Files
stack/packages/macp/src/risk-floor.ts
jason.woltje b8807e60df
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/push/publish Pipeline was successful
feat(agent-reflection): durable kernel — reflection.v1 capture + risk-floor + Phase-0 (#545)
2026-06-16 21:35:40 +00:00

139 lines
4.6 KiB
TypeScript

/**
* Diff risk-floor — deterministic review-need classifier.
*
* Given the set of changed files in a diff, derive a *minimum* review
* requirement ("floor") from the change surface. This is the mechanical half
* of the agent reflection loop (design §6): risky surfaces (auth, data, infra)
* trip a review requirement regardless of what the agent self-reports.
*
* Precedence (authoritative ordering, see design §5):
* CI/tests > human merge > reviewer verdict > self-reflection
* This module sits at the *floor*. It NEVER overrides CI or a human; a
* `needs_review: false` verdict means "no surface tripped the floor", not
* "safe to merge". Consumers MUST keep CI/tests authoritative above it.
*
* Pure and deterministic: no IO, no clock, no randomness. Same input → same
* verdict. Safe to call from a Stop hook via `node -e` or to port inline.
*/
/** Review surfaces, ordered most- to least-sensitive. */
export type ReviewSurface = 'auth' | 'data' | 'infra' | 'build' | 'ui' | 'test' | 'docs' | 'none';
export interface RiskFloorInput {
/** Paths of changed files, repo-relative. Order-insensitive. */
filesChanged: string[];
/** Optional diff size signals; reserved for future weighting. */
insertions?: number;
deletions?: number;
}
export interface RiskFloorVerdict {
/** True when the change surface meets/exceeds the review threshold. */
needs_review: boolean;
/** Aggregate risk score in [0, 1] — the max surface weight across files. */
score: number;
/** The dominant (highest-weight) surface across all changed files. */
surface: ReviewSurface;
/** Human-readable explanation naming the surface and tripping files. */
reason: string;
}
/** Default review threshold; `score >= THRESHOLD` ⇒ `needs_review`. */
export const DEFAULT_RISK_THRESHOLD = 0.5;
interface SurfaceRule {
surface: ReviewSurface;
weight: number;
/** Case-insensitive regex matched against the file path. */
pattern: RegExp;
}
/**
* Surface classification rules, evaluated highest-weight first. The first
* rule whose pattern matches a path classifies that file; the file's surface
* is the highest-risk surface it matches (rules are pre-sorted by weight).
*/
const SURFACE_RULES: readonly SurfaceRule[] = [
{
surface: 'auth',
weight: 1.0,
pattern: /auth|login|session|token|permission|rbac|credential|secret/i,
},
{
surface: 'data',
weight: 0.9,
pattern: /migration|prisma|schema|\.sql|entity|repository|seed/i,
},
{
surface: 'infra',
weight: 0.85,
pattern: /docker|\.woodpecker|compose|traefik|deploy|helm|k8s|terraform/i,
},
{
surface: 'build',
weight: 0.6,
pattern: /package\.json|tsconfig|turbo\.json|pnpm-|\.config\.|eslint|vite/i,
},
{ surface: 'ui', weight: 0.4, pattern: /\.tsx|\.css|components\/|apps\/web\// },
{ surface: 'test', weight: 0.2, pattern: /\.spec\.|\.test\.|__tests__\// },
{ surface: 'docs', weight: 0.1, pattern: /\.md$|docs\// },
];
const NONE_WEIGHT = 0.0;
/** Classify a single path to its highest-risk surface and weight. */
function classify(path: string): { surface: ReviewSurface; weight: number } {
for (const rule of SURFACE_RULES) {
if (rule.pattern.test(path)) {
return { surface: rule.surface, weight: rule.weight };
}
}
return { surface: 'none', weight: NONE_WEIGHT };
}
/**
* Evaluate the review risk-floor for a diff.
*
* @param input changed files (+ optional size signals)
* @param threshold review cutoff; defaults to {@link DEFAULT_RISK_THRESHOLD}
*/
export function evaluateRiskFloor(
input: RiskFloorInput,
threshold: number = DEFAULT_RISK_THRESHOLD,
): RiskFloorVerdict {
const files = (input.filesChanged ?? []).filter((f) => typeof f === 'string' && f.length > 0);
if (files.length === 0) {
return {
needs_review: false,
score: 0,
surface: 'none',
reason: 'no files changed',
};
}
let topSurface: ReviewSurface = 'none';
let topWeight = NONE_WEIGHT;
const tripping: string[] = [];
for (const file of files) {
const { surface, weight } = classify(file);
if (weight > topWeight) {
topWeight = weight;
topSurface = surface;
tripping.length = 0;
tripping.push(file);
} else if (weight === topWeight && surface === topSurface && surface !== 'none') {
tripping.push(file);
}
}
const needs_review = topWeight >= threshold;
const reason =
topSurface === 'none'
? `no sensitive surface in ${files.length} changed file(s)`
: `${topSurface} surface (weight ${topWeight}) in: ${tripping.join(', ')}`;
return { needs_review, score: topWeight, surface: topSurface, reason };
}