inference-bot pushed to main at co-op/docs 2026-09-27 17:25:55 +00:00
34ce3b6753 Document audio models (STT/TTS) with API examples
inference-bot closed issue co-op/support#1 2026-09-27 17:23:56 +00:00
Voice mode latency/broken in chat
inference-bot commented on issue co-op/support#1 2026-09-27 17:23:56 +00:00
Voice mode latency/broken in chat

Resolved. Root cause was two layers:

  1. No STT/TTS engine configured. Open WebUI's audio settings were empty (fallback = slow local whisper base for dictation; no TTS at all, so interactive…
inference-bot pushed to main at code/member-dashboard 2026-09-27 17:15:12 +00:00
5d63e0d54e Add .gitignore (exclude __pycache__/bytecode)
inference-bot pushed to main at code/admin-panel 2026-09-27 17:15:09 +00:00
c0157bac13 Add .gitignore (exclude __pycache__/bytecode)
inference-bot pushed to main at code/member-portal 2026-09-27 17:15:06 +00:00
0c3c12999c Remove tracked bytecode; ignore __pycache__
inference-bot pushed to main at code/litellm 2026-09-27 17:10:54 +00:00
8f42be988e Add Tinfoil audio models (whisper STT, voxtral-tts) for voice mode + API use
inference-bot pushed to main at code/member-portal 2026-09-27 17:00:57 +00:00
54fa4d3fc2 Filter audio models out of chat-facing /v1/models (visible to API users only)
inference-bot pushed to main at co-op/docs 2026-09-26 22:52:27 +00:00
40925b82b5 Add greenpt/glm-5.3 to model list
inference-bot pushed to main at code/litellm 2026-09-26 22:52:25 +00:00
5ea2256776 Add greenpt/glm-5.3 (full flagship, $1.10/$4.40 per 1M)
inference-bot pushed to main at code/member-portal 2026-09-26 22:39:28 +00:00
c7ed245939 Read usage aggregations from LiteLLM Postgres directly (HTTP fallback kept)
inference-bot pushed to main at code/member-portal 2026-09-26 22:21:14 +00:00
4600a69cac Fix dashboard 500s: raise httpx read timeout on /team/list + /spend/logs calls
inference-bot closed issue co-op/support#5 2026-09-26 22:16:39 +00:00
Update model list on user dashboard
inference-bot commented on issue co-op/support#5 2026-09-26 22:16:03 +00:00
Update model list on user dashboard

Fixed. The dashboard's usage breakdown was reading the raw internal model name from LiteLLM's spend logs instead of our provider/model alias — so GreenPT and PublicAI models showed as bare…

inference-bot pushed to main at code/member-portal 2026-09-26 22:14:37 +00:00
2ff8193c55 Dashboard usage: prefer model_group alias (provider/model names) — fixes support #5
inference-bot pushed to main at code/member-portal 2026-09-26 22:09:42 +00:00
5c269bf243 Support ?days=N filter on /admin/model-usage
inference-bot pushed to main at code/admin-panel 2026-09-26 22:09:39 +00:00
2b42812c22 Add Members/Model-usage tabs, 30-day/all-time range toggle, sortable columns
inference-bot pushed to main at code/member-portal 2026-09-26 21:33:29 +00:00
a48f11c654 Prefer model_group alias in model-usage aggregation
inference-bot pushed to main at code/admin-panel 2026-09-26 21:31:17 +00:00
25568680b4 Add model-usage table to admin panel
inference-bot pushed to main at code/member-portal 2026-09-26 21:31:12 +00:00
810b878014 Add /admin/model-usage endpoint (co-op per-model spend/tokens/requests)