Consolidate the architecture plan into fewer packages

docs/policy/architecture.md

@@ -29,21 +29,25 @@ Source-format details belong in input modules. Transcript-specific concepts
 such as segments, speakers, timestamps, and transcript schemas must not spread
 into runner, extractor, or validator framework code.
 
-Extraction-domain details belong in process modules. D&D-specific concepts
+Extraction-domain details belong in extract modules. D&D-specific concepts
 such as spells, NPCs, items, combat turns, and encounters must not spread into
 core source, runner, or LLM framework packages.
 
 Extracted facts should be grounded with source references. Source references
 should point to generic source units, not to transcript-only structures.
+Artifact records should require source references by default unless their schema
+explicitly opts into ungrounded fields. Generic pipeline code should preserve
+source-reference ranges exactly and should not merge or rewrite overlapping
+ranges.
 
 The application workflow is:
 
 ```text
-input -> chunk -> process -> merge -> normalize -> output
+input -> chunk -> extract -> merge -> normalize -> output
 ```
 
 These stages should remain explicit in the architecture. Chunking, merging, and
-normalization must not be hidden inside domain process modules when they represent
+normalization must not be hidden inside domain extract modules when they represent
 general pipeline behavior.
 
 ## Dependency Policy
@@ -70,46 +74,38 @@ CLI and executable entrypoint:
 
 Core deterministic model and policy:
 
-- `internal/core/config`: configuration structs, defaults, loading, precedence, and validation.
 - `internal/core/source`: source document, source unit, and source reference types.
-- `internal/core/sourcechunking`: deterministic chunking of ordered source units.
 - `internal/core/artifacts`: artifact envelope, artifact candidates, rejected artifacts, and manifests.
-- `internal/core/diagnostics`: run directories and diagnostics artifact paths.
+- `internal/core/config`: configuration structs, defaults, loading, precedence, and validation, once config exists.
-- `internal/core/reporting`: process reports and report serialization.
-- `internal/core/inputcatalog`: known input adapter keys and metadata.
-- `internal/core/extractorcatalog`: known extractor keys and metadata.
 
 Reusable framework plumbing:
 
 - `internal/framework/contracts`: core interfaces and transport-neutral request/response contracts.
-- `internal/framework/runner`: orchestration across adapters, extractors, validators, and artifact output.
+- `internal/framework/pipeline`: runner, pipeline-stage orchestration, registries, and small shared stage helpers.
-- `internal/framework/pipeline`: shared pipeline-stage orchestration types, when needed.
+- `internal/framework/validate`: shared validator runtime behavior and decision checks.
-- `internal/framework/extraction`: shared extraction helper code.
+- `internal/framework/llm`: LLM clients, scheduling, structured-output parsing, and response-schema registry, once LLM runtime exists.
-- `internal/framework/merge`: shared merge-stage behavior.
+- `internal/framework/prompt`: embedded prompt assets, prompt registry, and prompt rendering helpers, once prompt assets exist.
-- `internal/framework/normalize`: shared normalization-stage behavior.
-- `internal/framework/output`: output encoding contracts and shared helpers.
-- `internal/framework/validators`: shared validator runtime behavior and decision checks.
-- `internal/framework/llm`: LLM runtime, scheduling, and provider adapters.
-- `internal/framework/responseschema`: embedded structured-output schema registry.
-- `internal/framework/structuredoutput`: structured-output parsing and malformed-response handling.
-- `internal/framework/promptcontext`: source-document prompt rendering helpers.
-- `internal/framework/warnings`: shared warning records.
 
 Domain implementations:
 
 - `internal/modules/input/<name>`: input-stage modules that parse external input into core source documents.
 - `internal/modules/chunk/<name>`: chunk-stage modules.
-- `internal/modules/process/<domain>/<name>`: process-stage extractor modules.
+- `internal/modules/extract/<domain>/<name>`: extract-stage extractor modules.
 - `internal/modules/merge/<name>` or `internal/modules/merge/<domain>/<name>`: merge-stage modules.
 - `internal/modules/normalize/<name>` or `internal/modules/normalize/<domain>/<name>`: normalize-stage modules.
 - `internal/modules/output/<name>`: output-stage modules.
 - `internal/validators/<validator>`: built-in validator implementations.
-- `internal/prompts`: embedded prompt assets and prompt metadata registry.
 - `internal/transport/http`: shared HTTP client code, if needed by provider integrations.
 
 Package-private implementation constants may live near the package that owns
 them, preferably in `constants.go` when useful.
 
+Start with fewer, larger framework packages. Split a package only when a real
+boundary proves itself through import direction, ownership, test seams, or
+substantial file size. Do not create catalog, diagnostics, reporting,
+structured-output, response-schema, output, merge, normalize, extraction, or
+warnings packages merely because the concepts exist in the architecture.
+
 ## Stage Modules
 
 Concrete business logic should live under `internal/modules/<stage>/...`.
@@ -120,7 +116,7 @@ workflow visible in the filesystem:
 ```text
 internal/modules/input/...
 internal/modules/chunk/...
-internal/modules/process/...
+internal/modules/extract/...
 internal/modules/merge/...
 internal/modules/normalize/...
 internal/modules/output/...
@@ -141,18 +137,22 @@ decisions.
 
 Other packages should interact with source input through adapter contracts and
 core source types. Input module implementation details and external dependency
-types must not leak into framework or process module packages.
+types must not leak into framework or extract module packages.
 
-Input module metadata may preserve source-specific facts such as transcript speaker,
+Input module metadata may preserve source-specific facts such as transcript
-timestamps, Markdown heading path, page number, or block ID. Framework code may
+speaker, timestamps, Markdown heading path, page number, or block ID. Framework
-carry metadata through, but should not require a specific adapter's metadata
+code may carry metadata through, but should not require a specific adapter's
-shape.
+metadata shape.
+
+Core source metadata should remain `map[string]any`. Document well-known keys
+as conventions, and let input modules expose typed accessor helpers for their
+own metadata when useful.
 
 ## Extractors
 
 Extractors are independent modules that process source chunks or whole source
 documents and produce one kind of structured artifact candidate.
-Each process module owns:
+Each extract module owns:
 
 - its artifact semantics;
 - its prompt usage;
@@ -160,9 +160,14 @@ Each process module owns:
 - its validator chain;
 - any domain-specific mapping or interpretation.
 
-Process modules should depend on framework contracts and core source/artifact
+Extract modules should depend on framework contracts and core source/artifact
 types. They should not depend on concrete input module packages.
 
+Extraction requests should carry the active source chunk plus optional ambient
+context, such as a document synopsis, prior-chunk summaries, known entities, or
+other module-provided state. The context may be empty for simple modules, but
+the contract should not assume extraction is always chunk-local.
+
 Extractors should not be the only place where chunking, merging, or
 normalization happens. They may choose processing mode or provide domain-specific
 merge/normalization behavior when generic behavior is insufficient, but the
@@ -181,7 +186,7 @@ The pipeline has six conceptual stages:
 
 1. input: external source material becomes a `SourceDocument`;
 2. chunk: a `SourceDocument` becomes ordered source chunks;
-3. process: extractors produce artifact candidates from chunks or whole documents;
+3. extract: extractors produce artifact candidates from chunks or whole documents;
 4. merge: per-chunk candidates become a merged candidate collection;
 5. normalize: merged candidates are reconciled for duplicates, aliases, consistency, or cross-chunk issues;
 6. output: final artifacts are serialized.
@@ -200,6 +205,15 @@ The framework should allow serial and parallel chunk processing. The first
 implementation may execute chunks serially for determinism, but contracts should
 not prevent later parallel execution.
 
+Final durable output should use one artifact file per artifact type plus a
+run-level manifest/index file. Framework artifact flow should use a generic
+envelope with `json.RawMessage` payloads; extract modules should own typed Go
+structs at their boundaries and encode into that generic envelope before
+returning to framework code.
+
+Schemas should be versioned per extractor, with a separate envelope/manifest
+format version.
+
 ## Validators
 
 Validators should be independently testable and composable.
@@ -209,7 +223,11 @@ present. Validator decision semantics should be explicit: each candidate
 artifact should receive exactly one decision from each validator that evaluates
 it.
 
-Shared validator runtime mechanics belong under `internal/framework/validators`.
+LLM-backed review belongs in module-owned validator chains, not in a separate
+global review phase. Extract modules and normalize modules may both use
+deterministic and LLM-backed validators.
+
+Shared validator runtime mechanics belong under `internal/framework/validate`.
 Concrete validator behavior belongs under `internal/validators/<validator>`.
 
 ## LLM Runtime
@@ -290,11 +308,17 @@ be opt-in.
 ## Testing
 
 Core logic should be testable without real external services. Use fakes,
-fixtures, or local test doubles for adapters, extractors, validators, and LLM
+fixtures, or local test doubles for input modules, extract modules, validators,
-clients where practical.
+and LLM clients where practical.
 
 Contract-first work should include fake implementations that prove interfaces
-compose before real adapters or extractors depend on them.
+compose before real input modules or extract modules depend on them.
+
+Once the pipeline-stage contracts exist, maintain a fixture-driven walking
+skeleton that exercises input, chunk, extract, merge, normalize, and output
+stages with fake modules and fake external clients. This test should protect
+stage composition continuously while real modules are introduced over later
+checkpoints.
 
 Config examples should be load-tested once config files exist. Important CLI
 workflows should have parser or command tests. Adapter, extractor, and validator
@@ -312,7 +336,7 @@ unit, source reference, input adapter, extractor, chunker, merger, normalizer,
 artifact, validator, and run manifest.
 
 Source-format details belong in input module or integration docs.
-Domain-specific extraction details belong in process module or artifact docs.
+Domain-specific extraction details belong in extract module or artifact docs.
 
 When changing architecture, config, CLI behavior, stage modules, extractor
 contracts, validator contracts, LLM runtime behavior, or artifact schemas, update

docs/roadmap/1-core-contracts-and-skeleton.md

@@ -26,7 +26,7 @@ In scope:
 Out of scope:
 
 - real input modules;
-- real process modules;
+- real extract modules;
 - LLM provider calls;
 - prompt or response-schema assets;
 - diagnostics run directory;
@@ -47,7 +47,7 @@ contract packages:
   structured LLM interfaces used by later checkpoints.
 
 The contracts should be proven with fake implementations in tests. Those tests
-should demonstrate composition without real input modules, real process modules,
+should demonstrate composition without real input modules, real extract modules,
 LLM provider calls, prompt assets, or diagnostics infrastructure.
 
 Implementation staging belongs in

docs/roadmap/2-framework-composition.md

@@ -27,7 +27,7 @@ Out of scope:
 
 - real input parsing;
 - real input modules;
-- real process modules;
+- real extract modules;
 - real LLM calls;
 - prompt assets;
 - response schema assets;
@@ -38,13 +38,11 @@ Out of scope:
 
 The repository should contain a minimal framework composition layer:
 
-- `internal/framework/inputregistry` registers and builds input adapter
+- `internal/framework/pipeline` registers and builds input adapter constructors
-  constructors by stable key.
+  and extractor constructors by stable key.
-- `internal/framework/extractorregistry` registers and builds extractor
+- `internal/framework/validate` provides shared validator decision helpers and
-  constructors by stable key.
-- `internal/framework/validators` provides shared validator decision helpers and
   cardinality checks.
-- `internal/framework/runner` executes configured extractors against a
+- `internal/framework/pipeline` executes configured extractors against a
   `SourceDocument`, applies validator chains, and returns approved and rejected
   artifacts.
 
@@ -60,7 +58,7 @@ Implementation staging belongs in
 - `go test ./...` passes.
 - Fake adapter/extractor/validator registrations work in tests.
 - The runner operates on `SourceDocument`, not transcript-specific structures.
-- The runner does not import concrete D&D process module packages.
+- The runner does not import concrete D&D extract module packages.
 
 ## Review Questions
 

docs/roadmap/3-pipeline-stages-chunking-merge-normalize.md

@@ -7,18 +7,20 @@ This document describes planned work, not implemented behavior.
 ## Goal
 
 Make Notarius's application workflow first-class before adding real input
-modules or process modules.
+modules or extract modules.
 
 The workflow should be:
 
 ```text
-input -> chunk -> process -> merge -> normalize -> output
+input -> chunk -> extract -> merge -> normalize -> output
 ```
 
 Checkpoint 3 should define the contracts and minimal fake-tested framework
-behavior for chunking, per-chunk processing, merging, and normalization. It
+behavior for chunking, per-chunk extraction, merging, and normalization. It
-should not add real input modules, real domain process modules, LLM provider code,
+should also introduce a fixture-driven walking skeleton that exercises the full
-or output encoders.
+stage sequence with fake modules and a fake LLM client. It should not add real
+input modules, real domain extract modules, LLM provider code, or production
+output modules.
 
 ## Scope
 
@@ -26,13 +28,16 @@ In scope:
 
 - source chunk model;
 - chunker contract;
-- process-stage contract for extractors operating on chunks;
+- extract-stage contract for extractors operating on chunks;
 - merge-stage contract;
 - normalize-stage contract;
-- output-stage contract shape, if useful for pipeline completeness;
+- output-stage contract and fake output encoder for pipeline completeness;
 - runner/pipeline updates that exercise these stages with fake components;
 - generic append/chronological merge behavior for artifact candidates when
-  appropriate.
+  appropriate;
+- fixture-driven walking skeleton test for
+  `input -> chunk -> extract -> merge -> normalize -> output`;
+- fake `StructuredLLMClient` wired through a trivial extractor.
 
 Out of scope:
 
@@ -42,7 +47,8 @@ Out of scope:
 - prompt assets;
 - response schema assets;
 - diagnostics run directory;
-- production output serialization.
+- real CLI command behavior;
+- production output serialization or durable output writing.
 
 ## Target End State
 
@@ -50,15 +56,26 @@ The repository should contain explicit pipeline-stage contracts:
 
 - `InputAdapter`: external source input to `SourceDocument`.
 - `Chunker`: `SourceDocument` to ordered `SourceChunk` values.
-- `Extractor` or processor: `SourceChunk` to artifact candidates.
+- `Extractor`: `SourceChunk` to artifact candidates.
 - `Merger`: per-chunk candidates to merged candidates.
 - `Normalizer`: merged candidates to normalized candidates.
-- `OutputEncoder`: final artifact bundle to bytes, if introduced in this
+- `OutputEncoder`: final artifact bundle to bytes.
-  checkpoint.
 
-The runner should orchestrate fake implementations through chunk, process,
+The runner should orchestrate fake implementations through chunk, extract,
 merge, normalize, and approval/validation behavior in tests.
 
+The checkpoint should include one fixture-driven integration test that starts
+from fixture input bytes and ends at encoded output bytes. The fixture should
+use a fake input adapter, deterministic chunker, trivial extractor, fake
+structured LLM client, generic merger, no-op normalizer, and fake or minimal
+JSON output encoder. This is a contract exercise, not a useful user-facing
+workflow.
+
+The walking skeleton should live in `internal/framework/pipeline`, with
+fixtures under that package's `testdata/`. If the CLI has an extract command by
+then, the same fixture may also be exercised through CLI wiring; if not, CLI
+coverage remains deferred.
+
 ## Design Intent
 
 Chunking is a core application concern because many source documents, especially
@@ -109,21 +126,43 @@ Domain-specific normalizers may later:
 - enforce chronological or source-reference consistency;
 - attach normalization warnings.
 
+## Walking Skeleton Fixture
+
+The fixture-driven skeleton should prove the staged architecture continuously as
+new contracts are added. It should be deliberately small:
+
+- a fixture source document or raw source input with two or three source units;
+- a fake input adapter that parses the fixture into `SourceDocument`;
+- a deterministic chunker that produces multiple chunks;
+- a trivial extractor that calls the fake structured LLM client and emits one
+  artifact candidate per chunk;
+- a generic append-in-chunk-order merger;
+- a no-op normalizer;
+- a fake or minimal JSON output encoder;
+- an expected output fixture checked byte-for-byte or by unmarshaled structural
+  equality.
+
+The fake LLM client should be part of the test setup so the contract is
+exercised without introducing provider code, prompt assets, or response schema
+assets.
+
 ## Done Criteria
 
 - `go test ./...` passes.
 - Pipeline-stage contracts are explicit and source/domain agnostic.
-- Fake tests prove input source documents can be chunked, processed, merged, and
+- Fake tests prove input source documents can be chunked, extracted, merged, and
   normalized.
+- A fixture-driven walking skeleton proves fake input, chunk, extract, merge,
+  normalize, and output modules compose end to end with a fake LLM client.
 - Merge and normalize are distinct concepts in code and tests.
 - The runner no longer implies whole-document-only extraction as the core
   application model.
-- No concrete input module, process module, LLM provider, prompt, response schema,
+- No concrete input module, domain extract module, LLM provider, prompt,
-  diagnostics, config, or D&D artifact code is added.
+  response schema, diagnostics, config, or D&D artifact code is added.
 
 ## Review Questions
 
-- Is the workflow clearly represented as input, chunk, process, merge,
+- Is the workflow clearly represented as input, chunk, extract, merge,
   normalize, and output?
 - Are merge and normalize cleanly separated?
 - Can a generic merger handle simple chronological artifact streams?

docs/roadmap/6-dnd-spells-extractor.md

@@ -6,7 +6,7 @@ This document describes planned work, not implemented behavior.
 
 ## Goal
 
-Implement the first useful process-stage module: D&D spell casts from a
+Implement the first useful extract-stage module: D&D spell casts from a
 Seriatim transcript source document.
 
 This checkpoint should produce the first meaningful vertical slice from real
@@ -19,7 +19,7 @@ In scope:
 - D&D spell artifact schema and Go structs;
 - structured response schema asset;
 - prompt assets;
-- `internal/modules/process/dnd/spells`;
+- `internal/modules/extract/dnd/spells`;
 - source-reference and schema validators in the extractor chain;
 - fake LLM tests;
 - CLI-level integration test if the CLI path is ready.
@@ -50,7 +50,7 @@ type SpellCast struct {
 }
 ```
 
-Keep this schema inside the D&D spells process module or a D&D artifact package,
+Keep this schema inside the D&D spells extract module or a D&D artifact package,
 not inside core framework packages.
 
 ### Stage 2: Structured Response Schema
@@ -76,7 +76,7 @@ Prompts should:
 
 ### Stage 4: Process Module Implementation
 
-Implement `internal/modules/process/dnd/spells`.
+Implement `internal/modules/extract/dnd/spells`.
 
 The extractor should:
 
@@ -117,13 +117,13 @@ The test should use fake LLM wiring and fixture input.
 - `go test ./...` passes.
 - Seriatim input can flow through the runner into the D&D spells extractor.
 - Spell artifacts include valid source references.
-- D&D concepts are contained in process module/artifact packages and docs.
+- D&D concepts are contained in extract module/artifact packages and docs.
 - The first meaningful vertical slice is available through tests, and through
   CLI if the CLI path is ready.
 
 ## Review Questions
 
-- Is the spell process module domain-specific without making the framework
+- Is the spell extract module domain-specific without making the framework
   D&D-specific?
 - Are source references valid and useful for downstream validation?
 - Is prompt/schema ownership clear?

docs/roadmap/documentation.md

@@ -11,7 +11,7 @@ not describe implemented behavior.
 Notarius documentation should make three boundaries obvious:
 
 - source-format support belongs to input-stage modules;
-- extraction-domain behavior belongs to process-stage modules;
+- extraction-domain behavior belongs to extract-stage modules;
 - core framework behavior is source-agnostic and domain-agnostic.
 
 Documentation should avoid making the MVP look more transcript-specific or
@@ -47,7 +47,7 @@ Core docs should avoid transcript-specific terms such as segment, speaker,
 timestamp, and transcript range unless discussing an input adapter or an example.
 
 Core docs should avoid D&D-specific terms such as spell, NPC, item, combat, and
-encounter unless discussing process modules, artifact docs, or examples.
+encounter unless discussing extract modules, artifact docs, or examples.
 
 ### Input Module Docs Own Source Formats
 
@@ -95,12 +95,12 @@ Stage module docs should cover:
 - prompt and response-schema ownership;
 - examples.
 
-D&D concepts should be documented in D&D process-module or artifact docs, not in
+D&D concepts should be documented in D&D extract-module or artifact docs, not in
 generic runner or framework docs.
 
 ### CLI Docs Should Reflect Extensibility
 
-The CLI reference should present input modules, chunk modules, process modules,
+The CLI reference should present input modules, chunk modules, extract modules,
 merge modules, normalize modules, and output modules as selectable or
 configurable components as they become user-facing.
 
@@ -114,7 +114,7 @@ Once implemented, `docs/cli.md` should document:
 
 - positional source input path;
 - input module selection;
-- process module selection;
+- extract module selection;
 - chunk/merge/normalize/output selection when configurable;
 - config path behavior;
 - output path behavior;
@@ -127,7 +127,7 @@ Once implemented, `docs/cli.md` should document:
 
 - input module selection and module-specific options;
 - chunk module selection and module-specific options;
-- process module selection and module-specific options;
+- extract module selection and module-specific options;
 - merge module selection and module-specific options;
 - normalize module selection and module-specific options;
 - output module selection and module-specific options;
@@ -176,7 +176,7 @@ Before merging docs, check:
 
 - Does the document describe implemented behavior outside `docs/roadmap/`?
 - Are source-format details isolated to input module or integration docs?
-- Are D&D details isolated to process module or artifact docs?
+- Are D&D details isolated to extract module or artifact docs?
 - Is there one canonical home for the topic?
 - Do command examples match implemented CLI syntax?
 - Are examples valid, maintained, and free of secrets?

docs/roadmap/implementation.md

@@ -7,7 +7,7 @@ This is a staged implementation plan for
 an LLM coding agent to follow stage by stage.
 
 This plan implements only checkpoint 2. Do not implement real input modules,
-real process modules, source chunking, LLM provider clients, prompt assets,
+real extract modules, source chunking, LLM provider clients, prompt assets,
 response schema registries, diagnostics run directories, production config
 loading, or D&D artifact schemas in this pass.
 
@@ -22,7 +22,7 @@ Required boundaries:
 
 - framework packages must stay source-agnostic and domain-agnostic;
 - input adapter registry code must not import concrete input module packages;
-- extractor registry and runner code must not import concrete process module
+- extractor registry and runner code must not import concrete extract module
   packages;
 - runner code should operate on `SourceDocument`, not transcript-specific
   structures;
@@ -64,26 +64,26 @@ Add a constructor-based registry for `contracts.InputAdapter`.
 
 ### Files To Add
 
-- `internal/framework/inputregistry/registry.go`
+- `internal/framework/pipeline/input_registry.go`
-- `internal/framework/inputregistry/registry_test.go`
+- `internal/framework/pipeline/input_registry_test.go`
 
 ### Required API
 
-Create package `inputregistry`.
+Extend package `pipeline`.
 
 Define:
 
 ```go
-type Constructor func() (contracts.InputAdapter, error)
+type InputAdapterConstructor func() (contracts.InputAdapter, error)
 
-type Registry struct {
+type InputAdapterRegistry struct {
     // unexported fields
 }
 
-func New() *Registry
+func NewInputAdapterRegistry() *InputAdapterRegistry
-func (r *Registry) Register(key string, constructor Constructor) error
+func (r *InputAdapterRegistry) Register(key string, constructor InputAdapterConstructor) error
-func (r *Registry) Build(key string) (contracts.InputAdapter, error)
+func (r *InputAdapterRegistry) Build(key string) (contracts.InputAdapter, error)
-func (r *Registry) RegisteredKeys() []string
+func (r *InputAdapterRegistry) RegisteredKeys() []string
 ```
 
 ### Required Behavior
@@ -137,8 +137,8 @@ Use fake adapters only. Do not add concrete input module packages.
 Run:
 
 ```sh
-gofmt -w internal/framework/inputregistry
+gofmt -w internal/framework/pipeline
-go test ./internal/framework/inputregistry
+go test ./internal/framework/pipeline
 go test ./...
 ```
 
@@ -150,31 +150,31 @@ Add a constructor-based registry for `contracts.Extractor`.
 
 ### Files To Add
 
-- `internal/framework/extractorregistry/registry.go`
+- `internal/framework/pipeline/extractor_registry.go`
-- `internal/framework/extractorregistry/registry_test.go`
+- `internal/framework/pipeline/extractor_registry_test.go`
 
 ### Required API
 
-Create package `extractorregistry`.
+Extend package `pipeline`.
 
 Define:
 
 ```go
-type Constructor func() (contracts.Extractor, error)
+type ExtractorConstructor func() (contracts.Extractor, error)
 
-type Registry struct {
+type ExtractorRegistry struct {
     // unexported fields
 }
 
-func New() *Registry
+func NewExtractorRegistry() *ExtractorRegistry
-func (r *Registry) Register(key string, constructor Constructor) error
+func (r *ExtractorRegistry) Register(key string, constructor ExtractorConstructor) error
-func (r *Registry) Build(key string) (contracts.Extractor, error)
+func (r *ExtractorRegistry) Build(key string) (contracts.Extractor, error)
-func (r *Registry) RegisteredKeys() []string
+func (r *ExtractorRegistry) RegisteredKeys() []string
 ```
 
 ### Required Behavior
 
-Mirror `inputregistry` behavior, but for `contracts.Extractor`.
+Mirror input adapter registry behavior, but for `contracts.Extractor`.
 
 `Build` must reject extractors whose `Key()` does not match the normalized key.
 It should not validate artifact type, schema version, or validator chain. Those
@@ -196,15 +196,15 @@ Cover the same cases as the input adapter registry:
 - sorted `RegisteredKeys`;
 - nil registry behavior.
 
-Use fake extractors only. Do not add concrete process module packages.
+Use fake extractors only. Do not add concrete extract module packages.
 
 ### Validation
 
 Run:
 
 ```sh
-gofmt -w internal/framework/extractorregistry
+gofmt -w internal/framework/pipeline
-go test ./internal/framework/extractorregistry
+go test ./internal/framework/pipeline
 go test ./...
 ```
 
@@ -216,12 +216,12 @@ Add shared validator decision helpers and decision-cardinality enforcement.
 
 ### Files To Add
 
-- `internal/framework/validators/validators.go`
+- `internal/framework/validate/validate.go`
-- `internal/framework/validators/validators_test.go`
+- `internal/framework/validate/validate_test.go`
 
 ### Required API
 
-Create package `validators`.
+Create package `validate`.
 
 Define reason constants:
 
@@ -236,7 +236,7 @@ Define helpers:
 ```go
 func Approved(candidateIndex int) contracts.ValidationDecision
 func Rejected(candidateIndex int, reasonCode string, message string) contracts.ValidationDecision
-func EnforceDecisionCardinality(candidates []artifacts.Candidate, decisions []contracts.ValidationDecision) error
+func EnforceDecisionCardinality(candidates []artifacts.ArtifactCandidate, decisions []contracts.ValidationDecision) error
 ```
 
 ### Required Behavior
@@ -264,8 +264,8 @@ func EnforceDecisionCardinality(candidates []artifacts.Candidate, decisions []co
 - work with candidate indices, not slice positions;
 - allow an empty candidate slice only when decisions are also empty.
 
-Candidate indices are expected to be unique by the time validators run. If the
+Artifact candidate indices are expected to be unique by the time validators run.
-candidate slice itself contains duplicate indices, return an error.
+If the candidate slice itself contains duplicate indices, return an error.
 
 ### Required Tests
 
@@ -285,8 +285,8 @@ Cover:
 Run:
 
 ```sh
-gofmt -w internal/framework/validators
+gofmt -w internal/framework/validate
-go test ./internal/framework/validators
+go test ./internal/framework/validate
 go test ./...
 ```
 
@@ -294,17 +294,17 @@ go test ./...
 
 ### Goal
 
-Add runner package types and constructor without implementing the full run loop
+Add pipeline runner types and constructor without implementing the full run loop
 yet.
 
 ### Files To Add
 
-- `internal/framework/runner/runner.go`
+- `internal/framework/pipeline/runner.go`
-- `internal/framework/runner/runner_test.go`
+- `internal/framework/pipeline/runner_test.go`
 
 ### Required API
 
-Create package `runner`.
+Create or extend package `pipeline`.
 
 Define:
 
@@ -364,8 +364,8 @@ assertions. Runner should depend only on framework contracts and core packages.
 Run:
 
 ```sh
-gofmt -w internal/framework/runner
+gofmt -w internal/framework/pipeline
-go test ./internal/framework/runner
+go test ./internal/framework/pipeline
 go test ./...
 ```
 
@@ -378,8 +378,8 @@ artifacts.
 
 ### Files To Update
 
-- `internal/framework/runner/runner.go`
+- `internal/framework/pipeline/runner.go`
-- `internal/framework/runner/runner_test.go`
+- `internal/framework/pipeline/runner_test.go`
 
 ### Required API
 
@@ -396,7 +396,7 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error)
 1. reject nil runner or nil extractor factory;
 2. validate `input.Source` with `source.ValidateDocument`;
 3. reject an empty `ExtractorKeys` list;
-4. process extractor keys in input order;
+4. iterate extractor keys in input order;
 5. build each extractor through the factory;
 6. call `Extractor.Extract` with the source, LLM client, and metadata;
 7. append extractor warnings to `RunOutput.Warnings`;
@@ -406,9 +406,9 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error)
 11. reject candidates denied by validators;
 12. return approved/rejected artifacts in deterministic order.
 
-Candidate normalization must:
+Artifact candidate normalization must:
 
-- assign `Candidate.Index` using a global monotonically increasing counter;
+- assign `ArtifactCandidate.Index` using a global monotonically increasing counter;
 - fill empty `ExtractorKey`, `ArtifactType`, and `SchemaVersion` from the
   owning extractor;
 - return an error if a candidate's non-empty `ExtractorKey` differs from
@@ -423,7 +423,7 @@ Validation behavior:
 - if an extractor has no validators, all normalized candidates are approved;
 - each validator receives only currently eligible candidates;
 - each validator result must have `ValidatorName == Validator.Name()`;
-- call `validators.EnforceDecisionCardinality` for every validator result;
+- call `validate.EnforceDecisionCardinality` for every validator result;
 - approved decisions keep candidates eligible for the next validator;
 - rejected decisions create `artifacts.RejectedArtifact` records using the
   candidate, validator name, reason code, and message;
@@ -469,8 +469,8 @@ Use fake extractors, validators, and factories only.
 Run:
 
 ```sh
-gofmt -w internal/framework/runner
+gofmt -w internal/framework/pipeline
-go test ./internal/framework/runner
+go test ./internal/framework/pipeline
 go test ./...
 ```
 
@@ -478,16 +478,16 @@ go test ./...
 
 ### Goal
 
-Prove the extractor registry and runner compose without adding real process
+Prove the extractor registry and runner compose without adding real extract
 modules.
 
 ### Files To Add
 
-- `internal/framework/runner/registry_integration_test.go`
+- `internal/framework/pipeline/registry_integration_test.go`
 
 ### Required Test Scenario
 
-Use `extractorregistry.New()` to register two fake extractor constructors.
+Use `NewExtractorRegistry()` to register two fake extractor constructors.
 
 Run the runner with:
 
@@ -502,15 +502,15 @@ Assertions:
 - extractor execution follows configured key order;
 - approved artifacts are in deterministic order;
 - rejected artifacts are in deterministic order;
-- no concrete input module or process module packages are imported.
+- no concrete input module or extract module packages are imported.
 
 ### Validation
 
 Run:
 
 ```sh
-gofmt -w internal/framework/runner
+gofmt -w internal/framework/pipeline
-go test ./internal/framework/runner
+go test ./internal/framework/pipeline
 go test ./...
 go build ./cmd/notarius
 ```
@@ -528,7 +528,7 @@ Check:
 
 - no package names mention transcripts, Seriatim, D&D, spells, NPCs, items, or
   combat;
-- no concrete input module or process module package exists;
+- no concrete input module or extract module package exists;
 - no LLM provider code exists;
 - no prompt, response schema, diagnostics, config, or source chunking package
   was added;

docs/roadmap/initial-architecture.md

@@ -14,18 +14,18 @@ The first MVP should target audio transcripts generated by Seriatim. That
 choice should be implemented as an input-stage module, not as a
 transcript-specific assumption in the application core. Later input sources,
 such as unstructured Markdown notes or Obsidian documents, should be addable
-through new input and process modules without reshaping the framework.
+through new input and extract modules without reshaping the framework.
 
 The first extraction domain should be D&D session analysis, starting with spell
-casts. That domain should live in process-stage modules and related schemas, not
+casts. That domain should live in extract-stage modules and related schemas, not
 in core framework packages.
 
 The application should follow the same broad architecture as Audita:
 
-- deterministic core packages for config, source documents, artifacts, diagnostics, and reporting;
+- deterministic core packages for source documents, artifacts, and configuration once needed;
 - input-stage modules that translate external source formats into a small internal source model;
 - reusable framework packages for contracts, orchestration, LLM runtime, structured output, and validation;
-- independent process-stage modules that own domain-specific behavior;
+- independent extract-stage modules that own domain-specific behavior;
 - independent validator packages;
 - embedded prompt and JSON schema assets;
 - CLI orchestration that wires the pieces together without owning domain logic.
@@ -37,7 +37,7 @@ artifacts rather than proposing and applying transcript corrections.
 
 - Keep the core input model generic: ordered text units plus metadata.
 - Keep source-format details in hexagonal input modules.
-- Keep extraction-domain details in process modules.
+- Keep extraction-domain details in extract modules.
 - Treat evidence as source references, not transcript references.
 - Prefer narrow, useful abstractions over a universal document model.
 - Preserve enough provenance for validation, replay, and downstream inspection.
@@ -48,28 +48,14 @@ artifacts rather than proposing and applying transcript corrections.
 cmd/notarius
 internal/cli
 
-internal/core/config
 internal/core/source
-internal/core/sourcechunking
 internal/core/artifacts
-internal/core/diagnostics
-internal/core/reporting
-internal/core/extractorcatalog
-internal/core/inputcatalog
 
 internal/framework/contracts
-internal/framework/extraction
-internal/framework/runner
 internal/framework/pipeline
-internal/framework/merge
+internal/framework/validate
-internal/framework/normalize
-internal/framework/output
-internal/framework/validators
 internal/framework/llm
-internal/framework/responseschema
+internal/framework/prompt
-internal/framework/structuredoutput
-internal/framework/promptcontext
-internal/framework/warnings
 
 internal/modules/input/seriatim
 internal/modules/input/markdown
@@ -77,10 +63,10 @@ internal/modules/input/markdown
 internal/modules/chunk/generic
 internal/modules/chunk/dndtranscript
 
-internal/modules/process/dnd/spells
+internal/modules/extract/dnd/spells
-internal/modules/process/dnd/items
+internal/modules/extract/dnd/items
-internal/modules/process/dnd/npcs
+internal/modules/extract/dnd/npcs
-internal/modules/process/dnd/combat
+internal/modules/extract/dnd/combat
 
 internal/modules/merge/appendorder
 internal/modules/merge/dnd/spells
@@ -95,7 +81,6 @@ internal/validators/schema_validity
 internal/validators/domain_consistency
 internal/validators/llm_review
 
-internal/prompts
 examples
 docs/internal
 ```
@@ -104,6 +89,15 @@ The `markdown` input module and D&D-specific chunk, merge, normalize, and
 output modules are listed as likely future packages. The MVP should implement
 only the stage modules needed by the checkpoint sequence.
 
+`internal/core/config` should be added when production configuration exists.
+
+The framework package list is intentionally consolidated. `pipeline` should own
+runner orchestration, stage registries, and small merge/normalize/output helpers
+until those boundaries prove they need separate packages. `llm` should own
+structured output and response-schema mechanics until those concerns become too
+large or import-heavy. `prompt` should own prompt assets and rendering helpers
+once prompt assets exist.
+
 ## Core Concepts
 
 ### SourceDocument
@@ -138,6 +132,13 @@ Initial source-unit assumptions:
 - adapter-specific metadata may carry speaker, timestamps, heading paths, page
   numbers, or other source details.
 
+Core source metadata should remain `map[string]any`. Notarius should not define
+a universal document model. Instead, the project should document well-known
+metadata keys, such as `speaker`, `start`, `end`, and `heading_path`, as
+conventions. Input modules may export typed accessor helpers for their own
+metadata, such as `seriatim.SpeakerOf(unit)`, without leaking those helpers into
+core framework contracts.
+
 ### Input Module / Adapter Contract
 
 Hexagonal boundary for external source formats.
@@ -183,6 +184,11 @@ Initial source-reference validation should require:
 Transcript-oriented output can still present these as transcript segment ranges
 when the adapter metadata makes that interpretation available.
 
+Source references should preserve the exact ranges produced by extractors and
+validators. Overlapping ranges should not be merged or rewritten by generic
+pipeline code. If a domain module wants a derived compact range later, that
+should be additional output, not a replacement for the original evidence.
+
 ### Extractor
 
 Reusable module contract for producing one artifact type.
@@ -193,7 +199,7 @@ type Extractor interface {
     ArtifactType() string
     SchemaVersion() string
     Validators() []Validator
-    Process(ctx context.Context, req ProcessRequest) (ProcessResult, error)
+    Extract(ctx context.Context, req ExtractionRequest) (ExtractionResult, error)
 }
 ```
 
@@ -201,9 +207,16 @@ An extractor should receive either a whole source document or a source chunk,
 depending on processing mode. It should return typed artifact candidates plus
 warnings. It should not mutate the source document.
 
-Process modules own domain concepts. For example, D&D spell extraction should
+`ExtractionRequest` should be designed now to carry both the active chunk and
-live under `internal/modules/process/dnd/spells`; a future to-do extractor for
+optional ambient context, even if the MVP leaves that context empty. Useful
-notes should live under a different process-module path and use the same
+ambient context may include a document synopsis, prior-chunk summaries, known
+entities, or other module-provided state. D&D spell extraction can likely work
+per chunk, but combat, NPC, and identity-oriented extraction will need broader
+context. Adding the field later would force churn across every extractor.
+
+Extract modules own domain concepts. For example, D&D spell extraction should
+live under `internal/modules/extract/dnd/spells`; a future to-do extractor for
+notes should live under a different extract-module path and use the same
 framework contract.
 
 ### Chunker
@@ -247,14 +260,41 @@ Validators should cover:
 Validator output should follow Audita's decision-cardinality model: each
 candidate artifact receives exactly one decision per validator.
 
+LLM-backed review should be modeled as part of a module's validator chain, not
+as a separate global review phase. Extract modules should be able to attach one
+or more deterministic or LLM-backed validators. Normalize-stage modules may also
+run validator chains, including LLM-backed validators, when semantic
+reconciliation needs review.
+
 ### Artifact
 
 Final approved JSON output from one or more extractors.
 
 Artifacts should preserve enough metadata to support downstream validation,
-debugging, and replay. The exact top-level envelope is still open, but should
+debugging, and replay.
-include artifact type, schema version, extracted records, source references, and
+
-run manifest data.
+The pipeline should carry artifact candidates through a generic envelope with a
+`json.RawMessage` payload. Extract modules should own typed Go structs at their
+module boundary, then encode those typed records into the generic artifact
+candidate envelope before returning to framework code. This keeps stage
+contracts simple and avoids generic type plumbing across unrelated artifact
+families.
+
+Final durable output should be one file per artifact type plus a run-level
+manifest/index file. This supports partial success and lets downstream consumers
+read only the artifact types they need. Each artifact file should include its
+artifact type, extractor key, extractor schema version, envelope format version,
+records, source references, and enough provenance to connect it to the run
+manifest.
+
+Every artifact record should require source references unless that artifact
+schema explicitly opts into ungrounded fields. Artifact-level metadata, counts,
+run information, and other derived summary fields are exempt from the per-record
+grounding rule.
+
+Schemas should be versioned per extractor, with a separate envelope/manifest
+format version. A single global schema version would couple unrelated extractor
+release cadence.
 
 ### RunManifest
 
@@ -262,9 +302,14 @@ Per-run provenance record.
 
 ```go
 type RunManifest struct {
-    InputAdapter     string   `json:"input_adapter"`
+    EnvelopeVersion  string   `json:"envelope_version"`
+    InputModule      string   `json:"input_module"`
+    Chunker          string   `json:"chunker"`
     SourceDigests    []string `json:"source_digests"`
     Extractors       []string `json:"extractors"`
+    Merger           string   `json:"merger"`
+    Normalizer       string   `json:"normalizer"`
+    OutputEncoder    string   `json:"output_encoder"`
     SchemaVersion    string   `json:"schema_version"`
     ValidationStatus string   `json:"validation_status"`
 }
@@ -345,7 +390,7 @@ The architecture should support extractors outside the D&D domain. Examples:
 - decisions and action items from meeting transcripts;
 - named people, places, and dates from research notes.
 
-These should be addable as process modules without changing runner,
+These should be addable as extract modules without changing runner,
 validator, source-reference, or LLM framework contracts.
 
 ## Proposed Pipeline Flow
@@ -353,7 +398,7 @@ validator, source-reference, or LLM framework contracts.
 The application workflow should be first-class:
 
 ```text
-input -> chunk -> process -> merge -> normalize -> output
+input -> chunk -> extract -> merge -> normalize -> output
 ```
 
 Proposed runner flow:
@@ -367,7 +412,7 @@ Proposed runner flow:
 7. Resolve the configured chunker.
 8. Chunk source units into deterministic source chunks.
 9. Resolve configured extractor instances through a registry.
-10. Process chunks in extractor-defined mode.
+10. Extract from chunks in extractor-defined mode.
 11. Merge per-chunk artifact candidates deterministically.
 12. Normalize merged artifact candidates.
 13. Run deterministic validators before LLM-backed validators.
@@ -397,6 +442,11 @@ Reuse these architectural patterns:
 - validator decision cardinality and deterministic validator ordering;
 - CLI tests and fixture-driven integration tests.
 
+The fixture-driven integration-test pattern should begin at checkpoint 3 with a
+walking skeleton over fake modules and a fake LLM client. Later checkpoints
+should replace fake pieces with real Seriatim, runtime, and D&D modules without
+losing that end-to-end contract coverage.
+
 Avoid copying these Audita concepts directly:
 
 - transcript-specific core types;
@@ -422,32 +472,47 @@ compiling and targeted tests covering the newly introduced contracts or behavior
 5. [Seriatim Input Module](5-seriatim-input-module.md)
 6. [D&D Spells Extractor](6-dnd-spells-extractor.md)
 
-The first useful vertical slice should arrive at checkpoint 6: Seriatim
+The first contract-level walking skeleton should arrive at checkpoint 3: fixture
-transcript input to validated D&D spell artifact output. Earlier checkpoints are
+input through fake input, chunk, extract, merge, normalize, and output modules
-intentionally contract-first and may not produce useful user output yet.
+with a fake LLM client. The first useful vertical slice should arrive at
+checkpoint 6: Seriatim transcript input to validated D&D spell artifact output.
+Earlier checkpoints remain contract-first and may not produce useful user output
+yet.
+
+## Architecture Decisions
+
+- Final durable output should use one artifact file per artifact type plus a
+  run-level manifest/index file.
+- Framework artifact flow should use a generic envelope with `json.RawMessage`
+  payloads. Extract modules should use typed Go structs at their own boundaries.
+- Schemas should be versioned per extractor, with a separate envelope/manifest
+  format version.
+- Artifact records should require source references by default. Individual
+  schemas may explicitly opt into ungrounded fields. Artifact-level metadata is
+  exempt.
+- Source-reference ranges should be preserved exactly. Generic pipeline code
+  should not merge or rewrite overlapping ranges.
+- `ExtractionRequest` should carry the active chunk plus optional ambient
+  context for document synopsis, prior-chunk summaries, known entities, or
+  similar module-provided state.
+- LLM-backed review should be part of module-owned validator chains. Extract
+  modules and normalize modules may both use deterministic and LLM-backed
+  validators.
+- The Seriatim MVP should support only the minimal Seriatim schema. Broader
+  Seriatim schema support should be added later without changing core source
+  contracts.
+- Core source metadata should remain `map[string]any`. Well-known metadata keys
+  should be documented as conventions, and input modules may expose typed
+  accessor helpers for their own metadata.
 
 ## Open Design Questions
 
-- Should final output be one combined artifact envelope or one file per
+- Which artifact types should use generic append-in-chunk-order merge, and which
-  extractor?
+  should use domain-specific merge?
-- Should extractor output use typed Go structs per artifact or a generic
-  artifact record with `json.RawMessage` payloads?
-- Should schemas be versioned per extractor, globally, or both?
-- Should every record require source references, or should some top-level
-  artifact metadata be allowed without source references?
-- Should overlapping source-reference ranges be merged, preserved exactly, or
-  both?
-- Should extraction run independently per source chunk only, or should some
-  extractors receive whole-document context?
-- Which artifact types can use a generic append-in-chunk-order merger?
 - Which artifact types need domain-specific normalization for deduplication,
   identity resolution, or consistency?
-- Should LLM review be part of each extractor's validator chain or a separate
+- What should the configuration model look like for selecting input, chunk,
-  review phase?
+  extract, merge, normalize, output, and validator modules?
-- Should the Seriatim adapter accept only its minimal schema initially or also
-  support richer transcript schemas?
-- Should source-unit metadata be untyped `map[string]any`, typed extension
-  structs, or both?
 
 ## Near-Term Documentation Tasks
 

internal/core/artifacts/artifacts.go

@@ -7,7 +7,7 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
 )
 
-type Candidate struct {
+type ArtifactCandidate struct {
 	Index         int                `json:"index"`
 	ExtractorKey  string             `json:"extractor_key"`
 	ArtifactType  string             `json:"artifact_type"`
@@ -27,24 +27,28 @@ type Artifact struct {
 }
 
 type RejectedArtifact struct {
-	Candidate     Candidate `json:"candidate"`
+	Candidate     ArtifactCandidate `json:"candidate"`
-	ValidatorName string    `json:"validator_name"`
+	ValidatorName string            `json:"validator_name"`
-	ReasonCode    string    `json:"reason_code"`
+	ReasonCode    string            `json:"reason_code"`
-	Message       string    `json:"message"`
+	Message       string            `json:"message"`
 }
 
 type RunManifest struct {
 	RunID            string     `json:"run_id,omitempty"`
-	InputAdapter     string     `json:"input_adapter,omitempty"`
+	InputModule      string     `json:"input_module,omitempty"`
+	Chunker          string     `json:"chunker,omitempty"`
 	SourceDigests    []string   `json:"source_digests,omitempty"`
 	Extractors       []string   `json:"extractors,omitempty"`
+	Merger           string     `json:"merger,omitempty"`
+	Normalizer       string     `json:"normalizer,omitempty"`
+	OutputEncoder    string     `json:"output_encoder,omitempty"`
 	SchemaVersion    string     `json:"schema_version,omitempty"`
 	ValidationStatus string     `json:"validation_status,omitempty"`
 	StartedAt        *time.Time `json:"started_at,omitempty"`
 	CompletedAt      *time.Time `json:"completed_at,omitempty"`
 }
 
-func ArtifactFromCandidate(candidate Candidate) Artifact {
+func ArtifactFromCandidate(candidate ArtifactCandidate) Artifact {
 	return Artifact{
 		ExtractorKey:  candidate.ExtractorKey,
 		ArtifactType:  candidate.ArtifactType,

internal/core/artifacts/artifacts_test.go

@@ -9,7 +9,7 @@ import (
 )
 
 func TestArtifactFromCandidatePreservesCandidateFields(t *testing.T) {
-	candidate := Candidate{
+	candidate := ArtifactCandidate{
 		Index:         7,
 		ExtractorKey:  "generic-extractor",
 		ArtifactType:  "generic-artifact",
@@ -60,7 +60,7 @@ func TestArtifactFromCandidatePreservesCandidateFields(t *testing.T) {
 }
 
 func TestJSONMarshalUsesExpectedFieldNames(t *testing.T) {
-	candidate := Candidate{
+	candidate := ArtifactCandidate{
 		Index:         1,
 		ExtractorKey:  "generic-extractor",
 		ArtifactType:  "generic-artifact",

internal/framework/contracts/composition_test.go

@@ -107,7 +107,7 @@ func (extractor compositionExtractor) Extract(ctx context.Context, req contracts
 	}
 
 	return contracts.ExtractionResult{
-		Candidates: []artifacts.Candidate{
+		Candidates: []artifacts.ArtifactCandidate{
 			{
 				Index:         0,
 				ExtractorKey:  extractor.Key(),

internal/framework/contracts/contracts.go

@@ -53,8 +53,8 @@ type ExtractionRequest struct {
 }
 
 type ExtractionResult struct {
-	Candidates []artifacts.Candidate `json:"candidates,omitempty"`
+	Candidates []artifacts.ArtifactCandidate `json:"candidates,omitempty"`
-	Warnings   []Warning             `json:"warnings,omitempty"`
+	Warnings   []Warning                     `json:"warnings,omitempty"`
 }
 
 type Extractor interface {
@@ -66,9 +66,9 @@ type Extractor interface {
 }
 
 type ValidationRequest struct {
-	Source     *source.SourceDocument `json:"-"`
+	Source     *source.SourceDocument        `json:"-"`
-	Candidates []artifacts.Candidate  `json:"candidates"`
+	Candidates []artifacts.ArtifactCandidate `json:"candidates"`
-	Metadata   map[string]any         `json:"metadata,omitempty"`
+	Metadata   map[string]any                `json:"metadata,omitempty"`
 }
 
 type ValidationDecision struct {

internal/framework/contracts/contracts_test.go

@@ -58,19 +58,19 @@ func TestFakeExtractorReturnsCandidateAndValidator(t *testing.T) {
 
 	candidate := result.Candidates[0]
 	if candidate.Index != 0 {
-		t.Fatalf("Candidate.Index = %d, want 0", candidate.Index)
+		t.Fatalf("ArtifactCandidate.Index = %d, want 0", candidate.Index)
 	}
 	if candidate.ExtractorKey != extractor.Key() {
-		t.Fatalf("Candidate.ExtractorKey = %q, want %q", candidate.ExtractorKey, extractor.Key())
+		t.Fatalf("ArtifactCandidate.ExtractorKey = %q, want %q", candidate.ExtractorKey, extractor.Key())
 	}
 	if candidate.ArtifactType != extractor.ArtifactType() {
-		t.Fatalf("Candidate.ArtifactType = %q, want %q", candidate.ArtifactType, extractor.ArtifactType())
+		t.Fatalf("ArtifactCandidate.ArtifactType = %q, want %q", candidate.ArtifactType, extractor.ArtifactType())
 	}
 	if candidate.SchemaVersion != extractor.SchemaVersion() {
-		t.Fatalf("Candidate.SchemaVersion = %q, want %q", candidate.SchemaVersion, extractor.SchemaVersion())
+		t.Fatalf("ArtifactCandidate.SchemaVersion = %q, want %q", candidate.SchemaVersion, extractor.SchemaVersion())
 	}
 	if string(candidate.Payload) != `{"value":"example"}` {
-		t.Fatalf("Candidate.Payload = %s, want example payload", candidate.Payload)
+		t.Fatalf("ArtifactCandidate.Payload = %s, want example payload", candidate.Payload)
 	}
 }
 
@@ -112,7 +112,7 @@ func (extractor fakeExtractor) Validators() []Validator {
 
 func (extractor fakeExtractor) Extract(ctx context.Context, req ExtractionRequest) (ExtractionResult, error) {
 	return ExtractionResult{
-		Candidates: []artifacts.Candidate{
+		Candidates: []artifacts.ArtifactCandidate{
 			{
 				Index:         0,
 				ExtractorKey:  extractor.key,

internal/framework/pipeline/extractor_registry.go

@@ -1,4 +1,4 @@
-package extractorregistry
+package pipeline
 
 import (
 	"fmt"
@@ -8,19 +8,19 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 )
 
-type Constructor func() (contracts.Extractor, error)
+type ExtractorConstructor func() (contracts.Extractor, error)
 
-type Registry struct {
+type ExtractorRegistry struct {
-	constructors map[string]Constructor
+	constructors map[string]ExtractorConstructor
 }
 
-func New() *Registry {
+func NewExtractorRegistry() *ExtractorRegistry {
-	return &Registry{
+	return &ExtractorRegistry{
-		constructors: make(map[string]Constructor),
+		constructors: make(map[string]ExtractorConstructor),
 	}
 }
 
-func (r *Registry) Register(key string, constructor Constructor) error {
+func (r *ExtractorRegistry) Register(key string, constructor ExtractorConstructor) error {
 	if r == nil {
 		return fmt.Errorf("extractor registry must not be nil")
 	}
@@ -40,7 +40,7 @@ func (r *Registry) Register(key string, constructor Constructor) error {
 	return nil
 }
 
-func (r *Registry) Build(key string) (contracts.Extractor, error) {
+func (r *ExtractorRegistry) Build(key string) (contracts.Extractor, error) {
 	if r == nil {
 		return nil, fmt.Errorf("extractor registry must not be nil")
 	}
@@ -69,7 +69,7 @@ func (r *Registry) Build(key string) (contracts.Extractor, error) {
 	return extractor, nil
 }
 
-func (r *Registry) RegisteredKeys() []string {
+func (r *ExtractorRegistry) RegisteredKeys() []string {
 	if r == nil {
 		return nil
 	}

internal/framework/pipeline/extractor_registry_test.go

@@ -1,4 +1,4 @@
-package extractorregistry
+package pipeline
 
 import (
 	"context"
@@ -10,10 +10,10 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 )
 
-func TestRegisterAndBuild(t *testing.T) {
+func TestExtractorRegistryRegisterAndBuild(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
 
-	if err := registry.Register("generic-extractor", fakeConstructor("generic-extractor")); err != nil {
+	if err := registry.Register("generic-extractor", fakeExtractorConstructor("generic-extractor")); err != nil {
 		t.Fatalf("Register() error = %v, want nil", err)
 	}
 
@@ -26,10 +26,10 @@ func TestRegisterAndBuild(t *testing.T) {
 	}
 }
 
-func TestRegisterAndBuildTrimKeys(t *testing.T) {
+func TestExtractorRegistryRegisterAndBuildTrimKeys(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
 
-	if err := registry.Register(" generic-extractor ", fakeConstructor("generic-extractor")); err != nil {
+	if err := registry.Register(" generic-extractor ", fakeExtractorConstructor("generic-extractor")); err != nil {
 		t.Fatalf("Register() error = %v, want nil", err)
 	}
 
@@ -42,10 +42,10 @@ func TestRegisterAndBuildTrimKeys(t *testing.T) {
 	}
 }
 
-func TestRegisterRejectsEmptyKey(t *testing.T) {
+func TestExtractorRegistryRegisterRejectsEmptyKey(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
 
-	err := registry.Register(" \t", fakeConstructor("generic-extractor"))
+	err := registry.Register(" \t", fakeExtractorConstructor("generic-extractor"))
 
 	if err == nil {
 		t.Fatal("Register() error = nil, want error")
@@ -55,13 +55,13 @@ func TestRegisterRejectsEmptyKey(t *testing.T) {
 	}
 }
 
-func TestRegisterRejectsDuplicateKey(t *testing.T) {
+func TestExtractorRegistryRegisterRejectsDuplicateKey(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
-	if err := registry.Register("generic-extractor", fakeConstructor("generic-extractor")); err != nil {
+	if err := registry.Register("generic-extractor", fakeExtractorConstructor("generic-extractor")); err != nil {
 		t.Fatalf("Register() error = %v, want nil", err)
 	}
 
-	err := registry.Register(" generic-extractor ", fakeConstructor("generic-extractor"))
+	err := registry.Register(" generic-extractor ", fakeExtractorConstructor("generic-extractor"))
 
 	if err == nil {
 		t.Fatal("Register() error = nil, want error")
@@ -71,8 +71,8 @@ func TestRegisterRejectsDuplicateKey(t *testing.T) {
 	}
 }
 
-func TestRegisterRejectsNilConstructor(t *testing.T) {
+func TestExtractorRegistryRegisterRejectsNilConstructor(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
 
 	err := registry.Register("generic-extractor", nil)
 
@@ -84,8 +84,8 @@ func TestRegisterRejectsNilConstructor(t *testing.T) {
 	}
 }
 
-func TestBuildRejectsUnknownKey(t *testing.T) {
+func TestExtractorRegistryBuildRejectsUnknownKey(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
 
 	_, err := registry.Build("missing-extractor")
 
@@ -97,8 +97,8 @@ func TestBuildRejectsUnknownKey(t *testing.T) {
 	}
 }
 
-func TestBuildWrapsConstructorError(t *testing.T) {
+func TestExtractorRegistryBuildWrapsConstructorError(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
 	constructorErr := errors.New("constructor failed")
 	if err := registry.Register("generic-extractor", func() (contracts.Extractor, error) {
 		return nil, constructorErr
@@ -119,8 +119,8 @@ func TestBuildWrapsConstructorError(t *testing.T) {
 	}
 }
 
-func TestBuildRejectsNilExtractor(t *testing.T) {
+func TestExtractorRegistryBuildRejectsNilExtractor(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
 	if err := registry.Register("generic-extractor", func() (contracts.Extractor, error) {
 		return nil, nil
 	}); err != nil {
@@ -137,9 +137,9 @@ func TestBuildRejectsNilExtractor(t *testing.T) {
 	}
 }
 
-func TestBuildRejectsExtractorKeyMismatch(t *testing.T) {
+func TestExtractorRegistryBuildRejectsExtractorKeyMismatch(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
-	if err := registry.Register("generic-extractor", fakeConstructor("other-extractor")); err != nil {
+	if err := registry.Register("generic-extractor", fakeExtractorConstructor("other-extractor")); err != nil {
 		t.Fatalf("Register() error = %v, want nil", err)
 	}
 
@@ -153,10 +153,10 @@ func TestBuildRejectsExtractorKeyMismatch(t *testing.T) {
 	}
 }
 
-func TestRegisteredKeysReturnsSortedCopy(t *testing.T) {
+func TestExtractorRegistryRegisteredKeysReturnsSortedCopy(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
 	for _, key := range []string{"zeta", "alpha", "middle"} {
-		if err := registry.Register(key, fakeConstructor(key)); err != nil {
+		if err := registry.Register(key, fakeExtractorConstructor(key)); err != nil {
 			t.Fatalf("Register(%q) error = %v, want nil", key, err)
 		}
 	}
@@ -174,10 +174,10 @@ func TestRegisteredKeysReturnsSortedCopy(t *testing.T) {
 	}
 }
 
-func TestNilRegistryBehavior(t *testing.T) {
+func TestExtractorRegistryNilRegistryBehavior(t *testing.T) {
-	var registry *Registry
+	var registry *ExtractorRegistry
 
-	if err := registry.Register("generic-extractor", fakeConstructor("generic-extractor")); err == nil {
+	if err := registry.Register("generic-extractor", fakeExtractorConstructor("generic-extractor")); err == nil {
 		t.Fatal("Register() error = nil, want error")
 	}
 	if _, err := registry.Build("generic-extractor"); err == nil {
@@ -188,8 +188,8 @@ func TestNilRegistryBehavior(t *testing.T) {
 	}
 }
 
-func TestBuildRejectsEmptyKey(t *testing.T) {
+func TestExtractorRegistryBuildRejectsEmptyKey(t *testing.T) {
-	registry := New()
+	registry := NewExtractorRegistry()
 
 	_, err := registry.Build(" \n")
 
@@ -201,32 +201,32 @@ func TestBuildRejectsEmptyKey(t *testing.T) {
 	}
 }
 
-type fakeExtractor struct {
+type registryFakeExtractor struct {
 	key string
 }
 
-func fakeConstructor(key string) Constructor {
+func fakeExtractorConstructor(key string) ExtractorConstructor {
 	return func() (contracts.Extractor, error) {
-		return fakeExtractor{key: key}, nil
+		return registryFakeExtractor{key: key}, nil
 	}
 }
 
-func (extractor fakeExtractor) Key() string {
+func (extractor registryFakeExtractor) Key() string {
 	return extractor.key
 }
 
-func (extractor fakeExtractor) ArtifactType() string {
+func (extractor registryFakeExtractor) ArtifactType() string {
 	return "generic-artifact"
 }
 
-func (extractor fakeExtractor) SchemaVersion() string {
+func (extractor registryFakeExtractor) SchemaVersion() string {
 	return "v1"
 }
 
-func (extractor fakeExtractor) Validators() []contracts.Validator {
+func (extractor registryFakeExtractor) Validators() []contracts.Validator {
 	return nil
 }
 
-func (extractor fakeExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) {
+func (extractor registryFakeExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) {
 	return contracts.ExtractionResult{}, nil
 }

internal/framework/pipeline/input_registry.go

@@ -1,4 +1,4 @@
-package inputregistry
+package pipeline
 
 import (
 	"fmt"
@@ -8,19 +8,19 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 )
 
-type Constructor func() (contracts.InputAdapter, error)
+type InputAdapterConstructor func() (contracts.InputAdapter, error)
 
-type Registry struct {
+type InputAdapterRegistry struct {
-	constructors map[string]Constructor
+	constructors map[string]InputAdapterConstructor
 }
 
-func New() *Registry {
+func NewInputAdapterRegistry() *InputAdapterRegistry {
-	return &Registry{
+	return &InputAdapterRegistry{
-		constructors: make(map[string]Constructor),
+		constructors: make(map[string]InputAdapterConstructor),
 	}
 }
 
-func (r *Registry) Register(key string, constructor Constructor) error {
+func (r *InputAdapterRegistry) Register(key string, constructor InputAdapterConstructor) error {
 	if r == nil {
 		return fmt.Errorf("input adapter registry must not be nil")
 	}
@@ -40,7 +40,7 @@ func (r *Registry) Register(key string, constructor Constructor) error {
 	return nil
 }
 
-func (r *Registry) Build(key string) (contracts.InputAdapter, error) {
+func (r *InputAdapterRegistry) Build(key string) (contracts.InputAdapter, error) {
 	if r == nil {
 		return nil, fmt.Errorf("input adapter registry must not be nil")
 	}
@@ -69,7 +69,7 @@ func (r *Registry) Build(key string) (contracts.InputAdapter, error) {
 	return adapter, nil
 }
 
-func (r *Registry) RegisteredKeys() []string {
+func (r *InputAdapterRegistry) RegisteredKeys() []string {
 	if r == nil {
 		return nil
 	}

internal/framework/pipeline/input_registry_test.go

@@ -1,4 +1,4 @@
-package inputregistry
+package pipeline
 
 import (
 	"context"
@@ -11,10 +11,10 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 )
 
-func TestRegisterAndBuild(t *testing.T) {
+func TestInputAdapterRegistryRegisterAndBuild(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
 
-	if err := registry.Register("generic-input", fakeConstructor("generic-input")); err != nil {
+	if err := registry.Register("generic-input", fakeInputAdapterConstructor("generic-input")); err != nil {
 		t.Fatalf("Register() error = %v, want nil", err)
 	}
 
@@ -27,10 +27,10 @@ func TestRegisterAndBuild(t *testing.T) {
 	}
 }
 
-func TestRegisterAndBuildTrimKeys(t *testing.T) {
+func TestInputAdapterRegistryRegisterAndBuildTrimKeys(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
 
-	if err := registry.Register(" generic-input ", fakeConstructor("generic-input")); err != nil {
+	if err := registry.Register(" generic-input ", fakeInputAdapterConstructor("generic-input")); err != nil {
 		t.Fatalf("Register() error = %v, want nil", err)
 	}
 
@@ -43,10 +43,10 @@ func TestRegisterAndBuildTrimKeys(t *testing.T) {
 	}
 }
 
-func TestRegisterRejectsEmptyKey(t *testing.T) {
+func TestInputAdapterRegistryRegisterRejectsEmptyKey(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
 
-	err := registry.Register(" \t", fakeConstructor("generic-input"))
+	err := registry.Register(" \t", fakeInputAdapterConstructor("generic-input"))
 
 	if err == nil {
 		t.Fatal("Register() error = nil, want error")
@@ -56,13 +56,13 @@ func TestRegisterRejectsEmptyKey(t *testing.T) {
 	}
 }
 
-func TestRegisterRejectsDuplicateKey(t *testing.T) {
+func TestInputAdapterRegistryRegisterRejectsDuplicateKey(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
-	if err := registry.Register("generic-input", fakeConstructor("generic-input")); err != nil {
+	if err := registry.Register("generic-input", fakeInputAdapterConstructor("generic-input")); err != nil {
 		t.Fatalf("Register() error = %v, want nil", err)
 	}
 
-	err := registry.Register(" generic-input ", fakeConstructor("generic-input"))
+	err := registry.Register(" generic-input ", fakeInputAdapterConstructor("generic-input"))
 
 	if err == nil {
 		t.Fatal("Register() error = nil, want error")
@@ -72,8 +72,8 @@ func TestRegisterRejectsDuplicateKey(t *testing.T) {
 	}
 }
 
-func TestRegisterRejectsNilConstructor(t *testing.T) {
+func TestInputAdapterRegistryRegisterRejectsNilConstructor(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
 
 	err := registry.Register("generic-input", nil)
 
@@ -85,8 +85,8 @@ func TestRegisterRejectsNilConstructor(t *testing.T) {
 	}
 }
 
-func TestBuildRejectsUnknownKey(t *testing.T) {
+func TestInputAdapterRegistryBuildRejectsUnknownKey(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
 
 	_, err := registry.Build("missing-input")
 
@@ -98,8 +98,8 @@ func TestBuildRejectsUnknownKey(t *testing.T) {
 	}
 }
 
-func TestBuildWrapsConstructorError(t *testing.T) {
+func TestInputAdapterRegistryBuildWrapsConstructorError(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
 	constructorErr := errors.New("constructor failed")
 	if err := registry.Register("generic-input", func() (contracts.InputAdapter, error) {
 		return nil, constructorErr
@@ -120,8 +120,8 @@ func TestBuildWrapsConstructorError(t *testing.T) {
 	}
 }
 
-func TestBuildRejectsNilAdapter(t *testing.T) {
+func TestInputAdapterRegistryBuildRejectsNilAdapter(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
 	if err := registry.Register("generic-input", func() (contracts.InputAdapter, error) {
 		return nil, nil
 	}); err != nil {
@@ -138,9 +138,9 @@ func TestBuildRejectsNilAdapter(t *testing.T) {
 	}
 }
 
-func TestBuildRejectsAdapterKeyMismatch(t *testing.T) {
+func TestInputAdapterRegistryBuildRejectsAdapterKeyMismatch(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
-	if err := registry.Register("generic-input", fakeConstructor("other-input")); err != nil {
+	if err := registry.Register("generic-input", fakeInputAdapterConstructor("other-input")); err != nil {
 		t.Fatalf("Register() error = %v, want nil", err)
 	}
 
@@ -154,10 +154,10 @@ func TestBuildRejectsAdapterKeyMismatch(t *testing.T) {
 	}
 }
 
-func TestRegisteredKeysReturnsSortedCopy(t *testing.T) {
+func TestInputAdapterRegistryRegisteredKeysReturnsSortedCopy(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
 	for _, key := range []string{"zeta", "alpha", "middle"} {
-		if err := registry.Register(key, fakeConstructor(key)); err != nil {
+		if err := registry.Register(key, fakeInputAdapterConstructor(key)); err != nil {
 			t.Fatalf("Register(%q) error = %v, want nil", key, err)
 		}
 	}
@@ -175,10 +175,10 @@ func TestRegisteredKeysReturnsSortedCopy(t *testing.T) {
 	}
 }
 
-func TestNilRegistryBehavior(t *testing.T) {
+func TestInputAdapterRegistryNilRegistryBehavior(t *testing.T) {
-	var registry *Registry
+	var registry *InputAdapterRegistry
 
-	if err := registry.Register("generic-input", fakeConstructor("generic-input")); err == nil {
+	if err := registry.Register("generic-input", fakeInputAdapterConstructor("generic-input")); err == nil {
 		t.Fatal("Register() error = nil, want error")
 	}
 	if _, err := registry.Build("generic-input"); err == nil {
@@ -189,8 +189,8 @@ func TestNilRegistryBehavior(t *testing.T) {
 	}
 }
 
-func TestBuildRejectsEmptyKey(t *testing.T) {
+func TestInputAdapterRegistryBuildRejectsEmptyKey(t *testing.T) {
-	registry := New()
+	registry := NewInputAdapterRegistry()
 
 	_, err := registry.Build(" \n")
 
@@ -206,7 +206,7 @@ type fakeAdapter struct {
 	key string
 }
 
-func fakeConstructor(key string) Constructor {
+func fakeInputAdapterConstructor(key string) InputAdapterConstructor {
 	return func() (contracts.InputAdapter, error) {
 		return fakeAdapter{key: key}, nil
 	}

internal/framework/pipeline/registry_integration_test.go

@@ -1,4 +1,4 @@
-package runner
+package pipeline
 
 import (
 	"context"
@@ -8,14 +8,14 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
 	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
-	"gitea.maximumdirect.net/eric/notarius/internal/framework/extractorregistry"
+
-	validationhelpers "gitea.maximumdirect.net/eric/notarius/internal/framework/validators"
+	validate "gitea.maximumdirect.net/eric/notarius/internal/framework/validate"
 )
 
 func TestRunnerUsesExtractorRegistry(t *testing.T) {
 	var builtKeys []string
 	var executedKeys []string
-	registry := extractorregistry.New()
+	registry := NewExtractorRegistry()
 
 	registerIntegrationExtractor(t, registry, "second", &builtKeys, &executedKeys, []contracts.Validator{
 		integrationValidator{name: "reject-second", approve: false},
@@ -46,7 +46,7 @@ func TestRunnerUsesExtractorRegistry(t *testing.T) {
 	}
 }
 
-func registerIntegrationExtractor(t *testing.T, registry *extractorregistry.Registry, key string, builtKeys *[]string, executedKeys *[]string, validators []contracts.Validator) {
+func registerIntegrationExtractor(t *testing.T, registry *ExtractorRegistry, key string, builtKeys *[]string, executedKeys *[]string, validators []contracts.Validator) {
 	t.Helper()
 
 	if err := registry.Register(key, func() (contracts.Extractor, error) {
@@ -82,7 +82,7 @@ func (extractor integrationExtractor) Validators() []contracts.Validator {
 func (extractor integrationExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) {
 	*extractor.executedKeys = append(*extractor.executedKeys, extractor.key)
 	return contracts.ExtractionResult{
-		Candidates: []artifacts.Candidate{
+		Candidates: []artifacts.ArtifactCandidate{
 			{Payload: []byte(`{"value":true}`)},
 		},
 	}, nil
@@ -101,9 +101,9 @@ func (validator integrationValidator) Validate(ctx context.Context, req contract
 	decisions := make([]contracts.ValidationDecision, 0, len(req.Candidates))
 	for _, candidate := range req.Candidates {
 		if validator.approve {
-			decisions = append(decisions, validationhelpers.Approved(candidate.Index))
+			decisions = append(decisions, validate.Approved(candidate.Index))
 		} else {
-			decisions = append(decisions, validationhelpers.Rejected(candidate.Index, "invalid", "not accepted"))
+			decisions = append(decisions, validate.Rejected(candidate.Index, "invalid", "not accepted"))
 		}
 	}
 	return contracts.ValidationResult{

internal/framework/pipeline/runner.go

@@ -1,4 +1,4 @@
-package runner
+package pipeline
 
 import (
 	"context"
@@ -7,7 +7,7 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
 	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
-	"gitea.maximumdirect.net/eric/notarius/internal/framework/validators"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/validate"
 )
 
 type ExtractorFactory interface {
@@ -90,8 +90,8 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
 	return output, nil
 }
 
-func normalizeCandidates(extractor contracts.Extractor, candidates []artifacts.Candidate, nextIndex *int) ([]artifacts.Candidate, error) {
+func normalizeCandidates(extractor contracts.Extractor, candidates []artifacts.ArtifactCandidate, nextIndex *int) ([]artifacts.ArtifactCandidate, error) {
-	normalized := make([]artifacts.Candidate, 0, len(candidates))
+	normalized := make([]artifacts.ArtifactCandidate, 0, len(candidates))
 	for _, candidate := range candidates {
 		candidate.Index = *nextIndex
 		*nextIndex = *nextIndex + 1
@@ -119,7 +119,7 @@ func normalizeCandidates(extractor contracts.Extractor, candidates []artifacts.C
 	return normalized, nil
 }
 
-func runValidators(ctx context.Context, extractor contracts.Extractor, doc *source.SourceDocument, candidates []artifacts.Candidate, metadata map[string]any) ([]artifacts.Candidate, []artifacts.RejectedArtifact, []contracts.Warning, error) {
+func runValidators(ctx context.Context, extractor contracts.Extractor, doc *source.SourceDocument, candidates []artifacts.ArtifactCandidate, metadata map[string]any) ([]artifacts.ArtifactCandidate, []artifacts.RejectedArtifact, []contracts.Warning, error) {
 	eligible := candidates
 	var rejected []artifacts.RejectedArtifact
 	var warnings []contracts.Warning
@@ -140,7 +140,7 @@ func runValidators(ctx context.Context, extractor contracts.Extractor, doc *sour
 		if result.ValidatorName != validator.Name() {
 			return nil, rejected, warnings, fmt.Errorf("validator %q returned result for %q", validator.Name(), result.ValidatorName)
 		}
-		if err := validators.EnforceDecisionCardinality(eligible, result.Decisions); err != nil {
+		if err := validate.EnforceDecisionCardinality(eligible, result.Decisions); err != nil {
 			return nil, rejected, warnings, fmt.Errorf("validate extractor %q with validator %q: %w", extractor.Key(), validator.Name(), err)
 		}
 
@@ -149,7 +149,7 @@ func runValidators(ctx context.Context, extractor contracts.Extractor, doc *sour
 			decisions[decision.CandidateIndex] = decision
 		}
 
-		nextEligible := make([]artifacts.Candidate, 0, len(eligible))
+		nextEligible := make([]artifacts.ArtifactCandidate, 0, len(eligible))
 		for _, candidate := range eligible {
 			decision := decisions[candidate.Index]
 			if decision.Approved {

internal/framework/pipeline/runner_test.go

@@ -1,4 +1,4 @@
-package runner
+package pipeline
 
 import (
 	"context"
@@ -10,7 +10,7 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
 	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
-	validationhelpers "gitea.maximumdirect.net/eric/notarius/internal/framework/validators"
+	validate "gitea.maximumdirect.net/eric/notarius/internal/framework/validate"
 )
 
 func TestNewAndDataTypes(t *testing.T) {
@@ -99,11 +99,11 @@ func TestRunRejectsNilExtractorFromFactory(t *testing.T) {
 func TestRunUsesConfiguredExtractorOrderAndAssignsGlobalIndices(t *testing.T) {
 	var order []string
 	var seenIndices []int
-	recordIndices := func(candidates []artifacts.Candidate) []contracts.ValidationDecision {
+	recordIndices := func(candidates []artifacts.ArtifactCandidate) []contracts.ValidationDecision {
 		decisions := make([]contracts.ValidationDecision, 0, len(candidates))
 		for _, candidate := range candidates {
 			seenIndices = append(seenIndices, candidate.Index)
-			decisions = append(decisions, validationhelpers.Approved(candidate.Index))
+			decisions = append(decisions, validate.Approved(candidate.Index))
 		}
 		return decisions
 	}
@@ -133,7 +133,7 @@ func TestRunUsesConfiguredExtractorOrderAndAssignsGlobalIndices(t *testing.T) {
 
 func TestRunFillsEmptyCandidateExtractorMetadata(t *testing.T) {
 	factory := fakeFactory{extractors: map[string]contracts.Extractor{
-		"generic-extractor": fakeExtractor{key: "generic-extractor", artifactType: "generic-artifact", schemaVersion: "v1", candidates: []artifacts.Candidate{{Payload: []byte(`{"value":true}`)}}},
+		"generic-extractor": fakeExtractor{key: "generic-extractor", artifactType: "generic-artifact", schemaVersion: "v1", candidates: []artifacts.ArtifactCandidate{{Payload: []byte(`{"value":true}`)}}},
 	}}
 
 	output, err := New(factory).Run(context.Background(), RunInput{Source: validSourceDocument(), ExtractorKeys: []string{"generic-extractor"}})
@@ -150,18 +150,18 @@ func TestRunFillsEmptyCandidateExtractorMetadata(t *testing.T) {
 func TestRunRejectsCandidateMetadataMismatches(t *testing.T) {
 	tests := []struct {
 		name      string
-		candidate artifacts.Candidate
+		candidate artifacts.ArtifactCandidate
 		error     string
 	}{
-		{name: "extractor key", candidate: artifacts.Candidate{ExtractorKey: "other"}, error: "extractor_key"},
+		{name: "extractor key", candidate: artifacts.ArtifactCandidate{ExtractorKey: "other"}, error: "extractor_key"},
-		{name: "artifact type", candidate: artifacts.Candidate{ArtifactType: "other"}, error: "artifact_type"},
+		{name: "artifact type", candidate: artifacts.ArtifactCandidate{ArtifactType: "other"}, error: "artifact_type"},
-		{name: "schema version", candidate: artifacts.Candidate{SchemaVersion: "other"}, error: "schema_version"},
+		{name: "schema version", candidate: artifacts.ArtifactCandidate{SchemaVersion: "other"}, error: "schema_version"},
 	}
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			factory := fakeFactory{extractors: map[string]contracts.Extractor{
-				"generic-extractor": fakeExtractor{key: "generic-extractor", artifactType: "generic-artifact", schemaVersion: "v1", candidates: []artifacts.Candidate{tt.candidate}},
+				"generic-extractor": fakeExtractor{key: "generic-extractor", artifactType: "generic-artifact", schemaVersion: "v1", candidates: []artifacts.ArtifactCandidate{tt.candidate}},
 			}}
 
 			_, err := New(factory).Run(context.Background(), RunInput{Source: validSourceDocument(), ExtractorKeys: []string{"generic-extractor"}})
@@ -194,8 +194,8 @@ func TestRunApprovesCandidatesWithoutValidators(t *testing.T) {
 }
 
 func TestRunValidatorApprovalProducesApprovedArtifacts(t *testing.T) {
-	validator := fakeValidator{name: "generic-validator", decisions: func(candidates []artifacts.Candidate) []contracts.ValidationDecision {
+	validator := fakeValidator{name: "generic-validator", decisions: func(candidates []artifacts.ArtifactCandidate) []contracts.ValidationDecision {
-		return []contracts.ValidationDecision{validationhelpers.Approved(candidates[0].Index)}
+		return []contracts.ValidationDecision{validate.Approved(candidates[0].Index)}
 	}}
 	factory := fakeFactory{extractors: map[string]contracts.Extractor{
 		"generic-extractor": fakeExtractor{key: "generic-extractor", artifactType: "generic-artifact", schemaVersion: "v1", candidateCount: 1, validators: []contracts.Validator{validator}},
@@ -212,15 +212,15 @@ func TestRunValidatorApprovalProducesApprovedArtifacts(t *testing.T) {
 
 func TestRunValidatorRejectionRemovesCandidateFromLaterValidators(t *testing.T) {
 	var laterSeen int
-	rejectFirst := fakeValidator{name: "reject-first", decisions: func(candidates []artifacts.Candidate) []contracts.ValidationDecision {
+	rejectFirst := fakeValidator{name: "reject-first", decisions: func(candidates []artifacts.ArtifactCandidate) []contracts.ValidationDecision {
 		return []contracts.ValidationDecision{
-			validationhelpers.Rejected(candidates[0].Index, "invalid", "not accepted"),
+			validate.Rejected(candidates[0].Index, "invalid", "not accepted"),
-			validationhelpers.Approved(candidates[1].Index),
+			validate.Approved(candidates[1].Index),
 		}
 	}}
-	approveRemaining := fakeValidator{name: "approve-remaining", decisions: func(candidates []artifacts.Candidate) []contracts.ValidationDecision {
+	approveRemaining := fakeValidator{name: "approve-remaining", decisions: func(candidates []artifacts.ArtifactCandidate) []contracts.ValidationDecision {
 		laterSeen = len(candidates)
-		return []contracts.ValidationDecision{validationhelpers.Approved(candidates[0].Index)}
+		return []contracts.ValidationDecision{validate.Approved(candidates[0].Index)}
 	}}
 	factory := fakeFactory{extractors: map[string]contracts.Extractor{
 		"generic-extractor": fakeExtractor{key: "generic-extractor", artifactType: "generic-artifact", schemaVersion: "v1", candidateCount: 2, validators: []contracts.Validator{rejectFirst, approveRemaining}},
@@ -254,7 +254,7 @@ func TestRunSurfacesValidatorNameMismatch(t *testing.T) {
 }
 
 func TestRunSurfacesValidatorCardinalityError(t *testing.T) {
-	validator := fakeValidator{name: "generic-validator", decisions: func(candidates []artifacts.Candidate) []contracts.ValidationDecision {
+	validator := fakeValidator{name: "generic-validator", decisions: func(candidates []artifacts.ArtifactCandidate) []contracts.ValidationDecision {
 		return nil
 	}}
 	factory := factoryWithValidator(validator)
@@ -359,7 +359,7 @@ type fakeExtractor struct {
 	artifactType   string
 	schemaVersion  string
 	candidateCount int
-	candidates     []artifacts.Candidate
+	candidates     []artifacts.ArtifactCandidate
 	validators     []contracts.Validator
 	warnings       []contracts.Warning
 	err            error
@@ -386,9 +386,9 @@ func (extractor fakeExtractor) Extract(ctx context.Context, req contracts.Extrac
 	if extractor.order != nil {
 		*extractor.order = append(*extractor.order, extractor.key)
 	}
-	candidates := append([]artifacts.Candidate(nil), extractor.candidates...)
+	candidates := append([]artifacts.ArtifactCandidate(nil), extractor.candidates...)
 	for len(candidates) < extractor.candidateCount {
-		candidates = append(candidates, artifacts.Candidate{Payload: []byte(`{"value":true}`)})
+		candidates = append(candidates, artifacts.ArtifactCandidate{Payload: []byte(`{"value":true}`)})
 	}
 	return contracts.ExtractionResult{
 		Candidates: candidates,
@@ -399,7 +399,7 @@ func (extractor fakeExtractor) Extract(ctx context.Context, req contracts.Extrac
 type fakeValidator struct {
 	name       string
 	resultName string
-	decisions  func([]artifacts.Candidate) []contracts.ValidationDecision
+	decisions  func([]artifacts.ArtifactCandidate) []contracts.ValidationDecision
 	warnings   []contracts.Warning
 	err        error
 }
@@ -436,10 +436,10 @@ func factoryWithValidator(validator contracts.Validator) fakeFactory {
 	}}
 }
 
-func approveAll(candidates []artifacts.Candidate) []contracts.ValidationDecision {
+func approveAll(candidates []artifacts.ArtifactCandidate) []contracts.ValidationDecision {
 	decisions := make([]contracts.ValidationDecision, 0, len(candidates))
 	for _, candidate := range candidates {
-		decisions = append(decisions, validationhelpers.Approved(candidate.Index))
+		decisions = append(decisions, validate.Approved(candidate.Index))
 	}
 	return decisions
 }

internal/framework/validate/validate.go

@@ -1,4 +1,4 @@
-package validators
+package validate
 
 import (
 	"fmt"
@@ -30,7 +30,7 @@ func Rejected(candidateIndex int, reasonCode string, message string) contracts.V
 	}
 }
 
-func EnforceDecisionCardinality(candidates []artifacts.Candidate, decisions []contracts.ValidationDecision) error {
+func EnforceDecisionCardinality(candidates []artifacts.ArtifactCandidate, decisions []contracts.ValidationDecision) error {
 	if len(candidates) != len(decisions) {
 		return fmt.Errorf("validator returned %d decisions for %d candidates", len(decisions), len(candidates))
 	}

internal/framework/validate/validate_test.go

@@ -1,4 +1,4 @@
-package validators
+package validate
 
 import (
 	"strings"
@@ -43,7 +43,7 @@ func TestRejectedTrimsReasonAndMessage(t *testing.T) {
 }
 
 func TestEnforceDecisionCardinalityAllowsNonZeroCandidateIndices(t *testing.T) {
-	candidates := []artifacts.Candidate{{Index: 4}, {Index: 8}}
+	candidates := []artifacts.ArtifactCandidate{{Index: 4}, {Index: 8}}
 	decisions := []contracts.ValidationDecision{Approved(8), Approved(4)}
 
 	if err := EnforceDecisionCardinality(candidates, decisions); err != nil {
@@ -59,7 +59,7 @@ func TestEnforceDecisionCardinalityAllowsEmptyInputs(t *testing.T) {
 
 func TestEnforceDecisionCardinalityRejectsUnknownDecisionIndex(t *testing.T) {
 	err := EnforceDecisionCardinality(
-		[]artifacts.Candidate{{Index: 1}},
+		[]artifacts.ArtifactCandidate{{Index: 1}},
 		[]contracts.ValidationDecision{Approved(2)},
 	)
 
@@ -68,7 +68,7 @@ func TestEnforceDecisionCardinalityRejectsUnknownDecisionIndex(t *testing.T) {
 
 func TestEnforceDecisionCardinalityRejectsDuplicateDecisionIndex(t *testing.T) {
 	err := EnforceDecisionCardinality(
-		[]artifacts.Candidate{{Index: 1}, {Index: 2}},
+		[]artifacts.ArtifactCandidate{{Index: 1}, {Index: 2}},
 		[]contracts.ValidationDecision{Approved(1), Approved(1)},
 	)
 
@@ -77,7 +77,7 @@ func TestEnforceDecisionCardinalityRejectsDuplicateDecisionIndex(t *testing.T) {
 
 func TestEnforceDecisionCardinalityRejectsMissingDecisionIndex(t *testing.T) {
 	err := EnforceDecisionCardinality(
-		[]artifacts.Candidate{{Index: 1}, {Index: 2}},
+		[]artifacts.ArtifactCandidate{{Index: 1}, {Index: 2}},
 		[]contracts.ValidationDecision{Approved(1)},
 	)
 
@@ -86,7 +86,7 @@ func TestEnforceDecisionCardinalityRejectsMissingDecisionIndex(t *testing.T) {
 
 func TestEnforceDecisionCardinalityRejectsDuplicateCandidateIndex(t *testing.T) {
 	err := EnforceDecisionCardinality(
-		[]artifacts.Candidate{{Index: 1}, {Index: 1}},
+		[]artifacts.ArtifactCandidate{{Index: 1}, {Index: 1}},
 		[]contracts.ValidationDecision{Approved(1), Approved(1)},
 	)