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>
3.3 KiB
3.3 KiB
Step 1: the agent on the engine
Built 2026-10-20.
What was built
- The folder, copied from
../gcp_solution_architecture_agentwithout its engine:agents/,providers/,skills/,docs/,CONTEXT.md,k8s/,scripts/andeval/datasets/. Left behind: itsapp/(the engine is now../orchestration_engine), its tests and evaluation harness (written against the oldapp.*modules), its plans and scratch (its history stays with it), its CI workflows and requirements files. app/solution_architecture/: the Workflow and its subject's modules, from the engine's example of them (tests/reference_workflow), imports renamed.assembly.workflow_forbuilds the Workflow for the settings and the provider bundle: the Terraform runner and local tools, the pillar advisors, whether published modules may be used, and the reviews before a submission.app/main.py:serve(WORKFLOW, ROOT, build=workflow_for). The engine'sserveandcreate_apptook only a fixed Workflow; they now takebuild, used for the assembly while the card describes the Workflow (../orchestration_engine/execution_engine/main.py, with a test).scripts/: imports moved to the engine and toapp.solution_architecture.modules.- Packaging as the operating model agent's:
pyproject.toml(depends onexecution-engine), aDockerfiletaking the engine from a named build context and installing Terraform,.dockerignore,.gitignore,CLAUDE.md,README.md, these plans.git init, no commit. - Tests: the agent assembled from its own folder, every role file present; a whole pre-approved Execution on a scripted runtime, from a small complete spec, delivering every file the operating model agent digests and the solution guide.
- On the local platform:
solution-architecturein the dev kit's personal compose files (port 10040), as the operating model agent is, with Google Cloud's remote MCP servers on and reached with the mounted credentials. The Orchestration engine routessolution_architectureto it, and the sequencearchitecture_and_operating_modelto it and then to the operating model agent.
What differed from the plan
- The sample scope is refused by the real scoping Skill. The engine's tests skip scoping with a scripted shortcut; here the catalogue's essential fields must be settled, and a field that binds must be carried by a requirement. The test starts from a small complete spec and carries its four binding fields with the engine's own
carryingscript. - The schema review is real. With Terraform installed it reads the sample's placeholder resource types against the Google provider and refuses them once; the scripted target architect submits again in the same run.
Verified
- 2 tests pass;
ruffandmypyclean. The engine: 552 tests pass. - The scripted Execution's files, named as the engine publishes them as A2A artifacts, with the Orchestration engine's completion record, were given to the operating model agent's real digest (
digest.architecture). It read two Items from the components, the Customer case, and the architecture Execution as their source. - The container answers
/healthwith no MCP discovery gaps.
Not done
- No run with real models yet (step 2).
- The reference's evaluation harness is not ported (step 3); its datasets are copied.
k8s/is as the reference had it.