agentops-cockpit 0.5.0__tar.gz → 0.9.5__tar.gz

{agentops_cockpit-0.5.0 → agentops_cockpit-0.9.5}/Dockerfile

@@ -11,4 +11,7 @@ COPY src/ ./src/
 # Set PYTHONPATH so it can find the modules
 ENV PYTHONPATH=/app/src
 
-CMD ["python", "src/backend/agent.py"]
+# Run mandatory AgentOps Audit during build
+RUN python src/agent_ops_cockpit/ops/orchestrator.py --mode quick
+
+CMD ["python", "src/agent_ops_cockpit/agent.py"]

agentops_cockpit-0.9.5/Makefile

@@ -0,0 +1,134 @@
+# --- A2UI Starter Makefile ---
+
+# Project Variables
+PYTHON = $(shell if [ -f "./.venv/bin/python3.14" ]; then echo "./.venv/bin/python3.14"; elif [ -d ".venv" ]; then echo "./.venv/bin/python"; else echo "python3"; fi)
+PROJECT_ID ?= $(shell gcloud config get-value project)
+REGION ?= us-central1
+SERVICE_NAME = agent-ops-backend
+IMAGE_TAG = us-central1-docker.pkg.dev/$(PROJECT_ID)/agent-repo/$(SERVICE_NAME):latest
+
+.PHONY: help dev build deploy-cloud-run deploy-firebase deploy-gke audit deploy-prod scan-secrets ui-audit audit-all watch
+
+help:
+	@echo "Available commands:"
+	@echo "  make dev                       - Start local development server"
+	@echo "  make audit                     - [MASTER] Quick Safe-Build (uvx agentops-cockpit report --mode quick)"
+	@echo "  make audit-deep                - [MASTER] Deep System Audit (uvx agentops-cockpit report --mode deep)"
+	@echo "  make optimizer-audit           - [CODE] Quick code audit (uvx agentops-cockpit audit --quick)"
+	@echo "  make optimizer-audit-deep      - [CODE] Deep code audit (uvx agentops-cockpit audit)"
+	@echo "  make reliability               - Run unit tests and regression suite"
+	@echo "  make diagnose                  - [DevEx] System health check and env diagnosis"
+	@echo "  make email-report              - [GOV] Email the latest Persona-Approved report"
+	@echo "  make red-team                  - Run adversarial security audit"
+	@echo "  make load-test                 - Run base load test"
+	@echo "  make deploy-prod       - Deploy to production (All Audits -> Cloud Run + Firebase)"
+	@echo "  make deploy-cloud-run  - Deploy to Google Cloud Run"
+	@echo "  make deploy-firebase   - Deploy to Firebase Hosting"
+	@echo "  make watch             - Track ecosystem updates (ADK, A2A, LangChain, etc.)"
+
+
+
+
+dev:
+	npm run dev
+
+build:
+	npm run build
+
+# 🏁 Master Audit: Safe-Build (Essential for dev velocity)
+audit:
+	@$(PYTHON) src/agent_ops_cockpit/ops/orchestrator.py --mode quick
+
+# 🚀 Deep Master Audit: Full benchmarks and stress tests
+audit-deep:
+	@$(PYTHON) src/agent_ops_cockpit/ops/orchestrator.py --mode deep
+
+# 🌐 Global Audit: Point the Cockpit at an external repository
+# Usage: make audit-all TARGET=/path/to/your/agent
+TARGET ?= .
+audit-all:
+	@$(PYTHON) src/agent_ops_cockpit/ops/orchestrator.py --mode quick --path $(TARGET)
+
+# 🛡️ Reliability: Unit tests and regression suite
+reliability:
+	@$(PYTHON) src/agent_ops_cockpit/ops/reliability.py
+
+# 🩺 Diagnose: DevEx system check
+diagnose:
+	@PYTHONPATH=src $(PYTHON) -m agent_ops_cockpit.cli.main diagnose
+
+# 🔍 The Optimizer: Audit specific agent file for code-level waste
+optimizer-audit:
+	@$(PYTHON) src/agent_ops_cockpit/optimizer.py src/agent_ops_cockpit/agent.py --quick
+
+# 🔍 Deep Optimizer: Fetch live SDK evidence
+optimizer-audit-deep:
+	@$(PYTHON) src/agent_ops_cockpit/optimizer.py src/agent_ops_cockpit/agent.py
+
+# 🏛️ Architecture: Design review against Google Well-Architected Framework
+arch-review:
+	@$(PYTHON) src/agent_ops_cockpit/ops/arch_review.py
+
+# 🧗 Quality: Iterative Hill Climbing optimization
+quality-baseline:
+	@$(PYTHON) src/agent_ops_cockpit/eval/quality_climber.py climb
+
+# 🧪 Secrets: Scan for hardcoded credentials
+scan-secrets:
+	@$(PYTHON) src/agent_ops_cockpit/ops/secret_scanner.py .
+
+# 🎨 UI/UX: Face Auditor for frontend quality
+ui-audit:
+	@$(PYTHON) src/agent_ops_cockpit/ops/ui_auditor.py src
+
+# 🔥 Red Team: Unleash self-hacking security audit
+
+red-team:
+	@$(PYTHON) src/agent_ops_cockpit/eval/red_team.py src/agent_ops_cockpit/agent.py
+
+# ⚡ Load Test: Stress test your agent endpoint (Usage: make load_test REQUESTS=100 CONCURRENCY=10)
+REQUESTS ?= 50
+
+CONCURRENCY ?= 5
+URL ?= http://localhost:8000/agent/query?q=healthcheck
+
+load_test:
+	@$(PYTHON) src/agent_ops_cockpit/eval/load_test.py run --url $(URL) --requests $(REQUESTS) --concurrency $(CONCURRENCY)
+
+# 🚀 Production: The Vercel-style 1-click deploy (using Quick Audit for speed)
+deploy-prod: audit build
+
+	@echo "📦 Containerizing and deploying to Cloud Run..."
+	gcloud run deploy $(SERVICE_NAME) --source . --region $(REGION) --allow-unauthenticated --port 80
+	@echo "🔥 Deploying frontend to Firebase..."
+	firebase deploy --only hosting
+
+# 🚀 Cloud Run: The fastest way to production
+deploy-cloud-run:
+	gcloud run deploy $(SERVICE_NAME) --source . --region $(REGION) --allow-unauthenticated --port 80
+
+# 🔥 Firebase: Optimized for frontend hosting
+deploy-firebase: build
+	firebase deploy --only hosting
+
+# ☸️ GKE: Enterprise container orchestration
+deploy-gke:
+	docker build -t $(IMAGE_TAG) .
+	docker push $(IMAGE_TAG)
+	@echo "Updating deployment.yaml..."
+	sed -i '' 's|image: .*|image: $(IMAGE_TAG)|' deployment.yaml || true
+	kubectl apply -f deployment.yaml || echo "No deployment.yaml found. Please create one based on DEPLOYMENT.md"
+
+# 📡 Watch: Ecosystem sync check
+watch:
+	@$(PYTHON) src/agent_ops_cockpit/ops/watcher.py
+
+# 🔌 MCP: Start the Model Context Protocol server
+mcp-serve:
+	@$(PYTHON) src/agent_ops_cockpit/mcp_server.py
+
+# 📧 Reporting: Email the latest audit results
+email-report:
+	@read -p "Enter recipient email: " email; \
+	$(PYTHON) -m agent_ops_cockpit.cli.main email-report $$email
+

agentops_cockpit-0.9.5/PKG-INFO

@@ -0,0 +1,246 @@
+Metadata-Version: 2.4
+Name: agentops-cockpit
+Version: 0.9.5
+Summary: Production-grade Agent Operations (AgentOps) Platform
+Project-URL: Homepage, https://github.com/enriquekalven/agent-ops-cockpit
+Project-URL: Bug Tracker, https://github.com/enriquekalven/agent-ops-cockpit/issues
+Author-email: Enrique <enrique@example.com>
+License-File: LICENSE
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10
+Requires-Dist: aiohttp>=3.9.0
+Requires-Dist: fastapi>=0.100.0
+Requires-Dist: gitpython>=3.1.0
+Requires-Dist: mcp>=0.1.0
+Requires-Dist: packaging>=23.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: tenacity>=8.0.0
+Requires-Dist: typer>=0.9.0
+Requires-Dist: uvicorn>=0.20.0
+Description-Content-Type: text/markdown
+
+# 🕹️ AgentOps Cockpit
+
+<div align="center">
+  <img src="public/assets/trinity.png" alt="AgentOps Cockpit Trinity" width="100%" />
+</div>
+
+<div align="center">
+ <br />
+ <a href="https://agent-cockpit.web.app" target="_blank"><strong>🌐 Official Website & Live Demo</strong></a>
+ <br /><br />
+ <a href="https://deploy.cloud.google.com?repo=https://github.com/enriquekalven/agent-cockpit">
+   <img src="https://deploy.cloud.google.com/button.svg" alt="Deploy to Google Cloud" />
+ </a>
+ <br />
+ <br />
+ <img src="https://img.shields.io/github/stars/enriquekalven/agent-cockpit?style=for-the-badge&color=ffd700" alt="GitHub Stars" />
+ <img src="https://img.shields.io/github/license/enriquekalven/agent-cockpit?style=for-the-badge&color=007bff" alt="License" />
+ <img src="https://img.shields.io/badge/Google-Well--Architected-4285F4?style=for-the-badge&logo=google-cloud" alt="Google Well-Architected" />
+ <img src="https://img.shields.io/badge/A2A_Standard-Enabled-10b981?style=for-the-badge" alt="A2A Standard" />
+</div>
+
+<br />
+
+<div align="center">
+ <h3>"Infrastructure gives you the pipes. We give you the Intelligence."</h3>
+ <p>The developer distribution for building, optimizing, and securing AI agents on Google Cloud.</p>
+</div>
+
+---
+
+## 📽️ The Mission
+Most AI agent templates stop at a single Python file and an API key. **The AgentOps Cockpit** is for developers moving into production. It provides framework-agnostic governance, safety, and cost guardrails for the entire agentic ecosystem.
+
+- **Governance-as-Code**: Audit your agent against [Google Well-Architected](/docs/google-architecture) best practices with the **Evidence Bridge**—real-time citations for architectural integrity.
+- **SME Persona Audits**: Parallelized review of your codebase by automated "Principal SMEs" across FinOps, SecOps, and Architecture.
+- **Agentic Trinity**: Dedicated layers for the Engine (Logic), Face (UX), and Cockpit (Ops).
+- **A2A Connectivity**: Implements the [Agent-to-Agent Transmission Standard](/A2A_GUIDE.md) for secure swarm orchestration.
+- **MCP Native**: Registration as a [Model Context Protocol](https://modelcontextprotocol.io) server for 1P/2P/3P tool consumption.
+
+---
+
+## 🏗️ The Agentic Trinity
+We divide the complexity of production agents into three focused pillars:
+
+```mermaid
+graph LR
+   subgraph Trinity [The Agentic Trinity]
+       E(The Engine: Reasoning)
+       F(The Face: Interface)
+       C(The Cockpit: Operations)
+   end
+   E <--> C
+   F <--> C
+   E <--> F
+   style Trinity fill:#f9f9f9,stroke:#333,stroke-width:2px
+```
+
+- **⚙️ The Engine**: The reasoning core. Built with **ADK**, FastAPI, and Vertex AI.
+- **🎭 The Face**: The user experience. Adaptive UI surfaces and **GenUI** standards via the A2UI spec.
+- **🕹️ The Cockpit**: The operational brain. Cost control, semantic caching, shadow routing, and adversarial audits.
+
+<div align="center">
+ <img src="public/assets/ecosystem.png" alt="Ecosystem Integrations" width="100%" />
+</div>
+
+---
+
+## 🌐 Framework Agnostic Governance
+The Cockpit isn't just for ADK. It provides **Best Practices as Code** across all major agentic frameworks:
+
+<div align="center">
+ <img src="https://img.shields.io/badge/OpenAI_Agentkit-412991?style=for-the-badge&logo=openai" alt="OpenAI Agentkit" />
+ <img src="https://img.shields.io/badge/Anthropic_Claude-D97757?style=for-the-badge&logo=anthropic" alt="Anthropic" />
+ <img src="https://img.shields.io/badge/Microsoft_AutoGen-0078d4?style=for-the-badge&logo=microsoft" alt="Microsoft" />
+ <img src="https://img.shields.io/badge/AWS_Bedrock-FF9900?style=for-the-badge&logo=amazon-aws" alt="AWS" />
+ <img src="https://img.shields.io/badge/CopilotKit.ai-6366f1?style=for-the-badge" alt="CopilotKit" />
+ <img src="https://img.shields.io/badge/LangChain-1C3C3C?style=for-the-badge" alt="LangChain" />
+ <img src="https://img.shields.io/badge/ADK-4285F4?style=for-the-badge&logo=google-cloud" alt="ADK" />
+ <img src="public/assets/workflow.png" alt="Operational Workflow" width="100%" />
+</div>
+
+## 🛠️ Operational Flow
+
+```mermaid
+sequenceDiagram
+   participant U as User
+   participant C as Cockpit
+   participant E as Engine
+   participant F as Face
+   
+   U->>C: Prompt / Input
+   C->>C: Policy Audit (RFC-307)
+   C->>E: Execute Logic / Tools
+   E->>C: Action Proposals
+   C->>E: Approve (HITL)
+   E->>F: GenUI Metadata
+   F->>U: Reactive Surface (A2UI)
+```
+
+<br />
+
+<div align="center">
+ <img src="https://img.shields.io/badge/Python-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python" />
+ <img src="https://img.shields.io/badge/Go-00ADD8?style=flat-square&logo=go&logoColor=white" alt="Go" />
+ <img src="https://img.shields.io/badge/NodeJS-339933?style=flat-square&logo=node.js&logoColor=white" alt="NodeJS" />
+ <img src="https://img.shields.io/badge/TypeScript-3178C6?style=flat-square&logo=typescript&logoColor=white" alt="TypeScript" />
+ <img src="https://img.shields.io/badge/Streamlit-FF4B4B?style=flat-square&logo=streamlit&logoColor=white" alt="Streamlit" />
+ <img src="https://img.shields.io/badge/Angular-DD0031?style=flat-square&logo=angular&logoColor=white" alt="Angular" />
+ <img src="https://img.shields.io/badge/Lit-324FFF?style=flat-square&logo=lit&logoColor=white" alt="Lit" />
+</div>
+
+Whether you are building a swarm in **CrewAI**, a Go-based high-perf engine, or a **Streamlit** dashboard, the Cockpit ensures your agent maps to the **Google Well-Architected Framework**.
+
+
+---
+
+## 🚀 Key Innovation: The "Intelligence" Layer
+
+### 🛡️ Red Team Auditor (Self-Hacking)
+Don't wait for your users to find prompt injections. Use the built-in Adversarial Evaluator to launch self-attacks against your agent, testing for PII leaks, instruction overrides, and safety filter bypasses.
+
+### 🧠 Hive Mind (Semantic Caching)
+**Reduce LLM costs by up to 40%.** The Hive Mind checks for semantically similar queries in 10ms, serving cached answers for common questions without calling the LLM.
+
+### 🏛️ Arch Review & Framework Detection
+Every agent in the cockpit is graded against a framework-aware checklist. The Cockpit intelligently detects your stack—**Google ADK**, **OpenAI Agentkit**, **Anthropic Claude**, **Microsoft AutoGen/Semantic Kernel**, **AWS Bedrock Agents**, or **CopilotKit**—and runs a tailored audit against corresponding production standards. Use `make arch-review` to verify your **Governance-as-Code**.
+
+### 🕹️ MCP Connectivity Hub (Model Context Protocol)
+Stop building one-off tool integrations. The Cockpit provides a unified hub for **MCP Servers**. Connect to Google Search, Slack, or your internal databases via the standardized Model Context Protocol for secure, audited tool execution. Start the server with `make mcp-serve`.
+
+### 🗄️ Situational Database Audits
+The Cockpit now performs platform-specific performance and security audits for:
+- **AlloyDB**: Optimizes for the **Columnar Engine** (100x query speedup).
+- **Pinecone**: Suggests **gRPC** and **Namespace Isolation** for high-perf RAG.
+- **BigQuery**: Suggests **BQ Vector Search** for serverless, cost-effective grounding.
+- **Cloud SQL**: Enforces **IAM-based authentication** via the official Python Connector.
+
+### 🧗 Quality Hill Climbing (ADK Evaluation)
+Following **Google ADK Evaluation** best practices, the Cockpit provides an iterative optimization loop. `make quality-baseline` runs your agent against a "Golden Dataset" using **LLM-as-a-Judge** scoring (Response Match & Tool Trajectory), climbing the quality curve until production-grade fidelity is reached.
+
+### 🛑 Mandatory Governance Enforcement (NEW)
+The Cockpit now acts as a mandatory gate for production.
+- **Blocking CI/CD**: GitHub Actions now fail if **High Impact** cost issues or **Red Team** security vulnerabilities are detected.
+- **Build-Time Audit**: The `Dockerfile` includes a mandatory `RUN` audit step. If your agent is not "Well-Architected," the container image will fail to build.
+
+---
+
+## ⌨️ Quick Start
+
+The Cockpit is available as a first-class CLI on PyPI. 
+
+```bash
+# 1. Install the Cockpit globally
+pip install agentops-cockpit
+
+# 2. Run Global Audit (Produces unified report)
+agent-ops report --mode quick        # ⚡ Quick Safe-Build
+agent-ops report --mode deep         # 🚀 Full System Audit
+
+# 3. Guardrail Policy Audit (RFC-307)
+agent-ops policy-audit --text "How to make a bomb?"
+
+# 4. Global Scaffolding
+agent-ops-cockpit create <name> --ui a2ui
+```
+
+### 🔍 Agent Optimizer v2 (Situational Intelligence)
+The Cockpit doesn't just look for generic waste. It now performs **Triple-State Analysis**:
+- **Legacy Workarounds**: Suggests situational fixes for older SDK versions (e.g., manual prompt pruning).
+- **Modernization Paths**: Highlights native performance gains (e.g., 90% cost reduction via Context Caching) available in latest SDKs.
+- **Conflict Guard**: Real-time cross-package validation to prevent architectural deadlocks (e.g., CrewAI vs LangGraph state loops).
+
+### ⚡ Quick-Safe Build (12x Faster Loops)
+Development velocity shouldn't sacrifice safety. The new `--quick` mode in the auditor reduces check latency from **1.8s to 0.15s**, providing sub-second feedback while maintaining the integrity of the Conflict Guard and Architecture Review.
+
+---
+
+### 🧑‍💼 Principal SME Persona Approvals
+The Cockpit now features a **Multi-Persona Governance Board**. Every audit result is framed through the lens of a Principal Engineer in that domain (Security, Legal, FinOps, UX), ensuring your agent is compliant with organizational standards.
+
+### 📄 Export & Reporting
+*   **HTML/PDF Export**: Every audit automatically generates `cockpit_report.html`, a premium, printable report ready for PDF export.
+*   **Email Reports**: Send audit results directly to stakeholders via the CLI.
+
+---
+
+## 📊 Local Development
+The Cockpit provides a unified "Mission Control" to evaluate your agents instantly.
+
+```bash
+make audit         # 🕹️ Run Master Audit (Persona Approved)
+make audit-deep    # 🚀 Run Deep Audit (Full SME Verdicts)
+make email-report  # 📧 Email the latest result to a stakeholder
+make diagnose      # 🩺 Run environment health check
+make optimizer-audit # 🔍 Run Optimizer on specific agent files
+make reliability   # 🛡️ Run unit tests and regression suite
+make dev           # Start the local Engine + Face stack
+make arch-review   # 🏛️ Run the Google Well-Architected design review
+make quality-baseline # 🧗 Run iterative 'Hill Climbing' quality audit
+make red-team      # Execute a white-hat security audit
+make deploy-prod   # 🚀 1-click deploy to Google Cloud
+```
+
+---
+
+## 🧭 Roadmap
+- [x] **One-Click GitHub Action**: Automated governance audits on every PR.
+- [x] **Mandatory Build Gates**: Blocking CI/CD and Container audits for production safety.
+- [x] **Multi-Agent Orchestrator**: Standardized A2A Swarm/Coordinator patterns.
+- [ ] **Visual Mission Control**: Real-time cockpit observability dashboard.
+
+[View full roadmap →](/ROADMAP.md)
+
+---
+
+## 🤝 Community
+- **Star this repo** to help us build the future of AgentOps.
+- **Join the Discussion** for patterns on Google Cloud.
+- **Contribute**: Read our [Contributing Guide](/CONTRIBUTING.md).
+
+---
+*Reference: [Google Cloud Architecture Center - Agentic AI Overview](https://docs.cloud.google.com/architecture/agentic-ai-overview)*

agentops_cockpit-0.9.5/README.md

@@ -0,0 +1,222 @@
+# 🕹️ AgentOps Cockpit
+
+<div align="center">
+  <img src="public/assets/trinity.png" alt="AgentOps Cockpit Trinity" width="100%" />
+</div>
+
+<div align="center">
+ <br />
+ <a href="https://agent-cockpit.web.app" target="_blank"><strong>🌐 Official Website & Live Demo</strong></a>
+ <br /><br />
+ <a href="https://deploy.cloud.google.com?repo=https://github.com/enriquekalven/agent-cockpit">
+   <img src="https://deploy.cloud.google.com/button.svg" alt="Deploy to Google Cloud" />
+ </a>
+ <br />
+ <br />
+ <img src="https://img.shields.io/github/stars/enriquekalven/agent-cockpit?style=for-the-badge&color=ffd700" alt="GitHub Stars" />
+ <img src="https://img.shields.io/github/license/enriquekalven/agent-cockpit?style=for-the-badge&color=007bff" alt="License" />
+ <img src="https://img.shields.io/badge/Google-Well--Architected-4285F4?style=for-the-badge&logo=google-cloud" alt="Google Well-Architected" />
+ <img src="https://img.shields.io/badge/A2A_Standard-Enabled-10b981?style=for-the-badge" alt="A2A Standard" />
+</div>
+
+<br />
+
+<div align="center">
+ <h3>"Infrastructure gives you the pipes. We give you the Intelligence."</h3>
+ <p>The developer distribution for building, optimizing, and securing AI agents on Google Cloud.</p>
+</div>
+
+---
+
+## 📽️ The Mission
+Most AI agent templates stop at a single Python file and an API key. **The AgentOps Cockpit** is for developers moving into production. It provides framework-agnostic governance, safety, and cost guardrails for the entire agentic ecosystem.
+
+- **Governance-as-Code**: Audit your agent against [Google Well-Architected](/docs/google-architecture) best practices with the **Evidence Bridge**—real-time citations for architectural integrity.
+- **SME Persona Audits**: Parallelized review of your codebase by automated "Principal SMEs" across FinOps, SecOps, and Architecture.
+- **Agentic Trinity**: Dedicated layers for the Engine (Logic), Face (UX), and Cockpit (Ops).
+- **A2A Connectivity**: Implements the [Agent-to-Agent Transmission Standard](/A2A_GUIDE.md) for secure swarm orchestration.
+- **MCP Native**: Registration as a [Model Context Protocol](https://modelcontextprotocol.io) server for 1P/2P/3P tool consumption.
+
+---
+
+## 🏗️ The Agentic Trinity
+We divide the complexity of production agents into three focused pillars:
+
+```mermaid
+graph LR
+   subgraph Trinity [The Agentic Trinity]
+       E(The Engine: Reasoning)
+       F(The Face: Interface)
+       C(The Cockpit: Operations)
+   end
+   E <--> C
+   F <--> C
+   E <--> F
+   style Trinity fill:#f9f9f9,stroke:#333,stroke-width:2px
+```
+
+- **⚙️ The Engine**: The reasoning core. Built with **ADK**, FastAPI, and Vertex AI.
+- **🎭 The Face**: The user experience. Adaptive UI surfaces and **GenUI** standards via the A2UI spec.
+- **🕹️ The Cockpit**: The operational brain. Cost control, semantic caching, shadow routing, and adversarial audits.
+
+<div align="center">
+ <img src="public/assets/ecosystem.png" alt="Ecosystem Integrations" width="100%" />
+</div>
+
+---
+
+## 🌐 Framework Agnostic Governance
+The Cockpit isn't just for ADK. It provides **Best Practices as Code** across all major agentic frameworks:
+
+<div align="center">
+ <img src="https://img.shields.io/badge/OpenAI_Agentkit-412991?style=for-the-badge&logo=openai" alt="OpenAI Agentkit" />
+ <img src="https://img.shields.io/badge/Anthropic_Claude-D97757?style=for-the-badge&logo=anthropic" alt="Anthropic" />
+ <img src="https://img.shields.io/badge/Microsoft_AutoGen-0078d4?style=for-the-badge&logo=microsoft" alt="Microsoft" />
+ <img src="https://img.shields.io/badge/AWS_Bedrock-FF9900?style=for-the-badge&logo=amazon-aws" alt="AWS" />
+ <img src="https://img.shields.io/badge/CopilotKit.ai-6366f1?style=for-the-badge" alt="CopilotKit" />
+ <img src="https://img.shields.io/badge/LangChain-1C3C3C?style=for-the-badge" alt="LangChain" />
+ <img src="https://img.shields.io/badge/ADK-4285F4?style=for-the-badge&logo=google-cloud" alt="ADK" />
+ <img src="public/assets/workflow.png" alt="Operational Workflow" width="100%" />
+</div>
+
+## 🛠️ Operational Flow
+
+```mermaid
+sequenceDiagram
+   participant U as User
+   participant C as Cockpit
+   participant E as Engine
+   participant F as Face
+   
+   U->>C: Prompt / Input
+   C->>C: Policy Audit (RFC-307)
+   C->>E: Execute Logic / Tools
+   E->>C: Action Proposals
+   C->>E: Approve (HITL)
+   E->>F: GenUI Metadata
+   F->>U: Reactive Surface (A2UI)
+```
+
+<br />
+
+<div align="center">
+ <img src="https://img.shields.io/badge/Python-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python" />
+ <img src="https://img.shields.io/badge/Go-00ADD8?style=flat-square&logo=go&logoColor=white" alt="Go" />
+ <img src="https://img.shields.io/badge/NodeJS-339933?style=flat-square&logo=node.js&logoColor=white" alt="NodeJS" />
+ <img src="https://img.shields.io/badge/TypeScript-3178C6?style=flat-square&logo=typescript&logoColor=white" alt="TypeScript" />
+ <img src="https://img.shields.io/badge/Streamlit-FF4B4B?style=flat-square&logo=streamlit&logoColor=white" alt="Streamlit" />
+ <img src="https://img.shields.io/badge/Angular-DD0031?style=flat-square&logo=angular&logoColor=white" alt="Angular" />
+ <img src="https://img.shields.io/badge/Lit-324FFF?style=flat-square&logo=lit&logoColor=white" alt="Lit" />
+</div>
+
+Whether you are building a swarm in **CrewAI**, a Go-based high-perf engine, or a **Streamlit** dashboard, the Cockpit ensures your agent maps to the **Google Well-Architected Framework**.
+
+
+---
+
+## 🚀 Key Innovation: The "Intelligence" Layer
+
+### 🛡️ Red Team Auditor (Self-Hacking)
+Don't wait for your users to find prompt injections. Use the built-in Adversarial Evaluator to launch self-attacks against your agent, testing for PII leaks, instruction overrides, and safety filter bypasses.
+
+### 🧠 Hive Mind (Semantic Caching)
+**Reduce LLM costs by up to 40%.** The Hive Mind checks for semantically similar queries in 10ms, serving cached answers for common questions without calling the LLM.
+
+### 🏛️ Arch Review & Framework Detection
+Every agent in the cockpit is graded against a framework-aware checklist. The Cockpit intelligently detects your stack—**Google ADK**, **OpenAI Agentkit**, **Anthropic Claude**, **Microsoft AutoGen/Semantic Kernel**, **AWS Bedrock Agents**, or **CopilotKit**—and runs a tailored audit against corresponding production standards. Use `make arch-review` to verify your **Governance-as-Code**.
+
+### 🕹️ MCP Connectivity Hub (Model Context Protocol)
+Stop building one-off tool integrations. The Cockpit provides a unified hub for **MCP Servers**. Connect to Google Search, Slack, or your internal databases via the standardized Model Context Protocol for secure, audited tool execution. Start the server with `make mcp-serve`.
+
+### 🗄️ Situational Database Audits
+The Cockpit now performs platform-specific performance and security audits for:
+- **AlloyDB**: Optimizes for the **Columnar Engine** (100x query speedup).
+- **Pinecone**: Suggests **gRPC** and **Namespace Isolation** for high-perf RAG.
+- **BigQuery**: Suggests **BQ Vector Search** for serverless, cost-effective grounding.
+- **Cloud SQL**: Enforces **IAM-based authentication** via the official Python Connector.
+
+### 🧗 Quality Hill Climbing (ADK Evaluation)
+Following **Google ADK Evaluation** best practices, the Cockpit provides an iterative optimization loop. `make quality-baseline` runs your agent against a "Golden Dataset" using **LLM-as-a-Judge** scoring (Response Match & Tool Trajectory), climbing the quality curve until production-grade fidelity is reached.
+
+### 🛑 Mandatory Governance Enforcement (NEW)
+The Cockpit now acts as a mandatory gate for production.
+- **Blocking CI/CD**: GitHub Actions now fail if **High Impact** cost issues or **Red Team** security vulnerabilities are detected.
+- **Build-Time Audit**: The `Dockerfile` includes a mandatory `RUN` audit step. If your agent is not "Well-Architected," the container image will fail to build.
+
+---
+
+## ⌨️ Quick Start
+
+The Cockpit is available as a first-class CLI on PyPI. 
+
+```bash
+# 1. Install the Cockpit globally
+pip install agentops-cockpit
+
+# 2. Run Global Audit (Produces unified report)
+agent-ops report --mode quick        # ⚡ Quick Safe-Build
+agent-ops report --mode deep         # 🚀 Full System Audit
+
+# 3. Guardrail Policy Audit (RFC-307)
+agent-ops policy-audit --text "How to make a bomb?"
+
+# 4. Global Scaffolding
+agent-ops-cockpit create <name> --ui a2ui
+```
+
+### 🔍 Agent Optimizer v2 (Situational Intelligence)
+The Cockpit doesn't just look for generic waste. It now performs **Triple-State Analysis**:
+- **Legacy Workarounds**: Suggests situational fixes for older SDK versions (e.g., manual prompt pruning).
+- **Modernization Paths**: Highlights native performance gains (e.g., 90% cost reduction via Context Caching) available in latest SDKs.
+- **Conflict Guard**: Real-time cross-package validation to prevent architectural deadlocks (e.g., CrewAI vs LangGraph state loops).
+
+### ⚡ Quick-Safe Build (12x Faster Loops)
+Development velocity shouldn't sacrifice safety. The new `--quick` mode in the auditor reduces check latency from **1.8s to 0.15s**, providing sub-second feedback while maintaining the integrity of the Conflict Guard and Architecture Review.
+
+---
+
+### 🧑‍💼 Principal SME Persona Approvals
+The Cockpit now features a **Multi-Persona Governance Board**. Every audit result is framed through the lens of a Principal Engineer in that domain (Security, Legal, FinOps, UX), ensuring your agent is compliant with organizational standards.
+
+### 📄 Export & Reporting
+*   **HTML/PDF Export**: Every audit automatically generates `cockpit_report.html`, a premium, printable report ready for PDF export.
+*   **Email Reports**: Send audit results directly to stakeholders via the CLI.
+
+---
+
+## 📊 Local Development
+The Cockpit provides a unified "Mission Control" to evaluate your agents instantly.
+
+```bash
+make audit         # 🕹️ Run Master Audit (Persona Approved)
+make audit-deep    # 🚀 Run Deep Audit (Full SME Verdicts)
+make email-report  # 📧 Email the latest result to a stakeholder
+make diagnose      # 🩺 Run environment health check
+make optimizer-audit # 🔍 Run Optimizer on specific agent files
+make reliability   # 🛡️ Run unit tests and regression suite
+make dev           # Start the local Engine + Face stack
+make arch-review   # 🏛️ Run the Google Well-Architected design review
+make quality-baseline # 🧗 Run iterative 'Hill Climbing' quality audit
+make red-team      # Execute a white-hat security audit
+make deploy-prod   # 🚀 1-click deploy to Google Cloud
+```
+
+---
+
+## 🧭 Roadmap
+- [x] **One-Click GitHub Action**: Automated governance audits on every PR.
+- [x] **Mandatory Build Gates**: Blocking CI/CD and Container audits for production safety.
+- [x] **Multi-Agent Orchestrator**: Standardized A2A Swarm/Coordinator patterns.
+- [ ] **Visual Mission Control**: Real-time cockpit observability dashboard.
+
+[View full roadmap →](/ROADMAP.md)
+
+---
+
+## 🤝 Community
+- **Star this repo** to help us build the future of AgentOps.
+- **Join the Discussion** for patterns on Google Cloud.
+- **Contribute**: Read our [Contributing Guide](/CONTRIBUTING.md).
+
+---
+*Reference: [Google Cloud Architecture Center - Agentic AI Overview](https://docs.cloud.google.com/architecture/agentic-ai-overview)*

{agentops_cockpit-0.5.0/public → agentops_cockpit-0.9.5/docs}/A2A_GUIDE.md

@@ -7,7 +7,7 @@ Building a single agent is easy. Building a **Swarm** of agents that communicate
 | Layer | Responsibility | Protocol / Spec |
 | :--- | :--- | :--- |
 | **Surface** | Human-Agent Interaction | [A2UI Spec](/docs/a2ui) |
-| **Memory** | Cross-Agent Knowledge | [Vector Workspace (Hive Mind)](/src/backend/cache) |
+| **Memory** | Cross-Agent Knowledge | [Vector Workspace (Hive Mind)](/src/agent_ops_cockpit/cache) |
 | **Logic** | Tool & Reasoning Handshake | [A2P Handshake](#a2p-handshake) |
 | **Security** | Identity & Permissions | [GCP Workload Identity](https://cloud.google.com/kubernetes-engine/docs/how-to/workload-identity) |
 

{agentops_cockpit-0.5.0/public → agentops_cockpit-0.9.5/docs}/BE_INTEGRATION_GUIDE.md

@@ -14,7 +14,7 @@ The Engine comes pre-installed with the **Cockpit Middleware Stack**:
 We recommend building your tools as **MCP (Model Context Protocol)** or **ADK Extensions**. This ensures that the agent can discover and invoke them with high reliability.
 
 ```python
-# Example Tool in src/backend/tools/search.py
+# Example Tool in src/agent_ops_cockpit/tools/search.py
 from adk import Tool
 
 @Tool