mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-14 04:02:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix: auto-block repeated kanban retries

Browse source
This commit is contained in:
mwnickerson 2026-05-06 15:30:03 -04:00 • committed by Teknium
parent 595e906698
commit 411cfa26e3
5 changed files with 119 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

24
hermes_cli/kanban_db.py
View file

@ -1380,7 +1380,7 @@ def assign_task(conn: sqlite3.Connection, task_id: str, profile: Optional[str])
profile = _canonical_assignee(profile)
with write_txn(conn):
row = conn.execute(
"SELECT status, claim_lock FROM tasks WHERE id = ?", (task_id,)
"SELECT status, claim_lock, assignee FROM tasks WHERE id = ?", (task_id,)
).fetchone()
if not row:
return False
@ -1389,7 +1389,17 @@ def assign_task(conn: sqlite3.Connection, task_id: str, profile: Optional[str])
f"cannot reassign {task_id}: currently running (claimed). "
"Wait for completion or reclaim the stale lock first."
)
conn.execute("UPDATE tasks SET assignee = ? WHERE id = ?", (profile, task_id))
if row["assignee"] != profile:
# The retry guard is scoped to the task/profile combination. A
# human reassigning the task is an explicit recovery action, so the
# new profile should not inherit the previous profile's streak.
conn.execute(
"UPDATE tasks SET assignee = ?, consecutive_failures = 0, "
"last_failure_error = NULL WHERE id = ?",
(profile, task_id),
)
else:
conn.execute("UPDATE tasks SET assignee = ? WHERE id = ?", (profile, task_id))
_append_event(conn, task_id, "assigned", {"assignee": profile})
return True
@ -2569,11 +2579,11 @@ def set_workspace_path(
# Dispatcher (one-shot pass)
# ---------------------------------------------------------------------------
# After this many consecutive `spawn_failed` events on a task, the dispatcher
# stops retrying and parks the task in ``blocked`` with a reason so a human
# can investigate. Prevents the dispatcher from thrashing forever on a task
# whose profile doesn't exist, whose workspace is unmountable, etc.
DEFAULT_FAILURE_LIMIT = 5
# After this many consecutive non-success attempts on a task/profile, the
# dispatcher stops retrying and parks the task in ``blocked`` with a reason so
# a human can investigate. Prevents retry storms when a worker repeatedly times
# out, crashes, or cannot spawn.
DEFAULT_FAILURE_LIMIT = 2
# Legacy alias — callers / tests still reference the old name.
DEFAULT_SPAWN_FAILURE_LIMIT = DEFAULT_FAILURE_LIMIT