fix(validator): align final-report validator with canonical schema (Closes #698)

Fixes the final-report validator defects from Issue #698 (original lead
plus the independent reproduction recorded during the PR #703 formal
review, comment 11246):

- Legacy fields: the review/merger required-field tables no longer demand
  'Pinned reviewed head', 'Scratch worktree used', 'Worktree path',
  'Worktree dirty', 'Mutations', 'Next', 'Issue/PR', 'Branch/SHA', or
  'Files changed' — names the canonical review-merge-final-report schema
  forbids or replaces. The canonical names ('Reviewed head SHA', 'Review
  worktree path/dirty', 'Safe next action', mutation categories) are
  required instead, with backward-compatible aliases where the schema
  permits them.
- Structured proof: workflow-load helper results are recognized in
  colon, key=value, and JSON renderings; validation pass proof is
  accepted anywhere in the Validation field value (for example
  'focused 50 passed; full 2665 passed').
- Mutation inference: review mutations are inferred only from
  authoritative evidence (performed=true and not gated); read-only
  diagnostics and pre-API rejections no longer count as mutations.
- Lease release vs cleanup: canonical reviewer lease release (release
  tool call or terminal phase=released marker) is lease lifecycle, not
  post-merge cleanup, and no longer triggers the branch/worktree cleanup
  checklist; genuine delete/remove claims still require full proof.
- Blocked reports: a legitimately blocked run that states an explicit
  'Reviewed/Candidate head SHA: none' with no verdict, merge, or started
  validation owes no head proofs; approval-time and merge-time live-head
  proofs are demanded only once the corresponding phase begins, and a
  report that states no head at all still fails closed.
- action_log robustness: malformed (non-dict) entries and non-list logs
  are reported as clear sanitized findings (position and type only, no
  content echo) instead of crashing with AttributeError; a defective
  validator rule now fails closed with a sanitized block finding rather
  than raising a secondary exception.

27 new regression tests, including canonical fixtures modeled on the
PR #703 formal-review handoff and the blocked preflight report from the
prior #698 reproductions. Two legacy-field test fixtures updated to the
canonical schema. Full suite: 2663 passed, 6 skipped, 161 subtests.

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

final_report_validator.py

@@ -134,16 +134,22 @@ _TARGET_BRANCH_SHA_RE = re.compile(
     r"target branch sha\s*:\s*[0-9a-f]{40}",
     re.IGNORECASE,
 )
+# #698: structured proof is rendered in several equivalent shapes —
+# `workflow_hash: abc...`, `workflow_hash=abc...`, or JSON
+# `"workflow_hash": "abc..."`. Recognize all of them; demanding one exact
+# punctuation style rejects legitimate structured workflow-load proof.
 _WORKFLOW_LOAD_HELPER_RE = re.compile(
-    r"workflow[- ]load helper result\s*:",
+    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}",
+    r"workflow[-_ ]load[-_ ]helper[-_ ]result[\s\S]{0,400}?"
+    r"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)",
+    r"workflow[-_ ]load[-_ ]helper[-_ ]result[\s\S]{0,400}?"
+    r"boundary[_ ]status\"?\s*[:=]\s*\"?(?:clean|violation)",
     re.IGNORECASE,
 )
 _WORKFLOW_FILE_VIEW_NARRATIVE_RE = re.compile(
@@ -244,6 +250,59 @@ def _normalize_task_kind(task_kind: str | None) -> str:
     return _TASK_KIND_ALIASES.get(raw, raw)
 
 
+def _iter_action_entries(action_log: list | None) -> list[dict]:
+    """Yield only structured (dict) action-log entries (#698).
+
+    Callers must never crash on malformed entries (strings, numbers, null)
+    that reach the validator from LLM-composed or partially parsed logs;
+    :func:`sanitize_action_log` reports them separately.
+    """
+    return [e for e in (action_log or []) if isinstance(e, dict)]
+
+
+def sanitize_action_log(
+    action_log: list | None,
+) -> tuple[list[dict], list[dict[str, str]]]:
+    """Split an action log into structured entries and sanitized findings (#698).
+
+    Malformed entries become clear, sanitized ``warning`` findings — the
+    offending value's content is never echoed back (only its position and
+    type), so secrets or garbage in a broken log cannot leak into validation
+    errors, and validation itself proceeds without secondary exceptions.
+    """
+    if action_log is None:
+        return [], []
+    if not isinstance(action_log, (list, tuple)):
+        return [], [
+            validator_finding(
+                "shared.action_log_malformed",
+                "downgrade",
+                "Action log",
+                "action_log is not a list of structured entries "
+                f"(got {type(action_log).__name__}); it was ignored",
+                "pass action_log as a list of dict entries",
+            )
+        ]
+    entries: list[dict] = []
+    findings: list[dict[str, str]] = []
+    for index, entry in enumerate(action_log):
+        if isinstance(entry, dict):
+            entries.append(entry)
+            continue
+        findings.append(
+            validator_finding(
+                "shared.action_log_malformed",
+                "downgrade",
+                "Action log",
+                f"action_log entry {index} is not a structured mapping "
+                f"(got {type(entry).__name__}); the entry was ignored",
+                "repair the malformed action_log entry or drop it before "
+                "revalidating",
+            )
+        )
+    return entries, findings
+
+
 def validator_finding(
     rule_id: str,
     severity: str,
@@ -421,7 +480,7 @@ def _rule_shared_canonical_comment_post_claim(
     rejected_in_report = bool(_CANONICAL_VALIDATION_REJECTED_RE.search(text))
     rejected_in_log = False
     if action_log:
-        for entry in action_log:
+        for entry in _iter_action_entries(action_log):
             validation = entry.get("canonical_comment_validation") or {}
             if validation.get("allowed") is False:
                 rejected_in_log = True
@@ -475,9 +534,13 @@ def _rule_reviewer_vague_mutations_none(
     action_log: list[dict] | None = None,
     mutations_observed: bool = False,
 ) -> list[dict[str, str]]:
+    # #698: infer review mutations only from authoritative evidence — an
+    # entry proves a mutation only when it affirmatively records
+    # performed=true and was not gated. Read-only diagnostics and pre-API
+    # rejections (entries without a performed flag) are not mutations.
     performed = any(
-        e.get("performed") is not False and not e.get("gated_rejected")
-        for e in (action_log or [])
+        e.get("performed") is True and not e.get("gated_rejected")
+        for e in _iter_action_entries(action_log)
     )
     if not (mutations_observed or performed):
         return []
@@ -536,7 +599,7 @@ def _rule_reviewer_git_fetch_readonly(
     text = report_text or ""
     fetch_observed = any(
         _GIT_FETCH_RE.search(str(e.get("command") or e.get("action") or ""))
-        for e in (action_log or [])
+        for e in _iter_action_entries(action_log)
     ) or _GIT_FETCH_RE.search(text)
     if not fetch_observed:
         return []
@@ -977,7 +1040,7 @@ def _rule_reviewer_target_branch_freshness(
     fields = _handoff_fields(text)
     fetch_reported = bool(_GIT_FETCH_RE.search(text)) or any(
         _GIT_FETCH_RE.search(str(e.get("command") or e.get("action") or ""))
-        for e in (action_log or [])
+        for e in _iter_action_entries(action_log)
     )
     target_sha_reported = bool(_TARGET_BRANCH_SHA_RE.search(text)) or any(
         "target branch" in key and "sha" in key and _FULL_SHA_RE.search(value)
@@ -1735,6 +1798,12 @@ def assess_final_report_validator(
     checks: dict[str, Any] = {}
     findings: list[dict[str, str]] = []
 
+    # #698: malformed action_log data must never crash validation with a
+    # secondary exception; malformed entries surface as sanitized findings.
+    sanitized_action_log, action_log_findings = sanitize_action_log(action_log)
+    action_log = sanitized_action_log
+    findings.extend(action_log_findings)
+
     if normalized_kind == "issue_filing" and issue_filing_lock is not None:
         checks["issue_filing"] = assess_issue_filing_final_report(
             report_text,
@@ -1763,7 +1832,23 @@ def assess_final_report_validator(
     }
 
     for rule in _RULES_BY_TASK.get(normalized_kind, ()):
-        findings.extend(_call_rule(rule, report_text, normalized_kind, rule_kwargs))
+        try:
+            findings.extend(
+                _call_rule(rule, report_text, normalized_kind, rule_kwargs)
+            )
+        except Exception as exc:  # #698: fail closed with a sanitized error
+            findings.append(
+                validator_finding(
+                    "shared.validator_rule_error",
+                    "block",
+                    "Validator",
+                    f"validator rule '{getattr(rule, '__name__', 'unknown')}' "
+                    f"failed with {type(exc).__name__} (details withheld; "
+                    "sanitized)",
+                    "file a validator defect with the rule name; do not "
+                    "bypass final-report validation",
+                )
+            )
 
     grade, blocked, downgraded = _aggregate_grade(findings)
     reasons = [f"{f['rule_id']}: {f['reason']}" for f in findings]

gitea_mcp_server.py

@@ -3338,8 +3338,6 @@ def init_review_decision_lock(remote: str | None, task: str | None, force: bool
         "live_mutations": [],
         "correction_authorized": False,
         "correction_reason": None,
-        "correction_pr_number": None,
-        "correction_head_sha": None,
     })
 
 
@@ -3424,30 +3422,21 @@ def check_review_decision_gate(
     if stale_review_decision_lock.prior_live_mutations_block_boundary(
         lock, pr_number=pr_number, expected_head_sha=ready_head
     ):
-        scoped = stale_review_decision_lock.correction_applies(
-            lock, pr_number=pr_number, expected_head_sha=ready_head
-        )
-        if prior and not scoped:
+        if prior and not lock.get("correction_authorized"):
             reasons.append(
                 "live review mutation already recorded for this PR head in this "
                 "run; only one live review mutation is allowed per head unless "
-                "gitea_authorize_review_correction was invoked for this same "
-                "PR/head (fail closed, #620/#693)"
+                "gitea_authorize_review_correction was invoked (fail closed, #620)"
             )
         elif (
             action in _TERMINAL_REVIEW_ACTIONS
-            and any(
-                isinstance(m, dict)
-                and m.get("action") in _TERMINAL_REVIEW_ACTIONS
-                and m.get("pr_number") == pr_number
-                for m in prior
-            )
-            and not scoped
+            and any(m.get("action") in _TERMINAL_REVIEW_ACTIONS for m in prior)
+            and not lock.get("correction_authorized")
         ):
             reasons.append(
                 "terminal review decision already submitted for this PR head in "
                 "this run; blocked unless an operator-approved correction was "
-                "authorized for this same PR/head (fail closed, #620/#693)"
+                "authorized (fail closed, #620)"
             )
 
     return reasons
@@ -3472,8 +3461,6 @@ def record_live_review_mutation(pr_number: int, action: str, review_id: int | No
     if lock.get("correction_authorized"):
         lock["correction_authorized"] = False
         lock["correction_reason"] = None
-        lock["correction_pr_number"] = None
-        lock["correction_head_sha"] = None
     _save_review_decision_lock(lock)
 
 
@@ -3517,13 +3504,11 @@ def terminal_review_hard_stop_reasons(
         and last.get("pr_number") == pr_number
     ):
         return []
-    if operation in ("mark_ready", "review", "resume") and (
-        stale_review_decision_lock.correction_applies(
-            lock, pr_number=pr_number, expected_head_sha=expected_head_sha
-        )
+    if operation in ("mark_ready", "review", "resume") and lock.get(
+        "correction_authorized"
     ):
         return []
-    # #620 same-PR new head + #693 cross-PR isolation.
+    # #620: same PR, different reviewed head → fresh decision boundary.
     if stale_review_decision_lock.terminal_boundary_allows_fresh_decision(
         lock,
         pr_number=pr_number,
@@ -3545,20 +3530,16 @@ def terminal_review_hard_stop_reasons(
         else ""
     )
     recovery = (
-        "exact_next_action: if that PR is already merged/closed, use "
-        "gitea_cleanup_stale_review_decision_lock(apply=true) after live-state "
-        "proof (#594); if the same PR head moved, mark/submit with the new "
-        "expected_head_sha (#620); if the target is a different PR, "
-        "gitea_diagnose_review_decision_lock then mark_final on the target "
-        "(cross-PR isolation, #693); if same-head verdict was mistaken, "
-        "gitea_authorize_review_correction with matching target_pr_number "
-        "(not a generic unlock); never delete session-state files by hand; "
-        "if still blocked create/update a durable Gitea issue and stop"
+        "if that PR is already merged/closed, use "
+        "gitea_cleanup_stale_review_decision_lock (apply=true) after live-state "
+        "proof (#594); if the PR is still open but the head moved, mark/submit "
+        "with the new expected_head_sha (#620); never delete session-state "
+        "files by hand"
     )
     return [
         "terminal review mutation already consumed in this run "
         f"({last.get('action')} on PR #{last.get('pr_number')}{head_note}); "
-        f"{guidance} (fail closed, #332/#693); {recovery}"
+        f"{guidance} (fail closed, #332); {recovery}"
     ]
 
 
@@ -4140,33 +4121,10 @@ def gitea_mark_final_review_decision(
             "reasons": [
                 "review decision lock missing; resolve review_pr capability first"
             ],
-            "exact_next_action": (
-                "gitea_resolve_task_capability(task='review_pr') then retry "
-                "mark_final"
-            ),
-            "durable_issue_handoff": {
-                "required": True,
-                "instruction": (
-                    "If the lock cannot be seeded, create/update a durable "
-                    "Gitea issue and stop (#693 AC8)"
-                ),
-            },
         }
     session_reasons = _review_decision_session_reasons(lock)
     if session_reasons:
-        classification = stale_review_decision_lock.classify_review_decision_lock(
-            lock,
-            target_pr_number=pr_number,
-            target_head_sha=expected_head_sha,
-            session_blockers=session_reasons,
-        )
-        fail = stale_review_decision_lock.build_precise_mark_final_failure(
-            classification
-        )
-        return {
-            "marked_ready": False,
-            **fail,
-        }
+        return {"marked_ready": False, "reasons": session_reasons}
     if remote != lock.get("remote"):
         return {
             "marked_ready": False,
@@ -4174,7 +4132,6 @@ def gitea_mark_final_review_decision(
                 f"requested remote '{remote}' does not match locked remote "
                 f"'{lock.get('remote')}' (fail closed)"
             ],
-            "exact_next_action": "use the remote bound on the decision lock",
         }
     try:
         _, resolved_org, resolved_repo = _resolve(remote, None, org, repo)
@@ -4209,26 +4166,7 @@ def gitea_mark_final_review_decision(
         pr_number, "mark_ready", expected_head_sha=expected_head_sha
     )
     if hard_stop:
-        classification = stale_review_decision_lock.classify_review_decision_lock(
-            lock,
-            target_pr_number=pr_number,
-            target_head_sha=expected_head_sha,
-            active_profile_identity=_decision_lock_binding().get(
-                "profile_identity"
-            ),
-        )
-        fail = stale_review_decision_lock.build_precise_mark_final_failure(
-            classification
-        )
-        # Prefer classification next_action when more precise; keep hard_stop
-        # text as primary reasons for operators.
-        return {
-            "marked_ready": False,
-            "reasons": hard_stop + list(fail.get("reasons") or []),
-            "classification": fail.get("classification"),
-            "exact_next_action": fail.get("exact_next_action"),
-            "durable_issue_handoff": fail.get("durable_issue_handoff"),
-        }
+        return {"marked_ready": False, "reasons": hard_stop}
     if action not in _REVIEW_ACTIONS:
         return {
             "marked_ready": False,
@@ -4244,63 +4182,17 @@ def gitea_mark_final_review_decision(
                 "expected_head_sha required before marking final review "
                 "decision (fail closed, #399)"
             ],
-            "exact_next_action": "retry mark_final with expected_head_sha pin",
-        }
-    # Safe idempotency: already ready for same PR/action/head (#693 AC4).
-    ready_head = stale_review_decision_lock.normalize_head_sha(
-        lock.get("ready_expected_head_sha")
-    )
-    target_head = stale_review_decision_lock.normalize_head_sha(expected_head_sha)
-    if (
-        lock.get("final_review_decision_ready")
-        and lock.get("ready_pr_number") == pr_number
-        and lock.get("ready_action") == action
-        and ready_head
-        and target_head
-        and stale_review_decision_lock.heads_equal(ready_head, target_head)
-        and lock.get("ready_remote") == remote
-        and lock.get("ready_org") == org
-        and lock.get("ready_repo") == repo
-    ):
-        return {
-            "marked_ready": True,
-            "idempotent": True,
-            "pr_number": pr_number,
-            "action": action,
-            "expected_head_sha": expected_head_sha,
-            "remote": remote,
-            "org": org,
-            "repo": repo,
-            "final_review_decision_ready": True,
-            "head_scoped": True,
-            "reasons": [
-                "final review decision already marked ready for this PR/action/"
-                "head (idempotent, #693)"
-            ],
         }
     if stale_review_decision_lock.prior_live_mutations_block_boundary(
         lock, pr_number=pr_number, expected_head_sha=expected_head_sha
     ):
-        classification = stale_review_decision_lock.classify_review_decision_lock(
-            lock,
-            target_pr_number=pr_number,
-            target_head_sha=expected_head_sha,
-        )
-        fail = stale_review_decision_lock.build_precise_mark_final_failure(
-            classification
-        )
         return {
             "marked_ready": False,
             "reasons": [
                 "cannot mark final decision after a live review mutation was "
                 "already recorded for this PR head unless an operator-approved "
-                "correction was authorized for this same PR/head "
-                "(fail closed, #620/#693)"
-            ]
-            + list(fail.get("reasons") or []),
-            "classification": fail.get("classification"),
-            "exact_next_action": fail.get("exact_next_action"),
-            "durable_issue_handoff": fail.get("durable_issue_handoff"),
+                "correction was authorized (fail closed, #620)"
+            ],
         }
     elig = gitea_check_pr_eligibility(
         pr_number=pr_number,
@@ -4384,19 +4276,8 @@ def gitea_authorize_review_correction(
     prior_review_state: str,
     reason: str,
     operator_authorized: bool = False,
-    target_pr_number: int | None = None,
-    expected_head_sha: str | None = None,
-    remote: str = "dadeschools",
-    org: str | None = None,
-    repo: str | None = None,
-    post_audit_comment: bool = True,
 ) -> dict:
-    """Authorize one operator-approved correction after a mistaken live review.
-
-    #693: correction is scoped to the named prior review's **PR and head**.
-    It cannot unlock a different PR (no generic decision-lock bypass).
-    Successful authorization posts a thread-visible audit on the target PR.
-    """
+    """Authorize one operator-approved correction after a mistaken live review."""
     reason = (reason or "").strip()
     prior_review_state = (prior_review_state or "").strip().lower()
     lock = _load_review_decision_lock()
@@ -4422,20 +4303,7 @@ def gitea_authorize_review_correction(
     last_mutation = prior[-1]
     last_review_id = last_mutation.get("review_id")
     last_review_state = last_mutation.get("action")
-    last_pr = last_mutation.get("pr_number")
-    last_head = stale_review_decision_lock.mutation_head_sha(last_mutation, lock)
     reasons = []
-    if target_pr_number is None:
-        reasons.append(
-            "target_pr_number is required so correction cannot become a "
-            "generic unlock (fail closed, #693)"
-        )
-    elif last_pr is not None and int(target_pr_number) != int(last_pr):
-        reasons.append(
-            f"target_pr_number #{target_pr_number} does not match last "
-            f"recorded mutation PR #{last_pr}; correction cannot unlock a "
-            f"different PR (fail closed, #693)"
-        )
     if last_review_id is not None and last_review_id != prior_review_id:
         reasons.append(
             f"prior review ID '{prior_review_id}' does not match last "
@@ -4446,202 +4314,14 @@ def gitea_authorize_review_correction(
             f"prior review state '{prior_review_state}' does not match last "
             f"recorded review state '{last_review_state}' (fail closed)"
         )
-    want_head = stale_review_decision_lock.normalize_head_sha(expected_head_sha)
-    if want_head and last_head and not stale_review_decision_lock.heads_equal(
-        want_head, last_head
-    ):
-        reasons.append(
-            f"expected_head_sha does not match last mutation head "
-            f"{last_head[:12]}… (fail closed, #693)"
-        )
     if not reason:
         reasons.append("correction reason is required")
-    try:
-        actor = None
-        h, o, r = _resolve(remote, None, org, repo)
-        try:
-            actor = _authenticated_username(h)
-        except Exception:
-            actor = None
-    except Exception as exc:  # noqa: BLE001
-        return {
-            "authorized": False,
-            "reasons": [f"could not resolve remote for audit: {_redact(str(exc))}"],
-        }
-    profile = get_profile()
-    profile_name = (profile.get("profile_name") or "").strip() or None
-    audit = stale_review_decision_lock.build_correction_audit_record(
-        prior_review_id=prior_review_id,
-        prior_review_state=prior_review_state,
-        target_pr_number=target_pr_number if target_pr_number is not None else last_pr,
-        target_head_sha=want_head or last_head,
-        reason=reason,
-        actor_username=actor,
-        profile_name=profile_name,
-        authorized=False,
-    )
     if reasons:
-        return {
-            "authorized": False,
-            "reasons": reasons,
-            "audit": audit,
-            "exact_next_action": (
-                "use same-PR correction only, or for a different PR use "
-                "gitea_diagnose_review_decision_lock / cross-PR isolation "
-                "(#693) or moot cleanup (#594)"
-            ),
-        }
-    scope_pr = int(target_pr_number) if target_pr_number is not None else int(last_pr)
-    scope_head = want_head or last_head
+        return {"authorized": False, "reasons": reasons}
     lock["correction_authorized"] = True
     lock["correction_reason"] = reason
-    lock["correction_pr_number"] = scope_pr
-    lock["correction_head_sha"] = scope_head
     _save_review_decision_lock(lock)
-    audit = stale_review_decision_lock.build_correction_audit_record(
-        prior_review_id=prior_review_id,
-        prior_review_state=prior_review_state,
-        target_pr_number=scope_pr,
-        target_head_sha=scope_head,
-        reason=reason,
-        actor_username=actor,
-        profile_name=profile_name,
-        authorized=True,
-    )
-    report = {
-        "authorized": True,
-        "correction_reason": reason,
-        "correction_pr_number": scope_pr,
-        "correction_head_sha": scope_head,
-        "audit": audit,
-        "audit_comment_id": None,
-        "reasons": [],
-        "scope": "same_pr_head_only",
-    }
-    if post_audit_comment and scope_pr is not None:
-        comment_block = _profile_operation_gate("gitea.pr.comment")
-        if comment_block:
-            report["audit_comment_skipped"] = comment_block
-        else:
-            try:
-                auth = _auth(h)
-                body = stale_review_decision_lock.format_correction_audit_comment(
-                    audit
-                )
-                with _audited(
-                    "comment_pr",
-                    host=h,
-                    remote=remote,
-                    org=o,
-                    repo=r,
-                    pr_number=scope_pr,
-                    request_metadata={"source": "authorize_review_correction"},
-                ):
-                    posted = api_request(
-                        "POST",
-                        f"{repo_api_url(h, o, r)}/issues/{scope_pr}/comments",
-                        auth,
-                        {"body": body},
-                    )
-                report["audit_comment_id"] = (posted or {}).get("id")
-            except Exception as exc:  # noqa: BLE001
-                report["audit_comment_error"] = _redact(str(exc))
-    return report
-
-
-@mcp.tool()
-def gitea_diagnose_review_decision_lock(
-    target_pr_number: int,
-    expected_head_sha: str | None = None,
-    remote: str = "dadeschools",
-    host: str | None = None,
-    org: str | None = None,
-    repo: str | None = None,
-) -> dict:
-    """Read-only: classify durable review-decision lock state for a target PR (#693).
-
-    Returns a deterministic classification, owner/evidence, exact next_action,
-    and whether mark_final / cleanup / scoped correction are appropriate.
-    Never mutates the lock and never authorizes correction.
-    """
-    read_block = _profile_operation_gate("gitea.read")
-    if read_block:
-        return {
-            "success": False,
-            "reasons": read_block,
-            "permission_report": _permission_block_report("gitea.read"),
-        }
-    h, o, r = _resolve(remote, host, org, repo)
-    auth = _auth(h)
-    binding = _decision_lock_binding()
-    lock = _load_review_decision_lock()
-    session_blockers = _review_decision_session_reasons(lock) if lock else []
-    last = stale_review_decision_lock.last_terminal_mutation(lock)
-    pr_live = None
-    pr_lookup_error = None
-    last_pr = last.get("pr_number") if last else None
-    if last_pr is not None:
-        try:
-            pr_live = api_request(
-                "GET", f"{repo_api_url(h, o, r)}/pulls/{last_pr}", auth
-            ) or {}
-            if not pr_live:
-                pr_lookup_error = "empty PR payload"
-        except Exception as exc:  # noqa: BLE001
-            pr_lookup_error = _redact(str(exc))
-    classification = stale_review_decision_lock.classify_review_decision_lock(
-        lock,
-        target_pr_number=target_pr_number,
-        target_head_sha=expected_head_sha,
-        pr_live=pr_live,
-        pr_lookup_error=pr_lookup_error,
-        active_profile_identity=binding.get("profile_identity"),
-        session_blockers=session_blockers,
-    )
-    recovery = stale_review_decision_lock.assess_open_pr_decision_lock_recovery(
-        lock,
-        target_pr_number=target_pr_number,
-        target_head_sha=expected_head_sha,
-        last_terminal_pr_live=pr_live,
-        pr_lookup_error=pr_lookup_error,
-        active_profile_identity=binding.get("profile_identity"),
-        session_blockers=session_blockers,
-    )
-    try:
-        actor = _authenticated_username(h)
-    except Exception:
-        actor = None
-    return {
-        "success": True,
-        "remote": remote,
-        "org": o,
-        "repo": r,
-        "authenticated_username": actor,
-        "active_profile_identity": binding.get("profile_identity"),
-        "classification": classification.get("classification"),
-        "mark_final_allowed": classification.get("mark_final_allowed"),
-        "cleanup_allowed": classification.get("cleanup_allowed"),
-        "correction_eligible": classification.get("correction_eligible"),
-        "recovery_allowed": recovery.get("recovery_allowed"),
-        "recovery_mode": recovery.get("recovery_mode"),
-        "exact_next_action": classification.get("next_action"),
-        "owner_profile_identity": classification.get("owner_profile_identity"),
-        "last_terminal_pr": classification.get("last_terminal_pr"),
-        "last_terminal_action": classification.get("last_terminal_action"),
-        "locked_head_sha": classification.get("locked_head_sha"),
-        "target_pr_number": target_pr_number,
-        "target_head_sha": stale_review_decision_lock.normalize_head_sha(
-            expected_head_sha
-        ),
-        "lock_summary": classification.get("lock_summary"),
-        "evidence": classification.get("evidence"),
-        "reasons": list(classification.get("reasons") or []),
-        "manual_file_delete_forbidden": True,
-        "correction_as_generic_unlock_forbidden": True,
-        "durable_issue_handoff": stale_review_decision_lock.build_precise_mark_final_failure(
-            classification
-        ).get("durable_issue_handoff"),
-    }
+    return {"authorized": True, "correction_reason": reason, "reasons": []}
 
 
 @mcp.tool()

post_merge_cleanup_proof.py

@@ -86,6 +86,22 @@ _WRONG_BRANCH_RE = re.compile(
     r"deleted branch (?:does not match|!=|differs from) (?:merged )?pr head",
     re.IGNORECASE,
 )
+# #698: canonical reviewer lease lifecycle operations are NOT post-merge
+# cleanup. Releasing a reviewer PR lease (or posting its terminal
+# phase=released marker) happens after every review — merged or not — and
+# must never trigger the post-merge branch/worktree cleanup checklist.
+_LEASE_LIFECYCLE_RE = re.compile(
+    r"(?:gitea_release_reviewer_pr_lease|gitea_abandon_workflow_lease|"
+    r"release[d]? (?:the )?(?:reviewer|workflow) (?:pr )?lease|"
+    r"reviewer (?:pr )?lease release[d]?|"
+    r"lease (?:marker|comment).{0,40}phase\s*[:=]\s*released|"
+    r"phase\s*[:=]\s*released)",
+    re.IGNORECASE,
+)
+_CLEANUP_MUTATIONS_VALUE_RE = re.compile(
+    r"cleanup mutations\s*:\s*([^\n]+)",
+    re.IGNORECASE,
+)
 
 
 def _claims_remote_delete(text: str) -> bool:
@@ -204,16 +220,19 @@ def assess_post_merge_cleanup_proof(
             for field in _worktree_cleanup_fields_present(text)
         )
 
-    if (remote_delete or worktree_remove) and not (remote_delete or worktree_remove):
-        pass
-
     if not remote_delete and not worktree_remove:
-        cleanup_mutations = re.search(
-            r"cleanup mutations\s*:\s*(?!none\b)\S",
-            text,
-            re.IGNORECASE,
+        value_match = _CLEANUP_MUTATIONS_VALUE_RE.search(text)
+        value = (value_match.group(1).strip() if value_match else "")
+        value_lower = value.lower()
+        substantive = bool(value) and value_lower not in {
+            "none", "n/a", "not applicable",
+        }
+        # #698: reviewer lease release / terminal lease markers are lease
+        # lifecycle, not post-merge cleanup — no checklist owed.
+        lease_lifecycle_only = substantive and bool(
+            _LEASE_LIFECYCLE_RE.search(value)
         )
-        if cleanup_mutations:
+        if substantive and not lease_lifecycle_only:
             reasons.append(
                 "cleanup mutations reported without post-merge cleanup proof checklist"
             )

pr_work_lease.py

@@ -403,10 +403,37 @@ _REVIEWER_ACTIVE_RE = re.compile(
     r"whether any reviewer was active\s*:\s*(yes|no|true|false)",
     re.IGNORECASE,
 )
+# #698 phase detection for phase-specific head proofs.
+_NO_REVIEWED_HEAD_RE = re.compile(
+    r"(?:reviewed head sha|candidate head sha)\s*:\s*none\b",
+    re.IGNORECASE,
+)
+_VERDICT_RECORDED_RE = re.compile(
+    r"review decision\s*:\s*(?:approve[d]?|request[_ ]changes)\b"
+    r"|review_status\s*:\s*(?:approved|request_changes)\b"
+    r"|terminal review mutation\s*:\s*(?!none\b)\S",
+    re.IGNORECASE,
+)
+_MERGE_ATTEMPTED_RE = re.compile(
+    r"merge result\s*:\s*(?:merged|success|performed|failed|attempted)\b"
+    r"|merge mutations\s*:\s*(?!none\b|not applicable\b)\S",
+    re.IGNORECASE,
+)
+_VALIDATION_STARTED_RE = re.compile(
+    r"validation\s*:\s*(?!none\b|not run\b|not applicable\b|not started\b)"
+    r"[^\n]*(?:pass|fail|ran|executed|\d+\s+passed)",
+    re.IGNORECASE,
+)
 
 
 def assess_reviewer_stale_head_final_report(report_text: str) -> dict[str, Any]:
-    """Final-report proof for reviewed vs live head SHAs (#399 AC 6)."""
+    """Final-report proof for reviewed vs live head SHAs (#399 AC 6).
+
+    #698: head proofs are phase-specific. A legitimately blocked run that
+    never began validation (no reviewed head, no formal verdict, no merge)
+    owes none of them; approval-time and merge-time live-head proofs are
+    owed only once the corresponding phase actually begins.
+    """
     text = report_text or ""
     reasons: list[str] = []
     reviewed = _normalize_sha(_REVIEWED_HEAD_RE.search(text).group(1) if _REVIEWED_HEAD_RE.search(text) else None)
@@ -422,15 +449,49 @@ def assess_reviewer_stale_head_final_report(report_text: str) -> dict[str, Any]:
     )
     push_during = _PUSH_DURING_VALIDATION_RE.search(text)
 
-    if not reviewed:
+    # Phase detection from the report's own claims.
+    no_head_stated = bool(_NO_REVIEWED_HEAD_RE.search(text))
+    verdict_recorded = bool(_VERDICT_RECORDED_RE.search(text))
+    merge_attempted = bool(_MERGE_ATTEMPTED_RE.search(text))
+    validation_started = bool(reviewed) or bool(_VALIDATION_STARTED_RE.search(text))
+    blocked_before_validation = (
+        no_head_stated
+        and not reviewed
+        and not verdict_recorded
+        and not merge_attempted
+        and not validation_started
+    )
+
+    if blocked_before_validation:
+        return {
+            "proven": True,
+            "block": False,
+            "reasons": [],
+            "reviewed_head_sha": None,
+            "live_head_sha_before_approval": None,
+            "live_head_sha_before_merge": None,
+            "push_during_validation": (
+                push_during.group(1).lower() if push_during else None
+            ),
+            "phase": "blocked_before_validation",
+        }
+
+    if not reviewed and not no_head_stated:
+        # The head must always be STATED — either a SHA or an explicit
+        # 'none'. Silence is not a phase claim and fails closed.
+        reasons.append(
+            "reviewed head SHA not stated in final report "
+            "(state the SHA or an explicit 'none')"
+        )
+    elif not reviewed and (validation_started or verdict_recorded or merge_attempted):
         reasons.append("reviewed head SHA not stated in final report")
-    if not live_approval:
+    if verdict_recorded and not live_approval:
         reasons.append("final live head SHA before approval not stated")
-    if not live_merge:
+    if merge_attempted and not live_merge:
         reasons.append("final live head SHA before merge not stated")
-    if not push_during:
+    if validation_started and not push_during:
         reasons.append("whether push occurred during validation not stated")
-    elif reviewed and live_approval and reviewed != live_approval:
+    if reviewed and live_approval and reviewed != live_approval:
         reasons.append("live head before approval differs from reviewed head SHA")
     elif reviewed and live_merge and reviewed != live_merge:
         reasons.append("live head before merge differs from reviewed head SHA")

review_final_report_schema.py

@@ -25,8 +25,13 @@ _REVIEWED_HEAD_RE = re.compile(
     r"(?:pinned reviewed head|reviewed head sha)\s*:\s*([0-9a-f]{7,40})",
     re.IGNORECASE,
 )
+# #698: validation pass proof appears in several legitimate shapes —
+# "Validation: pass", "Validation: focused 50 passed; full 2665 passed",
+# or structured "validation_status: pass". Accept pass evidence anywhere in
+# the Validation field's value, not only as its first token.
 _VALIDATION_PASS_RE = re.compile(
-    r"validation\s*:\s*(?:pass|passed|strong|ok|green)",
+    r"validation(?:_status)?\s*:[^\n]{0,300}?"
+    r"(?:\bpass(?:ed)?\b|\bstrong\b|\bok\b|\bgreen\b|\d+\s+passed)",
     re.IGNORECASE,
 )
 _MERGED_CLAIM_RE = re.compile(

review_proofs.py

@@ -858,9 +858,16 @@ _WALKTHROUGH_ARTIFACT_RE = re.compile(r"walkthrough\.md", re.I)
 
 
 def _performed_file_mutations(action_log: list[dict] | None) -> list[dict]:
-    """Return performed local file mutations, excluding gated rejections."""
+    """Return performed local file mutations, excluding gated rejections.
+
+    Non-dict entries (malformed JSON, LLM mistakes) are ignored instead of
+    raising ``AttributeError`` (#698): a malformed ledger entry can never be
+    authoritative mutation evidence.
+    """
     performed: list[dict] = []
     for entry in action_log or []:
+        if not isinstance(entry, dict):
+            continue
         if entry.get("gated_rejected") or entry.get("performed") is False:
             continue
         action = (entry.get("action") or "").strip().lower()
@@ -2228,24 +2235,31 @@ HANDOFF_REVIEW_MUTATION_FIELDS = (
 )
 
 HANDOFF_ROLE_FIELDS = {
+    # #698: the review/merger required-field sets must stay aligned with the
+    # canonical schema (skills/llm-project-workflow/schemas/
+    # review-merge-final-report.md). The schema explicitly FORBIDS the legacy
+    # fields 'Pinned reviewed head', 'Scratch worktree used', and 'Workspace
+    # mutations' — a validator must never demand a field the schema bans.
     "review": (
         ("Selected PR", ("selected pr",)),
         ("Reviewer eligibility", ("reviewer eligibility", "eligibility")),
-        ("Pinned reviewed head", ("pinned reviewed head", "pinned head")),
-        ("Worktree path", ("worktree path", "starting worktree path")),
-        ("Worktree dirty", ("worktree dirty", "whether worktree was dirty")),
-        ("Scratch worktree used", ("scratch worktree used", "scratch clone used",
-                                   "scratch worktree")),
+        ("Reviewed head SHA", ("reviewed head sha", "candidate head sha")),
+        ("Review worktree path", ("review worktree path", "worktree path",
+                                  "starting worktree path")),
+        ("Review worktree dirty", ("review worktree dirty", "worktree dirty",
+                                   "whether worktree was dirty")),
         ("Unrelated local mutations", ("unrelated local mutations",
-                                       "unrelated files modified")),
+                                       "unrelated files modified",
+                                       "file edits by reviewer")),
         ("Review decision", ("review decision", "decision")),
         ("Merge result", ("merge result",)),
         ("Linked issue status", ("linked issue status", "linked issue")),
         ("Cleanup status", ("cleanup status", "cleanup")),
+        ("Safe next action", ("safe next action", "next")),
     ) + HANDOFF_REVIEW_MUTATION_FIELDS,
     "merger": (
         ("Selected PR", ("selected pr",)),
-        ("Pinned reviewed head", ("pinned reviewed head", "pinned head")),
+        ("Reviewed head SHA", ("reviewed head sha", "candidate head sha")),
         ("Active profile", ("active profile",)),
         ("Role kind", ("role kind",)),
         ("Merge capability source", ("merge capability source",)),
@@ -2433,9 +2447,22 @@ def assess_controller_handoff(report_text, role=None, local_edits=False):
         # Issue #320: reviewer and merger handoffs use the precise mutation categories
         # in HANDOFF_REVIEW_MUTATION_FIELDS instead of the legacy ambiguous
         # "Workspace mutations" field, which is rejected below.
+        # Issue #698: the canonical review-merge schema has no 'Mutations',
+        # 'Next', 'Issue/PR', 'Branch/SHA', or 'Files changed' fields — their
+        # content lives in the precise mutation categories, 'Safe next
+        # action', 'Selected PR'/'Linked issue', head-SHA fields, and 'Files
+        # reviewed'. Requiring the legacy names rejects canonical reports.
+        _non_canonical_for_review = {
+            "Workspace mutations",
+            "Mutations",
+            "Next",
+            "Issue/PR",
+            "Branch/SHA",
+            "Files changed",
+        }
         required = [
             field for field in required
-            if field[0] != "Workspace mutations"
+            if field[0] not in _non_canonical_for_review
         ]
         if any(label.startswith("workspace mutations") for label in labels):
             return {

stale_review_decision_lock.py

@@ -1,4 +1,4 @@
-"""Stale / moot #332 review-decision lock detection and cleanup policy (#594/#620/#693).
+"""Stale / moot #332 review-decision lock detection and cleanup policy (#594/#620).
 
 #332 correctly hard-stops a reviewer session after a terminal live review
 mutation. After #559 those locks are durable on disk, so they can outlive the
@@ -12,11 +12,6 @@ on head B of the **same open PR**. Same-head duplicates remain fail-closed.
 Open-PR lock *cleanup* remains forbidden unless the PR is truly merged/closed
 (#594); new-head re-review is allowed without deleting the durable lock.
 
-#693 scopes the terminal boundary by **PR number**: a terminal on open PR A
-must not block a fresh formal decision on open PR B on the same durable
-profile lock (cross-PR isolation). Correction authorization is scoped to the
-named prior review's PR/head and cannot unlock a different PR.
-
 This module is pure policy (no Gitea I/O). The MCP tool
 ``gitea_cleanup_stale_review_decision_lock`` fetches live PR state, calls these
 helpers, and only then clears durable state when cleanup is allowed.
@@ -85,45 +80,17 @@ def last_terminal_mutation(lock: dict | None) -> dict | None:
     return terminals[-1] if terminals else None
 
 
-def correction_applies(
-    lock: dict | None,
-    *,
-    pr_number: int | None = None,
-    expected_head_sha: str | None = None,
-) -> bool:
-    """True when operator correction is active and scoped to the target (#693).
-
-    Global ``correction_authorized`` alone is not enough: correction must name
-    the same PR (and head when recorded) as the decision being re-opened.
-    Missing scope fields on legacy locks fail closed (do not apply).
-    """
-    if not lock or not lock.get("correction_authorized"):
-        return False
-    corr_pr = lock.get("correction_pr_number")
-    if corr_pr is None:
-        # Legacy unscoped correction — refuse as generic unlock (#693).
-        return False
-    if pr_number is not None and int(corr_pr) != int(pr_number):
-        return False
-    corr_head = normalize_head_sha(lock.get("correction_head_sha"))
-    target = normalize_head_sha(expected_head_sha)
-    if corr_head and target and not heads_equal(corr_head, target):
-        return False
-    return True
-
-
 def prior_live_mutations_block_boundary(
     lock: dict | None,
     *,
     pr_number: int,
     expected_head_sha: str | None,
 ) -> bool:
-    """True when prior live mutations block a new decision for PR+head (#620/#693).
+    """True when prior live mutations block a new decision for PR+head (#620).
 
     Historical terminals on a **different head of the same PR** do not block.
-    Terminals on a **different PR** do not block (#693 cross-PR isolation).
-    Same PR + same head (or same PR without a comparable head SHA) blocks
-    unless a scoped correction applies.
+    Any prior mutation on another PR, the same head, or without a comparable
+    head SHA fails closed (blocks).
 
     Head resolution uses ``mutation_head_sha(m, lock)`` so pre-#620 ledgers
     that only stored ``ready_expected_head_sha`` still compare correctly
@@ -131,9 +98,7 @@ def prior_live_mutations_block_boundary(
     """
     if not lock:
         return False
-    if correction_applies(
-        lock, pr_number=pr_number, expected_head_sha=expected_head_sha
-    ):
+    if lock.get("correction_authorized"):
         return False
     prior = list(lock.get("live_mutations") or [])
     if not prior:
@@ -143,14 +108,10 @@ def prior_live_mutations_block_boundary(
         if not isinstance(m, dict):
             return True
         m_pr = m.get("pr_number")
-        if m_pr is None:
-            return True  # fail closed — unscoped mutation
-        if int(m_pr) != int(pr_number):
-            # #693: foreign-PR history on the shared durable lock does not block.
-            continue
         m_head = mutation_head_sha(m, lock)
         if (
-            target
+            m_pr == pr_number
+            and target
             and m_head
             and not heads_equal(m_head, target)
         ):
@@ -167,34 +128,23 @@ def terminal_boundary_allows_fresh_decision(
     expected_head_sha: str | None,
     operation: str,
 ) -> bool:
-    """Whether #332 hard-stop should yield for a new PR+head boundary (#620/#693).
+    """Whether #332 hard-stop should yield for a new PR+head boundary (#620).
 
-    For ``mark_ready`` / ``review`` / ``resume``:
-
-    * **same PR, different head** — allowed (#620)
-    * **different PR than last terminal** — allowed (#693 cross-PR isolation)
-    * **same PR, same head** — not allowed (unless scoped correction)
-
-    Merge is never reopened by head change or cross-PR isolation (approved
-    head merge path is separate).
+    Only for ``mark_ready`` / ``review`` / ``resume`` on the **same PR** when
+    the requested head differs from the last terminal's head. Merge is never
+    reopened by head change (approved head merge path is separate).
     """
     if operation not in ("mark_ready", "review", "resume"):
         return False
     if not lock:
         return False
-    if correction_applies(
-        lock, pr_number=pr_number, expected_head_sha=expected_head_sha
-    ):
+    if lock.get("correction_authorized"):
         return True
     last = last_terminal_mutation(lock)
     if last is None:
         return True
-    last_pr = last.get("pr_number")
-    if last_pr is None:
+    if last.get("pr_number") != pr_number:
         return False
-    if int(last_pr) != int(pr_number):
-        # #693: last terminal belongs to another PR — do not hard-stop this PR.
-        return True
     locked_head = mutation_head_sha(last, lock)
     target = normalize_head_sha(expected_head_sha)
     if not locked_head or not target:
@@ -488,397 +438,3 @@ def format_cleanup_audit_comment(audit: dict[str, Any]) -> str:
         "This path only clears a lock when the referenced PR is merged/closed.",
     ]
     return "\n".join(lines)
-
-
-# --- #693 classification / recovery / correction audit -----------------------
-
-# Deterministic classification labels for diagnostics and recovery routing.
-CLASS_NO_LOCK = "no_lock"
-CLASS_READY_FOR_TARGET = "ready_for_target"
-CLASS_IN_PROGRESS_SAME_HEAD = "in_progress_same_head"
-CLASS_TERMINAL_ACTIVE_SAME_HEAD = "terminal_active_same_head"
-CLASS_STALE_SUPERSEDED_HEAD = "stale_superseded_head"
-CLASS_FOREIGN_PR_TERMINAL = "foreign_pr_terminal"
-CLASS_MOOT_MERGED_CLOSED = "moot_merged_closed"
-CLASS_CORRECTION_ACTIVE = "correction_active"
-CLASS_SESSION_OR_PROFILE_MISMATCH = "session_or_profile_mismatch"
-CLASS_AMBIGUOUS = "ambiguous"
-
-
-def classify_review_decision_lock(
-    lock: dict | None,
-    *,
-    target_pr_number: int | None = None,
-    target_head_sha: str | None = None,
-    pr_live: dict | None = None,
-    pr_lookup_error: str | None = None,
-    active_profile_identity: str | None = None,
-    session_blockers: list[str] | None = None,
-) -> dict[str, Any]:
-    """Deterministic review-decision-lock classification (#693).
-
-    Returns classification, exact next_action, owner/evidence fields, and
-    whether mark_final / cleanup / correction are appropriate.
-    """
-    summary = lock_summary(lock)
-    target_head = normalize_head_sha(target_head_sha)
-    result: dict[str, Any] = {
-        "classification": CLASS_NO_LOCK,
-        "has_lock": lock is not None,
-        "lock_summary": summary,
-        "target_pr_number": target_pr_number,
-        "target_head_sha": target_head,
-        "last_terminal_pr": None,
-        "last_terminal_action": None,
-        "locked_head_sha": None,
-        "owner_profile_identity": (summary or {}).get("profile_identity"),
-        "session_profile": (summary or {}).get("session_profile"),
-        "updated_at": (summary or {}).get("updated_at"),
-        "correction_authorized": bool((lock or {}).get("correction_authorized")),
-        "correction_pr_number": (lock or {}).get("correction_pr_number"),
-        "correction_head_sha": normalize_head_sha(
-            (lock or {}).get("correction_head_sha")
-        ),
-        "mark_final_allowed": True,
-        "cleanup_allowed": False,
-        "correction_eligible": False,
-        "next_action": "gitea_resolve_task_capability(task='review_pr') then mark_final",
-        "reasons": [],
-        "evidence": {},
-    }
-
-    if lock is None:
-        result["reasons"].append("no review decision lock present")
-        return result
-
-    session_blockers = list(session_blockers or [])
-    if session_blockers:
-        result["classification"] = CLASS_SESSION_OR_PROFILE_MISMATCH
-        result["mark_final_allowed"] = False
-        result["next_action"] = (
-            "reconnect matching prgs-reviewer session or wait for lock TTL; "
-            "do not use gitea_authorize_review_correction as unlock; "
-            "do not delete session-state files"
-        )
-        result["reasons"].extend(session_blockers)
-        return result
-
-    stored = (
-        (lock.get("profile_identity") or lock.get("session_profile_lock") or "")
-        .strip()
-    )
-    active = (active_profile_identity or "").strip()
-    if active and stored and active != stored:
-        result["classification"] = CLASS_SESSION_OR_PROFILE_MISMATCH
-        result["mark_final_allowed"] = False
-        result["next_action"] = (
-            f"switch to profile '{stored}' or wait for moot cleanup; "
-            "do not use correction authorization as a generic unlock"
-        )
-        result["reasons"].append(
-            f"lock profile '{stored}' does not match active '{active}'"
-        )
-        return result
-
-    last = last_terminal_mutation(lock)
-    if last is None:
-        ready_pr = lock.get("ready_pr_number")
-        ready_head = normalize_head_sha(lock.get("ready_expected_head_sha"))
-        if (
-            target_pr_number is not None
-            and ready_pr == target_pr_number
-            and ready_head
-            and target_head
-            and heads_equal(ready_head, target_head)
-            and lock.get("final_review_decision_ready")
-        ):
-            result["classification"] = CLASS_IN_PROGRESS_SAME_HEAD
-            result["mark_final_allowed"] = True  # idempotent re-mark
-            result["next_action"] = (
-                "gitea_submit_pr_review with final_review_decision_ready=true "
-                "for the ready PR/head"
-            )
-            result["reasons"].append(
-                "final decision already marked ready for this PR/head (idempotent)"
-            )
-            return result
-        result["classification"] = CLASS_READY_FOR_TARGET
-        result["next_action"] = "gitea_mark_final_review_decision then submit"
-        result["reasons"].append("no terminal live mutations; mark_final allowed")
-        return result
-
-    last_pr = last.get("pr_number")
-    last_action = last.get("action")
-    locked_head = mutation_head_sha(last, lock)
-    result["last_terminal_pr"] = last_pr
-    result["last_terminal_action"] = last_action
-    result["locked_head_sha"] = locked_head
-    result["evidence"] = {
-        "last_review_id": last.get("review_id"),
-        "live_mutations_count": len(lock.get("live_mutations") or []),
-    }
-
-    if correction_applies(
-        lock, pr_number=target_pr_number, expected_head_sha=target_head
-    ):
-        result["classification"] = CLASS_CORRECTION_ACTIVE
-        result["mark_final_allowed"] = True
-        result["next_action"] = (
-            "gitea_mark_final_review_decision for the correction-scoped PR/head, "
-            "then submit once"
-        )
-        result["reasons"].append(
-            f"scoped correction active for PR #{lock.get('correction_pr_number')}"
-        )
-        return result
-
-    # Live state of last terminal PR when provided.
-    live = None
-    if pr_lookup_error:
-        result["classification"] = CLASS_AMBIGUOUS
-        result["mark_final_allowed"] = False
-        result["next_action"] = (
-            "retry diagnosis after live PR state is available; "
-            "fail closed under ambiguous evidence"
-        )
-        result["reasons"].append(f"live PR lookup failed: {pr_lookup_error}")
-        return result
-    if pr_live is not None:
-        live = classify_pr_live_state(pr_live)
-        result["evidence"]["last_terminal_pr_state"] = live.get("pr_state")
-        result["evidence"]["last_terminal_pr_merged"] = live.get("pr_merged")
-        if live.get("pr_merged_or_closed"):
-            result["classification"] = CLASS_MOOT_MERGED_CLOSED
-            result["cleanup_allowed"] = True
-            result["mark_final_allowed"] = target_pr_number is not None and (
-                int(last_pr) != int(target_pr_number)
-                if last_pr is not None and target_pr_number is not None
-                else True
-            )
-            result["next_action"] = (
-                "gitea_cleanup_stale_review_decision_lock(apply=true, "
-                f"expected_terminal_pr={last_pr}) then mark_final on the target PR"
-            )
-            result["reasons"].append(
-                f"terminal on PR #{last_pr} is moot (merged/closed); cleanup allowed"
-            )
-            return result
-
-    if target_pr_number is None:
-        result["classification"] = CLASS_AMBIGUOUS
-        result["mark_final_allowed"] = False
-        result["next_action"] = "re-run diagnosis with target_pr_number"
-        result["reasons"].append("target_pr_number required for open-PR classification")
-        return result
-
-    if last_pr is not None and int(last_pr) != int(target_pr_number):
-        # Cross-PR isolation: foreign terminal is history, not a block.
-        result["classification"] = CLASS_FOREIGN_PR_TERMINAL
-        result["mark_final_allowed"] = True
-        result["correction_eligible"] = False  # must not use correction to "unlock"
-        result["next_action"] = (
-            f"gitea_mark_final_review_decision(pr_number={target_pr_number}, ...) "
-            f"— foreign terminal on PR #{last_pr} does not block (#693); "
-            "do not call gitea_authorize_review_correction for cross-PR unlock"
-        )
-        result["reasons"].append(
-            f"last terminal is {last_action} on foreign open/closed PR #{last_pr}; "
-            f"target PR #{target_pr_number} is isolated (#693)"
-        )
-        return result
-
-    # Same PR as target.
-    if (
-        locked_head
-        and target_head
-        and not heads_equal(locked_head, target_head)
-    ):
-        result["classification"] = CLASS_STALE_SUPERSEDED_HEAD
-        result["mark_final_allowed"] = True
-        result["next_action"] = (
-            f"gitea_mark_final_review_decision with expected_head_sha="
-            f"{target_head} (#620 same-PR new head)"
-        )
-        result["reasons"].append(
-            f"terminal {last_action} on head {locked_head[:12]}…; target head "
-            f"{target_head[:12]}… — fresh formal review allowed without cleanup"
-        )
-        return result
-
-    # Same PR + same head (or missing head comparison) — active terminal.
-    result["classification"] = CLASS_TERMINAL_ACTIVE_SAME_HEAD
-    result["mark_final_allowed"] = False
-    result["correction_eligible"] = True
-    result["next_action"] = (
-        "if the prior verdict was mistaken: gitea_authorize_review_correction "
-        f"with prior_review_id={last.get('review_id')}, "
-        f"prior_review_state={last_action}, target_pr_number={target_pr_number}, "
-        "operator_authorized=true, then re-mark once; "
-        "if the prior verdict is correct: stop and hand off (do not duplicate)"
-    )
-    result["reasons"].append(
-        f"terminal {last_action} already recorded for PR #{target_pr_number} "
-        f"at this head; same-head duplicate blocked (#332/#620)"
-    )
-    return result
-
-
-def build_precise_mark_final_failure(
-    classification: dict[str, Any],
-) -> dict[str, Any]:
-    """One precise recovery instruction + durable issue handoff payload (#693 AC4/8)."""
-    cls = classification.get("classification")
-    next_action = classification.get("next_action") or (
-        "stop and create a durable Gitea issue with lock evidence"
-    )
-    reasons = list(classification.get("reasons") or [])
-    reasons.append(f"exact_next_action: {next_action}")
-    handoff = {
-        "required": cls
-        in (
-            CLASS_AMBIGUOUS,
-            CLASS_SESSION_OR_PROFILE_MISMATCH,
-            CLASS_TERMINAL_ACTIVE_SAME_HEAD,
-        )
-        and not classification.get("mark_final_allowed"),
-        "title_hint": (
-            "Review-decision-lock recovery failed during formal review"
-        ),
-        "classification": cls,
-        "exact_next_action": next_action,
-        "owner_profile_identity": classification.get("owner_profile_identity"),
-        "last_terminal_pr": classification.get("last_terminal_pr"),
-        "last_terminal_action": classification.get("last_terminal_action"),
-        "locked_head_sha": classification.get("locked_head_sha"),
-        "target_pr_number": classification.get("target_pr_number"),
-        "target_head_sha": classification.get("target_head_sha"),
-        "evidence": classification.get("evidence") or {},
-        "instruction": (
-            "If recovery cannot complete with the exact_next_action above, "
-            "create or update a durable Gitea issue with this payload and stop; "
-            "do not delete session-state files; do not misuse correction as unlock."
-        ),
-    }
-    return {
-        "reasons": reasons,
-        "classification": cls,
-        "exact_next_action": next_action,
-        "durable_issue_handoff": handoff,
-    }
-
-
-def build_correction_audit_record(
-    *,
-    prior_review_id: int | None,
-    prior_review_state: str | None,
-    target_pr_number: int | None,
-    target_head_sha: str | None,
-    reason: str | None,
-    actor_username: str | None,
-    profile_name: str | None,
-    authorized: bool,
-) -> dict[str, Any]:
-    """Structured durable audit for review-correction authorization (#693)."""
-    return {
-        "event": "review_correction_authorization",
-        "issue_ref": "#693",
-        "authorized": bool(authorized),
-        "timestamp": datetime.now(timezone.utc).isoformat(),
-        "actor_username": actor_username,
-        "profile_name": profile_name,
-        "prior_review_id": prior_review_id,
-        "prior_review_state": prior_review_state,
-        "target_pr_number": target_pr_number,
-        "target_head_sha": normalize_head_sha(target_head_sha),
-        "reason": reason,
-        "scope": "same_pr_head_only",
-    }
-
-
-def format_correction_audit_comment(audit: dict[str, Any]) -> str:
-    """Markdown body for a thread-visible correction authorization audit."""
-    status = "AUTHORIZED" if audit.get("authorized") else "DENIED"
-    lines = [
-        "## Review correction authorization audit (#693)",
-        "",
-        f"Status: **{status}**",
-        "",
-        f"- actor: `{audit.get('actor_username')}`",
-        f"- profile: `{audit.get('profile_name')}`",
-        f"- timestamp: `{audit.get('timestamp')}`",
-        f"- prior_review_id: `{audit.get('prior_review_id')}`",
-        f"- prior_review_state: `{audit.get('prior_review_state')}`",
-        f"- target_pr: `#{audit.get('target_pr_number')}`",
-        f"- target_head_sha: `{audit.get('target_head_sha')}`",
-        f"- reason: {audit.get('reason')}",
-        f"- scope: `{audit.get('scope')}` (cannot unlock a different PR)",
-        "",
-        "This is **not** a generic decision-lock unlock. Cross-PR recovery "
-        "uses isolation (#693) or moot cleanup (#594), never correction.",
-    ]
-    return "\n".join(lines)
-
-
-def assess_open_pr_decision_lock_recovery(
-    lock: dict | None,
-    *,
-    target_pr_number: int,
-    target_head_sha: str | None,
-    last_terminal_pr_live: dict | None = None,
-    pr_lookup_error: str | None = None,
-    active_profile_identity: str | None = None,
-    session_blockers: list[str] | None = None,
-    controller_recovery_authorized: bool = False,
-) -> dict[str, Any]:
-    """Assess guarded recovery for decision locks affecting an open target PR (#693).
-
-    Recovery here means *workflow recovery routing*, not necessarily lock wipe.
-    Foreign-PR terminals are recoverable by isolation (mark_final allowed).
-    Moot terminals use #594 cleanup. Same-head active terminals refuse wipe.
-    """
-    classification = classify_review_decision_lock(
-        lock,
-        target_pr_number=target_pr_number,
-        target_head_sha=target_head_sha,
-        pr_live=last_terminal_pr_live,
-        pr_lookup_error=pr_lookup_error,
-        active_profile_identity=active_profile_identity,
-        session_blockers=session_blockers,
-    )
-    cls = classification["classification"]
-    recovery_allowed = False
-    recovery_mode = None
-    if cls == CLASS_FOREIGN_PR_TERMINAL:
-        recovery_allowed = True
-        recovery_mode = "cross_pr_isolation"
-    elif cls == CLASS_STALE_SUPERSEDED_HEAD:
-        recovery_allowed = True
-        recovery_mode = "same_pr_new_head"
-    elif cls == CLASS_MOOT_MERGED_CLOSED:
-        recovery_allowed = True
-        recovery_mode = "moot_cleanup"
-    elif cls == CLASS_READY_FOR_TARGET:
-        recovery_allowed = True
-        recovery_mode = "none_required"
-    elif cls == CLASS_CORRECTION_ACTIVE:
-        recovery_allowed = True
-        recovery_mode = "scoped_correction"
-    elif cls == CLASS_TERMINAL_ACTIVE_SAME_HEAD:
-        recovery_allowed = False
-        recovery_mode = "correction_only_if_mistake"
-    else:
-        recovery_allowed = False
-        recovery_mode = "fail_closed"
-
-    if recovery_mode == "moot_cleanup" and not controller_recovery_authorized:
-        # Cleanup still needs apply + capability; assess reports path.
-        pass
-
-    return {
-        **classification,
-        "recovery_allowed": recovery_allowed,
-        "recovery_mode": recovery_mode,
-        "controller_recovery_authorized": bool(controller_recovery_authorized),
-        "manual_file_delete_forbidden": True,
-        "correction_as_generic_unlock_forbidden": True,
-    }

task_capability_map.py

@@ -117,23 +117,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
         "permission": "gitea.pr.review",
         "role": "reviewer",
     },
-    # #693: read-only classification of durable decision locks (incl. open PRs).
-    "diagnose_review_decision_lock": {
-        "permission": "gitea.read",
-        "role": "reviewer",
-    },
-    "gitea_diagnose_review_decision_lock": {
-        "permission": "gitea.read",
-        "role": "reviewer",
-    },
-    "authorize_review_correction": {
-        "permission": "gitea.pr.review",
-        "role": "reviewer",
-    },
-    "gitea_authorize_review_correction": {
-        "permission": "gitea.pr.review",
-        "role": "reviewer",
-    },
     "delete_branch": {
         "permission": "gitea.branch.delete",
         "role": "author",

tests/test_head_scoped_review_decision_lock.py

@@ -24,10 +24,6 @@ HEAD_C = "c" * 40
 
 
 def _lock(mutations=None, correction=False, ready_pr=None, ready_head=None, ready_action=None):
-    mutations = list(mutations or [])
-    corr_pr = None
-    if correction and mutations:
-        corr_pr = mutations[-1].get("pr_number")
     return {
         "task": "review_pr",
         "remote": "prgs",
@@ -44,11 +40,9 @@ def _lock(mutations=None, correction=False, ready_pr=None, ready_head=None, read
         "ready_remote": "prgs" if ready_pr else None,
         "ready_org": "Scaled-Tech-Consulting" if ready_pr else None,
         "ready_repo": "Gitea-Tools" if ready_pr else None,
-        "live_mutations": mutations,
+        "live_mutations": list(mutations or []),
         "correction_authorized": correction,
-        "correction_reason": "test" if correction else None,
-        "correction_pr_number": corr_pr,
-        "correction_head_sha": None,
+        "correction_reason": None,
     }
 
 
@@ -180,13 +174,12 @@ class TestHardStopHeadScope(unittest.TestCase):
         self.assertTrue(reasons)
         self.assertIn("#332", reasons[0])
 
-    def test_rc_head_a_allows_other_pr_via_cross_pr_isolation(self):
-        """#693: foreign-PR terminal must not hard-stop mark_ready on another PR."""
+    def test_rc_head_a_blocks_other_pr(self):
         _seed([RC_619_HEAD_A], ready_pr=619, ready_head=HEAD_A)
         reasons = mcp_server.terminal_review_hard_stop_reasons(
             700, "mark_ready", expected_head_sha=HEAD_B
         )
-        self.assertEqual(reasons, [])
+        self.assertTrue(reasons)
 
     def test_legacy_619_ledger_allows_new_head(self):
         """PR #619-style durable lock without mutation head_sha."""

tests/test_issue_693_review_decision_lock_recovery.py

@@ -1,427 +0,0 @@
-"""Review-decision-lock recovery / cross-PR isolation (#693).
-
-Reproduces the PR #688 → PR #692 formal-review sequence:
-
-  * durable lock holds REQUEST_CHANGES on open PR #688 @ head A (review_id 425)
-  * reviewer leases PR #692 @ head B (6d86db…)
-  * mark_final for #692 must succeed without correction unlock
-  * cleanup of open #688 terminal remains forbidden (#594)
-  * authorize_review_correction for #688 cannot unlock #692
-  * eventual #692 APPROVE is unique and head-bound (review_id 426)
-  * mark_final is idempotent for same PR/action/head
-  * diagnosis returns one exact next_action + durable handoff payload
-"""
-
-from __future__ import annotations
-
-import os
-import unittest
-from unittest.mock import patch
-
-import mcp_server
-import review_workflow_load
-import stale_review_decision_lock as srdl
-
-# PR #688 / #692 incident fixtures (sanitized reconstruction from issue #693)
-HEAD_688 = "c7a444eb4b41cf916fdbd20a4999ffd78af496d0"
-HEAD_692 = "6d86db793bbdfaed16bd54d93171f1dd66f234ca"
-PR_A = 688
-PR_B = 692
-REVIEW_ID_A = 425
-REVIEW_ID_B = 426
-
-RC_688 = {
-    "pr_number": PR_A,
-    "action": "request_changes",
-    "review_id": REVIEW_ID_A,
-    "review_state": "request_changes",
-    "head_sha": HEAD_688,
-}
-APPROVE_692 = {
-    "pr_number": PR_B,
-    "action": "approve",
-    "review_id": REVIEW_ID_B,
-    "review_state": "approve",
-    "head_sha": HEAD_692,
-}
-
-
-def _lock(mutations=None, **kwargs):
-    from datetime import datetime, timezone
-
-    now = datetime.now(timezone.utc).isoformat()
-    base = {
-        "task": "review_pr",
-        "remote": "prgs",
-        "org": "Scaled-Tech-Consulting",
-        "repo": "Gitea-Tools",
-        "session_pid": os.getpid(),
-        "session_profile": "prgs-reviewer",
-        "session_profile_lock": "prgs-reviewer",
-        "profile_identity": "prgs-reviewer",
-        "final_review_decision_ready": False,
-        "ready_pr_number": None,
-        "ready_action": None,
-        "ready_expected_head_sha": None,
-        "ready_remote": None,
-        "ready_org": None,
-        "ready_repo": None,
-        "live_mutations": list(mutations or []),
-        "correction_authorized": False,
-        "correction_reason": None,
-        "correction_pr_number": None,
-        "correction_head_sha": None,
-        "updated_at": now,
-        "recorded_at": now,
-        "writer_pid": os.getpid(),
-    }
-    base.update(kwargs)
-    # Ensure TTL fields stay fresh unless the caller is testing expiry.
-    if "recorded_at" not in kwargs:
-        base["recorded_at"] = now
-    if "updated_at" not in kwargs:
-        base["updated_at"] = now
-    return base
-
-
-REVIEWER_ENV = {
-    "GITEA_PROFILE_NAME": "prgs-reviewer",
-    "GITEA_ALLOWED_OPERATIONS": (
-        "gitea.read,gitea.pr.review,gitea.pr.approve,"
-        "gitea.pr.request_changes,gitea.pr.comment"
-    ),
-    "GITEA_SESSION_PROFILE_LOCK": "prgs-reviewer",
-}
-
-REVIEWER_PROFILE = {
-    "profile_name": "prgs-reviewer",
-    "allowed_operations": [
-        "gitea.read",
-        "gitea.pr.review",
-        "gitea.pr.approve",
-        "gitea.pr.request_changes",
-        "gitea.pr.comment",
-    ],
-    "forbidden_operations": ["gitea.pr.merge"],
-}
-
-
-def _seed(mutations=None, **kwargs):
-    review_workflow_load.record_review_workflow_load(mcp_server.PROJECT_ROOT)
-    mcp_server._save_review_decision_lock(_lock(mutations, **kwargs))
-    mcp_server.gitea_load_review_workflow()
-
-
-def _no_lease():
-    return {"block": False, "reasons": [], "mutation_allowed": True}
-
-
-def _open_pr(number, head):
-    return {
-        "number": number,
-        "state": "open",
-        "merged": False,
-        "merged_at": None,
-        "head": {"sha": head},
-    }
-
-
-class TestCrossPrIsolationPure(unittest.TestCase):
-    def test_foreign_terminal_does_not_block_mark_boundary(self):
-        lock = _lock([RC_688])
-        self.assertFalse(
-            srdl.prior_live_mutations_block_boundary(
-                lock, pr_number=PR_B, expected_head_sha=HEAD_692
-            )
-        )
-        self.assertTrue(
-            srdl.prior_live_mutations_block_boundary(
-                lock, pr_number=PR_A, expected_head_sha=HEAD_688
-            )
-        )
-
-    def test_terminal_boundary_allows_fresh_decision_on_other_pr(self):
-        lock = _lock([RC_688])
-        self.assertTrue(
-            srdl.terminal_boundary_allows_fresh_decision(
-                lock,
-                pr_number=PR_B,
-                expected_head_sha=HEAD_692,
-                operation="mark_ready",
-            )
-        )
-        self.assertFalse(
-            srdl.terminal_boundary_allows_fresh_decision(
-                lock,
-                pr_number=PR_A,
-                expected_head_sha=HEAD_688,
-                operation="mark_ready",
-            )
-        )
-
-    def test_unscoped_correction_does_not_apply(self):
-        lock = _lock([RC_688], correction_authorized=True, correction_reason="x")
-        # Missing correction_pr_number → fail closed (#693)
-        self.assertFalse(
-            srdl.correction_applies(lock, pr_number=PR_A, expected_head_sha=HEAD_688)
-        )
-
-    def test_scoped_correction_only_for_named_pr(self):
-        lock = _lock(
-            [RC_688],
-            correction_authorized=True,
-            correction_reason="mistake",
-            correction_pr_number=PR_A,
-            correction_head_sha=HEAD_688,
-        )
-        self.assertTrue(
-            srdl.correction_applies(lock, pr_number=PR_A, expected_head_sha=HEAD_688)
-        )
-        self.assertFalse(
-            srdl.correction_applies(lock, pr_number=PR_B, expected_head_sha=HEAD_692)
-        )
-
-
-class TestClassification(unittest.TestCase):
-    def test_foreign_pr_terminal_classification(self):
-        lock = _lock([RC_688])
-        c = srdl.classify_review_decision_lock(
-            lock,
-            target_pr_number=PR_B,
-            target_head_sha=HEAD_692,
-            pr_live=_open_pr(PR_A, HEAD_688),
-            active_profile_identity="prgs-reviewer",
-        )
-        self.assertEqual(c["classification"], srdl.CLASS_FOREIGN_PR_TERMINAL)
-        self.assertTrue(c["mark_final_allowed"])
-        self.assertFalse(c["correction_eligible"])
-        self.assertIn("do not call gitea_authorize_review_correction", c["next_action"])
-
-    def test_same_head_terminal_classification(self):
-        lock = _lock([RC_688])
-        c = srdl.classify_review_decision_lock(
-            lock,
-            target_pr_number=PR_A,
-            target_head_sha=HEAD_688,
-            pr_live=_open_pr(PR_A, HEAD_688),
-        )
-        self.assertEqual(c["classification"], srdl.CLASS_TERMINAL_ACTIVE_SAME_HEAD)
-        self.assertFalse(c["mark_final_allowed"])
-        self.assertTrue(c["correction_eligible"])
-
-    def test_precise_failure_includes_durable_handoff(self):
-        lock = _lock([RC_688])
-        c = srdl.classify_review_decision_lock(
-            lock, target_pr_number=PR_A, target_head_sha=HEAD_688
-        )
-        fail = srdl.build_precise_mark_final_failure(c)
-        self.assertIn("exact_next_action", fail)
-        self.assertIn("durable_issue_handoff", fail)
-        self.assertTrue(fail["durable_issue_handoff"]["required"])
-
-
-class TestPr692Sequence(unittest.TestCase):
-    def setUp(self):
-        self._env = patch.dict(os.environ, REVIEWER_ENV, clear=False)
-        self._env.start()
-        self._prof = patch.object(
-            mcp_server, "get_profile", return_value=REVIEWER_PROFILE
-        )
-        self._prof.start()
-
-    def tearDown(self):
-        self._prof.stop()
-        self._env.stop()
-        mcp_server._save_review_decision_lock(None)
-        review_workflow_load.clear_review_workflow_load()
-
-    def test_mark_final_692_succeeds_with_open_688_terminal(self):
-        _seed([RC_688], writer_pid=25883, session_pid=60615)
-        with patch("mcp_server._list_pr_lease_comments", return_value=[]), patch(
-            "mcp_server._pr_work_lease_reviewer_block", return_value=_no_lease()
-        ), patch.object(
-            mcp_server,
-            "gitea_check_pr_eligibility",
-            return_value={"head_sha": HEAD_692, "eligible": True},
-        ):
-            result = mcp_server.gitea_mark_final_review_decision(
-                pr_number=PR_B,
-                action="approve",
-                expected_head_sha=HEAD_692,
-                remote="prgs",
-                org="Scaled-Tech-Consulting",
-                repo="Gitea-Tools",
-            )
-        self.assertTrue(result["marked_ready"], result.get("reasons"))
-        lock = mcp_server._load_review_decision_lock()
-        self.assertEqual(lock["ready_pr_number"], PR_B)
-        self.assertEqual(
-            srdl.normalize_head_sha(lock["ready_expected_head_sha"]), HEAD_692
-        )
-        # Foreign terminal history preserved (non-destructive isolation).
-        self.assertEqual(lock["live_mutations"][0]["pr_number"], PR_A)
-
-    def test_mark_final_idempotent_same_binding(self):
-        _seed(
-            [RC_688],
-            final_review_decision_ready=True,
-            ready_pr_number=PR_B,
-            ready_action="approve",
-            ready_expected_head_sha=HEAD_692,
-            ready_remote="prgs",
-            ready_org="Scaled-Tech-Consulting",
-            ready_repo="Gitea-Tools",
-        )
-        with patch("mcp_server._list_pr_lease_comments", return_value=[]), patch(
-            "mcp_server._pr_work_lease_reviewer_block", return_value=_no_lease()
-        ), patch.object(
-            mcp_server,
-            "gitea_check_pr_eligibility",
-            return_value={"head_sha": HEAD_692, "eligible": True},
-        ):
-            result = mcp_server.gitea_mark_final_review_decision(
-                pr_number=PR_B,
-                action="approve",
-                expected_head_sha=HEAD_692,
-                remote="prgs",
-                org="Scaled-Tech-Consulting",
-                repo="Gitea-Tools",
-            )
-        self.assertTrue(result["marked_ready"])
-        self.assertTrue(result.get("idempotent"))
-
-    def test_cleanup_still_forbidden_while_688_open(self):
-        _seed([RC_688])
-        assessment = srdl.assess_stale_review_decision_lock(
-            mcp_server._load_review_decision_lock(),
-            pr_live=_open_pr(PR_A, HEAD_688),
-            active_profile_identity="prgs-reviewer",
-        )
-        self.assertFalse(assessment["cleanup_allowed"])
-        self.assertFalse(assessment["is_moot"])
-
-    def test_correction_cannot_unlock_different_pr(self):
-        _seed([RC_688])
-        r = mcp_server.gitea_authorize_review_correction(
-            prior_review_id=REVIEW_ID_A,
-            prior_review_state="request_changes",
-            reason="try unlock 692",
-            operator_authorized=True,
-            target_pr_number=PR_B,
-            remote="prgs",
-            org="Scaled-Tech-Consulting",
-            repo="Gitea-Tools",
-            post_audit_comment=False,
-        )
-        self.assertFalse(r["authorized"])
-        self.assertTrue(any("different PR" in x for x in r["reasons"]))
-
-    def test_scoped_correction_for_same_pr_posts_audit(self):
-        _seed([RC_688])
-        with patch(
-            "mcp_server._authenticated_username", return_value="sysadmin"
-        ), patch(
-            "mcp_server.get_auth_header", return_value="Basic dGVzdDp0ZXN0"
-        ), patch(
-            "mcp_server._auth", return_value="Basic dGVzdDp0ZXN0"
-        ), patch("mcp_server.api_request", return_value={"id": 99901}):
-            r = mcp_server.gitea_authorize_review_correction(
-                prior_review_id=REVIEW_ID_A,
-                prior_review_state="request_changes",
-                reason="mistaken RC wording",
-                operator_authorized=True,
-                target_pr_number=PR_A,
-                expected_head_sha=HEAD_688,
-                remote="prgs",
-                org="Scaled-Tech-Consulting",
-                repo="Gitea-Tools",
-                post_audit_comment=True,
-            )
-        self.assertTrue(r["authorized"], r.get("reasons"))
-        self.assertEqual(r.get("correction_pr_number"), PR_A)
-        self.assertEqual(
-            r.get("audit_comment_id"),
-            99901,
-            r.get("audit_comment_skipped") or r.get("audit_comment_error") or r,
-        )
-
-    def test_diagnose_foreign_terminal_next_action(self):
-        _seed([RC_688])
-        with patch(
-            "mcp_server._authenticated_username", return_value="sysadmin"
-        ), patch(
-            "mcp_server.get_auth_header", return_value="Basic dGVzdDp0ZXN0"
-        ), patch(
-            "mcp_server._auth", return_value="Basic dGVzdDp0ZXN0"
-        ), patch("mcp_server.api_request", return_value=_open_pr(PR_A, HEAD_688)):
-            d = mcp_server.gitea_diagnose_review_decision_lock(
-                target_pr_number=PR_B,
-                expected_head_sha=HEAD_692,
-                remote="prgs",
-                org="Scaled-Tech-Consulting",
-                repo="Gitea-Tools",
-            )
-        self.assertTrue(d["success"], d.get("reasons"))
-        self.assertEqual(d["classification"], srdl.CLASS_FOREIGN_PR_TERMINAL)
-        self.assertTrue(d["mark_final_allowed"])
-        self.assertIn("mark_final", d["exact_next_action"])
-        self.assertTrue(d["correction_as_generic_unlock_forbidden"])
-
-    def test_approval_ledger_unique_and_bound_after_sequence(self):
-        """After mark_final + record mutation, ledger binds unique approve to 692 head."""
-        _seed([RC_688])
-        with patch("mcp_server._list_pr_lease_comments", return_value=[]), patch(
-            "mcp_server._pr_work_lease_reviewer_block", return_value=_no_lease()
-        ), patch.object(
-            mcp_server,
-            "gitea_check_pr_eligibility",
-            return_value={"head_sha": HEAD_692, "eligible": True},
-        ):
-            marked = mcp_server.gitea_mark_final_review_decision(
-                pr_number=PR_B,
-                action="approve",
-                expected_head_sha=HEAD_692,
-                remote="prgs",
-                org="Scaled-Tech-Consulting",
-                repo="Gitea-Tools",
-            )
-        self.assertTrue(marked["marked_ready"])
-        mcp_server.record_live_review_mutation(PR_B, "approve", REVIEW_ID_B)
-        lock = mcp_server._load_review_decision_lock()
-        terminals = [
-            m
-            for m in lock["live_mutations"]
-            if m.get("action") in srdl.TERMINAL_REVIEW_ACTIONS
-            and m.get("pr_number") == PR_B
-        ]
-        self.assertEqual(len(terminals), 1)
-        self.assertEqual(terminals[0]["review_id"], REVIEW_ID_B)
-        self.assertEqual(
-            srdl.normalize_head_sha(terminals[0].get("head_sha")), HEAD_692
-        )
-        # Same-head duplicate still blocked.
-        self.assertTrue(
-            srdl.prior_live_mutations_block_boundary(
-                lock, pr_number=PR_B, expected_head_sha=HEAD_692
-            )
-        )
-
-
-class TestSessionRestartWriterPid(unittest.TestCase):
-    def tearDown(self):
-        mcp_server._save_review_decision_lock(None)
-        review_workflow_load.clear_review_workflow_load()
-
-    def test_writer_pid_change_does_not_inherit_foreign_block(self):
-        # session_pid 60615 origin, writer later 25883 — still foreign isolation.
-        _seed([RC_688], session_pid=60615, writer_pid=25883)
-        self.assertEqual(
-            mcp_server.terminal_review_hard_stop_reasons(
-                PR_B, "mark_ready", expected_head_sha=HEAD_692
-            ),
-            [],
-        )
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/test_issue_698_report_validator_schema_alignment.py

@@ -0,0 +1,461 @@
+"""Regression tests for #698: final-report validator vs canonical schema.
+
+Covers the original #698 lead plus the independent reproduction recorded
+during the PR #703 formal review (issue #698 comment 11246):
+
+1. non-dict ``action_log`` entries must fail structured, never crash;
+2. the validator must not demand legacy fields the canonical schema forbids
+   (``Pinned reviewed head``, ``Scratch worktree used``, ``Worktree path``,
+   ``Worktree dirty``, ``Mutations``, ``Next``);
+3. a legitimately blocked report (``Candidate head SHA: none``, no formal
+   verdict) must not owe approval/merge live-head proofs;
+4. canonical reviewer lease release must not be misclassified as post-merge
+   cleanup;
+5. structured workflow-load and validation proof must be recognized;
+6. review mutations are inferred only from authoritative evidence.
+"""
+
+from __future__ import annotations
+
+import sys
+import unittest
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+import final_report_validator as frv  # noqa: E402
+import post_merge_cleanup_proof as pmcp  # noqa: E402
+import pr_work_lease as pwl  # noqa: E402
+import review_proofs as rp  # noqa: E402
+from review_final_report_schema import (  # noqa: E402
+    assess_review_final_report_schema,
+)
+
+REVIEWED_HEAD = "a" * 40
+LIVE_HEAD = "a" * 40
+
+
+def _pr703_style_report(
+    *,
+    decision: str = "request_changes",
+    cleanup_mutations: str = (
+        "released reviewer PR lease via gitea_release_reviewer_pr_lease "
+        "(terminal lease marker phase=released posted)"
+    ),
+) -> str:
+    """Canonical-schema report modeled on the PR #703 formal review handoff."""
+    return f"""
+Formal review completed with a REQUEST_CHANGES verdict submitted and read
+back via the native review API.
+
+## Controller Handoff
+
+- Task: review-merge-pr
+- Repo: Scaled-Tech-Consulting/Gitea-Tools
+- Role: reviewer
+- Identity: sysadmin / prgs-reviewer
+- Active profile: prgs-reviewer
+- Runtime context: neutral workspace binding
+- Selected PR: 703
+- Linked issue: #702 open
+- Eligibility class: reviewable
+- Queue ordering policy: oldest eligible first
+- Inventory pagination proof: has_more=false, total_count=8
+- Earlier PRs skipped: none
+- Candidate head SHA: {REVIEWED_HEAD}
+- Reviewed head SHA: {REVIEWED_HEAD}
+- Target branch: master
+- Target branch SHA: {"2" * 40}
+- Already-landed gate: not landed
+- Author-safety result: pass (author differs from reviewer)
+- Prior request-changes state: none
+- Review worktree used: true
+- Review worktree path: branches/review-pr-703-independent
+- Review worktree inside branches: true
+- Review worktree HEAD state: detached at pinned head
+- Review worktree dirty before validation: clean
+- Review worktree dirty after validation: clean
+- Baseline worktree used: false
+- Baseline worktree path: none
+- Files reviewed: 4
+- Validation: focused 50 passed; related 94 passed; full 2665 passed, 6 skipped
+- Official validation integrity status: intact
+- Terminal review mutation: one REQUEST_CHANGES review submitted and read back
+- Review decision: {decision}
+- Merge preflight: not run
+- Merge result: none
+- Linked issue status: open (live fetch proof: gitea_view_issue)
+- Main checkout branch: master
+- Main checkout dirty state: clean
+- Main checkout updated: false
+- File edits by reviewer: none
+- Worktree/index mutations: none
+- Git ref mutations: git fetch prgs (recorded)
+- MCP/Gitea mutations: review submission and lease comments only
+- Review mutations: one formal REQUEST_CHANGES verdict
+- Merge mutations: none
+- Cleanup mutations: {cleanup_mutations}
+- External-state mutations: none
+- Read-only diagnostics: gitea_view_pr, gitea_get_pr_review_feedback
+- Blockers: findings F1-F6 recorded on the PR thread
+- Current status: review complete; author remediation required
+- Safe next action: author addresses findings and pushes a new head
+- Safety statement: no merge attempted; no self-review; no root-checkout edits
+- Workflow-load helper result: workflow_hash=da045d1e1f1f boundary_status=clean
+- Live head SHA before approval: {LIVE_HEAD}
+- Pushes occurred during validation: no
+"""
+
+
+def _blocked_preflight_report() -> str:
+    """Blocked-run report modeled on the #702 comment 11164 reproduction."""
+    return """
+Fresh review preflight stopped before any worktree or validation work.
+
+## Controller Handoff
+
+- Task: review-merge-pr
+- Repo: Scaled-Tech-Consulting/Gitea-Tools
+- Role: reviewer
+- Identity: sysadmin / prgs-reviewer
+- Active profile: prgs-reviewer
+- Runtime context: stale workspace binding detected
+- Selected PR: 701
+- Linked issue: #699 open
+- Eligibility class: blocked-before-validation
+- Queue ordering policy: oldest eligible first
+- Inventory pagination proof: has_more=false, total_count=8
+- Earlier PRs skipped: none
+- Candidate head SHA: none
+- Reviewed head SHA: none
+- Target branch: master
+- Target branch SHA: none
+- Already-landed gate: not run
+- Author-safety result: not run
+- Prior request-changes state: none
+- Review worktree used: false
+- Review worktree path: none
+- Review worktree inside branches: not applicable
+- Review worktree HEAD state: not applicable
+- Review worktree dirty before validation: not applicable
+- Review worktree dirty after validation: not applicable
+- Baseline worktree used: false
+- Baseline worktree path: none
+- Files reviewed: 0
+- Validation: not run
+- Official validation integrity status: not applicable
+- Terminal review mutation: none
+- Review decision: none
+- Merge preflight: not run
+- Merge result: none
+- Linked issue status: open (live fetch proof: gitea_view_issue)
+- Main checkout branch: master
+- Main checkout dirty state: clean
+- Main checkout updated: false
+- File edits by reviewer: none
+- Worktree/index mutations: none
+- Git ref mutations: none
+- MCP/Gitea mutations: none
+- Review mutations: none
+- Merge mutations: none
+- Cleanup mutations: none
+- External-state mutations: none
+- Read-only diagnostics: gitea_view_pr, gitea_get_runtime_context
+- Blockers: runtime bound to a foreign task worktree; mutation prohibited
+- Current status: stopped before validation began
+- Next actor: operator
+- Next action: repair the runtime workspace binding, then rerun the full
+  review workflow in a fresh reviewer session
+- Next prompt: Act as REVIEWER for PR 701 after the operator repairs the
+  runtime binding; acquire the lease before any validation.
+- Safe next action: operator repairs runtime binding, then a fresh reviewer
+  reruns the full workflow
+- Safety statement: no lease acquired; no verdict recorded; no source edits
+- Workflow-load helper result: workflow_hash=da045d1e1f1f boundary_status=clean
+"""
+
+
+class TestActionLogRobustness(unittest.TestCase):
+    """#698 original lead: non-dict action_log must not crash validation."""
+
+    MALFORMED = [
+        "git fetch prgs",
+        42,
+        None,
+        {"action": "edit", "path": "x.py", "performed": True, "tracked": True},
+    ]
+
+    def test_assess_final_report_validator_survives_malformed_entries(self):
+        result = frv.assess_final_report_validator(
+            _pr703_style_report(),
+            "review_pr",
+            action_log=self.MALFORMED,
+        )
+        self.assertIsInstance(result, dict)
+        rule_ids = {f["rule_id"] for f in result["findings"]}
+        self.assertIn("shared.action_log_malformed", rule_ids)
+
+    def test_malformed_entry_errors_are_sanitized(self):
+        _entries, findings = frv.sanitize_action_log(["secret-token-abc123"])
+        self.assertEqual(len(findings), 1)
+        reason = findings[0]["reason"]
+        self.assertNotIn("secret-token-abc123", reason)
+        self.assertIn("str", reason)
+        self.assertIn("entry 0", reason)
+
+    def test_non_list_action_log_is_reported_not_raised(self):
+        entries, findings = frv.sanitize_action_log("not-a-list")
+        self.assertEqual(entries, [])
+        self.assertEqual(len(findings), 1)
+        self.assertIn("not a list", findings[0]["reason"])
+
+    def test_performed_file_mutations_skips_non_dict_entries(self):
+        performed = rp._performed_file_mutations(
+            ["oops", {"action": "edited", "path": "a.py"}]
+        )
+        self.assertEqual(len(performed), 1)
+        self.assertEqual(performed[0]["path"], "a.py")
+
+    def test_schema_entrypoint_survives_string_only_log(self):
+        result = assess_review_final_report_schema(
+            _pr703_style_report(),
+            action_log=["just a string", "another string"],
+        )
+        self.assertIsInstance(result, dict)
+
+
+class TestLegacyFieldRequirementsRemoved(unittest.TestCase):
+    """#698: prohibited legacy fields must not be REQUIRED of reports."""
+
+    PROHIBITED = (
+        "Pinned reviewed head",
+        "Scratch worktree used",
+        "Worktree path",
+        "Worktree dirty",
+        "Workspace mutations",
+        "Mutations",
+        "Next",
+        "Issue/PR",
+        "Branch/SHA",
+        "Files changed",
+    )
+
+    def test_review_role_field_table_has_no_prohibited_requirements(self):
+        names = [name for name, _ in rp.HANDOFF_ROLE_FIELDS["review"]]
+        for prohibited in ("Pinned reviewed head", "Scratch worktree used",
+                           "Worktree path", "Worktree dirty"):
+            self.assertNotIn(prohibited, names)
+
+    def test_merger_role_field_table_has_no_pinned_reviewed_head(self):
+        names = [name for name, _ in rp.HANDOFF_ROLE_FIELDS["merger"]]
+        self.assertNotIn("Pinned reviewed head", names)
+
+    def test_canonical_report_missing_fields_never_include_prohibited(self):
+        result = rp.assess_controller_handoff(
+            _pr703_style_report(), role="review"
+        )
+        for prohibited in self.PROHIBITED:
+            self.assertNotIn(prohibited, result.get("missing_fields") or [])
+
+    def test_canonical_pr703_report_satisfies_required_fields(self):
+        result = rp.assess_controller_handoff(
+            _pr703_style_report(), role="review"
+        )
+        self.assertEqual(result.get("missing_fields") or [], [])
+        self.assertEqual(result.get("verdict"), "complete")
+
+
+class TestBlockedReportAccepted(unittest.TestCase):
+    """#698: blocked run with no reviewed head / verdict is legitimate."""
+
+    def test_stale_head_proof_waived_before_validation(self):
+        result = pwl.assess_reviewer_stale_head_final_report(
+            _blocked_preflight_report()
+        )
+        self.assertTrue(result["proven"])
+        self.assertEqual(result.get("phase"), "blocked_before_validation")
+
+    def test_blocked_report_passes_schema_validation(self):
+        result = assess_review_final_report_schema(_blocked_preflight_report())
+        blocking = [
+            f for f in result["findings"] if f["severity"] == "block"
+        ]
+        self.assertEqual(blocking, [], blocking)
+
+    def test_verdict_phase_still_demands_approval_head_proof(self):
+        report = _blocked_preflight_report().replace(
+            "- Review decision: none",
+            "- Review decision: approve",
+        ).replace(
+            "- Candidate head SHA: none",
+            f"- Candidate head SHA: {REVIEWED_HEAD}",
+        )
+        result = pwl.assess_reviewer_stale_head_final_report(report)
+        self.assertFalse(result["proven"])
+        joined = " ".join(result["reasons"])
+        self.assertIn("before approval", joined)
+
+    def test_merge_phase_still_demands_merge_head_proof(self):
+        report = _pr703_style_report().replace(
+            "- Merge result: none",
+            "- Merge result: merged",
+        )
+        result = pwl.assess_reviewer_stale_head_final_report(report)
+        self.assertFalse(result["proven"])
+        self.assertIn(
+            "final live head SHA before merge not stated",
+            result["reasons"],
+        )
+
+    def test_validation_phase_demands_push_disclosure(self):
+        report = _pr703_style_report().replace(
+            "- Pushes occurred during validation: no\n", ""
+        )
+        result = pwl.assess_reviewer_stale_head_final_report(report)
+        self.assertFalse(result["proven"])
+        self.assertIn(
+            "whether push occurred during validation not stated",
+            result["reasons"],
+        )
+
+
+class TestLeaseReleaseVsPostMergeCleanup(unittest.TestCase):
+    """#698 (PR #703 review reproduction): lease release is not cleanup."""
+
+    def test_lease_release_cleanup_mutations_do_not_demand_checklist(self):
+        result = pmcp.assess_post_merge_cleanup_proof(_pr703_style_report())
+        self.assertFalse(result["block"], result["reasons"])
+
+    def test_release_tool_name_alone_is_recognized(self):
+        report = _pr703_style_report(
+            cleanup_mutations="gitea_release_reviewer_pr_lease comment 11244"
+        )
+        result = pmcp.assess_post_merge_cleanup_proof(report)
+        self.assertFalse(result["block"], result["reasons"])
+
+    def test_substantive_non_lease_cleanup_still_demands_checklist(self):
+        report = _pr703_style_report(
+            cleanup_mutations="deleted stale scratch directory manually"
+        )
+        result = pmcp.assess_post_merge_cleanup_proof(report)
+        self.assertTrue(result["block"])
+
+    def test_remote_branch_delete_claims_still_demand_full_proof(self):
+        report = _pr703_style_report(
+            cleanup_mutations="gitea_delete_branch removed the remote branch"
+        )
+        result = pmcp.assess_post_merge_cleanup_proof(report)
+        self.assertTrue(result["block"])
+        self.assertTrue(
+            any("remote branch deletion missing" in r for r in result["reasons"])
+        )
+
+    def test_full_schema_run_accepts_lease_release_report(self):
+        result = assess_review_final_report_schema(_pr703_style_report())
+        lease_cleanup_blocks = [
+            f for f in result["findings"]
+            if f["rule_id"] == "reviewer.post_merge_cleanup_proof"
+        ]
+        self.assertEqual(lease_cleanup_blocks, [], lease_cleanup_blocks)
+
+
+class TestStructuredProofRecognition(unittest.TestCase):
+    """#698: structured workflow-load and validation proof must be accepted."""
+
+    def test_key_value_workflow_proof_recognized(self):
+        findings = frv._rule_reviewer_workflow_load_boundary(
+            _pr703_style_report()
+        )
+        self.assertEqual(findings, [], findings)
+
+    def test_colon_form_workflow_proof_still_recognized(self):
+        report = _pr703_style_report().replace(
+            "- Workflow-load helper result: workflow_hash=da045d1e1f1f "
+            "boundary_status=clean",
+            "- Workflow-load helper result: workflow_hash: da045d1e1f1f, "
+            "boundary_status: clean",
+        )
+        findings = frv._rule_reviewer_workflow_load_boundary(report)
+        self.assertEqual(findings, [], findings)
+
+    def test_incomplete_structured_proof_still_blocks(self):
+        report = _pr703_style_report().replace(
+            "workflow_hash=da045d1e1f1f boundary_status=clean",
+            "workflow_hash=da045d1e1f1f",
+        )
+        findings = frv._rule_reviewer_workflow_load_boundary(report)
+        self.assertTrue(findings)
+        self.assertIn("boundary_status", findings[0]["reason"])
+
+    def test_validation_counts_accepted_as_pass_proof(self):
+        # "Validation: focused 50 passed; ..." must satisfy the reviewed-head
+        # validation-proof rule (PR #703 reproduction).
+        result = assess_review_final_report_schema(_pr703_style_report())
+        head_blocks = [
+            f for f in result["findings"]
+            if f["rule_id"] == "reviewer.reviewed_head_without_validation"
+        ]
+        self.assertEqual(head_blocks, [], head_blocks)
+
+
+class TestAuthoritativeMutationInference(unittest.TestCase):
+    """#698: review mutations inferred only from authoritative evidence."""
+
+    def test_read_only_entries_do_not_imply_mutations(self):
+        report = "## Controller Handoff\n- Mutations: none\n"
+        findings = frv._rule_reviewer_vague_mutations_none(
+            report,
+            action_log=[
+                {"action": "gitea_view_pr"},
+                {"action": "gitea_get_pr_review_feedback", "performed": False},
+            ],
+        )
+        self.assertEqual(findings, [], findings)
+
+    def test_performed_mutation_still_blocks_vague_none(self):
+        report = "## Controller Handoff\n- Mutations: none\n"
+        findings = frv._rule_reviewer_vague_mutations_none(
+            report,
+            action_log=[{"action": "edit", "path": "a.py", "performed": True}],
+        )
+        self.assertTrue(findings)
+
+    def test_gated_rejection_is_not_a_mutation(self):
+        report = "## Controller Handoff\n- Mutations: none\n"
+        findings = frv._rule_reviewer_vague_mutations_none(
+            report,
+            action_log=[
+                {"action": "edit", "path": "a.py", "performed": True,
+                 "gated_rejected": True},
+            ],
+        )
+        self.assertEqual(findings, [], findings)
+
+
+class TestValidatorRuleErrorContainment(unittest.TestCase):
+    """#698: a defective rule fails closed with a sanitized error."""
+
+    def test_rule_exception_becomes_sanitized_block_finding(self):
+        def _boom(report_text):
+            raise ValueError("raw secret detail that must not leak")
+
+        original = frv._RULES_BY_TASK["review_pr"]
+        frv._RULES_BY_TASK["review_pr"] = [_boom]
+        try:
+            result = frv.assess_final_report_validator(
+                "report body", "review_pr"
+            )
+        finally:
+            frv._RULES_BY_TASK["review_pr"] = original
+        self.assertTrue(result["blocked"])
+        finding = next(
+            f for f in result["findings"]
+            if f["rule_id"] == "shared.validator_rule_error"
+        )
+        self.assertNotIn("raw secret detail", finding["reason"])
+        self.assertIn("ValueError", finding["reason"])
+        self.assertIn("_boom", finding["reason"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_mcp_server.py

@@ -2540,18 +2540,15 @@ class TestSubmitPrReview(unittest.TestCase):
         lock = _load_review_decision_lock() or {}
         lock["live_mutations"] = [{"pr_number": 8, "action": "approve", "review_id": 42, "review_state": "approve"}]
         _save_review_decision_lock(lock)
-        with patch("mcp_server.api_request", return_value={"id": 9001}):
-            r = gitea_authorize_review_correction(
-                prior_review_id=42,
-                prior_review_state="approve",
-                reason="typo",
-                operator_authorized=True,
-                target_pr_number=8,
-            )
+        r = gitea_authorize_review_correction(
+            prior_review_id=42,
+            prior_review_state="approve",
+            reason="typo",
+            operator_authorized=True,
+        )
         self.assertTrue(r["authorized"])
         lock = _load_review_decision_lock()
         self.assertTrue(lock["correction_authorized"])
-        self.assertEqual(lock["correction_pr_number"], 8)
 
     def test_authorize_review_correction_mismatch(self):
         from mcp_server import _load_review_decision_lock, _save_review_decision_lock
@@ -2565,7 +2562,6 @@ class TestSubmitPrReview(unittest.TestCase):
             prior_review_state="approve",
             reason="typo",
             operator_authorized=True,
-            target_pr_number=8,
         )
         self.assertFalse(r["authorized"])
         self.assertTrue(any("prior review ID" in x for x in r["reasons"]))
@@ -2576,22 +2572,10 @@ class TestSubmitPrReview(unittest.TestCase):
             prior_review_state="request_changes",
             reason="typo",
             operator_authorized=True,
-            target_pr_number=8,
         )
         self.assertFalse(r["authorized"])
         self.assertTrue(any("prior review state" in x for x in r["reasons"]))
 
-        # Cross-PR unlock refused (#693)
-        r = gitea_authorize_review_correction(
-            prior_review_id=42,
-            prior_review_state="approve",
-            reason="unlock other pr",
-            operator_authorized=True,
-            target_pr_number=692,
-        )
-        self.assertFalse(r["authorized"])
-        self.assertTrue(any("different PR" in x for x in r["reasons"]))
-
     def test_authorize_review_correction_requires_operator_auth(self):
         from mcp_server import _load_review_decision_lock, _save_review_decision_lock
         lock = _load_review_decision_lock() or {}
@@ -2604,7 +2588,6 @@ class TestSubmitPrReview(unittest.TestCase):
             prior_review_state="approve",
             reason="typo",
             operator_authorized=False,
-            target_pr_number=8,
         )
         self.assertFalse(r["authorized"])
         self.assertTrue(any("operator authorization" in x for x in r["reasons"]))
@@ -2662,7 +2645,6 @@ class TestSubmitPrReview(unittest.TestCase):
                     prior_review_state="approve",
                     reason="operator approved correcting mistaken approve",
                     operator_authorized=True,
-                    target_pr_number=8,
                 )
                 _mark_request_changes_ready(remote="prgs")
                 second = gitea_submit_pr_review(

tests/test_review_proofs.py

@@ -957,17 +957,20 @@ class TestControllerHandoff(unittest.TestCase):
             if not line.startswith("- Workspace mutations:"))
         result = assess_controller_handoff(review_base, role="review")
         self.assertEqual(result["verdict"], "incomplete")
-        self.assertIn("Pinned reviewed head", result["missing_fields"])
-        self.assertIn("Worktree path", result["missing_fields"])
+        # #698: the canonical schema forbids the legacy fields, so the
+        # validator must demand the canonical names instead.
+        self.assertIn("Reviewed head SHA", result["missing_fields"])
+        self.assertIn("Review worktree path", result["missing_fields"])
         self.assertIn("Merge result", result["missing_fields"])
+        for legacy in ("Pinned reviewed head", "Scratch worktree used"):
+            self.assertNotIn(legacy, result["missing_fields"])
 
         complete = review_base + "\n" + "\n".join([
             "- Selected PR: #999",
             "- Reviewer eligibility: passed",
-            "- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
-            "- Worktree path: /repo/branches/review-pr-999",
-            "- Worktree dirty: no",
-            "- Scratch worktree used: yes (/repo/branches/review-pr-999)",
+            "- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+            "- Review worktree path: /repo/branches/review-pr-999",
+            "- Review worktree dirty before validation: no",
             "- Unrelated local mutations: none",
             "- Review decision: approve",
             "- Merge result: merged",
@@ -1125,10 +1128,9 @@ class TestReviewHandoffPreciseMutationCategories(unittest.TestCase):
         "- Safety: no self-review; no self-merge; no secrets",
         "- Selected PR: #999",
         "- Reviewer eligibility: passed",
-        "- Pinned reviewed head: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
+        "- Reviewed head SHA: 0fdc8f582026b72a229d59a172c0a63ac4aaeaf9",
         "- Worktree path: /repo/branches/review-pr-999",
         "- Worktree dirty: no",
-        "- Scratch worktree used: yes (/repo/branches/review-pr-999)",
         "- Unrelated local mutations: none",
         "- Review decision: approve",
         "- Merge result: none",

tests/test_stale_review_decision_lock_cleanup.py

@@ -188,32 +188,20 @@ class TestActiveHardStopPreserved(unittest.TestCase):
         mcp_server._save_review_decision_lock(None)
         mcp_server.review_workflow_load.clear_review_workflow_load()
 
-    def test_open_approve_blocks_same_pr_not_other_pr_mark_ready(self):
-        _seed([APPROVED_OPEN])  # approve on PR #700
-        # Same PR still hard-stopped for mark_ready.
-        reasons_same = mcp_server.terminal_review_hard_stop_reasons(
-            700, "mark_ready"
-        )
-        self.assertTrue(reasons_same)
-        self.assertIn("#332", reasons_same[0])
-        # #693: other PR may mark_ready without cleanup.
-        self.assertEqual(
-            mcp_server.terminal_review_hard_stop_reasons(592, "mark_ready"),
-            [],
-        )
+    def test_open_approve_still_blocks_other_pr_mark_ready(self):
+        _seed([APPROVED_OPEN])
+        reasons = mcp_server.terminal_review_hard_stop_reasons(592, "mark_ready")
+        self.assertTrue(reasons)
+        self.assertIn("#332", reasons[0])
+        self.assertIn("gitea_cleanup_stale_review_decision_lock", reasons[0])
 
-    def test_request_changes_still_blocks_same_pr(self):
-        _seed([RC_OPEN])  # request_changes on PR #701
+    def test_request_changes_still_blocks_everything(self):
+        _seed([RC_OPEN])
         for op in ("merge", "mark_ready", "review"):
             self.assertTrue(
-                mcp_server.terminal_review_hard_stop_reasons(701, op),
+                mcp_server.terminal_review_hard_stop_reasons(592, op),
                 msg=op,
             )
-        # Foreign PR review path is open (#693).
-        self.assertEqual(
-            mcp_server.terminal_review_hard_stop_reasons(592, "mark_ready"),
-            [],
-        )
 
 
 # --------------------------------------------------------------------------- #

tests/test_terminal_review_hard_stop.py

@@ -1,10 +1,10 @@
-"""Tests for the session hard-stop after a terminal review mutation (#332/#693).
+"""Tests for the session hard-stop after a terminal review mutation (#332).
 
 Extends the single-terminal-decision machinery (#211): after a live
-REQUEST_CHANGES on a PR head the same-head path must stop; after an APPROVE
-only the merge sequence for that same PR may continue; #693 allows a
-*different* PR to be mark_ready/review in the same durable lock (cross-PR
-isolation); duplicate REQUEST_CHANGES at an unchanged head is suppressed.
+REQUEST_CHANGES the run must stop; after an APPROVE only the merge sequence
+for that same PR may continue; a different PR can never be reviewed or
+merged in the same run; duplicate REQUEST_CHANGES at an unchanged head is
+suppressed.
 """
 import os
 import unittest
@@ -15,10 +15,7 @@ import mcp_server
 HEAD_SHA = "a" * 40
 
 
-def _lock(mutations=None, correction=False, correction_pr=None):
-    mutations = list(mutations or [])
-    if correction and correction_pr is None and mutations:
-        correction_pr = mutations[-1].get("pr_number")
+def _lock(mutations=None, correction=False):
     return {
         "task": "review_pr",
         "remote": "prgs",
@@ -32,11 +29,9 @@ def _lock(mutations=None, correction=False, correction_pr=None):
         "ready_remote": None,
         "ready_org": None,
         "ready_repo": None,
-        "live_mutations": mutations,
+        "live_mutations": list(mutations or []),
         "correction_authorized": correction,
-        "correction_reason": "test" if correction else None,
-        "correction_pr_number": correction_pr if correction else None,
-        "correction_head_sha": None,
+        "correction_reason": None,
     }
 
 
@@ -69,35 +64,25 @@ class TestTerminalHardStopReasons(unittest.TestCase):
         self.assertEqual(
             mcp_server.terminal_review_hard_stop_reasons(5, "merge"), [])
 
-    def test_request_changes_blocks_same_pr_allows_other_pr_review(self):
+    def test_request_changes_blocks_everything(self):
         _seed([RC_A])
-        # Same PR: still hard-stopped for mark_ready/review/merge.
         for op in ("merge", "mark_ready", "review"):
-            reasons = mcp_server.terminal_review_hard_stop_reasons(5, op)
-            self.assertTrue(reasons, f"{op}/5")
-            self.assertIn("request_changes on PR #5", reasons[0])
-            self.assertIn("#332", reasons[0])
-        # #693: different PR may mark_ready / review (not merge via hard-stop alone).
-        self.assertEqual(
-            mcp_server.terminal_review_hard_stop_reasons(6, "mark_ready"), [])
-        self.assertEqual(
-            mcp_server.terminal_review_hard_stop_reasons(6, "review"), [])
-        # Merge of an unapproved other PR remains blocked by hard-stop path
-        # (last terminal is not approve of PR 6).
-        self.assertTrue(
-            mcp_server.terminal_review_hard_stop_reasons(6, "merge"))
+            for pr in (5, 6):
+                reasons = mcp_server.terminal_review_hard_stop_reasons(pr, op)
+                self.assertTrue(reasons, f"{op}/{pr}")
+                self.assertIn("request_changes on PR #5", reasons[0])
+                self.assertIn("#332", reasons[0])
 
-    def test_approve_allows_same_pr_merge_and_other_pr_review(self):
+    def test_approve_allows_same_pr_merge_only(self):
         _seed([APPROVED_A])
         self.assertEqual(
             mcp_server.terminal_review_hard_stop_reasons(5, "merge"), [])
         self.assertTrue(
             mcp_server.terminal_review_hard_stop_reasons(6, "merge"))
-        # #693 cross-PR isolation: other PR formal review path is open.
-        self.assertEqual(
-            mcp_server.terminal_review_hard_stop_reasons(6, "mark_ready"), [])
-        self.assertEqual(
-            mcp_server.terminal_review_hard_stop_reasons(6, "review"), [])
+        self.assertTrue(
+            mcp_server.terminal_review_hard_stop_reasons(6, "mark_ready"))
+        self.assertTrue(
+            mcp_server.terminal_review_hard_stop_reasons(6, "review"))
 
     def test_correction_reopens_review_path_only(self):
         _seed([RC_A], correction=True)
@@ -105,11 +90,9 @@ class TestTerminalHardStopReasons(unittest.TestCase):
             mcp_server.terminal_review_hard_stop_reasons(5, "mark_ready"), [])
         self.assertEqual(
             mcp_server.terminal_review_hard_stop_reasons(5, "review"), [])
-        # scoped correction never opens a cross-PR merge
+        # correction never opens a cross-PR merge
         self.assertTrue(
             mcp_server.terminal_review_hard_stop_reasons(6, "merge"))
-        # unscoped/cross-PR correction must not lift PR 6 via correction alone
-        # (PR 6 is allowed by isolation, not by correction scope)
 
 
 class TestMergeHardStopWiring(unittest.TestCase):
@@ -143,29 +126,14 @@ class TestMarkFinalHardStopWiring(unittest.TestCase):
         mcp_server._save_review_decision_lock(None)
         mcp_server.review_workflow_load.clear_review_workflow_load()
 
-    def test_mark_ready_same_pr_blocked_after_terminal_mutation(self):
+    def test_mark_ready_blocked_after_terminal_mutation(self):
         _seed([RC_A])
         result = mcp_server.gitea_mark_final_review_decision(
-            pr_number=5, action="approve", remote="prgs",
-            expected_head_sha=HEAD_SHA)
+            pr_number=6, action="approve", remote="prgs")
         self.assertFalse(result["marked_ready"])
         self.assertTrue(
             any("#332" in r for r in result["reasons"]), result["reasons"])
 
-    def test_mark_ready_other_pr_allowed_after_foreign_terminal(self):
-        """#693: foreign open-PR terminal must not block mark_final on PR B."""
-        _seed([RC_A])
-        no_lease = {"block": False, "reasons": [], "mutation_allowed": True}
-        with patch("mcp_server._list_pr_lease_comments", return_value=[]), \
-                patch("mcp_server._pr_work_lease_reviewer_block",
-                      return_value=no_lease), \
-                patch.object(mcp_server, "gitea_check_pr_eligibility",
-                             return_value={"head_sha": HEAD_SHA, "eligible": True}):
-            result = mcp_server.gitea_mark_final_review_decision(
-                pr_number=6, action="approve", remote="prgs",
-                expected_head_sha=HEAD_SHA)
-        self.assertTrue(result["marked_ready"], result.get("reasons"))
-
 
 def _feedback(blocking, stale=False, success=True):
     return {