fix: Enhance response validation in testProviderConnection and update gemini-3-flash model ID to gemini-3-flash-preview#112
Conversation
… gemini-3-flash model ID to gemini-3-flash-preview
🤖 Augment PR SummarySummary: Improves provider connection testing by treating empty-string model outputs as a valid response and surfacing 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
|
|
||
| if (result.text) { | ||
| // Check if we got a valid response - result.text can be empty string for some models | ||
| // Also check finishReason to ensure the request actually completed |
There was a problem hiding this comment.
The comment says we “check finishReason to ensure the request actually completed”, but the logic only checks result.text for null/undefined. This can be misleading (and may mask cases where finishReason indicates a non-successful completion) unless finishReason is actually validated or the comment is adjusted.
Severity: low
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
| defaultModels: [ | ||
| { id: 'gemini-3-pro-preview' }, | ||
| { id: 'gemini-3-flash' }, | ||
| { id: 'gemini-3-flash-preview' }, |
There was a problem hiding this comment.
Changing the default Google model ID to gemini-3-flash-preview may leave existing persisted configs still referencing gemini-3-flash in enabledModels, which could break model creation/testing if that ID is no longer accepted upstream. Consider whether you need any backwards-compat handling (e.g., migration/alias) for users who previously selected the old ID.
Severity: medium
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
1 participant
No description provided.