23f7624596
ADR-166 MCP Bridge Security Lock / Static-source security lock (push) Failing after 0s
ADR-166 MCP Bridge Security Lock / Compose default binds loopback + Mongo has auth (push) Failing after 2s
CodeQL Advanced / Analyze (rust) (push) Failing after 0s
ADR-166 MCP Bridge Security Lock / plugin-agent-federation bindHost default (push) Failing after 1s
ADR-166 MCP Bridge Security Lock / Runtime behavior — 401 + terminal gate + fail-closed (push) Failing after 4s
business-pods-smoke / smoke (push) Failing after 1s
all-plugins-smoke / smoke-all (push) Failing after 2s
CI/CD Pipeline / Security & Code Quality (push) Failing after 1s
CI/CD Pipeline / Test Suite (ubuntu-latest) (push) Failing after 1s
CI/CD Pipeline / Build & Package (macos-latest) (push) Has been skipped
CI/CD Pipeline / Build & Package (ubuntu-latest) (push) Has been skipped
CI/CD Pipeline / Build & Package (windows-latest) (push) Has been skipped
CI/CD Pipeline / Documentation & Examples (push) Failing after 1s
Clone Tracker (14-day rolling) / Snapshot clones for ruflo ecosystem (push) Failing after 1s
CodeQL Advanced / Analyze (actions) (push) Failing after 1s
CodeQL Advanced / Analyze (javascript-typescript) (push) Failing after 1s
federation-peer-rust / stable-noop (push) Failing after 1s
metaharness-ci / score (push) Failing after 1s
metaharness-ci / router-compat (push) Failing after 0s
metaharness-ci / similarity-tests (push) Failing after 0s
no-agentbbs-smoke / smoke-without-agentbbs (push) Failing after 1s
V3 CI/CD Pipeline / Build V3 (windows-latest) (push) Has been skipped
codex-integration-audit / Codex integration audit (push) Failing after 1s
helpers-manifest-guard / guard (push) Failing after 1s
🔗 Cross-Agent Integration Tests / 🤝 Agent Coordination Tests (push) Has been skipped
🔗 Cross-Agent Integration Tests / 🧠 Memory Sharing Integration (push) Has been skipped
🔗 Cross-Agent Integration Tests / 🛡️ Fault Tolerance Tests (push) Has been skipped
🔗 Cross-Agent Integration Tests / ⚡ Performance Integration Tests (push) Has been skipped
metaharness-ci / mcp-scan (push) Failing after 1s
metaharness-ci / eject-dryrun (push) Failing after 1s
metaharness-ci / metaharness-real-data (push) Failing after 0s
no-cli-optdep-bloat-2561 / guard (push) Failing after 1s
no-metaharness-smoke / smoke-without-metaharness (push) Failing after 1s
no-phantom-agentic-flow-subpath / guard (push) Failing after 1s
🔄 Automated Rollback Manager / 🚨 Failure Detection (push) Failing after 1s
V3 CI/CD Pipeline / Plugin hooks smoke / ubuntu-latest / Node 22 (push) Failing after 1s
V3 CI/CD Pipeline / ruflo-graph-intelligence build + test smoke (#2044, ADR-123) (push) Failing after 1s
CVE Audit Gate / Audit root (critical-blocking) (push) Failing after 2s
cost-tracker-smoke / smoke (push) Failing after 3s
oia-audit-weekly / audit (push) Failing after 2s
ruflo-agent-smoke / ruflo-agent structural smoke (push) Failing after 1s
📊 Status Badges Update / 📊 Update Status Badges (push) Failing after 1s
V3 CI/CD Pipeline / Static regression guards (#2267 YAML + (push) Failing after 1s
V3 CI/CD Pipeline / Test V3 Packages (push) Failing after 0s
V3 CI/CD Pipeline / agent_execute provider routing smoke (#2042) (push) Failing after 0s
CVE Audit Gate / Audit v3 (critical-blocking) (push) Failing after 1s
federation-peer-rust / stable-native (push) Failing after 2s
🔗 Cross-Agent Integration Tests / 🚀 Integration Test Setup (push) Failing after 2s
neural-trader-smoke / runtime-smoke (push) Failing after 1s
V3 CI/CD Pipeline / Build V3 (macos-latest) (push) Has been skipped
V3 CI/CD Pipeline / Build V3 (ubuntu-latest) (push) Has been skipped
V3 CI/CD Pipeline / Type Check V3 (push) Failing after 1s
V3 CI/CD Pipeline / Smoke (no better-sqlite3) / ubuntu-latest / Node 24 (push) Failing after 1s
V3 CI/CD Pipeline / Smoke (no better-sqlite3) / ubuntu-latest / Node 22 (push) Failing after 2s
V3 CI/CD Pipeline / browser rvf create flag smoke (#2015) (push) Failing after 0s
V3 CI/CD Pipeline / Dependency review (#2046) (push) Has been skipped
V3 CI/CD Pipeline / Supply-chain audit (#2046) (push) Failing after 0s
V3 CI/CD Pipeline / witness marker drift smoke (#2021) (push) Failing after 1s
V3 CI/CD Pipeline / neural-trader portfolio CG smoke (#2068, ADR-126 Phase 3) (push) Failing after 1s
V3 CI/CD Pipeline / neural-trader backtest signing smoke (#2068, ADR-126 Phase 4) (push) Failing after 1s
V3 CI/CD Pipeline / kg-extract type-import classification smoke (#2049) (push) Failing after 0s
V3 CI/CD Pipeline / witness verify precondition smoke (#1880) (push) Failing after 2s
V3 CI/CD Pipeline / neural-trader pipeline risk-gate smoke (#2068, ADR-126 Phase 5) (push) Failing after 0s
V3 CI/CD Pipeline / neural-trader feature attribution smoke (#2068, ADR-126 Phase 6) (push) Failing after 0s
V3 CI/CD Pipeline / plugin-registry signature verification smoke (#1922, CWE-347) (push) Failing after 4s
V3 CI/CD Pipeline / memory stats legacy-DB smoke (#2120) (push) Failing after 4s
V3 CI/CD Pipeline / github deprecated actions smoke (#2089, ADR-127 Phase 3) (push) Failing after 1s
V3 CI/CD Pipeline / graph query + pathfinder smoke (ADR-130 P2+P5) (push) Has been skipped
V3 CI/CD Pipeline / graph trajectory hooks smoke (ADR-130 P3) (push) Has been skipped
V3 CI/CD Pipeline / graph plugin adapter smoke (ADR-130 P4) (push) Has been skipped
V3 CI/CD Pipeline / graph benchmark (ADR-130 P6) (push) Has been skipped
V3 CI/CD Pipeline / statusline generator delegation smoke (#2195) (push) Failing after 1s
V3 CI/CD Pipeline / wizard init regression guard (#2206 (push) Failing after 1s
V3 CI/CD Pipeline / memory no-stray-db smoke (ADR-125 P7) (push) Failing after 1s
V3 CI/CD Pipeline / github-safe injection smoke (#2089, ADR-127 Phase 1) (push) Failing after 1s
V3 CI/CD Pipeline / github actions pin smoke (#2089, ADR-127 Phase 1) (push) Failing after 1s
V3 CI/CD Pipeline / github attribution opt-in smoke (#2089, ADR-127 Phase 4) (push) Failing after 1s
V3 CI/CD Pipeline / pre-bash hook safety smoke (#2017) (push) Failing after 1s
V3 CI/CD Pipeline / Memory import smoke / ubuntu-latest (push) Failing after 0s
V3 CI/CD Pipeline / MCP protocol smoke / ubuntu-latest (push) Failing after 2s
V3 CI/CD Pipeline / ruvllm WASM auto-init smoke (#2086) (push) Failing after 4s
V3 CI/CD Pipeline / MCP paired-tool round-trip smoke (#1889) (push) Failing after 1s
V3 CI/CD Pipeline / Plugin package install-safety (#1902/#1903/#1904) (push) Failing after 1s
V3 CI/CD Pipeline / Tool description discoverability (ADR-112) (push) Failing after 3s
V3 CI/CD Pipeline / CLI npx-install smoke (#1147 / (22) (push) Failing after 1s
V3 CI/CD Pipeline / CLI npx-install smoke (#1147 / (24) (push) Failing after 1s
V3 CI/CD Pipeline / Windows hook shim smoke (#2132) / ubuntu-latest (push) Failing after 2s
V3 CI/CD Pipeline / Windows hook execution smoke (#2132) / ubuntu-latest (push) Failing after 1s
V3 CI/CD Pipeline / Windows init hooks smoke (#2132) / ubuntu-latest (push) Failing after 1s
V3 CI/CD Pipeline / Vector-index dimension audit (#1947) (push) Failing after 0s
V3 CI/CD Pipeline / Hook-command install safety (#1921) (push) Failing after 1s
V3 CI/CD Pipeline / ToolOutputGuardrail smoke (ADR-131, (push) Failing after 1s
V3 CI/CD Pipeline / init-bundle invariants smoke (#2095, ADR-128 Phase 5) (push) Failing after 1s
V3 CI/CD Pipeline / wasm provider bridge smoke (ADR-129 P1) (push) Failing after 2s
V3 CI/CD Pipeline / wasm gallery CRUD smoke (ADR-129 P3) (push) Failing after 1s
V3 CI/CD Pipeline / wasm plugin bridge smoke (ADR-129 P4) (push) Failing after 0s
V3 CI/CD Pipeline / wasm compose smoke (ADR-129 P2) (push) Failing after 4s
V3 CI/CD Pipeline / graph schema smoke (ADR-130 P1) (push) Failing after 0s
Validate Marketplace / validate (push) Failing after 1s
🔍 Verification Pipeline / 🚀 Setup Verification (push) Failing after 1s
🔍 Verification Pipeline / 🛡️ Security Verification (push) Has been skipped
🔍 Verification Pipeline / 📝 Code Quality (push) Has been skipped
🔍 Verification Pipeline / 🧪 Test Verification (${{ matrix.os }}, Node ${{ matrix.node }}) (push) Has been skipped
🔍 Verification Pipeline / 🏗️ Build Verification (push) Has been skipped
🔍 Verification Pipeline / 📚 Documentation Verification (push) Has been skipped
CVE Audit Gate / High-severity report (warn only) (push) Has been cancelled
🔄 Automated Rollback Manager / 🔄 Execute Rollback (push) Has been cancelled
🔄 Automated Rollback Manager / ✅ Post-Rollback Verification (push) Has been cancelled
🔄 Automated Rollback Manager / 📊 Rollback Monitoring (push) Has been cancelled
V3 CI/CD Pipeline / Windows init hooks smoke (#2132) / windows-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook execution smoke (#2132) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook execution smoke (#2132) / windows-latest (push) Has been cancelled
🔄 Automated Rollback Manager / ⏳ Manual Rollback Approval (push) Has been cancelled
V3 CI/CD Pipeline / MCP protocol smoke / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Memory import smoke / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook shim smoke (#2132) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows hook shim smoke (#2132) / windows-latest (push) Has been cancelled
V3 CI/CD Pipeline / Windows init hooks smoke (#2132) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Witness verify (signed manifest) / macos-latest (push) Has been cancelled
V3 CI/CD Pipeline / Witness verify (signed manifest) / ubuntu-latest (push) Has been cancelled
V3 CI/CD Pipeline / Witness verify (signed manifest) / windows-latest (push) Has been cancelled
V3 CI/CD Pipeline / Publish to npm (alpha) (push) Has been cancelled
V3 CI/CD Pipeline / Smoke (no better-sqlite3) / macos-latest / Node 22 (push) Has been cancelled
V3 CI/CD Pipeline / Plugin hooks smoke / macos-latest / Node 22 (push) Has been cancelled
CI/CD Pipeline / Deploy & Release (push) Has been cancelled
CI/CD Pipeline / CI Status (push) Has been cancelled
🔗 Cross-Agent Integration Tests / 📊 Integration Test Report (push) Has been cancelled
🔄 Automated Rollback Manager / 🔍 Pre-Rollback Validation (push) Has been cancelled
🔍 Verification Pipeline / ⚡ Performance Verification (push) Has been cancelled
🔍 Verification Pipeline / 📊 Verification Report (push) Has been cancelled
238 lines
8.9 KiB
TypeScript
238 lines
8.9 KiB
TypeScript
/**
|
|
* @claude-flow/browser - Causal Recovery Tests (ADR-122 Phase 2)
|
|
*
|
|
* Acceptance criteria covered:
|
|
* - After N selector breaks on a domain, snapshot annotates the broken refs
|
|
* with non-zero `_causalRiskScore`
|
|
* - Cross-origin isolation: breaks on example.com don't pollute other.com
|
|
* - explain() returns prior break events + alternative locator suggestions
|
|
* - classifyBreak maps Playwright-style errors to our taxonomy
|
|
* - parseUrl normalises into (origin, path) for graph isolation
|
|
*/
|
|
|
|
import { describe, it, expect, beforeEach } from 'vitest';
|
|
import { CausalRecoveryService } from '../src/application/causal-recovery-service.js';
|
|
import { InMemoryBreakStore, classifyBreak, parseUrl } from '../src/infrastructure/causal-recovery-store.js';
|
|
import type { Snapshot } from '../src/domain/types.js';
|
|
|
|
describe('CausalRecoveryService', () => {
|
|
let service: CausalRecoveryService;
|
|
let store: InMemoryBreakStore;
|
|
|
|
beforeEach(() => {
|
|
store = new InMemoryBreakStore();
|
|
service = new CausalRecoveryService({ store });
|
|
});
|
|
|
|
describe('classifyBreak', () => {
|
|
it('maps not-found errors', () => {
|
|
expect(classifyBreak('Element not found: @e3')).toBe('element-not-found');
|
|
});
|
|
it('maps visibility errors', () => {
|
|
expect(classifyBreak('Element is not visible')).toBe('element-not-visible');
|
|
});
|
|
it('maps timeout errors', () => {
|
|
expect(classifyBreak('action timed out after 5000ms')).toBe('timeout');
|
|
});
|
|
it('maps detached errors', () => {
|
|
expect(classifyBreak('stale element reference: element is detached')).toBe('element-detached');
|
|
});
|
|
it('maps navigation errors', () => {
|
|
expect(classifyBreak('frame detached during navigation')).toBe('navigation-during-action');
|
|
});
|
|
it('defaults to unknown', () => {
|
|
expect(classifyBreak('something weird happened')).toBe('unknown');
|
|
expect(classifyBreak(undefined)).toBe('unknown');
|
|
});
|
|
});
|
|
|
|
describe('parseUrl', () => {
|
|
it('extracts origin + path', () => {
|
|
const { origin, path } = parseUrl('https://example.com/login?next=/dash');
|
|
expect(origin).toBe('https://example.com');
|
|
expect(path).toBe('/login?next=/dash');
|
|
});
|
|
it('handles invalid URLs gracefully', () => {
|
|
const { origin, path } = parseUrl('not-a-url');
|
|
expect(origin).toBe('not-a-url');
|
|
expect(path).toBe('/');
|
|
});
|
|
});
|
|
|
|
describe('reportBreak', () => {
|
|
it('records a break event with classified kind', async () => {
|
|
const event = await service.reportBreak({
|
|
url: 'https://example.com/login',
|
|
selector: '@e3',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'Element not found: @e3' },
|
|
sessionId: 's1',
|
|
});
|
|
expect(event.origin).toBe('https://example.com');
|
|
expect(event.path).toBe('/login');
|
|
expect(event.kind).toBe('element-not-found');
|
|
expect(event.selector).toBe('@e3');
|
|
expect(event.sessionId).toBe('s1');
|
|
});
|
|
|
|
it('preserves lastKnownRole/Name for future fuzzy matching', async () => {
|
|
const event = await service.reportBreak({
|
|
url: 'https://example.com/login',
|
|
selector: '@e3',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'timeout' },
|
|
lastKnownRole: 'button',
|
|
lastKnownName: 'Submit',
|
|
});
|
|
expect(event.lastKnownRole).toBe('button');
|
|
expect(event.lastKnownName).toBe('Submit');
|
|
});
|
|
});
|
|
|
|
describe('risk scoring + snapshot annotation', () => {
|
|
it('returns zero risk for never-seen selectors', async () => {
|
|
const risk = await service.getRisk('https://example.com', '@e1');
|
|
expect(risk.riskScore).toBe(0);
|
|
expect(risk.breakCount).toBe(0);
|
|
});
|
|
|
|
it('accumulates risk with repeated breaks', async () => {
|
|
for (let i = 0; i < 3; i++) {
|
|
await service.reportBreak({
|
|
url: 'https://example.com/login',
|
|
selector: '@e3',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'not found' },
|
|
});
|
|
}
|
|
const risk = await service.getRisk('https://example.com', '@e3');
|
|
expect(risk.breakCount).toBe(3);
|
|
expect(risk.riskScore).toBeGreaterThan(0);
|
|
expect(risk.lastBreakKind).toBe('element-not-found');
|
|
});
|
|
|
|
it('annotates a snapshot with _causalRiskScore on broken refs', async () => {
|
|
// Record one break on @e3
|
|
await service.reportBreak({
|
|
url: 'https://example.com/login',
|
|
selector: '@e3',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'not found' },
|
|
});
|
|
|
|
const snapshot: Snapshot = {
|
|
tree: { role: 'main', children: [{ role: 'button', ref: '@e3', name: 'Submit' }] },
|
|
refs: { '@e1': { role: 'textbox' }, '@e2': { role: 'textbox' }, '@e3': { role: 'button' } },
|
|
url: 'https://example.com/login',
|
|
title: 'Login',
|
|
timestamp: '2026-05-18T20:00:00Z',
|
|
};
|
|
const annotated = await service.annotateSnapshot(snapshot, 'https://example.com/login');
|
|
expect(annotated._causal['@e3'].breakCount).toBe(1);
|
|
expect(annotated._causal['@e3'].riskScore).toBeGreaterThan(0);
|
|
// Un-broken refs should be zero
|
|
expect(annotated._causal['@e1'].riskScore).toBe(0);
|
|
expect(annotated._causal['@e2'].riskScore).toBe(0);
|
|
});
|
|
|
|
it('decorates the snapshot tree in-place with risk markers', async () => {
|
|
await service.reportBreak({
|
|
url: 'https://example.com/login',
|
|
selector: '@e3',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'not found' },
|
|
});
|
|
const snapshot: Snapshot = {
|
|
tree: { role: 'main', children: [{ role: 'button', ref: '@e3', name: 'Submit' }] },
|
|
refs: { '@e3': { role: 'button' } },
|
|
url: 'https://example.com/login',
|
|
title: 'Login',
|
|
timestamp: '2026-05-18T20:00:00Z',
|
|
};
|
|
const annotated = await service.decorateTree(snapshot, 'https://example.com/login');
|
|
const btn = annotated.tree.children![0] as Record<string, unknown>;
|
|
expect(btn._causalRiskScore).toBeGreaterThan(0);
|
|
expect(btn._causalBreakCount).toBe(1);
|
|
});
|
|
});
|
|
|
|
describe('cross-origin isolation', () => {
|
|
it('breaks on example.com do not pollute other.com risk', async () => {
|
|
// 5 breaks on example.com
|
|
for (let i = 0; i < 5; i++) {
|
|
await service.reportBreak({
|
|
url: 'https://example.com/login',
|
|
selector: '@e3',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'not found' },
|
|
});
|
|
}
|
|
const other = await service.getRisk('https://other.com', '@e3');
|
|
expect(other.breakCount).toBe(0);
|
|
expect(other.riskScore).toBe(0);
|
|
|
|
const same = await service.getRisk('https://example.com', '@e3');
|
|
expect(same.breakCount).toBe(5);
|
|
});
|
|
});
|
|
|
|
describe('explain()', () => {
|
|
it('returns prior breaks + suggested locator strategies', async () => {
|
|
// Record several breaks with role+name metadata
|
|
for (let i = 0; i < 2; i++) {
|
|
await service.reportBreak({
|
|
url: 'https://example.com/login',
|
|
selector: '@e3',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'not found' },
|
|
lastKnownRole: 'button',
|
|
lastKnownName: 'Submit',
|
|
});
|
|
}
|
|
const explanation = await service.explain('https://example.com/login', '@e3', {
|
|
lastKnownRole: 'button',
|
|
lastKnownName: 'Submit',
|
|
});
|
|
expect(explanation.priorBreaks.length).toBeGreaterThanOrEqual(2);
|
|
// Should suggest role-based locator first (highest stability)
|
|
const roleSuggestion = explanation.suggestions.find(s => s.strategy === 'find-role');
|
|
expect(roleSuggestion).toBeDefined();
|
|
expect(roleSuggestion!.value).toContain('button');
|
|
expect(roleSuggestion!.value).toContain('Submit');
|
|
// testid is always suggested as the gold standard
|
|
const testidSuggestion = explanation.suggestions.find(s => s.strategy === 'find-testid');
|
|
expect(testidSuggestion).toBeDefined();
|
|
});
|
|
|
|
it('does not include unrelated origin breaks in explanation', async () => {
|
|
await service.reportBreak({
|
|
url: 'https://other.com/foo',
|
|
selector: '@e3',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'not found' },
|
|
});
|
|
const explanation = await service.explain('https://example.com', '@e3');
|
|
expect(explanation.priorBreaks).toHaveLength(0);
|
|
});
|
|
});
|
|
|
|
describe('listBreaks', () => {
|
|
it('returns all breaks for an origin', async () => {
|
|
await service.reportBreak({
|
|
url: 'https://example.com/a',
|
|
selector: '@e1',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'not found' },
|
|
});
|
|
await service.reportBreak({
|
|
url: 'https://example.com/b',
|
|
selector: '@e2',
|
|
action: 'fill',
|
|
actionResult: { success: false, error: 'not found' },
|
|
});
|
|
const breaks = await service.listBreaks('https://example.com');
|
|
expect(breaks).toHaveLength(2);
|
|
});
|
|
});
|
|
});
|