feat(types): pass through upstream cache tokens in TokenUsage

dsh displays cache-hit %, but llmsproxy dropped every upstream's cache
fields — deepseek prompt_cache_hit_tokens, OpenAI prompt_tokens_details.
cached_tokens, anthropic cache_read_input_tokens, gemini cachedContentTokenCount.

Changes:
- TokenUsage: add PromptTokensDetails (with CachedTokens) + PromptCacheHit/Miss
- MarshalJSON: emit prompt_tokens_details.cached_tokens (OpenAI v2 standard)
  and prompt_cache_hit/miss_tokens (DeepSeek legacy) — dsh reads the former
  first, falls back to the latter
- mergeUsage: preserve cache fields across stream chunks
- standardSSEChunk: parse the upstream raw prompt_tokens_details too
- deepseek.lua: forward prompt_cache_hit/miss_tokens + create
  prompt_tokens_details from them
- openai.lua: forward prompt_tokens_details.cached_tokens and legacy
  prompt_cache_hit/miss_tokens; normalize legacy hits into the standard
  object so dsh sees them regardless of upstream format
- anthropic.lua: map cache_read_input_tokens → prompt_tokens_details
- gemini.lua: map cachedContentTokenCount → prompt_tokens_details

internal/provider/provider.go

@@ -1058,12 +1058,17 @@ func standardSSEChunk(data string) string {
 			FinishReason *string `json:"finish_reason"`
 		} `json:"choices"`
 		UpstreamUsage struct {
-			PromptTokens     int `json:"prompt_tokens"`
-			CompletionTokens int `json:"completion_tokens"`
-			TotalTokens      int `json:"total_tokens"`
-			Prompt           int `json:"prompt"`
-			Completion       int `json:"completion"`
-			Total            int `json:"total"`
+			PromptTokens        int `json:"prompt_tokens"`
+			CompletionTokens    int `json:"completion_tokens"`
+			TotalTokens         int `json:"total_tokens"`
+			Prompt              int `json:"prompt"`
+			Completion          int `json:"completion"`
+			Total               int `json:"total"`
+			PromptCacheHit      int `json:"prompt_cache_hit_tokens"`
+			PromptCacheMiss     int `json:"prompt_cache_miss_tokens"`
+			PromptTokensDetails *struct {
+				CachedTokens int `json:"cached_tokens"`
+			} `json:"prompt_tokens_details"`
 		} `json:"usage"`
 	}
 	if err := json.Unmarshal([]byte(data), &raw); err != nil {
@@ -1076,9 +1081,16 @@ func standardSSEChunk(data string) string {
 	pu := raw.UpstreamUsage
 	if pu.Total > 0 || pu.TotalTokens > 0 {
 		usage = &types.TokenUsage{
-			Prompt:     pickFirst(pu.PromptTokens, pu.Prompt),
-			Completion: pickFirst(pu.CompletionTokens, pu.Completion),
-			Total:      pickFirst(pu.TotalTokens, pu.Total),
+			Prompt:          pickFirst(pu.PromptTokens, pu.Prompt),
+			Completion:      pickFirst(pu.CompletionTokens, pu.Completion),
+			Total:           pickFirst(pu.TotalTokens, pu.Total),
+			PromptCacheHit:  pu.PromptCacheHit,
+			PromptCacheMiss: pu.PromptCacheMiss,
+		}
+		if pu.PromptTokensDetails != nil && pu.PromptTokensDetails.CachedTokens > 0 {
+			usage.PromptTokensDetails = &types.PromptTokensDetails{
+				CachedTokens: pu.PromptTokensDetails.CachedTokens,
+			}
 		}
 	}
 	finish := ""