zevairouter 1.0.153 → 1.0.155

package/open-sse/executors/qoder.js

@@ -1,468 +0,0 @@
-/**
- * QoderExecutor — sends OpenAI-format chat requests to Qoder's COSY-signed
- * inference endpoint at api3.qoder.sh, then unwraps Qoder's `{statusCodeValue,
- * body}` SSE envelope back into plain OpenAI SSE for the rest of the pipeline.
- *
- * Differences vs the previous placeholder:
- *   - URL is api3.qoder.sh/algo/api/v2/service/pro/sse/agent_chat_generation
- *     with `&Encode=1` so we can ship the body through the WAF-bypass
- *     encoder.
- *   - Authentication is COSY (RSA + AES + MD5 + ~17 Cosy-* headers), not
- *     a static HMAC.
- *   - The request shape Qoder expects is non-trivial (chat_context with
- *     mirrored modelConfig, business block with stable IDs, system text
- *     hoisted out of the messages array). All ported from the reference.
- *   - Model identifier is one of the canonical Qoder keys (auto / ultimate /
- *     performance / efficient / lite + frontier "*model" ids); the
- *     translator layer feeds us "qoder/<key>" so we strip the prefix.
- *   - Per-model `model_config` is fetched live from /algo/api/v2/model/list
- *     and cached. Sending the wrong block silently downgrades to a
- *     different model upstream, so a missing entry is a hard error.
- */
-
-import { qoderEncodeBody } from "@/lib/qoder/encoding.js";
-import { buildCosyHeaders } from "@/lib/qoder/cosy.js";
-import { v4 as uuidv4 } from "uuid";
-import { createHash } from "crypto";
-
-import { BaseExecutor } from "./base.js";
-import { PROVIDERS } from "../config/providers.js";
-import { proxyAwareFetch } from "../utils/proxyFetch.js";
-import {
-  QODER_CHAT_URL_ENCODED,
-  QODER_MODEL_MAP,
-} from "@/lib/qoder/constants.js";
-import { getQoderModelConfig, resolveQoderModels } from "../services/qoderModels.js";
-
-/**
- * Hoist role:"system" messages out of the messages array (Qoder rejects
- * system in messages) and flatten any multipart content arrays.
- */
-function normalizeMessages(messages) {
-  if (!Array.isArray(messages) || messages.length === 0) {
-    return { messages: [], systemText: "" };
-  }
-  const systemParts = [];
-  const out = [];
-  for (const msg of messages) {
-    if (!msg || typeof msg !== "object") continue;
-    const text = extractText(msg.content);
-    if (msg.role === "system") {
-      if (text) systemParts.push(text);
-      continue;
-    }
-    const cloned = { ...msg };
-    cloned.content = text;
-    out.push(cloned);
-  }
-  return { messages: out, systemText: systemParts.join("\n\n") };
-}
-
-function extractText(content) {
-  if (typeof content === "string") return content;
-  if (content == null) return "";
-  if (Array.isArray(content)) {
-    const parts = [];
-    for (const item of content) {
-      if (item && typeof item === "object") {
-        if (item.type === "text" && typeof item.text === "string") {
-          parts.push(item.text);
-        } else if (typeof item.text === "string") {
-          parts.push(item.text);
-        }
-      }
-    }
-    return parts.join("\n");
-  }
-  return String(content);
-}
-
-function lastUserText(messages) {
-  for (let i = messages.length - 1; i >= 0; i--) {
-    const m = messages[i];
-    if (m?.role === "user" && typeof m.content === "string") {
-      return m.content;
-    }
-  }
-  return "";
-}
-
-function stableHash(prefix, ...parts) {
-  const h = createHash("sha256");
-  h.update(prefix);
-  for (const p of parts) {
-    h.update("\0");
-    h.update(String(p ?? ""));
-  }
-  return h.digest("hex").slice(0, 16);
-}
-
-function stableChatRecordId(model, messages, tools, maxTokens) {
-  const h = createHash("sha256");
-  h.update("qoder-record\0");
-  h.update(String(model));
-  for (const m of messages) {
-    if (!m || typeof m !== "object") continue;
-    if (m.role) { h.update("\0"); h.update(m.role); }
-    if (typeof m.content === "string" && m.content) {
-      h.update("\0"); h.update(m.content);
-    }
-  }
-  if (tools) {
-    h.update("\0");
-    try { h.update(JSON.stringify(tools)); } catch {}
-  }
-  h.update(`\0mt=${maxTokens}`);
-  return h.digest("hex").slice(0, 16);
-}
-
-function truncate(s, n) {
-  return s && s.length > n ? `${s.slice(0, n)}...` : s || "";
-}
-
-/**
- * Map the OpenAI-style request body into the exact shape Qoder expects.
- */
-async function buildQoderRequestBody({ model, body, credentials, log, proxyOptions, signal }) {
-  const qoderKey = String(model || "").replace(/^qoder\//, "");
-  
-  // Fetch model config from dynamic API instead of relying on static QODER_MODEL_MAP.
-  // This allows support for new Qoder models (e.g., qmodel_latest) without code changes.
-  let modelConfig = await getQoderModelConfig(credentials, qoderKey, { log, proxyOptions, signal });
-  if (!modelConfig) {
-    // Try a forced refresh once before giving up — the cache may simply
-    // not be populated yet on first ever call for this credential.
-    const refreshed = await resolveQoderModels(credentials, { forceRefresh: true, log, proxyOptions, signal });
-    const retried = refreshed?.rawConfigs.get(qoderKey);
-    if (!retried) {
-      throw new Error(
-        `qoder: model_config for "${qoderKey}" not yet known (run a model list fetch or check upstream connectivity)`,
-      );
-    }
-    modelConfig = { ...retried, key: qoderKey };
-  }
-
-  // Reject disabled models up-front. Earlier versions sent the request anyway
-  // and let upstream return 403 + a pricing URL, which surfaced as a generic
-  // "qoder error 403" with no actionable hint. We now refuse pre-flight so
-  // the caller knows exactly which model their plan can't use. Free-plan
-  // accounts typically only get qmodel_latest (Qwen3.7-Max) enabled; every
-  // other key reports enable:false and would 403 server-side.
-  if (modelConfig.enable === false) {
-    const planTier = credentials?.providerSpecificData?.planTier || "unknown";
-    const err = new Error(
-      `qoder: model "${qoderKey}" is not enabled for this account (plan: ${planTier}). ` +
-      `Try qmodel_latest, or upgrade at https://qoder.com/pricing.`,
-    );
-    err.status = 403;
-    err.code = "model_not_enabled";
-    throw err;
-  }
-
-  const { messages, systemText } = normalizeMessages(body.messages || []);
-  const tools = body.tools;
-  const isReasoning = !!modelConfig.is_reasoning;
-  const maxOutputTokens = Number(modelConfig.max_output_tokens) || 0;
-
-  let maxTokens = 32_768;
-  if (maxOutputTokens > 0) maxTokens = maxOutputTokens;
-  if (typeof body.max_tokens === "number" && body.max_tokens > 0 && body.max_tokens < maxTokens) {
-    maxTokens = body.max_tokens;
-  }
-  if (typeof body.max_completion_tokens === "number" && body.max_completion_tokens > 0 && body.max_completion_tokens < maxTokens) {
-    maxTokens = body.max_completion_tokens;
-  }
-
-  const lastUser = lastUserText(messages);
-  const psd = credentials.providerSpecificData || {};
-  const sessionId = stableHash("qoder-session", psd.userId, qoderKey);
-  const recordId = stableChatRecordId(qoderKey, messages, tools, maxTokens);
-
-  return {
-    qoderKey,
-    payload: {
-      request_id: uuidv4(),
-      request_set_id: recordId,
-      chat_record_id: recordId,
-      session_id: sessionId,
-      stream: true,
-      chat_task: "FREE_INPUT",
-      is_reply: true,
-      is_retry: false,
-      source: 1,
-      version: "3",
-      session_type: "qodercli",
-      agent_id: "agent_common",
-      task_id: "common",
-      code_language: "",
-      chat_prompt: "",
-      image_urls: null,
-      aliyun_user_type: "",
-      system: systemText,
-      messages,
-      tools: Array.isArray(tools) ? tools : [],
-      parameters: { max_tokens: maxTokens },
-      chat_context: {
-        chatPrompt: "",
-        imageUrls: null,
-        extra: {
-          context: [],
-          modelConfig: { key: qoderKey, is_reasoning: isReasoning },
-          originalContent: lastUser,
-        },
-        features: [],
-        text: lastUser,
-      },
-      model_config: modelConfig,
-      business: {
-        product: "cli",
-        version: "1.0.0",
-        type: "agent",
-        stage: "start",
-        id: uuidv4(),
-        name: truncate(lastUser, 30),
-        begin_at: Date.now(),
-      },
-    },
-    modelConfig,
-  };
-}
-
-/**
- * Wrap the upstream's `{statusCodeValue, body}` SSE envelope into plain
- * OpenAI SSE chunks the rest of the chatCore pipeline understands.
- *
- * Each upstream line looks like:
- *   data: {"statusCodeValue":200,"body":"{\"choices\":[{\"delta\":{...}}]}"}
- * The inner body is an OpenAI streaming chunk (or "[DONE]"). We unwrap it
- * and re-emit as `data: <inner>\n\n`. Errors become `data: [DONE]\n\n` plus
- * a synthetic OpenAI error chunk.
- */
-function wrapQoderSSE(response, model) {
-  if (!response.ok || !response.body) return response;
-
-  const decoder = new TextDecoder();
-  const encoder = new TextEncoder();
-  let buffer = "";
-  let doneEmitted = false;
-
-  // Process one already-extracted SSE line (no trailing newline). Returns
-  // false when the line indicated end-of-stream so the caller can stop
-  // forwarding any remaining chunks after [DONE].
-  const processLine = (line, controller) => {
-    const trimmed = line.replace(/\r$/, "").trim();
-    if (!trimmed) return;
-    if (!trimmed.startsWith("data:")) return;
-    if (doneEmitted) return; // never forward chunks past stream end
-
-    const data = trimmed.slice(5).trimStart();
-    if (data === "[DONE]") {
-      controller.enqueue(encoder.encode("data: [DONE]\n\n"));
-      doneEmitted = true;
-      return;
-    }
-
-    let envelope;
-    try { envelope = JSON.parse(data); } catch { return; }
-    const statusVal = typeof envelope.statusCodeValue === "number" ? envelope.statusCodeValue : 200;
-    const inner = typeof envelope.body === "string" ? envelope.body : "";
-    if (statusVal !== 200) {
-      const msg = inner || `upstream status ${statusVal}`;
-      const errChunk = JSON.stringify({
-        id: `qoder-error-${Date.now()}`,
-        object: "chat.completion.chunk",
-        created: Math.floor(Date.now() / 1000),
-        model,
-        choices: [{ index: 0, delta: { content: `\n[qoder error ${statusVal}: ${truncate(msg, 200)}]` }, finish_reason: "stop" }],
-      });
-      controller.enqueue(encoder.encode(`data: ${errChunk}\n\n`));
-      controller.enqueue(encoder.encode("data: [DONE]\n\n"));
-      doneEmitted = true;
-      return;
-    }
-    if (!inner) return;
-    if (inner === "[DONE]") {
-      controller.enqueue(encoder.encode("data: [DONE]\n\n"));
-      doneEmitted = true;
-      return;
-    }
-    // Inner is an OpenAI-shaped chunk. Strip any embedded newlines so the
-    // SSE frame stays a single event (a literal "\n" inside `inner` would
-    // otherwise split the frame across multiple data: lines and downstream
-    // parsers would reassemble them as separate events).
-    const sanitized = inner.replace(/\r?\n/g, "");
-    controller.enqueue(encoder.encode(`data: ${sanitized}\n\n`));
-  };
-
-  const transform = new TransformStream({
-    transform(chunk, controller) {
-      buffer += decoder.decode(chunk, { stream: true });
-      let nl;
-      while ((nl = buffer.indexOf("\n")) !== -1) {
-        const line = buffer.slice(0, nl);
-        buffer = buffer.slice(nl + 1);
-        processLine(line, controller);
-      }
-    },
-    flush(controller) {
-      // Finalize the decoder so any pending multi-byte sequence is
-      // released into `buffer` instead of being silently dropped.
-      buffer += decoder.decode();
-      // Drain any trailing line that arrived without a terminating newline
-      // (e.g. upstream closed the socket immediately after the last write,
-      // or a CDN stripped the final CRLF). Without this, the chunk that
-      // carries finish_reason is silently lost.
-      if (buffer.length > 0) {
-        processLine(buffer, controller);
-        buffer = "";
-      }
-      if (!doneEmitted) {
-        controller.enqueue(encoder.encode("data: [DONE]\n\n"));
-        doneEmitted = true;
-      }
-    },
-  });
-
-  const transformed = response.body.pipeThrough(transform);
-  // Build a Response with passable headers; the streaming handler reads
-  // `.body` as a ReadableStream regardless of Content-Type.
-  return new Response(transformed, {
-    status: response.status,
-    statusText: response.statusText,
-    headers: {
-      "Content-Type": "text/event-stream",
-      "Cache-Control": "no-cache",
-    },
-  });
-}
-
-export class QoderExecutor extends BaseExecutor {
-  constructor() {
-    super("qoder", PROVIDERS.qoder);
-  }
-
-  buildUrl() {
-    return QODER_CHAT_URL_ENCODED;
-  }
-
-  // Override execute entirely — Qoder needs:
-  //   - body built from translated chat completion payload
-  //   - body encoded with QoderEncodeBody before signing
-  //   - COSY headers built from the *encoded* body bytes
-  //   - response stream re-wrapped from {statusCodeValue, body} to OpenAI SSE
-  async execute({ model, body, stream, credentials, signal, log, proxyOptions = null }) {
-    const url = this.buildUrl();
-
-    const psd = credentials?.providerSpecificData || {};
-    if (!psd.userId) {
-      // No user id → no way to sign. Surface a 401 so the dashboard nudges
-      // the user back to OAuth.
-      const fakeResp = new Response(
-        JSON.stringify({ error: { message: "qoder credential is missing userId; reconnect the account" } }),
-        { status: 401, headers: { "Content-Type": "application/json" } },
-      );
-      return { response: fakeResp, url, headers: {}, transformedBody: body };
-    }
-    if (!credentials?.accessToken) {
-      // Same shape as the userId guard — clean 401 so chatCore reports
-      // "reconnect" rather than bubbling cosy.js's synchronous throw as 500.
-      const fakeResp = new Response(
-        JSON.stringify({ error: { message: "qoder credential is missing accessToken; reconnect the account" } }),
-        { status: 401, headers: { "Content-Type": "application/json" } },
-      );
-      return { response: fakeResp, url, headers: {}, transformedBody: body };
-    }
-
-    let qoderKey;
-    let payload;
-    try {
-      ({ qoderKey, payload } = await buildQoderRequestBody({ model, body, credentials, log, proxyOptions, signal }));
-    } catch (err) {
-      const status = typeof err?.status === "number" ? err.status : 400;
-      const fakeResp = new Response(
-        JSON.stringify({ error: { message: err.message, code: err?.code } }),
-        { status, headers: { "Content-Type": "application/json" } },
-      );
-      return { response: fakeResp, url, headers: {}, transformedBody: body };
-    }
-
-    const plainBody = Buffer.from(JSON.stringify(payload), "utf8");
-    const encodedBodyStr = qoderEncodeBody(plainBody);
-    const encodedBodyBuf = Buffer.from(encodedBodyStr, "latin1");
-
-    let cosyHeaders;
-    try {
-      cosyHeaders = buildCosyHeaders(
-        encodedBodyBuf,
-        url,
-        {
-          userId: psd.userId,
-          authToken: credentials.accessToken,
-          name: credentials.displayName || "",
-          email: credentials.email || "",
-          machineId: psd.machineId || "",
-        },
-      );
-    } catch (err) {
-      // cosy.js throws synchronously on missing userId/authToken — surface
-      // as 401 so chatCore prompts re-auth instead of returning a 500.
-      const fakeResp = new Response(
-        JSON.stringify({ error: { message: `qoder cosy signing failed: ${err.message}` } }),
-        { status: 401, headers: { "Content-Type": "application/json" } },
-      );
-      return { response: fakeResp, url, headers: {}, transformedBody: body };
-    }
-
-    const modelSource = (payload.model_config && payload.model_config.source) || "system";
-    const headers = {
-      "Content-Type": "application/json",
-      Accept: "text/event-stream",
-      "Cache-Control": "no-cache",
-      "X-Model-Key": qoderKey,
-      "X-Model-Source": modelSource,
-      // gzip triggers signature validation on Qoder's CDN; force identity.
-      "Accept-Encoding": "identity",
-      ...cosyHeaders,
-    };
-
-    let response;
-    try {
-      response = await proxyAwareFetch(
-        url,
-        { method: "POST", headers, body: encodedBodyBuf, signal },
-        proxyOptions,
-      );
-    } catch (err) {
-      throw err;
-    }
-
-    if (!response.ok) {
-      // Pass error response through unchanged so chatCore can capture it.
-      return { response, url, headers, transformedBody: payload };
-    }
-
-    const wrapped = wrapQoderSSE(response, `qoder/${qoderKey}`);
-    return { response: wrapped, url, headers, transformedBody: payload };
-  }
-
-  // Qoder device tokens don't refresh through OAuth — the upstream returns
-  // 403 for our flow. Surfacing failure via 401-on-chat is enough; the
-  // dashboard tells users to re-login when their token expires (~30 days).
-  async refreshCredentials() {
-    return null;
-  }
-
-  needsRefresh() {
-    return false;
-  }
-}
-
-export default QoderExecutor;
-
-// Internals exposed for unit tests. Not part of the public API — callers
-// should import QoderExecutor and use its public methods.
-export const __test__ = {
-  normalizeMessages,
-  wrapQoderSSE,
-  buildQoderRequestBody,
-};

package/open-sse/executors/qwen.js

@@ -1,129 +0,0 @@
-import { DefaultExecutor } from "./default.js";
-import { PROVIDERS } from "../config/providers.js";
-import { OAUTH_ENDPOINTS } from "../config/appConstants.js";
-
-/** portal.qwen.ai — static fingerprint matching stable Qwen Code release */
-const QWEN_USER_AGENT = "QwenCode/0.12.3 (linux; x64)";
-const QWEN_STAINLESS = {
-  os: "Linux",
-  arch: "x64",
-  lang: "js",
-  runtime: "node",
-  runtimeVersion: "v18.19.1",
-  packageVersion: "5.11.0",
-  retryCount: "1"
-};
-const QWEN_DEFAULT_SYSTEM_MESSAGE = {
-  role: "system",
-  content: [{ type: "text", text: "", cache_control: { type: "ephemeral" } }]
-};
-
-function ensureQwenSystemMessage(body) {
-  if (!body || typeof body !== "object") return body;
-  const next = { ...body };
-  if (Array.isArray(next.messages)) {
-    next.messages = [QWEN_DEFAULT_SYSTEM_MESSAGE, ...next.messages];
-  } else {
-    next.messages = [QWEN_DEFAULT_SYSTEM_MESSAGE];
-  }
-  return next;
-}
-
-function isQwenThinkingActive(body) {
-  const thinking = body?.thinking;
-  if (thinking === true || body?.enable_thinking === true) return true;
-  return typeof thinking === "object" && thinking !== null && !Array.isArray(thinking) && thinking.type === "enabled";
-}
-
-// Qwen rejects tool_choice="required" or object forms when thinking is active; neutralize to "auto".
-function sanitizeQwenThinkingToolChoice(body) {
-  if (!isQwenThinkingActive(body)) return body;
-  const tc = body.tool_choice;
-  const incompatible = tc === "required" || (typeof tc === "object" && tc !== null);
-  if (!incompatible) return body;
-  return { ...body, tool_choice: "auto" };
-}
-
-function buildQwenUpstreamHeaders(credentials, stream = true) {
-  const token = credentials?.apiKey || credentials?.accessToken || "";
-  const headers = {
-    "Content-Type": "application/json",
-    Authorization: `Bearer ${token}`,
-    "User-Agent": QWEN_USER_AGENT,
-    "X-DashScope-AuthType": "qwen-oauth",
-    "X-DashScope-CacheControl": "enable",
-    "X-DashScope-UserAgent": QWEN_USER_AGENT,
-    "X-Stainless-Arch": QWEN_STAINLESS.arch,
-    "X-Stainless-Lang": QWEN_STAINLESS.lang,
-    "X-Stainless-Os": QWEN_STAINLESS.os,
-    "X-Stainless-Package-Version": QWEN_STAINLESS.packageVersion,
-    "X-Stainless-Retry-Count": QWEN_STAINLESS.retryCount,
-    "X-Stainless-Runtime": QWEN_STAINLESS.runtime,
-    "X-Stainless-Runtime-Version": QWEN_STAINLESS.runtimeVersion,
-    Connection: "keep-alive",
-    "Accept-Language": "*",
-    "Sec-Fetch-Mode": "cors"
-  };
-  headers.Accept = stream ? "text/event-stream" : "application/json";
-  return headers;
-}
-
-export class QwenExecutor extends DefaultExecutor {
-  constructor() {
-    super("qwen");
-  }
-
-  // Qwen tokens are bound to a resource_url returned at OAuth time.
-  // Using portal.qwen.ai when the token is issued for another shard returns 401/403.
-  buildUrl(model, stream, urlIndex = 0, credentials = null) {
-    const resourceUrl = credentials?.providerSpecificData?.resourceUrl;
-    const host = resourceUrl ? resourceUrl.replace(/^https?:\/\//, "").replace(/\/$/, "") : "portal.qwen.ai";
-    return `https://${host}/v1/chat/completions`;
-  }
-
-  buildHeaders(credentials, stream = true) {
-    return buildQwenUpstreamHeaders(credentials, stream);
-  }
-
-  transformRequest(model, body, stream, credentials) {
-    let next = body && typeof body === "object" ? { ...body } : body;
-    if (stream && next?.messages && !next.stream_options && !next.thinking && !next.enable_thinking && next.stream !== false) {
-      next.stream_options = { include_usage: true };
-    }
-    next = sanitizeQwenThinkingToolChoice(next);
-    return ensureQwenSystemMessage(next);
-  }
-
-  // Override to capture resource_url from refresh response (required for buildUrl).
-  async refreshCredentials(credentials, log) {
-    if (!credentials?.refreshToken) return null;
-    try {
-      const response = await fetch(OAUTH_ENDPOINTS.qwen.token, {
-        method: "POST",
-        headers: { "Content-Type": "application/x-www-form-urlencoded", Accept: "application/json" },
-        body: new URLSearchParams({
-          grant_type: "refresh_token",
-          refresh_token: credentials.refreshToken,
-          client_id: PROVIDERS.qwen.clientId
-        })
-      });
-      if (!response.ok) return null;
-      const tokens = await response.json();
-      log?.info?.("TOKEN", "qwen refreshed");
-      return {
-        accessToken: tokens.access_token,
-        refreshToken: tokens.refresh_token || credentials.refreshToken,
-        expiresIn: tokens.expires_in,
-        providerSpecificData: {
-          ...(credentials.providerSpecificData || {}),
-          ...(tokens.resource_url ? { resourceUrl: tokens.resource_url } : {})
-        }
-      };
-    } catch (error) {
-      log?.error?.("TOKEN", `qwen refresh error: ${error.message}`);
-      return null;
-    }
-  }
-}
-
-export default QwenExecutor;