fixed tracking

src/providers/helpers.rs

@@ -261,9 +261,9 @@ pub fn parse_openai_response(resp_json: &Value, model: String) -> Result<Provide
         .or_else(|| usage["prompt_cache_hit_tokens"].as_u64())
         .unwrap_or(0) as u32;
 
-    // DeepSeek reports cache_write as prompt_cache_miss_tokens (tokens written to cache for future use).
-    // OpenAI doesn't report cache_write in this location, but may in the future.
-    let cache_write_tokens = usage["prompt_cache_miss_tokens"].as_u64().unwrap_or(0) as u32;
+    // DeepSeek reports prompt_cache_miss_tokens which are just regular non-cached tokens.
+    // They do not incur a separate cache_write fee, so we don't map them here to avoid double-charging.
+    let cache_write_tokens = 0;
 
     Ok(ProviderResponse {
         content,
@@ -300,9 +300,7 @@ pub fn parse_openai_stream_chunk(
             .or_else(|| u["prompt_cache_hit_tokens"].as_u64())
             .unwrap_or(0) as u32;
 
-        let cache_write_tokens = u["prompt_cache_miss_tokens"]
-            .as_u64()
-            .unwrap_or(0) as u32;
+        let cache_write_tokens = 0;
 
         Some(StreamUsage {
             prompt_tokens,