feat(ai): LLM metrics tracking and AI span inspector #5066

Job	Run time
e2e / 🧪 CLI v3 tests (ubuntu-latest - pnpm)	1m 50s
sdk-compat / Bun Runtime	2m 7s
sdk-compat / Node.js 22.12 (ubuntu-latest)	2m 3s
sdk-compat / Deno Runtime	2m 0s
e2e / 🧪 CLI v3 tests (ubuntu-latest - npm)	2m 0s
typecheck / typecheck	6m 24s
e2e / 🧪 CLI v3 tests (windows-latest - npm)	3m 32s
sdk-compat / Cloudflare Workers	2m 55s
sdk-compat / Node.js 20.20 (ubuntu-latest)	2m 14s
units / packages / 🧪 Unit Tests: Packages (1, 1)	6m 35s
e2e / 🧪 CLI v3 tests (windows-latest - pnpm)	3m 55s
units / internal / 🧪 Unit Tests: Internal (2, 8)	6m 36s
units / internal / 🧪 Unit Tests: Internal (4, 8)	6m 37s
units / internal / 🧪 Unit Tests: Internal (5, 8)	6m 7s
units / internal / 🧪 Unit Tests: Internal (8, 8)	2m 38s
units / internal / 🧪 Unit Tests: Internal (1, 8)	6m 0s
units / internal / 🧪 Unit Tests: Internal (3, 8)	6m 36s
units / webapp / 🧪 Unit Tests: Webapp (1, 8)	4m 31s
units / internal / 🧪 Unit Tests: Internal (6, 8)	6m 6s
units / webapp / 🧪 Unit Tests: Webapp (5, 8)	4m 30s
units / webapp / 🧪 Unit Tests: Webapp (2, 8)	4m 14s
units / internal / 🧪 Unit Tests: Internal (7, 8)	5m 34s
units / webapp / 🧪 Unit Tests: Webapp (4, 8)	3m 49s
units / webapp / 🧪 Unit Tests: Webapp (3, 8)	4m 31s
units / webapp / 🧪 Unit Tests: Webapp (7, 8)	4m 32s
units / webapp / 🧪 Unit Tests: Webapp (8, 8)	2m 41s
units / webapp / 🧪 Unit Tests: Webapp (6, 8)	2m 59s
units / webapp / 📊 Merge Reports	24s
units / packages / 📊 Merge Reports	1s
units / internal / 📊 Merge Reports	1s
	1h 54m 2s

Provide feedback