fix: resolve visual summarizer from agent model configuration - #141
Open
lihujun101 wants to merge 4 commits into
Open
lihujun101 wants to merge 4 commits into
lihujun101 wants to merge 4 commits into
Conversation
…ix-summarizer-config-lookup
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When
agent.flash.step_summarizer.modelis an empty string,VisualStepSummarizertries to resolvesummarizeras a utility node. The configuration defines it as an agent node, so the lookup fails and the exception handler falls back to Google, potentially reporting a missing Gemini API key even when another provider is configured.Remove
is_utils=Trueso this branch readsnodes.summarizerthrough the existing agent model resolver. The change is one line in one file. Explicit nonemptystep_summarizer.modelvalues still follow the existing Google path; this is a narrow fix related to #95.Validation: offline checks with a mocked model factory confirmed that the empty-model path selects the configured OpenAI model and an alternative Anthropic model without invoking the Google fallback.
git diff --checkpassed. No live model or device calls were made.