The local-model release. Four things that matter if you run Pengy against a model on your own machine, and they add up to the reason this project exists in the shape it does.
Local endpoints as a first-class config target. A local model behaves differently from a hosted
API: it takes longer to answer, it has a smaller context window, it has a max output token cap you
have to set, its streaming needs its read timeout raised, and it does not implement every API
parameter. Pengy now treats that as configuration, not as a bug: max_output_tokens with no cap
when unset, the read timeout raised for streaming, base_url as the switch.
Custom headers and query params. The config takes http_headers and http_query, and supports
${env:VAR} so a key lives in an environment variable rather than in a config file. The OpenAI SDK
had extra_headers; this makes them a documented, validated config surface, with the header names
and values checked.
Endpoint health check. Ask the endpoint what models it serves and how it is doing. The OpenAI
SDK's client.models.list() is the same call for all of them, including llama.cpp, and Ollama gets
its own native check. It reports models, endpoint, context window and the quantisation, and
pengy-cli --list-models prints it.
YOLO mode. Run without confirming tool calls, with a config policy for tools, a
/yolo slash command, a GUI toggle, and a web UI selector. This is a real usability feature with
real consequences, and it is where most of this project's argument lives: an agent that asks
permission for every command is safe and tiring, and an agent that asks for none is fast and
dangerous. The policy is configurable per tool, and the mode is visible in the UI.