root 27b1d27605
Some checks failed
lakehouse/auditor 9 blocking issues: todo!() macro call in tests/real-world/scrum_master_pipeline.ts
distillation: Phase 0 recon + Phase 1 schemas + Phase 2 transforms scaffold
Phase 0 — docs/recon/local-distillation-recon.md
Inventories the 23 KB JSONL streams + 20 vector corpora + auditor's
kb_index.ts as substrate for the now.md distillation pipeline. Maps
spec modules to existing producers, identifies real gaps, lists 9
schemas to formalize. ZERO implementation in recon — gating doc only.

Phase 1 — auditor/schemas/distillation/
9 schemas + foundation types + 48 tests passing in 502ms:

  types.ts                      shared validators + canonicalSha256
  evidence_record.ts            EVIDENCE_SCHEMA_VERSION=1, ModelRole enum
  scored_run.ts                 4 categories pinned, anchor_grounding ∈ [0,1]
  receipt.ts                    git_sha 40-char, sha256 file refs, validation_pass:bool
  playbook.ts                   non-empty source_run_ids + acceptance_criteria
  scratchpad_summary.ts         validation_status enum, hash sha256
  model_ledger.ts               success_rate ∈ [0,1], sample_count ≥ 1
  rag_sample.ts                 success_score ∈ {accepted, partially_accepted}
  sft_sample.ts                 quality_score MUST be 'accepted' (no leak)
  preference_sample.ts          chosen != rejected, source_run_ids must differ
  evidence_record.test.ts       10 tests, JSON-fixture round-trip
  schemas.test.ts               30 tests, inline fixtures
  realdata.test.ts              8 tests, real-JSONL probe

Real-data validation probe (one of the 3 notables from recon):
46 rows across 7 sources, 100% pass. distilled_facts/procedures alive.
Report at data/_kb/realdata_validation_report.md (also written by the
test). Confirms schema fits existing producers without migration.

Phase 2 scaffold — scripts/distillation/transforms.ts
Promoted PROBES from realdata.test.ts into a real TRANSFORMS array
covering 12 source streams (8 Tier 1 validated + 4 Tier 2 from
recon's untested-streams list). Pure functions: no I/O, no model
calls, no clock reads. Caller supplies recorded_at + sig_hash so
materializer is deterministic by construction.

Spec non-negotiables enforced at schema layer (defense in depth):
  - provenance{source_file, sig_hash, recorded_at} required everywhere
  - schema_version mismatch hard-rejects (forward-compat gate)
  - SFT no-leak: validateSftSample REJECTS partially_accepted, rejected,
    needs_human_review — three explicit tests
  - Every score has WHY (reasons non-empty)
  - Every playbook traces to source (source_run_ids non-empty)
  - Every preference has WHY (reason non-empty)
  - Receipts substantive (git_sha 40-char, sha256 64-char, validation_pass:bool)

Branch carries uncommitted auditor rebuild work (mode.rs + modes.toml
+ inference.ts + static.ts) blocked on upstream Ollama Cloud kimi-k2
500 ISE; held pending recon-driven design decisions.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-26 22:30:38 -05:00

87 lines
3.6 KiB
TypeScript

// ScoredRun — output of the deterministic Success Scorer (Phase 3).
// Spec mandates 4 categories with explicit reasons; we add scorer
// versioning so a future scorer change is detectable in historical data.
import {
ValidationResult, requireString, requireIsoTimestamp, requireProvenance, requireStringArray, requireNumber,
} from "./types";
export const SCORED_RUN_SCHEMA_VERSION = 1;
export const SCORE_CATEGORIES = ["accepted", "partially_accepted", "rejected", "needs_human_review"] as const;
export type ScoreCategory = (typeof SCORE_CATEGORIES)[number];
export interface ScoredRun {
schema_version: number;
evidence_run_id: string; // FK to EvidenceRecord.run_id
evidence_task_id: string; // FK to EvidenceRecord.task_id
category: ScoreCategory;
reasons: string[]; // human-readable, e.g. ["cargo_green=true", "anchor_grounding<0.7"]
scored_at: string; // ISO 8601
scorer_version: string; // e.g. "v1.0.0" — bumped on scorer code change
// Sub-scores that the scorer collapsed into the category. Persisted
// so a downstream UI can show "why" without re-running the scorer.
sub_scores?: {
cargo_green?: boolean;
anchor_grounding?: number;
schema_valid?: boolean;
pathway_replay_succeeded?: boolean;
observer_verdict?: "accept" | "reject" | "cycle";
[key: string]: unknown;
};
provenance: {
source_file: string;
line_offset?: number;
sig_hash: string;
recorded_at: string;
};
}
export function validateScoredRun(input: unknown): ValidationResult<ScoredRun> {
const errors: string[] = [];
if (typeof input !== "object" || input === null) {
return { valid: false, errors: ["expected object"] };
}
const r = input as Record<string, unknown>;
let ok = true;
if (r.schema_version !== SCORED_RUN_SCHEMA_VERSION) {
errors.push(`schema_version: expected ${SCORED_RUN_SCHEMA_VERSION}, got ${JSON.stringify(r.schema_version)}`);
ok = false;
}
ok = requireString(r.evidence_run_id, "evidence_run_id", errors) && ok;
ok = requireString(r.evidence_task_id, "evidence_task_id", errors) && ok;
ok = requireIsoTimestamp(r.scored_at, "scored_at", errors) && ok;
ok = requireString(r.scorer_version, "scorer_version", errors) && ok;
ok = requireStringArray(r.reasons, "reasons", errors) && ok;
if (Array.isArray(r.reasons) && r.reasons.length === 0) {
errors.push("reasons: must be non-empty (every score must have at least one reason)");
ok = false;
}
if (!SCORE_CATEGORIES.includes(r.category as ScoreCategory)) {
errors.push(`category: must be one of ${SCORE_CATEGORIES.join("|")}, got ${JSON.stringify(r.category)}`);
ok = false;
}
ok = requireProvenance(r.provenance, "provenance", errors) && ok;
if (r.sub_scores !== undefined) {
if (typeof r.sub_scores !== "object" || r.sub_scores === null) {
errors.push("sub_scores: expected object when present");
ok = false;
} else {
const ss = r.sub_scores as Record<string, unknown>;
if (ss.anchor_grounding !== undefined) {
if (!requireNumber(ss.anchor_grounding, "sub_scores.anchor_grounding", errors)) ok = false;
else if ((ss.anchor_grounding as number) < 0 || (ss.anchor_grounding as number) > 1) {
errors.push("sub_scores.anchor_grounding: must be in [0, 1]");
ok = false;
}
}
if (ss.observer_verdict !== undefined && !["accept", "reject", "cycle"].includes(ss.observer_verdict as string)) {
errors.push("sub_scores.observer_verdict: must be accept|reject|cycle");
ok = false;
}
}
}
if (!ok) return { valid: false, errors };
return { valid: true, value: r as unknown as ScoredRun };
}