feat(llm): allow any OpenAI-compatible endpoint via env-var base-url override - #1033
Closed
sudo-ai-git wants to merge 1 commit into
Closed
sudo-ai-git wants to merge 1 commit into
sudo-ai-git wants to merge 1 commit into
Conversation
…override Closes caura-ai#992. The chat LLM path (dedup judge, enrichment, contradiction detection, entity extraction) hardcoded provider base URLs, so it could not target a custom OpenAI-compatible endpoint and silently fell back to heuristics. Add _env_base_url() honoring OPENAI_BASE_URL / ANTHROPIC_BASE_URL / OPENROUTER_BASE_URL, with the module constant as fallback. Backward compatible. Verified: no override -> constant; override -> custom endpoint.
Member
|
Thank you for tackling OpenAI-compatible endpoints. We are consolidating #992 in #993, which covers both configurable base URLs and the incompatible response_format behavior with broader tests; this PR addresses only the URL half. Closing this as superseded so the repository has one implementation path. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #992
Problem: the chat LLM path (dedup judge, enrichment, contradiction detection, entity extraction) hardcoded provider base URLs in
common/llm/constants.py, so it could not target a custom OpenAI-compatible endpoint — the call failed,call_with_fallbackwalked to the fake provider, and LLM features silently ran on heuristics.Change: add
_env_base_url(provider)incommon/llm/_credentials.py, honoringOPENAI_BASE_URL/ANTHROPIC_BASE_URL/OPENROUTER_BASE_URL, with the module constant as fallback.resolve_openai_compatiblenow returns the override when set.Verified:
https://api.openai.com/v1(backward compatible)OPENAI_BASE_URL=https://compatible.example/v1-> returned verbatimFocused 1-file change (+18/-3). Happy to add a regression test + surface a tenant-config option if maintainers want it wired further.