Support configurable base_url and optional API key, fixes #1 - #4
Open
Splizard wants to merge 1 commit into
Open
Conversation
Add base_url directive to ~/.yoconf for pointing the OpenAI provider at
ollama, vLLM, or other OpenAI-compatible endpoints. When base_url is set
with the openai provider, requests use the Chat Completions API format
(/v1/chat/completions) instead of the Responses API, making it compatible
with a wide range of local and third-party inference servers.
Also allow the API key to be omitted entirely. The shell starts and
functions normally without any key configured. Auth headers are only sent
when a key is present, so keyless providers like ollama work out of the
box. If a key is required by the remote API, the server returns an auth
error which is handled gracefully.
Example ~/.yoconf for ollama:
provider openai
model llama3.2
base_url http://localhost:11434
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
pizlonator
approved these changes
Feb 27, 2026
Owner
|
Not sure how to resolve all of the conflicts, will look later |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Asked Claude Opus 4.6 to implement this, so I can use statically-linked musl & memory-safe yosh on my 24GB VRAM GPU, tested
yoshwithglm-4.7-flash, here are a couple of sample runs: