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>
59 lines
1.6 KiB
TypeScript
59 lines
1.6 KiB
TypeScript
// Gitea PR open. Reads PAT from ~/.git-credentials (set up by the
|
|
// credential-helper flow). All PRs open as DRAFT so J reviews before
|
|
// merge — never auto-merge.
|
|
|
|
import { readFile } from "node:fs/promises";
|
|
|
|
const GITEA_HOST = "https://git.agentview.dev";
|
|
const REPO_OWNER = "profit";
|
|
const REPO_NAME = "lakehouse";
|
|
const CRED_FILE = "/home/profit/.git-credentials";
|
|
|
|
async function readPat(): Promise<string> {
|
|
const raw = await readFile(CRED_FILE, "utf8");
|
|
for (const line of raw.split("\n")) {
|
|
const m = line.match(/^https:\/\/[^:]+:([^@]+)@git\.agentview\.dev/);
|
|
if (m) return m[1];
|
|
}
|
|
throw new Error(`no Gitea PAT found in ${CRED_FILE}`);
|
|
}
|
|
|
|
export interface OpenPrInput {
|
|
branch: string; // head branch (just pushed)
|
|
base?: string; // default "main"
|
|
title: string;
|
|
body: string;
|
|
}
|
|
|
|
export interface OpenPrResult {
|
|
number: number;
|
|
html_url: string;
|
|
}
|
|
|
|
export async function openPr(input: OpenPrInput): Promise<OpenPrResult> {
|
|
const pat = await readPat();
|
|
const url = `${GITEA_HOST}/api/v1/repos/${REPO_OWNER}/${REPO_NAME}/pulls`;
|
|
const payload = {
|
|
title: input.title,
|
|
body: input.body,
|
|
head: input.branch,
|
|
base: input.base ?? "main",
|
|
// Gitea uses "draft" flag — always on for bot PRs.
|
|
draft: true,
|
|
};
|
|
const r = await fetch(url, {
|
|
method: "POST",
|
|
headers: {
|
|
"content-type": "application/json",
|
|
"Authorization": `token ${pat}`,
|
|
},
|
|
body: JSON.stringify(payload),
|
|
signal: AbortSignal.timeout(30000),
|
|
});
|
|
if (!r.ok) {
|
|
throw new Error(`Gitea ${r.status}: ${await r.text()}`);
|
|
}
|
|
const j = await r.json() as any;
|
|
return { number: j.number, html_url: j.html_url };
|
|
}
|