v4.11.0 - QA Orchestrator Agent, scenario replay, regression tracking, contradiction detection

Author: jovanSAPFIONEER

.github/SECURITY.md

@@ -4,7 +4,8 @@
 
 | Version | Supported |
 |---------|-----------|
-| 4.10.x  | ✅ Yes — full support (current) |
+| 4.11.x  | ✅ Yes — full support (current) |
+| 4.10.x  | ✅ Security fixes only |
 | 4.9.x   | ✅ Security fixes only |
 | 4.8.x   | ✅ Security fixes only |
 | 4.7.x   | ✅ Security fixes only |
@@ -39,6 +40,7 @@ Network-AI includes built-in security features:
 - **FSM Behavioral Control Plane** (v3.3.0) -- state-scoped agent and tool authorization via `JourneyFSM` and `ToolAuthorizationMatrix`; unauthorized actions blocked with `ComplianceViolationError`
 - **ComplianceMonitor** (v3.3.0) -- real-time agent behavior surveillance with configurable violation policies, severity classification, and async audit loop
 - **Named Multi-Blackboard API** (v3.4.0) -- isolated `SharedBlackboard` instances per name with independent namespaces, validation configs, and agent scoping; prevents cross-task data leakage
+- **QA Orchestrator Agent** (v4.11.0) -- scenario replay through quality gates, cross-agent contradiction detection, feedback loop with retry limits, and regression tracking with historical snapshots
 
 ## Security Scan Results
 

.github/copilot-instructions.md

@@ -2,7 +2,7 @@
 
 ## Project Overview
 
-Network-AI is a TypeScript/Node.js multi-agent orchestrator — shared state, guardrails, budgets, and cross-framework coordination (v4.10.0). 1,617 tests across 20 suites.
+Network-AI is a TypeScript/Node.js multi-agent orchestrator — shared state, guardrails, budgets, and cross-framework coordination (v4.11.0). 1,684 tests across 21 suites.
 
 ## Architecture
 
@@ -33,7 +33,7 @@ Network-AI is a TypeScript/Node.js multi-agent orchestrator — shared state, gu
 
 ```bash
 npx tsc --noEmit              # Type-check (zero errors expected)
-npm run test:all              # All 1,582 tests across 20 suites
+npm run test:all              # All 1,684 tests across 21 suites
 npm test                      # Core orchestrator tests
 npm run test:adapters         # All 17 adapters
 ```

ARCHITECTURE.md

@@ -51,13 +51,15 @@ flowchart TD
         AG["AuthGuardian\n(HMAC / Ed25519 permission tokens)"]:::security
         AR["AdapterRegistry\n(route tasks to frameworks)"]:::routing
         QG["QualityGateAgent\n(validate blackboard writes)"]:::quality
+        QA["QAOrchestratorAgent\n(scenario replay, regression tracking)"]:::quality
         BB["SharedBlackboard\n(shared agent state)\npropose → validate → commit\nfilesystem mutex"]:::blackboard
         AD["Adapters — plug any framework in, swap freely\nLangChain · AutoGen · CrewAI · MCP · LlamaIndex · …"]:::adapters
 
         AG -->|"grant / deny"| AR
         AR -->|"tasks dispatched"| AD
         AD -->|"writes results"| BB
         QG -->|"validates"| BB
+        QA -->|"orchestrates"| QG
     end
 
     SO --> AUDIT["data/audit_log.jsonl\n(HMAC / Ed25519-signed)"]:::audit
@@ -198,6 +200,12 @@ Two-layer validation before blackboard writes:
 - Quarantine system for suspicious content
 - Adds LLM latency — use selectively
 
+**Layer 3 — QAOrchestratorAgent (coordination)**
+- Scenario replay: re-run blackboard entries through quality gates as a test harness
+- Feedback loop: route rejections back to agents with structured feedback and retry limits
+- Regression tracker: historical quality snapshots with trend comparison
+- Cross-agent contradiction detection: detect conflicting outputs from multiple agents on the same key
+
 ---
 
 ## The 3-Layer Memory Model
@@ -281,6 +289,7 @@ Network-AI/
 ├── lib/
 │   ├── locked-blackboard.ts      # Atomic commits with file-system mutexes
 │   ├── blackboard-validator.ts   # Content quality gate (Layer 1 + Layer 2)
+│   ├── qa-orchestrator.ts        # QA orchestrator (scenario replay, regression, contradictions)
 │   ├── fsm-journey.ts            # FSM state machine and compliance monitor
 │   └── swarm-utils.ts            # Helper utilities
 ├── scripts/                      # Python helper scripts (local orchestration only)

CHANGELOG.md

@@ -5,6 +5,18 @@ All notable changes to Network-AI will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [4.11.0] - 2026-03-22
+
+### Added
+- **QA Orchestrator Agent** (`QAOrchestratorAgent`) — coordination layer on top of QualityGateAgent and ComplianceMonitor
+  - Scenario replay: re-run blackboard entries through quality gates as a test harness
+  - Feedback loop: route rejections back to agents with structured feedback and retry limits
+  - Regression tracker: historical quality snapshots with trend comparison
+  - Cross-agent contradiction detection: detect conflicting outputs from multiple agents on the same blackboard key
+  - Pluggable contradiction detector for domain-specific conflict rules
+- 67 new tests across 12 test groups (1,684 total)
+- `test:qa` script in package.json
+
 ## [4.10.5] - 2026-03-22
 
 ### Fixed

CLAUDE.md

@@ -11,7 +11,7 @@ Network-AI is a TypeScript/Node.js multi-agent orchestrator — shared state, gu
 ```bash
 npm install                   # Install dependencies
 npx tsc --noEmit              # Type-check (zero errors expected)
-npm run test:all              # Run all 1,617 tests across 20 suites
+npm run test:all              # Run all 1,684 tests across 21 suites
 npm test                      # Core orchestrator tests only
 npm run test:security         # Security module tests
 npm run test:adapters         # All 17 adapter tests

CODEX.md

@@ -11,7 +11,7 @@ Network-AI is a TypeScript/Node.js multi-agent orchestrator — shared state, gu
 ```bash
 npm install                   # Install dependencies
 npx tsc --noEmit              # Type-check (zero errors expected)
-npm run test:all              # Run all 1,617 tests across 20 suites
+npm run test:all              # Run all 1,684 tests across 21 suites
 npm test                      # Core orchestrator tests only
 npm run test:security         # Security module tests
 npm run test:adapters         # All 17 adapter tests

CONTRIBUTING.md

@@ -16,7 +16,7 @@ Unsolicited PRs without a linked, approved issue will be closed.
 
 ### Code Quality
 
-- All 1,617 existing tests must pass (`npm run test:all`)
+- All 1,684 existing tests must pass (`npm run test:all`)
 - Zero TypeScript compile errors (`npx tsc --noEmit`)
 - New features must include tests with >90% branch coverage
 - Follow existing code style and patterns
@@ -78,7 +78,7 @@ Unsolicited PRs without a linked, approved issue will be closed.
 git clone https://github.com/Jovancoding/Network-AI.git
 cd Network-AI
 npm install
-npm run test:all  # Run all 1,617 tests (20 suites)
+npm run test:all  # Run all 1,684 tests (21 suites)
 npm run test:phase4  # Phase 4 behavioral control plane tests only
 npx tsc --noEmit  # Type-check
 ```

ENTERPRISE.md

@@ -42,6 +42,7 @@ Your agents
 │  JourneyFSM        ──── FSM state governance        │
 │  ComplianceMonitor ──── real-time violation policy  │
 │  BlackboardValidator─── content quality gate        │
+│  QAOrchestratorAgent── scenario replay & regression │
 │  ProjectContextManager─ Layer-3 persistent memory   │
 └─────────────────────────────────────────────────────┘
     │
@@ -99,7 +100,7 @@ Network-AI follows [Semantic Versioning](https://semver.org/):
 
 ### Stability Signals
 
-- 1,617 passing assertions across 20 suites
+- 1,684 passing assertions across 21 suites
 - Deterministic scoring — no random outcomes in permission evaluation or budget enforcement
 - CI runs on every push and every PR
 - All examples ship with the repo and run without mocking

INTEGRATION_GUIDE.md

@@ -403,10 +403,12 @@ Run these before declaring the integration production-ready:
 ### Functional
 
 - [ ] All agents execute via the adapter registry without errors
-- [ ] `npx ts-node test-standalone.ts` — 79 core tests pass
-- [ ] `npx ts-node test-security.ts` — 33 security tests pass
-- [ ] `npx ts-node test-adapters.ts` — 139 adapter tests pass
+- [ ] `npx ts-node test-standalone.ts` — 88 core tests pass
+- [ ] `npx ts-node test-security.ts` — 34 security tests pass
+- [ ] `npx ts-node test-adapters.ts` — 176 adapter tests pass
 - [ ] `npx ts-node test-phase4.ts` — 147 behavioral tests pass
+- [ ] `npx ts-node test-qa.ts` — 67 QA orchestrator tests pass
+- [ ] `npm run test:all` — all 1,684 tests pass across 21 suites
 - [ ] `npm run demo -- --08` runs to completion in < 10 seconds
 
 ### Race Condition Safety

QUICKSTART.md

@@ -150,6 +150,30 @@ const orchestrator = createSwarmOrchestrator({
 });
 ```
 
+For batch testing and regression tracking, use the QA Orchestrator:
+
+```typescript
+import { QAOrchestratorAgent } from 'network-ai';
+
+const qa = new QAOrchestratorAgent({
+  qualityThreshold: 0.7,
+  maxRetries: 2,
+  onFeedback: (fb) => console.log('Fix needed:', fb.issues),
+});
+
+// Run scenarios through quality gates
+const harness = await qa.runHarness([
+  { id: 'test-1', key: 'analysis', value: agentOutput, sourceAgent: 'analyst' },
+]);
+console.log(`Pass rate: ${harness.passRate}`);
+
+// Detect cross-agent contradictions
+const contradictions = qa.detectContradictions();
+
+// Track quality regressions over time
+const report = qa.getRegressionReport();
+```
+
 ---
 
 ## 6. Security
@@ -221,7 +245,8 @@ export class MyFrameworkAdapter extends BaseAdapter {
 npx ts-node test-standalone.ts    # 88 core tests
 npx ts-node test-security.ts      # 34 security tests
 npx ts-node test-adapters.ts      # 176 adapter tests (all 17 frameworks)
-npx ts-node test-cli.ts           # 65 CLI tests
+ npx ts-node test-cli.ts           # 65 CLI tests
+npx ts-node test-qa.ts             # 67 QA orchestrator tests
 ```
 
 ---
@@ -335,6 +360,7 @@ Your App
        ├── TaskDecomposer          — Break tasks into subtasks
        ├── BlackboardValidator     — Quality gate (Layer 1)
        ├── QualityGateAgent        — AI review (Layer 2)
+       ├── QAOrchestratorAgent     — Scenario replay, feedback loops, regression tracking
        └── AdapterRegistry         — Routes to any framework
             ├── CustomAdapter       ─── your functions / HTTP
             ├── LangChainAdapter    ─── LangChain / LangGraph