Spaces:
Running
Running
Commit History
6 days ago
-
deploy CREST_AI 940d4a7: CREST-iMAP c5184759 + CRESTIMAP_SHA stamp Running
Verified signature3f1dc17
11 days ago
-
deploy CREST_AI 939800a
Verified signaturef2497b5
14 days ago
-
caltrace: record calibration rounds for the review pilot
Verified signatureb692242
15 days ago
-
Compute priority: health user_ops count (autocal idle gate input); nowcast-brief forced refresh cooldown (10 min)
Verified signatured55630c
19 days ago
-
NARR reader hardening + TEMP gap visibility (CREST_AI 08a219d)
Verified signaturedd54d43
21 days ago
-
Health-check fix batch (CREST_AI 3dca271)
Verified signature2ac66f1
27 days ago
-
finalize_episodes: clip 'ended' to now; peak_obs from episode-window hydro rows only
Verified signature789a74f
28 days ago
-
CONUS state mosaic: full-basin runs warm-start from fleet pre-runs stitched across the gauge and its upstream gauges; full run is the default scheme again
Verified signature6193b98 -
Hindcast runs use the fleet's rows + states: value-based cache keys, merging fleet fetch, gap-safe cache plan, fleet state carried past the fleet period, speed scheme default
Verified signature1838f0f
29 days ago
-
UX-level user isolation: per-browser job ownership + tokens, configuration-tagged caches, calibration no longer locks the gauge, global + per-user CPU admission, tab guard
Verified signature90c988a
-
Auto-calibration plumbing: per-check miss history, params refresh from CREST_state (newer wins), baseline-relative save, params/ append-only in persist, autocal records on /api/events
Verified signature8469f55
-
CREST-miss guard part 2: a listed episode the guard disowns is dropped from the list and purged
Verified signature11e7351 -
CREST-miss guard: no inundation map when EF5's peak is < 30% of the observed peak at the trigger gauge; misses listed in the Events panel
Verified signature6885dec
-
events: never pair Delete with in-place Add (hub drops unchanged adds -> frames lost), manifest lists only stored frames, demotion clamped off, calendar-month list roll-off, reconcile_store; player preloads next frames
Verified signatureda72d4f
-
health: restart-aware tick liveness (warming / last-publish fallback) so a cold-started runner is not reported STALE
Verified signature4c4794d
-
health: TEMP freshness limits match NARR's real publish lag (45 d write-age, 2 months coverage)
Verified signature5557d05
-
admin archive: owner-only (ADMIN_USERS) view of EVERY stored 2-D inundation result (listed + rolled-off) — /api/admin/archive + Archive panel; open any result on the map (shared backend)
Verified signaturef2a65be
-
risk view: tile-first worldpop/OSM probes (CREST_riskdata pre-hosted parquet; live fetch = fallback)
Verified signatureae833ba
-
worldpop: parallel band fetches + slow-100m->1km heuristic (first live build sat >15 min on striped 100m ranges)
Verified signature0198428 -
osminfra: name each mirror's failure in the status + lz4/mail.ru mirrors
Verified signature5820aae -
osminfra: cache Overpass failures 60 s (not 6 h) + sticky last-good mirror
Verified signature57a6730 -
Risk view (map_visual lens for 2-D inundation): /api/riskprobe per-PIXEL depth/speed/flow-dir + DEFRA hazard class + WorldPop 2026-2030 population (resampled to the solver grid) + OSM infrastructure values; Dockerfile CRESTIMAP_REF -> e8652781 (maxspeed/flowdir rasters)
Verified signaturea8f20b9
-
obs store: replace-don't-merge on refetched windows so USGS-scrubbed provisional values (phantom floods) self-heal instead of persisting forever
Verified signatureac9fc1b
-
retention: monthly animation cleanup — when an event rolls off the list, clear only its animation (depth_* frames + archive.parquet) and KEEP the simulation results (manifest + max-depth + final + DEM) until RESULTS_MAX_AGE_D (365 d); orphan result folders swept at that horizon
Verified signaturef7984a1 -
retention: keep depth frames for ALL listed events (KEEP_FULL defaults to KEEP_EVENTS=40) so the time scrubber works for every event — demotion at 8 was deleting ended re-run episodes' frames within hours (user report 2026-08-21)
Verified signaturecd47070
-
health: watch MRMS Pass2 / PET / TEMP archive freshness
Verified signature7f30fae
-
event_run cold=1: full cold re-run of a listed episode (no warm-start frame; spec 'cold' stamp makes workers drop resident sessions) — basin re-run of the list
Verified signatureff0fe9c -
Event EF5 extent = HUC12 basin bounds (union with default square): the sqrt-area square centred on the outlet clipped elongated catchments (Spoon R 3,884/4,241 km2, Pope Ck 199/449); hucdomain.basin_bounds; run_gauge(domain_bbox=)
Verified signature42c3d5f -
Basin domains (never a rectangle): 2-D event domain = whole HUC12 basin of the trigger gauge (hf_data/hucdomain.py, WBD tables on CREST_data wbd/huc12); domain_huc.tif + domain.geojson in the bundle; CPU rung trims by HUC12 units; frontend draws HUC12 units + basin outline, no rectangle; Dockerfile pins crestimap 678cbf17
Verified signaturec5d8188
-
sync: episode final product takes peak observed flow from the scorer's full USGS series (manifest hydro understated 15.7 vs 34.5 on 03274650); run_nowcast_all.py parity
Verified signature73f10d8 -
health: queue ok keys off never-published bundles, not swept re-sims
Verified signatureff335a8 -
V30.1: wall-clock budget for the demoted CPU solve rung + tick wedge detection (a 39-h local solve had starved the hourly event tick)
Verified signaturee9f5960
-
V30 operations: episode final products (consolidated stats + event-scoped nowcast verification replace the running event on end), CPU rung demoted to last resort behind worker claims, provenance stamps in manifests, /api/health self-monitoring, runner-split plumbing (EVENT_TICK / EVENT_RUNNER_URL), event-score labels + no Model-options panel in nowcast mode
Verified signature3490275 -
V29 fixed episode windows: anchored at trigger-12h (no moving window), USGS-obs-based episode end, frame carry-forward on republish, warm-start IC from previous depth frame, in-flight queue shown in the event panel
Verified signature15fc593 -
queue sweep: stale = spec queued-stamp age + no fresh claim (id age alone swept re-enqueued episodes and killed a live claim mid-solve)
Verified signature27dce6c -
event ladder: delegated worker hand-off frees the runner (no more result-wait/CPU while claimed); new detections outrank episode re-sims; fresh claims survive re-enqueue; event_run gains t0 backdating + defer for refills
Verified signaturee2681d6 -
Nowcast MRMS rain-radar overlay (24h/48h/7d anim) + persistent 2D depth legend + queue worker wake-ping
Verified signaturee66a060
-
Serve cached fleet rows instantly while frames re-render (suppress duplicate live rows)
Verified signaturec051cae -
Fix rainless event sims: fill tar-missing MRMS hours from mrms_recent; surface missing forcing; fleet states + DI-LSTM DA for nowcast runs; 'nowcast' trace label
Verified signaturecf1e96b -
V27 P1: event job queue (shadow mode) — bundle EF5 grids + spec for GPU workers
Verified signature8b3c18a -
fix event overlay stale bounds; basin ring must contain trigger gauge
Verified signature2862bbc -
fix event overlay stale bounds; basin ring must contain trigger gauge
Verified signatureae21ae8 -
fix event overlay stale bounds; basin ring must contain trigger gauge
Verified signaturee40be37 -
event controls docked atop panel; animate:false zoom; multi-hue depth scale; pixelated overlay
Verified signature19ebb76 -
fix event overlay stale bounds; basin ring must contain trigger gauge
Verified signaturef68b7ff
-
UX: event aging + pins + basin boundary; precip bars on nowcast hydrograph
Verified signature31976e1
-
v2-aware serving: prefer dilstm_v2 ckpts, feat_version dispatch, per-gauge skill gate
Verified signature0f8731e -
nowcast risk: observation-gated flood tiers
Verified signature71e7bf5 -
events: 12 h sim backset
Verified signature9da5e81 -
event triggers: obs gate + dry-episode end
Verified signature15ffcec