Files
Gitea-Tools/issue_lock_store.py

1123 lines
39 KiB
Python

"""Keyed, persistent issue-lock storage (#443) with flock hardening (#438).
Replaces the single global ``/tmp/gitea_issue_lock.json`` slot with per-issue
lock files under ``GITEA_ISSUE_LOCK_DIR`` (default
``~/.cache/gitea-tools/issue-locks``). Each MCP session binds its active lock
via a per-process pointer file so concurrent repos/issues never clobber each
other. Acquisition is serialized per issue with ``fcntl.flock``.
"""
from __future__ import annotations
import errno
import fcntl
import json
import os
import re
import tempfile
from contextlib import contextmanager
from datetime import datetime, timedelta, timezone
from typing import Any
LOCK_DIR_ENV = "GITEA_ISSUE_LOCK_DIR"
DEFAULT_LOCK_DIR = os.path.expanduser("~/.cache/gitea-tools/issue-locks")
WORK_LEASE_TTL_HOURS = 4
AUTHOR_ISSUE_WORK_LEASE = "author_issue_work"
_SAFE_SEGMENT_RE = re.compile(r"[^A-Za-z0-9._+-]+")
class LockContentionError(RuntimeError):
"""Raised when an exclusive per-issue lock cannot be acquired."""
def default_lock_dir() -> str:
raw = (os.environ.get(LOCK_DIR_ENV) or DEFAULT_LOCK_DIR).strip()
return raw or DEFAULT_LOCK_DIR
def _sanitize_segment(value: str) -> str:
text = (value or "").strip()
if not text:
return "_"
return _SAFE_SEGMENT_RE.sub("_", text)
def lock_key(
*,
remote: str,
org: str,
repo: str,
issue_number: int,
) -> str:
return "-".join(
_sanitize_segment(part)
for part in (remote, org, repo, str(issue_number))
)
def lock_file_path(
*,
remote: str,
org: str,
repo: str,
issue_number: int,
lock_dir: str | None = None,
) -> str:
root = (lock_dir or default_lock_dir()).strip()
return os.path.join(root, f"{lock_key(remote=remote, org=org, repo=repo, issue_number=issue_number)}.json")
def session_pointer_path(lock_dir: str | None = None) -> str:
root = (lock_dir or default_lock_dir()).strip()
return os.path.join(root, f"session-{os.getpid()}.json")
def _ensure_lock_dir(lock_dir: str | None = None) -> str:
root = (lock_dir or default_lock_dir()).strip()
os.makedirs(root, mode=0o700, exist_ok=True)
return root
def flock_path(json_path: str) -> str:
return f"{json_path}.lock"
def is_process_alive(pid: int | None) -> bool:
if not pid or pid <= 0:
return False
try:
os.kill(int(pid), 0)
return True
except OSError as exc:
return exc.errno != errno.ESRCH
except (TypeError, ValueError):
return False
@contextmanager
def _exclusive_file_lock(lock_path: str):
os.makedirs(os.path.dirname(lock_path) or ".", exist_ok=True)
fd = os.open(lock_path, os.O_CREAT | os.O_RDWR, 0o600)
try:
try:
fcntl.flock(fd, fcntl.LOCK_EX | fcntl.LOCK_NB)
except BlockingIOError as exc:
raise LockContentionError(
f"could not acquire exclusive lock on '{lock_path}'"
) from exc
yield fd
finally:
try:
fcntl.flock(fd, fcntl.LOCK_UN)
finally:
os.close(fd)
def read_lock_file(path: str) -> dict[str, Any] | None:
lock_path = (path or "").strip()
if not lock_path or not os.path.exists(lock_path):
return None
try:
with open(lock_path, encoding="utf-8") as handle:
data = json.load(handle)
except (OSError, json.JSONDecodeError):
return None
return data if isinstance(data, dict) else None
def save_lock_file(path: str, data: dict[str, Any]) -> None:
lock_path = (path or "").strip()
if not lock_path:
raise ValueError("lock path is required (fail closed)")
parent = os.path.dirname(lock_path) or "."
os.makedirs(parent, mode=0o700, exist_ok=True)
payload = json.dumps(data, indent=2, sort_keys=True) + "\n"
fd, temp_path = tempfile.mkstemp(prefix=".lock-", suffix=".json", dir=parent)
try:
with os.fdopen(fd, "w", encoding="utf-8") as handle:
handle.write(payload)
handle.flush()
os.fsync(handle.fileno())
os.replace(temp_path, lock_path)
finally:
if os.path.exists(temp_path):
try:
os.remove(temp_path)
except OSError:
pass
def lock_generation(lock: dict[str, Any] | None) -> int:
"""Monotonic write counter for a durable lock record (#772 AC5).
Absent or unusable values read as ``0`` so a lock written before generations
existed still participates in compare-and-swap: its first recovery expects
``0`` and writes ``1``.
"""
if not isinstance(lock, dict):
return 0
try:
return int(lock.get("lock_generation") or 0)
except (TypeError, ValueError):
return 0
def bind_session_lock(
lock_data: dict[str, Any],
lock_dir: str | None = None,
*,
expected_generation: int | None = None,
renewal_sanctioned: bool = False,
recovery_sanctioned: bool = False,
) -> str:
"""Persist a keyed lock and bind it to the current process session.
``expected_generation`` turns the write into a compare-and-swap (#772 AC5).
Recovery decides it may take over a claim by reading the durable lock, but
that read and this write are separate steps; without a CAS two replacement
sessions can both observe the same dead owner, both pass assessment, and
both write — the second silently clobbering the first. Passing the
generation observed at assessment time makes exactly one of them win: the
loser's expectation no longer matches and it fails closed.
"""
remote = str(lock_data.get("remote") or "")
org = str(lock_data.get("org") or "")
repo = str(lock_data.get("repo") or "")
issue_number = int(lock_data.get("issue_number") or 0)
if not remote or not org or not repo or issue_number <= 0:
raise ValueError("lock record must include remote, org, repo, and issue_number")
root = _ensure_lock_dir(lock_dir)
path = lock_file_path(
remote=remote,
org=org,
repo=repo,
issue_number=issue_number,
lock_dir=root,
)
record = dict(lock_data)
record["lock_file_path"] = path
record["session_pid"] = os.getpid()
record.setdefault("pid", os.getpid())
pointer = {
"pid": os.getpid(),
"lock_file_path": path,
"issue_number": issue_number,
"branch_name": record.get("branch_name"),
"remote": remote,
"org": org,
"repo": repo,
}
sentinel = flock_path(path)
try:
with _exclusive_file_lock(sentinel):
existing = read_lock_file(path)
overwrite_block = assess_foreign_lock_overwrite(
existing, record, recovery_sanctioned=recovery_sanctioned
)
if overwrite_block:
raise RuntimeError(overwrite_block)
lease_block = assess_same_issue_lease_conflict(
existing,
issue_number=issue_number,
branch_name=str(record.get("branch_name") or ""),
worktree_path=str(record.get("worktree_path") or ""),
renewal_sanctioned=renewal_sanctioned,
recovery_sanctioned=recovery_sanctioned,
)
if lease_block:
raise RuntimeError(lease_block)
# #772 AC5: compare-and-swap inside the same critical section that
# already serializes writers, so the check and the write cannot be
# separated by another session's successful recovery.
current_generation = lock_generation(existing)
if (
expected_generation is not None
and current_generation != expected_generation
):
raise RuntimeError(
f"Issue #{issue_number} lock generation changed: expected "
f"{expected_generation}, found {current_generation}; another "
"session already recovered or replaced this claim (fail closed)"
)
record["lock_generation"] = current_generation + 1
save_lock_file(path, record)
save_lock_file(session_pointer_path(root), pointer)
except LockContentionError as exc:
competing = read_lock_file(path)
if competing:
owner_pid = competing.get("session_pid") or competing.get("pid")
raise RuntimeError(
f"Issue #{issue_number} lock contention: {exc}; competing owner "
f"pid={owner_pid} (fail closed)"
) from exc
raise RuntimeError(f"Issue #{issue_number} lock contention: {exc} (fail closed)") from exc
return path
def read_session_issue_lock(lock_dir: str | None = None) -> dict[str, Any] | None:
root = (lock_dir or default_lock_dir()).strip()
pointer = read_lock_file(session_pointer_path(root))
if not pointer:
return None
lock_path = str(pointer.get("lock_file_path") or "").strip()
if not lock_path:
return None
return read_lock_file(lock_path)
def load_issue_lock(
*,
remote: str,
org: str,
repo: str,
issue_number: int,
lock_dir: str | None = None,
) -> dict[str, Any] | None:
return read_lock_file(
lock_file_path(
remote=remote,
org=org,
repo=repo,
issue_number=issue_number,
lock_dir=lock_dir,
)
)
def iter_lock_files(lock_dir: str | None = None) -> list[str]:
root = (lock_dir or default_lock_dir()).strip()
if not os.path.isdir(root):
return []
paths: list[str] = []
for name in os.listdir(root):
if not name.endswith(".json") or name.startswith("session-"):
continue
paths.append(os.path.join(root, name))
return sorted(paths)
def find_lock_for_branch(
*,
remote: str,
org: str,
repo: str,
branch_name: str,
lock_dir: str | None = None,
) -> dict[str, Any] | None:
target = (branch_name or "").strip()
if not target:
return None
for path in iter_lock_files(lock_dir):
lock = read_lock_file(path)
if not lock:
continue
if (
str(lock.get("remote") or "") == remote
and str(lock.get("org") or "") == org
and str(lock.get("repo") or "") == repo
and str(lock.get("branch_name") or "").strip() == target
):
lock = dict(lock)
lock.setdefault("lock_file_path", path)
return lock
return None
def _lease_now(now: datetime | None = None) -> datetime:
return now or datetime.now(timezone.utc)
def _parse_lease_timestamp(value: str | None) -> datetime | None:
text = (value or "").strip()
if not text:
return None
try:
return datetime.fromisoformat(text.replace("Z", "+00:00")).astimezone(timezone.utc)
except ValueError:
return None
def lease_expires_at(lock: dict[str, Any] | None) -> datetime | None:
if not lock:
return None
lease = lock.get("work_lease")
if not isinstance(lease, dict):
return None
return _parse_lease_timestamp(lease.get("expires_at"))
def is_lease_expired(lock: dict[str, Any] | None, *, now: datetime | None = None) -> bool:
expires = lease_expires_at(lock)
if expires is None:
return False
return expires <= _lease_now(now)
def is_lease_live(lock: dict[str, Any] | None, *, now: datetime | None = None) -> bool:
return assess_lock_freshness(lock, now=now)["live"]
def assess_lock_freshness(
lock_data: dict[str, Any] | None,
*,
now: datetime | None = None,
) -> dict[str, Any]:
"""Classify a lock as live, expired, stale, or absent."""
current = _lease_now(now)
if not lock_data:
return {
"status": "absent",
"live": False,
"stale": False,
"reason": "no lock record",
}
expires_at = lease_expires_at(lock_data)
lease = lock_data.get("work_lease")
heartbeat_at = _parse_lease_timestamp(lock_data.get("last_heartbeat_at"))
if heartbeat_at is None and isinstance(lease, dict):
heartbeat_at = _parse_lease_timestamp(lease.get("last_heartbeat_at"))
pid = lock_data.get("session_pid")
if pid is None:
pid = lock_data.get("pid")
if pid is None:
pid = lock_data.get("owner_pid")
pid_missing = pid is None or str(pid).strip() == ""
try:
pid_int = int(pid) if not pid_missing else None
if pid_int is not None and pid_int <= 0:
pid_missing = True
pid_int = None
except (TypeError, ValueError):
pid_missing = True
pid_int = None
pid_alive = is_process_alive(pid_int) if pid_int is not None else False
if expires_at and expires_at <= current:
return {
"status": "expired",
"live": False,
"stale": True,
"reason": f"lease expired at {expires_at.isoformat()}",
"pid_alive": pid_alive,
"pid_missing": pid_missing,
}
# #860: a PID-less lock must never be considered live merely because
# expiration / heartbeat fields are absent. Missing PID is insufficient
# evidence of a live owner; treat as malformed/stale so recovery routes
# can evaluate corroborating pins instead of blocking on a false live flag.
if pid_missing:
return {
"status": "malformed",
"live": False,
"stale": True,
"reason": (
"lock has no usable session pid; cannot prove live ownership "
"(PID-less locks are never live by missing expiry alone)"
),
"pid_alive": False,
"pid_missing": True,
"heartbeat_at": heartbeat_at.isoformat() if heartbeat_at else None,
"expires_at": expires_at.isoformat() if expires_at else None,
}
if pid_int is not None and not pid_alive:
return {
"status": "stale",
"live": False,
"stale": True,
"reason": f"owner pid {pid_int} is not alive",
"pid_alive": False,
"pid_missing": False,
}
return {
"status": "live",
"live": True,
"stale": False,
"reason": "lock heartbeat and lease are fresh",
"pid_alive": pid_alive,
"pid_missing": False,
"heartbeat_at": heartbeat_at.isoformat() if heartbeat_at else None,
"expires_at": expires_at.isoformat() if expires_at else None,
}
def _same_realpath(left: str | None, right: str | None) -> bool:
if not left or not right:
return False
try:
return os.path.realpath(left) == os.path.realpath(right)
except OSError:
return left == right
def assess_expired_lock_reclaim(
existing_lock: dict[str, Any] | None,
*,
now: datetime | None = None,
) -> dict[str, Any]:
"""Decide whether an expired/stale author issue lock may be reclaimed (#601).
Required proof (any reclaim of non-live lock):
* lease not live (expired or dead pid)
* owner process dead OR worktree missing
* no force-delete of live foreign ownership
"""
if not existing_lock:
return {
"reclaim_allowed": True,
"reasons": ["no existing lock"],
"freshness": assess_lock_freshness(None, now=now),
}
freshness = assess_lock_freshness(existing_lock, now=now)
if freshness.get("live"):
return {
"reclaim_allowed": False,
"reasons": ["lock is still live; cannot reclaim (fail closed)"],
"freshness": freshness,
}
pid = existing_lock.get("session_pid")
if pid is None:
pid = existing_lock.get("pid")
dead = not is_process_alive(pid) if pid is not None else True
wt = str(existing_lock.get("worktree_path") or "")
missing_wt = (not wt) or (not os.path.isdir(os.path.realpath(wt)))
if not (dead or missing_wt):
return {
"reclaim_allowed": False,
"reasons": [
"expired/stale lock still has live owner pid and present worktree; "
"recovery review required (fail closed)"
],
"freshness": freshness,
"owner_pid_dead": dead,
"worktree_missing": missing_wt,
}
return {
"reclaim_allowed": True,
"reasons": [
"non-live lock with dead process and/or missing worktree; "
"sanctioned reclaim allowed"
],
"freshness": freshness,
"owner_pid_dead": dead,
"worktree_missing": missing_wt,
"prior_branch": existing_lock.get("branch_name"),
"prior_worktree": existing_lock.get("worktree_path"),
"prior_pid": pid,
}
def assess_same_issue_lease_conflict(
existing_lock: dict[str, Any] | None,
*,
issue_number: int,
branch_name: str,
worktree_path: str,
operation_type: str = AUTHOR_ISSUE_WORK_LEASE,
renewal_sanctioned: bool = False,
recovery_sanctioned: bool = False,
now: datetime | None = None,
) -> str | None:
"""Return a fail-closed error when a competing live lease blocks acquisition.
``renewal_sanctioned`` is set only when
``issue_lock_renewal.assess_exact_owner_lease_renewal`` has already proven,
from the durable lock plus live server-side observation, that this session
is the exact recorded owner of an *expired* lease (#760). It is never a
caller-supplied parameter of any MCP tool (#760 AC14): the server computes
it and passes it down. Left False, every pre-existing disposition is
unchanged.
"""
if not existing_lock:
return None
existing_issue = existing_lock.get("issue_number")
lease = existing_lock.get("work_lease")
existing_operation = (
lease.get("operation_type")
if isinstance(lease, dict)
else AUTHOR_ISSUE_WORK_LEASE
)
if existing_issue != issue_number or existing_operation != operation_type:
return None
existing_branch = existing_lock.get("branch_name")
existing_worktree = existing_lock.get("worktree_path")
same_owner = (
existing_branch == branch_name
and _same_realpath(str(existing_worktree or ""), worktree_path)
)
if recovery_sanctioned and existing_issue == issue_number and existing_branch == branch_name:
return None
if is_lease_expired(existing_lock, now=now):
# #760 AC1/AC2: exact-owner renewal is a different disposition from
# foreign takeover and is evaluated first. Before this, both branches
# below returned unconditionally, so the same_owner allowance further
# down was unreachable for every expired lease — an owner could never
# renew its own lock once the wall clock passed, no matter how complete
# its ownership evidence. Requires BOTH the locally recomputed
# same_owner match and the server-proven renewal waiver; either alone is
# insufficient.
if same_owner and renewal_sanctioned:
return None
reclaim = assess_expired_lock_reclaim(existing_lock, now=now)
if reclaim.get("reclaim_allowed"):
# #601: expired + dead pid / missing worktree may be reclaimed
# through the normal lock path (sanctioned overwrite).
return None
return (
f"Issue #{issue_number} has an expired {operation_type} lease on "
f"branch '{existing_branch}' from worktree '{existing_worktree}'. "
"Recovery review is required before takeover (fail closed)"
)
if same_owner:
return None
return (
f"Issue #{issue_number} already has an active {operation_type} lease on "
f"branch '{existing_branch}' from worktree '{existing_worktree}' "
"(fail closed)"
)
def _lock_claimant(lock: dict[str, Any] | None) -> dict[str, str]:
if not isinstance(lock, dict):
return {}
claimant = lock.get("claimant")
if not isinstance(claimant, dict):
lease = lock.get("work_lease")
claimant = lease.get("claimant") if isinstance(lease, dict) else None
if not isinstance(claimant, dict):
return {}
return {
"username": str(claimant.get("username") or ""),
"profile": str(claimant.get("profile") or ""),
}
def assess_foreign_lock_overwrite(
existing_lock: dict[str, Any] | None,
incoming_lock: dict[str, Any],
*,
recovery_sanctioned: bool = False,
now: datetime | None = None,
) -> str | None:
"""Block writes that would clobber an unrelated live lease on the same key."""
if not existing_lock:
return None
same_issue = existing_lock.get("issue_number") == incoming_lock.get("issue_number")
same_branch = existing_lock.get("branch_name") == incoming_lock.get("branch_name")
same_worktree = _same_realpath(
str(existing_lock.get("worktree_path") or ""),
str(incoming_lock.get("worktree_path") or ""),
)
if same_issue and same_branch and same_worktree:
return None
existing_claimant = _lock_claimant(existing_lock)
incoming_claimant = _lock_claimant(incoming_lock)
same_claimant = (
bool(existing_claimant.get("username"))
and existing_claimant.get("username") == incoming_claimant.get("username")
and existing_claimant.get("profile") == incoming_claimant.get("profile")
)
if recovery_sanctioned and same_issue and same_branch and same_claimant:
return None
if not is_lease_live(existing_lock, now=now):
# #860 F8: A non-live or PID-less lock still blocks foreign overwrite
# unless same claimant or sanctioned reclaim is proven.
if not same_claimant and same_issue:
reclaim = assess_expired_lock_reclaim(existing_lock, now=now)
if not reclaim.get("reclaim_allowed"):
return (
"Refusing foreign overwrite of non-live issue lock "
f"(issue #{existing_lock.get('issue_number')}, owner '{existing_claimant.get('username')}') "
"without sanctioned reclaim proof (fail closed)"
)
return None
return (
"Refusing to overwrite a live foreign issue lock "
f"(issue #{existing_lock.get('issue_number')}, "
f"branch '{existing_lock.get('branch_name')}', "
f"worktree '{existing_lock.get('worktree_path')}') (fail closed)"
)
def find_live_lock_for_branch(
branch_name: str,
lock_dir: str | None = None,
) -> dict[str, Any] | None:
target = (branch_name or "").strip()
if not target:
return None
for path in iter_lock_files(lock_dir):
lock = read_lock_file(path)
if not lock:
continue
if str(lock.get("branch_name") or "").strip() != target:
continue
if not is_lease_live(lock):
continue
record = dict(lock)
record.setdefault("lock_file_path", path)
return record
return None
def resolve_locked_branch_for_session(
branch_name: str | None = None,
lock_dir: str | None = None,
) -> str:
if branch_name:
lock = find_live_lock_for_branch(branch_name, lock_dir)
if lock:
return str(lock.get("branch_name") or "")
lock = read_session_issue_lock(lock_dir)
return str((lock or {}).get("branch_name") or "")
def has_active_issue_lock(
branch: str,
*,
lock_dir: str | None = None,
) -> bool:
target = (branch or "").strip()
if not target:
return False
for path in iter_lock_files(lock_dir):
lock = read_lock_file(path)
if not lock:
continue
if str(lock.get("branch_name") or "").strip() != target:
continue
if is_lease_live(lock):
return True
return False
def verify_lock_for_mutation(
lock_data: dict[str, Any] | None,
*,
issue_number: int | None = None,
branch_name: str | None = None,
worktree_path: str | None = None,
) -> dict[str, Any]:
"""Re-check lock ownership immediately before a mutation (#438)."""
reasons: list[str] = []
if not lock_data:
return {"proven": False, "block": True, "reasons": ["issue lock is missing (fail closed)"]}
freshness = assess_lock_freshness(lock_data)
if not freshness["live"]:
reasons.append(f"issue lock is not live: {freshness['reason']} (fail closed)")
if issue_number is not None and lock_data.get("issue_number") != issue_number:
reasons.append(
f"issue lock targets #{lock_data.get('issue_number')}, expected #{issue_number} (fail closed)"
)
if branch_name is not None and lock_data.get("branch_name") != branch_name:
reasons.append(
f"issue lock branch '{lock_data.get('branch_name')}' does not match "
f"'{branch_name}' (fail closed)"
)
if worktree_path is not None:
locked = os.path.realpath(str(lock_data.get("worktree_path") or ""))
declared = os.path.realpath(worktree_path)
if locked != declared:
reasons.append(
f"issue lock worktree '{locked}' does not match declared '{declared}' (fail closed)"
)
return {
"proven": not reasons,
"block": bool(reasons),
"reasons": reasons,
"freshness": freshness,
"lock_proof": format_lock_proof(lock_data, freshness=freshness),
}
def list_live_locks(
*,
lock_dir: str | None = None,
now: datetime | None = None,
) -> list[dict[str, Any]]:
"""Return live per-issue locks for queue visibility."""
live: list[dict[str, Any]] = []
for path in iter_lock_files(lock_dir):
record = read_lock_file(path)
if not record:
continue
freshness = assess_lock_freshness(record, now=now)
if not freshness["live"]:
continue
live.append(
{
"issue_number": record.get("issue_number"),
"branch_name": record.get("branch_name"),
"remote": record.get("remote"),
"org": record.get("org"),
"repo": record.get("repo"),
"worktree_path": record.get("worktree_path"),
"pid": record.get("session_pid") or record.get("pid"),
"claimant": (
record.get("claimant")
or (record.get("work_lease") or {}).get("claimant")
),
"freshness": freshness,
"lock_path": record.get("lock_file_path") or path,
}
)
return live
def format_lock_proof(
lock_data: dict[str, Any] | None,
*,
freshness: dict[str, Any] | None = None,
competing_live_locks: list[dict[str, Any]] | None = None,
released: bool | None = None,
) -> str:
"""Canonical issue-lock proof string for final reports."""
if not lock_data:
return "issue lock proof: not acquired"
fresh = freshness or assess_lock_freshness(lock_data)
owner = lock_data.get("claimant") or {}
if not owner and isinstance(lock_data.get("work_lease"), dict):
owner = lock_data["work_lease"].get("claimant") or {}
parts = [
"issue lock proof:",
f"acquired issue #{lock_data.get('issue_number')}",
f"branch {lock_data.get('branch_name')}",
f"owner {owner.get('profile') or 'unknown'}",
f"pid {lock_data.get('session_pid') or lock_data.get('pid')}",
f"freshness {fresh.get('status')}",
]
if competing_live_locks is not None:
parts.append(
"no competing live lock"
if not competing_live_locks
else f"competing live locks {len(competing_live_locks)}"
)
if released is True:
parts.append("lock released")
elif released is False:
parts.append("lock retained")
return "; ".join(parts)
# ── #871: durable linked-issue lock head refresh after branch synchronization ──
_FULL_SHA_RE = re.compile(r"^[0-9a-f]{40}$", re.IGNORECASE)
# Provenance recorded on the lock when the head is refreshed by a sanctioned
# merge-based branch synchronization (``gitea_update_pr_branch_by_merge``).
LOCK_HEAD_REFRESH_PROVENANCE_MERGE_SYNC = "gitea_update_pr_branch_by_merge"
def _norm_sha(value: Any) -> str | None:
text = str(value or "").strip().lower()
return text if _FULL_SHA_RE.match(text) else None
def _lock_claimant_view(lock: dict[str, Any] | None) -> dict[str, Any]:
if not isinstance(lock, dict):
return {}
claimant = lock.get("claimant")
if not isinstance(claimant, dict):
lease = lock.get("work_lease")
claimant = lease.get("claimant") if isinstance(lease, dict) else None
return dict(claimant) if isinstance(claimant, dict) else {}
def assess_durable_lock_head_refresh(
existing_lock: dict[str, Any] | None,
*,
remote: str,
org: str,
repo: str,
issue_number: int,
branch_name: str,
worktree_path: str,
pr_number: int | None,
identity: str | None,
profile: str | None,
current_pid: int | None,
expected_old_head: str | None,
new_head: str | None,
base_head: str | None = None,
) -> dict[str, Any]:
"""Fail-closed assessment for refreshing a durable lock's recorded head (#871).
A successful ``gitea_update_pr_branch_by_merge`` advances the *remote* PR head
but must also advance the durable linked-issue lock so a later dead-session
recovery can prove ownership. This decides whether that refresh is permitted;
it mutates nothing.
Every element of durable ownership is re-verified against the persisted lock —
repository, issue, branch, worktree, claimant identity/profile, and the live
owning session — and the recorded head is compare-and-swapped: the lock's
currently recorded synced head (if any) must equal ``expected_old_head``, so a
lock whose head or provenance changed concurrently is never overwritten.
"""
reasons: list[str] = []
old = _norm_sha(expected_old_head)
new = _norm_sha(new_head)
evidence: dict[str, Any] = {
"issue_number": issue_number,
"branch_name": branch_name,
"worktree_path": worktree_path,
"pr_number": pr_number,
"expected_old_head": old,
"new_head": new,
"base_head": _norm_sha(base_head),
}
if not isinstance(existing_lock, dict) or not existing_lock:
reasons.append("no durable lock exists for this issue; nothing to refresh")
return {"allowed": False, "reasons": reasons, "evidence": evidence,
"expected_generation": 0}
lock = dict(existing_lock)
evidence["current_generation"] = lock_generation(lock)
if lock.get("issue_number") != issue_number:
reasons.append(
f"durable lock targets issue #{lock.get('issue_number')}, not "
f"#{issue_number}; refusing head refresh"
)
for field, expected in (("remote", remote), ("org", org), ("repo", repo)):
actual = str(lock.get(field) or "").strip()
if actual != str(expected or "").strip():
reasons.append(
f"lock {field} '{actual}' does not match requested "
f"'{str(expected or '').strip()}'"
)
locked_branch = str(lock.get("branch_name") or "").strip()
if locked_branch != str(branch_name or "").strip():
reasons.append(
f"lock branch '{locked_branch}' does not match requested "
f"'{str(branch_name or '').strip()}'"
)
locked_worktree = str(lock.get("worktree_path") or "").strip()
try:
same_wt = bool(locked_worktree) and bool(worktree_path) and (
os.path.realpath(locked_worktree) == os.path.realpath(worktree_path)
)
except OSError:
same_wt = locked_worktree == (worktree_path or "")
if not same_wt:
reasons.append(
f"lock worktree '{locked_worktree}' does not match declared "
f"'{str(worktree_path or '').strip()}'"
)
claimant = _lock_claimant_view(lock)
locked_identity = str(claimant.get("username") or "").strip()
locked_profile = str(claimant.get("profile") or "").strip()
if not locked_identity or not locked_profile:
reasons.append(
"durable lock does not record a claimant identity/profile; "
"ownership could not be proven for head refresh"
)
if not str(identity or "").strip() or not str(profile or "").strip():
reasons.append(
"active session identity/profile is unknown; ownership could not be "
"proven for head refresh"
)
if locked_identity and str(identity or "").strip() and locked_identity != str(identity).strip():
reasons.append(
f"lock claimant '{locked_identity}' does not match active identity "
f"'{str(identity).strip()}'"
)
if locked_profile and str(profile or "").strip() and locked_profile != str(profile).strip():
reasons.append(
f"lock profile '{locked_profile}' does not match active profile "
f"'{str(profile).strip()}'"
)
# The refresh is written by the LIVE owning author session. A refresh is not
# a recovery: the current process must be the recorded owner.
recorded_pid = lock.get("session_pid")
if recorded_pid is None:
recorded_pid = lock.get("pid")
evidence["recorded_pid"] = recorded_pid
evidence["current_pid"] = current_pid
if current_pid is None:
reasons.append("current session pid is unknown; cannot prove live ownership")
else:
try:
if recorded_pid is None or int(recorded_pid) != int(current_pid):
reasons.append(
f"durable lock is owned by pid {recorded_pid}, not the current "
f"session pid {current_pid}; head refresh requires the live owner"
)
except (TypeError, ValueError):
reasons.append(
"durable lock owner pid is malformed; cannot prove live ownership"
)
if not old:
reasons.append("expected_old_head is not a full 40-char hex SHA (fail closed)")
if not new:
reasons.append("new_head is not a full 40-char hex SHA (fail closed)")
if old and new and old == new:
reasons.append(
"new head equals the expected old head; a sync must advance the head"
)
# Compare-and-swap on the recorded head: if the lock already records a synced
# head it must be exactly the expected old head, else another sync moved it.
recorded_synced = _norm_sha(lock.get("synced_pr_head"))
evidence["recorded_synced_pr_head"] = recorded_synced
if recorded_synced is not None and old is not None and recorded_synced != old:
reasons.append(
f"durable lock already records synced head {recorded_synced}, not the "
f"expected old head {old}; a concurrent sync changed it (CAS fail closed)"
)
if reasons:
return {"allowed": False, "reasons": reasons, "evidence": evidence,
"expected_generation": lock_generation(lock)}
return {
"allowed": True,
"reasons": [
f"durable lock for issue #{issue_number} branch '{locked_branch}' is "
f"owned by the live session; refresh recorded head {old} -> {new}"
],
"evidence": evidence,
"expected_generation": lock_generation(lock),
}
def apply_durable_lock_head_refresh(
*,
remote: str,
org: str,
repo: str,
issue_number: int,
branch_name: str,
worktree_path: str,
pr_number: int | None,
identity: str | None,
profile: str | None,
current_pid: int | None,
expected_old_head: str | None,
new_head: str | None,
synced_at: str,
base_head: str | None = None,
provenance: str = LOCK_HEAD_REFRESH_PROVENANCE_MERGE_SYNC,
lock_dir: str | None = None,
) -> dict[str, Any]:
"""CAS-refresh the durable lock's recorded head after a branch sync (#871).
Reads the durable lock from disk, re-asserts ownership via
``assess_durable_lock_head_refresh``, and — only when permitted — writes the
new synced head through ``bind_session_lock`` with a generation compare-and-
swap. Then re-reads the lock and proves it records the complete new head
(read-after-write). Any failure at any step returns ``refreshed=False`` with
reasons; the caller must treat that as a partial lifecycle failure and never
report a fully successful synchronization.
"""
existing = load_issue_lock(
remote=remote, org=org, repo=repo, issue_number=issue_number, lock_dir=lock_dir
)
assessment = assess_durable_lock_head_refresh(
existing,
remote=remote,
org=org,
repo=repo,
issue_number=issue_number,
branch_name=branch_name,
worktree_path=worktree_path,
pr_number=pr_number,
identity=identity,
profile=profile,
current_pid=current_pid,
expected_old_head=expected_old_head,
new_head=new_head,
base_head=base_head,
)
result: dict[str, Any] = {
"refreshed": False,
"read_after_write_ok": False,
"prior_head": _norm_sha(expected_old_head),
"new_head": _norm_sha(new_head),
"reasons": list(assessment.get("reasons") or []),
"evidence": assessment.get("evidence"),
}
if not assessment.get("allowed"):
return result
new = _norm_sha(new_head)
old = _norm_sha(expected_old_head)
record = dict(existing or {})
sync_block = {
"last_synced_pr_head": new,
"prior_pr_head": old,
"base_head": _norm_sha(base_head),
"pr_number": pr_number,
"provenance": provenance,
"synced_at": synced_at,
"synced_by_pid": current_pid,
"synced_by": {
"username": str(identity or "").strip() or None,
"profile": str(profile or "").strip() or None,
},
}
record["synced_pr_head"] = new
record["branch_sync"] = sync_block
history = record.get("branch_sync_history")
if not isinstance(history, list):
history = []
history = list(history)
history.append(sync_block)
record["branch_sync_history"] = history
try:
bind_session_lock(
record,
lock_dir=lock_dir,
expected_generation=assessment.get("expected_generation"),
renewal_sanctioned=True,
)
except Exception as exc: # CAS miss or write failure — partial lifecycle failure
result["reasons"].append(
f"durable lock head refresh write failed (fail closed): {exc}"
)
return result
after = load_issue_lock(
remote=remote, org=org, repo=repo, issue_number=issue_number, lock_dir=lock_dir
)
after_head = _norm_sha((after or {}).get("synced_pr_head"))
result["lock_generation_after"] = lock_generation(after)
if after_head == new and new is not None:
result["refreshed"] = True
result["read_after_write_ok"] = True
result["reasons"].append(
f"durable lock recorded head refreshed to {new} and verified by "
"read-after-write"
)
else:
result["reasons"].append(
"read-after-write verification failed: durable lock does not record "
f"the new head {new} (found {after_head}); partial lifecycle failure"
)
return result