Multi-Agent A2A with the Agent Development Kit(ADK), Azure Fabric, and Gemini CLI

--- title: Multi-Agent A2A with the Agent Development Kit(ADK), Azure Fabric, and Gemini CLI published: true series: Azure date: 2026-05-04 02:30:53 UTC tags: a2aprotocol,microsoftfabric,multiagentsystems,googleadk canonical_url: https://xbill999.medium.com/multi-agent-a2a-with-the-agent-development-kit-adk-azure-fabric-and-gemini-cli-db05e9859aa9 --- Leveraging the Google Agent Development Kit (ADK) and the underlying Gemini LLM to build Multi-Agent Applications with A2A protocol support using the Python programming language.  #### Aren’t There a Billion Python ADK Demos? Yes there are. Python has traditionally been the main coding language for ML and AI tools. The goal of this article is to provide a multi-agent test bed for building, debugging, and deploying multi-agent applications. #### What you talkin ‘bout Willis? So what is different about this lab compared to all the others out there? This is one of the first deep dives into a Multi-Agent application leveraging the advanced tooling of Gemini CLI. The starting point for the demo was an existing Codelab- which was updated and re-engineered with Gemini CLI. The original Codelab- is here: [Building a Multi-Agent System | Google Codelabs](https://codelabs.developers.google.com/codelabs/production-ready-ai-roadshow/1-building-a-multi-agent-system/building-a-multi-agent-system#0) #### What Is Python? Python is an interpreted language that allows for rapid development and testing and has deep libraries for working with ML and AI: [Welcome to Python.org](https://www.python.org/) #### Python Version Management One of the downsides of the wide deployment of Python has been managing the language versions across platforms and maintaining a supported version. The **pyenv** tool enables deploying consistent versions of Python: [GitHub - pyenv/pyenv: Simple Python version management](https://github.com/pyenv/pyenv) As of writing — the mainstream python version is 3.13. To validate your current Python: ```console python --version Python 3.13.13 ``` #### Microsoft Fabric Microsoft Fabric is an all-in-one, SaaS-based data analytics platform that unifies tools like Data Factory, Synapse, and Power BI into a single workspace, powered by AI and the OneLake data lake. It streamlines data engineering, warehousing, and real-time analytics without managing complex infrastructure, designed for both professional and citizen developers. [[1](https://learn.microsoft.com/en-us/fabric/fundamentals/microsoft-fabric-overview), [2](https://azure.microsoft.com/en-us/blog/introducing-microsoft-fabric-data-analytics-for-the-era-of-ai/), [3](https://www.youtube.com/watch?v=PbBJ0UgEWzE&t=416), [4](https://www.microsoft.com/en-us/microsoft-fabric), [5](https://www.microsoft.com/en-us/microsoft-fabric/resources/data-101/what-is-fabric)] Key Features and Capabilities: - OneLake: A single, unified, SaaS-based data lake (“OneDrive for data”) that stores all organization data, reducing silos. - Unified Components: Integrates Data Factory (ingestion), Synapse (engineering/warehousing), and Power BI (reporting) into one experience. - AI Integration: Includes Copilot for creating data flows, writing SQL, and generating reports. - SaaS Experience: Simplifies setup by eliminating the need for infrastructure management like resource groups, unlike traditional Azure services. - Open Data Formats: Uses Delta Lake/Parquet formats by default, allowing data to be shared across engines without duplication. [[1](https://learn.microsoft.com/en-us/fabric/fundamentals/microsoft-fabric-overview), [2](https://www.kai-waehner.de/blog/2024/10/04/what-is-microsoft-fabric-for-azure-cloud-beyond-the-buzz-and-how-it-competes-with-snowflake-and-databricks/), [3](https://sqlschool.com/blog/azure-vs-microsoft-fabric/), [4](https://monowar-mukul.medium.com/azure-data-fabric-the-hands-on-guide-part-1-8e64df6e36ca), [5](https://azure.microsoft.com/en-us/blog/introducing-microsoft-fabric-data-analytics-for-the-era-of-ai/), [6](https://www.microsoft.com/en-us/microsoft-fabric)] More details are available here: [What is Microsoft Fabric? | Microsoft Fabric](https://www.microsoft.com/en-us/microsoft-fabric/resources/data-101/what-is-fabric)  #### Why would I want Gemini CLI with Azure? Isn’t that a Google Thing? Yes- Gemini CLI leverages the Google Cloud console and Gemini models but it is also open source and platform agnostic. Many applications are already cross-cloud so this enables familiar tools to be run natively on Microsoft Azure. #### Azure Fabric Configuration To configure your Azure Service with the base system tools- this article provides a reference: [MCP Development with Python, and Azure Fabric](https://dev.to/gde/mcp-development-with-python-and-azure-fabric-1ak1) #### Gemini CLI If not pre-installed you can download the Gemini CLI to interact with the source files and provide real-time assistance: ```shell npm install -g @google/gemini-cli ``` #### Testing the Gemini CLI Environment Once you have all the tools and the correct Node.js version in place- you can test the startup of Gemini CLI. You will need to authenticate with a Key or your Google Account: ```plaintext ▝▜▄ Gemini CLI v0.33.1 ▝▜▄ ▗▟▀ Logged in with Google /auth ▝▀ Gemini Code Assist Standard /upgrade no sandbox (see /docs) /model Auto (Gemini 3) | 239.8 MB ``` #### Node Version Management Gemini CLI needs a consistent, up to date version of Node. The **nvm** command can be used to get a standard Node environment: [GitHub - nvm-sh/nvm: Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions](https://github.com/nvm-sh/nvm) #### Agent Development Kit The [Google Agent Development Kit](https://www.google.com/search?q=Google+Agent+Development+Kit&rlz=1CAIWTJ_enUS1114&oq=what+is+the+adk+google&gs_lcrp=EgZjaHJvbWUyBggAEEUYOTIICAEQABgWGB4yCAgCEAAYFhgeMggIAxAAGBYYHjIICAQQABgWGB4yCAgFEAAYFhgeMggIBhAAGBYYHjIKCAcQABgKGBYYHjINCAgQABiGAxiABBiKBTIKCAkQABiABBiiBNIBCDMxODlqMGo3qAIAsAIA&sourceid=chrome&ie=UTF-8&mstk=AUtExfB5Oo7ZHHcDEHu7aqZiPBA2l1c-QGh5dB7xkkDPIiYcn8O1Imt2IHNR7bzA6JnyDCSDCUGpGWTeBW14namlN_QqzJLLI5-px1BE9jfSxwli6njPDPERjm5pRqNP3uC6HhUKiRcTJ1T8x5LHQrCkVxylw7QWg0N8B4dQDIcWpnVX9Gc&csui=3&ved=2ahUKEwjYu-G8p-uSAxXrv4kEHUbpLo0QgK4QegQIARAB) (ADK) is an open-source, Python-based framework designed to streamline the creation, deployment, and orchestration of sophisticated, multi-agent AI systems. It treats agent development like software engineering, offering modularity, state management, and built-in tools (like Google Search) to build autonomous agents. The ADK can be installed from here: [Agent Development Kit (ADK)](https://google.github.io/adk-docs/) #### Agent Skills Gemini CLI can be customized to work with ADK agents. Both an Agent Development MCP server, and specific Agent skills are available. More details are here: [Agent Development Kit (ADK)](https://adk.dev/tutorials/coding-with-ai/) To get the Agent Skills in Gemini CLI: ```plaintext > /skills list Available Agent Skills: - adk-cheatsheet MUST READ before writing or modifying ADK agent code. ADK API quick reference for Python — agent types, tool definitions, orchestration patterns, callbacks, and state management. Includes an index of all ADK documentation pages. Do NOT use for creating new projects (use adk-scaffold). - adk-deploy-guide MUST READ before deploying any ADK agent. ADK deployment guide — Agent Engine, Cloud Run, GKE, CI/CD pipelines, secrets, observability, and production workflows. Use when deploying agents to Google Cloud or troubleshooting deployments. Do NOT use for API code patterns (use adk-cheatsheet), evaluation (use adk-eval-guide), or project scaffolding (use adk-scaffold). - adk-dev-guide ALWAYS ACTIVE — read at the start of any ADK agent development session. ADK development lifecycle and mandatory coding guidelines — spec-driven workflow, code preservation rules, model selection, and troubleshooting. - adk-eval-guide MUST READ before running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Use when evaluating agent quality, running adk eval, or debugging eval results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold). - adk-observability-guide MUST READ before setting up observability for ADK agents or when analyzing production traffic, debugging agent behavior, or improving agent performance. ADK observability guide — Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations, and troubleshooting. Use when configuring monitoring, tracing, or logging for agents, or when understanding how a deployed agent handles real traffic. - adk-scaffold MUST READ before creating or enhancing any ADK agent project. Use when the user wants to build a new agent (e.g. "build me a search agent") or enhance an existing project (e.g. "add CI/CD to my project", "add RAG"). ``` and the ADK documentation: ```plaintext > /mcp list Configured MCP servers: 🟢 adk-docs-mcp (from adk-docs-ext) - Ready (2 tools) Tools: - mcp_adk-docs-mcp_fetch_docs - mcp_adk-docs-mcp_list_doc_sources ``` #### Where do I start? The strategy for starting multi agent development is a incremental step by step approach. First, the basic development environment is setup with the required system variables, and a working Gemini CLI configuration. Then, ADK Multi-Agent is built, debugged, and tested locally. Finally — the entire solution is deployed to Azure ACA. #### Setup the Basic Environment At this point you should have a working Python environment and a working Gemini CLI installation. All of the relevant code examples and documentation is available in GitHub. The next step is to clone the GitHub repository to your local environment: ```shell cd ~ git clone https://github.com/xbill9/gemini-cli-azure cd mulit-fabric ``` Then run **init2.sh** from the cloned directory. The script will attempt to determine your shell environment and set the correct variables: ```shell source init2.sh ``` If your session times out or you need to re-authenticate- you can run the **set\_env.sh** script to reset your environment variables: ```shell source set_env.sh ``` Variables like PROJECT\_ID need to be setup for use in the various build scripts- so the **set\_env** script can be used to reset the environment if you time-out. Finally install the packages and dependencies: ```make make install ``` #### Verify The ADK Installation To verify the setup, run the ADK CLI locally with the researcher agent: ```console xbill@penguin:~/gemini-cli-azure/multi-fabric/agents$ adk run researcher /home/xbill/.local/lib/python3.13/site-packages/google/adk/features/_feature_decorator.py:72: UserWarning: [EXPERIMENTAL] feature FeatureName.PLUGGABLE_AUTH is enabled. check_feature_enabled() Log setup complete: /tmp/agents_log/agent.20260418_155613.log To access latest log: tail -F /tmp/agents_log/agent.latest.log {"asctime": "2026-04-18 15:56:13,235", "name": "root", "levelname": "INFO", "message": "Logging initialized for researcher", "filename": "logging_config.py", "lineno": 54, "service": "researcher", "log_level": "INFO"} {"asctime": "2026-04-18 15:56:13,236", "name": "researcher.agent", "levelname": "INFO", "message": "Initialized researcher agent with model: gemini-2.5-flash", "filename": "agent.py", "lineno": 85} ``` #### Test The ADK Web Interface This tests the ADK agent interactions with a browser: ```console xbill@penguin:~/gemini-cli-azure/multi-fabric/agents$ adk web --host 0.0.0.0 /home/xbill/.pyenv/versions/3.13.13/lib/python3.13/site-packages/google/adk/features/_feature_decorator.py:72: UserWarning: [EXPERIMENTAL] feature FeatureName.PLUGGABLE_AUTH is enabled. check_feature_enabled() 2026-04-10 17:49:11,850 - INFO - service_factory.py:266 - Using in-memory memory service 2026-04-10 17:49:11,850 - INFO - local_storage.py:84 - Using per-agent session storage rooted at /home/xbill/multi-agent/agents 2026-04-10 17:49:11,850 - INFO - local_storage.py:110 - Using file artifact service at /home/xbill/multi-agent/agents/.adk/artifacts /home/xbill/.pyenv/versions/3.13.13/lib/python3.13/site-packages/google/adk/cli/fast_api.py:198: UserWarning: [EXPERIMENTAL] InMemoryCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time. credential_service = InMemoryCredentialService() /home/xbill/.pyenv/versions/3.13.13/lib/python3.13/site-packages/google/adk/auth/credential_service/in_memory_credential_service.py:33: UserWarning: [EXPERIMENTAL] BaseCredentialService: This feature is experimental and may change or be removed in future versions without notice. It may introduce breaking changes at any time. super(). __init__ () INFO: Started server process [16063] INFO: Waiting for application startup. +-----------------------------------------------------------------------------+ | ADK Web Server started | | | | For local testing, access at http://0.0.0.0:8000. | +-----------------------------------------------------------------------------+ ``` Then use the web interface — either on the local interface **127.0.0.1** or the catch-all web interface **0.0.0.0** -depending on your environment:  Special note for Google Cloud Shell Deployments- add a CORS **allow\_origins** configuration exemption to allow the ADK agent to run: ```shell adk web --host 0.0.0.0 --allow_origins 'regex:.*' ``` #### Multi Agent Design The multi-agent deployment consists of 5 agents: - Researcher - Judge - Orchestrator - Content Builder - Course Builder An overview of the multi-agent system can be found here: [Multi-Agent A2A with the Agent Development Kit(ADK), Cloud Run, Agent Skills, and Gemini CLI](https://dev.to/gde/multi-agent-a2a-with-the-agent-development-kitadk-cloud-run-agent-skills-and-gemini-cli-4n1h) #### Running/Testing/Debugging Locally The main Makefile has been extended with extensive targets for managing the agents on the local development environment. The key targets include: ```plaintext ✦ Here is the output of make help with the warnings resolved: 1 Available commands: 2 install - Install all dependencies for root, agents, and app 3 install-fabric-cli - Install Microsoft Fabric CLI and Azure extension 4 start - Start all services locally (alias for start-local) 5 stop - Stop all local services (alias for stop-local) 6 run - Start all services locally (alias for start-local) 7 local - Show local service URLs 8 status - Show status of local services and Fabric deployment 9 start-local - Start all local services in background 10 stop-local - Stop all local processes 11 test - Run all tests (pytest) 12 test-researcher - Test the Researcher agent directly 13 test-judge - Test the Judge agent directly 14 test-orchestrator - Test the Orchestrator logic 15 lint - Run linting checks (ruff) 16 deploy - Deploy stacked agents to Azure Container Apps & Fabric 17 destroy - Delete Azure Resource Group and all resources 18 endpoint - Show public service endpoint 19 clean - Remove caches and logs ``` First check for local running agents: ```console xbill@penguin:~/gemini-cli-azure/multi-fabric$ make status make[1]: Entering directory '/home/xbill/gemini-cli-azure/multi-fabric' Checking status of locally running servers... --- Network Status --- No services listening on expected ports (8080, 5173). --- Process Status --- ``` Then all the agents can be started together: ```console xbill@penguin:~/gemini-cli-azure/multi-fabric$ make start Stopping any existing server processes... Starting Unified App Backend in background... Starting Frontend dev server in background... All services started. Logs: backend.log, frontend.log Frontend: http://localhost:5173 Backend: http://localhost:8080 make status xbill@penguin:~/gemini-cli-azure/multi-fabric$ make status make[1]: Entering directory '/home/xbill/gemini-cli-azure/multi-fabric' Checking status of locally running servers... --- Network Status --- tcp 0 0 0.0.0.0:8080 0.0.0.0:* LISTEN 19549/python3 --- Process Status --- xbill 19549 10.1 2.2 251904 147036 pts/1 S 22:34 0:05 /home/xbill/.pyenv/versions/3.13.13/bin/python3 -m unified_app.app ``` The entire project can be linted and tested as unit: ```plaintext ✦ I have completed the linting and formatting task for the project. Summary of Actions: - Initial Check: Ran ruff check . and identified 10 errors, including unused imports, unsorted imports, formatting issues, and multiple statements on one line. - Automated Fix: Executed ruff check . --fix, which automatically resolved 7 of the 10 errors. - Manual Fix: Manually corrected the remaining 3 E701 errors in unified_app/app.py by splitting multiple statements onto separate lines. - Verification: Verified all checks pass with a final ruff check . execution. All Python files are now compliant with the project's linting standards. > make test ✦ I have executed make test for the project. Summary of Results: - Total Tests Collected: 29 - Test Modules Run: - agents/content_builder/tests/test_agent.py (2 passed) - agents/judge/tests/test_agent.py (3 passed) - agents/orchestrator/test_orchestrator.py (5 passed) - agents/orchestrator/test_state_capturer.py (4 passed) - agents/researcher/tests/test_agent.py (2 passed) - app/tests/test_a2a_utils.py (2 passed) - app/tests/test_api.py (3 passed) - app/tests/test_auth.py (3 passed) - app/tests/test_logging_config.py (2 passed) - app/tests/test_utils.py (3 passed) Outcome: All 29 tests passed successfully. There were a couple of minor warnings related to deprecated modules inside third-party dependencies (authlib and google.adk), which are expected and do not affect the tests. ``` And end to end tested: ```plaintext ✦ I have successfully completed the linting and testing suite for the project. Results Overview: 1. Linting (make lint): - Resolved 10 issues using ruff. - Automatically fixed 7 errors (imports/formatting). - Manually fixed 3 E701 errors in unified_app/app.py by splitting multiple statements into separate lines. - Final check: Passed. 2. Unit & Integration Tests (make test): - Executed 29 tests across all microservices and the main application. - Result: All 29 tests passed. 3. End-to-End Tests (make e2e-test): - Started the local unified backend and frontend servers. - Successfully executed the E2E pipeline for the topic: "Create a short course about the history of the internet". - The system correctly orchestrated the Researcher (gathering info), Judge (evaluating findings), and Content Builder (writing Markdown modules). - Result: Successfully generated a 5-module course. The local services have been stopped to clean up the environment. The codebase is now lint-free and verified as functionally correct. ```  And the entire agent system will run in the local environment:  #### Local Logging / Debugging Gemini CLI has full access to the local agent logs for debugging and troubleshooting: ```plaintext ✦ The end-to-end test completed successfully! The system ran the course creation pipeline ("Create a short course about the history of the internet"), executing the researcher, judge, and content builder agents, and successfully generated the final output without errors. ``` #### Deploying to Azure Fabric The project level Makefile has targets for managing the Agent deployment to serverless endpoints: A utility script check the deployment to Azure Fabric: ```console xbill@penguin:~/gemini-cli-azure/multi-fabric$ make status make[1]: Entering directory '/home/xbill/gemini-cli-azure/multi-fabric' Checking status of locally running servers... --- Network Status --- tcp 0 0 0.0.0.0:8080 0.0.0.0:* LISTEN 20808/python3 --- Process Status --- xbill 20808 4.6 2.4 631760 160836 ? Sl 22:43 0:09 /home/xbill/.pyenv/versions/3.13.13/bin/python3 -m unified_app.app make[1]: Leaving directory '/home/xbill/gemini-cli-azure/multi-fabric' --- Azure Fabric / ACA Status --- Checking Azure Container Apps status in adk-rg-fabric... (ResourceGroupNotFound) Resource group 'adk-rg-fabric' could not be found. make: *** [Makefile:124: status] Error 1 ``` You can then deploy the services: ```plaintext ✓ Shell az account show -o table || echo "Not logged in to Azure" │ │ │ │ EnvironmentName HomeTenantId IsDefault Name State TenantDefaul │ │ tDomain TenantDisplayName TenantId │ │ ----------------- ------------------------------------ ----------- -------------------- ------- ------------ │ │ ------------------- ------------------- ------------------------------------ │ │ AzureCloud 40482c55-d00d-4c6d-8903-643d76a74b9c True Azure subscription 1 Enabled xbillglitnir │ │ com.onmicrosoft.com Default Directory 40482c55-d00d-4c6d-8903-643d76a74b9c │ ✦ The deployment to Azure Container Apps (ACA) was successful! Deployment Summary: - Resource Group: adk-rg-fabric - Location: westus2 - Container Registry: adkacrpenguin.azurecr.io - Public URL: https://course-creator.icysky-8598b612.westus2.azurecontainerapps.io (https://course-creator.icysky-8598b612.westus2.azurecontainerapps.io) Verification: I have verified that the remote service is healthy and the multi-agent pipeline is responding correctly. You can now use the public URL to access your AI Course Creator. Microsoft Fabric Integration: A WorkloadManifest.xml has been generated in the fabric/ directory. To complete the Fabric integration: 1. Register your backend App in Microsoft Entra ID. 2. Add the Fabric.Extend scope. 3. Upload fabric/WorkloadManifest.xml to the Fabric Admin Portal. Your system is now fully operational in the cloud! ``` Once the containers are deployed- you can then get the endpoint: ```plaintext > make status ✦ Here is the current status of your environments: Local Services - Backend (unified_app): Running in the background (PID 20808) and listening on port 8080. - Frontend: Not currently running locally (you can start it with make start-local or make frontend-local). Azure Container Apps (Cloud Deployment) - Status: Succeeded (Running smoothly) - App FQDN: course-creator.icysky-8598b612.westus2.azurecontainerapps.io (https://course-creator.icysky-8598b612.westus2.azurecontainerapps.io) Both your local backend and your Azure cloud deployment are currently active and healthy. ``` And check the endpoint: ```plaintext > make endpoint ✦ Here is your public Azure Container Apps endpoint: https://course-creator.icysky-8598b612.westus2.azurecontainerapps.io (https://course-creator.icysky-8598b612.westus2.azurecontainerapps.io) You can use this URL to access your deployed AI Course Creator. ``` The service will be visible in the Azure console:  #### Test End to End in Azure The entire agent system is tested on the remote Azure endpoint: ```plaintext ✦ The E2E test against the cloud-deployed Azure Container Apps endpoint was successful! I have verified that your public cloud environment is fully functional and correctly orchestrating the multi-agent course creation pipeline. ``` #### Running the Web Interface Start a connection to the Cloud Run deployed app: ```plaintext https://course-creator.icysky-8598b612.westus2.azurecontainerapps.io ``` Then connect to the app :  Then use online course generator:  #### Final Gemini CLI Code Review As a final step — Gemini CLI was used for a full code review of the project: ```plaintext Overall Code Review Summary After reviewing the app and agents directories, I can say this is an exceptionally well-engineered multi-agent system. High-Level Architecture: The architecture is sophisticated and effective. The use of a main orchestrator to manage a pipeline of specialized agents (researcher, judge, content_builder) is a strong and scalable pattern. The inclusion of a research-and-refine loop with the judge agent is a standout feature that significantly enhances the quality of the final output. Key Strengths: 1. Expert ADK Usage: The project demonstrates a deep understanding of the Google ADK, using advanced features like SequentialAgent, LoopAgent, RemoteA2aAgent, structured Pydantic outputs, and agent callbacks to their full potential. 2. Excellent Prompt Engineering: The instruction prompts for all agents are clear, specific, and well-crafted. This is the foundation of the system's success. 3. Robust State Management: The custom StateCapturer agent is a brilliant, reusable utility that cleanly handles the flow of information between agents. 4. Production-Ready Features: The system includes production-grade features like environment-aware authentication for service-to-service calls, robust error handling, and detailed logging. ``` #### Summary The Agent Development Kit (ADK) was used to build a multi-agent system with A2A support using the Gemini Flash LLM Model. This application was tested locally with Gemini CLI and then deployed to Azure Fabric. Several key take-aways and lessons learned were summarized from debugging and testing the multi-agent system- including deep log reviews. Finally, Gemini CLI was used for a complete project code review.