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/anthropic.lua

@@ -82,6 +82,13 @@ function adapter.transform_response(raw_body)
         unified.token_usage.prompt = resp.usage.input_tokens or 0
         unified.token_usage.completion = resp.usage.output_tokens or 0
         unified.token_usage.total = (resp.usage.input_tokens or 0) + (resp.usage.output_tokens or 0)
+        -- Anthropic reports cache_read_input_tokens; normalize into
+        -- OpenAI-standard prompt_tokens_details.cached_tokens so clients
+        -- (dsh) see the cache hit count.
+        local cacheRead = resp.usage.cache_read_input_tokens or 0
+        if cacheRead > 0 then
+            unified.token_usage.prompt_tokens_details = { cached_tokens = cacheRead }
+        end
     end
 
     if resp.content and #resp.content > 0 then
@@ -107,6 +114,10 @@ function adapter.transform_stream_chunk(raw_chunk)
             local c = u.output_tokens or 0
             if p > 0 or c > 0 then
                 uses = { prompt = p, completion = c, total = p + c }
+                local cacheRead = u.cache_read_input_tokens or 0
+                if cacheRead > 0 then
+                    uses.prompt_tokens_details = { cached_tokens = cacheRead }
+                end
             end
         end
         if uses ~= nil then