Repository navigation
run wizard: self-hosted model server option; viewer logo - #82
Merged
Merged
Conversation
Pick "self-hosted" as the provider to point the agent at llama.cpp, vLLM, LM Studio, MLX or any other OpenAI-compatible server: the wizard reads the model from /v1/models, rewrites localhost to host.docker.internal for the container, asks for an API key (hidden) when the server wants one, and asks what served the model, guessed from the Server header.
Hacktron Security Check - SkippedReason: Code Review is not active for this organization
|
rzonyx
previously approved these changes
Nov 8, 2026
rzonyx
approved these changes
Nov 8, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
hbench runwizard: aself-hostedprovider for any OpenAI-compatible server (llama.cpp, vLLM, LM Studio, MLX…)./v1/models(picks it if only one is loaded).localhost/127.0.0.1/[::1]tohost.docker.internalso the agent's container can reach it.OPENAI_BASE_URL/OPENAI_API_KEYwith-m openai/<id>. claude-code getsANTHROPIC_BASE_URL/ANTHROPIC_API_KEYwithanthropic/<id>. gemini-cli isn't offered the option."$SELF_HOSTED_API_KEY", never the key.--model-served-by, prefilled from the server'sServerheader.passwordfeature, which adds no new crates (zeroizeis already in the lock file).Testing
host.docker.internalrewrite, guessing the served-by label, and the answers filling in the run args and printed command. Clippy is clean.dspy_rlm::tests::runner_bridges_tools_with_fake_dspyfails because this machine has Python 3.9, which lacksX | Nonesyntax. That failure is unrelated to this PR.--allowed-host host.docker.internal.