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
233 lines
7.1 KiB
TypeScript
233 lines
7.1 KiB
TypeScript
/**
|
|
* Tests for the Optimizer Loop
|
|
*/
|
|
import { describe, it, expect, beforeEach } from 'vitest';
|
|
import { OptimizerLoop } from '../src/optimizer.js';
|
|
import { RunLedger } from '../src/ledger.js';
|
|
import { GuidanceCompiler } from '../src/compiler.js';
|
|
import type { PolicyBundle, RunEvent, Violation } from '../src/types.js';
|
|
|
|
function createMockEvent(overrides: Partial<RunEvent> = {}): RunEvent {
|
|
return {
|
|
eventId: `evt-${Math.random().toString(36).slice(2)}`,
|
|
taskId: `task-${Math.random().toString(36).slice(2)}`,
|
|
guidanceHash: 'abc123',
|
|
retrievedRuleIds: ['R001', 'R002'],
|
|
toolsUsed: ['Read', 'Edit'],
|
|
filesTouched: ['src/main.ts'],
|
|
diffSummary: { linesAdded: 50, linesRemoved: 10, filesChanged: 1 },
|
|
testResults: { ran: true, passed: 10, failed: 0, skipped: 0 },
|
|
violations: [],
|
|
outcomeAccepted: true,
|
|
reworkLines: 5,
|
|
intent: 'feature',
|
|
timestamp: Date.now(),
|
|
durationMs: 5000,
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
describe('OptimizerLoop', () => {
|
|
let optimizer: OptimizerLoop;
|
|
let ledger: RunLedger;
|
|
let bundle: PolicyBundle;
|
|
|
|
beforeEach(() => {
|
|
optimizer = new OptimizerLoop({
|
|
minEventsForOptimization: 5,
|
|
topViolationsPerCycle: 2,
|
|
});
|
|
|
|
ledger = new RunLedger();
|
|
|
|
const compiler = new GuidanceCompiler();
|
|
bundle = compiler.compile(`
|
|
# Safety Invariants
|
|
- [R001] Never commit secrets (critical) @security
|
|
- [R002] Always validate input (critical) @security
|
|
|
|
# Architecture
|
|
- [R010] Keep files under 500 lines @architecture
|
|
- [R011] Use typed interfaces @architecture
|
|
`);
|
|
});
|
|
|
|
describe('runCycle', () => {
|
|
it('should return empty results with no violations', async () => {
|
|
// Add clean events
|
|
for (let i = 0; i < 10; i++) {
|
|
ledger.logEvent(createMockEvent());
|
|
}
|
|
|
|
const result = await optimizer.runCycle(ledger, bundle);
|
|
expect(result.rankings).toEqual([]);
|
|
expect(result.changes).toEqual([]);
|
|
expect(result.promoted).toEqual([]);
|
|
});
|
|
|
|
it('should propose changes for top violations', async () => {
|
|
// Add events with violations
|
|
const violation: Violation = {
|
|
ruleId: 'R010',
|
|
description: 'File exceeds 500 lines',
|
|
severity: 'medium',
|
|
autoCorrected: false,
|
|
};
|
|
|
|
for (let i = 0; i < 10; i++) {
|
|
ledger.logEvent(createMockEvent({
|
|
violations: i < 6 ? [violation] : [],
|
|
reworkLines: i < 6 ? 20 : 2,
|
|
}));
|
|
}
|
|
|
|
const result = await optimizer.runCycle(ledger, bundle);
|
|
|
|
expect(result.rankings.length).toBeGreaterThan(0);
|
|
expect(result.rankings[0].ruleId).toBe('R010');
|
|
expect(result.changes.length).toBeGreaterThan(0);
|
|
});
|
|
|
|
it('should create ADRs for each evaluated change', async () => {
|
|
const violation: Violation = {
|
|
ruleId: 'R010',
|
|
description: 'File size violation',
|
|
severity: 'medium',
|
|
autoCorrected: false,
|
|
};
|
|
|
|
for (let i = 0; i < 10; i++) {
|
|
ledger.logEvent(createMockEvent({
|
|
violations: [violation],
|
|
reworkLines: 30,
|
|
}));
|
|
}
|
|
|
|
const result = await optimizer.runCycle(ledger, bundle);
|
|
|
|
expect(result.adrs.length).toBeGreaterThan(0);
|
|
expect(result.adrs[0].number).toBe(1);
|
|
expect(result.adrs[0].title).toBeDefined();
|
|
expect(result.adrs[0].rationale).toBeDefined();
|
|
});
|
|
});
|
|
|
|
describe('proposeChanges', () => {
|
|
it('should propose modifications for existing rules', () => {
|
|
const rankings = [
|
|
{ ruleId: 'R010', frequency: 10, cost: 25, score: 250 },
|
|
];
|
|
|
|
const changes = optimizer.proposeChanges(rankings, bundle);
|
|
expect(changes.length).toBe(1);
|
|
expect(changes[0].targetRuleId).toBe('R010');
|
|
expect(changes[0].changeType).toBe('modify');
|
|
});
|
|
|
|
it('should propose new rules for unmatched violations', () => {
|
|
const rankings = [
|
|
{ ruleId: 'NEW-001', frequency: 5, cost: 15, score: 75 },
|
|
];
|
|
|
|
const changes = optimizer.proposeChanges(rankings, bundle);
|
|
expect(changes.length).toBe(1);
|
|
expect(changes[0].changeType).toBe('add');
|
|
});
|
|
});
|
|
|
|
describe('evaluateChange', () => {
|
|
it('should evaluate change against baseline', () => {
|
|
for (let i = 0; i < 10; i++) {
|
|
ledger.logEvent(createMockEvent({ reworkLines: 20 }));
|
|
}
|
|
|
|
const baseline = ledger.computeMetrics();
|
|
const change = {
|
|
changeId: 'change-1',
|
|
targetRuleId: 'R010',
|
|
changeType: 'modify' as const,
|
|
originalText: 'Old rule text',
|
|
proposedText: 'New improved rule text',
|
|
rationale: 'Test change',
|
|
triggeringViolation: { ruleId: 'R010', frequency: 5, cost: 20, score: 100 },
|
|
};
|
|
|
|
const result = optimizer.evaluateChange(change, baseline, ledger);
|
|
expect(result.baseline).toBeDefined();
|
|
expect(result.candidate).toBeDefined();
|
|
expect(typeof result.shouldPromote).toBe('boolean');
|
|
expect(result.reason).toBeDefined();
|
|
});
|
|
});
|
|
|
|
describe('applyPromotions', () => {
|
|
it('should move promoted shards to constitution', () => {
|
|
// Find a shard rule ID
|
|
const shardRuleId = bundle.shards[0]?.rule.id;
|
|
if (!shardRuleId) return;
|
|
|
|
const changes = [{
|
|
changeId: 'c-1',
|
|
targetRuleId: shardRuleId,
|
|
changeType: 'promote' as const,
|
|
proposedText: 'Promoted rule',
|
|
rationale: 'Won twice',
|
|
triggeringViolation: { ruleId: shardRuleId, frequency: 3, cost: 10, score: 30 },
|
|
}];
|
|
|
|
const newBundle = optimizer.applyPromotions(bundle, [shardRuleId], changes);
|
|
|
|
// Constitution should have the promoted rule
|
|
const promotedRule = newBundle.constitution.rules.find(r => r.id === shardRuleId);
|
|
expect(promotedRule).toBeDefined();
|
|
expect(promotedRule!.isConstitution).toBe(true);
|
|
|
|
// Shards should not have the promoted rule
|
|
const shardRule = newBundle.shards.find(s => s.rule.id === shardRuleId);
|
|
expect(shardRule).toBeUndefined();
|
|
});
|
|
});
|
|
|
|
describe('ADR tracking', () => {
|
|
it('should track ADR history', async () => {
|
|
const violation: Violation = {
|
|
ruleId: 'R010',
|
|
description: 'test',
|
|
severity: 'medium',
|
|
autoCorrected: false,
|
|
};
|
|
|
|
for (let i = 0; i < 10; i++) {
|
|
ledger.logEvent(createMockEvent({ violations: [violation], reworkLines: 20 }));
|
|
}
|
|
|
|
await optimizer.runCycle(ledger, bundle);
|
|
const adrs = optimizer.getADRs();
|
|
expect(adrs.length).toBeGreaterThan(0);
|
|
});
|
|
});
|
|
|
|
describe('promotion tracking', () => {
|
|
it('should track win counts for promotion', async () => {
|
|
const violation: Violation = {
|
|
ruleId: 'R010',
|
|
description: 'test',
|
|
severity: 'medium',
|
|
autoCorrected: false,
|
|
};
|
|
|
|
// Run multiple cycles
|
|
for (let cycle = 0; cycle < 3; cycle++) {
|
|
for (let i = 0; i < 10; i++) {
|
|
ledger.logEvent(createMockEvent({ violations: [violation], reworkLines: 20 }));
|
|
}
|
|
await optimizer.runCycle(ledger, bundle);
|
|
}
|
|
|
|
const tracker = optimizer.getPromotionTracker();
|
|
// R010 should have some win counts
|
|
expect(tracker.size).toBeGreaterThan(0);
|
|
});
|
|
});
|
|
});
|