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
203 lines
7.9 KiB
TypeScript
203 lines
7.9 KiB
TypeScript
/**
|
||
* Tests for agenticow MCP tools.
|
||
*
|
||
* Two surfaces under test:
|
||
* 1. The HAPPY PATH — agenticow is installed (real package). The tool round-trips
|
||
* through actual COW branch / checkpoint / rollback / promote semantics on
|
||
* a temp .rvf file.
|
||
* 2. The DEGRADED PATH — agenticow is NOT installed (we vi.mock() it as
|
||
* ERR_MODULE_NOT_FOUND). Every tool must return `{degraded: true}` with no
|
||
* throw, matching the metaharness-tools / testgen-tools contract.
|
||
*
|
||
* Why both: agenticow is in `optionalDependencies`. CI runs with deps installed
|
||
* (happy path) but production users may not have it — the degraded path is
|
||
* the load-bearing architectural rule (zero hard runtime dep).
|
||
*/
|
||
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
|
||
import { mkdtempSync, rmSync, existsSync, statSync, readdirSync } from 'node:fs';
|
||
import { join } from 'node:path';
|
||
import { tmpdir } from 'node:os';
|
||
|
||
import { agenticowTools } from '../src/mcp-tools/agenticow-tools.js';
|
||
|
||
function findTool(name: string) {
|
||
const t = agenticowTools.find(t => t.name === name);
|
||
if (!t) throw new Error(`tool not found: ${name}`);
|
||
return t;
|
||
}
|
||
|
||
function dirBytes(p: string): number {
|
||
if (!existsSync(p)) return 0;
|
||
const st = statSync(p);
|
||
if (st.isFile()) return st.size;
|
||
let total = 0;
|
||
for (const e of readdirSync(p)) total += dirBytes(join(p, e));
|
||
return total;
|
||
}
|
||
|
||
// Detect agenticow availability at module scope (top-level await is allowed
|
||
// in vitest ESM modules). We need this before the `it.skipIf(...)` calls,
|
||
// which evaluate at definition time.
|
||
let havePkg = false;
|
||
try { await import('agenticow'); havePkg = true; } catch { havePkg = false; }
|
||
|
||
describe('agenticow MCP tools — happy path (real package)', () => {
|
||
let workdir: string;
|
||
let basePath: string;
|
||
|
||
beforeAll(() => {
|
||
workdir = mkdtempSync(join(tmpdir(), 'agenticow-tools-'));
|
||
basePath = join(workdir, 'base.rvf');
|
||
});
|
||
|
||
afterAll(() => {
|
||
try { rmSync(workdir, { recursive: true, force: true }); } catch { /* ignore */ }
|
||
});
|
||
|
||
it('exposes 9 tools (lifecycle + read/write verbs)', () => {
|
||
const names = agenticowTools.map(t => t.name).sort();
|
||
expect(names).toEqual([
|
||
'agenticow_branch',
|
||
'agenticow_checkpoint',
|
||
'agenticow_diff',
|
||
'agenticow_ingest',
|
||
'agenticow_lineage',
|
||
'agenticow_promote',
|
||
'agenticow_query',
|
||
'agenticow_rollback',
|
||
'agenticow_status',
|
||
]);
|
||
});
|
||
|
||
it.skipIf(!havePkg)('ingest → query round-trips vectors + text across a COW branch (issue: text persistence)', async () => {
|
||
const ingest = findTool('agenticow_ingest');
|
||
const query = findTool('agenticow_query');
|
||
const branch = findTool('agenticow_branch');
|
||
const v = (s: number) => Array.from({ length: 8 }, (_, i) => Math.sin(s + i));
|
||
const base = join(workdir, 'rw-base.rvf');
|
||
const br = join(workdir, 'rw-branch.rvf');
|
||
|
||
const ing = await ingest.handler({ path: base, records: [
|
||
{ id: 1, vector: v(1), text: 'alpha' }, { id: 2, vector: v(2), text: 'beta' },
|
||
], dimension: 8 }) as any;
|
||
expect(ing.success).toBe(true);
|
||
expect(ing.ingested.accepted).toBe(2);
|
||
|
||
// branch with the native ANN fast path, then ingest a branch-only vector
|
||
const b = await branch.handler({ basePath: base, branchPath: br, label: 'rw', nativeAnn: true }) as any;
|
||
expect(b.nativeAnn).toBe(true);
|
||
await ingest.handler({ path: br, records: [{ id: 3, vector: v(3), text: 'gamma' }] });
|
||
|
||
// query the branch: sees base ∪ branch, and text survives (0.2.4 fix)
|
||
const q = await query.handler({ path: br, vector: v(1), k: 3 }) as any;
|
||
expect(q.success).toBe(true);
|
||
const hit = q.hits.find((h: any) => h.id === 1);
|
||
expect(hit).toBeDefined();
|
||
expect(hit.text).toBe('alpha');
|
||
});
|
||
|
||
it.skipIf(!havePkg)('diff / lineage / status report branch state', async () => {
|
||
const ingest = findTool('agenticow_ingest');
|
||
const diff = findTool('agenticow_diff');
|
||
const lineage = findTool('agenticow_lineage');
|
||
const status = findTool('agenticow_status');
|
||
const v = (s: number) => Array.from({ length: 8 }, (_, i) => Math.cos(s + i));
|
||
const p = join(workdir, 'introspect.rvf');
|
||
await ingest.handler({ path: p, records: [{ id: 10, vector: v(1), text: 'x' }], dimension: 8 });
|
||
|
||
const d = await diff.handler({ path: p }) as any;
|
||
expect(d.success).toBe(true);
|
||
expect(Array.isArray(d.diff.added)).toBe(true);
|
||
|
||
const lin = await lineage.handler({ path: p }) as any;
|
||
expect(lin.success).toBe(true);
|
||
expect(lin.lineage.some((n: any) => n.role === 'working' || n.role === 'base')).toBe(true);
|
||
|
||
const st = await status.handler({ path: p }) as any;
|
||
expect(st.success).toBe(true);
|
||
expect(st.status.dimension).toBe(8);
|
||
});
|
||
|
||
it('new read/write verbs degrade + validate like the lifecycle verbs', async () => {
|
||
// path-traversal rejection is shared via resolveMemoryPath
|
||
const query = findTool('agenticow_query');
|
||
await expect(query.handler({ path: '../../etc/passwd', vector: [1, 2] })).rejects.toThrow(/disallowed/);
|
||
const ingest = findTool('agenticow_ingest');
|
||
await expect(ingest.handler({ path: 'ok.rvf', records: [] })).rejects.toThrow(/non-empty/);
|
||
});
|
||
|
||
it('every tool has a JSON-schema input + handler', () => {
|
||
for (const t of agenticowTools) {
|
||
expect(t.inputSchema.type).toBe('object');
|
||
expect(t.inputSchema.properties).toBeDefined();
|
||
expect(typeof t.handler).toBe('function');
|
||
}
|
||
});
|
||
|
||
it.skipIf(!havePkg)('agenticow_branch creates a tiny COW branch on a real base', async () => {
|
||
const branch = findTool('agenticow_branch');
|
||
// Use a small dim for test speed
|
||
const branchPath = join(workdir, 'b1.rvf');
|
||
const result: any = await branch.handler({
|
||
basePath, branchPath,
|
||
label: 'test-branch',
|
||
dimension: 32,
|
||
});
|
||
expect(result.success).toBe(true);
|
||
expect(result.degraded).toBeUndefined();
|
||
expect(result.label).toBe('test-branch');
|
||
expect(existsSync(branchPath)).toBe(true);
|
||
// The size win is the load-bearing claim — assert it's tiny
|
||
expect(dirBytes(branchPath)).toBeLessThan(2048);
|
||
});
|
||
|
||
it.skipIf(!havePkg)('agenticow_checkpoint persists state across reopen, agenticow_rollback restores it', async () => {
|
||
const cp = findTool('agenticow_checkpoint');
|
||
const rb = findTool('agenticow_rollback');
|
||
|
||
// checkpoint must persist via the .agenticow.json manifest. The base file
|
||
// was created earlier by the branch test (which writes the manifest).
|
||
const cpResult: any = await cp.handler({ path: basePath, label: 'cp-1' });
|
||
expect(cpResult.success).toBe(true);
|
||
expect(cpResult.label).toBe('cp-1');
|
||
// Manifest file should now exist next to the .rvf
|
||
expect(existsSync(`${basePath}.agenticow.json`)).toBe(true);
|
||
|
||
// Rollback now finds the checkpoint via the persisted manifest
|
||
const rbResult: any = await rb.handler({ path: basePath });
|
||
expect(rbResult.success).toBe(true);
|
||
expect(rbResult.rolledBack).toBe(true);
|
||
});
|
||
|
||
it('agenticow_branch rejects path traversal in basePath', async () => {
|
||
const branch = findTool('agenticow_branch');
|
||
await expect(branch.handler({
|
||
basePath: '../../../../etc/passwd',
|
||
branchPath: join(workdir, 'evil.rvf'),
|
||
label: 'evil',
|
||
dimension: 32,
|
||
})).rejects.toThrow(/disallowed characters/);
|
||
});
|
||
|
||
it('agenticow_branch rejects a malformed label', async () => {
|
||
const branch = findTool('agenticow_branch');
|
||
await expect(branch.handler({
|
||
basePath,
|
||
branchPath: join(workdir, 'b2.rvf'),
|
||
label: 'evil; rm -rf /',
|
||
dimension: 32,
|
||
})).rejects.toThrow(/may only contain/);
|
||
});
|
||
|
||
it('agenticow_branch requires dimension when creating a new memory file', async () => {
|
||
const branch = findTool('agenticow_branch');
|
||
const freshBase = join(workdir, 'nonexistent.rvf');
|
||
await expect(branch.handler({
|
||
basePath: freshBase,
|
||
branchPath: join(workdir, 'b3.rvf'),
|
||
label: 'fresh',
|
||
// no dimension
|
||
})).rejects.toThrow(/dimension is required/);
|
||
});
|
||
});
|