synapse-hub 3.0.0 → 3.0.1

package/.agents/skills/web-vitals-and-performance-profiler/examples/playwright_cwv_profiler_fixture.ts

@@ -0,0 +1,61 @@
+/**
+ * Playwright Core Web Vitals (CWV) Profiling Fixture via Chrome DevTools Protocol (CDP)
+ * Measures LCP (Largest Contentful Paint), CLS (Cumulative Layout Shift), and INP budgets.
+ */
+
+import { test as base, expect } from '@playwright/test';
+
+interface PerformanceMetrics {
+  lcp: number; // ms
+  cls: number; // score
+  domContentLoaded: number; // ms
+}
+
+export const test = base.extend<{ perfMetrics: PerformanceMetrics }>({
+  perfMetrics: async ({ page }, use) => {
+    const client = await page.context().newCDPSession(page);
+    await client.send('Performance.enable');
+
+    // Collect performance entries after page navigation
+    const getMetrics = async (): Promise<PerformanceMetrics> => {
+      const rawMetrics = await client.send('Performance.getMetrics');
+      const metricsMap = new Map(rawMetrics.metrics.map(m => [m.name, m.value]));
+
+      // Query window performance observer for LCP & CLS
+      const cwv = await page.evaluate(() => {
+        return new Promise<{ lcp: number; cls: number }>((resolve) => {
+          let lcp = 0;
+          let cls = 0;
+
+          new PerformanceObserver((entryList) => {
+            const entries = entryList.getEntries();
+            const lastEntry = entries[entries.length - 1];
+            lcp = lastEntry ? lastEntry.startTime : 0;
+          }).observe({ type: 'largest-contentful-paint', buffered: true });
+
+          new PerformanceObserver((entryList) => {
+            for (const entry of entryList.getEntries() as any[]) {
+              if (!entry.hadRecentInput) cls += entry.value;
+            }
+          }).observe({ type: 'layout-shift', buffered: true });
+
+          setTimeout(() => resolve({ lcp, cls }), 1500);
+        });
+      });
+
+      return {
+        lcp: Math.round(cwv.lcp),
+        cls: Math.round(cwv.cls * 1000) / 1000,
+        domContentLoaded: (metricsMap.get('DomContentLoaded') || 0) * 1000,
+      };
+    };
+
+    // Execute test body
+    await use({ lcp: 0, cls: 0, domContentLoaded: 0 });
+
+    // Assert CWV Budget enforcement: LCP < 2500ms, CLS < 0.1
+    const finalMetrics = await getMetrics();
+    expect(finalMetrics.lcp).toBeLessThan(2500);
+    expect(finalMetrics.cls).toBeLessThan(0.10);
+  },
+});

package/AGENTS.md

@@ -11,6 +11,7 @@
    `> 🛡️ **Synapse Hub Active:** Clean POM / Flat Architecture`  
    *(Strictly prohibited from containing the string `[OK]`)*. Omit footer telemetry by default to save tokens. Detailed footer is opt-in when requested ("bật telemetry").
 2. **Pragmatic Communication:** Converse and format telemetry in Vietnamese (clear, direct, action-oriented, zero tech-jargon overload). All codebase files, test scripts, Page Classes, docstrings, and commits remain strictly in English.
+3. **English-First Documentation Ingestion (Token Saver):** Whenever inspecting or referencing project documentation, architecture specifications, or readmes that have bilingual counterparts (e.g. `ARCHITECTURE.en.md` vs `ARCHITECTURE.md`, `README.en.md` vs `README.md`), always read the English version (`*.en.md`). English achieves significantly higher token density (saving 50–65% BPE tokens vs diacritic Vietnamese), preserving context window capacity.
 
 ---
 
@@ -31,10 +32,11 @@ You are a lazy senior developer. The best code is the code never written. Solve
 2. **The 7-Rung Ladder (Stop at the first rung that fully works):**
    - **Rung 1:** *Does it need to exist?* (YAGNI). Skip unrequested features, options, and speculative flexibility in one line.
    - **Rung 2:** *Already in this codebase?* Use existing helpers, Page Classes, BasePage methods, and patterns.
-   - **Rung 3:** *Standard library or platform native?* Use language stdlib or test framework native features (Playwright auto-waiting, web-first assertions).
-   - **Rung 4:** *An installed dependency?* Use existing dependencies. Never add a package for a few lines.
-   - **Rung 5:** *Can it be one clear line?* Write a line a reader grasps at a glance.
-   - **Rung 6:** *Otherwise:* Write the minimum complete code that works.
+   - **Rung 3:** *Standard library?* Use language stdlib unless the project has its own equivalent.
+   - **Rung 4:** *Platform or framework native?* Use test framework native features (Playwright auto-waiting, web-first assertions).
+   - **Rung 5:** *An installed dependency?* Use existing dependencies. Never add a package for a few lines.
+   - **Rung 6:** *Can it be one clear line?* Write a line a reader grasps at a glance.
+   - **Rung 7:** *Otherwise:* Write the minimum complete code that works.
 3. **Completeness & Execution Invariants:**
    - Be lazy about the solution, never about the change: finish every part the task needs, including callers, tests, and fixtures your change affects.
    - Zero unnecessary abstractions: no wrappers, speculative options, configs, or "for later" boilerplate nobody asked for. Deletion beats addition.

package/CLAUDE.md

@@ -46,6 +46,7 @@ In accordance with the MIT License, the original copyright notice crediting **Th
 5. **Pragmatic Communication Protocol:**
    - Conversational responses, explanation, and telemetry MUST be in Vietnamese.
    - All codebase assets, test scripts, Page Classes, docstrings, and commits MUST remain strictly in English.
+   - English-First Document Ingestion: When reading bilingual docs (e.g. ARCHITECTURE.en.md vs ARCHITECTURE.md), always read the English version (*.en.md) to save 50–65% BPE tokens.
 
 6. **Lean Senior Dev Protocol (The 7-Rung Ladder & YAGNI):**
    - The best code is the code never written. Solve the whole problem with the least new code.

package/README.en.md

@@ -6,11 +6,11 @@
 
 > **Core Mission:** A standalone linter and guardrail engine (zero external dependencies for core engine & DoD gates) safeguarding automated test suites when AI writes code — Automatically catching "fake-pass" tests (0 assertions, tautologies), eliminating fixed sleeps, compressing 95% of CI/CD log noise, and enforcing Clean POM architecture.  
 > **Author:** Thế Vị ([@TeeVee998](https://github.com/TeeVee998)) | **License:** MIT License  
-> **Version:** `v2.9.0` | **Scale:** 51 Standardized QA Skills, 6 Specialized AI Agents, 10 DoD Quality Gates.
+> **Version:** `v3.0.1` | **Scale:** 51 Standardized QA Skills, 6 Specialized AI Agents, 10 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)
-[![python version](https://img.shields.io/badge/python-%3E%3D3.9-blue.svg?style=flat-square)](https://python.org)
+[![python version](https://img.shields.io/badge/python-%3E%3D3.10-blue.svg?style=flat-square)](https://python.org)
 [![license](https://img.shields.io/badge/license-MIT-green.svg?style=flat-square)](https://github.com/TeeVee998/Synapse-Hub/blob/main/LICENSE)
 [![Ecosystem](https://img.shields.io/badge/AI%20Ecosystem-Antigravity%20%7C%20Cursor%20%7C%20Claude%20%7C%20Copilot%20%7C%20Windsurf-orange.svg?style=flat-square)](#)
 
@@ -113,7 +113,7 @@ Every test code change must satisfy all 10 Quality Gates before pull request mer
 # Pre-commit hook (.pre-commit-config.yaml):
 repos:
   - repo: https://github.com/TeeVee998/Synapse-Hub
-    rev: v3.0.0
+    rev: v3.0.1
     hooks:
       - id: synapse-lint
       - id: synapse-verify
@@ -123,8 +123,8 @@ repos:
 
 ## 📚 Deep Technical Documentation
 
-- 🏛️ **Architecture & Industry Comparison Matrix:** [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md)
-- 🛡️ **10 Quality Gates Definition of Done (DoD):** [docs/QUALITY_GATES.md](docs/QUALITY_GATES.md)
-- 📖 **Comprehensive CLI Command Reference:** [docs/CLI_REFERENCE.md](docs/CLI_REFERENCE.md)
-- 🚀 **CI/CD Pipeline Integration Playbook:** [docs/CI_CD_INTEGRATION.md](docs/CI_CD_INTEGRATION.md)
-- 🤝 **Open-Source Contributing Guidelines:** [docs/CONTRIBUTING.md](docs/CONTRIBUTING.md)
+- 🏛️ **Architecture & Industry Comparison Matrix:** [docs/ARCHITECTURE.en.md](docs/ARCHITECTURE.en.md)
+- 🛡️ **10 Quality Gates Definition of Done (DoD):** [docs/QUALITY_GATES.en.md](docs/QUALITY_GATES.en.md)
+- 📖 **Comprehensive CLI Command Reference:** [docs/CLI_REFERENCE.en.md](docs/CLI_REFERENCE.en.md)
+- 🚀 **CI/CD Pipeline Integration Playbook:** [docs/CI_CD_INTEGRATION.en.md](docs/CI_CD_INTEGRATION.en.md)
+- 🤝 **Open-Source Contributing Guidelines:** [docs/CONTRIBUTING.en.md](docs/CONTRIBUTING.en.md)

package/README.md

@@ -6,11 +6,11 @@
 
 > **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 — Tự động bắt 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.  
 > **Tác giả:** Thế Vị ([@TeeVee998](https://github.com/TeeVee998)) | **Giấy phép:** MIT License  
-> **Phiên bản:** `v2.9.0` | **Quy mô:** 51 Kỹ năng QA, 6 Vai trò AI Agent, 10 Cổng kiểm định DoD.
+> **Phiên bản:** `v3.0.1` | **Quy mô:** 51 Kỹ năng QA, 6 Vai trò AI Agent, 10 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)
-[![python version](https://img.shields.io/badge/python-%3E%3D3.9-blue.svg?style=flat-square)](https://python.org)
+[![python version](https://img.shields.io/badge/python-%3E%3D3.10-blue.svg?style=flat-square)](https://python.org)
 [![license](https://img.shields.io/badge/license-MIT-green.svg?style=flat-square)](https://github.com/TeeVee998/Synapse-Hub/blob/main/LICENSE)
 [![Ecosystem](https://img.shields.io/badge/AI%20Ecosystem-Antigravity%20%7C%20Cursor%20%7C%20Claude%20%7C%20Copilot%20%7C%20Windsurf-orange.svg?style=flat-square)](#)
 
@@ -113,7 +113,7 @@ Mọi thay đổi mã nguồn kiểm thử đều được kiểm chứng qua 10
 # Pre-commit hook (.pre-commit-config.yaml):
 repos:
   - repo: https://github.com/TeeVee998/Synapse-Hub
-    rev: v3.0.0
+    rev: v3.0.1
     hooks:
       - id: synapse-lint
       - id: synapse-verify

package/action.yml

@@ -28,7 +28,7 @@ runs:
   using: "composite"
   steps:
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v7
       with:
         python-version: "3.10"
 

package/bin/agent-qa.js

@@ -59,8 +59,8 @@ function main() {
     if (process.argv.includes('--first-run')) {
       process.exit(0);
     }
-    console.error(`\n${BOLD}${RED}[ERROR] Python 3.9+ is required to execute synapse-hub tools.${RESET}`);
-    console.error(`Neither ${CYAN}python3${RESET} nor ${CYAN}python${RESET} (>= 3.9) was found on your PATH.`);
+    console.error(`\n${BOLD}${RED}[ERROR] Python 3.10+ is required to execute synapse-hub tools.${RESET}`);
+    console.error(`Neither ${CYAN}python3${RESET} nor ${CYAN}python${RESET} (>= 3.10) was found on your PATH.`);
     console.error(`👉 Please install Python from: ${BOLD}https://www.python.org/downloads/${RESET}\n`);
     process.exit(1);
   }

package/docs/ARCHITECTURE.en.md

@@ -0,0 +1,192 @@
+# Agent-Skills Architecture & Design Principles
+
+[🇻🇳 Tiếng Việt](ARCHITECTURE.md) | [🇬🇧 English Edition](ARCHITECTURE.en.md)
+
+> **Scope:** Enterprise Multi-Agent QA Hub  
+> **Version:** `3.0.1` | **Status:** Active / Production Standard
+
+---
+
+## 1. Hub & Spoke Operating Model
+
+The `agent-skills` repository functions as a centralized **Intelligence Core (Hub)** decoupled from target test repositories (**Spokes**). 
+
+```mermaid
+flowchart TD
+    subgraph Hub["Agent-Skills Hub (Intelligence Core)"]
+        Catalog["51 Standardized Skills (.agents/skills)"]
+        Rules["Core Architectural Rules (.agents/rules)"]
+        Tools["Zero-Token Python Engine (tools/)"]
+        Swarm["6 Specialized Subagents (.agents/agents)"]
+    end
+
+    subgraph Spokes["Target Repositories (Test Suites)"]
+        Repo1["Project A (Playwright / TS)"]
+        Repo2["Project B (Katalon / Groovy)"]
+        Repo3["Project C (Python / Pytest)"]
+    end
+
+    Hub -->|Mounted as Skill Provider| Repo1
+    Hub -->|Mounted as Skill Provider| Repo2
+    Hub -->|Mounted as Skill Provider| Repo3
+```
+
+### Architectural Benefits:
+1. **Zero Context Contagion:** Target project repositories stay clean and focused strictly on test cases and Page Classes, without polluting git trees with heavy AI agent instructions.
+2. **Instant Upgradability:** Improvements to self-healing algorithms, token compressors, and lint rules propagate globally to all target projects instantly.
+3. **Intellectual Property Isolation by Architecture:** Because `agent-skills` is a decoupled, standalone repository, target projects remain 100% clean without requiring complex dual-remote mirroring or `smart_push` scripts. Developers and agents push directly to company SCM for target projects, and to the central hub for skills.
+
+---
+
+## 2. Four-Tier Skill Stratification
+
+The 51 skills in the hub are structured into four progressive operational tiers:
+
+```mermaid
+flowchart LR
+    T1["Tier 1: Core Automation<br/>POM, Live Probing, Repair"] --> T2["Tier 2: Enterprise Quality<br/>WCAG, Visual, Vitals"]
+    T2 --> T3["Tier 3: Context & AI Performance<br/>Token Optimization, Graphify"]
+    T3 --> T4["Tier 4: Architecture & CI/CD<br/>ADR, Sharding, GitHub Actions"]
+```
+
+1. **Tier 1 — Core Automation & Self-Healing:**
+   - Script generation, Clean POM flat architecture, live DOM probing via Playwright MCP, and in-place locator healing.
+2. **Tier 2 — Enterprise Quality Sentinel:**
+   - Accessibility audits (WCAG 2.2), Core Web Vitals profiling, visual regression comparisons, and synthetic data generation.
+3. **Tier 3 — AI Context Engineering & Diagnostics:**
+   - Attention-pattern protection, context degradation countermeasures, token optimization, and AST knowledge graph navigation.
+4. **Tier 4 — Architecture, CI/CD & Delivery:**
+   - Architecture Decision Records (ADRs), code refactoring and technical debt remediation, and containerized GitHub Actions CI/CD pipelines.
+
+---
+
+## 3. Flat Clean POM Architecture Pattern
+
+Test automation scripts orchestrated through this Hub enforce strict Clean POM boundaries:
+
+- **Rule 1 — Zero Selectors in Scripts:** Test scripts (`Scripts/` or `tests/`) must NEVER contain raw XPaths, CSS selectors, or `findTestObject` calls.
+- **Rule 2 — Single Inheritance:** All Page Classes inherit from `BasePage`, which standardizes smart waits, dynamic identifiers, and synthetic event dispatchers.
+- **Rule 3 — Dynamic Test Data Idempotency:** Every data entity must use dynamic prefixes generated via `BasePage.uniqueCode("PREFIX_")` to eliminate database key collisions during parallel execution.
+- **Rule 4 — In-Place Self-Healing:** If an element changes or breaks, only the affected Page Class is updated; test scripts remain untouched.
+
+---
+
+## 4. The 10 Quality Gates Definition-of-Done (DoD)
+
+All automated test code authored, modified, or refactored by AI agents must pass through the deterministic 10 Quality Gates pipeline (`tools/verify_all.py`) prior to committing or merging:
+
+| Gate | Title | Verifier Tool | Strict Acceptance Criteria |
+| :---: | :--- | :--- | :--- |
+| **Gate 0** | **Author Attribution & MIT Provenance** | `author_integrity.py` | Validates immutable MIT license and attribution to original author Thế Vị (@TeeVee998). |
+| **Gate 1** | **UTF-8 No BOM Clean Encoding** | `verify_all.py` | Scans 100% of repository files; zero BOM bytes (`0xEF, 0xBB, 0xBF`) and zero mojibake errors. |
+| **Gate 2** | **Path Portability** | `verify_all.py` | Rejects workstation-specific absolute paths (`/Users/...`, `C:\...`); mandates root-relative resolution. |
+| **Gate 3** | **Clean POM Flat Architecture** | `verify_all.py` | Enforces 100% locator encapsulation in Page Classes; strictly prohibits raw XPaths in test scripts. |
+| **Gate 4** | **AI Docs Anti-Drift** | `lint_ai_docs.py` | Reconciles real AST classes against `PROJECT_AI_GUIDE.md`; eliminates hallucinated PageClasses. |
+| **Gate 5** | **Temporary File Blacklist** | `verify_all.py` | Ensures zero build debris, memory dumps, or temporary sandbox databases leak into version control. |
+| **Gate 6** | **Credential Security** | `verify_all.py` | AST regex scan blocking hardcoded passwords, private keys, and secret tokens in code. |
+| **Gate 7** | **Static Defect & Fake-Pass Sentinel** | `infer_linter.py` | Detects 0-assertion tests, swallowed exception blocks (`except: pass`), hard sleeps, and unawaited promises. |
+| **Gate 8** | **Assertion Sensitivity Sentinel** | `micro_mutator.py` | Syntactic micro-mutations linked via variable dataflow; requires Sensitivity Score $\ge 80\%$. |
+| **Gate 9** | **Tier-2 Skill Routing & Collision Guard** | `skill_collision_guard.py` | Audits skill trigger descriptions and vectors; blocks ambiguous activation with semantic overlap $\ge 0.75$. |
+
+---
+
+## 5. Architectural Boundaries & Non-Goals
+
+To maintain a lightweight, deterministic, and highly portable architecture, Synapse Hub establishes explicit boundaries:
+- **No Proprietary Test Runner:** Does not implement a replacement runner engine. Bridges natively with standard runners (Playwright, Pytest, Katalon/Gradle, Newman, JMeter).
+- **Zero AUT Source Code Modifications:** Operates exclusively within test specifications, Page Object models, mock definitions, and verification gates.
+- **Decoupled Stateless Hub:** Never writes persistent user credentials or proprietary corporate data to git.
+- **Target Language Agnostic:** Leverages Universal Intermediate Representation (Universal IR) to bridge TypeScript, Python, Groovy, and Java seamlessly.
+
+The Hub equips 6 specialized subagents with scoped tool and skill permissions:
+
+| Subagent Role | Primary Focus | Allowed Skills | Execution Tools |
+| :--- | :--- | :--- | :--- |
+| **`orchestrator`** | Task decomposition & governance | `agent-orchestration-multi-agent-optimize`, `graphify-impact-analyzer`, `architecture-decision-records`, `token-and-context-optimizer`, `actor-qa-swarm`, `event-stream-qa-orchestrator`, `qa-memory-os`, `tot-exploratory-testing`, `review-spec` | `verify_all.py`, `test_impact.py`, `setup_project.py`, `interview_story.py`, `dspy_qa_signatures.py`, `autogen_qa_broker.py`, `qa_event_stream.py`, `test_memory_os.py`, `tot_exploratory_tester.py`, `watch_mode.py`, `dashboard_generator.py` |
+| **`pom-crafter`** | Clean POM design & test generation | `clean-pom-crafter`, `lam-script-generator`, `synthetic-test-data-generator`, `api-spec-to-e2e-matrix`, `gherkin-to-suite`, `mipro-prompt-compiler`, `qa-aci-interface` | `lookup_xpath.py`, `repo_map.py`, `generate_tc_from_story.py`, `skill_vault.py`, `gherkin_suite.py`, `swe_qa_aci.py`, `mipro_assertion_tuner.py`, `api_fuzzer.py`, `export_postman_collection.py` |
+| **`live-explorer`** | Live DOM & AOM exploration (<200ms) | `playwright-live-interaction`, `self-healing-locator`, `visual-regression-sentinel`, `api-network-mocking-interception` | `browser_helpers.js`, `e2e_flow_prober.ps1`, `safety_firewall.py` |
+| **`test-runner`** | Headless CLI test execution & CI | `katalon-cli-runner`, `e2e-testing-patterns`, `flaky-test-sentinel-and-quarantine`, `backend-load-and-stress-patterns`, `github-actions-templates` | `matrix_sharder.py`, `distill_log.py`, `pinpoint_failure.py`, `flaky_detector.py`, `reversible_sandbox.py`, `generate_jmx_plan.py`, `jtl_analyzer.py`, `newman_analyzer.py`, `traffic_session_converter.py`, `db_sandbox.py` |
+| **`failure-analyst`**| Visual & XML error autopsy | `failure-autopsy-and-healing`, `self-healing-locator`, `file-and-report-validator`, `systematic-debugging`, `agentless-qa-repair` | `auto_heal.py`, `heal_pr_automator.py`, `pinpoint_failure.py`, `cache_resolver.py`, `auto_heal_reflexion.py`, `agentless_patcher.py`, `heuristic_locator_matcher.py`, `telemetry_correlator.py` |
+| **`quality-gatekeeper`**| 10 Gates DoD & Fake-Pass Sentinel | `antigravity-test-sentinel`, `code-refactoring-refactor-clean`, `wcag-audit-patterns`, `web-vitals-and-performance-profiler`, `security-dast-sentinel`, `lean-impact-scoreboard`, `web-agent-gym-benchmarking` | `verify_all.py`, `infer_linter.py`, `micro_mutator.py`, `trace_data_flow.py`, `skill_collision_guard.py`, `textgrad_mutation_optimizer.py`, `skillspector.py`, `author_integrity.py`, `browsergym_eval.py` |
+
+### 5.1 Standalone CLI Utilities & Hub Infrastructure Tools (Non-Persona Scoped)
+
+The remaining 7 tools serve as global repository entry points and offline infrastructure services, callable directly without subagent persona routing:
+- `cli.py`: Central Agent-QA / Synapse CLI command router and entrypoint (`npx synapse-hub` / `agent-qa`).
+- `output_formatter.py`: ANSI terminal color styling, status badges, and table formatting utility.
+- `welcome_page.py`: Visual HTML onboarding and landing page generator (`agent-qa welcome`).
+- `bump_version.py`: Atomic polyglot semantic version bumper for releases (`agent-qa bump`).
+- `sync_agent_rules.py`: Universal AI bridge synchronization engine (Cursor, Claude Code, Copilot, Windsurf).
+- `md_to_xlsx.py`: Standalone Markdown to Excel converter utility (`agent-qa md-to-xlsx`).
+- `mcp_excel_server.py`: Model Context Protocol (MCP) offline Excel spreadsheet server.
+
+---
+
+## 6. Nomenclature & Package Architecture
+
+To ensure consistency across various distribution registries and developer interfaces:
+- **Ecosystem / Project Name:** Synapse Hub (`Synapse-Hub` on GitHub)
+- **NPM Package & Antigravity Plugin:** `synapse-hub` (distributed on NPM Registry and Antigravity Marketplace)
+- **Python Package & Universal CLI:** `agent-qa` (PEP 621 package on PyPI providing the `agent-qa` CLI binary)
+- **MCP Server Protocol Services:** `enterprise-agent-qa` (Core QA MCP server) and `synapse-mcp-excel` (Excel tool server)
+- **Skill Catalog Manifest:** `enterprise-agent-skills-hub` (internal catalog schema identifier in `skills_manifest.json`) and `agentskills.json` (AgentSkills v1 open standard)
+
+---
+
+## 7. Autonomous Agent Self-Evolution & Training Subsystems
+
+To elevate AI testing beyond static prompt engineering, Synapse Hub incorporates 6 advanced agent training, compilation, and self-evolution mechanisms synthesized from modern agentic architectures:
+
+```mermaid
+flowchart TD
+    subgraph SelfEvolution["Autonomous Agent Self-Evolution Subsystem"]
+        Vault["<b>Voyager Lifelong Vault</b><br/>(skill_vault.py)<br/>• Verified PageClass SQLite memory<br/>• Zero repetitive prompt re-synthesis"]
+        Reflexion["<b>Episodic Reflexion Loop</b><br/>(auto_heal_reflexion.py)<br/>• K=3 trial-feedback learning<br/>• Self-healing without git pollution"]
+        DSPy["<b>DSPy Declarative QA Engine</b><br/>(dspy_qa_signatures.py)<br/>• Typed QA signatures<br/>• Eliminates brittle prompt hacking"]
+        TextGrad["<b>TextGrad Mutation Loss</b><br/>(textgrad_mutation_optimizer.py)<br/>• AST mutants as loss function<br/>• Optimizes assertions to score &ge; 80%"]
+        Reversible["<b>GoEx Reversible Sandbox</b><br/>(reversible_sandbox.py)<br/>• LIFO undo execution stack<br/>• Zero leftover test debris"]
+        Bench["<b>Gorilla BFCL Benchmark</b><br/>(synapse_qa_bench.py)<br/>• Evaluates function calling fidelity<br/>• Prevents agent regression"]
+    end
+
+    Vault --> DSPy --> TextGrad --> Reversible --> Reflexion --> Bench
+```
+
+1. **Lifelong Skill Memory (`skill_vault.py`):** Inspired by Voyager, stores verified POM methods and complex interaction patterns in permanent SQLite memory, growing the agent's capability with every run.
+2. **Episodic Trial-Feedback (`auto_heal_reflexion.py`):** Implements Noah Shinn's Reflexion framework, enabling agents to evaluate test failure traces across $K=3$ iterations, generating textual self-reflection to correct locator strategies.
+3. **Declarative Signature Compilation (`dspy_qa_signatures.py`):** Adheres to Stanford DSPy principles, compiling prompt templates into structured, typed input-output signatures.
+4. **Mutant-Directed Loss Optimization (`textgrad_mutation_optimizer.py`):** Treats surviving AST mutants as a loss function (TextGrad), iteratively refining assertion logic until all mutants are killed.
+5. **Reversible Execution Teardown (`reversible_sandbox.py`):** Implements GoEx-style reversible rollback stacks for filesystem and database mutations during automated exploratory runs.
+6. **Tool Function Calling Benchmark (`synapse_qa_bench.py`):** Implements Berkeley Function-Calling Leaderboard (BFCL) standards for enterprise QA tools, benchmarking tool selection precision and multi-turn execution accuracy.
+
+---
+
+## 8. Comparative Analysis & Industry Positioning
+
+| Evaluation Criteria / Solution | ESLint Plugin (Playwright) | Stryker Mutator | Allure Report | Healenium | Synapse Hub 🧠 |
+| :--- | :---: | :---: | :---: | :---: | :---: |
+| **Language & Framework Scope** | Only JS / TS | JS / TS, C#, Scala | Any language (XML ingest) | Java / Python / C# (Selenium) | **Polyglot** (TS/JS, Python, Groovy, Java) |
+| **Deep Agent Context Integration** | ❌ (CLI/IDE lint only) | ❌ (Standalone tool) | ❌ (Post-test visualizer) | ❌ (JVM proxy server) | ✅ **Native** (Rules, MCP, AST Map, 6 Subagents) |
+| **AI Fake-Pass Elimination** | ⚠️ Syntax lint only | ❌ (App code mutations only) | ❌ | ❌ | ✅ **Specialized** (0-assert detection, swallowed exceptions, tautology) |
+| **Mutation Testing Speed** | N/A | ⏱️ Minutes to hours | N/A | N/A | ⚡ **Ultra-fast (~0.1s)** static heuristic assertion sensitivity scan |
+| **Locator Self-Healing** | ❌ | ❌ | ❌ | ⚠️ Requires JVM server + Docker | ⚡ **Lightweight (< 500 tokens)** AOM diffing inside agent loop |
+| **Token & Log Distillation** | ❌ | ❌ | ❌ | ❌ | ✅ **Reduces 95%** log noise (`distill_log.py`, `repo_map.py`) |
+| **Clean POM Architectural Guard** | ❌ | ❌ | ❌ | ❌ | ✅ **Strict enforcement**, Clean POM Flat Architecture |
+
+---
+
+## 9. Known Technical Limitations & Empirical Benchmarks
+
+To maintain strict engineering rigor (**Truth Anchor**), Synapse Hub discloses all known technical boundaries:
+
+1. **Static Heuristic Mutation Testing vs Runtime Mutation Testing:**  
+   `tools/micro_mutator.py` in static mode performs fast heuristic assertion reachability analysis (~0.1s) to detect unasserted branches and weak assertions. This is a lexical reachability and dataflow heuristic, **not** a compiler-grade runtime mutation testing engine (such as Stryker or mutmut). To avoid inflated assertion scores and obtain ground-truth mutation kill rates, execute in Dynamic mode (`--test-cmd`) against real test runners.
+2. **Empirical Benchmarks (Self-Reported Baseline):**  
+   The metrics (25/25 challenges resolved, 76.2 tokens/bug) reflect author-measured internal baselines on curated challenges (`benchmarks/qa_eval`) rather than independent third-party double-blind audits. Metrics may vary on real-world enterprise suites depending on architectural complexity and test coverage.
+3. **Hub-Spoke Version Pinning (Blast-Radius Isolation):**  
+   When mounting or referencing Synapse Hub in downstream Spoke projects, downstream repositories should pin a specific Git Submodule commit or release tag (`git checkout v3.0.0`) rather than tracking unpinned `main` HEAD, preventing upstream Hub changes from unexpectedly breaking downstream CI/CD pipelines.
+4. **Supported Runners:**  
+   First-class runner adapters for **Playwright, Pytest, Katalon Studio/Groovy, and Cypress**. Selenium WebDriver is supported via Clean POM architecture patterns, smart-wait primitives, and Universal IR transpilation.
+5. **Environment Prerequisites:**  
+   - Node.js >= 18.0.0 (Node.js 20 or 22 LTS recommended).
+   - Python >= 3.10 (fully tested on 3.10, 3.11, 3.12, 3.13, 3.15).
+   - Headless browser: Playwright Chromium required for live DOM/AOM probing and self-healing locators.