feat(ai): LLM metrics tracking and AI span inspector #5019

Job	Run time
typecheck / typecheck	6m 16s
sdk-compat / Deno Runtime	2m 2s
sdk-compat / Node.js 22.12 (ubuntu-latest)	1m 55s
e2e / 🧪 CLI v3 tests (ubuntu-latest - npm)	1m 47s
sdk-compat / Cloudflare Workers	2m 7s
e2e / 🧪 CLI v3 tests (windows-latest - npm)	4m 53s
e2e / 🧪 CLI v3 tests (ubuntu-latest - pnpm)	1m 58s
sdk-compat / Node.js 20.20 (ubuntu-latest)	2m 9s
units / packages / 🧪 Unit Tests: Packages (1, 1)	9m 0s
sdk-compat / Bun Runtime	1m 57s
e2e / 🧪 CLI v3 tests (windows-latest - pnpm)	5m 4s
units / webapp / 🧪 Unit Tests: Webapp (7, 8)	6m 6s
units / webapp / 🧪 Unit Tests: Webapp (1, 8)	6m 4s
units / internal / 🧪 Unit Tests: Internal (5, 8)	4m 34s
units / internal / 🧪 Unit Tests: Internal (3, 8)	10m 2s
units / webapp / 🧪 Unit Tests: Webapp (4, 8)	4m 14s
units / webapp / 🧪 Unit Tests: Webapp (3, 8)	8m 44s
units / internal / 🧪 Unit Tests: Internal (6, 8)	5m 49s
units / webapp / 🧪 Unit Tests: Webapp (5, 8)	8m 1s
units / internal / 🧪 Unit Tests: Internal (4, 8)	5m 46s
units / webapp / 🧪 Unit Tests: Webapp (2, 8)	4m 2s
units / internal / 🧪 Unit Tests: Internal (7, 8)	5m 37s
units / internal / 🧪 Unit Tests: Internal (1, 8)	5m 32s
units / internal / 🧪 Unit Tests: Internal (8, 8)	6m 20s
units / webapp / 🧪 Unit Tests: Webapp (6, 8)	2m 46s
units / internal / 🧪 Unit Tests: Internal (2, 8)	10m 20s
units / webapp / 🧪 Unit Tests: Webapp (8, 8)	2m 45s
units / webapp / 📊 Merge Reports	44s
units / packages / 📊 Merge Reports	19s
units / internal / 📊 Merge Reports	25s
	2h 17m 18s

Provide feedback