luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(usage): read Responses-shape cached_tokens in extractUsageFromResponse

Browse Source 
Non-streaming codex traffic recorded cached_tokens: 0 even when upstream
prompt caching worked. The Claude-format branch (which OpenAI Responses
usage also matches) never read input_tokens_details, and the OpenAI
branch ignored a top-level flat cached_tokens. Read both in both
branches; Responses prompts are cache-inclusive so canonicalizeUsage
passes the value through without folding. 5 new regression tests.
This commit is contained in:
IEatCodeDaily
2026-09-03 09:47:29 +07:00
committed by decolua
parent 5caa72f5fb
commit e7dd72a8d7
2 changed files with 81 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
open-sse/handlers/chatCore/requestDetail.js
View File

@@ -25,10 +25,16 @@ export function extractUsageFromResponse(responseBody) {
if (!responseBody || typeof responseBody !== "object") return null;
// Claude format
// Note: OpenAI Responses usage ({input_tokens, input_tokens_details:{cached_tokens}})
// also matches this branch. Its prompt is cache-INCLUSIVE and its cache rides in
// input_tokens_details, so emit it as cached_tokens — the convention
// canonicalizeUsage() passes through without folding. Reading it here keeps
// cache accounting correct for /v1/responses and codex traffic.
if (responseBody.usage?.input_tokens !== undefined) {
return {
prompt_tokens: responseBody.usage.input_tokens || 0,
completion_tokens: responseBody.usage.output_tokens || 0,
cached_tokens: responseBody.usage.cached_tokens ?? responseBody.usage.input_tokens_details?.cached_tokens,
cache_read_input_tokens: responseBody.usage.cache_read_input_tokens,
cache_creation_input_tokens: responseBody.usage.cache_creation_input_tokens
};
@@ -39,7 +45,7 @@ export function extractUsageFromResponse(responseBody) {
return {
prompt_tokens: responseBody.usage.prompt_tokens || 0,
completion_tokens: responseBody.usage.completion_tokens || 0,
cached_tokens: responseBody.usage.prompt_tokens_details?.cached_tokens,
cached_tokens: responseBody.usage.cached_tokens ?? responseBody.usage.prompt_tokens_details?.cached_tokens,
reasoning_tokens: responseBody.usage.completion_tokens_details?.reasoning_tokens
};
}