llm-ingestion-pipeline-secu.../pyproject.toml
Kjell Tore Guttormsen a9c4ccd8c7 feat: scaffold package + report and sanitize modules (TDD)
Build order steps 1-2 of docs/PLAN.md:
- pyproject.toml (llm-ingestion-guard, stdlib-only core, extras [ml]/[judge]/[dev]), LICENSE (MIT)
- report: Finding/Report/Severity/Source shared type (pure data)
- sanitize: carrier stripping (zero-width, BIDI, Unicode-tag, HTML comment,
  data: URI) with the byte-identical / removes-only invariant
- docs/PLAN.md: v1 implementation plan (positioning A, gap-expanded scope,
  llm-security reuse map)

15 tests passing.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01K8GmKRCdsPjWYAKWsNgeQS
2026-07-04 09:24:20 +02:00

34 lines
1.1 KiB
TOML

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[project]
name = "llm-ingestion-guard"
version = "0.1.0"
description = "A minimal, dependency-light defensive layer for LLM ingestion pipelines — the write-time siblings of query-time chatbot guardrails."
readme = "README.md"
requires-python = ">=3.10"
license = { file = "LICENSE" }
authors = [{ name = "Kjell Tore Guttormsen" }]
keywords = ["llm", "security", "prompt-injection", "rag", "ingestion", "guardrails", "write-time"]
classifiers = [
"Development Status :: 3 - Alpha",
"Intended Audience :: Developers",
"License :: OSI Approved :: MIT License",
"Programming Language :: Python :: 3",
"Topic :: Security",
]
dependencies = [] # stdlib-only core — see design principle 1
[project.optional-dependencies]
ml = [] # pluggable embedding/classifier detectors (placeholder)
judge = [] # LLM-judge / source-grounding implementation (placeholder)
dev = ["pytest>=8"]
[tool.hatch.build.targets.wheel]
packages = ["src/llm_ingestion_guard"]
[tool.pytest.ini_options]
testpaths = ["tests"]
pythonpath = ["src"]
addopts = "-q"