docs: link to OpenRouter docs and remove duplicated content

- Replace local docs link with https://openrouter.ai/docs/features/prompt-caching
- Remove duplicated Effect AI usage examples and notes
- Keep README minimal to avoid content going stale
- Code examples are in the actual .ts files

Author: subtleGradient

typescript/effect-ai/src/prompt-caching/README.md

@@ -5,45 +5,8 @@ Examples demonstrating prompt caching with @effect/ai and @effect/ai-openrouter.
 ## Documentation
 
 For full prompt caching documentation including all providers, pricing, and configuration details, see:
-- **[Prompt Caching Guide](../../../../docs/prompt-caching.md)**
+- **[OpenRouter Prompt Caching Guide](https://openrouter.ai/docs/features/prompt-caching)**
 
 ## Examples in This Directory
 
 See the TypeScript files in this directory for specific examples.
-
-## Effect AI Usage
-
-```typescript
-import * as OpenRouterLanguageModel from '@effect/ai-openrouter/OpenRouterLanguageModel';
-
-const OpenRouterModelLayer = OpenRouterLanguageModel.layer({
-  model: 'anthropic/claude-3.5-sonnet',
-  config: {
-    stream_options: { include_usage: true }, // Required for cache metrics
-  },
-});
-
-const program = Effect.gen(function* () {
-  const response = yield* LanguageModel.generateText({
-    prompt: Prompt.make([{
-      role: 'user',
-      content: [{
-        type: 'text',
-        text: 'Large context...',
-        options: {
-          openrouter: { cacheControl: { type: 'ephemeral' } }
-        }
-      }]
-    }])
-  });
-
-  // Check cache metrics
-  const cached = response.usage.cachedInputTokens ?? 0;
-});
-```
-
-## Effect-Specific Notes
-
-- Use layer-based dependency injection for client and model configuration
-- `stream_options.include_usage` must be set in the model layer config
-- Cache metrics appear in `response.usage.cachedInputTokens`