fix(gemini-adapter): pass request URL context for model extraction#8
Open
hariom888 wants to merge 1 commit into
Open
fix(gemini-adapter): pass request URL context for model extraction#8hariom888 wants to merge 1 commit into
hariom888 wants to merge 1 commit into
Conversation
…d to gemini-1.5-flash
The standardFetch function called adapterRegistry.process(responseData) with only the response, never passing the request. The Gemini adapter's normalize() function accepts an optional request parameter to extract the model name, but it was always undefined, causing the model to always fall back to the hardcoded default 'gemini-1.5-flash'.
Fix: build a requestContext object { url, body } in standardFetch and pass it as the second argument to adapterRegistry.process(). Update the Gemini adapter to extract the model name from the URL pattern /models/MODEL:action.
The modelVersion field in the response still takes priority when present.
Other adapters (OpenAI, Anthropic) are unaffected because they ignore the extra argument.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes Gemini model extraction fallback behavior caused by missing request context propagation.
Previously,
standardFetch()calledadapterRegistry.process(responseData)with only the response object, so the Gemini adapter's optionalrequestparameter was alwaysundefined. This caused the adapter to always fall back to the hardcoded default modelgemini-1.5-flash.Changes
Build a
requestContextobject{ url, body }insidestandardFetch()Pass request context as the second argument to
adapterRegistry.process()Update Gemini adapter model extraction logic to parse model names from URL patterns:
/models/MODEL:actionPreserve
modelVersionpriority when present in responsesAdded DOM typings support for
RequestcompatibilityImpact
Verification
npm run buildpasses successfullyCloses #5