283 lines
11 KiB
Go
283 lines
11 KiB
Go
package pipeline
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"path"
|
|
"time"
|
|
|
|
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
|
|
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
|
|
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
|
|
)
|
|
|
|
type chunkPlanExecution struct {
|
|
accepted bool
|
|
chunks []source.Chunk
|
|
plan *source.ChunkPlan
|
|
warnings []contracts.Warning
|
|
rejection *contracts.RejectedOutput
|
|
lookup ChunkPlanDecision
|
|
record *ChunkPlanRecord
|
|
action string
|
|
summary artifacts.ChunkPlanSummary
|
|
}
|
|
|
|
func effectiveChunkCacheMode(mode ChunkCacheMode) ChunkCacheMode {
|
|
if mode == "" {
|
|
return ChunkCacheBypass
|
|
}
|
|
parsed, _ := ParseChunkCacheMode(string(mode))
|
|
return parsed
|
|
}
|
|
|
|
// Chunk-plan lookup and publication happen serially before lane workers start.
|
|
// The runner therefore does not add synchronization around the store.
|
|
func (r *Runner) runChunkPlan(ctx context.Context, input RunInput, doc *source.SourceDocument, sourceInput contracts.LLMInputMaterial, sessionID string) (chunkPlanExecution, error) {
|
|
mode := effectiveChunkCacheMode(input.ChunkCacheMode)
|
|
chunker := input.Prepared.chunker
|
|
result := chunkPlanExecution{
|
|
lookup: ChunkPlanDecision{Reason: "chunk plan lookup skipped"},
|
|
summary: artifacts.ChunkPlanSummary{
|
|
Mode: string(mode), SourceDigest: doc.Digest, RequestedModule: chunker.Key(), LookupStatus: "skipped",
|
|
LookupReason: "chunk plan lookup skipped", ValidationStatus: "not_run", PublicationStatus: "not_requested",
|
|
},
|
|
}
|
|
|
|
if mode == ChunkCacheAuto {
|
|
record, decision, err := input.ChunkPlans.Load(doc.Digest)
|
|
result.lookup = decision
|
|
result.summary.LookupStatus = chunkPlanLookupStatus(decision.Status)
|
|
result.summary.LookupReason = chunkPlanLookupReason(decision.Status)
|
|
if err != nil {
|
|
result.summary.LookupStatus = "skipped"
|
|
result.summary.LookupReason = chunkPlanLookupReason("")
|
|
return result, fmt.Errorf("load chunk plan: %w", err)
|
|
}
|
|
switch decision.Status {
|
|
case ChunkPlanHit:
|
|
plan, chunks, validationErr := validateAndMaterializeChunkPlan(doc, record.Plan)
|
|
if validationErr == nil {
|
|
if err := result.setCandidate(record, "reused"); err != nil {
|
|
return result, fmt.Errorf("clone reused chunk plan record: %w", err)
|
|
}
|
|
validationWarnings, rejection, err := r.validateChunks(ctx, doc, chunker.Key(), chunks, sourceInput, sessionID, input.pipeline.ChunkReferences.ReferenceSet, input.Metadata, input.Prepared.chunkValidators, 1, input.Debug)
|
|
result.plan = &plan
|
|
result.chunks = chunks
|
|
result.warnings = append(cloneWarnings(record.Warnings), validationWarnings...)
|
|
result.rejection = rejection
|
|
result.accepted = rejection == nil && err == nil
|
|
result.setValidation(validationWarnings, rejection, err)
|
|
return result, err
|
|
}
|
|
result.lookup = ChunkPlanDecision{Status: ChunkPlanInvalid, Reason: chunkPlanLookupReason(ChunkPlanInvalid)}
|
|
result.summary.LookupStatus = "invalid"
|
|
result.summary.LookupReason = chunkPlanLookupReason(ChunkPlanInvalid)
|
|
case ChunkPlanMissing, ChunkPlanInvalid:
|
|
// Generate below.
|
|
default:
|
|
return result, fmt.Errorf("load chunk plan returned unsupported decision status")
|
|
}
|
|
}
|
|
if mode == ChunkCacheAuto || mode == ChunkCacheRefresh {
|
|
result.summary.PublicationStatus = "not_published"
|
|
}
|
|
|
|
var producerWarnings []contracts.Warning
|
|
accepted, rejection, err := runWithRetry(ctx, input.pipeline.Chunk.Retries, func(attempt int) (bool, *contracts.RejectedOutput, error) {
|
|
attemptStarted := time.Now().UTC()
|
|
attemptPath := path.Join("chunk", fmt.Sprintf("attempt-%02d", attempt))
|
|
attemptCtx, llmScope := withDebugLLMScope(ctx, attemptPath)
|
|
terminal := newAttemptTerminalRecorder(input.Debug, attemptPath, "chunk", llmScope, debugTimedEnvelope{Stage: string(StageChunk), ModuleKey: chunker.Key(), Attempt: attempt, StartedAt: attemptStarted})
|
|
requestMetadata, metadataErr := cloneMetadata(input.Metadata)
|
|
if metadataErr != nil {
|
|
return false, nil, terminal.record(nil, fmt.Errorf("clone chunk request metadata: %w", metadataErr))
|
|
}
|
|
chunkResult, callErr := chunker.Plan(attemptCtx, contracts.ChunkRequest{
|
|
Source: doc, SourceInput: sourceInput.Clone(), SessionID: sessionID,
|
|
References: CloneReferenceSet(input.pipeline.ChunkReferences.ReferenceSet),
|
|
LLMProfile: input.pipeline.Chunk.LLMProfile, Metadata: requestMetadata,
|
|
})
|
|
if callErr != nil {
|
|
return false, nil, terminal.record(nil, fmt.Errorf("chunk source with chunker %q: %w", chunker.Key(), callErr))
|
|
}
|
|
plan, chunks, validationErr := validateAndMaterializeChunkPlan(doc, chunkResult.Plan)
|
|
if validationErr != nil {
|
|
attemptErr := fmt.Errorf("validate chunk plan from chunker %q: %w", chunker.Key(), validationErr)
|
|
payload := map[string]any{"plan": debugChunkPlanEnvelope(chunkResult.Plan), "warnings": debugWarningEnvelopes(chunkResult.Warnings)}
|
|
return false, nil, terminal.record(payload, attemptErr)
|
|
}
|
|
planDigest, digestErr := source.DigestChunkPlan(plan)
|
|
if digestErr != nil {
|
|
return false, nil, terminal.record(nil, fmt.Errorf("digest generated chunk plan: %w", digestErr))
|
|
}
|
|
producerMetadata, _, metadataErr := moduleManifestMetadata(chunker)
|
|
if metadataErr != nil {
|
|
return false, nil, terminal.record(nil, fmt.Errorf("clone chunker manifest metadata: %w", metadataErr))
|
|
}
|
|
profile := ""
|
|
if input.pipeline.ChunkExecutionClass == contracts.ExecutionClassLLMBacked {
|
|
profile = input.pipeline.Chunk.LLMProfile
|
|
}
|
|
candidate := ChunkPlanRecord{
|
|
SchemaVersion: ChunkPlanSchemaVersion, SourceDigest: doc.Digest, PlanDigest: planDigest,
|
|
Plan: source.CloneChunkPlan(plan),
|
|
Producer: ChunkPlanProducer{
|
|
InputModule: input.Prepared.input.Key(), ChunkModule: chunker.Key(), LLMProfile: profile,
|
|
References: append([]artifacts.ReferenceProvenance(nil), referenceTargetProvenance(input.pipeline.ChunkReferences)...),
|
|
Metadata: producerMetadata,
|
|
},
|
|
Warnings: cloneWarnings(chunkResult.Warnings), CreatedAt: time.Now().UTC(),
|
|
}
|
|
action := "generated"
|
|
if mode == ChunkCacheRefresh {
|
|
action = "refreshed"
|
|
}
|
|
if mode == ChunkCacheBypass {
|
|
action = "bypassed"
|
|
}
|
|
if candidateErr := result.setCandidate(candidate, action); candidateErr != nil {
|
|
return false, nil, terminal.record(nil, fmt.Errorf("clone generated chunk plan record: %w", candidateErr))
|
|
}
|
|
validationWarnings, rejected, validationErr := r.validateChunks(attemptCtx, doc, chunker.Key(), chunks, sourceInput, sessionID, input.pipeline.ChunkReferences.ReferenceSet, input.Metadata, input.Prepared.chunkValidators, attempt, input.Debug)
|
|
attemptWarnings := append(cloneWarnings(chunkResult.Warnings), validationWarnings...)
|
|
payload := map[string]any{
|
|
"plan": debugChunkPlanEnvelope(plan), "materialized_chunks": debugSourceChunkEnvelopes(chunks),
|
|
"warnings": debugWarningEnvelopes(attemptWarnings), "rejection": debugRejectedOutputPtr(rejected),
|
|
}
|
|
if validationErr != nil || rejected != nil {
|
|
result.setValidation(validationWarnings, rejected, validationErr)
|
|
return false, rejected, terminal.record(payload, validationErr)
|
|
}
|
|
result.chunks = chunks
|
|
result.plan = &plan
|
|
result.warnings = attemptWarnings
|
|
producerWarnings = cloneWarnings(chunkResult.Warnings)
|
|
result.setValidation(validationWarnings, nil, nil)
|
|
if debugErr := terminal.record(payload, nil); debugErr != nil {
|
|
return false, nil, debugErr
|
|
}
|
|
return true, nil, nil
|
|
})
|
|
if err != nil {
|
|
if result.summary.ValidationStatus == "not_run" {
|
|
result.summary.ValidationStatus = "error"
|
|
}
|
|
return result, err
|
|
}
|
|
result.accepted = accepted
|
|
result.rejection = rejection
|
|
if !accepted {
|
|
return result, nil
|
|
}
|
|
|
|
if mode == ChunkCacheAuto || mode == ChunkCacheRefresh {
|
|
record, cloneErr := cloneChunkPlanRecord(*result.record)
|
|
if cloneErr != nil {
|
|
return result, fmt.Errorf("clone chunk plan record for publication: %w", cloneErr)
|
|
}
|
|
record.Warnings = cloneWarnings(producerWarnings)
|
|
if err := input.ChunkPlans.Save(record); err != nil {
|
|
return result, fmt.Errorf("save chunk plan: %w", err)
|
|
}
|
|
result.summary.PublicationStatus = "published"
|
|
}
|
|
return result, nil
|
|
}
|
|
|
|
func chunkPlanLookupStatus(status ChunkPlanStatus) string {
|
|
switch status {
|
|
case ChunkPlanHit:
|
|
return "hit"
|
|
case ChunkPlanMissing:
|
|
return "missing"
|
|
case ChunkPlanInvalid:
|
|
return "invalid"
|
|
default:
|
|
return "skipped"
|
|
}
|
|
}
|
|
|
|
func chunkPlanLookupReason(status ChunkPlanStatus) string {
|
|
switch status {
|
|
case ChunkPlanHit:
|
|
return "stored chunk plan is valid"
|
|
case ChunkPlanMissing:
|
|
return "chunk plan not found"
|
|
case ChunkPlanInvalid:
|
|
return "stored chunk plan is invalid"
|
|
default:
|
|
return "chunk plan lookup skipped"
|
|
}
|
|
}
|
|
|
|
func (result *chunkPlanExecution) setCandidate(record ChunkPlanRecord, action string) error {
|
|
cloned, err := cloneChunkPlanRecord(record)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
result.record = &cloned
|
|
result.action = action
|
|
result.summary.Action = action
|
|
result.summary.SourceDigest = record.SourceDigest
|
|
result.summary.CandidateDigest = record.PlanDigest
|
|
return nil
|
|
}
|
|
|
|
func (result *chunkPlanExecution) setValidation(warnings []contracts.Warning, rejection *contracts.RejectedOutput, err error) {
|
|
switch {
|
|
case err != nil:
|
|
result.summary.ValidationStatus = "error"
|
|
case rejection != nil:
|
|
result.summary.ValidationStatus = "rejected"
|
|
case len(warnings) > 0:
|
|
result.summary.ValidationStatus = "approved_with_warnings"
|
|
default:
|
|
result.summary.ValidationStatus = "approved"
|
|
}
|
|
}
|
|
|
|
func cloneChunkPlanRecord(record ChunkPlanRecord) (ChunkPlanRecord, error) {
|
|
record.Plan = source.CloneChunkPlan(record.Plan)
|
|
record.Producer.References = append([]artifacts.ReferenceProvenance(nil), record.Producer.References...)
|
|
metadata, err := cloneMetadata(record.Producer.Metadata)
|
|
if err != nil {
|
|
return ChunkPlanRecord{}, fmt.Errorf("clone chunk plan producer metadata: %w", err)
|
|
}
|
|
record.Producer.Metadata = metadata
|
|
record.Warnings = cloneWarnings(record.Warnings)
|
|
return record, nil
|
|
}
|
|
|
|
func applyChunkPlanExecution(output *RunOutput, result chunkPlanExecution) error {
|
|
if output == nil {
|
|
return nil
|
|
}
|
|
summary := result.summary
|
|
output.ChunkPlan = &summary
|
|
if output.Manifest.ChunkPlan == nil {
|
|
return nil
|
|
}
|
|
manifest := output.Manifest.ChunkPlan
|
|
manifest.Action = result.action
|
|
if result.record == nil {
|
|
return nil
|
|
}
|
|
record := result.record
|
|
manifest.SourceDigest = record.SourceDigest
|
|
manifest.PlanDigest = record.PlanDigest
|
|
manifest.PlanSchemaVersion = record.SchemaVersion
|
|
manifest.ProducerInputModule = record.Producer.InputModule
|
|
manifest.ProducerModule = record.Producer.ChunkModule
|
|
manifest.ProducerLLMProfile = record.Producer.LLMProfile
|
|
manifest.ProducerReferences = append([]artifacts.ReferenceProvenance(nil), record.Producer.References...)
|
|
metadata, err := cloneMetadata(record.Producer.Metadata)
|
|
if err != nil {
|
|
return fmt.Errorf("clone chunk plan manifest producer metadata: %w", err)
|
|
}
|
|
manifest.ProducerMetadata = metadata
|
|
createdAt := record.CreatedAt
|
|
manifest.CreatedAt = &createdAt
|
|
return nil
|
|
}
|