Vertex AI Agent GardenからAI AgentをAgent Engineにデプロイしてみた

gcloud services enable \
  aiplatform.googleapis.com \
  storage.googleapis.com \
  logging.googleapis.com

Welcome to Cloud Shell! Type "help" to get started, or type "gemini" to try prompting with Gemini CLI.
Your Cloud Platform project in this session is set to my-project-id.
Use `gcloud config set project [PROJECT_ID]` to change to a different project.
export AGENT_NAME=financial-advisor-${RANDOM} && uvx agent-starter-pack==0.15.4 create ${AGENT_NAME} -d agent_engine -ag -a adk@financial-advisor && cd ${AGENT_NAME} && make install && make backend user@cloudshell:~ (my-project-id)$ export AGENT_NAME=financial-advisor-${RANDOM} && uvx agent-starter-pack==0.15.4 create ${AGENT_NAME} -d agent_engine -ag -a adk@financial-advisor && cd ${AGENT_NAME} && make install && make backend
Installed 59 packages in 1.20s

=== Welcome to Agent Garden! 🌱 ===
Powered by Google Cloud - Agent Starter Pack 

This tool will help you deploy production-ready AI agents from Agent Garden to Google Cloud!

> Fetching template: python/agents/financial-advisor
🔒 Remote template requires agent-starter-pack version 0.22.1
📦 Switching to version 0.22.1...
Installed 59 packages in 537ms
✅ Using version-locked template

📍 Agent Engine Supported Regions:
   https://cloud.google.com/vertex-ai/generative-ai/docs/agent-engine/overview#supported-regions

Enter desired GCP region (Gemini uses global endpoint by default) (us-central1): asia-northeast1
> Successfully configured project: my-project-id
> Testing GCP and Vertex AI Connection...
> ✓ Successfully verified connection to Vertex AI in project my-project-id
ℹ️  Adding 'app' object to financial_advisor/agent.py for backward compatibility

> Success! Your agent project is ready.

📖 Project README: cat financial-advisor-xxxxx/README.md
   Online Development Guide: https://goo.gle/asp-dev

🚀 To get started, run the following command:
   cd financial-advisor-xxxxx && make install && make playground
uv sync
Using CPython 3.12.3 interpreter at: /usr/bin/python3
Creating virtual environment at: .venv
Resolved 180 packages in 4ms
      Built financial-advisor @ file:///home/user/financial-advisor-xxxxx
Prepared 1 package in 1.21s
Installed 163 packages in 3.46s
 + absl-py==2.3.1
 + agent-starter-pack==0.22.1
 + aiohappyeyeballs==2.6.1
 + aiohttp==3.12.15
 + aiosignal==1.4.0
 + aiosqlite==0.21.0
 + alembic==1.16.5
 + annotated-types==0.7.0
 + anyio==4.11.0
 + arrow==1.3.0
 + attrs==25.3.0
 + authlib==1.6.5
 + backoff==2.2.1
 + binaryornot==0.4.4
 + cachetools==6.2.0
 + certifi==2025.8.3
 + cffi==2.0.0
 + chardet==5.2.0
 + charset-normalizer==3.4.3
 + click==8.3.0
 + cloudpickle==3.1.1
 + cookiecutter==2.6.0
 + cryptography==46.0.2
 + distro==1.9.0
 + docstring-parser==0.17.0
 + fastapi==0.118.0
 + fastuuid==0.13.5
 + filelock==3.19.1
 + financial-advisor==0.1.0 (from file:///home/user/financial-advisor-xxxxx)
 + frozenlist==1.7.0
 + fsspec==2025.9.0
 + google-adk==1.19.0
 + google-api-core==2.28.1
 + google-api-python-client==2.184.0
 + google-auth==2.41.1
 + google-auth-httplib2==0.2.0
 + google-cloud-aiplatform==1.126.1
 + google-cloud-appengine-logging==1.6.2
 + google-cloud-audit-log==0.3.2
 + google-cloud-bigquery==3.38.0
 + google-cloud-bigquery-storage==2.34.0
 + google-cloud-bigtable==2.32.0
 + google-cloud-core==2.4.3
 + google-cloud-discoveryengine==0.13.12
 + google-cloud-logging==3.12.1
 + google-cloud-monitoring==2.27.2
 + google-cloud-resource-manager==1.14.2
 + google-cloud-secret-manager==2.24.0
 + google-cloud-spanner==3.58.0
 + google-cloud-speech==2.33.0
 + google-cloud-storage==3.5.0
 + google-cloud-trace==1.16.2
 + google-crc32c==1.7.1
 + google-genai==1.52.0
 + google-resumable-media==2.7.2
 + googleapis-common-protos==1.70.0
 + graphviz==0.21
 + greenlet==3.2.4
 + grpc-google-iam-v1==0.14.2
 + grpc-interceptor==0.15.4
 + grpcio==1.75.1
 + grpcio-status==1.75.1
 + h11==0.16.0
 + hf-xet==1.1.10
 + httpcore==1.0.9
 + httplib2==0.31.0
 + httpx==0.28.1
 + httpx-sse==0.4.1
 + huggingface-hub==0.35.3
 + idna==3.10
 + importlib-metadata==8.7.0
 + iniconfig==2.1.0
 + jinja2==3.1.6
 + jiter==0.11.0
 + joblib==1.5.2
 + jsonschema==4.25.1
 + jsonschema-specifications==2025.9.1
 + litellm==1.76.3
 + mako==1.3.10
 + markdown-it-py==4.0.0
 + markupsafe==3.0.3
 + mcp==1.16.0
 + mdurl==0.1.2
 + multidict==6.6.4
 + nest-asyncio==1.6.0
 + nltk==3.9.2
 + numpy==2.3.3
 + openai==2.1.0
 + opentelemetry-api==1.37.0
 + opentelemetry-exporter-gcp-logging==1.9.0a0
 + opentelemetry-exporter-gcp-monitoring==1.9.0a0
 + opentelemetry-exporter-gcp-trace==1.9.0
 + opentelemetry-exporter-otlp-proto-common==1.37.0
 + opentelemetry-exporter-otlp-proto-http==1.37.0
 + opentelemetry-instrumentation==0.58b0
 + opentelemetry-instrumentation-google-genai==0.4b0
 + opentelemetry-proto==1.37.0
 + opentelemetry-resourcedetector-gcp==1.9.0a0
 + opentelemetry-sdk==1.37.0
 + opentelemetry-semantic-conventions==0.58b0
 + opentelemetry-util-genai==0.2b0
 + packaging==25.0
 + pandas==2.3.3
 + pluggy==1.6.0
 + propcache==0.3.2
 + proto-plus==1.26.1
 + protobuf==6.32.1
 + pyarrow==22.0.0
 + pyasn1==0.6.1
 + pyasn1-modules==0.4.2
 + pycparser==2.23
 + pydantic==2.12.5
 + pydantic-core==2.41.5
 + pydantic-settings==2.11.0
 + pygments==2.19.2
 + pyparsing==3.2.5
 + pytest==9.0.1
 + pytest-asyncio==1.3.0
 + python-dateutil==2.9.0.post0
 + python-dotenv==1.2.1
 + python-multipart==0.0.20
 + python-slugify==8.0.4
 + pytz==2025.2
 + pyyaml==6.0.3
 + referencing==0.36.2
 + regex==2025.9.18
 + requests==2.32.5
 + rich==14.1.0
 + rouge-score==0.1.2
 + rpds-py==0.27.1
 + rsa==4.9.1
 + ruamel-yaml==0.18.15
 + ruamel-yaml-clib==0.2.14
 + scikit-learn==1.7.2
 + scipy==1.16.2
 + shapely==2.1.2
 + six==1.17.0
 + sniffio==1.3.1
 + sqlalchemy==2.0.43
 + sqlalchemy-spanner==1.16.0
 + sqlparse==0.5.3
 + sse-starlette==3.0.2
 + starlette==0.48.0
 + tabulate==0.9.0
 + tenacity==9.1.2
 + text-unidecode==1.3
 + threadpoolctl==3.6.0
 + tiktoken==0.11.0
 + tokenizers==0.22.1
 + tqdm==4.67.1
 + types-python-dateutil==2.9.0.20250822
 + typing-extensions==4.15.0
 + typing-inspection==0.4.2
 + tzdata==2025.2
 + tzlocal==5.3.1
 + uritemplate==4.2.0
 + urllib3==2.5.0
 + uvicorn==0.37.0
 + watchdog==6.0.0
 + websockets==15.0.1
 + wrapt==1.17.3
 + yarl==1.20.1
 + zipp==3.23.0
# Export dependencies to requirements file using uv export.
(uv export --no-hashes --no-header --no-dev --no-emit-project --no-annotate > financial_advisor/app_utils/.requirements.txt 2>/dev/null || \
uv export --no-hashes --no-header --no-dev --no-emit-project > financial_advisor/app_utils/.requirements.txt) && \
uv run -m financial_advisor.app_utils.deploy \
        --source-packages=./financial_advisor \
        --entrypoint-module=financial_advisor.agent_engine_app \
        --entrypoint-object=agent_engine \
        --requirements-file=financial_advisor/app_utils/.requirements.txt

    ╔═══════════════════════════════════════════════════════════╗
    ║                                                           ║
    ║   🤖 DEPLOYING AGENT TO VERTEX AI AGENT ENGINE 🤖         ║
    ║                                                           ║
    ╚═══════════════════════════════════════════════════════════╝
    

📋 Deployment Parameters:
  Project: my-project-id
  Location: asia-northeast1
  Display Name: financial-advisor-xxxxx
  Min Instances: 1
  Max Instances: 10
  CPU: 4
  Memory: 8Gi
  Container Concurrency: 9

🌍 Environment Variables:
  GOOGLE_CLOUD_AGENT_ENGINE_ENABLE_TELEMETRY: true
  GOOGLE_CLOUD_REGION: asia-northeast1
  NUM_WORKERS: 1
  OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT: true
INFO:root:Importing financial_advisor.agent_engine_app.agent_engine

🚀 Creating new agent: financial-advisor-xxxxx
🚀 Deploying to Vertex AI Agent Engine (this can take 3-5 minutes)...
INFO:vertexai_genai.agentengines:Creating in-memory tarfile of source_packages
INFO:vertexai_genai.agentengines:Using agent framework: google-adk
INFO:vertexai_genai.agentengines:View progress and logs at https://console.cloud.google.com/logs/query?project=my-project-id.
INFO:vertexai_genai.agentengines:Agent Engine created. To use it in another session:
INFO:vertexai_genai.agentengines:agent_engine=client.agent_engines.get(name='projects/123456789012/locations/asia-northeast1/reasoningEngines/1234567890123456789')
INFO:root:Agent Engine ID written to deployment_metadata.json

✅ Deployment successful!
Service Account: service-123456789012@gcp-sa-aiplatform-re.iam.gserviceaccount.com

📊 Open Console Playground: https://console.cloud.google.com/vertex-ai/agents/locations/asia-northeast1/agent-engines/1234567890123456789/playground?project=my-project-id

export AGENT_NAME=financial-advisor-${RANDOM} && \
uvx agent-starter-pack==0.15.4 create ${AGENT_NAME} -d agent_engine -ag -a adk@financial-advisor && \
cd ${AGENT_NAME} && \
make install && \
make backend

uvx agent-starter-pack==0.15.4 create ${AGENT_NAME} -d agent_engine -ag -a adk@financial-advisor

> Fetching template: python/agents/financial-advisor
🔒 Remote template requires agent-starter-pack version 0.22.1
📦 Switching to version 0.22.1...
Installed 59 packages in 537ms
✅ Using version-locked template

📍 Agent Engine Supported Regions:
   https://cloud.google.com/vertex-ai/generative-ai/docs/agent-engine/overview#supported-regions

Enter desired GCP region (Gemini uses global endpoint by default) (us-central1): asia-northeast1
> Successfully configured project: my-project-id
> Testing GCP and Vertex AI Connection...
> ✓ Successfully verified connection to Vertex AI in project my-project-id

uv sync
Using CPython 3.12.3 interpreter at: /usr/bin/python3
Creating virtual environment at: .venv
Resolved 180 packages in 4ms
      Built financial-advisor @ file:///home/user/financial-advisor-xxxxx
Prepared 1 package in 1.21s
Installed 163 packages in 3.46s

(uv export --no-hashes --no-header --no-dev --no-emit-project --no-annotate > financial_advisor/app_utils/.requirements.txt 2>/dev/null || \
uv export --no-hashes --no-header --no-dev --no-emit-project > financial_advisor/app_utils/.requirements.txt)

uv run -m financial_advisor.app_utils.deploy \
    --source-packages=./financial_advisor \
    --entrypoint-module=financial_advisor.agent_engine_app \
    --entrypoint-object=agent_engine \
    --requirements-file=financial_advisor/app_utils/.requirements.txt

📋 Deployment Parameters:
  Project: my-project-id
  Location: asia-northeast1
  Display Name: financial-advisor-xxxxx
  Min Instances: 1
  Max Instances: 10
  CPU: 4
  Memory: 8Gi
  Container Concurrency: 9

🌍 Environment Variables:
  GOOGLE_CLOUD_AGENT_ENGINE_ENABLE_TELEMETRY: true
  GOOGLE_CLOUD_REGION: asia-northeast1
  NUM_WORKERS: 1
  OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT: true

INFO:root:Importing financial_advisor.agent_engine_app.agent_engine
🚀 Creating new agent: financial-advisor-xxxxx
🚀 Deploying to Vertex AI Agent Engine (this can take 3-5 minutes)...
INFO:vertexai_genai.agentengines:Creating in-memory tarfile of source_packages
INFO:vertexai_genai.agentengines:Using agent framework: google-adk

INFO:vertexai_genai.agentengines:Agent Engine created. To use it in another session:
INFO:vertexai_genai.agentengines:agent_engine=client.agent_engines.get(name='projects/123456789012/locations/asia-northeast1/reasoningEngines/1234567890123456789')

✅ Deployment successful!
Service Account: service-123456789012@gcp-sa-aiplatform-re.iam.gserviceaccount.com

📊 Open Console Playground: https://console.cloud.google.com/vertex-ai/agents/...