• Joined on 2026-02-17
grenade closed issue helexa/helexa#264 2026-08-17 12:51:53 +00:00
upstream: let an API key read its own allocation and top up, without handing services the account password
grenade commented on issue helexa/helexa#264 2026-08-17 12:51:48 +00:00
upstream: let an API key read its own allocation and top up, without handing services the account password

Merged to main as 18683d90 (branch feat/upstream-key-auth-allocation, CI run 1142 green — Format, Clippy, Test, CUDA type-check, Web).

Acceptance, all covered by `web_pg::api_key_reads_allo…

grenade pushed to main at helexa/helexa 2026-08-17 12:51:37 +00:00
18683d904d Merge branch 'feat/upstream-key-auth-allocation'
46fe3d525c feat(upstream): an API key can read and refill its own allocation
Compare 2 commits »
grenade pushed to feat/upstream-key-auth-allocation at helexa/helexa 2026-08-17 11:55:29 +00:00
46fe3d525c feat(upstream): an API key can read and refill its own allocation
grenade created branch feat/upstream-key-auth-allocation in helexa/helexa 2026-08-17 11:55:28 +00:00
grenade opened issue helexa/helexa#264 2026-08-17 11:49:07 +00:00
upstream: let an API key read its own allocation and top up, without handing services the account password
grenade opened issue grenade/moments#9 2026-08-17 11:03:08 +00:00
slash-less route URLs 301 to port 14443 and hang until the browser times out
grenade closed issue grenade/moments#4 2026-08-17 10:34:23 +00:00
frankie (pg standby) needs db-perms.sh re-run when reachable
grenade commented on issue grenade/moments#4 2026-08-17 10:34:19 +00:00
frankie (pg standby) needs db-perms.sh re-run when reachable

Ran and verified. Both pg hosts are reachable again, and the standby now has the app-owned file with the two mappings that matter:

frankie:  moments.conf:cert_cn nikola.kosherinata.internal  …
grenade pushed to main at grenade/moments 2026-08-17 10:14:08 +00:00
6ee4cf5299 feat(api): make healthz verify the schema, not just that the process is up
grenade pushed to main at grenade/moments 2026-08-17 10:04:27 +00:00
7e186f76ae fix(ci): restart the api only after the worker has finished migrating
grenade pushed to main at grenade/moments 2026-08-17 09:59:06 +00:00
ef8521b9fb fix(ci): prerender the web bundle after the api/worker deploy, not beside it
grenade closed issue grenade/moments#8 2026-08-17 09:59:06 +00:00
build-web races the api/worker deploys, so the crawler snapshot may not match the api
grenade opened issue grenade/moments#8 2026-08-17 09:58:03 +00:00
build-web races the api/worker deploys, so the crawler snapshot may not match the api
grenade commented on issue helexa/helexa#263 2026-08-17 05:20:43 +00:00
helexa.ai serves unmetered inference to anyone with no credential — and anonymous web chat depends on it

Operator decisions (2026-08-17)

  • Free access to the large model stays. Anonymous keeps reaching Qwen/Qwen3.8-27B; the earlier suggestion to demote free users to the small tier is…
grenade opened issue helexa/helexa#263 2026-08-17 05:16:25 +00:00
helexa.ai serves unmetered inference to anyone with no credential — and anonymous web chat depends on it
grenade opened issue helexa/helexa#262 2026-08-17 05:08:20 +00:00
anonymous callers are exempt from fair-share, so any unauthenticated client can starve authenticated ones
grenade opened issue helexa/helexa#261 2026-08-15 20:42:44 +00:00
return the candle fork upstream — or stop calling it temporary; 3 of its 4 commits were never offered
grenade opened issue helexa/helexa#260 2026-08-15 20:42:14 +00:00
return the cudarc fork upstream — 3 commits, 82 lines, and a PR that was never actually filed
grenade opened issue helexa/helexa#259 2026-08-15 20:26:54 +00:00
research: quant strategy, and whether NVFP4 on the Blackwell cards buys real throughput