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

Final cleanup after checkpoint 3 and remove the completed implementation plan

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-03 11:26:49 -05:00
parent 25fbd791c8
commit d6dadb6c70
5 changed files with 235 additions and 924 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/policy/architecture.md
View File

@@ -211,6 +211,13 @@ envelope with `json.RawMessage` payloads; extract modules should own typed Go
structs at their boundaries and encode into that generic envelope before structs at their boundaries and encode into that generic envelope before
returning to framework code. returning to framework code.
Output-stage warnings are intentionally out-of-band. An `OutputEncoder` may
return warnings about serialization, formatting, truncation, or destination
concerns, but those warnings are appended to the runner result after encoding
and are not expected to appear inside the encoded artifact bytes. CLI,
diagnostic, or reporting layers should surface output-stage warnings from the
runner result.
Schemas should be versioned per extractor, with a separate envelope/manifest Schemas should be versioned per extractor, with a separate envelope/manifest
format version. format version.

891
docs/roadmap/implementation.md
View File

@@ -1,891 +0,0 @@
# Implementation Plan: Checkpoint 3 Pipeline Stages
## Status
This is a staged implementation plan for
[`3-pipeline-stages-chunking-merge-normalize.md`](3-pipeline-stages-chunking-merge-normalize.md).
It is intended for an LLM coding agent to follow stage by stage.
This plan implements only checkpoint 3. Do not add real Seriatim parsing, real
D&D extraction, production config file loading, CLI command behavior, LLM
provider clients, prompt assets, response schema assets, diagnostics run
directories, or durable output writing.
## Policy Context
Follow:
- [`docs/policy/architecture.md`](../policy/architecture.md)
- [`docs/policy/documentation.md`](../policy/documentation.md)
Required boundaries:
- framework code must stay source-agnostic and domain-agnostic;
- concrete business logic remains under `internal/modules/<stage>/...`, but this
checkpoint should use fake modules only;
- framework plumbing should remain consolidated under `internal/framework/pipeline`
unless a boundary proves itself;
- capabilities are flat strings, not a type system;
- pipeline profiles are fixed-shape templates, not arbitrary step lists;
- no structural module wiring through ad hoc CLI flags.
## Global Implementation Decisions
- Add no third-party dependencies.
- Keep new checkpoint 3 framework code in `internal/framework/pipeline`.
- Keep shared request/result contracts in `internal/framework/contracts` when
stage modules will implement or consume them.
- Do not create new framework packages for chunking, merge, normalize, output,
warnings, response schemas, or structured output.
- Use in-memory pipeline profile structs only. Do not implement YAML/TOML
parsing in this checkpoint.
- Keep one shared chunker per resolved pipeline. Per-lane chunker overrides are
deferred.
- Execute chunks serially in checkpoint 3. Contracts must not prevent later
parallel execution.
- Sort artifact lane IDs during resolution for deterministic output and digest
behavior.
- Use `sha256:<hex>` for resolved pipeline digests.
- Preserve existing validator decision-cardinality behavior.
- Run `gofmt` on all touched Go files before validation.
## Stage 1: Stage Contracts And Source Chunks
### Goal
Define the source chunk model and contracts for chunk, merge, normalize, and
output stages.
### Files To Update
- `internal/framework/contracts/contracts.go`
- `internal/framework/contracts/contracts_test.go`
- `internal/framework/contracts/composition_test.go`
### Required API
Add:
```go
type SourceChunk struct {
ID string `json:"id"`
SourceID string `json:"source_id"`
Index int `json:"index"`
Units []source.SourceUnit `json:"units"`
Metadata map[string]any `json:"metadata,omitempty"`
}
type ChunkRequest struct {
Source *source.SourceDocument `json:"-"`
Metadata map[string]any `json:"metadata,omitempty"`
}
type ChunkResult struct {
Chunks []SourceChunk `json:"chunks"`
Warnings []Warning `json:"warnings,omitempty"`
}
type Chunker interface {
Key() string
Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error)
}
```
Extend `ExtractionRequest`:
```go
type ExtractionRequest struct {
Source *source.SourceDocument `json:"-"`
Chunk *SourceChunk `json:"chunk,omitempty"`
AmbientContext map[string]any `json:"ambient_context,omitempty"`
LLMClient StructuredLLMClient `json:"-"`
Metadata map[string]any `json:"metadata,omitempty"`
}
```
Add:
```go
type ChunkArtifacts struct {
Chunk SourceChunk `json:"chunk"`
Candidates []artifacts.ArtifactCandidate `json:"candidates"`
}
type MergeRequest struct {
Source *source.SourceDocument `json:"-"`
LaneID string `json:"lane_id"`
ChunkArtifacts []ChunkArtifacts `json:"chunk_artifacts"`
Metadata map[string]any `json:"metadata,omitempty"`
}
type MergeResult struct {
Candidates []artifacts.ArtifactCandidate `json:"candidates"`
Warnings []Warning `json:"warnings,omitempty"`
}
type Merger interface {
Key() string
Merge(ctx context.Context, req MergeRequest) (MergeResult, error)
}
type NormalizeRequest struct {
Source *source.SourceDocument `json:"-"`
LaneID string `json:"lane_id"`
Candidates []artifacts.ArtifactCandidate `json:"candidates"`
Metadata map[string]any `json:"metadata,omitempty"`
}
type NormalizeResult struct {
Candidates []artifacts.ArtifactCandidate `json:"candidates"`
Warnings []Warning `json:"warnings,omitempty"`
}
type Normalizer interface {
Key() string
Normalize(ctx context.Context, req NormalizeRequest) (NormalizeResult, error)
}
type OutputRequest struct {
Manifest artifacts.RunManifest `json:"manifest"`
Approved []artifacts.Artifact `json:"approved,omitempty"`
Rejected []artifacts.RejectedArtifact `json:"rejected,omitempty"`
Warnings []Warning `json:"warnings,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"`
}
type OutputResult struct {
Bytes []byte `json:"-"`
ContentType string `json:"content_type,omitempty"`
Warnings []Warning `json:"warnings,omitempty"`
}
type OutputEncoder interface {
Key() string
Encode(ctx context.Context, req OutputRequest) (OutputResult, error)
}
```
If `gofmt` aligns fields differently, keep the formatted output.
### Required Behavior
- Existing fake extractor tests must still compile with `ExtractionRequest{Source: doc}`.
- `SourceChunk` is a framework contract type, not a core source type.
- `SourceChunk.Units` should be copied by implementations where mutation risk
exists; this stage only defines the contract.
### Required Tests
Update fake implementations in existing contract tests to prove:
- fake chunker satisfies `contracts.Chunker`;
- fake merger satisfies `contracts.Merger`;
- fake normalizer satisfies `contracts.Normalizer`;
- fake output encoder satisfies `contracts.OutputEncoder`;
- fake extractor can receive a `SourceChunk` and ambient context.
### Validation
Run:
```sh
gofmt -w internal/framework/contracts
go test ./internal/framework/contracts
go test ./...
```
## Stage 2: Module Metadata And Stage Registries
### Goal
Teach pipeline registries about module metadata and add registries for chunk,
merge, normalize, configured validators, and output modules.
### Files To Update
- `internal/framework/pipeline/input_registry.go`
- `internal/framework/pipeline/input_registry_test.go`
- `internal/framework/pipeline/extractor_registry.go`
- `internal/framework/pipeline/extractor_registry_test.go`
### Files To Add
- `internal/framework/pipeline/module.go`
- `internal/framework/pipeline/chunker_registry.go`
- `internal/framework/pipeline/chunker_registry_test.go`
- `internal/framework/pipeline/merger_registry.go`
- `internal/framework/pipeline/merger_registry_test.go`
- `internal/framework/pipeline/normalizer_registry.go`
- `internal/framework/pipeline/normalizer_registry_test.go`
- `internal/framework/pipeline/validator_registry.go`
- `internal/framework/pipeline/validator_registry_test.go`
- `internal/framework/pipeline/output_registry.go`
- `internal/framework/pipeline/output_registry_test.go`
### Required API
Add:
```go
type ModuleStage string
const (
StageInput ModuleStage = "input"
StageChunk ModuleStage = "chunk"
StageExtract ModuleStage = "extract"
StageMerge ModuleStage = "merge"
StageNormalize ModuleStage = "normalize"
StageValidate ModuleStage = "validate"
StageOutput ModuleStage = "output"
)
type ModuleSpec struct {
Key string
Stage ModuleStage
Provides []string
Requires []string
}
```
Add metadata registration methods to existing registries:
```go
func (r *InputAdapterRegistry) RegisterWithSpec(spec ModuleSpec, constructor InputAdapterConstructor) error
func (r *InputAdapterRegistry) Spec(key string) (ModuleSpec, bool)
func (r *ExtractorRegistry) RegisterWithSpec(spec ModuleSpec, constructor ExtractorConstructor) error
func (r *ExtractorRegistry) Spec(key string) (ModuleSpec, bool)
```
Keep existing `Register` methods. They should call `RegisterWithSpec` with a
default spec using the provided key and correct stage.
Add typed registries for other stages:
```go
type ChunkerConstructor func() (contracts.Chunker, error)
type ChunkerRegistry struct { /* unexported fields */ }
func NewChunkerRegistry() *ChunkerRegistry
func (r *ChunkerRegistry) Register(key string, constructor ChunkerConstructor) error
func (r *ChunkerRegistry) RegisterWithSpec(spec ModuleSpec, constructor ChunkerConstructor) error
func (r *ChunkerRegistry) Build(key string) (contracts.Chunker, error)
func (r *ChunkerRegistry) Spec(key string) (ModuleSpec, bool)
func (r *ChunkerRegistry) RegisteredKeys() []string
```
Repeat the same pattern for `MergerRegistry`, `NormalizerRegistry`,
`ValidatorRegistry`, and `OutputEncoderRegistry`.
`ValidatorRegistry` should use:
```go
type ValidatorConstructor func() (contracts.Validator, error)
```
Because `contracts.Validator` uses `Name()` rather than `Key()`,
`ValidatorRegistry.Build` must require `validator.Name()` to match the
registered key.
### Required Behavior
- Registry keys are trimmed.
- Specs are normalized by trimming `Key`, `Provides`, and `Requires`.
- Empty capability strings are ignored.
- `Provides` and `Requires` are deduplicated and sorted for deterministic
behavior.
- `RegisterWithSpec` rejects an empty key, wrong stage, nil constructor, and
duplicate key.
- `Spec` returns false for unknown keys and nil registries.
- `Build` rejects unknown keys, constructor errors, nil modules, and key
mismatches.
- Existing registry tests continue to pass.
### Required Tests
For each new registry, cover the same behavior as existing input/extractor
registries:
- successful registration and build;
- metadata registration and lookup;
- capability normalization;
- wrong stage rejection;
- key trimming;
- empty key rejection;
- duplicate key rejection;
- nil constructor rejection;
- unknown key build error;
- constructor error wrapping;
- nil module rejection;
- key mismatch rejection;
- sorted `RegisteredKeys`;
- nil registry behavior.
For `ValidatorRegistry`, key mismatch checks should compare the registry key to
`Validator.Name()`.
For existing input/extractor registries, add tests for metadata registration,
default specs from `Register`, capability normalization, and wrong stage
rejection.
### Validation
Run:
```sh
gofmt -w internal/framework/pipeline
go test ./internal/framework/pipeline
go test ./...
```
## Stage 3: Resolved Pipeline Model
### Goal
Add fixed-shape pipeline profile structs, default resolution, lane selection,
capability validation, and resolved pipeline digesting.
### Files To Add
- `internal/framework/pipeline/profile.go`
- `internal/framework/pipeline/profile_test.go`
### Files To Update
- `internal/core/artifacts/artifacts.go`
- `internal/core/artifacts/artifacts_test.go`
### Required API
Update `artifacts.RunManifest` to include:
```go
PipelineID string `json:"pipeline_id,omitempty"`
PipelineDigest string `json:"pipeline_digest,omitempty"`
```
Add lane-level manifest details rather than relying on the existing shared
`Extractors`, `Merger`, or `Normalizer` fields for multi-lane runs:
```go
type ArtifactLaneManifest struct {
ID string `json:"id"`
Extractor string `json:"extractor"`
Merger string `json:"merger"`
Normalizer string `json:"normalizer"`
Validators []string `json:"validators,omitempty"`
}
```
Then add:
```go
ArtifactLanes []ArtifactLaneManifest `json:"artifact_lanes,omitempty"`
```
Do not remove the existing singular fields in this checkpoint unless doing so is
required to make the package compile. Treat `ArtifactLanes` as the authoritative
manifest representation for checkpoint 3's multi-lane pipeline model.
Add pipeline model types:
```go
type ModuleBinding struct {
Module string `json:"module"`
LLMProfile string `json:"llm_profile,omitempty"`
Options map[string]any `json:"options,omitempty"`
}
type ArtifactLaneProfile struct {
Extract ModuleBinding `json:"extract"`
Merge ModuleBinding `json:"merge,omitempty"`
Normalize ModuleBinding `json:"normalize,omitempty"`
Validators []ModuleBinding `json:"validators,omitempty"`
}
type PipelineProfile struct {
ID string `json:"id"`
Input ModuleBinding `json:"input"`
Chunk ModuleBinding `json:"chunk,omitempty"`
Artifacts map[string]ArtifactLaneProfile `json:"artifacts"`
Output ModuleBinding `json:"output,omitempty"`
}
type ResolveOptions struct {
Only []string
}
type ResolvedArtifactLane struct {
ID string
Extract ModuleBinding
Merge ModuleBinding
Normalize ModuleBinding
Validators []ModuleBinding
}
type ResolvedPipeline struct {
ID string
Digest string
Input ModuleBinding
Chunk ModuleBinding
ArtifactLanes []ResolvedArtifactLane
Output ModuleBinding
}
```
Add defaults:
```go
const (
DefaultChunkModule = "generic"
DefaultMergeModule = "appendorder"
DefaultNormalizeModule = "noop"
DefaultOutputModule = "json"
DefaultLLMProfile = "default"
)
```
Add:
```go
type ModuleCatalog struct {
Inputs *InputAdapterRegistry
Chunkers *ChunkerRegistry
Extractors *ExtractorRegistry
Mergers *MergerRegistry
Normalizers *NormalizerRegistry
Validators *ValidatorRegistry
Outputs *OutputEncoderRegistry
}
func Binding(module string) ModuleBinding
func ResolvePipeline(profile PipelineProfile, options ResolveOptions, catalog ModuleCatalog) (ResolvedPipeline, error)
```
### Required Behavior
`ResolvePipeline` must:
- trim `PipelineProfile.ID`;
- reject empty pipeline IDs;
- require non-empty input module;
- require at least one artifact lane before and after `Only` filtering;
- apply defaults for missing chunk, merge, normalize, output, and binding
`llm_profile` values;
- trim all module keys;
- trim lane names in `ResolveOptions.Only`;
- reject empty or unknown lane names in `ResolveOptions.Only`;
- deduplicate repeated `Only` lane names;
- sort selected lane IDs alphabetically;
- reject unknown module keys using registry metadata, not constructors;
- validate flat capability requirements before execution;
- compute `ResolvedPipeline.Digest` from canonical JSON of the resolved
pipeline excluding the digest field itself.
Capability validation algorithm:
1. Start with capabilities provided by the input module.
2. Validate chunker requirements against current capabilities, then add chunker
provided capabilities.
3. For each selected lane, start with input plus chunk capabilities.
4. Validate extractor requirements, then add extractor provided capabilities.
5. Validate merger requirements, then add merger provided capabilities.
6. Validate normalizer requirements, then add normalizer provided capabilities.
7. Validate configured validator requirements in lane order, then add validator
provided capabilities. If no validators are configured for a lane, do not
attempt capability validation for extractor-owned default validators.
8. Validate output requirements against the union of pipeline-level capabilities
and all selected lane capabilities.
Error messages must name the pipeline ID, lane ID when applicable, stage, module
key, and missing capability when applicable.
`Binding(module)` should trim the module key and leave `LLMProfile` empty and
`Options` nil before resolution. Resolution should fill empty `LLMProfile`
values with `DefaultLLMProfile` on all resolved bindings.
### Required Tests
Cover:
- successful resolution with explicit modules;
- default chunk, merge, normalize, output, and `llm_profile`;
- lane selection with `Only`;
- `Only` trimming and deduplication;
- unknown `Only` lane rejection;
- empty `Only` lane rejection;
- empty artifact set rejection;
- empty pipeline ID rejection;
- missing input rejection;
- unknown module key rejection for each stage;
- missing capability rejection for input/chunk/extract/merge/normalize/validate/output
interactions;
- deterministic lane ordering;
- deterministic digest for equivalent input maps;
- digest changes when a module binding changes;
- manifest JSON still omits empty optional fields.
Use fake registries and fake specs only. Do not add config file parsing.
### Validation
Run:
```sh
gofmt -w internal/core/artifacts internal/framework/pipeline
go test ./internal/core/artifacts
go test ./internal/framework/pipeline
go test ./...
```
## Stage 4: Generic Merge And Normalize Helpers
### Goal
Add generic append-in-chunk-order merge and no-op normalization behavior inside
`internal/framework/pipeline`.
### Files To Add
- `internal/framework/pipeline/generic_stages.go`
- `internal/framework/pipeline/generic_stages_test.go`
### Required API
Add:
```go
type AppendOrderMerger struct{}
func (m AppendOrderMerger) Key() string
func (m AppendOrderMerger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error)
type NoopNormalizer struct{}
func (n NoopNormalizer) Key() string
func (n NoopNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error)
```
### Required Behavior
`AppendOrderMerger` must:
- return key `appendorder`;
- concatenate candidates by `ChunkArtifacts` slice order and candidate order;
- copy candidate slices so caller mutation does not affect the result;
- preserve source refs and metadata exactly;
- append no warnings.
`NoopNormalizer` must:
- return key `noop`;
- copy candidates so caller mutation does not affect the result;
- preserve ordering and source refs exactly;
- append no warnings.
### Required Tests
Cover:
- key values;
- append order across multiple chunks;
- stable candidate order within chunks;
- no-op normalize preserves order;
- result slices are caller-mutation safe;
- nil/empty input returns empty candidates and no error.
### Validation
Run:
```sh
gofmt -w internal/framework/pipeline
go test ./internal/framework/pipeline
go test ./...
```
## Stage 5: Pipeline Runner Refactor
### Goal
Refactor the existing runner from extractor-only execution to resolved pipeline
execution across input, chunk, extract, merge, normalize, validate, and output.
### Files To Update
- `internal/framework/pipeline/runner.go`
- `internal/framework/pipeline/runner_test.go`
- `internal/framework/pipeline/registry_integration_test.go`
### Required API
Replace the extractor-only runner constructor with:
```go
type Registries struct {
Inputs *InputAdapterRegistry
Chunkers *ChunkerRegistry
Extractors *ExtractorRegistry
Mergers *MergerRegistry
Normalizers *NormalizerRegistry
Validators *ValidatorRegistry
Outputs *OutputEncoderRegistry
}
type Runner struct {
// unexported fields
}
func New(registries Registries) *Runner
```
Replace `RunInput` with:
```go
type RunInput struct {
Pipeline ResolvedPipeline
SourceID string
Path string
RawInput []byte
LLMClient contracts.StructuredLLMClient
Metadata map[string]any
}
```
Replace or extend `RunOutput` with:
```go
type RunOutput struct {
Manifest artifacts.RunManifest `json:"manifest"`
Approved []artifacts.Artifact `json:"approved,omitempty"`
Rejected []artifacts.RejectedArtifact `json:"rejected,omitempty"`
Warnings []contracts.Warning `json:"warnings,omitempty"`
EncodedOutput []byte `json:"-"`
ContentType string `json:"content_type,omitempty"`
}
```
Keep the existing candidate metadata normalization behavior, but it should now
run per extractor and across all selected lanes.
### Required Behavior
`Run` must:
1. reject nil runner;
2. reject missing registries for stages used by the pipeline;
`Validators` is required only when at least one selected lane declares
validator bindings;
3. reject empty resolved pipeline ID or digest;
4. build the input adapter and parse `RawInput`;
5. validate the resulting `SourceDocument`;
6. build the chunker and produce chunks;
7. reject empty chunk results;
8. for each selected artifact lane in resolved order:
- build extractor, merger, and normalizer;
- extract from every chunk serially;
- pass `Source`, active `Chunk`, `LLMClient`, and metadata to the extractor;
- normalize candidate metadata with global monotonically increasing indices;
- merge per-chunk candidates;
- normalize merged candidates;
- run configured lane validators against normalized candidates when the lane
declares validators;
- otherwise run the extractor-owned default validator chain;
- append approved artifacts and rejected artifacts to output;
9. build the output encoder and encode the final output bundle;
10. populate `RunManifest` with pipeline ID, pipeline digest, input module,
chunker, lane-level extractor/merger/normalizer/validator keys, output
encoder, source digest, and validation status;
11. return partial output plus wrapped errors on failure.
Validation status:
- `approved` when all candidates from all lanes survive validation and no lane
returns rejected artifacts;
- `rejected` when at least one candidate is rejected and execution otherwise
succeeds;
- `failed` when returning an error after a manifest has been initialized.
Warnings:
- collect warnings from input, chunk, extract, merge, normalize, validator, and
output stages where those stages expose warnings;
- existing input adapters do not expose warnings, so no input warnings are
required in this checkpoint.
Do not validate source references inside the runner in checkpoint 3. Source
reference validation remains a later deterministic validator.
### Required Tests
Refactor existing runner tests and add coverage for:
- nil runner error;
- missing registry errors;
- invalid resolved pipeline error;
- input adapter build and parse errors;
- invalid source document error;
- chunker build and chunk errors;
- empty chunk result error;
- extractor runs once per chunk;
- extractor receives active chunk and LLM client;
- merge receives per-chunk candidates;
- normalize receives merged candidates;
- validator approvals and rejections still work;
- configured validators are built and run in lane order;
- extractor-owned default validators run when a lane does not configure
validators;
- configured validators replace extractor-owned default validators when present;
- global candidate indices across lanes and chunks;
- warnings from chunk, extract, merge, normalize, validator, and output stages;
- output encoder receives manifest and artifacts;
- manifest pipeline ID, digest, and artifact lane details are populated;
- partial output is returned when a later lane fails.
Use fake modules only.
### Validation
Run:
```sh
gofmt -w internal/framework/pipeline
go test ./internal/framework/pipeline
go test ./...
```
## Stage 6: Fixture-Driven Walking Skeleton
### Goal
Add an end-to-end fixture-driven integration test that exercises the full staged
path with fake modules and a fake LLM client.
### Files To Add
- `internal/framework/pipeline/testdata/walking_skeleton_input.json`
- `internal/framework/pipeline/testdata/walking_skeleton_output.json`
- `internal/framework/pipeline/walking_skeleton_test.go`
### Required Fixture Shape
Use a small input fixture with two or three source units in a simple fake JSON
format. Do not use Seriatim.
Example input shape:
```json
{
"id": "fixture-source",
"units": [
{"id": "u1", "text": "First event."},
{"id": "u2", "text": "Second event."},
{"id": "u3", "text": "Third event."}
]
}
```
The expected output fixture should contain:
- manifest with `pipeline_id` and `pipeline_digest`;
- approved artifacts emitted from multiple chunks;
- no rejected artifacts for the happy path;
- warnings only if fake stages deliberately emit them.
Compare expected output by unmarshaled structural equality, not raw bytes, so
formatting differences do not fail the test.
### Required Test Setup
Register fake modules with metadata:
- fake input adapter key `fake/input`, provides `plain_text`;
- fake chunker key `fake/chunk`, requires `plain_text`, provides `chunks`;
- fake extractor key `fake/extract`, requires `chunks`, provides
`fake_artifacts`;
- append-order merger key `appendorder`, requires `fake_artifacts`;
- no-op normalizer key `noop`;
- fake output encoder key `json`.
Use an in-memory `PipelineProfile`:
```go
PipelineProfile{
ID: "walking-skeleton",
Input: Binding("fake/input"),
Chunk: Binding("fake/chunk"),
Artifacts: map[string]ArtifactLaneProfile{
"events": {Extract: Binding("fake/extract")},
},
Output: Binding("json"),
}
```
Resolve the profile, run the runner with fixture bytes and fake LLM client, then
assert the encoded output matches the expected fixture structurally.
### Required Behavior
- The fake input adapter parses raw fixture bytes into `SourceDocument`.
- The fake chunker produces at least two chunks.
- The fake extractor calls the fake structured LLM client once per chunk.
- The fake extractor returns one artifact candidate per chunk.
- The append-order merger preserves chunk order.
- The no-op normalizer preserves candidates.
- The fake output encoder produces deterministic JSON bytes.
- The test fails before execution if required capabilities are missing.
### Additional Tests
Add focused tests for the walking skeleton failure path:
- missing required capability fails during resolution;
- `Only` with an unknown lane fails during resolution;
- fake LLM call count equals chunk count in the happy path.
### Validation
Run:
```sh
gofmt -w internal/framework/pipeline
go test ./internal/framework/pipeline
go test ./...
```
## Stage 7: Final Checkpoint 3 Review Pass
### Goal
Clean up naming, formatting, and accidental scope creep before checkpoint 3 is
considered complete.
### Required Review
Check:
- no Seriatim parser exists;
- no D&D module exists;
- no production config file loader exists;
- no CLI behavior was added;
- no LLM provider code exists;
- no prompt, response schema, diagnostics, or durable output package exists;
- no new framework package was created beyond `contracts`, `pipeline`, and
`validate`;
- stage contracts remain source/domain agnostic;
- capabilities remain flat strings;
- resolved pipeline profiles remain fixed-shape templates;
- walking skeleton uses fake modules only.
### Required Validation
Run:
```sh
gofmt -w internal/core internal/framework
go test ./...
go build ./cmd/notarius
```
## Open Questions
None. The deferred choices identified while drafting this plan are intentionally
out of scope for checkpoint 3 and should remain deferred until later roadmap
items.

36
internal/framework/contracts/contracts.go
View File

@@ -35,10 +35,12 @@ type StructuredLLMClient interface {
} }
type ParseRequest struct { type ParseRequest struct {
SourceID string `json:"source_id,omitempty"` SourceID string `json:"source_id,omitempty"`
Path string `json:"path,omitempty"` Path string `json:"path,omitempty"`
Raw []byte `json:"-"` Raw []byte `json:"-"`
Metadata map[string]any `json:"metadata,omitempty"` LLMProfile string `json:"llm_profile,omitempty"`
Options map[string]any `json:"options,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"`
} }
type InputAdapter interface { type InputAdapter interface {
@@ -55,8 +57,10 @@ type SourceChunk struct {
} }
type ChunkRequest struct { type ChunkRequest struct {
Source *source.SourceDocument `json:"-"` Source *source.SourceDocument `json:"-"`
Metadata map[string]any `json:"metadata,omitempty"` LLMProfile string `json:"llm_profile,omitempty"`
Options map[string]any `json:"options,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"`
} }
type ChunkResult struct { type ChunkResult struct {
@@ -74,6 +78,8 @@ type ExtractionRequest struct {
Chunk *SourceChunk `json:"chunk,omitempty"` Chunk *SourceChunk `json:"chunk,omitempty"`
AmbientContext map[string]any `json:"ambient_context,omitempty"` AmbientContext map[string]any `json:"ambient_context,omitempty"`
LLMClient StructuredLLMClient `json:"-"` LLMClient StructuredLLMClient `json:"-"`
LLMProfile string `json:"llm_profile,omitempty"`
Options map[string]any `json:"options,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"` Metadata map[string]any `json:"metadata,omitempty"`
} }
@@ -99,6 +105,8 @@ type MergeRequest struct {
Source *source.SourceDocument `json:"-"` Source *source.SourceDocument `json:"-"`
LaneID string `json:"lane_id"` LaneID string `json:"lane_id"`
ChunkArtifacts []ChunkArtifacts `json:"chunk_artifacts"` ChunkArtifacts []ChunkArtifacts `json:"chunk_artifacts"`
LLMProfile string `json:"llm_profile,omitempty"`
Options map[string]any `json:"options,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"` Metadata map[string]any `json:"metadata,omitempty"`
} }
@@ -116,6 +124,8 @@ type NormalizeRequest struct {
Source *source.SourceDocument `json:"-"` Source *source.SourceDocument `json:"-"`
LaneID string `json:"lane_id"` LaneID string `json:"lane_id"`
Candidates []artifacts.ArtifactCandidate `json:"candidates"` Candidates []artifacts.ArtifactCandidate `json:"candidates"`
LLMProfile string `json:"llm_profile,omitempty"`
Options map[string]any `json:"options,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"` Metadata map[string]any `json:"metadata,omitempty"`
} }
@@ -132,6 +142,8 @@ type Normalizer interface {
type ValidationRequest struct { type ValidationRequest struct {
Source *source.SourceDocument `json:"-"` Source *source.SourceDocument `json:"-"`
Candidates []artifacts.ArtifactCandidate `json:"candidates"` Candidates []artifacts.ArtifactCandidate `json:"candidates"`
LLMProfile string `json:"llm_profile,omitempty"`
Options map[string]any `json:"options,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"` Metadata map[string]any `json:"metadata,omitempty"`
} }
@@ -161,11 +173,13 @@ type Warning struct {
} }
type OutputRequest struct { type OutputRequest struct {
Manifest artifacts.RunManifest `json:"manifest"` Manifest artifacts.RunManifest `json:"manifest"`
Approved []artifacts.Artifact `json:"approved,omitempty"` Approved []artifacts.Artifact `json:"approved,omitempty"`
Rejected []artifacts.RejectedArtifact `json:"rejected,omitempty"` Rejected []artifacts.RejectedArtifact `json:"rejected,omitempty"`
Warnings []Warning `json:"warnings,omitempty"` Warnings []Warning `json:"warnings,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"` LLMProfile string `json:"llm_profile,omitempty"`
Options map[string]any `json:"options,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"`
} }
type OutputResult struct { type OutputResult struct {

103
internal/framework/pipeline/runner.go
View File

@@ -65,10 +65,12 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
return failOutput(output), fmt.Errorf("build input adapter %q: %w", input.Pipeline.Input.Module, err) return failOutput(output), fmt.Errorf("build input adapter %q: %w", input.Pipeline.Input.Module, err)
} }
doc, err := adapter.Parse(ctx, contracts.ParseRequest{ doc, err := adapter.Parse(ctx, contracts.ParseRequest{
SourceID: input.SourceID, SourceID: input.SourceID,
Path: input.Path, Path: input.Path,
Raw: input.RawInput, Raw: input.RawInput,
Metadata: input.Metadata, LLMProfile: input.Pipeline.Input.LLMProfile,
Options: cloneOptions(input.Pipeline.Input.Options),
Metadata: input.Metadata,
}) })
if err != nil { if err != nil {
return failOutput(output), fmt.Errorf("parse input with adapter %q: %w", adapter.Key(), err) return failOutput(output), fmt.Errorf("parse input with adapter %q: %w", adapter.Key(), err)
@@ -83,8 +85,10 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
return failOutput(output), fmt.Errorf("build chunker %q: %w", input.Pipeline.Chunk.Module, err) return failOutput(output), fmt.Errorf("build chunker %q: %w", input.Pipeline.Chunk.Module, err)
} }
chunkResult, err := chunker.Chunk(ctx, contracts.ChunkRequest{ chunkResult, err := chunker.Chunk(ctx, contracts.ChunkRequest{
Source: doc, Source: doc,
Metadata: input.Metadata, LLMProfile: input.Pipeline.Chunk.LLMProfile,
Options: cloneOptions(input.Pipeline.Chunk.Options),
Metadata: input.Metadata,
}) })
output.Warnings = append(output.Warnings, chunkResult.Warnings...) output.Warnings = append(output.Warnings, chunkResult.Warnings...)
if err != nil { if err != nil {
@@ -112,11 +116,13 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
return failOutput(output), fmt.Errorf("build output encoder %q: %w", input.Pipeline.Output.Module, err) return failOutput(output), fmt.Errorf("build output encoder %q: %w", input.Pipeline.Output.Module, err)
} }
encoded, err := encoder.Encode(ctx, contracts.OutputRequest{ encoded, err := encoder.Encode(ctx, contracts.OutputRequest{
Manifest: output.Manifest, Manifest: output.Manifest,
Approved: output.Approved, Approved: output.Approved,
Rejected: output.Rejected, Rejected: output.Rejected,
Warnings: output.Warnings, Warnings: output.Warnings,
Metadata: input.Metadata, LLMProfile: input.Pipeline.Output.LLMProfile,
Options: cloneOptions(input.Pipeline.Output.Options),
Metadata: input.Metadata,
}) })
output.Warnings = append(output.Warnings, encoded.Warnings...) output.Warnings = append(output.Warnings, encoded.Warnings...)
if err != nil { if err != nil {
@@ -142,24 +148,28 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
return fmt.Errorf("build normalizer %q for lane %q: %w", lane.Normalize.Module, lane.ID, err) return fmt.Errorf("build normalizer %q for lane %q: %w", lane.Normalize.Module, lane.ID, err)
} }
var validators []contracts.Validator var validators []validatorExecution
if len(lane.Validators) > 0 { if len(lane.Validators) > 0 {
validators, err = r.buildConfiguredValidators(lane) validators, err = r.buildConfiguredValidators(lane)
if err != nil { if err != nil {
return err return err
} }
} else { } else {
validators = extractor.Validators() for _, validator := range extractor.Validators() {
validators = append(validators, validatorExecution{validator: validator})
}
} }
chunkArtifacts := make([]contracts.ChunkArtifacts, 0, len(chunks)) chunkArtifacts := make([]contracts.ChunkArtifacts, 0, len(chunks))
for index := range chunks { for index := range chunks {
chunk := chunks[index] chunk := chunks[index]
result, err := extractor.Extract(ctx, contracts.ExtractionRequest{ result, err := extractor.Extract(ctx, contracts.ExtractionRequest{
Source: doc, Source: doc,
Chunk: &chunk, Chunk: &chunk,
LLMClient: input.LLMClient, LLMClient: input.LLMClient,
Metadata: input.Metadata, LLMProfile: lane.Extract.LLMProfile,
Options: cloneOptions(lane.Extract.Options),
Metadata: input.Metadata,
}) })
output.Warnings = append(output.Warnings, result.Warnings...) output.Warnings = append(output.Warnings, result.Warnings...)
if err != nil { if err != nil {
@@ -180,6 +190,8 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
Source: doc, Source: doc,
LaneID: lane.ID, LaneID: lane.ID,
ChunkArtifacts: chunkArtifacts, ChunkArtifacts: chunkArtifacts,
LLMProfile: lane.Merge.LLMProfile,
Options: cloneOptions(lane.Merge.Options),
Metadata: input.Metadata, Metadata: input.Metadata,
}) })
output.Warnings = append(output.Warnings, mergeResult.Warnings...) output.Warnings = append(output.Warnings, mergeResult.Warnings...)
@@ -191,6 +203,8 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
Source: doc, Source: doc,
LaneID: lane.ID, LaneID: lane.ID,
Candidates: mergeResult.Candidates, Candidates: mergeResult.Candidates,
LLMProfile: lane.Normalize.LLMProfile,
Options: cloneOptions(lane.Normalize.Options),
Metadata: input.Metadata, Metadata: input.Metadata,
}) })
output.Warnings = append(output.Warnings, normalizeResult.Warnings...) output.Warnings = append(output.Warnings, normalizeResult.Warnings...)
@@ -198,6 +212,10 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
return fmt.Errorf("normalize lane %q with normalizer %q: %w", lane.ID, normalizer.Key(), err) return fmt.Errorf("normalize lane %q with normalizer %q: %w", lane.ID, normalizer.Key(), err)
} }
if err := validateCandidateEnvelope(extractor, normalizeResult.Candidates); err != nil {
return fmt.Errorf("validate normalized candidates for lane %q: %w", lane.ID, err)
}
approved, rejected, warnings, err := runValidators(ctx, extractor.Key(), validators, doc, normalizeResult.Candidates, input.Metadata) approved, rejected, warnings, err := runValidators(ctx, extractor.Key(), validators, doc, normalizeResult.Candidates, input.Metadata)
output.Warnings = append(output.Warnings, warnings...) output.Warnings = append(output.Warnings, warnings...)
output.Rejected = append(output.Rejected, rejected...) output.Rejected = append(output.Rejected, rejected...)
@@ -211,14 +229,22 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
return nil return nil
} }
func (r *Runner) buildConfiguredValidators(lane ResolvedArtifactLane) ([]contracts.Validator, error) { type validatorExecution struct {
validators := make([]contracts.Validator, 0, len(lane.Validators)) validator contracts.Validator
binding ModuleBinding
}
func (r *Runner) buildConfiguredValidators(lane ResolvedArtifactLane) ([]validatorExecution, error) {
validators := make([]validatorExecution, 0, len(lane.Validators))
for _, binding := range lane.Validators { for _, binding := range lane.Validators {
validator, err := r.registries.Validators.Build(binding.Module) validator, err := r.registries.Validators.Build(binding.Module)
if err != nil { if err != nil {
return nil, fmt.Errorf("build validator %q for lane %q: %w", binding.Module, lane.ID, err) return nil, fmt.Errorf("build validator %q for lane %q: %w", binding.Module, lane.ID, err)
} }
validators = append(validators, validator) validators = append(validators, validatorExecution{
validator: validator,
binding: binding,
})
} }
return validators, nil return validators, nil
} }
@@ -359,18 +385,51 @@ func normalizeCandidates(extractor contracts.Extractor, candidates []artifacts.A
return normalized, nil return normalized, nil
} }
func runValidators(ctx context.Context, extractorKey string, validators []contracts.Validator, doc *source.SourceDocument, candidates []artifacts.ArtifactCandidate, metadata map[string]any) ([]artifacts.ArtifactCandidate, []artifacts.RejectedArtifact, []contracts.Warning, error) { func validateCandidateEnvelope(extractor contracts.Extractor, candidates []artifacts.ArtifactCandidate) error {
seen := make(map[int]struct{}, len(candidates))
for _, candidate := range candidates {
if _, ok := seen[candidate.Index]; ok {
return fmt.Errorf("candidate index %d is duplicated", candidate.Index)
}
seen[candidate.Index] = struct{}{}
if candidate.ExtractorKey == "" {
return fmt.Errorf("candidate index %d extractor_key must not be empty", candidate.Index)
}
if candidate.ExtractorKey != extractor.Key() {
return fmt.Errorf("candidate index %d extractor_key %q does not match extractor %q", candidate.Index, candidate.ExtractorKey, extractor.Key())
}
if candidate.ArtifactType == "" {
return fmt.Errorf("candidate index %d artifact_type must not be empty", candidate.Index)
}
if candidate.ArtifactType != extractor.ArtifactType() {
return fmt.Errorf("candidate index %d artifact_type %q does not match extractor %q artifact type %q", candidate.Index, candidate.ArtifactType, extractor.Key(), extractor.ArtifactType())
}
if candidate.SchemaVersion == "" {
return fmt.Errorf("candidate index %d schema_version must not be empty", candidate.Index)
}
if candidate.SchemaVersion != extractor.SchemaVersion() {
return fmt.Errorf("candidate index %d schema_version %q does not match extractor %q schema version %q", candidate.Index, candidate.SchemaVersion, extractor.Key(), extractor.SchemaVersion())
}
}
return nil
}
func runValidators(ctx context.Context, extractorKey string, validators []validatorExecution, doc *source.SourceDocument, candidates []artifacts.ArtifactCandidate, metadata map[string]any) ([]artifacts.ArtifactCandidate, []artifacts.RejectedArtifact, []contracts.Warning, error) {
eligible := candidates eligible := candidates
var rejected []artifacts.RejectedArtifact var rejected []artifacts.RejectedArtifact
var warnings []contracts.Warning var warnings []contracts.Warning
for validatorIndex, validator := range validators { for validatorIndex, execution := range validators {
validator := execution.validator
if validator == nil { if validator == nil {
return nil, rejected, warnings, fmt.Errorf("extractor %q validator[%d] must not be nil", extractorKey, validatorIndex) return nil, rejected, warnings, fmt.Errorf("extractor %q validator[%d] must not be nil", extractorKey, validatorIndex)
} }
result, err := validator.Validate(ctx, contracts.ValidationRequest{ result, err := validator.Validate(ctx, contracts.ValidationRequest{
Source: doc, Source: doc,
Candidates: eligible, Candidates: eligible,
LLMProfile: execution.binding.LLMProfile,
Options: cloneOptions(execution.binding.Options),
Metadata: metadata, Metadata: metadata,
}) })
warnings = append(warnings, result.Warnings...) warnings = append(warnings, result.Warnings...)

122
internal/framework/pipeline/runner_test.go
View File

@@ -311,6 +311,66 @@ func TestRunPassesInputRequestFields(t *testing.T) {
} }
} }
func TestRunPassesModuleBindingConfigToStageRequests(t *testing.T) {
modules := defaultRunnerModules()
pipeline := resolvedPipelineWithValidators("configured")
pipeline.Input = ModuleBinding{Module: "input", LLMProfile: "input-profile", Options: map[string]any{"input_option": "input-value"}}
pipeline.Chunk = ModuleBinding{Module: "chunk", LLMProfile: "chunk-profile", Options: map[string]any{"chunk_option": "chunk-value"}}
pipeline.Output = ModuleBinding{Module: "output", LLMProfile: "output-profile", Options: map[string]any{"output_option": "output-value"}}
pipeline.ArtifactLanes[0].Extract = ModuleBinding{Module: "extract-alpha", LLMProfile: "extract-profile", Options: map[string]any{"extract_option": "extract-value"}}
pipeline.ArtifactLanes[0].Merge = ModuleBinding{Module: "merge", LLMProfile: "merge-profile", Options: map[string]any{"merge_option": "merge-value"}}
pipeline.ArtifactLanes[0].Normalize = ModuleBinding{Module: "normalize", LLMProfile: "normalize-profile", Options: map[string]any{"normalize_option": "normalize-value"}}
pipeline.ArtifactLanes[0].Validators[0] = ModuleBinding{Module: "configured", LLMProfile: "validator-profile", Options: map[string]any{"validator_option": "validator-value"}}
_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: pipeline})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
if got := modules.input.requests[0].LLMProfile; got != "input-profile" {
t.Fatalf("input LLMProfile = %q, want input-profile", got)
}
if got := modules.input.requests[0].Options["input_option"]; got != "input-value" {
t.Fatalf("input Options = %#v, want input option", modules.input.requests[0].Options)
}
if got := modules.chunker.requests[0].LLMProfile; got != "chunk-profile" {
t.Fatalf("chunk LLMProfile = %q, want chunk-profile", got)
}
if got := modules.chunker.requests[0].Options["chunk_option"]; got != "chunk-value" {
t.Fatalf("chunk Options = %#v, want chunk option", modules.chunker.requests[0].Options)
}
if got := modules.extractors["extract-alpha"].requests[0].LLMProfile; got != "extract-profile" {
t.Fatalf("extract LLMProfile = %q, want extract-profile", got)
}
if got := modules.extractors["extract-alpha"].requests[0].Options["extract_option"]; got != "extract-value" {
t.Fatalf("extract Options = %#v, want extract option", modules.extractors["extract-alpha"].requests[0].Options)
}
if got := modules.mergers["merge"].requests[0].LLMProfile; got != "merge-profile" {
t.Fatalf("merge LLMProfile = %q, want merge-profile", got)
}
if got := modules.mergers["merge"].requests[0].Options["merge_option"]; got != "merge-value" {
t.Fatalf("merge Options = %#v, want merge option", modules.mergers["merge"].requests[0].Options)
}
if got := modules.normalizers["normalize"].requests[0].LLMProfile; got != "normalize-profile" {
t.Fatalf("normalize LLMProfile = %q, want normalize-profile", got)
}
if got := modules.normalizers["normalize"].requests[0].Options["normalize_option"]; got != "normalize-value" {
t.Fatalf("normalize Options = %#v, want normalize option", modules.normalizers["normalize"].requests[0].Options)
}
if got := modules.validators["configured"].requests[0].LLMProfile; got != "validator-profile" {
t.Fatalf("validator LLMProfile = %q, want validator-profile", got)
}
if got := modules.validators["configured"].requests[0].Options["validator_option"]; got != "validator-value" {
t.Fatalf("validator Options = %#v, want validator option", modules.validators["configured"].requests[0].Options)
}
if got := modules.output.requests[0].LLMProfile; got != "output-profile" {
t.Fatalf("output LLMProfile = %q, want output-profile", got)
}
if got := modules.output.requests[0].Options["output_option"]; got != "output-value" {
t.Fatalf("output Options = %#v, want output option", modules.output.requests[0].Options)
}
}
func TestRunPassesPerChunkCandidatesToMergeAndNormalize(t *testing.T) { func TestRunPassesPerChunkCandidatesToMergeAndNormalize(t *testing.T) {
modules := defaultRunnerModules() modules := defaultRunnerModules()
@@ -346,6 +406,54 @@ func TestRunPassesPerChunkCandidatesToMergeAndNormalize(t *testing.T) {
} }
} }
func TestRunRejectsInvalidPostNormalizeCandidateEnvelope(t *testing.T) {
tests := []struct {
name string
candidates []artifacts.ArtifactCandidate
want string
}{
{
name: "duplicate index",
candidates: []artifacts.ArtifactCandidate{
runnerCandidate(0),
runnerCandidate(0),
},
want: "duplicated",
},
{
name: "missing extractor key",
candidates: []artifacts.ArtifactCandidate{
{Index: 0, ArtifactType: "artifact", SchemaVersion: "v1", Payload: []byte(`{"value":true}`)},
},
want: "extractor_key",
},
{
name: "mismatched schema version",
candidates: []artifacts.ArtifactCandidate{
{Index: 0, ExtractorKey: "extract-alpha", ArtifactType: "artifact", SchemaVersion: "other", Payload: []byte(`{"value":true}`)},
},
want: "schema_version",
},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
modules := defaultRunnerModules()
modules.normalizers["normalize"].result = test.candidates
output, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
assertRunError(t, err, test.want)
if output.Manifest.ValidationStatus != "failed" {
t.Fatalf("ValidationStatus = %q, want failed", output.Manifest.ValidationStatus)
}
if len(output.Approved) != 0 {
t.Fatalf("len(Approved) = %d, want no approved artifacts", len(output.Approved))
}
})
}
}
func TestRunValidatorApprovalAndRejection(t *testing.T) { func TestRunValidatorApprovalAndRejection(t *testing.T) {
modules := defaultRunnerModules() modules := defaultRunnerModules()
rejectFirst := &runnerValidator{ rejectFirst := &runnerValidator{
@@ -784,6 +892,7 @@ type runnerExtractor struct {
validators []contracts.Validator validators []contracts.Validator
warnings []contracts.Warning warnings []contracts.Warning
err error err error
requests []contracts.ExtractionRequest
seenChunkIDs []string seenChunkIDs []string
seenLLMClients []contracts.StructuredLLMClient seenLLMClients []contracts.StructuredLLMClient
seenMetadata []map[string]any seenMetadata []map[string]any
@@ -806,6 +915,7 @@ func (extractor *runnerExtractor) Validators() []contracts.Validator {
} }
func (extractor *runnerExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) { func (extractor *runnerExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) {
extractor.requests = append(extractor.requests, req)
if req.Chunk != nil { if req.Chunk != nil {
extractor.seenChunkIDs = append(extractor.seenChunkIDs, req.Chunk.ID) extractor.seenChunkIDs = append(extractor.seenChunkIDs, req.Chunk.ID)
} }
@@ -880,6 +990,7 @@ type runnerValidator struct {
err error err error
order *[]string order *[]string
calls int calls int
requests []contracts.ValidationRequest
} }
func (validator *runnerValidator) Name() string { func (validator *runnerValidator) Name() string {
@@ -888,6 +999,7 @@ func (validator *runnerValidator) Name() string {
func (validator *runnerValidator) Validate(ctx context.Context, req contracts.ValidationRequest) (contracts.ValidationResult, error) { func (validator *runnerValidator) Validate(ctx context.Context, req contracts.ValidationRequest) (contracts.ValidationResult, error) {
validator.calls++ validator.calls++
validator.requests = append(validator.requests, req)
if validator.order != nil { if validator.order != nil {
*validator.order = append(*validator.order, validator.name) *validator.order = append(*validator.order, validator.name)
} }
@@ -981,6 +1093,16 @@ func candidateIndices(candidates []artifacts.ArtifactCandidate) []int {
return indices return indices
} }
func runnerCandidate(index int) artifacts.ArtifactCandidate {
return artifacts.ArtifactCandidate{
Index: index,
ExtractorKey: "extract-alpha",
ArtifactType: "artifact",
SchemaVersion: "v1",
Payload: []byte(`{"value":true}`),
}
}
func assertRunError(t *testing.T, err error, want string) { func assertRunError(t *testing.T, err error, want string) {
t.Helper() t.Helper()