fix: resolve conflicts for PR #422

Merge prgs/master into feat/issue-403-workflow-load-boundaries.
Preserve workflow-load boundary rules (#403) alongside master's
audit reconciliation boundary and workspace verification gates.

final_report_validator.py

@@ -118,6 +118,22 @@ _TARGET_BRANCH_SHA_RE = re.compile(
     r"target branch sha\s*:\s*[0-9a-f]{40}",
     re.IGNORECASE,
 )
+_WORKFLOW_LOAD_HELPER_RE = re.compile(
+    r"workflow[- ]load helper result\s*:",
+    re.IGNORECASE,
+)
+_WORKFLOW_LOAD_HASH_RE = re.compile(
+    r"workflow[- ]load helper result[\s\S]{0,400}?workflow[_ ]hash\s*:\s*[0-9a-f]{12}",
+    re.IGNORECASE,
+)
+_WORKFLOW_LOAD_BOUNDARY_RE = re.compile(
+    r"workflow[- ]load helper result[\s\S]{0,400}?boundary[_ ]status\s*:\s*(?:clean|violation)",
+    re.IGNORECASE,
+)
+_WORKFLOW_FILE_VIEW_NARRATIVE_RE = re.compile(
+    r"(?:read|viewed|loaded)\s+(?:the\s+)?(?:canonical\s+)?(?:workflow|review-merge-pr\.md)",
+    re.IGNORECASE,
+)
 _FULL_SHA_RE = re.compile(r"\b[0-9a-f]{40}\b", re.IGNORECASE)
 _RECONCILE_STALE_FIELDS = (
     "pr number opened",
@@ -1024,6 +1040,54 @@ def _rule_shared_author_reviewer_same_run(report_text: str) -> list[dict[str, st
     )
 
 
+def _rule_reviewer_workflow_load_boundary(report_text: str) -> list[dict[str, str]]:
+    """#403: require structured workflow-load helper result, not file-view narrative."""
+    if not report_text.strip():
+        return []
+    findings: list[dict[str, str]] = []
+    has_helper = bool(_WORKFLOW_LOAD_HELPER_RE.search(report_text))
+    has_hash = bool(_WORKFLOW_LOAD_HASH_RE.search(report_text))
+    has_boundary = bool(_WORKFLOW_LOAD_BOUNDARY_RE.search(report_text))
+    has_narrative_only = bool(_WORKFLOW_FILE_VIEW_NARRATIVE_RE.search(report_text))
+
+    if has_narrative_only and not has_helper:
+        findings.append(validator_finding(
+            "reviewer.workflow_load_boundary",
+            "block",
+            "Workflow-load helper result",
+            (
+                "canonical workflow file-view narrative without structured "
+                "gitea_load_review_workflow helper result"
+            ),
+            (
+                "include Workflow-load helper result with workflow_hash and "
+                "boundary_status from gitea_load_review_workflow"
+            ),
+        ))
+        return findings
+
+    if has_helper and (not has_hash or not has_boundary):
+        missing = []
+        if not has_hash:
+            missing.append("workflow_hash")
+        if not has_boundary:
+            missing.append("boundary_status")
+        findings.append(validator_finding(
+            "reviewer.workflow_load_boundary",
+            "block",
+            "Workflow-load helper result",
+            (
+                "workflow-load helper result incomplete; missing "
+                + ", ".join(missing)
+            ),
+            (
+                "copy workflow_load_helper_result fields from "
+                "gitea_load_review_workflow into the final report"
+            ),
+        ))
+    return findings
+
+
 def _rule_audit_reconciliation_boundary(report_text: str) -> list[dict[str, str]]:
     from audit_reconciliation_mode import assess_audit_reconciliation_report
 
@@ -1100,6 +1164,7 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
         _rule_reviewer_already_landed_eligible,
         _rule_reviewer_already_landed_state,
         _rule_reviewer_target_branch_freshness,
+        _rule_reviewer_workflow_load_boundary,
         _rule_reviewer_mutation_ledger,
         _rule_reviewer_review_mutation,
         _rule_reviewer_post_merge_cleanup_proof,

gitea_mcp_server.py

@@ -714,6 +714,7 @@ import role_session_router  # noqa: E402
 import role_namespace_gate  # noqa: E402
 import task_capability_map  # noqa: E402
 import review_proofs  # noqa: E402
+import review_workflow_boundary  # noqa: E402
 import review_workflow_load  # noqa: E402
 import agent_temp_artifacts
 import issue_lock_worktree  # noqa: E402
@@ -6924,14 +6925,42 @@ def gitea_get_runtime_context(
     return result
 
 
+@mcp.tool()
+def gitea_record_pre_review_command(
+    command: str,
+    cwd: str | None = None,
+    classification: str | None = None,
+) -> dict:
+    """Classify and record a command executed before workflow load (#403).
+
+    Read-only with respect to Gitea API. Pre-review inventory/diagnostic commands
+    may be recorded as allowed; boundary violations block reviewer mutations.
+    """
+    recorded = review_workflow_boundary.record_pre_review_command(
+        command,
+        cwd=cwd,
+        project_root=PROJECT_ROOT,
+        classification=classification,
+    )
+    boundary_state = review_workflow_boundary.assess_boundary_status(PROJECT_ROOT)
+    return {
+        "success": True,
+        "recorded": recorded,
+        "boundary_status": boundary_state.get("boundary_status"),
+        "boundary_clean": boundary_state.get("boundary_clean"),
+        "reasons": list(boundary_state.get("reasons") or []),
+    }
+
+
 @mcp.tool()
 def gitea_load_review_workflow(
     prompt_text: str | None = None,
 ) -> dict:
-    """Load and record canonical review-merge workflow proof for this session (#389).
+    """Load and record canonical review-merge workflow proof for this session (#389, #403).
 
     Read-only with respect to Gitea API; records in-process workflow source/hash
-    proof required before reviewer review or merge mutations.
+    proof and session boundary state required before reviewer review or merge
+    mutations.
     """
     try:
         recorded = review_workflow_load.record_review_workflow_load(
@@ -6943,8 +6972,11 @@ def gitea_load_review_workflow(
             "reasons": [str(exc)],
             "recovery_handoff": review_workflow_load.recovery_handoff_without_replay(),
         }
+    boundary_reasons = review_workflow_boundary.boundary_blockers(PROJECT_ROOT)
+    helper = review_workflow_boundary.workflow_load_helper_result(
+        recorded, PROJECT_ROOT)
     return {
-        "success": True,
+        "success": not boundary_reasons,
         "loaded": True,
         "workflow_source": recorded["workflow_source"],
         "task_mode": recorded["task_mode"],
@@ -6956,7 +6988,14 @@ def gitea_load_review_workflow(
             "prompt_conflicts_with_workflow"],
         "prompt_conflict_reasons": recorded.get("prompt_conflict_reasons") or [],
         "workflow_load_proof_present": True,
-        "reasons": [],
+        "boundary_status": recorded.get("boundary_status"),
+        "boundary_clean": recorded.get("boundary_clean"),
+        "workflow_load_helper_result": helper,
+        "reasons": boundary_reasons,
+        "recovery_handoff": (
+            review_workflow_load.recovery_handoff_without_replay()
+            if boundary_reasons else []
+        ),
     }
 
 

review_workflow_boundary.py

@@ -0,0 +1,259 @@
+"""Reviewer session boundary tracking for workflow-load gate (#403).
+
+Pre-review commands executed before ``gitea_load_review_workflow`` must be
+classified. Boundary violations block downstream reviewer mutations even when
+workflow hash proof is present.
+"""
+
+from __future__ import annotations
+
+import os
+import re
+from typing import Any
+
+CLASSIFICATION_READ_ONLY_INVENTORY = "read_only_inventory"
+CLASSIFICATION_DIAGNOSTIC = "diagnostic"
+CLASSIFICATION_BOUNDARY_VIOLATION = "boundary_violation"
+CLASSIFICATION_UNCLASSIFIED = "unclassified"
+
+ALLOWED_CLASSIFICATIONS = frozenset({
+    CLASSIFICATION_READ_ONLY_INVENTORY,
+    CLASSIFICATION_DIAGNOSTIC,
+    CLASSIFICATION_BOUNDARY_VIOLATION,
+    CLASSIFICATION_UNCLASSIFIED,
+})
+
+_PRE_REVIEW_COMMANDS: list[dict[str, Any]] = []
+
+_READ_ONLY_INVENTORY_PATTERNS = (
+    re.compile(
+        r"\bgitea[_-](?:list|view|whoami|get[-_]|resolve[-_]task|check[-_]pr|route[-_]task)",
+        re.I,
+    ),
+    re.compile(r"\bgit\s+(?:fetch|remote\s+update|branch\s+-a|log|show|rev-parse)\b", re.I),
+    re.compile(r"\bgit\s+status\b", re.I),
+    re.compile(r"\bgit\s+worktree\s+list\b", re.I),
+)
+
+_DIAGNOSTIC_PATTERNS = (
+    re.compile(r"\bgit\s+diff(?:\s+--stat)?\b", re.I),
+    re.compile(r"\bwhich\s+pytest\b", re.I),
+    re.compile(r"\bpytest\s+--version\b", re.I),
+)
+
+_BOUNDARY_VIOLATION_PATTERNS: tuple[tuple[re.Pattern[str], str], ...] = (
+    (re.compile(r"\b(?:pytest|python\s+-m\s+pytest|python\s+-m\s+unittest)\b", re.I),
+     "validation command before workflow load"),
+    (re.compile(r"\bprofiles\.json\b", re.I), "local profile config inspection"),
+    (re.compile(r"\bgitea-mcp(?:\.v2-contexts)?\.json\b", re.I),
+     "local Gitea MCP config inspection"),
+    (re.compile(r"\b\.env(?:\.|$|\b)", re.I), "credential file inspection"),
+    (re.compile(r"\bkeychain\b", re.I), "credential store inspection"),
+    (re.compile(r"\bpkill\b", re.I), "MCP repair activity"),
+    (re.compile(r"\b(?:edit|write|modify).{0,40}\bmcp\b", re.I),
+     "MCP config exploration"),
+    (re.compile(r"\bgit\s+(?:add|commit|reset|clean|checkout|merge|rebase|push)\b", re.I),
+     "git mutation before workflow load"),
+)
+
+
+def clear_pre_review_commands() -> None:
+    """Test helper and session reset."""
+    global _PRE_REVIEW_COMMANDS
+    _PRE_REVIEW_COMMANDS = []
+
+
+def pre_review_commands() -> list[dict[str, Any]]:
+    """Return a shallow copy of recorded pre-review commands."""
+    return [dict(entry) for entry in _PRE_REVIEW_COMMANDS]
+
+
+def _normalize_path(path: str | None) -> str:
+    return os.path.realpath(os.path.abspath((path or "").strip() or os.getcwd()))
+
+
+def is_main_checkout_path(cwd: str | None, project_root: str | None) -> bool:
+    """True when *cwd* is the stable control checkout (not under branches/)."""
+    if not project_root:
+        return False
+    root = _normalize_path(project_root)
+    path = _normalize_path(cwd)
+    if path != root:
+        return False
+    marker = f"{os.sep}branches{os.sep}"
+    return marker not in path
+
+
+def classify_pre_review_command(
+    command: str,
+    *,
+    cwd: str | None = None,
+    project_root: str | None = None,
+) -> dict[str, Any]:
+    """Classify a command executed before workflow load."""
+    text = (command or "").strip()
+    path = _normalize_path(cwd)
+    root = _normalize_path(project_root) if project_root else None
+    reasons: list[str] = []
+
+    for pattern, label in _BOUNDARY_VIOLATION_PATTERNS:
+        if pattern.search(text):
+            if label.startswith("validation") and root and not is_main_checkout_path(path, root):
+                continue
+            if label.startswith("git mutation") and root and not is_main_checkout_path(path, root):
+                continue
+            reasons.append(label)
+            return {
+                "command": text,
+                "cwd": path,
+                "classification": CLASSIFICATION_BOUNDARY_VIOLATION,
+                "reasons": reasons,
+            }
+
+    for pattern in _READ_ONLY_INVENTORY_PATTERNS:
+        if pattern.search(text):
+            return {
+                "command": text,
+                "cwd": path,
+                "classification": CLASSIFICATION_READ_ONLY_INVENTORY,
+                "reasons": [],
+            }
+
+    for pattern in _DIAGNOSTIC_PATTERNS:
+        if pattern.search(text):
+            return {
+                "command": text,
+                "cwd": path,
+                "classification": CLASSIFICATION_DIAGNOSTIC,
+                "reasons": [],
+            }
+
+    if root and is_main_checkout_path(path, root):
+        if re.search(r"\b(?:cat|head|less|read)\b", text, re.I):
+            if re.search(r"workflow|skill|runbook", text, re.I):
+                return {
+                    "command": text,
+                    "cwd": path,
+                    "classification": CLASSIFICATION_BOUNDARY_VIOLATION,
+                    "reasons": [
+                        "canonical workflow viewed as local file without "
+                        "gitea_load_review_workflow (narrative load is not proof)"
+                    ],
+                }
+
+    return {
+        "command": text,
+        "cwd": path,
+        "classification": CLASSIFICATION_UNCLASSIFIED,
+        "reasons": [
+            "pre-review command not classified; record via "
+            "gitea_record_pre_review_command before workflow load"
+        ],
+    }
+
+
+def record_pre_review_command(
+    command: str,
+    *,
+    cwd: str | None = None,
+    project_root: str | None = None,
+    classification: str | None = None,
+) -> dict[str, Any]:
+    """Record and classify a pre-review command for the current session."""
+    assessed = classify_pre_review_command(
+        command, cwd=cwd, project_root=project_root)
+    if classification:
+        if classification not in ALLOWED_CLASSIFICATIONS:
+            assessed["classification"] = CLASSIFICATION_UNCLASSIFIED
+            assessed["reasons"] = [
+                f"unknown classification '{classification}'; fail closed"
+            ]
+        else:
+            assessed["classification"] = classification
+            assessed["reasons"] = []
+    entry = {
+        **assessed,
+        "session_pid": os.getpid(),
+    }
+    _PRE_REVIEW_COMMANDS.append(entry)
+    return dict(entry)
+
+
+def assess_boundary_status(project_root: str | None = None) -> dict[str, Any]:
+    """Summarize pre-review boundary state for session proof and reports."""
+    violations = [
+        entry for entry in _PRE_REVIEW_COMMANDS
+        if entry.get("classification") == CLASSIFICATION_BOUNDARY_VIOLATION
+    ]
+    unclassified = [
+        entry for entry in _PRE_REVIEW_COMMANDS
+        if entry.get("classification") == CLASSIFICATION_UNCLASSIFIED
+    ]
+    reasons: list[str] = []
+    for entry in violations:
+        reasons.extend(entry.get("reasons") or [
+            f"boundary violation: {entry.get('command', '')[:80]}"
+        ])
+    for entry in unclassified:
+        reasons.extend(entry.get("reasons") or [
+            "unclassified pre-review command blocks reviewer mutations"
+        ])
+
+    clean = not reasons
+    return {
+        "boundary_status": "clean" if clean else "violation",
+        "boundary_clean": clean,
+        "pre_review_command_count": len(_PRE_REVIEW_COMMANDS),
+        "boundary_violation_count": len(violations),
+        "unclassified_command_count": len(unclassified),
+        "violations": [
+            {
+                "command": v.get("command"),
+                "cwd": v.get("cwd"),
+                "reasons": list(v.get("reasons") or []),
+            }
+            for v in violations
+        ],
+        "reasons": reasons,
+    }
+
+
+def boundary_blockers(project_root: str | None = None) -> list[str]:
+    """Reasons reviewer mutations must fail closed due to boundary state."""
+    status = assess_boundary_status(project_root)
+    if status.get("boundary_clean"):
+        return []
+    return list(status.get("reasons") or [
+        "reviewer session boundary violation before workflow load"
+    ])
+
+
+def workflow_load_helper_result(
+    load: dict | None,
+    project_root: str | None = None,
+) -> dict[str, Any]:
+    """Structured helper result for final reports (#403)."""
+    boundary = assess_boundary_status(project_root)
+    if load is None:
+        return {
+            "workflow_load_proof_present": False,
+            "workflow_source": None,
+            "workflow_hash": None,
+            "final_report_schema_hash": None,
+            "boundary_status": boundary.get("boundary_status"),
+            "boundary_clean": False,
+            "reasons": [
+                "gitea_load_review_workflow helper result missing from report"
+            ],
+        }
+    return {
+        "workflow_load_proof_present": True,
+        "workflow_source": load.get("workflow_source"),
+        "workflow_hash": load.get("workflow_hash"),
+        "final_report_schema_path": load.get("final_report_schema_path"),
+        "final_report_schema_hash": load.get("final_report_schema_hash"),
+        "boundary_status": load.get("boundary_status", boundary.get("boundary_status")),
+        "boundary_clean": bool(load.get("boundary_clean", boundary.get("boundary_clean"))),
+        "pre_review_command_count": boundary.get("pre_review_command_count"),
+        "reasons": [],
+    }

review_workflow_load.py

@@ -1,4 +1,4 @@
-"""Canonical review-merge workflow load proof for reviewer mutations (#389)."""
+"""Canonical review-merge workflow load proof for reviewer mutations (#389, #403)."""
 
 from __future__ import annotations
 
@@ -7,6 +7,8 @@ import os
 import re
 from pathlib import Path
 
+import review_workflow_boundary as boundary
+
 WORKFLOW_REL_PATH = (
     "skills/llm-project-workflow/workflows/review-merge-pr.md"
 )
@@ -95,10 +97,16 @@ def record_review_workflow_load(
     global _REVIEW_WORKFLOW_LOAD
     meta = build_canonical_workflow_metadata(
         project_root, prompt_text=prompt_text)
+    boundary_state = boundary.assess_boundary_status(project_root)
     _REVIEW_WORKFLOW_LOAD = {
         **meta,
         "session_pid": os.getpid(),
         "loaded": True,
+        "boundary_status": boundary_state.get("boundary_status"),
+        "boundary_clean": boundary_state.get("boundary_clean"),
+        "pre_review_command_count": boundary_state.get("pre_review_command_count"),
+        "boundary_violation_count": boundary_state.get("boundary_violation_count"),
+        "boundary_reasons": list(boundary_state.get("reasons") or []),
     }
     return dict(_REVIEW_WORKFLOW_LOAD)
 
@@ -107,6 +115,7 @@ def clear_review_workflow_load() -> None:
     """Test helper and review_pr session reset."""
     global _REVIEW_WORKFLOW_LOAD
     _REVIEW_WORKFLOW_LOAD = None
+    boundary.clear_pre_review_commands()
 
 
 def workflow_load_status(project_root: str | None = None) -> dict:
@@ -125,6 +134,9 @@ def workflow_load_status(project_root: str | None = None) -> dict:
             ],
         }
     reasons = _session_validation_reasons(load, project_root)
+    boundary_reasons = boundary.boundary_blockers(project_root)
+    if boundary_reasons:
+        reasons = list(reasons) + boundary_reasons
     return {
         "workflow_load_proof_present": True,
         "workflow_load_valid": not reasons,
@@ -136,6 +148,10 @@ def workflow_load_status(project_root: str | None = None) -> dict:
         "prompt_conflicts_with_workflow": load.get(
             "prompt_conflicts_with_workflow"),
         "session_pid": load.get("session_pid"),
+        "boundary_status": load.get("boundary_status"),
+        "boundary_clean": load.get("boundary_clean"),
+        "workflow_load_helper_result": boundary.workflow_load_helper_result(
+            load, project_root),
         "reasons": reasons,
     }
 
@@ -179,9 +195,12 @@ def review_workflow_load_blockers(
     project_root: str | None = None,
 ) -> list[str]:
     """Reasons reviewer mutations must fail closed."""
+    boundary_reasons = boundary.boundary_blockers(project_root)
+    if boundary_reasons and _REVIEW_WORKFLOW_LOAD is None:
+        return boundary_reasons
     status = workflow_load_status(project_root)
     if not status.get("workflow_load_proof_present"):
-        return list(status.get("reasons") or [])
+        return list(status.get("reasons") or []) + boundary_reasons
     if not status.get("workflow_load_valid"):
         return list(status.get("reasons") or [])
     return []

skills/llm-project-workflow/schemas/review-merge-final-report.md

@@ -63,8 +63,14 @@ Do not use legacy fields: `Pinned reviewed head`, `Scratch worktree used`,
 - Current status:
 - Safe next action:
 - Safety statement:
+- Workflow-load helper result:
 ```
 
+The **Workflow-load helper result** field must carry structured output from
+`gitea_load_review_workflow` (workflow_hash, final_report_schema_hash,
+boundary_status). Narrative claims that workflow files were viewed locally are
+not sufficient (#403).
+
 ### Already-landed handoff overrides
 
 When eligibility class is `ALREADY_LANDED_RECONCILE_REQUIRED`:

skills/llm-project-workflow/workflows/review-merge-pr.md

@@ -36,6 +36,44 @@ If available, load it first and report:
 
 If the canonical workflow cannot be loaded and the project requires it, stop and produce a recovery handoff only.
 
+## 0A. Workflow-load and session boundary anchor (#403)
+
+The MCP gate is the authority — not local file viewing.
+
+Before any reviewer mutation:
+
+1. Record pre-review commands with `gitea_record_pre_review_command` when they
+   are not automatically classified (inventory/diagnostic commands may be
+   recorded explicitly for proof).
+2. Call `gitea_load_review_workflow` to establish workflow hash proof **and**
+   session boundary state in the same in-process session proof.
+3. Do not claim the workflow was loaded by reading
+   `skills/llm-project-workflow/workflows/review-merge-pr.md` as a local file;
+   that narrative does not satisfy the validator.
+
+Allowed before workflow load (classify as `read_only_inventory` or
+`diagnostic`):
+
+* `gitea_whoami`, `gitea_resolve_task_capability`, `gitea_list_prs`,
+  `gitea_view_pr`, `gitea_get_runtime_context`
+* `git fetch` / `git remote update` for inventory
+* `git status`, `git worktree list` (read-only)
+
+Boundary violations (block downstream reviewer mutations even after load):
+
+* validation commands (`pytest`, `python -m unittest`) in the main checkout
+* local profile/credential/config inspection (`profiles.json`, `gitea-mcp.json`,
+  `.env`, keychain dumps)
+* MCP repair (`pkill`, MCP config edits)
+* git mutations before workflow load
+
+Final reports must include a structured **Workflow-load helper result** block
+copied from `gitea_load_review_workflow`, including at minimum:
+
+* `workflow_hash`
+* `final_report_schema_hash`
+* `boundary_status` (`clean` or `violation`)
+
 ## 1. Start with live identity, profile, runtime, and capability checks
 
 Prove:

tests/test_audit.py

@@ -294,9 +294,11 @@ class TestGatedToolAudit(_AuditWiringBase):
         super().setUp()
         from tests.test_mcp_server import _init_reviewer_session, _install_owned_reviewer_lease
         import reviewer_pr_lease
+        import review_workflow_load
 
         # Session init clears any prior session lease (#407) and loads workflow (#389).
         _init_reviewer_session("prgs")
+        self.addCleanup(review_workflow_load.clear_review_workflow_load)
         self._lease_patch = _install_owned_reviewer_lease(8)
         self._lease_patch.start()
         self._auth_identity_patch = patch(

tests/test_mcp_server.py

@@ -1057,7 +1057,8 @@ class TestMergePR(unittest.TestCase):
                "GITEA_ALLOWED_OPERATIONS": "read,merge"}
         with patch.dict(os.environ, env, clear=True):
             r = gitea_merge_pr(
-                pr_number=8, confirmation=self._confirm(8), remote="prgs")
+                pr_number=8, confirmation=self._confirm(8), remote="prgs",
+                expected_head_sha=new_sha)
         self.assertFalse(r["performed"])
         self.assertTrue(r.get("approval_visible"))
         self.assertFalse(r.get("approval_at_current_head"))

tests/test_permission_reports.py

@@ -95,8 +95,12 @@ class PermissionReportBase(unittest.TestCase):
         self._dir = tempfile.TemporaryDirectory()
         self.config_path = os.path.join(self._dir.name, "profiles.json")
         self._write_config(CONFIG)
+        import review_workflow_load
+        review_workflow_load.record_review_workflow_load(mcp_server.PROJECT_ROOT)
 
     def tearDown(self):
+        import review_workflow_load
+        review_workflow_load.clear_review_workflow_load()
         self._remotes.stop()
         mcp_server._IDENTITY_CACHE.clear()
         mcp_server.review_workflow_load.clear_review_workflow_load()

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()

tests/test_terminal_review_hard_stop.py

@@ -36,10 +36,13 @@ def _lock(mutations=None, correction=False):
 
 
 def _seed(mutations=None, correction=False):
+    import review_workflow_load
+    review_workflow_load.record_review_workflow_load(mcp_server.PROJECT_ROOT)
     mcp_server._save_review_decision_lock(_lock(mutations, correction))
     mcp_server.gitea_load_review_workflow()
 
 
+
 APPROVED_A = {"pr_number": 5, "action": "approve", "review_id": 1,
               "review_state": "approve"}
 RC_A = {"pr_number": 5, "action": "request_changes", "review_id": 2,
@@ -94,6 +97,8 @@ class TestTerminalHardStopReasons(unittest.TestCase):
 
 class TestMergeHardStopWiring(unittest.TestCase):
     def tearDown(self):
+        import review_workflow_load
+        review_workflow_load.clear_review_workflow_load()
         mcp_server._save_review_decision_lock(None)
         mcp_server.review_workflow_load.clear_review_workflow_load()
 
@@ -116,6 +121,8 @@ class TestMergeHardStopWiring(unittest.TestCase):
 
 class TestMarkFinalHardStopWiring(unittest.TestCase):
     def tearDown(self):
+        import review_workflow_load
+        review_workflow_load.clear_review_workflow_load()
         mcp_server._save_review_decision_lock(None)
         mcp_server.review_workflow_load.clear_review_workflow_load()
 
@@ -149,6 +156,8 @@ def _mark(action, pr_number=6, **kwargs):
 
 class TestDuplicateRequestChangesSuppression(unittest.TestCase):
     def tearDown(self):
+        import review_workflow_load
+        review_workflow_load.clear_review_workflow_load()
         mcp_server._save_review_decision_lock(None)
         mcp_server.review_workflow_load.clear_review_workflow_load()