- Cap maximum cooldown for rate limit handling in account unavailability and single-model chat flows

- Dynamic custom model fetching for model selection

open-sse/config/errorConfig.js

@@ -38,6 +38,9 @@ export const BACKOFF_CONFIG = {
 // Default cooldown for transient/unknown errors
 export const TRANSIENT_COOLDOWN_MS = 30 * 1000;
 
+// Hard cap for provider-reported rate limit cooldown (e.g. codex resets_at can be 5-6h)
+export const MAX_RATE_LIMIT_COOLDOWN_MS = 30 * 60 * 1000;
+
 // Cooldown durations (ms)
 const COOLDOWN = {
   long: 2 * 60 * 1000,

open-sse/config/providerModels.js

@@ -219,7 +219,6 @@ export const PROVIDER_MODELS = {
     // Gemini 3.1 series
     { id: "gemini-3.1-pro-preview", name: "Gemini 3.1 Pro Preview" },
     { id: "gemini-3.1-flash-lite-preview", name: "Gemini 3.1 Flash Lite Preview" },
-    { id: "gemini-3.1-flash-image-preview", name: "Gemini 3.1 Flash Image Preview" },
     // Gemini 3 series
     { id: "gemini-3-flash-preview", name: "Gemini 3 Flash Preview" },
     // Gemini 2.5 series
@@ -342,6 +341,7 @@ export const PROVIDER_MODELS = {
     { id: "DeepSeek-V3.2", name: "DeepSeek-V3.2" },
   ],
   deepseek: [
+    { id: "deepseek-v4-flash", name: "DeepSeek V4 Flash" },
     { id: "deepseek-chat", name: "DeepSeek V3.2 Chat" },
     { id: "deepseek-reasoner", name: "DeepSeek V3.2 Reasoner" },
   ],

open-sse/handlers/chatCore.js

@@ -24,7 +24,7 @@ import { detectClientTool, isNativePassthrough } from "../utils/clientDetector.j
  * @param {object} options.credentials - Provider credentials
  * @param {string} options.sourceFormatOverride - Override detected source format (e.g. "openai-responses")
  */
-export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, sourceFormatOverride, providerThinking }) {
+export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, sourceFormatOverride, providerThinking }) {
   const { provider, model } = modelInfo;
   const requestStartTime = Date.now();
 
@@ -82,7 +82,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
     log?.debug?.("PASSTHROUGH", `${clientTool} → ${provider} | native lossless`);
     translatedBody = { ...body, model };
   } else {
-    translatedBody = translateRequest(sourceFormat, targetFormat, model, body, stream, credentials, provider, reqLogger, stripList, connectionId);
+    translatedBody = translateRequest(sourceFormat, targetFormat, model, body, stream, credentials, provider, reqLogger, stripList, connectionId, rtkEnabled);
     if (!translatedBody) {
       trackPendingRequest(model, provider, connectionId, false, true);
       return createErrorResult(HTTP_STATUS.BAD_REQUEST, `Failed to translate request for ${sourceFormat} → ${targetFormat}`);

open-sse/rtk/flag.js

@@ -1,11 +0,0 @@
-// Synchronous RTK toggle cache. Updated by /api/settings PATCH handler
-// and initialized from DB on server boot.
-let enabled = false;
-
-export function setRtkEnabled(value) {
-  enabled = Boolean(value);
-}
-
-export function isRtkEnabled() {
-  return enabled;
-}

open-sse/rtk/index.js

@@ -3,21 +3,38 @@
 import { RAW_CAP, MIN_COMPRESS_SIZE } from "./constants.js";
 import { autoDetectFilter } from "./autodetect.js";
 import { safeApply } from "./applyFilter.js";
-import { isRtkEnabled } from "./flag.js";
-
-export { isRtkEnabled, setRtkEnabled } from "./flag.js";
 
 // Compress tool_result content in-place. Returns stats or null if disabled/failed.
-export function compressMessages(body) {
-  if (!isRtkEnabled()) return null;
-  if (!body || !Array.isArray(body.messages)) return null;
+export function compressMessages(body, enabled) {
+  if (!enabled) return null;
+  if (!body) return null;
+  // Support both OpenAI/Claude "messages" and OpenAI Responses "input"
+  const items = Array.isArray(body.messages) ? body.messages
+    : Array.isArray(body.input) ? body.input
+    : null;
+  if (!items) return null;
 
   const stats = { bytesBefore: 0, bytesAfter: 0, hits: [] };
   try {
-    for (let i = 0; i < body.messages.length; i++) {
-      const msg = body.messages[i];
+    for (let i = 0; i < items.length; i++) {
+      const msg = items[i];
       if (!msg) continue;
 
+      // Shape 4: OpenAI Responses — top-level { type:"function_call_output", output: string | [{type:"input_text", text}] }
+      if (msg.type === "function_call_output") {
+        if (typeof msg.output === "string") {
+          msg.output = compressText(msg.output, stats, "openai-responses-string");
+        } else if (Array.isArray(msg.output)) {
+          for (let k = 0; k < msg.output.length; k++) {
+            const part = msg.output[k];
+            if (part && part.type === "input_text" && typeof part.text === "string") {
+              part.text = compressText(part.text, stats, "openai-responses-array");
+            }
+          }
+        }
+        continue;
+      }
+
       // Shape 1: OpenAI tool message — { role:"tool", content: "string" }
       if (msg.role === "tool" && typeof msg.content === "string") {
         msg.content = compressText(msg.content, stats, "openai-tool");

open-sse/services/combo.js

@@ -39,6 +39,15 @@ export function getRotatedModels(models, comboName, strategy) {
   return rotatedModels;
 }
 
+/**
+ * Reset in-memory rotation state when combo/settings change
+ * @param {string} [comboName] - Combo name to reset; omit to clear all
+ */
+export function resetComboRotation(comboName) {
+  if (comboName) comboRotationState.delete(comboName);
+  else comboRotationState.clear();
+}
+
 /**
  * Get combo models from combos data
  * @param {string} modelStr - Model string to check

open-sse/translator/index.js

@@ -71,12 +71,12 @@ function stripContentTypes(body, stripList = []) {
 }
 
 // Translate request: source -> openai -> target
-export function translateRequest(sourceFormat, targetFormat, model, body, stream = true, credentials = null, provider = null, reqLogger = null, stripList = [], connectionId = null) {
+export function translateRequest(sourceFormat, targetFormat, model, body, stream = true, credentials = null, provider = null, reqLogger = null, stripList = [], connectionId = null, rtkEnabled = false) {
   ensureInitialized();
   let result = body;
 
   // RTK: compress tool_result content before any translation (shape-agnostic)
-  const rtkStats = compressMessages(result);
+  const rtkStats = compressMessages(result, rtkEnabled);
   if (rtkStats) {
     const line = formatRtkLog(rtkStats);
     if (line) console.log(line);