auditor: kb_query surfaces scrum-master reviews for files in PR diff
Some checks failed
lakehouse/auditor 2 blocking issues: unimplemented!() macro call in tests/real-world/hard_task_escalation.ts

Wires the cohesion-plan Phase C link: the scrum-master pipeline writes
per-file reviews to data/_kb/scrum_reviews.jsonl on accept; the
auditor now reads that same file and emits one kb_query finding per
scrum review whose `file` matches a path in the PR's diff.

Severity heuristic: attempt 1-3 → info, attempt 4+ → warn. Reaching
the cloud specialist (attempt 4+) means the ladder had to escalate,
which is meaningful signal reviewers should see. Tree-split fired is
also surfaced in the finding summary.

audit.ts now passes pr.files.map(f => f.path) into runKbCheck (the
old signature dropped it on the floor). Also adds auditor/audit_one.ts
— a dry-run CLI for auditing a single PR without posting to Gitea,
useful for verifying check behavior without spamming review comments.

Verified: after writing scrum_reviews for auditor/audit.ts and
mcp-server/observer.ts (both in PR #7), audit_one 7 surfaced both as
info findings with preview + accepted_model + tree_split flag. A
scrum review for playbook_memory.rs (NOT in PR #7) was correctly
filtered out.
This commit is contained in:
profit 2026-04-22 21:18:21 -05:00
parent 89d188074b
commit dc01ba0a3b
3 changed files with 132 additions and 2 deletions

View File

@ -52,7 +52,7 @@ export async function auditPr(pr: PrSnapshot, opts: AuditOptions = {}): Promise<
runStaticCheck(diff),
opts.skip_dynamic ? Promise.resolve(stubFinding("dynamic", "skipped by options")) : runDynamicCheck(),
opts.skip_inference ? Promise.resolve(stubFinding("inference", "skipped by options")) : runInferenceCheck(claims, diff),
runKbCheck(claims),
runKbCheck(claims, pr.files.map(f => f.path)),
]);
const allFindings: Finding[] = [

68
auditor/audit_one.ts Normal file
View File

@ -0,0 +1,68 @@
// One-shot dry-run audit of a single PR. Useful for verifying check
// behavior (kb_query scrum surfacing, inference prompts, etc.) without
// posting to Gitea. Does NOT touch state.json and does NOT post
// commit status or PR comments.
//
// Run: bun run auditor/audit_one.ts <pr-number>
import { getPrSnapshot } from "./gitea.ts";
import { auditPr } from "./audit.ts";
async function main() {
const prNumRaw = process.argv[2];
if (!prNumRaw) {
console.error("usage: bun run auditor/audit_one.ts <pr-number>");
process.exit(2);
}
const prNum = Number(prNumRaw);
if (!Number.isFinite(prNum)) {
console.error(`invalid PR number: ${prNumRaw}`);
process.exit(2);
}
console.log(`[audit_one] fetching PR #${prNum}...`);
const pr = await getPrSnapshot(prNum);
console.log(`[audit_one] PR #${pr.number}: "${pr.title}" (head=${pr.head_sha.slice(0, 12)})`);
console.log(`[audit_one] files in diff: ${pr.files.length}`);
for (const f of pr.files) console.log(` - ${f.path} (+${f.additions}/-${f.deletions})`);
console.log("");
const verdict = await auditPr(pr, {
dry_run: true, // no Gitea posting
skip_dynamic: true, // don't run fixture
skip_inference: process.env.LH_AUDITOR_SKIP_INFERENCE === "1",
});
console.log("\n═══ VERDICT ═══");
console.log(`overall: ${verdict.overall}`);
console.log(`one-liner: ${verdict.one_liner}`);
console.log(`findings: total=${verdict.metrics.findings_total} block=${verdict.metrics.findings_block} warn=${verdict.metrics.findings_warn} info=${verdict.metrics.findings_info}`);
console.log("");
// Print findings, highlighting kb_query scrum surfacing
const byCheck: Record<string, typeof verdict.findings> = {};
for (const f of verdict.findings) (byCheck[f.check] ||= []).push(f);
for (const [check, findings] of Object.entries(byCheck)) {
console.log(`── ${check} (${findings.length}) ──`);
for (const f of findings) {
const tag = f.severity === "block" ? "🛑" : f.severity === "warn" ? "⚠️ " : " ";
console.log(` ${tag} [${f.severity}] ${f.summary}`);
if (f.summary.includes("scrum-master")) {
for (const e of f.evidence) {
console.log(`${e.slice(0, 200)}`);
}
}
}
}
const scrumFindings = verdict.findings.filter(f => f.summary.includes("scrum-master"));
console.log("");
console.log(`═══ SCRUM WIRE CHECK: ${scrumFindings.length} scrum-master findings surfaced by kb_query ═══`);
if (scrumFindings.length === 0) {
console.log(" (none — either no matching scrum_reviews.jsonl rows, or files didn't match PR diff)");
}
process.exit(0);
}
main().catch(e => { console.error("[audit_one] fatal:", e); process.exit(1); });

View File

@ -8,6 +8,7 @@
// What this check reads (all file-backed, append-only or periodic):
// data/_kb/outcomes.jsonl — per-scenario outcomes (kb.ts)
// data/_kb/error_corrections.jsonl — fail→succeed deltas on same sig
// data/_kb/scrum_reviews.jsonl — scrum-master accepted reviews
// data/_observer/ops.jsonl — observer ring → disk stream
// data/_bot/cycles/*.json — bot cycle results
//
@ -21,10 +22,11 @@ import type { Claim, Finding } from "../types.ts";
const KB_DIR = "/home/profit/lakehouse/data/_kb";
const OBSERVER_OPS = "/home/profit/lakehouse/data/_observer/ops.jsonl";
const BOT_CYCLES_DIR = "/home/profit/lakehouse/data/_bot/cycles";
const SCRUM_REVIEWS_JSONL = "/home/profit/lakehouse/data/_kb/scrum_reviews.jsonl";
const TAIL_LINES = 500;
const MAX_BOT_CYCLE_FILES = 30;
export async function runKbCheck(claims: Claim[]): Promise<Finding[]> {
export async function runKbCheck(claims: Claim[], prFiles: string[] = []): Promise<Finding[]> {
const findings: Finding[] = [];
// 1. Recent scenario outcomes: are strong-claim-style phrases showing
@ -48,6 +50,15 @@ export async function runKbCheck(claims: Claim[]): Promise<Finding[]> {
const obsFindings = await checkObserverStream();
findings.push(...obsFindings);
// 5. Scrum-master reviews — surface prior accepted reviews for any
// file in this PR's diff. Cohesion plan Phase C wire: the
// auditor gets to "borrow" the scrum-master's deeper per-file
// analysis instead of re-doing that work.
if (prFiles.length > 0) {
const scrumFindings = await checkScrumReviews(prFiles);
findings.push(...scrumFindings);
}
return findings;
}
@ -181,3 +192,54 @@ function observerBySource(ops: any[]): string {
}
return Object.entries(c).sort((a, b) => b[1] - a[1]).map(([k, v]) => `${k}=${v}`).join(", ") || "empty";
}
// Scrum-master reviews — the scrum pipeline writes one row per
// accepted per-file review. We match reviews whose `file` matches
// any path in the PR's diff, then surface the *preview* + which
// model the escalation ladder had to reach. If the scrum-master
// needed the 123B specialist or larger to resolve a file, that's
// a meaningful signal about the code's complexity — and it's
// surfaced to the PR without the auditor having to re-run the
// escalation ladder itself.
async function checkScrumReviews(prFiles: string[]): Promise<Finding[]> {
const rows = await tailJsonl<any>(SCRUM_REVIEWS_JSONL, TAIL_LINES);
if (rows.length === 0) return [];
// Match by exact file OR filename suffix — PR files arrive as
// `auditor/audit.ts`-style relative paths; scrum stores the same.
const norm = (p: string) => p.replace(/^\/+/, "").replace(/^home\/profit\/lakehouse\//, "");
const prSet = new Set(prFiles.map(norm));
// Keep only the most recent review per file (last-wins).
const latestByFile = new Map<string, any>();
for (const r of rows) {
const f = norm(String(r.file ?? ""));
if (!f) continue;
if (!prSet.has(f)) continue;
latestByFile.set(f, r);
}
if (latestByFile.size === 0) return [];
const findings: Finding[] = [];
for (const [file, r] of latestByFile) {
const model = String(r.accepted_model ?? "?");
const attempt = r.accepted_on_attempt ?? "?";
const treeSplit = !!r.tree_split_fired;
// Heuristic: if the scrum-master had to escalate past attempt 3,
// or had to tree-split, that's context the PR reviewer should see.
// Severity: info for low-escalation, warn if escalated far up
// the ladder (cloud specialist required).
const heavyEscalation = Number(attempt) >= 4;
const sev: "warn" | "info" = heavyEscalation ? "warn" : "info";
findings.push({
check: "kb_query",
severity: sev,
summary: `scrum-master review for \`${file}\` — accepted on attempt ${attempt} by \`${model}\`${treeSplit ? " (tree-split)" : ""}`,
evidence: [
`reviewed_at: ${r.reviewed_at ?? "?"}`,
`preview: ${String(r.suggestions_preview ?? "").slice(0, 300).replace(/\n/g, " ")}`,
],
});
}
return findings;
}