feat(cli): add --model-base-url passthrough to fle inspect-eval - #391
Open
phaestos2501 wants to merge 1 commit into
Open
feat(cli): add --model-base-url passthrough to fle inspect-eval#391phaestos2501 wants to merge 1 commit into
phaestos2501 wants to merge 1 commit into
Conversation
inspect eval natively accepts --model-base-url, but fle inspect-eval provided no way to forward it, so pointing a run at a local or self-hosted OpenAI-compatible endpoint (vLLM, LM Studio, llama-server) required exporting provider-specific env vars instead of a CLI flag. Forward the flag when provided.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
inspect evalnatively accepts--model-base-url, butfle inspect-evalprovides no way to forward it, so pointing a run at a local or self-hosted OpenAI-compatible endpoint (vLLM, LM Studio, llama-server) — or a hosted OpenAI-compatible API not in the provider list — requires exporting provider-specific env vars instead of a CLI flag.Change
Forward
--model-base-urltoinspect evalwhen provided.Verification
Live run with the invocation above (deepseek-v4-flash) resolved through Inspect's
OpenAICompatibleAPI, executed a full trajectory against a Factorio container, and scored normally.🤖 Generated with Claude Code