0.3.3 swept 83 lexicon patterns arm by arm and left the other ten regex-bearing modules on 0.3.2's hand-written rows. Generalising the sweep found three more, and the two on the input path matter more than the count suggests: `sanitize` is step 1 of `prepare_input`, and `MAX_SCAN_CHARS` is applied in `scan_lexicon` and `scan_output` only, so there was no cap to extrapolate to. That missing input cap is now a documented residual of its own -- extending it changes the contract for existing callers and is not something to smuggle into a ReDoS patch. Version synced in all four places + CHANGELOG. LIMITATIONS 30 -> 31 items; the 0.3.3 entry claiming the lexicon sweep's scope is corrected in place, since "the output path" was never the whole surface either. 676 tests, coverage 128/128 + 6/6 gaps, sweep clean across 150 patterns.
38 lines
1.5 KiB
TOML
38 lines
1.5 KiB
TOML
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "llm-ingestion-guard"
|
|
version = "0.3.4"
|
|
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", "openpyxl>=3.1"]
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["src/llm_ingestion_guard"]
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
pythonpath = ["src"]
|
|
addopts = "-q"
|