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>
78 lines
2.8 KiB
TypeScript
78 lines
2.8 KiB
TypeScript
import { test, expect } from "bun:test";
|
|
import { normalizeInputSync, normalizeInput } from "./normalize.ts";
|
|
|
|
test("structured FillEvent → fast path", () => {
|
|
const n = normalizeInputSync({
|
|
kind: "baseline_fill", role: "Welder", city: "Nashville",
|
|
state: "TN", count: 4,
|
|
});
|
|
expect(n.extraction_method).toBe("structured");
|
|
expect(n.role).toBe("Welder");
|
|
expect(n.city).toBe("Nashville");
|
|
expect(n.state).toBe("TN");
|
|
expect(n.count).toBe(4);
|
|
expect(n.confidence).toBe("high");
|
|
expect(n.missing_fields.length).toBe(0);
|
|
});
|
|
|
|
test("misplacement kind → rescue intent", () => {
|
|
const n = normalizeInputSync({ kind: "misplacement", role: "Welder", city: "Nashville", state: "TN", count: 1 });
|
|
expect(n.intent).toBe("rescue");
|
|
});
|
|
|
|
test("structured with full state name normalizes to abbrev", () => {
|
|
const n = normalizeInputSync({ role: "Welder", city: "Nashville", state: "Tennessee" });
|
|
expect(n.state).toBe("TN");
|
|
});
|
|
|
|
test("natural-language regex path extracts count + role + city + state", () => {
|
|
const n = normalizeInputSync("I need 3 Welders in Nashville, TN for next week");
|
|
expect(n.role).toBe("Welder");
|
|
expect(n.city).toBe("Nashville");
|
|
expect(n.state).toBe("TN");
|
|
expect(n.count).toBe(3);
|
|
expect(n.intent).toBe("fill");
|
|
expect(n.extraction_method).toBe("regex");
|
|
});
|
|
|
|
test("natural language with plural role + full state name", () => {
|
|
const n = normalizeInputSync("fill 5 Forklift Operators in Chicago, Illinois");
|
|
expect(n.role).toBe("Forklift Operator");
|
|
expect(n.city).toBe("Chicago");
|
|
expect(n.state).toBe("IL");
|
|
expect(n.count).toBe(5);
|
|
});
|
|
|
|
test("rescue intent keyword beats fill", () => {
|
|
const n = normalizeInputSync("we need to rescue the Nashville welder fill, 2 workers");
|
|
expect(n.intent).toBe("rescue");
|
|
expect(n.count).toBe(2);
|
|
expect(n.role).toBe("Welder");
|
|
});
|
|
|
|
test("partial input reports missing fields with confidence=low or medium", () => {
|
|
const n = normalizeInputSync("need welders");
|
|
expect(n.role).toBe("Welder");
|
|
expect(n.city).toBeNull();
|
|
expect(n.state).toBeNull();
|
|
expect(n.count).toBeNull();
|
|
expect(n.missing_fields).toContain("city");
|
|
expect(n.missing_fields).toContain("state");
|
|
expect(n.confidence).toBe("low");
|
|
});
|
|
|
|
test("empty object does NOT go through structured path (no role or city)", () => {
|
|
const n = normalizeInputSync({});
|
|
expect(n.extraction_method).toBe("regex");
|
|
});
|
|
|
|
test("async normalizeInput on clean structured input matches sync", async () => {
|
|
const input = { role: "Welder", city: "Nashville", state: "TN", count: 3 };
|
|
const sync = normalizeInputSync(input);
|
|
const async_ = await normalizeInput(input);
|
|
expect(async_.role).toBe(sync.role);
|
|
expect(async_.city).toBe(sync.city);
|
|
expect(async_.state).toBe(sync.state);
|
|
expect(async_.count).toBe(sync.count);
|
|
});
|