InferenceBot

inference-bot pushed to main at co-op/docs

2026-10-19 20:53:23 +00:00

12da5c1268 docs: chat task models — OWUI task model pinned to greenpt/glm-5.3-flash, suggestions state

inference-bot pushed to main at code/member-dashboard

2026-10-19 18:06:42 +00:00

2dee1ea71d fmtMoney: snap |n| < half a cent to exact 0 — kills $-0.00 from float-residue spend

inference-bot pushed to main at code/admin-panel

2026-10-19 18:05:00 +00:00

71c4e68a5c fmt: snap |n| < half a cent to exact 0 — kills $-0.00 from float-residue spend

inference-bot pushed to main at code/member-portal

2026-10-19 17:43:01 +00:00

5425efee1f overview: normalize float-residue spend (e.g. -5.55e-17 after cycle reset) to 0 so the panel never renders -0.00

inference-bot pushed to main at code/admin-panel

2026-10-19 17:16:32 +00:00

b8f737d1ee panel: Admin accounts show raw spend only — Status/Activated/Spend/Reset (30-day spend in Balance mode, all-time in All Time); drop allowance/credits/remaining/adjust

inference-bot pushed to main at code/member-dashboard

2026-10-19 17:09:13 +00:00

9cc636dd99 Co-op usage: sort by cost (default) or requests; uniform rank badges (no special #1 styling)

inference-bot pushed to main at code/member-dashboard

2026-10-19 17:04:05 +00:00

cdff951594 Matrix card: concise redesign per Nathan — 'Current Matrix ID' display, 'Use @local' button when on an external ID, 'Use external account' reveals a validated field; no my/your mixing

inference-bot pushed to main at code/member-dashboard

2026-10-19 16:49:40 +00:00

88bda332c3 dashboard: show the member's registered Matrix ID prominently (registered box + notes), surface load errors, add 'Use my co-op account instead' clear button

inference-bot pushed to main at code/member-portal

2026-10-19 16:47:51 +00:00

fd13bc6ea2 broker/matrix-mxid GET: local_mxid_for_email was async-def but never awaited — response contained a coroutine and FastAPI 500'd ('coroutine object is not iterable'), so the dashboard silently showed no registered Matrix ID. Make it a plain sync def (blocking urllib).

inference-bot pushed to main at code/litellm

2026-10-19 15:26:47 +00:00

79f0447089 gateway: build-time patch keeping image-gen pricing on the shared cost-map key (upstream #10023/#12471) so image spend is tracked

inference-bot pushed to main at co-op/docs

2026-10-19 14:50:15 +00:00

1f3f0ce9b8 librechat-sandbox: per-member image billing restored; system key is safety-net only

inference-bot pushed to main at co-op/docs

2026-10-19 14:30:42 +00:00

fde5d143c5 librechat-sandbox: image gen bills to system key (no gate); fallback usage monitored in digest

inference-bot pushed to main at co-op/docs

2026-10-19 05:50:55 +00:00

0e708a99c6 librechat-sandbox: homepage-canonical palette + green logo (flash-glitch fix)

inference-bot pushed to main at co-op/docs

2026-10-19 05:29:17 +00:00

467d19357d librechat-sandbox: per-member key auto-load (portal feed + sync-keys.js), redaction gotcha

inference-bot pushed to main at code/member-portal

2026-10-19 05:15:40 +00:00

97ebe69553 portal: /admin/librechat/keys — dedicated-token feed of member chat keys for the sandbox's key auto-load

7f04920327 broker: retire the old LiteLLM key before re-creating a same-name key

Compare 2 commits »

inference-bot pushed to main at co-op/docs

2026-10-19 04:53:14 +00:00

6a0d092e53 librechat-sandbox: manifest-pinned deploy flow, builder-cache + ECONNRESET pitfalls, branding overlay, keyless image path; current deployed tag

inference-bot pushed to main at co-op/docs

2026-10-19 02:54:32 +00:00

bac352f50e LibreChat sandbox: accessible image generation via MCP tool; two MCP servers; new overlay tag

inference-bot pushed to main at co-op/docs

2026-10-19 02:31:05 +00:00

34a23a34f3 LibreChat sandbox: rewrite maintenance doc for the volume-config + overlay-image architecture

inference-bot pushed to main at co-op/docs

2026-10-18 21:32:30 +00:00

fa979a5ed9 Add LibreChat sandbox maintenance documentation

inference-bot opened issue co-op/support#24

2026-10-18 19:15:09 +00:00

Security & bug audit — October 2026 (third pass): 1 critical, 2 high, sandbox debug-mode risk