feat(release): v2.0.6 — custom model apiFormat routing fix

fix: wire apiFormat from custom model DB into routing layer (#204)

.github/workflows/docker-publish.yml

@@ -31,14 +31,14 @@ jobs:
         uses: docker/setup-buildx-action@v3
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v4
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Build and push by digest
         id: build
-        uses: docker/build-push-action@v6
+        uses: docker/build-push-action@v7
         with:
           context: .
           target: runner-base
@@ -87,7 +87,7 @@ jobs:
           merge-multiple: true
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v4
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}

.github/workflows/electron-release.yml

@@ -78,7 +78,7 @@ jobs:
           cache: npm
 
       - name: Cache node_modules
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: node_modules
           key: ${{ runner.os }}-node-${{ hashFiles('package-lock.json') }}
@@ -120,7 +120,7 @@ jobs:
           fi
 
       - name: Upload artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: electron-${{ matrix.platform }}
           path: release-assets/
@@ -136,7 +136,7 @@ jobs:
           fetch-depth: 0
 
       - name: Download all artifacts
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v8
         with:
           path: release-assets
           merge-multiple: true
@@ -172,6 +172,5 @@ jobs:
             release-assets/*.blockmap
             release-assets/*.source.tar.gz
             release-assets/*.source.zip
-            release-assets/OmniRoute.exe
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

CHANGELOG.md

@@ -7,6 +7,66 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+## [2.0.6] — 2026-03-07
+
+> ### 🐛 Bug Fix — Custom Model API Format Routing
+
+### 🐛 Bug Fixes
+
+- **#204 — Custom model `apiFormat` not used in routing** — Custom models configured with `apiFormat: "responses"` in the dashboard were still being routed through the Chat Completions translator. The `apiFormat` field was stored in the DB and displayed in the UI, but never consumed by the routing layer. Fix: `getModelInfo()` now returns `apiFormat` from the custom model DB, and both `resolveModelOrError()` functions override `targetFormat` to `openai-responses` when set. PR #233
+
+### ✅ Issues Closed
+
+- **#205** — Combo endpoint support — Already implemented in v2.0.2
+- **#206** — Manual model→endpoint mapping — Already implemented in v2.0.2
+- **#223** — CLI fingerprint parity — Responded with 4-phase roadmap
+
+### 📁 Files Changed
+
+| File                              | Change                                                                 |
+| --------------------------------- | ---------------------------------------------------------------------- |
+| `src/sse/services/model.ts`       | Added `lookupCustomModelApiFormat()`, enriched `getModelInfo()` return |
+| `src/sse/handlers/chat.ts`        | Override `targetFormat` when `apiFormat === "responses"`               |
+| `src/sse/handlers/chatHelpers.ts` | Same override in duplicate `resolveModelOrError()`                     |
+
+---
+
+## [2.0.5] — 2026-03-06
+
+> ### 🐛 Bug Fix, Electron Auto-Update & Dependency Bumps
+
+### 🐛 Bug Fixes
+
+- **#224 — Chat→Responses translation creates invalid reasoning IDs** — Removed synthetic reasoning item generation in `openaiToOpenAIResponsesRequest()`. The translator was creating reasoning items with IDs like `reasoning_15`, but OpenAI's Responses API requires server-generated `rs_*` IDs, causing `400 Invalid Request` errors from Responses-compatible upstreams. Fix: omit reasoning items entirely during translation
+- **CI: duplicate OmniRoute.exe in release workflow** — Removed redundant explicit `release-assets/OmniRoute.exe` entry that caused `softprops/action-gh-release` to fail with 404 on duplicate upload. PR #222 by @benzntech
+
+### ✨ New Features
+
+- **Electron Auto-Update** — Added auto-update functionality to the desktop app using `electron-updater`. Includes IPC handlers for check/download/install, "Check for Updates" in system tray menu, desktop notification when update is ready, and silent startup check (3s delay). PR #221 by @benzntech
+
+### 📦 Dependencies
+
+- Bump `actions/cache` from 4 to 5 (#225)
+- Bump `actions/download-artifact` from 4 to 8 (#226)
+- Bump `docker/login-action` from 3 to 4 (#227)
+- Bump `actions/upload-artifact` from 4 to 7 (#228)
+- Bump `docker/build-push-action` from 6 to 7 (#229)
+- Bump `express-rate-limit` from 8.2.1 to 8.3.0 (#230)
+
+### 📁 Files Changed
+
+| File                                              | Change                                               |
+| ------------------------------------------------- | ---------------------------------------------------- |
+| `open-sse/translator/request/openai-responses.ts` | Remove synthetic reasoning item generation           |
+| `.github/workflows/electron-release.yml`          | Remove duplicate exe entry, bump GH Actions          |
+| `.github/workflows/docker-publish.yml`            | Bump docker/login-action and build-push-action       |
+| `electron/main.js`                                | Auto-updater setup, IPC handlers, tray menu          |
+| `electron/package.json`                           | Added electron-updater dep and GitHub publish config |
+| `electron/preload.js`                             | Exposed update APIs via contextBridge                |
+| `package-lock.json`                               | Updated express-rate-limit                           |
+
+---
+
 ## [2.0.4] — 2026-03-06
 
 > ### 🐛 Bug Fixes — Round-Robin Persistence & Docker Compatibility

electron/main.js

@@ -26,10 +26,12 @@ const {
   nativeImage,
   shell,
   session,
+  Notification,
 } = require("electron");
 const path = require("path");
 const { spawn } = require("child_process");
 const fs = require("fs");
+const { autoUpdater } = require("electron-updater");
 
 // ── Single Instance Lock ───────────────────────────────────
 const gotTheLock = app.requestSingleInstanceLock();
@@ -62,6 +64,11 @@ let serverPort = 20128;
 
 const getServerUrl = () => `http://localhost:${serverPort}`;
 
+// ── Auto-Updater Configuration ──────────────────────────────
+autoUpdater.autoDownload = false;
+autoUpdater.autoInstallOnAppQuit = true;
+autoUpdater.logger = console;
+
 // ── Helper: Send IPC event to renderer (#5) ────────────────
 function sendToRenderer(channel, data) {
   if (mainWindow && !mainWindow.isDestroyed()) {
@@ -103,6 +110,77 @@ async function waitForServerExit(proc, timeoutMs = 5000) {
   ]);
 }
 
+// ── Auto-Updater Event Handlers ─────────────────────────────
+function setupAutoUpdater() {
+  autoUpdater.on("checking-for-update", () => {
+    sendToRenderer("update-status", { status: "checking" });
+    console.log("[Electron] Checking for updates...");
+  });
+
+  autoUpdater.on("update-available", (info) => {
+    sendToRenderer("update-status", { status: "available", version: info.version });
+    console.log("[Electron] Update available:", info.version);
+  });
+
+  autoUpdater.on("update-not-available", (info) => {
+    sendToRenderer("update-status", { status: "not-available", version: info.version });
+    console.log("[Electron] No update available");
+  });
+
+  autoUpdater.on("download-progress", (progress) => {
+    sendToRenderer("update-status", {
+      status: "downloading",
+      percent: Math.round(progress.percent),
+      transferred: progress.transferred,
+      total: progress.total,
+    });
+  });
+
+  autoUpdater.on("update-downloaded", (info) => {
+    sendToRenderer("update-status", { status: "downloaded", version: info.version });
+    console.log("[Electron] Update downloaded:", info.version);
+
+    if (Notification.isSupported()) {
+      const notification = new Notification({
+        title: "OmniRoute Update Ready",
+        body: `Version ${info.version} is ready to install. Click to restart.`,
+      });
+      notification.on("click", () => {
+        autoUpdater.quitAndInstall();
+      });
+      notification.show();
+    }
+  });
+
+  autoUpdater.on("error", (error) => {
+    sendToRenderer("update-status", { status: "error", message: error.message });
+    console.error("[Electron] Update error:", error);
+  });
+}
+
+async function checkForUpdates(silent = false) {
+  if (isDev) {
+    console.log("[Electron] Dev mode — skipping auto-update");
+    if (!silent) {
+      sendToRenderer("update-status", { status: "error", message: "Updates disabled in dev mode" });
+    }
+    return;
+  }
+  await autoUpdater.checkForUpdates();
+}
+
+async function downloadUpdate() {
+  await autoUpdater.downloadUpdate();
+}
+
+function installUpdate() {
+  if (nextServer) {
+    nextServer.kill("SIGTERM");
+    nextServer = null;
+  }
+  autoUpdater.quitAndInstall();
+}
+
 // ── Content Security Policy (#15) ──────────────────────────
 function setupContentSecurityPolicy() {
   session.defaultSession.webRequest.onHeadersReceived((details, callback) => {
@@ -236,6 +314,11 @@ function createTray() {
       ],
     },
     { type: "separator" },
+    {
+      label: "Check for Updates",
+      click: () => checkForUpdates(false),
+    },
+    { type: "separator" },
     {
       label: "Quit",
       click: () => {
@@ -391,6 +474,36 @@ function setupIpcHandlers() {
   });
 
   ipcMain.on("window-close", () => mainWindow?.close());
+
+  // Auto-update IPC handlers
+  ipcMain.handle("check-for-updates", async () => {
+    try {
+      await checkForUpdates(false);
+      return { success: true };
+    } catch (error) {
+      console.error("[Electron] Check for updates failed:", error);
+      sendToRenderer("update-status", { status: "error", message: error.message });
+      return { success: false, error: error.message };
+    }
+  });
+
+  ipcMain.handle("download-update", async () => {
+    try {
+      await downloadUpdate();
+      return { success: true };
+    } catch (error) {
+      console.error("[Electron] Download update failed:", error);
+      sendToRenderer("update-status", { status: "error", message: error.message });
+      return { success: false, error: error.message };
+    }
+  });
+
+  ipcMain.handle("install-update", () => {
+    installUpdate();
+    // No return value — app will quit and restart
+  });
+
+  ipcMain.handle("get-app-version", () => app.getVersion());
 }
 
 // ── App Lifecycle ──────────────────────────────────────────
@@ -407,6 +520,14 @@ app.whenReady().then(async () => {
   createWindow();
   createTray();
   setupIpcHandlers();
+  setupAutoUpdater();
+
+  // Check for updates after a short delay (don't block startup)
+  if (!isDev) {
+    setTimeout(() => {
+      checkForUpdates(true);
+    }, 3000);
+  }
 
   // macOS: recreate window when dock icon clicked
   app.on("activate", () => {

electron/package.json

@@ -15,7 +15,9 @@
     "build:linux": "electron-builder --linux",
     "pack": "electron-builder --dir"
   },
-  "dependencies": {},
+  "dependencies": {
+    "electron-updater": "^6.8.3"
+  },
   "devDependencies": {
     "electron": "^40.6.1",
     "electron-builder": "^25.1.8"
@@ -28,6 +30,11 @@
       "output": "dist-electron",
       "buildResources": "assets"
     },
+    "publish": {
+      "provider": "github",
+      "owner": "diegosouzapw",
+      "repo": "OmniRoute"
+    },
     "files": [
       "main.js",
       "preload.js",

electron/preload.js

@@ -13,9 +13,18 @@ const { contextBridge, ipcRenderer } = require("electron");
 
 // ── Channel Whitelist ──────────────────────────────────────
 const VALID_CHANNELS = {
-  invoke: ["get-app-info", "open-external", "get-data-dir", "restart-server"],
+  invoke: [
+    "get-app-info",
+    "open-external",
+    "get-data-dir",
+    "restart-server",
+    "check-for-updates",
+    "download-update",
+    "install-update",
+    "get-app-version",
+  ],
   send: ["window-minimize", "window-maximize", "window-close"],
-  receive: ["server-status", "port-changed"],
+  receive: ["server-status", "port-changed", "update-status"],
 };
 
 // ── Fix #16: Generic IPC wrappers ──────────────────────────
@@ -48,6 +57,12 @@ contextBridge.exposeInMainWorld("electronAPI", {
   openExternal: (url) => safeInvoke("open-external", url),
   getDataDir: () => safeInvoke("get-data-dir"),
   restartServer: () => safeInvoke("restart-server"),
+  getAppVersion: () => safeInvoke("get-app-version"),
+
+  // ── Auto-Update ──────────────────────────────────────────
+  checkForUpdates: () => safeInvoke("check-for-updates"),
+  downloadUpdate: () => safeInvoke("download-update"),
+  installUpdate: () => safeInvoke("install-update"),
 
   // ── Send (fire-and-forget) ───────────────────────────────
   minimizeWindow: () => safeSend("window-minimize"),
@@ -58,6 +73,7 @@ contextBridge.exposeInMainWorld("electronAPI", {
   // Fix #6: Returns a disposer function for precise cleanup
   onServerStatus: (callback) => safeOn("server-status", callback),
   onPortChanged: (callback) => safeOn("port-changed", callback),
+  onUpdateStatus: (callback) => safeOn("update-status", callback),
 
   // ── Static Properties ────────────────────────────────────
   isElectron: true,

open-sse/translator/request/openai-responses.ts

@@ -275,30 +275,11 @@ export function openaiToOpenAIResponsesRequest(
 
     // Convert assistant messages
     if (role === "assistant") {
-      // Add reasoning content before assistant output
-      if (msg.reasoning_content) {
-        input.push({
-          type: "reasoning",
-          id: `reasoning_${input.length}`,
-          summary: [{ type: "summary_text", text: toString(msg.reasoning_content) }],
-        });
-      }
+      // Skip reasoning_content — OpenAI Responses API requires server-generated
+      // rs_* IDs for reasoning items. Synthesizing client-side IDs (e.g. reasoning_N)
+      // causes 400 errors from Responses-compatible upstreams. (#224)
 
-      // Handle thinking blocks in array content
-      if (Array.isArray(msg.content)) {
-        for (const blockValue of msg.content) {
-          const block = toRecord(blockValue);
-          if (block.type === "thinking" || block.type === "redacted_thinking") {
-            input.push({
-              type: "reasoning",
-              id: `reasoning_${input.length}`,
-              summary: [
-                { type: "summary_text", text: toString(block.thinking || block.data, "...") },
-              ],
-            });
-          }
-        }
-      }
+      // Skip thinking blocks in array content — same rs_* ID constraint applies
 
       // Build assistant output content
       const outputContent: unknown[] = [];

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "omniroute",
-  "version": "2.0.3",
+  "version": "2.0.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omniroute",
-      "version": "2.0.3",
+      "version": "2.0.5",
       "hasInstallScript": true,
       "license": "MIT",
       "workspaces": [
@@ -6596,12 +6596,12 @@
       }
     },
     "node_modules/express-rate-limit": {
-      "version": "8.2.1",
-      "resolved": "https://registry.npmjs.org/express-rate-limit/-/express-rate-limit-8.2.1.tgz",
-      "integrity": "sha512-PCZEIEIxqwhzw4KF0n7QF4QqruVTcF73O5kFKUnGOyjbCCgizBBiFaYpd/fnBLUMPw/BWw9OsiN7GgrNYr7j6g==",
+      "version": "8.3.0",
+      "resolved": "https://registry.npmjs.org/express-rate-limit/-/express-rate-limit-8.3.0.tgz",
+      "integrity": "sha512-KJzBawY6fB9FiZGdE/0aftepZ91YlaGIrV8vgblRM3J8X+dHx/aiowJWwkx6LIGyuqGiANsjSwwrbb8mifOJ4Q==",
       "license": "MIT",
       "dependencies": {
-        "ip-address": "10.0.1"
+        "ip-address": "10.1.0"
       },
       "engines": {
         "node": ">= 16"
@@ -6613,15 +6613,6 @@
         "express": ">= 4.11"
       }
     },
-    "node_modules/express-rate-limit/node_modules/ip-address": {
-      "version": "10.0.1",
-      "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.0.1.tgz",
-      "integrity": "sha512-NWv9YLW4PoW2B7xtzaS3NCot75m6nK7Icdv0o3lfMceJVRfSoQwqD4wEH5rLwoKJwUiZ/rfpiVBhnaF0FK4HoA==",
-      "license": "MIT",
-      "engines": {
-        "node": ">= 12"
-      }
-    },
     "node_modules/fast-copy": {
       "version": "4.0.2",
       "resolved": "https://registry.npmjs.org/fast-copy/-/fast-copy-4.0.2.tgz",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "2.0.4",
+  "version": "2.0.6",
   "description": "Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.",
   "type": "module",
   "bin": {

src/sse/handlers/chat.ts

@@ -369,7 +369,14 @@ async function resolveModelOrError(modelStr: string, body: any) {
   const { provider, model } = modelInfo;
   const sourceFormat = detectFormat(body);
   const providerAlias = PROVIDER_ID_TO_ALIAS[provider] || provider;
-  const targetFormat = getModelTargetFormat(providerAlias, model) || getTargetFormat(provider);
+
+  // If the custom model specifies apiFormat="responses", override targetFormat
+  // to route through the Responses API translator instead of Chat Completions
+  let targetFormat = getModelTargetFormat(providerAlias, model) || getTargetFormat(provider);
+  if ((modelInfo as any).apiFormat === "responses") {
+    targetFormat = "openai-responses";
+    log.info("ROUTING", `Custom model apiFormat=responses → targetFormat=openai-responses`);
+  }
 
   if (modelStr !== `${provider}/${model}`) {
     log.info("ROUTING", `${modelStr} → ${provider}/${model}`);

src/sse/handlers/chatHelpers.ts

@@ -34,7 +34,12 @@ const HTTP_STATUS = {
  * @param {Function} errorResponse - Error response factory
  * @returns {Promise<{ error?: Response, provider: string, model: string, sourceFormat: string, targetFormat: string }>}
  */
-export async function resolveModelOrError(modelStr: string, body: any, log: any, errorResponse: Function) {
+export async function resolveModelOrError(
+  modelStr: string,
+  body: any,
+  log: any,
+  errorResponse: Function
+) {
   const modelInfo = await getModelInfo(modelStr);
 
   if (!modelInfo.provider) {
@@ -44,7 +49,8 @@ export async function resolveModelOrError(modelStr: string, body: any, log: any,
         `Ambiguous model '${modelStr}'. Use provider/model prefix (ex: gh/${modelStr} or cc/${modelStr}).`;
       log.warn("CHAT", message, {
         model: modelStr,
-        candidates: (modelInfo as any).candidateAliases || (modelInfo as any).candidateProviders || [],
+        candidates:
+          (modelInfo as any).candidateAliases || (modelInfo as any).candidateProviders || [],
       });
       return { error: errorResponse(HTTP_STATUS.BAD_REQUEST, message) };
     }
@@ -56,7 +62,14 @@ export async function resolveModelOrError(modelStr: string, body: any, log: any,
   const { provider, model } = modelInfo;
   const sourceFormat = detectFormat(body);
   const providerAlias = PROVIDER_ID_TO_ALIAS[provider] || provider;
-  const targetFormat = getModelTargetFormat(providerAlias, model) || getTargetFormat(provider);
+
+  // If the custom model specifies apiFormat="responses", override targetFormat
+  // to route through the Responses API translator instead of Chat Completions
+  let targetFormat = getModelTargetFormat(providerAlias, model) || getTargetFormat(provider);
+  if ((modelInfo as any).apiFormat === "responses") {
+    targetFormat = "openai-responses";
+    log.info("ROUTING", `Custom model apiFormat=responses → targetFormat=openai-responses`);
+  }
 
   // Log routing
   if (modelStr !== `${provider}/${model}`) {

src/sse/services/model.ts

@@ -1,5 +1,5 @@
 // Re-export from open-sse with localDb integration
-import { getModelAliases, getComboByName, getProviderNodes } from "@/lib/localDb";
+import { getModelAliases, getComboByName, getProviderNodes, getCustomModels } from "@/lib/localDb";
 import {
   parseModel,
   resolveModelAliasFromMap,
@@ -16,13 +16,30 @@ export async function resolveModelAlias(alias) {
   return resolveModelAliasFromMap(alias, aliases);
 }
 
+/**
+ * Look up the apiFormat for a custom model from the DB.
+ * Returns "responses" if the model is configured for the Responses API, otherwise undefined.
+ */
+async function lookupCustomModelApiFormat(
+  providerId: string,
+  modelId: string
+): Promise<string | undefined> {
+  try {
+    const models = await getCustomModels(providerId);
+    if (!Array.isArray(models)) return undefined;
+    const match = models.find((m: any) => m.id === modelId);
+    return match?.apiFormat === "responses" ? "responses" : undefined;
+  } catch {
+    return undefined;
+  }
+}
+
 /**
  * Get full model info (parse or resolve)
  */
 export async function getModelInfo(modelStr) {
   const parsed = parseModel(modelStr);
 
-  // Check custom provider nodes first (for both alias and non-alias formats)
   // Check custom provider nodes first (for both alias and non-alias formats)
   if (parsed.providerAlias || parsed.provider) {
     // Ensure prefixToCheck is always a concise identifier, not a full model string
@@ -32,14 +49,26 @@ export async function getModelInfo(modelStr) {
     const openaiNodes = await getProviderNodes({ type: "openai-compatible" });
     const matchedOpenAI = openaiNodes.find((node) => node.prefix === prefixToCheck);
     if (matchedOpenAI) {
-      return { provider: matchedOpenAI.id, model: parsed.model };
+      const apiFormat = await lookupCustomModelApiFormat(
+        matchedOpenAI.id as string,
+        parsed.model as string
+      );
+      return { provider: matchedOpenAI.id, model: parsed.model, ...(apiFormat && { apiFormat }) };
     }
 
     // Check Anthropic Compatible nodes
     const anthropicNodes = await getProviderNodes({ type: "anthropic-compatible" });
     const matchedAnthropic = anthropicNodes.find((node) => node.prefix === prefixToCheck);
     if (matchedAnthropic) {
-      return { provider: matchedAnthropic.id, model: parsed.model };
+      const apiFormat = await lookupCustomModelApiFormat(
+        matchedAnthropic.id as string,
+        parsed.model as string
+      );
+      return {
+        provider: matchedAnthropic.id,
+        model: parsed.model,
+        ...(apiFormat && { apiFormat }),
+      };
     }
   }