Add Anthropic prompt caching (direct + via OpenRouter)

Caches the system prompt/tools and growing conversation history via
cache_control breakpoints, cutting cost and latency on repeated turns.
Covers both the regular chat path and the tool-calling loop
(chatWithToolMessages), which has its own request-building code and was
initially missed. Cost calculation now accounts for cache write/read
pricing instead of treating all input tokens as full price. Verified
live: cache reads grow turn-over-turn in oAI.log.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

oAI/Providers/AIProvider.swift

@@ -130,11 +130,23 @@ struct ChatResponse: Codable {
         let promptTokens: Int
         let completionTokens: Int
         let totalTokens: Int
+        let cacheCreationInputTokens: Int?
+        let cacheReadInputTokens: Int?
+
+        init(promptTokens: Int, completionTokens: Int, totalTokens: Int, cacheCreationInputTokens: Int? = nil, cacheReadInputTokens: Int? = nil) {
+            self.promptTokens = promptTokens
+            self.completionTokens = completionTokens
+            self.totalTokens = totalTokens
+            self.cacheCreationInputTokens = cacheCreationInputTokens
+            self.cacheReadInputTokens = cacheReadInputTokens
+        }
 
         enum CodingKeys: String, CodingKey {
             case promptTokens = "prompt_tokens"
             case completionTokens = "completion_tokens"
             case totalTokens = "total_tokens"
+            case cacheCreationInputTokens = "cache_creation_input_tokens"
+            case cacheReadInputTokens = "cache_read_input_tokens"
         }
     }