Files
breakpilot-compliance/backend-compliance/tests/test_silent_intake.py
T
Benjamin Admin 77459d06d6 fix(onboarding): apply hypothesis/vocabulary review decisions (ISO13485, patch-policy rationale, summary)
Two reviewed knowledge decisions (2026-06-28) + the deferred cosmetic counter, before #59.

1. ISO13485 removed from the incident_management hypothesis. ISO 13485 CAPA / quality-safety incident
   handling is NOT security incident management — the mapping was too broad and would seed false
   hypotheses for the empirical loop. A dedicated manage_quality_and_safety_incidents capability can come
   later IF a target needs it; not forced now. (ISO27001/TISAX/IEC62443 keep incident_management.)

2. patch_policy_doc -> secure_signed_update_distribution stays `partial`, but the curated rationale is
   sharpened: "indicates update governance, does not evidence signed distribution" (a patch policy is not
   proof of SIGNED distribution). New optional SignalMapping.rationale field carries the curated note.
   (github_actions_ci -> SDL and dependency_scanning -> vuln-mgmt reviewed and APPROVED as-is.)

3. Cosmetic (folded in since we touched the file): the silent-intake summary now counts detected and
   indications SEPARATELY ("N automatisch erkannt, M Indikation(en)") instead of lumping partial signals
   into "automatisch erkannt" — consistent with the three-state model just shipped.

Tests: ISO13485 no longer resolves to incident_management; summary counts split correctly. 29 onboarding
tests pass, mypy --strict clean, demo runs, check-loc 0. Runtime-visible (hypothesis resolution + summary
text) -> deploy + smoke.
2026-06-28 16:18:28 +02:00

102 lines
5.6 KiB
Python

"""Silent Knowledge Pass — recognise before asking (Phase 0).
Pins the deterministic signal->capability/product-fact mapping and the product effect that matters: when
the Silent Pass feeds detected capabilities into the Advisor, the delta shrinks and the number of
next-best questions DROPS — "we already recognised X, only these few remain" instead of a question wall.
"""
from __future__ import annotations
import os
import yaml
from compliance.onboarding import (
IntakeSignal,
OnboardingInput,
SignalMapping,
advisor_start,
resolve_for_certifications,
silent_intake,
)
from compliance.onboarding import CapabilityHypothesis
from compliance.transition_reasoning import TargetRequirement
_DIR = os.path.dirname(__file__)
_MAP = [SignalMapping(**m) for m in yaml.safe_load(
open(os.path.join(_DIR, "..", "knowledge", "onboarding", "intake_signal_map.yaml"), encoding="utf-8"))["mappings"]]
_LIB = [CapabilityHypothesis(**h) for h in yaml.safe_load(
open(os.path.join(_DIR, "..", "knowledge", "certification_hypotheses", "hypotheses.yaml"), encoding="utf-8"))["hypotheses"]]
_CRA = yaml.safe_load(open(os.path.join(_DIR, "..", "knowledge", "transition_patterns",
"transition_pattern_iso27001_to_cra_maschinenvo_v1.yaml"), encoding="utf-8"))
_REQ = [TargetRequirement(capability_id=a["capability"]) for a in _CRA["likely_covered"]]
_REQ += [TargetRequirement(capability_id=d["capability"], expected_evidence=d.get("expected_evidence", []))
for d in _CRA["delta_requirements"]]
# scanner findings (injected): a machine builder with a public CVD policy, an SBOM + signed releases in
# the repo, a product risk-assessment doc, and a cloud-connected PLC product.
_SIGNALS = [
IntakeSignal(source="website", signal="cvd_policy_present", detail="/.well-known/security.txt"),
IntakeSignal(source="repository", signal="sbom_present", detail="sbom.cdx.json"),
IntakeSignal(source="repository", signal="signed_releases"),
IntakeSignal(source="document", signal="product_risk_assessment_doc"),
IntakeSignal(source="product", signal="cloud_connectivity"),
IntakeSignal(source="product", signal="plc_sps"),
]
def test_silent_intake_is_deterministic_signal_mapping():
res = silent_intake(_SIGNALS, _MAP)
caps = set(res.capability_ids())
assert {"coordinated_vulnerability_disclosure", "sbom_creation", "secure_signed_update_distribution",
"product_cyber_risk_assessment"} <= caps
assert "sbom" in res.evidence_found # evidence already in hand -> no upload needed
facts = {f.key for f in res.product_facts}
assert "connected_to_internet" in facts and "is_machine" in facts
def test_silent_pass_reduces_the_questions():
inp = OnboardingInput(company="x", certifications=["ISO27001", "ISO9001"], target=["CRA"])
hyp = resolve_for_certifications(inp.certifications, _LIB)
without = advisor_start(inp, hyp, _REQ, target_id="CRA", corpus_status={"CRA": "validated"})
detected = silent_intake(_SIGNALS, _MAP).capability_ids()
with_pass = advisor_start(inp, hyp, _REQ, target_id="CRA", corpus_status={"CRA": "validated"},
detected_capabilities=detected)
# the whole point: recognising things automatically leaves FEWER open questions
assert len(with_pass.capability_delta) < len(without.capability_delta)
assert len(with_pass.next_best_questions) <= len(without.next_best_questions)
assert with_pass.auto_detected # recognised without asking
assert "automatisch erkannt (Intake)" in with_pass.headline
def test_detected_capabilities_are_not_asked_again():
inp = OnboardingInput(company="x", certifications=["ISO27001"], target=["CRA"])
hyp = resolve_for_certifications(inp.certifications, _LIB)
detected = silent_intake(_SIGNALS, _MAP).capability_ids()
res = advisor_start(inp, hyp, _REQ, target_id="CRA", corpus_status={"CRA": "validated"},
detected_capabilities=detected)
asked = {q.capability_id for q in res.next_best_questions}
assert "sbom_creation" not in asked and "sbom_creation" not in res.capability_delta
def test_partial_signal_is_indicative_not_detected():
# a PARTIAL signal (CI present -> secure dev lifecycle) raises assumption strength but is NOT a
# detected capability: it must NOT shrink the delta the way a concrete artifact does.
res = silent_intake([IntakeSignal(source="repository", signal="github_actions_ci")], _MAP)
assert "secure_development_lifecycle" not in res.capability_ids() # not counted as present
assert res.indicative_capability_ids() == ["secure_development_lifecycle"] # surfaced as an indication
# the summary counts detected and indications SEPARATELY (no over-claim of "automatisch erkannt")
assert "0 Fähigkeit(en) automatisch erkannt, 1 Indikation(en)" in res.summary
def test_partial_indication_does_not_remove_the_question():
inp = OnboardingInput(company="x", certifications=["ISO27001"], target=["CRA"])
hyp = resolve_for_certifications(inp.certifications, _LIB)
si = silent_intake([IntakeSignal(source="repository", signal="github_actions_ci")], _MAP)
res = advisor_start(inp, hyp, _REQ, target_id="CRA", corpus_status={"CRA": "validated"},
detected_capabilities=si.capability_ids(),
indicative_capabilities=si.indicative_capability_ids())
assert "secure_development_lifecycle" not in res.auto_detected # partial != detected
assert "secure_development_lifecycle" in res.indications # strength shown
assert "secure_development_lifecycle" in res.capability_delta # gap still open / asked