synapse-hub 2.4.2 → 2.4.3

package/README.en.md

@@ -6,7 +6,7 @@
 > **Core Mission:** A standalone, zero-dependency Linter & Guardrail engine (zero external dependencies for core engine & DoD gates) protecting test suite integrity in the era of AI code generation — Catching tautological "fake-pass" tests, eliminating hard sleeps, distilling 95% CI log noise, and enforcing Clean POM architecture. Specialized tools (Excel export, Canvas visual diff) leverage standard optional extras (`openpyxl`, `Pillow`).  
 > **Extended Ecosystem:** Bundled with 38 production QA skills, 6 specialized AI roles, and 9 DoD Quality Gates supporting Playwright, Cypress, Pytest, and Katalon.  
 > **Author:** Thế Vị ([@TeeVee998](https://github.com/TeeVee998))  
-> **Hub Version:** `v2.4.2` | **Scope:** 38 Standardized Skills, 6 Specialized AI Agents, 58 CLI Commands & 60+ Test Engineering Tools, 9 DoD Quality Gates.
+> **Hub Version:** `v2.4.3` | **Scope:** 38 Standardized Skills, 6 Specialized AI Agents, 58 CLI Commands & 60+ Test Engineering Tools, 9 DoD Quality Gates.
 
 [![npm version](https://img.shields.io/npm/v/synapse-hub.svg?style=flat-square&color=blue)](https://www.npmjs.com/package/synapse-hub)
 [![node version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg?style=flat-square)](https://nodejs.org)

package/README.md

@@ -6,7 +6,7 @@
 > **Định vị cốt lõi:** Bộ Linter & Guardrails độc lập (zero external dependencies cho core engine & DoD gates) bảo vệ độ tin cậy của test suite khi AI viết code — Phát hiện & ngăn chặn test "pass ảo" (0 assert, tautology), loại bỏ hoàn toàn sleep cố định, nén 95% log CI/CD, và chuẩn hóa cấu trúc Clean POM. Các tính năng nâng cao (xuất bảng Excel chuẩn doanh nghiệp, so sánh ảnh Canvas) sử dụng thư viện mở rộng tùy chọn (`openpyxl`, `Pillow`).  
 > **Module mở rộng:** Sẵn sàng kết nối 38 kỹ năng QA chuyên sâu, 6 vai trò AI Swarm và 9 Cổng kiểm định DoD hỗ trợ Playwright, Cypress, Pytest và Katalon.  
 > **Tác giả:** Thế Vị ([@TeeVee998](https://github.com/TeeVee998))  
-> **Phiên bản Hub:** `v2.4.2` | **Quy mô:** 38 Kỹ năng chuẩn hóa, 6 Vai trò AI Agent, 58 Lệnh CLI & 60+ Công cụ kiểm thử chuyên sâu, 9 Cổng kiểm định DoD.
+> **Phiên bản Hub:** `v2.4.3` | **Quy mô:** 38 Kỹ năng chuẩn hóa, 6 Vai trò AI Agent, 58 Lệnh CLI & 60+ Công cụ kiểm thử chuyên sâu, 9 Cổng kiểm định DoD.
 
 [![npm version](https://img.shields.io/npm/v/synapse-hub.svg?style=flat-square&color=blue)](https://www.npmjs.com/package/synapse-hub)
 [![node version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg?style=flat-square)](https://nodejs.org)

package/docs/ARCHITECTURE.md

@@ -1,7 +1,7 @@
 # Agent-Skills Architecture & Design Principles
 
 > **Scope:** Enterprise Multi-Agent QA Hub  
-> **Version:** `2.4.2` | **Status:** Active / Production Standard
+> **Version:** `2.4.3` | **Status:** Active / Production Standard
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "synapse-hub",
-  "version": "2.4.2",
+  "version": "2.4.3",
   "description": "Enterprise AI Agent Intelligence Hub & Autonomous Skill Network",
   "publishConfig": {
     "access": "public"

package/skills_manifest.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "name": "Enterprise Agent Skills Hub",
-  "version": "2.4.2",
+  "version": "2.4.3",
   "description": "Unified Catalog of 38 Specialized Skills for Autonomous AI Agents in Enterprise Software Quality Engineering, Performance, and Architecture.",
   "totalSkills": 38,
   "categories": {

package/synapse.config.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://raw.githubusercontent.com/TeeVee998/Synapse-Hub/main/docs/schemas/synapse.config.schema.json",
-  "version": "2.4.2",
+  "version": "2.4.3",
   "quality_gates": {
     "mutation_min_score": 80,
     "gates": {

package/tools/__init__.py

@@ -6,7 +6,7 @@ Repository: https://github.com/TeeVee998/Synapse-Hub
 License: MIT
 """
 
-__version__ = "2.4.2"
+__version__ = "2.4.3"
 __author__ = "Thế Vị (@TeeVee998)"
 
 __all__ = [

package/tools/browser_helpers.js

@@ -13,7 +13,7 @@
 (function () {
   'use strict';
 
-  if (window.__qa && window.__qa.__version === '2.4.2') {
+  if (window.__qa && window.__qa.__version === '2.4.3') {
     return window.__qa;
   }
 
@@ -47,7 +47,7 @@
   }
 
   const qa = {
-    __version: '2.4.2',
+    __version: '2.4.3',
 
     /**
      * 1. Smart Action Batching

package/tools/check_env.py

@@ -75,6 +75,7 @@ class DiagnosticRunner:
         self.results = []
         self.warnings = []
         self.errors = []
+        self.is_standalone = False
 
     def log_check(self, name, status, message, fix_hint=""):
         badge = f"{GREEN}[PASS]{RESET}" if status == "PASS" else (f"{YELLOW}[WARN]{RESET}" if status == "WARN" else f"{RED}[FAIL]{RESET}")
@@ -206,8 +207,8 @@ class DiagnosticRunner:
             self.log_check("Python Virtual Environment", "PASS", f"Python {py_ver} (Optional: create .venv if using auxiliary runners)")
 
     def check_project_structure(self):
+        # 1. QA Hub Repository Check
         is_hub = (self.target_dir / "skills_manifest.json").exists() or (self.target_dir / ".agents" / "skills").is_dir()
-
         if is_hub:
             required_dirs = [".agents/skills", ".agents/rules", "tools", "tests"]
             missing = [rd for rd in required_dirs if not (self.target_dir / rd).exists()]
@@ -220,24 +221,78 @@ class DiagnosticRunner:
                                "Restore from official agent-skills Git repository.")
             return
 
-        is_playwright = (self.target_dir / "playwright.config.ts").exists() or (self.target_dir / "playwright.config.js").exists()
+        # 2. Standalone Host / User Home Detection
+        is_user_home = False
+        try:
+            is_user_home = self.target_dir.resolve() == Path.home().resolve()
+        except Exception:
+            pass
+
+        has_project_marker = any([
+            (self.target_dir / marker).exists() for marker in [
+                ".git", "package.json", "requirements.txt", "pom.xml", "build.gradle",
+                "pytest.ini", "cypress.config.ts", "cypress.config.js",
+                "playwright.config.ts", "playwright.config.js", "Keywords", "Scripts"
+            ]
+        ]) or bool(list(self.target_dir.glob("*.prj")))
+
+        if is_user_home or not has_project_marker:
+            self.is_standalone = True
+            self.log_check("Project Structure (Standalone)", "PASS",
+                           "Host machine environment verified. (To diagnose a specific test project: agent-qa doctor <path>)")
+            return
+
+        # 3. Playwright Check
+        pkg_json = self.target_dir / "package.json"
+        has_playwright_pkg = pkg_json.exists() and "@playwright/test" in pkg_json.read_text(encoding="utf-8", errors="ignore")
+        is_playwright = (self.target_dir / "playwright.config.ts").exists() or (self.target_dir / "playwright.config.js").exists() or has_playwright_pkg
         if is_playwright:
-            required_dirs = ["tests"]
+            has_tests = (self.target_dir / "tests").is_dir() or (self.target_dir / "e2e").is_dir() or (self.target_dir / "src").is_dir()
+            if has_tests:
+                self.log_check("Project Structure (Playwright)", "PASS", "Playwright test project structure verified")
+            else:
+                self.log_check("Project Structure (Playwright)", "WARN", "Missing 'tests/' or 'e2e/' directory for Playwright specs",
+                               "Create a 'tests/' directory or run 'npx playwright test --init'")
+            return
+
+        # 4. Cypress Check
+        is_cypress = (self.target_dir / "cypress.config.ts").exists() or (self.target_dir / "cypress.config.js").exists() or (self.target_dir / "cypress").is_dir()
+        if is_cypress:
+            if (self.target_dir / "cypress").is_dir():
+                self.log_check("Project Structure (Cypress)", "PASS", "Cypress test project structure verified")
+            else:
+                self.log_check("Project Structure (Cypress)", "WARN", "Missing 'cypress/' directory",
+                               "Create a 'cypress/' directory for E2E specs")
+            return
+
+        # 5. Pytest / Python Selenium Check
+        is_pytest = (self.target_dir / "pytest.ini").exists() or (self.target_dir / "conftest.py").exists()
+        has_py_tests = (self.target_dir / "tests").is_dir() or bool(list(self.target_dir.glob("test_*.py")))
+        if is_pytest or (has_py_tests and (self.target_dir / "requirements.txt").exists()):
+            self.log_check("Project Structure (Pytest)", "PASS", "Python/Pytest test project structure verified")
+            return
+
+        # 6. Katalon Studio (Enterprise Web Clean POM)
+        is_katalon = bool(list(self.target_dir.glob("*.prj"))) or (self.target_dir / "Keywords").is_dir() or (self.target_dir / "Scripts").is_dir()
+        if is_katalon:
+            required_dirs = ["Scripts", "Keywords", "Profiles"]
             missing = [rd for rd in required_dirs if not (self.target_dir / rd).exists()]
             if not missing:
-                self.log_check("Project Structure (Playwright)", "PASS", "Playwright project structure verified")
+                self.log_check("Project Structure (Clean POM)", "PASS", "Clean POM structure verified (Keywords, Profiles, Scripts)")
             else:
-                self.log_check("Project Structure (Playwright)", "FAIL", f"Missing directories: {', '.join(missing)}")
+                self.log_check("Project Structure (POM)", "WARN" if len(missing) < len(required_dirs) else "FAIL",
+                               f"Missing directories: {', '.join(missing)}",
+                               "Verify git clone command or select target test project directory.")
             return
 
-        required_dirs = ["Scripts", "Keywords", "Profiles"]
-        missing = [rd for rd in required_dirs if not (self.target_dir / rd).exists()]
-        if not missing:
-            self.log_check("Project Structure (Clean POM)", "PASS", "Clean POM structure verified (Keywords, Profiles, Scripts)")
-        else:
-            self.log_check("Project Structure (POM)", "WARN" if len(missing) < len(required_dirs) else "FAIL",
-                           f"Missing directories: {', '.join(missing)}",
-                           "Verify git clone command or select target test project directory.")
+        # 7. Generic Test Project (any project with tests/ or test/)
+        if (self.target_dir / "tests").is_dir() or (self.target_dir / "test").is_dir() or (self.target_dir / "e2e").is_dir():
+            self.log_check("Project Structure (Automated Tests)", "PASS", "Standard automated test directory detected")
+            return
+
+        # Fallback: General project structure missing test suite
+        self.log_check("Project Structure", "WARN", "No automated test directories detected (tests/, Scripts/, cypress/)",
+                       "Run 'agent-qa setup .' to initialize Clean POM / Playwright configuration for this project.")
 
     def check_network(self):
         env_file = self.target_dir / ".env"
@@ -253,6 +308,9 @@ class DiagnosticRunner:
 
         base = os.environ.get("BASE_URL", "").rstrip("/")
         if not base:
+            if getattr(self, "is_standalone", False):
+                self.log_check("Network / Server Base URL", "PASS", "Host standalone check (configure BASE_URL in project .env when targeting an AUT)")
+                return
             self.log_check("Network / Server Base URL", "WARN", "BASE_URL not configured in .env",
                            "Copy .env.example to .env and configure BASE_URL to verify connectivity.")
             return

package/tools/cli.py

@@ -41,7 +41,7 @@ RESET = "\033[0m"
 def cmd_version(args):
     """Displays the current hub version, skill catalog count, and license information."""
     manifest_path = os.path.join(REPO_ROOT, "skills_manifest.json")
-    version = "2.4.2"
+    version = "2.4.3"
     if os.path.exists(manifest_path):
         try:
             import json
@@ -516,7 +516,7 @@ def cmd_mcp_excel(args):
 
 def _hub_version():
     manifest_path = os.path.join(REPO_ROOT, "skills_manifest.json")
-    version = "2.4.2"
+    version = "2.4.3"
     if os.path.exists(manifest_path):
         try:
             import json

package/tools/mcp_excel_server.py

@@ -23,7 +23,7 @@ if hasattr(sys.stdout, 'reconfigure'):
     except Exception:
         pass
 
-SERVER_VERSION = "2.4.2"
+SERVER_VERSION = "2.4.3"
 
 NS_MAIN = "{http://schemas.openxmlformats.org/spreadsheetml/2006/main}"
 NS_REL = "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}"

package/tools/mcp_server.py

@@ -47,7 +47,7 @@ import gherkin_suite
 import api_fuzzer
 
 SERVER_NAME = "enterprise-agent-qa"
-SERVER_VERSION = "2.4.2"
+SERVER_VERSION = "2.4.3"
 
 MCP_TOOLS = [
     {

package/tools/setup_project.py

@@ -394,6 +394,14 @@ def inject_antigravity_global_plugin():
             if not os.path.exists(dst_readme) or not os.path.samefile(src_readme, dst_readme):
                 shutil.copy2(src_readme, dst_readme)
 
+        # 3. LICENSE & NOTICE (MIT License Provenance & Author Attribution)
+        for meta_file in ("LICENSE", "NOTICE"):
+            src_meta = os.path.join(HUB_ROOT, meta_file)
+            dst_meta = os.path.join(target_plugin_dir, meta_file)
+            if os.path.exists(src_meta):
+                if not os.path.exists(dst_meta) or not os.path.samefile(src_meta, dst_meta):
+                    shutil.copy2(src_meta, dst_meta)
+
         # Helper to sync directory (junction or copy)
         def sync_dir(src, dst):
             if not os.path.exists(src):

package/tools/update_sentinel.py

@@ -65,7 +65,7 @@ def get_local_version():
         try:
             with open(pkg_file, "r", encoding="utf-8") as f:
                 data = json.load(f)
-                return data.get("version", "2.4.2")
+                return data.get("version", "2.4.3")
         except (OSError, json.JSONDecodeError):
             pass
 
@@ -74,11 +74,11 @@ def get_local_version():
         try:
             with open(manifest_file, "r", encoding="utf-8") as f:
                 data = json.load(f)
-                return data.get("version", "2.4.2")
+                return data.get("version", "2.4.3")
         except (OSError, json.JSONDecodeError):
             pass
 
-    return "2.4.2"
+    return "2.4.3"
 
 
 def fetch_remote_version():
@@ -321,14 +321,15 @@ def perform_update():
             except (subprocess.SubprocessError, OSError):
                 pass
         else:
-            # Refresh plugin.json in global plugin
+            # Refresh metadata files in global plugin
             try:
                 import shutil
-                src_pkg = os.path.join(HUB_ROOT, "plugin.json")
-                dst_pkg = os.path.join(GLOBAL_PLUGIN_DIR, "plugin.json")
-                if os.path.exists(src_pkg):
-                    shutil.copy2(src_pkg, dst_pkg)
-                    print(f"  {GREEN}[OK] Refreshed plugin.json in: {GLOBAL_PLUGIN_DIR}{RESET}")
+                for meta_f in ("plugin.json", "LICENSE", "NOTICE", "README.md"):
+                    src_f = os.path.join(HUB_ROOT, meta_f)
+                    dst_f = os.path.join(GLOBAL_PLUGIN_DIR, meta_f)
+                    if os.path.exists(src_f):
+                        shutil.copy2(src_f, dst_f)
+                print(f"  {GREEN}[OK] Refreshed metadata & LICENSE in: {GLOBAL_PLUGIN_DIR}{RESET}")
             except OSError:
                 pass
 

package/tools/welcome_page.py

@@ -48,7 +48,7 @@ def get_hub_metadata() -> Dict[str, Any]:
     """Retrieves version and catalog count from skills_manifest.json."""
     manifest_path = os.path.join(HUB_ROOT, "skills_manifest.json")
     meta = {
-        "version": "2.4.2",
+        "version": "2.4.3",
         "totalSkills": 38,
         "author": "Thế Vị (@TeeVee998)",
         "repo": "https://github.com/TeeVee998/Synapse-Hub"

package/benchmarks/qa_eval/reports/BENCHMARK_REPORT.md

@@ -1,94 +0,0 @@
-# QA Agent Benchmark Evaluation Report (Eval Harness)
-
-> **Evaluation Suite:** Enterprise QA Automation Self-Healing & Defect Sentinel Benchmark  
-> **Target Framework:** `agent-skills` QA Hub  
-> **Timestamp:** `2026-11-01T21:24:43.176168`  
-> **Run Scope:** FULL — 25/25 challenges across all 5 domains.  
-> **Discipline:** Truth Anchor (No Fake Pass) + Hard Policy Enforcement + 9 Quality Gates  
-
----
-
-## 1. Executive Summary
-
-| Core Benchmark Metric | Measured Score | Enterprise SLA Target | Status |
-| :--- | :--- | :--- | :--- |
-| **Autonomous Resolution Rate** | **100.0%** | $\ge 90.0\%$ | ✅ PASS |
-| **Mean Time to Resolution (MTTR)** | **0.0s** | $\le 3.00\text{s}$ | ✅ PASS |
-| **Average Token Cost** | **76.2 tokens** | $\le 500\text{ tokens}$ | ✅ PASS |
-| **AST Mutation Score** | **100.0%** | $\ge 80.0\%$ | ✅ PASS |
-| **Zero-Side-Effect Rate** | **100.0%** | $100.0\%$ | ✅ PASS |
-| **Action Safety Firewall Clearance** | **100.0%** | $100.0\%$ | ✅ PASS |
-
----
-
-## 2. Performance Breakdown by Failure Domain
-
-```mermaid
-xychart-beta
-    title "Autonomous Resolution Rate by Domain (%)"
-    x-axis ["API Contract", "Mutation/Tautology", "Locator Drift", "Stale DOM", "Timing & Race"]
-    y-axis "Resolution Rate (%)" 0 --> 100
-    bar [100.0, 100.0, 100.0, 100.0, 100.0]
-```
-
-| Failure Domain | Total Challenges | Passed | Resolution Rate | Avg MTTR | Avg Tokens |
-| :--- | :---: | :---: | :---: | :---: | :---: |
-| **Api Contract Drift** | 5 | 5 | 100.0% | 0.0s | 77.8 |
-| **Fake Pass Tautology** | 5 | 5 | 100.0% | 0.0s | 67.0 |
-| **Locator Drift** | 5 | 5 | 100.0% | 0.0s | 52.4 |
-| **Stale And Mutation** | 5 | 5 | 100.0% | 0.0s | 94.6 |
-| **Timing And Race** | 5 | 5 | 100.0% | 0.0s | 89.4 |
-
----
-
-## 3. Empirical Instrumentation & Measurement Protocol
-
-| Evaluation Domain | Measurement Tool | Verification Mechanism |
-| :--- | :---: | :--- |
-| **Locator Drift Healing** | `tools/heuristic_locator_matcher.py` | 3-Layer matching cascade verified dynamically against DOM element tags & attributes |
-| **API Contract Shift** | `tools/api_drift_sentinel.py` | AST assertion contract validation on response headers and status codes |
-| **Timing & Race Conditions** | `tools/cache_resolver.py` | Smart barrier replacement eliminating `Thread.sleep` and verifying detachment |
-| **Stale Elements** | In-place dynamic refetching | Mutation detachment prevention with dynamic attribute locators |
-| **Tautology / Fake-Pass** | `tools/micro_mutator.py` | Active AST mutant injection (requires $\ge 80\%$ mutation score) |
-| **Destructive Action Guard** | `tools/safety_firewall.py` | Regex and AST pre-flight firewall blocking irreversible actions |
-
----
-
-## 4. Detailed Challenge Matrix
-
-| ID | Challenge Name | Domain | Difficulty | MTTR | Tokens | Mutation Score | Status |
-| :--- | :--- | :--- | :---: | :---: | :---: | :---: | :---: |
-| `QA-CHALLENGE-06` | Numeric ID Serialized as String (Type Mutation) | `api_contract_drift` | MEDIUM | 0.000s | 77 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-07` | Payload Response Field Rename | `api_contract_drift` | EASY | 0.000s | 91 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-08` | Nested Response Object Flattened | `api_contract_drift` | MEDIUM | 0.000s | 82 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-09` | HTTP Creation Status Code Shift (200 OK -> 201 Created) | `api_contract_drift` | EASY | 0.000s | 64 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-10` | Authentication Header Prefix Upgrade | `api_contract_drift` | EASY | 0.000s | 75 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-21` | Swallowed HTTP 500 Error in Empty Catch Block | `fake_pass_tautology` | EASY | 0.000s | 65 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-22` | Zero-Assertion Smoke Test (Tautological Pass) | `fake_pass_tautology` | EASY | 0.000s | 84 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-23` | Tautological assert true == true | `fake_pass_tautology` | EASY | 0.000s | 58 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-24` | Unawaited Async Assertion (Silent Green Trap) | `fake_pass_tautology` | MEDIUM | 0.000s | 64 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-25` | Unbounded Relational Assertion (status >= 200) | `fake_pass_tautology` | EASY | 0.000s | 64 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-01` | Dynamic CSS-in-JS Hash Locator Shift | `locator_drift` | MEDIUM | 0.000s | 50 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-02` | Nested Shadow DOM Component Piercing | `locator_drift` | HARD | 0.000s | 62 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-03` | Semantic Text Label Evolution | `locator_drift` | EASY | 0.000s | 50 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-04` | Legacy ID Removed in Favor of data-testid | `locator_drift` | EASY | 0.000s | 50 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-05` | HTML Tag Evolution: Anchor to ARIA Button | `locator_drift` | MEDIUM | 0.000s | 50 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-16` | WebSocket Table Auto-Refresh Stale Reference | `stale_and_mutation` | HARD | 0.000s | 88 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-17` | Tab Switch Component Unmount Detach | `stale_and_mutation` | MEDIUM | 0.000s | 103 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-18` | Pagination Replaces tbody (Stale Row Index) | `stale_and_mutation` | MEDIUM | 0.000s | 97 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-19` | Reopened Modal Generates Fresh DOM Node | `stale_and_mutation` | MEDIUM | 0.000s | 111 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-20` | Locale Swap Invalidates Hardcoded Text Selectors | `stale_and_mutation` | EASY | 0.000s | 74 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-11` | Network Latency Spike (3,500ms Throttle) Breaking Static Sleep | `timing_and_race` | MEDIUM | 0.000s | 88 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-12` | PrimeNG Modal Backdrop Fading Intercept | `timing_and_race` | HARD | 0.000s | 91 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-13` | Debounced Search Input Autocomplete Race | `timing_and_race` | MEDIUM | 0.000s | 104 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-14` | Async Chart SVG Animation Race Condition | `timing_and_race` | MEDIUM | 0.000s | 82 | 100.0% | ✅ PASS |
-| `QA-CHALLENGE-15` | Infinite Scroll Lazy Loaded Chunk Detach | `timing_and_race` | MEDIUM | 0.000s | 82 | 100.0% | ✅ PASS |
-
----
-
-## 5. Verification & Methodological Rigor
-
-All benchmark challenges were evaluated against deterministic test oracles:
-1. **Deterministic Resolution:** Healed selectors and patches were verified against DOM snapshots and API schemas.
-2. **Mutation Quality Verification:** Tautology challenges were verified using `tools/micro_mutator.py` to ensure assertions caught injected mutants.
-3. **Safety Clearance:** Action statements were evaluated using `tools/safety_firewall.py` in dry-run mode to confirm zero destructive side effects.

package/benchmarks/qa_eval/reports/eval_results.json

@@ -1,461 +0,0 @@
-{
-  "timestamp": "2026-11-01T21:24:43.176168",
-  "total_challenges": 25,
-  "passed_challenges": 25,
-  "failed_challenges": 0,
-  "resolution_rate_pct": 100.0,
-  "avg_mttr_sec": 0.0,
-  "avg_token_consumption": 76.2,
-  "avg_mutation_score": 100.0,
-  "zero_side_effect_rate_pct": 100.0,
-  "safety_firewall_clearance_pct": 100.0,
-  "categories": {
-    "api_contract_drift": {
-      "total": 5,
-      "passed": 5,
-      "tokens": 389,
-      "time": 0.0001,
-      "resolution_rate": 100.0,
-      "avg_tokens": 77.8,
-      "avg_time": 0.0
-    },
-    "fake_pass_tautology": {
-      "total": 5,
-      "passed": 5,
-      "tokens": 335,
-      "time": 0.0004,
-      "resolution_rate": 100.0,
-      "avg_tokens": 67.0,
-      "avg_time": 0.0
-    },
-    "locator_drift": {
-      "total": 5,
-      "passed": 5,
-      "tokens": 262,
-      "time": 0.0002,
-      "resolution_rate": 100.0,
-      "avg_tokens": 52.4,
-      "avg_time": 0.0
-    },
-    "stale_and_mutation": {
-      "total": 5,
-      "passed": 5,
-      "tokens": 473,
-      "time": 0.0,
-      "resolution_rate": 100.0,
-      "avg_tokens": 94.6,
-      "avg_time": 0.0
-    },
-    "timing_and_race": {
-      "total": 5,
-      "passed": 5,
-      "tokens": 447,
-      "time": 0.0,
-      "resolution_rate": 100.0,
-      "avg_tokens": 89.4,
-      "avg_time": 0.0
-    }
-  },
-  "details": [
-    {
-      "id": "QA-CHALLENGE-06",
-      "name": "Numeric ID Serialized as String (Type Mutation)",
-      "category": "api_contract_drift",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0001,
-      "max_time_allowed_sec": 2.0,
-      "time_compliant": true,
-      "token_consumption": 77,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Updated assertion contract: assert str(response.data.invoice_id) == '10423'"
-    },
-    {
-      "id": "QA-CHALLENGE-07",
-      "name": "Payload Response Field Rename",
-      "category": "api_contract_drift",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 1.5,
-      "time_compliant": true,
-      "token_consumption": 91,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Updated assertion contract: assert (response.json().get('email_address') or response.json().get('user_email')) == 'qa@example.com'"
-    },
-    {
-      "id": "QA-CHALLENGE-08",
-      "name": "Nested Response Object Flattened",
-      "category": "api_contract_drift",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.0,
-      "time_compliant": true,
-      "token_consumption": 82,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Updated assertion contract: tier = response.json().get('tier') or response.json().get('profile', {}).get('tier'); assert tier == 'GOLD'"
-    },
-    {
-      "id": "QA-CHALLENGE-09",
-      "name": "HTTP Creation Status Code Shift (200 OK -> 201 Created)",
-      "category": "api_contract_drift",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 1.0,
-      "time_compliant": true,
-      "token_consumption": 64,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Updated assertion contract: assert response.status_code in (200, 201)"
-    },
-    {
-      "id": "QA-CHALLENGE-10",
-      "name": "Authentication Header Prefix Upgrade",
-      "category": "api_contract_drift",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 1.5,
-      "time_compliant": true,
-      "token_consumption": 75,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Updated assertion contract: headers = {'Authorization': f'Bearer {auth_token}'}"
-    },
-    {
-      "id": "QA-CHALLENGE-21",
-      "name": "Swallowed HTTP 500 Error in Empty Catch Block",
-      "category": "fake_pass_tautology",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0002,
-      "max_time_allowed_sec": 1.0,
-      "time_compliant": true,
-      "token_consumption": 65,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Injected robust assertion (Mutation Score: 100.0%): REMOVE_SWALLOWED_CATCH_AND_ASSERT"
-    },
-    {
-      "id": "QA-CHALLENGE-22",
-      "name": "Zero-Assertion Smoke Test (Tautological Pass)",
-      "category": "fake_pass_tautology",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0001,
-      "max_time_allowed_sec": 1.5,
-      "time_compliant": true,
-      "token_consumption": 84,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Injected robust assertion (Mutation Score: 100.0%): INJECT_POST_CONDITION_ASSERTION"
-    },
-    {
-      "id": "QA-CHALLENGE-23",
-      "name": "Tautological assert true == true",
-      "category": "fake_pass_tautology",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0001,
-      "max_time_allowed_sec": 1.0,
-      "time_compliant": true,
-      "token_consumption": 58,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Injected robust assertion (Mutation Score: 100.0%): MUTATION_TESTING_KILLS_TAUTOLOGY"
-    },
-    {
-      "id": "QA-CHALLENGE-24",
-      "name": "Unawaited Async Assertion (Silent Green Trap)",
-      "category": "fake_pass_tautology",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 1.5,
-      "time_compliant": true,
-      "token_consumption": 64,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Injected robust assertion (Mutation Score: 100.0%): AST_ASYNC_AWAIT_ENFORCEMENT"
-    },
-    {
-      "id": "QA-CHALLENGE-25",
-      "name": "Unbounded Relational Assertion (status >= 200)",
-      "category": "fake_pass_tautology",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 1.2,
-      "time_compliant": true,
-      "token_consumption": 64,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Injected robust assertion (Mutation Score: 100.0%): BOUNDED_INTERVAL_ASSERTION"
-    },
-    {
-      "id": "QA-CHALLENGE-01",
-      "name": "Dynamic CSS-in-JS Hash Locator Shift",
-      "category": "locator_drift",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0002,
-      "max_time_allowed_sec": 2.0,
-      "time_compliant": true,
-      "token_consumption": 50,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Autonomous cascade healed: 'button.btn-submit' -> '[data-testid='submit-order-btn']' (confidence 0.98)"
-    },
-    {
-      "id": "QA-CHALLENGE-02",
-      "name": "Nested Shadow DOM Component Piercing",
-      "category": "locator_drift",
-      "difficulty": "HARD",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 3.0,
-      "time_compliant": true,
-      "token_consumption": 62,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Autonomous cascade healed: '#customer-email' -> 'template:has-text('<input id='customer-email' type='email' data-testid='user-email'/>')' (confidence 0.94)"
-    },
-    {
-      "id": "QA-CHALLENGE-03",
-      "name": "Semantic Text Label Evolution",
-      "category": "locator_drift",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 1.5,
-      "time_compliant": true,
-      "token_consumption": 50,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Autonomous cascade healed: '//button[text()='Submit Order']' -> '#order-cta' (confidence 0.9)"
-    },
-    {
-      "id": "QA-CHALLENGE-04",
-      "name": "Legacy ID Removed in Favor of data-testid",
-      "category": "locator_drift",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 1.5,
-      "time_compliant": true,
-      "token_consumption": 50,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Autonomous cascade healed: '#customer_name' -> '[data-testid='customer-name-field']' (confidence 0.98)"
-    },
-    {
-      "id": "QA-CHALLENGE-05",
-      "name": "HTML Tag Evolution: Anchor to ARIA Button",
-      "category": "locator_drift",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.0,
-      "time_compliant": true,
-      "token_consumption": 50,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Autonomous cascade healed: 'a.nav-export' -> 'button' (confidence 0.9)"
-    },
-    {
-      "id": "QA-CHALLENGE-16",
-      "name": "WebSocket Table Auto-Refresh Stale Reference",
-      "category": "stale_and_mutation",
-      "difficulty": "HARD",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.5,
-      "time_compliant": true,
-      "token_consumption": 88,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Eliminated stale element trap: DYNAMIC_LOCATOR_REQUERY"
-    },
-    {
-      "id": "QA-CHALLENGE-17",
-      "name": "Tab Switch Component Unmount Detach",
-      "category": "stale_and_mutation",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.0,
-      "time_compliant": true,
-      "token_consumption": 103,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Eliminated stale element trap: TAB_MOUNT_SYNCHRONIZATION"
-    },
-    {
-      "id": "QA-CHALLENGE-18",
-      "name": "Pagination Replaces tbody (Stale Row Index)",
-      "category": "stale_and_mutation",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.0,
-      "time_compliant": true,
-      "token_consumption": 97,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Eliminated stale element trap: PAGINATION_NETWORK_SYNC"
-    },
-    {
-      "id": "QA-CHALLENGE-19",
-      "name": "Reopened Modal Generates Fresh DOM Node",
-      "category": "stale_and_mutation",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.0,
-      "time_compliant": true,
-      "token_consumption": 111,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Eliminated stale element trap: VISIBLE_SELECTOR_REBIND"
-    },
-    {
-      "id": "QA-CHALLENGE-20",
-      "name": "Locale Swap Invalidates Hardcoded Text Selectors",
-      "category": "stale_and_mutation",
-      "difficulty": "EASY",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 1.5,
-      "time_compliant": true,
-      "token_consumption": 74,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Eliminated stale element trap: LOCALE_AGNOSTIC_DATA_ATTRIBUTES"
-    },
-    {
-      "id": "QA-CHALLENGE-11",
-      "name": "Network Latency Spike (3,500ms Throttle) Breaking Static Sleep",
-      "category": "timing_and_race",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.5,
-      "time_compliant": true,
-      "token_consumption": 88,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Replaced brittle timing with dynamic smart barrier: DYNAMIC_SMART_WAIT"
-    },
-    {
-      "id": "QA-CHALLENGE-12",
-      "name": "PrimeNG Modal Backdrop Fading Intercept",
-      "category": "timing_and_race",
-      "difficulty": "HARD",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 3.0,
-      "time_compliant": true,
-      "token_consumption": 91,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Replaced brittle timing with dynamic smart barrier: OVERLAY_SAFE_DISPATCH"
-    },
-    {
-      "id": "QA-CHALLENGE-13",
-      "name": "Debounced Search Input Autocomplete Race",
-      "category": "timing_and_race",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.5,
-      "time_compliant": true,
-      "token_consumption": 104,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Replaced brittle timing with dynamic smart barrier: CDP_RESPONSE_BARRIER"
-    },
-    {
-      "id": "QA-CHALLENGE-14",
-      "name": "Async Chart SVG Animation Race Condition",
-      "category": "timing_and_race",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.0,
-      "time_compliant": true,
-      "token_consumption": 82,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Replaced brittle timing with dynamic smart barrier: SVG_VISIBILITY_SMART_WAIT"
-    },
-    {
-      "id": "QA-CHALLENGE-15",
-      "name": "Infinite Scroll Lazy Loaded Chunk Detach",
-      "category": "timing_and_race",
-      "difficulty": "MEDIUM",
-      "status": "PASSED",
-      "resolved": true,
-      "safety_cleared": true,
-      "time_to_heal_sec": 0.0,
-      "max_time_allowed_sec": 2.0,
-      "time_compliant": true,
-      "token_consumption": 82,
-      "mutation_score": 100.0,
-      "zero_side_effect": true,
-      "resolution_notes": "Replaced brittle timing with dynamic smart barrier: VIRTUAL_SCROLL_INTO_VIEW"
-    }
-  ]
-}