@claude-flow/cli 3.25.4 → 3.25.6

package/plugins/ruflo-metaharness/.claude-flow/metrics/security-audit.json

@@ -0,0 +1,191 @@
+{
+  "timestamp": "2026-07-09T14:15:20.255Z",
+  "mode": "headless",
+  "workerType": "audit",
+  "model": "haiku",
+  "durationMs": 151388,
+  "executionId": "audit_1783606368867_ahysui",
+  "success": true,
+  "findings": {
+    "reportMetadata": {
+      "timestamp": "2026-07-09",
+      "target": "ruflo-metaharness plugin",
+      "scope": "scripts/, commands/, agents/, skills/ directories"
+    },
+    "summary": {
+      "overallRiskScore": 32,
+      "riskLevel": "Low-to-Moderate",
+      "totalVulnerabilities": 11,
+      "severity": {
+        "critical": 0,
+        "high": 1,
+        "medium": 5,
+        "low": 5
+      },
+      "productionReadiness": "Acceptable with recommended fixes",
+      "estimatedRemediationTime": "14-18 hours"
+    },
+    "vulnerabilities": [
+      {
+        "severity": "high",
+        "file": "scripts/audit-trend.mjs",
+        "line": 75,
+        "description": "Path traversal vulnerability: unvalidated file paths from --baseline and --current flags are directly used with readFileSync() without directory constraints. An attacker could read arbitrary files (e.g., --baseline /etc/passwd).",
+        "category": "Path Traversal",
+        "impact": "Information disclosure - exposure of sensitive files outside intended directories",
+        "fixComplexity": "low",
+        "fix": "Normalize and validate paths using path.resolve() to ensure they stay within designated directory"
+      },
+      {
+        "severity": "medium",
+        "file": "scripts/drift-from-history.mjs",
+        "line": 172,
+        "description": "Path traversal in --baseline-file parameter: arbitrary file paths accepted without validation.",
+        "category": "Path Traversal",
+        "impact": "Information disclosure - access to sensitive files outside intended scope",
+        "fixComplexity": "low",
+        "fix": "Implement path validation helper restricting to current directory"
+      },
+      {
+        "severity": "medium",
+        "file": "scripts/evolve.mjs",
+        "line": 83,
+        "description": "Missing numeric validation: parseInt() result not checked for NaN; invalid --generations could cause process hangs",
+        "category": "Input Validation",
+        "impact": "DoS via invalid numeric input causing process hangs or undefined behavior",
+        "fixComplexity": "low",
+        "fix": "Add isNaN() check and bounds validation (1-50)"
+      },
+      {
+        "severity": "medium",
+        "file": "scripts/test-with-openrouter.mjs",
+        "line": 64,
+        "description": "Command injection potential: execSync() uses template literal string interpolation without proper escaping. Although currently called with hardcoded 'OPENROUTER_API_KEY', the pattern is vulnerable if reused.",
+        "category": "Command Injection",
+        "impact": "Command injection risk if pattern is copied with untrusted input",
+        "fixComplexity": "low",
+        "fix": "Replace with spawnSync() array form to avoid shell interpretation"
+      },
+      {
+        "severity": "medium",
+        "file": "scripts/redblue.mjs",
+        "line": 84,
+        "description": "Incomplete flag validation: unknown flags are forwarded without validation (passthrough mechanism). Could allow malicious flag injection from untrusted contexts",
+        "category": "Input Validation",
+        "impact": "Potential flag injection leading to unexpected behavior or exposure of internal functionality",
+        "fixComplexity": "medium",
+        "fix": "Implement allow-list of safe flags before forwarding"
+      },
+      {
+        "severity": "medium",
+        "file": "scripts/redblue.mjs",
+        "line": 112,
+        "description": "Missing timeout bounds validation: parsed timeout values not validated for positive/reasonable bounds. Negative, zero, or extremely large values could cause DoS",
+        "category": "Input Validation",
+        "impact": "DoS via negative or zero timeouts causing process hangs",
+        "fixComplexity": "low",
+        "fix": "Add range checking: if (timeout < 100 || timeout > 3600000) throw Error()"
+      },
+      {
+        "severity": "low",
+        "file": "scripts/audit-trend.mjs",
+        "line": 78,
+        "description": "Information disclosure: error messages include full absolute paths in user-facing output",
+        "category": "Information Disclosure",
+        "impact": "Minor filesystem structure exposure in error messages",
+        "fixComplexity": "low",
+        "fix": "Use relative paths or just filename in error messages"
+      },
+      {
+        "severity": "low",
+        "file": "scripts/redblue.mjs",
+        "line": 202,
+        "description": "Silent error swallowing: file cleanup errors are silently ignored with empty catch blocks",
+        "category": "Error Handling",
+        "impact": "Silent errors making troubleshooting difficult; potential resource leaks",
+        "fixComplexity": "low",
+        "fix": "Add debug logging for ignored errors"
+      },
+      {
+        "severity": "low",
+        "file": "scripts/learn.mjs",
+        "line": 104,
+        "description": "Unvalidated JSON parsing from subprocess: greedy regex extraction ({[\\s\\S]*?}) with no size limits. Large payloads could cause memory exhaustion",
+        "category": "DoS Prevention",
+        "impact": "DoS via memory exhaustion from large JSON payloads",
+        "fixComplexity": "low",
+        "fix": "Add size limit before parsing: if (json.length > 10MB) throw Error()"
+      },
+      {
+        "severity": "low",
+        "file": "scripts/drift-from-history.mjs",
+        "line": 44,
+        "description": "Environment variables used without validation: METAHARNESS_AUDIT_NAMESPACE and CLI_PKG used directly without schema validation",
+        "category": "Input Validation",
+        "impact": "Namespace/package spoofing if environment variables are controlled by attacker",
+        "fixComplexity": "low",
+        "fix": "Validate environment variables against whitelist/regex patterns on startup"
+      },
+      {
+        "severity": "low",
+        "file": "scripts/mint.mjs",
+        "line": 27,
+        "description": "Missing format validation: --name and --template parameters not validated against format requirements",
+        "category": "Input Validation",
+        "impact": "Invalid harness generation with malformed names",
+        "fixComplexity": "low",
+        "fix": "Add format validation (alphanumeric + colon/hyphen): /^[a-zA-Z0-9:-]+$/"
+      }
+    ],
+    "positiveFindings": [
+      "✅ No hardcoded secrets - all sensitive data sourced from environment variables",
+      "✅ Pinned dependency versions using tilde ranges (~0.3.0), not @latest",
+      "✅ Graceful degradation for optional @metaharness/* dependencies (ADR-150)",
+      "✅ Safe subprocess handling with consistent shell:false and array-based argv",
+      "✅ Safe JSON parsing with proper try-catch blocks",
+      "✅ All subprocesses have hard timeouts (prevents hangs)",
+      "✅ Good separation of concerns with shared helpers",
+      "✅ No eval(), Function(), or dynamic code execution"
+    ],
+    "recommendations": [
+      {
+        "priority": "CRITICAL",
+        "action": "Fix path traversal vulnerabilities in audit-trend.mjs and drift-from-history.mjs",
+        "timeline": "Week 1",
+        "effort": "2-3 hours"
+      },
+      {
+        "priority": "HIGH",
+        "action": "Add comprehensive numeric parameter validation across all scripts",
+        "timeline": "Week 1-2",
+        "effort": "3-4 hours"
+      },
+      {
+        "priority": "HIGH",
+        "action": "Fix command injection risk pattern in test-with-openrouter.mjs (line 64-65)",
+        "timeline": "Week 1",
+        "effort": "1 hour"
+      },
+      {
+        "priority": "HIGH",
+        "action": "Implement flag validation in redblue.mjs with allow-list",
+        "timeline": "Week 2",
+        "effort": "2-3 hours"
+      },
+      {
+        "priority": "MEDIUM",
+        "action": "Add environment variable schema validation on startup",
+        "timeline": "Week 2",
+        "effort": "1-2 hours"
+      },
+      {
+        "priority": "MEDIUM",
+        "action": "Sanitize error messages to prevent information disclosure",
+        "timeline": "Week 2",
+        "effort": "1-2 hours"
+      }
+    ]
+  },
+  "rawOutputPreview": "Based on my comprehensive security analysis of the ruflo-metaharness codebase, here's the security audit report in JSON format:\n\n```json\n{\n  \"reportMetadata\": {\n    \"timestamp\": \"2026-07-09\",\n    \"target\": \"ruflo-metaharness plugin\",\n    \"scope\": \"scripts/, commands/, agents/, skills/ directories\"\n  },\n  \"summary\": {\n    \"overallRiskScore\": 32,\n    \"riskLevel\": \"Low-to-Moderate\",\n    \"totalVulnerabilities\": 11,\n    \"severity\": {\n      \"critical\": 0,\n      \"high\": 1,\n      \"medium\": 5,\n      \"low\": 5\n    },\n    \"productionReadiness\": \"Acceptable with recommended fixes\",\n    \"estimatedRemediationTime\": \"14-18 hours\"\n  },\n  \"vulnerabilities\": [\n    {\n      \"severity\": \"high\",\n      \"file\": \"scripts/audit-trend.mjs\",\n      \"line\": 75,\n      \"description\": \"Path traversal vulnerability: unvalidated file paths from --baseline and --current flags are directly used with readFileSync() without directory constraints. An attacker could read arbitrary files (e.g., --baseline /etc/passwd).\",\n      \"category\": \"Path Traversal\",\n      \"impact\": \"Information disclosure - exposure of sensitive files outside intended directories\",\n      \"fixComplexity\": \"low\",\n      \"fix\": \"Normalize and validate paths using path.resolve() to ensure they stay within designated directory\"\n    },\n    {\n      \"severity\": \"medium\",\n      \"file\": \"scripts/drift-from-history.mjs\",\n      \"line\": 172,\n      \"description\": \"Path traversal in --baseline-file parameter: arbitrary file paths accepted without validation.\",\n      \"category\": \"Path Traversal\",\n      \"impact\": \"Information disclosure - access to sensitive files outside intended scope\",\n      \"fixComplexity\": \"low\",\n      \"fix\": \"Implement path validation helper restricting to current directory\"\n    },\n    {\n      \"severity\": \"medium\",\n      \"file\": \"scripts/evolve.mjs\",\n      \"line\": 83,\n      \"description\": \"Missing numeric validation: parseInt() result not checked for NaN; invalid --generations could cause process hangs\",\n      \"category\": \"Input ",
+  "rawOutputLength": 9183
+}

package/plugins/ruflo-metaharness/.claude-flow/metrics/test-gaps.json

@@ -0,0 +1,68 @@
+{
+  "timestamp": "2026-07-09T13:55:16.742Z",
+  "mode": "headless",
+  "workerType": "testgaps",
+  "model": "sonnet",
+  "durationMs": 181882,
+  "executionId": "testgaps_1783605134860_9jssz9",
+  "success": true,
+  "findings": {
+    "sections": [
+      {
+        "title": "Test Coverage Analysis — `plugins/ruflo-metaharness`",
+        "content": "\nThis plugin uses a hand-rolled test harness (`test-*.mjs` scripts with a custom `assert()` helper, no Jest/Vitest), plus `scripts/smoke.sh` (bash, mostly structural/CLI-registration grep checks) run in CI via `no-metaharness-smoke.yml` / `metaharness-ci.yml`.\n\n**Existing coverage:**\n| Test file | Covers |\n|---|---|\n| `test-similarity.mjs` | `_similarity.mjs` (all 5 fns) + `_harness.mjs` severity primitives |\n| `test-graceful-degradation.mjs` | CLI-level exit-0/degraded contract for `score/genome/mcp-scan/threat-model/oia-audit/audit-list/audit-trend/mint` only |\n| `test-mcp-tools.mjs` | MCP tool handler contract (shape, no-throw) against compiled dist |\n| `test-parallel-pipeline.mjs` | `router-parallel-analyze.mjs` as a black-box subprocess against a synthesized JSONL fixture |\n| `test-pipeline-roundtrip.mjs` | `oia-audit` → `audit-trend` e2e chain |\n| `test-with-openrouter.mjs` | Real e2e against OpenRouter (costs money, needs GCP secret) |\n| `smoke.sh` | Structural grep + CLI subcommand/`--help` registration for everything |\n\n",
+        "level": 2
+      },
+      {
+        "title": "1. Untested functions/classes",
+        "content": "\n**`_invoke.mjs` — zero direct unit tests.** This is the highest-value gap: it's the extracted shared plumbing (per its own header, \"converged security/perf/arch review\") used by ~15 scripts, made of small pure/near-pure functions, yet no test imports it directly — only indirectly through subprocess-level e2e tests that need npm/network.\n- `classifyDegraded(stderr, exitCode, reasonPrefix)` — untested\n- `injectJson(args, wantJson)` — untested\n- `parseTrailingJson(stdout)` — untested (this one **replaced a live bug** per the comment — the exact kind of function that regresses silently without a unit test)\n- `satisfiesTildeRange(version, pinVersion)` — untested\n- `findLocalPackageDir(pkg, pinVersion)` — untested (env-seam `RUFLO_METAHARNESS_SKIP_LOCAL` exists but nothing exercises it)\n- `cacheBaseDir()` — untested (env-seam `RUFLO_METAHARNESS_CACHE_BASE` exists but nothing exercises it)\n- `makeDegradedEmitter(pkg, pinVersion)` — untested\n\n**`_darwin.mjs` / `_redblue.mjs`** — only exercised transitively (network-dependent, via smoke.sh registration checks), never unit-tested directly:\n- `_darwin.mjs`: `runDarwin`, `runDarwinAsync` (streaming/`onProgress`/abort-signal paths), `importGepa`\n- `_redblue.mjs`: `runRedblue`, `emitRedblueDegradedJsonAndExit`\n\n**Pure parsing/logic functions, module-private (not exported), with no direct test:**\n- `security-bench.mjs: parseSecurityBenchMarkdown()` — 3 independent regex extractions (overall verdict, gate lines, baseline table)\n- `redblue.mjs: buildUpstreamArgs()` — per-subcommand argv construction + validation (`attack` family check, `report` requires `--in`)\n- `evolve.mjs: looksLikeGepaTranscript()`, `extractGepaTranscripts()`, `summarizeTraces()`, `safetyChecks()`\n- `audit-list.mjs: parseDurationMs()` — duration-spec parser (`7d`, `24h`, `1w`, `1m`)\n- `gepa.mjs: readJsonFile()`, `loadGenomeOrExit()`\n- `router-parallel-analyze.mjs: median()`, `pctile()`, `mean()` — pure stats, only exercised indirectly through a full subprocess run in `test-parallel-pipeline.mjs`\n\n**Note:** all of the above are unexported module-level functions in CLI scripts that run `main()` on import — that's *why* nobody unit-tests them directly today. Testing them requires either (a) exporting them (cheap, mirrors what `_similarity.mjs` already does) or (b) testing through stdout/exit-code capture of the whole script. Skeletons below assume (a) since it's the established pattern in this codebase.\n\n",
+        "level": 2
+      },
+      {
+        "title": "2. Edge cases not covered",
+        "content": "\n- `parseTrailingJson`: multiple `{...}` blocks where an earlier block is unparseable JSON but a *later* one nests braces the lazy regex fragments (the exact bug class the comment says this fixed) — no fixture actually exercises nested-object recovery via the greedy fallback.\n- `satisfiesTildeRange`: version with a `-alpha.N` suffix, `pinVersion` without a leading `~`, garbage input.\n- `classifyDegraded`: `exitCode === 0` with degraded-looking stderr (should NOT degrade — success takes precedence over noisy stderr); `stderr` undefined vs empty string.\n- `findLocalPackageDir`: version present but pre-1.0 (`0.x.y`) tilde matching; symlinked node_modules; two ancestors both having a stale version (should pick a satisfying one over the first found).\n- `parseDurationMs`: unit `m` is ambiguous (30-day \"month\" vs minutes) — worth a regression test pinning the intended semantics; malformed specs (`7`, `d7`, `-7d`).\n- `parseSecurityBenchMarkdown`: `overallMatch` is `null` (upstream changed emoji/wording) — does the caller handle a `null` gate list gracefully?\n- `buildUpstreamArgs('attack')`: missing `--count` (`ARGS.count === null`) should omit the flag, not emit `--count null`.\n\n",
+        "level": 2
+      },
+      {
+        "title": "3. Missing error handling tests",
+        "content": "\n- `ensureCachedInstall`: `mkdirSync` throw path (`cache-dir-create-failed`) and `npm install` non-zero exit (`install-failed`) — both branches untested.\n- `importOptionalLibrary`: the `recoverable` regex gate — an *unrelated* `TypeError` thrown from within an installed module must NOT be swallowed (re-thrown), only `MODULE_NOT_FOUND`-shaped errors should fall through to cached-install. No test proves non-recoverable errors propagate.\n- `evolve.mjs safetyChecks()`: none of `--generations`/`--children`/`--concurrency` out-of-range, invalid `--sandbox`/`--selection`/`--mutator`, or nonexistent `--repo` path are unit-tested (only reachable via full CLI spawn today).\n- `security-bench.mjs safetyChecks()`: `--population`/`--cycles` bounds untested directly.\n- `redblue.mjs`: `report` without `--in`, `attack` with invalid family — both call `process.exit(2)`, untested.\n\n",
+        "level": 2
+      },
+      {
+        "title": "4. Integration test gaps",
+        "content": "\n- **`evolve` / `gepa` / `learn` / `redblue` / `bench` / `security-bench` are absent from `test-graceful-degradation.mjs`.** The file's own header explicitly scopes to 8 skills and says nothing about these six. Given ADR-150's architectural constraint (\"ruflo remains operational if every MetaHarness package is removed\") is supposed to apply project-wide, this is a real gate gap, not just a nice-to-have — a regression in `_darwin.mjs`'s or `_redblue.mjs`'s degraded path for these specific subcommands would ship silently.\n- `drift-from-history.mjs` composing 3 primitives (`audit-list` → `similarity`/`audit-trend`) has no dedicated round-trip test analogous to `test-pipeline-roundtrip.mjs` — only structural grep in `smoke.sh`.\n- No test exercises `RUFLO_METAHARNESS_CACHE_BASE` / `RUFLO_METAHARNESS_SKIP_LOCAL` env seams that `_invoke.mjs` explicitly documents as \"used by test-graceful-degradation.mjs\" — grep confirms they aren't actually referenced there.\n\n",
+        "level": 2
+      },
+      {
+        "title": "Test skeletons",
+        "content": "\n**New file: `scripts/test-invoke.mjs`** (mirrors `test-similarity.mjs`'s style; requires exporting nothing new — everything below is already exported)\n\n```js\n#!/usr/bin/env node\n// test-invoke.mjs — unit tests for the shared _invoke.mjs plumbing\n// (classifyDegraded, injectJson, parseTrailingJson, satisfiesTildeRange,\n// findLocalPackageDir, cacheBaseDir). No network, no subprocess spawns.\n\nimport { mkdtempSync, mkdirSync, writeFileSync, rmSync } from 'node:fs';\nimport { tmpdir } from 'node:os';\nimport { join } from 'node:path';\nimport {\n  classifyDegraded, injectJson, parseTrailingJson,\n  satisfiesTildeRange, findLocalPackageDir, cacheBaseDir,\n} from './_invoke.mjs';\n\nlet passed = 0, failed = 0;\nconst failures = [];\nfunction assert(cond, label) {\n  if (cond) { console.log(`  ✓ ${label}`); passed++; }\n  else { console.log(`  ✗ ${label}`); failures.push(label); failed++; }\n}\n\nconsole.log('# classifyDegraded');\nassert(classifyDegraded('', null, 'x').degraded === true, 'null exitCode -> timeout');\nassert(classifyDegraded('', null, 'x').reason === 'x-timeout', 'timeout reason prefixed');\nassert(classifyDegraded('npm ERR! 404', 1, 'x').reason === 'x-not-available', 'npm ERR matches DEGRADED_RX');\nassert(classifyDegraded('some noisy stderr', 0, 'x').degraded === false, 'exit 0 with noisy stderr is NOT degraded');\nassert(classifyDegraded(undefined, 1, 'x').degraded === false, 'undefined stderr does not throw / does not false-positive');\n\nconsole.log('\\n# injectJson');\nassert(injectJson(['run'], true).includes('--json'), 'appends --json when wanted');\nassert(!injectJson(['run'], false).includes('--json'), 'omits --json when not wanted');\nassert(injectJson(['run', '--json'], true).filter((a) => a === '--json').length === 1, 'no duplicate --json');\n\nconsole.log('\\n# parseTrailingJson');\nassert(parseTrailingJson('progress\\n{\"a\":1}\\n{\"b\":2}').b === 2, 'picks LAST block, not first');\nassert(parseTrailingJson('{\"a\": {\"nested\": {\"deep\": 1}}}').a.nested.deep === 1, 'greedy fallback recovers nested braces');\nassert(parseTrailingJson('no json here') === null, 'no braces -> null, never throws');\nassert(parseTrailingJson('{\"a\":1} garbage {not json}').a === 1, 'unparseable trailing block falls back to earlier valid one');\n\nconsole.log('\\n# satisfiesTildeRange');\nassert(satisfiesTildeRange('0.8.3', '~0.8.0') === true, 'patch >= pin satisfies');\nassert(satisfiesTildeRange('0.8.0', '~0.8.0') === true, 'exact patch satisfies');\nassert(satisfiesTildeRange('0.9.0', '~0.8.0') === false, 'minor bump does not satisfy tilde range');\nassert(satisfiesTildeRange('not-a-version', '~0.8.0') === false, 'garbage version -> false, not throw');\nassert(satisfiesTildeRange('0.8.3', 'garbage-pin') === false, 'garbage pin -> false, not throw');\n\nconsole.log('\\n# cacheBaseDir + RUFLO_METAHARNESS_CACHE_BASE seam');\n{\n  const prev = process.env.RUFLO_METAHARNESS_CACHE_BASE;\n  delete process.env.RUFLO_METAHARNESS_CACHE_BASE;\n  assert(cacheBaseDir().endsWith('.ruflo'), 'defaults to ~/.ruflo');\n  process.env.RUFLO_METAHARNESS_CACHE_BASE = '/tmp/custom-cache';\n  assert(cacheBaseDir() === '/tmp/custom-cache', 'env override respected');\n  if (prev === undefined) delete process.env.RUFLO_METAHARNESS_CACHE_BASE;\n  else process.env.RUFLO_METAHARNESS_CACHE_BASE = prev;\n}\n\nconsole.log('\\n# findLocalPackageDir + RUFLO_METAHARNESS_SKIP_LOCAL seam');\n{\n  const fixture = mkdtempSync(join(tmpdir(), 'invoke-fixture-'));\n  const pkgDir = join(fixture, 'node_modules', '@metaharness', 'darwin');\n  mkdirSync(pkgDir, { recursive: true });\n  writeFileSync(join(pkgDir, 'package.json'), JSON.stringify({ version: '0.8.3' }));\n  const prevCwd = process.cwd();\n  process.chdir(fixture);\n  try {\n    assert(findLocalPackageDir('@metaharness/darwin', '~0.8.0') === pkgDir, 'finds satisfying local install by walking cwd');\n    assert(findLocalPackageDir('@metaharness/darwin', '~0.9.0') === null, 'rejects local install that does not satisfy pin');\n    process.env.RUFLO_METAHARNESS_SKIP_LOCAL = '1';\n    assert(findLocalPackageDir('@metaharness/darwin', '~0.8.0') === null, 'SKIP_LOCAL seam disables resolution entirely');\n  } finally {\n    delete process.env.RUFLO_METAHARNESS_SKIP_LOCAL;\n    process.chdir(prevCwd);\n    rmSync(fixture, { recursive: true, force: true });\n  }\n}\n\nconsole.log(`\\n${passed} passed, ${failed} failed`);\nif (failed > 0) { console.log('Failures:', failures.join(', ')); process.exit(1); }\n```\n\n**Extend `test-graceful-degradation.mjs`** — add the 6 missing skills to close the ADR-150 gate gap:\n\n```js\n// Add alongside the existing 8-skill list:\nconst MISSING_SKILLS = ['evolve', 'gepa', 'learn', 'redblue', 'bench', 'security-bench'];\nfor (const skill of MISSING_SKILLS) {\n  // same drill as the existing loop: spawn with npm_config_registry pointed\n  // at an unresolvable host, assert exitCode === 0 and stdout contains\n  // \"degraded\": true — these six currently escape the drill entirely.\n}\n```\n\n**New file: `scripts/test-cli-parsers.mjs`** (requires adding `export` to the named functions in `security-bench.mjs`, `redblue.mjs`, `audit-list.mjs`, `evolve.mjs`, `gepa.mjs` — currently module-private, which is *why* they're untestable in isolation today):\n\n```js\n#!/usr/bin/env node\n// test-cli-parsers.mjs — unit tests for pure parsing/validation logic\n// embedded in CLI scripts. Requires exporting: parseSecurityBenchMarkdown\n// (security-bench.mjs), buildUpstreamArgs (redblue.mjs), parseDurationMs\n// (audit-list.mjs), looksLikeGepaTranscript/extractGepaTranscripts/\n// summarizeTraces (evolve.mjs).\n\nimport { parseSecurityBenchMarkdown } from './security-bench.mjs';\nimport { parseDurationMs } from './audit-list.mjs';\nimport { looksLikeGepaTranscript, extractGepaTranscripts, summarizeTraces } from './evolve.mjs';\n\nlet passed = 0, failed = 0;\nconst failures = [];\nfunction assert(cond, label) {\n  if (cond) { console.log(`  ✓ ${label}`); passed++; }\n  else { console.log(`  ✗ ${label}`); failures.push(label); failed++; }\n}\n\nconsole.log('# parseSecurityBenchMarkdown');\nconst md = `\n**Overall: ✅ PASS**\n- ✅ **TPR improvement ≥ 25% vs fixed harness** — +150%\n- ❌ **FPR ≤ 5%** — 8%\n| B1 baseline | 0.42 | 0.60 | 0.10 | 0.90 | 0.95 | 2 | $0.10 |\n`;\nconst parsed = parseSecurityBenchMarkdown(md);\nassert(parsed.overall.ok === true, 'overall PASS parsed');\nassert(parsed.gates.length === 2, 'both gate lines parsed');\nassert(parsed.gates[1].ok === false, 'FAIL gate icon parsed correctly');\nassert(parsed.baselines[0].fitness === 0.42, 'baseline table row parsed');\nassert(parseSecurityBenchMarkdown('no matches here').overall === null, 'missing Overall line -> null, not throw');\nassert(parseSecurityBenchMarkdown('no matches here').gates.length === 0, 'no gate lines -> empty array, not throw');\n\nconsole.log('\\n# parseDurationMs');\nassert(parseDurationMs('7d') === 7 * 86400_000, '7d parses');\nassert(parseDurationMs('24h') === 24 * 3600_000, '24h parses');\nassert(parseDurationMs('1w') === 7 * 86400_000, '1w parses');\nassert(parseDurationMs('garbage') === null, 'malformed spec -> null');\nassert(parseDurationMs('-7d') === null, 'negative spec -> null (regex requires digits only)');\nassert(parseDurationMs('7') === null, 'missing unit -> null');\n\nconsole.log('\\n# evolve.mjs gepa-transcript helpers');\nassert(looksLikeGepaTranscript([{ actionRaw: 'x' }]) === true, 'actionRaw-shaped entries recognized');\nassert(looksLikeGepaTranscript([{ obs: 'y' }]) === true, 'obs-shaped entries recognized');\nassert(looksLikeGepaTranscript([]) === false, 'empty array is not a transcript');\nassert(looksLikeGepaTranscript([{ foo: 1 }]) === false, 'unrelated shape rejected');\nassert(looksLikeGepaTranscript(null) === false, 'null input -> false, not throw');\n\nconst record = { transcript: [{ actionRaw: 'a' }], traces: [{ taskId: 't1', exitCode: 1, timedOut: true, blockedActions: ['x'] }] };\nassert(extractGepaTranscripts(record).length === 1, 'top-level transcript extracted');\nconst summary = summarizeTraces(record);\nassert(summary.tasks === 1 && summary.failed === 1 && summary.timedOut === 1 && summary.blockedActions === 1, 'summarizeTraces tallies correctly');\nassert(summarizeTraces({}).tasks === 0, 'missing traces array -> zeroed summary, not throw');\n\nconsole.log(`\\n${passed} passed, ${failed} failed`);\nif (failed > 0) { console.log('Failures:', failures.join(', ')); process.exit(1); }\n```\n\n**New file: `scripts/test-router-parallel-math.mjs`** (requires exporting `median`/`pctile`/`mean` from `router-parallel-analyze.mjs`):\n\n```js\n#!/usr/bin/env node\nimport { median, pctile, mean } from './router-parallel-analyze.mjs';\n\nlet passed = 0, failed = 0;\nfunction assert(cond, label) { if (cond) passed++; else { console.log(`✗ ${label}`); failed++; } }\n\nassert(median([1, 2, 3]) === 2, 'odd-length median');\nassert(median([1, 2, 3, 4]) === 2.5, 'even-length median averages middle two');\nassert(median([]) === undefined || Number.isNaN(median([])), 'empty array does not throw');\nassert(pctile([1, 2, 3, 4, 5], 0.5) === median([1, 2, 3, 4, 5]), 'p50 matches median');\nassert(mean([2, 4, 6]) === 4, 'mean computes correctly');\nassert(Number.isNaN(mean([])) || mean([]) === 0, 'empty array mean defined (pin the actual convention)');\n\nconsole.log(`${passed} passed, ${failed} failed`);\nif (failed > 0) process.exit(1);\n```\n\n",
+        "level": 2
+      },
+      {
+        "title": "Priority",
+        "content": "1. `scripts/test-invoke.mjs` — closes the biggest real gap (shared plumbing, zero direct tests, already caused one documented regression).\n2. Extend `test-graceful-degradation.mjs` to the 6 missing skills — closes an actual ADR-150 CI gate hole.\n3. `test-cli-parsers.mjs` + `test-router-parallel-math.mjs` — cheap, pure-function tests once the target functions are exported (small, low-risk diffs to each source file).",
+        "level": 2
+      }
+    ],
+    "codeBlocks": [
+      {
+        "language": "js",
+        "code": "#!/usr/bin/env node\n// test-invoke.mjs — unit tests for the shared _invoke.mjs plumbing\n// (classifyDegraded, injectJson, parseTrailingJson, satisfiesTildeRange,\n// findLocalPackageDir, cacheBaseDir). No network, no subprocess spawns.\n\nimport { mkdtempSync, mkdirSync, writeFileSync, rmSync } from 'node:fs';\nimport { tmpdir } from 'node:os';\nimport { join } from 'node:path';\nimport {\n  classifyDegraded, injectJson, parseTrailingJson,\n  satisfiesTildeRange, findLocalPackageDir, cacheBaseDir,\n} from './_invoke.mjs';\n\nlet passed = 0, failed = 0;\nconst failures = [];\nfunction assert(cond, label) {\n  if (cond) { console.log(`  ✓ ${label}`); passed++; }\n  else { console.log(`  ✗ ${label}`); failures.push(label); failed++; }\n}\n\nconsole.log('# classifyDegraded');\nassert(classifyDegraded('', null, 'x').degraded === true, 'null exitCode -> timeout');\nassert(classifyDegraded('', null, 'x').reason === 'x-timeout', 'timeout reason prefixed');\nassert(classifyDegraded('npm ERR! 404', 1, 'x').reason === 'x-not-available', 'npm ERR matches DEGRADED_RX');\nassert(classifyDegraded('some noisy stderr', 0, 'x').degraded === false, 'exit 0 with noisy stderr is NOT degraded');\nassert(classifyDegraded(undefined, 1, 'x').degraded === false, 'undefined stderr does not throw / does not false-positive');\n\nconsole.log('\\n# injectJson');\nassert(injectJson(['run'], true).includes('--json'), 'appends --json when wanted');\nassert(!injectJson(['run'], false).includes('--json'), 'omits --json when not wanted');\nassert(injectJson(['run', '--json'], true).filter((a) => a === '--json').length === 1, 'no duplicate --json');\n\nconsole.log('\\n# parseTrailingJson');\nassert(parseTrailingJson('progress\\n{\"a\":1}\\n{\"b\":2}').b === 2, 'picks LAST block, not first');\nassert(parseTrailingJson('{\"a\": {\"nested\": {\"deep\": 1}}}').a.nested.deep === 1, 'greedy fallback recovers nested braces');\nassert(parseTrailingJson('no json here') === null, 'no braces -> null, never throws');\nassert(parseTrailingJson('{\"a\":1} garbage {not json}').a === 1, 'unparseable trailing block falls back to earlier valid one');\n\nconsole.log('\\n# satisfiesTildeRange');\nassert(satisfiesTildeRange('0.8.3', '~0.8.0') === true, 'patch >= pin satisfies');\nassert(satisfiesTildeRange('0.8.0', '~0.8.0') === true, 'exact patch satisfies');\nassert(satisfiesTildeRange('0.9.0', '~0.8.0') === false, 'minor bump does not satisfy tilde range');\nassert(satisfiesTildeRange('not-a-version', '~0.8.0') === false, 'garbage version -> false, not throw');\nassert(satisfiesTildeRange('0.8.3', 'garbage-pin') === false, 'garbage pin -> false, not throw');\n\nconsole.log('\\n# cacheBaseDir + RUFLO_METAHARNESS_CACHE_BASE seam');\n{\n  const prev = process.env.RUFLO_METAHARNESS_CACHE_BASE;\n  delete process.env.RUFLO_METAHARNESS_CACHE_BASE;\n  assert(cacheBaseDir().endsWith('.ruflo'), 'defaults to ~/.ruflo');\n  process.env.RUFLO_METAHARNESS_CACHE_BASE = '/tmp/custom-cache';\n  assert(cacheBaseDir() === '/tmp/custom-cache', 'env override respected');\n  if (prev === undefined) delete process.env.RUFLO_METAHARNESS_CACHE_BASE;\n  else process.env.RUFLO_METAHARNESS_CACHE_BASE = prev;\n}\n\nconsole.log('\\n# findLocalPackageDir + RUFLO_METAHARNESS_SKIP_LOCAL seam');\n{\n  const fixture = mkdtempSync(join(tmpdir(), 'invoke-fixture-'));\n  const pkgDir = join(fixture, 'node_modules', '@metaharness', 'darwin');\n  mkdirSync(pkgDir, { recursive: true });\n  writeFileSync(join(pkgDir, 'package.json'), JSON.stringify({ version: '0.8.3' }));\n  const prevCwd = process.cwd();\n  process.chdir(fixture);\n  try {\n    assert(findLocalPackageDir('@metaharness/darwin', '~0.8.0') === pkgDir, 'finds satisfying local install by walking cwd');\n    assert(findLocalPackageDir('@metaharness/darwin', '~0.9.0') === null, 'rejects local install that does not satisfy pin');\n    process.env.RUFLO_METAHARNESS_SKIP_LOCAL = '1';\n    assert(findLocalPackageDir('@metaharness/darwin', '~0.8.0') === null, 'SKIP_LOCAL seam disables resolution entirely');\n  } finally {\n    delete process.env.RUFLO_METAHARNESS_SKIP_LOCAL;\n    process.chdir(prevCwd);\n    rmSync(fixture, { recursive: true, force: true });\n  }\n}\n\nconsole.log(`\\n${passed} passed, ${failed} failed`);\nif (failed > 0) { console.log('Failures:', failures.join(', ')); process.exit(1); }"
+      },
+      {
+        "language": "js",
+        "code": "// Add alongside the existing 8-skill list:\nconst MISSING_SKILLS = ['evolve', 'gepa', 'learn', 'redblue', 'bench', 'security-bench'];\nfor (const skill of MISSING_SKILLS) {\n  // same drill as the existing loop: spawn with npm_config_registry pointed\n  // at an unresolvable host, assert exitCode === 0 and stdout contains\n  // \"degraded\": true — these six currently escape the drill entirely.\n}"
+      },
+      {
+        "language": "js",
+        "code": "#!/usr/bin/env node\n// test-cli-parsers.mjs — unit tests for pure parsing/validation logic\n// embedded in CLI scripts. Requires exporting: parseSecurityBenchMarkdown\n// (security-bench.mjs), buildUpstreamArgs (redblue.mjs), parseDurationMs\n// (audit-list.mjs), looksLikeGepaTranscript/extractGepaTranscripts/\n// summarizeTraces (evolve.mjs).\n\nimport { parseSecurityBenchMarkdown } from './security-bench.mjs';\nimport { parseDurationMs } from './audit-list.mjs';\nimport { looksLikeGepaTranscript, extractGepaTranscripts, summarizeTraces } from './evolve.mjs';\n\nlet passed = 0, failed = 0;\nconst failures = [];\nfunction assert(cond, label) {\n  if (cond) { console.log(`  ✓ ${label}`); passed++; }\n  else { console.log(`  ✗ ${label}`); failures.push(label); failed++; }\n}\n\nconsole.log('# parseSecurityBenchMarkdown');\nconst md = `\n**Overall: ✅ PASS**\n- ✅ **TPR improvement ≥ 25% vs fixed harness** — +150%\n- ❌ **FPR ≤ 5%** — 8%\n| B1 baseline | 0.42 | 0.60 | 0.10 | 0.90 | 0.95 | 2 | $0.10 |\n`;\nconst parsed = parseSecurityBenchMarkdown(md);\nassert(parsed.overall.ok === true, 'overall PASS parsed');\nassert(parsed.gates.length === 2, 'both gate lines parsed');\nassert(parsed.gates[1].ok === false, 'FAIL gate icon parsed correctly');\nassert(parsed.baselines[0].fitness === 0.42, 'baseline table row parsed');\nassert(parseSecurityBenchMarkdown('no matches here').overall === null, 'missing Overall line -> null, not throw');\nassert(parseSecurityBenchMarkdown('no matches here').gates.length === 0, 'no gate lines -> empty array, not throw');\n\nconsole.log('\\n# parseDurationMs');\nassert(parseDurationMs('7d') === 7 * 86400_000, '7d parses');\nassert(parseDurationMs('24h') === 24 * 3600_000, '24h parses');\nassert(parseDurationMs('1w') === 7 * 86400_000, '1w parses');\nassert(parseDurationMs('garbage') === null, 'malformed spec -> null');\nassert(parseDurationMs('-7d') === null, 'negative spec -> null (regex requires digits only)');\nassert(parseDurationMs('7') === null, 'missing unit -> null');\n\nconsole.log('\\n# evolve.mjs gepa-transcript helpers');\nassert(looksLikeGepaTranscript([{ actionRaw: 'x' }]) === true, 'actionRaw-shaped entries recognized');\nassert(looksLikeGepaTranscript([{ obs: 'y' }]) === true, 'obs-shaped entries recognized');\nassert(looksLikeGepaTranscript([]) === false, 'empty array is not a transcript');\nassert(looksLikeGepaTranscript([{ foo: 1 }]) === false, 'unrelated shape rejected');\nassert(looksLikeGepaTranscript(null) === false, 'null input -> false, not throw');\n\nconst record = { transcript: [{ actionRaw: 'a' }], traces: [{ taskId: 't1', exitCode: 1, timedOut: true, blockedActions: ['x'] }] };\nassert(extractGepaTranscripts(record).length === 1, 'top-level transcript extracted');\nconst summary = summarizeTraces(record);\nassert(summary.tasks === 1 && summary.failed === 1 && summary.timedOut === 1 && summary.blockedActions === 1, 'summarizeTraces tallies correctly');\nassert(summarizeTraces({}).tasks === 0, 'missing traces array -> zeroed summary, not throw');\n\nconsole.log(`\\n${passed} passed, ${failed} failed`);\nif (failed > 0) { console.log('Failures:', failures.join(', ')); process.exit(1); }"
+      },
+      {
+        "language": "js",
+        "code": "#!/usr/bin/env node\nimport { median, pctile, mean } from './router-parallel-analyze.mjs';\n\nlet passed = 0, failed = 0;\nfunction assert(cond, label) { if (cond) passed++; else { console.log(`✗ ${label}`); failed++; } }\n\nassert(median([1, 2, 3]) === 2, 'odd-length median');\nassert(median([1, 2, 3, 4]) === 2.5, 'even-length median averages middle two');\nassert(median([]) === undefined || Number.isNaN(median([])), 'empty array does not throw');\nassert(pctile([1, 2, 3, 4, 5], 0.5) === median([1, 2, 3, 4, 5]), 'p50 matches median');\nassert(mean([2, 4, 6]) === 4, 'mean computes correctly');\nassert(Number.isNaN(mean([])) || mean([]) === 0, 'empty array mean defined (pin the actual convention)');\n\nconsole.log(`${passed} passed, ${failed} failed`);\nif (failed > 0) process.exit(1);"
+      }
+    ]
+  },
+  "rawOutputPreview": "## Test Coverage Analysis — `plugins/ruflo-metaharness`\n\nThis plugin uses a hand-rolled test harness (`test-*.mjs` scripts with a custom `assert()` helper, no Jest/Vitest), plus `scripts/smoke.sh` (bash, mostly structural/CLI-registration grep checks) run in CI via `no-metaharness-smoke.yml` / `metaharness-ci.yml`.\n\n**Existing coverage:**\n| Test file | Covers |\n|---|---|\n| `test-similarity.mjs` | `_similarity.mjs` (all 5 fns) + `_harness.mjs` severity primitives |\n| `test-graceful-degradation.mjs` | CLI-level exit-0/degraded contract for `score/genome/mcp-scan/threat-model/oia-audit/audit-list/audit-trend/mint` only |\n| `test-mcp-tools.mjs` | MCP tool handler contract (shape, no-throw) against compiled dist |\n| `test-parallel-pipeline.mjs` | `router-parallel-analyze.mjs` as a black-box subprocess against a synthesized JSONL fixture |\n| `test-pipeline-roundtrip.mjs` | `oia-audit` → `audit-trend` e2e chain |\n| `test-with-openrouter.mjs` | Real e2e against OpenRouter (costs money, needs GCP secret) |\n| `smoke.sh` | Structural grep + CLI subcommand/`--help` registration for everything |\n\n## 1. Untested functions/classes\n\n**`_invoke.mjs` — zero direct unit tests.** This is the highest-value gap: it's the extracted shared plumbing (per its own header, \"converged security/perf/arch review\") used by ~15 scripts, made of small pure/near-pure functions, yet no test imports it directly — only indirectly through subprocess-level e2e tests that need npm/network.\n- `classifyDegraded(stderr, exitCode, reasonPrefix)` — untested\n- `injectJson(args, wantJson)` — untested\n- `parseTrailingJson(stdout)` — untested (this one **replaced a live bug** per the comment — the exact kind of function that regresses silently without a unit test)\n- `satisfiesTildeRange(version, pinVersion)` — untested\n- `findLocalPackageDir(pkg, pinVersion)` — untested (env-seam `RUFLO_METAHARNESS_SKIP_LOCAL` exists but nothing exercises it)\n- `cacheBaseDir()` — untested (env-seam `RUFLO_METAHARNESS_CACHE_BASE` ex",
+  "rawOutputLength": 16417
+}

package/plugins/ruflo-metaharness/.claude-flow/neural/stats.json

@@ -1,6 +1,6 @@
 {
-  "trajectoriesRecorded": 51,
-  "patternsLearned": 51,
+  "trajectoriesRecorded": 131,
+  "patternsLearned": 131,
   "signalsProcessed": 0,
-  "lastAdaptation": 1782427967363
+  "lastAdaptation": 1783606647775
 }

package/plugins/ruflo-metaharness/scripts/smoke.sh

@@ -204,14 +204,27 @@ LOADER="$ROOT/../../v3/@claude-flow/cli/src/commands/index.ts"
 grep -q "metaharness: () => import" "$LOADER" 2>/dev/null || miss="$miss not-registered-in-loader"
 [[ -z "$miss" ]] && ok || bad "$miss"
 
-step "16. ruflo wrapper has metaharness in optionalDependencies (architectural constraint #2)"
+step "16. ruflo wrapper keeps metaharness out of hard dependencies (ADR-150 constraint #2)"
 F="$ROOT/../../ruflo/package.json"
+# ADR-150 §"Architectural constraint" rule #2 states that when @metaharness/*
+# or `metaharness` appears in a package's dep graph, it MUST be in
+# `optionalDependencies` — never in `dependencies`. It does NOT require
+# ruflo to depend on metaharness at all. Historically this smoke asserted
+# the presence of metaharness in ruflo optionalDeps, which conflicted with
+# the #2561 "guard" budget (RUFLO_MAX=0 for optionalDependencies) that was
+# added to protect the cold `npx -y ruflo@alpha --version` startup path
+# from a heavy optional-dep install. #2561 is stronger evidence: metaharness
+# is on its FORBIDDEN list because installing it during ruflo's postinstall
+# caused a measured `npx --version` timeout. Correct reading of ADR-150 #2:
+# if metaharness IS present anywhere in ruflo's deps, it MUST be optional;
+# absence is fine (ruflo delegates to @claude-flow/cli, which itself keeps
+# metaharness as a runtime dynamic import via ADR-150 rule #1).
 node -e "
 const j = JSON.parse(require('fs').readFileSync('$F','utf-8'));
-const od = j.optionalDependencies || {};
-if (!od.metaharness) { console.error('missing metaharness in optionalDependencies'); process.exit(1); }
-if (j.dependencies && j.dependencies.metaharness) { console.error('metaharness leaked into dependencies'); process.exit(1); }
-" 2>/dev/null && ok || bad "ruflo wrapper missing metaharness optionalDep"
+const deps = j.dependencies || {};
+const forbidden = Object.keys(deps).filter(k => k === 'metaharness' || k.startsWith('@metaharness/'));
+if (forbidden.length) { console.error('ADR-150 rule #2 violated: ' + forbidden.join(', ') + ' must be optionalDependencies, not dependencies'); process.exit(1); }
+" 2>/dev/null && ok || bad "metaharness leaked into ruflo wrapper hard dependencies"
 
 step "17r. _harness.mjs pinned-version + no-@latest regression guard (supersedes iter 27)"
 F="$ROOT/scripts/_harness.mjs"