feat: require validation cwd and HEAD proof in reviewer reports (Closes #398)

Add assess_validation_cwd_proof_report so reviewer final reports must prove
pwd, git rev-parse HEAD, git status, and expected PR head SHA before
claiming validation ran in a branches/ worktree. Wire the verifier into
final_report_validator and gitea_validate_review_final_report.

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

final_report_validator.py

@@ -456,6 +456,42 @@ def _rule_reviewer_git_fetch_readonly(
     return []
 
 
+def _rule_reviewer_validation_cwd_proof(
+    report_text: str,
+    *,
+    validation_session: dict | None = None,
+) -> list[dict[str, str]]:
+    from reviewer_validation_cwd_proof import assess_validation_cwd_proof_report
+
+    session = validation_session or {}
+    claims = (
+        session.get("validation_ran")
+        or session.get("command")
+        or session.get("baseline_validation_ran")
+    )
+    if not claims and "validation command:" not in (report_text or "").lower():
+        return []
+
+    result = assess_validation_cwd_proof_report(
+        report_text,
+        validation_session=session,
+    )
+    if result.get("proven") or not result.get("claims_validation"):
+        return []
+    severity = "block" if result.get("violations") else "downgrade"
+    return [
+        validator_finding(
+            "reviewer.validation_cwd_proof",
+            severity,
+            "Validation cwd/HEAD proof",
+            reason,
+            result.get("safe_next_action")
+            or "document pwd, HEAD SHA, and explicit cwd before validation",
+        )
+        for reason in (result.get("violations") or result.get("reasons") or ["incomplete"])
+    ]
+
+
 def _rule_reviewer_validation_command(report_text: str) -> list[dict[str, str]]:
     text = report_text or ""
     if not _BARE_PYTEST_RE.search(text):
@@ -864,6 +900,7 @@ _RULES_BY_TASK: dict[str, list[Callable[..., list[dict[str, str]]]]] = {
         _rule_reviewer_mutation_categories,
         _rule_reviewer_git_fetch_readonly,
         _rule_reviewer_validation_command,
+        _rule_reviewer_validation_cwd_proof,
         _rule_reviewer_validation_structured,
         _rule_reviewer_linked_issue,
         _rule_reviewer_baseline_on_failure,
@@ -970,6 +1007,7 @@ def assess_final_report_validator(
     local_edits: bool = False,
     issue_filing_lock: dict | None = None,
     session_pr_opened: bool = False,
+    validation_session: dict | None = None,
 ) -> dict[str, Any]:
     """Validate final-report text against task-specific proof rules (#327).
 
@@ -1025,6 +1063,7 @@ def assess_final_report_validator(
         "mutations_observed": mutations_observed,
         "local_edits": local_edits,
         "session_pr_opened": session_pr_opened,
+        "validation_session": validation_session,
     }
 
     for rule in _RULES_BY_TASK.get(normalized_kind, ()):

gitea_mcp_server.py

@@ -5506,6 +5506,7 @@ def gitea_validate_review_final_report(
     action_log: list[dict] | None = None,
     mutations_observed: bool = False,
     local_edits: bool = False,
+    validation_session: dict | None = None,
 ) -> dict:
     """Read-only: machine-validate reviewer final report schema before output (#391).
 
@@ -5523,6 +5524,7 @@ def gitea_validate_review_final_report(
         action_log=action_log,
         mutations_observed=mutations_observed,
         local_edits=local_edits,
+        validation_session=validation_session,
     )
 
 

review_final_report_schema.py

@@ -301,6 +301,7 @@ def assess_review_final_report_schema(
     action_log: list[dict] | None = None,
     mutations_observed: bool = False,
     local_edits: bool = False,
+    validation_session: dict | None = None,
 ) -> dict[str, Any]:
     """Validate reviewer final report text before session completion (#391)."""
     base = assess_final_report_validator(
@@ -312,6 +313,7 @@ def assess_review_final_report_schema(
         action_log=action_log,
         mutations_observed=mutations_observed,
         local_edits=local_edits,
+        validation_session=validation_session,
     )
     extra: list[dict[str, str]] = []
     for rule in _SCHEMA_RULES:

review_proofs.py

@@ -5487,6 +5487,13 @@ def assess_validation_integrity_report(report_text, **kwargs):
     return _assess(report_text, **kwargs)
 
 
+def assess_validation_cwd_proof_report(report_text, **kwargs):
+    """#398: validation commands require explicit worktree cwd and HEAD proof."""
+    from reviewer_validation_cwd_proof import assess_validation_cwd_proof_report as _assess
+
+    return _assess(report_text, **kwargs)
+
+
 def assess_already_landed_classification_report(report_text, **kwargs):
     """#295: already-landed PRs are reconciliation-only, not review eligible."""
     from reviewer_already_landed_classification import (

reviewer_validation_cwd_proof.py

@@ -0,0 +1,233 @@
+"""Explicit worktree and cwd proof for PR review validation (#398)."""
+
+from __future__ import annotations
+
+import re
+from typing import Any
+
+_FULL_SHA = re.compile(r"^[0-9a-f]{40}$", re.IGNORECASE)
+
+_PWD_RE = re.compile(
+    r"(?:^|\n)\s*(?:pwd|working\s+directory|cwd)\s*:\s*(\S+)",
+    re.IGNORECASE,
+)
+_HEAD_RE = re.compile(
+    r"(?:git\s+rev-parse\s+head|observed\s+head\s+sha)\s*:\s*([0-9a-f]{7,40})",
+    re.IGNORECASE | re.MULTILINE,
+)
+_EXPECTED_HEAD_RE = re.compile(
+    r"(?:expected\s+(?:pr\s+)?head\s+sha|candidate\s+head\s+sha|pinned\s+head)\s*:\s*([0-9a-f]{7,40})",
+    re.IGNORECASE,
+)
+_STATUS_RE = re.compile(
+    r"git\s+status\s+(?:--short\s+--branch|--short|-sb)\s*:\s*(.+)",
+    re.IGNORECASE,
+)
+_VALIDATION_CMD_RE = re.compile(
+    r"validation\s+command\s*:\s*(.+)",
+    re.IGNORECASE,
+)
+_GIT_C_CMD_RE = re.compile(r"git\s+-C\s+\S+", re.IGNORECASE)
+_CD_CMD_RE = re.compile(r"(?:^|&&\s*)cd\s+\S+", re.IGNORECASE)
+_BASELINE_CWD_RE = re.compile(
+    r"baseline\s+(?:worktree|working\s+directory|cwd)\s*:\s*(\S+)",
+    re.IGNORECASE,
+)
+_BASELINE_SHA_RE = re.compile(
+    r"baseline\s+(?:target\s+)?sha\s*:\s*([0-9a-f]{7,40})",
+    re.IGNORECASE,
+)
+_BASELINE_CMD_RE = re.compile(
+    r"baseline\s+validation\s+command\s*:\s*(.+)",
+    re.IGNORECASE,
+)
+
+
+def _normalize_path(path: str) -> str:
+    return (path or "").replace("\\", "/").rstrip("/")
+
+
+def _path_under_branches(path: str, project_root: str | None = None) -> bool:
+    normalized = _normalize_path(path)
+    if not normalized:
+        return False
+    if "/branches/" in f"{normalized}/":
+        return True
+    if normalized.endswith("/branches"):
+        return True
+    if project_root:
+        root = _normalize_path(project_root)
+        if normalized.startswith(f"{root}/"):
+            rel = normalized[len(root) + 1 :]
+            return rel == "branches" or rel.startswith("branches/")
+    return False
+
+
+def _expand_sha(sha: str) -> str:
+    return (sha or "").strip().lower()
+
+
+def _sha_matches(expected: str, observed: str) -> bool:
+    exp = _expand_sha(expected)
+    obs = _expand_sha(observed)
+    if not exp or not obs:
+        return False
+    if len(exp) == 40 and len(obs) == 40:
+        return exp == obs
+    return obs.startswith(exp) or exp.startswith(obs)
+
+
+def _command_has_explicit_cwd(command: str, cwd: str) -> bool:
+    text = (command or "").strip()
+    if not text:
+        return False
+    if _GIT_C_CMD_RE.search(text):
+        return True
+    if _CD_CMD_RE.search(text):
+        return True
+    if cwd and cwd in text:
+        return True
+    return False
+
+
+def assess_validation_cwd_proof_report(
+    report_text: str,
+    *,
+    validation_session: dict | None = None,
+    project_root: str | None = None,
+) -> dict[str, Any]:
+    """Require cwd/HEAD proof before reviewer validation claims (#398)."""
+    text = report_text or ""
+    session = dict(validation_session or {})
+    reasons: list[str] = []
+    violations: list[str] = []
+
+    claims_validation = bool(
+        session.get("validation_ran")
+        or _VALIDATION_CMD_RE.search(text)
+        or session.get("command")
+    )
+    if not claims_validation:
+        return {
+            "proven": True,
+            "block": False,
+            "claims_validation": False,
+            "reasons": [],
+            "violations": [],
+            "safe_next_action": "proceed",
+        }
+
+    expected_head = (
+        session.get("expected_head_sha")
+        or session.get("candidate_head_sha")
+        or ""
+    ).strip()
+    if not expected_head:
+        match = _EXPECTED_HEAD_RE.search(text)
+        expected_head = (match.group(1) if match else "").strip()
+
+    observed_head = (session.get("observed_head_sha") or "").strip()
+    if not observed_head:
+        match = _HEAD_RE.search(text)
+        observed_head = (match.group(1) if match else "").strip()
+
+    cwd = (
+        session.get("working_directory")
+        or session.get("cwd")
+        or session.get("pwd")
+        or ""
+    ).strip()
+    if not cwd:
+        match = _PWD_RE.search(text)
+        cwd = (match.group(1) if match else "").strip().rstrip(",.;")
+
+    command = (session.get("command") or "").strip()
+    if not command:
+        match = _VALIDATION_CMD_RE.search(text)
+        command = (match.group(1) if match else "").strip().rstrip(".;")
+
+    if not cwd:
+        reasons.append(
+            "validation claimed without pwd/working-directory proof (#398)"
+        )
+    elif not _path_under_branches(cwd, project_root):
+        violations.append(
+            f"validation cwd {cwd!r} is not under branches/ (#398)"
+        )
+        reasons.append(
+            "reviewer validation must run from a branches/ worktree, "
+            "not the main checkout (#398)"
+        )
+
+    if not observed_head:
+        reasons.append(
+            "validation claimed without git rev-parse HEAD / observed HEAD SHA "
+            "proof (#398)"
+        )
+    elif expected_head and not _sha_matches(expected_head, observed_head):
+        violations.append(
+            f"observed HEAD {observed_head} does not match expected "
+            f"PR head {expected_head} (#398)"
+        )
+        reasons.append("validation HEAD SHA must match pinned PR head (#398)")
+
+    if not _STATUS_RE.search(text) and session.get("git_status") is None:
+        reasons.append(
+            "validation claimed without git status --short --branch proof (#398)"
+        )
+
+    if command and cwd and not _command_has_explicit_cwd(command, cwd):
+        if session.get("tool_working_directory") is not True:
+            reasons.append(
+                "validation command must use git -C <worktree>, "
+                "cd <worktree> && ..., or tool-provided cwd metadata (#398)"
+            )
+
+    baseline_ran = bool(
+        session.get("baseline_validation_ran")
+        or _BASELINE_CMD_RE.search(text)
+    )
+    if baseline_ran:
+        baseline_cwd = (session.get("baseline_worktree_path") or "").strip()
+        if not baseline_cwd:
+            match = _BASELINE_CWD_RE.search(text)
+            baseline_cwd = (match.group(1) if match else "").strip().rstrip(",.;")
+        if not baseline_cwd or not _path_under_branches(baseline_cwd, project_root):
+            reasons.append(
+                "baseline validation claimed without baseline worktree cwd "
+                "under branches/ (#398)"
+            )
+        baseline_sha = (session.get("baseline_target_sha") or "").strip()
+        if not baseline_sha:
+            match = _BASELINE_SHA_RE.search(text)
+            baseline_sha = (match.group(1) if match else "").strip()
+        if not baseline_sha:
+            reasons.append(
+                "baseline validation claimed without baseline target SHA (#398)"
+            )
+        baseline_cmd = (session.get("baseline_command") or "").strip()
+        if not baseline_cmd:
+            match = _BASELINE_CMD_RE.search(text)
+            baseline_cmd = (match.group(1) if match else "").strip()
+        if not baseline_cmd:
+            reasons.append(
+                "baseline validation claimed without exact baseline command (#398)"
+            )
+
+    proven = not reasons and not violations
+    return {
+        "proven": proven,
+        "block": bool(violations) or not proven,
+        "claims_validation": True,
+        "expected_head_sha": expected_head or None,
+        "observed_head_sha": observed_head or None,
+        "working_directory": cwd or None,
+        "reasons": reasons,
+        "violations": violations,
+        "safe_next_action": (
+            "before validation record pwd, git rev-parse HEAD, git status, "
+            "expected PR head SHA; run commands with git -C or cd in the same line"
+            if not proven
+            else "proceed"
+        ),
+    }

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

@@ -574,6 +574,28 @@ Do not claim “full-suite failures are pre-existing” unless baseline proof is
 
 ## 23. Validation command proof rule
 
+Before any diff, test, or compile validation, record in the same command
+transcript or final report:
+
+* `pwd` or explicit working directory
+* `git rev-parse HEAD`
+* `git status --short --branch`
+* expected PR head SHA (candidate head SHA)
+
+Validation commands must use one of:
+
+* `git -C <review_worktree> ...`
+* `cd <review_worktree> && ...` in the same command
+* tool-provided explicit working-directory metadata
+
+Do not rely on inferred shell cwd from a prior command in a different block.
+
+`gitea_validate_review_final_report` rejects validation claims without
+cwd/HEAD proof when `validation_session` is supplied.
+
+Baseline validation must document baseline worktree path, baseline target SHA,
+cwd proof, exact baseline command, and baseline result using the same rules.
+
 Report the exact validation command as executed.
 
 Report the working directory where validation ran.
@@ -1096,6 +1118,7 @@ Controller Handoff:
 * Baseline worktree path:
 * Files reviewed:
 * Validation:
+* Validation cwd/HEAD proof:
 * Official validation integrity status:
 * Terminal review mutation:
 * Review decision:

tests/test_llm_workflow_split.py

@@ -207,6 +207,12 @@ def test_validation_integrity_verifier_exported():
     assert callable(assess_validation_integrity_report)
 
 
+def test_validation_cwd_proof_verifier_exported():
+    from review_proofs import assess_validation_cwd_proof_report
+
+    assert callable(assess_validation_cwd_proof_report)
+
+
 def test_prior_blocker_skip_verifier_exported():
     from review_proofs import assess_prior_blocker_skip_proof
 

tests/test_reviewer_validation_cwd_proof.py

@@ -0,0 +1,135 @@
+"""Tests for validation cwd/HEAD proof verifier (#398)."""
+import sys
+import unittest
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from final_report_validator import assess_final_report_validator  # noqa: E402
+from reviewer_validation_cwd_proof import assess_validation_cwd_proof_report  # noqa: E402
+
+ROOT = "/Users/jasonwalker/Development/Gitea-Tools"
+WORKTREE = f"{ROOT}/branches/review-feat-issue-398"
+HEAD = "f5953549aad5e822f14f52d3ea3c6d7990109384"
+
+
+def _proof_backed_report() -> str:
+    return "\n".join([
+        f"Candidate head SHA: {HEAD}",
+        f"pwd: {WORKTREE}",
+        f"git rev-parse HEAD: {HEAD}",
+        "git status --short --branch: ## feat/issue-398...prgs/master",
+        f"Validation command: cd {WORKTREE} && venv/bin/python -m pytest tests/ -q",
+        "Result: 1497 passed, 6 skipped",
+    ])
+
+
+class TestValidationCwdProof(unittest.TestCase):
+    def test_no_validation_claim_passes(self):
+        result = assess_validation_cwd_proof_report("Review decision: approve")
+        self.assertTrue(result["proven"])
+
+    def test_missing_cwd_proof_fails(self):
+        result = assess_validation_cwd_proof_report(
+            f"Validation command: pytest tests/\nCandidate head SHA: {HEAD}",
+            validation_session={"validation_ran": True, "expected_head_sha": HEAD},
+        )
+        self.assertFalse(result["proven"])
+        self.assertTrue(result["block"])
+
+    def test_main_checkout_cwd_blocks(self):
+        result = assess_validation_cwd_proof_report(
+            "\n".join([
+                f"Candidate head SHA: {HEAD}",
+                f"pwd: {ROOT}",
+                f"git rev-parse HEAD: {HEAD}",
+                "git status --short --branch: ## master",
+                "Validation command: pytest tests/ -q",
+            ]),
+            validation_session={"validation_ran": True, "expected_head_sha": HEAD},
+            project_root=ROOT,
+        )
+        self.assertFalse(result["proven"])
+        self.assertTrue(result["violations"])
+
+    def test_wrong_head_blocks(self):
+        wrong = "a" * 40
+        result = assess_validation_cwd_proof_report(
+            "\n".join([
+                f"Candidate head SHA: {HEAD}",
+                f"pwd: {WORKTREE}",
+                f"git rev-parse HEAD: {wrong}",
+                "git status --short --branch: clean",
+                f"Validation command: cd {WORKTREE} && pytest -q",
+            ]),
+            validation_session={"validation_ran": True, "expected_head_sha": HEAD},
+            project_root=ROOT,
+        )
+        self.assertFalse(result["proven"])
+        self.assertTrue(result["violations"])
+
+    def test_fully_proof_backed_passes(self):
+        result = assess_validation_cwd_proof_report(
+            _proof_backed_report(),
+            validation_session={"validation_ran": True, "expected_head_sha": HEAD},
+            project_root=ROOT,
+        )
+        self.assertTrue(result["proven"], result["reasons"])
+
+    def test_baseline_without_cwd_fails(self):
+        result = assess_validation_cwd_proof_report(
+            "\n".join([
+                _proof_backed_report(),
+                "Baseline validation command: pytest tests/ -q",
+            ]),
+            validation_session={
+                "validation_ran": True,
+                "expected_head_sha": HEAD,
+                "baseline_validation_ran": True,
+            },
+            project_root=ROOT,
+        )
+        self.assertFalse(result["proven"])
+        self.assertTrue(
+            any("baseline" in r.lower() for r in result["reasons"])
+        )
+
+    def test_baseline_with_full_proof_passes(self):
+        result = assess_validation_cwd_proof_report(
+            "\n".join([
+                _proof_backed_report(),
+                f"Baseline worktree: {ROOT}/branches/baseline-master-pr376",
+                f"Baseline target SHA: {HEAD}",
+                f"Baseline validation command: cd {ROOT}/branches/baseline-master-pr376 && pytest -q",
+            ]),
+            validation_session={
+                "validation_ran": True,
+                "expected_head_sha": HEAD,
+                "baseline_validation_ran": True,
+            },
+            project_root=ROOT,
+        )
+        self.assertTrue(result["proven"], result["reasons"])
+
+    def test_final_report_validator_integration(self):
+        result = assess_final_report_validator(
+            "Validation command: pytest tests/ -q",
+            "review_pr",
+            validation_session={"validation_ran": True},
+        )
+        self.assertTrue(result["blocked"] or result["downgraded"])
+        self.assertTrue(
+            any(
+                f.get("rule_id") == "reviewer.validation_cwd_proof"
+                for f in result.get("findings") or []
+            )
+        )
+
+    def test_exported_from_review_proofs(self):
+        from review_proofs import assess_validation_cwd_proof_report as exported
+
+        self.assertTrue(callable(exported))
+
+
+if __name__ == "__main__":
+    unittest.main()