assurance-core

Did your agent read everything it was supposed to read?

Every tool call can return 200 and the answer still be built on two thirds of the data.

Groundedness checks the output against the input. This checks the input against the question.

pip install assurance-core

from assurance_core.coverage import Coverage

Coverage.of(
    expected=["msa.md", "amendment-1.md", "amendment-2.md"],  # what the question spans
    found=["msa.md"],                                          # what your retriever returned
    where="the retrieved set",
).summary()

# '1 of 3 items — not in the retrieved set: amendment-1.md, amendment-2.md'

Zero dependencies · Python 3.10+ · no model decides any of it

Use it for

Keys are anything you can name, so the same three lines cover:

	expected	found
RAG	documents the question spans	chunks the retriever returned
Code review agents	`git diff --name-only`	files the agent opened
Compliance	controls in scope	controls with evidence
Data pipelines	partitions declared	partitions loaded
Eval harnesses	cases declared	cases actually run
Batch jobs	records enumerated	records processed

Six runnable examples in examples/, held green by CI.

A gap is six different facts, not one

Most tools give you one missing bucket. It throws away the only thing you need — what to do next.

	means	so
`missing`	nothing matched it	chase the owner
`gone`	a tombstone says it was here	that's an incident
`ambiguous`	two candidates	a human picks; we won't
`unreadable`	present, nothing legible	untested, not absent
`unauthorized`	present, you may not see it	escalate the task, not the answer
`truncated`	the listing hit a cap	the denominator is wrong

A capped "24 of 24 — complete" is worse than no number at all, so truncated makes complete false on its own. We don't know what we didn't see is not nothing.

The wording is deliberate too: "not in this folder", never "missing". The first is a fact about a directory listing. The second is a guess about the world.

No model, and it's gated not claimed

Every module is walked by an AST test that fails on a model or service import. CI runs it on 3.10 – 3.13, then imports all sixteen modules from an installed copy and asserts nothing leaked into sys.modules.

Swap the model and the prose changes. The arithmetic doesn't.

Modules


`coverage`	Did the worker read everything the task required?
`staleness`	Do recorded figures still match the source?
`admission`	Should this source inform the answer, given provenance?
`verification` · `task_contract` · `run_outcome`	What was done meant to be, and what happened?
`policy` · `principal` · `worker` · `effects`	Who may have which worker produce which effect?
`rule_of_two` · `run_budget`	Too many risk properties at once? Limits enforced by code?
`report_period` · `sequence` · `semantic_checks`	Which month, which series, which figure

Honest limits

It will not derive your expected set. That's your declaration on purpose — a denominator a tool invents is one nobody can argue with
Many conditions still have no verifier, so the honest answer stays complete but unverified
Source admission is provenance-only — inert on a corpus with no tombstones or supersessions
Staleness needs a prior artifact record, which this library does not provide
Not a runtime, an agent framework, or anything that does something on its own

In 0.3.0

Coverage(expected=..., found=...) without missing used to report complete is True on 11 of 12. The library that exists to stop successful-looking wrong answers had an API that made one. Coverage.of() now derives the gap, unaccounted blocks completion, and read counts the intersection. If you build Coverage(...) directly, move to Coverage.of(...).

Family

assurance-cli — same checks as a command, for CI · assurance-mcp — same checks as MCP tools

Upstream is I-Ops; this repo is a publication, never a source. Apache-2.0 · Contributing · Security

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

assurance_core-0.3.2.tar.gz (99.7 kB view details)

Uploaded Aug 29, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

assurance_core-0.3.2-py3-none-any.whl (79.5 kB view details)

Uploaded Aug 29, 2026 Python 3

File details

Details for the file assurance_core-0.3.2.tar.gz.

File metadata

Download URL: assurance_core-0.3.2.tar.gz
Upload date: Aug 29, 2026
Size: 99.7 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for assurance_core-0.3.2.tar.gz
Algorithm	Hash digest
SHA256	`388329aa986fae9ab595ee08cd0538d1d1aab23d918c615e3d0fea68b63a32b8`
MD5	`bd4101be4b746ce307707313f6687624`
BLAKE2b-256	`a375220a37ff447782437488c591f4d41641f81e7f255cd423f5264676146886`

See more details on using hashes here.

Provenance

The following attestation bundles were made for assurance_core-0.3.2.tar.gz:

Publisher: publish.yml on i-ops-hq/assurance-core

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: assurance_core-0.3.2.tar.gz
- Subject digest: 388329aa986fae9ab595ee08cd0538d1d1aab23d918c615e3d0fea68b63a32b8
- Sigstore transparency entry: 2643846985
- Sigstore integration time: Aug 29, 2026
Source repository:
- Permalink: i-ops-hq/assurance-core@2e673c16512e3d21bb82d803942d48df1e86a880
- Branch / Tag: refs/tags/v0.3.2
- Owner: https://github.com/i-ops-hq
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@2e673c16512e3d21bb82d803942d48df1e86a880
- Trigger Event: push