profit ac01fffd9a checkpoint: matrix-agent-validated (2026-04-25)
Architectural snapshot of the lakehouse codebase at the point where the
full matrix-driven agent loop with Mem0 versioning + deletion was
validated end-to-end.

WHAT THIS REPO IS
A clean single-commit snapshot of the lakehouse code. Heavy test data
(.parquet datasets, vector indexes) excluded — see REPLICATION.md for
regen path. Full lakehouse history at git.agentview.dev/profit/lakehouse.

WHAT WAS PROVEN
- Vector retrieval across multi-corpora matrix (chicago_permits + entity
  briefs + sec_tickers + distilled procedural + llm_team runs)
- Observer hand-review (cloud + heuristic fallback) gating each candidate
- Local-model agent loop (qwen3.5:latest) with tool use + scratchpad
- Playbook seal on success → next-iter retrieval surfaces it as preamble
- Mem0 versioning + deletion in pathway_memory:
    * UPSERT: ADD on new workflow, UPDATE bumps replay_count on identical
    * REVISE: chains versions, parent.superseded_at + superseded_by stamped
    * RETIRE: marks specific trace retired with reason, excluded from retrieval
    * HISTORY: walks chain root→tip, cycle-safe

KEY DIRECTORIES
- crates/vectord/src/pathway_memory.rs — Mem0 ops live here
- crates/vectord/src/playbook_memory.rs — original Mem0 reference
- tests/agent_test/ — local-model agent harness + PRD + session archives
- scripts/dump_raw_corpus.sh — MinIO bucket dump (raw test corpus)
- scripts/vectorize_raw_corpus.ts — corpus → vector indexes
- scripts/analyze_chicago_contracts.ts — real inference pipeline
- scripts/seal_agent_playbook.ts — Mem0 upsert from agent traces

Replication: see REPLICATION.md for Debian 13 clean install + cloud-only
adaptation (no local Ollama).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-25 19:43:27 -05:00

52 lines
2.2 KiB
TypeScript

import { test, expect } from "bun:test";
import { computeSignature, specDigest } from "./kb.ts";
// kb signature invariants — required so the KB's retrieval layer
// doesn't silently drift when we add fields to ScenarioSpec.
test("computeSignature is stable across reorderings of unrelated fields", () => {
const a = {
client: "Acme Corp",
events: [
{ kind: "baseline_fill", role: "Welder", count: 3, city: "Toledo", state: "OH" },
],
};
const b = { ...a, date: "2026-05-01", contract: { deadline: "2026-05-15" } } as any;
const c = { ...a, staffer: { id: "S-1", name: "X", tenure_months: 10, role: "senior" } } as any;
const sigA = computeSignature(a);
const sigB = computeSignature(b);
const sigC = computeSignature(c);
expect(sigA).toBe(sigB);
expect(sigA).toBe(sigC);
});
test("computeSignature changes when role changes", () => {
const base = { client: "Acme", events: [{ kind: "baseline_fill", role: "Welder", count: 3, city: "Toledo", state: "OH" }] };
const swapped = { client: "Acme", events: [{ kind: "baseline_fill", role: "Electrician", count: 3, city: "Toledo", state: "OH" }] };
expect(computeSignature(base)).not.toBe(computeSignature(swapped));
});
test("computeSignature changes when city or count changes", () => {
const base = { client: "A", events: [{ kind: "baseline_fill", role: "Welder", count: 3, city: "Toledo", state: "OH" }] };
const cityChange = { ...base, events: [{ ...base.events[0], city: "Detroit", state: "MI" }] };
const countChange = { ...base, events: [{ ...base.events[0], count: 5 }] };
expect(computeSignature(base)).not.toBe(computeSignature(cityChange));
expect(computeSignature(base)).not.toBe(computeSignature(countChange));
});
test("specDigest includes each event's role + city", () => {
const spec = {
client: "Acme",
events: [
{ kind: "baseline_fill", role: "Welder", count: 3, city: "Toledo", state: "OH" },
{ kind: "emergency", role: "Loader", count: 2, city: "Chicago", state: "IL" },
],
};
const digest = specDigest(spec);
expect(digest).toContain("Acme");
expect(digest).toContain("Welder");
expect(digest).toContain("Toledo,OH");
expect(digest).toContain("Loader");
expect(digest).toContain("Chicago,IL");
});