Several updates at once

This commit is contained in:
connor committed 2026-11-02 09:58:14 -05:00
1 parent 6b9b1697f2
commit 0a42f1547f
12 files changed
+396 -170

No files matched your search

+39 -65
View File
@@ -3,16 +3,42 @@
"provider": {
"litellm": {
"npm": "@ai-sdk/openai-compatible",
"name": "LiteLLM \u00b7 LOCAL-ONLY",
"name": "LiteLLM · LOCAL-ONLY",
"options": {
"baseURL": "{env:LITELLM_BASE}/v1",
"apiKey": "{env:LITELLM_KEY}"
},
"models": {
"gpt-oss-20b": {
"name": "gpt-oss-20b (local, resident)",
"qwen3.8-flash-next-iq3s-med": {
"name": "Qwen3.8-Flash-Next IQ3_S (local Strata, medium reasoning)",
"limit": {
"context": 65536,
"context": 196608,
"output": 32768
},
"cost": {
"input": 0.0,
"output": 0.0,
"cache_read": 0.0,
"cache_write": 0.0
}
},
"qwen3.8-flash-next-iq3s": {
"name": "Qwen3.8-Flash-Next IQ3_S (local Strata, full reasoning - slow)",
"limit": {
"context": 196608,
"output": 32768
},
"cost": {
"input": 0.0,
"output": 0.0,
"cache_read": 0.0,
"cache_write": 0.0
}
},
"qwen3-next-80b-128k": {
"name": "qwen3-next-80b (local, 128k agentic)",
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
@@ -22,8 +48,8 @@
"cache_write": 0.0
}
},
"qwen3-coder-30b": {
"name": "qwen3-coder-30b (local, on demand)",
"qwen3-next-80b": {
"name": "qwen3-next-80b (local, 32k)",
"limit": {
"context": 32768,
"output": 8192
@@ -48,32 +74,6 @@
"cache_write": 0.0
}
},
"local/librarian": {
"name": "Librarian - local gpt-oss",
"limit": {
"context": 65536,
"output": 8192
},
"cost": {
"input": 0.0,
"output": 0.0,
"cache_read": 0.0,
"cache_write": 0.0
}
},
"local/explore": {
"name": "Explore - local gpt-oss",
"limit": {
"context": 65536,
"output": 8192
},
"cost": {
"input": 0.0,
"output": 0.0,
"cache_read": 0.0,
"cache_write": 0.0
}
},
"muse-glimmer-30b-low": {
"name": "Muse Glimmer 30B (local, low reasoning)",
"limit": {
@@ -87,32 +87,6 @@
"cache_write": 0.0
}
},
"qwen3.8-27b-gsq-s-low": {
"name": "Qwen3.8-27B GSQ IQ3_S (local, low reasoning)",
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
"input": 0.0,
"output": 0.0,
"cache_read": 0.0,
"cache_write": 0.0
}
},
"qwen3.8-27b-gsq-s-med": {
"name": "Qwen3.8-27B GSQ IQ3_S (local, medium reasoning)",
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
"input": 0.0,
"output": 0.0,
"cache_read": 0.0,
"cache_write": 0.0
}
},
"muse-glimmer-30b": {
"name": "Muse Glimmer 30B (local, full reasoning - slow)",
"limit": {
@@ -132,23 +106,23 @@
"enabled_providers": [
"litellm"
],
"model": "litellm/local/librarian",
"small_model": "litellm/local/librarian",
"model": "litellm/qwen3.8-flash-next-iq3s-med",
"small_model": "litellm/qwen3.8-flash-next-iq3s-med",
"agent": {
"dev": {
"model": "litellm/qwen3.8-27b-gsq-s-med"
"model": "litellm/qwen3.8-flash-next-iq3s-med"
},
"architect": {
"model": "litellm/qwen3.8-27b-gsq-s-med"
"model": "litellm/qwen3.8-flash-next-iq3s-med"
},
"review": {
"model": "litellm/qwen3.8-27b-gsq-s-med"
"model": "litellm/qwen3.8-flash-next-iq3s-med"
},
"duck": {
"model": "litellm/qwen3.8-27b-gsq-s-med"
"model": "litellm/qwen3.8-flash-next-iq3s-med"
},
"brainstorm": {
"model": "litellm/qwen3.8-27b-gsq-s-med"
"model": "litellm/qwen3.8-flash-next-iq3s-med"
}
}
}