golangLAKEHOUSE/internal/materializer/validate.go

package materializer

import (
	"fmt"
	"regexp"
	"strings"
	"time"

	"git.agentview.dev/profit/golangLAKEHOUSE/internal/distillation"
)

// ValidateEvidenceRecord ports validateEvidenceRecord from
// auditor/schemas/distillation/evidence_record.ts. Returns nil on
// success or a slice of human-readable error messages — the
// materializer logs the slice into distillation_skips.jsonl so an
// operator can see why a row was rejected without diff'ing logic.
//
// The validator is intentionally separate from
// distillation.ValidateScoredRun: scoring runs and evidence records
// have different shapes and the scorer's validator only covers the
// scored-run side.
func ValidateEvidenceRecord(r distillation.EvidenceRecord) []string {
	var errs []string

	if r.RunID == "" {
		errs = append(errs, "run_id: must be non-empty")
	}
	if r.TaskID == "" {
		errs = append(errs, "task_id: must be non-empty")
	}
	if !validISOTimestamp(r.Timestamp) {
		errs = append(errs, fmt.Sprintf("timestamp: not a valid ISO 8601 timestamp: %s", trim(r.Timestamp, 60)))
	}
	if r.SchemaVersion != distillation.EvidenceSchemaVersion {
		errs = append(errs, fmt.Sprintf("schema_version: expected %d, got %d", distillation.EvidenceSchemaVersion, r.SchemaVersion))
	}
	errs = append(errs, validateProvenanceFields(r.Provenance)...)

	if r.ModelRole != "" && !isValidModelRole(r.ModelRole) {
		errs = append(errs, fmt.Sprintf("model_role: must be a known role, got %q", r.ModelRole))
	}
	if r.InputHash != "" && !isHexSha256(r.InputHash) {
		errs = append(errs, "input_hash: must be hex sha256 when present")
	}
	if r.OutputHash != "" && !isHexSha256(r.OutputHash) {
		errs = append(errs, "output_hash: must be hex sha256 when present")
	}
	if r.ObserverConfidence < 0 || r.ObserverConfidence > 100 {
		errs = append(errs, "observer_confidence: must be in [0, 100]")
	}
	if r.HumanOverride != nil {
		if r.HumanOverride.Overrider == "" {
			errs = append(errs, "human_override.overrider: must be non-empty")
		}
		if r.HumanOverride.Reason == "" {
			errs = append(errs, "human_override.reason: must be non-empty")
		}
		if !validISOTimestamp(r.HumanOverride.OverriddenAt) {
			errs = append(errs, "human_override.overridden_at: must be ISO 8601")
		}
		switch r.HumanOverride.Decision {
		case "accept", "reject", "needs_review":
		default:
			errs = append(errs, "human_override.decision: must be accept|reject|needs_review")
		}
	}

	if len(errs) == 0 {
		return nil
	}
	return errs
}

func validateProvenanceFields(p distillation.Provenance) []string {
	var errs []string
	if p.SourceFile == "" {
		errs = append(errs, "provenance.source_file: must be non-empty")
	}
	if !isHexSha256(p.SigHash) {
		errs = append(errs, fmt.Sprintf("provenance.sig_hash: not a valid hex sha256: %s", trim(p.SigHash, 80)))
	}
	if !validISOTimestamp(p.RecordedAt) {
		errs = append(errs, "provenance.recorded_at: must be ISO 8601")
	}
	return errs
}

var (
	// Permissive ISO 8601 (matches TS regex):
	//   YYYY-MM-DDTHH:MM:SS(.fraction)?(Z|±HH:MM)?
	isoTimestampRE = regexp.MustCompile(`^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:\.\d+)?(?:Z|[+-]\d{2}:?\d{2})?$`)
	hexSha256RE    = regexp.MustCompile(`^[0-9a-f]{64}$`)
)

func validISOTimestamp(s string) bool {
	if s == "" {
		return false
	}
	if !isoTimestampRE.MatchString(s) {
		return false
	}
	// Belt-and-suspenders: confirm it's actually parseable too.
	if _, err := time.Parse(time.RFC3339, s); err == nil {
		return true
	}
	if _, err := time.Parse(time.RFC3339Nano, s); err == nil {
		return true
	}
	return false
}

func isHexSha256(s string) bool {
	return hexSha256RE.MatchString(s)
}

func isValidModelRole(role distillation.ModelRole) bool {
	switch role {
	case distillation.RoleExecutor, distillation.RoleReviewer, distillation.RoleExtractor,
		distillation.RoleVerifier, distillation.RoleCategorizer, distillation.RoleTiebreaker,
		distillation.RoleApplier, distillation.RoleEmbedder, distillation.RoleOther:
		return true
	}
	return false
}

func trim(s string, n int) string {
	if len(s) <= n {
		return s
	}
	return strings.ReplaceAll(s[:n], "\n", " ")
}