docs(ai): Improve README with model discovery and capabilities documentation

- Added note that library only includes tool-calling capable models
- Added Model Discovery section showing how to enumerate models
- Added examples for finding models with specific capabilities
- Added cache read/write costs to model capabilities display
- Clarified that models are auto-fetched from APIs at build time

packages/pods/package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "@mariozechner/pi",
-	"version": "0.5.9",
+	"version": "0.5.10",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "@mariozechner/pi",
-			"version": "0.5.9",
+			"version": "0.5.10",
 			"license": "MIT",
 			"dependencies": {
 				"@ai-sdk/openai": "^2.0.5",

packages/pods/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@mariozechner/pi",
-	"version": "0.5.9",
+	"version": "0.5.10",
 	"description": "CLI tool for managing vLLM deployments on GPU pods",
 	"type": "module",
 	"bin": {
@@ -34,7 +34,7 @@
 		"node": ">=20.0.0"
 	},
 	"dependencies": {
-		"@mariozechner/pi-agent": "^0.5.9",
+		"@mariozechner/pi-agent": "^0.5.10",
 		"chalk": "^5.5.0"
 	},
 	"devDependencies": {}