378 lines
13 KiB
Go
378 lines
13 KiB
Go
package contracts
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
|
|
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
|
|
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
|
|
)
|
|
|
|
type StructuredCompletionRequest struct {
|
|
StageName string `json:"stage_name"`
|
|
PromptID string `json:"prompt_id,omitempty"`
|
|
PromptVersion string `json:"prompt_version,omitempty"`
|
|
ProfileID string `json:"profile_id,omitempty"`
|
|
SessionID string `json:"session_id,omitempty"`
|
|
Inputs LLMInputSet `json:"inputs,omitempty"`
|
|
Vars map[string]any `json:"vars,omitempty"`
|
|
}
|
|
|
|
type StructuredCompletionResponse struct {
|
|
Content json.RawMessage `json:"content"`
|
|
Provider string `json:"provider,omitempty"`
|
|
Model string `json:"model,omitempty"`
|
|
ProfileID string `json:"profile_id,omitempty"`
|
|
PromptTokens int `json:"prompt_tokens,omitempty"`
|
|
CompletionTokens int `json:"completion_tokens,omitempty"`
|
|
TotalTokens int `json:"total_tokens,omitempty"`
|
|
}
|
|
|
|
type StructuredLLMClient interface {
|
|
CompleteStructured(ctx context.Context, req StructuredCompletionRequest, out any) (StructuredCompletionResponse, error)
|
|
}
|
|
|
|
type LLMProfileManifestProvider interface {
|
|
LLMProfileManifests() []artifacts.LLMProfileManifest
|
|
}
|
|
|
|
type LLMInputMaterial struct {
|
|
Name string `json:"name"`
|
|
MediaType string `json:"media_type,omitempty"`
|
|
Content []byte `json:"-"`
|
|
Digest string `json:"digest,omitempty"`
|
|
OriginURI string `json:"origin_uri,omitempty"`
|
|
SizeBytes int64 `json:"size_bytes,omitempty"`
|
|
}
|
|
|
|
func NewLLMInputMaterial(name string, mediaType string, content []byte, digest string, originURI string) LLMInputMaterial {
|
|
return LLMInputMaterial{
|
|
Name: name,
|
|
MediaType: mediaType,
|
|
Content: append([]byte(nil), content...),
|
|
Digest: digest,
|
|
OriginURI: originURI,
|
|
SizeBytes: int64(len(content)),
|
|
}
|
|
}
|
|
|
|
func (material LLMInputMaterial) Clone() LLMInputMaterial {
|
|
material.Content = append([]byte(nil), material.Content...)
|
|
return material
|
|
}
|
|
|
|
type LLMInputSet map[string]LLMInputMaterial
|
|
|
|
func (set LLMInputSet) Clone() LLMInputSet {
|
|
if len(set) == 0 {
|
|
return nil
|
|
}
|
|
out := make(LLMInputSet, len(set))
|
|
for key, material := range set {
|
|
out[key] = material.Clone()
|
|
}
|
|
return out
|
|
}
|
|
|
|
type ParseRequest struct {
|
|
SourceID string `json:"source_id,omitempty"`
|
|
Path string `json:"path,omitempty"`
|
|
Raw []byte `json:"-"`
|
|
LLMProfile string `json:"llm_profile,omitempty"`
|
|
Options map[string]any `json:"options,omitempty"`
|
|
Metadata map[string]any `json:"metadata,omitempty"`
|
|
}
|
|
|
|
type InputAdapter interface {
|
|
Key() string
|
|
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"`
|
|
StartUnitID int `json:"start_unit_id"`
|
|
EndUnitID int `json:"end_unit_id"`
|
|
Content []byte `json:"-"`
|
|
MediaType string `json:"media_type"`
|
|
Units []source.SourceUnit `json:"units"`
|
|
Metadata map[string]any `json:"metadata,omitempty"`
|
|
}
|
|
|
|
type ChunkRequest struct {
|
|
Source *source.SourceDocument `json:"-"`
|
|
SourceInput LLMInputMaterial `json:"source_input,omitempty"`
|
|
SessionID string `json:"session_id,omitempty"`
|
|
References ReferenceSet `json:"references,omitempty"`
|
|
LLMClient StructuredLLMClient `json:"-"`
|
|
LLMProfile string `json:"llm_profile,omitempty"`
|
|
Options map[string]any `json:"options,omitempty"`
|
|
Metadata map[string]any `json:"metadata,omitempty"`
|
|
}
|
|
|
|
type ChunkResult struct {
|
|
Chunks []SourceChunk `json:"chunks"`
|
|
Warnings []Warning `json:"warnings,omitempty"`
|
|
}
|
|
|
|
type Chunker interface {
|
|
Key() string
|
|
ReferenceSlots() []ReferenceSlot
|
|
Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error)
|
|
}
|
|
|
|
const (
|
|
ReferenceBindingSourceConfig = "config"
|
|
ReferenceBindingSourceCLI = "cli"
|
|
)
|
|
|
|
type ReferenceSlot struct {
|
|
Name string `json:"name"`
|
|
Description string `json:"description,omitempty"`
|
|
Required bool `json:"required,omitempty"`
|
|
AcceptedMediaTypes []string `json:"accepted_media_types,omitempty"`
|
|
Multiple bool `json:"multiple,omitempty"`
|
|
MaxBytes int64 `json:"max_bytes,omitempty"`
|
|
}
|
|
|
|
func CloneReferenceSlots(slots []ReferenceSlot) []ReferenceSlot {
|
|
if len(slots) == 0 {
|
|
return nil
|
|
}
|
|
out := make([]ReferenceSlot, len(slots))
|
|
for i, slot := range slots {
|
|
slot.AcceptedMediaTypes = append([]string(nil), slot.AcceptedMediaTypes...)
|
|
out[i] = slot
|
|
}
|
|
return out
|
|
}
|
|
|
|
type ReferenceOrigin struct {
|
|
Type string `json:"type"`
|
|
URI string `json:"uri,omitempty"`
|
|
}
|
|
|
|
type ReferenceItem struct {
|
|
SlotName string `json:"slot_name"`
|
|
MediaType string `json:"media_type,omitempty"`
|
|
Content []byte `json:"-"`
|
|
Digest string `json:"digest,omitempty"`
|
|
Origin ReferenceOrigin `json:"origin"`
|
|
SizeBytes int64 `json:"size_bytes,omitempty"`
|
|
BindingSource string `json:"binding_source,omitempty"`
|
|
}
|
|
|
|
type ResolvedReferenceSlot struct {
|
|
Slot ReferenceSlot `json:"slot"`
|
|
Items []ReferenceItem `json:"items,omitempty"`
|
|
}
|
|
|
|
type ReferenceSet struct {
|
|
Slots map[string]ResolvedReferenceSlot `json:"slots,omitempty"`
|
|
}
|
|
|
|
type ExtractionRequest struct {
|
|
Source *source.SourceDocument `json:"-"`
|
|
Chunk *SourceChunk `json:"chunk,omitempty"`
|
|
AmbientContext map[string]any `json:"ambient_context,omitempty"`
|
|
SourceInput LLMInputMaterial `json:"source_input,omitempty"`
|
|
SessionID string `json:"session_id,omitempty"`
|
|
References ReferenceSet `json:"references,omitempty"`
|
|
LLMClient StructuredLLMClient `json:"-"`
|
|
LLMProfile string `json:"llm_profile,omitempty"`
|
|
Options map[string]any `json:"options,omitempty"`
|
|
Metadata map[string]any `json:"metadata,omitempty"`
|
|
}
|
|
|
|
type ExtractionResult struct {
|
|
Output ExtractOutput `json:"output"`
|
|
Warnings []Warning `json:"warnings,omitempty"`
|
|
}
|
|
|
|
type Extractor interface {
|
|
Key() string
|
|
ReferenceSlots() []ReferenceSlot
|
|
Extract(ctx context.Context, req ExtractionRequest) (ExtractionResult, error)
|
|
}
|
|
|
|
type RawPayload struct {
|
|
Content []byte `json:"-"`
|
|
MediaType string `json:"media_type"`
|
|
Metadata map[string]any `json:"metadata,omitempty"`
|
|
Warnings []Warning `json:"warnings,omitempty"`
|
|
}
|
|
|
|
type ExecutionClass string
|
|
|
|
const (
|
|
ExecutionClassDeterministic ExecutionClass = "deterministic"
|
|
ExecutionClassLLMBacked ExecutionClass = "llm_backed"
|
|
)
|
|
|
|
type ValidationRequest struct {
|
|
Stage string `json:"stage"`
|
|
LaneID string `json:"lane_id,omitempty"`
|
|
ModuleKey string `json:"module_key"`
|
|
Source *source.SourceDocument `json:"-"`
|
|
SourceID string `json:"source_id,omitempty"`
|
|
SourceInput LLMInputMaterial `json:"source_input,omitempty"`
|
|
SessionID string `json:"session_id,omitempty"`
|
|
References ReferenceSet `json:"references,omitempty"`
|
|
LLMClient StructuredLLMClient `json:"-"`
|
|
LLMProfile string `json:"llm_profile,omitempty"`
|
|
Options map[string]any `json:"options,omitempty"`
|
|
Metadata map[string]any `json:"metadata,omitempty"`
|
|
Schema ResponseSchema `json:"schema,omitempty"`
|
|
Payload RawPayload `json:"payload"`
|
|
ChunkID string `json:"chunk_id,omitempty"`
|
|
ChunkIndex int `json:"chunk_index,omitempty"`
|
|
Chunk *SourceChunk `json:"chunk,omitempty"`
|
|
Chunks []SourceChunk `json:"chunks,omitempty"`
|
|
ExtractOutputs []ExtractOutput `json:"extract_outputs,omitempty"`
|
|
MergeOutput MergeOutput `json:"merge_output,omitempty"`
|
|
}
|
|
|
|
type ValidationResult struct {
|
|
Approved bool `json:"approved"`
|
|
ReasonCode string `json:"reason_code,omitempty"`
|
|
Message string `json:"message,omitempty"`
|
|
DiagnosticArtifactPath string `json:"diagnostic_artifact_path,omitempty"`
|
|
Warnings []Warning `json:"warnings,omitempty"`
|
|
}
|
|
|
|
type Validator interface {
|
|
Name() string
|
|
ExecutionClass() ExecutionClass
|
|
Validate(ctx context.Context, req ValidationRequest) (ValidationResult, error)
|
|
}
|
|
|
|
type ResponseSchema struct {
|
|
ID string `json:"id,omitempty"`
|
|
Name string `json:"name,omitempty"`
|
|
Version string `json:"version,omitempty"`
|
|
JSONSchema []byte `json:"-"`
|
|
}
|
|
|
|
type ExtractOutput struct {
|
|
LaneID string `json:"lane_id"`
|
|
ExtractorKey string `json:"extractor_key"`
|
|
SourceID string `json:"source_id"`
|
|
ChunkID string `json:"chunk_id"`
|
|
ChunkIndex int `json:"chunk_index"`
|
|
Schema ResponseSchema `json:"schema,omitempty"`
|
|
Payload RawPayload `json:"payload"`
|
|
}
|
|
|
|
type MergeRequest struct {
|
|
Source *source.SourceDocument `json:"-"`
|
|
LaneID string `json:"lane_id"`
|
|
ExtractOutputs []ExtractOutput `json:"extract_outputs"`
|
|
SourceInput LLMInputMaterial `json:"source_input,omitempty"`
|
|
SessionID string `json:"session_id,omitempty"`
|
|
References ReferenceSet `json:"references,omitempty"`
|
|
LLMClient StructuredLLMClient `json:"-"`
|
|
LLMProfile string `json:"llm_profile,omitempty"`
|
|
Options map[string]any `json:"options,omitempty"`
|
|
Metadata map[string]any `json:"metadata,omitempty"`
|
|
}
|
|
|
|
type MergeResult struct {
|
|
Output MergeOutput `json:"output"`
|
|
Warnings []Warning `json:"warnings,omitempty"`
|
|
}
|
|
|
|
type MergeOutput struct {
|
|
LaneID string `json:"lane_id"`
|
|
MergerKey string `json:"merger_key"`
|
|
SourceID string `json:"source_id,omitempty"`
|
|
Schema ResponseSchema `json:"schema,omitempty"`
|
|
Payload RawPayload `json:"payload"`
|
|
}
|
|
|
|
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"`
|
|
MergeOutput MergeOutput `json:"merge_output"`
|
|
SourceInput LLMInputMaterial `json:"source_input,omitempty"`
|
|
SessionID string `json:"session_id,omitempty"`
|
|
References ReferenceSet `json:"references,omitempty"`
|
|
LLMClient StructuredLLMClient `json:"-"`
|
|
LLMProfile string `json:"llm_profile,omitempty"`
|
|
Options map[string]any `json:"options,omitempty"`
|
|
Metadata map[string]any `json:"metadata,omitempty"`
|
|
}
|
|
|
|
type NormalizeResult struct {
|
|
Output NormalizeOutput `json:"output"`
|
|
Warnings []Warning `json:"warnings,omitempty"`
|
|
}
|
|
|
|
type NormalizeOutput struct {
|
|
LaneID string `json:"lane_id"`
|
|
NormalizerKey string `json:"normalizer_key"`
|
|
SourceID string `json:"source_id,omitempty"`
|
|
Schema ResponseSchema `json:"schema,omitempty"`
|
|
Payload RawPayload `json:"payload"`
|
|
}
|
|
|
|
type Normalizer interface {
|
|
Key() string
|
|
ReferenceSlots() []ReferenceSlot
|
|
Normalize(ctx context.Context, req NormalizeRequest) (NormalizeResult, error)
|
|
}
|
|
|
|
type Warning struct {
|
|
Scope string `json:"scope,omitempty"`
|
|
ReasonCode string `json:"reason_code"`
|
|
Message string `json:"message"`
|
|
}
|
|
|
|
type OutputRequest struct {
|
|
Manifest artifacts.RunManifest `json:"manifest"`
|
|
NormalizeOutputs []NormalizeOutput `json:"normalize_outputs,omitempty"`
|
|
Rejected []RejectedOutput `json:"rejected,omitempty"`
|
|
Warnings []Warning `json:"warnings,omitempty"`
|
|
LLMProfile string `json:"llm_profile,omitempty"`
|
|
Options map[string]any `json:"options,omitempty"`
|
|
Metadata map[string]any `json:"metadata,omitempty"`
|
|
}
|
|
|
|
type OutputFile struct {
|
|
Name string `json:"name"`
|
|
ContentType string `json:"content_type,omitempty"`
|
|
Bytes []byte `json:"-"`
|
|
}
|
|
|
|
type OutputResult struct {
|
|
Files []OutputFile `json:"files,omitempty"`
|
|
Warnings []Warning `json:"warnings,omitempty"`
|
|
}
|
|
|
|
type OutputEncoder interface {
|
|
Key() string
|
|
Encode(ctx context.Context, req OutputRequest) (OutputResult, error)
|
|
}
|
|
|
|
type RejectedOutput struct {
|
|
Stage string `json:"stage"`
|
|
LaneID string `json:"lane_id,omitempty"`
|
|
ModuleKey string `json:"module_key,omitempty"`
|
|
ChunkID string `json:"chunk_id,omitempty"`
|
|
ChunkIndex int `json:"chunk_index,omitempty"`
|
|
ValidatorName string `json:"validator_name,omitempty"`
|
|
ReasonCode string `json:"reason_code,omitempty"`
|
|
Message string `json:"message"`
|
|
AttemptCount int `json:"attempt_count,omitempty"`
|
|
DiagnosticArtifactPath string `json:"diagnostic_artifact_path,omitempty"`
|
|
}
|
|
|
|
type ManifestMetadataProvider interface {
|
|
ManifestMetadata() map[string]any
|
|
}
|