JesusMan0529 opened a new pull request, #378: URL: https://github.com/apache/hugegraph-ai/pull/378
Fixes #91. After editing `.env` while the demo process is running, a page refresh now reloads the shared LLM settings and updates the chat, extraction, Text2Gremlin, embedding, and reranker forms. Render the provider fields after the reload, including when the provider type stays the same, and honor the configured SiliconFlow reranker model. Validation: - Regression reproduced before the fix: all three provider cases failed. - 107 related config, demo CLI, middleware, and API tests passed with `SKIP_EXTERNAL_SERVICES=true`. - Root Ruff formatting/lint and `git diff --check` passed. - Tests use the real `.env` loader and Gradio session/event processing. Live provider calls and browser end-to-end testing were not run. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
