fix(litellm): add dedicated handler for LiteLLM models refresh #4919
+91
−0
Conversation
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
Fixes Kilo-Org#4790 Previously, LiteLLM models were fetched through the generic `requestRouterModels` handler, which only flushed the cache when API credentials changed. This meant that clicking "Refresh Models" without changing credentials would return cached models instead of fetching fresh ones from the server. This fix adds a dedicated `requestLiteLLMModels` handler that: - Always flushes the cache before fetching (consistent with Ollama and LM Studio handlers) - Fetches fresh models from the LiteLLM server - Sends the updated model list to the webview Changes: - Add `requestLiteLLMModels` message type to WebviewMessage.ts - Add `litellmModels` response type to ExtensionMessage.ts - Add new handler in webviewMessageHandler.ts - Add tests for the new handler Co-Authored-By: Claude <[email protected]>
|
Ari4ka
approved these changes
Jan 11, 2026
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Outdated suggestions cannot be applied.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.
Fixes #4790
Summary
Previously, LiteLLM models were fetched through the generic
requestRouterModelshandler, which only flushed the cache when API credentials changed. This meant that clicking "Refresh Models" without changing credentials would return cached models instead of fetching fresh ones from the server.Changes
requestLiteLLMModelsmessage type toWebviewMessage.tslitellmModelsresponse type toExtensionMessage.tswebviewMessageHandler.tsthat:Test Plan
requestLiteLLMModelshandlerCo-Authored-By: Claude [email protected]