Auditor self-test branch: real-world pipelines + cohesion Phase C + KB index (PR #8)
Bundles 12 commits validating the auditor + scrum_master architecture end-to-end: - enrich_prd_pipeline / hard_task_escalation / scrum_master_pipeline stress tests - Tree-split + scrum_reviews.jsonl + kb_query surfacing - Verdict → audit_lessons feedback loop (closed) - kb_index aggregator with confidence-based severity policy - 9-run + 5-run empirical tests proved the predictive-compounding property - Level 1 correction: temp=0 cloud inference for deterministic per-claim verdicts - audit_one.ts dry-run CLI - Fixes: static quoted-string guard, empirical-claim classification, symbol-resolver gate, repo-file size cap See PR #8 for run-by-run commit history.
This commit was merged in pull request #8.
This commit is contained in:
+135
-6
@@ -13,6 +13,8 @@
|
||||
// with a 15KB diff + claim list).
|
||||
|
||||
import type { Claim, Finding } from "../types.ts";
|
||||
import { Glob } from "bun";
|
||||
import { readFile } from "node:fs/promises";
|
||||
|
||||
const GATEWAY = process.env.LH_GATEWAY_URL ?? "http://localhost:3100";
|
||||
const MODEL = process.env.LH_AUDITOR_REVIEW_MODEL ?? "gpt-oss:120b";
|
||||
@@ -22,6 +24,7 @@ const MODEL = process.env.LH_AUDITOR_REVIEW_MODEL ?? "gpt-oss:120b";
|
||||
// block finding when the file was simply outside the truncation window.
|
||||
const MAX_DIFF_CHARS = 40000;
|
||||
const CALL_TIMEOUT_MS = 120_000;
|
||||
const REPO_ROOT = "/home/profit/lakehouse";
|
||||
|
||||
export async function runInferenceCheck(claims: Claim[], diff: string): Promise<Finding[]> {
|
||||
if (claims.length === 0) {
|
||||
@@ -33,6 +36,21 @@ export async function runInferenceCheck(claims: Claim[], diff: string): Promise<
|
||||
}];
|
||||
}
|
||||
|
||||
// Empirical claims (runtime metrics / observed outcomes) can't be
|
||||
// verified from the diff. Drop them from the cloud prompt so the
|
||||
// reviewer doesn't chase ghosts. A future `runtime_evidence` check
|
||||
// can validate these against data/_kb/*/summary.json outputs.
|
||||
const verifiable = claims.filter(c => c.strength !== "empirical");
|
||||
const empiricalCount = claims.length - verifiable.length;
|
||||
if (verifiable.length === 0) {
|
||||
return [{
|
||||
check: "inference",
|
||||
severity: "info",
|
||||
summary: `all ${claims.length} claims are empirical (runtime metrics) — skipping cloud inference`,
|
||||
evidence: [`empirical claims can't be verified from a static diff; needs runtime-evidence check`],
|
||||
}];
|
||||
}
|
||||
|
||||
const truncated = diff.length > MAX_DIFF_CHARS
|
||||
? diff.slice(0, MAX_DIFF_CHARS) + `\n...[${diff.length - MAX_DIFF_CHARS} more chars truncated]`
|
||||
: diff;
|
||||
@@ -70,7 +88,7 @@ export async function runInferenceCheck(claims: Claim[], diff: string): Promise<
|
||||
|
||||
const userMsg = [
|
||||
`Ship-claims the author made (numbered 0..N-1):`,
|
||||
claims.map((c, i) => ` ${i}. [${c.strength}] "${c.text}" at ${c.location}`).join("\n"),
|
||||
verifiable.map((c, i) => ` ${i}. [${c.strength}] "${c.text}" at ${c.location}`).join("\n"),
|
||||
"",
|
||||
`Diff:`,
|
||||
"```",
|
||||
@@ -94,9 +112,22 @@ export async function runInferenceCheck(claims: Claim[], diff: string): Promise<
|
||||
{ role: "system", content: systemMsg },
|
||||
{ role: "user", content: userMsg },
|
||||
],
|
||||
// Deterministic classification — temp=0 is greedy-sample, so
|
||||
// identical input yields identical output on the same model
|
||||
// version. This kills the signature creep we observed in the
|
||||
// 9-run empirical test (sig_count 16→27 from cloud phrasing
|
||||
// variance at temp=0.2).
|
||||
//
|
||||
// IMPORTANT: keep think=true. gpt-oss:120b is a reasoning
|
||||
// model; setting think=false caused it to return empty content
|
||||
// on large prompts (observed during Level 1 validation: 13421
|
||||
// tokens used, empty content returned). The reasoning trace is
|
||||
// variable prose, but at temp=0 the FINAL classification is
|
||||
// still deterministic because greedy sampling converges to
|
||||
// the same conclusion from the same starting state.
|
||||
max_tokens: 3000,
|
||||
temperature: 0.2,
|
||||
think: true, // T3 overseer should reason — JSON shape is still required
|
||||
temperature: 0,
|
||||
think: true,
|
||||
}),
|
||||
signal: AbortSignal.timeout(CALL_TIMEOUT_MS),
|
||||
});
|
||||
@@ -152,7 +183,9 @@ export async function runInferenceCheck(claims: Claim[], diff: string): Promise<
|
||||
for (const v of parsed.claim_verdicts ?? []) {
|
||||
if (v?.backed === false) {
|
||||
const idx = typeof v.claim_idx === "number" ? v.claim_idx : -1;
|
||||
const claim = claims[idx];
|
||||
// Indices point at the verifiable[] list we sent the cloud,
|
||||
// not the full claims[] list. Translate back.
|
||||
const claim = verifiable[idx];
|
||||
if (!claim) continue;
|
||||
// Strong+unbacked = BLOCK. That's the whole point of the auditor.
|
||||
const sev: Finding["severity"] = claim.strength === "strong" ? "block"
|
||||
@@ -172,17 +205,113 @@ export async function runInferenceCheck(claims: Claim[], diff: string): Promise<
|
||||
}
|
||||
|
||||
for (const g of parsed.unflagged_gaps ?? []) {
|
||||
const summary = String(g?.summary ?? "?");
|
||||
const location = String(g?.location ?? "?");
|
||||
// False-positive guard — when the cloud says "X not defined in this
|
||||
// diff" or "missing implementation of X", the cloud may just mean
|
||||
// "X is not in the added lines," not "X doesn't exist in the repo."
|
||||
// Extract candidate symbol names and grep the repo. If any symbol
|
||||
// is defined elsewhere, drop the finding — it's a known-symbol
|
||||
// reference, not a placeholder.
|
||||
if (/not\s+defined|missing\s+implementation|never\s+referenced\s+or\s+integrated/i.test(summary)) {
|
||||
const symbols = extractSymbols(summary);
|
||||
if (symbols.length > 0) {
|
||||
const resolved = await symbolsExistInRepo(symbols);
|
||||
if (resolved.length === symbols.length) {
|
||||
// Every named symbol exists somewhere in the repo — silent drop.
|
||||
continue;
|
||||
}
|
||||
if (resolved.length > 0) {
|
||||
// Partially resolved — demote to info with a note.
|
||||
findings.push({
|
||||
check: "inference",
|
||||
severity: "info",
|
||||
summary: `cloud gap partially resolved by repo grep: ${summary.slice(0, 120)}`,
|
||||
evidence: [
|
||||
`location: ${location.slice(0, 140)}`,
|
||||
`resolved via grep: ${resolved.join(",")}`,
|
||||
`unresolved: ${symbols.filter(s => !resolved.includes(s)).join(",")}`,
|
||||
],
|
||||
});
|
||||
continue;
|
||||
}
|
||||
}
|
||||
}
|
||||
findings.push({
|
||||
check: "inference",
|
||||
severity: "warn",
|
||||
summary: `cloud-flagged gap not in any claim: ${String(g?.summary ?? "?").slice(0, 120)}`,
|
||||
evidence: [`location: ${String(g?.location ?? "?").slice(0, 140)}`],
|
||||
summary: `cloud-flagged gap not in any claim: ${summary.slice(0, 120)}`,
|
||||
evidence: [`location: ${location.slice(0, 140)}`],
|
||||
});
|
||||
}
|
||||
|
||||
return findings;
|
||||
}
|
||||
|
||||
// Pull out plausible code-symbol names from a summary string.
|
||||
// Matches:
|
||||
// - identifier with backticks: `foo_bar`
|
||||
// - identifier followed by parens: foo_bar()
|
||||
// - CamelCase types
|
||||
// - snake_case_functions
|
||||
// Filters out common English words that could be matched accidentally.
|
||||
const STOPWORDS = new Set([
|
||||
"not","the","and","for","this","that","with","but","are","was","has",
|
||||
"have","been","any","missing","implementation","diff","defined","never",
|
||||
"referenced","integrated","flow","code","file","some","only","when",
|
||||
]);
|
||||
function extractSymbols(text: string): string[] {
|
||||
const out = new Set<string>();
|
||||
// `backticked` symbols
|
||||
for (const m of text.matchAll(/`([A-Za-z_][A-Za-z0-9_]{2,})`/g)) out.add(m[1]);
|
||||
// foo() or foo_bar() calls
|
||||
for (const m of text.matchAll(/\b([A-Za-z_][A-Za-z0-9_]{2,})\s*\(/g)) out.add(m[1]);
|
||||
// CamelCase types (3+ chars, must start with uppercase)
|
||||
for (const m of text.matchAll(/\b([A-Z][A-Za-z0-9]{2,})\b/g)) out.add(m[1]);
|
||||
return Array.from(out).filter(s => !STOPWORDS.has(s.toLowerCase()));
|
||||
}
|
||||
|
||||
// Scan the repo for at least one definition of each symbol. Uses Bun's
|
||||
// Glob to walk TS/Rust/Python/JS sources; ignores node_modules, data/,
|
||||
// and target/. Skips files > 500KB — those are fixtures/snapshots that
|
||||
// won't contain a definition line and slurping them slows the audit.
|
||||
async function symbolsExistInRepo(symbols: string[]): Promise<string[]> {
|
||||
const patterns = ["**/*.ts", "**/*.tsx", "**/*.rs", "**/*.py", "**/*.js"];
|
||||
const skip = (p: string) => p.includes("/node_modules/") || p.startsWith("data/") || p.includes("/target/") || p.startsWith("dist/");
|
||||
const MAX_FILE_BYTES = 500_000;
|
||||
const { stat } = await import("node:fs/promises");
|
||||
const resolved = new Set<string>();
|
||||
const toFind = new Set(symbols);
|
||||
for (const pat of patterns) {
|
||||
if (toFind.size === 0) break;
|
||||
const glob = new Glob(pat);
|
||||
for await (const f of glob.scan({ cwd: REPO_ROOT, onlyFiles: true })) {
|
||||
if (skip(f)) continue;
|
||||
try { const s = await stat(`${REPO_ROOT}/${f}`); if (s.size > MAX_FILE_BYTES) continue; } catch { continue; }
|
||||
let content: string;
|
||||
try { content = await readFile(`${REPO_ROOT}/${f}`, "utf8"); } catch { continue; }
|
||||
for (const sym of Array.from(toFind)) {
|
||||
// Definition heuristics: `function sym`, `fn sym`, `const sym`,
|
||||
// `let sym`, `def sym`, `class sym`, `struct sym`, `enum sym`,
|
||||
// `trait sym`, `async function sym`, `pub (async )?fn sym`.
|
||||
const re = new RegExp(
|
||||
`\\b(function|async\\s+function|const|let|var|def|class|struct|enum|trait|impl|type|interface|fn|pub\\s+(async\\s+)?fn)\\s+${escapeRe(sym)}\\b`
|
||||
);
|
||||
if (re.test(content)) {
|
||||
resolved.add(sym);
|
||||
toFind.delete(sym);
|
||||
if (toFind.size === 0) break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return Array.from(resolved);
|
||||
}
|
||||
|
||||
function escapeRe(s: string): string {
|
||||
return s.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
|
||||
}
|
||||
|
||||
// Lift the first balanced JSON object out of the response. Tolerates
|
||||
// leading prose, code fences, and model reasoning preamble when the
|
||||
// cloud model ignored "strict JSON only."
|
||||
|
||||
Reference in New Issue
Block a user