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
177 lines
6.8 KiB
JavaScript
Executable File
177 lines
6.8 KiB
JavaScript
Executable File
#!/usr/bin/env node
|
||
// test-health-integration — runtime integration test for cost-health.
|
||
//
|
||
// The iter-75 bug (BUDGET_QUIET=1 silently swallowing HARD_STOP) was a
|
||
// classic test-pyramid gap: each subcheck's smoke contract passed
|
||
// (anomaly.mjs / burn.mjs / budget.mjs each correctly exit 1 on alert),
|
||
// but the COMPOSITE behavior was wrong — cost-health spawned budget.mjs
|
||
// with BUDGET_QUIET=1 and budget.mjs returned exit 0 in that mode.
|
||
//
|
||
// Structural source-grep smoke can detect the pattern in one file, but
|
||
// can't validate the cross-script contract. This runtime test exercises
|
||
// the composite end-to-end with synthetic fixtures and asserts each
|
||
// subcheck's signal correctly reaches cost-health's exit code.
|
||
//
|
||
// USAGE
|
||
// node scripts/test-health-integration.mjs # default
|
||
// TEST_HEALTH_KEEP_FIXTURE=1 node scripts/test-health-integration.mjs
|
||
// # leave .swarm intact for debugging
|
||
//
|
||
// EXIT CODES
|
||
// 0 all assertions passed
|
||
// 1 at least one assertion failed
|
||
// 2 fixture setup error (likely CLI unavailable in CI)
|
||
|
||
import { spawn, spawnSync } from 'node:child_process';
|
||
import { mkdtempSync, rmSync, mkdirSync } from 'node:fs';
|
||
import { join, dirname } from 'node:path';
|
||
import { fileURLToPath } from 'node:url';
|
||
import { tmpdir } from 'node:os';
|
||
|
||
const SCRIPTS_DIR = dirname(fileURLToPath(import.meta.url));
|
||
const HEALTH = join(SCRIPTS_DIR, 'health.mjs');
|
||
const BUDGET = join(SCRIPTS_DIR, 'budget.mjs');
|
||
const NS = 'cost-tracking';
|
||
|
||
let passed = 0, failed = 0;
|
||
const failures = [];
|
||
|
||
function assert(cond, label) {
|
||
if (cond) {
|
||
console.log(` ✓ ${label}`);
|
||
passed++;
|
||
} else {
|
||
console.log(` ✗ ${label}`);
|
||
failures.push(label);
|
||
failed++;
|
||
}
|
||
}
|
||
|
||
function memStore(cwd, key, valueObj) {
|
||
const r = spawnSync('npx', [
|
||
'@claude-flow/cli@latest', 'memory', 'store',
|
||
'--namespace', NS, '--key', key,
|
||
'--value', JSON.stringify(valueObj),
|
||
], { cwd, stdio: ['ignore', 'pipe', 'pipe'], encoding: 'utf-8' });
|
||
return r.status === 0;
|
||
}
|
||
|
||
function runHealth(cwd) {
|
||
return new Promise((resolve) => {
|
||
const p = spawn('node', [HEALTH, '--format', 'json'], { cwd, stdio: ['ignore', 'pipe', 'pipe'] });
|
||
let stdout = '';
|
||
p.stdout.on('data', (d) => { stdout += d.toString(); });
|
||
p.on('close', (code) => {
|
||
let json = null;
|
||
const m = /\{[\s\S]*\}/.exec(stdout);
|
||
if (m) { try { json = JSON.parse(m[0]); } catch {} }
|
||
resolve({ exitCode: code, json });
|
||
});
|
||
});
|
||
}
|
||
|
||
function runBudget(cwd, subcommand, ...extra) {
|
||
const r = spawnSync('node', [BUDGET, subcommand, ...extra], {
|
||
cwd, stdio: ['ignore', 'pipe', 'pipe'], encoding: 'utf-8',
|
||
});
|
||
return r.status;
|
||
}
|
||
|
||
async function main() {
|
||
const fixture = mkdtempSync(join(tmpdir(), 'cost-health-test-'));
|
||
mkdirSync(join(fixture, '.swarm'), { recursive: true });
|
||
console.log(`# cost-health integration test (fixture: ${fixture})\n`);
|
||
|
||
// -----------------------------------------------------------------------
|
||
// Case 1: empty namespace → cost-health overall OK, exit 0.
|
||
// Validates each subcheck handles empty input gracefully (the iter-75 fix
|
||
// CI step is exactly this case, but for a clean cwd).
|
||
// -----------------------------------------------------------------------
|
||
console.log('Case 1: empty namespace');
|
||
{
|
||
// Use a fresh subdir so .swarm doesn't share state with later cases.
|
||
const cwd = join(fixture, 'case-1-empty');
|
||
mkdirSync(join(cwd, '.swarm'), { recursive: true });
|
||
const r = await runHealth(cwd);
|
||
if (!r.json) {
|
||
console.error(' → no JSON output; CLI likely unavailable');
|
||
process.exit(2);
|
||
}
|
||
assert(r.exitCode === 0, 'empty input → exit 0');
|
||
assert(r.json.overall.ok === true, 'empty input → overall.ok === true');
|
||
}
|
||
|
||
// -----------------------------------------------------------------------
|
||
// Case 2: budget HARD_STOP → cost-health overall ⚠, exit 1.
|
||
// EXACT REGRESSION TARGET FOR ITER 75. If budget.mjs ever again
|
||
// short-circuits process.exit(1) when BUDGET_QUIET=1 is set, this
|
||
// assertion fails.
|
||
// -----------------------------------------------------------------------
|
||
console.log('Case 2: budget HARD_STOP via BUDGET_QUIET=1');
|
||
{
|
||
const cwd = join(fixture, 'case-2-hardstop');
|
||
mkdirSync(join(cwd, '.swarm'), { recursive: true });
|
||
// 5 sessions × $0.10 = $0.50 spend
|
||
for (let i = 0; i < 5; i++) {
|
||
const ts = new Date(Date.now() - (i + 2) * 86_400_000).toISOString();
|
||
const ok = memStore(cwd, `session-baseline-${i}`, {
|
||
sessionId: `baseline-${i}`, capturedAt: ts,
|
||
total_cost_usd: 0.10, messageCount: 5, byModel: {},
|
||
});
|
||
if (!ok) { console.error(' → fixture write failed'); process.exit(2); }
|
||
}
|
||
// Set $0.20 budget → 250% utilization → HARD_STOP
|
||
if (runBudget(cwd, 'set', '0.20') !== 0) {
|
||
console.error(' → budget set failed');
|
||
process.exit(2);
|
||
}
|
||
const r = await runHealth(cwd);
|
||
if (!r.json) { console.error(' → no JSON output'); process.exit(2); }
|
||
assert(r.exitCode === 1, 'HARD_STOP → exit 1 (iter-75 regression target)');
|
||
assert(r.json.overall.ok === false, 'HARD_STOP → overall.ok === false');
|
||
const budgetCheck = r.json.checks.find((c) => c.name === 'budget');
|
||
assert(budgetCheck && budgetCheck.exitCode === 1,
|
||
'subcheck budget exit code propagated as 1 (was bypassed by BUDGET_QUIET=1 in iter 75)');
|
||
}
|
||
|
||
// -----------------------------------------------------------------------
|
||
// Case 3: subcheck skip flag honored.
|
||
// -----------------------------------------------------------------------
|
||
console.log('Case 3: --skip flag honored');
|
||
{
|
||
const cwd = join(fixture, 'case-3-skip');
|
||
mkdirSync(join(cwd, '.swarm'), { recursive: true });
|
||
const p = spawn('node', [HEALTH, '--format', 'json', '--skip', 'burn,projection'], {
|
||
cwd, stdio: ['ignore', 'pipe', 'pipe'],
|
||
});
|
||
let stdout = '';
|
||
p.stdout.on('data', (d) => { stdout += d.toString(); });
|
||
const exitCode = await new Promise((res) => p.on('close', res));
|
||
const m = /\{[\s\S]*\}/.exec(stdout);
|
||
const json = m ? JSON.parse(m[0]) : null;
|
||
assert(json && json.checks.length === 2,
|
||
`--skip burn,projection → only 2 checks ran (budget+anomaly), got ${json?.checks?.length}`);
|
||
assert(json && json.config.skipped.includes('burn') && json.config.skipped.includes('projection'),
|
||
'config.skipped reflects CLI args');
|
||
}
|
||
|
||
// Cleanup
|
||
if (process.env.TEST_HEALTH_KEEP_FIXTURE !== '1') {
|
||
rmSync(fixture, { recursive: true, force: true });
|
||
} else {
|
||
console.log(`\n(fixture kept at ${fixture})`);
|
||
}
|
||
|
||
console.log(`\n${passed} passed, ${failed} failed`);
|
||
if (failed > 0) {
|
||
console.log('\nFailures:');
|
||
for (const f of failures) console.log(` - ${f}`);
|
||
process.exit(1);
|
||
}
|
||
}
|
||
|
||
main().catch((e) => {
|
||
console.error('test-health-integration crashed:', e.message || e);
|
||
process.exit(2);
|
||
});
|