+ jHjxRt^RIt^RIt^RIt^RIt^RIt^RIHt^RIHt^RI H t ^RI H t H t HtHt^RIHtHtHt^RIHt^RIHt^R IHt^R IHtHtHtHtHtH t H!t!H"t"H#t#^R I$H%t%H&t&H't'^R I(H)t*^R I+H,t-^RI.H/t/^RI0H1t2H3t4H5t6]!4t7]!RR4t8]!RR4t9]!RR4t:]!RR4t;]!RR4t<]!RR4t=]!RR4t>]!RR4t?]!RR4t@]!RR4tA]!RR4tBRR ltCR!R"ltDR#R$ltER%R&ltFR'tGRR(R)lltHRR*R+lltIR,tJR-R.ltK]R/R0l4tLR1R2ltMRR3R4lltNR5R6ltOR7R8ltPR9R:ltQR;R<ltRR=R>ltSRR@RAlltTRBRCltURDREltVRFtWRGRHltXRIRJltYRRKRLlltZRRMRNllt[R?t\RORPlt]RQRRlt^RSRTlt_0Rmt`RRURVlltaRRWRXlltbRRYRZlltcRR[R\lltdRR]R^llte^rrr)r<r= normalizedkeys&& r1!_normalize_dashboard_cron_updatesrN6sgmm$J/  1*/BJO0:? 8@TVbc 8Z!4Z 5Kbf!g :J 3Jy4I J U Ug 9J&)%_job_owner_profile.._s4NAuuT{f$??f (??s??F)r&anyr!)rQrRjobssf& r1_job_owner_profiler`QsG%g{DA 3NN333NN N NN !& ))r3cRV^8dQhR\R\\,R\/#rPrS)r0s"r1r2r2ds%x}r3c@\W4pV'g \4hV#)a Owning profile for the get/update/pause/resume/trigger/delete family; 404 when no profile holds the job. Same hint validation as the run lookup, so a wrong-profile hint from the cross-profile list cannot 404 (or act on the wrong store for) a job the server can locate.)r`r:)rQrRselecteds&& r1 _job_profilerdds"&2H  Or3c*V'g \4hV#N)r:)jobs&r1_foundrhns  Jr3c$V^8dQhR\/#r-rRr?)r0s"r1r2r2ts(*(*#(*r3cBT;'gRP4pVP4R8wd\VRR4#.p\4FNp\ VP R4;'gR4pV'gK1VP \VRR44KP /p.pVFp\V\4'gKVP R4;'gVP R4pV'dVR8XdVPV4KgVP V4p V e3VP R 4'gKV P R 4'dKWuV&K \VP44V,# \d\P!RT4EKTi;i) allrUTrXz'Failed to list cron jobs for profile %srWrQunknownis_default_profile)striplowerr&r(r?rYextend Exception_log exception isinstancer>appendlistvalues) rR requestedall_jobsitemrXby_idunkeyedrgjidexistings & r1_list_cron_jobs_syncrts\!!E((*IE!%idCC&(H#%488F#))r*  L OO24dK L &(*E$&G#t$$ ggdm00swwx0 cY& NN3  99S>   GG( ) )(,,?S2T2T#J!"   ' ))- L NNDd K K Ls;E77"FFcFV^8dQhR\R\\,/#r-rQrRrS)r0s"r1r2r2s"\\s\Xc]\r3c@\\\W4RV44#)get_job)rhr&rdrQrRs&&r1_get_cron_job_syncrs (f)F SYZ [[r3z%Y-%m-%d_%H-%M-%ScRV^8dQhR\\,R\R\/#)r-rRrQr.)rr?r)r0s"r1r2r2s% ; ;8C= ;# ;$ ;r3cV'd\V4wr#M \4p\V4R, R, V, # \d\4pL7i;i)uIOutput docs live under the job's home — resolve it even without a hint.cronoutput)r)rt_get_hermes_homer)rRrQ_r=s&& r1_cron_output_runs_dirrsU .09OA|()   & 1F ::  .+-L .s AAAc:V^8dQhR\\,/#rjrr?)r0s"r1r2r2s++x}+r3c#N"V'gRxR#\V4wr\T4P4\ 4P48XdRxR#\ \ T44pTx\T4R# \d RxR#i;i \T4i;i5i)aKeep reads in the owner's profile context for the whole run-history build. Filename stems, the execution ledger and ``hermes_time``'s configured zone all resolve through the *current* ``get_hermes_home()``; without this scope a cross-profile listing decodes another profile's docs with the dashboard's zone (an hours-off timestamp) and reads the dashboard's executions.db. The dashboard's own profile needs no override (its home is already current). N)r)rtrresolver_set_hermes_home_overrider?_reset_hermes_home_override)rRrr=tokens& r1_owner_home_scopers  ,W5 L!!#'7'9'A'A'CC  %c,&7 8E+#E*   $E*s@B% A?AB%.B2 B%?BB%BB% B""B%cFV^8dQhR\R\\,/#)r-pathr.)rrfloat)r0s"r1r2r2s**T*huo*r3c \P!VP\4p\ 4pTe!TP TR7P4#TP4P4# \dR#i;i)uEpoch seconds for an output filename's wall time. save_job_output writes the stem with hermes_time.now() — the configured IANA timezone (HERMES_TIMEZONE / config), falling back to server-local. Read it back with that same ZONE, not a fixed offset snapshot of today's local offset: a snapshot is wrong when the configured zone differs from the server's, and off by an hour for a historical file across a DST transition. With no configured zone, astimezone() on the naive datetime resolves the offset in effect on the filename's own date. N)tzinfo) rstrptimestem_CRON_OUTPUT_FILENAME_FORMAT ValueError _get_timezonereplace timestamp astimezone)rnaivetzs& r1_cron_output_run_timestamprsr!!$))-IJ B ~}}B}'1133     ' ' )) s%A33 BBc<V^8dQhR\R\R\/#)r-r max_charsr.)rintr?)r0s"r1r2r2s!5545C5#5r3cVPRRR7p\P!RRT4P 4p\ T4T8:dT#TRT^, P 4R,# \dR#i;i)z utf-8-sigr)encodingerrorsrnz\s+ Nu…) read_textOSErrorresubrqlenrstrip)rrrawpreviews&& r1_cron_output_run_previewrsznnk)nDffVS#&,,.G 7|y  ?Y] # * * ,u 44 sA.. A=<A=c~V^8dQhR\\\\3,,R\\,/#r-rgr.)rr>r?rr)r0s"r1r2r2s+htCH~&>8E?r3ct\V\4'gR#VPR4p\V\\34'd \ V4#\V\ 4'd@VP 4pV'gR#\P!V4P4#R# \dR#i;i)N last_run_at) rwr>rYrrr?rqr fromisoformatrr)rgrtexts& r1_cron_job_last_run_timestamprs c4  ''- C#U|$$Sz#syy{ ))$/99; ;   s#B(( B76B7chV^8dQhR\\\\3,,R\/#r)rr>r?r)r0s"r1r2r2s',,8DcN#;,,r3c\V\4'gR#\VPR4;'gR4P 4pV'gR#VP RR4P 4#)rn last_statusrr)rwr>r?rYrqrupper)rgstatuss& r1_cron_output_status_labelrsV c4  '--2 . 4 4 6F  >>#s # ) ) ++r3c V^8dQhR\R\R\\,R\\\3,/#)r- started_attitlerr.)rr?rr>r)r0s"r1r2r2s9U3#SWX[]`X`Sar3cRRTRT;'gRRRRVRVRVR^R ^R ^R ^R RR RRRRR/#)rrNsource cron_outputr last_activeended_at input_tokens output_tokens message_counttool_call_countrGcwdarchivedF is_activer9)rrrs&&&r1_cron_output_run_rowrsX7??d-jzJ1 tEU r3cFV^8dQhR\R\\,/#)r-rr.)rrr)r0s"r1r2r2sr3c\V\4'dVP4'gR#\P!VP44P 4# \ dR#i;irf)rwr?rqrrrr)rs&r1 _iso_to_epochrsS dC  %%djjl3==?? s1A"" A10A1chV^8dQhR\R\\\\3,,/#r-canonical_job_idr.)r?ryr>r)r0s"r1r2r2$s'T#s(^8Lr3ct^RIHpV!V^dR7p.pTFp\TP R4;'gR4R 9dK.TP R\TP R4;'gR4R\ TP R44;'gRR\ TP R44R\TP R4;'gR4R \TP R 4;'gR4P4/4K TPR R R 7T# \d.u#i;i)uhTerminal execution-ledger rows for the job, newest first. Each script-only fire creates exactly one ledger row (claimed → completed / failed), so the ledger — not filename proximity to ``last_run_at`` — is the per-attempt record that pairs an output doc with its real status. Read inside the owner-home scope so it opens the OWNER's cron/executions.db. )list_executions)rQlimitrrnrW claimed_at finished_aterrorcVR,#)rr9rs&r1+_owner_profile_executions..=s,r3TrMreverse) completedfailedro) cron.executionsrrtr?rYrxrrqsort)rrrowsterminalrows& r1_owner_profile_executionsr$s3&6cB&(H swwx &&B '/Q Q  #cggdm))r* - (=>EE# =)?@ c#''(+11r2 S)//R0668    MM/M> O  sD'' D76D7r@cjV^8dQhR\\\3,R\R\R\/#)r-attemptr grace_secondsr.)r>r?rrbool)r0s"r1r2r2As:BB #s(^B).B?DB Br3cVR,\P!VR,48dR#VR,pVRJ;'g WV,8*#)aWhether an output doc's timestamp falls inside a ledger attempt's window. ``save_job_output`` runs after the script finishes but before ``finish_execution`` closes the attempt, and both clocks are ``hermes_time.now()`` in the owner's zone, so a doc written by an attempt lands within ``[claimed_at, finished_at + grace]`` of THAT attempt (a still- open attempt has no ``finished_at``). Older attempts closed before this doc was written, which is what keeps a fast-firing job's status from bleeding onto an earlier run's row. The doc's filename keeps whole seconds only, so the claim is floored to its second: an attempt claimed at ``:00.500`` that writes at ``:00.750`` files its doc as ``:00``. gMbP?rFrN)mathfloor)rrrfinishs&&& r1_execution_containsrAsFEDJJw|'<== ] #F T> A AZM+AAAr3cHV^8dQhR\R\R\R\/#)r-rrfallbackr.rk)r0s"r1r2r2Vs.``C``s`s`r3cT;'gRPRR4P4pVR8XdV#V'gV#VR8XdV'dV RV 2#V RV 2#)rnrrUNKNOWNFAILED · )rr)rrrlabels&&& r1_execution_status_titlerVse \\r " "3 , 2 2 4E  %*h%65eWD _%PTU]T^G__r3c4V^8dQhR\\\\3,,R\R\\,R\R\ \ \\\3,,\ \\\3,,3,/#)r-rgrrRrr.)rr>r?rrtuplery)r0s"r1r2r2_sv@@ $sCx. !@@c]@  @  4S#X d38n!5 56 @r3c |\W!4p\RVPR44RRR7p\ V4p.pVRVFqp\ V4p V fVP 4Pp \V4p TPRR V R VP 2/\Y;'gR V 4C4Ks V'g;\;QJdR V4F 'gK RM R M !R V44'dWv3#\V4p V f.V3#Rp \V\4'd3\!VP#R4;'gR4P%4p \'V4;'gR p V 'dV RV 2p RR V R2/\WV 4C.V3# \d.pELti;i \dRp ELIi;i)a{SessionDB-less run records for jobs that never create agent sessions: ``(docs, attempts)``. Script-only (no_agent) jobs deliberately skip SessionDB (cron/scheduler.run_job), so their completed runs are invisible to the run-history endpoint. Their output docs (one .md per fire under cron/output//) and the execution ledger (one row per fire) are the only per-run records. ``docs`` are rows in /api/sessions shape with source='cron_output', newest first, so the frontend reuses SessionInfo; ids use a cron_output: prefix that can never collide with a SessionDB session id. ``attempts`` are the job's terminal ledger rows, newest first. A doc never records its execution, so which attempt it stands for is decided by ``_reconcile_cron_runs`` beside the sessions, never here, and never from ``last_run_at`` proximity, which mislabels an older doc when the newest run's doc is missing. c3T"TFqP4'gKVxK R#5irf)is_file)rZrs& r1r\)_list_cron_output_runs..vs H5dTT5s( (z*.mdcVP#rf)rX)rs&r1r(_list_cron_output_runs..wsTYYr3TrNrrW cron_output::Script-only runc38"TFqR,R9xK R#5i)rNrrr9)rZrs& r1r\rsXxG8$(??xsFrn last_errorrz:latest)rsortedglobrrrstatst_mtimerrxrrr^rrwr>r?rYrqr) rgrrRr output_dirfilesattemptsdocsrrr latest_tsrs &&&& r1_list_cron_output_runsr_s('wAJ Hjoof5 H& ))9:H!#Dfu /5   !!YY[11 +40 L!1 2!DII;? ":/K/K:KWU   ssXxXsssXxXXX~ -S1I8|G#tcggl+11r288: %c * ? ?.?E'gY' -.g6  y 9    E  !  !s#%FF* F'&F'* F;:F;g@chV^8dQhR\R\\\\3,,/#r)r?rr>r)r0s"r1r2r2s'  s xS#X7O r3cD^RIHpV!V4# \dR#i;i)zThe job's claimed/running ledger attempt under a live owner, or None (fail closed). Must run inside the owner-home scope so it reads the OWNER's executions.db. )live_inflight_executionN)rrrt)rrs& r1_live_inflight_executionrs( ;&'788 s  cV^8dQhR\\\3,R\\\\3,,R\/#)r-sessioninflightr.r>r?rrr)r0s"r1r2r2s<``4S>`Xd38n5M`RV`r3cV'dVPR4eR#VPR4'dVR,VPR48H#\VPR44p\VPR4;'g^4pTRJ;'dY2\ , 8# \\3dR#i;i)a&Whether the scheduler still OWNS this never-closed run session (#88443). ``is_active`` is a 300s activity window, so a live run inside a long tool call (no heartbeat, no message) reads inactive exactly like a zombie whose process died. Ownership is the durable answer: the job's in-flight attempt is held by a live process and this session is that attempt's run. A unified-runtime run names its execution, so that is exact; a legacy run must have started under the claim, so an older never-closed run of the same job predates it and stays a zombie. rNFcron_execution_idrWrr)rYrr TypeErrorr_OWNERSHIP_CLAIM_GRACE_SECONDS)r r!rrs&& r1 _run_owned_byr's w{{:.:{{&''*+x||D/AAAx||L9:J7;;|499:  T ! _ _jA_4_&__ z "s+B*B**B?>B?cV^8dQhR\\\3,R\\,R\\,/#)r-r rRr.r")r0s"r1r2r2s9HHd38nHx}HX`aeXfHr3cdVPR4R8wdR#VPR4;'g\VPR44pV'gR#VPR4eR#\V4;_uu_4\V\ V44uuRRR4# +'giR#;i)a``scheduler_owned`` for one session row, or None when it is not a cron run session. The session-detail endpoint stamps this so a client re-checking a run it already has open (a restored tab, a send) gets the same answer as the runs list. A unified-runtime run's ``local-*`` id says nothing, so the caller stamps the row's ``cron_job_id`` / ``cron_execution_id`` (``SessionDB.cron_run_identity``) first; a legacy ``cron_{job_id}_{timestamp}`` id still names its job. rrN cron_job_idrWrF)rYrrr'r)r rRrQs&& r1cron_run_scheduler_ownedr+s{{8& [[ ' Q Q+>w{{4?P+QF {{:* 7 # #W&>v&FG $ # # #s >B B/ cRV^8dQhR\R\\,R\/#r-rQrRrr?rr)r0s"r1r2r2s+5n5nS5n8C=5nPS5nr3c \W4pTpRpV'd?\VRV4pV'd*VPR4'd\VR,4p\ ^\ \ V4^d44p\V4;_uu_4\VRR7pVPWF^R7pVP4\P!4p \V4p VFp V PR4RJ;'d,WPRV PR ^44, R 8V R &\W4V R &\!V PR 44V R &V'gKW;R&K \#WTW64wrRRR4R\%XX X WF4RV/# \\3d^pEL.i;i TP4i;i +'giLQ;i)uRun history for a cron job, newest first: agent sessions PLUS script-only fires. Agent runs are ordinary ``source='cron'`` sessions: a legacy ``cron_{job_id}_{timestamp}`` id, or a unified-runtime ``local-*`` id bound to this job by its scheduler admission. Backed by ``SessionDB.list_cron_job_runs`` — bounded index range scans, so cost scales with this job's runs, not total cron history. Script-only (no_agent) jobs never write sessions; their per-fire output docs (``_list_cron_output_runs``) fill the gaps. The two representations are reconciled PER EXECUTION, not by branch: a job can switch modes without changing its id (update_job supports no_agent on an existing record), so a surviving historical agent session must not hide newer script-only fires and a recent session must not hide older script output. Rows carrying the same execution (an agent fire writes BOTH a session and an output doc) are de-duplicated by execution id, or by timestamp window for a legacy session that names none; script-only rows that match no session are added in. All owner-scoped reads (SessionDB, output docs, execution ledger, filename timezone) run inside the owner's profile scope so the dashboard's own zone/store is never borrowed cross-profile. NrrWT) read_only)roffsetrrri,rscheduler_ownedrrRrunsr)r`r&rYr?maxminrr%rrr*list_cron_job_runsclosetimerr'rr_reconcile_cron_runs)rQrRrrc canonicalrglimit_ndb session_runsnowr!srrs&&& r1_list_cron_job_runs_syncr@s*"&2HI C$Xy&A 3774==CIIaSZ-. 8 $ $ )(d C 00RS0TL HHJiik+I6AUU:.$6uuC%% WXW\W\]iklWmBnr?rr)r0s"r1r2r2sx<<tCH~&< tCH~ <4S>"< <  <  $sCx. <r3c HaaRRlpVUu/uF%qfPR4'gKVR,VbK' upoVUu.uFqfPR4'dKVNK pp\V4UU u.uFwrV R,R9gKW3NK p pp V UU u0uFwrV R,S9gKVkK p pp \4p \V4p VEFp\ VPR4;'g^4oV UU u.uF$wrW9gK \ V S4'gK!W3NK& ppp V'g#V!SV4'gV P V4K\VVV3RlR7wppV PV4V PV4VR,S9gV!SV4'dKV P /VCR \VR,VR ,VR ,4/C4EK V FwppW9dKVR ,;'g VR ,pV!VV4'dK9VR ,pT P RR V RV 2/\T\VR,VR4T;'gR4C4K V PRRR7V RV#uupiuupiuup piuup piuup pi)a/One row per execution, newest first: each terminal ledger attempt is its session, else the output doc it wrote, else a metadata row from the ledger. An agent fire writes BOTH a session and an output doc; sessions carry the richer record (tokens, message counts, chat navigation), so the session wins and is never dropped. A unified-runtime session names its execution, so that pairing is exact. A doc only has a window guess (``_execution_contains``), so docs pair with attempts only once every attempt's session is known (``_doc_writer``), one doc per attempt: the doc folds into its writer's session, or into a legacy session (which names no execution) by time, and otherwise is its writer's row with the ledger status. A doc no attempt claims is matched against every session by time, and kept if none matches. ctV^8dQhR\R\\\\3,,R\ /#)r-doc_tssessionsr.)rryr>r?rr)r0s"r1r2*_reconcile_cron_runs..__annotate__-s3bbbd38n)=b$br3cxa\;QJdV3RlV4F 'gK R# R#!V3RlV44#)c3F<"TFp\SV\4xK R#5irf_doc_matches_session_SESSION_DOC_MATCH_SECONDS)rZr?rDs& r1r\8_reconcile_cron_runs..matches...s"aX`ST'3MNNX`s!TF)r^)rDrEsf&r1matches%_reconcile_cron_runs..matches-s.saX`assasasaX`aaar3r$rrWrcf<\SV^,SPV^,R,44#)rW) _doc_writerrY)c by_executionrDs&r1r&_reconcile_cron_runs..?s+{61Q4Q]QaQabcdebfgkblQm7nr3)rMrrrrr z:exec:r NcJ\VPR4;'g^4#)rrrYrs&r1rrTUseAEE,$7$<$<1=r3Trr) rY enumeratesetryrrrxr5addrrr)r=rrrrrMr?legacyindexar representedpairedmergeddoc candidatesrwhenrrSrDs&&&&& @@r1r9r9s&b8Db|!uuM`Ga-A)*A-|bL% HAUU3F-GaaF H+4X+>i+>xu!H+QhBh  +>Hi)1MXUQtW 5L55KM%F , Fsww|,11219QXU,!1DQ1O!uj Q6<00 c" Z-now 5 4=L (GFF,C,C  rrg'>wx?PRYZaRbdghodp'qrs$#w   }%>>)> 4   L!1 2&@ "-gh.?HYZ\a\i\ieik  # KK=tKL &5>Mc HiM Qs?JJJ J 2J JJ/J< J JJc V^8dQhR\R\\\3,R\\\\3,,R\ /#)r-rDrr r.)rr>r?rrr)r0s"r1r2r2Ys?   S#X $sTWx.AY ^c r3cVR,pVRJ;'dW8VRJ;'g\W\4'*VR,)3#)aSort key over a doc's candidate attempts, likeliest writer first. ``save_job_output`` runs before ``finish_execution``, so an attempt that closed before the doc's second only reaches it through the grace. Among the rest, an attempt whose own session spans the doc beats an overlapping one that has none (a manual run claimed while a tick's run was still going); then the newest claim wins. rNrrI)rDrr rs&&& r1rQrQYsP] #Fd..v4``3FE_``   r3cjV^8dQhR\R\\\3,R\R\/#)r-rDr rr.)rr>r?rr)r0s"r1r2r2is8 B B Bc3h BPU BZ^ Br3c\VPR4;'g^4p\VPR4;'gVPR4;'gT4pW2, Tu;8*;'d WB,8*#u#)u@Whether an output doc belongs to a session's run. The doc is written when the run FINISHES, so its filename timestamp sits at the run's end — compare against the session's full span, not its start: ``[started_at - grace, last_active + grace]`` (``last_active`` covers the still-open case where ``ended_at`` is None). rrrrV)rDr rstartends&&& r1rJrJisj '++l+00q 1E  J'NN7;;}+ENN OC  F A Ac.A AA AAr3cRV^8dQhR\R\R\\,/#r-rQbodyrRr?rr)r0s"r1r2r2ys%#]Xc]r3c\W4p\V4wrE\\VRV44p\ VP V4pRV9d\ VPR4V4\PV4'd%/VCVCpRV9d RV9dRVR&\V4\VRW4p \T 4# \dh\dp \R\T 4R7T hRp ? ii;i)rrJskillsskillN update_jobr6)rdr)rhr&rNr<rrY_EXECUTION_FIELDS intersectionrrr rr?) rQrkrRrc profile_namer=rr< effectivergexcs &&& r1_update_cron_job_syncrwysF,HG%7%A" 0y&QR3DLL,O W $ 1'++n2M| \  ) )' 2 2/8/w/I7"wg'=%) '" 29 =&|\6S #;  GCH=3FGs$A5B?1B??C1C1C,,C1cFV^8dQhR\R\\,/#rrS)r0s"r1r2r2s"```x}`r3c@\\\W4RV44#) pause_jobrhrrdrs&&r1_pause_cron_job_syncr|s *<+H+W]^ __r3cFV^8dQhR\R\\,/#rrS)r0s"r1r2r2s"aa#a ar3c@\\\W4RV44#) resume_jobr{rs&&r1_resume_cron_job_syncrs *<+H,X^_ ``r3cFV^8dQhR\R\\,/#rrS)r0s"r1r2r2s;;3;#;r3c\W4p\\VRV44pVPRR4'*;'gVPR4R8Hp\ W#R,VR7p\VRVR,4pV'd(VPR4VPR48wdV#V'g\ R R R 7hV'dV#/VCRR RR /C#)resolve_job_refenabledTstatepausedrW)forcerriz:Job is already running or was claimed by another schedulerr6Fr)rdrhr&rYr"r )rQrRrcrgrran refresheds&& r1_trigger_cron_job_syncrsF,H '2CVL MC  4( ( H HCGGG,<,HE $X4y FC&xCIFIY]]=1SWW]5KK 4pqq ;c :9eWk ::r3cFV^8dQhR\R\\,/#rrS)r0s"r1r2r2s# r3c\W4p\VRV4pT'g \ 4hRR/# \dp\R\ T4R7ThRp?ii;i) remove_jobrqr6NokT)rdrrr r?r:)rQrRrcremovedrvs&& r1_delete_cron_job_syncrs_F,HG*8\6J  $< GCH=3FGs 0 AAAz/api/cron/jobsc$V^8dQhR\/#rjrk)r0s"r1r2r2sGG#Gr3c>"\\V4GRjxL #L5irf)rr)rRs&r1list_cron_jobsrs'("\\W4GRjxL #L5irf)rrrs&&r1 get_cron_jobrs'(:FL LL Lrz/api/cron/jobs/{job_id}/runscRV^8dQhR\R\\,R\/#r-r.)r0s"r1r2r2s+ZZSZ8C=ZPSZr3c@"\\WV4GRjxL #L5irf)rr@)rQrRrs&&&r1r6r6s'(@&SXY YY Y cFV^8dQhR\R\\,/#r-rkrR)rrr?)r0s"r1r2r2s"NN N Nr3c>"\\W4GRjxL #L5irf)rr)rkrRs&&r1create_cron_jobrs'(=tM MM Mrz/api/cron/delivery-targetsc:V^8dQhR\\,/#rjr)r0s"r1r2r2s  Xc] r3c0"RRRRRRRR/.p^R IHp\V4;_uu_4VPV!44RRR4R V/# +'giR T/#;i \dh\ d\ P!R 4R T/#i;i5i) uDelivery targets for the cron dropdown: implicit ``local`` plus the configured gateway platforms (a platform without a cron home channel is still listed with ``home_target_set: false`` so the UI can say so). ``cron_delivery_targets()`` reads each platform's home channel through ``get_secret``, which fails closed once this process hosts more than one profile home (the dashboard/desktop ``serve`` backend flips multi-profile hosting on the first ``?profile=`` request). The read must therefore run inside the profile scope, exactly like the sibling cron routes — otherwise the poll raises ``UnscopedSecretError`` on every tick and the dropdown silently loses every configured platform.rWrErXzLocal (save only)home_target_setT home_env_varNcron_delivery_targetsz%GET /api/cron/delivery-targets failedtargets)cron.scheduler_deliveryrr+rsr rtrurv)rRrrs& r1get_cron_delivery_targetsrsgv':? w @sP BA!A A!B A A!BA!!B6B BBBcRV^8dQhR\R\R\\,/#rjrl)r0s"r1r2r2s*VV#V]VXc]Vr3c@"\\WV4GRjxL #L5irf)rrw)rQrkrRs&&&r1update_cron_jobrs'(=vWU UU Urz/api/cron/jobs/{job_id}/pausecFV^8dQhR\R\\,/#rrS)r0s"r1r2r2s"OOOx}Or3c>"\\W4GRjxL #L5irf)rr|rs&&r1pause_cron_jobrs'("\\W4GRjxL #L5irf)rrrs&&r1resume_cron_jobr'(=vO OO Orz/api/cron/jobs/{job_id}/triggercFV^8dQhR\R\\,/#rrS)r0s"r1r2r2s"QQ3Q#Qr3c>"\\W4GRjxL #L5irf)rrrs&&r1trigger_cron_jobrs'(>P PP PrcFV^8dQhR\R\\,/#rrS)r0s"r1r2r2rr3c>"\\W4GRjxL #L5irf)rrrs&&r1delete_cron_jobrrrz/api/cron/firec$V^8dQhR\/#)r-request)r )r0s"r1r2r2sWPWPWWPr3c d"^RIHpVPPRR4pVP R4'dVR,P 4MRp\ P!\4GRjxL pV!4!T\VRRR RR 7\VRRR RR 7;'gR\VRRR RR 7;'gRR 7pVf\RR/RR7#VP4GRjxL p\V\4'dT;'g/PR4MRpV'g\RR/RR7#\\ V4GRjxL pV'g\RRRV/^R7#\#WV4GRjxL p V f\\$VRVR4GRjxL \\*V4GRjxL 'd-\&P,!RW4\RRRRRVR V/^R7#\RR!RVR V/R"R#\/\04/R$7#V wr\V \4'dV P3RV4V R"8XdR#\/\04/MRp \WV R$7#ELELw \d/pELi;iEL,ELL \d\&P(!RTRR7EL i;iL5i)%uChronos managed-cron fire webhook (NAS -> agent) — gateway forwarder. Gated by the NAS-minted JWT (path is in ``PUBLIC_API_PATHS``), not the dashboard cookie. Execution belongs to the GATEWAY process (it owns the live platform adapters relay-fronted and E2EE targets need), so the fire is forwarded to the gateway api_server's own ``/api/cron/fire`` on loopback and its response passed through (the gateway re-verifies the JWT). Gateway unreachable -> 503 so NAS retries; deliberately NO local-execution fallback. )get_fire_verifier AuthorizationrnzBearer :NNNrchronosexpected_audiencedefault nas_jwks_url portal_url)rr jwks_or_keyissuerrzinvalid fire tokeni)r7rQzmissing job_idrqrgonenote_fire_forward_failurezscheduled fire could not be forwarded to the gateway api_server (127.0.0.1 loopback unreachable); the gateway process may be down or its api_server adapter not bound (missing API_SERVER_KEY)z&could not stamp last_fire_error for %sTexc_infozcron fire dropped: gateway for profile %r is deliberately stopped (desired_state=stopped); job %s will resume via Chronos reconcile on next gateway startgateway_stoppedr8zMgateway deliberately stopped; fire dropped, jobs re-arm on next gateway startrRzgateway unreachable; retryiz Retry-After)r7headers)%plugins.cron_providers.chronos.verifyrrrY startswithrqasyncio to_threadr'rr jsonrtrwr>rr!r#r&rudebugr$infor?_CRON_FIRE_RETRY_AFTER_SECONDS setdefault) rrauthrcfgclaimsrkrQrR forwardedr7 gateway_bodyrs & r1cron_fire_webhookrsH ??   3D $ : :DHNN E!!+. .C  !#vy:MWYZCNBOWWSWsFI|RHPPD F ~W&:;MM\\^#,6dD+A+Adjjb  h 'tF W&67SII++A6JJG Xvx@cRR3GTJJI X(&++   "((FP P P II:    /mfw     2HfiQX Y"C(F$GH  !*K,%%&1FQUXFX}c"@AB^bG  w OOQ /$ KK  X JJ?RV W W X QsA0J02I!31J0%J0>J0I'-I$.I'2J0J0-"J0I; J0 J0<I>=J0JJJ!J04J.5 J0?B#J0$I'' I84J07I88J0>J0J$J+'J0*J++J0cFV^8dQhR\\,R\/#)r-rRr.)rr?ry)r0s"r1r2r2_sXc]tr3c(^RIHpHp\V4;_uu_4V!4pRp^RIHpV!4Uu.uF$qfP R4'gKVR,NK& ppRR.VOpRRR4.pXFYp V!V 4p X'd6V P R .4Fp V P R 4R 8XgKWKR &K! VPV 4K[ V#uupi \d\P!RRR 7Li;i +'giL;i)a Built-in + ``profile``'s plugin blueprints, with the ``deliver`` slot's options rewritten from that profile's configured gateway platforms. Plugin discovery can import plugin code, so this runs off the event loop, inside the profile scope that picks the plugin manager.)blueprint_catalog_entrylist_blueprintsNrrWoriginrEz?cron_delivery_targets unavailable; using static deliver optionsTrfieldsrXrDoptions) cron.blueprint_catalogrrr+rrrYrtrurrx) rRrrcatalogdeliver_optionsrt platformsentriesrentryfs & r1_blueprint_catalog_syncr_sP w ' '!# i E*?*AQ*AQUU4[4*AIQ'=9=O (G '* YYx,55=I-#2iL- u  NR i JJXcg h i ( 's? DCC C CC#C>;D=C>>D D z/api/cron/blueprintsc:V^8dQhR\\,/#rjr)r0s"r1r2r2|s<<  z /api/cron/blueprints/instantiatec0V^8dQhR\R\/#r)rr?)r0s"r1r2r2s<<&D =C(C$C(5C&6C(;D=<C(>C!CC!!C(&C((D:=D:>7D55D::D=)rmrf))r)N>ropromptrArnno_agentr)z__doc__rrrrr8 contextlibrrpathlibrtypingrrrrfastapir r r fastapi.responsesr hermes_cli.web_depsr hermes_cli.configrhermes_cli.web_server_cronrrrrrrrrrhermes_cli.web_modelsrrrhermes_cli.web_routers._commonrru hermes_timerrhermes_state_keysrhermes_constantsrrrrr rrouterr!r"r#r$r%r&r'r(r)r*r+r:rNr`rdrhrrrrrrrrrrrrrrrr&rr'r+r@rKr9rQrJrrrwr|rrrrrYrrr6postrrputrrrrdeleterrrrrrr9r3r1rs %,,55*$%_^651 68TU!">@\] $%DFb c!%&FHd!e$()LNj$k!68TU="56 02NO.0LM#$BDde46VWB6*& (*V\ 3 ;++6**5",&:B*`@J"% `,H(5nr#<~  BH*`a;,"$ GG %&M'M *+Z,Z NN () * 2 %&V'V ,-O.O -.P/P ./Q0Q()P*P WPWPt8 "#<$<" /0<1