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]>
This commit is contained in:
2026-07-13 17:37:13 -04:00
co-authored by Claude Fable 5
parent 237656702f
commit ee90a5e7a2
7 changed files with 701 additions and 41 deletions
+67 -6
View File
@@ -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")