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
197 lines
7.9 KiB
TypeScript
197 lines
7.9 KiB
TypeScript
/**
|
|
* @claude-flow/browser - Action Routing + GOAP Preflight Tests (ADR-122 Phase 5)
|
|
*
|
|
* Acceptance criteria covered:
|
|
* - ≥30% of typical browser actions classify as Tier 1 (Agent Booster, $0)
|
|
* - High causal risk escalates Tier 1 → Tier 2+
|
|
* - Per-trajectory cost report aggregates by tier + computes Tier-1 share
|
|
* - GOAP preflight catches missing-cookie precondition before live session
|
|
* - GOAP preflight catches unsafe-URL on `open` steps
|
|
* - GOAP preflight produces routing plan with estimated total cost
|
|
*/
|
|
|
|
import { describe, it, expect } from 'vitest';
|
|
import { ActionRouter } from '../src/application/action-router.js';
|
|
import { GoapPreflightService } from '../src/application/goap-preflight.js';
|
|
import { CookieVaultService } from '../src/application/cookie-vault-service.js';
|
|
import { CausalRecoveryService } from '../src/application/causal-recovery-service.js';
|
|
|
|
describe('ActionRouter', () => {
|
|
describe('classification', () => {
|
|
it('classifies pure DOM verbs with resolved refs as Tier 1', () => {
|
|
const router = new ActionRouter();
|
|
const decision = router.classify({ action: 'click', selector: '@e1', hasResolvedRef: true });
|
|
expect(decision.tier).toBe('tier-1-booster');
|
|
expect(decision.estimatedCostUsd).toBe(0);
|
|
expect(decision.model).toBe('agent-booster');
|
|
});
|
|
|
|
it('classifies find verbs as Tier 2', () => {
|
|
const router = new ActionRouter();
|
|
expect(router.classify({ action: 'findByText', selector: 'Submit' }).tier).toBe('tier-2-haiku');
|
|
expect(router.classify({ action: 'findByRole', selector: 'button' }).tier).toBe('tier-2-haiku');
|
|
});
|
|
|
|
it('escalates Tier 1 → Tier 2 when causal risk is high', () => {
|
|
const router = new ActionRouter({ riskEscalationThreshold: 0.4 });
|
|
const decision = router.classify({
|
|
action: 'click',
|
|
selector: '@e3',
|
|
hasResolvedRef: true,
|
|
causalRiskScore: 0.7,
|
|
});
|
|
expect(decision.tier).toBe('tier-2-haiku');
|
|
expect(decision.rationale).toContain('causal risk');
|
|
});
|
|
|
|
it('classifies high-complexity hints as Tier 3', () => {
|
|
const router = new ActionRouter();
|
|
const decision = router.classify({ action: 'click', complexity: 'high' });
|
|
expect(decision.tier).toBe('tier-3-frontier');
|
|
});
|
|
|
|
it('classifies eval as Tier 3', () => {
|
|
const router = new ActionRouter();
|
|
expect(router.classify({ action: 'eval' }).tier).toBe('tier-3-frontier');
|
|
});
|
|
});
|
|
|
|
describe('cost rollup', () => {
|
|
it('aggregates per-trajectory cost by tier', () => {
|
|
const router = new ActionRouter();
|
|
const trajectoryId = 'traj-1';
|
|
// 3 Tier 1, 1 Tier 2, 1 Tier 3
|
|
router.record(trajectoryId, router.classify({ action: 'click', selector: '@e1', hasResolvedRef: true }));
|
|
router.record(trajectoryId, router.classify({ action: 'fill', selector: '@e2', hasResolvedRef: true }));
|
|
router.record(trajectoryId, router.classify({ action: 'click', selector: '@e3', hasResolvedRef: true }));
|
|
router.record(trajectoryId, router.classify({ action: 'findByText', selector: 'Submit' }));
|
|
router.record(trajectoryId, router.classify({ action: 'eval' }));
|
|
|
|
const report = router.getCostReport(trajectoryId);
|
|
expect(report).toBeDefined();
|
|
expect(report!.byTier['tier-1-booster'].count).toBe(3);
|
|
expect(report!.byTier['tier-2-haiku'].count).toBe(1);
|
|
expect(report!.byTier['tier-3-frontier'].count).toBe(1);
|
|
expect(report!.totalCostUsd).toBeCloseTo(0 + 0 + 0 + 0.0002 + 0.005, 5);
|
|
expect(report!.tier1Share).toBeCloseTo(3 / 5, 2);
|
|
});
|
|
|
|
it('representative workload achieves ≥30% Tier-1 share', () => {
|
|
const router = new ActionRouter();
|
|
const trajectoryId = 'traj-rep';
|
|
// Typical login flow: open + snapshot + fill + fill + click → 4 pure DOM, 1 navigation
|
|
const actions = [
|
|
{ action: 'open', selector: 'https://example.com' },
|
|
{ action: 'snapshot' as const },
|
|
{ action: 'fill', selector: '@e1', hasResolvedRef: true },
|
|
{ action: 'fill', selector: '@e2', hasResolvedRef: true },
|
|
{ action: 'click', selector: '@e3', hasResolvedRef: true },
|
|
{ action: 'wait', selector: '.dashboard' },
|
|
{ action: 'getText', selector: '.welcome' },
|
|
];
|
|
for (const a of actions) router.record(trajectoryId, router.classify(a as { action: string; selector?: string; hasResolvedRef?: boolean }));
|
|
const report = router.getCostReport(trajectoryId)!;
|
|
expect(report.tier1Share).toBeGreaterThanOrEqual(0.3);
|
|
});
|
|
});
|
|
});
|
|
|
|
describe('GoapPreflightService', () => {
|
|
it('passes preflight when all preconditions are met', async () => {
|
|
const vault = new CookieVaultService();
|
|
await vault.store({
|
|
cookie: { name: 'sid', value: 'opaque-token', domain: 'example.com' },
|
|
origin: 'https://example.com',
|
|
});
|
|
const preflight = new GoapPreflightService({ cookieVault: vault });
|
|
|
|
const result = await preflight.preflight({
|
|
goal: 'View dashboard',
|
|
origin: 'https://example.com',
|
|
steps: [
|
|
{
|
|
action: 'open',
|
|
target: 'https://example.com/dashboard',
|
|
preconditions: { requireCookie: { origin: 'https://example.com', name: 'sid' } },
|
|
},
|
|
{ action: 'click', target: '@e1' },
|
|
],
|
|
});
|
|
|
|
expect(result.ok).toBe(true);
|
|
expect(result.findings.filter(f => f.blocking)).toHaveLength(0);
|
|
expect(result.routingPlan).toHaveLength(2);
|
|
expect(result.estimatedCostUsd).toBeGreaterThanOrEqual(0);
|
|
});
|
|
|
|
it('blocks when a required cookie is missing from the vault', async () => {
|
|
const vault = new CookieVaultService();
|
|
const preflight = new GoapPreflightService({ cookieVault: vault });
|
|
|
|
const result = await preflight.preflight({
|
|
goal: 'View dashboard',
|
|
steps: [
|
|
{
|
|
action: 'open',
|
|
target: 'https://example.com/dashboard',
|
|
preconditions: { requireCookie: { origin: 'https://example.com', name: 'sid' } },
|
|
},
|
|
],
|
|
});
|
|
|
|
expect(result.ok).toBe(false);
|
|
const missing = result.findings.find(f => f.kind === 'missing-cookie');
|
|
expect(missing).toBeDefined();
|
|
expect(missing!.blocking).toBe(true);
|
|
});
|
|
|
|
it('warns (non-blocking) when origin has high causal risk', async () => {
|
|
const causal = new CausalRecoveryService();
|
|
for (let i = 0; i < 12; i++) {
|
|
await causal.reportBreak({
|
|
url: 'https://example.com/login',
|
|
selector: '@e3',
|
|
action: 'click',
|
|
actionResult: { success: false, error: 'not found' },
|
|
});
|
|
}
|
|
const preflight = new GoapPreflightService({ causalService: causal });
|
|
|
|
const result = await preflight.preflight({
|
|
goal: 'Click submit',
|
|
origin: 'https://example.com',
|
|
steps: [
|
|
{
|
|
action: 'click',
|
|
target: '@e3',
|
|
preconditions: { maxAvgCausalRisk: 0.5 },
|
|
},
|
|
],
|
|
});
|
|
|
|
const warning = result.findings.find(f => f.kind === 'high-causal-risk');
|
|
expect(warning).toBeDefined();
|
|
expect(warning!.blocking).toBe(false);
|
|
// ok stays true because high-causal-risk is non-blocking by design
|
|
expect(result.ok).toBe(true);
|
|
});
|
|
|
|
it('produces a routing plan with per-step decisions + total cost', async () => {
|
|
const preflight = new GoapPreflightService();
|
|
const result = await preflight.preflight({
|
|
goal: 'Compose login',
|
|
steps: [
|
|
{ action: 'open', target: 'https://example.com' },
|
|
{ action: 'fill', target: '@e1', routing: { action: 'fill', selector: '@e1', hasResolvedRef: true } },
|
|
{ action: 'findByText', target: 'Sign in', routing: { action: 'findByText', selector: 'Sign in' } },
|
|
],
|
|
});
|
|
|
|
expect(result.routingPlan).toHaveLength(3);
|
|
const tiers = result.routingPlan.map(p => p.decision.tier);
|
|
expect(tiers).toContain('tier-1-booster'); // fill with ref
|
|
expect(tiers).toContain('tier-2-haiku'); // findByText
|
|
expect(result.estimatedCostUsd).toBeGreaterThan(0);
|
|
});
|
|
});
|