 Alexander Korolev
|
cfbe115acb
spec: HA add-on + recipe-repo architecture (implementation plan)
|
преди 1 седмица |
|
Alexander Korolev
|
60da850fd5
mimo26-pro-mopd-8x-sparkring: full bench 2026.10.1 — 91/100
|
преди 1 седмица |
|
Alexander Korolev
|
9c02032032
report viewer: follow-log (SSE) — live tail of bench .log files
|
преди 1 седмица |
|
Alexander Korolev
|
a82e875c2c
karmic-kraken: image build + GLM53 B12X recipe + fail-fast readiness
|
преди 1 седмица |
|
Alexander Korolev
|
8fc0188614
stacks: adopt upstream updates (kindling re-vendor, SparkRing 10-04, karmic tip 636afde9)
|
преди 2 седмици |
|
Alexander Korolev
|
84074f6272
recipe contract gate: sm121 validate + make-check test; archive 22 superseded lanes
|
преди 2 седмици |
|
Alexander Korolev
|
2608d645c2
AGENTS.md: document ensure-powered power on + persisted web jobs registry
|
преди 2 седмици |
|
Alexander Korolev
|
d67d9d8ffa
web: jobs registry persists across restarts (web-jobs.json next to the global config; in-flight jobs marked failed with a runlock hint on boot); FTL full parity — 209 keys in all 6 locales, 19 health/exec/doctor/messages translated per locale
|
преди 2 седмици |
|
Alexander Korolev
|
162b9417a5
power.rs back under the 500-line cap: HA entity toggling (toggle_one/toggle_entities/extra_ids/call) moved to power/toggle.rs, plug decisions (OnAction/decide_on/stale_nodes) to power/plug.rs; stale doc comment cleaned
|
преди 2 седмици |
|
Alexander Korolev
|
3acc8fa855
power on: ensure-powered — nodes believed down with an already-on plug get a 30 s plug power cycle (2-5 s cuts left the PSU rail energized and the machine in soft-off); per-node outcome report becomes the job message; CLI uses a 1.5 s TCP reachability probe, web uses the last snapshot
|
преди 2 седмици |
|
Alexander Korolev
|
9cf3deb380
web logs: ANSI SGR rendering in log windows — themed palette (8 colors/bold/dim/italic/underline, fg replaces fg), strip OSC + non-SGR CSI, carriage-return progress frames collapse to the last frame, debounced batched re-render, raw text kept for copy; node probe + playwright timing fix
|
преди 2 седмици |
|
Alexander Korolev
|
b9da59a70f
web token: viewer links in the embedded recipes panel carry the auth token (query fallback + localStorage) — bare /r/ links 401'd in token mode
|
преди 2 седмици |
|
Alexander Korolev
|
b5cf4a4ba8
web topo: cap frame pads (5-level nesting pushed the outer frame above the canvas — the 'top frame cut off'), draw the map at container width with scroll, add a persisted cluster filter (hidden clusters recompute the nest depth)
|
преди 2 седмици |
|
Alexander Korolev
|
5eecadc573
web: stop works off the recipes actually running on the cluster — single running recipe stops directly (no picking), several get a picker of running ones only, container list names the node; serve-form fallback kept for up-but-empty clusters
|
преди 2 седмици |
|
Alexander Korolev
|
6ccb448146
web: fix two-step confirms (power on/off) doing nothing — openDialogHtml stored the placeholder go instead of opts.go, so Confirm closed the dialog without firing the request; playwright regression covers the full power-on flow
|
преди 2 седмици |
|
Alexander Korolev
|
1421e95250
campaign 2026-10-03: MiMo 2x/Pro 8x benched (pluto/wired), kindling 2x+TP6, karmic-kraken image, depth-hang forensics
|
преди 2 седмици |
|
Alexander Korolev
|
fef19db3bb
bench: MiMo 4x kraken full re-run via pluto (wired) — depth suite now works
|
преди 2 седмици |
|
Alexander Korolev
|
4a99ace3ce
fix(bench): --ssh-host depth suite — create the remote scratch dir before cd
|
преди 2 седмици |
|
Alexander Korolev
|
cad1944a7d
bench: kindling 4x + MiMo 4x kraken via pluto (wired) — WiFi-isolation campaign
|
преди 2 седмици |
|
Alexander Korolev
|
b70649a547
feat(bench): --ssh-host — run tool-eval-bench on a remote host over SSH
|
преди 3 седмици |
|
Alexander Korolev
|
034c9b848f
recipes/mimo-*-sparkring: bump sparkring image to dev-20261001-kraken
|
преди 3 седмици |
|
Alexander Korolev
|
7559d62476
recipes/mimo-*-sparkring: float the model id + dflash drafter
|
преди 3 седмици |
|
Alexander Korolev
|
c2871f857a
kindling 4x re-bench on 27cf839 image (label kindling-4x-27cf839): 94/100 (166/176), identical to the a3c3a1d baseline — same fails TC-43/51/68/80, same depth curve. The megamoe #67 + spec-config #64 in the new image neither regress nor improve GLM-5.3-Flash 4x quality. Model now floats via refs/main (da920bb0 at bench time); manifest predates the models-field, so it carries no snapshot (next bench will).
|
преди 3 седмици |
|
Alexander Korolev
|
24d6737bc3
de-pin model revisions: kindling 2x/4x model -> floating org/model id (engine resolves via NAS refs/main -> latest snapshot, same as every other recipe; the pinned da920bb0 stays as an informational comment); 6x notes its tp6pad source rev. Bench manifest now records the model's resolved refs/main snapshot so a floating model stays reproducible (backward-compatible #[serde(default)]).
|
преди 3 седмици |
|
Alexander Korolev
|
729f454eaa
kindling 4x: full campaign report package (md/json/log/manifest/recipe snapshot) — 94/100 quality, depth curve to 256K with no decode cliff (tg 60-88 t/s), TTFT 2.1s @256K c1
|
преди 3 седмици |
|
Alexander Korolev
|
f944aea35c
kindling 4x: first full campaign — quality 166/176 (94/100, best on cluster), perf table, boot bugs ledger (spec-config form, UMA gate coin flip, control-file dirs); spec section + report artifacts (json+log snapshot, depth suite in flight)
|
преди 3 седмици |
|
Alexander Korolev
|
b58b87fa8f
skill serve-boot-triage: 4b — long-running local work (benches) dies under the tool harness; move it to a cluster node (build sm121 there, tmux session, host-side tokenizer path, report copy-back)
|
преди 3 седмици |
|
Alexander Korolev
|
bfbbf854b3
bench: the script-pty wrapper is macOS-only — util-linux script (Linux nodes) has no positional command and parsed the harness flags as its own ('unrecognized option --base-url'); non-macOS goes to the direct-exec fallback
|
преди 3 седмици |
|
Alexander Korolev
|
e6204c6b95
kindling recipes: control paths are FILES, not the cache dirs — VLLM_{ADAPTIVE_K,DRAFT_TRUNC}_CONTROL pointed at the mounted dir roots, and their _read_control() does os.stat+open on the path (stat succeeds on a dir, open does not) => IsADirectoryError killed the engine core right after KV allocation; point them at <dir>/control (absent file = safe defaults: tau 0.3 / adapt, written file persists + live-control)
|
преди 3 седмици |
|
Alexander Korolev
|
571a5499f1
history: 2026-10-02 night — kindling 4x e2e (spec-config doubling, triple-quote form, upstream 27cf839 re-vendor, GB10 UMA gate coin flip fixed via GMU 0.86 + last-moment drop_caches mod), serve-boot-triage skill, headless dgx6/7/8, upstream sweep (MiMo/GLM/DFlash2 pins current, eugr nightly-20261001 new)
|
преди 3 седмици |
