351 lines
12 KiB
Go
351 lines
12 KiB
Go
package runner
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"path/filepath"
|
|
"time"
|
|
|
|
"gitea.maximumdirect.net/eric/audita/internal/core/config"
|
|
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
|
|
"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
|
|
"gitea.maximumdirect.net/eric/audita/internal/framework/llm"
|
|
"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
|
|
"gitea.maximumdirect.net/eric/audita/internal/framework/validators"
|
|
)
|
|
|
|
const (
|
|
ModuleStatusSuccess = "success"
|
|
ModuleStatusFailed = "failed"
|
|
)
|
|
|
|
// ModuleFactory resolves one module instance for one run spec.
|
|
type ModuleFactory interface {
|
|
ModuleForSpec(spec contracts.ModuleRunSpec) (contracts.TranscriptModule, error)
|
|
}
|
|
|
|
// Runner executes module instances sequentially against a working transcript.
|
|
type Runner struct {
|
|
factory ModuleFactory
|
|
}
|
|
|
|
type ValidationScheduler interface {
|
|
Run(ctx context.Context, fn func(context.Context) error) error
|
|
}
|
|
|
|
// ModuleResult captures deterministic per-module execution output.
|
|
type ModuleResult struct {
|
|
ModuleKey string `json:"module_key"`
|
|
ModuleInstance string `json:"module_instance"`
|
|
ReplacementPolicy proposals.ReplacementPolicy `json:"replacement_policy"`
|
|
Status string `json:"status"`
|
|
ProposalCount int `json:"proposal_count"`
|
|
ValidatorDecisions []ValidatorDecisionRecord `json:"validator_decisions,omitempty"`
|
|
ValidatorRejected []ValidatorRejectedChange `json:"validator_rejected,omitempty"`
|
|
AppliedChanges []proposals.AppliedChange `json:"applied_changes,omitempty"`
|
|
SkippedChanges []proposals.SkippedChange `json:"skipped_changes,omitempty"`
|
|
ErrorMessage string `json:"error_message,omitempty"`
|
|
StartedAt time.Time `json:"started_at"`
|
|
CompletedAt time.Time `json:"completed_at"`
|
|
}
|
|
|
|
type ValidatorDecisionRecord struct {
|
|
ValidatorName string `json:"validator_name"`
|
|
ProposalIndex int `json:"proposal_index"`
|
|
Approved bool `json:"approved"`
|
|
ReasonCode string `json:"reason_code"`
|
|
Message string `json:"message"`
|
|
DiagnosticArtifactPath string `json:"diagnostic_artifact_path,omitempty"`
|
|
}
|
|
|
|
type ValidatorRejectedChange struct {
|
|
ValidatorName string `json:"validator_name"`
|
|
ProposalIndex int `json:"proposal_index"`
|
|
ModuleKey string `json:"module_key"`
|
|
ModuleInstance string `json:"module_instance"`
|
|
TargetSegmentID int `json:"target_segment_id"`
|
|
OriginalText string `json:"original_text"`
|
|
CorrectedText string `json:"corrected_text"`
|
|
ReasonCode string `json:"reason_code"`
|
|
Message string `json:"message"`
|
|
}
|
|
|
|
// RunInput is the deterministic runner input.
|
|
type RunInput struct {
|
|
Config *config.Config
|
|
Transcript *schema.Transcript
|
|
Glossary *schema.Glossary
|
|
ModuleSpecs []contracts.ModuleRunSpec
|
|
ValidationLLMClient contracts.StructuredLLMClient
|
|
ValidationLLMScheduler ValidationScheduler
|
|
ValidationDiagnosticsDir string
|
|
}
|
|
|
|
// RunOutput is the deterministic runner output.
|
|
type RunOutput struct {
|
|
FinalTranscript *schema.Transcript `json:"-"`
|
|
ModuleResults []ModuleResult `json:"module_results"`
|
|
}
|
|
|
|
func New(factory ModuleFactory) *Runner {
|
|
return &Runner{factory: factory}
|
|
}
|
|
|
|
func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
|
|
if r == nil || r.factory == nil {
|
|
return RunOutput{}, fmt.Errorf("runner module factory is required")
|
|
}
|
|
|
|
working := cloneTranscript(input.Transcript)
|
|
results := make([]ModuleResult, 0, len(input.ModuleSpecs))
|
|
|
|
for _, spec := range input.ModuleSpecs {
|
|
startedAt := time.Now().UTC()
|
|
module, err := r.factory.ModuleForSpec(spec)
|
|
if err != nil {
|
|
failed := ModuleResult{
|
|
ModuleKey: spec.ModuleKey,
|
|
ModuleInstance: spec.InstanceName,
|
|
Status: ModuleStatusFailed,
|
|
ErrorMessage: err.Error(),
|
|
StartedAt: startedAt,
|
|
CompletedAt: time.Now().UTC(),
|
|
}
|
|
results = append(results, failed)
|
|
return RunOutput{FinalTranscript: working, ModuleResults: results}, fmt.Errorf("module %q setup failed: %w", spec.InstanceName, err)
|
|
}
|
|
|
|
policy := module.ReplacementPolicy()
|
|
proposed, err := module.Propose(ctx, contracts.ProposalRequest{
|
|
ExecutionContext: contracts.ExecutionContext{
|
|
Config: input.Config,
|
|
WorkingTranscript: working,
|
|
Glossary: input.Glossary,
|
|
},
|
|
RunSpec: contracts.ModuleRunSpec{
|
|
ModuleKey: spec.ModuleKey,
|
|
InstanceName: spec.InstanceName,
|
|
ReplacementPolicy: policy,
|
|
},
|
|
})
|
|
if err != nil {
|
|
failed := ModuleResult{
|
|
ModuleKey: spec.ModuleKey,
|
|
ModuleInstance: spec.InstanceName,
|
|
ReplacementPolicy: policy,
|
|
Status: ModuleStatusFailed,
|
|
ErrorMessage: err.Error(),
|
|
StartedAt: startedAt,
|
|
CompletedAt: time.Now().UTC(),
|
|
}
|
|
results = append(results, failed)
|
|
return RunOutput{FinalTranscript: working, ModuleResults: results}, fmt.Errorf("module %q failed: %w", spec.InstanceName, err)
|
|
}
|
|
|
|
enriched := make([]proposals.EnrichedCorrectionProposal, 0, len(proposed))
|
|
for i, p := range proposed {
|
|
enriched = append(enriched, proposals.EnrichedCorrectionProposal{
|
|
CorrectionProposal: p,
|
|
ProposalMetadata: proposals.ProposalMetadata{
|
|
ProposalIndex: i,
|
|
ModuleKey: spec.ModuleKey,
|
|
ModuleInstance: spec.InstanceName,
|
|
},
|
|
})
|
|
}
|
|
|
|
validatorDecisions := make([]ValidatorDecisionRecord, 0)
|
|
validatorRejected := make([]ValidatorRejectedChange, 0)
|
|
eligible := enriched
|
|
for _, validator := range module.Validators() {
|
|
var diagnosticsWriter validators.InteractionDiagnosticsWriter
|
|
if input.ValidationDiagnosticsDir != "" {
|
|
diagnosticsWriter = &llmDiagnosticsWriterAdapter{
|
|
writer: llm.NewDiagnosticsWriter(
|
|
filepath.Join(input.ValidationDiagnosticsDir, spec.InstanceName),
|
|
validatorSecrets(input.Config),
|
|
),
|
|
}
|
|
}
|
|
|
|
vResult, vErr := validator.Validate(ctx, contracts.ValidationRequest{
|
|
WorkingTranscript: working,
|
|
CandidateProposal: eligible,
|
|
ModuleKey: spec.ModuleKey,
|
|
ModuleInstance: spec.InstanceName,
|
|
ReplacementPolicy: policy,
|
|
Glossary: input.Glossary,
|
|
Config: input.Config,
|
|
LLMClient: validationLLMClientAdapter{client: input.ValidationLLMClient},
|
|
Scheduler: input.ValidationLLMScheduler,
|
|
DiagnosticsWriter: diagnosticsWriter,
|
|
})
|
|
if vErr != nil {
|
|
failed := ModuleResult{
|
|
ModuleKey: spec.ModuleKey,
|
|
ModuleInstance: spec.InstanceName,
|
|
ReplacementPolicy: policy,
|
|
Status: ModuleStatusFailed,
|
|
ProposalCount: len(enriched),
|
|
ValidatorDecisions: validatorDecisions,
|
|
ValidatorRejected: validatorRejected,
|
|
ErrorMessage: vErr.Error(),
|
|
StartedAt: startedAt,
|
|
CompletedAt: time.Now().UTC(),
|
|
}
|
|
results = append(results, failed)
|
|
return RunOutput{FinalTranscript: working, ModuleResults: results}, fmt.Errorf("module %q validator %q failed: %w", spec.InstanceName, validator.Name(), vErr)
|
|
}
|
|
if err := validators.EnforceDecisionCardinality(eligible, vResult.Decisions); err != nil {
|
|
failed := ModuleResult{
|
|
ModuleKey: spec.ModuleKey,
|
|
ModuleInstance: spec.InstanceName,
|
|
ReplacementPolicy: policy,
|
|
Status: ModuleStatusFailed,
|
|
ProposalCount: len(enriched),
|
|
ValidatorDecisions: validatorDecisions,
|
|
ValidatorRejected: validatorRejected,
|
|
ErrorMessage: err.Error(),
|
|
StartedAt: startedAt,
|
|
CompletedAt: time.Now().UTC(),
|
|
}
|
|
results = append(results, failed)
|
|
return RunOutput{FinalTranscript: working, ModuleResults: results}, fmt.Errorf("module %q validator %q cardinality failed: %w", spec.InstanceName, validator.Name(), err)
|
|
}
|
|
|
|
nextEligible := make([]proposals.EnrichedCorrectionProposal, 0, len(eligible))
|
|
byIndex := make(map[int]proposals.EnrichedCorrectionProposal, len(eligible))
|
|
for _, p := range eligible {
|
|
byIndex[p.ProposalIndex] = p
|
|
}
|
|
for _, d := range vResult.Decisions {
|
|
validatorDecisions = append(validatorDecisions, ValidatorDecisionRecord{
|
|
ValidatorName: validator.Name(),
|
|
ProposalIndex: d.ProposalIndex,
|
|
Approved: d.Approved,
|
|
ReasonCode: d.ReasonCode,
|
|
Message: d.Message,
|
|
DiagnosticArtifactPath: d.DiagnosticArtifactPath,
|
|
})
|
|
if d.Approved {
|
|
nextEligible = append(nextEligible, byIndex[d.ProposalIndex])
|
|
continue
|
|
}
|
|
p := byIndex[d.ProposalIndex]
|
|
validatorRejected = append(validatorRejected, ValidatorRejectedChange{
|
|
ValidatorName: validator.Name(),
|
|
ProposalIndex: p.ProposalIndex,
|
|
ModuleKey: p.ModuleKey,
|
|
ModuleInstance: p.ModuleInstance,
|
|
TargetSegmentID: p.TargetSegmentID,
|
|
OriginalText: p.OriginalText,
|
|
CorrectedText: p.CorrectedText,
|
|
ReasonCode: d.ReasonCode,
|
|
Message: d.Message,
|
|
})
|
|
}
|
|
eligible = nextEligible
|
|
}
|
|
|
|
applyResult := proposals.ApplyProposals(working, eligible, policy)
|
|
working = applyResult.Transcript
|
|
|
|
results = append(results, ModuleResult{
|
|
ModuleKey: spec.ModuleKey,
|
|
ModuleInstance: spec.InstanceName,
|
|
ReplacementPolicy: policy,
|
|
Status: ModuleStatusSuccess,
|
|
ProposalCount: len(enriched),
|
|
ValidatorDecisions: validatorDecisions,
|
|
ValidatorRejected: validatorRejected,
|
|
AppliedChanges: applyResult.Applied,
|
|
SkippedChanges: applyResult.Skipped,
|
|
StartedAt: startedAt,
|
|
CompletedAt: time.Now().UTC(),
|
|
})
|
|
}
|
|
|
|
return RunOutput{FinalTranscript: working, ModuleResults: results}, nil
|
|
}
|
|
|
|
func cloneTranscript(t *schema.Transcript) *schema.Transcript {
|
|
if t == nil {
|
|
return &schema.Transcript{}
|
|
}
|
|
segments := make([]schema.Segment, len(t.Segments))
|
|
for i, s := range t.Segments {
|
|
var categories []string
|
|
if s.Categories != nil {
|
|
categories = append([]string(nil), s.Categories...)
|
|
}
|
|
segments[i] = schema.Segment{
|
|
ID: s.ID,
|
|
Speaker: s.Speaker,
|
|
Start: s.Start,
|
|
End: s.End,
|
|
Text: s.Text,
|
|
Categories: categories,
|
|
}
|
|
}
|
|
return &schema.Transcript{Segments: segments}
|
|
}
|
|
|
|
type validationLLMClientAdapter struct {
|
|
client contracts.StructuredLLMClient
|
|
}
|
|
|
|
func (a validationLLMClientAdapter) CompleteStructured(ctx context.Context, req validators.StructuredCompletionRequest, out any) (validators.StructuredCompletionResponse, error) {
|
|
if a.client == nil {
|
|
return validators.StructuredCompletionResponse{}, fmt.Errorf("validation structured LLM client is not configured")
|
|
}
|
|
messages := make([]contracts.LLMMessage, len(req.Messages))
|
|
for i, m := range req.Messages {
|
|
messages[i] = contracts.LLMMessage{Role: m.Role, Content: m.Content}
|
|
}
|
|
resp, err := a.client.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
|
|
StageName: req.StageName,
|
|
Messages: messages,
|
|
Model: req.Model,
|
|
}, out)
|
|
if err != nil {
|
|
return validators.StructuredCompletionResponse{}, err
|
|
}
|
|
return validators.StructuredCompletionResponse{
|
|
PromptTokens: resp.PromptTokens,
|
|
CompletionTokens: resp.CompletionTokens,
|
|
TotalTokens: resp.TotalTokens,
|
|
}, nil
|
|
}
|
|
|
|
type llmDiagnosticsWriterAdapter struct {
|
|
writer *llm.DiagnosticsWriter
|
|
}
|
|
|
|
func (a *llmDiagnosticsWriterAdapter) WriteInteraction(stage string, requestMetadata any, requestPayload any, responsePayload any, errorPayload any) (validators.InteractionArtifacts, error) {
|
|
if a == nil || a.writer == nil {
|
|
return validators.InteractionArtifacts{}, fmt.Errorf("diagnostics writer is not configured")
|
|
}
|
|
art, err := a.writer.WriteInteraction(stage, requestMetadata, requestPayload, responsePayload, errorPayload)
|
|
if err != nil {
|
|
return validators.InteractionArtifacts{}, err
|
|
}
|
|
return validators.InteractionArtifacts{
|
|
RequestMetadataPath: art.RequestMetadataPath,
|
|
RequestPayloadPath: art.RequestPayloadPath,
|
|
ResponsePayloadPath: art.ResponsePayloadPath,
|
|
ErrorPayloadPath: art.ErrorPayloadPath,
|
|
}, nil
|
|
}
|
|
|
|
func validatorSecrets(cfg *config.Config) []string {
|
|
if cfg == nil {
|
|
return nil
|
|
}
|
|
effective := cfg.EffectiveValidationLLMConfig()
|
|
return []string{
|
|
cfg.PrimaryLLM.APIKey,
|
|
effective.APIKey,
|
|
cfg.ValidationLLM.APIKey,
|
|
}
|
|
}
|