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
242 lines
7.9 KiB
TypeScript
242 lines
7.9 KiB
TypeScript
/**
|
|
* Validation script for hyperbolic-reasoning plugin
|
|
* Tests all 5 MCP tools with valid data
|
|
*/
|
|
|
|
import { hyperbolicReasoningTools, getTool, getToolNames } from '../dist/mcp-tools.js';
|
|
import type { MCPToolResult } from '../dist/types.js';
|
|
|
|
// Helper to parse MCP result
|
|
function parseResult(result: MCPToolResult): { success: boolean; data: any; error?: string } {
|
|
if (result.isError) {
|
|
const parsed = JSON.parse(result.content[0]?.text || '{}');
|
|
return { success: false, data: null, error: parsed.message || 'Unknown error' };
|
|
}
|
|
const data = JSON.parse(result.content[0]?.text || '{}');
|
|
return { success: true, data };
|
|
}
|
|
|
|
async function validate() {
|
|
console.log('=== Hyperbolic Reasoning Plugin Validation ===\n');
|
|
|
|
const toolNames = getToolNames();
|
|
console.log(`Found ${toolNames.length} tools: ${toolNames.join(', ')}\n`);
|
|
|
|
let passed = 0;
|
|
let failed = 0;
|
|
const results: { tool: string; status: string; error?: string }[] = [];
|
|
|
|
let embeddingIndexId: string | null = null;
|
|
|
|
// Test 1: hyperbolic_embed_hierarchy
|
|
try {
|
|
console.log('Testing hyperbolic_embed_hierarchy...');
|
|
const tool = getTool('hyperbolic_embed_hierarchy');
|
|
if (!tool) throw new Error('Tool not found');
|
|
|
|
const rawResult = await tool.handler({
|
|
hierarchy: {
|
|
nodes: [
|
|
{ id: 'entity', parent: null },
|
|
{ id: 'animal', parent: 'entity' },
|
|
{ id: 'mammal', parent: 'animal' },
|
|
{ id: 'dog', parent: 'mammal' },
|
|
{ id: 'cat', parent: 'mammal' },
|
|
{ id: 'bird', parent: 'animal' },
|
|
{ id: 'plant', parent: 'entity' },
|
|
{ id: 'tree', parent: 'plant' },
|
|
{ id: 'flower', parent: 'plant' }
|
|
],
|
|
edges: []
|
|
},
|
|
model: 'poincare_ball',
|
|
parameters: {
|
|
dimensions: 32,
|
|
curvature: -1.0,
|
|
learnCurvature: false,
|
|
epochs: 50,
|
|
learningRate: 0.01
|
|
}
|
|
});
|
|
|
|
const { success, data, error } = parseResult(rawResult);
|
|
if (!success) throw new Error(error);
|
|
if (!data.indexId) throw new Error('Missing indexId');
|
|
if (typeof data.curvature !== 'number') throw new Error('Invalid response format');
|
|
|
|
embeddingIndexId = data.indexId;
|
|
console.log(` OK: Index: ${data.indexId}, curvature: ${data.curvature.toFixed(2)}, nodes: ${data.totalNodes}`);
|
|
passed++;
|
|
results.push({ tool: 'hyperbolic_embed_hierarchy', status: 'PASS' });
|
|
} catch (e: any) {
|
|
console.log(` FAIL: ${e.message}`);
|
|
failed++;
|
|
results.push({ tool: 'hyperbolic_embed_hierarchy', status: 'FAIL', error: e.message });
|
|
}
|
|
|
|
// Test 2: hyperbolic_taxonomic_reason (requires embedding from test 1)
|
|
try {
|
|
console.log('Testing hyperbolic_taxonomic_reason...');
|
|
const tool = getTool('hyperbolic_taxonomic_reason');
|
|
if (!tool) throw new Error('Tool not found');
|
|
|
|
if (!embeddingIndexId) {
|
|
throw new Error('No embedding index available (test 1 may have failed)');
|
|
}
|
|
|
|
const rawResult = await tool.handler({
|
|
query: {
|
|
type: 'is_a',
|
|
subject: 'dog',
|
|
object: 'animal'
|
|
},
|
|
taxonomy: embeddingIndexId,
|
|
inference: {
|
|
transitive: true,
|
|
fuzzy: false,
|
|
confidence: 0.8
|
|
}
|
|
});
|
|
|
|
const { success, data, error } = parseResult(rawResult);
|
|
if (!success) throw new Error(error);
|
|
if (typeof data.confidence !== 'number') throw new Error('Invalid response format');
|
|
|
|
console.log(` OK: Result: ${data.result}, confidence: ${data.confidence.toFixed(2)}`);
|
|
passed++;
|
|
results.push({ tool: 'hyperbolic_taxonomic_reason', status: 'PASS' });
|
|
} catch (e: any) {
|
|
console.log(` FAIL: ${e.message}`);
|
|
failed++;
|
|
results.push({ tool: 'hyperbolic_taxonomic_reason', status: 'FAIL', error: e.message });
|
|
}
|
|
|
|
// Test 3: hyperbolic_semantic_search (requires embedding from test 1)
|
|
try {
|
|
console.log('Testing hyperbolic_semantic_search...');
|
|
const tool = getTool('hyperbolic_semantic_search');
|
|
if (!tool) throw new Error('Tool not found');
|
|
|
|
if (!embeddingIndexId) {
|
|
throw new Error('No embedding index available (test 1 may have failed)');
|
|
}
|
|
|
|
const rawResult = await tool.handler({
|
|
query: 'mammal',
|
|
index: embeddingIndexId,
|
|
searchMode: 'nearest',
|
|
constraints: {
|
|
maxDepth: 10
|
|
},
|
|
topK: 5
|
|
});
|
|
|
|
const { success, data, error } = parseResult(rawResult);
|
|
if (!success) throw new Error(error);
|
|
if (!Array.isArray(data.items)) throw new Error('Invalid response format');
|
|
|
|
console.log(` OK: Found ${data.items.length} items in ${data.searchTimeMs?.toFixed(2) || 'N/A'}ms`);
|
|
passed++;
|
|
results.push({ tool: 'hyperbolic_semantic_search', status: 'PASS' });
|
|
} catch (e: any) {
|
|
console.log(` FAIL: ${e.message}`);
|
|
failed++;
|
|
results.push({ tool: 'hyperbolic_semantic_search', status: 'FAIL', error: e.message });
|
|
}
|
|
|
|
// Test 4: hyperbolic_hierarchy_compare
|
|
try {
|
|
console.log('Testing hyperbolic_hierarchy_compare...');
|
|
const tool = getTool('hyperbolic_hierarchy_compare');
|
|
if (!tool) throw new Error('Tool not found');
|
|
|
|
const rawResult = await tool.handler({
|
|
source: {
|
|
nodes: [
|
|
{ id: 'root', parent: null },
|
|
{ id: 'A', parent: 'root' },
|
|
{ id: 'B', parent: 'root' },
|
|
{ id: 'A1', parent: 'A' }
|
|
],
|
|
edges: []
|
|
},
|
|
target: {
|
|
nodes: [
|
|
{ id: 'root', parent: null },
|
|
{ id: 'A', parent: 'root' },
|
|
{ id: 'C', parent: 'root' },
|
|
{ id: 'A1', parent: 'A' }
|
|
],
|
|
edges: []
|
|
},
|
|
alignment: 'wasserstein',
|
|
metrics: ['structural_similarity', 'semantic_similarity']
|
|
});
|
|
|
|
const { success, data, error } = parseResult(rawResult);
|
|
if (!success) throw new Error(error);
|
|
if (typeof data.similarity !== 'number') throw new Error('Invalid response format');
|
|
if (!Array.isArray(data.alignments)) throw new Error('Missing alignments');
|
|
|
|
console.log(` OK: Similarity: ${data.similarity.toFixed(3)}, alignments: ${data.alignments.length}`);
|
|
passed++;
|
|
results.push({ tool: 'hyperbolic_hierarchy_compare', status: 'PASS' });
|
|
} catch (e: any) {
|
|
console.log(` FAIL: ${e.message}`);
|
|
failed++;
|
|
results.push({ tool: 'hyperbolic_hierarchy_compare', status: 'FAIL', error: e.message });
|
|
}
|
|
|
|
// Test 5: hyperbolic_entailment_graph
|
|
try {
|
|
console.log('Testing hyperbolic_entailment_graph...');
|
|
const tool = getTool('hyperbolic_entailment_graph');
|
|
if (!tool) throw new Error('Tool not found');
|
|
|
|
const rawResult = await tool.handler({
|
|
action: 'build',
|
|
concepts: [
|
|
{ id: 'c1', text: 'All dogs are mammals', type: 'universal' },
|
|
{ id: 'c2', text: 'All mammals are animals', type: 'universal' },
|
|
{ id: 'c3', text: 'Rex is a dog', type: 'instance' },
|
|
{ id: 'c4', text: 'Rex is an animal', type: 'instance' }
|
|
],
|
|
entailmentThreshold: 0.7,
|
|
transitiveClosure: true,
|
|
pruneStrategy: 'none'
|
|
});
|
|
|
|
const { success, data, error } = parseResult(rawResult);
|
|
if (!success) throw new Error(error);
|
|
if (!data.graphId) throw new Error('Invalid response format');
|
|
|
|
console.log(` OK: Graph: ${data.graphId}, nodes: ${data.stats?.nodeCount || 'N/A'}`);
|
|
passed++;
|
|
results.push({ tool: 'hyperbolic_entailment_graph', status: 'PASS' });
|
|
} catch (e: any) {
|
|
console.log(` FAIL: ${e.message}`);
|
|
failed++;
|
|
results.push({ tool: 'hyperbolic_entailment_graph', status: 'FAIL', error: e.message });
|
|
}
|
|
|
|
// Summary
|
|
console.log('\n=== Summary ===');
|
|
console.log(`Passed: ${passed}/${toolNames.length}`);
|
|
console.log(`Failed: ${failed}/${toolNames.length}`);
|
|
|
|
if (failed > 0) {
|
|
console.log('\nFailed tools:');
|
|
results.filter(r => r.status === 'FAIL').forEach(r => {
|
|
console.log(` - ${r.tool}: ${r.error}`);
|
|
});
|
|
process.exit(1);
|
|
}
|
|
|
|
console.log('\nAll tools validated successfully!');
|
|
}
|
|
|
|
validate().catch(e => {
|
|
console.error('Validation error:', e);
|
|
process.exit(1);
|
|
});
|