feat: the solution architecture agent on the shared Execution engine

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>
This commit is contained in:
2026-10-21 19:49:28 +01:00
commit c84dbdea20
127 changed files with 14672 additions and 0 deletions

11
.agents/plans/README.md Normal file
View File

@@ -0,0 +1,11 @@
# Plans
One directory per iteration.
| # | Directory | Status | What it is |
| --- | --- | --- | --- |
| 1 | `iter-01-on-the-engine/` | step 1 built 2026-10-20 | The reference agent's subject as a Workflow on the shared Execution engine, in the operating model agent's pattern, behind the Orchestration engine |
Each iteration has a `MAP.md` (intent, each step's status, sources of truth) and `steps/step-N.md`, written when a step is finished. A step with no file is not done.
The reference's own history, iterations 1 to 10, is in `../gcp_solution_architecture_agent/.agents/plans/`.

View File

@@ -0,0 +1,25 @@
# Plan Map
**Iteration:** 1, on the engine
**Intent:** The reference agent's subject, cloud solution architecture, as an agent in the operating model agent's pattern: the shared Execution engine and one Workflow, called through the Orchestration engine, its files passed on to the operating model agent.
**Status:** step 1 built 2026-10-20
## Decided by the owner, 2026-10-20
- A new agent in `solution_architecture_agent/`, copied from `gcp_solution_architecture_agent/` and aligned to `tom_analysis/`'s pattern. The reference is left as it is.
- Every request reaches it through the Orchestration engine, and its output is passed to the operating model agent there.
## Sources of truth
- `CONTEXT.md` and `docs/adr/`, from the reference.
- `../orchestration_engine/tests/reference_workflow/`: the engine's example of this Workflow, which `app/solution_architecture/` was brought from.
- `../orchestration_engine/docs/adr/0003-one-orchestration-engine-above-the-agents.md`.
- `../tom_analysis/app/operating_model/digest.py`: what the operating model agent reads of this agent's files.
## Status
| Step | What | Done when | Status |
| --- | --- | --- | --- |
| 1 | The agent on the engine: its folder, `app/` as the Workflow, the image, on the local platform behind the Orchestration engine | A pre-approved Execution on the agent's own roles, Skills and provider bundle delivers every file the operating model agent digests; the container answers on the platform | built (`steps/step-1.md`) |
| 2 | A run with real models through the Orchestration engine, then the sequence into the operating model agent | One request for `architecture_and_operating_model` yields both sets of Deliverables under one Customer case | planned |
| 3 | The evaluation harness on the engine, from the reference's `eval/` | The reference's cases run against this agent | planned |

View File

@@ -0,0 +1,30 @@
# Step 1: the agent on the engine
Built 2026-10-20.
## What was built
- **The folder,** copied from `../gcp_solution_architecture_agent` without its engine: `agents/`, `providers/`, `skills/`, `docs/`, `CONTEXT.md`, `k8s/`, `scripts/` and `eval/datasets/`. Left behind: its `app/` (the engine is now `../orchestration_engine`), its tests and evaluation harness (written against the old `app.*` 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_for` builds 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's `serve` and `create_app` took only a fixed Workflow; they now take `build`, 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 to `app.solution_architecture.modules`.
- **Packaging as the operating model agent's:** `pyproject.toml` (depends on `execution-engine`), a `Dockerfile` taking 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-architecture` in 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 routes `solution_architecture` to it, and the sequence `architecture_and_operating_model` to 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 `carrying` script.
- **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; `ruff` and `mypy` clean. 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 `/health` with 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.