Metadata-Version: 2.4
Name: agentic-pipeline-doctor
Version: 0.1.0
Summary: AI-driven CI/CD failure analyzer and auto-remediator using Observer-Reasoner-Actuator.
Keywords: cicd,devops,langchain,llm,github-actions,gitlab-ci,jenkins,circleci
Author-email: Pipeline Doctor <doctor@pipeline.io>
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Build Tools
License-File: LICENSE
Requires-Dist: langchain>=0.1.0,<1.0.0
Requires-Dist: langchain-openai>=0.0.1
Requires-Dist: pydantic>=2.0,<3.0.0
Requires-Dist: typer[all]>=0.9.0,<1.0.0
Requires-Dist: python-dotenv>=1.0,<2.0.0
Requires-Dist: pyyaml>=6.0,<7.0.0
Requires-Dist: requests>=2.31.0,<3.0.0
Requires-Dist: gitpython>=3.1.0,<4.0.0
Requires-Dist: pytest>=7.4.0 ; extra == "dev"
Requires-Dist: pytest-cov>=4.1.0 ; extra == "dev"
Requires-Dist: black>=23.7.0 ; extra == "dev"
Requires-Dist: ruff>=0.0.280 ; extra == "dev"
Requires-Dist: mypy>=1.4.0 ; extra == "dev"
Requires-Dist: types-requests ; extra == "dev"
Requires-Dist: ipython>=8.14.0 ; extra == "dev"
Provides-Extra: dev

# agentic-pipeline-doctor

Production-ready Python package that uses LangChain + LLMs to autonomously analyze and remediate CI/CD failures using an **Observer → Reasoner → Actuator** architecture with safety guardrails.

## Install

```bash
pip install -e ".[dev]"
```

## CLI

Analyze a log:

```bash
pipeline-doctor analyze --log-path ./build.log --repo-path . --verbose
```

Heal (dry-run by default unless guardrails allow operations):

```bash
pipeline-doctor heal --log-path ./build.log --repo-path . --dry-run
```

## Library

```python
from agentic_pipeline_doctor import PipelineDoctor

doctor = PipelineDoctor(repo_path=".", log_path="./build.log")
result = doctor.analyze()
print(result.report)
```

## Docs

- `QUICKSTART.md`
- `ARCHITECTURE.md`
- `PROJECT_STRUCTURE.md`
- `IMPLEMENTATION_SUMMARY.md`


