feat: add Tavily as parallel search provider option#1
Open
ParakhJaggi wants to merge 2 commits intointerskh:mainfrom
Open
feat: add Tavily as parallel search provider option#1ParakhJaggi wants to merge 2 commits intointerskh:mainfrom
ParakhJaggi wants to merge 2 commits intointerskh:mainfrom
Conversation
added 2 commits
March 23, 2026 16:24
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds Tavily as a configurable search and content extraction provider alongside the existing Querit.ai integration. This is an additive change — all existing Querit code, dependencies, and env vars remain untouched.
What changed
Provider selection logic
selectProvider()helper insearch.jsreadsSEARCH_PROVIDERenv var ("tavily"or"querit")TAVILY_API_KEYis set andQUERIT_API_KEYis absent, uses Tavily; otherwise defaults to Queritsearch.js
tavilySearch()function using@tavily/coreSDK--site-include→includeDomains,--site-exclude→excludeDomains,--date→timeRange,--country→country,-n→maxResults(capped at 20)--langis used with Tavily (unsupported)formatResults()shapeusage()to document both providerscontent.js
tavilyExtract()function using Tavily Extract APIextractWithProvider()dispatcher: tries Tavily Extract when configured, falls back to existing jsdom+Readability pipeline on failureDocumentation
TAVILY_API_KEYandSEARCH_PROVIDERas optional env vars in metadataFiles changed
package.json— added@tavily/coredependencypackage-lock.json— lockfile updatedsearch.js— provider selection + Tavily search pathcontent.js— Tavily Extract with jsdom fallbackSKILL.md— optional env var documentationREADME.md— Tavily setup and provider selection docsDependency changes
@tavily/core@^0.7.2topackage.jsonEnvironment variable changes
TAVILY_API_KEY— Tavily API key, required when using Tavily providerSEARCH_PROVIDER— optional,"tavily"or"querit"; auto-detects if unsetNotes for reviewers
-nexceeds 20--langfilter has no Tavily equivalent; a warning is printed and the filter is ignoredAutomated Review
requires.envis now empty with both keys moved tooptionalEnv;content.js usage()documents TAVILY_API_KEY;extractWithProvider()warns when SEARCH_PROVIDER=tavily but TAVILY_API_KEY is missing; and SKILL.md limitations shows provider-specific max results. The Querit path is fully preserved as an else-branch, the auto-detection logic is consistent betweensearch.jsandcontent.js, dependencies are correctly updated in bothpackage.jsonandpackage-lock.json, andREADME.mdis updated with clear dual-provider setup instructions. Three minor issues remain but none are blocking.