Stop sending prompt cache keys on Claude chat conversions (#2003)

Responses conversions still use promptCacheKey, but chat completions now stay a pure shape transform. This keeps Claude -> chat requests aligned with providers that do not understand the field and keeps stream checks consistent with production behavior.

Constraint: Issue #1919 requires removing prompt_cache_key from Claude -> OpenAI Chat requests
Rejected: Add a runtime toggle for chat injection | requested behavior is unconditional removal
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep promptCacheKey limited to Claude -> Responses conversions unless a provider-specific contract is proven
Tested: cargo test anthropic_to_openai
Tested: cargo test anthropic_to_responses_with_cache_key
Tested: cargo test transform_claude_request_for_api_format_responses
Not-tested: Full src-tauri test suite
Related: #1919

src/types.ts

@@ -166,7 +166,7 @@ export interface ProviderMeta {
   apiKeyField?: ClaudeApiKeyField;
   // 是否将 base_url 视为完整 API 端点（代理直接使用此 URL，不拼接路径）
   isFullUrl?: boolean;
-  // Prompt cache key for OpenAI-compatible endpoints (improves cache hit rate)
+  // Prompt cache key for OpenAI Responses-compatible endpoints (improves cache hit rate)
   promptCacheKey?: string;
   // 供应商类型（用于识别 Copilot 等特殊供应商）
   providerType?: string;