Add pipeline stage contracts

This commit is contained in:
2026-07-03 15:24:07 +00:00
parent 3cf2ac577f
commit 75a0a9fa79
3 changed files with 480 additions and 10 deletions

View File

@@ -46,10 +46,35 @@ type InputAdapter interface {
Parse(ctx context.Context, req ParseRequest) (*source.SourceDocument, error)
}
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)
}
type ExtractionRequest struct {
Source *source.SourceDocument `json:"-"`
LLMClient StructuredLLMClient `json:"-"`
Metadata map[string]any `json:"metadata,omitempty"`
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"`
}
type ExtractionResult struct {
@@ -65,6 +90,45 @@ type Extractor interface {
Extract(ctx context.Context, req ExtractionRequest) (ExtractionResult, error)
}
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 ValidationRequest struct {
Source *source.SourceDocument `json:"-"`
Candidates []artifacts.ArtifactCandidate `json:"candidates"`
@@ -95,3 +159,22 @@ type Warning struct {
ReasonCode string `json:"reason_code"`
Message string `json:"message"`
}
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)
}