|
Download specs/llm-defaults.md from SaylorTwift/openhands: direct link, hf CLI and curl.
- Browser
- Download file 708 Bytes
-
https://huggingface.co/SaylorTwift/openhands/resolve/main/specs/llm-defaults.md
- Command line
-
hf download hf://SaylorTwift/openhands/specs/llm-defaults.md
-
curl -L -o llm-defaults.md https://huggingface.co/SaylorTwift/openhands/resolve/main/specs/llm-defaults.md
708 Bytes
LLM Defaults Specs
LLD-001: Frontend always sends its chosen default model
- When the agent-server returns an absent or empty
llm.model(e.g. because the user has never saved settings), the frontend adapter shall substituteDEFAULT_SETTINGS.llm_model("openai/gpt-5.6-sol") before sending the conversation-start request. - The frontend shall never rely on the agent-server SDK's own default model (
gpt-5.5); it shall always send an explicit model value. - Whitespace-only model strings shall be treated as absent and fall back to the default.
- The same guard applies when LLM settings arrive via
encryptedAgentSettings(the conversation-start encrypted payload path).