llm-ingestion-pipeline-secu.../pyproject.toml
Kjell Tore Guttormsen 24e57ca10b feat(inbox): two-stage upload front-end — text formats (stage 2a)
Realistic-upload showcase (PLAN §247), first slice. A stage-1 front-end reads
dropped files and materializes them into an OKF bundle {concept_path: text} +
provenance; receive() wires extract -> import_bundle -> verdict. This slice
covers .txt/.md (stdlib only); .zip/.csv/folder/.docx/.pptx follow.

- Front-end lives in tests/ (showcase/dev-scoped), core stays stdlib-only:
  dependencies=[] untouched; python-docx/python-pptx added to the [dev] extra
  (used from stage 2d/2e), never a public [extract] extra (not v1 per PLAN).
- .txt injection -> guard T1 -> REJECT; clean .txt -> ADMIT; a dropped .md keeps
  its frontmatter so a dangerous value -> T2 REJECT; an index.* upload
  materializes onto the reserved uploads/index.md -> T4 REJECT.
- Detach-proof: neuter extraction to an empty bundle -> the poisoned upload
  ADMITs, proving the verdict depends on extraction carrying the payload.

Tests 282 -> 288.
2026-07-06 11:04:23 +02:00

38 lines
1.5 KiB
TOML

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[project]
name = "llm-ingestion-guard"
version = "0.2.0"
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)
# Showcase-only extraction parsers for the two-stage OKF inbox demo (docs/PLAN.md
# §247). Deliberately in `dev`, NOT the core `dependencies` (which stays []) and
# NOT a public `[extract]` extra — the front-end is an in-repo demonstration, not
# v1 shipped code. They pull lxml/Pillow transitively; that footprint is dev-only.
dev = ["pytest>=8", "python-docx>=1.2", "python-pptx>=1.0"]
[tool.hatch.build.targets.wheel]
packages = ["src/llm_ingestion_guard"]
[tool.pytest.ini_options]
testpaths = ["tests"]
pythonpath = ["src"]
addopts = "-q"