everything-gemini 2.0.0 → 2.1.0

package/tests/cli.test.js

@@ -90,10 +90,10 @@ it('should benchmark ecosystem components and output valid JSON with --json', ()
   const res = runCli('benchmark --json');
   assert.strictEqual(res.status, 0);
   const data = JSON.parse(res.stdout);
-  assert.strictEqual(data.totalComponents, 80);
-  assert.strictEqual(data.progressiveSkillsCount, 60);
+  assert.strictEqual(data.totalComponents, 84);
+  assert.strictEqual(data.progressiveSkillsCount, 63);
   assert.strictEqual(data.scopedAgentsCount, 13);
-  assert.strictEqual(data.lifecycleHooksCount, 7);
+  assert.strictEqual(data.lifecycleHooksCount, 8);
   assert(data.totalRunbookTokens > 15000, 'Expected >15,000 runbook tokens');
   assert(data.estimatedTokensSavedPerTurn > 8000, 'Expected significant token savings');
 });
@@ -316,7 +316,7 @@ try {
     const dryRes = runCli(`bundle --output "${bundleTarget}" --dry-run`);
     assert.strictEqual(dryRes.status, 0);
     assert.match(dryRes.stdout, /DRY RUN MODE ACTIVATED/);
-    assert.match(dryRes.stdout, /Skills to bundle: 60/);
+    assert.match(dryRes.stdout, /Skills to bundle: 63/);
     assert.strictEqual(fs.existsSync(bundleTarget), false, 'Dry run should not create destination directory');
 
     // JSON Dry-run mode
@@ -324,7 +324,7 @@ try {
     assert.strictEqual(jsonRes.status, 0);
     const dryData = JSON.parse(jsonRes.stdout);
     assert.strictEqual(dryData.dryRun, true);
-    assert.strictEqual(dryData.manifest.components.totalCount, 80);
+    assert.strictEqual(dryData.manifest.components.totalCount, 84);
 
     // Live mode
     const liveRes = runCli(`bundle --output "${bundleTarget}"`);
@@ -446,6 +446,63 @@ try {
     assert.match(resTriton.stdout, /Triton/);
   });
 
+  // Info for v2.1.0 Google Research Harness2 & Google Family skills
+  it('should display info for v2.1.0 Harness2, Google Flow, and Dataproc Spark skills', () => {
+    const resH2 = runCli('info harness2-recursive-optimization');
+    assert.strictEqual(resH2.status, 0);
+    assert.match(resH2.stdout, /Harness² Recursive Optimization/);
+
+    const resFlow = runCli('info google-flow-orchestrator');
+    assert.strictEqual(resFlow.status, 0);
+    assert.match(resFlow.stdout, /Google Flow Orchestrator/);
+
+    const resSpark = runCli('info dataproc-spark-analytics');
+    assert.strictEqual(resSpark.status, 0);
+    assert.match(resSpark.stdout, /Dataproc Spark Analytics/);
+  });
+
+  // Harness2 command and export format verification
+  it('should synthesize Google Research Harness2 workspace in dry-run, live, and JSON export modes', () => {
+    const h2Target = path.join(tempWorkspace, 'harness2-test-ws');
+
+    // Dry-run mode
+    const dryRes = runCli(`harness2 "${h2Target}" --dry-run`);
+    assert.strictEqual(dryRes.status, 0);
+    assert.match(dryRes.stdout, /DRY RUN MODE ACTIVATED/);
+    assert.match(dryRes.stdout, /Previewing Google Research Harness² Surfaces/);
+    assert.strictEqual(fs.existsSync(h2Target), false, 'Dry run should not create destination directory');
+
+    // JSON Dry-run mode
+    const jsonRes = runCli(`harness2 "${h2Target}" --dry-run --json`);
+    assert.strictEqual(jsonRes.status, 0);
+    const dryData = JSON.parse(jsonRes.stdout);
+    assert.strictEqual(dryData.dryRun, true);
+    assert.strictEqual(dryData.manifest.metrics.total_skills, 63);
+    assert.strictEqual(dryData.manifest.metrics.total_subagents, 13);
+    assert.strictEqual(dryData.manifest.metrics.total_hooks, 8);
+
+    // Live mode
+    const liveRes = runCli(`harness2 "${h2Target}"`);
+    assert.strictEqual(liveRes.status, 0);
+    assert.match(liveRes.stdout, /Google Research Harness² Workspace Synthesized Successfully/);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'harness.yaml')), true);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'harness.json')), true);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'prompts', 'GEMINI.md')), true);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'memory', 'memory_spec.json')), true);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'guidance', 'tool_selection_rules.md')), true);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'subagents', 'planner.md')), true);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'skills', 'harness2-recursive-optimization', 'SKILL.md')), true);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'scripts', 'harness_probe.sh')), true);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'scripts', 'harness_snapshot.sh')), true);
+    assert.strictEqual(fs.existsSync(path.join(h2Target, 'scripts', 'harness_rollback.sh')), true);
+
+    // Export with --format harness2
+    const h2ExportTarget = path.join(tempWorkspace, 'harness2-export-ws');
+    const exportRes = runCli(`export --format harness2 --output "${h2ExportTarget}"`);
+    assert.strictEqual(exportRes.status, 0);
+    assert.strictEqual(fs.existsSync(path.join(h2ExportTarget, 'harness.yaml')), true);
+  });
+
   // Graph command verification
   it('should render interaction graph in terminal, mermaid, and JSON formats', () => {
     const resTerm = runCli('graph');
@@ -467,14 +524,63 @@ try {
   });
 
   // Benchmark Components Verification
-  it('should report 80 components, 60 skills, and 13 subagents in benchmark --json', () => {
+  it('should report 84 components, 63 skills, and 13 subagents in benchmark --json', () => {
     const res = runCli('benchmark --json');
     assert.strictEqual(res.status, 0);
     const data = JSON.parse(res.stdout);
-    assert.strictEqual(data.totalComponents, 80, 'Total components should be 80');
-    assert.strictEqual(data.progressiveSkillsCount, 60, 'Progressive skills should be 60');
+    assert.strictEqual(data.totalComponents, 84, 'Total components should be 84');
+    assert.strictEqual(data.progressiveSkillsCount, 63, 'Progressive skills should be 63');
     assert.strictEqual(data.scopedAgentsCount, 13, 'Scoped agents should be 13');
-    assert.strictEqual(data.lifecycleHooksCount, 7, 'Lifecycle hooks should be 7');
+    assert.strictEqual(data.lifecycleHooksCount, 8, 'Lifecycle hooks should be 8');
+  });
+
+  // Harness² Run & Ingest-Trace tests
+  it('should support harness2 run with local benchmark, hard spend limits, and dry-run/json modes', () => {
+    const testTasksDir = path.join(tempWorkspace, 'harness2-tasks');
+    // Dry-run mode
+    const dryRes = runCli(`harness2 run --dir "${testTasksDir}" --bench local --max-usd 15 --dry-run`);
+    assert.strictEqual(dryRes.status, 0);
+    assert.match(dryRes.stdout, /DRY RUN MODE ACTIVATED/);
+    assert.match(dryRes.stdout, /Spend Ceiling: \$15\.00 USD/);
+
+    // JSON export mode
+    const jsonRes = runCli(`harness2 run --dir "${testTasksDir}" --bench local --max-usd 25 --json`);
+    assert.strictEqual(jsonRes.status, 0);
+    const runData = JSON.parse(jsonRes.stdout);
+    assert.strictEqual(runData.engine, 'everything-gemini-harness2-runner');
+    assert.strictEqual(runData.benchmark, 'local');
+    assert.strictEqual(runData.spendGuardrail.maxSpendUsd, 25);
+    assert.strictEqual(runData.result.status, 'PASSED');
+  });
+
+  it('should support harness2 ingest-trace to generate automated regression probes', () => {
+    const sampleTracePath = path.join(tempWorkspace, 'production-failure.json');
+    fs.writeFileSync(sampleTracePath, JSON.stringify({
+      id: 'trace-spark-oom',
+      error: 'OutOfMemoryError: Container killed due to 16GB memory ceiling',
+      tool: 'dataproc-spark-analytics',
+      timestamp: '2026-10-19T18:00:00Z',
+      stack: 'Fatal: JVM worker heap exhausted at SparkExecutor.scala:42'
+    }, null, 2), 'utf8');
+
+    const traceOutDir = path.join(tempWorkspace, 'regression-tasks');
+    const ingestRes = runCli(`harness2 ingest-trace "${sampleTracePath}" --dir "${traceOutDir}"`);
+    assert.strictEqual(ingestRes.status, 0);
+    assert.match(ingestRes.stdout, /Production Trace Ingested into Harness² Regression Test/);
+
+    const generatedTask = path.join(traceOutDir, 'regression-trace-spark-oom.json');
+    assert.strictEqual(fs.existsSync(generatedTask), true);
+    const taskContent = JSON.parse(fs.readFileSync(generatedTask, 'utf8'));
+    assert.strictEqual(taskContent.id, 'regression-trace-spark-oom');
+    assert.strictEqual(taskContent.sourceTrace, 'production-failure.json');
+    assert.match(taskContent.errorCategory, /OutOfMemoryError/);
+  });
+
+  it('should display info for budget-guard lifecycle hook', () => {
+    const res = runCli('info budget-guard');
+    assert.strictEqual(res.status, 0);
+    assert.match(res.stdout, /budget-guard/);
+    assert.match(res.stdout, /PreToolUse/);
   });
 
 } finally {