feat(ai): LLM metrics tracking and AI span inspector #5078

Job	Run time
sdk-compat / Bun Runtime	2m 3s
sdk-compat / Node.js 22.12 (ubuntu-latest)	2m 4s
typecheck / typecheck	7m 0s
sdk-compat / Deno Runtime	2m 48s
e2e / 🧪 CLI v3 tests (windows-latest - pnpm)	3m 51s
sdk-compat / Cloudflare Workers	2m 18s
units / packages / 🧪 Unit Tests: Packages (1, 1)	8m 52s
sdk-compat / Node.js 20.20 (ubuntu-latest)	1m 55s
units / webapp / 🧪 Unit Tests: Webapp (6, 8)	2m 50s
e2e / 🧪 CLI v3 tests (windows-latest - npm)	4m 49s
e2e / 🧪 CLI v3 tests (ubuntu-latest - npm)	1m 51s
e2e / 🧪 CLI v3 tests (ubuntu-latest - pnpm)	1m 53s
units / webapp / 🧪 Unit Tests: Webapp (3, 8)	6m 0s
units / webapp / 🧪 Unit Tests: Webapp (5, 8)	7m 43s
units / webapp / 🧪 Unit Tests: Webapp (4, 8)	4m 2s
units / webapp / 🧪 Unit Tests: Webapp (7, 8)	8m 50s
units / webapp / 🧪 Unit Tests: Webapp (2, 8)	4m 7s
units / webapp / 🧪 Unit Tests: Webapp (8, 8)	4m 6s
units / webapp / 🧪 Unit Tests: Webapp (1, 8)	5m 56s
units / internal / 🧪 Unit Tests: Internal (4, 8)	6m 30s
units / internal / 🧪 Unit Tests: Internal (2, 8)	8m 46s
units / internal / 🧪 Unit Tests: Internal (1, 8)	7m 0s
units / internal / 🧪 Unit Tests: Internal (8, 8)	2m 52s
units / internal / 🧪 Unit Tests: Internal (3, 8)	8m 40s
units / internal / 🧪 Unit Tests: Internal (7, 8)	5m 40s
units / internal / 🧪 Unit Tests: Internal (6, 8)	6m 21s
units / internal / 🧪 Unit Tests: Internal (5, 8)	6m 17s
units / internal / 📊 Merge Reports	1s
units / webapp / 📊 Merge Reports	1s
units / packages / 📊 Merge Reports	1s
	2h 15m 7s

Provide feedback