connorandClaude Opus 5
e25bb71fb7
dev, architect, review, duck and brainstorm move from litellm/muse-glimmer-30b-low to litellm/qwen3.8-27b-gsq-s-med, in both the local-only and personal profiles. Glimmer's model entries are left in place so reverting is a one-line change. ⚠ MEDIUM, not low -- do not "align" this with the -low convention Glimmer uses. Qwen's own model card: "lower reasoning effort does not always reduce overall task completion time" on multi-turn agentic work, because insufficient analysis causes more failed actions and retries, raising latency AND total tokens. The low-effort result that justifies muse-glimmer-30b-low was measured on Glimmer and does not transfer. ⚠ The key is reasoning_effort, NOT Glimmer's reasoning_strength. The wrong key is dropped by kwarg filtering before it reaches the template, returns 200, and silently leaves the model at its default -- which for qwen3.8 is xhigh. Levels are low / medium / xhigh; there is no `high`. Verified the control actually moves rather than merely being accepted: 171 reasoning tokens at low against 430 at medium on one prompt. Requires qwen3.8-27b-gsq-s-med in ~/config/litellm/config.yaml (untracked; snapshot at config.yaml.pre-qwen38low). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FZomrX5fYmPYLusxcXTwvq
155 lines
3.7 KiB
JSON
155 lines
3.7 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
|
|
}
|
|
},
|
|
"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": {
|
|
"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/qwen3.8-27b-gsq-s-med"
|
|
},
|
|
"architect": {
|
|
"model": "litellm/qwen3.8-27b-gsq-s-med"
|
|
},
|
|
"review": {
|
|
"model": "litellm/qwen3.8-27b-gsq-s-med"
|
|
},
|
|
"duck": {
|
|
"model": "litellm/qwen3.8-27b-gsq-s-med"
|
|
},
|
|
"brainstorm": {
|
|
"model": "litellm/qwen3.8-27b-gsq-s-med"
|
|
}
|
|
}
|
|
}
|