⚡ Bolt: [performance improvement] Pre-allocate byte slice in SSE stream builder

[rschumann]

💡 What: Replaced fmt.Sprintf with make([]byte, 0, capacity) and append()/strconv.AppendInt() in BuildOpenAIStreamChunkFast and BuildOpenAIStreamFinishChunkFast.

🎯 Why: fmt.Sprintf uses reflection and allocates multiple strings/byte slices during string formatting, which is slow for SSE event streaming in hot loops.

📊 Impact: Reduces memory allocations in the SSE generation hot path from 8 per chunk down to 1, and decreases execution time from ~1000ns to ~230ns per operation (~4.5x faster).

🔬 Measurement: Benchmarks run via go test -bench=BenchmarkBuildOpenAIStream -benchmem ./internal/runtime/executor.

---

PR created automatically by Jules for task 13061306331548908214 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.