lakehouse/auditor/index.ts
root dc6dd1d30c auditor: per-PR audit cap (default 3) — daemon halts further audits until reset
Adds MAX_AUDITS_PER_PR (env LH_AUDITOR_MAX_AUDITS_PER_PR, default 3).
The poller increments a per-PR counter on each successful audit; when
the counter reaches the cap it skips that PR with a "capped" log line
until the operator manually clears state.audit_count_per_pr[<PR#>].

Why:
"I don't want it to continuously loop even if it finds a problem.
We need a maximum until we can come back."

Without this, the daemon polls every 90s and audits every new head
SHA. If each fix-commit surfaces new findings (which is what
kimi_architect is designed to do), the audit loop runs unbounded
while the operator is away. At ~$0.30/audit on Opus and 5-10 pushes
a day, that's $1-3/day idle burn — fine for a couple days, painful
for weeks.

Cap mechanics:
- Counter starts at 0 per PR (or whatever exists in state.json)
- Increments only on successful audit (failures don't count)
- Comparison is >= so cap=3 means audits 1, 2, 3 run; 4+ skip
- Skip is logged: "capped at N/M audits — clear state.json
  audit_count_per_pr.<N> to resume"
- New `cycles_skipped_capped` counter on State for observability

Reset:
  jq '.audit_count_per_pr = (.audit_count_per_pr - {"11": 4})' \
    /home/profit/lakehouse/data/_auditor/state.json > /tmp/s.json && \
    mv /tmp/s.json /home/profit/lakehouse/data/_auditor/state.json
- Daemon picks up the change on the next cycle (no restart needed —
  state is reloaded each cycle)
- Or set the entry to 0 if you want to keep the key

Disable cap: LH_AUDITOR_MAX_AUDITS_PER_PR=0
Reduce cap: LH_AUDITOR_MAX_AUDITS_PER_PR=1   (one audit per PR head, then pause)

Pre-existing PR audits today (4 on PR #11) are NOT seeded into the
counter by this commit — operator decides post-deploy whether to set
state.audit_count_per_pr.11 to today's actual count or leave at 0.
Setting to 4 (or 3) immediately halts further audits on PR #11.

Verification:
  bun build auditor/index.ts   compiles
  systemctl restart lakehouse-auditor   active

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 07:24:23 -05:00

183 lines
6.9 KiB
TypeScript

// Auditor poller — the top-level entry. Polls Gitea for open PRs on
// a fixed interval, dedupes by head SHA, runs audit + posts verdict
// for each new (pr, sha) pair.
//
// Run manually:
// bun run auditor/index.ts
//
// Stop:
// touch auditor.paused (skips next cycle)
// pkill -f auditor/index.ts (kills in-flight)
//
// State:
// data/_auditor/state.json — last-audited SHA per PR
// data/_auditor/verdicts/{id}.json — per-run verdict records
//
// This entry runs forever. A systemd unit would wrap it once the
// workflow is trusted (same pattern as mcp-server, observer).
import { readFile, writeFile, mkdir, access } from "node:fs/promises";
import { listOpenPrs } from "./gitea.ts";
import { auditPr } from "./audit.ts";
const POLL_INTERVAL_MS = 90_000; // 90s — enough budget for audit runs to complete
const PAUSE_FILE = "/home/profit/lakehouse/auditor.paused";
const STATE_FILE = "/home/profit/lakehouse/data/_auditor/state.json";
// Per-PR audit cap. Prevents the daemon from running away on a PR
// when each push surfaces new findings — operator wants to review
// in batch, not have the daemon burn budget while they're away.
// Default 3 audits per PR. Override via LH_AUDITOR_MAX_AUDITS_PER_PR.
// Set to 0 to disable the cap.
//
// Reset (after manual review): edit data/_auditor/state.json and
// set audit_count_per_pr.<N> = 0 (or delete the key). Daemon picks
// up the change on the next cycle without restart.
const MAX_AUDITS_PER_PR = Number(process.env.LH_AUDITOR_MAX_AUDITS_PER_PR) || 3;
interface State {
// Map: PR number → last-audited head SHA. Lets us dedupe audits
// across restarts (poller can crash/restart without re-auditing
// all open PRs from scratch).
last_audited: Record<string, string>;
// Map: PR number → number of audits run on that PR since last reset.
// Daemon halts auditing a PR once this hits MAX_AUDITS_PER_PR.
// Operator clears the entry to resume.
audit_count_per_pr: Record<string, number>;
started_at: string;
cycles_total: number;
cycles_skipped_paused: number;
cycles_skipped_capped: number;
audits_run: number;
last_cycle_at?: string;
}
async function fileExists(path: string): Promise<boolean> {
try { await access(path); return true; } catch { return false; }
}
async function loadState(): Promise<State> {
try {
const raw = await readFile(STATE_FILE, "utf8");
const s = JSON.parse(raw);
return {
last_audited: s.last_audited ?? {},
started_at: s.started_at ?? new Date().toISOString(),
audit_count_per_pr: s.audit_count_per_pr ?? {},
cycles_total: s.cycles_total ?? 0,
cycles_skipped_paused: s.cycles_skipped_paused ?? 0,
cycles_skipped_capped: s.cycles_skipped_capped ?? 0,
audits_run: s.audits_run ?? 0,
last_cycle_at: s.last_cycle_at,
};
} catch {
return {
last_audited: {},
audit_count_per_pr: {},
started_at: new Date().toISOString(),
cycles_total: 0,
cycles_skipped_paused: 0,
cycles_skipped_capped: 0,
audits_run: 0,
};
}
}
async function saveState(s: State): Promise<void> {
await mkdir("/home/profit/lakehouse/data/_auditor", { recursive: true });
await writeFile(STATE_FILE, JSON.stringify(s, null, 2));
}
async function runCycle(state: State): Promise<State> {
state.cycles_total += 1;
state.last_cycle_at = new Date().toISOString();
if (await fileExists(PAUSE_FILE)) {
state.cycles_skipped_paused += 1;
console.log(`[auditor] cycle ${state.cycles_total}: paused (touch ${PAUSE_FILE} exists)`);
return state;
}
let prs;
try {
prs = await listOpenPrs();
} catch (e) {
console.error(`[auditor] listOpenPrs failed: ${(e as Error).message}`);
return state;
}
console.log(`[auditor] cycle ${state.cycles_total}: ${prs.length} open PR(s)`);
for (const pr of prs) {
const prKey = String(pr.number);
const last = state.last_audited[prKey];
if (last === pr.head_sha) {
console.log(`[auditor] skip PR #${pr.number} (SHA ${pr.head_sha.slice(0, 8)} already audited)`);
continue;
}
// Per-PR audit cap — once a PR has been audited MAX_AUDITS_PER_PR
// times, halt further audits until the operator manually clears
// audit_count_per_pr[<N>] in state.json. Prevents runaway burn
// when each fix surfaces new findings.
const auditedSoFar = state.audit_count_per_pr[prKey] ?? 0;
if (MAX_AUDITS_PER_PR > 0 && auditedSoFar >= MAX_AUDITS_PER_PR) {
console.log(`[auditor] skip PR #${pr.number} (capped at ${auditedSoFar}/${MAX_AUDITS_PER_PR} audits — clear state.json audit_count_per_pr.${prKey} to resume)`);
state.cycles_skipped_capped += 1;
continue;
}
console.log(`[auditor] audit PR #${pr.number} (${pr.head_sha.slice(0, 8)}) — ${pr.title.slice(0, 60)} [${auditedSoFar + 1}/${MAX_AUDITS_PER_PR}]`);
try {
// Skip dynamic by default: it mutates live playbook state and
// re-runs on every PR update would pollute quickly. Operator
// can run dynamic via `bun run auditor/fixtures/cli.ts` manually
// OR set LH_AUDITOR_RUN_DYNAMIC=1 to opt in.
const run_dynamic = process.env.LH_AUDITOR_RUN_DYNAMIC === "1";
const verdict = await auditPr(pr, {
skip_dynamic: !run_dynamic,
skip_inference: process.env.LH_AUDITOR_SKIP_INFERENCE === "1",
});
console.log(`[auditor] verdict=${verdict.overall} findings=${verdict.metrics.findings_total} (block=${verdict.metrics.findings_block} warn=${verdict.metrics.findings_warn})`);
state.last_audited[prKey] = pr.head_sha;
state.audit_count_per_pr[prKey] = auditedSoFar + 1;
state.audits_run += 1;
if (state.audit_count_per_pr[prKey] >= MAX_AUDITS_PER_PR) {
console.log(`[auditor] PR #${pr.number} reached cap (${MAX_AUDITS_PER_PR} audits) — daemon will skip further audits until reset`);
}
} catch (e) {
console.error(`[auditor] audit failed: ${(e as Error).message}`);
}
}
return state;
}
async function main(): Promise<void> {
console.log(`[auditor] starting poller — interval ${POLL_INTERVAL_MS / 1000}s`);
console.log(`[auditor] pause file: ${PAUSE_FILE}`);
console.log(`[auditor] state file: ${STATE_FILE}`);
let state = await loadState();
console.log(`[auditor] loaded state: ${Object.keys(state.last_audited).length} PRs previously audited, ${state.cycles_total} cycles so far`);
// Single-shot mode for CLI testing: `bun run auditor/index.ts --once`
const once = process.argv.includes("--once");
if (once) {
state = await runCycle(state);
await saveState(state);
console.log(`[auditor] single-shot complete. total audits: ${state.audits_run}`);
return;
}
// Loop.
while (true) {
state = await runCycle(state);
await saveState(state);
await new Promise(res => setTimeout(res, POLL_INTERVAL_MS));
}
}
main().catch(e => {
console.error("[auditor] fatal:", e);
process.exit(1);
});