audita/internal/cli/review_artifacts.go

package cli

import (
	"path/filepath"
	"sort"

	"gitea.maximumdirect.net/eric/audita/internal/framework/runner"
)

const (
	correctionDispositionApplied  = "applied"
	correctionDispositionRejected = "rejected"
	correctionDispositionSkipped  = "skipped"
	correctionDispositionFailed   = "failed"
)

type correctionLedgerEntry struct {
	RunID                         string                          `json:"run_id,omitempty"`
	ModuleKey                     string                          `json:"module_key"`
	ModuleInstance                string                          `json:"module_instance"`
	ProposalIndex                 int                             `json:"proposal_index"`
	SegmentID                     int                             `json:"segment_id,omitempty"`
	OriginalText                  string                          `json:"original_text,omitempty"`
	ProposedCorrectedText         string                          `json:"proposed_corrected_text,omitempty"`
	AppliedCorrectedText          string                          `json:"applied_corrected_text,omitempty"`
	ReplacementPolicy             string                          `json:"replacement_policy,omitempty"`
	Disposition                   string                          `json:"disposition"`
	DispositionReasonCode         string                          `json:"disposition_reason_code,omitempty"`
	DispositionMessage            string                          `json:"disposition_message,omitempty"`
	DeterministicValidatorResults []ledgerValidatorDecisionRecord `json:"deterministic_validator_decisions,omitempty"`
	LLMValidatorResults           []ledgerValidatorDecisionRecord `json:"llm_validator_decisions,omitempty"`
}

type ledgerValidatorDecisionRecord struct {
	ValidatorKey string `json:"validator_key"`
	Approved     bool   `json:"approved"`
	ReasonCode   string `json:"reason_code"`
	Message      string `json:"message,omitempty"`
}

func buildCorrectionLedger(runDirPath string, runOutput *runner.RunOutput) []correctionLedgerEntry {
	if runOutput == nil || len(runOutput.ModuleResults) == 0 {
		return nil
	}
	runID := ""
	if runDirPath != "" {
		runID = filepath.Base(runDirPath)
	}

	entries := make([]correctionLedgerEntry, 0)
	llmBacked := map[string]bool{
		"spoken_form_plausibility": true,
		"meaning_reversal_review":  true,
		"editorial_review":         true,
	}

	for _, module := range runOutput.ModuleResults {
		decisionsByProposal := make(map[int][]runner.ValidatorDecisionRecord)
		for _, decision := range module.ValidatorDecisions {
			decisionsByProposal[decision.ProposalIndex] = append(decisionsByProposal[decision.ProposalIndex], decision)
		}

		for _, change := range module.AppliedChanges {
			entries = append(entries, correctionLedgerEntry{
				RunID:                         runID,
				ModuleKey:                     module.ModuleKey,
				ModuleInstance:                module.ModuleInstance,
				ProposalIndex:                 change.ProposalIndex,
				SegmentID:                     change.TargetSegmentID,
				OriginalText:                  change.OriginalText,
				ProposedCorrectedText:         change.CorrectedText,
				AppliedCorrectedText:          change.CorrectedText,
				ReplacementPolicy:             string(module.ReplacementPolicy),
				Disposition:                   correctionDispositionApplied,
				DeterministicValidatorResults: filterLedgerDecisions(decisionsByProposal[change.ProposalIndex], false, llmBacked),
				LLMValidatorResults:           filterLedgerDecisions(decisionsByProposal[change.ProposalIndex], true, llmBacked),
			})
		}
		for _, change := range module.SkippedChanges {
			entries = append(entries, correctionLedgerEntry{
				RunID:                         runID,
				ModuleKey:                     module.ModuleKey,
				ModuleInstance:                module.ModuleInstance,
				ProposalIndex:                 change.ProposalIndex,
				SegmentID:                     change.TargetSegmentID,
				OriginalText:                  change.OriginalText,
				ProposedCorrectedText:         change.CorrectedText,
				ReplacementPolicy:             string(module.ReplacementPolicy),
				Disposition:                   correctionDispositionSkipped,
				DispositionReasonCode:         string(change.SkipReason),
				DispositionMessage:            change.Message,
				DeterministicValidatorResults: filterLedgerDecisions(decisionsByProposal[change.ProposalIndex], false, llmBacked),
				LLMValidatorResults:           filterLedgerDecisions(decisionsByProposal[change.ProposalIndex], true, llmBacked),
			})
		}
		for _, rejection := range module.ValidatorRejected {
			entries = append(entries, correctionLedgerEntry{
				RunID:                         runID,
				ModuleKey:                     module.ModuleKey,
				ModuleInstance:                module.ModuleInstance,
				ProposalIndex:                 rejection.ProposalIndex,
				SegmentID:                     rejection.TargetSegmentID,
				OriginalText:                  rejection.OriginalText,
				ProposedCorrectedText:         rejection.CorrectedText,
				ReplacementPolicy:             string(module.ReplacementPolicy),
				Disposition:                   correctionDispositionRejected,
				DispositionReasonCode:         rejection.ReasonCode,
				DispositionMessage:            rejection.Message,
				DeterministicValidatorResults: filterLedgerDecisions(decisionsByProposal[rejection.ProposalIndex], false, llmBacked),
				LLMValidatorResults:           filterLedgerDecisions(decisionsByProposal[rejection.ProposalIndex], true, llmBacked),
			})
		}
		if module.Status == runner.ModuleStatusFailed {
			entries = append(entries, correctionLedgerEntry{
				RunID:                 runID,
				ModuleKey:             module.ModuleKey,
				ModuleInstance:        module.ModuleInstance,
				Disposition:           correctionDispositionFailed,
				DispositionReasonCode: "module_failed",
				DispositionMessage:    module.ErrorMessage,
			})
		}
	}

	sort.SliceStable(entries, func(i, j int) bool {
		if entries[i].ModuleInstance != entries[j].ModuleInstance {
			return entries[i].ModuleInstance < entries[j].ModuleInstance
		}
		if entries[i].ProposalIndex != entries[j].ProposalIndex {
			return entries[i].ProposalIndex < entries[j].ProposalIndex
		}
		return entries[i].Disposition < entries[j].Disposition
	})

	return entries
}

func filterLedgerDecisions(in []runner.ValidatorDecisionRecord, wantLLM bool, llmBacked map[string]bool) []ledgerValidatorDecisionRecord {
	if len(in) == 0 {
		return nil
	}
	out := make([]ledgerValidatorDecisionRecord, 0, len(in))
	for _, decision := range in {
		if llmBacked[decision.ValidatorName] != wantLLM {
			continue
		}
		out = append(out, ledgerValidatorDecisionRecord{
			ValidatorKey: decision.ValidatorName,
			Approved:     decision.Approved,
			ReasonCode:   decision.ReasonCode,
			Message:      decision.Message,
		})
	}
	return out
}