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/handlers/chatCore/requestDetail.js

@@ -80,14 +80,29 @@ export function saveUsageStats({ provider, model, tokens, connectionId, apiKey,
 
   if (inTokens === 0 && outTokens === 0) return;
 
+  // Extract cache/reasoning tokens (unified from different formats)
+  const cacheRead = tokens.cache_read_input_tokens || tokens.cached_tokens || tokens.prompt_tokens_details?.cached_tokens || 0;
+  const cacheCreation = tokens.cache_creation_input_tokens || 0;
+  const reasoning = tokens.reasoning_tokens || 0;
+
   const time = new Date().toLocaleTimeString("en-US", { hour12: false, hour: "2-digit", minute: "2-digit", second: "2-digit" });
   const accountSuffix = connectionId ? ` | account=${connectionId.slice(0, 8)}...` : "";
-  console.log(`${COLORS.green}[${time}] 📊 [${label}] ${provider.toUpperCase()} | in=${inTokens} | out=${outTokens}${accountSuffix}${COLORS.reset}`);
+  
+  let msg = `${COLORS.green}[${time}] 📊 [${label}] ${provider?.toUpperCase() || "UNKNOWN"} | in=${inTokens} | out=${outTokens}${accountSuffix}`;
+  if (tokens.estimated) msg += ` ${COLORS.yellow}(estimated)${COLORS.reset}`;
+  if (cacheRead) msg += ` | cache_read=${cacheRead}`;
+  if (cacheCreation) msg += ` | cache_create=${cacheCreation}`;
+  if (reasoning) msg += ` | reasoning=${reasoning}`;
+  msg += `${COLORS.reset}`;
+  console.log(msg);
 
-  // Normalize to OpenAI token shape for storage
+  // Normalize to OpenAI token shape for storage (include all token types)
   const normalized = {
     prompt_tokens: tokens.prompt_tokens ?? tokens.input_tokens ?? 0,
-    completion_tokens: tokens.completion_tokens ?? tokens.output_tokens ?? 0
+    completion_tokens: tokens.completion_tokens ?? tokens.output_tokens ?? 0,
+    cache_read_input_tokens: cacheRead,
+    cache_creation_input_tokens: cacheCreation,
+    reasoning_tokens: reasoning,
   };
 
   saveRequestUsage({

open-sse/handlers/chatCore/streamingHandler.js

@@ -5,7 +5,7 @@ import { pipeWithDisconnect } from "../../utils/streamHandler.js";
 import { PROVIDERS } from "../../config/providers.js";
 import { STREAM_STALL_TIMEOUT_MS } from "../../config/runtimeConfig.js";
 import { buildAbortedResponsesTerminalBytes } from "../../utils/responsesStreamHelpers.js";
-import { buildRequestDetail, extractRequestConfig, saveUsageStats } from "./requestDetail.js";
+import { buildRequestDetail, extractRequestConfig } from "./requestDetail.js";
 import { saveRequestDetail } from "@/lib/usageDb.js";
 
 const SSE_HEADERS = {
@@ -99,8 +99,6 @@ export function buildOnStreamComplete({ provider, model, connectionId, apiKey, r
     }, { id: streamDetailId })).catch(err => {
       console.error("[RequestDetail] Failed to update streaming content:", err.message);
     });
-
-    saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, label: "STREAM USAGE" });
   };
 
   return { onStreamComplete, streamDetailId };

open-sse/utils/stream.js

@@ -1,7 +1,8 @@
 import { translateResponse, initState } from "../translator/index.js";
 import { FORMATS } from "../translator/formats.js";
 import { trackPendingRequest, appendRequestLog } from "@/lib/usageDb.js";
-import { extractUsage, hasValidUsage, estimateUsage, logUsage, addBufferToUsage, filterUsageForFormat, COLORS } from "./usageTracking.js";
+import { extractUsage, hasValidUsage, estimateUsage, addBufferToUsage, filterUsageForFormat, COLORS } from "./usageTracking.js";
+import { saveUsageStats } from "../handlers/chatCore/requestDetail.js";
 import { parseSSELine, hasValuableContent, fixInvalidId, formatSSE } from "./streamHelpers.js";
 import { getOpenAIResponsesEventName, isOpenAIResponsesTerminalEvent, formatIncompleteOpenAIResponsesStreamFailure } from "./responsesStreamHelpers.js";
 import { dbg, isDebugEnabled } from "./debugLog.js";
@@ -331,7 +332,7 @@ export function createSSEStream(options = {}) {
           }
 
           if (hasValidUsage(usage)) {
-            logUsage(provider, usage, model, connectionId, apiKey);
+            saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey });
           } else {
             appendRequestLog({ model, provider, connectionId, tokens: null, status: "200 OK" }).catch(() => { });
           }
@@ -414,7 +415,7 @@ export function createSSEStream(options = {}) {
         }
 
         if (hasValidUsage(state?.usage)) {
-          logUsage(state.provider || targetFormat, state.usage, model, connectionId, apiKey);
+          saveUsageStats({ provider: state.provider || targetFormat, model, tokens: state.usage, connectionId, apiKey });
         } else {
           appendRequestLog({ model, provider, connectionId, tokens: null, status: "200 OK" }).catch(() => { });
         }

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(() => { });
-}