wyxrouter 0.4.71

package/open-sse/executors/vertex.js

@@ -0,0 +1,131 @@
+import { BaseExecutor } from "./base.js";
+import { PROVIDERS } from "../config/providers.js";
+import { parseVertexSaJson, refreshVertexToken } from "../services/tokenRefresh.js";
+import { proxyAwareFetch } from "../utils/proxyFetch.js";
+
+// Cache project IDs resolved from raw API keys { apiKey → projectId }
+const projectIdCache = new Map();
+
+/**
+ * Resolve GCP project ID from a raw Vertex API key.
+ * Sends a dummy 404 request and parses "projects/{id}" from the error message.
+ */
+async function resolveProjectId(apiKey) {
+  if (projectIdCache.has(apiKey)) return projectIdCache.get(apiKey);
+
+  const res = await fetch(
+    `https://aiplatform.googleapis.com/v1/publishers/google/models/__probe__:generateContent?key=${apiKey}`,
+    { method: "POST", headers: { "Content-Type": "application/json" }, body: "{}" }
+  );
+  const json = await res.json().catch(() => null);
+  const msg = json?.[0]?.error?.message || json?.error?.message || "";
+  const match = msg.match(/projects\/([^/]+)\//);
+  const projectId = match?.[1] || null;
+
+  if (projectId) projectIdCache.set(apiKey, projectId);
+  return projectId;
+}
+
+/**
+ * VertexExecutor - Google Cloud Vertex AI
+ *
+ * "vertex"         → Gemini models via regional/global Vertex endpoint
+ * "vertex-partner" → Partner models (Llama, Mistral, GLM, DeepSeek, Qwen)
+ *                    via global OpenAI-compatible endpoint
+ *
+ * Auth: SA JSON (stored as apiKey) → JWT assertion → Bearer token (via jose)
+ * Token is minted/cached in tokenRefresh.js, not here.
+ */
+export class VertexExecutor extends BaseExecutor {
+  constructor(providerId = "vertex") {
+    super(providerId, PROVIDERS[providerId] || {});
+  }
+
+  buildUrl(model, stream, urlIndex = 0, credentials = null) {
+    const saJson = parseVertexSaJson(credentials?.apiKey);
+    const rawKey = !saJson ? credentials?.apiKey : null;
+    const projectId = saJson?.project_id || credentials?.providerSpecificData?.projectId;
+
+    if (this.provider === "vertex-partner") {
+      // Partner models require project_id in path regardless of auth method
+      if (!projectId) throw new Error("Vertex partner models require a project_id. Add it in providerSpecificData or use Service Account JSON.");
+      const url = `https://aiplatform.googleapis.com/v1/projects/${projectId}/locations/global/endpoints/openapi/chat/completions`;
+      return rawKey ? `${url}?key=${rawKey}` : url;
+    }
+
+    // Gemini on Vertex
+    const action = stream ? "streamGenerateContent" : "generateContent";
+
+    if (saJson) {
+      // SA JSON + Bearer token: must use project-scoped path to avoid RESOURCE_PROJECT_INVALID
+      const location = credentials?.providerSpecificData?.location || "us-central1";
+      let url = `https://aiplatform.googleapis.com/v1/projects/${projectId}/locations/${location}/publishers/google/models/${model}:${action}`;
+      if (stream) url += "?alt=sse";
+      return url;
+    }
+
+    // Raw API key: use global publishers endpoint with ?key= param
+    // ?alt=sse is required for proper SSE streaming (matches every other Gemini executor)
+    let url = `https://aiplatform.googleapis.com/v1/publishers/google/models/${model}:${action}`;
+    if (stream) url += "?alt=sse";
+    if (rawKey) url += stream ? `&key=${rawKey}` : `?key=${rawKey}`;
+    return url;
+  }
+
+  buildHeaders(credentials, stream = true) {
+    const headers = { "Content-Type": "application/json" };
+
+    // Only set Bearer token if using SA JSON flow (raw key goes in URL ?key=)
+    if (credentials.accessToken) {
+      headers["Authorization"] = `Bearer ${credentials.accessToken}`;
+    }
+
+    if (stream) headers["Accept"] = "text/event-stream";
+
+    return headers;
+  }
+
+  async refreshCredentials(credentials, log) {
+    const saJson = parseVertexSaJson(credentials?.apiKey);
+    if (!saJson) return null;
+
+    const result = await refreshVertexToken(saJson, log);
+    if (!result) return null;
+
+    return { accessToken: result.accessToken, expiresAt: result.expiresAt };
+  }
+
+  async execute({ model, body, stream, credentials, signal, log, proxyOptions = null }) {
+    const saJson = parseVertexSaJson(credentials?.apiKey);
+
+    // SA JSON flow: mint Bearer token (cached)
+    if (saJson) {
+      const result = await refreshVertexToken(saJson, log);
+      if (!result?.accessToken) throw new Error("Vertex: failed to mint access token from Service Account JSON");
+      credentials.accessToken = result.accessToken;
+    }
+
+    // vertex-partner with raw key: auto-resolve project_id if not provided
+    if (this.provider === "vertex-partner" && !saJson && !credentials?.providerSpecificData?.projectId) {
+      const projectId = await resolveProjectId(credentials.apiKey);
+      if (!projectId) throw new Error("Vertex: could not resolve project_id from API key. Please add it manually in provider settings.");
+      log?.debug?.("VERTEX", `Resolved project_id: ${projectId}`);
+      credentials.providerSpecificData = { ...credentials.providerSpecificData, projectId };
+    }
+
+    const url = this.buildUrl(model, stream, 0, credentials);
+    const headers = this.buildHeaders(credentials, stream);
+    const transformedBody = this.transformRequest(model, body, stream, credentials);
+
+    const response = await proxyAwareFetch(url, {
+      method: "POST",
+      headers,
+      body: JSON.stringify(transformedBody),
+      signal,
+    }, proxyOptions);
+
+    return { response, url, headers, transformedBody };
+  }
+}
+
+export default VertexExecutor;

package/open-sse/executors/xiaomi-tokenplan.js

@@ -0,0 +1,19 @@
+import { DefaultExecutor } from "./default.js";
+import { resolveXiaomiTokenplanBaseUrl } from "../config/providers.js";
+import { getModelTargetFormat } from "../config/providerModels.js";
+import { FORMATS } from "../translator/formats.js";
+
+export class XiaomiTokenplanExecutor extends DefaultExecutor {
+  constructor() {
+    super("xiaomi-tokenplan");
+  }
+
+  // Claude-native aliases route to the Anthropic-compatible messages endpoint
+  buildUrl(model, stream, urlIndex = 0, credentials = null) {
+    const baseUrl = resolveXiaomiTokenplanBaseUrl(credentials);
+    if (getModelTargetFormat(model, model) === FORMATS.CLAUDE) {
+      return `${baseUrl.replace(/\/v1\/?$/, "/anthropic/v1")}/messages`;
+    }
+    return `${baseUrl}/chat/completions`;
+  }
+}

package/open-sse/handlers/chatCore/nonStreamingHandler.js

@@ -0,0 +1,230 @@
+import { FORMATS } from "../../translator/formats.js";
+import { needsTranslation } from "../../translator/index.js";
+import { ollamaBodyToOpenAI } from "../../translator/response/ollama-to-openai.js";
+import { addBufferToUsage, filterUsageForFormat } from "../../utils/usageTracking.js";
+import { createErrorResult } from "../../utils/error.js";
+import { HTTP_STATUS } from "../../config/runtimeConfig.js";
+import { parseSSEToOpenAIResponse } from "./sseToJsonHandler.js";
+import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats } from "./requestDetail.js";
+import { appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
+import { decloakToolNames } from "../../utils/claudeCloaking.js";
+
+/**
+ * Translate non-streaming response body from provider format → OpenAI format.
+ */
+export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat) {
+  if (targetFormat === sourceFormat || targetFormat === FORMATS.OPENAI) return responseBody;
+
+  // Gemini / Antigravity
+  if (targetFormat === FORMATS.GEMINI || targetFormat === FORMATS.ANTIGRAVITY || targetFormat === FORMATS.GEMINI_CLI || targetFormat === FORMATS.VERTEX) {
+    const response = responseBody.response || responseBody;
+    if (!response?.candidates?.[0]) return responseBody;
+
+    const candidate = response.candidates[0];
+    const content = candidate.content;
+    const usage = response.usageMetadata || responseBody.usageMetadata;
+    let textContent = "", reasoningContent = "";
+    const toolCalls = [];
+
+    if (content?.parts) {
+      for (const part of content.parts) {
+        if (part.thought === true && part.text) reasoningContent += part.text;
+        else if (part.text !== undefined) textContent += part.text;
+        if (part.functionCall) {
+          toolCalls.push({
+            id: `call_${part.functionCall.name}_${Date.now()}_${toolCalls.length}`,
+            type: "function",
+            function: { name: part.functionCall.name, arguments: JSON.stringify(part.functionCall.args || {}) }
+          });
+        }
+      }
+    }
+
+    const message = { role: "assistant" };
+    if (textContent) message.content = textContent;
+    if (reasoningContent) message.reasoning_content = reasoningContent;
+    if (toolCalls.length > 0) message.tool_calls = toolCalls;
+    if (!message.content && !message.tool_calls) message.content = "";
+
+    let finishReason = (candidate.finishReason || "stop").toLowerCase();
+    if (finishReason === "stop" && toolCalls.length > 0) finishReason = "tool_calls";
+
+    const result = {
+      id: `chatcmpl-${response.responseId || Date.now()}`,
+      object: "chat.completion",
+      created: Math.floor(new Date(response.createTime || Date.now()).getTime() / 1000),
+      model: response.modelVersion || "gemini",
+      choices: [{ index: 0, message, finish_reason: finishReason }]
+    };
+
+    if (usage) {
+      result.usage = {
+        prompt_tokens: (usage.promptTokenCount || 0) + (usage.thoughtsTokenCount || 0),
+        completion_tokens: usage.candidatesTokenCount || 0,
+        total_tokens: usage.totalTokenCount || 0
+      };
+      if (usage.thoughtsTokenCount > 0) {
+        result.usage.completion_tokens_details = { reasoning_tokens: usage.thoughtsTokenCount };
+      }
+    }
+    return result;
+  }
+
+  // Claude
+  if (targetFormat === FORMATS.CLAUDE) {
+    // Always translate a Claude-format body to OpenAI, even if `content` is
+    // missing/null (e.g. M3 with max_tokens:1 spends the budget on thinking
+    // and returns `content: null`). Returning the raw body would leave the
+    // OpenAI client without a `choices` array and surface as a UI test error.
+    if (responseBody.content && !Array.isArray(responseBody.content)) return responseBody;
+
+    let textContent = "", thinkingContent = "";
+    const toolCalls = [];
+
+    for (const block of (responseBody.content || [])) {
+      if (block.type === "text") {
+        // Strip markdown code block markers (e.g. kimi wraps JSON in ```json...```)
+        const raw = block.text ?? "";
+        const text = raw.replace(/^\s*```\s*json\s*\n?/i, "").replace(/\n?\s*```\s*$/i, "");
+        textContent += text;
+      } else if (block.type === "thinking") thinkingContent += block.thinking || "";
+      else if (block.type === "tool_use") {
+        toolCalls.push({ id: block.id, type: "function", function: { name: block.name, arguments: JSON.stringify(block.input || {}) } });
+      }
+    }
+
+    const message = { role: "assistant" };
+    if (textContent) message.content = textContent;
+    if (thinkingContent) message.reasoning_content = thinkingContent;
+    if (toolCalls.length > 0) message.tool_calls = toolCalls;
+    if (!message.content && !message.tool_calls) message.content = "";
+
+    let finishReason = responseBody.stop_reason || "stop";
+    if (finishReason === "end_turn") finishReason = "stop";
+    if (finishReason === "tool_use") finishReason = "tool_calls";
+
+    const result = {
+      id: `chatcmpl-${responseBody.id || Date.now()}`,
+      object: "chat.completion",
+      created: Math.floor(Date.now() / 1000),
+      model: responseBody.model || "claude",
+      choices: [{ index: 0, message, finish_reason: finishReason }]
+    };
+
+    if (responseBody.usage) {
+      result.usage = {
+        prompt_tokens: responseBody.usage.input_tokens || 0,
+        completion_tokens: responseBody.usage.output_tokens || 0,
+        total_tokens: (responseBody.usage.input_tokens || 0) + (responseBody.usage.output_tokens || 0)
+      };
+    }
+    return result;
+  }
+
+  // Ollama
+  if (targetFormat === FORMATS.OLLAMA) {
+    return ollamaBodyToOpenAI(responseBody);
+  }
+
+  return responseBody;
+}
+
+/**
+ * Handle non-streaming response from provider.
+ */
+export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, trackDone, appendLog }) {
+  trackDone();
+  const contentType = providerResponse.headers.get("content-type") || "";
+  let responseBody;
+
+  if (contentType.includes("text/event-stream")) {
+    const sseText = await providerResponse.text();
+    const parsed = parseSSEToOpenAIResponse(sseText, model);
+    if (!parsed) {
+      appendLog({ status: `FAILED ${HTTP_STATUS.BAD_GATEWAY}` });
+      return createErrorResult(HTTP_STATUS.BAD_GATEWAY, "Invalid SSE response for non-streaming request");
+    }
+    responseBody = parsed;
+  } else {
+    try {
+      responseBody = await providerResponse.json();
+    } catch (err) {
+      appendLog({ status: `FAILED ${HTTP_STATUS.BAD_GATEWAY}` });
+      console.error(`[ChatCore] Failed to parse JSON from ${provider}:`, err.message);
+      return createErrorResult(HTTP_STATUS.BAD_GATEWAY, `Invalid JSON response from ${provider}`);
+    }
+  }
+
+  reqLogger.logProviderResponse(providerResponse.status, providerResponse.statusText, providerResponse.headers, responseBody);
+  if (onRequestSuccess) await onRequestSuccess();
+
+  // Decloak tool_use names once on raw Claude body, before any translation (INPUT side)
+  responseBody = decloakToolNames(responseBody, toolNameMap);
+
+  const usage = extractUsageFromResponse(responseBody);
+  appendLog({ tokens: usage, status: "200 OK" });
+  saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint });
+
+  const translatedResponse = needsTranslation(targetFormat, sourceFormat)
+    ? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat)
+    : responseBody;
+
+  // Fix finish_reason for tool_calls: some providers return non-standard values (e.g. "other")
+  if (translatedResponse?.choices?.[0]) {
+    const choice = translatedResponse.choices[0];
+    const msg = choice.message;
+    const hasToolCalls = Array.isArray(msg?.tool_calls) && msg.tool_calls.length > 0;
+    if (hasToolCalls && choice.finish_reason !== "tool_calls") {
+      choice.finish_reason = "tool_calls";
+    }
+  }
+
+  // Ensure OpenAI-required fields
+  if (!translatedResponse.object) translatedResponse.object = "chat.completion";
+  if (!translatedResponse.created) translatedResponse.created = Math.floor(Date.now() / 1000);
+
+  // Strip Azure-specific fields
+  delete translatedResponse.prompt_filter_results;
+  if (translatedResponse?.choices) {
+    for (const choice of translatedResponse.choices) delete choice.content_filter_results;
+  }
+
+  if (translatedResponse?.usage) {
+    translatedResponse.usage = filterUsageForFormat(addBufferToUsage(translatedResponse.usage), sourceFormat);
+  }
+
+  // Strip reasoning_content — some clients (e.g. Firecrawl AI SDK) have JSON parsers that
+  // break on this non-standard field, even though OpenAI allows it in extensions.
+  if (translatedResponse?.choices) {
+    for (const choice of translatedResponse.choices) {
+      if (choice?.message) delete choice.message.reasoning_content;
+    }
+  }
+
+  reqLogger.logConvertedResponse(translatedResponse);
+
+  const totalLatency = Date.now() - requestStartTime;
+  saveRequestDetail(buildRequestDetail({
+    provider, model, connectionId,
+    latency: { ttft: totalLatency, total: totalLatency },
+    tokens: usage || { prompt_tokens: 0, completion_tokens: 0 },
+    request: extractRequestConfig(body, stream),
+    providerRequest: finalBody || translatedBody || null,
+    providerResponse: responseBody || null,
+    response: {
+      content: translatedResponse?.choices?.[0]?.message?.content || translatedResponse?.content || null,
+      thinking: translatedResponse?.choices?.[0]?.message?.reasoning_content || translatedResponse?.reasoning_content || null,
+      finish_reason: translatedResponse?.choices?.[0]?.finish_reason || "unknown"
+    },
+    status: "success"
+  }, { endpoint: clientRawRequest?.endpoint || null })).catch(err => {
+    console.error("[RequestDetail] Failed to save:", err.message);
+  });
+
+  return {
+    success: true,
+    response: new Response(JSON.stringify(translatedResponse), {
+      headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" }
+    })
+  };
+}

package/open-sse/handlers/chatCore/requestDetail.js

@@ -0,0 +1,102 @@
+import { saveRequestUsage, appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
+import { COLORS } from "../../utils/stream.js";
+
+const OPTIONAL_PARAMS = [
+  "temperature", "top_p", "top_k",
+  "max_tokens", "max_completion_tokens",
+  "thinking", "reasoning", "enable_thinking",
+  "presence_penalty", "frequency_penalty",
+  "seed", "stop", "tools", "tool_choice",
+  "response_format", "prediction", "store", "metadata",
+  "n", "logprobs", "top_logprobs", "logit_bias",
+  "user", "parallel_tool_calls"
+];
+
+export function extractRequestConfig(body, stream) {
+  const config = { messages: body.messages || [], model: body.model, stream };
+  for (const param of OPTIONAL_PARAMS) {
+    if (body[param] !== undefined) config[param] = body[param];
+  }
+  return config;
+}
+
+export function extractUsageFromResponse(responseBody) {
+  if (!responseBody || typeof responseBody !== "object") return null;
+
+  // Claude format
+  if (responseBody.usage?.input_tokens !== undefined) {
+    return {
+      prompt_tokens: responseBody.usage.input_tokens || 0,
+      completion_tokens: responseBody.usage.output_tokens || 0,
+      cache_read_input_tokens: responseBody.usage.cache_read_input_tokens,
+      cache_creation_input_tokens: responseBody.usage.cache_creation_input_tokens
+    };
+  }
+
+  // OpenAI format
+  if (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
+    };
+  }
+
+  // Gemini format
+  if (responseBody.usageMetadata) {
+    return {
+      prompt_tokens: responseBody.usageMetadata.promptTokenCount || 0,
+      completion_tokens: responseBody.usageMetadata.candidatesTokenCount || 0,
+      reasoning_tokens: responseBody.usageMetadata.thoughtsTokenCount
+    };
+  }
+
+  return null;
+}
+
+export function buildRequestDetail(base, overrides = {}) {
+  return {
+    provider: base.provider || "unknown",
+    model: base.model || "unknown",
+    connectionId: base.connectionId || undefined,
+    timestamp: new Date().toISOString(),
+    latency: base.latency || { ttft: 0, total: 0 },
+    tokens: base.tokens || { prompt_tokens: 0, completion_tokens: 0 },
+    request: base.request,
+    providerRequest: base.providerRequest || null,
+    providerResponse: base.providerResponse || null,
+    response: base.response || {},
+    status: base.status || "success",
+    ...overrides
+  };
+}
+
+export function saveUsageStats({ provider, model, tokens, connectionId, apiKey, endpoint, label = "USAGE" }) {
+  if (!tokens || typeof tokens !== "object") return;
+
+  const inTokens = tokens.input_tokens ?? tokens.prompt_tokens ?? 0;
+  const outTokens = tokens.output_tokens ?? tokens.completion_tokens ?? 0;
+
+  if (inTokens === 0 && outTokens === 0) return;
+
+  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}`);
+
+  // Normalize to OpenAI token shape for storage
+  const normalized = {
+    prompt_tokens: tokens.prompt_tokens ?? tokens.input_tokens ?? 0,
+    completion_tokens: tokens.completion_tokens ?? tokens.output_tokens ?? 0
+  };
+
+  saveRequestUsage({
+    provider: provider || "unknown",
+    model: model || "unknown",
+    tokens: normalized,
+    timestamp: new Date().toISOString(),
+    connectionId: connectionId || undefined,
+    apiKey: apiKey || undefined,
+    endpoint: endpoint || null
+  }).catch(() => {});
+}