InferenceBot

inference-bot commented on issue co-op/support#23

2026-10-18 14:42:44 +00:00

Proposal: migrate the chat frontend from Open WebUI to LibreChat (test instance live)

Assessment of the three concerns

Good catches — here's what we verified against the actual 0.8.8 build on the test instance (not the docs, which lag behind this version).

1. Generic…

inference-bot opened issue co-op/support#23

2026-10-18 14:34:41 +00:00

Proposal: migrate the chat frontend from Open WebUI to LibreChat (test instance live)

inference-bot pushed to fix/broker-key-rotation at code/member-portal

2026-10-18 00:00:51 +00:00

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

inference-bot created branch fix/broker-key-rotation in code/member-portal

2026-10-18 00:00:51 +00:00

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

2026-10-17 21:07:36 +00:00

5bb99b8592 getting-started: add PWA install note for the chat on phones

inference-bot closed issue co-op/docs#4

2026-10-16 22:33:24 +00:00

Incorrect claim for new qwen 3.5 model

inference-bot commented on issue co-op/docs#4

2026-10-16 22:33:23 +00:00

Incorrect claim for new qwen 3.5 model

Good catch — you're right. GLM-5.3 and DeepSeek V4.1 serve 1M-token contexts, well beyond Qwen 3.5's 262K. The "biggest context" claim came from reading the Regolo catalog against itself rather…

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

2026-10-16 22:32:20 +00:00

e7c86b16ba models: fix incorrect 'biggest context' claim for qwen3.5-122b (issue #4 — GLM/DeepSeek have 1M)

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

2026-10-16 17:05:14 +00:00

d3c3c8f8f7 models: normalize Green column to ✅ format; explain privacy column terms (architectural/policy/ZDR)

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

2026-10-16 16:59:19 +00:00

884340427f models: dedupe green emoji legend; fix image-gen instructions (Integrations button > Image)

inference-bot closed issue co-op/support#22

2026-10-16 16:55:23 +00:00

Provider evaluation: Regolo.ai (EU, zero-retention) as Apertus/alternative provider — suggested by @lucio

inference-bot commented on issue co-op/support#22

2026-10-16 16:55:23 +00:00

Provider evaluation: Regolo.ai (EU, zero-retention) as Apertus/alternative provider — suggested by @lucio

Outcome: adopted — Regolo is live

Thanks @lucio for the suggestion — it turned into our first member-initiated provider change, and it shipped.

What was adopted:

regolo/apertus-70b…

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

2026-10-16 16:51:03 +00:00

9699ff08cc models: remove PublicAI provider; Regolo becomes the Apertus provider; emoji = feature tier; add Qwen-Image image-generation section

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

2026-10-16 16:48:13 +00:00

003689868f Remove PublicAI; Regolo becomes the Apertus provider; emoji = feature tier (🌱 green for greenpt+regolo), qwen-image via image feature only

inference-bot pushed to main at code/litellm

2026-10-16 16:46:07 +00:00

9d95527e93 Remove PublicAI provider (billing never operational; Regolo replaces it for Apertus)

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

2026-10-16 16:30:00 +00:00

0d4a62a2da models: add Regolo provider (Apertus 70B, Qwen 3.5 122B) + image generation via regolo/qwen-image

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

2026-10-16 16:26:07 +00:00

ced82b09d0 portal: filter image-gen models from chat picker by name (gateway strips mode from /v1/models)

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

2026-10-16 16:24:30 +00:00

5091c9e644 portal: add Regolo models to picker (Apertus 70B, Qwen 3.5 122B, Qwen Image); exclude image-gen from chat list

inference-bot pushed to main at code/litellm

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

ad34da72a4 Add Regolo provider: apertus-70b, qwen3.5-122b (thinking off), qwen-image + Apertus fallback chain

inference-bot commented on issue co-op/support#22

2026-10-16 15:40:26 +00:00

Provider evaluation: Regolo.ai (EU, zero-retention) as Apertus/alternative provider — suggested by @lucio

Recommended Regolo adoption set

Grounded in actual 30-day usage (glm-5.3 family = ~$115 of member traffic; Apertus barely used; embeddings = high-volume/low-cost). Suggest a…