Files
magnus919_agent-skills/spring-ai/README.md
T
Magnus HedemarkandGitHub 3c0a21493a feat(spring-ai): add offline integration diagnostics (#508)
* feat(skill): add spring ai diagnostics

* fix(spring-ai): harden project compatibility diagnostics

* Register Spring AI skill and normalize metadata

* fix(spring-ai): scope Maven versions to dependency elements

* fix(spring-ai): validate the shipped diagnostic fixture

* docs(spring-ai): state the limits of static diagnostics

* docs(spring-ai): clarify warning exit semantics

* test(spring-ai): load the sibling diagnostic module explicitly

* fix(spring-ai): ignore Java block comments in diagnostics

* fix(spring-ai): preserve Java text block contents
2026-09-14 17:34:07 -04:00

44 lines
2.3 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# spring-ai — Diagnose Spring AI projects before they surprise you
## Why Install This Skill
Spring AI projects combine fast-moving framework APIs with model providers, retrieval stores, memory, tools, and streaming. A project can compile while leaking conversation context, logging prompts, executing an unauthorized tool, or treating partial output as complete.
This skill gives your agent a read-only diagnostic workflow for actual Maven and Gradle projects. It reports build versions, configuration hazards, source-level integration clues, and actionable findings as machine-readable JSON so you can retain evidence with a commit or incident record.
## What You Get
| Path | Purpose |
|---|---|
| `SKILL.md` | Version posture, workflow, boundaries, and recovery expectations. |
| `scripts/spring_ai_check.py` | Stdlib-only Maven/Gradle/config/source diagnostic CLI. |
| `scripts/test_spring_ai_check.py` | Offline tests for parsing, findings, JSON, and error behavior. |
| `references/compatibility-and-setup.md` | Current setup checks and version-sensitive API notes. |
| `references/integration-boundaries.md` | ChatClient, memory, retrieval, tools/MCP, streaming, and observability checks. |
| `references/source-index.md` | Official Spring AI and Spring Boot URLs with verification date. |
| `examples/minimal-project/` | Static diagnostic fixture used by the tests; not a runnable application. |
| `evals/evals.json` | Seven schema-v1 output-quality cases. |
## Quick Start
No API key is required for diagnostics:
```sh
python3 spring-ai/scripts/spring_ai_check.py --root ./my-spring-app --json
```
Use `--strict` in CI when warnings should fail the check. The tool never contacts a model provider.
## Triggers
- Diagnose Spring AI Maven or Gradle compatibility and configuration.
- Inspect ChatClient/advisor, retrieval, memory, tool/MCP, streaming, or observability integration.
- Prepare a local Spring AI smoke-test or troubleshoot a failed integration.
## Requirements
- Python 3.8+ standard library.
- A Maven or Gradle project directory for useful results.
- Maven/Gradle and provider credentials only when running the projects own tests; the diagnostic CLI does not need them.
- Re-check official documentation for upgrades; supported documentation posture is Spring AI 2.0.1 current stable and 1.0.9 maintenance reference as verified 2026-09-14.