The reference agent's subject, cloud solution architecture, as an agent in the operating model agent's pattern: the Execution engine (from orchestration_engine) and one Workflow in app/solution_architecture, built for the settings and provider bundle by assembly.workflow_for. Copied from gcp_solution_architecture_agent at 8b397cd without its own engine: its role files, Skills, provider bundle, ADRs, vocabulary, scripts and evaluation datasets. The image takes the engine from a named build context and installs Terraform. It is called through the Orchestration engine, and its files are what the operating model agent digests. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
18 lines
1.0 KiB
Markdown
18 lines
1.0 KiB
Markdown
# Solution architecture agent
|
|
|
|
Turns a request for a cloud solution into a reviewed architecture: scope, requirements, the products chosen, a Target architecture with its Checks, Terraform, validation, a solution guide and a work breakdown structure. Google Cloud is the first provider (`providers/gcp.yaml`).
|
|
|
|
It is the Execution engine (`../orchestration_engine`) and one Workflow, `app/solution_architecture/`. Requests reach it through the Orchestration engine; its delivered files are what the operating model agent (`../tom_analysis`) starts from.
|
|
|
|
Vocabulary is in [CONTEXT.md](CONTEXT.md), decisions in [docs/adr/](docs/adr/), and what has been built in [.agents/plans/](.agents/plans/README.md).
|
|
|
|
```bash
|
|
python3 -m venv .venv
|
|
.venv/bin/pip install -e ../orchestration_engine --config-settings editable_mode=compat
|
|
.venv/bin/pip install -e '.[dev]'
|
|
.venv/bin/python -m pytest -q
|
|
.venv/bin/python -m app.main # the A2A server
|
|
```
|
|
|
|
The image: `podman build --build-context engine=../orchestration_engine -t solution-architecture .`
|