Repository navigation
feat(lumo): add a --web-search flag to serve - #13
Merged
Merged
Conversation
The OpenAI-compatible server never enabled Lumo's native web search, so a model served through it could only answer from its training data. The client already supports it (the interactive chat gates lumo.ToolWebSearch behind a flag); serve just did not pass any tools. Add `proton lumo serve --web-search` (and $LUMO_WEB_SEARCH), which requests lumo.ToolWebSearch for every generation. When set, answers can draw on up-to-date web results; off by default, so behaviour is unchanged otherwise.
major0
approved these changes
Sep 23, 2026
This was referenced Sep 23, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Add
proton lumo serve --web-search(and the$LUMO_WEB_SEARCHenv var) toenable Lumo's native web search on the OpenAI-compatible server.
Why
The server never passed any tools to
Generate, so a model reached through/v1/chat/completionscould only answer from its training data -- it could notuse Lumo's built-in web search. The client already supports it: the interactive
lumo chatgateslumo.ToolWebSearchbehind a flag; onlyservewas missingthe wiring.
How
--web-searchflag (default off; default overridable via$LUMO_WEB_SEARCH).chatHandlerthreads it into the streaming and non-streaming paths, which nowrequest
webSearchTools(webSearch)inGenerateOpts.Tools.Verified
go test ./internal/cli/lumo/passes (addedTestWebSearchTools).proton lumo serve --web-searchthen a/v1/chat/completionsquestionneeding fresh information returned a current, web-sourced answer.
Complements #12 (which restores generation on the retired endpoint); this only
affects which tools each generation requests.