fix(kanban): retry corrupt-board dispatch after quarantine

This commit is contained in:
Donovan Yohan
2026-05-27 11:48:23 -07:00
committed by Teknium
parent fc47b7285c
commit c94ad89818
2 changed files with 144 additions and 16 deletions
+49 -15
View File
@@ -5424,7 +5424,13 @@ class GatewayRunner:
HEALTH_WINDOW = 6
bad_ticks = 0
last_warn_at = 0
disabled_corrupt_boards: dict[str, tuple[str, int | None, int | None]] = {}
# Avoid hot-looping corrupt-looking board DBs, but do not suppress
# same-fingerprint retries forever: transient WAL/open races can
# surface as "database disk image is malformed" for one tick.
CORRUPT_BOARD_RETRY_AFTER_SECONDS = 300
disabled_corrupt_boards: dict[
str, tuple[tuple[str, int | None, int | None], float]
] = {}
def _board_db_fingerprint(slug: str) -> tuple[str, int | None, int | None]:
path = _kb.kanban_db_path(slug)
@@ -5439,6 +5445,9 @@ class GatewayRunner:
return (resolved, stat.st_mtime_ns, stat.st_size)
def _is_corrupt_board_db_error(exc: Exception) -> bool:
corrupt_guard_error = getattr(_kb, "KanbanDbCorruptError", None)
if corrupt_guard_error is not None and isinstance(exc, corrupt_guard_error):
return True
if not isinstance(exc, sqlite3.DatabaseError):
return False
msg = str(exc).lower()
@@ -5458,14 +5467,27 @@ class GatewayRunner:
"""
conn = None
fingerprint = _board_db_fingerprint(slug)
disabled_fingerprint = disabled_corrupt_boards.get(slug)
if disabled_fingerprint == fingerprint:
return None
if disabled_fingerprint is not None:
logger.info(
"kanban dispatcher: board %s database changed; retrying dispatch",
slug,
)
disabled_entry = disabled_corrupt_boards.get(slug)
if disabled_entry is not None:
disabled_fingerprint, disabled_at = disabled_entry
age = time.monotonic() - disabled_at
if (
disabled_fingerprint == fingerprint
and age < CORRUPT_BOARD_RETRY_AFTER_SECONDS
):
return None
if disabled_fingerprint == fingerprint:
logger.info(
"kanban dispatcher: board %s database fingerprint unchanged "
"after %.0fs quarantine; retrying dispatch",
slug,
age,
)
else:
logger.info(
"kanban dispatcher: board %s database changed; retrying dispatch",
slug,
)
disabled_corrupt_boards.pop(slug, None)
try:
conn = _kb.connect(board=slug)
@@ -5485,20 +5507,32 @@ class GatewayRunner:
)
except sqlite3.DatabaseError as exc:
if _is_corrupt_board_db_error(exc):
disabled_corrupt_boards[slug] = fingerprint
disabled_corrupt_boards[slug] = (fingerprint, time.monotonic())
logger.error(
"kanban dispatcher: board %s database %s is not a valid "
"SQLite database; disabling dispatch for this board "
"until the file changes or the gateway restarts. Move "
"or restore the file, then run `hermes kanban init` if "
"you need a fresh board.",
"SQLite database; pausing dispatch for this board until "
"the file changes, the gateway restarts, or the "
"quarantine timer expires. Move or restore the file, "
"then run `hermes kanban init` if you need a fresh board.",
slug,
fingerprint[0],
)
return None
logger.exception("kanban dispatcher: tick failed on board %s", slug)
return None
except Exception:
except Exception as exc:
if _is_corrupt_board_db_error(exc):
disabled_corrupt_boards[slug] = (fingerprint, time.monotonic())
logger.error(
"kanban dispatcher: board %s database %s is not a valid "
"SQLite database; pausing dispatch for this board until "
"the file changes, the gateway restarts, or the "
"quarantine timer expires. Move or restore the file, "
"then run `hermes kanban init` if you need a fresh board.",
slug,
fingerprint[0],
)
return None
logger.exception("kanban dispatcher: tick failed on board %s", slug)
return None
finally: