⚡ Bolt: [performance improvement] Pre-allocate byte slices in SSE event building to avoid fmt.Sprintf reflection and allocations

[rschumann]

💡 What: Replaced fmt.Sprintf with pre-allocated []byte and append/strconv.AppendInt in BuildOpenAIStreamChunkFast and BuildOpenAIStreamFinishChunkFast.
🎯 Why: fmt.Sprintf allocates memory and uses reflection, causing unnecessary overhead in the hot path of SSE event chunk building. Pre-allocating slice capacity and appending avoids intermediate strings and speeds up processing significantly.
📊 Impact: Reduces memory allocations from 8 allocations/op to 1 allocation/op and drops latency by ~8-9x per SSE chunk construction.
🔬 Measurement: Tested with benchmark tests, the op time dropped from ~1655 ns/op to ~184 ns/op. Allocations went from 8 down to 1.

---

PR created automatically by Jules for task 16758369544364900772 started by @rschumann

[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.