ac01fffd9a
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>
50 lines
1.8 KiB
TypeScript
50 lines
1.8 KiB
TypeScript
// Standalone runner for auditor fixtures. Invoke:
|
|
//
|
|
// bun run auditor/fixtures/cli.ts hybrid_38_40_45
|
|
//
|
|
// Prints human-readable per-layer breakdown + JSON result so the
|
|
// output can be captured by the dynamic check without re-running.
|
|
|
|
import { runHybridFixture, type FixtureResult } from "./hybrid_38_40_45.ts";
|
|
|
|
const fixtureArg = process.argv[2] ?? "hybrid_38_40_45";
|
|
|
|
let result: FixtureResult;
|
|
switch (fixtureArg) {
|
|
case "hybrid_38_40_45":
|
|
result = await runHybridFixture();
|
|
break;
|
|
default:
|
|
console.error(`unknown fixture: ${fixtureArg}`);
|
|
process.exit(2);
|
|
}
|
|
|
|
// Human-readable summary
|
|
console.error(""); // blank line to stderr so stdout JSON stays clean
|
|
console.error(`─── Fixture: ${result.fixture} ───`);
|
|
console.error(` overall: ${result.overall.toUpperCase()}`);
|
|
console.error(` shipped: [${result.shipped_phases.join(", ") || "—"}]`);
|
|
console.error(` placeholder: [${result.placeholder_phases.join(", ") || "—"}]`);
|
|
console.error("");
|
|
for (const l of result.layers) {
|
|
const mark = l.ok ? "✓" : "✗";
|
|
const phaseStr = `Phase ${l.phase}`.padEnd(11);
|
|
console.error(` ${mark} ${phaseStr} ${l.layer.padEnd(30)} ${String(l.latency_ms).padStart(6)}ms`);
|
|
if (l.ok) {
|
|
console.error(` ${l.evidence.slice(0, 200)}`);
|
|
} else {
|
|
console.error(` ERROR: ${l.error?.slice(0, 240) ?? "unknown"}`);
|
|
}
|
|
}
|
|
console.error("");
|
|
for (const n of result.notes) console.error(` note: ${n}`);
|
|
console.error("");
|
|
|
|
// Machine-readable output on stdout.
|
|
console.log(JSON.stringify(result, null, 2));
|
|
|
|
// Exit code reflects overall: 0 pass, 2 partial, 1 fail.
|
|
// Dynamic check reads this AND the JSON; partial-pass is treated
|
|
// as informative (some layers shipped), not blocking on its own.
|
|
process.exit(result.overall === "pass" ? 0 : result.overall === "partial_pass" ? 2 : 1);
|