profit
156dae6732
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.
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";
|
|
|
|
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 }>;
|
|
}
|