agentops-cockpit 0.9.7__tar.gz → 0.9.8__tar.gz

{agentops_cockpit-0.9.7 → agentops_cockpit-0.9.8}/.gitignore

@@ -43,4 +43,8 @@ __pycache__/
 *.pyd
 .pytest_cache/
 .venv/
-.python-version
+# Terraform
+.terraform/
+*.tfstate
+*.tfstate.*
+.terraform.lock.hcl

{agentops_cockpit-0.9.7 → agentops_cockpit-0.9.8}/Makefile

@@ -15,8 +15,14 @@ help:
 	@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 arch-review               - [ARCH] Reasoning-based architecture review (v1.0)"
+	@echo "  make arch-review-export        - [ARCH] Generate Executive v1.1 HTML Report"
+	@echo "  make arch-benchmark            - [ARCH] Run v1.2 Reliability Waterfall (Stress Test)"
+	@echo "  make apply-fixes               - [PHASE 4] Auto-remediate detected architectural gaps"
+	@echo "  make propose-fixes             - [PHASE 5] Create fix branch and commit remediations"
 	@echo "  make reliability               - Run unit tests and regression suite"
+	@echo "  make smoke-test               - [E2E] End-to-End Persona Journey smoke tests"
+	@echo "  make regression                - [FULL] Master Reliability + Smoke Tests"
 	@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"
@@ -53,6 +59,14 @@ audit-all:
 reliability:
 	@$(PYTHON) src/agent_ops_cockpit/ops/reliability.py
 
+# 🧪 Smoke Test: E2E Persona Validation
+smoke-test:
+	@$(PYTHON) src/agent_ops_cockpit/ops/reliability.py --smoke
+
+# 🚀 Regression: The Full Suite (Unit + Smoke)
+regression:
+	@PYTHONPATH=src $(PYTHON) -c "from agent_ops_cockpit.ops.reliability import run_regression_suite; run_regression_suite()"
+
 # 🩺 Diagnose: DevEx system check
 diagnose:
 	@PYTHONPATH=src $(PYTHON) -m agent_ops_cockpit.cli.main diagnose
@@ -67,7 +81,23 @@ optimizer-audit-deep:
 
 # 🏛️ Architecture: Design review against Google Well-Architected Framework
 arch-review:
-	@$(PYTHON) src/agent_ops_cockpit/ops/arch_review.py
+	@$(PYTHON) src/agent_ops_cockpit/ops/arch_review.py audit
+
+# 🏛️ Executive: Generate v1.1 HTML Summary
+arch-review-export:
+	@$(PYTHON) src/agent_ops_cockpit/ops/arch_review.py audit --export
+
+# 🌊 Reliability: v1.2 Automated Benchmarking
+arch-benchmark:
+	@$(PYTHON) src/agent_ops_cockpit/ops/arch_review.py benchmark --count 50
+
+# 🚀 The Closer: Auto-remediation engine for architecture gaps
+apply-fixes:
+	@$(PYTHON) src/agent_ops_cockpit/ops/arch_review.py apply-fixes
+
+# 🌿 The Ambassador: Autonomous PR Factory
+propose-fixes:
+	@$(PYTHON) src/agent_ops_cockpit/ops/arch_review.py propose-fixes
 
 # 🧗 Quality: Iterative Hill Climbing optimization
 quality-baseline:
@@ -79,7 +109,7 @@ scan-secrets:
 
 # 🎨 UI/UX: Face Auditor for frontend quality
 ui-audit:
-	@$(PYTHON) src/agent_ops_cockpit/ops/ui_auditor.py src
+	@$(PYTHON) src/agent_ops_cockpit/ops/ui_auditor.py $(TARGET)
 
 # 🔥 Red Team: Unleash self-hacking security audit
 
@@ -95,9 +125,8 @@ 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
-
+# 🚀 Production: The Vercel-style 1-click deploy (using Full Regression Suite)
+deploy-prod: regression 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..."

agentops_cockpit-0.9.8/PKG-INFO

@@ -0,0 +1,172 @@
+Metadata-Version: 2.4
+Name: agentops-cockpit
+Version: 0.9.8
+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.md) best practices with the **Evidence Bridge**—real-time citations for architectural integrity.
+- **SME Persona Audits**: Parallelized review of your codebase by automated [**Principal SMEs**](docs/TECHNICAL_AUDIT_GUIDE.md) across FinOps, SecOps, Architecture, and Quality.
+- **Agentic Trinity**: Dedicated layers for the Engine (Logic), Face (UX), and Cockpit (Ops).
+- **A2A Connectivity**: Implements the [**Agent-to-Agent Transmission Standard**](docs/TECHNICAL_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 TD
+   subgraph Trinity [The Agentic Trinity 2.0]
+       E(The Engine: Reasoning)
+       F(The Face: Interface)
+       C(The Cockpit: Operations)
+       S{Sovereignty & Compliance}
+   end
+   E <--> C
+   F <--> C
+   E <--> F
+   E -.-> S
+   F -.-> S
+   C -.-> S
+   style Trinity fill:#f8fafc,stroke:#334155,stroke-width:2px
+   style S fill:#0ea5e9,color:#fff,stroke:#0284c7
+```
+
+- **⚙️ The Engine**: The reasoning core. Built with **ADK**, FastAPI, and Vertex AI.
+- **🎭 The Face**: The user experience. [Adaptive UI surfaces](docs/TECHNICAL_UX_GUIDE.md) and **GenUI** standards via the A2UI spec.
+- **🕹️ The Cockpit**: The operational brain. [Cost control](docs/TECHNICAL_FINOPS_GUIDE.md), semantic caching, shadow routing, and [adversarial audits](docs/TECHNICAL_REDTEAM_GUIDE.md).
+
+<div align="center">
+ <img src="public/assets/ecosystem.png" alt="Ecosystem Integrations" width="100%" />
+</div>
+
+---
+
+## 🏛️ v1.3: The "Autonomous Architect" Standard (NEW)
+Evolving from a compliance tool to an autonomous evolution engine. See the [**v1.3 Roadmap**](/docs/ROADMAP_V13.md).
+
+- **🚀 Context-Aware Patching**: Moving from templates to LLM-Synthesized PRs that match your project's style.
+- **🧪 Digital Twin Simulation**: `make simulation-run` for high-concurrency "Stress-Reasoning" test. [**Read Guide**](docs/TECHNICAL_ARCH_REVIEW.md).
+- **🧗 Hill Climbing Optimization**: Iterative prompt tuning to reach the Global Peak. [**Read Guide**](docs/TECHNICAL_QUALITY_GUIDE.md).
+- **🌍 Strategic Exit Strategy**: Automated TCO reports and migration plans for moving between cloud providers.
+
+---
+
+## 🚀 Key Innovation: The "Intelligence" Layer
+
+### 🛡️ Red Team Auditor (Adversarial SRE)
+Don't wait for your users to find prompt injections. Use the built-in [**Adversarial Evaluator**](docs/TECHNICAL_REDTEAM_GUIDE.md) to launch self-attacks against your agent, testing for PII leaks, instruction overrides, and multilingual jailbreaks.
+
+### 🧠 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 & Autonomous Evolution
+Every agent in the cockpit is graded against a framework-aware checklist. The Cockpit intelligently detects your stack and runs a tailored [**Architecture Review**](docs/TECHNICAL_ARCH_REVIEW.md). v1.3 introduces **Autonomous Evolution**—the ability to synthesize code fixes directly from audit findings.
+
+### 🕹️ MCP Connectivity Hub (Model Context Protocol)
+Stop building one-off tool integrations. The Cockpit provides a unified hub for **MCP Servers**. Connect to 1P/2P/3P tools 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**, **Pinecone**, **BigQuery**, and **Cloud SQL**.
+
+---
+
+### 🛡️ Advanced Governance & Discovery
+Modern agents don't just live in `agent.py`. The Cockpit uses a centralized **Discovery Engine** to intelligently map your project:
+- **`.gitignore` Compliance**: Zero-noise scanning that respects your project's ignore rules.
+- **Library Isolation**: Intelligently ignores hits in `venv` or `node_modules` to focus on your code.
+- **Config-Driven**: Use `cockpit.yaml` to define custom entry points, exclusions, and CI/CD thresholds.
+
+---
+
+## ⌨️ Master Command Registry
+
+The Cockpit is available as a first-class CLI and a comprehensive Makefile-based operational toolkit.
+
+| Registry | Description |
+| :--- | :--- |
+| 🕹️ [**Makefile Commands**](docs/TECHNICAL_COMMANDS_MASTER.md) | Standard local development and orchestration shortcuts. |
+| 🚀 [**UVX Master Guide**](docs/TECHNICAL_UVX_MASTER.md) | Portable, zero-install commands for CI/CD and automation. |
+
+---
+
+## 🧑‍💼 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:
+*   [**🏛️ Architecture**](docs/TECHNICAL_ARCH_REVIEW.md)
+*   [**💰 FinOps**](docs/TECHNICAL_FINOPS_GUIDE.md)
+*   [**🛡️ Red Team**](docs/TECHNICAL_REDTEAM_GUIDE.md)
+*   [**🧗 Quality**](docs/TECHNICAL_QUALITY_GUIDE.md)
+*   [**🌐 Infrastructure**](docs/TECHNICAL_INFRA_GUIDE.md)
+*   [**🎭 UX/UI**](docs/TECHNICAL_UX_GUIDE.md)
+
+---
+
+## 🚀 1-Click Production Pipeline
+`make deploy-prod` triggers the following lifecycle:
+1. Runs the Quick Safe-Build (`make audit`).
+2. Compiles production frontend assets.
+3. Deploys the Engine to **Google Cloud Run**.
+4. Deploys the Face to **Firebase Hosting**.
+
+---
+
+## 🤝 Ecosystem & Attribution
+The AgentOps Cockpit is designed to leverage and secure the best-of-breed tools in the Google Cloud ecosystem. We explicitly acknowledge and leverage the excellent work from:
+
+*   **[GoogleCloudPlatform/agent-starter-pack](https://github.com/GoogleCloudPlatform/agent-starter-pack/)**: We leverage this as a core reference for the **Agent Development Kit (ADK)** patterns and Vertex AI Agent Engine integration.
+*   **A2A Standard**: Our implementation follow the Agent-to-Agent Transmission Protocol for swarm intelligence.
+
+---
+*Reference: [Google Cloud Architecture Center - Agentic AI Overview](https://docs.cloud.google.com/architecture/agentic-ai-overview)*

agentops_cockpit-0.9.8/README.md

@@ -0,0 +1,148 @@
+# 🕹️ 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.md) best practices with the **Evidence Bridge**—real-time citations for architectural integrity.
+- **SME Persona Audits**: Parallelized review of your codebase by automated [**Principal SMEs**](docs/TECHNICAL_AUDIT_GUIDE.md) across FinOps, SecOps, Architecture, and Quality.
+- **Agentic Trinity**: Dedicated layers for the Engine (Logic), Face (UX), and Cockpit (Ops).
+- **A2A Connectivity**: Implements the [**Agent-to-Agent Transmission Standard**](docs/TECHNICAL_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 TD
+   subgraph Trinity [The Agentic Trinity 2.0]
+       E(The Engine: Reasoning)
+       F(The Face: Interface)
+       C(The Cockpit: Operations)
+       S{Sovereignty & Compliance}
+   end
+   E <--> C
+   F <--> C
+   E <--> F
+   E -.-> S
+   F -.-> S
+   C -.-> S
+   style Trinity fill:#f8fafc,stroke:#334155,stroke-width:2px
+   style S fill:#0ea5e9,color:#fff,stroke:#0284c7
+```
+
+- **⚙️ The Engine**: The reasoning core. Built with **ADK**, FastAPI, and Vertex AI.
+- **🎭 The Face**: The user experience. [Adaptive UI surfaces](docs/TECHNICAL_UX_GUIDE.md) and **GenUI** standards via the A2UI spec.
+- **🕹️ The Cockpit**: The operational brain. [Cost control](docs/TECHNICAL_FINOPS_GUIDE.md), semantic caching, shadow routing, and [adversarial audits](docs/TECHNICAL_REDTEAM_GUIDE.md).
+
+<div align="center">
+ <img src="public/assets/ecosystem.png" alt="Ecosystem Integrations" width="100%" />
+</div>
+
+---
+
+## 🏛️ v1.3: The "Autonomous Architect" Standard (NEW)
+Evolving from a compliance tool to an autonomous evolution engine. See the [**v1.3 Roadmap**](/docs/ROADMAP_V13.md).
+
+- **🚀 Context-Aware Patching**: Moving from templates to LLM-Synthesized PRs that match your project's style.
+- **🧪 Digital Twin Simulation**: `make simulation-run` for high-concurrency "Stress-Reasoning" test. [**Read Guide**](docs/TECHNICAL_ARCH_REVIEW.md).
+- **🧗 Hill Climbing Optimization**: Iterative prompt tuning to reach the Global Peak. [**Read Guide**](docs/TECHNICAL_QUALITY_GUIDE.md).
+- **🌍 Strategic Exit Strategy**: Automated TCO reports and migration plans for moving between cloud providers.
+
+---
+
+## 🚀 Key Innovation: The "Intelligence" Layer
+
+### 🛡️ Red Team Auditor (Adversarial SRE)
+Don't wait for your users to find prompt injections. Use the built-in [**Adversarial Evaluator**](docs/TECHNICAL_REDTEAM_GUIDE.md) to launch self-attacks against your agent, testing for PII leaks, instruction overrides, and multilingual jailbreaks.
+
+### 🧠 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 & Autonomous Evolution
+Every agent in the cockpit is graded against a framework-aware checklist. The Cockpit intelligently detects your stack and runs a tailored [**Architecture Review**](docs/TECHNICAL_ARCH_REVIEW.md). v1.3 introduces **Autonomous Evolution**—the ability to synthesize code fixes directly from audit findings.
+
+### 🕹️ MCP Connectivity Hub (Model Context Protocol)
+Stop building one-off tool integrations. The Cockpit provides a unified hub for **MCP Servers**. Connect to 1P/2P/3P tools 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**, **Pinecone**, **BigQuery**, and **Cloud SQL**.
+
+---
+
+### 🛡️ Advanced Governance & Discovery
+Modern agents don't just live in `agent.py`. The Cockpit uses a centralized **Discovery Engine** to intelligently map your project:
+- **`.gitignore` Compliance**: Zero-noise scanning that respects your project's ignore rules.
+- **Library Isolation**: Intelligently ignores hits in `venv` or `node_modules` to focus on your code.
+- **Config-Driven**: Use `cockpit.yaml` to define custom entry points, exclusions, and CI/CD thresholds.
+
+---
+
+## ⌨️ Master Command Registry
+
+The Cockpit is available as a first-class CLI and a comprehensive Makefile-based operational toolkit.
+
+| Registry | Description |
+| :--- | :--- |
+| 🕹️ [**Makefile Commands**](docs/TECHNICAL_COMMANDS_MASTER.md) | Standard local development and orchestration shortcuts. |
+| 🚀 [**UVX Master Guide**](docs/TECHNICAL_UVX_MASTER.md) | Portable, zero-install commands for CI/CD and automation. |
+
+---
+
+## 🧑‍💼 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:
+*   [**🏛️ Architecture**](docs/TECHNICAL_ARCH_REVIEW.md)
+*   [**💰 FinOps**](docs/TECHNICAL_FINOPS_GUIDE.md)
+*   [**🛡️ Red Team**](docs/TECHNICAL_REDTEAM_GUIDE.md)
+*   [**🧗 Quality**](docs/TECHNICAL_QUALITY_GUIDE.md)
+*   [**🌐 Infrastructure**](docs/TECHNICAL_INFRA_GUIDE.md)
+*   [**🎭 UX/UI**](docs/TECHNICAL_UX_GUIDE.md)
+
+---
+
+## 🚀 1-Click Production Pipeline
+`make deploy-prod` triggers the following lifecycle:
+1. Runs the Quick Safe-Build (`make audit`).
+2. Compiles production frontend assets.
+3. Deploys the Engine to **Google Cloud Run**.
+4. Deploys the Face to **Firebase Hosting**.
+
+---
+
+## 🤝 Ecosystem & Attribution
+The AgentOps Cockpit is designed to leverage and secure the best-of-breed tools in the Google Cloud ecosystem. We explicitly acknowledge and leverage the excellent work from:
+
+*   **[GoogleCloudPlatform/agent-starter-pack](https://github.com/GoogleCloudPlatform/agent-starter-pack/)**: We leverage this as a core reference for the **Agent Development Kit (ADK)** patterns and Vertex AI Agent Engine integration.
+*   **A2A Standard**: Our implementation follow the Agent-to-Agent Transmission Protocol for swarm intelligence.
+
+---
+*Reference: [Google Cloud Architecture Center - Agentic AI Overview](https://docs.cloud.google.com/architecture/agentic-ai-overview)*

agentops_cockpit-0.9.8/docs/DEPLOYMENT.md

@@ -0,0 +1,70 @@
+# 🚀 Production Deployment
+## The "Autonomous" Standard (v1.3)
+
+Deploying a "Well-Architected" agent requires orchestration across two primary Google Cloud environments. The Cockpit automates this through the `make deploy-prod` command.
+
+---
+
+## ⚙️ The Engine (Cloud Run)
+The Python backend (FastAPI) is deployed as a serverless service.
+- **Scaling**: scale-to-zero enabled.
+- **Regions**: `us-central1` recommended for proximity to Vertex AI.
+- **Best Practice**: Enable **Startup CPU Boost** to reduce cold-start latency (TTR).
+
+## 🧠 Agent Engine (Vertex AI)
+Recommended for agents that require deep integration with the Google Cloud agentic ecosystem.
+- **Why**: Managed runtime, built-in tracing, and **Context Caching** support.
+
+## ☸️ Enterprise Engine (GKE)
+Recommended for high-intensity or specialized isolation workloads.
+- **Why**: Full control over networking and GPU resources.
+
+---
+
+## 🏗️ 1-Click Deployment Sequence
+`make deploy-prod` executes the following high-fidelity pipeline:
+
+### Stage 1: The Quick "Safe-Build"
+Runs `make audit` (~15s).
+- Architecture sanity check.
+- Secret leakage detection.
+- Fast Red-Team (common injections).
+- Token optimization audit.
+
+### Stage 2: Face Build
+Executes `npm run build` to compile the React/Vite frontend into production assets.
+
+### Stage 3: Infrastructure Push
+- Containerizes the Engine and pushes to **Artifact Registry**.
+- Deploys the service to **Google Cloud Run**.
+- Deploys static assets to **Firebase Hosting**.
+
+---
+
+## 📊 Infrastructure Decision Matrix
+
+| Feature | Agent Engine | Cloud Run | GKE |
+| :--- | :--- | :--- | :--- |
+| **Orchestration** | Managed (ADK) | Custom (FastAPI) | Custom (K8s) |
+| **Scaling** | Automatic | Scale-to-Zero | Dynamic / GPU |
+| **Observability** | Vertex AI Traces | Cloud Logging | Prometheus / Istio |
+| **Best Case** | Fast Prototyping | Standard Web Agents | High-Perf Enterprise |
+
+---
+
+## 🛡️ v1.3: Deep System Audit
+For production-gate promotion, move from "Safe-Build" to "Deep Audit":
+```bash
+make audit-deep
+```
+- Full Adversarial Red-Teaming.
+- Iterative Quality Hill Climbing.
+- Precision Load Testing (`make load-test`).
+
+---
+
+## 🔑 Secret Management
+Never commit `.env` files. Use **Google Cloud Secret Manager** and map them as environment variables in Cloud Run.
+
+---
+*Generated by the AgentOps Cockpit. Sovereign Systems Division (v1.3).*

{agentops_cockpit-0.9.7 → agentops_cockpit-0.9.8}/index.html

@@ -4,6 +4,9 @@
     <meta charset="UTF-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>AgentOps Cockpit</title>
+    <meta name="description" content="Production-grade AI Agent Governance and Operations Cockpit." />
+    <meta property="og:image" content="/og-image.png" />
+    <meta property="og:title" content="AgentOps Cockpit" />
     <link rel="preconnect" href="https://fonts.googleapis.com">
     <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
     <link href="https://fonts.googleapis.com/css2?family=Plus+Jakarta+Sans:wght@400;500;600;700;800&family=JetBrains+Mono:wght@400;500;600&display=swap" rel="stylesheet">

{agentops_cockpit-0.9.7 → agentops_cockpit-0.9.8}/package.json

@@ -1,7 +1,7 @@
 {
   "name": "agent-ops-cockpit",
   "private": true,
-  "version": "0.7.0",
+  "version": "0.9.8",
   "type": "module",
   "scripts": {
     "dev": "vite",

agentops_cockpit-0.9.8/public/AGENT_OPS_STORY.md

@@ -0,0 +1,31 @@
+# 📖 The Agentic Trinity Vision
+
+## "Infrastructure is a solved problem. Intelligence is the new frontier."
+
+Most agent templates treat production as an afterthought. They give you a VPC and an API key, but leave you alone when the token bill hits $5,000 or when a user jailbreaks your agent's system prompt.
+
+The **AgentOps Cockpit** was born from a simple realization: **Building a demo is easy; running a profitable agent is hard.**
+
+---
+
+### The Architecture: The Trinity
+We believe every production agent must be built on three balanced pillars:
+
+#### 1. The Engine (The Day 0 Brain)
+This is where reasoning happens. By using Google's **Agent Development Kit (ADK)** and **Gemini 2.0**, we ensure that tool orchestration is deterministic and high-fidelity. The Engine isn't just a wrapper; it's a reasoning machine.
+
+#### 2. The Face (The Day 1 Experience)
+Text-in / Text-out is for chatbots, not for applications. **The Face** uses the **A2UI (Agent-to-User Interface)** protocol to transform JSON reasoning into interactive React components. It creates "Generative UI" that surfaces exactly what the user needs to see, right when the agent decides it.
+
+#### 3. The Cockpit (The Day 2 Governance)
+This is our unique contribution to the ecosystem. The Cockpit manages what happens *after* the agent is live.
+- **Profitability**: Semantic caching and prompt compression.
+- **Safety**: Automated adversarial red-teaming.
+- **Compliance**: VPC-native PII scrubbing.
+
+---
+
+### Our North Star: 10K Star Governance
+Our goal is to be the **Control Plane** for the agentic era. Whether you use LangChain, CrewAI, or raw custom logic, the Cockpit provides the specialized monitoring and auditing that ensure your AI agents are "Well-Architected" and enterprise-ready.
+
+Welcome to the future of **High-Fidelity Agent Ops**.

agentops_cockpit-0.9.8/public/AUDIT_SCENARIOS.md

@@ -0,0 +1,101 @@
+# AgentOps Cockpit v1.0: Audit Scenarios & Capabilities
+
+This document showcases the difference between "Heuristic Matching" (v0.9) and "Reasoning-Based Auditing" (v1.0) using the new AST and Semantic Graph Probing engines.
+
+---
+
+## 🟢 Scenario 1: The "Lazy" PII Masking (Simple)
+
+### The Code
+```python
+# agent.py
+user_input = get_user_query()
+# TODO: implement PII mask
+response = llm.invoke(user_input)
+```
+
+### ❌ Old v0.9 Auditor Result
+*   **Status:** `PASSED`
+*   **Rationale:** Found keyword "mask" in comments.
+*   **Verdict:** Dangerous false positive.
+
+### ✅ New v1.0 Auditor (Reasoning)
+*   **Status:** `FAIL (CRITICAL)`
+*   **Finding:** `Incomplete PII Protection`
+*   **Reasoning:** 
+    1.  AST analysis identifies `user_input` as a raw variable.
+    2.  No call to a "scrubber" function detected between variable assignment and LLM `invoke`.
+    3.  Semantic scanner identifies "TODO" comment as an active risk rather than a feature.
+*   **ADR Recommendation:** Inject `google-adk` PII Scrubber before `llm.invoke`.
+
+---
+
+## 🟡 Scenario 2: The "Thundering Herd" Bottleneck (Medium)
+
+### The Code
+```python
+async def get_data():
+    user = await db.get_user()
+    history = await db.get_history()
+    profile = await db.get_profile()
+    return user, history, profile
+```
+
+### ❌ Old v0.9 Auditor Result
+*   **Status:** `PASSED`
+*   **Rationale:** Code is valid Python/Async.
+*   **Verdict:** Ignores performance anti-patterns.
+
+### ✅ New v1.0 Auditor (Reasoning)
+*   **Status:** `FAIL (MEDIUM IMPACT)`
+*   **Finding:** `Sequential Bottleneck Detected`
+*   **Reasoning:** 
+    1.  AST walker identifies 3+ `await` calls in a direct sequence.
+    2.  Analyzes child nodes to determine these are independent data fetches.
+*   **Strategic ROI:** "Current latency is `T1 + T2 + T3`. Parallelizing via `asyncio.gather` reduces latency to `MAX(T1, T2, T3)`, improving responsiveness by ~60%."
+
+---
+
+## 🔴 Scenario 3: Cross-Framework Conflict (Complex)
+
+### The Code
+```python
+from langgraph.graph import StateGraph
+from crewai import Agent, Task, Crew
+
+# ... logic using a CrewAI Agent as a node in a LangGraph State machine ...
+```
+
+### ❌ Old v0.9 Auditor Result
+*   **Status:** `PASSED`
+*   **Rationale:** Found keywords "langgraph" and "crewai".
+*   **Verdict:** Both frameworks are supported, so audit passes.
+
+### ✅ New v1.0 Auditor (Reasoning)
+*   **Status:** `WARNING (ARCHITECTURAL CONFLICT)`
+*   **Finding:** `Orchestration Overlap`
+*   **Reasoning:** 
+    1.  Graph analysis detects two competing "Loop Managers" (LangGraph and CrewAI).
+    2.  Identifies high risk of **Cyclic State Deadlock** where the LangGraph state and CrewAI internal state diverge.
+*   **Consulting Edge:** "You are attempting to manage state in two places. Recommend refactoring CrewAI agents into raw `tools` within LangGraph or using CrewAI in a purely sequential sub-task mode."
+
+---
+
+## 🏆 Scenario 4: The "Silent" Model Waste (FinOps)
+
+### The Code
+```python
+# process_batch.py
+results = []
+for item in large_dataset:
+    # Processing simple classification
+    res = gemini_pro.generate_content(f"Is this category A or B: {item}")
+    results.append(res)
+```
+
+### ✅ New v1.0 Auditor (Reasoning)
+*   **Finding:** `High-Tier Model Inefficiency`
+*   **Reasoning:** 
+    1.  Detects `gemini-1.5-pro` (High Performance/Cost) inside a `for-loop`.
+    2.  Semantic analyzer determines the task is "simple classification" based on the prompt string prefix.
+*   **Business Impact:** "You are using a sledgehammer for a nail. Switching this loop to `gemini-1.5-flash` will reduce monthly token spend from $400 to $40 with zero accuracy loss."