golangLAKEHOUSE/internal/distillation/types.go

// Package distillation is the Go port of the Rust v1.0.0 distillation
// substrate (frozen at e7636f2). Per ADR-001 #4: port LOGIC, not
// bit-identical reproducibility.
//
// What this package owns (this commit):
//   - The deterministic scorer: EvidenceRecord → ScoredRun
//   - Score categories + scorer version constant
//   - SftSample type + validator with the contamination firewall
//     (the safety-critical piece — rejected/needs_human_review must
//     NEVER ship to SFT)
//
// What's deferred to follow-up commits:
//   - Materialization layer (file iteration, jsonl read/write,
//     date-partitioned storage) — operational tooling on top of
//     the scorer logic
//   - export_preference, export_rag (other export shapes)
//   - acceptance harness (the gate that locks v1.0.0)
//   - replay, receipts, evidence-index builders
//
// The scorer + SftSample validator are the LOAD-BEARING pieces
// per project_distillation_substrate.md memory. The rest is plumbing
// that can land incrementally without changing the logic the
// downstream learning loop depends on.

package distillation

import (
	"encoding/json"
	"errors"
	"fmt"
	"strings"
	"time"
)

// ScoreCategory is one of the 4 deterministic verdicts. Matches Rust
// SCORE_CATEGORIES exactly.
type ScoreCategory string

const (
	CategoryAccepted          ScoreCategory = "accepted"
	CategoryPartiallyAccepted ScoreCategory = "partially_accepted"
	CategoryRejected          ScoreCategory = "rejected"
	CategoryNeedsHumanReview  ScoreCategory = "needs_human_review"
)

// AllScoreCategories lists every legal category — used by validators.
var AllScoreCategories = []ScoreCategory{
	CategoryAccepted,
	CategoryPartiallyAccepted,
	CategoryRejected,
	CategoryNeedsHumanReview,
}

// ScorerVersion is hardcoded — the deterministic-output contract
// requires this. Bump the literal in the same commit as any scoring-
// rule change so the version stamp moves atomically with logic.
// Mirrors the Rust SCORER_VERSION (also v1.0.0 at e7636f2).
const ScorerVersion = "v1.0.0"

// SftQualityScore enumerates the categories LEGAL in SFT exports.
// SFT_NEVER (defined below) is the inverse — categories that NEVER
// ship to SFT under any flag combination. The contamination firewall
// is enforced at the schema layer (ValidateSftSample) AND by the
// exporter; defense in depth.
type SftQualityScore string

const (
	SftQualityAccepted          SftQualityScore = "accepted"
	SftQualityPartiallyAccepted SftQualityScore = "partially_accepted"
)

// SftQualityScores lists quality scores legal in SFT samples.
// Default is SftQualityAccepted only; --include-partial CLI flag
// expands to both. rejected and needs_human_review are NEVER legal.
var SftQualityScores = []SftQualityScore{
	SftQualityAccepted,
	SftQualityPartiallyAccepted,
}

// SftNever is the contamination firewall: ScoreCategories that NEVER
// ship to SFT under ANY caller flag. Enforced at the schema layer
// (ValidateSftSample) AND at the exporter layer. Per the Rust
// e7636f2 spec: "Hard non-negotiable: this set never expands. If you
// find yourself adding 'needs_human_review' or 'rejected' here, stop
// — that's the contamination the spec forbids."
//
// Exported so callers AND the validator share the same source of
// truth. Modifying this constant changes the contract; reviewers
// should treat any commit that touches it as a security review.
var SftNever = []ScoreCategory{
	CategoryRejected,
	CategoryNeedsHumanReview,
}

// SftSampleSchemaVersion bumps when the on-wire SftSample shape
// changes incompatibly. Match the Rust SFT_SAMPLE_SCHEMA_VERSION.
const SftSampleSchemaVersion = 1

// ScoredRunSchemaVersion bumps when the on-wire ScoredRun shape
// changes incompatibly. Match the Rust SCORED_RUN_SCHEMA_VERSION.
const ScoredRunSchemaVersion = 1

// EvidenceSchemaVersion mirrors the Rust EVIDENCE_SCHEMA_VERSION.
// This package consumes EvidenceRecord; producing it is a separate
// concern (the materialization layer not yet ported).
const EvidenceSchemaVersion = 1

// ModelRole categorizes the kind of model output represented by an
// EvidenceRecord. Used by the SFT exporter to filter "real model
// output" from pure-extraction rows.
type ModelRole string

const (
	RoleExecutor    ModelRole = "executor"
	RoleReviewer    ModelRole = "reviewer"
	RoleExtractor   ModelRole = "extractor"
	RoleVerifier    ModelRole = "verifier"
	RoleCategorizer ModelRole = "categorizer"
	RoleTiebreaker  ModelRole = "tiebreaker"
	RoleApplier     ModelRole = "applier"
	RoleEmbedder    ModelRole = "embedder"
	RoleOther       ModelRole = "other"
)

// Provenance is the source-linkage every distillation record carries.
// SourceFile is required (no record without source linkage); other
// fields are best-effort for de-duplication and trace-back.
type Provenance struct {
	SourceFile  string `json:"source_file"`
	LineOffset  int64  `json:"line_offset,omitempty"`
	SigHash     string `json:"sig_hash"`
	RecordedAt  string `json:"recorded_at"` // ISO 8601
}

// ObserverVerdict is what an observer returned for an executor's
// output. Matches the Rust enum but as a string type for JSON
// flexibility.
type ObserverVerdict string

const (
	VerdictAccept ObserverVerdict = "accept"
	VerdictReject ObserverVerdict = "reject"
	VerdictCycle  ObserverVerdict = "cycle"
)

// EvidenceRecord is one row in the canonical evidence stream.
// Producing it (transforms from raw KB streams) is a separate
// concern; this package consumes it.
//
// Fields mirror the Rust EvidenceRecord at e7636f2. Optional fields
// use Go pointers / slices so missing-vs-empty stays distinguishable
// for the scorer's heuristics.
type EvidenceRecord struct {
	RunID         string `json:"run_id"`
	TaskID        string `json:"task_id"`
	Timestamp     string `json:"timestamp"`
	SchemaVersion int    `json:"schema_version"`

	Provenance Provenance `json:"provenance"`

	ModelName     string    `json:"model_name,omitempty"`
	ModelProvider string    `json:"model_provider,omitempty"`
	ModelRole     ModelRole `json:"model_role,omitempty"`

	InputHash  string `json:"input_hash,omitempty"`
	OutputHash string `json:"output_hash,omitempty"`

	SourceFiles []string `json:"source_files,omitempty"`
	CommandsRun []string `json:"commands_run,omitempty"`

	RetrievedContext *RetrievedContext `json:"retrieved_context,omitempty"`

	ObserverNotes      []string         `json:"observer_notes,omitempty"`
	ObserverVerdict    ObserverVerdict  `json:"observer_verdict,omitempty"`
	ObserverConfidence float64          `json:"observer_confidence,omitempty"`
	ScratchpadSummary  string           `json:"scratchpad_summary,omitempty"`

	SuccessMarkers []string `json:"success_markers,omitempty"`
	FailureMarkers []string `json:"failure_markers,omitempty"`

	ValidationResults map[string]any `json:"validation_results,omitempty"`

	HumanOverride *HumanOverride `json:"human_override,omitempty"`

	CostUSD   float64 `json:"cost_usd,omitempty"`
	LatencyMs int64   `json:"latency_ms,omitempty"`
	Text      string  `json:"text,omitempty"`
}

// RetrievedContext captures what the model saw via retrieval. Matches
// the Rust shape exactly so the JSON round-trips byte-identical (per
// ADR-001 #4 "logic, not bit-identical" — but on-wire compatibility
// is desirable for tooling that consumes EvidenceRecord JSONL).
type RetrievedContext struct {
	MatrixCorpora             []string `json:"matrix_corpora,omitempty"`
	MatrixHits                int      `json:"matrix_hits,omitempty"`
	MatrixChunksKept          int      `json:"matrix_chunks_kept,omitempty"`
	MatrixChunksDropped       int      `json:"matrix_chunks_dropped,omitempty"`
	PathwayFingerprintsSeen   int      `json:"pathway_fingerprints_seen,omitempty"`
}

// HumanOverride captures a human-in-the-loop decision overriding the
// scorer's verdict. Recorded but doesn't change the scorer's output;
// downstream consumers (UI, distillation acceptance) decide how to
// treat it.
type HumanOverride struct {
	Overrider     string `json:"overrider"`
	Decision      string `json:"decision"` // accept|reject|needs_review
	Reason        string `json:"reason"`
	OverriddenAt  string `json:"overridden_at"`
}

// SubScores carries the deterministic scorer's intermediate signals
// alongside the final ScoreCategory. Persisted on every ScoredRun
// so a downstream UI can show "why" without re-running the scorer.
type SubScores struct {
	CargoGreen              *bool  `json:"cargo_green,omitempty"`
	AnchorGrounding         *float64 `json:"anchor_grounding,omitempty"`
	SchemaValid             *bool  `json:"schema_valid,omitempty"`
	PathwayReplaySucceeded  *bool  `json:"pathway_replay_succeeded,omitempty"`
	ObserverVerdict         ObserverVerdict `json:"observer_verdict,omitempty"`
	AcceptedOnAttempt       *int   `json:"accepted_on_attempt,omitempty"`
	// Extra fields the Rust schema accepted as `[key: string]: unknown`.
	// Captured here as a free-form map so future signals don't require
	// type-system changes.
	Extras map[string]any `json:"-"`
}

// ScoredRun is the deterministic scorer's output. One per
// EvidenceRecord. Provenance ties back to the materialized evidence
// row (not the raw source stream).
type ScoredRun struct {
	SchemaVersion    int           `json:"schema_version"`
	EvidenceRunID    string        `json:"evidence_run_id"`
	EvidenceTaskID   string        `json:"evidence_task_id"`
	Category         ScoreCategory `json:"category"`
	Reasons          []string      `json:"reasons"` // non-empty
	ScoredAt         string        `json:"scored_at"`
	ScorerVersion    string        `json:"scorer_version"`
	SubScores        *SubScores    `json:"sub_scores,omitempty"`
	Provenance       Provenance    `json:"provenance"`
}

// SftSample is one entry in exports/sft/instruction_response.jsonl.
// The contamination firewall lives in ValidateSftSample.
type SftSample struct {
	SchemaVersion int             `json:"schema_version"`
	ID            string          `json:"id"`
	Instruction   string          `json:"instruction"`
	Context       string          `json:"context"` // empty allowed; null/missing not
	Response      string          `json:"response"`
	SourceRunID   string          `json:"source_run_id"`
	QualityScore  SftQualityScore `json:"quality_score"`
	CreatedAt     string          `json:"created_at"`
	Provenance    Provenance      `json:"provenance"`
}

// ─── Validators ──────────────────────────────────────────────────

// ValidationError is a single field-level violation.
type ValidationError struct {
	Field   string
	Message string
}

func (e ValidationError) Error() string {
	return fmt.Sprintf("%s: %s", e.Field, e.Message)
}

// ValidationErrors is the joinable error returned by the validators
// when one or more fields violate the schema.
type ValidationErrors []ValidationError

func (es ValidationErrors) Error() string {
	if len(es) == 0 {
		return "no errors"
	}
	parts := make([]string, len(es))
	for i, e := range es {
		parts[i] = e.Error()
	}
	return strings.Join(parts, "; ")
}

// HasErrors returns true when one or more errors are present.
func (es ValidationErrors) HasErrors() bool { return len(es) > 0 }

// ValidateScoredRun mirrors the Rust validateScoredRun. Returns nil
// on success or a ValidationErrors with the field-level violations.
func ValidateScoredRun(r ScoredRun) error {
	var errs ValidationErrors
	if r.SchemaVersion != ScoredRunSchemaVersion {
		errs = append(errs, ValidationError{
			"schema_version",
			fmt.Sprintf("expected %d, got %d", ScoredRunSchemaVersion, r.SchemaVersion),
		})
	}
	if r.EvidenceRunID == "" {
		errs = append(errs, ValidationError{"evidence_run_id", "must be non-empty"})
	}
	if r.EvidenceTaskID == "" {
		errs = append(errs, ValidationError{"evidence_task_id", "must be non-empty"})
	}
	if !validISOTimestamp(r.ScoredAt) {
		errs = append(errs, ValidationError{"scored_at", "must be ISO 8601 timestamp"})
	}
	if r.ScorerVersion == "" {
		errs = append(errs, ValidationError{"scorer_version", "must be non-empty"})
	}
	if len(r.Reasons) == 0 {
		errs = append(errs, ValidationError{"reasons", "must be non-empty (every score needs a reason)"})
	}
	if !isValidCategory(r.Category) {
		errs = append(errs, ValidationError{"category", fmt.Sprintf("must be one of %v, got %q", AllScoreCategories, r.Category)})
	}
	if err := validateProvenance(r.Provenance, "provenance"); err != nil {
		errs = append(errs, err...)
	}
	if r.SubScores != nil && r.SubScores.AnchorGrounding != nil {
		ag := *r.SubScores.AnchorGrounding
		if ag < 0 || ag > 1 {
			errs = append(errs, ValidationError{"sub_scores.anchor_grounding", "must be in [0, 1]"})
		}
	}
	if errs.HasErrors() {
		return errs
	}
	return nil
}

// ValidateSftSample is the contamination firewall. Returns ErrSftContamination
// (wrapped) when quality_score is in SftNever — which is the safety-critical
// guarantee the spec calls non-negotiable.
//
// Other field violations come back as ValidationErrors.
func ValidateSftSample(s SftSample) error {
	var errs ValidationErrors
	if s.SchemaVersion != SftSampleSchemaVersion {
		errs = append(errs, ValidationError{
			"schema_version",
			fmt.Sprintf("expected %d, got %d", SftSampleSchemaVersion, s.SchemaVersion),
		})
	}
	if s.ID == "" {
		errs = append(errs, ValidationError{"id", "must be non-empty"})
	}
	if strings.TrimSpace(s.Instruction) == "" {
		errs = append(errs, ValidationError{"instruction", "must be non-whitespace (no empty pairs)"})
	}
	if strings.TrimSpace(s.Response) == "" {
		errs = append(errs, ValidationError{"response", "must be non-whitespace (no empty pairs)"})
	}
	// Context is required-string but empty is allowed.
	// (Field is always typed as string in Go, so the only way to
	// distinguish "set" from "missing" was via the JSON layer; here
	// empty is fine.)
	if s.SourceRunID == "" {
		errs = append(errs, ValidationError{"source_run_id", "must be non-empty"})
	}
	if !validISOTimestamp(s.CreatedAt) {
		errs = append(errs, ValidationError{"created_at", "must be ISO 8601 timestamp"})
	}
	if err := validateProvenance(s.Provenance, "provenance"); err != nil {
		errs = append(errs, err...)
	}

	// Contamination firewall. Hard non-negotiable per the spec.
	if !isLegalSftQualityScore(s.QualityScore) {
		// If it's in SftNever, surface the firewall sentinel — callers
		// can errors.Is(err, ErrSftContamination) to reliably detect
		// "the spec said never" as opposed to "you typo'd a category."
		if isContaminationCategory(s.QualityScore) {
			return fmt.Errorf("%w: quality_score %q in SftNever (rejected/needs_human_review never legal in SFT)",
				ErrSftContamination, s.QualityScore)
		}
		errs = append(errs, ValidationError{
			"quality_score",
			fmt.Sprintf("must be one of %v, got %q", SftQualityScores, s.QualityScore),
		})
	}

	if errs.HasErrors() {
		return errs
	}
	return nil
}

// ErrSftContamination is the firewall sentinel — when ValidateSftSample
// rejects a sample because its quality_score is in SftNever, callers
// can errors.Is(err, ErrSftContamination) to reliably distinguish
// "spec violation" from "typo'd category."
var ErrSftContamination = errors.New("distillation: SFT contamination — quality_score in SftNever")

// ─── Internal helpers ────────────────────────────────────────────

func isValidCategory(c ScoreCategory) bool {
	for _, v := range AllScoreCategories {
		if c == v {
			return true
		}
	}
	return false
}

func isLegalSftQualityScore(q SftQualityScore) bool {
	for _, v := range SftQualityScores {
		if q == v {
			return true
		}
	}
	return false
}

func isContaminationCategory(q SftQualityScore) bool {
	// Compare as ScoreCategory — the on-wire string is the same; this
	// just guards the firewall against typos that happen to match
	// SftNever string-wise.
	for _, v := range SftNever {
		if string(v) == string(q) {
			return true
		}
	}
	return false
}

func validISOTimestamp(s string) bool {
	if s == "" {
		return false
	}
	// time.Parse with RFC3339 covers most ISO 8601. We accept both
	// the basic and nano variants since the Rust producers vary.
	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 validateProvenance(p Provenance, field string) ValidationErrors {
	var errs ValidationErrors
	if p.SourceFile == "" {
		errs = append(errs, ValidationError{field + ".source_file", "must be non-empty"})
	}
	if p.SigHash == "" {
		errs = append(errs, ValidationError{field + ".sig_hash", "must be non-empty"})
	}
	if !validISOTimestamp(p.RecordedAt) {
		errs = append(errs, ValidationError{field + ".recorded_at", "must be ISO 8601 timestamp"})
	}
	return errs
}

// MarshalSubScores is a shim — Go's encoding/json doesn't merge a
// "rest" map into the struct's JSON output by default. Callers that
// need Extras serialized into the same object can use this helper.
func MarshalSubScores(s *SubScores) ([]byte, error) {
	if s == nil {
		return []byte("null"), nil
	}
	// First marshal the typed fields normally.
	type alias SubScores
	base, err := json.Marshal((*alias)(s))
	if err != nil {
		return nil, err
	}
	if len(s.Extras) == 0 {
		return base, nil
	}
	// Decode back to a map, merge Extras, re-encode. Less efficient
	// but keeps the field semantics correct (typed fields override
	// extras on collision — first-write-wins for known keys).
	var combined map[string]any
	if err := json.Unmarshal(base, &combined); err != nil {
		return nil, err
	}
	for k, v := range s.Extras {
		if _, exists := combined[k]; !exists {
			combined[k] = v
		}
	}
	return json.Marshal(combined)
}