Evan
7398983350
On dual-stack hosts (notably macOS), `localhost` resolves to both ::1 and 127.0.0.1 with IPv6 tried first. Local LLM servers (Ollama, vLLM, LM Studio) installed via the standard scripts bind IPv4 only, so the IPv6 connection attempt fails immediately and Happy Eyeballs fallback to IPv4 isn't reliably triggered for connection-refused errors, producing spurious "Configured local provider offline" warnings in the daemon even when the server is up and reachable via curl. Companion to librefang/librefang#3112 which fixes the hardcoded URL constants in the main repo. After both land, existing installs pick up the fix on their next registry sync.
105 lines
2.1 KiB
TOML
105 lines
2.1 KiB
TOML
# Ollama — https://ollama.com
|
|
# Current-generation models only. Additional models are discovered dynamically at runtime.
|
|
|
|
[provider]
|
|
id = "ollama"
|
|
display_name = "Ollama"
|
|
api_key_env = "OLLAMA_API_KEY"
|
|
base_url = "http://127.0.0.1:11434/v1"
|
|
key_required = false
|
|
|
|
[[models]]
|
|
id = "gemma4"
|
|
display_name = "Gemma 4"
|
|
tier = "local"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = ["gemma4:latest"]
|
|
|
|
[[models]]
|
|
id = "deepseek-r1:latest"
|
|
display_name = "DeepSeek R1"
|
|
tier = "local"
|
|
context_window = 64000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = false
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = ["deepseek-r1"]
|
|
|
|
[[models]]
|
|
id = "qwen3"
|
|
display_name = "Qwen 3"
|
|
tier = "local"
|
|
context_window = 40960
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.325
|
|
output_cost_per_m = 1.95
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = ["qwen3:latest"]
|
|
|
|
[[models]]
|
|
id = "qwq"
|
|
display_name = "QwQ"
|
|
tier = "local"
|
|
context_window = 40960
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.15
|
|
output_cost_per_m = 0.58
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
supports_thinking = true
|
|
aliases = ["qwq:latest"]
|
|
|
|
[[models]]
|
|
id = "llama4"
|
|
display_name = "Llama 4"
|
|
tier = "local"
|
|
context_window = 128000
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = true
|
|
supports_vision = true
|
|
supports_streaming = true
|
|
aliases = ["llama4:latest"]
|
|
|
|
[[models]]
|
|
id = "mistral:latest"
|
|
display_name = "Mistral"
|
|
tier = "local"
|
|
context_window = 32768
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "phi4"
|
|
display_name = "Phi-4"
|
|
tier = "local"
|
|
context_window = 16384
|
|
max_output_tokens = 4096
|
|
input_cost_per_m = 0.0
|
|
output_cost_per_m = 0.0
|
|
supports_tools = true
|
|
supports_vision = false
|
|
supports_streaming = true
|
|
aliases = ["phi4:latest"]
|