nezumi/9router
1
0
Fork 0
mirror of https://github.com/Nezumi-2711/9router.git synced 2026-09-22 13:38:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix : usage convert

Browse Source
This commit is contained in:
decolua
2026-02-04 09:54:11 +07:00
parent 7881db81ec
commit e6e44ac364
10 changed files with 974 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
open-sse/config/providerModels.js
+5 -2
View File
@@ -27,6 +27,7 @@ export const PROVIDER_MODELS = {
{ id: "gemini-2.5-flash-lite", name: "Gemini 2.5 Flash Lite" },
],
qw: [ // Qwen Code
// { id: "qwen3-coder-next", name: "Qwen3 Coder Next" },
{ id: "qwen3-coder-plus", name: "Qwen3 Coder Plus" },
{ id: "qwen3-coder-flash", name: "Qwen3 Coder Flash" },
{ id: "vision-model", name: "Qwen3 Vision Model" },
@@ -38,7 +39,7 @@ export const PROVIDER_MODELS = {
{ id: "deepseek-r1", name: "DeepSeek R1" },
{ id: "deepseek-v3.2-chat", name: "DeepSeek V3.2 Chat" },
{ id: "deepseek-v3.2-reasoner", name: "DeepSeek V3.2 Reasoner" },
{ id: "minimax-m2", name: "MiniMax M2" },
{ id: "minimax-m2.1", name: "MiniMax M2.1" },
{ id: "glm-4.7", name: "GLM 4.7" },
],
ag: [ // Antigravity - special case: models call different backends
@@ -59,7 +60,7 @@ export const PROVIDER_MODELS = {
{ id: "gpt-5.1-codex", name: "GPT-5.1 Codex" },
// { id: "gpt-5.1-codex-mini", name: "GPT-5.1 Codex Mini" },
{ id: "gpt-5.1-codex-max", name: "GPT-5.1 Codex Max" },
{ id: "gpt-4.1", name: "GPT-4.1" },
// { id: "gpt-4.1", name: "GPT-4.1" },
{ id: "claude-4.5-sonnet", name: "Claude 4.5 Sonnet" },
{ id: "claude-4.5-opus", name: "Claude 4.5 Opus" },
{ id: "claude-4.5-haiku", name: "Claude 4.5 Haiku" },
@@ -101,6 +102,8 @@ export const PROVIDER_MODELS = {
{ id: "glm-4.6v", name: "GLM 4.6V (Vision)" },
],
kimi: [
{ id: "kimi-k2.5", name: "Kimi K2.5" },
{ id: "kimi-k2.5-thinking", name: "Kimi K2.5 Thinking" },
{ id: "kimi-latest", name: "Kimi Latest" },
],
minimax: [
open-sse/handlers/chatCore.js
+4 -3
View File
@@ -3,7 +3,7 @@ import { translateRequest, needsTranslation } from "../translator/index.js";
import { FORMATS } from "../translator/formats.js";
import { createSSETransformStreamWithLogger, createPassthroughStreamWithLogger, COLORS } from "../utils/stream.js";
import { createStreamController, pipeWithDisconnect } from "../utils/streamHandler.js";
import { addBufferToUsage } from "../utils/usageTracking.js";
import { addBufferToUsage, filterUsageForFormat } from "../utils/usageTracking.js";
import { refreshWithRetry } from "../services/tokenRefresh.js";
import { createRequestLogger } from "../utils/requestLogger.js";
import { getModelTargetFormat, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.js";
@@ -435,9 +435,10 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat)
: responseBody;
// Add buffer to usage for client (to prevent CLI context errors)
// Add buffer and filter usage for client (to prevent CLI context errors)
if (translatedResponse?.usage) {
translatedResponse.usage = addBufferToUsage(translatedResponse.usage);
const buffered = addBufferToUsage(translatedResponse.usage);
translatedResponse.usage = filterUsageForFormat(buffered, sourceFormat);
}
return {
open-sse/services/usage.js
+78
View File
@@ -48,6 +48,8 @@ export async function getUsageForProvider(connection) {
return await getClaudeUsage(accessToken);
case "codex":
return await getCodexUsage(accessToken);
case "kiro":
return await getKiroUsage(accessToken, providerSpecificData);
case "qwen":
return await getQwenUsage(accessToken, providerSpecificData);
case "iflow":
@@ -367,6 +369,82 @@ async function getCodexUsage(accessToken) {
}
}
/**
* Kiro (AWS CodeWhisperer) Usage
*/
async function getKiroUsage(accessToken, providerSpecificData) {
try {
const profileArn = providerSpecificData?.profileArn;
if (!profileArn) {
return { message: "Kiro connected. Profile ARN not available for quota tracking." };
}
// Kiro uses AWS CodeWhisperer GetUsageLimits API
const payload = {
origin: "AI_EDITOR",
profileArn: profileArn,
resourceType: "AGENTIC_REQUEST",
};
const response = await fetch("https://codewhisperer.us-east-1.amazonaws.com", {
method: "POST",
headers: {
"Authorization": `Bearer ${accessToken}`,
"Content-Type": "application/x-amz-json-1.0",
"x-amz-target": "AmazonCodeWhispererService.GetUsageLimits",
"Accept": "application/json",
},
body: JSON.stringify(payload),
});
if (!response.ok) {
const errorText = await response.text();
throw new Error(`Kiro API error (${response.status}): ${errorText}`);
}
const data = await response.json();
// Parse usage data from usageBreakdownList
const usageList = data.usageBreakdownList || [];
const quotaInfo = {};
usageList.forEach((breakdown) => {
const resourceType = breakdown.resourceType?.toLowerCase() || "unknown";
const used = breakdown.currentUsageWithPrecision || 0;
const total = breakdown.usageLimitWithPrecision || 0;
quotaInfo[resourceType] = {
used,
total,
remaining: total - used,
resetTime: data.nextDateReset ? new Date(data.nextDateReset).toISOString() : null,
unlimited: false,
};
// Add free trial if available
if (breakdown.freeTrialInfo) {
const freeUsed = breakdown.freeTrialInfo.currentUsageWithPrecision || 0;
const freeTotal = breakdown.freeTrialInfo.usageLimitWithPrecision || 0;
quotaInfo[`${resourceType}_freetrial`] = {
used: freeUsed,
total: freeTotal,
remaining: freeTotal - freeUsed,
resetTime: data.nextDateReset ? new Date(data.nextDateReset).toISOString() : null,
unlimited: false,
};
}
});
return {
plan: data.subscriptionInfo?.subscriptionTitle || "Kiro",
quotas: quotaInfo,
};
} catch (error) {
throw new Error(`Failed to fetch Kiro usage: ${error.message}`);
}
}
/**
* Qwen Usage
*/
open-sse/utils/stream.js
+9 -7
View File
@@ -1,7 +1,7 @@
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, COLORS } from "./usageTracking.js";
import { extractUsage, hasValidUsage, estimateUsage, logUsage, addBufferToUsage, filterUsageForFormat, COLORS } from "./usageTracking.js";
// Re-export COLORS for backward compatibility
export { COLORS };
@@ -145,13 +145,14 @@ export function createSSEStream(options = {}) {
const isFinishChunk = parsed.choices?.[0]?.finish_reason;
if (isFinishChunk && !hasValidUsage(parsed.usage)) {
const estimated = estimateUsage(body, totalContentLength, FORMATS.OPENAI);
parsed.usage = estimated; // Already has buffer from formatUsage
parsed.usage = filterUsageForFormat(estimated, FORMATS.OPENAI); // Filter + already has buffer
output = `data: ${JSON.stringify(parsed)}\n`;
usage = estimated;
injectedUsage = true;
} else if (isFinishChunk && usage) {
// Add buffer to usage for client (but keep original for logging)
parsed.usage = addBufferToUsage(usage);
// Add buffer and filter usage for client (but keep original for logging)
const buffered = addBufferToUsage(usage);
parsed.usage = filterUsageForFormat(buffered, FORMATS.OPENAI);
output = `data: ${JSON.stringify(parsed)}\n`;
injectedUsage = true;
}
@@ -234,11 +235,12 @@ export function createSSEStream(options = {}) {
const isFinishChunk = item.type === "message_delta" || item.choices?.[0]?.finish_reason;
if (state.finishReason && isFinishChunk && !hasValidUsage(item.usage) && totalContentLength > 0) {
const estimated = estimateUsage(body, totalContentLength, sourceFormat);
item.usage = estimated; // Already has buffer from formatUsage
item.usage = filterUsageForFormat(estimated, sourceFormat); // Filter + already has buffer
state.usage = estimated;
} else if (state.finishReason && isFinishChunk && state.usage) {
// Add buffer to usage for client (but keep original in state.usage for logging)
item.usage = addBufferToUsage(state.usage);
// Add buffer and filter usage for client (but keep original in state.usage for logging)
const buffered = addBufferToUsage(state.usage);
item.usage = filterUsageForFormat(buffered, sourceFormat);
}
const output = formatSSE(item, sourceFormat);
open-sse/utils/usageTracking.js
+61 -1
View File
@@ -43,14 +43,72 @@ export function addBufferToUsage(usage) {
result.prompt_tokens += BUFFER_TOKENS;
}
// Update total_tokens if exists
// Calculate or update total_tokens
if (result.total_tokens !== undefined) {
result.total_tokens += BUFFER_TOKENS;
} else if (result.prompt_tokens !== undefined && result.completion_tokens !== undefined) {
// Calculate total_tokens if not exists
result.total_tokens = result.prompt_tokens + result.completion_tokens;
}
return result;
}
export function filterUsageForFormat(usage, targetFormat) {
if (!usage || typeof usage !== "object") return usage;
// Helper to pick only defined fields from usage
const pickFields = (fields) => {
const filtered = {};
for (const field of fields) {
if (usage[field] !== undefined) {
filtered[field] = usage[field];
}
}
return filtered;
};
// Define allowed fields for each format
const formatFields = {
[FORMATS.CLAUDE]: [
'input_tokens', 'output_tokens',
'cache_read_input_tokens', 'cache_creation_input_tokens',
'estimated'
],
[FORMATS.GEMINI]: [
'promptTokenCount', 'candidatesTokenCount', 'totalTokenCount',
'cachedContentTokenCount', 'thoughtsTokenCount',
'estimated'
],
[FORMATS.OPENAI_RESPONSES]: [
'input_tokens', 'output_tokens',
'input_tokens_details', 'output_tokens_details',
'estimated'
],
// OpenAI format (default for OPENAI, CODEX, KIRO, etc.)
default: [
'prompt_tokens', 'completion_tokens', 'total_tokens',
'cached_tokens', 'reasoning_tokens',
'prompt_tokens_details', 'completion_tokens_details',
'estimated'
]
};
// Get fields for target format
let fields = formatFields[targetFormat];
// Use same fields for similar formats
if (targetFormat === FORMATS.GEMINI_CLI || targetFormat === FORMATS.ANTIGRAVITY) {
fields = formatFields[FORMATS.GEMINI];
} else if (targetFormat === FORMATS.OPENAI_RESPONSE) {
fields = formatFields[FORMATS.OPENAI_RESPONSES];
} else if (!fields) {
fields = formatFields.default;
}
return pickFields(fields);
}
/**
* Normalize usage object - ensure all values are valid numbers
*/
@@ -66,6 +124,7 @@ export function normalizeUsage(usage) {
assignNumber("prompt_tokens", usage?.prompt_tokens);
assignNumber("completion_tokens", usage?.completion_tokens);
assignNumber("total_tokens", usage?.total_tokens);
assignNumber("cache_read_input_tokens", usage?.cache_read_input_tokens);
assignNumber("cache_creation_input_tokens", usage?.cache_creation_input_tokens);
assignNumber("cached_tokens", usage?.cached_tokens);
@@ -141,6 +200,7 @@ export function extractUsage(chunk) {
return normalizeUsage({
prompt_tokens: chunk.usageMetadata?.promptTokenCount || 0,
completion_tokens: chunk.usageMetadata?.candidatesTokenCount || 0,
total_tokens: chunk.usageMetadata?.totalTokenCount,
cached_tokens: chunk.usageMetadata?.cachedContentTokenCount,
reasoning_tokens: chunk.usageMetadata?.thoughtsTokenCount
});