connor
40f6cba599
Adds muse-glimmer-30b and muse-glimmer-30b-low to the local and personal profiles, and points the five named agents at the -low alias. -low, not the bare alias, because that is the configuration llmbench actually measured: 15/24 tests_pass on the real suite at reasoning_strength low, the best any local model has scored there. The bare alias runs at Glimmer's default, which is its HIGHEST reasoning setting and cannot be turned off -- measured 906 completion tokens for a one-line riddle against 360 at low. Both are declared, so switching is a model change, not an edit. Context is 131072, from llama-swap's own `-c`. These agents already exist in work.json/work-strict.json on gpt-5.6-terra and are untouched there; local and personal had no agent block at all, so this is additive.
129 lines
3.1 KiB
JSON
129 lines
3.1 KiB
JSON
{
|
|
"$schema": "https://opencode.ai/config.json",
|
|
"provider": {
|
|
"litellm": {
|
|
"npm": "@ai-sdk/openai-compatible",
|
|
"name": "LiteLLM \u00b7 LOCAL-ONLY",
|
|
"options": {
|
|
"baseURL": "{env:LITELLM_BASE}/v1",
|
|
"apiKey": "{env:LITELLM_KEY}"
|
|
},
|
|
"models": {
|
|
"gpt-oss-20b": {
|
|
"name": "gpt-oss-20b (local, resident)",
|
|
"limit": {
|
|
"context": 65536,
|
|
"output": 8192
|
|
},
|
|
"cost": {
|
|
"input": 0.0,
|
|
"output": 0.0,
|
|
"cache_read": 0.0,
|
|
"cache_write": 0.0
|
|
}
|
|
},
|
|
"qwen3-coder-30b": {
|
|
"name": "qwen3-coder-30b (local, on demand)",
|
|
"limit": {
|
|
"context": 32768,
|
|
"output": 8192
|
|
},
|
|
"cost": {
|
|
"input": 0.0,
|
|
"output": 0.0,
|
|
"cache_read": 0.0,
|
|
"cache_write": 0.0
|
|
}
|
|
},
|
|
"gemma3-12b": {
|
|
"name": "gemma3-12b (local, on demand)",
|
|
"limit": {
|
|
"context": 32768,
|
|
"output": 8192
|
|
},
|
|
"cost": {
|
|
"input": 0.0,
|
|
"output": 0.0,
|
|
"cache_read": 0.0,
|
|
"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": {
|
|
"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": {
|
|
"context": 131072,
|
|
"output": 8192
|
|
},
|
|
"cost": {
|
|
"input": 0.0,
|
|
"output": 0.0,
|
|
"cache_read": 0.0,
|
|
"cache_write": 0.0
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"enabled_providers": [
|
|
"litellm"
|
|
],
|
|
"model": "litellm/local/librarian",
|
|
"small_model": "litellm/local/librarian",
|
|
"agent": {
|
|
"dev": {
|
|
"model": "litellm/muse-glimmer-30b-low"
|
|
},
|
|
"architect": {
|
|
"model": "litellm/muse-glimmer-30b-low"
|
|
},
|
|
"review": {
|
|
"model": "litellm/muse-glimmer-30b-low"
|
|
},
|
|
"duck": {
|
|
"model": "litellm/muse-glimmer-30b-low"
|
|
},
|
|
"brainstorm": {
|
|
"model": "litellm/muse-glimmer-30b-low"
|
|
}
|
|
}
|
|
}
|