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/lua/adapters/gemini.lua

@@ -100,6 +100,10 @@ function adapter.transform_stream_chunk(raw_chunk)
         local t = chunk.usageMetadata.totalTokenCount or 0
         if p > 0 or c > 0 or t > 0 then
             uses = { prompt = p, completion = c, total = t }
+            local cacheRead = chunk.usageMetadata.cachedContentTokenCount or 0
+            if cacheRead > 0 then
+                uses.prompt_tokens_details = { cached_tokens = cacheRead }
+            end
         end
     end