+ jHj jRt^RIHt^RIt^RIt^RIt^RIt^RIH t RRlt R RRllt RR lt R#) uCron: teardown of a worker that outlived its ``run_job``. ``ThreadPoolExecutor.shutdown(wait=False)`` after an inactivity timeout does not stop a worker already inside ``run_conversation``. Finalizing its SessionDB from ``run_job``'s ``finally`` would close a handle the worker is still writing to — the checkpoint/WAL-unlink overlap behind #102827. The worker's Future owns the teardown instead. ) annotationsN)Optionalc V^8dQhRRRR/#)futurezconcurrent.futures.FuturereturnNone)formats"C/home/ubuntu/.hermes/hermes-agent/cron/scheduler_detached_worker.py __annotate__r s ! !*C ! !c\P!\4;_uu_4VP4pVe^RIHpV!V4RRR4R# +'giR#;i)uDone-callback: close a SessionDB whose constructor finished after run_job's init timeout (worker abandoned via ``shutdown(wait=False)``), else its .db/WAL/SHM handles leak to EMFILE. If the constructor later completes inside that abandoned worker, the Future's result — an open SessionDB holding .db / WAL / SHM file handles — would be orphaned and never closed, leaking descriptors until EMFILE (#72782). This callback retrieves and closes that eventual late result. N)release_or_close) contextlibsuppress Exceptionresulthermes_state_registryr)rdbrs& r _close_late_session_db_resultrs?   Y ' ' ]]_ > > R ( ' ' 's #A A! c 0V^8dQhRRRRRRRRRRR R /#) rrz#Optional[concurrent.futures.Future]job_idstrjob_namecron_session_idworkdirz Optional[str]rboolr )r s"r r r !s> /LO[^#0 r c aaaaaaaa VeVP4'dR#^RIHoHo RVV VVVVVV3RllpVP V4R#)zReturn True when the worker is still running and its Future will finalize the session and tear the agent down on completion; False when the caller must do it now.F)_finalize_cron_session_teardown_cron_agentcV^8dQhRR/#)rrrr )r s"r r 6defer_teardown_to_running_worker..__annotate__+s00D0r c d<S'dS!SSSSSSR7S!SS4R# S!SS4i;i))rNr ) _futurerr agentrrr session_dbrs &r _finish1defer_teardown_to_running_worker.._finish+s8 0&z5&(O/68 ! /  /s $$ /T)donecron.schedulerrr add_done_callback) rr&r%rrrrr'rr s &ffffff @@r defer_teardown_to_running_workerr,!s7 ~K00 W% r c V^8dQhRRRR/#)rprocesszsubprocess.Popenrrr )r s"r r r 8s0@Tr c \P!VPR\VRR4 2RR7P 4R#)aKeep the reap contract when the waiter returns before the worker exits. The ledger turning terminal lets ``_wait_for_external_cron_worker_body`` return while the worker is still in final teardown. The gateway remains the worker's parent, so if nobody calls ``wait()`` afterwards the worker lingers as a zombie (STAT=Z) under the gateway until it is restarted (#114509). A short-lived daemon thread holds that single responsibility and ends with the process exit it waits for. zcron-worker-reap-pid?T)targetnamedaemonN) threadingThreadwaitgetattrstart)r.s&r "reap_terminal_worker_in_backgroundr:8s9|| %!= > ? egr )N) __doc__ __future__rconcurrent.futures concurrentr subprocessr5typingrrr,r:r r r rAs-# !.r