Merge branch 'main' into enable-v1-for-oss

README.md

@@ -8,7 +8,7 @@
 
 <div align="center">
   <a href="https://github.com/OpenHands/OpenHands/blob/main/LICENSE"><img src="https://img.shields.io/badge/LICENSE-MIT-20B2AA?style=for-the-badge" alt="MIT License"></a>
-  <a href="https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=811504672#gid=811504672"><img src="https://img.shields.io/badge/SWEBench-72.8-00cc00?logoColor=FFE165&style=for-the-badge" alt="Benchmark Score"></a>
+  <a href="https://docs.google.com/spreadsheets/d/1wOUdFCMyY6Nt0AIqF705KN4JKOWgeI4wUGUP60krXXs/edit?gid=811504672#gid=811504672"><img src="https://img.shields.io/badge/SWEBench-77.6-00cc00?logoColor=FFE165&style=for-the-badge" alt="Benchmark Score"></a>
   <br/>
   <a href="https://docs.openhands.dev/sdk"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation"></a>
   <a href="https://arxiv.org/abs/2511.03690"><img src="https://img.shields.io/badge/Paper-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Tech Report"></a>

evaluation/README.md

@@ -1,5 +1,10 @@
 # Evaluation
 
+> [!WARNING]
+> **This directory is deprecated.** Our new benchmarks are located at [OpenHands/benchmarks](https://github.com/OpenHands/benchmarks).
+>
+> If you have already implemented a benchmark in this directory and would like to contribute it, we are happy to have the contribution. However, if you are starting anew, please use the new location.
+
 This folder contains code and resources to run experiments and evaluations.
 
 ## For Benchmark Users

frontend/__tests__/components/features/settings/mcp-settings/mcp-server-form.validation.test.tsx

@@ -1,6 +1,6 @@
 import { render, screen, fireEvent } from "@testing-library/react";
 import { describe, it, expect, vi } from "vitest";
-import { MCPServerForm } from "../mcp-server-form";
+import { MCPServerForm } from "#/components/features/settings/mcp-settings/mcp-server-form";
 
 // i18n mock
 vi.mock("react-i18next", () => ({

frontend/__tests__/components/features/settings/mcp-settings/mcp-server-list.test.tsx

@@ -1,6 +1,6 @@
 import { render, screen } from "@testing-library/react";
 import { describe, it, expect, vi } from "vitest";
-import { MCPServerList } from "../mcp-server-list";
+import { MCPServerList } from "#/components/features/settings/mcp-settings/mcp-server-list";
 
 // Mock react-i18next
 vi.mock("react-i18next", () => ({

frontend/__tests__/components/v1/chat/event-content-helpers/get-observation-content.test.ts

@@ -1,5 +1,5 @@
 import { describe, it, expect } from "vitest";
-import { getObservationContent } from "../get-observation-content";
+import { getObservationContent } from "#/components/v1/chat/event-content-helpers/get-observation-content";
 import { ObservationEvent } from "#/types/v1/core";
 import { BrowserObservation } from "#/types/v1/core/base/observation";
 

frontend/__tests__/services/actions.test.ts

@@ -1,5 +1,5 @@
 import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
-import { handleStatusMessage } from "../actions";
+import { handleStatusMessage } from "#/services/actions";
 import { StatusMessage } from "#/types/message";
 import { queryClient } from "#/query-client-config";
 import { useStatusStore } from "#/state/status-store";

frontend/__tests__/utils/custom-toast-handlers.test.ts

@@ -3,7 +3,7 @@ import toast from "react-hot-toast";
 import {
   displaySuccessToast,
   displayErrorToast,
-} from "../custom-toast-handlers";
+} from "#/utils/custom-toast-handlers";
 
 // Mock react-hot-toast
 vi.mock("react-hot-toast", () => ({

frontend/__tests__/utils/settings-utils.test.ts

@@ -1,5 +1,5 @@
 import { describe, it, expect } from "vitest";
-import { parseMaxBudgetPerTask, extractSettings } from "../settings-utils";
+import { parseMaxBudgetPerTask, extractSettings } from "#/utils/settings-utils";
 
 describe("parseMaxBudgetPerTask", () => {
   it("should return null for empty string", () => {

frontend/__tests__/utils/toast-duration.test.ts

@@ -1,5 +1,5 @@
 import { describe, it, expect } from "vitest";
-import { calculateToastDuration } from "../toast-duration";
+import { calculateToastDuration } from "#/utils/toast-duration";
 
 describe("calculateToastDuration", () => {
   it("should return minimum duration for short messages", () => {

frontend/__tests__/utils/vscode-url-helper.test.ts

@@ -1,5 +1,5 @@
 import { describe, it, expect, beforeEach, afterEach } from "vitest";
-import { transformVSCodeUrl } from "../vscode-url-helper";
+import { transformVSCodeUrl } from "#/utils/vscode-url-helper";
 
 describe("transformVSCodeUrl", () => {
   const originalWindowLocation = window.location;