
phm-lite-check
io.github.PHM-Audit/phm-lite-check
Deterministic physics plausibility checks for LLM outputs and robotics data. Offline, stdlib-only.
Documentation
phm-lite-check
Deterministic physics plausibility checking for LLM outputs and robotics / embodied-AI datasets. Zero dependencies, pure standard library, Python >= 3.8.
This package is an independent, community-provided library: it is the
offline subset of the PHM physical-judgment engine (proprietary core
methods are intentionally excluded). A companion plugin
(phm-physics-check) is listed on the Dify Marketplace.
Not affiliated with, endorsed by, or sponsored by LangChain, AutoGen, or Dify. Integration adapters are community-provided.
Approved by the PyRIT creator — microsoft/PyRIT
A scorer wrapper of this package lives in
microsoft/PyRIT PR #3507
(physics_consistency_scorer). Status as of 2026-11-10:
- Six first-round correctness issues (maintainer + automated reviewer) were fixed same-day (2026-11-08).
- The PyRIT creator (richlundeen) approved the PR ("no blocking concerns remain"), verified 356 scoped tests, Ruff and the scoped type check.
- He then pushed follow-up integration commits on this PR's branch:
an upstream-main merge to clear conflicts (eb8948e) and a hook adaptation
to the new
ScoringExpectationscorer API with documented numeric checks (8a163d9). - The PR remains open pending the maintainer's merge; nothing is left open on this side.
Claimed on MCPush
Ownership-verified listing approved on MCPush: security grade A, 3 tools, no sign-in required, local & free (v1.0.1).
What it checks
Text / quantities (check_text, full_check)
- Dimensional / unit consistency (SI + common units)
- Universal speed limit (c)
- Absolute temperature floor (0 K)
- Non-negativity of mass / length / energy
- Probability range [0, 1]
- Kinematic relations (free-fall family, tolerance-checked)
- Conservation checks (energy / momentum, tolerance-checked)
Robotics records (check_robotics_record)
- Quaternion normalization (|q| within tolerance of 1.0)
- Timestamp sanity: monotonicity, duplicates, NaN/Inf, outlier gaps (possible frame loss)
- NaN / Inf scan over numeric arrays
- Unit annotation presence for common motion fields
Design guarantees
- Deterministic: same input -> same output, always reproducible.
- Zero dependencies: pure standard library; framework adapters import their host lazily.
- Verdicts: PASS / WARN / FAIL with structured violation records.
- No network calls: everything runs offline in-process.
NOTE: this package contains only the deterministic offline subset of the PHM physical-judgment engine. Proprietary core methods are intentionally excluded. (Deployment-specific deep checks are available separately via a configurable remote engine endpoint, not included in this package.)
Install
Option A — from the GitHub repo (no package index needed):
pip install git+https://github.com/PHM-Audit/phm-lite-check
Option B — from a Release wheel (faster, no git clone):
pip install https://github.com/PHM-Audit/phm-lite-check/releases/download/v1.0.0/phm_lite_check-1.0.0-py3-none-any.whl
Optional extras (once installed):
pip install "phm-lite-check[langchain]" # + langchain-core (adapter tests)
pip install "phm-lite-check[autogen]" # + autogen-agentchat
PyPI listing is planned; both options above work today.
Quickstart — library
from phm_lite_check import check_text, check_robotics_record
check_text("The drone descends at 450 km/h and confidence is 1.8.")
# {"verdict": "FAIL", "violations": [...], ...}
check_robotics_record({
"quaternion": [1.395, 0.0, 0.0, 0.0], # |q| >> 1 -> FAIL
"timestamps": [0.0, 0.1, 0.05], # not monotonic -> FAIL
"position": [1.0, 2.0], # no unit annotated -> WARN
})
Quickstart — LangChain
from phm_lite_check.integrations import langchain_tool
tools = langchain_tool.get_langchain_tools() # 3 @tool callables
agent = create_react_agent(llm, tools) # your usual wiring
Quickstart — AutoGen (v0.4+)
from autogen_agentchat.agents import AssistantAgent
from phm_lite_check.integrations import autogen_tool
assistant = AssistantAgent(
name="checked_assistant",
model_client=..., # your model client
tools=autogen_tool.get_autogen_tools(),
)
Tools exposed by both adapters
| Tool | Input | Checks |
|---|---|---|
physics_text_check | free text with quantities | unit consistency, limits, probabilities |
physics_quantity_check | value + unit | one quantity against physical law |
robotics_data_check | JSON record | quaternions, timestamps, NaN/Inf, units |
Tests
pip install -e ".[dev]"
pytest tests/ -q
License
MIT
Benchmark
The judgment rules shipped here are exercised in public by DPC-Bench v0.2 — a paired clean/corrupted physical-consistency detection benchmark (7 task families incl. a real NGSIM I-80 family, three-caliber L1/L2/L3 labels).
https://github.com/PHM-Audit/phm-lite-check/releases/download/v1.0.1/phm-lite-check-mcpb-1.0.1.mcpb# mcpb: https://github.com/PHM-Audit/phm-lite-check/releases/download/v1.0.1/phm-lite-check-mcpb-1.0.1.mcpb