Metadata-Version: 2.4
Name: agi-app-tescia-diagnostic
Version: 2026.5.22
Summary: AGILAB TeSciA-style diagnostic workflow with evidence scoring and regression-plan artifacts
Author: Jean-Pierre Morard
Maintainer: Jean-Pierre Morard
License-Expression: BSD-3-Clause
Project-URL: Documentation, https://thalesgroup.github.io/agilab
Project-URL: Source, https://github.com/ThalesGroup/agilab/tree/main/src/agilab/lib/agi-app-tescia-diagnostic
Project-URL: Issues, https://github.com/ThalesGroup/agilab/issues
Project-URL: Homepage, https://github.com/ThalesGroup/agilab
Project-URL: Repository, https://github.com/ThalesGroup/agilab
Project-URL: Discussions, https://github.com/ThalesGroup/agilab/discussions
Project-URL: Changelog, https://github.com/ThalesGroup/agilab/releases
Keywords: agilab,apps,reproducibility,workflow-orchestration
Classifier: Intended Audience :: Developers
Classifier: Development Status :: 4 - Beta
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.13
Classifier: Operating System :: MacOS
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Requires-Python: >=3.13
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: agi-core<2027.0,>=2026.05.13
Dynamic: license-file

# agi-app-tescia-diagnostic

[![PyPI version](https://img.shields.io/pypi/v/agi-app-tescia-diagnostic.svg?cacheSeconds=300)](https://pypi.org/project/agi-app-tescia-diagnostic/)
[![Python versions](https://img.shields.io/pypi/pyversions/agi-app-tescia-diagnostic.svg)](https://pypi.org/project/agi-app-tescia-diagnostic/)
[![License: BSD 3-Clause](https://img.shields.io/pypi/l/agi-app-tescia-diagnostic)](https://opensource.org/licenses/BSD-3-Clause)

`agi-app-tescia-diagnostic` packages the `tescia_diagnostic_project`
AGILAB app. It is a diagnostic-method example that turns weak assumptions,
evidence, candidate fixes, and regression plans into structured artifacts.

## Purpose

Use this package to test a TeSciA-style engineering diagnostic workflow. The
default path scores bundled cases deterministically; optional local AI engines
can draft new cases, but validated scoring remains explicit and reproducible.

## Installed Project

The distribution name is `agi-app-tescia-diagnostic`; the AGILAB
project name is `tescia_diagnostic_project`. The package exposes both
`tescia_diagnostic` and `tescia_diagnostic_project` through the `agilab.apps`
entry point group, so `AgiEnv(app="tescia_diagnostic_project")` resolves the
project without a monorepo checkout.

## Install

```bash
pip install agi-app-tescia-diagnostic
```

The `agi-apps` umbrella pulls this package on Python 3.13+ because the TeSciA
diagnostic app uses the same Python floor as its packaged worker environment.
Install it directly when validating the diagnostic app package from an index or
a locally built wheel.

## Run In AGILAB

Select `tescia_diagnostic_project`, open `ORCHESTRATE`, then run `INSTALL` and
`EXECUTE` with bundled cases. Inspect the exported reports under `ANALYSIS` or
the project output directory.

## Expected Inputs

The default input is a bundled JSON case file. Optional local-AI generation
requires a configured local endpoint and fails closed if the generated JSON does
not match the expected schema.

## Expected Outputs

The app writes diagnostic reports, summary CSV files, reducer summaries, and a
`student_score` field that records whether the diagnosis, better fix, and
regression plan are supported by evidence.

## Change One Thing

Add one diagnostic case with a deliberately weak proposed fix and two candidate
regression tests. The app should keep the stronger fix only when the evidence
and tests support it.

## Scope

This is a repeatable diagnostic example. It does not execute remediation
commands, replace incident management, or silently trust model-generated
content.
