feat: add workflow-load session boundary proof (Closes #403)

Extend the review workflow load gate with pre-review command classification,
boundary violation tracking, and structured helper-result requirements in
final reports. Adds gitea_record_pre_review_command MCP tool.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>

tests/test_review_workflow_boundary.py

@@ -0,0 +1,138 @@
+"""Tests for workflow-load session boundary tracking (#403)."""
+
+import os
+import sys
+import unittest
+from unittest.mock import patch
+
+sys.path.insert(0, str(__import__("pathlib").Path(__file__).resolve().parent.parent))
+
+import final_report_validator
+import review_workflow_boundary
+import review_workflow_load
+import mcp_server
+
+
+class TestPreReviewClassification(unittest.TestCase):
+    def setUp(self):
+        review_workflow_boundary.clear_pre_review_commands()
+        review_workflow_load.clear_review_workflow_load()
+
+    def test_inventory_command_allowed(self):
+        result = review_workflow_boundary.classify_pre_review_command(
+            "gitea_list_prs remote=prgs",
+            cwd="/tmp",
+            project_root="/repo/Gitea-Tools",
+        )
+        self.assertEqual(
+            result["classification"],
+            review_workflow_boundary.CLASSIFICATION_READ_ONLY_INVENTORY,
+        )
+
+    def test_main_checkout_pytest_is_boundary_violation(self):
+        root = "/repo/Gitea-Tools"
+        result = review_workflow_boundary.classify_pre_review_command(
+            "python -m pytest tests/",
+            cwd=root,
+            project_root=root,
+        )
+        self.assertEqual(
+            result["classification"],
+            review_workflow_boundary.CLASSIFICATION_BOUNDARY_VIOLATION,
+        )
+
+    def test_profiles_json_inspection_is_boundary_violation(self):
+        result = review_workflow_boundary.classify_pre_review_command(
+            "cat profiles.json",
+            cwd="/repo/Gitea-Tools",
+            project_root="/repo/Gitea-Tools",
+        )
+        self.assertEqual(
+            result["classification"],
+            review_workflow_boundary.CLASSIFICATION_BOUNDARY_VIOLATION,
+        )
+
+
+class TestWorkflowLoadBoundaryGate(unittest.TestCase):
+    def setUp(self):
+        review_workflow_boundary.clear_pre_review_commands()
+        review_workflow_load.clear_review_workflow_load()
+        mcp_server.init_review_decision_lock("prgs", "review_pr")
+        mcp_server.record_preflight_check("whoami")
+        mcp_server.record_preflight_check("capability", "reviewer")
+
+    def _root(self) -> str:
+        return str(__import__("pathlib").Path(__file__).resolve().parent.parent)
+
+    def test_boundary_violation_blocks_mutation_after_load(self):
+        root = self._root()
+        review_workflow_boundary.record_pre_review_command(
+            "python -m pytest tests/",
+            cwd=root,
+            project_root=root,
+        )
+        res = mcp_server.gitea_load_review_workflow()
+        self.assertFalse(res["success"])
+        self.assertEqual(res["boundary_status"], "violation")
+        blocked = mcp_server.gitea_mark_final_review_decision(
+            42, "approve", remote="prgs")
+        self.assertFalse(blocked["marked_ready"])
+        joined = " ".join(blocked["reasons"]).lower()
+        self.assertTrue(
+            "validation" in joined or "boundary" in joined or "workflow" in joined
+        )
+
+    def test_clean_inventory_then_load_passes(self):
+        root = self._root()
+        review_workflow_boundary.record_pre_review_command(
+            "gitea_list_prs remote=prgs",
+            cwd=root,
+            project_root=root,
+        )
+        res = mcp_server.gitea_load_review_workflow()
+        self.assertTrue(res["success"])
+        self.assertEqual(res["boundary_status"], "clean")
+        blockers = review_workflow_load.review_workflow_load_blockers(root)
+        self.assertEqual(blockers, [])
+
+    def test_file_view_narrative_fails_validator_without_helper(self):
+        report = (
+            "## Controller Handoff\n"
+            "- Task: review-merge-pr\n"
+            "- I read the canonical workflow review-merge-pr.md before review.\n"
+        )
+        findings = final_report_validator.assess_final_report_validator(
+            report,
+            task_kind="review_pr",
+        )
+        self.assertTrue(any(
+            f["rule_id"] == "reviewer.workflow_load_boundary"
+            for f in findings.get("findings") or []
+        ))
+
+    def test_helper_result_passes_validator(self):
+        root = self._root()
+        review_workflow_load.record_review_workflow_load(root)
+        helper = review_workflow_boundary.workflow_load_helper_result(
+            review_workflow_load._REVIEW_WORKFLOW_LOAD,
+            root,
+        )
+        report = (
+            "## Controller Handoff\n"
+            "- Task: review-merge-pr\n"
+            f"- Workflow-load helper result: workflow_hash: {helper['workflow_hash']}; "
+            f"boundary_status: {helper['boundary_status']}\n"
+        )
+        findings = final_report_validator.assess_final_report_validator(
+            report,
+            task_kind="review_pr",
+        )
+        boundary_findings = [
+            f for f in (findings.get("findings") or [])
+            if f.get("rule_id") == "reviewer.workflow_load_boundary"
+        ]
+        self.assertEqual(boundary_findings, [])
+
+
+if __name__ == "__main__":
+    unittest.main()