8d02c7f441
Adds kimi_architect as a fifth check kind in the auditor. Runs sequentially after static/dynamic/inference/kb_query, consumes their findings as context, and asks Kimi For Coding "what did everyone miss?" — targeting load-bearing issues that deepseek N=3 voting can't see (compile errors, false telemetry, schema bypasses, determinism leaks). 7/7 grounded on the distillation v1.0.0 audit experiment 2026-04-27. Off by default. Enable on the lakehouse-auditor service: systemctl edit lakehouse-auditor.service Environment=LH_AUDITOR_KIMI=1 Tunable env (all optional): LH_AUDITOR_KIMI_MODEL default kimi-for-coding LH_AUDITOR_KIMI_MAX_TOKENS default 12000 LH_GATEWAY_URL default http://localhost:3100 Guardrails: - Failure-isolated. Any Kimi error / 429 / TOS revocation returns a single info-level skip-finding so the existing pipeline never blocks on a Kimi outage. - Cost-bounded. Cached verdicts at data/_auditor/kimi_verdicts/<pr>- <sha>.json with 24h TTL — re-audits within the window return cached findings instead of re-calling upstream. New commits produce new SHAs so caching is per-head, not per-day. - 6min upstream timeout (vs 2min for openrouter inference) — Kimi is a reasoning model and the audit prompt is large. - Grounding verification baked in. Every finding's cited file:line is greppped against the actual file before the verdict is persisted. Per-finding evidence carries [grounding: verified at FILE:LINE] or [grounding: line N > EOF] / [grounding: file not found]. Confab- ulation rate goes into data/_kb/kimi_audits.jsonl as grounding_rate for "is this still valuable" tracking. Persisted artifacts: data/_auditor/kimi_verdicts/<pr>-<sha>.json full verdict + raw Kimi response + grounding data/_kb/kimi_audits.jsonl one row per call: latency, tokens, findings, grounding rate Verdict-rendering: kimi_architect now appears in the per-check sections of the human-readable comment posted to PRs (auditor/audit.ts checkOrder), after kb_query. Verification: bun build auditor/checks/kimi_architect.ts compiles bun build auditor/audit.ts compiles parser sanity (3-finding fixture) 3/3 lifted correctly Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
73 lines
2.8 KiB
TypeScript
73 lines
2.8 KiB
TypeScript
// Shared types for the claim-auditor. Every field exists for a reason;
|
|
// if something can't be verified from a check, it goes into `evidence`
|
|
// so the verdict is inspectable, not a black box.
|
|
|
|
export type CheckKind = "static" | "dynamic" | "inference" | "kb_query" | "kimi_architect";
|
|
|
|
export type Severity = "info" | "warn" | "block";
|
|
|
|
export interface Claim {
|
|
// Verbatim phrase that raised the claim — e.g. "Phase 38 shipped",
|
|
// "verified end-to-end", "works after restart". Used as the "what
|
|
// does the author assert" input to downstream checks.
|
|
text: string;
|
|
// Where it came from. `commit_sha` is the short hash; `location`
|
|
// is a file:line for in-diff claims, or "pr_body" / "commit_message".
|
|
commit_sha: string;
|
|
location: string;
|
|
// Heuristic rating of how strong the claim is. "green+tested"
|
|
// is strong; "should work" is weak. Drives sensitivity — stronger
|
|
// claims get harder-blocked on weak evidence.
|
|
//
|
|
// "empirical" is a separate class: runtime measurements like
|
|
// "N cloud calls" / "306s end-to-end" / "accepted on attempt N".
|
|
// These cannot be verified from a static diff — only from the test
|
|
// output that produced them. Inference skips diff-verification for
|
|
// empirical claims; they become info-level context unless a future
|
|
// runtime_evidence check contradicts them.
|
|
strength: "weak" | "moderate" | "strong" | "empirical";
|
|
}
|
|
|
|
export interface Finding {
|
|
check: CheckKind;
|
|
severity: Severity;
|
|
claim_text?: string;
|
|
// Free-form short description: "field added but never read", "no
|
|
// test covers this code path", "cloud model says placeholder".
|
|
summary: string;
|
|
// Concrete evidence: file paths, line numbers, log excerpts, test
|
|
// output, cloud-model verdict. No handwaving.
|
|
evidence: string[];
|
|
}
|
|
|
|
export interface Verdict {
|
|
pr_number: number;
|
|
head_sha: string;
|
|
audited_at: string;
|
|
overall: "approve" | "request_changes" | "block";
|
|
findings: Finding[];
|
|
// Real numbers that downstream policy can gate on. e.g. if the
|
|
// hybrid test produced latency numbers or token counts, they
|
|
// surface here so /auditor/history is queryable.
|
|
metrics: Record<string, number>;
|
|
// Short one-line justification for the `overall` verdict. What
|
|
// gets posted as the commit-status description in Gitea (max 140
|
|
// chars) must fit here.
|
|
one_liner: string;
|
|
}
|
|
|
|
export interface PrSnapshot {
|
|
number: number;
|
|
head_sha: string;
|
|
base_sha: string;
|
|
title: string;
|
|
body: string;
|
|
state: "open" | "closed" | "merged";
|
|
author: string;
|
|
// Array of commit messages in the PR (not diffs — those are
|
|
// fetched on-demand per-check).
|
|
commits: Array<{ sha: string; message: string; author: string }>;
|
|
// File paths touched by the PR, with lines-added / lines-removed.
|
|
files: Array<{ path: string; additions: number; deletions: number }>;
|
|
}
|