Compare commits

..
Author SHA1 Message Date
sysadminandClaude Opus 4.8 300a4ca08f chore(#681): preserve dirty control-checkout WIP from PR #680 review session
Moves the three uncommitted test-isolation changes off the root/control
checkout into a dedicated issue-681 branch, per issue #681 recovery path
(AC2: retained test-isolation changes land on a dedicated issue branch
with review; never smuggled into #604/PR #680).

Preserved as-is (NOT endorsed) for review:
- gitea_mcp_server.py: test-mode early return in _verify_role_mutation_workspace
- issue_lock_worktree.py: strips *.py lines from porcelain under pytest/unittest
- tests/test_preflight_read_survival.py: patches out branches-only + root-checkout guards

These weaken workspace/dirtiness guards under test and require review before
any adoption; committed here only to restore the control checkout to clean
master without discarding unique work.

Refs #681

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-12 10:35:28 -04:00
19 changed files with 253 additions and 4387 deletions
+113 -911
View File
File diff suppressed because it is too large Load Diff
+11 -1
View File
@@ -72,9 +72,19 @@ def read_worktree_git_state(
)
head_sha = (head_res.stdout or "").strip() if head_res.returncode == 0 else None
base_branch, base_sha = _find_matching_base_ref(path, head_sha, extra_bases)
porcelain = status_res.stdout or ""
import sys
if "pytest" in sys.modules or "unittest" in sys.modules:
porcelain = "\n".join(
line for line in porcelain.splitlines()
if not line.strip().endswith(".py")
)
if porcelain:
porcelain += "\n"
return {
"current_branch": current_branch,
"porcelain_status": status_res.stdout or "",
"porcelain_status": porcelain,
"inspected_git_root": (root_res.stdout or "").strip() if root_res.returncode == 0 else None,
"head_sha": head_sha,
"base_branch": base_branch,
-1
View File
@@ -13,7 +13,6 @@ from typing import Any
AUTHORIZED_CLEANUP_TOOLS = frozenset({
"gitea_cleanup_post_merge_moot_lease",
"gitea_cleanup_obsolete_reviewer_comment_lease",
"gitea_reconcile_merged_cleanups",
"gitea_delete_branch",
"gitea_cleanup_merged_pr_branch",
+43 -657
View File
@@ -524,26 +524,13 @@ def assess_lease_inventory(
"reclaimable_review_leases": reclaimable,
}
# Canonical next-action vocabulary for reviewer lease handoff (#599, #691).
# Canonical next-action vocabulary for reviewer lease handoff (#599).
NEXT_ACTION_ACQUIRE = "acquire"
NEXT_ACTION_WAIT = "wait"
NEXT_ACTION_RESUME_EXACT_OWNER_SESSION = "resume_exact_owner_session"
NEXT_ACTION_RELEASE_EXPIRED_LEASE = "release_expired_lease"
NEXT_ACTION_OPERATOR_AUTHORIZED_CLEANUP = "operator_authorized_cleanup"
NEXT_ACTION_REPAIR_WORKTREE_BINDING = "repair_worktree_binding"
NEXT_ACTION_CLEANUP_OBSOLETE_LEASE = "cleanup_obsolete_reviewer_comment_lease"
CLEANUP_OBSOLETE_LEASE_TOOL = "gitea_cleanup_obsolete_reviewer_comment_lease"
CLEANUP_OBSOLETE_LEASE_CONFIRMATION_PREFIX = "CLEANUP OBSOLETE REVIEWER LEASE "
# Formal terminal review verdicts that complete a leased-head workflow (#691).
_TERMINAL_REVIEW_VERDICTS = frozenset({
"APPROVED",
"REQUEST_CHANGES",
"approved",
"request_changes",
"REQUESTCHANGES",
})
_HANDOFF_CLASSIFICATIONS = frozenset({
"no_lease",
@@ -552,12 +539,6 @@ _HANDOFF_CLASSIFICATIONS = frozenset({
"foreign_active",
"foreign_reclaimable",
"foreign_expired",
"foreign_active_current_head",
"foreign_expired_current_head",
"foreign_completed_superseded_head",
"foreign_expired_superseded_head",
"orphaned_owner_missing",
"ambiguous_conflicting_evidence",
"instructed_lease_missing_with_replacement",
"worktree_binding_mismatch",
})
@@ -570,476 +551,6 @@ def _norm_path(value: str | None) -> str:
return os.path.normpath(text.rstrip("/"))
def _normalize_verdict(value: str | None) -> str:
text = (value or "").strip().upper().replace("-", "_").replace(" ", "_")
if text in {"REQUESTCHANGES", "REQUEST_CHANGES", "CHANGES_REQUESTED"}:
return "REQUEST_CHANGES"
if text in {"APPROVED", "APPROVE"}:
return "APPROVED"
return text
def formal_terminal_review_for_head(
formal_reviews: list[dict] | None,
*,
leased_head: str | None,
) -> dict[str, Any] | None:
"""Return the latest undismissed terminal formal review for *leased_head*."""
head = _normalize_sha(leased_head)
if not head:
return None
matches: list[dict[str, Any]] = []
for review in formal_reviews or []:
if review.get("dismissed"):
continue
verdict = _normalize_verdict(
review.get("verdict") or review.get("state") or review.get("body_state")
)
if verdict not in {"APPROVED", "REQUEST_CHANGES"}:
continue
rhead = _normalize_sha(
review.get("reviewed_head_sha")
or review.get("commit_id")
or review.get("head_sha")
)
if rhead != head:
continue
matches.append({**review, "verdict": verdict, "reviewed_head_sha": rhead})
if not matches:
return None
return matches[-1]
def find_newest_nonterminal_lease(
comments: list[dict],
*,
pr_number: int,
now: datetime | None = None,
include_expired: bool = True,
) -> dict[str, Any] | None:
"""Newest non-terminal lease marker, optionally including expired ones (#691).
Unlike ``find_active_reviewer_lease``, this retains expired non-terminal
markers so diagnosis/cleanup can still name the obsolete lease after
``expires_at`` (comment-backed ledger; no control-plane ``lease_id``).
"""
now = now or datetime.now(timezone.utc)
entries = list(reversed(_lease_entries(comments, pr_number=pr_number)))
for entry in entries:
phase = (entry.get("phase") or "").strip().lower()
if phase in _TERMINAL_PHASES:
# Newest terminal ends the ledger chain for active acquisition, but
# an older non-terminal is not "active". Stop at newest marker.
return None
expired = _lease_expired(entry, now=now)
if expired and not include_expired:
return None
lease = dict(entry)
lease["freshness"] = classify_lease_freshness(lease, now=now)
lease["expired"] = expired
return lease
return None
def cleanup_confirmation_for_pr(pr_number: int) -> str:
return f"{CLEANUP_OBSOLETE_LEASE_CONFIRMATION_PREFIX}{int(pr_number)}"
def assess_obsolete_reviewer_comment_lease_cleanup(
comments: list[dict],
*,
pr_number: int,
current_head_sha: str | None,
formal_reviews: list[dict] | None = None,
repo: str | None = None,
expected_repo: str | None = None,
requesting_session_id: str | None = None,
controller_recovery_authorized: bool = False,
worktree_exists: bool | None = None,
worktree_clean: bool | None = None,
worktree_has_unpreserved_work: bool | None = None,
owner_process_alive: bool | None = None,
owner_pid_observed: int | None = None,
requesting_pid: int | None = None,
current_head_review_in_progress: bool = False,
expected_lease_comment_id: int | None = None,
expected_session_id: str | None = None,
expected_leased_head: str | None = None,
confirmation: str | None = None,
apply: bool = False,
now: datetime | None = None,
) -> dict[str, Any]:
"""Guarded cleanup eligibility for obsolete comment-backed reviewer leases (#691).
Cleanup is never transfer/adoption/repoint and never uses PID equality as
ownership. Eligible only when evidence proves the lease is past expiry and/or
pinned to a superseded head with a completed formal terminal review, and
every safety boundary holds.
"""
now = now or datetime.now(timezone.utc)
reasons: list[str] = []
fail_closed_reasons: list[str] = []
current_head = _normalize_sha(current_head_sha)
req_session = (requesting_session_id or "").strip()
lease = find_newest_nonterminal_lease(
comments, pr_number=pr_number, now=now, include_expired=True
)
if not lease:
# Fall back to active finder (unexpired only) for report consistency.
lease = find_active_reviewer_lease(comments, pr_number=pr_number, now=now)
classification = "no_lease"
cleanup_allowed = False
release_body: str | None = None
audit_comment_body: str | None = None
terminal_review = None
leased_head = None
head_superseded = False
past_expiry = False
expires_parseable = True
if not lease:
fail_closed_reasons.append(
f"PR #{pr_number}: no non-terminal comment-backed reviewer lease to clean"
)
classification = "no_lease"
else:
leased_head = _normalize_sha(lease.get("candidate_head"))
expires_raw = lease.get("expires_at")
expires_at = _parse_timestamp(expires_raw)
if expires_raw and expires_at is None:
expires_parseable = False
fail_closed_reasons.append(
"lease expires_at cannot be parsed or trusted (fail closed)"
)
past_expiry = bool(expires_at and expires_at <= now)
freshness = lease.get("freshness") or classify_lease_freshness(lease, now=now)
owner_session = (lease.get("session_id") or "").strip()
is_requesting_owner = bool(
req_session and owner_session and req_session == owner_session
)
# Identity pins (repo / PR / session / head / comment) must match when
# the caller supplies expected evidence.
lease_repo = (lease.get("repo") or "").strip()
exp_repo = (expected_repo or repo or "").strip()
if exp_repo and lease_repo and exp_repo != lease_repo:
fail_closed_reasons.append(
f"repository identity mismatch: lease repo={lease_repo!r} "
f"expected={exp_repo!r}"
)
if lease.get("pr_number") not in (None, pr_number):
fail_closed_reasons.append(
f"PR identity mismatch: lease pr={lease.get('pr_number')} "
f"requested={pr_number}"
)
if expected_lease_comment_id is not None:
cid = lease.get("comment_id")
if cid is None or int(cid) != int(expected_lease_comment_id):
fail_closed_reasons.append(
"lease comment_id does not match expected evidence "
f"(lease={cid}, expected={expected_lease_comment_id})"
)
if expected_session_id:
if owner_session != expected_session_id.strip():
fail_closed_reasons.append(
"lease session_id does not match expected evidence "
f"(lease={owner_session}, expected={expected_session_id})"
)
if expected_leased_head:
exp_head = _normalize_sha(expected_leased_head)
if not exp_head or exp_head != leased_head:
fail_closed_reasons.append(
"leased head does not match expected evidence "
f"(lease={leased_head}, expected={exp_head})"
)
# PID equality is never ownership proof (#691).
if (
owner_pid_observed is not None
and requesting_pid is not None
and int(owner_pid_observed) == int(requesting_pid)
):
reasons.append(
"observed PID equals requesting PID but PID equality is NOT "
"ownership proof; ignored for authorization"
)
if is_requesting_owner:
fail_closed_reasons.append(
"requesting session owns the lease; use "
"gitea_release_reviewer_pr_lease (owner path), not non-owner cleanup"
)
if current_head_review_in_progress:
fail_closed_reasons.append(
"a current-head review submission is in progress; cleanup denied"
)
if not current_head:
fail_closed_reasons.append(
"current PR head SHA missing or unparseable (fail closed)"
)
if not leased_head:
fail_closed_reasons.append(
"lease candidate_head missing or unparseable (fail closed)"
)
head_superseded = bool(
current_head and leased_head and current_head != leased_head
)
head_matches_current = bool(
current_head and leased_head and current_head == leased_head
)
terminal_review = formal_terminal_review_for_head(
formal_reviews, leased_head=leased_head
)
has_terminal = terminal_review is not None
# Worktree safety.
if worktree_has_unpreserved_work is True or worktree_clean is False:
fail_closed_reasons.append(
"lease worktree is dirty or has unpreserved work; cleanup denied"
)
if (
worktree_exists is True
and worktree_clean is None
and worktree_has_unpreserved_work is None
):
# Unknown cleanliness when path exists — fail closed.
fail_closed_reasons.append(
"lease worktree exists but cleanliness is unknown (fail closed)"
)
# Classification matrix (#691).
if head_matches_current and freshness in {"active", "stale_warning"}:
classification = "foreign_active_current_head"
fail_closed_reasons.append(
"genuinely active foreign lease on the current PR head; "
"cleanup denied (fail closed)"
)
elif head_matches_current and past_expiry:
classification = "foreign_expired_current_head"
# Expired on current head: owner-missing / orphan path may apply.
if owner_process_alive is True:
fail_closed_reasons.append(
"lease expired on current head but owner process still alive "
"with plausible activity; cleanup denied"
)
elif worktree_clean is False:
fail_closed_reasons.append(
"owner process absent but worktree dirty; cleanup denied"
)
elif owner_process_alive is False and (
worktree_clean is True or worktree_exists is False
):
if controller_recovery_authorized:
classification = "orphaned_owner_missing"
else:
fail_closed_reasons.append(
"controller/recovery capability not authorized for orphan cleanup"
)
else:
fail_closed_reasons.append(
"insufficient orphan evidence for expired current-head lease "
"(need owner_process_alive=false and clean/absent worktree)"
)
elif head_superseded and has_terminal and past_expiry:
classification = "foreign_expired_superseded_head"
elif head_superseded and has_terminal and not past_expiry:
classification = "foreign_completed_superseded_head"
elif head_superseded and not has_terminal:
classification = "ambiguous_conflicting_evidence"
fail_closed_reasons.append(
"lease head is superseded but no formal terminal review exists "
"for the leased head (fail closed)"
)
elif not head_superseded and not past_expiry and freshness in {
"active", "stale_warning"
}:
classification = "foreign_active_current_head"
fail_closed_reasons.append(
"foreign lease still active on current head; wait or use owner release"
)
elif past_expiry and not head_superseded:
classification = "foreign_expired_current_head"
else:
classification = "ambiguous_conflicting_evidence"
fail_closed_reasons.append(
"lease evidence is ambiguous; cleanup denied (fail closed)"
)
# Recent owner progress on a non-superseded active lease blocks cleanup.
minutes = _minutes_since_activity(lease, now=now)
if (
head_matches_current
and freshness == "active"
and minutes is not None
and minutes < STALE_WARNING_MINUTES
):
fail_closed_reasons.append(
"owner session has recent authenticated progress on current head; "
"cleanup denied"
)
# Authority + confirmation for apply.
if not controller_recovery_authorized:
if classification in {
"foreign_completed_superseded_head",
"foreign_expired_superseded_head",
"foreign_expired_current_head",
"orphaned_owner_missing",
}:
fail_closed_reasons.append(
"controller/recovery capability required "
"(controller_recovery_authorized=true)"
)
expected_conf = cleanup_confirmation_for_pr(pr_number)
if apply:
if (confirmation or "").strip() != expected_conf:
fail_closed_reasons.append(
f"confirmation must equal exactly {expected_conf!r}"
)
# Superseded + terminal path does not require past_expiry (AC1).
eligible_class = classification in {
"foreign_completed_superseded_head",
"foreign_expired_superseded_head",
"orphaned_owner_missing",
"foreign_expired_current_head",
}
# foreign_expired_current_head needs orphan/clean worktree + authority.
if classification == "foreign_expired_current_head":
if worktree_clean is not True and worktree_exists is not False:
if "worktree" not in " ".join(fail_closed_reasons):
fail_closed_reasons.append(
"expired current-head cleanup requires proven-clean "
"worktree or absent worktree"
)
if owner_process_alive is True:
fail_closed_reasons.append(
"owner process still alive on expired current-head lease"
)
cleanup_allowed = (
eligible_class
and expires_parseable
and not fail_closed_reasons
and not is_requesting_owner
)
if cleanup_allowed:
release_body = format_lease_body(
repo=lease.get("repo") or exp_repo or "",
pr_number=pr_number,
issue_number=lease.get("issue_number"),
reviewer_identity=lease.get("reviewer_identity") or "",
profile=lease.get("profile") or "unknown",
session_id=owner_session or "unknown",
worktree=lease.get("worktree") or "",
phase="released",
candidate_head=leased_head,
target_branch=lease.get("target_branch") or "master",
target_branch_sha=lease.get("target_branch_sha"),
last_activity=now,
blocker="obsolete-superseded-or-expired-lease",
)
audit_comment_body = (
"## Canonical obsolete reviewer lease cleanup (#691)\n\n"
f"- pr: #{pr_number}\n"
f"- lease_comment_id: {lease.get('comment_id')}\n"
f"- session_id: {owner_session}\n"
f"- leased_head: {leased_head}\n"
f"- current_head: {current_head}\n"
f"- expires_at: {lease.get('expires_at')}\n"
f"- classification: {classification}\n"
f"- terminal_review_verdict: "
f"{(terminal_review or {}).get('verdict')}\n"
f"- tool: {CLEANUP_OBSOLETE_LEASE_TOOL}\n"
"- action: posted terminal phase=released lease marker; "
"did not transfer validation, decision, or workflow proof; "
"did not repoint lease to the new head; did not delete history\n"
)
reasons.append(
f"cleanup eligible ({classification}); post terminal released "
"marker via sanctioned tool"
)
else:
reasons.extend(fail_closed_reasons)
return {
"pr_number": pr_number,
"classification": classification,
"blocker_kind": classification if not cleanup_allowed else "none",
"cleanup_allowed": cleanup_allowed,
"mutation_allowed": False, # never grants review mutation
"mutation_eligibility": "prohibited" if not cleanup_allowed else "cleanup_only",
"exact_next_action": (
NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
if cleanup_allowed
else (
NEXT_ACTION_WAIT
if classification
in {
"foreign_active_current_head",
"ambiguous_conflicting_evidence",
}
else NEXT_ACTION_OPERATOR_AUTHORIZED_CLEANUP
)
),
"cleanup_tool": CLEANUP_OBSOLETE_LEASE_TOOL,
"required_confirmation": cleanup_confirmation_for_pr(pr_number),
"leased_head": leased_head,
"current_head": current_head,
"head_superseded": head_superseded,
"past_expiry": past_expiry,
"expires_at": (lease or {}).get("expires_at") if lease else None,
"expires_parseable": expires_parseable,
"terminal_review": terminal_review,
"terminal_review_present": terminal_review is not None,
"worktree_state": {
"path": (lease or {}).get("worktree") if lease else None,
"exists": worktree_exists,
"clean": worktree_clean,
"has_unpreserved_work": worktree_has_unpreserved_work,
},
"owner_session_evidence": {
"session_id": (lease or {}).get("session_id") if lease else None,
"reviewer_identity": (
(lease or {}).get("reviewer_identity") if lease else None
),
"process_alive": owner_process_alive,
"pid_observed": owner_pid_observed,
"pid_is_not_ownership_proof": True,
"requesting_session_is_owner": bool(
lease
and req_session
and (lease.get("session_id") or "").strip() == req_session
),
},
"active_lease": lease,
"release_body": release_body,
"audit_comment_body": audit_comment_body,
"controller_recovery_authorized": controller_recovery_authorized,
"reasons": reasons if reasons else fail_closed_reasons,
"fail_closed_reasons": fail_closed_reasons,
"forbidden": [
"manual comment deletion",
"database edits",
"mtime manipulation",
"PID-based ownership",
"direct session-state seeding",
"lease stealing or adoption",
"repointing old lease to new head",
"transfer of validation or decision state",
"worktree reuse by replacement reviewer",
],
}
def diagnose_reviewer_pr_lease_handoff(
comments: list[dict],
*,
@@ -1050,50 +561,40 @@ def diagnose_reviewer_pr_lease_handoff(
env_bound_worktree: str | None = None,
instructed_session_id: str | None = None,
instructed_comment_id: int | None = None,
current_head_sha: str | None = None,
formal_reviews: list[dict] | None = None,
worktree_exists: bool | None = None,
worktree_clean: bool | None = None,
owner_process_alive: bool | None = None,
now: datetime | None = None,
) -> dict[str, Any]:
"""Classify open-PR reviewer lease handoff and emit a canonical next action (#599, #691).
"""Classify open-PR reviewer lease handoff and emit a canonical next action (#599).
Read-only diagnosis. Never steals, releases, or adopts a foreign lease.
Fail-closed acquisition rules for active foreign leases remain intact.
Returns a structured diagnosis with:
- classification (including #691 superseded/expired distinctions)
- next_action (including cleanup_obsolete_reviewer_comment_lease)
- classification
- next_action (one of wait / resume_exact_owner_session /
release_expired_lease / operator_authorized_cleanup /
repair_worktree_binding / acquire)
- active_lease identity fields when present
- worktree_binding match result
- instructed-lease mismatch flags
- cleanup tool/confirmation when cleanup-eligible
"""
now = now or datetime.now(timezone.utc)
session_id = (current_session_id or "").strip()
identity = (current_reviewer_identity or "").strip()
instructed_sid = (instructed_session_id or "").strip()
reasons: list[str] = []
current_head = _normalize_sha(current_head_sha)
active = find_active_reviewer_lease(comments, pr_number=pr_number, now=now)
# Also surface expired non-terminal newest marker for #691 diagnosis.
newest_nt = find_newest_nonterminal_lease(
comments, pr_number=pr_number, now=now, include_expired=True
)
lease_for_class = active or newest_nt
session_lease = get_session_lease()
# Worktree binding: env-bound vs proposed vs active lease worktree.
env_wt = _norm_path(env_bound_worktree)
prop_wt = _norm_path(proposed_worktree)
lease_wt = _norm_path((lease_for_class or {}).get("worktree") if lease_for_class else None)
lease_wt = _norm_path((active or {}).get("worktree") if active else None)
binding_mismatch = False
binding_details: dict[str, Any] = {
"env_bound_worktree": env_bound_worktree or None,
"proposed_worktree": proposed_worktree or None,
"lease_worktree": (lease_for_class or {}).get("worktree") if lease_for_class else None,
"lease_worktree": (active or {}).get("worktree") if active else None,
"match": True,
}
paths = [p for p in (env_wt, prop_wt, lease_wt) if p]
@@ -1107,13 +608,13 @@ def diagnose_reviewer_pr_lease_handoff(
# Instructed lease gone while a different lease is active (PR #592-style).
instructed_missing_with_replacement = False
if instructed_sid or instructed_comment_id is not None:
if not lease_for_class:
if not active:
reasons.append(
"instructed lease is gone and no active replacement lease remains"
)
else:
owner = (lease_for_class.get("session_id") or "").strip()
cid = lease_for_class.get("comment_id")
owner = (active.get("session_id") or "").strip()
cid = active.get("comment_id")
sid_mismatch = bool(instructed_sid and owner and owner != instructed_sid)
cid_mismatch = (
instructed_comment_id is not None
@@ -1130,94 +631,35 @@ def diagnose_reviewer_pr_lease_handoff(
# Classification + next_action.
classification = "no_lease"
next_action = NEXT_ACTION_ACQUIRE
cleanup_hint: dict[str, Any] | None = None
if lease_for_class:
owner = (lease_for_class.get("session_id") or "").strip()
freshness = lease_for_class.get("freshness") or classify_lease_freshness(
lease_for_class, now=now
if active:
owner = (active.get("session_id") or "").strip()
freshness = active.get("freshness") or classify_lease_freshness(
active, now=now
)
owner_identity = (lease_for_class.get("reviewer_identity") or "").strip()
owner_identity = (active.get("reviewer_identity") or "").strip()
is_own = bool(session_id and owner and owner == session_id)
# Same identity alone is NOT ownership for resume; session_id must match.
same_identity = bool(
identity and owner_identity and identity == owner_identity
)
leased_head = _normalize_sha(lease_for_class.get("candidate_head"))
head_superseded = bool(
current_head and leased_head and current_head != leased_head
)
head_current = bool(
current_head and leased_head and current_head == leased_head
)
past_expiry = bool(lease_for_class.get("expired")) or freshness == "expired"
if not past_expiry:
past_expiry = _lease_expired(lease_for_class, now=now)
terminal = formal_terminal_review_for_head(
formal_reviews, leased_head=leased_head
)
if is_own and freshness in {"active", "stale_warning"} and not past_expiry:
if is_own and freshness in {"active", "stale_warning"}:
classification = "own_active"
next_action = NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
elif is_own and (freshness in {"reclaimable", "expired"} or past_expiry):
elif is_own and freshness in {"reclaimable", "expired"}:
classification = "own_expired"
next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
reasons.append(
f"own lease freshness is '{freshness}'; release via "
"gitea_release_reviewer_pr_lease then re-acquire"
)
elif not is_own and head_superseded and terminal and past_expiry:
classification = "foreign_expired_superseded_head"
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign lease expired and pinned to superseded head with "
"formal terminal review; use guarded obsolete-lease cleanup"
)
elif not is_own and head_superseded and terminal and not past_expiry:
classification = "foreign_completed_superseded_head"
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign lease pinned to superseded head with completed formal "
"review; use guarded obsolete-lease cleanup (do not wait indefinitely)"
)
elif not is_own and head_superseded and not terminal:
classification = "ambiguous_conflicting_evidence"
next_action = NEXT_ACTION_WAIT
reasons.append(
"lease head superseded but no formal terminal review for leased "
"head; fail closed / wait (no indefinite steal)"
)
elif not is_own and head_current and past_expiry:
classification = "foreign_expired_current_head"
if owner_process_alive is False and worktree_clean is True:
classification = "orphaned_owner_missing"
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign expired lease on current head; owner process absent "
"and worktree clean — guarded orphan cleanup eligible"
)
elif owner_process_alive is False and worktree_clean is False:
classification = "ambiguous_conflicting_evidence"
next_action = NEXT_ACTION_WAIT
reasons.append(
"owner process absent but worktree dirty; cleanup denied"
)
else:
next_action = NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
reasons.append(
"foreign expired lease on current head; use guarded cleanup "
"when worktree/process evidence permits"
)
elif not is_own and freshness in {"active", "stale_warning"} and not past_expiry:
classification = (
"foreign_active_current_head" if head_current or not current_head
else "foreign_active"
)
elif not is_own and freshness in {"active", "stale_warning"}:
classification = "foreign_active"
next_action = NEXT_ACTION_WAIT
reasons.append(
f"foreign active reviewer lease (session_id={owner}, "
f"phase={lease_for_class.get('phase')}, freshness={freshness}); "
f"phase={active.get('phase')}, freshness={freshness}); "
"do not submit; do not steal"
)
if same_identity:
@@ -1232,12 +674,11 @@ def diagnose_reviewer_pr_lease_handoff(
f"foreign reclaimable lease (session_id={owner}); clear only via "
"sanctioned gitea_release_reviewer_pr_lease when reclaimable"
)
elif not is_own and (freshness == "expired" or past_expiry):
elif not is_own and freshness == "expired":
classification = "foreign_expired"
next_action = NEXT_ACTION_RELEASE_EXPIRED_LEASE
reasons.append(
f"foreign expired lease (session_id={owner}); use sanctioned release "
f"or {CLEANUP_OBSOLETE_LEASE_TOOL}"
f"foreign expired lease (session_id={owner}); use sanctioned release"
)
else:
classification = "foreign_active"
@@ -1250,26 +691,13 @@ def diagnose_reviewer_pr_lease_handoff(
if instructed_missing_with_replacement and classification.startswith(
"foreign"
):
# Preserve #691 cleanup path when superseded/expired; otherwise
# keep the PR #592 instructed-missing label.
if next_action != NEXT_ACTION_CLEANUP_OBSOLETE_LEASE:
classification = "instructed_lease_missing_with_replacement"
if next_action == NEXT_ACTION_WAIT:
reasons.append(
"replacement foreign lease is active — wait; "
"operator_authorized_cleanup only with explicit operator authority"
)
if next_action == NEXT_ACTION_CLEANUP_OBSOLETE_LEASE:
cleanup_hint = {
"cleanup_tool": CLEANUP_OBSOLETE_LEASE_TOOL,
"required_confirmation": cleanup_confirmation_for_pr(pr_number),
"controller_recovery_authorized_required": True,
"leased_head": leased_head,
"current_head": current_head,
"expires_at": lease_for_class.get("expires_at"),
"terminal_review_verdict": (terminal or {}).get("verdict"),
}
classification = "instructed_lease_missing_with_replacement"
# Foreign active still means wait; reclaimable still release.
if next_action == NEXT_ACTION_WAIT:
reasons.append(
"replacement foreign lease is active — wait; "
"operator_authorized_cleanup only with explicit operator authority"
)
else:
classification = "no_lease"
next_action = NEXT_ACTION_ACQUIRE
@@ -1292,55 +720,29 @@ def diagnose_reviewer_pr_lease_handoff(
)
lease_summary = None
if lease_for_class:
if active:
lease_summary = {
"comment_id": lease_for_class.get("comment_id"),
"session_id": lease_for_class.get("session_id"),
"phase": lease_for_class.get("phase"),
"candidate_head": lease_for_class.get("candidate_head"),
"expires_at": lease_for_class.get("expires_at"),
"last_activity": lease_for_class.get("last_activity"),
"freshness": lease_for_class.get("freshness")
or classify_lease_freshness(lease_for_class, now=now),
"reviewer_identity": lease_for_class.get("reviewer_identity"),
"profile": lease_for_class.get("profile"),
"worktree": lease_for_class.get("worktree"),
"blocker": lease_for_class.get("blocker"),
"comment_id": active.get("comment_id"),
"session_id": active.get("session_id"),
"phase": active.get("phase"),
"candidate_head": active.get("candidate_head"),
"expires_at": active.get("expires_at"),
"last_activity": active.get("last_activity"),
"freshness": active.get("freshness")
or classify_lease_freshness(active, now=now),
"reviewer_identity": active.get("reviewer_identity"),
"profile": active.get("profile"),
"worktree": active.get("worktree"),
"blocker": active.get("blocker"),
}
return {
"pr_number": pr_number,
"classification": classification,
"blocker_kind": classification,
"next_action": next_action,
"exact_next_action": next_action,
"active_lease": lease_summary,
"session_lease": session_lease,
"worktree_binding": binding_details,
"leased_head": (lease_summary or {}).get("candidate_head"),
"current_head": current_head,
"expires_at": (lease_summary or {}).get("expires_at"),
"terminal_review_state": (
formal_terminal_review_for_head(
formal_reviews,
leased_head=(lease_summary or {}).get("candidate_head"),
)
if lease_summary
else None
),
"worktree_state": {
"exists": worktree_exists,
"clean": worktree_clean,
"path": (lease_summary or {}).get("worktree"),
},
"owner_session_evidence": {
"session_id": (lease_summary or {}).get("session_id"),
"process_alive": owner_process_alive,
"pid_is_not_ownership_proof": True,
},
"cleanup": cleanup_hint,
"cleanup_tool": (cleanup_hint or {}).get("cleanup_tool"),
"required_confirmation": (cleanup_hint or {}).get("required_confirmation"),
"instructed_session_id": instructed_session_id,
"instructed_comment_id": instructed_comment_id,
"instructed_lease_missing_with_replacement": instructed_missing_with_replacement,
@@ -1349,19 +751,6 @@ def diagnose_reviewer_pr_lease_handoff(
and not binding_mismatch
and bool(session_lease)
),
"mutation_eligibility": (
"allowed"
if (
next_action == NEXT_ACTION_RESUME_EXACT_OWNER_SESSION
and not binding_mismatch
and bool(session_lease)
)
else (
"cleanup_only"
if next_action == NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
else "prohibited"
)
),
"reasons": reasons,
"forbidden": [
"manual lock deletion",
@@ -1369,8 +758,5 @@ def diagnose_reviewer_pr_lease_handoff(
"mtime manipulation",
"direct _SESSION_LEASE seeding",
"silent foreign lease steal",
"PID-based ownership",
"repointing old lease to new head",
"transfer of validation or decision state",
],
}
+13 -457
View File
@@ -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,
}
-27
View File
@@ -76,16 +76,6 @@ TASK_CAPABILITY_MAP: dict[str, dict[str, str]] = {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
# #691: guarded non-owner cleanup of obsolete comment-backed reviewer leases.
# Apply path posts lease release + audit comments (gitea.pr.comment).
"cleanup_obsolete_reviewer_comment_lease": {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
"gitea_cleanup_obsolete_reviewer_comment_lease": {
"permission": "gitea.pr.comment",
"role": "reviewer",
},
"blind_pr_queue_review": {
"permission": "gitea.pr.review",
"role": "reviewer",
@@ -117,23 +107,6 @@ 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",
+10 -39
View File
@@ -57,23 +57,9 @@ class TestCreateIssueWorkspaceGuard(unittest.TestCase):
# Without worktree_path/env hints, workspace resolves to PROJECT_ROOT. When that
# path is the stable control checkout (not under branches/), mutation must fail.
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
try:
res = srv.gitea_create_issue(title="Test issue", body="body text")
except RuntimeError as exc:
self.assertIn("stable control checkout", str(exc))
else:
# #683: production guards return typed blockers at entrypoints
self.assertFalse(res.get("success"))
self.assertFalse(res.get("performed"))
blob = " ".join(res.get("reasons") or []) + " " + str(
res.get("blocker_kind") or ""
)
self.assertTrue(
"stable control checkout" in blob
or "missing_issue_worktree" in blob
or "control checkout" in blob.lower()
)
self.assertTrue(res.get("exact_next_action"))
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(title="Test issue", body="body text")
self.assertIn("stable control checkout", str(ctx.exception))
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@patch("gitea_mcp_server._profile_permission_block", return_value=None)
@@ -119,17 +105,11 @@ class TestCreateIssueWorkspaceGuard(unittest.TestCase):
)
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
try:
res = srv.gitea_create_issue(
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(
title="Test issue", body="body", worktree_path=missing_path
)
except RuntimeError as exc:
self.assertIn("does not exist", str(exc))
else:
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or [])
self.assertIn("does not exist", blob)
self.assertTrue(res.get("exact_next_action") or res.get("reasons"))
self.assertIn("does not exist (fail closed)", str(ctx.exception))
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@patch("gitea_mcp_server._profile_permission_block", return_value=None)
@@ -162,20 +142,11 @@ class TestCreateIssueWorkspaceGuard(unittest.TestCase):
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
with patch("gitea_mcp_server._get_workspace_porcelain", return_value=""):
try:
res = srv.gitea_create_issue(
title="Test issue",
body="body",
worktree_path=wrong_repo_path,
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(
title="Test issue", body="body", worktree_path=wrong_repo_path
)
except RuntimeError as exc:
self.assertIn(
"does not belong to the target repository", str(exc)
)
else:
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or [])
self.assertIn("does not belong to the target repository", blob)
self.assertIn("does not belong to the target repository", str(ctx.exception))
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@patch("gitea_mcp_server._profile_permission_block", return_value=None)
+4 -11
View File
@@ -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."""
+2 -11
View File
@@ -267,19 +267,10 @@ class TestReconcilerCommentThroughCanonicalPath(unittest.TestCase):
with patch.dict(os.environ, {}, clear=False):
os.environ.pop("GITEA_AUTHOR_WORKTREE", None)
os.environ.pop("GITEA_ACTIVE_WORKTREE", None)
try:
res = srv.gitea_create_issue_comment(
with self.assertRaises(RuntimeError):
srv.gitea_create_issue_comment(
515, "author note", remote="prgs"
)
except RuntimeError:
pass # legacy raise path
else:
# #683: typed blocker at mutation entrypoint
self.assertFalse(res.get("success"))
self.assertFalse(res.get("performed"))
self.assertTrue(
res.get("blocker_kind") or res.get("reasons")
)
mock_api.assert_not_called()
@@ -1,472 +0,0 @@
"""#683: block unattributed root WIP; pytest cannot disable production guards.
Regression coverage required by issue #683:
1. Session locked to issue A blocks unrelated target issue B until B is selected.
2. Diagnostic source edit on the root checkout is blocked.
3. Same legitimate edit succeeds after issue ownership + isolated worktree bind.
4. Running under pytest does not deactivate production guards when force-on.
5. Dirty tracked Python files remain visible to porcelain consumers.
6. Monkeypatching one helper cannot silently turn the full guard path into a no-op.
7. Real mutation entrypoint proves production guards run before side effects.
8. Same-issue edits in a valid isolated worktree remain unaffected.
9. Blocker includes stable reason + exact recovery action.
"""
from __future__ import annotations
import os
import sys
import tempfile
import textwrap
import unittest
from pathlib import Path
from unittest.mock import MagicMock, patch
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import gitea_mcp_server as mcp_server # noqa: E402
import issue_lock_worktree # noqa: E402
import workflow_scope_guard as wsg # noqa: E402
CONTROL_ROOT = str(Path(__file__).resolve().parent.parent)
if "branches" in Path(__file__).resolve().parts:
# Running from a worktree under branches/ — parent of branches is control.
parts = Path(__file__).resolve().parts
idx = parts.index("branches")
CONTROL_ROOT = str(Path(*parts[:idx])) if idx > 0 else CONTROL_ROOT
class TestProductionGuardsForceOn(unittest.TestCase):
def tearDown(self):
for key in (
wsg.FORCE_PRODUCTION_GUARDS_ENV,
"GITEA_TEST_FORCE_DIRTY",
"GITEA_TEST_PORCELAIN",
"GITEA_AUTHOR_WORKTREE",
"GITEA_ACTIVE_WORKTREE",
):
os.environ.pop(key, None)
wsg.clear_workflow_failure_ledger()
def test_force_on_under_pytest_keeps_production_active(self):
self.assertTrue(wsg.production_guards_active(in_test_mode=False))
self.assertFalse(wsg.production_guards_active(in_test_mode=True))
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
self.assertTrue(wsg.production_guards_active(in_test_mode=True))
self.assertTrue(wsg.production_guards_forced())
def test_no_early_return_in_verify_role_mutation_workspace_source(self):
src = Path(mcp_server.__file__).read_text(encoding="utf-8")
# Rejected 300a4ca pattern must not exist.
self.assertNotIn(
"if _preflight_in_test_mode():\n return _resolve_preflight_workspace_path",
src,
)
# Docstring contract for #683.
self.assertIn("#683", src)
self.assertIn("must NOT early-return solely because pytest", src)
class TestPorcelainIntegrity(unittest.TestCase):
def test_read_worktree_git_state_surfaces_dirty_py(self):
with tempfile.TemporaryDirectory() as tmp:
# Use a real git repo so porcelain is truthful.
import subprocess
subprocess.run(["git", "init"], cwd=tmp, check=True, capture_output=True)
subprocess.run(
["git", "config", "user.email", "[email protected]"],
cwd=tmp,
check=True,
capture_output=True,
)
subprocess.run(
["git", "config", "user.name", "t"],
cwd=tmp,
check=True,
capture_output=True,
)
py_path = Path(tmp) / "sample_mod.py"
py_path.write_text("x = 1\n", encoding="utf-8")
subprocess.run(["git", "add", "sample_mod.py"], cwd=tmp, check=True)
subprocess.run(
["git", "commit", "-m", "init"],
cwd=tmp,
check=True,
capture_output=True,
)
py_path.write_text("x = 2\n", encoding="utf-8")
state = issue_lock_worktree.read_worktree_git_state(tmp)
porcelain = state.get("porcelain_status") or ""
self.assertIn("sample_mod.py", porcelain)
self.assertTrue(any(line.strip().endswith(".py") for line in porcelain.splitlines()))
def test_production_reader_source_rejects_pytest_py_filter(self):
src = Path(issue_lock_worktree.__file__).read_text(encoding="utf-8")
findings = wsg.assert_no_pytest_porcelain_filter(src)
self.assertEqual(findings, [])
# Negative: the rejected 300a4ca pattern is detected.
rejected = textwrap.dedent(
"""
porcelain = status_res.stdout or ""
import sys
if "pytest" in sys.modules or "unittest" in sys.modules:
porcelain = "\\n".join(
line for line in porcelain.splitlines()
if not line.strip().endswith(".py")
)
"""
)
self.assertTrue(wsg.assert_no_pytest_porcelain_filter(rejected))
class TestIssueScopeOwnership(unittest.TestCase):
def test_out_of_scope_issue_blocked_until_selected(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=100,
target_issue_number=200,
branch_name="fix/issue-100-example",
role_kind="author",
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_OUT_OF_SCOPE_ISSUE)
self.assertIn("exact_next_action", result)
self.assertIn("owning issue", result["exact_next_action"].lower())
self.assertTrue(result["reasons"])
def test_same_issue_scope_allowed(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=100,
target_issue_number=100,
branch_name="fix/issue-100-example",
role_kind="author",
)
self.assertFalse(result["block"])
self.assertEqual(result["exact_next_action"], "proceed")
def test_missing_lock_when_required(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=None,
target_issue_number=None,
role_kind="author",
require_lock_for_author=True,
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_MISSING_ISSUE_SCOPE)
def test_branch_issue_mismatch(self):
result = wsg.assess_issue_scope_ownership(
locked_issue_number=50,
branch_name="fix/issue-99-other",
role_kind="author",
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_OUT_OF_SCOPE_ISSUE)
class TestRootDiagnosticEdit(unittest.TestCase):
def test_dirty_root_source_blocked(self):
result = wsg.assess_root_source_mutation(
workspace_path=CONTROL_ROOT,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M gitea_mcp_server.py\n M tests/test_x.py\n",
role_kind="author",
)
self.assertTrue(result["block"])
self.assertEqual(result["blocker_kind"], wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT)
self.assertIn("gitea_mcp_server.py", result["dirty_source_files"])
self.assertIn("exact_next_action", result)
self.assertIn("branches/", result["exact_next_action"])
def test_isolated_worktree_same_issue_unaffected(self):
wt = f"{CONTROL_ROOT}/branches/issue-100-example"
result = wsg.assess_root_source_mutation(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M helper.py\n",
current_branch="fix/issue-100-example",
locked_issue_number=100,
role_kind="author",
)
self.assertFalse(result["block"])
self.assertTrue(result["under_branches"])
def test_legitimate_after_ownership_and_worktree(self):
wt = f"{CONTROL_ROOT}/branches/issue-683-workflow-guard-hardening"
composed = wsg.assess_production_mutation_guards(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M workflow_scope_guard.py\n",
current_branch="fix/issue-683-workflow-guard-hardening",
locked_issue_number=683,
target_issue_number=683,
role_kind="author",
require_author_lock=True,
in_test_mode=True,
)
# Force-on required for production path under pytest.
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
try:
composed = wsg.assess_production_mutation_guards(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M workflow_scope_guard.py\n",
current_branch="fix/issue-683-workflow-guard-hardening",
locked_issue_number=683,
target_issue_number=683,
role_kind="author",
require_author_lock=True,
in_test_mode=True,
)
self.assertFalse(composed["block"])
self.assertFalse(composed.get("skipped"))
finally:
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
class TestTypedBlockerResponse(unittest.TestCase):
def test_block_response_has_stable_kind_and_next_action(self):
assessment = wsg.assess_issue_scope_ownership(
locked_issue_number=1,
target_issue_number=2,
role_kind="author",
)
resp = wsg.block_response(assessment)
self.assertFalse(resp["success"])
self.assertFalse(resp["performed"])
self.assertEqual(resp["blocker_kind"], wsg.BLOCKER_OUT_OF_SCOPE_ISSUE)
self.assertIsInstance(resp["exact_next_action"], str)
self.assertTrue(resp["exact_next_action"])
self.assertTrue(resp["reasons"])
def test_production_guard_error_roundtrip(self):
err = wsg.ProductionGuardError(
"blocked",
blocker_kind=wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT,
reasons=["dirty root"],
)
resp = wsg.block_response(err, issue_number=683)
self.assertEqual(resp["blocker_kind"], wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT)
self.assertEqual(resp["issue_number"], 683)
self.assertIn("exact_next_action", resp)
class TestDurableFailureRecording(unittest.TestCase):
def setUp(self):
wsg.clear_workflow_failure_ledger()
def tearDown(self):
wsg.clear_workflow_failure_ledger()
def test_record_before_source_mutation(self):
pending = wsg.assess_durable_failure_recorded(
require_record=True, pending_source_mutation=True
)
self.assertTrue(pending["block"])
self.assertEqual(pending["blocker_kind"], wsg.BLOCKER_UNRECORDED_FAILURE)
wsg.record_workflow_failure(
kind="transport_eof",
detail="EOF during review session (#584 cluster)",
issue_number=683,
task="comment_issue",
)
after = wsg.assess_durable_failure_recorded(
require_record=True, pending_source_mutation=True
)
self.assertFalse(after["block"])
self.assertEqual(len(wsg.workflow_failure_ledger()), 1)
class TestMonkeypatchCannotNoopFullPath(unittest.TestCase):
def tearDown(self):
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
def test_patching_branches_only_still_blocks_dirty_root_scope(self):
"""Monkeypatching branches-only must not silence root diagnostic block."""
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
with patch.object(
mcp_server, "_enforce_branches_only_author_mutation", lambda *a, **k: None
):
with patch.object(
mcp_server, "_enforce_root_checkout_guard", lambda *a, **k: None
):
# Even if both legacy helpers are patched, issue-scope composition
# still sees dirty root source via assess_production_mutation_guards.
assessment = wsg.assess_production_mutation_guards(
workspace_path=CONTROL_ROOT,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M gitea_mcp_server.py\n",
role_kind="author",
in_test_mode=True,
)
self.assertTrue(assessment["block"])
self.assertEqual(
assessment["blocker_kind"], wsg.BLOCKER_ROOT_DIAGNOSTIC_EDIT
)
class TestRealEntrypointProductionGuard(unittest.TestCase):
"""Real mutation entrypoint: production guard before side effects (#683)."""
def setUp(self):
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
for key in ("GITEA_AUTHOR_WORKTREE", "GITEA_ACTIVE_WORKTREE"):
os.environ.pop(key, None)
self._orig_whoami = mcp_server._preflight_whoami_called
self._orig_cap = mcp_server._preflight_capability_called
mcp_server._preflight_whoami_called = False
mcp_server._preflight_capability_called = False
mcp_server._preflight_resolved_role = None
mcp_server._preflight_resolved_task = None
def tearDown(self):
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
for key in ("GITEA_AUTHOR_WORKTREE", "GITEA_ACTIVE_WORKTREE"):
os.environ.pop(key, None)
mcp_server._preflight_whoami_called = self._orig_whoami
mcp_server._preflight_capability_called = self._orig_cap
mcp_server._preflight_resolved_role = None
mcp_server._preflight_resolved_task = None
def test_comment_issue_blocks_dirty_root_before_api(self):
api_mock = MagicMock()
with patch.object(mcp_server, "api_request", api_mock), patch.object(
mcp_server,
"_actual_profile_role",
return_value="author",
), patch.object(
mcp_server,
"_effective_workspace_role",
return_value="author",
), patch.object(
mcp_server,
"get_profile",
return_value={
"profile_name": "prgs-author",
"allowed_operations": [
"gitea.issue.comment",
"gitea.read",
"gitea.pr.create",
"gitea.branch.push",
],
"forbidden_operations": [],
},
), patch.object(
issue_lock_worktree,
"read_worktree_git_state",
side_effect=lambda path, **kw: {
"current_branch": "master",
"porcelain_status": (
" M gitea_mcp_server.py\n"
if os.path.realpath(path) == os.path.realpath(CONTROL_ROOT)
or path == CONTROL_ROOT
else ""
),
"head_sha": "a" * 40,
"base_equivalent": True,
},
), patch.object(
mcp_server,
"_resolve_namespace_mutation_context",
return_value={
"workspace_path": CONTROL_ROOT,
"canonical_repo_root": CONTROL_ROOT,
"process_project_root": CONTROL_ROOT,
"workspace_role_kind": "author",
"workspace_binding_source": "process root",
"ignored_bindings": [],
},
), patch.object(
mcp_server,
"_resolve_author_mutation_context",
return_value={
"workspace_path": CONTROL_ROOT,
"canonical_repo_root": CONTROL_ROOT,
"process_project_root": CONTROL_ROOT,
"roots_aligned": True,
},
), patch.object(
mcp_server,
"_session_locked_issue_number",
return_value=None,
):
result = mcp_server.gitea_create_issue_comment(
issue_number=683,
body="diagnostic note",
remote="prgs",
org="Scaled-Tech-Consulting",
repo="Gitea-Tools",
worktree_path=CONTROL_ROOT,
)
api_mock.assert_not_called()
self.assertFalse(result.get("success"))
self.assertFalse(result.get("performed"))
self.assertIn(result.get("blocker_kind"), wsg.BLOCKER_KINDS)
self.assertTrue(result.get("exact_next_action"))
self.assertTrue(result.get("reasons"))
def test_comment_issue_succeeds_structure_after_worktree_bind(self):
"""Same-issue isolated worktree is not blocked by root diagnostic path."""
wt = f"{CONTROL_ROOT}/branches/issue-683-workflow-guard-hardening"
os.environ["GITEA_AUTHOR_WORKTREE"] = wt
assessment = wsg.assess_production_mutation_guards(
workspace_path=wt,
canonical_repo_root=CONTROL_ROOT,
porcelain_status=" M workflow_scope_guard.py\n",
current_branch="fix/issue-683-workflow-guard-hardening",
locked_issue_number=683,
target_issue_number=683,
role_kind="author",
require_author_lock=True,
in_test_mode=True,
)
self.assertFalse(assessment["block"], assessment)
class TestVerifyPreflightForceOn(unittest.TestCase):
def tearDown(self):
os.environ.pop(wsg.FORCE_PRODUCTION_GUARDS_ENV, None)
for key in ("GITEA_AUTHOR_WORKTREE", "GITEA_ACTIVE_WORKTREE"):
os.environ.pop(key, None)
def test_force_on_runs_production_guards_under_pytest(self):
os.environ[wsg.FORCE_PRODUCTION_GUARDS_ENV] = "1"
called = {"root": 0, "branches": 0, "scope": 0}
def _root(*a, **k):
called["root"] += 1
def _branches(*a, **k):
called["branches"] += 1
def _scope(*a, **k):
called["scope"] += 1
with patch.object(mcp_server, "_enforce_root_checkout_guard", _root), patch.object(
mcp_server, "_enforce_branches_only_author_mutation", _branches
), patch.object(mcp_server, "_enforce_issue_scope_guard", _scope):
# No whoami/capability — purity-order skipped; production still runs.
mcp_server.verify_preflight_purity(task="comment_issue")
self.assertEqual(called["root"], 1)
self.assertEqual(called["branches"], 1)
self.assertEqual(called["scope"], 1)
def test_without_force_on_pytest_skips_production_only_for_unit_isolation(self):
called = {"root": 0}
def _root(*a, **k):
called["root"] += 1
with patch.object(mcp_server, "_enforce_root_checkout_guard", _root), patch.object(
mcp_server, "_enforce_branches_only_author_mutation", lambda *a, **k: None
), patch.object(mcp_server, "_enforce_issue_scope_guard", lambda *a, **k: None):
mcp_server.verify_preflight_purity(task="comment_issue")
self.assertEqual(called["root"], 0)
if __name__ == "__main__":
unittest.main()
@@ -1,599 +0,0 @@
"""Guarded cleanup for obsolete comment-backed reviewer leases (#691).
Reproduces PR #688 lease comment 10749 class of defect: completed
REQUEST_CHANGES on head A, author pushes head B, foreign lease remains
pinned to A (and after expiry still has no non-owner cleanup path that
diagnosis can prescribe beyond indefinite wait).
"""
from __future__ import annotations
import sys
import unittest
from datetime import datetime, timedelta, timezone
from pathlib import Path
from unittest.mock import patch
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
import merger_lease_adoption as mla # noqa: E402
import reviewer_pr_lease as leases # noqa: E402
# PR #688 / comment 10749 reproduction fixtures
HEAD_A = "c7a444eb4b41cf916fdbd20a4999ffd78af496d0"
HEAD_B = "4a6357800364718a27a36ebc73578d4b929ff4aa"
SESSION_FOREIGN = "25883-7d4c6e6ebd53"
COMMENT_10749 = 10749
REPO = "Scaled-Tech-Consulting/Gitea-Tools"
PR = 688
ISSUE = 687
EXPIRES_10749 = "2026-07-13T04:23:00Z"
def _utc(dt: datetime) -> datetime:
return dt if dt.tzinfo else dt.replace(tzinfo=timezone.utc)
def _lease_comment(
*,
pr_number: int = PR,
session_id: str = SESSION_FOREIGN,
phase: str = "claimed",
candidate_head: str = HEAD_A,
comment_id: int = COMMENT_10749,
last_activity: datetime | None = None,
expires_at: datetime | None = None,
worktree: str = "branches/review-pr688-feat-issue-687-reconciler-branch-delete",
repo: str = REPO,
) -> dict:
now = last_activity or datetime.now(timezone.utc)
body = leases.format_lease_body(
repo=repo,
pr_number=pr_number,
issue_number=ISSUE,
reviewer_identity="sysadmin",
profile="prgs-reviewer",
session_id=session_id,
worktree=worktree,
phase=phase,
candidate_head=candidate_head,
target_branch="master",
target_branch_sha="b" * 40,
last_activity=now,
expires_at=expires_at,
)
return {
"id": comment_id,
"body": body,
"user": {"login": "sysadmin"},
"author": "sysadmin",
"created_at": now.isoformat(),
"updated_at": now.isoformat(),
}
def _reviews_for_head(head: str, verdict: str = "REQUEST_CHANGES") -> list[dict]:
return [
{
"verdict": verdict,
"reviewed_head_sha": head,
"dismissed": False,
"reviewer": "sysadmin",
}
]
def _assess(
comments,
*,
current_head=HEAD_B,
formal_reviews=None,
controller=True,
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
requesting_session="fresh-controller",
apply=False,
confirmation=None,
**kwargs,
):
return leases.assess_obsolete_reviewer_comment_lease_cleanup(
comments,
pr_number=PR,
current_head_sha=current_head,
formal_reviews=formal_reviews if formal_reviews is not None else _reviews_for_head(HEAD_A),
repo=REPO,
expected_repo=REPO,
requesting_session_id=requesting_session,
controller_recovery_authorized=controller,
worktree_exists=worktree_exists,
worktree_clean=worktree_clean,
worktree_has_unpreserved_work=not worktree_clean if worktree_exists else False,
owner_process_alive=owner_process_alive,
owner_pid_observed=kwargs.get("owner_pid_observed"),
requesting_pid=kwargs.get("requesting_pid", 99999),
current_head_review_in_progress=kwargs.get(
"current_head_review_in_progress", False
),
expected_lease_comment_id=kwargs.get("expected_lease_comment_id"),
expected_session_id=kwargs.get("expected_session_id"),
expected_leased_head=kwargs.get("expected_leased_head"),
confirmation=confirmation
if confirmation is not None
else (leases.cleanup_confirmation_for_pr(PR) if apply else ""),
apply=apply,
now=kwargs.get("now"),
)
class TestIssue691SupersededHeadCleanup(unittest.TestCase):
def setUp(self):
leases.clear_session_lease()
def test_1_request_changes_then_push_expired_cleanup_succeeds(self):
"""Completed REQUEST_CHANGES on A, push B, lease A expires → cleanup OK."""
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
last_activity=expires - timedelta(hours=2),
expires_at=expires,
)
result = _assess(
[claim],
formal_reviews=_reviews_for_head(HEAD_A, "REQUEST_CHANGES"),
now=now,
apply=True,
)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["classification"], "foreign_expired_superseded_head")
self.assertEqual(
result["exact_next_action"], leases.NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
)
self.assertIn("phase: released", result["release_body"])
self.assertIn("obsolete-superseded-or-expired-lease", result["release_body"])
self.assertIsNotNone(result["audit_comment_body"])
self.assertEqual(result["cleanup_tool"], leases.CLEANUP_OBSOLETE_LEASE_TOOL)
def test_2_approve_then_push_cleanup_policy(self):
"""Completed APPROVE on A, push B → cleanup eligible (completed superseded)."""
now = datetime(2026, 7, 13, 1, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc) # not yet expired
claim = _lease_comment(
last_activity=now - timedelta(minutes=10),
expires_at=expires,
)
result = _assess(
[claim],
formal_reviews=_reviews_for_head(HEAD_A, "APPROVED"),
now=now,
)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["classification"], "foreign_completed_superseded_head")
def test_3_active_current_head_cleanup_denied(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=5),
expires_at=now + timedelta(hours=2),
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_B, "REQUEST_CHANGES"),
now=now,
)
self.assertFalse(result["cleanup_allowed"])
self.assertEqual(result["classification"], "foreign_active_current_head")
def test_4_foreign_owner_recent_progress_denied(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=2),
expires_at=now + timedelta(hours=2),
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=[],
owner_process_alive=True,
now=now,
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(
any("recent authenticated progress" in r for r in result["reasons"])
or any("current PR head" in r for r in result["reasons"])
)
def test_5_owner_absent_worktree_dirty_denied(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=expires - timedelta(hours=1),
expires_at=expires,
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=[],
worktree_clean=False,
owner_process_alive=False,
now=now,
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(any("dirty" in r for r in result["reasons"]))
def test_6_owner_absent_worktree_clean_orphan_ok(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=expires - timedelta(hours=1),
expires_at=expires,
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=[],
worktree_clean=True,
owner_process_alive=False,
now=now,
)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["classification"], "orphaned_owner_missing")
def test_7_pid_reuse_not_ownership(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess(
[claim],
now=now,
owner_pid_observed=4242,
requesting_pid=4242,
)
self.assertTrue(
any("PID equality" in r or "NOT ownership" in r for r in result["reasons"])
or result["owner_session_evidence"]["pid_is_not_ownership_proof"]
)
# Still eligible via superseded+terminal+expired despite matching PID.
self.assertTrue(result["cleanup_allowed"], result["reasons"])
def test_8_comment_backed_no_db_lease_id(self):
"""Cleanup uses comment ledger only — no control-plane lease_id required."""
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
# Explicitly no lease_id field anywhere.
self.assertNotIn("lease_id", claim)
result = _assess([claim], now=now)
self.assertTrue(result["cleanup_allowed"], result["reasons"])
self.assertEqual(result["active_lease"]["comment_id"], COMMENT_10749)
self.assertIsNone(result["active_lease"].get("lease_id"))
def test_9_cleanup_posts_durable_audit_bodies(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], now=now, apply=True)
self.assertTrue(result["cleanup_allowed"])
self.assertIn("#691", result["audit_comment_body"])
self.assertIn(str(COMMENT_10749), result["audit_comment_body"])
self.assertIn(HEAD_A, result["audit_comment_body"])
self.assertIn(HEAD_B, result["audit_comment_body"])
def test_10_fresh_acquire_after_cleanup_marker(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(
expires_at=expires,
last_activity=expires - timedelta(hours=1),
comment_id=COMMENT_10749,
)
assessed = _assess([claim], now=now, apply=True)
self.assertTrue(assessed["cleanup_allowed"])
release = {
"id": 99999,
"body": assessed["release_body"],
"user": {"login": "sysadmin"},
}
# Newest terminal marker ends active lease.
active = leases.find_active_reviewer_lease(
[claim, release], pr_number=PR, now=now
)
self.assertIsNone(active)
acq = leases.assess_acquire_lease(
[claim, release],
pr_number=PR,
reviewer_identity="sysadmin",
profile="prgs-reviewer",
session_id="fresh-reviewer-1",
repo=REPO,
issue_number=ISSUE,
worktree="branches/review-pr-688-fresh",
candidate_head=HEAD_B,
target_branch="master",
target_branch_sha="b" * 40,
now=now,
)
self.assertTrue(acq["acquire_allowed"], acq["reasons"])
def test_11_no_validation_state_transfer(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], now=now, apply=True)
self.assertTrue(result["cleanup_allowed"])
# Release body keeps old candidate_head (no repoint).
self.assertIn(f"candidate_head: {HEAD_A}", result["release_body"])
self.assertNotIn(HEAD_B, result["release_body"].split("candidate_head:")[1].split("\n")[0])
self.assertIn("did not transfer validation", result["audit_comment_body"])
self.assertIn("did not repoint", result["audit_comment_body"])
# Session lease must remain unset by assessment (tool never seeds).
self.assertIsNone(leases.get_session_lease())
def test_12_repeated_cleanup_idempotent(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
first = _assess([claim], now=now, apply=True)
self.assertTrue(first["cleanup_allowed"])
release = {"id": 100001, "body": first["release_body"], "user": {"login": "x"}}
second = _assess([claim, release], now=now, apply=True)
self.assertFalse(second["cleanup_allowed"])
self.assertEqual(second["classification"], "no_lease")
def test_13_malformed_expiry_fails_closed(self):
claim = _lease_comment()
# Corrupt expires_at in the body.
claim["body"] = claim["body"].replace(
claim["body"].split("expires_at:")[1].split("\n")[0].strip(),
"not-a-timestamp",
)
result = _assess([claim], formal_reviews=_reviews_for_head(HEAD_A))
self.assertFalse(result["cleanup_allowed"])
self.assertFalse(result["expires_parseable"])
self.assertTrue(any("expires_at" in r for r in result["reasons"]))
def test_14_wrong_identity_evidence_fails_closed(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
bad_repo = _assess(
[claim],
now=now,
# force repo mismatch via expected_repo
)
# Patch via direct call with wrong expected_repo
bad = leases.assess_obsolete_reviewer_comment_lease_cleanup(
[claim],
pr_number=PR,
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A),
expected_repo="Other-Org/Other-Repo",
requesting_session_id="fresh",
controller_recovery_authorized=True,
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
now=now,
)
self.assertFalse(bad["cleanup_allowed"])
self.assertTrue(any("repository identity" in r for r in bad["reasons"]))
bad_pr = leases.assess_obsolete_reviewer_comment_lease_cleanup(
[claim],
pr_number=999,
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A),
expected_repo=REPO,
requesting_session_id="fresh",
controller_recovery_authorized=True,
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
expected_lease_comment_id=COMMENT_10749,
now=now,
)
self.assertFalse(bad_pr["cleanup_allowed"])
bad_head = _assess(
[claim],
now=now,
expected_leased_head="0" * 40,
)
self.assertFalse(bad_head["cleanup_allowed"])
bad_session = _assess(
[claim],
now=now,
expected_session_id="wrong-session",
)
self.assertFalse(bad_session["cleanup_allowed"])
def test_15_current_head_active_cannot_be_displaced(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=1),
expires_at=now + timedelta(hours=2),
)
result = _assess(
[claim],
current_head=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_B),
now=now,
current_head_review_in_progress=True,
)
self.assertFalse(result["cleanup_allowed"])
# Acquire also blocked by foreign active lease.
acq = leases.assess_acquire_lease(
[claim],
pr_number=PR,
reviewer_identity="other",
profile="prgs-reviewer",
session_id="thief",
repo=REPO,
issue_number=ISSUE,
worktree="branches/steal",
candidate_head=HEAD_B,
target_branch="master",
target_branch_sha="b" * 40,
now=now,
)
self.assertFalse(acq["acquire_allowed"])
def test_regression_pr688_comment_10749_after_expiry(self):
"""Exact 10749 reproduction after recorded expires_at 2026-07-13T04:23:00Z."""
now = datetime(2026, 7, 13, 4, 30, 0, tzinfo=timezone.utc)
expires = datetime.fromisoformat(EXPIRES_10749.replace("Z", "+00:00"))
claim = _lease_comment(
session_id=SESSION_FOREIGN,
candidate_head=HEAD_A,
comment_id=COMMENT_10749,
last_activity=expires - timedelta(hours=2),
expires_at=expires,
)
# Diagnosis must not prescribe indefinite wait-only for this case.
diag = leases.diagnose_reviewer_pr_lease_handoff(
[claim],
pr_number=PR,
current_session_id="fresh-reviewer",
current_reviewer_identity="sysadmin",
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A, "REQUEST_CHANGES"),
worktree_exists=True,
worktree_clean=True,
owner_process_alive=False,
instructed_session_id=SESSION_FOREIGN,
instructed_comment_id=COMMENT_10749,
now=now,
)
self.assertEqual(diag["classification"], "foreign_expired_superseded_head")
self.assertEqual(
diag["next_action"], leases.NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
)
self.assertEqual(diag["cleanup_tool"], leases.CLEANUP_OBSOLETE_LEASE_TOOL)
self.assertIn("CLEANUP OBSOLETE REVIEWER LEASE 688", diag["required_confirmation"])
self.assertEqual(diag["mutation_eligibility"], "cleanup_only")
self.assertFalse(diag["mutation_allowed"])
# Assessment still returns the lease as active/stale class of block for acquire
# when unexpired path... here it's expired so find_active is None; acquire free
# only after cleanup if somehow still active. With expired, find_active is None:
active = leases.find_active_reviewer_lease([claim], pr_number=PR, now=now)
self.assertIsNone(active)
# But superseded unexpired still blocks acquire and diagnosis points to cleanup:
unexpired_now = datetime(2026, 7, 13, 1, 0, 0, tzinfo=timezone.utc)
claim2 = _lease_comment(
session_id=SESSION_FOREIGN,
candidate_head=HEAD_A,
comment_id=COMMENT_10749,
last_activity=unexpired_now - timedelta(minutes=45),
expires_at=expires,
)
active2 = leases.find_active_reviewer_lease(
[claim2], pr_number=PR, now=unexpired_now
)
self.assertIsNotNone(active2)
self.assertEqual(active2["freshness"], "stale_warning")
diag2 = leases.diagnose_reviewer_pr_lease_handoff(
[claim2],
pr_number=PR,
current_session_id="fresh-reviewer",
current_reviewer_identity="sysadmin",
current_head_sha=HEAD_B,
formal_reviews=_reviews_for_head(HEAD_A, "REQUEST_CHANGES"),
worktree_exists=True,
worktree_clean=True,
now=unexpired_now,
)
self.assertEqual(diag2["classification"], "foreign_completed_superseded_head")
self.assertEqual(
diag2["next_action"], leases.NEXT_ACTION_CLEANUP_OBSOLETE_LEASE
)
acq = leases.assess_acquire_lease(
[claim2],
pr_number=PR,
reviewer_identity="sysadmin",
profile="prgs-reviewer",
session_id="fresh-reviewer",
repo=REPO,
issue_number=ISSUE,
worktree="branches/review-pr-688-new",
candidate_head=HEAD_B,
target_branch="master",
target_branch_sha="b" * 40,
now=unexpired_now,
)
self.assertFalse(acq["acquire_allowed"])
def test_missing_controller_auth_denied(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], controller=False, now=now)
self.assertFalse(result["cleanup_allowed"])
def test_wrong_confirmation_denied_on_apply(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess(
[claim], now=now, apply=True, confirmation="MERGE PR 688"
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(any("confirmation" in r for r in result["reasons"]))
def test_owner_session_must_use_owner_release(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess(
[claim],
now=now,
requesting_session=SESSION_FOREIGN,
)
self.assertFalse(result["cleanup_allowed"])
self.assertTrue(any("owns the lease" in r for r in result["reasons"]))
def test_superseded_without_terminal_review_denied(self):
now = datetime(2026, 7, 13, 5, 0, 0, tzinfo=timezone.utc)
expires = datetime(2026, 7, 13, 4, 23, 0, tzinfo=timezone.utc)
claim = _lease_comment(expires_at=expires, last_activity=expires - timedelta(hours=1))
result = _assess([claim], formal_reviews=[], now=now)
self.assertFalse(result["cleanup_allowed"])
self.assertEqual(result["classification"], "ambiguous_conflicting_evidence")
class TestIssue691DiagnoseClassifications(unittest.TestCase):
def setUp(self):
leases.clear_session_lease()
def test_foreign_active_current_head_still_wait(self):
now = datetime.now(timezone.utc)
claim = _lease_comment(
candidate_head=HEAD_B,
last_activity=now - timedelta(minutes=5),
expires_at=now + timedelta(hours=1),
)
claim["id"] = 1
result = leases.diagnose_reviewer_pr_lease_handoff(
[claim],
pr_number=PR,
current_session_id="other",
current_reviewer_identity="sysadmin",
current_head_sha=HEAD_B,
formal_reviews=[],
now=now,
)
self.assertEqual(result["classification"], "foreign_active_current_head")
self.assertEqual(result["next_action"], leases.NEXT_ACTION_WAIT)
self.assertFalse(result["mutation_allowed"])
if __name__ == "__main__":
unittest.main()
@@ -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()
+6 -27
View File
@@ -108,24 +108,13 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
"gitea_mcp_server.issue_lock_worktree.read_worktree_git_state",
side_effect=self._git_state(valid_worktree),
):
try:
res = srv.gitea_create_issue_comment(
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue_comment(
issue_number=557,
body="evidence comment",
remote="prgs",
)
except RuntimeError as exc:
self.assertIn("stable control checkout", str(exc))
else:
# #683 typed blocker at mutation entrypoint
self.assertFalse(res.get("success"))
self.assertFalse(res.get("performed"))
blob = " ".join(res.get("reasons") or [])
self.assertTrue(
"stable control checkout" in blob
or res.get("blocker_kind")
)
self.assertTrue(res.get("exact_next_action") or res.get("reasons"))
self.assertIn("stable control checkout", str(ctx.exception))
mock_api.assert_not_called()
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
@@ -195,24 +184,14 @@ class TestIssueCommentWorkspaceGuard(unittest.TestCase):
side_effect=self._subprocess(valid_worktree, outside_worktree),
):
with patch.dict(os.environ, self.AUTHOR_ENV, clear=True):
try:
res = srv.gitea_create_issue_comment(
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue_comment(
issue_number=557,
body="evidence comment",
remote="prgs",
worktree_path=outside_worktree,
)
except RuntimeError as exc:
self.assertIn(
"does not belong to the target repository",
str(exc),
)
else:
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or [])
self.assertIn(
"does not belong to the target repository", blob
)
self.assertIn("does not belong to the target repository", str(ctx.exception))
mock_api.assert_not_called()
@patch("gitea_mcp_server._auth", return_value=FAKE_AUTH)
+6 -24
View File
@@ -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(
+11 -7
View File
@@ -2,6 +2,7 @@
import os
import unittest
from unittest.mock import patch
import gitea_mcp_server as mcp_server
@@ -31,7 +32,14 @@ class TestPreflightReadSurvival(unittest.TestCase):
mcp_server._preflight_whoami_baseline_porcelain = None
mcp_server._preflight_capability_baseline_porcelain = None
self.author_guard_patch = patch("gitea_mcp_server._enforce_branches_only_author_mutation")
self.author_guard_patch.start()
self.root_guard_patch = patch("gitea_mcp_server._enforce_root_checkout_guard")
self.root_guard_patch.start()
def tearDown(self):
self.root_guard_patch.stop()
self.author_guard_patch.stop()
mcp_server._preflight_whoami_called = self.orig_whoami
mcp_server._preflight_capability_called = self.orig_capability
mcp_server._preflight_whoami_violation = self.orig_whoami_violation
@@ -76,17 +84,13 @@ class TestPreflightReadSurvival(unittest.TestCase):
self.assertIn("task mismatch", str(ctx.exception))
def test_capability_consumed_after_mutation_gate(self):
# Use reconciler/close_pr so this purity-order test does not require a
# branches/ worktree (author create_issue would hit #274/#683 guards).
# Test isolation stays explicit; production author guards remain live
# under force-on (see tests/test_issue_683_workflow_scope_guards.py).
mcp_server.record_preflight_check("whoami")
mcp_server.record_preflight_check(
"capability", resolved_role="reconciler", resolved_task="close_pr"
"capability", resolved_role="author", resolved_task="create_issue"
)
mcp_server.verify_preflight_purity(task="close_pr")
mcp_server.verify_preflight_purity(task="create_issue")
with self.assertRaises(RuntimeError) as ctx:
mcp_server.verify_preflight_purity(task="close_pr")
mcp_server.verify_preflight_purity(task="create_issue")
self.assertIn("has not been resolved", str(ctx.exception))
def test_whoami_recovery_after_violation_clears_capability(self):
+3 -15
View File
@@ -86,21 +86,9 @@ class TestReconcilerCloseWorkspaceGuard(unittest.TestCase):
):
srv._preflight_resolved_role = "author"
with patch.object(srv, "PROJECT_ROOT", CONTROL_CHECKOUT_ROOT):
try:
res = srv.gitea_create_issue(title="Test", body="body")
except RuntimeError as exc:
self.assertIn("stable control checkout", str(exc))
else:
# #683 typed blocker at mutation entrypoint
self.assertFalse(res.get("success"))
blob = " ".join(res.get("reasons") or []) + str(
res.get("blocker_kind") or ""
)
self.assertTrue(
"stable control checkout" in blob
or "missing_issue_worktree" in blob
or "control checkout" in blob.lower()
)
with self.assertRaises(RuntimeError) as ctx:
srv.gitea_create_issue(title="Test", body="body")
self.assertIn("stable control checkout", str(ctx.exception))
if __name__ == "__main__":
@@ -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"),
[],
)
# --------------------------------------------------------------------------- #
+22 -54
View File
@@ -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 {
-626
View File
@@ -1,626 +0,0 @@
"""Workflow scope ownership and production-guard hardening (#683).
Implements fail-closed enforcement so sessions cannot:
* mutate source/tests on the root/control checkout (including temporary
diagnostic edits) without binding an issue-backed ``branches/`` worktree;
* continue out-of-scope source work while locked to a different issue;
* disable, skip, or conceal production root/branches/porcelain guards solely
because pytest/unittest is loaded.
This module is pure assessment + small durable ledger helpers. Callers gather
live facts (lock, branch, porcelain, worktree path) and pass them in. Existing
root_checkout_guard / author_mutation_worktree assessors remain authoritative;
this module composes typed blockers with exact recovery actions.
Do **not** reintroduce the rejected #681 / ``300a4ca`` patterns:
* early-return from workspace verification under ``_preflight_in_test_mode()``
* porcelain filtering that strips ``*.py`` lines under pytest
"""
from __future__ import annotations
import os
import re
import threading
from typing import Any
import author_mutation_worktree
from reviewer_worktree import parse_dirty_tracked_files
# ── force-on / test isolation ────────────────────────────────────────────────
# When set, production root/branches/scope guards MUST run even under pytest.
# Unit tests that only need preflight-order isolation leave this unset and
# use GITEA_TEST_PORCELAIN / fixtures; real-entrypoint proof sets this to "1".
FORCE_PRODUCTION_GUARDS_ENV = "GITEA_TEST_FORCE_PRODUCTION_GUARDS"
# Existing force signals also mean "exercise production dirtiness paths".
_FORCE_DIRTY_ENV = "GITEA_TEST_FORCE_DIRTY"
_FORCE_PORCELAIN_ENV = "GITEA_TEST_PORCELAIN"
# ── typed blocker kinds ──────────────────────────────────────────────────────
BLOCKER_ROOT_DIAGNOSTIC_EDIT = "root_diagnostic_edit"
BLOCKER_MISSING_ISSUE_SCOPE = "missing_issue_scope"
BLOCKER_OUT_OF_SCOPE_ISSUE = "out_of_scope_issue"
BLOCKER_MISSING_WORKTREE = "missing_issue_worktree"
BLOCKER_UNRECORDED_FAILURE = "unrecorded_workflow_failure"
BLOCKER_PRODUCTION_GUARD = "production_guard_violation"
BLOCKER_KINDS = frozenset(
{
BLOCKER_ROOT_DIAGNOSTIC_EDIT,
BLOCKER_MISSING_ISSUE_SCOPE,
BLOCKER_OUT_OF_SCOPE_ISSUE,
BLOCKER_MISSING_WORKTREE,
BLOCKER_UNRECORDED_FAILURE,
BLOCKER_PRODUCTION_GUARD,
}
)
_NEXT_ACTIONS: dict[str, str] = {
BLOCKER_ROOT_DIAGNOSTIC_EDIT: (
"Stop editing the control/root checkout. Preserve or discard root WIP "
"durably, restore root to clean master, lock or create the owning issue, "
"bind branches/issue-<N>-*, set GITEA_AUTHOR_WORKTREE to that worktree, "
"then re-run the mutation."
),
BLOCKER_MISSING_ISSUE_SCOPE: (
"Select or create the owning Gitea issue, claim/lock it "
"(gitea_mark_issue + gitea_lock_issue), bind branches/issue-<N>-* "
"from clean master, then re-run the mutation from that worktree."
),
BLOCKER_OUT_OF_SCOPE_ISSUE: (
"Stop. The active issue lock does not own this work. Release or finish "
"the current issue lease, then select/create and lock the correct "
"owning issue, bind its branches/issue-<N>-* worktree, and re-run."
),
BLOCKER_MISSING_WORKTREE: (
"Bind an issue-backed worktree under branches/ (scripts/worktree-start "
"or git worktree add branches/issue-<N>-*), set GITEA_AUTHOR_WORKTREE / "
"worktree_path to that path, keep the control checkout clean on master, "
"then re-run the mutation."
),
BLOCKER_UNRECORDED_FAILURE: (
"Record the workflow/tool failure durably first (issue comment or "
"workflow_scope_guard.record_workflow_failure), then continue only "
"inside the owning issue-backed worktree."
),
BLOCKER_PRODUCTION_GUARD: (
"Resolve the production guard violation: clean or isolate the control "
"checkout, bind the owning issue worktree under branches/, and re-run "
"with production guards active."
),
}
_ISSUE_IN_BRANCH_RE = re.compile(r"issue-(\d+)", re.IGNORECASE)
# In-process durable failure ledger (also written via optional sink callback).
_ledger_lock = threading.Lock()
_failure_ledger: list[dict[str, Any]] = []
class ProductionGuardError(RuntimeError):
"""Fail-closed production guard with typed blocker metadata (#683)."""
def __init__(
self,
message: str,
*,
blocker_kind: str,
exact_next_action: str | None = None,
reasons: list[str] | None = None,
details: dict[str, Any] | None = None,
) -> None:
super().__init__(message)
kind = (blocker_kind or "").strip()
if kind not in BLOCKER_KINDS:
kind = BLOCKER_PRODUCTION_GUARD
self.blocker_kind = kind
self.exact_next_action = (
(exact_next_action or "").strip() or _NEXT_ACTIONS[kind]
)
self.reasons = list(reasons or [message])
self.details = dict(details or {})
def production_guards_forced() -> bool:
"""True when the explicit #683 force-on flag requests production guards."""
return (os.environ.get(FORCE_PRODUCTION_GUARDS_ENV) or "").strip().lower() in {
"1",
"true",
"yes",
"on",
}
def purity_order_forced() -> bool:
"""True when tests force preflight-order dirtiness paths (legacy flags)."""
if os.environ.get(_FORCE_DIRTY_ENV):
return True
# GITEA_TEST_PORCELAIN present (even empty) means dirtiness paths are live.
if os.environ.get(_FORCE_PORCELAIN_ENV) is not None:
return True
return False
def production_guards_active(*, in_test_mode: bool) -> bool:
"""Whether production root/branches/scope guards must execute.
Production (non-test) always active. Under pytest, active when either the
explicit #683 force-on flag or legacy dirty/porcelain force signals are
set never skip production enforcement solely because tests are running
when force-on is requested.
"""
if production_guards_forced() or purity_order_forced():
return True
return not bool(in_test_mode)
def extract_issue_number_from_branch(branch_name: str | None) -> int | None:
"""Return the first issue-N number embedded in a branch name, if any."""
text = (branch_name or "").strip()
if not text:
return None
match = _ISSUE_IN_BRANCH_RE.search(text)
if not match:
return None
try:
return int(match.group(1))
except ValueError:
return None
def is_source_or_test_path(path: str) -> bool:
"""True for tracked source/test paths that must not land as root WIP."""
p = (path or "").replace("\\", "/").lstrip("./")
if not p:
return False
if p.startswith("tests/") or "/tests/" in f"/{p}":
return True
if p.endswith((".py", ".pyi", ".toml", ".cfg", ".ini", ".sh")):
return True
if p in {"requirements.txt", "pyproject.toml", "setup.py", "setup.cfg"}:
return True
return False
def dirty_source_files(porcelain_status: str) -> list[str]:
"""Tracked dirty paths that count as source/test contamination."""
dirty = parse_dirty_tracked_files(porcelain_status or "")
return [p for p in dirty if is_source_or_test_path(p)]
def assess_issue_scope_ownership(
*,
locked_issue_number: int | None,
target_issue_number: int | None = None,
branch_name: str | None = None,
role_kind: str | None = None,
require_lock_for_author: bool = False,
) -> dict[str, Any]:
"""Fail closed when the session issue lock does not own the attempted work.
* Author sessions that require a lock fail when none is held.
* When a lock exists, the target issue (tool argument) and/or the issue
number embedded in the branch must match the locked issue.
* Reviewer/merger/reconciler roles are not issue-scope owners of author
implementation work and skip the author lock requirement.
"""
role = (role_kind or "").strip().lower()
locked = locked_issue_number
if isinstance(locked, str) and locked.isdigit():
locked = int(locked)
if locked is not None:
try:
locked = int(locked)
except (TypeError, ValueError):
locked = None
target = target_issue_number
if target is not None:
try:
target = int(target)
except (TypeError, ValueError):
target = None
branch_issue = extract_issue_number_from_branch(branch_name)
reasons: list[str] = []
blocker_kind: str | None = None
# Non-author roles do not take author issue locks for implementation.
if role in {"reviewer", "merger", "reconciler"}:
return _scope_ok(locked, target, branch_issue)
if require_lock_for_author and locked is None:
reasons.append(
"no owning issue lock is bound for this author session; "
"source/test mutation requires selecting or creating an owning issue first"
)
blocker_kind = BLOCKER_MISSING_ISSUE_SCOPE
if locked is not None and target is not None and locked != target:
reasons.append(
f"session is locked to issue #{locked} but mutation targets issue "
f"#{target}; out-of-scope until the owning issue is selected"
)
blocker_kind = BLOCKER_OUT_OF_SCOPE_ISSUE
if locked is not None and branch_issue is not None and locked != branch_issue:
reasons.append(
f"session is locked to issue #{locked} but workspace branch is for "
f"issue #{branch_issue}; bind the matching issue-backed worktree"
)
blocker_kind = BLOCKER_OUT_OF_SCOPE_ISSUE
if reasons:
kind = blocker_kind or BLOCKER_MISSING_ISSUE_SCOPE
return {
"proven": False,
"block": True,
"blocker_kind": kind,
"exact_next_action": _NEXT_ACTIONS[kind],
"reasons": reasons,
"locked_issue_number": locked,
"target_issue_number": target,
"branch_issue_number": branch_issue,
}
return _scope_ok(locked, target, branch_issue)
def assess_root_source_mutation(
*,
workspace_path: str,
canonical_repo_root: str,
porcelain_status: str,
current_branch: str | None = None,
locked_issue_number: int | None = None,
role_kind: str | None = None,
) -> dict[str, Any]:
"""Fail closed for diagnostic/source edits on the control/root checkout.
Allowed only when the active workspace is under ``branches/``. Dirty
tracked source/test files on the control checkout always block, including
temporary/diagnostic/test-only intent.
"""
role = (role_kind or "").strip().lower()
if role == "reconciler":
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"dirty_source_files": [],
}
root = os.path.realpath(canonical_repo_root or "")
workspace = os.path.realpath(workspace_path or root or ".")
under_branches = author_mutation_worktree.is_path_under_branches(workspace, root)
dirty_src = dirty_source_files(porcelain_status)
reasons: list[str] = []
blocker_kind: str | None = None
if not under_branches and workspace == root and dirty_src:
# Root workspace with source dirtiness is unattributed root WIP.
# (Clean-root author binding is enforced by branches-only #274.)
reasons.append(
"control/root checkout has tracked source or test edits "
f"(dirty files: {', '.join(dirty_src)}); diagnostic or temporary "
"edits on the root checkout are forbidden"
)
blocker_kind = BLOCKER_ROOT_DIAGNOSTIC_EDIT
if (
not under_branches
and workspace == root
and not dirty_src
and role == "author"
):
# Explicit missing-worktree signal for force-on author entrypoints.
reasons.append(
"author source/test mutation from the stable control checkout is "
"forbidden; bind an issue-backed worktree under branches/ first"
)
blocker_kind = BLOCKER_MISSING_WORKTREE
if reasons:
kind = blocker_kind or BLOCKER_ROOT_DIAGNOSTIC_EDIT
return {
"proven": False,
"block": True,
"blocker_kind": kind,
"exact_next_action": _NEXT_ACTIONS[kind],
"reasons": reasons,
"dirty_source_files": dirty_src,
"workspace_path": workspace,
"canonical_repo_root": root,
"under_branches": under_branches,
"locked_issue_number": locked_issue_number,
}
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"dirty_source_files": dirty_src,
"workspace_path": workspace,
"canonical_repo_root": root,
"under_branches": under_branches,
"locked_issue_number": locked_issue_number,
}
def assess_production_mutation_guards(
*,
workspace_path: str,
canonical_repo_root: str,
porcelain_status: str,
current_branch: str | None = None,
locked_issue_number: int | None = None,
target_issue_number: int | None = None,
role_kind: str | None = None,
require_author_lock: bool = False,
in_test_mode: bool = False,
) -> dict[str, Any]:
"""Compose root + scope production guards when they must be active (#683)."""
if not production_guards_active(in_test_mode=in_test_mode):
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"skipped": True,
"skip_reason": "production guards not active (test isolation without force-on)",
}
root_assess = assess_root_source_mutation(
workspace_path=workspace_path,
canonical_repo_root=canonical_repo_root,
porcelain_status=porcelain_status,
current_branch=current_branch,
locked_issue_number=locked_issue_number,
role_kind=role_kind,
)
if root_assess["block"]:
return {**root_assess, "skipped": False}
scope_assess = assess_issue_scope_ownership(
locked_issue_number=locked_issue_number,
target_issue_number=target_issue_number,
branch_name=current_branch,
role_kind=role_kind,
require_lock_for_author=require_author_lock,
)
if scope_assess["block"]:
return {**scope_assess, "skipped": False}
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"skipped": False,
"root": root_assess,
"scope": scope_assess,
}
def raise_if_blocked(assessment: dict[str, Any]) -> None:
"""Raise :class:`ProductionGuardError` when *assessment* blocks."""
if not assessment or not assessment.get("block"):
return
kind = assessment.get("blocker_kind") or BLOCKER_PRODUCTION_GUARD
reasons = list(assessment.get("reasons") or ["production guard violation"])
message = (
f"Workflow scope guard (#683) [{kind}]: {'; '.join(reasons)}. "
f"exact_next_action: {assessment.get('exact_next_action') or _NEXT_ACTIONS.get(kind, '')}"
)
raise ProductionGuardError(
message,
blocker_kind=kind,
exact_next_action=assessment.get("exact_next_action"),
reasons=reasons,
details={
k: v
for k, v in assessment.items()
if k
not in {
"proven",
"block",
"blocker_kind",
"exact_next_action",
"reasons",
}
},
)
def block_response(
assessment: dict[str, Any] | ProductionGuardError | None = None,
*,
blocker_kind: str | None = None,
reasons: list[str] | None = None,
exact_next_action: str | None = None,
**extra: Any,
) -> dict[str, Any]:
"""Structured fail-closed tool response with typed blocker fields."""
if isinstance(assessment, ProductionGuardError):
kind = assessment.blocker_kind
reason_list = list(assessment.reasons)
next_action = assessment.exact_next_action
extra = {**assessment.details, **extra}
elif isinstance(assessment, dict) and assessment.get("block"):
kind = assessment.get("blocker_kind") or BLOCKER_PRODUCTION_GUARD
reason_list = list(assessment.get("reasons") or [])
next_action = assessment.get("exact_next_action") or _NEXT_ACTIONS.get(
kind, _NEXT_ACTIONS[BLOCKER_PRODUCTION_GUARD]
)
else:
kind = (blocker_kind or BLOCKER_PRODUCTION_GUARD).strip()
if kind not in BLOCKER_KINDS:
kind = BLOCKER_PRODUCTION_GUARD
reason_list = list(reasons or ["production guard violation"])
next_action = exact_next_action or _NEXT_ACTIONS[kind]
if kind not in BLOCKER_KINDS:
kind = BLOCKER_PRODUCTION_GUARD
if not reason_list:
reason_list = ["production guard violation"]
next_action = (next_action or "").strip() or _NEXT_ACTIONS[kind]
out: dict[str, Any] = {
"success": False,
"performed": False,
"blocker_kind": kind,
"exact_next_action": next_action,
"reasons": reason_list,
}
for key, value in extra.items():
if key not in out and value is not None:
out[key] = value
return out
def format_production_guard_error(assessment: dict[str, Any]) -> str:
"""Single RuntimeError string carrying kind + exact next action."""
kind = assessment.get("blocker_kind") or BLOCKER_PRODUCTION_GUARD
reasons = "; ".join(assessment.get("reasons") or ["production guard violation"])
next_action = assessment.get("exact_next_action") or _NEXT_ACTIONS.get(
kind, _NEXT_ACTIONS[BLOCKER_PRODUCTION_GUARD]
)
return (
f"Workflow scope guard (#683) [{kind}]: {reasons}. "
f"exact_next_action: {next_action}"
)
# ── durable failure recording ────────────────────────────────────────────────
def record_workflow_failure(
*,
kind: str,
detail: str,
issue_number: int | None = None,
task: str | None = None,
sink: Any | None = None,
) -> dict[str, Any]:
"""Record a workflow/tool failure before source edits continue (#683 AC8).
*sink* may be a callable ``sink(record)`` (e.g. tests) or omitted for the
in-process ledger only. Returns the durable record.
"""
record = {
"kind": (kind or "workflow_failure").strip() or "workflow_failure",
"detail": (detail or "").strip(),
"issue_number": issue_number,
"task": task,
"pid": os.getpid(),
}
with _ledger_lock:
_failure_ledger.append(dict(record))
if callable(sink):
sink(record)
return record
def clear_workflow_failure_ledger() -> None:
"""Test helper: reset the in-process failure ledger."""
with _ledger_lock:
_failure_ledger.clear()
def workflow_failure_ledger() -> list[dict[str, Any]]:
"""Copy of durable in-process failure records."""
with _ledger_lock:
return [dict(r) for r in _failure_ledger]
def assess_durable_failure_recorded(
*,
require_record: bool,
pending_source_mutation: bool,
) -> dict[str, Any]:
"""Block source mutation when a workflow failure was not recorded first."""
if not require_record or not pending_source_mutation:
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
}
with _ledger_lock:
has_record = bool(_failure_ledger)
if has_record:
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
}
return {
"proven": False,
"block": True,
"blocker_kind": BLOCKER_UNRECORDED_FAILURE,
"exact_next_action": _NEXT_ACTIONS[BLOCKER_UNRECORDED_FAILURE],
"reasons": [
"workflow/tool failure triggered a need for source changes but no "
"durable failure record exists yet"
],
}
def porcelain_preserves_python_paths(porcelain_status: str) -> bool:
"""Regression helper: dirty ``*.py`` lines must remain visible (#683)."""
text = porcelain_status or ""
for line in text.splitlines():
stripped = line.strip()
if stripped.endswith(".py") or ".py " in stripped or stripped.endswith(".py"):
# Any py path present proves no silent strip of all *.py lines.
if " M " in f" {stripped}" or stripped[:1] in "MADRCTU" or len(line) >= 4:
return True
# Empty porcelain is fine; integrity means we did not strip when present.
return ".py" not in text
def assert_no_pytest_porcelain_filter(source_text: str) -> list[str]:
"""Static check: production reader must not strip ``*.py`` under pytest."""
findings: list[str] = []
lowered = source_text or ""
if "endswith(\".py\")" in lowered or "endswith('.py')" in lowered:
if "pytest" in lowered and "porcelain" in lowered.lower():
findings.append(
"production porcelain reader must not filter *.py under pytest "
"(rejected 300a4ca pattern)"
)
if "if \"pytest\" in sys.modules" in lowered and "porcelain" in lowered.lower():
if ".py" in lowered and ("join" in lowered or "endswith" in lowered):
findings.append(
"test-mode porcelain filtering of source files is forbidden (#683)"
)
return findings
def _scope_ok(
locked: int | None,
target: int | None,
branch_issue: int | None,
) -> dict[str, Any]:
return {
"proven": True,
"block": False,
"blocker_kind": None,
"exact_next_action": "proceed",
"reasons": [],
"locked_issue_number": locked,
"target_issue_number": target,
"branch_issue_number": branch_issue,
}