⚡ Bolt: Optimize ZimaOS and Ollama model fetching

[bobdivx]

💡 What: Refactored collectZimaOSV1ModelEntries and fetchOllamaTagNames in src/lib/forge-openai-surface.ts to execute downstream gateway API HTTP requests in parallel using Promise.all rather than sequential execution inside loops.

🎯 Why: Fetching models sequentially blocks execution until the slower or timed-out fallback endpoints resolve, slowing down the interface and overall sync process. Executing all available configured gateway fallback routes in parallel guarantees the function evaluates as fast as the single slowest response (rather than their sum).

📊 Impact: Reduces overall latency of AI model listing operations, notably speeding up AI sync processes and rendering times for AI capability lists across the application interface.

🔬 Measurement: Verify changes by checking test suites pass (pnpm check and pnpm test) and observing the execution speed inside application flows evaluating available models (e.g. Chat settings, model orchestration routes).

---

PR created automatically by Jules for task 6495858125349309947 started by @bobdivx

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
forge	Ready	Preview, Comment	May 6, 2026 7:03pm

[gemini-code-assist]

Code Review

This pull request refactors the collectZimaOSV1ModelEntries function to parallelize network requests using Promise.all, reducing latency by fetching multiple paths concurrently instead of sequentially. A corresponding entry was added to .jules/bolt.md to document the trade-off between network overhead and performance. I have no feedback to provide as there were no review comments to evaluate.