fix: merge logUsage + saveUsageStats to prevent duplicate usage stats for streaming requests

- Enhanced saveUsageStats to include cache tokens (cache_read, cache_creation), reasoning tokens, and estimated flag
- Replaced logUsage calls in stream.js with saveUsageStats (2 locations)
- Removed duplicate saveUsageStats call from streamingHandler.js onStreamComplete
- Removed logUsage function and unused imports from usageTracking.js
- Each streaming request now writes exactly 1 usage record instead of 2

open-sse/utils/usageTracking.js

@@ -2,7 +2,6 @@
  * Token Usage Tracking - Extract, normalize, estimate and log token usage
  */
 
-import { saveRequestUsage, appendRequestLog } from "@/lib/usageDb.js";
 import { FORMATS } from "../translator/formats.js";
 
 // ANSI color codes
@@ -299,49 +298,3 @@ export function estimateUsage(body, contentLength, targetFormat = FORMATS.OPENAI
     targetFormat
   );
 }
-
-/**
- * Log usage with cache info (green color)
- */
-export function logUsage(provider, usage, model = null, connectionId = null, apiKey = null) {
-  if (!usage || typeof usage !== "object") return;
-
-  const p = provider?.toUpperCase() || "UNKNOWN";
-
-  // Support both formats:
-  // - OpenAI: prompt_tokens, completion_tokens
-  // - Claude: input_tokens, output_tokens
-  const inTokens = usage?.prompt_tokens || usage?.input_tokens || 0;
-  const outTokens = usage?.completion_tokens || usage?.output_tokens || 0;
-  const accountPrefix = connectionId ? connectionId.slice(0, 8) + "..." : "unknown";
-
-  let msg = `[${getTimeString()}] 📊 ${COLORS.green}[USAGE] ${p} | in=${inTokens} | out=${outTokens} | account=${accountPrefix}${COLORS.reset}`;
-
-  // Add estimated flag if present
-  if (usage.estimated) {
-    msg += ` ${COLORS.yellow}(estimated)${COLORS.reset}`;
-  }
-
-  // Add cache info if present (unified from different formats)
-  const cacheRead = usage.cache_read_input_tokens || usage.cached_tokens || usage.prompt_tokens_details?.cached_tokens;
-  if (cacheRead) msg += ` | cache_read=${cacheRead}`;
-
-  const cacheCreation = usage.cache_creation_input_tokens;
-  if (cacheCreation) msg += ` | cache_create=${cacheCreation}`;
-
-  const reasoning = usage.reasoning_tokens;
-  if (reasoning) msg += ` | reasoning=${reasoning}`;
-
-  console.log(msg);
-
-  // Save to usage DB
-  const tokens = {
-    prompt_tokens: inTokens,
-    completion_tokens: outTokens,
-    cache_read_input_tokens: cacheRead || 0,
-    cache_creation_input_tokens: cacheCreation || 0,
-    reasoning_tokens: reasoning || 0
-  };
-  saveRequestUsage({ model, provider, connectionId, tokens, apiKey: apiKey || undefined }).catch(() => { });
-  appendRequestLog({ model, provider, connectionId, tokens, status: "200 OK" }).catch(() => { });
-}