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

2026-10-03 16:48:21 +00:00

92158da5ea Dashboard: Matrix chat card — self-serve one extra federated MXID below API keys

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

2026-10-03 16:48:18 +00:00

563881d63c Matrix: member-set extra MXID (matrix_mxid column + broker get/set + sync prefers it)

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

2026-10-03 15:34:36 +00:00

c022a0b52e models: add cached-input pricing column (cache-read rates per model)

inference-bot commented on issue co-op/support#7

2026-10-03 04:38:16 +00:00

Chat UX: value-based model picker (Private / Green / Public grouping)

Implemented (options 1 + 2) — closing.

The value-based picker framing shipped via config-only changes, no fork needed:

Friendly names + value-tier emoji set in the portal's…

inference-bot closed issue co-op/support#7

2026-10-03 04:37:15 +00:00

Chat UX: value-based model picker (Private / Green / Public grouping)

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

2026-10-03 04:36:31 +00:00

a647284170 models: remove phantom tinfoil/glm-5-3 and kimi-k3 (not served); reconcile to gateway catalog

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

2026-10-03 04:31:53 +00:00

888ac8c299 models: value-tier emoji (🔒/🌱/📖) matching the chat picker

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

2026-10-03 04:30:14 +00:00

3cdc250d52 Chat model picker: value-tier emoji + friendly names in /v1/models (🔒 private / 🌱 green / 📖 public), id stays canonical

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

2026-10-03 04:15:49 +00:00

dcdde204b0 models: greenpt/deepseek-v4.1-flash as default; Tinfoil deepseek as TEE twin

inference-bot pushed to main at code/litellm

2026-10-03 04:15:47 +00:00

a0ae99329f Add greenpt/deepseek-v4.1-flash as default (renewable, not Experimental); fallback → tinfoil deepseek

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

2026-10-03 04:04:56 +00:00

1fe0e47802 Update code-comment example (green-r -> glm-5.3-flash)

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

2026-10-03 04:04:54 +00:00

0a79c80483 docs: remove green-l/green-r from model list and API examples

inference-bot pushed to main at code/litellm

2026-10-03 04:04:51 +00:00

516167aaf9 Remove green-l/green-r models (GreenPT marks them not recommended)

inference-bot commented on issue co-op/support#9

2026-10-02 22:11:49 +00:00

Toward the next governance model

Draft: Next-stage Charter (for discussion)…

inference-bot pushed to main at code/litellm

2026-10-02 21:39:10 +00:00

b6e8542146 config: remove duplicate broken audio-model entries (audio_transcription//audio_speech/ prefixes); keep the correct openai/ routing

inference-bot closed issue code/litellm#2

2026-10-02 21:32:53 +00:00

Upgrade LiteLLM v1.84.0 → v1.103.2 with ~1–2 min downtime (pre-migrate + swap)

inference-bot commented on issue code/litellm#2

2026-10-02 21:32:53 +00:00

Upgrade LiteLLM v1.84.0 → v1.103.2 with ~1–2 min downtime (pre-migrate + swap)

Executed 2026-10-02 ~21:25 UTC — v1.103.2 live. Downtime: under 2 minutes.

What actually happened:

Pre-migration (live, zero downtime): since no docker access from the agent host, the…

inference-bot pushed to main at code/litellm

2026-10-02 21:32:52 +00:00

b9af62a614 README: current base image v1.103.2

inference-bot pushed to main at code/litellm

2026-10-02 21:25:31 +00:00

a2864ce34a Upgrade to LiteLLM v1.103.2 (schema pre-migrated live; CVE fix line + streaming-usage bugfix window)

inference-bot commented on issue code/litellm#2

2026-10-02 19:43:15 +00:00

Upgrade LiteLLM v1.84.0 → v1.103.2 with ~1–2 min downtime (pre-migrate + swap)

Follow-up from member report (2026-10-02, prompt-cache reporting): streaming responses through the gateway drop usage.prompt_tokens_details.cached_tokens from the final usage chunk…