feat(review-workflow): raise A-bar with capability, sweep, live-state, and role-boundary proofs (#179)

Extends review_proofs.py with the four #179 proofs, the successor set to
the #173 checkout/inventory proofs:

- assess_capability_evidence: a capability claim (review_pr, merge_pr, ...)
  counts only with exact evidence citing gitea_resolve_task_capability
  output or equivalent runtime context; no claims at all fails closed.
- assess_sweep_evidence: secret/provenance sweeps must state the exact
  command/script/pattern/named method, the scope scanned, and a boolean
  result; vague summaries are downgraded and a missing sweep fails closed.
- assess_live_state_recheck: an explicit pre-mutation recheck must prove
  the PR is still open, the live head equals the pinned head (full
  40-hex), the base branch is unchanged, and blocking review state was
  checked and absent; not performing it fails closed.
- assess_role_boundary: a reviewer run using an author namespace (or vice
  versa) is clean only with an explicit justification; unreported
  namespace usage fails closed.

build_final_report now takes the four proofs as keyword arguments: any
missing or failed proof downgrades the grade, merge_allowed additionally
requires the proven live-state recheck, and a merge performed without it
is a blocked violation. Existing #173 semantics are unchanged otherwise;
gates only get stricter.

tests/test_review_proofs.py adds 29 tests covering the issue's harness
assertions: capability claims without evidence downgraded, vague sweeps
downgraded, missing/stale live-state recheck downgrades and blocks merge
(violation when a merge is claimed anyway), unjustified author-namespace
use downgraded, and the #173 positive baseline preserved.

SKILL.md sections F/G and the review-pr/merge-pr templates now require the
capability evidence, exact sweep, pre-verdict and pre-merge live-state
rechecks, and reviewer-namespace discipline.

Closes #179

Co-Authored-By: Claude Fable 5 <[email protected]>

tests/test_review_proofs.py

@@ -21,10 +21,13 @@ import unittest
 sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
 
 from review_proofs import (  # noqa: E402
+    assess_capability_evidence,
     assess_controller_handoff,
     assess_inventory_completeness,
+    assess_live_state_recheck,
     assess_role_boundary,
     assess_self_review_contamination,
+    assess_sweep_evidence,
     assess_validation_report,
     build_final_report,
     pr_inventory_trust_gate,
@@ -116,6 +119,63 @@ def _good_role_boundary():
     )
 
 
+def _good_capability_evidence():
+    return assess_capability_evidence([
+        {
+            "task": "review_pr",
+            "allowed": True,
+            "evidence_source": (
+                "gitea_resolve_task_capability(review_pr) output: "
+                "allowed_in_current_session=true, profile prgs-reviewer"
+            ),
+        },
+        {
+            "task": "merge_pr",
+            "allowed": True,
+            "evidence_source": (
+                "gitea_resolve_task_capability(merge_pr) output: "
+                "allowed_in_current_session=true, profile prgs-reviewer"
+            ),
+        },
+    ])
+
+
+def _good_sweep(**overrides):
+    sweep = {
+        "command": (
+            "git diff prgs/master...HEAD | grep -inE "
+            "'password|token|secret|api[_-]?key|authorization|bearer|https?://'"
+        ),
+        "scope": "full PR diff against prgs/master",
+        "clean": True,
+    }
+    sweep.update(overrides)
+    return assess_sweep_evidence(sweep)
+
+
+def _good_live_state(**overrides):
+    recheck = {
+        "pr_state": "open",
+        "pinned_head_sha": PINNED,
+        "live_head_sha": PINNED,
+        "pinned_base_ref": "master",
+        "live_base_ref": "master",
+        "blocking_change_requests": False,
+    }
+    recheck.update(overrides)
+    return assess_live_state_recheck(recheck)
+
+
+def _good_role_boundary_179(**overrides):
+    kwargs = {
+        "task_role": "reviewer",
+        "namespaces_used": ["gitea-reviewer"],
+        "justification": None,
+    }
+    kwargs.update(overrides)
+    return assess_role_boundary(**kwargs)
+
+
 class TestCheckoutProof(unittest.TestCase):
     """Required behavior 1 + 2: prove HEAD == pinned PR head or stop."""
 
@@ -466,6 +526,9 @@ class TestFinalReport(unittest.TestCase):
             "identity_eligible": True,
             "merge_performed": False,
             "issue_status_verified": True,
+            "capability_evidence": _good_capability_evidence(),
+            "sweep": _good_sweep(),
+            "live_state": _good_live_state(),
             "role_boundary": _good_role_boundary(),
         }
         kwargs.update(overrides)
@@ -879,5 +942,209 @@ class TestPRInventoryTrustGate(unittest.TestCase):
         self.assertTrue(res["corroborated"])
 
 
+class TestCapabilityEvidence(unittest.TestCase):
+    """#179 gap 1: capability claims need exact evidence."""
+
+    def test_evidence_backed_claims_are_proven(self):
+        result = _good_capability_evidence()
+        self.assertTrue(result["proven"])
+        self.assertEqual(result["reasons"], [])
+
+    def test_claim_without_evidence_source_is_not_proven(self):
+        result = assess_capability_evidence([
+            {"task": "review_pr", "allowed": True, "evidence_source": ""},
+        ])
+        self.assertFalse(result["proven"])
+        self.assertTrue(any("evidence" in r.lower() for r in result["reasons"]))
+
+    def test_no_claims_at_all_fails_closed(self):
+        result = assess_capability_evidence([])
+        self.assertFalse(result["proven"])
+
+    def test_disallowed_task_is_not_proven(self):
+        result = assess_capability_evidence([
+            {
+                "task": "merge_pr",
+                "allowed": False,
+                "evidence_source": "gitea_resolve_task_capability output",
+            },
+        ])
+        self.assertFalse(result["proven"])
+
+
+class TestSweepEvidence(unittest.TestCase):
+    """#179 gap 2: secret/provenance sweep must be exact."""
+
+    def test_exact_sweep_is_proven(self):
+        result = _good_sweep()
+        self.assertEqual(result["verdict"], "exact")
+        self.assertTrue(result["proven"])
+
+    def test_vague_sweep_without_command_is_downgraded(self):
+        result = _good_sweep(command="")
+        self.assertEqual(result["verdict"], "vague")
+        self.assertFalse(result["proven"])
+
+    def test_sweep_without_scope_is_downgraded(self):
+        result = _good_sweep(scope="")
+        self.assertEqual(result["verdict"], "vague")
+        self.assertFalse(result["proven"])
+
+    def test_missing_sweep_fails_closed(self):
+        result = assess_sweep_evidence(None)
+        self.assertEqual(result["verdict"], "missing")
+        self.assertFalse(result["proven"])
+
+    def test_unstated_result_is_downgraded(self):
+        result = _good_sweep(clean=None)
+        self.assertFalse(result["proven"])
+
+
+class TestLiveStateRecheck(unittest.TestCase):
+    """#179 gap 3: explicit pre-mutation live-state recheck."""
+
+    def test_clean_recheck_is_proven(self):
+        result = _good_live_state()
+        self.assertTrue(result["proven"])
+        self.assertFalse(result["block"])
+
+    def test_missing_recheck_fails_closed(self):
+        result = assess_live_state_recheck(None)
+        self.assertFalse(result["proven"])
+        self.assertTrue(result["block"])
+
+    def test_closed_pr_blocks(self):
+        result = _good_live_state(pr_state="closed")
+        self.assertFalse(result["proven"])
+        self.assertTrue(result["block"])
+
+    def test_moved_head_blocks(self):
+        result = _good_live_state(live_head_sha=OTHER)
+        self.assertFalse(result["proven"])
+        self.assertTrue(any("head" in r.lower() for r in result["reasons"]))
+
+    def test_changed_base_blocks(self):
+        result = _good_live_state(live_base_ref="develop")
+        self.assertFalse(result["proven"])
+
+    def test_unresolved_blocking_reviews_block(self):
+        result = _good_live_state(blocking_change_requests=True)
+        self.assertFalse(result["proven"])
+
+    def test_unchecked_blocking_state_fails_closed(self):
+        result = _good_live_state(blocking_change_requests=None)
+        self.assertFalse(result["proven"])
+
+
+class TestRoleBoundary179(unittest.TestCase):
+    """#179 gap 4: reviewer flows avoid unjustified author-namespace use."""
+
+    def test_native_namespace_only_is_clean(self):
+        result = _good_role_boundary_179()
+        self.assertTrue(result["proven"])
+
+    def test_foreign_namespace_without_justification_is_downgraded(self):
+        result = _good_role_boundary_179(
+            namespaces_used=["gitea-reviewer", "gitea-author"]
+        )
+        self.assertFalse(result["proven"])
+        self.assertTrue(any("justif" in r.lower() for r in result["reasons"]))
+
+    def test_foreign_namespace_with_justification_is_clean(self):
+        result = _good_role_boundary_179(
+            namespaces_used=["gitea-reviewer", "gitea-author"],
+            justification=(
+                "author namespace read-only whoami used to evidence "
+                "self-review contamination status"
+            ),
+        )
+        self.assertTrue(result["proven"])
+
+    def test_unreported_namespaces_fail_closed(self):
+        result = _good_role_boundary_179(namespaces_used=None)
+        self.assertFalse(result["proven"])
+
+
+class TestFinalReport179Bar(unittest.TestCase):
+    """#179 acceptance adds capability, sweep, live-state, and role proofs."""
+
+    def _report(self, **overrides):
+        kwargs = {
+            "checkout_proof": _good_checkout(),
+            "inventory": _good_inventory(),
+            "validation": _good_validation(),
+            "contamination": _good_contamination(),
+            "identity_eligible": True,
+            "merge_performed": False,
+            "issue_status_verified": True,
+            "capability_evidence": _good_capability_evidence(),
+            "sweep": _good_sweep(),
+            "live_state": _good_live_state(),
+            "role_boundary": _good_role_boundary(),
+        }
+        kwargs.update(overrides)
+        return build_final_report(**kwargs)
+
+    def test_all_179_proofs_present_is_grade_a(self):
+        report = self._report()
+        self.assertEqual(report["grade"], "A")
+        self.assertTrue(report["capability_evidence_proven"])
+        self.assertEqual(report["sweep_verdict"], "exact")
+        self.assertTrue(report["live_state_recheck_proven"])
+        self.assertTrue(report["role_boundary_clean"])
+
+    def test_missing_capability_evidence_downgrades(self):
+        report = self._report(capability_evidence=None)
+        self.assertNotEqual(report["grade"], "A")
+        self.assertFalse(report["capability_evidence_proven"])
+
+    def test_unevidenced_capability_claim_downgrades(self):
+        report = self._report(
+            capability_evidence=assess_capability_evidence([
+                {"task": "review_pr", "allowed": True, "evidence_source": ""},
+            ])
+        )
+        self.assertNotEqual(report["grade"], "A")
+
+    def test_vague_sweep_downgrades(self):
+        report = self._report(sweep=_good_sweep(command=""))
+        self.assertNotEqual(report["grade"], "A")
+        self.assertEqual(report["sweep_verdict"], "vague")
+
+    def test_missing_sweep_downgrades(self):
+        report = self._report(sweep=None)
+        self.assertNotEqual(report["grade"], "A")
+
+    def test_missing_live_state_recheck_downgrades_and_blocks_merge(self):
+        report = self._report(live_state=None)
+        self.assertNotEqual(report["grade"], "A")
+        self.assertFalse(report["merge_allowed"])
+        self.assertFalse(report["live_state_recheck_proven"])
+
+    def test_stale_live_state_blocks_merge(self):
+        report = self._report(live_state=_good_live_state(live_head_sha=OTHER))
+        self.assertNotEqual(report["grade"], "A")
+        self.assertFalse(report["merge_allowed"])
+
+    def test_merge_claim_without_live_recheck_is_a_violation(self):
+        report = self._report(live_state=None, merge_performed=True)
+        self.assertEqual(report["grade"], "blocked")
+        self.assertTrue(report["violations"])
+
+    def test_unjustified_author_namespace_downgrades(self):
+        report = self._report(
+            role_boundary=_good_role_boundary_179(
+                namespaces_used=["gitea-reviewer", "gitea-author"]
+            )
+        )
+        self.assertNotEqual(report["grade"], "A")
+        self.assertFalse(report["role_boundary_clean"])
+
+    def test_positive_baseline_from_173_still_holds(self):
+        report = self._report()
+        self.assertTrue(report["inventory_complete"])
+        self.assertTrue(report["validated_on_pinned_head"])
+
+
 if __name__ == "__main__":
     unittest.main()