synapse-hub 2.2.3 → 2.4.0

package/.agents/skills/web-vitals-and-performance-profiler/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: web-vitals-and-performance-profiler
-description: "Measure Core Web Vitals (LCP, CLS, INP) and network waterfalls via CDP."
+description: "Measure Core Web Vitals (LCP, CLS, INP) and network waterfalls via CDP. Use when the user asks why a page is slow or needs CWV budgets enforced in CI."
 ---
 
 # Web Vitals & Performance Profiler Skill

package/.agents/skills/web-vitals-and-performance-profiler/examples/cwv_budget_policy.json

@@ -0,0 +1,6 @@
+{
+  "LCP_ms": 2500,
+  "CLS_score": 0.1,
+  "INP_ms": 200,
+  "networkThrottle": "Fast 3G"
+}

package/.agents/templates/completion_report.md

@@ -1,57 +1,57 @@
-# AI SESSION COMPLETION REPORT TEMPLATE
-
-> **Instructions:** Use this standardized schema at the conclusion of every AI working session to ensure auditability, cross-session comparability, and historical accuracy.
-
----
-
-## 1. Session Metadata
-- **Date & Time:** `YYYY-MM-DD HH:mm`
-- **Agent / Engineer:** `Antigravity / Claude Code / Cursor / QA Engineer`
-- **Target Functional Module:** `[e.g., User Administration & RBAC]`
-- **Master Test Suite / Test Cases:** `[e.g., Group_07_01_CumCongNghiep.ts / TC-123 to TC-135]`
-
----
-
-## 2. Test Execution Evidence
-- **Exit Code:** `0 (PASS) / 1 (FAIL)`
-- **Total Test Cases:** `[Count]`
-  - ✅ **Passed:** `[Count]`
-  - ❌ **Failed:** `[Count]`
-- **Detailed Execution Artifacts:**
-  - Allure / Katalon Report: `Reports/<Timestamp>/...`
-  - Verified UI Assertions & Toasts: `[e.g., "Created successfully" (NFC Normalized)]`
-
----
-
-## 3. Truth Anchor & Defect Findings
-*(Select exactly one option below)*
-- [ ] **No Defects Discovered:** All scripts passed cleanly; business workflows operate strictly as specified.
-- [ ] **Real AUT Defect Identified:**
-  - Defect Description / Test Case: `[e.g., TC-123 - GIS polygon coordinate collision on save]`
-  - Logged into: `KNOWN_ISSUES.md` (Issue ID: `ISSUE-AUT-xx`)
-  - Commitment: **Assertions remained strict; no fake pass applied.**
-
----
-
-## 4. File Changes Breakdown
-| Action | File Path | Purpose & Technical Summary |
-|---|---|---|
-| **Added** | `[File Path]` | `[Reason for addition]` |
-| **Modified** | `[File Path]` | `[Summary of modification]` |
-| **Deleted** | `[File Path]` | `[Reason for removal]` |
-
----
-
-## 5. Quality Gate Enforcement (Definition of Done)
-- [x] **100% UTF-8 No BOM:** Verified (`tools/git_pre_commit_guard.py`)
-- [x] **Zero Raw XPaths in Scripts:** Verified (Strict Clean POM adherence)
-- [x] **Path Portability:** Verified (Zero local absolute machine paths)
-- [x] **AI Docs Anti-Drift Linter:** Verified (`tools/lint_ai_docs.py` v2.0 passed)
-- [x] **Temporary File Blacklist:** Verified (Temporary `.properties` cleaned)
-- [x] **Credential Security:** Verified (No plaintext passwords; `APP_PASSWORD` injected)
-
----
-
-## 6. Handoff & Memory Synchronization
-- [x] Updated `PROJECT_STATE.md` with latest operational state.
-- [ ] **Next Immediate Actions:** `[Concise instructions for the next agent session]`
+# AI SESSION COMPLETION REPORT TEMPLATE
+
+> **Instructions:** Use this standardized schema at the conclusion of every AI working session to ensure auditability, cross-session comparability, and historical accuracy.
+
+---
+
+## 1. Session Metadata
+- **Date & Time:** `YYYY-MM-DD HH:mm`
+- **Agent / Engineer:** `Antigravity / Claude Code / Cursor / QA Engineer`
+- **Target Functional Module:** `[e.g., User Administration & RBAC]`
+- **Master Test Suite / Test Cases:** `[e.g., Group_07_01_CumCongNghiep.ts / TC-123 to TC-135]`
+
+---
+
+## 2. Test Execution Evidence
+- **Exit Code:** `0 (PASS) / 1 (FAIL)`
+- **Total Test Cases:** `[Count]`
+  - ✅ **Passed:** `[Count]`
+  - ❌ **Failed:** `[Count]`
+- **Detailed Execution Artifacts:**
+  - Allure / Katalon Report: `Reports/<Timestamp>/...`
+  - Verified UI Assertions & Toasts: `[e.g., "Created successfully" (NFC Normalized)]`
+
+---
+
+## 3. Truth Anchor & Defect Findings
+*(Select exactly one option below)*
+- [ ] **No Defects Discovered:** All scripts passed cleanly; business workflows operate strictly as specified.
+- [ ] **Real AUT Defect Identified:**
+  - Defect Description / Test Case: `[e.g., TC-123 - GIS polygon coordinate collision on save]`
+  - Logged into: `KNOWN_ISSUES.md` (Issue ID: `ISSUE-AUT-xx`)
+  - Commitment: **Assertions remained strict; no fake pass applied.**
+
+---
+
+## 4. File Changes Breakdown
+| Action | File Path | Purpose & Technical Summary |
+|---|---|---|
+| **Added** | `[File Path]` | `[Reason for addition]` |
+| **Modified** | `[File Path]` | `[Summary of modification]` |
+| **Deleted** | `[File Path]` | `[Reason for removal]` |
+
+---
+
+## 5. Quality Gate Enforcement (Definition of Done)
+- [x] **100% UTF-8 No BOM:** Verified (`tools/git_pre_commit_guard.py`)
+- [x] **Zero Raw XPaths in Scripts:** Verified (Strict Clean POM adherence)
+- [x] **Path Portability:** Verified (Zero local absolute machine paths)
+- [x] **AI Docs Anti-Drift Linter:** Verified (`tools/lint_ai_docs.py` v2.0 passed)
+- [x] **Temporary File Blacklist:** Verified (Temporary `.properties` cleaned)
+- [x] **Credential Security:** Verified (No plaintext passwords; `APP_PASSWORD` injected)
+
+---
+
+## 6. Handoff & Memory Synchronization
+- [x] Updated `PROJECT_STATE.md` with latest operational state.
+- [ ] **Next Immediate Actions:** `[Concise instructions for the next agent session]`

package/.agents/workflows/analyze_requirement_document.md

@@ -0,0 +1,18 @@
+---
+description: Perform automated Ambiguity Analysis, Gap Detection, and Boundary Verification on Business Requirements Documents (BRD, PRD, User Stories).
+skills:
+  - rbt-manual-testing
+---
+
+# /analyze_requirement_document — Requirement Ambiguity & Gap Analysis
+
+Scans and audits functional specifications, user stories, or PRDs to detect defects, contradictions, and missing edge cases early in the lifecycle.
+
+---
+
+## 4-Step Analysis Pipeline
+
+1. **Happy Path & Flow Extraction:** Extract primary user journeys and business outcomes.
+2. **Ambiguity Detection:** Identify vague phrases ("fast response", "system should handle errors", "user-friendly"), unstated timeout intervals, unhandled edge conditions, and conflicting rules.
+3. **Gap Analysis:** Highlight missing alternate paths, unauthorized user flows, data volume constraints, and concurrency scenarios.
+4. **Numbered Q&A Register:** Generate an actionable register of questions (`Q1, Q2, Q3...`) with context and proposed default assumptions for product owner / BA sign-off.

package/.agents/workflows/export_testcases_excel.md

@@ -0,0 +1,32 @@
+---
+description: Convert a Markdown Test Case table into a corporate-styled, formatted Excel spreadsheet (.xlsx) using the native tools/md_to_xlsx.py engine.
+skills:
+  - rbt-manual-testing
+---
+
+# /export_testcases_excel — Markdown to Styled Excel Converter
+
+Converts any Markdown Test Case document or artifact into an enterprise-ready, professional Excel workbook (`.xlsx`) using the native Python openpyxl engine.
+
+---
+
+## Execution Command
+
+```bash
+# Export with default name (input.xlsx)
+agent-qa export-excel path/to/test_cases.md
+
+# Export with custom destination and worksheet title
+agent-qa export-excel path/to/test_cases.md -o output_name.xlsx --sheet-name "Regression Suite"
+```
+
+## Features of Exported Workbooks
+
+- **Navy Blue Header:** Dark blue fill (`#1F4E78`), bold white text, vertically centered.
+- **Frozen Header:** Top row frozen (`A2`) for continuous scrolling.
+- **AutoFilter:** Filter dropdowns automatically enabled on all columns.
+- **Color-Coded Status Badges:**
+  - `Risk Level`: High (Soft Red), Medium (Soft Yellow), Low (Soft Green).
+  - `Priority`: Critical/High (Soft Red/Orange), Medium (Soft Yellow), Low (Soft Green).
+  - `Automatable`: Yes (Soft Green), Partial (Soft Yellow), No (Soft Gray).
+- **Auto-Formatting:** Multi-line `<br>` tags converted to true Excel newlines with text wrapping and optimized column widths.

package/.agents/workflows/generate_combinatorial_test_data.md

@@ -0,0 +1,28 @@
+---
+description: Generate concrete combinatorial test data sets (JSON, CSV, Markdown) covering all parameter combinations from a cross-module dimension matrix or Pairwise specification.
+skills:
+  - synthetic-test-data-generator
+---
+
+# /generate_combinatorial_test_data — Combinatorial Test Data Synthesis
+
+Converts an abstract dimension matrix or Pairwise specification into concrete, idempotent synthetic test data fixtures ready for automation or manual execution.
+
+---
+
+## 1. Input Requirements
+
+Provide either:
+- A Markdown table of dimensions/values from `/generate_cross_module_test_plan`.
+- A list of parameters with allowed values, boundaries, and negative test values.
+
+---
+
+## 2. Output Modes
+
+1. **GENERATE Mode (File Export):**
+   - Synthesizes formatted data records in JSON, CSV, or Markdown.
+   - Enforces unique dynamic prefixes (`AUTO_<timestamp>`) to prevent database unique-constraint collisions.
+2. **PIPELINE Mode (Live Seeding):**
+   - Dispatches browser actions or API seeders (`tools/db_sandbox.py`) to create records directly in the target environment.
+   - Automatically pairs each creation step with a teardown cleanup action.

package/.agents/workflows/generate_cross_module_test_plan.md

@@ -0,0 +1,37 @@
+---
+description: Analyze end-to-end user journeys traversing multiple interconnected modules, construct Data Flow Diagrams, and generate optimized Pairwise (All-Pairs) combinatorial test matrices.
+skills:
+  - clean-pom-crafter
+  - e2e-testing-patterns
+  - synthetic-test-data-generator
+---
+
+# /generate_cross_module_test_plan — Cross-Module Analysis & Pairwise Matrix
+
+Use this workflow when a business feature spans across multiple sequential modules, where each module has distinct option dimensions and combinatorial outputs determine the final result.
+
+---
+
+## 1. Operational Modes
+
+- **DOCUMENT Mode (Default):** Ingests functional specifications, user journey maps, or architecture documents.
+- **BROWSER Mode:** Probes the live web application using headless Playwright to discover sequential UI modules and input dimensions.
+
+---
+
+## 2. Execution Pipeline
+
+### Step 1: Sequential Module Mapping & Data Flow
+1. Map the end-to-end workflow chain (e.g., Module 1: Customer Profile -> Module 2: Billing & Currency -> Module 3: Tax Profile -> Module 4: Invoice Generation).
+2. Generate a Mermaid Data Flow Diagram illustrating data dependencies between modules.
+
+### Step 2: Dimension Catalog & Constraints Extraction
+1. List all configurable dimensions and allowed values per module.
+2. Identify mutual exclusions, invalid business combinations, and hard constraints.
+
+### Step 3: Combinatorial Matrix Synthesis (Pairwise / All-Pairs)
+1. Apply **Pairwise Testing (All-Pairs)** reduction to compress multi-dimensional exponential combinations (e.g., reduce $3 \times 4 \times 3 \times 2 \times 4 = 288$ combinations down to ~20-25 optimal test sets covering 100% of two-way interactions).
+2. Format the output matrix with columns: `#`, `Module 1`, `Module 2`, ..., `Expected Result`, `Priority`.
+
+### Step 4: Verification Checkpoint
+- Present the reduced Pairwise Matrix to the user for validation and sign-off before test case or test data synthesis.

package/.agents/workflows/generate_manual_testcases_rbt.md

@@ -0,0 +1,56 @@
+---
+description: Generate comprehensive manual test cases using the 6-stage AI-RBT (Risk-Based Testing) methodology with ambiguity checkpoints and 15-field validation checklist.
+skills:
+  - rbt-manual-testing
+---
+
+# /generate_manual_testcases_rbt — 6-Stage AI-RBT Manual Test Generation
+
+Execute the structured 6-stage **AI-Driven Risk-Based Testing (AI-RBT)** pipeline defined in `.agents/skills/rbt-manual-testing/SKILL.md`.
+
+## Execution Rules & Pipeline Checkpoints
+
+- **Execution Mode:** FULL RBT (strictly sequential, never combine stages in a single pass).
+- **Mandatory Checkpoints:** The agent **MUST PAUSE** for user feedback at:
+  - **Stage 2 Checkpoint:** Present numbered Ambiguity Q&A (`Q1, Q2...`) with assumptions, and wait for confirmation.
+  - **Stage 4 Checkpoint:** Present Traceability Matrix (RTM) and High-Level Scenarios for user review.
+
+---
+
+## 6-Stage Pipeline Steps
+
+### Stage 1: Context & Framing
+1. Ingest project description, business domain, target persona, and release milestones (MVP vs Full).
+2. Confirm understanding and proceed to Stage 2.
+
+### Stage 2: Analysis & Ambiguity Q&A
+1. Map Happy Paths, Alternate Paths, and Exception Paths.
+2. Identify requirement ambiguities, contradictions, or missing validation rules.
+3. Emit a structured Q&A table (`Q1, Q2...`) with proposed assumptions.
+4. 🛑 **PAUSE — Await user confirmation before proceeding.**
+
+### Stage 3: System Decomposition
+1. Break down features into Modules -> Sub-modules -> UI components.
+2. Document cross-module dependencies and shared state.
+
+### Stage 4: Traceability Matrix (RTM) & Gap Analysis
+1. Map requirement identifiers (`REQ-xxx`) to high-level test scenarios.
+2. Highlight missing coverage gaps and non-functional scenarios.
+3. 🛑 **PAUSE — Await user review of scenario coverage.**
+
+### Stage 5: Detailed Test Case Generation & Risk Scoring
+1. Assign Risk Levels (`High`, `Medium`, `Low`) based on business impact.
+2. Apply test design techniques: Equivalence Partitioning (EP), Boundary Value Analysis (BVA), Decision Tables, State Transitions.
+3. Apply the **Field-Level Validation Checklist (15 Field Types)**: generate isolated validation test cases for each input field (do not merge fields).
+4. Include non-functional scenarios: Double Submit, Race Conditions, Network Drops, Browser Back/Refresh.
+
+### Stage 6: Template Mapping & Deliverable Packaging
+1. Assemble all test cases into the standard 12-column Markdown specification:
+   ```markdown
+   | TC ID | Module | Risk Level | Test Title | Pre-Condition | Test Steps | Expected Result | Priority | Test Data | Automatable | Auto Type | Tags |
+   ```
+2. Verify all test cases from Stage 5 are preserved without truncation.
+3. Inform user they can export to styled Excel via:
+   ```bash
+   agent-qa export-excel path/to/test_cases.md -o output.xlsx
+   ```

package/.agents/workflows/generate_requirements_from_website.md

@@ -0,0 +1,25 @@
+---
+description: Reverse-engineer structured functional requirements and user story specifications by inspecting a live web application using headless Playwright.
+skills:
+  - playwright-live-interaction
+  - clean-pom-crafter
+---
+
+# /generate_requirements_from_website — Live Web Reverse-Engineering
+
+Reverse-engineers functional requirements, acceptance criteria, and input field rules directly from a deployed web application when written specifications are missing or outdated.
+
+---
+
+## Execution Pipeline
+
+1. **Target Navigation:** Launch headless Playwright session at 1920x1080 and navigate to the target URL.
+2. **Compact AOM Survey:** Extract the interactive Accessibility Tree (`qa.getCompactAOM()`) to discover forms, controls, roles, and validation messages.
+3. **Behavioral Probing:**
+   - Probe required fields by triggering empty form submissions.
+   - Inspect client-side HTML5 validation attributes (`pattern`, `min`, `max`, `maxlength`, `required`).
+   - Identify active dropdown choices and conditional UI toggles.
+4. **Structured Requirements Document:** Output a structured Markdown specification with:
+   - Feature summary and business objective.
+   - User Stories with Gherkin Acceptance Criteria (`Given-When-Then`).
+   - Field Specification Table: Name, Type, Required, Format Rules, Min/Max Limits, Error Messages.

package/.agents/workflows/generate_testcases_from_requirements.md

@@ -0,0 +1,21 @@
+---
+description: Fast single-pass generation of structured manual test cases directly from requirements or user stories (QUICK Mode of rbt-manual-testing).
+skills:
+  - rbt-manual-testing
+---
+
+# /generate_testcases_from_requirements — Rapid Single-Pass Test Generation
+
+Generates structured test cases in a single pass without pausing for multi-stage checkpoints. Best for isolated forms, standalone dialogs, or well-defined user stories.
+
+## Workflow Pipeline
+
+1. **Ingest Requirements:** Read the provided requirement text, user story, or acceptance criteria.
+2. **Path Identification:** Map Happy Paths, Negative Paths, and Boundary Value scenarios.
+3. **Field Validation:** Identify all form input fields and apply the **15-Field Validation Checklist** from `rbt-manual-testing`:
+   - Text, Email, Phone, Password, Number, Date, Date Range, Dropdown, Multi-Select, Checkbox/Radio, Textarea, File Upload, OTP/MFA, Range Slider, Rich Text.
+4. **Standard 12-Column Output:** Emit complete test cases formatted in the standard Markdown table with automation metadata (`Automatable`, `Auto Type`, `@Tags`).
+5. **Excel Export Command:** Recommend the user convert the markdown table to Excel via:
+   ```bash
+   agent-qa export-excel path/to/cases.md -o cases.xlsx
+   ```

package/.agents/workflows/graphify.md

@@ -1,10 +1,10 @@
----
-name: graphify
-description: Turn any folder of files into a navigable knowledge graph
----
-
-# Workflow: graphify
-
-Follow the graphify skill to run the full pipeline.
-
-If no path argument is given, use `.` (current directory).
+---
+name: graphify
+description: Turn any folder of files into a navigable knowledge graph
+---
+
+# Workflow: graphify
+
+Follow the graphify skill to run the full pipeline.
+
+If no path argument is given, use `.` (current directory).

package/.agents/workflows/verify.md

@@ -1,6 +1,6 @@
 ---
 name: verify
-description: Execute 8 Quality Gates to verify complete codebase integrity and enforce deterministic safety boundaries before handoff.
+description: Execute 9 Quality Gates to verify complete codebase integrity and enforce deterministic safety boundaries before handoff.
 trigger: /verify
 ---
 
@@ -21,7 +21,7 @@ python tools/safety_firewall.py --code "page.click('<selector>')" --dry-run
 ---
 
 ## 2. Hard Quality Gates Verification (8 DoD Gates)
-Execute all 8 Quality Gates (UTF-8 No BOM, Path Portability, Clean POM, AI Docs Linter, Cleanup Blacklist, Credential Security, Infer Linter, and AST Micro-Mutation Testing):
+Execute all 9 Quality Gates (Author Attribution, UTF-8 No BOM, Path Portability, Clean POM, AI Docs Linter, Cleanup Blacklist, Credential Security, Infer Linter, and Syntactic Micro-Mutation Testing):
 
 ```bash
 python tools/verify_all.py

package/.cursor/rules/language.mdc

@@ -1,7 +1,7 @@
----
-description: Always respond in Vietnamese.
-globs:
-alwaysApply: true
----
-
-Please always respond in Vietnamese.
+---
+description: Always respond in Vietnamese.
+globs:
+alwaysApply: true
+---
+
+Please always respond in Vietnamese.

package/.cursor/rules/synapse-qa.mdc

@@ -0,0 +1,23 @@
+---
+description: Synapse-Hub Enterprise QA Automation & Testing Rules
+globs: **/*
+---
+
+<!-- ============================================================================== -->
+<!-- AUTO-GENERATED FROM AGENTS.md — DO NOT EDIT DIRECTLY.                          -->
+<!-- Run: python3 tools/sync_agent_rules.py                                          -->
+<!-- ============================================================================== -->
+
+
+# Synapse-Hub QA Automation Rules for Cursor IDE
+
+## Mandatory Author Attribution
+This project incorporates Synapse Hub created by Thế Vị (@TeeVee998) under the MIT License.
+Attribution notices must be preserved.
+
+## Core Rules
+1. **Clean POM Architecture:** No raw selectors (XPath/CSS) in test scripts. All selectors belong in Page Classes extending BasePage.
+2. **Truth Anchor:** Never fake test passes. Report genuine defects.
+3. **Smart Wait:** Prohibit static delays (`Thread.sleep`). Use dynamic smart waits.
+4. **Idempotent Test Data:** Prefix with `AUTO_` and dynamic timestamps; teardown after creation.
+5. **Bilingual Discipline:** Converse in Vietnamese; write code and git commits strictly in English.

package/.cursorrules

@@ -2,6 +2,12 @@
 # Author & Creator: Thế Vị (@TeeVee998) <https://github.com/TeeVee998/Synapse-Hub>
 # License: MIT License (Mandatory Attribution Preservation)
 
+# ==============================================================================
+# AUTO-GENERATED FROM AGENTS.md — DO NOT EDIT DIRECTLY.
+# Run: python3 tools/sync_agent_rules.py
+# ==============================================================================
+
+
 # ==============================================================================
 # AUTHOR ATTRIBUTION & OPEN SOURCE LICENSING GUARD
 # ==============================================================================
@@ -14,6 +20,7 @@
 # ==============================================================================
 
 - Always read and follow AGENTS.md for operating standards.
+- Communicate with the user in Vietnamese; avoid unnecessary technical jargon overload ("don't be too tech"). All code, tests, and docs stay in English.
 - Enforce Clean POM Flat Architecture: all locators encapsulated in Page Classes.
 - Zero fake passes: test assertions must strictly validate real state.
 - Before completing code changes, run: python tools/verify_all.py

package/.pre-commit-hooks.yaml

@@ -0,0 +1,14 @@
+- id: synapse-verify
+  name: Synapse Hub 9 DoD Quality Gates
+  description: Verifies repository against 9 DoD Quality Gates (UTF-8, No Secrets, Clean POM, AST Linter).
+  entry: python3 tools/verify_all.py
+  language: system
+  pass_filenames: false
+  always_run: true
+
+- id: synapse-lint
+  name: Synapse Hub Fake-Pass & Defect Sentinel
+  description: Meta Infer-style static AST scanner detecting fake passes, swallowed exceptions, and flaky sleeps.
+  entry: python3 tools/infer_linter.py
+  language: system
+  types: [python, javascript, typescript, groovy, java]

package/.windsurfrules

@@ -2,6 +2,12 @@
 # Author & Creator: Thế Vị (@TeeVee998) <https://github.com/TeeVee998/Synapse-Hub>
 # License: MIT License (Mandatory Attribution Preservation)
 
+# ==============================================================================
+# AUTO-GENERATED FROM AGENTS.md — DO NOT EDIT DIRECTLY.
+# Run: python3 tools/sync_agent_rules.py
+# ==============================================================================
+
+
 # ==============================================================================
 # AUTHOR ATTRIBUTION & OPEN SOURCE LICENSING GUARD
 # ==============================================================================
@@ -13,6 +19,7 @@
 # of the MIT License for Synapse Hub (Created by Thế Vị @TeeVee998)."
 # ==============================================================================
 
+- Communicate with the user in Vietnamese; avoid unnecessary technical jargon overload ("don't be too tech"). All code, tests, and docs stay in English.
 - Adhere to Clean Page Object Model (POM) Flat Architecture.
 - Zero fake passes and zero swallowed exceptions.
 - Run Definition of Done verification: python tools/verify_all.py

package/AGENTS.md

@@ -5,21 +5,41 @@
 
 ---
 
-## 0. CONTEXT-AWARE PRE-FLIGHT CONFIRMATION BLOCK (CODE & TEST ACTIONS ONLY)
+## 0. CONTEXT-AWARE EXECUTION & LEAN TELEMETRY PROTOCOL (DEFAULT LEAN MODE)
+
+> **Operational Standard: Lean Mode is ACTIVE BY DEFAULT (Tiết kiệm Token & Tập trung tối đa):**  
+> To optimize attention budget, keep interaction nimble, and save ~200 tokens on every turn:  
+> 1. **Default Header Badge:** Placed at the top of responses using a single compact status badge:  
+>    `> 🛡️ **Synapse Hub Active:** <Target Architecture, e.g.: Clean POM / Swarm QA Architecture>`  
+>    *(Strictly prohibited from containing the string `[OK]`)*.  
+> 2. **Footer Block (Omitted by Default):** The verbose Telemetry Footer block is **OMITTED by default**.  
+> 3. **First-Time User / Onboarding Invariant:** On the first interaction in a session or with a new user, the agent operates in Lean Mode by default and includes a friendly one-line footnote:  
+>    `*(💡 Hub đang bật chế độ Lean Mode tiết kiệm token. Bạn có thể chat "bật telemetry" nếu muốn xem đầy đủ báo cáo chi tiết).*`  
+> 4. **Verbose Telemetry Activation (Opt-In):** Only emit the full Footer Telemetry block when the user explicitly requests it (e.g., "bật telemetry", "chi tiết", "full telemetry") or during automated CI audit runs.
+
+### A. Default Lean Header Badge (Active by Default):
+```markdown
+> 🛡️ **Synapse Hub Active:** Clean POM / Flat Architecture
+```
 
-> **Trigger Condition:** This confirmation block is **MANDATORY ONLY** when executing technical tasks: generating code, editing test scripts, refactoring Page Classes, or executing runner tools.  
-> **Conversational Exemption:** For general discussions, architecture questions, planning, and Q&A, **DO NOT emit this block** — respond directly and concisely.  
-> **Dynamic Context:** The architecture and technique fields must adapt dynamically to the target project's `PROJECT_AI_GUIDE.md` (e.g., Playwright/TS, Clean POM/Groovy, Pytest/Python, REST API).
+### B. Full Skill Context Header (Opt-In / Verbose Mode):
+```markdown
+> ✅ **Đã tải Skill Hub:** `agent-skills` & Hướng dẫn dự án (`PROJECT_AI_GUIDE.md`)  
+> 🏛️ **Kiến trúc:** <Kiến trúc mục tiêu, vd: Clean POM / Flat Architecture>  
+> ⚡ **Công nghệ:** <Công nghệ thực tế, vd: Playwright Live / API Mocking / Pytest>  
+> 🛡️ **Kỷ luật:** Truth Anchor (Không Fake Pass) + Zero-Token Error Blacklist  
+```
 
+### C. Detailed Telemetry Footer (Opt-In / When Requested):
 ```markdown
-> ✅ **[OK] Skill Hub Loaded:** `agent-skills` & Project Guide (`PROJECT_AI_GUIDE.md`)  
-> 🏛️ **[OK] Architecture:** <Target Architecture, e.g.: Clean POM / Flat Architecture>  
-> ⚡ **[OK] Target Tech:** <Actual Project Tech, e.g.: Playwright Live / API Mocking / Pytest>  
-> 🛡️ **[OK] Discipline:** Truth Anchor (No Fake Pass) + Zero-Token Error Blacklist  
-> 🎯 **[OK] Execution Plan:**  
-> • <Immediate Action Item 1>  
-> • <Immediate Action Item 2>  
+---
+> 📊 **Telemetry Thực Tế:** Turn #<turn> ┃ Thao tác: <steps> bước ┃ Xác thực: Truth Anchor Verified (Không số liệu phỏng đoán ngoài API)  
+> 🎯 **Task vừa xong:** "<yêu cầu>" ┃ Kết quả: <tóm tắt ngắn gọn kết quả thực tế>  
+> 📋 **Kế hoạch tiếp theo:**  
+> • <Hành động kế tiếp 1>  
+> • <Hành động kế tiếp 2>  
 ```
+> *Lưu ý Truth Anchor:* Telemetry chỉ báo cáo dữ kiện có thể kiểm chứng thực tế (số bước, file thay đổi, kết quả chạy lệnh). Tuyệt đối cấm bịa đặt hạn mức 5h/7d hoặc chi phí USD/VNĐ khi môi trường API không cung cấp.
 
 ---
 
@@ -34,6 +54,17 @@
 
 ---
 
+## 0.2 PRAGMATIC COMMUNICATION & HUMAN-FRIENDLY EXPLANATION PROTOCOL
+
+> **Clear, Pragmatic Communication — Zero Tech Jargon Overload (MANDATORY):**  
+> When communicating, explaining issues, or reporting progress to the user:  
+> 1. **Clear & Direct to the Point:** Explain problems, solutions, and outcomes in concise, plain language. Focus on 3 core pillars: *What is the issue?*, *How is it being resolved?*, and *What are the results or next steps?*.  
+> 2. **Zero Tech-Jargon Overload ("Don't be too tech"):** Avoid overusing academic jargon, obscure acronyms, or unnecessarily deep technical minutiae. Express ideas using practical, intuitive, everyday language. When technical terms are strictly required, explain them simply and accessibly.  
+> 3. **Pragmatic & Action-Oriented:** Deliver actionable solutions and straightforward choices so the user can easily make decisions without getting bogged down in theory. Maintain a natural, collaborative, and friendly pair-programming tone.  
+> 4. **Bilingual Separation (Vietnamese for Chat, English for Repo & Code):** Always converse, reply, and format conversational chat blocks (including Header & Footer telemetry) in Vietnamese. All codebase assets, test scripts, Page Classes, docstrings, rule files, and git commits must remain strictly in English.  
+
+---
+
 ## 1. CORE ARCHITECTURE & CODE STANDARDS
 
 1. **Clean Page Object Model (POM):**
@@ -81,7 +112,7 @@
      * Breaking API change suspected -> Run `tools/api_drift_sentinel.py`.
      * Parallel CI/CD runner setup needed -> Run `tools/matrix_sharder.py`.
      * Verifying test assertion quality -> Run `tools/micro_mutator.py` (reject if Mutation Score < 80%).
-     * Before completing code tasks -> Autonomously run `tools/verify_all.py` (8 Quality Gates DoD).
+     * Before completing code tasks -> Autonomously run `tools/verify_all.py` (9 Quality Gates DoD).
 
 ---
 
@@ -100,7 +131,7 @@ This repository defines specialized multi-agent profiles (configured in `.agents
 5. **Failure Autopsy Analyst (`failure-analyst`):**
    - Performs closed-loop diagnosis (`auto_heal.py`), auto-generates Jira/Markdown bug tickets with RCA (`bug_reporter.py`), executes CI self-healing & PR drafting (`ci_healing_hook.py`, `heal_pr_automator.py`), and resolves fixes from SQLite memory (`cache_resolver.py`).
 6. **Quality Gatekeeper & Sentinel (`quality-gatekeeper`):**
-   - Enforces 8 Quality Gates (`verify_all.py`), scans fake passes (`infer_linter.py`), injects AST micro-mutants (`micro_mutator.py` requiring >= 80% mutation score), audits visual regression masks (`smart_visual_masker.py`), and checks DB leaks (`trace_data_flow.py`).
+   - Enforces 9 Quality Gates (`verify_all.py`), scans fake passes (`infer_linter.py`), injects syntactic micro-mutants (`micro_mutator.py` requiring >= 80% mutation score), audits visual regression masks (`smart_visual_masker.py`), and checks DB leaks (`trace_data_flow.py`).
 
 ### 4.1 SINGLE FRONT-DOOR PROTOCOL & DETERMINISTIC FSM WORKFLOW
 
@@ -117,7 +148,7 @@ flowchart TD
         Stage2["<b>Stage 2: Code Synthesis</b><br/>• Subagent: pom-crafter<br/>• Clean POM + Flat Architecture<br/>• Zero XPaths in scripts"]
         Stage3["<b>Stage 3: Headless Execution</b><br/>• Subagent: test-runner<br/>• Run headless CLI + distill logs<br/>• Output Pass/Fail status"]
         Stage4["<b>Stage 4: Failure Autopsy & Healing</b><br/>• Subagent: failure-analyst<br/>• Activated ONLY if Stage 3 Fails<br/>• In-place healing via JUnit XML/Screenshot"]
-        Stage5["<b>Stage 5: Final Acceptance (DoD)</b><br/>• Subagent: quality-gatekeeper<br/>• 8 Quality Gates + Mutation Score >= 80%<br/>• Task Done"]
+        Stage5["<b>Stage 5: Final Acceptance (DoD)</b><br/>• Subagent: quality-gatekeeper<br/>• 9 Quality Gates + Mutation Score >= 80%<br/>• Task Done"]
         
         Stage1 --> Stage2 --> Stage3
         Stage3 -->|Pass| Stage5
@@ -133,9 +164,11 @@ flowchart TD
 | Specific User / System Intent | Designated Subagent | Situational Tool |
 | :--- | :--- | :--- |
 | **Inspect live DOM / probe selectors** | `live-explorer` | `tools/browser_helpers.js`, `tools/safety_firewall.py` |
+| **Stress-test spec / user story (0-context)** | `orchestrator` | `tools/goldfish_review.py` |
 | **Author Page Classes or test scripts** | `pom-crafter` | `tools/repo_map.py`, `tools/universal_ir.py` |
 | **Execute headless suites / CI runs** | `test-runner` | `tools/distill_log.py`, `tools/matrix_sharder.py` |
 | **Triage failed test runs / RCA** | `failure-analyst` | `tools/pinpoint_failure.py`, `tools/auto_heal.py` |
+| **Audit test drift against spec (Deficit/Scope)** | `quality-gatekeeper` | `tools/spec_drift_sentinel.py` |
 | **Enforce Quality Gates before commit** | `quality-gatekeeper` | `tools/verify_all.py`, `tools/micro_mutator.py` |
 
 ---
@@ -145,7 +178,7 @@ flowchart TD
 All quality control and audit tasks are dispatched via scripts in `tools/` (Refer to `tools/TOOLS_RUNBOOK.md`):
 
 ```bash
-# 1. Run 8 Quality Gates Verification
+# 1. Run 9 Quality Gates Verification
 python tools/verify_all.py
 
 # 2. Run AST linter for fake passes and empty catches
@@ -159,4 +192,10 @@ python tools/distill_log.py <path_to_log>
 
 # 5. Query zero-token error memory cache
 python tools/cache_resolver.py query "<error_message>"
+
+# 6. Stress-test test specifications (Goldfish Model)
+python tools/goldfish_review.py <spec_file>
+
+# 7. Audit spec-to-code alignment and drift
+python tools/spec_drift_sentinel.py --spec <spec_file> --code <code_path>
 ```