Files
dots/common/.pi/agent/models.json
T
coja 1e39e0cb4b [Sync] replace the flat layout with the unified stow tree
Supersedes the old flat .config/ layout (last published 2026-06-28) with the
private repo's structure: one shared base plus per-host overlays.

- packages: common/ gui/ lw/ fl/ wm/ plus install.sh and bin/ tooling
  (dotsync, reconcile-hyde.sh)
- new README covering the layout, deploy order and the HyDE dependency
- current HyDE waybar rig (layouts/, cava), pi agent extensions, claude/
  config, tmux, presenterm, aichat roles
- fish: kp (keepassxc-cli + fzf picker, db path from $KP_DB) and
  bind_M_n_history (alt+1..9 recalls the nth history entry)
- drops cruft that should never have been tracked: the duplicate top-level
  .pi/ copy, btop.log, zellij config.kdl.bak, fish_variables
- .pi/agent/auth.json is gitignored; auth.json.example ships instead

Host-specific work sessions and the personal backlog stay in the private
tree. Endpoint locators in the llamacpp/whisper guides are placeholders
($SERVER, <own-domain>) — the guides themselves stay, since they are the
useful part.
2026-08-13 02:53:06 +02:00

215 lines
7.6 KiB
JSON

{
"providers": {
"duskadiy": {
"baseUrl": "https://llm.duskadiy.com/api/v1",
"api": "openai-completions",
"apiKey": "$DUSKADIY_API_KEY",
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"maxTokensField": "max_tokens"
},
"models": [
{
"id": "gemma-4-E4B-it-UD-Q8_K_XL",
"name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 65536,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "gemma-4-26B-A4B-it-UD-IQ4_XS",
"name": "Gemma 4 26B · 24k · vision — quality generalist",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 24576,
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3-Coder-30B-Instruct-UD-Q3_K_XL",
"name": "Qwen3 Coder 30B · 32k — main agent coder",
"reasoning": false,
"input": ["text"],
"contextWindow": 32768,
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3-Coder-Next-UD-IQ3_XXS",
"name": "Qwen3 Coder Next 80B · 128k — long sessions",
"reasoning": false,
"input": ["text"],
"contextWindow": 131072,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3.6-35B-A3B-MTP-UD-IQ3_XXS",
"name": "Qwen3.6 35B · 24k · vision — daily driver",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 24576,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3.6-35B-A3B-Thinking",
"name": "Qwen3.6 35B Thinking · 24k · vision — hard problems",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text", "image"],
"contextWindow": 24576,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3.5-9B-UD-Q6_K_XL",
"name": "Qwen3.5 9B · 32k · vision — quick tasks",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text", "image"],
"contextWindow": 32768,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "GLM-4.7-Flash-UD-Q4_K_XL",
"name": "GLM-4.7 Flash · 24k — quality coder",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text"],
"contextWindow": 24576,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "gpt-oss-20b",
"name": "gpt-oss 20B · 64k — fast reasoning + tools",
"reasoning": true,
"input": ["text"],
"contextWindow": 65536,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "gpt-oss-20b-low",
"name": "gpt-oss 20B low · 64k — snappy answers",
"reasoning": true,
"input": ["text"],
"contextWindow": 65536,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
}
]
},
"localcpp": {
"baseUrl": "http://192.168.0.204:11343/v1",
"api": "openai-completions",
"apiKey": "no-key-required",
"compat": {
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"maxTokensField": "max_tokens"
},
"models": [
{
"id": "gemma-4-E4B-it-UD-Q8_K_XL",
"name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 65536,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "gemma-4-26B-A4B-it-UD-IQ4_XS",
"name": "Gemma 4 26B · 24k · vision — quality generalist",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 24576,
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3-Coder-30B-Instruct-UD-Q3_K_XL",
"name": "Qwen3 Coder 30B · 32k — main agent coder",
"reasoning": false,
"input": ["text"],
"contextWindow": 32768,
"maxTokens": 4096,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3-Coder-Next-UD-IQ3_XXS",
"name": "Qwen3 Coder Next 80B · 128k — long sessions",
"reasoning": false,
"input": ["text"],
"contextWindow": 131072,
"maxTokens": 16384,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3.6-35B-A3B-MTP-UD-IQ3_XXS",
"name": "Qwen3.6 35B · 24k · vision — daily driver",
"reasoning": false,
"input": ["text", "image"],
"contextWindow": 24576,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3.6-35B-A3B-Thinking",
"name": "Qwen3.6 35B Thinking · 24k · vision — hard problems",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text", "image"],
"contextWindow": 24576,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "Qwen3.5-9B-UD-Q6_K_XL",
"name": "Qwen3.5 9B · 32k · vision — quick tasks",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text", "image"],
"contextWindow": 32768,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "GLM-4.7-Flash-UD-Q4_K_XL",
"name": "GLM-4.7 Flash · 24k — quality coder",
"reasoning": true,
"compat": { "thinkingFormat": "qwen-chat-template" },
"input": ["text"],
"contextWindow": 24576,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "gpt-oss-20b",
"name": "gpt-oss 20B · 64k — fast reasoning + tools",
"reasoning": true,
"input": ["text"],
"contextWindow": 65536,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
},
{
"id": "gpt-oss-20b-low",
"name": "gpt-oss 20B low · 64k — snappy answers",
"reasoning": true,
"input": ["text"],
"contextWindow": 65536,
"maxTokens": 8192,
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
}
]
}
}
}