mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-08 03:01:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

fix(kanban): heartbeat tool extends claim TTL, not just last_heartbeat_at

Browse source 
The kanban_heartbeat tool called heartbeat_worker but never
heartbeat_claim, so a worker that loops the tool while a single tool
call blocks the agent for >DEFAULT_CLAIM_TTL_SECONDS still got
reclaimed by release_stale_claims. The function name and
heartbeat_claim's own docstring imply otherwise:

  "Workers that know they'll exceed 15 minutes should call this
   every few minutes to keep ownership."

But there was no caller in the worker tool path. Workers couldn't
invoke heartbeat_claim themselves either — it isn't exposed as a tool.

Fix: _handle_heartbeat now calls heartbeat_claim first, reading
HERMES_KANBAN_CLAIM_LOCK from the worker env (the dispatcher pins
this in _default_spawn). Falls back to _claimer_id() for locally-
driven workers that didn't go through dispatcher spawn.

Test: tests/tools/test_kanban_tools.py::test_heartbeat_extends_claim_expires
rewinds claim_expires into the past, calls the tool, and asserts the
new value is at least now + DEFAULT_CLAIM_TTL_SECONDS // 2. Verified to
fail against the unfixed code (claim_expires stays at the rewound
value).

Closes the root cause underlying the symptom in #21141 (15-min
respawns of long-running workers). #21141 separately addresses
post-reclaim cleanup; this fixes the upstream "shouldn't have been
reclaimed in the first place" half.
This commit is contained in:
stephen0110 2026-05-07 12:50:30 +02:00 • committed by Teknium
parent bf843adf05
commit 40b51c93a2
2 changed files with 72 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

18
tools/kanban_tools.py
View file

@ -315,7 +315,15 @@ def _handle_block(args: dict, **kw) -> str:
def _handle_heartbeat(args: dict, **kw) -> str:
"""Signal that the worker is still alive during a long operation."""
"""Signal that the worker is still alive during a long operation.
Extends the claim TTL via ``heartbeat_claim`` AND records a heartbeat
event via ``heartbeat_worker``. Without the ``heartbeat_claim`` half,
a diligent worker that loops this tool while a single tool call
blocks the agent for >DEFAULT_CLAIM_TTL_SECONDS still gets reclaimed
by ``release_stale_claims`` — which is exactly the trap that
``heartbeat_claim``'s docstring warns against.
"""
tid = _default_task_id(args.get("task_id"))
if not tid:
return tool_error(
@ -328,6 +336,14 @@ def _handle_heartbeat(args: dict, **kw) -> str:
try:
kb, conn = _connect()
try:
# Extend the claim TTL first. The dispatcher pins
# HERMES_KANBAN_CLAIM_LOCK in the worker env at spawn time
# (see _default_spawn in kanban_db.py); falling back to the
# default _claimer_id() covers locally-driven workers that
# never went through the dispatcher path.
claim_lock = os.environ.get("HERMES_KANBAN_CLAIM_LOCK")
kb.heartbeat_claim(conn, tid, claimer=claim_lock)
ok = kb.heartbeat_worker(
conn,
tid,