mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-02 13:22:11 +03:00
c6eadc504b
- Fix getLoggedInputTokens to return full prompt_tokens (input + cache_read + cache_creation) - Fix usageExtractor for non-streaming Claude responses to calculate total correctly - Add formatUsageLog helper to show CR=<cache_read> in logs - Add migration 012 to fix historical token counts in usage_history - Move prompt cache metrics from Settings to /dashboard/cache page Per Claude API docs: Total input tokens = input_tokens + cache_creation_input_tokens + cache_read_input_tokens Fixes issue where totalInputTokens (71k) was less than totalCacheCreationTokens (1.35M). Tested: - All 1134 unit tests pass - Cache metrics API returns correct totals - Migration is idempotent and tracked in _omniroute_migrations - Logs show cache read tokens: 'in=6055 | out=211 | CR=22399' Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
75 lines
2.7 KiB
TypeScript
75 lines
2.7 KiB
TypeScript
/**
|
|
* Extract usage from non-streaming response body
|
|
* Handles different provider response formats
|
|
*/
|
|
export function extractUsageFromResponse(responseBody, provider) {
|
|
if (!responseBody || typeof responseBody !== "object") return null;
|
|
|
|
// OpenAI format (has prompt_tokens / completion_tokens)
|
|
if (
|
|
responseBody.usage &&
|
|
typeof responseBody.usage === "object" &&
|
|
responseBody.usage.prompt_tokens !== undefined
|
|
) {
|
|
return {
|
|
prompt_tokens: responseBody.usage.prompt_tokens || 0,
|
|
completion_tokens: responseBody.usage.completion_tokens || 0,
|
|
cached_tokens: responseBody.usage.prompt_tokens_details?.cached_tokens,
|
|
reasoning_tokens: responseBody.usage.completion_tokens_details?.reasoning_tokens,
|
|
};
|
|
}
|
|
|
|
// OpenAI Responses API format (input_tokens / output_tokens)
|
|
const responsesUsage = responseBody.response?.usage || responseBody.usage;
|
|
if (
|
|
responsesUsage &&
|
|
typeof responsesUsage === "object" &&
|
|
(responsesUsage.input_tokens !== undefined || responsesUsage.output_tokens !== undefined)
|
|
) {
|
|
return {
|
|
prompt_tokens: responsesUsage.input_tokens || 0,
|
|
completion_tokens: responsesUsage.output_tokens || 0,
|
|
cache_read_input_tokens: responsesUsage.cache_read_input_tokens,
|
|
cached_tokens:
|
|
responsesUsage.input_tokens_details?.cached_tokens ??
|
|
responsesUsage.cache_read_input_tokens,
|
|
cache_creation_input_tokens: responsesUsage.cache_creation_input_tokens,
|
|
reasoning_tokens:
|
|
responsesUsage.reasoning_tokens || responsesUsage.output_tokens_details?.reasoning_tokens,
|
|
};
|
|
}
|
|
|
|
// Claude format
|
|
if (
|
|
responseBody.usage &&
|
|
typeof responseBody.usage === "object" &&
|
|
(responseBody.usage.input_tokens !== undefined ||
|
|
responseBody.usage.output_tokens !== undefined)
|
|
) {
|
|
const inputTokens = responseBody.usage.input_tokens || 0;
|
|
const cacheRead = responseBody.usage.cache_read_input_tokens || 0;
|
|
const cacheCreation = responseBody.usage.cache_creation_input_tokens || 0;
|
|
|
|
// Total prompt tokens = input + cache_read + cache_creation (per Claude API docs)
|
|
const promptTokens = inputTokens + cacheRead + cacheCreation;
|
|
|
|
return {
|
|
prompt_tokens: promptTokens,
|
|
completion_tokens: responseBody.usage.output_tokens || 0,
|
|
cache_read_input_tokens: cacheRead,
|
|
cache_creation_input_tokens: cacheCreation,
|
|
};
|
|
}
|
|
|
|
// Gemini format
|
|
if (responseBody.usageMetadata && typeof responseBody.usageMetadata === "object") {
|
|
return {
|
|
prompt_tokens: responseBody.usageMetadata.promptTokenCount || 0,
|
|
completion_tokens: responseBody.usageMetadata.candidatesTokenCount || 0,
|
|
reasoning_tokens: responseBody.usageMetadata.thoughtsTokenCount,
|
|
};
|
|
}
|
|
|
|
return null;
|
|
}
|