27b1d27605
Some checks failed
lakehouse/auditor 9 blocking issues: todo!() macro call in tests/real-world/scrum_master_pipeline.ts
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>
66 lines
3.0 KiB
TypeScript
66 lines
3.0 KiB
TypeScript
// ScratchpadSummary — structured normalization of a tree-split or
|
|
// long-running scratchpad. Distinct from EvidenceRecord because a
|
|
// scratchpad accumulates across many calls; this schema captures the
|
|
// state at a checkpoint moment.
|
|
import {
|
|
ValidationResult, requireString, requireIsoTimestamp, requireProvenance, requireStringArray,
|
|
} from "./types";
|
|
|
|
export const SCRATCHPAD_SCHEMA_VERSION = 1;
|
|
|
|
export interface ScratchpadSummary {
|
|
schema_version: number;
|
|
run_id: string;
|
|
current_objective: string;
|
|
completed_steps: string[];
|
|
failed_steps: string[];
|
|
pending_steps: string[];
|
|
important_paths: string[]; // file paths the scratchpad references
|
|
decisions: string[]; // architectural/scope decisions made
|
|
unresolved_questions: string[];
|
|
validation_status: "pass" | "fail" | "partial" | "pending";
|
|
next_command?: string; // recommendation for next action
|
|
source_scratchpad_hash: string; // sha256 of the full source scratchpad text — diff detection
|
|
summarized_at: string; // ISO 8601
|
|
provenance: { source_file: string; line_offset?: number; sig_hash: string; recorded_at: string };
|
|
}
|
|
|
|
const STATUS = ["pass", "fail", "partial", "pending"];
|
|
|
|
export function validateScratchpadSummary(input: unknown): ValidationResult<ScratchpadSummary> {
|
|
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 !== SCRATCHPAD_SCHEMA_VERSION) {
|
|
errors.push(`schema_version: expected ${SCRATCHPAD_SCHEMA_VERSION}, got ${JSON.stringify(r.schema_version)}`);
|
|
ok = false;
|
|
}
|
|
ok = requireString(r.run_id, "run_id", errors) && ok;
|
|
ok = requireString(r.current_objective, "current_objective", errors) && ok;
|
|
ok = requireIsoTimestamp(r.summarized_at, "summarized_at", errors) && ok;
|
|
if (typeof r.source_scratchpad_hash !== "string" || !/^[0-9a-f]{64}$/.test(r.source_scratchpad_hash as string)) {
|
|
errors.push("source_scratchpad_hash: must be hex sha256");
|
|
ok = false;
|
|
}
|
|
ok = requireStringArray(r.completed_steps, "completed_steps", errors) && ok;
|
|
ok = requireStringArray(r.failed_steps, "failed_steps", errors) && ok;
|
|
ok = requireStringArray(r.pending_steps, "pending_steps", errors) && ok;
|
|
ok = requireStringArray(r.important_paths, "important_paths", errors) && ok;
|
|
ok = requireStringArray(r.decisions, "decisions", errors) && ok;
|
|
ok = requireStringArray(r.unresolved_questions, "unresolved_questions", errors) && ok;
|
|
if (!STATUS.includes(r.validation_status as string)) {
|
|
errors.push(`validation_status: must be one of ${STATUS.join("|")}`);
|
|
ok = false;
|
|
}
|
|
if (r.next_command !== undefined && typeof r.next_command !== "string") {
|
|
errors.push("next_command: expected string when present");
|
|
ok = false;
|
|
}
|
|
ok = requireProvenance(r.provenance, "provenance", errors) && ok;
|
|
|
|
if (!ok) return { valid: false, errors };
|
|
return { valid: true, value: r as unknown as ScratchpadSummary };
|
|
}
|