feat: require transient validation failure history in reviewer reports (Closes #396)

Add assess_validation_failure_history_report so reviewer final reports must
document every validation failure observed during a session, not only the
final passing result. Wire the verifier into final_report_validator,
gitea_validate_review_final_report, and the review-merge workflow template.

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

final_report_validator.py

@@ -456,6 +456,40 @@ def _rule_reviewer_git_fetch_readonly(
     return []
 
 
+def _rule_reviewer_validation_failure_history(
+    report_text: str,
+    *,
+    validation_session: dict | None = None,
+) -> list[dict[str, str]]:
+    from reviewer_validation_failure_history import (
+        assess_validation_failure_history_report,
+    )
+
+    session = validation_session or {}
+    observed = session.get("observed_failures") or []
+    if not observed:
+        return []
+
+    result = assess_validation_failure_history_report(
+        report_text,
+        validation_session=session,
+    )
+    if result.get("proven"):
+        return []
+    severity = "block" if result.get("violations") else "downgrade"
+    return [
+        validator_finding(
+            "reviewer.validation_failure_history",
+            severity,
+            "Validation failure history",
+            reason,
+            result.get("safe_next_action")
+            or "document every observed validation failure before claiming pass",
+        )
+        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 +898,7 @@ _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_failure_history,
         _rule_reviewer_validation_structured,
         _rule_reviewer_linked_issue,
         _rule_reviewer_baseline_on_failure,
@@ -970,6 +1005,7 @@ 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 +1061,7 @@ 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, ()):