+ jHj?7Rt^RIt^RIt^RIt^RIt^RIHt^RIHt^RI H t ^RI H t ]P!]4t] tRtRtRt]!R R 04t!R R 4tR tRtRtRtRtRtRtRtRtRt R#)aThe last viewer closing a session ends it on the owner, lifecycle included (#134889 LC-1/LC-2/LC-6). Main's classic CLI and TUI ran the end of a conversation in their own process: ``end_session``, the memory providers' ``on_session_end`` extraction and plugin ``on_session_finalize`` (which also closes the Relay conversation scope). Under the gateway those clients are viewers: the agent, its memory manager and the Relay scope live in the owner, so ``session.detach {end_reason}`` from the last viewer is where the owner runs them. A close that lands while a turn is still queued or running is remembered and completed when the FIFO goes idle, so exiting mid-turn still ends the row. The pending close is also kept in ``state_meta`` (``CLOSE_PREFIX + session_id``): a gateway stop or restart before the FIFO goes idle would otherwise drop it, and nothing else ends a local row. Boot recovery re-arms it (``rearm_persisted_closes``), so the restarted owner's first idle point ends it. Each stored close carries its own operation id, and every delete is compare-and-delete on that exact record under the owner-epoch fence: a cancelled older close, a reattach or a stale owner can only remove the record it saw, never a newer close stored since. N)partial) local_receipt)VIEWER_CLOSE_PREFIX)RuntimeStoreErrorzSELECT 1 FROM session_admissions WHERE target_session_id=? AND status IN ('queued','started','unknown') UNION ALL SELECT 1 FROM worker_executions WHERE session_id IN (?,?) AND status IN ('registered','running','unknown') LIMIT 1c\VPV4R,R,# \\\3d)TPP T4;'gTu#i;i)entry session_id)rdbrKeyError TypeErrorget_compression_tip) authorityrs&&A/home/ubuntu/.hermes/hermes-agent/gateway/session_viewer_close.py_physical_targetr#sXJY\\:6w? MM x 3J||// ;IIzIJs#&7A$A$#A$cVPP4;_uu_4pVP\WV34P 4RJuuRRR4# +'giR#;iN)r _read_ctxexecute _BUSY_SQLfetchone)r rtargetconns&&& r_busyr*sH    ! !T||I 'GHQQS[__ " ! ! !s (A A' new_session tui_closecBa]tRt^4toRtRtRRlt]R4tRt Vt R#) _PendingClosezOne viewer close; identity, not the reason, tells a settler its close is still the pending one. ``record`` is its ``state_meta`` value: a unique operation id plus the reason.NcWnT;'g:\P!R\P!4P RV/RR7VnR#)opreasonT) sort_keysN)rjsondumpsuuiduuid4hexrecord)selfrr&s&&&r__init___PendingClose.__init__9s7 ff D$**,2B2BHf+Uae f c\P!V4R,pV!W!4# \\\3dTpL"i;i)r)r!loads ValueErrorr r )clsr&rs&& r from_record_PendingClose.from_record=sD ZZ'1F6""Ix0 F s'AA)rr&r) __name__ __module__ __qualname____firstlineno____doc__ __slots__r( classmethodr/__static_attributes____classdictcell__) __classdict__s@rrr4s*V$Ig##r*rc "VPV,pVP'dR#VP'dR#^RIHpHpVP p\\PV\W4344pV!VPV3WgR7VFpV!WhRV 2R7K \V4;VPV&p \P!\ WV P"4GRjxL \%WW94'g1\P!\&WV P"4GRjxL R#\)W4GRjxL R#L[LL 5i)aq``session.detach {end_reason}`` left *session_id* without viewers: close it now, or once idle. Its own async delegations end now, mid-turn too, as main's CLI exit and TUI close ended them (#134889 LC-7); each returns as an interrupted completion, and ones its still-running turn starts later are refused until a viewer attaches again. Other sessions' work is untouched.N)interrupt_for_sessionrefuse_for_session) session_keyparent_session_idsz viewer_close:)r>parent_session_idr)sessions subscribers supersededtools.async_delegationr<r=routetupledictfromkeysr profile_idrpending_closesasyncio to_thread_persist_closer&_still_pendingforget_persisted_closesettle_viewer_close) r rrliver<r=rEparentsparentcloses &&& rclose_viewer_sessionrUFs   j )D  P JJEDMM:/? /V"WXYG ,,j9ui%TabhaiRjk3@3HHIZ(5   NI5<< PPP ) = = 6 u||\\\ i 444 Q ]4s;9E B.E *E+?E *E+E ?E E E  E cbaaaa^RIHoVVVV3RlpSPPV4R#)_epochcl<S!VSP4VPR\S,S34R#)zaINSERT INTO state_meta(key,value) VALUES(?,?) ON CONFLICT(key) DO UPDATE SET value=excluded.valueN)epochr CLOSE_PREFIXrrYr r&rs&rwrite_persist_close..writecs-tY__% x"Z/8 :r*N)hermes_state_runtimerYr _execute_write)r rr&r^rYsfff @rrMrM`s$+::LL&r*caaaa^RIHoVVVV3Rlp\SPP V44# \ d#p\ PRST4Rp?R#Rp?ii;i)zBlocking: drop *session_id*'s stored close only if it is still exactly *record* (that close completed or was cancelled), and only while this authority owns the store. Returns whether a row went.rXc|<S!VSP4VPR\S,S34P#)z.DELETE FROM state_meta WHERE key=? AND value=?)r[rr\rowcountr]s&rr^%forget_persisted_close..writeps9tY__%||L)J6?AAI Jr*z%Stored close for %s left in place: %sNF)r`rYboolr rarloggerinfo)r rr&r^excrYsfff @rrOrOjsW,JJILL//677  ;ZMs#9 A&A!!A&cVPP\V,4pVfR#VPP V4pVeVP V8XdR#\ WV4R#)zBlocking, for a viewer attach: drop the stored close unless it is the one now pending in memory (a detach that ran after the attach stored it; it is that close's own to settle).N)r get_metar\rJgetr&rO)r rr&pendings&& rcancel_persisted_closern{sY\\ " "<*#< =F ~&&**:6Gw~~79&9r*c>VPP4;_uu_4pVPR\R,34P 4pRRR4.pXFwrEV\ \4RpVP PV4pVeVP'dKJVP'd\WV4KjVPPV\PV44VPV4K V# +'giL;i)aBoot/serve recovery, after the local sessions are restored: every stored close whose session is mounted with no viewer goes back to ``pending_closes``. The caller schedules the drain, whose idle point (after any queued turn; never past an ``unknown`` one) completes it. Returns the ids.z2SELECT key, value FROM state_meta WHERE key LIKE ?%N)r rrr\fetchalllenrArlrCrBrOrJ setdefaultrr/append)r rstoredarmedkeyr&rrQs& rrearm_persisted_closesrxs    ! !TRUadgUgTijssu " E \*+, !!%%j1 <4???      "9& A   ++J 8Q8QRX8YZ Z  L " !s -D  D c "VPPV4pVPPV4pVeVeVP'dVPP VR4R#\ WW24GRjxL 'gR#\ W4p\P!\WV4GRjxL 'dR#\P!VPPV4GRjxL p\WW24'gR#TPV^RI HpHp^RIHpV!V\%W`WP&4\%WpV4R7GRjxL p V 'g\)WW4V4GRjxL R#\P!\*WVP,4GRjxL VP'dR#T;'g/PR4;'g5VP.'d!VP.P0P2MRp \5WWJVP&4GRjxL R#ELEL|ELDLLLL5i)aComplete a pending viewer close once *session_id* has no viewer and an idle FIFO: stamp the row with the viewer's reason, commit the cached agent's memory and fire ``on_session_finalize``. The drain calls this at every idle point; a viewer attaching meanwhile cancels the close.N)end_idle_viewer_sessionreopen_if_reattached) tracked_write)thensource)rJrlrArBpop_resolve_abandoned_unknownrrKrLrr get_sessionrNgateway.session_acp_lifecyclerzr{gateway.session_runtime_workersr|rr_requeue_if_busyrOr&r~platformvalue_run_close_lifecycle) r rrTrQrrowrzr{r|endedrs && rrPrPs  $ $ ( ( 4E    ! !* -D } (8(8(8  $$Z6+I4O O O i 4F  uiV DDD!!),,":":FC CC ) = =   ,[= 73JWacoco+p%,-Aj%Y[ [E ydEJJJ   2I5<< XXX  rx(__4;;;T[[-A-A-G-G\^H y%,, OOO1 P E C [ KXPsAI-IH0 I ,I7H38 I0I2H63AIH9 II/H;0/IH= I6 III- B:B4 B:9B:&B6'B:?.B:-B8.B:6B:8B:c "VPp\VRR4pVeV!VP4\VRR4pVfR#V!W#WAPR7GRjxL pV'd\P RV4\VRR4p V\ 9d)V e#V !VPRRVVRR7GRjxL R#R#R#LdL 5i) zWhat main's client ran at exit and ``/new``, in the process that owns the session: the memory providers' end-of-session commit (the cached agent is evicted at a boundary, as a gateway ``/new`` does) and the finalize hooks under the owning profile's scope._evict_cached_agent_at_boundaryN_finalize_session_off_loop)rrrr>z7Session-end plugin message(s) for %s dropped: no viewer_reset_session_off_loopr)r>rrrold_session_idnew_session_id)runnergetattrrErgrh_RESET_REASONS) r rQrrrrevictfinalizemessagesresets &&&&& rrrs  F F=t DE  djjv;TBH6_i_ijjH MvV F5t rs  ,@2   8 $" H J`M;78##$54'" :(!PH><V 5@r*