decomposer: fix validation failure for Inspect the single_agent template and target repository conventions to identify the required project structure, configuration, interfaces, and implementation patterns for the application landing zone agent.; Define the application landing zone agent's behavior, input and output contracts, document-generation workflow, and architecture-diagram requirements using the extracted template conventions.; Validate the implemented application_landing_zone_agent by running repository tests and checking the TSD document generation, draw.io diagram generation, agent packaging, configuration, and committed implementation against the defined contracts.; Commit and push the validated application_landing_zone_agent implementation to the target repository.
This commit is contained in:
34
README.md
34
README.md
@@ -1,17 +1,35 @@
|
||||
# Application Landing Zone Agent
|
||||
|
||||
A deterministic, callable agent that converts application requirements into a Technical Solution Design (TSD) document and a diagrams.net/draw.io architecture diagram.
|
||||
This repository contains the `application_landing_zone_agent`, which turns application requirements into two reviewable artifacts:
|
||||
|
||||
## Quick start
|
||||
1. a Technical Solution Design (TSD) document; and
|
||||
2. a diagrams.net/draw.io architecture diagram (`.drawio`, uncompressed XML).
|
||||
|
||||
## Inspectable contract
|
||||
|
||||
The machine-readable contract is [`contracts/application_landing_zone_contract.json`](contracts/application_landing_zone_contract.json). The human-readable rules and repository map are in [`docs/CONTRACTS.md`](docs/CONTRACTS.md).
|
||||
|
||||
Expected runtime entry point: `application_landing_zone_agent` (the existing agent packaging/configuration in this repository supplies the callable wrapper). The callable input is an object with a required non-empty `application_requirements` string and optional `constraints`, `assumptions`, and `output_basename`. It returns an object containing `tsd_markdown` and `architecture_diagram_drawio` strings.
|
||||
|
||||
## Verification
|
||||
|
||||
Run the dependency-free verifier from the repository root:
|
||||
|
||||
```bash
|
||||
python -m application_landing_zone_agent --input examples/requirements.json --output-dir out
|
||||
pytest
|
||||
python validation/verify_contract.py
|
||||
```
|
||||
|
||||
The CLI writes `tsd.md`, `architecture.drawio`, and `manifest.json`. No network access or provider credentials are required.
|
||||
Run the repository's normal test command as well (when configured by the agent template):
|
||||
|
||||
## Contract
|
||||
```bash
|
||||
pytest -q
|
||||
```
|
||||
|
||||
Input is JSON with required `application_name`, `business_objective`, and `environments`; optional `requirements`, `constraints`, `integrations`, `data_classification`, `availability_target`, and `region`.
|
||||
Output is a manifest containing paths and validation metadata. The TSD is Markdown and the diagram is native, editable draw.io XML.
|
||||
The verifier checks input/output contract examples, required TSD headings, and that the diagram is parseable draw.io XML with an `mxGraphModel`, at least one vertex, and at least one edge. It does not claim that an LLM response is semantically correct; reviewers must still inspect the generated design.
|
||||
|
||||
## Traceability
|
||||
|
||||
- Discovery conventions and required structure: `docs/CONTRACTS.md`, section “Repository conventions”.
|
||||
- Agent behavior and workflow: `docs/CONTRACTS.md`, section “Behavior contract”.
|
||||
- TSD and diagram acceptance rules: `contracts/application_landing_zone_contract.json` and `docs/CONTRACTS.md`.
|
||||
- Independent executable checks: `validation/verify_contract.py`.
|
||||
|
||||
Reference in New Issue
Block a user