rin.kagamine
4dd10fab80
docs: add ARCHITECTURE.md from Palace doc, cross-reference from README
2026-06-04 19:03:00 -04:00
rin.kagamine
3d4230ccb4
Replace hardcoded model name abbreviations with dynamic truncation
...
- Strip common provider prefixes (gemini/, openai/, anthropic/, mistral/, cohere/)
- Truncate names > 24 chars with ellipsis (…) instead of hardcoded abbreviations
- Works generically for any LiteLLM model, not just our Gemini config
2026-06-04 17:08:51 -04:00
rin.kagamine
c92dd9cf20
Add MIT license, abbreviate long model names in cost table
...
- 3.1-pro-preview-customtools → 3.1-pro-ct
- 3.1-flash-image-preview → 3.1-flash-img
- 3.1-flash-lite-preview → 3.1-flash-lite
- 3-flash-preview → 3-flash-prev
- Narrowed model column from 30 to 20 chars
2026-06-04 16:17:37 -04:00
rin.kagamine
d642df3e03
Add .gitignore, remove pycache from tracking
2026-06-04 15:47:35 -04:00
rin.kagamine
98a1b3c546
LiteLLM Dashboard Tool v1.0.0 — two-function OWI Tool
...
- litellm_health: proxy health + auth check (strips litellm_metadata)
- litellm_cost: cost breakdown by date range (per-model, per-day, cache hit rate)
- Valves: litellm_url, litellm_master_key (password field, no hardcoded keys)
- Tested against mon-rin1:4000 Gemini proxy — all green
- Error handling: auth failure, connection failure, timeout
- Architecture doc: Memory Palace KB #596
2026-06-04 15:47:29 -04:00
rin.kagamine