Merge pull request 'fix(onboarding): partial != detected — indication, not auto-detect (Fix B)' (#49) from feat/partial-decouple into main

backend-compliance/compliance/api/onboarding_routes.py

@@ -41,6 +41,7 @@ class AdvisorResponse(BaseModel):
     silent_intake_summary: str = ""
     headline: str = ""
     auto_detected: List[str] = Field(default_factory=list)
+    indications: List[str] = Field(default_factory=list)        # partial signal: raises strength, still asked
     inferred_assumptions: List[InferredAssumption] = Field(default_factory=list)
     rejected_assumptions: List[RejectedAssumption] = Field(default_factory=list)
     top_5_questions: List[AdvisorQuestion] = Field(default_factory=list)
@@ -66,6 +67,7 @@ def advisor_start_endpoint(req: OnboardingAdvisorRequest) -> AdvisorResponse:
         products=req.products, markets=req.markets, industry=req.industry or "")
     return AdvisorResponse(
         silent_intake_summary=si_summary, headline=result.headline, auto_detected=result.auto_detected,
+        indications=result.indications,
         inferred_assumptions=result.inferred_assumptions, rejected_assumptions=result.rejected_assumptions,
         top_5_questions=result.next_best_questions, capability_delta=result.capability_delta,
         top_measures=result.top_measures, evidence_requests=result.evidence_requests,

backend-compliance/compliance/onboarding/engine.py

@@ -75,6 +75,7 @@ def advisor_start(
     corpus_status: Optional[Dict[str, str]] = None,
     uncertain: Optional[List[Dict[str, str]]] = None,
     detected_capabilities: Optional[Sequence[str]] = None,
+    indicative_capabilities: Optional[Sequence[str]] = None,
 ) -> AdvisorResult:
     """Run the onboarding flow: (silent intake +) certs -> profile -> delta -> ranked questions + measures.
 
@@ -86,6 +87,9 @@ def advisor_start(
     required = {r.capability_id for r in target_requirements}
     profile = _profile(inp, cert_hypotheses, detected_capabilities)
     auto_detected = sorted(set(detected_capabilities or []) & required)
+    # partial/indicative signals raise assumption strength but are NOT fed into the profile -> the gap
+    # stays open and is still asked. Surface only those still relevant and NOT already auto-detected.
+    indications = sorted((set(indicative_capabilities or []) & required) - set(auto_detected))
     assess = assess_transition(
         TransitionContext(company_id=inp.company or "company", target=TransitionGoal(target_id=target_id)),
         list(target_requirements), profile)
@@ -135,6 +139,7 @@ def advisor_start(
     probably = [c for c in assess.summary.probably_covered if c not in set(auto_detected)]
     return AdvisorResult(
         inferred_assumptions=inferred, rejected_assumptions=rejected, auto_detected=auto_detected,
+        indications=indications,
         next_best_questions=next_q, capability_delta=delta, top_measures=measures,
         evidence_requests=evidence, unsupported_domains=unsupported,
         completeness_summary=rep.completeness_summary,

backend-compliance/compliance/onboarding/schemas.py

@@ -53,7 +53,8 @@ class AdvisorMeasure(BaseModel):
 class AdvisorResult(BaseModel):
     inferred_assumptions: List[InferredAssumption] = Field(default_factory=list)
     rejected_assumptions: List[RejectedAssumption] = Field(default_factory=list)
-    auto_detected: List[str] = Field(default_factory=list)                     # Silent Pass: recognised w/o asking
+    auto_detected: List[str] = Field(default_factory=list)                     # detected (concrete artifact): recognised w/o asking
+    indications: List[str] = Field(default_factory=list)                       # partial signal: raises assumption strength, STILL asked
     next_best_questions: List[AdvisorQuestion] = Field(default_factory=list)   # max 5
     capability_delta: List[str] = Field(default_factory=list)
     top_measures: List[AdvisorMeasure] = Field(default_factory=list)

backend-compliance/compliance/onboarding/silent_intake.py

@@ -66,10 +66,15 @@ class SilentIntakeResult(BaseModel):
     summary: str = ""
 
     def capability_ids(self) -> List[str]:
-        """The detected capability ids — fed into the Advisor as already-present (delta-reducing).
+        """The DETECTED capability ids (relationship == detected) — fed into the Advisor as already-present
+        (delta-reducing, not asked). ONLY observation-kind signals reach here (requirements never become a
+        present capability); a merely PARTIAL/indicative signal does NOT (see indicative_capability_ids)."""
+        return sorted({d.capability for d in self.detected_capabilities if d.relationship == "detected"})
 
-        ONLY observation-kind signals reach here (requirements never become a present capability)."""
+    def indicative_capability_ids(self) -> List[str]:
-        return sorted({d.capability for d in self.detected_capabilities})
+        """Capabilities backed only by a PARTIAL/indicative signal — they raise assumption strength but do
+        NOT replace a question (the gap stays open and is still asked, just with an indication shown)."""
+        return sorted({d.capability for d in self.detected_capabilities if d.relationship != "detected"})
 
 
 def silent_intake(

backend-compliance/compliance/services/onboarding_service.py

@@ -76,5 +76,6 @@ def run_advisor(
                           known_evidence=list(known_evidence), target=[target])
     result = advisor_start(
         inp, resolve_for_certifications(certifications, _HYP_LIB), reqs, target_id=target,
-        covers_targets=covers, corpus_status={target: "validated"}, detected_capabilities=si.capability_ids())
+        covers_targets=covers, corpus_status={target: "validated"},
+        detected_capabilities=si.capability_ids(), indicative_capabilities=si.indicative_capability_ids())
     return result, si.summary

backend-compliance/tests/test_onboarding_endpoint.py

@@ -61,6 +61,18 @@ def test_requirement_signal_does_not_auto_detect_capability():
     assert "sbom_creation" in asked or "sbom_creation" in d["capability_delta"]       # still an open gap
 
 
+def test_partial_signal_surfaces_as_indication_and_is_still_asked():
+    # a PARTIAL observation (a CI pipeline) raises assumption strength but does NOT replace the question
+    body = dict(_BODY, scanner_findings=[{"signal_id": "github_actions_ci", "source_type": "repository"}])
+    r = _client.post("/onboarding/advisor-start", json=body)
+    assert r.status_code == 200, r.text
+    d = r.json()
+    assert "secure_development_lifecycle" not in d["auto_detected"]            # partial != detected
+    assert "secure_development_lifecycle" in d["indications"]                  # but its strength is shown
+    asked = {q["capability_id"] for q in d["top_5_questions"]}
+    assert "secure_development_lifecycle" in asked or "secure_development_lifecycle" in d["capability_delta"]
+
+
 def test_unknown_target_is_404():
     body = dict(_BODY, target="NOPE")
     r = _client.post("/onboarding/advisor-start", json=body)

backend-compliance/tests/test_silent_intake.py

@@ -77,3 +77,23 @@ def test_detected_capabilities_are_not_asked_again():
                         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
+
+
+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