Import a Google ADK agent — one agent on Gemini
The Agent Config of an application built on Google’s Agent Development Kit —
one agent on Gemini, with the Google Search tool ADK ships — drafted into
Aggrega files by aggrega import, with the application’s image answered once
in an answers file, and built for Docker Compose.
Import a Google ADK agent walks it step by step: the command, what it asks for, the files it writes and why each line is there, the build, and the agent running. This folder holds each stage of that walkthrough:
| folder or file | what it holds |
|---|---|
source/ | the agent’s configuration, support_agent/root_agent.yaml, the .aggrega-config.yaml that makes the folder a workspace, and support_agent/import-answers.yaml, the values no configuration holds: the application’s image, and the name of the Kubernetes Secret a build for Kubernetes reads the Gemini API key from |
draft/ | the files aggrega import support_agent --target compose wrote, unchanged, release.lock included, and what it printed: stdout.txt on standard output, import.txt on standard error |
The configuration is written for this example. The application’s code and the environment file ADK’s scaffold writes are not part of it: the import never reads either, and the Release names the image the application runs in.
In a checkout of the documentation repository, check.sh runs the import
again, compares what it writes and prints with draft/, compares the blocks
the walkthrough quotes with these files, and validates and builds what the
import wrote. It needs the standard-library catalog
(where to get one)
checked out beside this repository, or its directory named in
AGGREGA_CATALOG_DIRS.
Scaffold the example
You can run this example’s import with the commands below, or have your AI assistant run it for you.
Write the example into a new folder named after it:
aggrega scaffold --example import-google-adkIt then prints the commands to run next. The first changes into the new folder:
cd import-google-adkBuild
The import drafts the Aggrega files beside the project, in source/. It weighs
the project against the standard-library catalog, which the workspace’s default
registry publishes as a signed snapshot: the first import fetches it, verifies
it, keeps it in the workspace’s content cache and names it by its digest in the
record it writes beside the drafts. A workspace that names its own catalog
folders — in AGGREGA_CATALOG_DIRS, or under workspace.catalog_dirs —
imports against those instead. The import reads the image from
support_agent/import-answers.yaml, then pulls what the drafted Release
depends on, so the build follows at once:
cd sourceaggrega import support_agent --target composeaggrega build --release release.yamlThe image the example names stands for one you build from your project; building it and running the stack are in the walkthrough linked above.
With an AI assistant
An AI assistant set up with Aggrega’s tools can do the same: paste this prompt into it.
Use the Aggrega tools only, and create no folder yourself. If the Workspace folder holds no `import-google-adk` folder yet, call the `scaffold` tool once with `example` set to `import-google-adk` and no `dir`: it writes the example into a new `import-google-adk` folder, whose `source` folder holds what this example imports. Then call the `import` tool with `workspace_root` set to `import-google-adk/source`, `source` set to `support_agent` and `target` set to `compose`: it reads the answers it needs from `import-answers.yaml` inside the `support_agent` folder, writes its drafts into `import-google-adk/source` and pulls what they need. Then call the `validate` tool with `workspace_root` set to `import-google-adk/source` and `release` set to `release.yaml`, and the `build` tool with `workspace_root` set to `import-google-adk/source`, `release` set to `release.yaml` and `write` set to true. Tell me which files the build wrote; they are under `import-google-adk/source/dist/`.Test it
With the stack running as the walkthrough runs it, on the image its
Dockerfile builds, send the agent a message at the port the Release
publishes:
curl -sS -X POST http://127.0.0.1:8000/run -H 'Content-Type: application/json' \ -d '{"app_name": "support_agent", "user_id": "u1", "session_id": "s1", "new_message": {"role": "user", "parts": [{"text": "Where is my order 1234? Answer in one short sentence."}]}}'The run’s Gemini key was a placeholder, so the request answered HTTP 500,
Internal Server Error, and the service’s log names Gemini’s refusal:
google.genai.errors.ClientError: 400 INVALID_ARGUMENT. {'error': {'code': 400, 'message': 'API key not valid. Please pass a valid API key.', 'status': 'INVALID_ARGUMENT', [… omitted: the error's details]}}Imported with --target helm, on the image pushed to a registry the cluster
reads, as
the walkthrough
shows, the agent answers the same message at the same address once a local
port is forwarded to its Service:
kubectl port-forward -n <namespace> svc/support-agent-default 8000:8000