Skip to content

Conversation

@mcowger
Copy link
Contributor

@mcowger mcowger commented Nov 28, 2025

Context

Prevent fetchers from running unconditionally. Fixes #4065

Implementation

Add hasConfiguredProfile helper to filter model fetch candidates based on
listApiConfigMeta, preventing unnecessary API calls for providers without
configured profiles.

  • Extract listApiConfigMeta from state to check configured providers
  • Filter candidates to only fetch models for providers in use
  • Make litellm and io-intelligence type properties optional
  • Add apiKey to glama and vercel-ai-gateway candidate options
  • Update tests to verify profile-based filtering behavior

How to Test

Start a vscode instance with vscode configured only for Kilo gateway with a proxy server. Note that fetchers are not run for unconfigured providers.

Get in Touch

mcowger

@changeset-bot
Copy link

changeset-bot bot commented Nov 28, 2025

🦋 Changeset detected

Latest commit: 1d3e797

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package
Name Type
kilo-code Minor

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

… profiles. Fixes Kilo-Org#4065

Add hasConfiguredProfile helper to filter model fetch candidates based on
listApiConfigMeta, preventing unnecessary API calls for providers without
configured profiles.

- Extract listApiConfigMeta from state to check configured providers
- Filter candidates to only fetch models for providers in use
- Make litellm and io-intelligence type properties optional
- Add apiKey to glama and vercel-ai-gateway candidate options
- Update tests to verify profile-based filtering behavior
@mcowger mcowger force-pushed the mcowger/startupqueries branch from 0920abd to b765d99 Compare November 28, 2025 02:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Unconfigured Providers perform a model fetch on startup

1 participant