registry}}",
+		"{path: '   ', artifact: {step: previous, lane: registry}}",
+		"{path: null, artifact: {step: previous, lane: registry}}",
+	} {
+		t.Run(value, func(t *testing.T) {
+			content := fmt.Sprintf("version: 5\npipelines:\n  session:\n    input: {module: input}\n    artifacts:\n      lane:\n        extract:\n          module: extract\n          references:\n            party: %s\n", value)
+			_, err := loadConfigSource(configkit.Bytes("document.yml", []byte(content)), LoadOptions{})
+			path := "/pipelines/session/artifacts/lane/extract/references/party"
+			if value == "{path: ''}" || value == "{path: '   '}" || value == "{path: null, artifact: {step: previous, lane: registry}}" {
+				path += "/path"
+			}
+			assertDocumentDiagnosticAt(t, err, path)
+		})
+	}
+}
+
+func TestDocumentPreservesSupportedEmptyValidatorsAndReferenceForms(t *testing.T) {
+	t.Parallel()
+	loaded, err := loadConfigSource(configkit.Bytes("document.yml", []byte(`version: 5
+pipelines:
+  session:
+    input: {module: input}
+    chunk: {module: chunk, validators: []}
+    artifacts:
+      lane:
+        validators: []
+        extract:
+          module: extract
+          validators: []
+          references:
+            external: {path: /data/party.txt}
+            generated: {artifact: {step: previous, lane: registry}}
+        merge: {module: merge, validators: []}
+        normalize: {module: normalize, validators: []}
+`)), LoadOptions{})
+	if err != nil {
+		t.Fatal(err)
+	}
+	profile := loaded.Config.Pipelines["session"]
+	lane := profile.Artifacts["lane"]
+	for _, override := range []bool{profile.Chunk.Validators.Set, lane.Extract.Validators.Set, lane.Merge.Validators.Set, lane.Normalize.Validators.Set} {
+		if !override {
+			t.Fatal("supported empty validator override lost explicitness")
+		}
+	}
+	if len(lane.Validators) != 0 || lane.Extract.References["external"].Path != "/data/party.txt" ||
+		lane.Extract.References["generated"].Artifact.Lane != "registry" {
+		t.Fatalf("lane = %#v", lane)
+	}
+}
+
+func TestDocumentPipelineNormalizesCanonicalIdentifiers(t *testing.T) {
+	t.Parallel()
+
+	loaded, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(`version: 5
+pipelines:
+  " session ":
+    llm_profile: " local "
+    input:
+      module: " seriatim "
+    artifacts:
+      " spells ":
+        extract:
+          module: " dnd/spells "
+          structured_output_repair_attempts: 0
+          validators: []
+        merge:
+          module: dnd/merge
+          references:
+            previous:
+              artifact:
+                step: " default "
+                lane: " spells "
+`)), LoadOptions{})
+	if err != nil {
+		var loadError *configkit.LoadError
+		if errors.As(err, &loadError) {
+			t.Fatalf("loadDocumentSource() diagnostics = %#v", loadError.Diagnostics())
+		}
+		t.Fatalf("loadDocumentSource() error = %v", err)
+	}
+	profile, ok := loaded.Config.Pipelines["session"]
+	if !ok || profile.Input.Module != "seriatim" || profile.LLMProfile == nil || *profile.LLMProfile != "local" {
+		t.Fatalf("normalized pipeline = %#v", loaded.Config.Pipelines)
+	}
+	lane, ok := profile.Artifacts["spells"]
+	if !ok || lane.Extract.StructuredOutputRepairAttempts == nil || *lane.Extract.StructuredOutputRepairAttempts != 0 || lane.Extract.Validators == nil || len(lane.Extract.Validators) != 0 {
+		t.Fatalf("normalized lane = %#v", profile.Artifacts)
+	}
+	selector := lane.Merge.References["previous"].Artifact
+	if selector == nil || selector.Step != "default" || selector.Lane != "spells" {
+		t.Fatalf("artifact selector = %#v", selector)
+	}
+}
+
+func TestDocumentPipelineRejectsInvalidShapes(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name   string
+		source string
+		path   string
+	}{
+		{
+			name: "both pipeline forms",
+			source: `version: 5
+pipelines:
+  session:
+    input: {module: seriatim}
+    artifacts: {}
+    steps:
+      - id: first
+        artifacts: {}
+`,
+			path: "/pipelines/session/steps",
+		},
+		{
+			name: "empty ordered steps",
+			source: `version: 5
+pipelines:
+  session:
+    input: {module: seriatim}
+    steps: []
+`,
+			path: "/pipelines/session/steps",
+		},
+		{
+			name: "normalized pipeline collision",
+			source: `version: 5
+pipelines:
+  session: {input: {module: seriatim}}
+  " session ": {input: {module: seriatim}}
+`,
+			path: "/pipelines/session",
+		},
+		{
+			name: "duplicate lane across ordered steps",
+			source: `version: 5
+pipelines:
+  session:
+    input: {module: seriatim}
+    steps:
+      - id: first
+        artifacts: {summary: {extract: {module: dnd/summary}}}
+      - id: second
+        artifacts: {summary: {extract: {module: dnd/summary}}}
+`,
+			path: "/pipelines/session/steps/1/artifacts/summary",
+		},
+		{
+			name: "invalid reference union",
+			source: `version: 5
+pipelines:
+  session:
+    input: {module: seriatim}
+    references:
+      party: {path: ./party.txt, artifact: {step: one, lane: summary}}
+`,
+			path: "/pipelines/session/references/party",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			_, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(test.source)), LoadOptions{})
+			assertDocumentDiagnosticAt(t, err, test.path)
+		})
+	}
+}
+
+func TestDocumentPipelineRejectsInvalidBindingPlacementAndPresence(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name   string
+		source string
+		path   string
+	}{
+		{
+			name: "input validators",
+			source: `version: 5
+pipelines:
+  session:
+    input:
+      module: seriatim
+      validators: [{module: generic/valid_json}]
+`,
+			path: "/pipelines/session/input/validators",
+		},
+		{
+			name: "blank selected profile",
+			source: `version: 5
+pipelines:
+  session:
+    llm_profile: "   "
+    input: {module: seriatim}
+`,
+			path: "/pipelines/session/llm_profile",
+		},
+		{
+			name: "null validators",
+			source: `version: 5
+pipelines:
+  session:
+    input: {module: seriatim}
+    chunk: {module: generic/chunk, validators: null}
+`,
+			path: "/pipelines/session/chunk/validators",
+		},
+		{
+			name: "negative retry budget",
+			source: `version: 5
+pipelines:
+  session:
+    input: {module: seriatim, retries: -1}
+`,
+			path: "/pipelines/session/input/retries",
+		},
+	}
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			_, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(test.source)), LoadOptions{})
+			assertDocumentDiagnosticAt(t, err, test.path)
+		})
+	}
+}
+
+func assertDocumentDiagnosticAt(t *testing.T, err error, path string) {
+	t.Helper()
+	var loadError *configkit.LoadError
+	if !errors.As(err, &loadError) {
+		t.Fatalf("error = %v, want ConfigKit load error", err)
+	}
+	for _, diagnostic := range loadError.Diagnostics() {
+		if diagnostic.Path.String() == path {
+			return
+		}
+	}
+	t.Fatalf("diagnostics = %#v, want a diagnostic at %s", loadError.Diagnostics(), path)
+}

internal/core/config/redaction.go

@@ -4,28 +4,10 @@ import (
 	"reflect"
 	"strings"
 
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
 )
 
-func (c Config) Redacted() Config {
-	return redactConfig(cloneConfig(c))
-}
-
-func (c Config) RedactedSummaryPayload() any {
-	return c.Redacted()
-}
-
-func (e EffectiveConfig) RedactedSummaryPayload() any {
-	return EffectiveConfig{
-		Config:             e.Config.Redacted(),
-		PipelineID:         e.PipelineID,
-		Only:               append([]string(nil), e.Only...),
-		ReferenceOverrides: append([]pipeline.ReferenceBinding(nil), e.ReferenceOverrides...),
-		ReferenceUnbinds:   append([]pipeline.ReferenceUnbind(nil), e.ReferenceUnbinds...),
-		ResolvedPipeline:   cloneResolvedPipeline(e.ResolvedPipeline),
-	}
-}
-
 func (e EffectiveConfig) RedactedResolvedPipelinePayload() pipeline.ResolvedPipeline {
 	return cloneResolvedPipeline(e.ResolvedPipeline)
 }
@@ -91,31 +73,6 @@ func cloneResolvedArtifactLane(in pipeline.ResolvedArtifactLane) pipeline.Resolv
 	return out
 }
 
-func redactConfig(cfg Config) Config {
-	for id, profile := range cfg.Pipelines {
-		profile.Input = redactBinding(profile.Input)
-		profile.Chunk = redactBinding(profile.Chunk)
-		profile.Output = redactBinding(profile.Output)
-		redactLanes := func(lanes map[string]pipeline.ArtifactLaneProfile) {
-			for laneID, lane := range lanes {
-				lane.Extract = redactBinding(lane.Extract)
-				lane.Merge = redactBinding(lane.Merge)
-				lane.Normalize = redactBinding(lane.Normalize)
-				for i := range lane.Validators {
-					lane.Validators[i] = redactBinding(lane.Validators[i])
-				}
-				lanes[laneID] = lane
-			}
-		}
-		redactLanes(profile.Artifacts)
-		for i := range profile.Steps {
-			redactLanes(profile.Steps[i].Artifacts)
-		}
-		cfg.Pipelines[id] = profile
-	}
-	return cfg
-}
-
 func redactBinding(binding pipeline.ModuleBinding) pipeline.ModuleBinding {
 	binding.Options = redactOptions(binding.Options)
 	for i := range binding.Validators.Validators {
@@ -188,3 +145,21 @@ func sensitiveConfigKey(key string) bool {
 	key = strings.ToLower(key)
 	return strings.Contains(key, "api_key") || strings.Contains(key, "apikey") || strings.Contains(key, "authorization") || strings.Contains(key, "bearer") || strings.Contains(key, "password") || strings.Contains(key, "secret") || strings.Contains(key, "token")
 }
+
+// sensitiveDocumentPath applies the existing option-key classification to the
+// fully typed ConfigKit document. Dynamic option maps can be nested below any
+// producer or validator, so every key after an options container participates.
+func sensitiveDocumentPath(path configkit.Path) bool {
+	segments := strings.Split(strings.TrimPrefix(path.String(), "/"), "/")
+	withinOptions := false
+	for _, segment := range segments {
+		segment = strings.ReplaceAll(strings.ReplaceAll(segment, "~1", "/"), "~0", "~")
+		if withinOptions && sensitiveConfigKey(segment) {
+			return true
+		}
+		if segment == "options" {
+			withinOptions = true
+		}
+	}
+	return false
+}

internal/core/config/redaction_test.go

@@ -114,83 +114,6 @@ func TestRedactedResolvedPipelinePayloadRedactsEveryBinding(t *testing.T) {
 	}
 }
 
-func TestRedactedEffectiveConfigPayloadDoesNotAliasSource(t *testing.T) {
-	binding := redactionTestBinding("effective")
-	effective := EffectiveConfig{
-		Config: Config{Pipelines: map[string]pipeline.PipelineProfile{
-			"redaction-test": {Input: binding},
-		}},
-		ResolvedPipeline: pipeline.ResolvedPipeline{Input: binding},
-	}
-
-	payload := effective.RedactedSummaryPayload().(EffectiveConfig)
-	payload.Config.Pipelines["redaction-test"].Input.Options["safe"] = "mutated"
-	payload.ResolvedPipeline.Input.Options["safe"] = "mutated"
-
-	assertRedactionTestBindingUnchanged(t, effective.Config.Pipelines["redaction-test"].Input, "effective")
-	assertRedactionTestBindingUnchanged(t, effective.ResolvedPipeline.Input, "effective")
-}
-
-func TestRedactedSummaryPayloadsCoverEveryEffectiveConfigBinding(t *testing.T) {
-	bindings := map[string]pipeline.ModuleBinding{}
-	for _, name := range []string{"input", "chunk", "output", "extract", "merge", "normalize", "lane-validator"} {
-		bindings[name] = redactionTestBinding("summary-" + name)
-	}
-	effective := EffectiveConfig{
-		Config: Config{Pipelines: map[string]pipeline.PipelineProfile{
-			"redaction-test": {
-				Input:  bindings["input"],
-				Chunk:  bindings["chunk"],
-				Output: bindings["output"],
-				Artifacts: map[string]pipeline.ArtifactLaneProfile{
-					"safe-lane": {
-						Extract:    bindings["extract"],
-						Merge:      bindings["merge"],
-						Normalize:  bindings["normalize"],
-						Validators: []pipeline.ModuleBinding{bindings["lane-validator"]},
-					},
-				},
-			},
-		}},
-		ResolvedPipeline: pipeline.ResolvedPipeline{
-			Input:  bindings["input"],
-			Chunk:  bindings["chunk"],
-			Output: bindings["output"],
-			Steps: []pipeline.ResolvedPipelineStep{{
-				ID: "default",
-				ArtifactLanes: []pipeline.ResolvedArtifactLane{{
-					ID:         "safe-lane",
-					Extract:    bindings["extract"],
-					Merge:      bindings["merge"],
-					Normalize:  bindings["normalize"],
-					Validators: []pipeline.ModuleBinding{bindings["lane-validator"]},
-				}},
-			}},
-		},
-	}
-
-	payload, ok := effective.RedactedSummaryPayload().(EffectiveConfig)
-	if !ok {
-		t.Fatal("RedactedSummaryPayload() returned an unexpected type")
-	}
-	encoded, err := json.Marshal(payload)
-	if err != nil {
-		t.Fatal(err)
-	}
-	text := string(encoded)
-	for name := range bindings {
-		if strings.Contains(text, "summary-"+name+"-secret") || strings.Contains(text, "summary-"+name+"-nested-secret") {
-			t.Fatalf("summary payload contains sensitive option for %q: %s", name, text)
-		}
-		if !strings.Contains(text, "summary-"+name+"-safe") {
-			t.Fatalf("summary payload omitted safe option for %q: %s", name, text)
-		}
-	}
-	if !strings.Contains(text, "[REDACTED]") {
-		t.Fatalf("summary payload contains no redaction marker: %s", text)
-	}
-}
-
 func TestRedactedResolvedPipelinePayloadHandlesTypedOptionContainers(t *testing.T) {
 	type optionMap map[string]string
 	type optionList []optionMap
@@ -225,39 +148,6 @@ func TestRedactedResolvedPipelinePayloadHandlesTypedOptionContainers(t *testing.
 	}
 }
 
-func TestRedactedEffectiveConfigPayloadOwnsValidationPolicies(t *testing.T) {
-	semantic := pipeline.SemanticRejectionRejectOutput
-	validator := pipeline.ValidatorFailureFailRun
-	configured := &pipeline.ValidationPolicyOverride{SemanticRejection: &semantic, ValidatorFailure: &validator}
-	effective := EffectiveConfig{
-		Config: Config{Pipelines: map[string]pipeline.PipelineProfile{
-			"main": {ValidationPolicy: configured},
-		}},
-		ResolvedPipeline: pipeline.ResolvedPipeline{
-			ConfiguredValidationPolicy: configured,
-			ChunkValidationPolicy: pipeline.ValidationPolicy{
-				ProducerStructuralFailure: pipeline.ProducerStructuralFailureFailRun,
-				SemanticRejection:         pipeline.SemanticRejectionRejectOutput,
-				ValidatorFailure:          pipeline.ValidatorFailureFailRun,
-			},
-		},
-	}
-
-	payload := effective.RedactedSummaryPayload().(EffectiveConfig)
-	encoded, err := json.Marshal(payload)
-	if err != nil {
-		t.Fatal(err)
-	}
-	if !strings.Contains(string(encoded), `"configured_validation_policy":{"semantic_rejection":"reject_output","validator_failure":"fail_run"}`) || !strings.Contains(string(encoded), `"chunk_validation_policy":{"producer_structural_failure":"fail_run","semantic_rejection":"reject_output","validator_failure":"fail_run"}`) {
-		t.Fatalf("redacted payload omitted validation policy: %s", encoded)
-	}
-	*payload.Config.Pipelines["main"].ValidationPolicy.SemanticRejection = pipeline.SemanticRejectionFailRun
-	*payload.ResolvedPipeline.ConfiguredValidationPolicy.ValidatorFailure = pipeline.ValidatorFailureWarnContinue
-	if *effective.Config.Pipelines["main"].ValidationPolicy.SemanticRejection != pipeline.SemanticRejectionRejectOutput || *effective.ResolvedPipeline.ConfiguredValidationPolicy.ValidatorFailure != pipeline.ValidatorFailureFailRun {
-		t.Fatal("redacted payload aliases validation policy")
-	}
-}
-
 func redactionTestBinding(name string) pipeline.ModuleBinding {
 	return pipeline.ModuleBinding{
 		Module: "safe-" + name,

internal/core/config/sequence_normalization_test.go

@@ -0,0 +1,92 @@
+package config
+
+import (
+	"bytes"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestSequenceNormalizationPreservesRuntimeAndProvenance(t *testing.T) {
+	t.Parallel()
+	for _, test := range []struct {
+		name, body, pointer, want string
+	}{
+		{
+			name:    "step identifier",
+			body:    "steps:\n      - id: ' first '\n        artifacts: {spells: {extract: {module: dnd/spells}}}",
+			pointer: "/pipelines/session/steps/0/id",
+			want:    "first",
+		},
+		{
+			name:    "standalone validator",
+			body:    "artifacts:\n      spells:\n        extract:\n          module: dnd/spells\n          validators: [{module: ' generic/valid_json '}]",
+			pointer: "/pipelines/session/artifacts/spells/extract/validators/0/module",
+			want:    "generic/valid_json",
+		},
+		{
+			name: "nested fields and source paths",
+			body: `steps:
+      - id: first
+        artifacts:
+          " spells ":
+            extract:
+              module: " dnd/spells "
+              llm_profile: " local "
+              validators: [{module: " generic/valid_json "}]
+              references:
+                " party ": {path: "./party.txt"}
+                registry: {artifact: {step: " previous ", lane: " nouns "}}`,
+			// Map-key moves are explained at their enclosing container, where
+			// the original declaration and the new canonical keys coexist.
+			pointer: "/pipelines/session/steps",
+			want:    "party.txt",
+		},
+	} {
+		t.Run(test.name, func(t *testing.T) {
+			root := t.TempDir()
+			path := filepath.Join(root, "config.yml")
+			if err := os.WriteFile(path, []byte("version: 5\npipelines:\n  session:\n    input: {module: seriatim}\n    "+test.body+"\n"), 0o600); err != nil {
+				t.Fatal(err)
+			}
+			loaded, err := Load(path, LoadOptions{})
+			if err != nil {
+				t.Fatal(err)
+			}
+			profile := loaded.Config.Pipelines["session"]
+			switch test.name {
+			case "step identifier":
+				if profile.Steps[0].ID != "first" {
+					t.Fatalf("step = %#v", profile.Steps[0])
+				}
+			case "standalone validator":
+				if profile.Artifacts["spells"].Extract.Validators.Validators[0].Module != test.want {
+					t.Fatal("validator was not normalized")
+				}
+			default:
+				binding := profile.Steps[0].Artifacts["spells"].Extract
+				if binding.Module != "dnd/spells" || binding.LLMProfile != "local" ||
+					binding.Validators.Validators[0].Module != "generic/valid_json" ||
+					binding.References["party"].Path != filepath.Join(root, "party.txt") ||
+					binding.References["registry"].Artifact.Step != "previous" ||
+					binding.References["registry"].Artifact.Lane != "nouns" {
+					t.Fatalf("binding = %#v", binding)
+				}
+			}
+			var effective, explanation bytes.Buffer
+			if err := loaded.WriteEffective(&effective); err != nil {
+				t.Fatal(err)
+			}
+			if err := loaded.WriteExplanation(&explanation, test.pointer); err != nil {
+				t.Fatal(err)
+			}
+			if !strings.Contains(effective.String(), test.want) ||
+				!strings.Contains(explanation.String(), test.want) ||
+				!strings.Contains(explanation.String(), path) ||
+				!strings.Contains(explanation.String(), "normalization") {
+				t.Fatalf("missing effective value or provenance:\n%s\n%s", effective.String(), explanation.String())
+			}
+		})
+	}
+}

internal/core/config/validation.go

@@ -2,7 +2,6 @@ package config
 
 import (
 	"fmt"
-	"net/url"
 	"sort"
 	"strings"
 
@@ -10,15 +9,14 @@ import (
 )
 
 func (c Config) Validate() error {
-	c.Concurrency.recomputeStageWorkerDefaults()
 	if err := validatePromptKit(c.PromptKit); err != nil {
 		return err
 	}
 	if err := validateStateSurfaces(c); err != nil {
 		return err
 	}
-	if c.Concurrency.TotalLLM <= 0 {
-		return fmt.Errorf("total LLM concurrency must be greater than zero")
+	if err := validateTotalLLMConcurrency(c.Concurrency.TotalLLM); err != nil {
+		return err
 	}
 	if err := validateStageWorkers(c.Concurrency); err != nil {
 		return err
@@ -33,70 +31,42 @@ func validateStageWorkers(cfg ConcurrencyConfig) error {
 	}
 	sort.Strings(keys)
 	for _, key := range keys {
-		if strings.TrimSpace(key) == "" {
-			return fmt.Errorf("concurrency.stage_workers key must not be empty")
-		}
-		if key != "extract" {
-			return fmt.Errorf("concurrency.stage_workers key %q is not supported", key)
+		if err := validateStageWorkerKey(key); err != nil {
+			return err
 		}
 	}
 	extractWorkers, ok := cfg.StageWorkers["extract"]
 	if !ok {
 		extractWorkers = cfg.TotalLLM
 	}
-	if extractWorkers < 1 || extractWorkers > cfg.TotalLLM {
-		return fmt.Errorf("concurrency.stage_workers.extract must be between 1 and concurrency.total_llm (%d)", cfg.TotalLLM)
-	}
-	return nil
+	return validateExtractWorkerCount(extractWorkers, cfg.TotalLLM)
 }
 
 func validatePromptKit(cfg PromptKitConfig) error {
-	if strings.TrimSpace(cfg.ProfileDir) != "" && strings.TrimSpace(cfg.ProfileFile) != "" {
-		return fmt.Errorf("promptkit profile_dir and profile_file are mutually exclusive")
+	if err := validatePromptKitProfileSources(cfg.ProfileDir, cfg.ProfileFile); err != nil {
+		return err
 	}
 	if cfg.LocalBackend == nil {
 		return nil
 	}
-	endpoint := strings.TrimSpace(cfg.LocalBackend.Endpoint)
-	if endpoint == "" {
-		return fmt.Errorf("promptkit.local_backend.endpoint must not be empty when set")
-	}
-	parsed, err := url.Parse(endpoint)
-	if err != nil ||
-		(!strings.EqualFold(parsed.Scheme, "http") && !strings.EqualFold(parsed.Scheme, "https")) ||
-		!parsed.IsAbs() ||
-		parsed.Hostname() == "" ||
-		parsed.User != nil ||
-		parsed.RawQuery != "" ||
-		parsed.ForceQuery ||
-		strings.Contains(endpoint, "#") {
-		return fmt.Errorf("promptkit.local_backend.endpoint must be an absolute HTTP or HTTPS URL with a host and no user information, query, or fragment")
-	}
-	if cfg.LocalBackend.ConcurrencyLimit < 0 {
-		return fmt.Errorf("promptkit.local_backend.concurrency_limit must not be negative")
-	}
-	return nil
+	return validatePromptKitLocalBackend(cfg.LocalBackend.Endpoint, cfg.LocalBackend.ConcurrencyLimit)
 }
 
 func validateStateSurfaces(cfg Config) error {
-	if strings.TrimSpace(cfg.Output.Directory) == "" {
-		return fmt.Errorf("output.directory must not be empty")
+	if err := validateRequiredPath("output.directory", cfg.Output.Directory); err != nil {
+		return err
 	}
-	if strings.TrimSpace(cfg.Debug.Directory) == "" {
-		return fmt.Errorf("debug.directory must not be empty")
+	if err := validateRequiredPath("debug.directory", cfg.Debug.Directory); err != nil {
+		return err
 	}
-	if err := cfg.Cache.ChunkPlans.Mode.Validate(); err != nil {
-		return fmt.Errorf("cache.chunk_plans.mode: %w", err)
+	if err := validateChunkPlanCacheMode(string(cfg.Cache.ChunkPlans.Mode)); err != nil {
+		return err
 	}
-	for name, value := range map[string]string{
-		"output.directory":            cfg.Output.Directory,
-		"cache.chunk_plans.directory": cfg.Cache.ChunkPlans.Directory,
-		"cache.checkpoints.directory": cfg.Cache.Checkpoints.Directory,
-		"debug.directory":             cfg.Debug.Directory,
-	} {
-		if strings.ContainsRune(value, '\x00') {
-			return fmt.Errorf("%s must not contain NUL", name)
-		}
+	if err := validateOptionalPath("cache.chunk_plans.directory", cfg.Cache.ChunkPlans.Directory); err != nil {
+		return err
+	}
+	if err := validateOptionalPath("cache.checkpoints.directory", cfg.Cache.Checkpoints.Directory); err != nil {
+		return err
 	}
 	return nil
 }

internal/core/config/validation_contract_test.go

@@ -25,7 +25,6 @@ func TestValidateConcurrencyRules(t *testing.T) {
 			setup: func(cfg *Config) {
 				cfg.Concurrency.TotalLLM = 3
 				cfg.Concurrency.StageWorkers = map[string]int{"extract": 0}
-				cfg.Concurrency.extractWorkersConfigured = true
 			},
 			want: "stage_workers.extract must be between 1",
 		},
@@ -34,7 +33,6 @@ func TestValidateConcurrencyRules(t *testing.T) {
 			setup: func(cfg *Config) {
 				cfg.Concurrency.TotalLLM = 3
 				cfg.Concurrency.StageWorkers = map[string]int{"extract": 4}
-				cfg.Concurrency.extractWorkersConfigured = true
 			},
 			want: "stage_workers.extract must be between 1",
 		},
@@ -43,7 +41,6 @@ func TestValidateConcurrencyRules(t *testing.T) {
 			setup: func(cfg *Config) {
 				cfg.Concurrency.TotalLLM = 3
 				cfg.Concurrency.StageWorkers = map[string]int{"extract": 1}
-				cfg.Concurrency.extractWorkersConfigured = true
 			},
 		},
 		{
@@ -51,7 +48,6 @@ func TestValidateConcurrencyRules(t *testing.T) {
 			setup: func(cfg *Config) {
 				cfg.Concurrency.TotalLLM = 3
 				cfg.Concurrency.StageWorkers = map[string]int{"extract": 3}
-				cfg.Concurrency.extractWorkersConfigured = true
 			},
 		},
 		{

internal/core/config/validation_policy_contract_test.go

@@ -4,17 +4,19 @@ import (
 	"strings"
 	"testing"
 
+	configkit "gitea.maximumdirect.net/eric/ConfigKit"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
 )
 
 func TestValidationPolicyFileConfigurationIsStrictAndPresenceAware(t *testing.T) {
-	const valid = `version: 4
+	const valid = `version: 5
 pipelines:
   main:
     validation_policy:
       producer_structural_failure: reject_output
       semantic_rejection: fail_run
-    input: seriatim
+    input:
+      module: seriatim
     chunk:
       module: generic
       validation_policy:
@@ -26,7 +28,11 @@ pipelines:
           validation_policy:
             semantic_rejection: reject_output
 `
-	cfg := applyFileConfig(t, valid)
+	loaded, err := loadDocumentSource(configkit.Bytes("valid.yml", []byte(valid)), LoadOptions{})
+	if err != nil {
+		t.Fatal(err)
+	}
+	cfg := loaded.Config
 	profile := cfg.Pipelines["main"]
 	if profile.ValidationPolicy == nil || profile.ValidationPolicy.ProducerStructuralFailure == nil || *profile.ValidationPolicy.ProducerStructuralFailure != pipeline.ProducerStructuralFailureRejectOutput || profile.ValidationPolicy.SemanticRejection == nil || *profile.ValidationPolicy.SemanticRejection != pipeline.SemanticRejectionFailRun || profile.ValidationPolicy.ValidatorFailure != nil {
 		t.Fatalf("pipeline validation policy = %#v", profile.ValidationPolicy)
@@ -50,8 +56,8 @@ pipelines:
 		{"invalid enum", strings.Replace(valid, "semantic_rejection: fail_run", "semantic_rejection: continue", 1)},
 	} {
 		t.Run(test.name, func(t *testing.T) {
-			if _, err := ParseFileConfigYAML([]byte(test.yaml)); err == nil {
-				t.Fatal("ParseFileConfigYAML() error = nil, want strict validation-policy rejection")
+			if _, err := loadDocumentSource(configkit.Bytes("invalid.yml", []byte(test.yaml)), LoadOptions{}); err == nil {
+				t.Fatal("loadDocumentSource() error = nil, want strict validation-policy rejection")
 			}
 		})
 	}

internal/core/debugbundle/bundle_test.go

@@ -3,6 +3,8 @@ package debugbundle
 import (
 	"bytes"
 	"encoding/json"
+	"errors"
+	"io"
 	"os"
 	"path/filepath"
 	"strings"
@@ -89,7 +91,7 @@ func TestSummaryWriterWritesEverySummaryArtifact(t *testing.T) {
 	if err := summary.WriteInvocation(Invocation{Operation: "run"}); err != nil {
 		t.Fatal(err)
 	}
-	if err := summary.WriteRedactedEffectiveConfig(testRedactedSummaryPayload{}); err != nil {
+	if err := summary.WriteEffectiveConfig(testEffectiveConfigWriter{content: "version: 5\n"}); err != nil {
 		t.Fatal(err)
 	}
 	if err := summary.WriteResolvedPipeline(testRedactedResolvedPipelinePayload{}); err != nil {
@@ -119,7 +121,7 @@ func TestSummaryWriterWritesEverySummaryArtifact(t *testing.T) {
 
 	for _, name := range []string{
 		ArtifactInvocationMetadata,
-		ArtifactEffectiveConfig,
+		ArtifactEffectiveConfigYAML,
 		ArtifactResolvedPipeline,
 		ArtifactResolvedReferences,
 		ArtifactCheckpointEvents,
@@ -139,6 +141,20 @@ func TestSummaryWriterWritesEverySummaryArtifact(t *testing.T) {
 	}
 }
 
+func TestWriteEffectiveConfigDoesNotPublishPartialRendering(t *testing.T) {
+	bundle, err := Allocate(t.TempDir(), testBundleRunID, time.Unix(0, 42))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := bundle.Summary().WriteEffectiveConfig(testEffectiveConfigWriter{err: errors.New("render failed")}); err == nil {
+		t.Fatal("WriteEffectiveConfig() error = nil, want render failure")
+	}
+	path := filepath.Join(bundle.SummaryRoot(), ArtifactEffectiveConfigYAML)
+	if _, err := os.Stat(path); !os.IsNotExist(err) {
+		t.Fatalf("effective configuration artifact exists after rendering failure: %v", err)
+	}
+}
+
 func TestWriteInvocationPreservesReasoningEffortOverrideStates(t *testing.T) {
 	replacement := "focused"
 	cleared := ""
@@ -216,10 +232,17 @@ func TestSummaryWriterInternalWritesConfineArtifacts(t *testing.T) {
 	}
 }
 
-type testRedactedSummaryPayload struct{}
+type testEffectiveConfigWriter struct {
+	content string
+	err     error
+}
 
-func (testRedactedSummaryPayload) RedactedSummaryPayload() any {
-	return map[string]any{"redacted": true}
+func (writer testEffectiveConfigWriter) WriteEffective(output io.Writer) error {
+	if writer.err != nil {
+		return writer.err
+	}
+	_, err := io.WriteString(output, writer.content)
+	return err
 }
 
 type testRedactedResolvedPipelinePayload struct{}

internal/core/debugbundle/summary.go

@@ -1,7 +1,9 @@
 package debugbundle
 
 import (
+	"bytes"
 	"fmt"
+	"io"
 	"strings"
 	"time"
 
@@ -12,19 +14,19 @@ import (
 )
 
 const (
-	ArtifactInvocationMetadata = "invocation.json"
-	ArtifactEffectiveConfig    = "effective-config.json"
-	ArtifactResolvedPipeline   = "resolved-pipeline.json"
-	ArtifactResolvedReferences = "resolved-references.json"
-	ArtifactCheckpointEvents   = "checkpoint-events.json"
-	ArtifactRunManifest        = "run-manifest.json"
-	ArtifactChunkPlan          = "chunk-plan.json"
-	ArtifactRunReport          = "run-report.json"
-	ArtifactDiagnostics        = "final-diagnostics.json"
-	ArtifactErrorLog           = "error.log"
+	ArtifactInvocationMetadata  = "invocation.json"
+	ArtifactEffectiveConfigYAML = "effective-config.yml"
+	ArtifactResolvedPipeline    = "resolved-pipeline.json"
+	ArtifactResolvedReferences  = "resolved-references.json"
+	ArtifactCheckpointEvents    = "checkpoint-events.json"
+	ArtifactRunManifest         = "run-manifest.json"
+	ArtifactChunkPlan           = "chunk-plan.json"
+	ArtifactRunReport           = "run-report.json"
+	ArtifactDiagnostics         = "final-diagnostics.json"
+	ArtifactErrorLog            = "error.log"
 )
 
-type RedactedSummaryPayload interface{ RedactedSummaryPayload() any }
+type EffectiveConfigWriter interface{ WriteEffective(io.Writer) error }
 type RedactedResolvedPipelinePayload interface {
 	RedactedResolvedPipelinePayload() pipeline.ResolvedPipeline
 }
@@ -37,6 +39,7 @@ type Invocation struct {
 	InputPath               string    `json:"input_path,omitempty"`
 	ConfigPath              string    `json:"config_path,omitempty"`
 	ConfigSource            string    `json:"config_source,omitempty"`
+	ConfigProfile           string    `json:"config_profile,omitempty"`
 	OnlyLanes               []string  `json:"only_lanes,omitempty"`
 	ChunkCacheOverride      string    `json:"chunk_cache_override,omitempty"`
 	ReasoningEffortOverride *string   `json:"reasoning_effort_override,omitempty"`
@@ -80,11 +83,15 @@ func (w *SummaryWriter) WriteInvocation(payload Invocation) error {
 	}
 	return w.writeJSON(ArtifactInvocationMetadata, payload)
 }
-func (w *SummaryWriter) WriteRedactedEffectiveConfig(payload RedactedSummaryPayload) error {
+func (w *SummaryWriter) WriteEffectiveConfig(payload EffectiveConfigWriter) error {
 	if payload == nil {
-		return fmt.Errorf("redacted summary payload must not be nil")
+		return fmt.Errorf("effective configuration writer must not be nil")
 	}
-	return w.writeJSON(ArtifactEffectiveConfig, payload.RedactedSummaryPayload())
+	var rendered bytes.Buffer
+	if err := payload.WriteEffective(&rendered); err != nil {
+		return fmt.Errorf("render effective configuration: %w", err)
+	}
+	return w.writeBytes(ArtifactEffectiveConfigYAML, rendered.Bytes())
 }
 func (w *SummaryWriter) WriteResolvedPipeline(payload RedactedResolvedPipelinePayload) error {
 	if payload == nil {

internal/core/fileio/fileio.go

@@ -2,7 +2,10 @@
 package fileio
 
 import (
+	"crypto/rand"
+	"encoding/hex"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"os"
 	"path"
@@ -92,6 +95,16 @@ func WriteJSON(root, name string, payload any, dirMode, fileMode os.FileMode) er
 	return WriteBytes(root, name, append(data, '\n'), dirMode, fileMode)
 }
 
+// WriteJSONWithProcessPermissions writes indented JSON beneath root using the
+// process and filesystem creation policy for new directories and files.
+func WriteJSONWithProcessPermissions(root, name string, payload any) error {
+	data, err := json.MarshalIndent(payload, "", "  ")
+	if err != nil {
+		return fmt.Errorf("marshal artifact %q: %w", name, err)
+	}
+	return WriteBytesWithProcessPermissions(root, name, append(data, '\n'))
+}
+
 func WriteBytes(root, name string, data []byte, dirMode, fileMode os.FileMode) error {
 	target, err := SafePath(root, name)
 	if err != nil {
@@ -109,6 +122,26 @@ func WriteBytes(root, name string, data []byte, dirMode, fileMode os.FileMode) e
 	return nil
 }
 
+// WriteBytesWithProcessPermissions atomically writes data beneath root while
+// allowing the process umask and filesystem default ACLs to select effective
+// permissions for newly created entries.
+func WriteBytesWithProcessPermissions(root, name string, data []byte) error {
+	target, err := SafePath(root, name)
+	if err != nil {
+		return err
+	}
+	if err := os.MkdirAll(filepath.Dir(target), 0o777); err != nil {
+		return fmt.Errorf("write artifact %q: %w", name, err)
+	}
+	if err := rejectSymlinkComponents(root, name); err != nil {
+		return err
+	}
+	if err := writeAtomicWithProcessPermissions(target, data); err != nil {
+		return fmt.Errorf("write artifact %q: %w", name, err)
+	}
+	return nil
+}
+
 func rejectSymlinkComponents(root, name string) error {
 	absRoot, err := filepath.Abs(root)
 	if err != nil {
@@ -163,3 +196,51 @@ func writeAtomic(target string, data []byte, fileMode os.FileMode) error {
 	keep = false
 	return nil
 }
+
+func writeAtomicWithProcessPermissions(target string, data []byte) error {
+	directory := filepath.Dir(target)
+	base := filepath.Base(target)
+	seen := make(map[string]struct{}, 32)
+	for attempt := 0; attempt < 32; attempt++ {
+		suffix := make([]byte, 16)
+		if _, err := rand.Read(suffix); err != nil {
+			return fmt.Errorf("generate temporary file name: %w", err)
+		}
+		temporaryPath := filepath.Join(directory, "."+base+".tmp-"+hex.EncodeToString(suffix))
+		if _, exists := seen[temporaryPath]; exists {
+			continue
+		}
+		seen[temporaryPath] = struct{}{}
+
+		temporary, err := os.OpenFile(temporaryPath, os.O_WRONLY|os.O_CREATE|os.O_EXCL, 0o666)
+		if errors.Is(err, os.ErrExist) {
+			continue
+		}
+		if err != nil {
+			return err
+		}
+		return writeAndPublish(temporary, temporaryPath, target, data)
+	}
+	return fmt.Errorf("create temporary file for %q: exhausted unique names", target)
+}
+
+func writeAndPublish(temporary *os.File, temporaryPath, target string, data []byte) error {
+	keep := true
+	defer func() {
+		if keep {
+			_ = os.Remove(temporaryPath)
+		}
+	}()
+	if _, err := temporary.Write(data); err != nil {
+		_ = temporary.Close()
+		return err
+	}
+	if err := temporary.Close(); err != nil {
+		return err
+	}
+	if err := os.Rename(temporaryPath, target); err != nil {
+		return err
+	}
+	keep = false
+	return nil
+}

internal/core/fileio/fileio_process_permissions_unix_test.go

@@ -0,0 +1,131 @@
+//go:build linux || darwin
+
+package fileio
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"syscall"
+	"testing"
+)
+
+func TestWriteBytesWithProcessPermissionsHonorsUmask(t *testing.T) {
+	for _, test := range []struct {
+		name     string
+		umask    int
+		dirMode  os.FileMode
+		fileMode os.FileMode
+	}{
+		{name: "private", umask: 0o077, dirMode: 0o700, fileMode: 0o600},
+		{name: "group", umask: 0o007, dirMode: 0o770, fileMode: 0o660},
+	} {
+		t.Run(test.name, func(t *testing.T) {
+			previousUmask := syscall.Umask(test.umask)
+			defer syscall.Umask(previousUmask)
+
+			root := filepath.Join(t.TempDir(), "cache")
+			if err := WriteBytesWithProcessPermissions(root, "nested/value", []byte("value")); err != nil {
+				t.Fatal(err)
+			}
+			for path, want := range map[string]os.FileMode{
+				root:                                   test.dirMode,
+				filepath.Join(root, "nested"):          test.dirMode,
+				filepath.Join(root, "nested", "value"): test.fileMode,
+			} {
+				assertPermissions(t, path, want)
+			}
+			assertNoTemporarySiblings(t, filepath.Join(root, "nested"))
+		})
+	}
+}
+
+func TestWriteBytesWithProcessPermissionsLeavesExistingRootUntouched(t *testing.T) {
+	previousUmask := syscall.Umask(0o077)
+	defer syscall.Umask(previousUmask)
+
+	root := filepath.Join(t.TempDir(), "cache")
+	syscall.Umask(0)
+	if err := os.Mkdir(root, 0o751); err != nil {
+		t.Fatal(err)
+	}
+	syscall.Umask(0o077)
+	if err := WriteBytesWithProcessPermissions(root, "nested/value", []byte("value")); err != nil {
+		t.Fatal(err)
+	}
+	assertPermissions(t, root, 0o751)
+}
+
+func TestWriteBytesWithProcessPermissionsReplacementUsesCurrentPolicy(t *testing.T) {
+	root := filepath.Join(t.TempDir(), "cache")
+	previousUmask := syscall.Umask(0o077)
+	defer syscall.Umask(previousUmask)
+	if err := WriteBytesWithProcessPermissions(root, "value", []byte("before")); err != nil {
+		t.Fatal(err)
+	}
+	before, err := os.Stat(filepath.Join(root, "value"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	syscall.Umask(0o007)
+	if err := WriteBytesWithProcessPermissions(root, "value", []byte("after")); err != nil {
+		t.Fatal(err)
+	}
+	after, err := os.Stat(filepath.Join(root, "value"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if before.Sys().(*syscall.Stat_t).Ino == after.Sys().(*syscall.Stat_t).Ino {
+		t.Fatal("replacement retained the old inode")
+	}
+	assertPermissions(t, filepath.Join(root, "value"), 0o660)
+	data, err := os.ReadFile(filepath.Join(root, "value"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(data) != "after" {
+		t.Fatalf("replacement content = %q, want %q", data, "after")
+	}
+}
+
+func TestWriteJSONWithProcessPermissionsFormatsJSON(t *testing.T) {
+	previousUmask := syscall.Umask(0o077)
+	defer syscall.Umask(previousUmask)
+
+	root := filepath.Join(t.TempDir(), "cache")
+	if err := WriteJSONWithProcessPermissions(root, "value.json", map[string]string{"value": "ok"}); err != nil {
+		t.Fatal(err)
+	}
+	data, err := os.ReadFile(filepath.Join(root, "value.json"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(data) != "{\n  \"value\": \"ok\"\n}\n" {
+		t.Fatalf("JSON = %q", data)
+	}
+}
+
+func assertPermissions(t *testing.T, path string, want os.FileMode) {
+	t.Helper()
+	info, err := os.Stat(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := info.Mode().Perm(); got != want {
+		t.Fatalf("%s mode = %#o, want %#o", path, got, want)
+	}
+}
+
+func assertNoTemporarySiblings(t *testing.T, directory string) {
+	t.Helper()
+	entries, err := os.ReadDir(directory)
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, entry := range entries {
+		if strings.Contains(entry.Name(), ".tmp-") {
+			t.Fatalf("temporary file remains: %s", entry.Name())
+		}
+	}
+}

internal/framework/checkpoint/filesystem_permissions_unix_test.go

@@ -0,0 +1,98 @@
+//go:build linux || darwin
+
+package checkpoint
+
+import (
+	"os"
+	"path/filepath"
+	"syscall"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+)
+
+func TestFilesystemCheckpointPermissionsFollowUmask(t *testing.T) {
+	for _, test := range []struct {
+		name     string
+		umask    int
+		dirMode  os.FileMode
+		fileMode os.FileMode
+	}{
+		{name: "private", umask: 0o077, dirMode: 0o700, fileMode: 0o600},
+		{name: "group", umask: 0o007, dirMode: 0o770, fileMode: 0o660},
+	} {
+		t.Run(test.name, func(t *testing.T) {
+			previousUmask := syscall.Umask(test.umask)
+			defer syscall.Umask(previousUmask)
+
+			root := filepath.Join(t.TempDir(), "checkpoints")
+			identity, err := NewIdentity(representativeIdentityInput())
+			if err != nil {
+				t.Fatal(err)
+			}
+			recorder, err := NewFilesystemRecorder(root, identity)
+			if err != nil {
+				t.Fatal(err)
+			}
+			if err := recorder.SourceSucceeded("source-module", sourceDocumentForPermissions()); err != nil {
+				t.Fatal(err)
+			}
+
+			relative, err := identity.RelativePath()
+			if err != nil {
+				t.Fatal(err)
+			}
+			identityRoot := filepath.Join(root, filepath.FromSlash(relative))
+			sourceRoot := filepath.Join(identityRoot, "source")
+			for path, want := range map[string]os.FileMode{
+				root:         test.dirMode,
+				identityRoot: test.dirMode,
+				sourceRoot:   test.dirMode,
+				filepath.Join(sourceRoot, "manifest.json"):        test.fileMode,
+				filepath.Join(sourceRoot, "source-document.json"): test.fileMode,
+			} {
+				assertCheckpointPermissions(t, path, want)
+			}
+		})
+	}
+}
+
+func TestFilesystemCheckpointLeavesExistingRootUntouched(t *testing.T) {
+	previousUmask := syscall.Umask(0o077)
+	defer syscall.Umask(previousUmask)
+
+	root := filepath.Join(t.TempDir(), "checkpoints")
+	syscall.Umask(0)
+	if err := os.Mkdir(root, 0o751); err != nil {
+		t.Fatal(err)
+	}
+	syscall.Umask(0o077)
+	identity, err := NewIdentity(representativeIdentityInput())
+	if err != nil {
+		t.Fatal(err)
+	}
+	recorder, err := NewFilesystemRecorder(root, identity)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := recorder.SourceSucceeded("source-module", sourceDocumentForPermissions()); err != nil {
+		t.Fatal(err)
+	}
+	assertCheckpointPermissions(t, root, 0o751)
+}
+
+func sourceDocumentForPermissions() *source.SourceDocument {
+	document := checkpointDocument()
+	return &document
+}
+
+func assertCheckpointPermissions(t *testing.T, path string, want os.FileMode) {
+	t.Helper()
+	info, err := os.Stat(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := info.Mode().Perm(); got != want {
+		t.Fatalf("%s mode = %#o, want %#o", path, got, want)
+	}
+}

internal/framework/checkpoint/filesystem_test.go

@@ -5,7 +5,6 @@ import (
 	"encoding/json"
 	"os"
 	"path/filepath"
-	"runtime"
 	"strings"
 	"testing"
 	"unicode/utf8"
@@ -106,27 +105,6 @@ func TestFilesystemCheckpointRoundTripsAllStages(t *testing.T) {
 		})
 	}
 
-	if runtime.GOOS != "windows" {
-		t.Run("restrictive permissions", func(t *testing.T) {
-			root := filepath.Join(fixture.root, mustRelativePath(t, fixture.identity))
-			err := filepath.Walk(root, func(path string, info os.FileInfo, err error) error {
-				if err != nil {
-					return err
-				}
-				want := os.FileMode(0o600)
-				if info.IsDir() {
-					want = 0o700
-				}
-				if got := info.Mode().Perm(); got != want {
-					t.Errorf("%s permissions = %o, want %o", path, got, want)
-				}
-				return nil
-			})
-			if err != nil {
-				t.Fatal(err)
-			}
-		})
-	}
 }
 
 func TestFilesystemCheckpointRejectsMissingAndCorruptState(t *testing.T) {