refactor(open-sse): extract buildUsage helper, dedup token-details (B2)

Add helpers/usageHelper.js for conditional prompt/completion token details.
Apply to gemini/codex/claude response translators; keep each provider's token
math intact. No behavior change; golden + gate: no regression.

Co-authored-by: Cursor <cursoragent@cursor.com>

open-sse/translator/helpers/usageHelper.js

@@ -0,0 +1,14 @@
+// Build OpenAI usage object. Caller computes prompt/completion/total (provider math).
+// Optional details added only when > 0 (matches existing claude/gemini/codex behavior).
+export function buildUsage({ promptTokens, completionTokens, totalTokens, cachedTokens = 0, cacheCreationTokens = 0, reasoningTokens = 0 }) {
+  const usage = { prompt_tokens: promptTokens, completion_tokens: completionTokens, total_tokens: totalTokens };
+  if (cachedTokens > 0 || cacheCreationTokens > 0) {
+    usage.prompt_tokens_details = {};
+    if (cachedTokens > 0) usage.prompt_tokens_details.cached_tokens = cachedTokens;
+    if (cacheCreationTokens > 0) usage.prompt_tokens_details.cache_creation_tokens = cacheCreationTokens;
+  }
+  if (reasoningTokens > 0) {
+    usage.completion_tokens_details = { reasoning_tokens: reasoningTokens };
+  }
+  return usage;
+}

open-sse/translator/response/claude-to-openai.js

@@ -1,6 +1,7 @@
 import { register } from "../index.js";
 import { FORMATS } from "../formats.js";
 import { buildChunk } from "../helpers/chunkBuilder.js";
+import { buildUsage } from "../helpers/usageHelper.js";
 
 // Create OpenAI chunk helper
 function createChunk(state, delta, finishReason = null) {
@@ -127,19 +128,13 @@ export function claudeToOpenAIResponse(chunk, state) {
         const finalChunk = createChunk(state, {}, state.finishReason);
 
         if (state.usage) {
-          finalChunk.usage = {
-            prompt_tokens: state.usage.prompt_tokens,
-            completion_tokens: state.usage.completion_tokens,
-            total_tokens: state.usage.total_tokens
-          };
-
-          const cacheRead = state.usage.cache_read_input_tokens;
-          const cacheCreate = state.usage.cache_creation_input_tokens;
-          if (cacheRead > 0 || cacheCreate > 0) {
-            finalChunk.usage.prompt_tokens_details = {};
-            if (cacheRead > 0) finalChunk.usage.prompt_tokens_details.cached_tokens = cacheRead;
-            if (cacheCreate > 0) finalChunk.usage.prompt_tokens_details.cache_creation_tokens = cacheCreate;
-          }
+          finalChunk.usage = buildUsage({
+            promptTokens: state.usage.prompt_tokens,
+            completionTokens: state.usage.completion_tokens,
+            totalTokens: state.usage.total_tokens,
+            cachedTokens: state.usage.cache_read_input_tokens || 0,
+            cacheCreationTokens: state.usage.cache_creation_input_tokens || 0
+          });
         }
 
         results.push(finalChunk);

open-sse/translator/response/gemini-to-openai.js

@@ -1,6 +1,7 @@
 import { register } from "../index.js";
 import { FORMATS } from "../formats.js";
 import { buildChunk } from "../helpers/chunkBuilder.js";
+import { buildUsage } from "../helpers/usageHelper.js";
 
 // Build chunk meta for current gemini state
 function chunkMeta(state) {
@@ -144,25 +145,7 @@ export function geminiToOpenAIResponse(chunk, state) {
     // completion_tokens = candidatesTokenCount + thoughtsTokenCount (match Go code)
     const completionTokens = candidatesTokens + thoughtsTokens;
     
-    state.usage = {
-      prompt_tokens: promptTokens,
-      completion_tokens: completionTokens,
-      total_tokens: totalTokens
-    };
-    
-    // Add prompt_tokens_details if cached tokens exist
-    if (cachedTokens > 0) {
-      state.usage.prompt_tokens_details = {
-        cached_tokens: cachedTokens
-      };
-    }
-    
-    // Add completion_tokens_details if reasoning tokens exist
-    if (thoughtsTokens > 0) {
-      state.usage.completion_tokens_details = {
-        reasoning_tokens: thoughtsTokens
-      };
-    }
+    state.usage = buildUsage({ promptTokens, completionTokens, totalTokens, cachedTokens, reasoningTokens: thoughtsTokens });
   }
 
   // Finish reason - include usage in final chunk

open-sse/translator/response/openai-responses.js

@@ -5,6 +5,7 @@
 import { register } from "../index.js";
 import { FORMATS } from "../formats.js";
 import { buildChunk } from "../helpers/chunkBuilder.js";
+import { buildUsage } from "../helpers/usageHelper.js";
 
 /**
  * Translate OpenAI chunk to Responses API events
@@ -466,18 +467,7 @@ export function openaiResponsesToOpenAIResponse(chunk, state) {
       // Cache info is in input_tokens_details.cached_tokens
       const cacheReadTokens = responseUsage.input_tokens_details?.cached_tokens || responseUsage.cache_read_input_tokens || 0;
       
-      state.usage = {
-        prompt_tokens: inputTokens,
-        completion_tokens: outputTokens,
-        total_tokens: inputTokens + outputTokens
-      };
-      
-      // Add prompt_tokens_details if cache tokens exist
-      if (cacheReadTokens > 0) {
-        state.usage.prompt_tokens_details = {
-          cached_tokens: cacheReadTokens
-        };
-      }
+      state.usage = buildUsage({ promptTokens: inputTokens, completionTokens: outputTokens, totalTokens: inputTokens + outputTokens, cachedTokens: cacheReadTokens });
     }
     
     if (!state.finishReasonSent) {