notarius/internal/framework/checkpoint/loader.go

package checkpoint

import (
	"encoding/base64"
	"encoding/json"
	"fmt"
	"os"
	"strings"

	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
	coreworkspace "gitea.maximumdirect.net/eric/notarius/internal/core/workspace"
	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)

type WorkspaceLoader struct {
	root           string
	identityDigest string
}

func NewWorkspaceLoader(settings coreworkspace.Settings, identity coreworkspace.CheckpointIdentity) (pipeline.CheckpointLoader, error) {
	root, err := settings.CheckpointDirectory(identity)
	if err != nil {
		return nil, err
	}
	if strings.TrimSpace(root) == "" {
		return pipeline.NoopCheckpointLoader(), nil
	}
	return &WorkspaceLoader{root: root, identityDigest: identity.Digest}, nil
}

func (l *WorkspaceLoader) Enabled() bool {
	return l != nil && strings.TrimSpace(l.root) != ""
}

func (l *WorkspaceLoader) Source(moduleKey string) (pipeline.SourceCheckpoint, pipeline.CheckpointDecision) {
	var manifest coreworkspace.SourceManifest
	if decision := l.readJSON("source/manifest.json", &manifest); !decision.Reused {
		return pipeline.SourceCheckpoint{}, decision
	}
	if decision := l.validateManifest(manifest.StageManifest, coreworkspace.StageSource, "", moduleKey, coreworkspace.StatusSucceeded, nil); !decision.Reused {
		return pipeline.SourceCheckpoint{}, decision
	}
	var payload sourceDocumentEnvelope
	if decision := l.readJSON("source/source-document.json", &payload); !decision.Reused {
		return pipeline.SourceCheckpoint{}, decision
	}
	doc := cloneSourceDocument(payload.Document)
	if err := source.ValidateDocument(&doc); err != nil {
		return pipeline.SourceCheckpoint{}, invalidDecision("source checkpoint document is invalid: %v", err)
	}
	if strings.TrimSpace(manifest.SourceID) != "" && manifest.SourceID != doc.ID {
		return pipeline.SourceCheckpoint{}, invalidDecision("source checkpoint source id does not match payload")
	}
	if !fingerprintsEqual(coreworkspaceToPipelineFingerprints(manifest.OutputDigests), digestFingerprints("source_document", doc.Digest)) {
		return pipeline.SourceCheckpoint{}, invalidDecision("source checkpoint output digest does not match payload")
	}
	return pipeline.SourceCheckpoint{Document: &doc}, reusedDecision()
}

func (l *WorkspaceLoader) Chunk(moduleKey string, sourceDigest string) (pipeline.ChunkCheckpoint, pipeline.CheckpointDecision) {
	expectedDependencies := digestFingerprints("source_document", sourceDigest)
	var manifest coreworkspace.ChunkManifest
	if decision := l.readJSON("chunk/manifest.json", &manifest); !decision.Reused {
		return pipeline.ChunkCheckpoint{}, decision
	}
	if decision := l.validateManifest(manifest.StageManifest, coreworkspace.StageChunk, "", moduleKey, coreworkspace.StatusSucceeded, expectedDependencies); !decision.Reused {
		return pipeline.ChunkCheckpoint{}, decision
	}
	var payload chunksEnvelope
	if decision := l.readJSON("chunk/chunks.json", &payload); !decision.Reused {
		return pipeline.ChunkCheckpoint{}, decision
	}
	chunks, err := sourceChunksFromEnvelope(payload.Chunks)
	if err != nil {
		return pipeline.ChunkCheckpoint{}, invalidDecision("chunk checkpoint payload is invalid: %v", err)
	}
	if len(chunks) == 0 {
		return pipeline.ChunkCheckpoint{}, invalidDecision("chunk checkpoint payload has no chunks")
	}
	outputDigests, err := chunkOutputDigests(chunks)
	if err != nil {
		return pipeline.ChunkCheckpoint{}, invalidDecision("chunk checkpoint output cannot be digested: %v", err)
	}
	if !fingerprintsEqual(coreworkspaceToPipelineFingerprints(manifest.OutputDigests), outputDigests) {
		return pipeline.ChunkCheckpoint{}, invalidDecision("chunk checkpoint output digests do not match payload")
	}
	return pipeline.ChunkCheckpoint{Chunks: chunks, Warnings: cloneWarnings(payload.Warnings)}, reusedDecision()
}

func (l *WorkspaceLoader) Extract(laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint) (pipeline.ExtractCheckpoint, pipeline.CheckpointDecision) {
	var manifest coreworkspace.ExtractLaneManifest
	if d := l.readJSON(laneManifestPath("extract", laneID), &manifest); !d.Reused {
		return pipeline.ExtractCheckpoint{}, d
	}
	if d := l.validateLaneManifest(manifest.StageManifest, coreworkspace.StageExtract, laneID, moduleKey, dependencies, coreworkspace.StatusSucceeded, coreworkspace.StatusSucceededWithRejections); !d.Reused {
		return pipeline.ExtractCheckpoint{}, d
	}
	var payload artifactExtractEnvelope
	if d := l.readJSON(lanePayloadPath("extract", laneID, "outputs.json"), &payload); !d.Reused {
		return pipeline.ExtractCheckpoint{}, d
	}
	outputs, err := artifactCheckpointOutputs(payload.Outputs)
	if err != nil {
		return pipeline.ExtractCheckpoint{}, invalidDecision("extract artifact checkpoint payload is invalid: %v", err)
	}
	if !fingerprintsEqual(coreworkspaceToPipelineFingerprints(manifest.OutputDigests), artifactOutputDigests(outputs)) {
		return pipeline.ExtractCheckpoint{}, invalidDecision("extract artifact checkpoint output digests do not match payload")
	}
	return pipeline.ExtractCheckpoint{Outputs: outputs, Rejected: cloneRejectedOutputs(payload.Rejected), Warnings: cloneWarnings(payload.Warnings)}, reusedDecision()
}

func (l *WorkspaceLoader) Merge(laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint) (pipeline.MergeCheckpoint, pipeline.CheckpointDecision) {
	var manifest coreworkspace.MergeLaneManifest
	if d := l.readJSON(laneManifestPath("merge", laneID), &manifest); !d.Reused {
		return pipeline.MergeCheckpoint{}, d
	}
	if d := l.validateLaneManifest(manifest.StageManifest, coreworkspace.StageMerge, laneID, moduleKey, dependencies, coreworkspace.StatusSucceeded); !d.Reused {
		return pipeline.MergeCheckpoint{}, d
	}
	var payload artifactSingleEnvelope
	if d := l.readJSON(lanePayloadPath("merge", laneID, "output.json"), &payload); !d.Reused {
		return pipeline.MergeCheckpoint{}, d
	}
	values, err := artifactCheckpointOutputs([]artifactCheckpointEnvelope{payload.Output})
	if err != nil {
		return pipeline.MergeCheckpoint{}, invalidDecision("merge artifact checkpoint payload is invalid: %v", err)
	}
	if !fingerprintsEqual(coreworkspaceToPipelineFingerprints(manifest.OutputDigests), artifactOutputDigests(values)) {
		return pipeline.MergeCheckpoint{}, invalidDecision("merge artifact checkpoint output digest does not match payload")
	}
	return pipeline.MergeCheckpoint{Output: values[0], Warnings: cloneWarnings(payload.Warnings)}, reusedDecision()
}

func (l *WorkspaceLoader) Normalize(laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint) (pipeline.NormalizeCheckpoint, pipeline.CheckpointDecision) {
	var manifest coreworkspace.NormalizeLaneManifest
	if d := l.readJSON(laneManifestPath("normalize", laneID), &manifest); !d.Reused {
		return pipeline.NormalizeCheckpoint{}, d
	}
	if d := l.validateLaneManifest(manifest.StageManifest, coreworkspace.StageNormalize, laneID, moduleKey, dependencies, coreworkspace.StatusSucceeded); !d.Reused {
		return pipeline.NormalizeCheckpoint{}, d
	}
	var payload artifactSingleEnvelope
	if d := l.readJSON(lanePayloadPath("normalize", laneID, "output.json"), &payload); !d.Reused {
		return pipeline.NormalizeCheckpoint{}, d
	}
	values, err := artifactCheckpointOutputs([]artifactCheckpointEnvelope{payload.Output})
	if err != nil {
		return pipeline.NormalizeCheckpoint{}, invalidDecision("normalize artifact checkpoint payload is invalid: %v", err)
	}
	if !fingerprintsEqual(coreworkspaceToPipelineFingerprints(manifest.OutputDigests), artifactOutputDigests(values)) {
		return pipeline.NormalizeCheckpoint{}, invalidDecision("normalize artifact checkpoint output digest does not match payload")
	}
	return pipeline.NormalizeCheckpoint{Output: values[0], Warnings: cloneWarnings(payload.Warnings)}, reusedDecision()
}

func artifactCheckpointOutputs(values []artifactCheckpointEnvelope) ([]pipeline.CheckpointArtifact, error) {
	if len(values) == 0 {
		return nil, nil
	}
	out := make([]pipeline.CheckpointArtifact, 0, len(values))
	for _, v := range values {
		content, err := contentFromEnvelope(v.Content)
		if err != nil {
			return nil, err
		}
		if strings.TrimSpace(string(v.Kind)) == "" || strings.TrimSpace(v.Schema.ID) == "" || strings.TrimSpace(v.Schema.Version) == "" || strings.TrimSpace(v.SchemaDigest) == "" {
			return nil, fmt.Errorf("artifact codec identity is incomplete")
		}
		out = append(out, pipeline.CheckpointArtifact{LaneID: v.LaneID, ModuleKey: v.ModuleKey, SourceID: v.SourceID, ChunkID: v.ChunkID, ChunkIndex: v.ChunkIndex, ChunkRef: v.ChunkRef, SchemaDigest: v.SchemaDigest, Artifact: contracts.SerializedArtifact{Kind: v.Kind, Schema: v.Schema, MediaType: v.Content.MediaType, Content: content, Metadata: cloneMetadata(v.Content.Metadata)}})
	}
	return out, nil
}

func (l *WorkspaceLoader) readJSON(name string, out any) pipeline.CheckpointDecision {
	if !l.Enabled() {
		return pipeline.CheckpointDecision{Reason: "checkpoint loading disabled"}
	}
	target, err := coreworkspace.SafePath(l.root, name)
	if err != nil {
		return invalidDecision("checkpoint path is invalid: %v", err)
	}
	data, err := os.ReadFile(target)
	if err != nil {
		if os.IsNotExist(err) {
			return pipeline.CheckpointDecision{Reason: "checkpoint artifact is missing"}
		}
		return invalidDecision("read checkpoint artifact: %v", err)
	}
	if err := json.Unmarshal(data, out); err != nil {
		return invalidDecision("decode checkpoint artifact: %v", err)
	}
	return reusedDecision()
}

func (l *WorkspaceLoader) validateManifest(manifest coreworkspace.StageManifest, stage coreworkspace.StageName, laneID string, moduleKey string, status coreworkspace.StageStatus, dependencies []pipeline.CheckpointFingerprint) pipeline.CheckpointDecision {
	return l.validateLaneManifest(manifest, stage, laneID, moduleKey, dependencies, status)
}

func (l *WorkspaceLoader) validateLaneManifest(manifest coreworkspace.StageManifest, stage coreworkspace.StageName, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, statuses ...coreworkspace.StageStatus) pipeline.CheckpointDecision {
	if manifest.WorkspaceSchemaVersion == coreworkspace.WorkspaceSchemaVersionV1 {
		return invalidDecision("checkpoint workspace schema version %q is incompatible with %q and must be recomputed", manifest.WorkspaceSchemaVersion, coreworkspace.WorkspaceSchemaVersion)
	}
	if manifest.WorkspaceSchemaVersion != coreworkspace.WorkspaceSchemaVersion {
		return invalidDecision("checkpoint workspace schema version %q is not supported", manifest.WorkspaceSchemaVersion)
	}
	if strings.TrimSpace(l.identityDigest) != "" && manifest.Metadata["checkpoint_identity_digest"] != l.identityDigest {
		return invalidDecision("checkpoint identity digest does not match current invocation")
	}
	if manifest.Stage != stage {
		return invalidDecision("checkpoint stage %q does not match %q", manifest.Stage, stage)
	}
	if strings.TrimSpace(laneID) != "" && manifest.LaneID != laneID {
		return invalidDecision("checkpoint lane %q does not match %q", manifest.LaneID, laneID)
	}
	if strings.TrimSpace(moduleKey) != "" && manifest.ModuleKey != moduleKey {
		return invalidDecision("checkpoint module %q does not match %q", manifest.ModuleKey, moduleKey)
	}
	statusOK := false
	for _, status := range statuses {
		if manifest.Status == status {
			statusOK = true
			break
		}
	}
	if !statusOK {
		return invalidDecision("checkpoint status %q cannot be reused", manifest.Status)
	}
	if !fingerprintsEqual(coreworkspaceToPipelineFingerprints(manifest.DependencyFingerprints), dependencies) {
		return invalidDecision("checkpoint dependency fingerprints do not match")
	}
	return reusedDecision()
}

func sourceChunksFromEnvelope(values []chunkEnvelope) ([]source.Chunk, error) {
	if len(values) == 0 {
		return nil, nil
	}
	out := make([]source.Chunk, 0, len(values))
	for _, value := range values {
		content, err := contentFromEnvelope(value.Content)
		if err != nil {
			return nil, err
		}
		annotations, err := source.CanonicalizeChunkAnnotations(value.Annotations)
		if err != nil {
			return nil, fmt.Errorf("canonicalize chunk %q annotations: %w", value.ID, err)
		}
		planAnnotations, err := source.CanonicalizeChunkAnnotations(value.PlanAnnotations)
		if err != nil {
			return nil, fmt.Errorf("canonicalize chunk %q plan_annotations: %w", value.ID, err)
		}
		out = append(out, source.Chunk{
			ID:              value.ID,
			SourceID:        value.SourceID,
			Index:           value.Index,
			Ref:             value.Ref,
			Content:         content,
			MediaType:       value.Content.MediaType,
			Units:           cloneSourceUnits(value.Units),
			Metadata:        cloneMetadata(value.Metadata),
			Annotations:     annotations,
			PlanAnnotations: planAnnotations,
		})
	}
	return out, nil
}

func contentFromEnvelope(value binaryEnvelope) ([]byte, error) {
	content, err := base64.StdEncoding.DecodeString(value.ContentBase64)
	if err != nil {
		return nil, fmt.Errorf("decode content_base64: %w", err)
	}
	if digest := strings.TrimSpace(value.ContentDigest); digest != "" && digest != contentDigest(content) {
		return nil, fmt.Errorf("content digest mismatch")
	}
	return content, nil
}

func coreworkspaceToPipelineFingerprints(values []coreworkspace.Fingerprint) []pipeline.CheckpointFingerprint {
	if len(values) == 0 {
		return nil
	}
	out := make([]pipeline.CheckpointFingerprint, 0, len(values))
	for _, value := range values {
		out = append(out, pipeline.CheckpointFingerprint{Name: value.Name, Value: value.Value})
	}
	return normalizeFingerprints(out)
}

func fingerprintsEqual(a []pipeline.CheckpointFingerprint, b []pipeline.CheckpointFingerprint) bool {
	a = normalizeFingerprints(a)
	b = normalizeFingerprints(b)
	if len(a) != len(b) {
		return false
	}
	for i := range a {
		if a[i] != b[i] {
			return false
		}
	}
	return true
}

func reusedDecision() pipeline.CheckpointDecision {
	return pipeline.CheckpointDecision{Reused: true, Reason: "checkpoint is valid"}
}

func invalidDecision(format string, args ...any) pipeline.CheckpointDecision {
	return pipeline.CheckpointDecision{Reason: fmt.Sprintf(format, args...)}
}