n9router 0.4.49 → 0.4.51

package/app/open-sse/config/providerModels.js

@@ -4,7 +4,6 @@ import REGISTRY from "../providers/registry/index.js";
 import { PROVIDER_MODELS } from "../providers/index.js";
 import { modelQuotaFamily, modelStrip, modelTargetFormat, normalizeModelId } from "../providers/models/schema.js";
 import { CODEX_REVIEW_SUFFIX } from "../providers/models/helpers.js";
-
 export { PROVIDER_MODELS };
 
 
@@ -70,8 +69,13 @@ export function getModelUpstreamId(aliasOrId, modelId) {
   const baseId = suffix ? modelId.slice(0, sufMatch.index).trim() : modelId;
   const models = PROVIDER_MODELS[aliasOrId];
   const found = findModel(models, baseId, aliasOrId);
-  if (found?.upstreamModelId) return found.upstreamModelId + suffix;
-  if (found?.id) return found.id + suffix;
+  const resolvedId = found?.upstreamModelId || found?.id;
+  if (resolvedId) {
+    const presetMatch = resolvedId.match(/\([^()]+\)\s*$/);
+    const presetSuffix = presetMatch?.[0] || "";
+    const resolvedBase = presetSuffix ? resolvedId.slice(0, presetMatch.index).trim() : resolvedId;
+    return resolvedBase + (suffix || presetSuffix);
+  }
   if (aliasOrId === "cx" && typeof baseId === "string" && baseId.endsWith(CODEX_REVIEW_SUFFIX)) {
     return baseId.slice(0, -CODEX_REVIEW_SUFFIX.length) + suffix;
   }

package/app/open-sse/config/runtimeConfig.js

@@ -65,6 +65,8 @@ export const GEMINI_NATIVE_TTS_FETCH_TIMEOUT_MS = envMs("GEMINI_NATIVE_TTS_FETCH
 export const DEFAULT_MAX_TOKENS = 64000;
 export const DEFAULT_MIN_TOKENS = 32000;
 
+export const TOKEN_SAVER_HEADER = "x-9router-token-saver";
+
 // Retry config for 429 responses (legacy - kept for backward compatibility)
 export const RETRY_CONFIG = {
   maxAttempts: 2,

package/app/open-sse/config/ttsModels.js

@@ -33,6 +33,21 @@ const GEMINI_VOICES = [
   "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat",
 ].map((id) => ({ id, name: id, type: "tts" }));
 
+// Xiaomi MiMo preset voices (from https://mimo.mi.com/docs/zh-CN/quick-start/usage-guide/audio/speech-synthesis-v2.5).
+// Voice id is passed via `audio.voice`; `mimo_default` = default (冰糖 on CN cluster, Mia elsewhere).
+// Voices are language-independent — the spoken language is a separate hint, not bound to the voice.
+const MIMO_VOICES = [
+  { id: "mimo_default", name: "mimo_default" },
+  { id: "冰糖",           name: "冰糖" },
+  { id: "茉莉",           name: "茉莉" },
+  { id: "苏打",           name: "苏打" },
+  { id: "白桦",           name: "白桦" },
+  { id: "Mia",           name: "Mia" },
+  { id: "Chloe",         name: "Chloe" },
+  { id: "Milo",          name: "Milo" },
+  { id: "Dean",          name: "Dean" },
+].map((v) => ({ type: "tts", ...v }));
+
 // ── TTS Config (config-driven, single source of truth) ─────────────────────
 export const TTS_MODELS_CONFIG = {
   openai: {
@@ -107,6 +122,14 @@ export const TTS_MODELS_CONFIG = {
     },
     allVoices: GEMINI_VOICES,
   },
+  "xiaomi-mimo": {
+    models: [
+      { id: "mimo-v2.5-tts", name: "MiMo V2.5 TTS", type: "tts" },
+    ],
+    voices: {
+      "mimo-v2.5-tts": MIMO_VOICES,
+    },
+  },
 };
 
 // ── Helper: get voices for a specific model ────────────────────────────────

package/app/open-sse/executors/antigravity.js

@@ -148,6 +148,10 @@ export class AntigravityExecutor extends BaseExecutor {
   transformRequest(model, body, stream, credentials) {
     const projectId = credentials?.projectId || this.generateProjectId();
 
+    // OpenAI clients may include stream_options even for non-streaming calls.
+    // Google generateContent rejects that combination before processing the request.
+    if (stream !== true) delete body.stream_options;
+
     // ─── Image generation: completely different request structure ───
     if (isImageModel(model)) {
       const imageConfig = parseImageConfig(model);
@@ -276,7 +280,7 @@ export class AntigravityExecutor extends BaseExecutor {
     return {
       ...body,
       project: projectId,
-      model: model,
+      model: body.model || model,
       userAgent: "antigravity",
       requestType: "agent",
       requestId: buildIdeRequestId({ body, request: transformedRequest, credentials, model, requestType: "agent" }),

package/app/open-sse/executors/base.js

@@ -3,6 +3,7 @@ import { shouldRefreshCredentials } from "../services/oauthCredentialManager.js"
 import { proxyAwareFetch } from "../utils/proxyFetch.js";
 import { dbg } from "../utils/debugLog.js";
 import { ANTHROPIC_API_VERSION, OPENAI_COMPAT_BASE, ANTHROPIC_COMPAT_BASE } from "../providers/shared.js";
+import { resolveOpenAICompatibleApiType } from "../services/provider.js";
 
 /**
  * BaseExecutor - Base class for provider executors
@@ -30,7 +31,7 @@ export class BaseExecutor {
     if (this.provider?.startsWith?.("openai-compatible-")) {
       const baseUrl = credentials?.providerSpecificData?.baseUrl || OPENAI_COMPAT_BASE;
       const normalized = baseUrl.replace(/\/$/, "");
-      const path = this.provider.includes("responses") ? "/responses" : "/chat/completions";
+      const path = resolveOpenAICompatibleApiType(this.provider, credentials) === "responses" ? "/responses" : "/chat/completions";
       return `${normalized}${path}`;
     }
     if (this.provider?.startsWith?.("anthropic-compatible-")) {
@@ -127,7 +128,7 @@ export class BaseExecutor {
     for (let urlIndex = 0; urlIndex < fallbackCount; urlIndex++) {
       const url = this.buildUrl(model, stream, urlIndex, credentials);
       const transformedBody = this.transformRequest(model, body, stream, credentials);
-      const headers = this.buildHeaders(credentials, stream);
+      const headers = this.buildHeaders(credentials, stream, url, model);
 
       if (!retryAttemptsByUrl[urlIndex]) retryAttemptsByUrl[urlIndex] = 0;
 

package/app/open-sse/executors/codebuddy-cn.js

@@ -18,6 +18,35 @@ export class CodeBuddyExecutor extends DefaultExecutor {
     const transformed = super.transformRequest(model, body, stream, credentials);
     transformed.stream = true;
 
+    // Tencent's content filter flags CLI agent system prompts ("You are Claude
+    // Code, Anthropic's official CLI...") as prompt injection / sensitive content
+    // and rejects the whole request. Detect agent system prompts (length catch-all
+    // + identity-marker regex) and replace them with a neutral one, while leaving
+    // legitimate user system prompts untouched. content may be a string or typed
+    // blocks ([{type:"text",text}]) depending on the incoming client format, so
+    // flatten before matching and preserve the original shape on replacement.
+    const NEUTRAL_PROMPT = "You are a helpful AI assistant that helps with software engineering tasks.";
+    const AGENT_PATTERN = /you are claude code|claude.?code.+official.+cli|anthropic.+official.+cli|anxthxropic.+official.+cli|you are (?:cursor|windsurf|cline|aider|continue|copilot|cody)|you are an? (?:ai )?(?:coding |code )?agent|cc_entrypoint\s*=\s*(?:cli|vscode|jetbrains|gui)|claude.?code.+issues|give feedback.+claude.?code|you are .{0,30}(?:powerful )?ai agent|orchestration capabilities|OhMyOpenCode|<agent-identity>|<Role>|<Behavior_Instructions>/i;
+    const flatten = (content) =>
+      typeof content === "string"
+        ? content
+        : Array.isArray(content)
+          ? content.map((b) => (b && typeof b.text === "string" ? b.text : "")).join("\n")
+          : "";
+    if (Array.isArray(transformed.messages)) {
+      transformed.messages = transformed.messages.map((message) => {
+        if (!message || message.role !== "system") return message;
+        const text = flatten(message.content);
+        if (!text) return message;
+        if (text.length > 2000 || AGENT_PATTERN.test(text)) {
+          return typeof message.content === "string"
+            ? { ...message, content: NEUTRAL_PROMPT }
+            : { ...message, content: [{ type: "text", text: NEUTRAL_PROMPT }] };
+        }
+        return message;
+      });
+    }
+
     // CodeBuddy only surfaces model reasoning when the request carries the CLI's
     // OpenAI-style params: reasoning_effort + reasoning_summary:"auto". 9router's
     // thinking pipeline sets reasoning_effort only when the client asks, and never

package/app/open-sse/executors/codebuddy-intl.js

@@ -0,0 +1,44 @@
+import { DefaultExecutor } from "./default.js";
+
+/**
+ * CodeBuddyIntlExecutor — talks to https://www.codebuddy.ai/v2/chat/completions
+ *
+ * Same OpenAI-compatible-but-stream-only gateway behavior as codebuddy-cn:
+ * non-stream requests are rejected, and reasoning is surfaced only when the
+ * request carries the IDE's OpenAI-style reasoning params. Force stream and
+ * mirror reasoning_summary exactly like CodeBuddyExecutor.
+ */
+export class CodeBuddyIntlExecutor extends DefaultExecutor {
+  constructor() {
+    super("codebuddy-intl");
+  }
+
+  transformRequest(model, body, stream, credentials) {
+    const transformed = super.transformRequest(model, body, stream, credentials);
+    transformed.stream = true;
+
+    const eff = transformed.reasoning_effort;
+    if (eff === "none" || eff === "off") {
+      delete transformed.reasoning_effort;
+    } else if (eff) {
+      transformed.reasoning_summary = "auto";
+    }
+
+    // CodeBuddy rejects plain OpenAI shape (11101 invalid request): needs a
+    // leading system prompt + user content as typed blocks, not a bare string.
+    const source = Array.isArray(transformed.messages) ? transformed.messages : [];
+    transformed.messages = [{ role: "system", content: "You are CodeBuddy Code." }];
+    for (const message of source) {
+      if (!message || typeof message !== "object" || ["system", "developer"].includes(message.role)) continue;
+      if (message.role === "user" && typeof message.content === "string") {
+        transformed.messages.push({ ...message, content: [{ type: "text", text: message.content }] });
+      } else {
+        transformed.messages.push({ ...message });
+      }
+    }
+
+    return transformed;
+  }
+}
+
+export default CodeBuddyIntlExecutor;

package/app/open-sse/executors/codex.js

@@ -8,6 +8,7 @@ import {
 import { normalizeResponsesInput } from "../translator/formats/responsesApi.js";
 import { fetchImageAsBase64 } from "../translator/concerns/image.js";
 import { getModelUpstreamId } from "../config/providerModels.js";
+import { getThinkingLevels } from "../providers/thinkingLevels.js";
 import { DEFAULT_RETRY_CONFIG, HTTP_STATUS, resolveRetryEntry } from "../config/runtimeConfig.js";
 import { dbg } from "../utils/debugLog.js";
 import { resolveSessionId } from "../utils/sessionManager.js";
@@ -124,8 +125,12 @@ function resolveCacheSessionId(body, credentials) {
   });
 }
 
-function normalizeReasoningEffort(value) {
-  return value === "max" ? "xhigh" : value;
+function normalizeReasoningEffort(model, value) {
+  const supportedLevels = getThinkingLevels("codex", model);
+  if (supportedLevels?.includes(value)) return value;
+  if (value === "ultra" && supportedLevels?.includes("max")) return "max";
+  if (value === "max" || value === "ultra") return "xhigh";
+  return value;
 }
 
 function findNestedMessage(value, depth = 0) {
@@ -440,10 +445,10 @@ export class CodexExecutor extends BaseExecutor {
 
     // Priority: explicit reasoning.effort > reasoning_effort param > model suffix > default (medium)
     if (!body.reasoning) {
-      const effort = normalizeReasoningEffort(body.reasoning_effort || modelEffort || 'low');
+      const effort = normalizeReasoningEffort(body.model, body.reasoning_effort || modelEffort || 'low');
       body.reasoning = { effort, summary: "auto" };
     } else {
-      body.reasoning.effort = normalizeReasoningEffort(body.reasoning.effort);
+      body.reasoning.effort = normalizeReasoningEffort(body.model, body.reasoning.effort);
       if (!body.reasoning.summary) body.reasoning.summary = "auto";
     }
     delete body.reasoning_effort;