Merge branch 'main' into fix-timeout-message-tests

Revert implementation changes - keep main branch implementation
Remove prompt changes - keep only timeout message fixes
2026-04-29 03:00:45 -04:00 · 2025-08-15 15:40:45 -04:00 · 2025-08-15 19:39:05 +00:00 · 2025-08-15 19:35:20 +00:00 · 2025-08-15 19:24:03 +00:00 · 2025-08-15 18:42:34 +00:00
49 changed files with 2098 additions and 6212 deletions
--- a/.github/workflows/e2e-tests.yml
+++ b/.github/workflows/e2e-tests.yml
@@ -183,7 +183,7 @@ jobs:

          # Run the tests with detailed output
          cd tests/e2e
-          poetry run python -m pytest test_e2e_workflow.py::test_github_token_configuration test_e2e_workflow.py::test_conversation_start -v --no-header --capture=no --timeout=600
+          poetry run python -m pytest test_settings.py::test_github_token_configuration test_conversation.py::test_conversation_start -v --no-header --capture=no --timeout=600

      - name: Upload test results
        if: always()
--- a/.gitignore
+++ b/.gitignore
@@ -255,10 +255,5 @@ containers/runtime/project.tar.gz
 containers/runtime/code
 **/node_modules/

-# VSCode extension test files
-openhands/integrations/vscode/.vscode-test/
-openhands/integrations/vscode/out/
-openhands/integrations/vscode/node_modules/
-
 # test results
 test-results
--- a/.vscode/settings.json
+++ b/.vscode/settings.json
@@ -3,9 +3,4 @@
    "files.eol": "\n",
    "files.trimTrailingWhitespace": true,
    "files.insertFinalNewline": true,
-    "python.testing.pytestArgs": [
-        "tests"
-    ],
-    "python.testing.unittestEnabled": false,
-    "python.testing.pytestEnabled": true,
 }
--- a/frontend/tests/routes/settings-with-payment.test.tsx
+++ b/frontend/tests/routes/settings-with-payment.test.tsx
@@ -1,6 +1,6 @@
 import { screen, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
-import { afterEach, describe, expect, it, vi } from "vitest";
+import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
 import { createRoutesStub } from "react-router";
 import { renderWithProviders } from "test-utils";
 import OpenHands from "#/api/open-hands";
@@ -36,6 +36,8 @@ vi.mock("react-i18next", async () => {
          "SETTINGS$NAV_API_KEYS": "API Keys",
          "SETTINGS$NAV_LLM": "LLM",
          "SETTINGS$NAV_USER": "User",
+          "SETTINGS$NAV_SECRETS": "Secrets",
+          "SETTINGS$NAV_MCP": "MCP",
          "SETTINGS$TITLE": "Settings"
        };
        return translations[key] || key;
@@ -47,8 +49,33 @@ vi.mock("react-i18next", async () => {
  };
 });

+// Mock useConfig hook
+const { mockUseConfig } = vi.hoisted(() => ({
+  mockUseConfig: vi.fn(),
+}));
+vi.mock("#/hooks/query/use-config", () => ({
+  useConfig: mockUseConfig,
+}));
+
 describe("Settings Billing", () => {
-  const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
+  beforeEach(() => {
+    // Set default config to OSS mode
+    mockUseConfig.mockReturnValue({
+      data: {
+        APP_MODE: "oss",
+        GITHUB_CLIENT_ID: "123",
+        POSTHOG_CLIENT_KEY: "456",
+        FEATURE_FLAGS: {
+          ENABLE_BILLING: false,
+          HIDE_LLM_SETTINGS: false,
+          ENABLE_JIRA: false,
+          ENABLE_JIRA_DC: false,
+          ENABLE_LINEAR: false,
+        },
+      },
+      isLoading: false,
+    });
+  });

  const RoutesStub = createRoutesStub([
    {
@@ -79,19 +106,7 @@ describe("Settings Billing", () => {
  });

  it("should not render the credits tab if OSS mode", async () => {
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "oss",
-      GITHUB_CLIENT_ID: "123",
-      POSTHOG_CLIENT_KEY: "456",
-      FEATURE_FLAGS: {
-        ENABLE_BILLING: false,
-        HIDE_LLM_SETTINGS: false,
-        ENABLE_JIRA: false,
-        ENABLE_JIRA_DC: false,
-        ENABLE_LINEAR: false,
-      },
-    });
-
+    // OSS mode is set by default in beforeEach
    renderSettingsScreen();

    const navbar = await screen.findByTestId("settings-navbar");
@@ -100,17 +115,20 @@ describe("Settings Billing", () => {
  });

  it("should render the credits tab if SaaS mode and billing is enabled", async () => {
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "saas",
-      GITHUB_CLIENT_ID: "123",
-      POSTHOG_CLIENT_KEY: "456",
-      FEATURE_FLAGS: {
-        ENABLE_BILLING: true,
-        HIDE_LLM_SETTINGS: false,
-        ENABLE_JIRA: false,
-        ENABLE_JIRA_DC: false,
-        ENABLE_LINEAR: false,
+    mockUseConfig.mockReturnValue({
+      data: {
+        APP_MODE: "saas",
+        GITHUB_CLIENT_ID: "123",
+        POSTHOG_CLIENT_KEY: "456",
+        FEATURE_FLAGS: {
+          ENABLE_BILLING: true,
+          HIDE_LLM_SETTINGS: false,
+          ENABLE_JIRA: false,
+          ENABLE_JIRA_DC: false,
+          ENABLE_LINEAR: false,
+        },
      },
+      isLoading: false,
    });

    renderSettingsScreen();
@@ -121,17 +139,20 @@ describe("Settings Billing", () => {

  it("should render the billing settings if clicking the credits item", async () => {
    const user = userEvent.setup();
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "saas",
-      GITHUB_CLIENT_ID: "123",
-      POSTHOG_CLIENT_KEY: "456",
-      FEATURE_FLAGS: {
-        ENABLE_BILLING: true,
-        HIDE_LLM_SETTINGS: false,
-        ENABLE_JIRA: false,
-        ENABLE_JIRA_DC: false,
-        ENABLE_LINEAR: false,
+    mockUseConfig.mockReturnValue({
+      data: {
+        APP_MODE: "saas",
+        GITHUB_CLIENT_ID: "123",
+        POSTHOG_CLIENT_KEY: "456",
+        FEATURE_FLAGS: {
+          ENABLE_BILLING: true,
+          HIDE_LLM_SETTINGS: false,
+          ENABLE_JIRA: false,
+          ENABLE_JIRA_DC: false,
+          ENABLE_LINEAR: false,
+        },
      },
+      isLoading: false,
    });

    renderSettingsScreen();
--- a/frontend/tests/routes/settings.test.tsx
+++ b/frontend/tests/routes/settings.test.tsx
@@ -19,6 +19,9 @@ vi.mock("react-i18next", async () => {
          SETTINGS$NAV_CREDITS: "Credits",
          SETTINGS$NAV_API_KEYS: "API Keys",
          SETTINGS$NAV_LLM: "LLM",
+          SETTINGS$NAV_SECRETS: "Secrets",
+          SETTINGS$NAV_MCP: "MCP",
+          SETTINGS$NAV_USER: "User",
          SETTINGS$TITLE: "Settings",
        };
        return translations[key] || key;
@@ -119,22 +122,21 @@ describe("Settings Screen", () => {
  });

  it("should render the saas navbar", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    // @ts-expect-error - only return app mode
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "saas",
-    });
+    const saasConfig = { APP_MODE: "saas" };
+
+    // Clear any existing query data and set the config
+    mockQueryClient.clear();
+    mockQueryClient.setQueryData(["config"], saasConfig);
+
    const sectionsToInclude = [
+      "user",
      "integrations",
      "application",
      "credits", // The nav item shows "credits" text but routes to /billing
      "secrets",
      "api keys",
    ];
-    const sectionsToExclude = ["llm"];
-
-    // Clear any existing query data
-    mockQueryClient.clear();
+    const sectionsToExclude = ["llm", "mcp"];

    renderSettingsScreen();

@@ -151,8 +153,6 @@ describe("Settings Screen", () => {
      });
      expect(sectionElement).not.toBeInTheDocument();
    });
-
-    getConfigSpy.mockRestore();
  });

  it("should not be able to access saas-only routes in oss mode", async () => {
--- a/frontend/package-lock.json
+++ b/frontend/package-lock.json
@@ -18,9 +18,9 @@
        "@reduxjs/toolkit": "^2.8.2",
        "@stripe/react-stripe-js": "^3.9.0",
        "@stripe/stripe-js": "^7.8.0",
-        "@tailwindcss/postcss": "^4.1.11",
-        "@tailwindcss/vite": "^4.1.11",
-        "@tanstack/react-query": "^5.84.2",
+        "@tailwindcss/postcss": "^4.1.12",
+        "@tailwindcss/vite": "^4.1.12",
+        "@tanstack/react-query": "^5.85.3",
        "@uidotdev/usehooks": "^2.4.1",
        "@vitejs/plugin-react": "^5.0.0",
        "@xterm/addon-fit": "^0.10.0",
@@ -30,14 +30,14 @@
        "date-fns": "^4.1.0",
        "eslint-config-airbnb-typescript": "^18.0.0",
        "framer-motion": "^12.23.12",
-        "i18next": "^25.3.2",
+        "i18next": "^25.3.6",
        "i18next-browser-languagedetector": "^8.2.0",
        "i18next-http-backend": "^3.0.2",
        "isbot": "^5.1.29",
        "jose": "^6.0.12",
        "lucide-react": "^0.539.0",
        "monaco-editor": "^0.52.2",
-        "posthog-js": "^1.259.0",
+        "posthog-js": "^1.260.1",
        "react": "^19.1.1",
        "react-dom": "^19.1.1",
        "react-highlight": "^0.15.0",
@@ -60,8 +60,8 @@
        "ws": "^8.18.2"
      },
      "devDependencies": {
-        "@babel/parser": "^7.28.0",
-        "@babel/traverse": "^7.28.0",
+        "@babel/parser": "^7.28.3",
+        "@babel/traverse": "^7.28.3",
        "@babel/types": "^7.28.2",
        "@mswjs/socket.io-binding": "^0.2.0",
        "@playwright/test": "^1.54.2",
@@ -69,7 +69,7 @@
        "@tailwindcss/typography": "^0.5.16",
        "@tanstack/eslint-plugin-query": "^5.83.1",
        "@testing-library/dom": "^10.4.1",
-        "@testing-library/jest-dom": "^6.6.4",
+        "@testing-library/jest-dom": "^6.7.0",
        "@testing-library/react": "^16.3.0",
        "@testing-library/user-event": "^14.6.1",
        "@types/node": "^24.2.0",
@@ -226,13 +226,12 @@
      }
    },
    "node_modules/@babel/generator": {
-      "version": "7.28.0",
-      "resolved": "https://registry.npmjs.org/@babel/generator/-/generator-7.28.0.tgz",
-      "integrity": "sha512-lJjzvrbEeWrhB4P3QBsH7tey117PjLZnDbLiQEKjQ/fNJTjuq4HSqgFA+UNSwZT8D7dxxbnuSBMsa1lrWzKlQg==",
-      "license": "MIT",
+      "version": "7.28.3",
+      "resolved": "https://registry.npmjs.org/@babel/generator/-/generator-7.28.3.tgz",
+      "integrity": "sha512-3lSpxGgvnmZznmBkCRnVREPUFJv2wrv9iAoFDvADJc0ypmdOxdUtcLeBgBJ6zE0PMeTKnxeQzyk0xTBq4Ep7zw==",
      "dependencies": {
-        "@babel/parser": "^7.28.0",
-        "@babel/types": "^7.28.0",
+        "@babel/parser": "^7.28.3",
+        "@babel/types": "^7.28.2",
        "@jridgewell/gen-mapping": "^0.3.12",
        "@jridgewell/trace-mapping": "^0.3.28",
        "jsesc": "^3.0.2"
@@ -459,12 +458,11 @@
      }
    },
    "node_modules/@babel/parser": {
-      "version": "7.28.0",
-      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.28.0.tgz",
-      "integrity": "sha512-jVZGvOxOuNSsuQuLRTh13nU0AogFlw32w/MT+LV6D3sP5WdbW61E77RnkbaO2dUvmPAYrBDJXGn5gGS6tH4j8g==",
-      "license": "MIT",
+      "version": "7.28.3",
+      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.28.3.tgz",
+      "integrity": "sha512-7+Ey1mAgYqFAx2h0RuoxcQT5+MlG3GTV0TQrgr7/ZliKsm/MNDxVVutlWaziMq7wJNAz8MTqz55XLpWvva6StA==",
      "dependencies": {
-        "@babel/types": "^7.28.0"
+        "@babel/types": "^7.28.2"
      },
      "bin": {
        "parser": "bin/babel-parser.js"
@@ -616,17 +614,16 @@
      }
    },
    "node_modules/@babel/traverse": {
-      "version": "7.28.0",
-      "resolved": "https://registry.npmjs.org/@babel/traverse/-/traverse-7.28.0.tgz",
-      "integrity": "sha512-mGe7UK5wWyh0bKRfupsUchrQGqvDbZDbKJw+kcRGSmdHVYrv+ltd0pnpDTVpiTqnaBru9iEvA8pz8W46v0Amwg==",
-      "license": "MIT",
+      "version": "7.28.3",
+      "resolved": "https://registry.npmjs.org/@babel/traverse/-/traverse-7.28.3.tgz",
+      "integrity": "sha512-7w4kZYHneL3A6NP2nxzHvT3HCZ7puDZZjFMqDpBPECub79sTtSO5CGXDkKrTQq8ksAwfD/XI2MRFX23njdDaIQ==",
      "dependencies": {
        "@babel/code-frame": "^7.27.1",
-        "@babel/generator": "^7.28.0",
+        "@babel/generator": "^7.28.3",
        "@babel/helper-globals": "^7.28.0",
-        "@babel/parser": "^7.28.0",
+        "@babel/parser": "^7.28.3",
        "@babel/template": "^7.27.2",
-        "@babel/types": "^7.28.0",
+        "@babel/types": "^7.28.2",
        "debug": "^4.3.1"
      },
      "engines": {
@@ -3405,6 +3402,15 @@
        "@jridgewell/trace-mapping": "^0.3.24"
      }
    },
+    "node_modules/@jridgewell/remapping": {
+      "version": "2.3.5",
+      "resolved": "https://registry.npmjs.org/@jridgewell/remapping/-/remapping-2.3.5.tgz",
+      "integrity": "sha512-LI9u/+laYG4Ds1TDKSJW2YPrIlcVYOwi2fUC6xB43lueCjgxV4lffOCZCtYFiH6TNOX+tQKXx97T4IKHbhyHEQ==",
+      "dependencies": {
+        "@jridgewell/gen-mapping": "^0.3.5",
+        "@jridgewell/trace-mapping": "^0.3.24"
+      }
+    },
    "node_modules/@jridgewell/resolve-uri": {
      "version": "3.1.2",
      "resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.2.tgz",
@@ -5899,26 +5905,24 @@
      }
    },
    "node_modules/@tailwindcss/node": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/node/-/node-4.1.11.tgz",
-      "integrity": "sha512-yzhzuGRmv5QyU9qLNg4GTlYI6STedBWRE7NjxP45CsFYYq9taI0zJXZBMqIC/c8fViNLhmrbpSFS57EoxUmD6Q==",
-      "license": "MIT",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/node/-/node-4.1.12.tgz",
+      "integrity": "sha512-3hm9brwvQkZFe++SBt+oLjo4OLDtkvlE8q2WalaD/7QWaeM7KEJbAiY/LJZUaCs7Xa8aUu4xy3uoyX4q54UVdQ==",
      "dependencies": {
-        "@ampproject/remapping": "^2.3.0",
-        "enhanced-resolve": "^5.18.1",
-        "jiti": "^2.4.2",
+        "@jridgewell/remapping": "^2.3.4",
+        "enhanced-resolve": "^5.18.3",
+        "jiti": "^2.5.1",
        "lightningcss": "1.30.1",
        "magic-string": "^0.30.17",
        "source-map-js": "^1.2.1",
-        "tailwindcss": "4.1.11"
+        "tailwindcss": "4.1.12"
      }
    },
    "node_modules/@tailwindcss/oxide": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide/-/oxide-4.1.11.tgz",
-      "integrity": "sha512-Q69XzrtAhuyfHo+5/HMgr1lAiPP/G40OMFAnws7xcFEYqcypZmdW8eGXaOUIeOl1dzPJBPENXgbjsOyhg2nkrg==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide/-/oxide-4.1.12.tgz",
+      "integrity": "sha512-gM5EoKHW/ukmlEtphNwaGx45fGoEmP10v51t9unv55voWh6WrOL19hfuIdo2FjxIaZzw776/BUQg7Pck++cIVw==",
      "hasInstallScript": true,
-      "license": "MIT",
      "dependencies": {
        "detect-libc": "^2.0.4",
        "tar": "^7.4.3"
@@ -5927,28 +5931,27 @@
        "node": ">= 10"
      },
      "optionalDependencies": {
-        "@tailwindcss/oxide-android-arm64": "4.1.11",
-        "@tailwindcss/oxide-darwin-arm64": "4.1.11",
-        "@tailwindcss/oxide-darwin-x64": "4.1.11",
-        "@tailwindcss/oxide-freebsd-x64": "4.1.11",
-        "@tailwindcss/oxide-linux-arm-gnueabihf": "4.1.11",
-        "@tailwindcss/oxide-linux-arm64-gnu": "4.1.11",
-        "@tailwindcss/oxide-linux-arm64-musl": "4.1.11",
-        "@tailwindcss/oxide-linux-x64-gnu": "4.1.11",
-        "@tailwindcss/oxide-linux-x64-musl": "4.1.11",
-        "@tailwindcss/oxide-wasm32-wasi": "4.1.11",
-        "@tailwindcss/oxide-win32-arm64-msvc": "4.1.11",
-        "@tailwindcss/oxide-win32-x64-msvc": "4.1.11"
+        "@tailwindcss/oxide-android-arm64": "4.1.12",
+        "@tailwindcss/oxide-darwin-arm64": "4.1.12",
+        "@tailwindcss/oxide-darwin-x64": "4.1.12",
+        "@tailwindcss/oxide-freebsd-x64": "4.1.12",
+        "@tailwindcss/oxide-linux-arm-gnueabihf": "4.1.12",
+        "@tailwindcss/oxide-linux-arm64-gnu": "4.1.12",
+        "@tailwindcss/oxide-linux-arm64-musl": "4.1.12",
+        "@tailwindcss/oxide-linux-x64-gnu": "4.1.12",
+        "@tailwindcss/oxide-linux-x64-musl": "4.1.12",
+        "@tailwindcss/oxide-wasm32-wasi": "4.1.12",
+        "@tailwindcss/oxide-win32-arm64-msvc": "4.1.12",
+        "@tailwindcss/oxide-win32-x64-msvc": "4.1.12"
      }
    },
    "node_modules/@tailwindcss/oxide-android-arm64": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-android-arm64/-/oxide-android-arm64-4.1.11.tgz",
-      "integrity": "sha512-3IfFuATVRUMZZprEIx9OGDjG3Ou3jG4xQzNTvjDoKmU9JdmoCohQJ83MYd0GPnQIu89YoJqvMM0G3uqLRFtetg==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-android-arm64/-/oxide-android-arm64-4.1.12.tgz",
+      "integrity": "sha512-oNY5pq+1gc4T6QVTsZKwZaGpBb2N1H1fsc1GD4o7yinFySqIuRZ2E4NvGasWc6PhYJwGK2+5YT1f9Tp80zUQZQ==",
      "cpu": [
        "arm64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "android"
@@ -5958,13 +5961,12 @@
      }
    },
    "node_modules/@tailwindcss/oxide-darwin-arm64": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-darwin-arm64/-/oxide-darwin-arm64-4.1.11.tgz",
-      "integrity": "sha512-ESgStEOEsyg8J5YcMb1xl8WFOXfeBmrhAwGsFxxB2CxY9evy63+AtpbDLAyRkJnxLy2WsD1qF13E97uQyP1lfQ==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-darwin-arm64/-/oxide-darwin-arm64-4.1.12.tgz",
+      "integrity": "sha512-cq1qmq2HEtDV9HvZlTtrj671mCdGB93bVY6J29mwCyaMYCP/JaUBXxrQQQm7Qn33AXXASPUb2HFZlWiiHWFytw==",
      "cpu": [
        "arm64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "darwin"
@@ -5974,13 +5976,12 @@
      }
    },
    "node_modules/@tailwindcss/oxide-darwin-x64": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-darwin-x64/-/oxide-darwin-x64-4.1.11.tgz",
-      "integrity": "sha512-EgnK8kRchgmgzG6jE10UQNaH9Mwi2n+yw1jWmof9Vyg2lpKNX2ioe7CJdf9M5f8V9uaQxInenZkOxnTVL3fhAw==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-darwin-x64/-/oxide-darwin-x64-4.1.12.tgz",
+      "integrity": "sha512-6UCsIeFUcBfpangqlXay9Ffty9XhFH1QuUFn0WV83W8lGdX8cD5/+2ONLluALJD5+yJ7k8mVtwy3zMZmzEfbLg==",
      "cpu": [
        "x64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "darwin"
@@ -5990,13 +5991,12 @@
      }
    },
    "node_modules/@tailwindcss/oxide-freebsd-x64": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-freebsd-x64/-/oxide-freebsd-x64-4.1.11.tgz",
-      "integrity": "sha512-xdqKtbpHs7pQhIKmqVpxStnY1skuNh4CtbcyOHeX1YBE0hArj2romsFGb6yUmzkq/6M24nkxDqU8GYrKrz+UcA==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-freebsd-x64/-/oxide-freebsd-x64-4.1.12.tgz",
+      "integrity": "sha512-JOH/f7j6+nYXIrHobRYCtoArJdMJh5zy5lr0FV0Qu47MID/vqJAY3r/OElPzx1C/wdT1uS7cPq+xdYYelny1ww==",
      "cpu": [
        "x64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "freebsd"
@@ -6006,13 +6006,12 @@
      }
    },
    "node_modules/@tailwindcss/oxide-linux-arm-gnueabihf": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm-gnueabihf/-/oxide-linux-arm-gnueabihf-4.1.11.tgz",
-      "integrity": "sha512-ryHQK2eyDYYMwB5wZL46uoxz2zzDZsFBwfjssgB7pzytAeCCa6glsiJGjhTEddq/4OsIjsLNMAiMlHNYnkEEeg==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm-gnueabihf/-/oxide-linux-arm-gnueabihf-4.1.12.tgz",
+      "integrity": "sha512-v4Ghvi9AU1SYgGr3/j38PD8PEe6bRfTnNSUE3YCMIRrrNigCFtHZ2TCm8142X8fcSqHBZBceDx+JlFJEfNg5zQ==",
      "cpu": [
        "arm"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "linux"
@@ -6022,13 +6021,12 @@
      }
    },
    "node_modules/@tailwindcss/oxide-linux-arm64-gnu": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm64-gnu/-/oxide-linux-arm64-gnu-4.1.11.tgz",
-      "integrity": "sha512-mYwqheq4BXF83j/w75ewkPJmPZIqqP1nhoghS9D57CLjsh3Nfq0m4ftTotRYtGnZd3eCztgbSPJ9QhfC91gDZQ==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm64-gnu/-/oxide-linux-arm64-gnu-4.1.12.tgz",
+      "integrity": "sha512-YP5s1LmetL9UsvVAKusHSyPlzSRqYyRB0f+Kl/xcYQSPLEw/BvGfxzbH+ihUciePDjiXwHh+p+qbSP3SlJw+6g==",
      "cpu": [
        "arm64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "linux"
@@ -6038,13 +6036,12 @@
      }
    },
    "node_modules/@tailwindcss/oxide-linux-arm64-musl": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm64-musl/-/oxide-linux-arm64-musl-4.1.11.tgz",
-      "integrity": "sha512-m/NVRFNGlEHJrNVk3O6I9ggVuNjXHIPoD6bqay/pubtYC9QIdAMpS+cswZQPBLvVvEF6GtSNONbDkZrjWZXYNQ==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-arm64-musl/-/oxide-linux-arm64-musl-4.1.12.tgz",
+      "integrity": "sha512-V8pAM3s8gsrXcCv6kCHSuwyb/gPsd863iT+v1PGXC4fSL/OJqsKhfK//v8P+w9ThKIoqNbEnsZqNy+WDnwQqCA==",
      "cpu": [
        "arm64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "linux"
@@ -6054,13 +6051,12 @@
      }
    },
    "node_modules/@tailwindcss/oxide-linux-x64-gnu": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-x64-gnu/-/oxide-linux-x64-gnu-4.1.11.tgz",
-      "integrity": "sha512-YW6sblI7xukSD2TdbbaeQVDysIm/UPJtObHJHKxDEcW2exAtY47j52f8jZXkqE1krdnkhCMGqP3dbniu1Te2Fg==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-x64-gnu/-/oxide-linux-x64-gnu-4.1.12.tgz",
+      "integrity": "sha512-xYfqYLjvm2UQ3TZggTGrwxjYaLB62b1Wiysw/YE3Yqbh86sOMoTn0feF98PonP7LtjsWOWcXEbGqDL7zv0uW8Q==",
      "cpu": [
        "x64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "linux"
@@ -6070,13 +6066,12 @@
      }
    },
    "node_modules/@tailwindcss/oxide-linux-x64-musl": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-x64-musl/-/oxide-linux-x64-musl-4.1.11.tgz",
-      "integrity": "sha512-e3C/RRhGunWYNC3aSF7exsQkdXzQ/M+aYuZHKnw4U7KQwTJotnWsGOIVih0s2qQzmEzOFIJ3+xt7iq67K/p56Q==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-linux-x64-musl/-/oxide-linux-x64-musl-4.1.12.tgz",
+      "integrity": "sha512-ha0pHPamN+fWZY7GCzz5rKunlv9L5R8kdh+YNvP5awe3LtuXb5nRi/H27GeL2U+TdhDOptU7T6Is7mdwh5Ar3A==",
      "cpu": [
        "x64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "linux"
@@ -6086,9 +6081,9 @@
      }
    },
    "node_modules/@tailwindcss/oxide-wasm32-wasi": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-wasm32-wasi/-/oxide-wasm32-wasi-4.1.11.tgz",
-      "integrity": "sha512-Xo1+/GU0JEN/C/dvcammKHzeM6NqKovG+6921MR6oadee5XPBaKOumrJCXvopJ/Qb5TH7LX/UAywbqrP4lax0g==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-wasm32-wasi/-/oxide-wasm32-wasi-4.1.12.tgz",
+      "integrity": "sha512-4tSyu3dW+ktzdEpuk6g49KdEangu3eCYoqPhWNsZgUhyegEda3M9rG0/j1GV/JjVVsj+lG7jWAyrTlLzd/WEBg==",
      "bundleDependencies": [
        "@napi-rs/wasm-runtime",
        "@emnapi/core",
@@ -6100,14 +6095,13 @@
      "cpu": [
        "wasm32"
      ],
-      "license": "MIT",
      "optional": true,
      "dependencies": {
-        "@emnapi/core": "^1.4.3",
-        "@emnapi/runtime": "^1.4.3",
-        "@emnapi/wasi-threads": "^1.0.2",
-        "@napi-rs/wasm-runtime": "^0.2.11",
-        "@tybys/wasm-util": "^0.9.0",
+        "@emnapi/core": "^1.4.5",
+        "@emnapi/runtime": "^1.4.5",
+        "@emnapi/wasi-threads": "^1.0.4",
+        "@napi-rs/wasm-runtime": "^0.2.12",
+        "@tybys/wasm-util": "^0.10.0",
        "tslib": "^2.8.0"
      },
      "engines": {
@@ -6115,17 +6109,17 @@
      }
    },
    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/core": {
-      "version": "1.4.3",
+      "version": "1.4.5",
      "inBundle": true,
      "license": "MIT",
      "optional": true,
      "dependencies": {
-        "@emnapi/wasi-threads": "1.0.2",
+        "@emnapi/wasi-threads": "1.0.4",
        "tslib": "^2.4.0"
      }
    },
    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/runtime": {
-      "version": "1.4.3",
+      "version": "1.4.5",
      "inBundle": true,
      "license": "MIT",
      "optional": true,
@@ -6134,7 +6128,7 @@
      }
    },
    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/wasi-threads": {
-      "version": "1.0.2",
+      "version": "1.0.4",
      "inBundle": true,
      "license": "MIT",
      "optional": true,
@@ -6143,18 +6137,18 @@
      }
    },
    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@napi-rs/wasm-runtime": {
-      "version": "0.2.11",
+      "version": "0.2.12",
      "inBundle": true,
      "license": "MIT",
      "optional": true,
      "dependencies": {
        "@emnapi/core": "^1.4.3",
        "@emnapi/runtime": "^1.4.3",
-        "@tybys/wasm-util": "^0.9.0"
+        "@tybys/wasm-util": "^0.10.0"
      }
    },
    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@tybys/wasm-util": {
-      "version": "0.9.0",
+      "version": "0.10.0",
      "inBundle": true,
      "license": "MIT",
      "optional": true,
@@ -6169,13 +6163,12 @@
      "optional": true
    },
    "node_modules/@tailwindcss/oxide-win32-arm64-msvc": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-arm64-msvc/-/oxide-win32-arm64-msvc-4.1.11.tgz",
-      "integrity": "sha512-UgKYx5PwEKrac3GPNPf6HVMNhUIGuUh4wlDFR2jYYdkX6pL/rn73zTq/4pzUm8fOjAn5L8zDeHp9iXmUGOXZ+w==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-arm64-msvc/-/oxide-win32-arm64-msvc-4.1.12.tgz",
+      "integrity": "sha512-iGLyD/cVP724+FGtMWslhcFyg4xyYyM+5F4hGvKA7eifPkXHRAUDFaimu53fpNg9X8dfP75pXx/zFt/jlNF+lg==",
      "cpu": [
        "arm64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "win32"
@@ -6185,13 +6178,12 @@
      }
    },
    "node_modules/@tailwindcss/oxide-win32-x64-msvc": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-x64-msvc/-/oxide-win32-x64-msvc-4.1.11.tgz",
-      "integrity": "sha512-YfHoggn1j0LK7wR82TOucWc5LDCguHnoS879idHekmmiR7g9HUtMw9MI0NHatS28u/Xlkfi9w5RJWgz2Dl+5Qg==",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-x64-msvc/-/oxide-win32-x64-msvc-4.1.12.tgz",
+      "integrity": "sha512-NKIh5rzw6CpEodv/++r0hGLlfgT/gFN+5WNdZtvh6wpU2BpGNgdjvj6H2oFc8nCM839QM1YOhjpgbAONUb4IxA==",
      "cpu": [
        "x64"
      ],
-      "license": "MIT",
      "optional": true,
      "os": [
        "win32"
@@ -6201,16 +6193,15 @@
      }
    },
    "node_modules/@tailwindcss/postcss": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/postcss/-/postcss-4.1.11.tgz",
-      "integrity": "sha512-q/EAIIpF6WpLhKEuQSEVMZNMIY8KhWoAemZ9eylNAih9jxMGAYPPWBn3I9QL/2jZ+e7OEz/tZkX5HwbBR4HohA==",
-      "license": "MIT",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/postcss/-/postcss-4.1.12.tgz",
+      "integrity": "sha512-5PpLYhCAwf9SJEeIsSmCDLgyVfdBhdBpzX1OJ87anT9IVR0Z9pjM0FNixCAUAHGnMBGB8K99SwAheXrT0Kh6QQ==",
      "dependencies": {
        "@alloc/quick-lru": "^5.2.0",
-        "@tailwindcss/node": "4.1.11",
-        "@tailwindcss/oxide": "4.1.11",
+        "@tailwindcss/node": "4.1.12",
+        "@tailwindcss/oxide": "4.1.12",
        "postcss": "^8.4.41",
-        "tailwindcss": "4.1.11"
+        "tailwindcss": "4.1.12"
      }
    },
    "node_modules/@tailwindcss/typography": {
@@ -6230,14 +6221,13 @@
      }
    },
    "node_modules/@tailwindcss/vite": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/@tailwindcss/vite/-/vite-4.1.11.tgz",
-      "integrity": "sha512-RHYhrR3hku0MJFRV+fN2gNbDNEh3dwKvY8XJvTxCSXeMOsCRSr+uKvDWQcbizrHgjML6ZmTE5OwMrl5wKcujCw==",
-      "license": "MIT",
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/@tailwindcss/vite/-/vite-4.1.12.tgz",
+      "integrity": "sha512-4pt0AMFDx7gzIrAOIYgYP0KCBuKWqyW8ayrdiLEjoJTT4pKTjrzG/e4uzWtTLDziC+66R9wbUqZBccJalSE5vQ==",
      "dependencies": {
-        "@tailwindcss/node": "4.1.11",
-        "@tailwindcss/oxide": "4.1.11",
-        "tailwindcss": "4.1.11"
+        "@tailwindcss/node": "4.1.12",
+        "@tailwindcss/oxide": "4.1.12",
+        "tailwindcss": "4.1.12"
      },
      "peerDependencies": {
        "vite": "^5.2.0 || ^6 || ^7"
@@ -6261,22 +6251,20 @@
      }
    },
    "node_modules/@tanstack/query-core": {
-      "version": "5.83.1",
-      "resolved": "https://registry.npmjs.org/@tanstack/query-core/-/query-core-5.83.1.tgz",
-      "integrity": "sha512-OG69LQgT7jSp+5pPuCfzltq/+7l2xoweggjme9vlbCPa/d7D7zaqv5vN/S82SzSYZ4EDLTxNO1PWrv49RAS64Q==",
-      "license": "MIT",
+      "version": "5.85.3",
+      "resolved": "https://registry.npmjs.org/@tanstack/query-core/-/query-core-5.85.3.tgz",
+      "integrity": "sha512-9Ne4USX83nHmRuEYs78LW+3lFEEO2hBDHu7mrdIgAFx5Zcrs7ker3n/i8p4kf6OgKExmaDN5oR0efRD7i2J0DQ==",
      "funding": {
        "type": "github",
        "url": "https://github.com/sponsors/tannerlinsley"
      }
    },
    "node_modules/@tanstack/react-query": {
-      "version": "5.85.0",
-      "resolved": "https://registry.npmjs.org/@tanstack/react-query/-/react-query-5.85.0.tgz",
-      "integrity": "sha512-t1HMfToVMGfwEJRya6GG7gbK0luZJd+9IySFNePL1BforU1F3LqQ3tBC2Rpvr88bOrlU6PXyMLgJD0Yzn4ztUw==",
-      "license": "MIT",
+      "version": "5.85.3",
+      "resolved": "https://registry.npmjs.org/@tanstack/react-query/-/react-query-5.85.3.tgz",
+      "integrity": "sha512-AqU8TvNh5GVIE8I+TUU0noryBRy7gOY0XhSayVXmOPll4UkZeLWKDwi0rtWOZbwLRCbyxorfJ5DIjDqE7GXpcQ==",
      "dependencies": {
-        "@tanstack/query-core": "5.83.1"
+        "@tanstack/query-core": "5.85.3"
      },
      "funding": {
        "type": "github",
@@ -6334,17 +6322,15 @@
      }
    },
    "node_modules/@testing-library/jest-dom": {
-      "version": "6.6.4",
-      "resolved": "https://registry.npmjs.org/@testing-library/jest-dom/-/jest-dom-6.6.4.tgz",
-      "integrity": "sha512-xDXgLjVunjHqczScfkCJ9iyjdNOVHvvCdqHSSxwM9L0l/wHkTRum67SDc020uAlCoqktJplgO2AAQeLP1wgqDQ==",
+      "version": "6.7.0",
+      "resolved": "https://registry.npmjs.org/@testing-library/jest-dom/-/jest-dom-6.7.0.tgz",
+      "integrity": "sha512-RI2e97YZ7MRa+vxP4UUnMuMFL2buSsf0ollxUbTgrbPLKhMn8KVTx7raS6DYjC7v1NDVrioOvaShxsguLNISCA==",
      "dev": true,
-      "license": "MIT",
      "dependencies": {
        "@adobe/css-tools": "^4.4.0",
        "aria-query": "^5.0.0",
        "css.escape": "^1.5.1",
        "dom-accessibility-api": "^0.6.3",
-        "lodash": "^4.17.21",
        "picocolors": "^1.1.1",
        "redent": "^3.0.0"
      },
@@ -11134,9 +11120,9 @@
      }
    },
    "node_modules/i18next": {
-      "version": "25.3.4",
-      "resolved": "https://registry.npmjs.org/i18next/-/i18next-25.3.4.tgz",
-      "integrity": "sha512-AHklEYFLiRRxW1Cb6zE9lfnEtYvsydRC8nRS3RSKGX3zCqZ8nLZwMaUsrb80YuccPNv2RNokDL8LkTNnp+6mDw==",
+      "version": "25.3.6",
+      "resolved": "https://registry.npmjs.org/i18next/-/i18next-25.3.6.tgz",
+      "integrity": "sha512-dThZ0CTCM3sUG/qS0ZtQYZQcUI6DtBN8yBHK+SKEqihPcEYmjVWh/YJ4luic73Iq6Uxhp6q7LJJntRK5+1t7jQ==",
      "funding": [
        {
          "type": "individual",
@@ -11151,7 +11137,6 @@
          "url": "https://www.i18next.com/how-to/faq#i18next-is-awesome.-how-can-i-support-the-project"
        }
      ],
-      "license": "MIT",
      "dependencies": {
        "@babel/runtime": "^7.27.6"
      },
@@ -14817,10 +14802,9 @@
      "license": "MIT"
    },
    "node_modules/posthog-js": {
-      "version": "1.259.0",
-      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.259.0.tgz",
-      "integrity": "sha512-6usLnJshky8fQ82ask7PIJh4BSFOU0VkRbFg8Zanm/HIlYMG1VOdRWlToA63JXeO7Bzm9TuREq1wFm5U2VEVCg==",
-      "license": "SEE LICENSE IN LICENSE",
+      "version": "1.260.1",
+      "resolved": "https://registry.npmjs.org/posthog-js/-/posthog-js-1.260.1.tgz",
+      "integrity": "sha512-DD8ZSRpdScacMqtqUIvMFme8lmOWkOvExG8VvjONE7Cm3xpRH5xXpfrwMJE4bayTGWKMx4ij6SfphK6dm/o2ug==",
      "dependencies": {
        "core-js": "^3.38.1",
        "fflate": "^0.4.8",
@@ -17029,10 +17013,9 @@
      }
    },
    "node_modules/tailwindcss": {
-      "version": "4.1.11",
-      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.1.11.tgz",
-      "integrity": "sha512-2E9TBm6MDD/xKYe+dvJZAmg3yxIEDNRc0jwlNyDg/4Fil2QcSLjFKGVff0lAf1jjeaArlG/M75Ey/EYr/OJtBA==",
-      "license": "MIT"
+      "version": "4.1.12",
+      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.1.12.tgz",
+      "integrity": "sha512-DzFtxOi+7NsFf7DBtI3BJsynR+0Yp6etH+nRPTbpWnS2pZBaSksv/JGctNwSWzbFjp0vxSqknaUylseZqMDGrA=="
    },
    "node_modules/tapable": {
      "version": "2.2.2",
--- a/frontend/package.json
+++ b/frontend/package.json
@@ -17,9 +17,9 @@
    "@reduxjs/toolkit": "^2.8.2",
    "@stripe/react-stripe-js": "^3.9.0",
    "@stripe/stripe-js": "^7.8.0",
-    "@tailwindcss/postcss": "^4.1.11",
-    "@tailwindcss/vite": "^4.1.11",
-    "@tanstack/react-query": "^5.84.2",
+    "@tailwindcss/postcss": "^4.1.12",
+    "@tailwindcss/vite": "^4.1.12",
+    "@tanstack/react-query": "^5.85.3",
    "@uidotdev/usehooks": "^2.4.1",
    "@vitejs/plugin-react": "^5.0.0",
    "@xterm/addon-fit": "^0.10.0",
@@ -29,14 +29,14 @@
    "date-fns": "^4.1.0",
    "eslint-config-airbnb-typescript": "^18.0.0",
    "framer-motion": "^12.23.12",
-    "i18next": "^25.3.2",
+    "i18next": "^25.3.6",
    "i18next-browser-languagedetector": "^8.2.0",
    "i18next-http-backend": "^3.0.2",
    "isbot": "^5.1.29",
    "jose": "^6.0.12",
    "lucide-react": "^0.539.0",
    "monaco-editor": "^0.52.2",
-    "posthog-js": "^1.259.0",
+    "posthog-js": "^1.260.1",
    "react": "^19.1.1",
    "react-dom": "^19.1.1",
    "react-highlight": "^0.15.0",
@@ -84,8 +84,8 @@
    ]
  },
  "devDependencies": {
-    "@babel/parser": "^7.28.0",
-    "@babel/traverse": "^7.28.0",
+    "@babel/parser": "^7.28.3",
+    "@babel/traverse": "^7.28.3",
    "@babel/types": "^7.28.2",
    "@mswjs/socket.io-binding": "^0.2.0",
    "@playwright/test": "^1.54.2",
@@ -93,7 +93,7 @@
    "@tailwindcss/typography": "^0.5.16",
    "@tanstack/eslint-plugin-query": "^5.83.1",
    "@testing-library/dom": "^10.4.1",
-    "@testing-library/jest-dom": "^6.6.4",
+    "@testing-library/jest-dom": "^6.7.0",
    "@testing-library/react": "^16.3.0",
    "@testing-library/user-event": "^14.6.1",
    "@types/node": "^24.2.0",
--- a/frontend/src/components/layout/container.tsx
+++ b/frontend/src/components/layout/container.tsx
@@ -1,5 +1,5 @@
 import clsx from "clsx";
-import React, { useEffect, useRef, useState } from "react";
+import React, { useRef, useState } from "react";
 import { NavTab } from "./nav-tab";
 import { ScrollLeftButton } from "./scroll-left-button";
 import { ScrollRightButton } from "./scroll-right-button";
@@ -25,18 +25,12 @@ export function Container({
  children,
  className,
 }: ContainerProps) {
-  const [containerWidth, setContainerWidth] = useState(0);
  const [canScrollLeft, setCanScrollLeft] = useState(false);
  const [canScrollRight, setCanScrollRight] = useState(false);
+  const [showScrollButtons, setShowScrollButtons] = useState(false);
  const containerRef = useRef<HTMLDivElement | null>(null);
  const scrollContainerRef = useRef<HTMLDivElement>(null);

-  // Track container width using ResizeObserver
-  useTrackElementWidth({
-    elementRef: containerRef,
-    callback: setContainerWidth,
-  });
-
  // Check scroll position and update button states
  const updateScrollButtons = () => {
    if (scrollContainerRef.current) {
@@ -47,10 +41,19 @@ export function Container({
    }
  };

-  // Update scroll buttons when tabs change or container width changes
-  useEffect(() => {
-    updateScrollButtons();
-  }, [labels, containerWidth]);
+  // Track container width using ResizeObserver
+  useTrackElementWidth({
+    elementRef: containerRef,
+    callback: (width: number) => {
+      // Only update scroll button visibility when crossing the threshold
+      const shouldShowScrollButtons =
+        width < 598 && Boolean(labels) && labels!.length > 0;
+      if (shouldShowScrollButtons) {
+        setShowScrollButtons(shouldShowScrollButtons);
+      }
+      updateScrollButtons();
+    },
+  });

  // Scroll functions
  const scrollLeft = () => {
@@ -65,8 +68,6 @@ export function Container({
    }
  };

-  const showScrollButtons = containerWidth < 598 && labels && labels.length > 0;
-
  return (
    <div
      ref={containerRef}
--- a/frontend/src/hooks/use-track-element-width.ts
+++ b/frontend/src/hooks/use-track-element-width.ts
@@ -1,18 +1,38 @@
-import { useEffect } from "react";
+import { useEffect, useCallback, useRef } from "react";

 interface UseTrackElementWidthProps {
  elementRef: React.RefObject<HTMLElement | null>;
  callback: (width: number) => void;
+  delay?: number; // Optional delay parameter with default
 }

 export const useTrackElementWidth = ({
  elementRef,
  callback,
+  delay = 100, // Default 100ms delay
 }: UseTrackElementWidthProps) => {
+  const timeoutRef = useRef<NodeJS.Timeout | null>(null);
+
+  // Create debounced callback that only fires after delay
+  const debouncedCallback = useCallback(
+    (width: number) => {
+      // Clear existing timeout
+      if (timeoutRef.current) {
+        clearTimeout(timeoutRef.current);
+      }
+
+      // Set new timeout
+      timeoutRef.current = setTimeout(() => {
+        callback(width);
+      }, delay);
+    },
+    [callback, delay],
+  );
+
  useEffect(() => {
    const resizeObserver = new ResizeObserver((entries) => {
      for (const entry of entries) {
-        callback(entry.contentRect.width);
+        debouncedCallback(entry.contentRect.width);
      }
    });

@@ -21,7 +41,11 @@ export const useTrackElementWidth = ({
    }

    return () => {
+      // Clean up timeout and observer
+      if (timeoutRef.current) {
+        clearTimeout(timeoutRef.current);
+      }
      resizeObserver.disconnect();
    };
-  }, []);
+  }, [debouncedCallback]);
 };
--- a/frontend/src/mocks/handlers.ts
+++ b/frontend/src/mocks/handlers.ts
@@ -25,7 +25,7 @@ export const MOCK_DEFAULT_USER_SETTINGS: ApiSettings | PostApiSettings = {
  security_analyzer: DEFAULT_SETTINGS.SECURITY_ANALYZER,
  remote_runtime_resource_factor:
    DEFAULT_SETTINGS.REMOTE_RUNTIME_RESOURCE_FACTOR,
-  provider_tokens_set: { github: null, gitlab: null, bitbucket: null },
+  provider_tokens_set: {},
  enable_default_condenser: DEFAULT_SETTINGS.ENABLE_DEFAULT_CONDENSER,
  enable_sound_notifications: DEFAULT_SETTINGS.ENABLE_SOUND_NOTIFICATIONS,
  enable_proactive_conversation_starters:
--- a/frontend/src/utils/status.ts
+++ b/frontend/src/utils/status.ts
@@ -122,5 +122,5 @@ export function getStatusCode(
    return runtimeStatus;
  }

-  return "STATUS$ERROR"; // illegal state
+  return I18nKey.CHAT_INTERFACE$AGENT_ERROR_MESSAGE;
 }
--- a/openhands/agenthub/codeact_agent/prompts/system_prompt.j2
+++ b/openhands/agenthub/codeact_agent/prompts/system_prompt.j2
@@ -98,3 +98,11 @@ Your primary role is to assist users by executing commands, modifying code, and
  - Confirm whether they want it as a separate file or just in the conversation
  - Ask if they want documentation files to be included in version control
 </DOCUMENTATION>
+
+<PROCESS_MANAGEMENT>
+* When terminating processes:
+  - Do NOT use general keywords with commands like `pkill -f server` or `pkill -f python` as this might accidentally kill other important servers or processes
+  - Always use specific keywords that uniquely identify the target process
+  - Prefer using `ps aux` to find the exact process ID (PID) first, then kill that specific PID
+  - When possible, use more targeted approaches like finding the PID from a pidfile or using application-specific shutdown commands
+</PROCESS_MANAGEMENT>
--- a/openhands/cli/commands.py
+++ b/openhands/cli/commands.py
@@ -4,7 +4,7 @@ import sys
 from pathlib import Path
 from typing import Any

-import toml
+import tomlkit
 from prompt_toolkit import HTML, print_formatted_text
 from prompt_toolkit.patch_stdout import patch_stdout
 from prompt_toolkit.shortcuts import clear, print_container
@@ -520,7 +520,7 @@ def load_config_file(file_path: Path) -> dict:
    if file_path.exists():
        try:
            with open(file_path, 'r') as f:
-                return toml.load(f)
+                return dict(tomlkit.load(f))
        except Exception:
            pass

@@ -530,9 +530,36 @@ def load_config_file(file_path: Path) -> dict:


 def save_config_file(config_data: dict, file_path: Path) -> None:
-    """Save the config file."""
+    """Save the config file with proper MCP formatting."""
+    doc = tomlkit.document()
+
+    for key, value in config_data.items():
+        if key == 'mcp':
+            # Handle MCP section specially
+            mcp_section = tomlkit.table()
+
+            for mcp_key, mcp_value in value.items():
+                # Create array with inline tables for server configurations
+                server_array = tomlkit.array()
+                for server_config in mcp_value:
+                    if isinstance(server_config, dict):
+                        # Create inline table for each server
+                        inline_table = tomlkit.inline_table()
+                        for server_key, server_val in server_config.items():
+                            inline_table[server_key] = server_val
+                        server_array.append(inline_table)
+                    else:
+                        # Handle non-dict values (like string URLs)
+                        server_array.append(server_config)
+                mcp_section[mcp_key] = server_array
+
+            doc[key] = mcp_section
+        else:
+            # Handle non-MCP sections normally
+            doc[key] = value
+
    with open(file_path, 'w') as f:
-        toml.dump(config_data, f)
+        f.write(tomlkit.dumps(doc))


 def _ensure_mcp_config_structure(config_data: dict) -> None:
--- a/openhands/core/config/llm_config.py
+++ b/openhands/core/config/llm_config.py
@@ -183,3 +183,13 @@ class LLMConfig(BaseModel):
        # Azure issue: https://github.com/All-Hands-AI/OpenHands/issues/7755
        if self.model.startswith('azure') and self.api_version is None:
            self.api_version = '2024-12-01-preview'
+
+        # Set AWS credentials as environment variables for LiteLLM Bedrock
+        if self.aws_access_key_id:
+            os.environ['AWS_ACCESS_KEY_ID'] = self.aws_access_key_id.get_secret_value()
+        if self.aws_secret_access_key:
+            os.environ['AWS_SECRET_ACCESS_KEY'] = (
+                self.aws_secret_access_key.get_secret_value()
+            )
+        if self.aws_region_name:
+            os.environ['AWS_REGION_NAME'] = self.aws_region_name
--- a/openhands/events/action/commands.py
+++ b/openhands/events/action/commands.py
@@ -19,7 +19,9 @@ class CmdRunAction(Action):
    blocking: bool = False  # if True, the command will be run in a blocking manner, but a timeout must be set through _set_hard_timeout
    is_static: bool = False  # if True, runs the command in a separate process
    cwd: str | None = None  # current working directory, only used if is_static is True
-    hidden: bool = False
+    hidden: bool = (
+        False  # if True, this command does not go through the LLM or event stream
+    )
    action: str = ActionType.RUN
    runnable: ClassVar[bool] = True
    confirmation_state: ActionConfirmationStatus = ActionConfirmationStatus.CONFIRMED
--- a/openhands/events/observation/commands.py
+++ b/openhands/events/observation/commands.py
@@ -115,9 +115,12 @@ class CmdOutputObservation(Observation):
        **kwargs: Any,
    ) -> None:
        # Truncate content before passing it to parent
-        truncated_content = self._maybe_truncate(content)
+        # Hidden commands don't go through LLM/event stream, so no need to truncate
+        truncate = not hidden
+        if truncate:
+            content = self._maybe_truncate(content)

-        super().__init__(truncated_content)
+        super().__init__(content)

        self.command = command
        self.observation = observation
--- a/openhands/integrations/vscode/README.md
+++ b/openhands/integrations/vscode/README.md
@@ -1,52 +1,14 @@
 # OpenHands VS Code Extension

-A unified VS Code extension that provides both launcher and runtime capabilities for OpenHands:
- **Launcher**: Start OpenHands conversations directly from VS Code with your current file or selected text
- **Runtime**: Execute OpenHands actions directly within VS Code (file operations, editor commands, etc.)
+The official OpenHands companion extension for Visual Studio Code.

-## What it does
+This extension seamlessly integrates OpenHands into your VSCode workflow, allowing you to start coding sessions with your AI agent directly from your editor.

-### Launcher Features
- **Start conversation**: Opens OpenHands in a terminal (safely reuses idle terminals or creates new ones)
- **Send current file**: Starts OpenHands with your active file
- **Send selection**: Starts OpenHands with selected text
- **Safe terminal management**: Never interrupts running processes; creates new terminals when needed
-
-Access launcher commands via Command Palette (Ctrl+Shift+P) or right-click menu.
-
-### Runtime Features
- **Backend Communication**: Connects to OpenHands backend via WebSocket for real-time action execution
- **File Operations**: Execute file read/write operations directly in VS Code
- **Editor Commands**: Perform editor actions like opening files, navigating to lines, etc.
- **Automatic Connection**: Connects to OpenHands backend when available, gracefully handles offline state
+![OpenHands VSCode Extension Demo](https://raw.githubusercontent.com/All-Hands-AI/OpenHands/main/assets/images/vscode-extension-demo.gif)

 ## Features

-### Safe Terminal Management
- **Non-Intrusive**: Never interrupts running processes in existing terminals
- **Smart Reuse**: Only reuses terminals that have completed OpenHands commands
- **Safe Fallback**: Creates new terminals when existing ones may be busy
- **Shell Integration**: Uses VS Code's Shell Integration API when available for better command tracking
- **Conservative Approach**: When in doubt, creates a new terminal to avoid conflicts
-
-### Virtual Environment Support
- **Auto-Detection**: Automatically finds and activates Python virtual environments
- **Multiple Patterns**: Supports `.venv`, `venv`, and `.virtualenv` directories
- **Cross-Platform**: Works on Windows, macOS, and Linux
-
-### Runtime Configuration
- **Server URL**: Configure OpenHands backend URL via VS Code settings (`openhands.serverUrl`)
- **On-Demand Connection**: Connects to backend only when OpenHands is configured to use VSCode as runtime
- **Graceful Fallback**: Works offline when backend is not available
-
-## Setup
-
-1. Install OpenHands: `pip install openhands`
-2. Install the VS Code extension (extension installs automatically when you run `openhands`)
-3. **Optional**: Configure OpenHands backend URL in VS Code settings:
-   - Open VS Code Settings (Ctrl+,)
-   - Search for "openhands"
-   - Set "OpenHands: Server URL" (default: `http://localhost:3000`)
+- **Start a New Conversation**: Launch OpenHands in a new terminal with a single command.
 - **Use Your Current File**: Automatically send the content of your active file to OpenHands to start a task.
 - **Use a Selection**: Send only the highlighted text from your editor to OpenHands for focused tasks.
 - **Safe Terminal Management**: The extension intelligently reuses idle terminals or creates new ones, ensuring it never interrupts an active process.
--- a/openhands/integrations/vscode/package-lock.json
+++ b/openhands/integrations/vscode/package-lock.json
--- a/openhands/integrations/vscode/package.json
+++ b/openhands/integrations/vscode/package.json
@@ -1,7 +1,7 @@
 {
  "name": "openhands-vscode",
  "displayName": "OpenHands Integration",
-  "description": "Integrates OpenHands with VS Code for conversation starting, context passing, and runtime execution.",
+  "description": "Integrates OpenHands with VS Code for easy conversation starting and context passing.",
  "version": "0.0.1",
  "publisher": "openhands",
  "license": "MIT",
@@ -16,9 +16,7 @@
  "activationEvents": [
    "onCommand:openhands.startConversation",
    "onCommand:openhands.startConversationWithFileContext",
-    "onCommand:openhands.startConversationWithSelectionContext",
-    "onCommand:openhands.testConnection",
-    "onStartupFinished"
+    "onCommand:openhands.startConversationWithSelectionContext"
  ],
  "main": "./out/extension.js",
  "contributes": {
@@ -37,11 +35,6 @@
        "command": "openhands.startConversationWithSelectionContext",
        "title": "Start with Selected Text",
        "category": "OpenHands"
-      },
-      {
-        "command": "openhands.testConnection",
-        "title": "Test Connection",
-        "category": "OpenHands"
      }
    ],
    "submenus": [
@@ -82,16 +75,6 @@
          "when": "editorHasSelection"
        }
      ]
-    },
-    "configuration": {
-      "title": "OpenHands",
-      "properties": {
-        "openhands.serverUrl": {
-          "type": "string",
-          "default": "http://localhost:3000",
-          "description": "URL of the OpenHands backend server for runtime connection."
-        }
-      }
    }
  },
  "scripts": {
@@ -105,14 +88,16 @@
    "typecheck": "tsc --noEmit"
  },
  "devDependencies": {
-    "@types/glob": "^8.1.0",
-    "@types/mocha": "^10.0.6",
-    "@types/node": "^20.12.12",
    "@types/vscode": "^1.98.2",
+    "typescript": "^5.0.0",
+    "@types/mocha": "^10.0.6",
+    "mocha": "^10.4.0",
+    "@vscode/test-electron": "^2.3.9",
+    "@types/node": "^20.12.12",
+    "@types/glob": "^8.1.0",
+    "@vscode/vsce": "^3.5.0",
    "@typescript-eslint/eslint-plugin": "^7.18.0",
    "@typescript-eslint/parser": "^7.18.0",
-    "@vscode/test-electron": "^2.3.9",
-    "@vscode/vsce": "^3.5.0",
    "eslint": "^8.57.0",
    "eslint-config-airbnb-base": "^15.0.0",
    "eslint-config-airbnb-typescript": "^18.0.0",
@@ -120,12 +105,6 @@
    "eslint-plugin-import": "^2.29.1",
    "eslint-plugin-prettier": "^5.5.0",
    "eslint-plugin-unused-imports": "^4.1.4",
-    "mocha": "^10.4.0",
-    "prettier": "^3.5.3",
-    "typescript": "^5.0.0"
-  },
-  "dependencies": {
-    "openhands-types": "git+https://github.com/enyst/openhands-types.git",
-    "socket.io-client": "^4.8.1"
+    "prettier": "^3.5.3"
  }
 }
--- a/openhands/integrations/vscode/src/extension.ts
+++ b/openhands/integrations/vscode/src/extension.ts
@@ -1,27 +1,10 @@
 import * as vscode from "vscode";
 import * as fs from "fs";
 import * as path from "path";
-import { SocketService } from "./services/socket-service";
-import { VSCodeRuntimeActionHandler } from "./services/runtime-action-handler";

 // Create output channel for debug logging
 const outputChannel = vscode.window.createOutputChannel("OpenHands Debug");

-// Runtime services - initialized lazily when needed
-let socketService: SocketService | null = null;
-let runtimeActionHandler: VSCodeRuntimeActionHandler | null = null;
-
-// Connection status tracking
-enum ConnectionStatus {
-  DISCONNECTED = "disconnected",
-  CONNECTING = "connecting",
-  CONNECTED = "connected",
-  ERROR = "error",
-}
-
-let connectionStatus: ConnectionStatus = ConnectionStatus.DISCONNECTED;
-let connectionError: string | null = null;
-
 /**
 * This implementation uses VSCode's Shell Integration API.
 *
@@ -297,119 +280,7 @@ function startOpenHandsInTerminal(options: {
  }
 }

-// Old initializeRuntime function removed - replaced with lazy connection via ensureConnected()
-
-/**
- * Lazy connection to OpenHands backend - only connects when needed
- */
-async function ensureConnected(): Promise<boolean> {
-  // If already connected, return true
-  if (connectionStatus === ConnectionStatus.CONNECTED && socketService) {
-    return true;
-  }
-
-  // If currently connecting, don't start another connection attempt
-  if (connectionStatus === ConnectionStatus.CONNECTING) {
-    vscode.window.showInformationMessage(
-      "⏳ Already connecting to OpenHands...",
-    );
-    return false;
-  }
-
-  // Attempt to connect
-  connectionStatus = ConnectionStatus.CONNECTING;
-  connectionError = null;
-
-  try {
-    // Get server URL from configuration
-    const config = vscode.workspace.getConfiguration("openhands");
-    const serverUrl = config.get<string>("serverUrl", "http://localhost:3000");
-
-    outputChannel.appendLine(
-      `DEBUG: Connecting to OpenHands backend at: ${serverUrl}`,
-    );
-
-    // Initialize services if not already done
-    if (!socketService) {
-      socketService = new SocketService(serverUrl);
-    }
-
-    if (!runtimeActionHandler) {
-      runtimeActionHandler = new VSCodeRuntimeActionHandler();
-      runtimeActionHandler.setSocketService(socketService);
-
-      // Set up event listener for incoming actions
-      socketService.onEvent((event) => {
-        if (runtimeActionHandler) {
-          runtimeActionHandler.handleAction(event);
-        }
-      });
-    }
-
-    // Attempt connection
-    await socketService.connect();
-
-    connectionStatus = ConnectionStatus.CONNECTED;
-    outputChannel.appendLine(
-      "DEBUG: Successfully connected to OpenHands backend",
-    );
-    vscode.window.showInformationMessage(
-      "✅ Connected to OpenHands - ready to execute actions in VSCode",
-    );
-
-    return true;
-  } catch (error) {
-    connectionStatus = ConnectionStatus.ERROR;
-    connectionError = error instanceof Error ? error.message : String(error);
-
-    outputChannel.appendLine(
-      `ERROR: Failed to connect to OpenHands backend: ${connectionError}`,
-    );
-
-    // Show user-friendly error message
-    const errorMsg = `❌ Cannot connect to OpenHands server. Is OpenHands running?\n\nError: ${connectionError}`;
-    const result = await vscode.window.showErrorMessage(
-      errorMsg,
-      "Retry Connection",
-      "Check Configuration",
-    );
-
-    if (result === "Retry Connection") {
-      // Reset status and try again
-      connectionStatus = ConnectionStatus.DISCONNECTED;
-      return ensureConnected();
-    }
-    if (result === "Check Configuration") {
-      // Open settings
-      vscode.commands.executeCommand(
-        "workbench.action.openSettings",
-        "openhands.serverUrl",
-      );
-    }
-
-    return false;
-  }
-}
-
-/**
- * Clean up runtime services
- */
-function cleanupRuntime(): void {
-  if (socketService) {
-    socketService.disconnect();
-    socketService = null;
-  }
-  runtimeActionHandler = null;
-  connectionStatus = ConnectionStatus.DISCONNECTED;
-  connectionError = null;
-  outputChannel.appendLine("DEBUG: OpenHands runtime services cleaned up");
-}
-
 export function activate(context: vscode.ExtensionContext) {
-  // Note: Runtime services are now initialized lazily when user runs commands
-  outputChannel.appendLine(
-    "DEBUG: OpenHands extension activated - runtime will connect on-demand",
-  );
  // Clean up terminal tracking when terminals are closed
  const terminalCloseDisposable = vscode.window.onDidCloseTerminal(
    (terminal) => {
@@ -421,12 +292,8 @@ export function activate(context: vscode.ExtensionContext) {
  // Command: Start New Conversation
  const startConversationDisposable = vscode.commands.registerCommand(
    "openhands.startConversation",
-    async () => {
-      // Ensure connection before starting conversation
-      const connected = await ensureConnected();
-      if (connected) {
-        startOpenHandsInTerminal({});
-      }
+    () => {
+      startOpenHandsInTerminal({});
    },
  );
  context.subscriptions.push(startConversationDisposable);
@@ -434,12 +301,7 @@ export function activate(context: vscode.ExtensionContext) {
  // Command: Start Conversation with Active File Content
  const startWithFileContextDisposable = vscode.commands.registerCommand(
    "openhands.startConversationWithFileContext",
-    async () => {
-      // Ensure connection before starting conversation
-      const connected = await ensureConnected();
-      if (!connected) {
-        return;
-      }
+    () => {
      const editor = vscode.window.activeTextEditor;
      if (!editor) {
        // No active editor, start conversation without task
@@ -474,12 +336,7 @@ export function activate(context: vscode.ExtensionContext) {
  // Command: Start Conversation with Selected Text
  const startWithSelectionContextDisposable = vscode.commands.registerCommand(
    "openhands.startConversationWithSelectionContext",
-    async () => {
-      // Ensure connection before starting conversation
-      const connected = await ensureConnected();
-      if (!connected) {
-        return;
-      }
+    () => {
      outputChannel.appendLine(
        "DEBUG: startConversationWithSelectionContext command triggered!",
      );
@@ -515,29 +372,9 @@ export function activate(context: vscode.ExtensionContext) {
    },
  );
  context.subscriptions.push(startWithSelectionContextDisposable);
-
-  // Command: Test Connection to OpenHands
-  const testConnectionDisposable = vscode.commands.registerCommand(
-    "openhands.testConnection",
-    async () => {
-      outputChannel.appendLine(
-        "DEBUG: Testing connection to OpenHands backend...",
-      );
-      const connected = await ensureConnected();
-      if (connected) {
-        vscode.window.showInformationMessage(
-          "✅ OpenHands connection successful!",
-        );
-      }
-      // Error handling is done in ensureConnected()
-    },
-  );
-  context.subscriptions.push(testConnectionDisposable);
 }

 export function deactivate() {
-  // Clean up runtime services
-  cleanupRuntime();
  // Clean up resources if needed, though for this simple extension,
  // VS Code handles terminal disposal.
 }
--- a/openhands/integrations/vscode/src/services/runtime-action-handler.ts
+++ b/openhands/integrations/vscode/src/services/runtime-action-handler.ts
@@ -1,317 +0,0 @@
-import * as vscode from "vscode";
-import {
-  OpenHandsEventType,
-  OpenHandsObservationEvent,
-  OpenHandsParsedEvent,
-  isOpenHandsAction,
-} from "openhands-types";
-import { SocketService } from "./socket-service";
-
-export class VSCodeRuntimeActionHandler {
-  private workspacePath: string | undefined;
-
-  private socketService: SocketService | null = null;
-
-  constructor() {
-    // Determine the workspace path for security restrictions
-    const { workspaceFolders } = vscode.workspace;
-    if (workspaceFolders && workspaceFolders.length > 0) {
-      this.workspacePath = workspaceFolders[0].uri.fsPath;
-      console.log(`Workspace path set to: ${this.workspacePath}`);
-    } else {
-      console.warn(
-        "No workspace folder found. File operations will be restricted.",
-      );
-    }
-  }
-
-  setSocketService(socketService: SocketService): void {
-    this.socketService = socketService;
-    console.log("SocketService set for VSCodeRuntimeActionHandler");
-  }
-
-  private sanitizePath(filePath: string): string | null {
-    if (!this.workspacePath) {
-      console.error(
-        "No workspace path defined. Blocking file operation for security.",
-      );
-      return null;
-    }
-
-    // Handle absolute and relative paths
-    let resolvedPath = filePath;
-    if (!filePath.startsWith("/")) {
-      resolvedPath = `${this.workspacePath}/${filePath}`;
-    }
-
-    // Basic check to prevent path traversal
-    if (!resolvedPath.startsWith(this.workspacePath)) {
-      console.error(
-        `Path traversal attempt detected. Path ${resolvedPath} is outside workspace ${this.workspacePath}.`,
-      );
-      return null;
-    }
-
-    return resolvedPath;
-  }
-
-  private static async openOrFocusFile(filePath: string): Promise<void> {
-    try {
-      const uri = vscode.Uri.file(filePath);
-      const document = await vscode.workspace.openTextDocument(uri);
-      await vscode.window.showTextDocument(document);
-    } catch (error) {
-      console.error(`Failed to open file ${filePath}:`, error);
-    }
-  }
-
-  handleAction(event: OpenHandsParsedEvent): void {
-    if (!isOpenHandsAction(event) || !event.args) {
-      console.error("Invalid event received for action handling:", event);
-      return;
-    }
-
-    console.log(`Handling action: ${event.action} with args:`, event.args);
-
-    switch (event.action) {
-      case "run":
-        this.handleRunAction(event);
-        break;
-      case "read":
-        this.handleReadAction(event);
-        break;
-      case "write":
-        this.handleWriteAction(event);
-        break;
-      case "edit":
-        this.handleEditAction(event);
-        break;
-      default:
-        console.warn(`Unsupported action received: ${event.action}`);
-        this.sendErrorObservation(event, `Unsupported action: ${event.action}`);
-    }
-  }
-
-  private sendObservation(
-    event: OpenHandsParsedEvent,
-    observationType: string,
-    content: string,
-    extras: Record<string, unknown> = {},
-    error: boolean = false,
-  ): void {
-    const observationEvent: OpenHandsObservationEvent<OpenHandsEventType> = {
-      id: Date.now(),
-      observation: observationType as OpenHandsEventType,
-      content,
-      extras,
-      message: error
-        ? `Error during ${observationType} operation`
-        : `VSCode executed ${observationType} operation`,
-      source: "environment",
-      cause: -1,
-      timestamp: new Date().toISOString(),
-    };
-    if ("id" in event && typeof event.id === "number") {
-      observationEvent.cause = event.id;
-    }
-
-    if (this.socketService) {
-      this.socketService.sendEvent(
-        observationEvent as unknown as OpenHandsParsedEvent,
-      );
-    } else {
-      console.error("Cannot send observation: SocketService is not set");
-      console.log("Observation that would have been sent:", observationEvent);
-    }
-  }
-
-  private sendErrorObservation(
-    event: OpenHandsParsedEvent,
-    errorMessage: string,
-  ): void {
-    this.sendObservation(
-      event,
-      "action" in event ? event.action || "unknown" : "unknown",
-      errorMessage,
-      {},
-      true,
-    );
-  }
-
-  private handleRunAction(event: OpenHandsParsedEvent): void {
-    if (!isOpenHandsAction(event) || event.action !== "run") {
-      this.sendErrorObservation(event, "Invalid event type for run action");
-      return;
-    }
-    const args = event.args as Record<string, unknown>;
-    const command = args.command as string | undefined;
-    if (!command) {
-      this.sendErrorObservation(event, "No command provided for run action");
-      return;
-    }
-
-    // Create or get a terminal for OpenHands commands
-    const terminalName = "OpenHands Runtime";
-    let terminal = vscode.window.terminals.find((t) => t.name === terminalName);
-    if (!terminal) {
-      terminal = vscode.window.createTerminal(terminalName);
-    }
-    terminal.show(true); // Show the terminal but preserve focus on editor
-
-    // Send the command to the terminal
-    terminal.sendText(command);
-
-    // For now, we can't reliably capture terminal output programmatically
-    // So we'll send a placeholder observation
-    this.sendObservation(
-      event,
-      "run",
-      `Command '${command}' sent to terminal. Output will be visible in the '${terminalName}' terminal.`,
-      { command, exit_code: 0 },
-    );
-  }
-
-  private async handleReadAction(event: OpenHandsParsedEvent): Promise<void> {
-    if (!isOpenHandsAction(event) || event.action !== "read") {
-      this.sendErrorObservation(event, "Invalid event type for read action");
-      return;
-    }
-    const args = event.args as { path?: string };
-    const filePath = args.path;
-    if (!filePath) {
-      this.sendErrorObservation(event, "No path provided for read action");
-      return;
-    }
-
-    const sanitizedPath = this.sanitizePath(filePath);
-    if (!sanitizedPath) {
-      this.sendErrorObservation(
-        event,
-        `Invalid path: ${filePath}. Path resolves outside the workspace.`,
-      );
-      return;
-    }
-
-    try {
-      const uri = vscode.Uri.file(sanitizedPath);
-      const contentBuffer = await vscode.workspace.fs.readFile(uri);
-      const content = contentBuffer.toString();
-      this.sendObservation(event, "read", content, { path: filePath });
-      // Optionally open the file in the editor for viewing
-      await VSCodeRuntimeActionHandler.openOrFocusFile(sanitizedPath);
-    } catch (error) {
-      console.error(`Error reading file ${sanitizedPath}:`, error);
-      this.sendErrorObservation(
-        event,
-        `Error reading file ${filePath}: ${error instanceof Error ? error.message : String(error)}`,
-      );
-    }
-  }
-
-  private async handleWriteAction(event: OpenHandsParsedEvent): Promise<void> {
-    if (!isOpenHandsAction(event) || event.action !== "write") {
-      this.sendErrorObservation(event, "Invalid event type for write action");
-      return;
-    }
-    const args = event.args as { path: string; content: string };
-    const filePath = args.path;
-    const { content } = args;
-    if (!filePath || content === undefined) {
-      this.sendErrorObservation(
-        event,
-        "Missing path or content for write action",
-      );
-      return;
-    }
-
-    const sanitizedPath = this.sanitizePath(filePath);
-    if (!sanitizedPath) {
-      this.sendErrorObservation(
-        event,
-        `Invalid path: ${filePath}. Path resolves outside the workspace.`,
-      );
-      return;
-    }
-
-    try {
-      const uri = vscode.Uri.file(sanitizedPath);
-      const contentBuffer = new TextEncoder().encode(content);
-      await vscode.workspace.fs.writeFile(uri, contentBuffer);
-      this.sendObservation(
-        event,
-        "write",
-        `File ${filePath} written successfully`,
-        { path: filePath },
-      );
-      // Open the file in the editor for viewing
-      await VSCodeRuntimeActionHandler.openOrFocusFile(sanitizedPath);
-    } catch (error) {
-      console.error(`Error writing to file ${sanitizedPath}:`, error);
-      this.sendErrorObservation(
-        event,
-        `Error writing to file ${filePath}: ${error instanceof Error ? error.message : String(error)}`,
-      );
-    }
-  }
-
-  private async handleEditAction(event: OpenHandsParsedEvent): Promise<void> {
-    if (!isOpenHandsAction(event) || event.action !== "edit") {
-      this.sendErrorObservation(event, "Invalid event type for edit action");
-      return;
-    }
-    const args = event.args as { path: string; content: string };
-    const filePath = args.path;
-    const newContent = args.content;
-    if (!filePath || newContent === undefined) {
-      this.sendErrorObservation(
-        event,
-        "Missing path or content for edit action",
-      );
-      return;
-    }
-
-    const sanitizedPath = this.sanitizePath(filePath);
-    if (!sanitizedPath) {
-      this.sendErrorObservation(
-        event,
-        `Invalid path: ${filePath}. Path resolves outside the workspace.`,
-      );
-      return;
-    }
-
-    try {
-      const uri = vscode.Uri.file(sanitizedPath);
-      // Read the current content to potentially show a diff
-      let oldContent = "";
-      try {
-        const currentContentBuffer = await vscode.workspace.fs.readFile(uri);
-        oldContent = currentContentBuffer.toString();
-      } catch (error) {
-        console.warn(
-          `Could not read current content of ${filePath} for diff, file might not exist yet.`,
-          error,
-        );
-      }
-
-      // Write the new content
-      const contentBuffer = new TextEncoder().encode(newContent);
-      await vscode.workspace.fs.writeFile(uri, contentBuffer);
-
-      // Open or focus the file to show changes
-      await VSCodeRuntimeActionHandler.openOrFocusFile(sanitizedPath);
-
-      this.sendObservation(
-        event,
-        "edit",
-        `File ${filePath} edited successfully`,
-        { path: filePath, old_content: oldContent, new_content: newContent },
-      );
-    } catch (error) {
-      console.error(`Error editing file ${sanitizedPath}:`, error);
-      this.sendErrorObservation(
-        event,
-        `Error editing file ${filePath}: ${error instanceof Error ? error.message : String(error)}`,
-      );
-    }
-  }
-}
--- a/openhands/integrations/vscode/src/services/socket-service.ts
+++ b/openhands/integrations/vscode/src/services/socket-service.ts
@@ -1,245 +0,0 @@
-import { io, Socket } from "socket.io-client";
-import { OpenHandsParsedEvent } from "openhands-types";
-import * as vscode from "vscode";
-import * as path from "path";
-
-export class SocketService {
-  private socket: Socket | null = null;
-
-  private serverUrl: string;
-
-  private conversationId: string | null = null;
-
-  private connectionId: string | null = null;
-
-  private eventListeners: Array<(event: OpenHandsParsedEvent) => void> = [];
-
-  private heartbeatInterval: NodeJS.Timeout | null = null;
-
-  constructor(serverUrl: string) {
-    this.serverUrl = serverUrl;
-  }
-
-  async connect(): Promise<void> {
-    try {
-      // Step 1: Register this VSCode instance with the server
-      await this.registerVSCodeInstance();
-
-      // Step 2: Initialize a conversation via HTTP API
-      const response = await fetch(`${this.serverUrl}/api/conversations`, {
-        method: "POST",
-        headers: {
-          "Content-Type": "application/json",
-        },
-        body: JSON.stringify({ initial_user_msg: "VSCode Runtime Connection" }),
-      });
-
-      if (!response.ok) {
-        throw new Error(
-          `Failed to initialize conversation: ${response.status} ${response.statusText}`,
-        );
-      }
-
-      const data = await response.json();
-      // TODO: Type check, do this better
-      this.conversationId = (
-        data as { conversation_id: string }
-      ).conversation_id;
-
-      // Now connect via Socket.IO
-      this.socket = io(this.serverUrl, {
-        query: {
-          conversation_id: this.conversationId,
-          latest_event_id: "-1",
-        },
-      });
-
-      this.socket.on("connect", () => {
-        console.log("Connected to OpenHands backend via Socket.IO");
-      });
-
-      this.socket.on("oh_event", (event: OpenHandsParsedEvent) => {
-        console.log("Received event:", event);
-        this.eventListeners.forEach((listener) => listener(event));
-      });
-
-      this.socket.on("disconnect", () => {
-        console.log("Disconnected from OpenHands backend");
-      });
-
-      this.socket.on("error", (error: unknown) => {
-        console.error("Socket.IO error:", error);
-      });
-
-      this.socket.on("connect_error", (error: unknown) => {
-        console.error("Socket.IO connection error:", error);
-      });
-
-      // Step 3: Start heartbeat to keep registration alive
-      this.startHeartbeat();
-    } catch (error) {
-      console.error("Error connecting to OpenHands backend:", error);
-      throw error;
-    }
-  }
-
-  disconnect(): void {
-    // Stop heartbeat
-    this.stopHeartbeat();
-
-    // Unregister from VSCode registry
-    if (this.connectionId) {
-      this.unregisterVSCodeInstance().catch((error) => {
-        console.error("Failed to unregister VSCode instance:", error);
-      });
-    }
-
-    // Disconnect socket
-    if (this.socket) {
-      this.socket.disconnect();
-      this.socket = null;
-      console.log("Socket.IO connection closed");
-    }
-
-    // Reset state
-    this.conversationId = null;
-    this.connectionId = null;
-  }
-
-  onEvent(listener: (event: OpenHandsParsedEvent) => void): void {
-    this.eventListeners.push(listener);
-  }
-
-  sendEvent(event: OpenHandsParsedEvent): void {
-    if (this.socket && this.socket.connected) {
-      this.socket.emit("oh_event", event);
-      console.log("Sent event:", event);
-    } else {
-      console.error("Cannot send event: Socket is not connected");
-    }
-  }
-
-  getConnectionId(): string | null {
-    return this.connectionId;
-  }
-
-  private async registerVSCodeInstance(): Promise<void> {
-    try {
-      // Get workspace information
-      const workspaceFolder = vscode.workspace.workspaceFolders?.[0];
-      const workspacePath = workspaceFolder?.uri.fsPath || "";
-      const workspaceName =
-        workspaceFolder?.name ||
-        path.basename(workspacePath) ||
-        "Unknown Workspace";
-
-      // Get VSCode version
-      const vscodeVersion = vscode.version;
-
-      // Get extension version (from package.json)
-      const extensionVersion =
-        vscode.extensions.getExtension("openhands.openhands-vscode")
-          ?.packageJSON?.version || "0.0.1";
-
-      // Define capabilities
-      const capabilities = [
-        "file_operations",
-        "text_editing",
-        "workspace_navigation",
-        "terminal_access",
-      ];
-
-      const registrationData = {
-        workspace_path: workspacePath,
-        workspace_name: workspaceName,
-        vscode_version: vscodeVersion,
-        extension_version: extensionVersion,
-        capabilities,
-      };
-
-      console.log("Registering VSCode instance:", registrationData);
-
-      const response = await fetch(`${this.serverUrl}/api/vscode/register`, {
-        method: "POST",
-        headers: {
-          "Content-Type": "application/json",
-        },
-        body: JSON.stringify(registrationData),
-      });
-
-      if (!response.ok) {
-        throw new Error(
-          `Failed to register VSCode instance: ${response.status} ${response.statusText}`,
-        );
-      }
-
-      const data = await response.json();
-      this.connectionId = (data as { connection_id: string }).connection_id;
-
-      console.log(
-        `VSCode instance registered with connection ID: ${this.connectionId}`,
-      );
-    } catch (error) {
-      console.error("Error registering VSCode instance:", error);
-      throw error;
-    }
-  }
-
-  private async unregisterVSCodeInstance(): Promise<void> {
-    if (!this.connectionId) {
-      return;
-    }
-
-    try {
-      const response = await fetch(
-        `${this.serverUrl}/api/vscode/unregister/${this.connectionId}`,
-        {
-          method: "DELETE",
-        },
-      );
-
-      if (!response.ok) {
-        console.warn(
-          `Failed to unregister VSCode instance: ${response.status} ${response.statusText}`,
-        );
-      } else {
-        console.log(`VSCode instance unregistered: ${this.connectionId}`);
-      }
-    } catch (error) {
-      console.error("Error unregistering VSCode instance:", error);
-    }
-  }
-
-  private startHeartbeat(): void {
-    if (!this.connectionId) {
-      return;
-    }
-
-    // Send heartbeat every 30 seconds
-    this.heartbeatInterval = setInterval(async () => {
-      try {
-        const response = await fetch(
-          `${this.serverUrl}/api/vscode/heartbeat/${this.connectionId}`,
-          {
-            method: "POST",
-          },
-        );
-
-        if (!response.ok) {
-          console.warn(
-            `Heartbeat failed: ${response.status} ${response.statusText}`,
-          );
-        }
-      } catch (error) {
-        console.error("Heartbeat error:", error);
-      }
-    }, 30000); // 30 seconds
-  }
-
-  private stopHeartbeat(): void {
-    if (this.heartbeatInterval) {
-      clearInterval(this.heartbeatInterval);
-      this.heartbeatInterval = null;
-    }
-  }
-}
--- a/openhands/integrations/vscode/src/test/suite/index.ts
+++ b/openhands/integrations/vscode/src/test/suite/index.ts
@@ -1,6 +1,6 @@
 import * as path from "path";
 import Mocha = require("mocha"); // Changed import style
-import { glob } from "glob"; // Use named import for modern glob
+import glob = require("glob"); // Changed import style

 export function run(): Promise<void> {
  // Create the mocha test
@@ -14,10 +14,14 @@ export function run(): Promise<void> {
  const testsRoot = path.resolve(__dirname, ".."); // Root of the /src/test folder (compiled to /out/test)

  return new Promise((c, e) => {
-    (async () => {
-      try {
-        // Use glob to find all test files (ending with .test.js in the compiled output)
-        const files = await glob("**/**.test.js", { cwd: testsRoot });
+    // Use glob to find all test files (ending with .test.js in the compiled output)
+    glob(
+      "**/**.test.js",
+      { cwd: testsRoot },
+      (err: NodeJS.ErrnoException | null, files: string[]) => {
+        if (err) {
+          return e(err);
+        }

        // Add files to the test suite
        files.forEach((f: string) => mocha.addFile(path.resolve(testsRoot, f)));
@@ -35,10 +39,7 @@ export function run(): Promise<void> {
          console.error(err);
          e(err);
        }
-      } catch (err) {
-        console.error("Error finding test files:", err);
-        e(err);
-      }
-    })();
+      },
+    );
  });
 }
--- a/openhands/integrations/vscode/src/test/suite/runtime-action-handler.test.ts
+++ b/openhands/integrations/vscode/src/test/suite/runtime-action-handler.test.ts
@@ -1,164 +0,0 @@
-import * as assert from "assert";
-import * as vscode from "vscode";
-import { VSCodeRuntimeActionHandler } from "../../services/runtime-action-handler";
-import { SocketService } from "../../services/socket-service";
-
-suite("VSCodeRuntimeActionHandler Test Suite", () => {
-  let handler: VSCodeRuntimeActionHandler;
-  let mockSocketService: SocketService;
-  let originalWorkspaceFolders: PropertyDescriptor | undefined;
-
-  setup(() => {
-    // Create handler instance
-    handler = new VSCodeRuntimeActionHandler();
-
-    // Create mock socket service
-    mockSocketService = {
-      onEvent: () => {},
-      sendEvent: () => {},
-      connect: () => Promise.resolve(),
-      disconnect: () => {},
-      getConnectionId: () => null,
-    } as any;
-
-    // Store original workspace folders for restoration
-    originalWorkspaceFolders = Object.getOwnPropertyDescriptor(
-      vscode.workspace,
-      "workspaceFolders",
-    );
-  });
-
-  teardown(() => {
-    // Restore original workspace folders
-    if (originalWorkspaceFolders) {
-      Object.defineProperty(
-        vscode.workspace,
-        "workspaceFolders",
-        originalWorkspaceFolders,
-      );
-    }
-  });
-
-  suite("Constructor and Initialization", () => {
-    test("should initialize without workspace", () => {
-      // Mock no workspace folders
-      Object.defineProperty(vscode.workspace, "workspaceFolders", {
-        get: () => undefined,
-        configurable: true,
-      });
-
-      const handlerNoWorkspace = new VSCodeRuntimeActionHandler();
-      assert.ok(
-        handlerNoWorkspace,
-        "Handler should be created even without workspace",
-      );
-    });
-
-    test("should initialize with workspace", () => {
-      // Mock workspace folders
-      const mockWorkspaceFolder = {
-        uri: vscode.Uri.file("/test/workspace"),
-        name: "test-workspace",
-        index: 0,
-      };
-
-      Object.defineProperty(vscode.workspace, "workspaceFolders", {
-        get: () => [mockWorkspaceFolder],
-        configurable: true,
-      });
-
-      const handlerWithWorkspace = new VSCodeRuntimeActionHandler();
-      assert.ok(
-        handlerWithWorkspace,
-        "Handler should be created with workspace",
-      );
-    });
-
-    test("should handle multiple workspace folders", () => {
-      // Mock multiple workspace folders
-      const mockWorkspaceFolders = [
-        {
-          uri: vscode.Uri.file("/test/workspace1"),
-          name: "workspace1",
-          index: 0,
-        },
-        {
-          uri: vscode.Uri.file("/test/workspace2"),
-          name: "workspace2",
-          index: 1,
-        },
-      ];
-
-      Object.defineProperty(vscode.workspace, "workspaceFolders", {
-        get: () => mockWorkspaceFolders,
-        configurable: true,
-      });
-
-      const handlerMultiWorkspace = new VSCodeRuntimeActionHandler();
-      assert.ok(
-        handlerMultiWorkspace,
-        "Handler should be created with multiple workspaces",
-      );
-    });
-  });
-
-  suite("SocketService Integration", () => {
-    test("should accept socket service", () => {
-      handler.setSocketService(mockSocketService);
-      assert.ok(true, "Should accept socket service without error");
-    });
-
-    test("should handle socket service events", () => {
-      let eventListenerAdded = false;
-      const mockSocketWithEventTracking = {
-        onEvent: (listener: any) => {
-          eventListenerAdded = true;
-          assert.ok(
-            typeof listener === "function",
-            "Event listener should be a function",
-          );
-        },
-        sendEvent: () => {},
-        connect: () => Promise.resolve(),
-        disconnect: () => {},
-        getConnectionId: () => null,
-      } as any;
-
-      handler.setSocketService(mockSocketWithEventTracking);
-      assert.ok(
-        eventListenerAdded,
-        "Should add event listener to socket service",
-      );
-    });
-  });
-
-  suite("Action Validation", () => {
-    test("should validate action structure", () => {
-      // Test with valid action-like object
-      const validAction = {
-        event_type: "action",
-        action: "run",
-        args: { command: "echo test" },
-      };
-
-      // We can't directly test isOpenHandsAction without importing it,
-      // but we can test that the handler doesn't throw with valid structure
-      assert.ok(validAction.event_type, "Valid action should have event_type");
-      assert.ok(validAction.action, "Valid action should have action");
-    });
-
-    test("should handle invalid action structure", () => {
-      // Test with invalid action-like object
-      const invalidAction = {
-        // Missing required fields
-        some_field: "value",
-      };
-
-      // Handler should be able to process this without throwing
-      assert.ok(
-        typeof invalidAction === "object",
-        "Should handle object input",
-      );
-    });
-  });
-});
--- a/openhands/integrations/vscode/src/test/suite/socket-service.test.ts
+++ b/openhands/integrations/vscode/src/test/suite/socket-service.test.ts
@@ -1,305 +0,0 @@
-import * as assert from "assert";
-import { SocketService } from "../../services/socket-service";
-
-// Mock Socket.IO client (for future use if needed)
-// const mockSocket = {
-//   on: () => {},
-//   emit: () => {},
-//   disconnect: () => {},
-//   connected: true,
-//   id: "mock-socket-id",
-// };
-
-// Mock fetch globally
-const originalFetch = global.fetch;
-
-suite("SocketService Test Suite", () => {
-  let socketService: SocketService;
-  let mockFetch: any;
-
-  setup(() => {
-    // Create service instance
-    socketService = new SocketService("http://localhost:3000");
-
-    // Reset fetch mock
-    mockFetch = null;
-  });
-
-  teardown(() => {
-    // Restore original fetch
-    if (originalFetch) {
-      global.fetch = originalFetch;
-    }
-
-    // Clean up service
-    if (socketService) {
-      socketService.disconnect();
-    }
-  });
-
-  suite("Constructor and Initialization", () => {
-    test("should initialize with server URL", () => {
-      const service = new SocketService("http://test-server:8080");
-      assert.ok(service, "SocketService should be created");
-    });
-
-    test("should store server URL correctly", () => {
-      const serverUrl = "http://custom-server:9000";
-      const service = new SocketService(serverUrl);
-      // We can't directly access private properties, but we can test behavior
-      assert.ok(service, "Service should be initialized with custom URL");
-    });
-
-    test("should have null connection ID initially", () => {
-      const connectionId = socketService.getConnectionId();
-      assert.strictEqual(
-        connectionId,
-        null,
-        "Connection ID should be null initially",
-      );
-    });
-  });
-
-  suite("Event Handling Interface", () => {
-    test("should allow adding event listeners", () => {
-      const listener = (event: any) => {
-        console.log("Event received:", event);
-      };
-
-      // This tests the public interface
-      socketService.onEvent(listener);
-      assert.ok(true, "Should allow adding event listeners without error");
-    });
-
-    test("should allow sending events when not connected", () => {
-      const mockEvent = {
-        id: "test-event-id",
-        timestamp: new Date().toISOString(),
-        source: "vscode",
-        message: "test message",
-        event_type: "test",
-      } as any;
-
-      // This should not throw even if not connected
-      socketService.sendEvent(mockEvent);
-      assert.ok(
-        true,
-        "Should allow sending events without error when disconnected",
-      );
-    });
-  });
-
-  suite("Registration Workflow", () => {
-    test("should prepare correct registration data", async () => {
-      let registrationCalled = false;
-      let registrationData: any = null;
-
-      // Mock successful registration
-      mockFetch = (url: string, options?: any) => {
-        if (url.includes("/api/vscode/register")) {
-          registrationCalled = true;
-          registrationData = JSON.parse(options.body);
-
-          return Promise.resolve({
-            ok: true,
-            json: () =>
-              Promise.resolve({
-                connection_id: "test-connection-id",
-                status: "registered",
-              }),
-          });
-        }
-        if (url.includes("/api/conversations")) {
-          return Promise.resolve({
-            ok: true,
-            json: () =>
-              Promise.resolve({
-                conversation_id: "test-conversation-id",
-              }),
-          });
-        }
-        return Promise.resolve({ ok: false, status: 404 });
-      };
-      global.fetch = mockFetch as any;
-
-      try {
-        await socketService.connect();
-      } catch (error) {
-        // Expected to fail due to Socket.IO mocking limitations
-      }
-
-      assert.ok(registrationCalled, "Registration should be called");
-      assert.ok(registrationData, "Registration data should be captured");
-      assert.ok(
-        registrationData.workspace_path !== undefined,
-        "Should include workspace path",
-      );
-      assert.ok(
-        registrationData.vscode_version,
-        "Should include VSCode version",
-      );
-      assert.ok(
-        registrationData.extension_version,
-        "Should include extension version",
-      );
-      assert.ok(
-        Array.isArray(registrationData.capabilities),
-        "Should include capabilities array",
-      );
-      assert.ok(
-        registrationData.capabilities.includes("file_operations"),
-        "Should include file_operations capability",
-      );
-    });
-
-    test("should handle registration failure", async () => {
-      mockFetch = (url: string) => {
-        if (url.includes("/api/vscode/register")) {
-          return Promise.resolve({
-            ok: false,
-            status: 500,
-            statusText: "Internal Server Error",
-          });
-        }
-        return Promise.resolve({ ok: false, status: 404 });
-      };
-      global.fetch = mockFetch as any;
-
-      try {
-        await socketService.connect();
-        assert.fail("Should have thrown an error for registration failure");
-      } catch (error) {
-        assert.ok(error instanceof Error, "Should throw an Error");
-        assert.ok(
-          (error as Error).message.includes(
-            "Failed to register VSCode instance",
-          ),
-          "Should have descriptive error message",
-        );
-      }
-    });
-
-    test("should handle network errors during registration", async () => {
-      mockFetch = () => Promise.reject(new Error("Network error"));
-      global.fetch = mockFetch as any;
-
-      try {
-        await socketService.connect();
-        assert.fail("Should have thrown an error for network failure");
-      } catch (error) {
-        assert.ok(error instanceof Error, "Should throw an Error");
-        assert.ok(
-          (error as Error).message.includes("Network error"),
-          "Should propagate network error",
-        );
-      }
-    });
-  });
-
-  suite("Conversation Creation", () => {
-    test("should create conversation after successful registration", async () => {
-      let conversationCalled = false;
-      let conversationData: any = null;
-
-      mockFetch = (url: string, options?: any) => {
-        if (url.includes("/api/vscode/register")) {
-          return Promise.resolve({
-            ok: true,
-            json: () =>
-              Promise.resolve({
-                connection_id: "test-connection-id",
-                status: "registered",
-              }),
-          });
-        }
-        if (url.includes("/api/conversations")) {
-          conversationCalled = true;
-          conversationData = JSON.parse(options.body);
-
-          return Promise.resolve({
-            ok: true,
-            json: () =>
-              Promise.resolve({
-                conversation_id: "test-conversation-id",
-              }),
-          });
-        }
-        return Promise.resolve({ ok: false, status: 404 });
-      };
-      global.fetch = mockFetch as any;
-
-      try {
-        await socketService.connect();
-      } catch (error) {
-        // Expected to fail due to Socket.IO mocking limitations
-      }
-
-      assert.ok(conversationCalled, "Conversation creation should be called");
-      assert.ok(conversationData, "Conversation data should be captured");
-      assert.strictEqual(
-        conversationData.initial_user_msg,
-        "VSCode Runtime Connection",
-        "Should have correct initial message",
-      );
-    });
-
-    test("should handle conversation creation failure", async () => {
-      mockFetch = (url: string) => {
-        if (url.includes("/api/vscode/register")) {
-          return Promise.resolve({
-            ok: true,
-            json: () =>
-              Promise.resolve({
-                connection_id: "test-connection-id",
-                status: "registered",
-              }),
-          });
-        }
-        if (url.includes("/api/conversations")) {
-          return Promise.resolve({
-            ok: false,
-            status: 400,
-            statusText: "Bad Request",
-          });
-        }
-        return Promise.resolve({ ok: false, status: 404 });
-      };
-      global.fetch = mockFetch as any;
-
-      try {
-        await socketService.connect();
-        assert.fail(
-          "Should have thrown an error for conversation creation failure",
-        );
-      } catch (error) {
-        assert.ok(error instanceof Error, "Should throw an Error");
-        assert.ok(
-          (error as Error).message.includes(
-            "Failed to initialize conversation",
-          ),
-          "Should have descriptive error message",
-        );
-      }
-    });
-  });
-
-  suite("Disconnection and Cleanup", () => {
-    test("should handle disconnection gracefully when not connected", () => {
-      try {
-        socketService.disconnect();
-        assert.ok(true, "Should handle disconnection without error");
-      } catch (error) {
-        assert.fail("Disconnection should not throw error when not connected");
-      }
-    });
-
-    test("should handle multiple disconnects safely", () => {
-      // Test that disconnect doesn't throw and cleans up properly
-      socketService.disconnect();
-
-      // Try to disconnect again - should not throw
-      socketService.disconnect();
-      assert.ok(true, "Multiple disconnects should be safe");
-    });
-  });
-});
--- a/openhands/llm/llm.py
+++ b/openhands/llm/llm.py
@@ -94,6 +94,7 @@ FUNCTION_CALLING_SUPPORTED_MODELS = [
    'kimi-k2-instruct',
    'Qwen3-Coder-480B-A35B-Instruct',
    'qwen3-coder',  # this will match both qwen3-coder-480b (openhands provider) and qwen3-coder (for openrouter)
+    'gpt-5',
    'gpt-5-2025-08-07',
 ]

@@ -108,7 +109,9 @@ REASONING_EFFORT_SUPPORTED_MODELS = [
    'o4-mini-2025-04-16',
    'gemini-2.5-flash',
    'gemini-2.5-pro',
+    'gpt-5',
    'gpt-5-2025-08-07',
+    'claude-opus-4-1-20250805',  # we need to remove top_p for opus 4.1
 ]

 MODELS_WITHOUT_STOP_WORDS = [
--- a/openhands/runtime/init.py
+++ b/openhands/runtime/init.py
@@ -8,7 +8,6 @@ from openhands.runtime.impl.docker.docker_runtime import (
 from openhands.runtime.impl.kubernetes.kubernetes_runtime import KubernetesRuntime
 from openhands.runtime.impl.local.local_runtime import LocalRuntime
 from openhands.runtime.impl.remote.remote_runtime import RemoteRuntime
-from openhands.runtime.vscode.vscode_runtime import VsCodeRuntime
 from openhands.utils.import_utils import get_impl

 # mypy: disable-error-code="type-abstract"
@@ -19,7 +18,6 @@ _DEFAULT_RUNTIME_CLASSES: dict[str, type[Runtime]] = {
    'local': LocalRuntime,
    'kubernetes': KubernetesRuntime,
    'cli': CLIRuntime,
-    'vscode': VsCodeRuntime,
 }

 # Try to import third-party runtimes if available
@@ -112,7 +110,6 @@ __all__ = [
    'DockerRuntime',
    'KubernetesRuntime',
    'CLIRuntime',
-    'VsCodeRuntime',
    'LocalRuntime',
    'get_runtime_cls',
 ]
--- a/openhands/runtime/base.py
+++ b/openhands/runtime/base.py
@@ -1038,7 +1038,9 @@ fi
        self, command: str, cwd: str | None
    ) -> CommandResult:
        """This function is used by the GitHandler to execute shell commands."""
-        obs = self.run(CmdRunAction(command=command, is_static=True, cwd=cwd))
+        obs = self.run(
+            CmdRunAction(command=command, is_static=True, hidden=True, cwd=cwd)
+        )
        exit_code = 0
        content = ''

--- a/openhands/runtime/builder/docker.py
+++ b/openhands/runtime/builder/docker.py
@@ -37,7 +37,7 @@ class DockerRuntimeBuilder(RuntimeBuilder):

    @staticmethod
    def check_buildx(is_podman: bool = False) -> bool:
-        """Check if Docker Buildx is available"""
+        """Check if Docker Buildx is available."""
        try:
            result = subprocess.run(
                ['docker' if not is_podman else 'podman', 'buildx', 'version'],
@@ -176,29 +176,32 @@ class DockerRuntimeBuilder(RuntimeBuilder):
                bufsize=1,
            )

+            output_lines = []
            if process.stdout:
                for line in iter(process.stdout.readline, ''):
                    line = line.strip()
                    if line:
+                        output_lines.append(line)  # Store all output lines
                        self._output_logs(line)

            return_code = process.wait()

            if return_code != 0:
+                # Use the collected output for error reporting
+                output_str = '\n'.join(output_lines)
                raise subprocess.CalledProcessError(
                    return_code,
                    process.args,
-                    output=process.stdout.read() if process.stdout else None,
-                    stderr=process.stderr.read() if process.stderr else None,
+                    output=output_str,  # Use the collected output
+                    stderr=None,
                )

        except subprocess.CalledProcessError as e:
-            logger.error(f'Image build failed:\n{e}')  # TODO: {e} is empty
-            logger.error(f'Command output:\n{e.output}')
-            if self.rolling_logger.is_enabled():
-                logger.error(
-                    'Docker build output:\n' + self.rolling_logger.all_lines
-                )  # Show the error
+            logger.error(f'Image build failed with exit code {e.returncode}')
+            if e.output:
+                logger.error(f'Command output:\n{e.output}')
+            elif self.rolling_logger.is_enabled() and self.rolling_logger.all_lines:
+                logger.error(f'Docker build output:\n{self.rolling_logger.all_lines}')
            raise

        except subprocess.TimeoutExpired:
--- a/openhands/runtime/impl/action_execution/action_execution_client.py
+++ b/openhands/runtime/impl/action_execution/action_execution_client.py
@@ -322,6 +322,8 @@ class ActionExecutionClient(Runtime):
                )
                assert response.is_closed
                output = response.json()
+                if getattr(action, 'hidden', False):
+                    output.get('extras')['hidden'] = True
                obs = observation_from_dict(output)
                obs._cause = action.id  # type: ignore[attr-defined]
            except httpx.TimeoutException:
--- a/openhands/runtime/utils/bash.py
+++ b/openhands/runtime/utils/bash.py
@@ -312,7 +312,11 @@ class BashSession:
        return command_output.rstrip()

    def _handle_completed_command(
-        self, command: str, pane_content: str, ps1_matches: list[re.Match]
+        self,
+        command: str,
+        pane_content: str,
+        ps1_matches: list[re.Match],
+        hidden: bool,
    ) -> CmdOutputObservation:
        is_special_key = self._is_special_key(command)
        assert len(ps1_matches) >= 1, (
@@ -359,6 +363,7 @@ class BashSession:
            content=command_output,
            command=command,
            metadata=metadata,
+            hidden=hidden,
        )

    def _handle_nochange_timeout_command(
@@ -549,11 +554,9 @@ class BashSession:
            metadata = CmdOutputMetadata()  # No metadata available
            metadata.suffix = (
                f'\n[Your command "{command}" is NOT executed. '
-                f'The previous command is still running - You CANNOT send new commands until the previous command is completed. '
+                'The previous command is still running - You CANNOT send new commands until the previous command is completed. '
                'By setting `is_input` to `true`, you can interact with the current process: '
-                "You may wait longer to see additional output of the previous command by sending empty command '', "
-                'send other commands to interact with the current process, '
-                'or send keys ("C-c", "C-z", "C-d") to interrupt/kill the previous command before sending your new command.]'
+                f'{TIMEOUT_MESSAGE_TEMPLATE}]'
            )
            logger.debug(f'PREVIOUS COMMAND OUTPUT: {raw_command_output}')
            command_output = self._get_command_output(
@@ -566,6 +569,7 @@ class BashSession:
                command=command,
                content=command_output,
                metadata=metadata,
+                hidden=getattr(action, 'hidden', False),
            )

        # Send actual command/inputs to the pane
@@ -616,6 +620,7 @@ class BashSession:
                    command,
                    pane_content=cur_pane_output,
                    ps1_matches=ps1_matches,
+                    hidden=getattr(action, 'hidden', False),
                )

            # Timeout checks should only trigger if a new prompt hasn't appeared yet.
--- a/openhands/runtime/utils/bash_constants.py
+++ b/openhands/runtime/utils/bash_constants.py
@@ -2,6 +2,6 @@
 TIMEOUT_MESSAGE_TEMPLATE = (
    "You may wait longer to see additional output by sending empty command '', "
    'send other commands to interact with the current process, '
-    'send keys to interrupt/kill the command, '
+    'send keys ("C-c", "C-z", "C-d") to interrupt/kill the previous command before sending your new command, '
    'or use the timeout parameter in execute_bash for future commands.'
 )
--- a/openhands/runtime/utils/runtime_templates/Dockerfile.j2
+++ b/openhands/runtime/utils/runtime_templates/Dockerfile.j2
@@ -1,5 +1,7 @@
 FROM {{ base_image }}

+SHELL ["/bin/bash", "-c"]
+
 # Shared environment variables
 ENV POETRY_VIRTUALENVS_PATH=/openhands/poetry \
    MAMBA_ROOT_PREFIX=/openhands/micromamba \
@@ -94,13 +96,8 @@ RUN \
        install -m 0755 -d /etc/apt/keyrings && \
        curl -fsSL https://download.docker.com/linux/debian/gpg -o /etc/apt/keyrings/docker.asc && \
        chmod a+r /etc/apt/keyrings/docker.asc && \
-        # Add the repository to Apt sources
-        # For Debian, if it's noble (testing/unstable), use bookworm (stable) repository
-        if [ "$(lsb_release -cs)" = "noble" ]; then \
-            echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/debian bookworm stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null; \
-        else \
-            echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/debian $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null; \
-        fi; \
+        # Add the repository to Apt sources (default to bookworm for stability)
+        echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/debian bookworm stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null; \
    fi && \
    # Install Docker Engine, containerd, and Docker Compose
    apt-get update && \
--- a/openhands/runtime/utils/windows_bash.py
+++ b/openhands/runtime/utils/windows_bash.py
@@ -855,9 +855,7 @@ class WindowsPowershellSession:
                            f'\n[Your command "{command}" is NOT executed. '
                            f'The previous command is still running - You CANNOT send new commands until the previous command is completed. '
                            'By setting `is_input` to `true`, you can interact with the current process: '
-                            "You may wait longer to see additional output of the previous command by sending empty command '', "
-                            'send other commands to interact with the current process, '
-                            'or send keys ("C-c", "C-z", "C-d") to interrupt/kill the previous command before sending your new command.]'
+                            f'{TIMEOUT_MESSAGE_TEMPLATE}]'
                        )

                        return CmdOutputObservation(
--- a/openhands/runtime/vscode/init.py
+++ b/openhands/runtime/vscode/init.py
@@ -1,3 +0,0 @@
-from .vscode_runtime import VsCodeRuntime
-
-__all__ = ['VsCodeRuntime']
--- a/openhands/runtime/vscode/vscode_runtime.py
+++ b/openhands/runtime/vscode/vscode_runtime.py
@@ -1,419 +0,0 @@
-import asyncio
-import uuid
-from pathlib import Path
-from typing import Callable
-
-import aiohttp
-import socketio  # Added for type hinting
-
-from openhands.core.config import OpenHandsConfig
-from openhands.core.logger import openhands_logger as logger
-from openhands.events.action import (
-    Action,
-    BrowseInteractiveAction,
-    BrowseURLAction,
-    CmdRunAction,
-    FileEditAction,
-    FileReadAction,
-    FileWriteAction,
-    IPythonRunCellAction,
-    MCPAction,
-)
-from openhands.events.observation import (
-    ErrorObservation,
-    Observation,
-)
-from openhands.events.serialization import event_from_dict, event_to_dict
-from openhands.events.stream import EventStream
-from openhands.runtime.base import Runtime
-from openhands.runtime.plugins import PluginRequirement
-from openhands.runtime.runtime_status import RuntimeStatus
-
-# GLOBAL_SOCKET_IO_CLIENT = None # Removed
-
-
-class VsCodeRuntime(Runtime):
-    """
-    A runtime that delegates action execution to a VS Code extension.
-    This class sends actions to the VS Code extension via the main Socket.IO server
-    and receives observations in return.
-    """
-
-    def __init__(
-        self,
-        config: OpenHandsConfig,
-        event_stream: EventStream,
-        sid: str = 'default',
-        plugins: list[PluginRequirement] | None = None,
-        env_vars: dict[str, str] | None = None,
-        status_callback: Callable[[str, RuntimeStatus, str], None] | None = None,
-        attach_to_existing: bool = False,
-        headless_mode: bool = False,
-        user_id: str | None = None,
-        # VSCode-specific parameters (optional for testing/injection)
-        sio_server: socketio.AsyncServer | None = None,
-        socket_connection_id: str | None = None,
-    ):
-        super().__init__(
-            config=config,
-            event_stream=event_stream,
-            sid=sid,
-            plugins=plugins,
-            env_vars=env_vars,
-            status_callback=status_callback,
-            attach_to_existing=attach_to_existing,
-            headless_mode=headless_mode,
-            user_id=user_id,
-        )
-        self.sid = sid
-        self.plugins = plugins or []
-        self.env_vars = env_vars or {}
-        self.status_callback = status_callback
-        self.attach_to_existing = attach_to_existing
-        self.headless_mode = headless_mode
-        self.user_id = user_id
-
-        # VSCode-specific attributes
-        self.sio_server = sio_server  # Will be set from shared.py if None
-        self.socket_connection_id = socket_connection_id  # Will be discovered if None
-        self._running_actions: dict[str, asyncio.Future[Observation]] = {}
-        self._server_url = 'http://localhost:3000'  # Default OpenHands server port
-
-        logger.info(f'VsCodeRuntime initialized with sid={sid}')
-
-    async def _get_available_vscode_instances(self) -> list[dict]:
-        """Query the server registry for available VSCode instances."""
-        try:
-            async with aiohttp.ClientSession() as session:
-                async with session.get(
-                    f'{self._server_url}/api/vscode/instances'
-                ) as response:
-                    if response.status == 200:
-                        instances = await response.json()
-                        if not isinstance(instances, list):
-                            logger.error(
-                                'Unexpected response shape for /api/vscode/instances; expected a list'
-                            )
-                            return []
-                        logger.info(
-                            f'Found {len(instances)} available VSCode instances'
-                        )
-                        return instances
-                    else:
-                        logger.error(
-                            f'Failed to get VSCode instances: HTTP {response.status}'
-                        )
-                        return []
-        except Exception as e:
-            logger.error(f'Error querying VSCode instances: {e}')
-            return []
-
-    async def _validate_vscode_connection(self, connection_id: str) -> bool:
-        """Validate that a VSCode connection is still active."""
-        try:
-            async with aiohttp.ClientSession() as session:
-                async with session.get(
-                    f'{self._server_url}/api/vscode/instance/{connection_id}'
-                ) as response:
-                    if response.status == 200:
-                        data = await response.json()
-                        status = data.get('status', 'unknown')
-                        logger.debug(
-                            f'VSCode connection {connection_id} status: {status}'
-                        )
-                        return status == 'active'
-                    else:
-                        logger.warning(
-                            f'VSCode connection {connection_id} validation failed: HTTP {response.status}'
-                        )
-                        return False
-        except Exception as e:
-            logger.error(f'Error validating VSCode connection {connection_id}: {e}')
-            return False
-
-    async def _discover_and_connect(self) -> bool:
-        """Discover available VSCode instances and establish connection."""
-        # Get sio_server from shared.py if not provided
-        if self.sio_server is None:
-            try:
-                from openhands.server.shared import sio
-
-                self.sio_server = sio
-                logger.info('Retrieved Socket.IO server from shared.py')
-            except ImportError as e:
-                logger.error(f'Failed to import Socket.IO server from shared.py: {e}')
-                return False
-
-        # If socket_connection_id is already set (e.g., for testing), validate it
-        if self.socket_connection_id:
-            if await self._validate_vscode_connection(self.socket_connection_id):
-                logger.info(
-                    f'Using existing VSCode connection: {self.socket_connection_id}'
-                )
-                return True
-            else:
-                logger.warning(
-                    f'Existing connection {self.socket_connection_id} is no longer valid'
-                )
-                self.socket_connection_id = None
-
-        # Discover available VSCode instances
-        instances = await self._get_available_vscode_instances()
-        if not instances:
-            logger.error('No VSCode instances are currently registered with OpenHands')
-            return False
-
-        # Filter for active instances
-        active_instances = [
-            inst for inst in instances if inst.get('status') == 'active'
-        ]
-        if not active_instances:
-            logger.error('No active VSCode instances found')
-            return False
-
-        # Use the first active instance (could be enhanced to let user choose)
-        selected_instance = active_instances[0]
-        self.socket_connection_id = selected_instance['connection_id']
-
-        logger.info(f'Connected to VSCode instance: {self.socket_connection_id}')
-        logger.info(f'Workspace: {selected_instance.get("workspace_path", "Unknown")}')
-        logger.info(f'Capabilities: {selected_instance.get("capabilities", [])}')
-
-        return True
-
-    async def _send_action_to_vscode(self, action: Action) -> Observation:
-        # Ensure we have a valid connection
-        if self.sio_server is None or self.socket_connection_id is None:
-            logger.info('No VSCode connection established, attempting discovery...')
-            if not await self._discover_and_connect():
-                return ErrorObservation(
-                    content='No VSCode instances available. Please ensure VSCode with OpenHands extension is running and connected.'
-                )
-
-        # Validate connection is still active before sending action
-        if self.socket_connection_id and not await self._validate_vscode_connection(
-            self.socket_connection_id
-        ):
-            logger.warning(
-                'VSCode connection became inactive, attempting to reconnect...'
-            )
-            self.socket_connection_id = None  # Force rediscovery
-            if not await self._discover_and_connect():
-                return ErrorObservation(
-                    content='VSCode connection lost and no alternative instances available.'
-                )
-
-        event_id = str(uuid.uuid4())
-
-        # Use proper serialization to create event payload for VSCode
-        oh_event_payload = event_to_dict(action)
-        oh_event_payload['event_id'] = event_id
-        oh_event_payload['message'] = getattr(
-            action, 'message', f'Delegating {type(action).__name__} to VSCode'
-        )
-
-        future: asyncio.Future[Observation] = asyncio.get_event_loop().create_future()
-        self._running_actions[event_id] = future
-
-        logger.info(
-            f'Sending action to VSCode (event_id: {event_id}, socket_id: {self.socket_connection_id}): {type(action)}'
-        )
-        logger.debug(f'Action details: {oh_event_payload}')
-
-        try:
-            if self.sio_server is None or not hasattr(self.sio_server, 'emit'):
-                logger.error("sio_server is None or does not have an 'emit' method.")
-                # Clean up future before returning
-                self._running_actions.pop(event_id, None)
-                future.cancel()  # Ensure future is not left pending
-                return ErrorObservation(
-                    content='sio_server is misconfigured for VsCodeRuntime.'
-                )
-
-            await self.sio_server.emit(
-                'oh_event', oh_event_payload, to=self.socket_connection_id
-            )
-            logger.debug(
-                f'Action emitted to socket_connection_id: {self.socket_connection_id}'
-            )
-
-        except Exception as e:
-            logger.error(
-                f'Error emitting action to VSCode (socket_id: {self.socket_connection_id}): {e}'
-            )
-            # Clean up future before returning
-            self._running_actions.pop(event_id, None)
-            if not future.done():  # Check if future is already resolved/cancelled
-                future.set_exception(
-                    e
-                )  # Propagate exception to the future if not already done
-            return ErrorObservation(
-                content=f'Failed to send action to VS Code extension: {e}'
-            )
-
-        try:
-            observation = await asyncio.wait_for(
-                future, timeout=self.config.sandbox.timeout
-            )
-            logger.info(
-                f'Received observation for event_id {event_id} from socket_id: {self.socket_connection_id}'
-            )
-            return observation
-        except asyncio.TimeoutError:
-            logger.error(
-                f'Timeout waiting for observation for event_id {event_id} from socket_id: {self.socket_connection_id}'
-            )
-            # The future is automatically cancelled by wait_for on timeout.
-            # We just need to ensure it's removed from _running_actions, which finally does.
-            return ErrorObservation(
-                content=f'Timeout waiting for VS Code extension response for action: {type(action)}'
-            )
-        except asyncio.CancelledError:
-            logger.info(f'Action {event_id} was cancelled while awaiting observation.')
-            return ErrorObservation(content=f'Action {type(action)} was cancelled.')
-        finally:
-            self._running_actions.pop(event_id, None)
-
-    def handle_observation_from_vscode(self, observation_event: dict):
-        cause_event_id = observation_event.get('cause')
-        if not cause_event_id:
-            logger.error(
-                f"Received observation event from VSCode without a 'cause' ID: {observation_event}"
-            )
-            return
-
-        if cause_event_id in self._running_actions:
-            future = self._running_actions[cause_event_id]
-
-            try:
-                # Use proper deserialization to convert observation event back to Observation object
-                observation = event_from_dict(observation_event)
-                assert isinstance(observation, Observation)
-            except Exception as e:
-                logger.error(
-                    f'Failed to deserialize observation from VSCode for cause {cause_event_id}: {e}'
-                )
-                observation = ErrorObservation(
-                    content=f'Failed to deserialize observation from VSCode: {e}. Raw event: {observation_event}'
-                )
-
-            if not future.done():
-                future.set_result(observation)
-            else:
-                logger.warning(
-                    f'Future for event_id {cause_event_id} was already done.'
-                )
-        else:
-            logger.warning(
-                f'Received observation for unknown event_id or already handled: {cause_event_id}'
-            )
-
-    def _run_async_action(self, action) -> Observation:
-        """Helper to run async action in sync context."""
-        try:
-            # Try to get the current event loop
-            asyncio.get_running_loop()
-            # If we're already in an async context, we need to use a different approach
-            # Create a new task and run it
-            import concurrent.futures
-
-            with concurrent.futures.ThreadPoolExecutor() as executor:
-                future = executor.submit(
-                    asyncio.run, self._send_action_to_vscode(action)
-                )
-                return future.result()
-        except RuntimeError:
-            # No event loop running, safe to use asyncio.run
-            return asyncio.run(self._send_action_to_vscode(action))
-
-    def run(self, action: CmdRunAction) -> Observation:
-        """Execute a shell command via VSCode."""
-        return self._run_async_action(action)
-
-    def read(self, action: FileReadAction) -> Observation:
-        """Read a file via VSCode."""
-        return self._run_async_action(action)
-
-    def write(self, action: FileWriteAction) -> Observation:
-        """Write to a file via VSCode."""
-        return self._run_async_action(action)
-
-    def edit(self, action: FileEditAction) -> Observation:
-        """Edit a file via VSCode."""
-        return self._run_async_action(action)
-
-    def browse(self, action: BrowseURLAction) -> Observation:
-        """Browse a URL via VSCode."""
-        return self._run_async_action(action)
-
-    def browse_interactive(self, action: BrowseInteractiveAction) -> Observation:
-        """Browse interactively via VSCode."""
-        return self._run_async_action(action)
-
-    def run_ipython(self, action: IPythonRunCellAction) -> Observation:
-        """Execute Python code via VSCode."""
-        return self._run_async_action(action)
-
-    async def call_tool_mcp(self, action: MCPAction) -> Observation:
-        """Call MCP tool via VSCode."""
-        return await self._send_action_to_vscode(action)
-
-    async def connect(self):
-        """Connect to VSCode extension via Socket.IO.
-
-        This method discovers available VSCode instances and establishes connection.
-        """
-        logger.info('VsCodeRuntime connecting to available VSCode instances...')
-
-        if await self._discover_and_connect():
-            logger.info('VsCodeRuntime successfully connected to VSCode extension')
-        else:
-            logger.error('VsCodeRuntime failed to connect to any VSCode extension')
-            raise RuntimeError(
-                'No VSCode instances available. Please ensure VSCode with OpenHands extension is running and connected to OpenHands server.'
-            )
-
-    def copy_from(self, path: str) -> Path:
-        """Copy files from the VSCode workspace to the host.
-
-        For VSCode runtime, file operations are handled through the extension,
-        so files are already accessible on the host. Return the path as-is.
-        """
-        logger.debug(f'VSCode Runtime: copy_from {path} (no-op)')
-        return Path(path)
-
-    def copy_to(self, host_src: str, sandbox_dest: str, recursive: bool = False):
-        """Copy files from the host to the VSCode workspace.
-
-        For VSCode runtime, file operations are handled through the extension,
-        so this is a no-op as files are already accessible on the host.
-        """
-        logger.debug(
-            f'VSCode Runtime: copy_to {host_src} -> {sandbox_dest} (no-op, recursive={recursive})'
-        )
-
-    def get_mcp_config(self, extra_stdio_servers: list | None = None):
-        """Get MCP configuration for this runtime.
-
-        Returns the MCP configuration from the runtime config.
-        """
-        return self.config.mcp
-
-    def list_files(self, path: str | None = None) -> list[str]:
-        """List files in the given path.
-
-        For VSCode runtime, we delegate file listing to the extension.
-        This is a synchronous wrapper around the async file listing operation.
-        """
-        # For now, return empty list as file operations should go through VSCode extension
-        logger.debug(f'VSCode Runtime: list_files {path} (delegated to extension)')
-        return []
-
-    async def close(self):
-        logger.info('Closing VsCodeRuntime. Outstanding actions will be cancelled.')
-        for event_id, future in self._running_actions.items():
-            if not future.done():
-                future.cancel()
-                logger.info(f'Cancelled pending action: {event_id}')
-        self._running_actions.clear()
-        logger.info('VsCodeRuntime closed.')
--- a/openhands/server/app.py
+++ b/openhands/server/app.py
@@ -28,7 +28,6 @@ from openhands.server.routes.secrets import app as secrets_router
 from openhands.server.routes.security import app as security_api_router
 from openhands.server.routes.settings import app as settings_router
 from openhands.server.routes.trajectory import app as trajectory_router
-from openhands.server.routes.vscode import app as vscode_api_router
 from openhands.server.shared import conversation_manager, server_config
 from openhands.server.types import AppMode

@@ -72,6 +71,5 @@ app.include_router(settings_router)
 app.include_router(secrets_router)
 if server_config.app_mode == AppMode.OSS:
    app.include_router(git_api_router)
-    app.include_router(vscode_api_router)
 app.include_router(trajectory_router)
 add_health_endpoints(app)
--- a/openhands/server/routes/vscode.py
+++ b/openhands/server/routes/vscode.py
@@ -1,290 +0,0 @@
-"""VSCode Integration API Routes
-
-Provides endpoints for VSCode extension registration, discovery, and management.
-Implements the server-side registry for the Lazy Connection Pattern.
-"""
-
-import time
-import uuid
-
-from fastapi import APIRouter, HTTPException
-from fastapi import status as http_status
-from pydantic import BaseModel, Field
-
-from openhands.core.logger import openhands_logger as logger
-from openhands.server.dependencies import get_dependencies
-
-app = APIRouter(prefix='/api/vscode', dependencies=get_dependencies())
-
-# Global VSCode instance registry
-# In production, this could be moved to a persistent store
-_vscode_registry: dict[str, 'VSCodeInstance'] = {}
-
-
-class VSCodeInstance(BaseModel):
-    """Information about a registered VSCode instance"""
-
-    connection_id: str
-    workspace_path: str
-    workspace_name: str
-    vscode_version: str
-    extension_version: str
-    capabilities: list[str]
-    registered_at: float
-    last_heartbeat: float
-    status: str = 'active'  # active, idle, disconnected
-
-
-class VSCodeRegistrationRequest(BaseModel):
-    """Request payload for VSCode instance registration"""
-
-    workspace_path: str = Field(
-        ..., min_length=1, description='Path to the workspace directory'
-    )
-    workspace_name: str = Field(..., min_length=1, description='Name of the workspace')
-    vscode_version: str = Field(..., min_length=1, description='VSCode version')
-    extension_version: str = Field(..., min_length=1, description='Extension version')
-    capabilities: list[str] = Field(
-        default=[], description='List of capabilities supported by this instance'
-    )
-
-
-class VSCodeRegistrationResponse(BaseModel):
-    """Response for successful VSCode registration"""
-
-    connection_id: str
-    message: str
-
-
-class VSCodeInstanceInfo(BaseModel):
-    """Public information about a VSCode instance"""
-
-    connection_id: str
-    workspace_name: str
-    workspace_path: str
-    status: str
-    registered_at: float
-    last_heartbeat: float
-
-
-@app.post('/register', response_model=VSCodeRegistrationResponse)
-async def register_vscode_instance(request: VSCodeRegistrationRequest):
-    """Register a new VSCode instance with the server
-
-    This endpoint is called by the VSCode extension when it connects to OpenHands.
-    It creates a unique connection_id and stores the instance information.
-    """
-    try:
-        # Generate unique connection ID
-        connection_id = str(uuid.uuid4())
-        current_time = time.time()
-
-        # Create VSCode instance record
-        instance = VSCodeInstance(
-            connection_id=connection_id,
-            workspace_path=request.workspace_path,
-            workspace_name=request.workspace_name,
-            vscode_version=request.vscode_version,
-            extension_version=request.extension_version,
-            capabilities=request.capabilities,
-            registered_at=current_time,
-            last_heartbeat=current_time,
-            status='active',
-        )
-
-        # Store in registry
-        _vscode_registry[connection_id] = instance
-
-        logger.info(
-            f"Registered VSCode instance: {connection_id} for workspace '{request.workspace_name}'"
-        )
-
-        return VSCodeRegistrationResponse(
-            connection_id=connection_id,
-            message=f"Successfully registered VSCode instance for workspace '{request.workspace_name}'",
-        )
-
-    except Exception as e:
-        logger.error(f'Failed to register VSCode instance: {e}')
-        raise HTTPException(
-            status_code=http_status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=f'Registration failed: {str(e)}',
-        )
-
-
-@app.get('/instances', response_model=list[VSCodeInstanceInfo])
-async def get_vscode_instances():
-    """Get list of all registered VSCode instances
-
-    This endpoint is used by VsCodeRuntime to discover available VSCode instances.
-    Returns public information about each registered instance.
-    """
-    try:
-        # Clean up stale instances (no heartbeat for > 5 minutes)
-        current_time = time.time()
-        stale_threshold = 5 * 60  # 5 minutes
-
-        stale_ids = [
-            conn_id
-            for conn_id, instance in _vscode_registry.items()
-            if current_time - instance.last_heartbeat > stale_threshold
-        ]
-
-        for conn_id in stale_ids:
-            logger.info(f'Removing stale VSCode instance: {conn_id}')
-            del _vscode_registry[conn_id]
-
-        # Return active instances
-        instances = [
-            VSCodeInstanceInfo(
-                connection_id=instance.connection_id,
-                workspace_name=instance.workspace_name,
-                workspace_path=instance.workspace_path,
-                status=instance.status,
-                registered_at=instance.registered_at,
-                last_heartbeat=instance.last_heartbeat,
-            )
-            for instance in _vscode_registry.values()
-        ]
-
-        logger.debug(f'Returning {len(instances)} VSCode instances')
-        return instances
-
-    except Exception as e:
-        logger.error(f'Failed to get VSCode instances: {e}')
-        raise HTTPException(
-            status_code=http_status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=f'Failed to retrieve instances: {str(e)}',
-        )
-
-
-@app.post('/heartbeat/{connection_id}')
-async def vscode_heartbeat(connection_id: str):
-    """Update heartbeat for a VSCode instance
-
-    This endpoint should be called periodically by VSCode extensions
-    to indicate they are still active and connected.
-    """
-    try:
-        if connection_id not in _vscode_registry:
-            raise HTTPException(
-                status_code=http_status.HTTP_404_NOT_FOUND,
-                detail=f'VSCode instance {connection_id} not found',
-            )
-
-        # Update heartbeat timestamp
-        _vscode_registry[connection_id].last_heartbeat = time.time()
-        _vscode_registry[connection_id].status = 'active'
-
-        logger.debug(f'Updated heartbeat for VSCode instance: {connection_id}')
-        return {'message': 'Heartbeat updated'}
-
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f'Failed to update heartbeat for {connection_id}: {e}')
-        raise HTTPException(
-            status_code=http_status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=f'Heartbeat update failed: {str(e)}',
-        )
-
-
-@app.delete('/unregister/{connection_id}')
-async def unregister_vscode_instance(connection_id: str):
-    """Unregister a VSCode instance
-
-    This endpoint is called when a VSCode instance disconnects
-    or is no longer available.
-    """
-    try:
-        if connection_id not in _vscode_registry:
-            raise HTTPException(
-                status_code=http_status.HTTP_404_NOT_FOUND,
-                detail=f'VSCode instance {connection_id} not found',
-            )
-
-        instance = _vscode_registry[connection_id]
-        del _vscode_registry[connection_id]
-
-        logger.info(
-            f"Unregistered VSCode instance: {connection_id} for workspace '{instance.workspace_name}'"
-        )
-        return {'message': f'Successfully unregistered VSCode instance {connection_id}'}
-
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f'Failed to unregister VSCode instance {connection_id}: {e}')
-        raise HTTPException(
-            status_code=http_status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=f'Unregistration failed: {str(e)}',
-        )
-
-
-@app.get('/instance/{connection_id}', response_model=VSCodeInstanceInfo)
-async def get_vscode_instance(connection_id: str):
-    """Get information about a specific VSCode instance"""
-    try:
-        if connection_id not in _vscode_registry:
-            raise HTTPException(
-                status_code=http_status.HTTP_404_NOT_FOUND,
-                detail=f'VSCode instance {connection_id} not found',
-            )
-
-        instance = _vscode_registry[connection_id]
-        return VSCodeInstanceInfo(
-            connection_id=instance.connection_id,
-            workspace_name=instance.workspace_name,
-            workspace_path=instance.workspace_path,
-            status=instance.status,
-            registered_at=instance.registered_at,
-            last_heartbeat=instance.last_heartbeat,
-        )
-
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f'Failed to get VSCode instance {connection_id}: {e}')
-        raise HTTPException(
-            status_code=http_status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=f'Failed to retrieve instance: {str(e)}',
-        )
-
-
-@app.get('/registry/stats')
-async def get_registry_stats():
-    """Get statistics about the VSCode registry
-
-    Useful for monitoring and debugging.
-    """
-    try:
-        current_time = time.time()
-        total_instances = len(_vscode_registry)
-
-        # Count by status
-        status_counts: dict[str, int] = {}
-        for instance in _vscode_registry.values():
-            status = instance.status
-            status_counts[status] = status_counts.get(status, 0) + 1
-
-        # Count recent activity (last 5 minutes)
-        recent_threshold = 5 * 60  # 5 minutes
-        recent_activity = sum(
-            1
-            for instance in _vscode_registry.values()
-            if current_time - instance.last_heartbeat < recent_threshold
-        )
-
-        return {
-            'total_instances': total_instances,
-            'status_counts': status_counts,
-            'recent_activity': recent_activity,
-            'registry_size': len(_vscode_registry),
-        }
-
-    except Exception as e:
-        logger.error(f'Failed to get registry stats: {e}')
-        raise HTTPException(
-            status_code=http_status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=f'Failed to retrieve stats: {str(e)}',
-        )
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.3 and should not be changed by hand.

 [[package]]
 name = "aiofiles"
@@ -404,7 +404,7 @@ description = "LTS Port of Python audioop"
 optional = false
 python-versions = ">=3.13"
 groups = ["main"]
-markers = "python_version >= \"3.13\""
+markers = "python_version == \"3.13\""
 files = [
    {file = "audioop_lts-0.2.1-cp313-abi3-macosx_10_13_universal2.whl", hash = "sha256:fd1345ae99e17e6910f47ce7d52673c6a1a70820d78b67de1b7abb3af29c426a"},
    {file = "audioop_lts-0.2.1-cp313-abi3-macosx_10_13_x86_64.whl", hash = "sha256:e175350da05d2087e12cea8e72a70a1a8b14a17e92ed2022952a4419689ede5e"},
@@ -2997,8 +2997,8 @@ files = [
 google-api-core = {version = ">=1.34.1,<2.0.dev0 || >=2.11.dev0,<3.0.0dev", extras = ["grpc"]}
 google-auth = ">=2.14.1,<2.24.0 || >2.24.0,<2.25.0 || >2.25.0,<3.0.0dev"
 proto-plus = [
-    {version = ">=1.22.3,<2.0.0dev"},
    {version = ">=1.25.0,<2.0.0dev", markers = "python_version >= \"3.13\""},
+    {version = ">=1.22.3,<2.0.0dev"},
 ]
 protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<6.0.0dev"

@@ -3020,8 +3020,8 @@ googleapis-common-protos = ">=1.56.2,<2.0.0"
 grpcio = {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""}
 grpcio-status = {version = ">=1.49.1,<2.0.0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""}
 proto-plus = [
-    {version = ">=1.22.3,<2.0.0"},
    {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
+    {version = ">=1.22.3,<2.0.0"},
 ]
 protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<7.0.0"
 requests = ">=2.18.0,<3.0.0"
@@ -3239,8 +3239,8 @@ google-api-core = {version = ">=1.34.1,<2.0.dev0 || >=2.11.dev0,<3.0.0", extras
 google-auth = ">=2.14.1,<2.24.0 || >2.24.0,<2.25.0 || >2.25.0,<3.0.0"
 grpc-google-iam-v1 = ">=0.14.0,<1.0.0"
 proto-plus = [
-    {version = ">=1.22.3,<2.0.0"},
    {version = ">=1.25.0,<2.0.0", markers = "python_version >= \"3.13\""},
+    {version = ">=1.22.3,<2.0.0"},
 ]
 protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<7.0.0"

@@ -6663,8 +6663,8 @@ files = [
 [package.dependencies]
 googleapis-common-protos = ">=1.52,<2.0"
 grpcio = [
-    {version = ">=1.63.2,<2.0.0", markers = "python_version < \"3.13\""},
    {version = ">=1.66.2,<2.0.0", markers = "python_version >= \"3.13\""},
+    {version = ">=1.63.2,<2.0.0", markers = "python_version < \"3.13\""},
 ]
 opentelemetry-api = ">=1.15,<2.0"
 opentelemetry-exporter-otlp-proto-common = "1.34.1"
@@ -9438,7 +9438,6 @@ files = [
    {file = "setuptools-80.9.0-py3-none-any.whl", hash = "sha256:062d34222ad13e0cc312a4c02d73f059e86a4acbfbdea8f8f76b28c99f306922"},
    {file = "setuptools-80.9.0.tar.gz", hash = "sha256:f36b47402ecde768dbfafc46e8e4207b4360c654f1f3bb84475f0a28628fb19c"},
 ]
-markers = {evaluation = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}

 [package.extras]
 check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\"", "ruff (>=0.8.0) ; sys_platform != \"cygwin\""]
@@ -9682,7 +9681,7 @@ description = "Standard library aifc redistribution. \"dead battery\"."
 optional = false
 python-versions = "*"
 groups = ["main"]
-markers = "python_version >= \"3.13\""
+markers = "python_version == \"3.13\""
 files = [
    {file = "standard_aifc-3.13.0-py3-none-any.whl", hash = "sha256:f7ae09cc57de1224a0dd8e3eb8f73830be7c3d0bc485de4c1f82b4a7f645ac66"},
    {file = "standard_aifc-3.13.0.tar.gz", hash = "sha256:64e249c7cb4b3daf2fdba4e95721f811bde8bdfc43ad9f936589b7bb2fae2e43"},
@@ -9699,7 +9698,7 @@ description = "Standard library chunk redistribution. \"dead battery\"."
 optional = false
 python-versions = "*"
 groups = ["main"]
-markers = "python_version >= \"3.13\""
+markers = "python_version == \"3.13\""
 files = [
    {file = "standard_chunk-3.13.0-py3-none-any.whl", hash = "sha256:17880a26c285189c644bd5bd8f8ed2bdb795d216e3293e6dbe55bbd848e2982c"},
    {file = "standard_chunk-3.13.0.tar.gz", hash = "sha256:4ac345d37d7e686d2755e01836b8d98eda0d1a3ee90375e597ae43aaf064d654"},
@@ -9811,7 +9810,7 @@ test = ["pytest", "pytest-cov"]
 type = "git"
 url = "https://github.com/ryanhoangt/SWE-bench.git"
 reference = "fix-modal-patch-eval"
-resolved_reference = "03846bfaa2f1bad5e72354094ac308590d5e2b37"
+resolved_reference = "aa0f1ed4c3b57828c8b9b2821b0ce74e201cf813"

 [[package]]
 name = "swegym"
--- a/task.md
+++ b/task.md
@@ -1,391 +0,0 @@
-# VSCode Runtime Task Summary
-
-## BREAKTHROUGH: Architecture Analysis Complete!
-
-After deep analysis, I discovered that the **Socket.IO architecture is actually brilliant and correct!** The current implementation is not "hallucinated" - it's a sophisticated message broker pattern.
-
-## What a VSCode Runtime Should Be Like
-
-A VSCode Runtime should enable OpenHands agents to execute actions directly within a user's VSCode environment, leveraging the editor's capabilities for file operations, terminal access, and workspace management.
-
-### Key Characteristics:
-1. **Seamless Integration**: Actions execute in the user's actual VSCode workspace
-2. **Real-time Feedback**: User can see agent actions happening in their editor
-3. **Native Capabilities**: Leverage VSCode's file system, terminal, and extension ecosystem
-4. **On-Demand Connection**: Only connect when user explicitly chooses VSCode runtime
-5. **Multiple Instance Support**: Handle multiple VSCode windows/workspaces
-
-### Architecture Pattern (CORRECT):
- **VSCode Extension**: Acts as a Socket.IO client (like web frontend)
- **Main OpenHands Server**: Central Socket.IO message broker
- **VsCodeRuntime**: Routes actions via Socket.IO server to specific VSCode connections
- **Communication**: Socket.IO events routed through main server (reuses existing infrastructure)
-
-## What Current VSCode Implementation Does
-
-### Current Architecture (Actually Brilliant!)
-The current implementation uses a **Socket.IO message broker pattern**:
-
-1. **VSCode Extension** connects to main OpenHands Socket.IO server (like web frontend)
-2. **VsCodeRuntime** uses the same Socket.IO server to route events to specific connections
-3. **Main Server** acts as message broker between runtime and extension
-4. **Events** flow: Runtime → Socket.IO Server → VSCode Extension → Back via Socket.IO
-
-### Current Implementation Files:
- `openhands/runtime/vscode/vscode_runtime.py` - Python runtime class
- `openhands/integrations/vscode/src/services/socket-service.ts` - Extension Socket.IO client
- `openhands/integrations/vscode/src/services/runtime-action-handler.ts` - Action execution
- `openhands/server/shared.py` - Main Socket.IO server instance
-
-### What Works:
- ✅ Socket.IO architecture is elegant and reuses existing infrastructure
- ✅ Extension connects and receives events properly
- ✅ Action serialization and event structure are correct
- ✅ Basic message routing framework exists
-
-## The Real Problems Identified
-
-### 1. **Missing Constructor Parameters**
-VsCodeRuntime requires `sio_server` and `socket_connection_id` parameters, but AgentSession only passes standard runtime parameters. The VSCode-specific parameters default to `None`, causing runtime failures.
-
-### 2. **Connection Coordination Gap**
- VSCode Extension connects to Socket.IO server and gets a `connection_id`
- VsCodeRuntime needs that same `connection_id` to send events
- **No mechanism exists to pass the connection_id from extension to runtime!**
-
-### 3. **Timing Issues**
- VSCode Extension connects automatically on startup
- VsCodeRuntime is created later when user starts a conversation
- Connection happens before runtime needs it (should be on-demand)
-
-## Proposed Solution: Lazy Connection Pattern
-
-### Core Problem Identified
-The original Runtime Registration Pattern had a **fundamental timing issue**:
- VSCode Extension activates when VSCode starts
- Extension immediately tries to connect to OpenHands server
- **But OpenHands server might not be running yet!**
- Connection fails, extension becomes unusable
-
-### Better Approach: Lazy Connection
-Instead of connecting immediately on extension activation:
-
-1. **VSCode starts** → Extension activates (but **doesn't connect**)
-2. **User starts OpenHands** → Server starts and waits
-3. **User runs VSCode command** (e.g., "Start Conversation") → Extension connects on-demand
-4. **Extension registers** with server after successful connection
-5. **VsCodeRuntime discovers** the registered connection when needed
-
-### Benefits
- ✅ **No timing dependency** - Extension works regardless of OpenHands startup order
- ✅ **Matches user mental model** - "I'll connect when I need OpenHands"
- ✅ **Simpler implementation** - No retry patterns or background polling
- ✅ **Resource efficient** - No unnecessary connections
-
-## Implementation Plan: Lazy Connection Pattern
-
-### Phase 1: Extension Lazy Connection ✅ COMPLETED
-**Goal**: Remove immediate connection, add lazy connection triggered by user commands
-
-#### Sub-steps:
-1. ✅ **Modify `activate()` function** - Remove `initializeRuntime()` call
-2. ✅ **Add connection status tracking** - Track connection state in extension
-3. ✅ **Modify user commands** - Trigger connection before executing commands
-4. ✅ **Add user feedback** - Show connection status/errors in VSCode UI
-5. ✅ **Handle connection failures** - Graceful error handling with retry options
-6. ✅ **Add test command** - `openhands.testConnection` for manual testing
-
-### Phase 2: Server Registration System ⏳ NEXT
-**Goal**: Add VSCode registry and discovery APIs to OpenHands server
-
-#### Sub-steps:
-1. **Add VSCode registry data structure** - Track `connection_id → VSCode instance info`
-2. **Implement registration API endpoint** - `/api/vscode/register` POST endpoint
-3. **Add discovery API endpoint** - `/api/vscode/discover` GET endpoint
-4. **Handle disconnection cleanup** - Remove stale registry entries
-5. **Add Socket.IO event handlers** - Handle VSCode-specific events
-
-### Phase 3: Runtime Discovery & Error Handling
-**Goal**: Update VsCodeRuntime to discover connections and handle errors gracefully
-
-#### Sub-steps:
-1. **Implement connection discovery** - Query server registry in `connect()`
-2. **Add timeout handling** - Proper timeouts for all actions
-3. **Add clear error messages** - User-friendly error messages for all failure modes
-4. **Handle disconnection scenarios** - Runtime behavior when VSCode disconnects
-5. **Add connection validation** - Verify connection before sending actions
-
-### Phase 4: Integration & Testing
-**Goal**: Test full flow and error scenarios
-
-#### Sub-steps:
-1. **Test happy path** - Full flow from VSCode command to runtime execution
-2. **Test error scenarios** - Server not running, VSCode disconnects, timeouts
-3. **Add comprehensive logging** - Debug information for troubleshooting
-4. **Performance testing** - Ensure no performance regressions
-5. **Documentation update** - Update README and docs
-
-## Error Scenarios to Handle
-
-### Extension Side:
- ❌ **OpenHands server not running** when user tries to connect
- ❌ **Connection drops** during operation
- ❌ **Server rejects registration** (duplicate, invalid data)
- ❌ **Network issues** (timeouts, DNS failures)
-
-### Server Side:
- ❌ **VSCode connects but never registers** (stale connections)
- ❌ **VSCode disconnects without cleanup** (registry cleanup)
- ❌ **Multiple VSCode instances** registering (conflict resolution)
- ❌ **Stale registry entries** (periodic cleanup)
-
-### Runtime Side:
- ❌ **No VSCode instances available** (clear user message)
- ❌ **VSCode disconnects during action** (timeout/retry logic)
- ❌ **Actions sent but no response** (timeout handling)
- ❌ **Invalid responses from VSCode** (validation/error handling)
-
-**Status**: Phase 2 Complete! Ready for Phase 3 - Runtime Discovery & Error Handling!
-
-## Phase 2 Implementation Status ✅ COMPLETED
-
-### Server Registration System - DONE
- ✅ **VSCode Registry API** (`/api/vscode/*` endpoints)
-  - ✅ `POST /api/vscode/register` - Register VSCode instance
-  - ✅ `GET /api/vscode/instances` - List registered instances
-  - ✅ `POST /api/vscode/heartbeat/{id}` - Keep registration alive
-  - ✅ `DELETE /api/vscode/unregister/{id}` - Remove registration
-  - ✅ `GET /api/vscode/instance/{id}` - Get specific instance info
-  - ✅ `GET /api/vscode/registry/stats` - Registry statistics
- ✅ **In-memory registry** with automatic stale cleanup (5min timeout)
- ✅ **Pydantic models** for request/response validation
- ✅ **Error handling** with proper HTTP status codes
- ✅ **Integrated with FastAPI** app in `server/app.py`
-
-### Extension Registration Integration - DONE
- ✅ **Modified SocketService** to register on connect
- ✅ **Workspace information** extraction (path, name)
- ✅ **Version information** (VSCode + extension versions)
- ✅ **Capabilities declaration** (file ops, editing, etc.)
- ✅ **Heartbeat system** (30-second intervals)
- ✅ **Automatic unregistration** on disconnect
- ✅ **TypeScript compilation** successful
-
-### What Phase 2 Achieved:
-1. **Server-side registry** tracks all VSCode instances
-2. **Extension auto-registers** when connecting to OpenHands
-3. **Heartbeat mechanism** keeps registrations fresh
-4. **Clean unregistration** when VSCode disconnects
-5. **Discovery API** ready for VsCodeRuntime to use
-
-
-## Phase 3 Implementation Status ✅ COMPLETED
-
-### VsCodeRuntime Discovery & Error Handling - DONE
- ✅ **Removed Constructor Dependencies**: No longer requires `sio_server`/`socket_connection_id` parameters
- ✅ **Dynamic Discovery**: `_get_available_vscode_instances()` queries `/api/vscode/instances`
- ✅ **Connection Validation**: `_validate_vscode_connection()` checks instance health
- ✅ **Auto-Discovery**: `_discover_and_connect()` finds and connects to active VSCode instances
- ✅ **Lazy Connection**: Only connects when actions need to be sent
- ✅ **Connection Recovery**: Automatically reconnects if VSCode instance becomes inactive
- ✅ **Comprehensive Error Handling**: Clear error messages for all failure scenarios
- ✅ **Socket.IO Integration**: Gets `sio_server` from `shared.py` automatically
-
-### Enhanced VsCodeRuntime Features:
- ✅ **Smart Connection Management**: Validates connections before sending actions
- ✅ **Automatic Failover**: Switches to alternative VSCode instances if available
- ✅ **User-Friendly Errors**: Clear messages when no VSCode instances available
- ✅ **Workspace Information**: Logs workspace path and capabilities on connection
- ✅ **Health Monitoring**: Continuous validation of connection status
-
-### What Phase 3 Achieved:
-1. **Eliminated Constructor Dependencies**: VsCodeRuntime works with standard AgentSession parameters
-2. **Implemented Discovery Pattern**: Runtime finds VSCode instances dynamically
-3. **Added Connection Resilience**: Handles disconnections and reconnections gracefully
-4. **Enhanced Error Handling**: Comprehensive error messages and recovery logic
-5. **Completed Lazy Connection**: Full end-to-end lazy connection pattern implementation
-
-**Architecture Complete**: VSCode Extension registers → Server tracks instances → VsCodeRuntime discovers & connects → Actions flow seamlessly!
-
-**Next**: Phase 4 - Unit Testing (Before Integration Testing)
-
-## Phase 4 Unit Testing Plan 🧪
-
-### Testing Strategy
-Following software engineering best practices: **Unit Testing → Integration Testing → End-to-End Testing**
-
-### Testing Patterns Identified:
- **Python**: pytest with unittest.mock for mocking
- **TypeScript**: vitest with mocking capabilities
- **Existing Coverage**: CLI VSCode integration, URL helpers, runtime patterns
-
-### Unit Testing Scope
-
-#### 4.1 Python VsCodeRuntime Tests ✅ TODO
-**File**: `tests/unit/runtime/test_vscode_runtime.py`
-
-**Test Categories**:
-1. **Constructor & Initialization**
-   - ✅ Standard parameters (config, event_stream, sid)
-   - ✅ Optional VSCode parameters (sio_server, socket_connection_id)
-   - ✅ Server URL construction from config
-   - ✅ Default attribute initialization
-
-2. **Discovery System**
-   - ✅ `_get_available_vscode_instances()` - HTTP requests to `/api/vscode/instances`
-   - ✅ `_validate_vscode_connection()` - Connection health checks
-   - ✅ `_discover_and_connect()` - Full discovery workflow
-   - ✅ Error handling for network failures, empty responses
-   - ✅ Instance filtering (active vs inactive)
-
-3. **Connection Management**
-   - ✅ `connect()` method - Discovery and connection establishment
-   - ✅ Socket.IO server retrieval from shared.py
-   - ✅ Connection validation before actions
-   - ✅ Automatic reconnection on connection loss
-   - ✅ Failover to alternative instances
-
-4. **Action Execution**
-   - ✅ `_send_action_to_vscode()` - Core action sending logic
-   - ✅ Event serialization and UUID generation
-   - ✅ Socket.IO emit calls with proper parameters
-   - ✅ Future management and timeout handling
-   - ✅ Error handling for emit failures
-
-5. **Observation Handling**
-   - ✅ `handle_observation_from_vscode()` - Response processing
-   - ✅ Event deserialization and validation
-   - ✅ Future resolution with observations
-   - ✅ Error handling for malformed responses
-
-6. **Runtime Interface Methods**
-   - ✅ All action methods (run, read, write, edit, browse, etc.)
-   - ✅ Async/sync wrapper `_run_async_action()`
-   - ✅ File operations (copy_from, copy_to, list_files)
-   - ✅ MCP configuration and tool calls
-
-#### 4.2 Python Server Routes Tests ✅ COMPLETED
-**File**: `tests/unit/server/test_vscode_routes.py` - **23/23 tests passing (100%)**
-
-**Test Categories Completed**:
-1. **Registration Endpoint** (`POST /api/vscode/register`) - **5/5 tests**
-   - ✅ Valid registration requests with full/minimal data
-   - ✅ Invalid request validation (missing fields, malformed JSON)
-   - ✅ Registry storage and response format
-   - ✅ Empty capabilities handling
-   - ✅ Enhanced Pydantic validation with Field constraints
-
-2. **Discovery Endpoint** (`GET /api/vscode/instances`) - **4/4 tests**
-   - ✅ Empty registry response
-   - ✅ Single and multiple instances response
-   - ✅ Status filtering and data format
-   - ✅ Stale instance cleanup (5-minute threshold)
-
-3. **Instance Management** - **8/8 tests**
-   - ✅ Heartbeat endpoint (`POST /api/vscode/heartbeat/{connection_id}`)
-   - ✅ Unregister endpoint (`DELETE /api/vscode/unregister/{connection_id}`)
-   - ✅ Instance details (`GET /api/vscode/instance/{connection_id}`)
-   - ✅ Registry stats (`GET /api/vscode/registry/stats`)
-   - ✅ Non-existent instance handling for all endpoints
-   - ✅ Complex stats with multiple statuses and recent activity
-
-4. **Error Handling** - **6/6 tests**
-   - ✅ Server error simulations (UUID generation failures)
-   - ✅ Invalid connection IDs and formats
-   - ✅ Malformed request bodies and type validation
-   - ✅ Empty string field validation
-   - ✅ Extremely long field values
-   - ✅ Concurrent modification scenarios
-
-**Technical Achievements**:
- Enhanced validation with `min_length=1` constraints for required fields
- Comprehensive FastAPI TestClient integration
- Mock time.time() for predictable testing
- Registry cleanup fixtures for test isolation
- Realistic error scenarios without problematic mocking
-
-#### 4.3 TypeScript Extension Tests ✅ COMPLETED
-**Files**:
- `openhands/integrations/vscode/src/test/suite/socket-service.test.ts`
- `openhands/integrations/vscode/src/test/suite/runtime-action-handler.test.ts`
-
-**Test Categories Completed**:
-1. **SocketService Class** - **3/3 tests passing**
-   - ✅ Basic functionality and assertions
-   - ✅ VSCode API access and integration
-   - ✅ Fetch mocking capabilities for HTTP testing
-
-2. **RuntimeActionHandler Class** - **3/3 tests passing**
-   - ✅ Basic functionality and assertions
-   - ✅ VSCode workspace API access
-   - ✅ Workspace folder mocking capabilities
-
-3. **Extension Integration** - **1/1 tests passing**
-   - ✅ Extension activation and presence validation
-
-
-#### 4.4 Integration Points Tests ✅ TODO
-**File**: `tests/unit/integration/test_vscode_integration.py`
-
-**Test Categories**:
-1. **Socket.IO Event Flow**
-   - ✅ Event serialization/deserialization compatibility
-   - ✅ Message format validation between Python and TypeScript
-   - ✅ Error event handling
-
-2. **Registry Coordination**
-   - ✅ Extension registration → Runtime discovery flow
-   - ✅ Connection ID consistency
-   - ✅ Workspace metadata propagation
-
-### Testing Implementation Order:
-1. **Phase 4.1**: VsCodeRuntime unit tests (Python) - Foundation
-2. **Phase 4.2**: Server routes unit tests (Python) - API validation
-3. **Phase 4.3**: Extension services unit tests (TypeScript) - Client validation
-4. **Phase 4.4**: Integration points tests - Cross-component validation
-
-### Success Criteria:
- ✅ All unit tests pass with >90% code coverage
- ✅ Mock-based testing isolates components properly
- ✅ Error scenarios comprehensively tested
- ✅ Regression prevention for discovered issues
- ✅ Foundation ready for integration testing
-
-**Current Status**: Phase 4.1 ✅ COMPLETED - VsCodeRuntime unit tests comprehensive coverage achieved
-
-## Phase 4.1 Implementation Status ✅ COMPLETED
-
-### VsCodeRuntime Unit Tests - COMPREHENSIVE COVERAGE
-**File**: `tests/unit/runtime/test_vscode_runtime.py`
-
-#### Action Tests Status:
-**Documented Skips**: Action tests are skipped with comprehensive FIXME comments explaining the technical challenges:
- **Async/Sync Boundary**: `run_action()` is synchronous but calls async methods internally
- **Complex Mocking**: Requires intricate async operation mocking for HTTP and Socket.IO
- **Event Loop Conflicts**: Tests hang due to asyncio event loop management issues
-
-#### Current Test Status: **14/18 tests passing, 4 skipped** (100% implemented, 78% passing)
-
-**Achievements**:
- ✅ Complete constructor and initialization testing
- ✅ Comprehensive discovery system testing with error scenarios
- ✅ Full connection management testing including failover
- ✅ Error handling and recovery logic validation
- ✅ Integration workflow testing (discovery → connection)
- ✅ Proper documentation of complex async testing challenges
-
-**Quality Metrics**:
- **Test Coverage**: All major code paths covered
- **Error Scenarios**: Network failures, empty responses, validation failures
- **Integration**: End-to-end workflow validation
- **Documentation**: Clear FIXME comments for skipped tests
-
-
-## Important Notes
-
-**Git Remote**: We work on the `upstream` remote (https://github.com/All-Hands-AI/OpenHands.git), not origin. Always push to `upstream`!
-
-```bash
-git push upstream vscode-runtime  # ✅ Correct
-git push origin vscode-runtime    # ❌ Wrong remote
-```
--- a/test_coverage_analysis.md
+++ b/test_coverage_analysis.md
@@ -1,90 +0,0 @@
-# VSCode Extension Test Coverage Analysis - COMPLETED ✅
-
-## Final Coverage: 67% (42 lines missing) - ALL TESTS PASSING 🎉
-
-## ✅ COMPLETED: All New Behaviors Fully Tested
-
-### A. Extension Detection Edge Cases - ✅ COMPLETE:
-1. ✅ `--list-extensions` returns non-zero exit code → continues with installation
-2. ✅ `--list-extensions` throws exception → continues with installation
-3. ✅ Extension ID found in middle of list → detects correctly
-4. ✅ Empty stdout from `--list-extensions` → continues with installation
-5. ✅ Extension ID partially matches → does not match (exact match only)
-
-### B. Success Flag Creation - ✅ COMPLETE:
-1. ✅ `_mark_installation_successful()` OSError → logs but continues
-2. ✅ Flag creation succeeds → logs debug message
-3. ✅ Flag creation only on SUCCESS, not on failure
-
-### C. Retry Logic Validation - ✅ COMPLETE:
-1. ✅ Installation fails → does NOT create flag (allows retry)
-2. ✅ Installation succeeds → creates flag (prevents retry)
-3. ✅ Flag exists → skips all operations
-
-### D. New Error Messages - ✅ COMPLETE:
-1. ✅ All methods fail → shows retry message
-2. ✅ Different editors → shows correct editor name in messages
-
-### E. Helper Function Coverage - ✅ COMPLETE:
-1. ✅ `_is_extension_installed()` with various subprocess outcomes
-2. ✅ `_mark_installation_successful()` with various file system states
-
-## ✅ COMPLETED: All Legacy Tests Updated
-
-### Subprocess Call Count Changes - ✅ FIXED:
- ✅ All tests now account for initial `--list-extensions` call
- ✅ Tests expecting 0 subprocess calls now expect 1
- ✅ Tests expecting 1 subprocess call now expect 2
-
-### Flag File Name Changes - ✅ FIXED:
- ✅ Old: `.vscode_extension_install_attempted`
- ✅ New: `.vscode_extension_installed`
-
-### Error Message Changes - ✅ FIXED:
- ✅ Old: "Could not create VS Code extension attempt flag file"
- ✅ New: "Could not create VS Code extension success flag file"
-
-### Windsurf Command Detection - ✅ FIXED:
- ✅ Tests now correctly expect `surf` command (not `windsurf`)
-
-## 📊 FINAL TEST SUITE STATUS:
-
-### Test Results: 31/31 PASSING ✅
- ✅ **17 Core Tests**: All major functionality covered
- ✅ **6 New Comprehensive Tests**: Edge cases and new behavior
- ✅ **8 Updated Legacy Tests**: Fixed for new behavior patterns
-
-### New Tests Added:
-1. ✅ `test_extension_detection_in_middle_of_list`
-2. ✅ `test_extension_detection_partial_match_ignored`
-3. ✅ `test_list_extensions_fails_continues_installation`
-4. ✅ `test_list_extensions_exception_continues_installation`
-5. ✅ `test_mark_installation_successful_os_error`
-6. ✅ `test_installation_failure_no_flag_created`
-
-### Coverage Analysis:
- **67% Total Coverage** (up from 65% initially)
- **42 lines missing** (down from 44 initially)
- **All critical new functionality**: 100% tested
- **All edge cases**: Comprehensively covered
- **All error scenarios**: Fully validated
-
-### Missing Coverage (Non-Critical):
- Lines 19-55: Early exit conditions and environment detection
- Lines 213, 221-222: Some error handling paths
- Lines 294-318: Helper functions in edge cases
-
-## 🎯 MISSION ACCOMPLISHED
-
-**The new extension installation behavior is now comprehensively tested with:**
- ✅ Success-based flagging (no flag on failure = retry allowed)
- ✅ Extension detection via `--list-extensions`
- ✅ Robust error handling and user messaging
- ✅ Complete retry logic validation
- ✅ All edge cases covered
-
-**Quality Assurance:**
- 🧪 31 comprehensive tests
- 📊 67% coverage with all critical paths tested
- 🔄 Full CI/CD pipeline passing
- 📝 All behavioral changes documented and validated
--- a/tests/e2e/test_conversation.py
+++ b/tests/e2e/test_conversation.py
@@ -0,0 +1,604 @@
+"""
+E2E: Conversation start test
+
+This test assumes the GitHub token has already been configured (by the
+settings test) and verifies that a conversation can be started and the
+agent responds to a README line-count question.
+"""
+
+import os
+import time
+
+from playwright.sync_api import Page, expect
+
+
+def get_readme_line_count():
+    """Get the line count of the main README.md file for verification."""
+    current_dir = os.getcwd()
+    if current_dir.endswith('tests/e2e'):
+        repo_root = os.path.abspath(os.path.join(current_dir, '../..'))
+    else:
+        repo_root = current_dir
+
+    readme_path = os.path.join(repo_root, 'README.md')
+    print(f'Looking for README.md at: {readme_path}')
+    try:
+        with open(readme_path, 'r', encoding='utf-8') as f:
+            lines = f.readlines()
+            return len(lines)
+    except (FileNotFoundError, IOError, OSError) as e:
+        print(f'Error reading README.md: {e}')
+        return 0
+
+
+def test_conversation_start(page: Page):
+    """
+    Test starting a conversation with the OpenHands agent:
+    1. Navigate to OpenHands (assumes GitHub token is already configured)
+    2. Select the OpenHands repository
+    3. Click Launch
+    4. Wait for the agent to initialize
+    5. Ask a question about the README.md file
+    6. Verify the agent responds correctly
+    """
+    # Create test-results directory if it doesn't exist
+    os.makedirs('test-results', exist_ok=True)
+
+    expected_line_count = get_readme_line_count()
+    print(f'Expected README.md line count: {expected_line_count}')
+
+    # Navigate to the OpenHands application
+    print('Step 1: Navigating to OpenHands application...')
+    page.goto('http://localhost:12000')
+    page.wait_for_load_state('networkidle', timeout=30000)
+
+    # Take initial screenshot
+    page.screenshot(path='test-results/conv_01_initial_load.png')
+    print('Screenshot saved: conv_01_initial_load.png')
+
+    # Step 2: Select the OpenHands repository
+    print('Step 2: Selecting openhands-agent/OpenHands repository...')
+
+    # Wait for the home screen to load
+    home_screen = page.locator('[data-testid="home-screen"]')
+    expect(home_screen).to_be_visible(timeout=15000)
+    print('Home screen is visible')
+
+    # Look for the repository dropdown/selector
+    repo_dropdown = page.locator('[data-testid="repo-dropdown"]')
+    expect(repo_dropdown).to_be_visible(timeout=15000)
+    print('Repository dropdown is visible')
+
+    # Click on the repository input to open dropdown
+    repo_dropdown.click()
+    page.wait_for_timeout(1000)
+
+    # Type the repository name
+    try:
+        page.keyboard.press('Control+a')  # Select all
+        page.keyboard.type('openhands-agent/OpenHands')
+        print('Used keyboard.type() for React Select component')
+    except Exception as e:
+        print(f'Keyboard input failed: {e}')
+
+    page.wait_for_timeout(2000)  # Wait for search results
+
+    # Try to find and click the repository option
+    option_selectors = [
+        '[data-testid="repo-dropdown"] [role="option"]:has-text("openhands-agent/OpenHands")',
+        '[data-testid="repo-dropdown"] [role="option"]:has-text("OpenHands")',
+        '[data-testid="repo-dropdown"] div[id*="option"]:has-text("openhands-agent/OpenHands")',
+        '[data-testid="repo-dropdown"] div[id*="option"]:has-text("OpenHands")',
+        '[role="option"]:has-text("openhands-agent/OpenHands")',
+        '[role="option"]:has-text("OpenHands")',
+        'div:has-text("openhands-agent/OpenHands"):not([id="aria-results"])',
+        'div:has-text("OpenHands"):not([id="aria-results"])',
+    ]
+
+    option_found = False
+    for selector in option_selectors:
+        try:
+            option = page.locator(selector).first
+            if option.is_visible(timeout=3000):
+                print(f'Found repository option with selector: {selector}')
+                try:
+                    option.click(force=True)
+                    print('Successfully clicked option with force=True')
+                    option_found = True
+                    page.wait_for_timeout(2000)
+                    break
+                except Exception:
+                    continue
+        except Exception:
+            continue
+
+    if not option_found:
+        print(
+            'Could not find repository option in dropdown, trying keyboard navigation'
+        )
+        page.keyboard.press('ArrowDown')
+        page.wait_for_timeout(500)
+        page.keyboard.press('Enter')
+        print('Used keyboard navigation to select option')
+
+    page.screenshot(path='test-results/conv_02_repo_selected.png')
+    print('Screenshot saved: conv_02_repo_selected.png')
+
+    # Step 3: Click Launch button
+    print('Step 3: Clicking Launch button...')
+
+    launch_button = page.locator('[data-testid="repo-launch-button"]')
+    expect(launch_button).to_be_visible(timeout=10000)
+
+    # Wait for the button to be enabled (not disabled)
+    max_wait_attempts = 30
+    button_enabled = False
+    for attempt in range(max_wait_attempts):
+        try:
+            is_disabled = launch_button.is_disabled()
+            if not is_disabled:
+                print(
+                    f'Repository Launch button is now enabled (attempt {attempt + 1})'
+                )
+                button_enabled = True
+                break
+            else:
+                print(
+                    f'Launch button still disabled, waiting... (attempt {attempt + 1}/{max_wait_attempts})'
+                )
+                page.wait_for_timeout(2000)
+        except Exception as e:
+            print(f'Error checking button state (attempt {attempt + 1}): {e}')
+            page.wait_for_timeout(2000)
+
+    try:
+        if button_enabled:
+            launch_button.click()
+            print('Launch button clicked normally')
+        else:
+            print('Launch button still disabled, trying JavaScript force click...')
+            result = page.evaluate("""() => {
+                const button = document.querySelector('[data-testid="repo-launch-button"]');
+                if (button) {
+                    console.log('Found button, removing disabled attribute');
+                    button.removeAttribute('disabled');
+                    console.log('Clicking button');
+                    button.click();
+                    return true;
+                }
+                return false;
+            }""")
+            if result:
+                print('Successfully force-clicked Launch button with JavaScript')
+            else:
+                print('JavaScript could not find the Launch button')
+    except Exception as e:
+        print(f'Error clicking Launch button: {e}')
+        page.screenshot(path='test-results/conv_03_launch_error.png')
+        print('Screenshot saved: conv_03_launch_error.png')
+        raise
+
+    # Step 4: Wait for conversation interface to load
+    print('Step 4: Waiting for conversation interface to load...')
+
+    navigation_timeout = 300000  # 5 minutes
+    check_interval = 10000  # 10 seconds
+
+    page.screenshot(path='test-results/conv_04_after_launch.png')
+    print('Screenshot saved: conv_04_after_launch.png')
+
+    loading_selectors = [
+        '[data-testid="loading-indicator"]',
+        '[data-testid="loading-spinner"]',
+        '.loading-spinner',
+        '.spinner',
+        'div:has-text("Loading...")',
+        'div:has-text("Initializing...")',
+        'div:has-text("Please wait...")',
+    ]
+
+    for selector in loading_selectors:
+        try:
+            loading = page.locator(selector)
+            if loading.is_visible(timeout=5000):
+                print(f'Found loading indicator with selector: {selector}')
+                print('Waiting for loading to complete...')
+                expect(loading).not_to_be_visible(timeout=120000)
+                print('Loading completed')
+                break
+        except Exception:
+            continue
+
+    try:
+        current_url = page.url
+        print(f'Current URL: {current_url}')
+        if '/conversation/' in current_url or '/chat/' in current_url:
+            print('URL indicates conversation page has loaded')
+    except Exception as e:
+        print(f'Error checking URL: {e}')
+
+    start_time = time.time()
+    conversation_loaded = False
+    while time.time() - start_time < navigation_timeout / 1000:
+        try:
+            selectors = [
+                '.scrollbar.flex.flex-col.grow',
+                '[data-testid="chat-input"]',
+                '[data-testid="app-route"]',
+                '[data-testid="conversation-screen"]',
+                '[data-testid="message-input"]',
+                '.conversation-container',
+                '.chat-container',
+                'textarea',
+                'form textarea',
+                'div[role="main"]',
+                'main',
+            ]
+
+            for selector in selectors:
+                try:
+                    element = page.locator(selector)
+                    if element.is_visible(timeout=2000):
+                        print(
+                            f'Found conversation interface element with selector: {selector}'
+                        )
+                        conversation_loaded = True
+                        break
+                except Exception:
+                    continue
+
+            if conversation_loaded:
+                break
+
+            if (time.time() - start_time) % (check_interval / 1000) < 1:
+                elapsed = int(time.time() - start_time)
+                page.screenshot(path=f'test-results/conv_05_waiting_{elapsed}s.png')
+                print(f'Screenshot saved: conv_05_waiting_{elapsed}s.png')
+
+            page.wait_for_timeout(5000)
+        except Exception as e:
+            print(f'Error checking for conversation interface: {e}')
+            page.wait_for_timeout(5000)
+
+    if not conversation_loaded:
+        print('Timed out waiting for conversation interface to load')
+        page.screenshot(path='test-results/conv_06_timeout.png')
+        print('Screenshot saved: conv_06_timeout.png')
+        raise TimeoutError('Timed out waiting for conversation interface to load')
+
+    # Step 5: Wait for agent to initialize
+    print('Step 5: Waiting for agent to initialize...')
+
+    try:
+        chat_input = page.locator('[data-testid="chat-input"]')
+        expect(chat_input).to_be_visible(timeout=60000)
+        submit_button = page.locator('[data-testid="chat-input"] button[type="submit"]')
+        expect(submit_button).to_be_visible(timeout=10000)
+        print('Agent interface is loaded')
+        page.wait_for_timeout(10000)
+    except Exception as e:
+        print(f'Could not confirm agent interface is loaded: {e}')
+
+    page.screenshot(path='test-results/conv_07_agent_ready.png')
+    print('Screenshot saved: conv_07_agent_ready.png')
+
+    # Step 6: Wait for agent to be fully ready for input
+    print('Step 6: Waiting for agent to be fully ready for input...')
+
+    max_wait_time = 480
+    start_time = time.time()
+    agent_ready = False
+    print(f'Waiting up to {max_wait_time} seconds for agent to be ready...')
+
+    while time.time() - start_time < max_wait_time:
+        elapsed = int(time.time() - start_time)
+        if elapsed % 30 == 0 and elapsed > 0:
+            page.screenshot(path=f'test-results/conv_waiting_{elapsed}s.png')
+            print(f'Screenshot saved: conv_waiting_{elapsed}s.png (waiting {elapsed}s)')
+
+        try:
+            status_messages = []
+            status_bar_selector = '.bg-base-secondary .text-stone-400'
+            try:
+                status_elements = page.locator(status_bar_selector)
+                if status_elements.count() > 0:
+                    for i in range(status_elements.count()):
+                        text = status_elements.nth(i).text_content()
+                        if text and text.strip():
+                            status_messages.append(text.strip())
+            except Exception:
+                pass
+
+            ready_indicators = [
+                'div:has-text("Agent is ready")',
+                'div:has-text("Waiting for user input")',
+                'div:has-text("Awaiting input")',
+                'div:has-text("Task completed")',
+                'div:has-text("Agent has finished")',
+            ]
+
+            input_ready = False
+            submit_ready = False
+            try:
+                input_field = page.locator('[data-testid="chat-input"] textarea')
+                submit_button = page.locator(
+                    '[data-testid="chat-input"] button[type="submit"]'
+                )
+                if (
+                    input_field.is_visible(timeout=2000)
+                    and input_field.is_enabled(timeout=2000)
+                    and submit_button.is_visible(timeout=2000)
+                    and submit_button.is_enabled(timeout=2000)
+                ):
+                    print(
+                        'Chat input field and submit button are both visible and enabled'
+                    )
+                    input_ready = True
+                    submit_ready = True
+            except Exception:
+                pass
+
+            connecting_or_starting = any(
+                msg
+                for msg in status_messages
+                if 'connecting' in msg.lower()
+                or 'starting' in msg.lower()
+                or 'runtime to start' in msg.lower()
+            )
+
+            has_ready_indicator = False
+            for indicator in ready_indicators:
+                try:
+                    element = page.locator(indicator)
+                    if element.is_visible(timeout=2000):
+                        print(f'Agent appears ready (found: {indicator})')
+                        has_ready_indicator = True
+                        break
+                except Exception:
+                    continue
+
+            if (
+                (has_ready_indicator or not connecting_or_starting)
+                and input_ready
+                and submit_ready
+            ):
+                print(
+                    '✅ Agent is ready for user input - input field and submit button are enabled'
+                )
+                agent_ready = True
+                break
+            elif (
+                not connecting_or_starting
+                and not status_messages
+                and input_ready
+                and submit_ready
+            ):
+                print(
+                    'No status messages found and input is ready, agent appears ready...'
+                )
+                agent_ready = True
+                break
+        except Exception as e:
+            print(f'Error checking agent ready state: {e}')
+
+        page.wait_for_timeout(2000)
+
+    if not agent_ready:
+        page.screenshot(path='test-results/conv_timeout_waiting_for_agent.png')
+        raise AssertionError(
+            f'Agent did not become ready for input within {max_wait_time} seconds'
+        )
+
+    # Step 7: Ask a question about the README.md file
+    print('Step 7: Asking question about README.md file...')
+
+    input_selectors = [
+        '[data-testid="chat-input"] textarea',
+        '[data-testid="message-input"]',
+        'textarea',
+        'form textarea',
+        'input[type="text"]',
+        '[placeholder*="message"]',
+        '[placeholder*="question"]',
+        '[placeholder*="ask"]',
+        '[contenteditable="true"]',
+    ]
+
+    message_input = None
+    for selector in input_selectors:
+        try:
+            input_element = page.locator(selector)
+            if input_element.is_visible(timeout=5000):
+                print(f'Found message input with selector: {selector}')
+                message_input = input_element
+                break
+        except Exception:
+            continue
+
+    if not message_input:
+        print('Could not find message input, trying to reload the page')
+        page.screenshot(path='test-results/conv_08_no_input_found.png')
+        print('Screenshot saved: conv_08_no_input_found.png')
+
+        try:
+            print('Reloading the page...')
+            page.reload()
+            page.wait_for_load_state('networkidle', timeout=30000)
+            print('Page reloaded')
+            for selector in input_selectors:
+                try:
+                    input_element = page.locator(selector)
+                    if input_element.is_visible(timeout=5000):
+                        print(
+                            f'Found message input after reload with selector: {selector}'
+                        )
+                        message_input = input_element
+                        break
+                except Exception:
+                    continue
+        except Exception as e:
+            print(f'Error reloading page: {e}')
+
+        if not message_input:
+            print('Still could not find message input, taking final screenshot')
+            page.screenshot(path='test-results/conv_09_reload_failed.png')
+            print('Screenshot saved: conv_09_reload_failed.png')
+            raise AssertionError('Could not find message input field after reload')
+
+    message_input.fill(
+        'How many lines are there in the README.md file in the root directory of this repository? Please use wc -l README.md to count the lines.'
+    )
+    print('Entered question about README.md line count')
+
+    submit_selectors = [
+        '[data-testid="chat-input"] button[type="submit"]',
+        'button[type="submit"]',
+        'button:has-text("Send")',
+        'button:has-text("Submit")',
+        'button svg[data-testid="send-icon"]',
+        'button.send-button',
+        'form button',
+        'button:right-of(textarea)',
+        'button:right-of(input[type="text"])',
+    ]
+
+    submit_button = None
+    for selector in submit_selectors:
+        try:
+            button_element = page.locator(selector)
+            if button_element.is_visible(timeout=5000):
+                print(f'Found submit button with selector: {selector}')
+                submit_button = button_element
+                break
+        except Exception:
+            continue
+
+    button_enabled = False
+    if submit_button:
+        max_wait_time = 60
+        start_time = time.time()
+        while time.time() - start_time < max_wait_time:
+            try:
+                if not submit_button.is_disabled():
+                    button_enabled = True
+                    print('Submit button is enabled')
+                    break
+                print(
+                    f'Waiting for submit button to be enabled... ({int(time.time() - start_time)}s)'
+                )
+            except Exception as e:
+                print(f'Error checking if button is disabled: {e}')
+            page.wait_for_timeout(2000)
+
+    if not submit_button or not button_enabled:
+        print('Submit button not found or never became enabled, trying alternatives')
+        try:
+            message_input.press('Enter')
+            print('Pressed Enter key to submit')
+            button_enabled = True
+        except Exception as e:
+            print(f'Error pressing Enter key: {e}')
+            if submit_button:
+                try:
+                    page.evaluate("""() => {
+                        const button = document.querySelector('[data-testid="chat-input"] button[type="submit"]');
+                        if (button) {
+                            button.removeAttribute('disabled');
+                            button.click();
+                            return true;
+                        }
+                        return false;
+                    }""")
+                    print('Used JavaScript to force click submit button')
+                    button_enabled = True
+                except Exception as e2:
+                    print(f'JavaScript force click failed: {e2}')
+        if not button_enabled:
+            page.screenshot(path='test-results/conv_09_submit_failed.png')
+            print('Screenshot saved: conv_09_submit_failed.png')
+            raise RuntimeError('Could not submit message')
+    else:
+        submit_button.click()
+
+    print('Clicked submit button')
+
+    page.screenshot(path='test-results/conv_08_question_sent.png')
+    print('Screenshot saved: conv_08_question_sent.png')
+
+    print('Step 8: Waiting for agent response to README question...')
+
+    response_wait_time = 180
+    response_start_time = time.time()
+
+    while time.time() - response_start_time < response_wait_time:
+        elapsed = int(time.time() - response_start_time)
+
+        if elapsed % 30 == 0 and elapsed > 0:
+            page.screenshot(path=f'test-results/conv_response_wait_{elapsed}s.png')
+            print(
+                f'Screenshot saved: conv_response_wait_{elapsed}s.png (waiting {elapsed}s for response)'
+            )
+
+        try:
+            agent_messages = page.locator('[data-testid="agent-message"]').all()
+            if elapsed % 30 == 0:
+                print(f'Found {len(agent_messages)} agent messages')
+
+            for i, msg in enumerate(agent_messages):
+                try:
+                    content = msg.text_content()
+                    if content and len(content.strip()) > 10:
+                        content_lower = content.lower()
+                        import re
+
+                        line_count_pattern = r'\b(\d{3})\b'
+                        line_counts = re.findall(line_count_pattern, content)
+                        if (
+                            (
+                                str(expected_line_count) in content
+                                and 'readme' in content_lower
+                            )
+                            or (
+                                'line' in content_lower
+                                and 'readme' in content_lower
+                                and any(
+                                    num in content
+                                    for num in ['183', str(expected_line_count)]
+                                )
+                            )
+                            or (
+                                'line' in content_lower
+                                and 'readme' in content_lower
+                                and line_counts
+                                and any(100 <= int(num) <= 300 for num in line_counts)
+                            )
+                        ):
+                            print(
+                                '✅ Found agent response about README.md with line count!'
+                            )
+                            page.screenshot(
+                                path='test-results/conv_09_agent_response.png'
+                            )
+                            print('Screenshot saved: conv_09_agent_response.png')
+                            page.screenshot(path='test-results/conv_10_final_state.png')
+                            print('Screenshot saved: conv_10_final_state.png')
+                            print(
+                                '✅ Test completed successfully - agent provided correct README line count'
+                            )
+                            return
+                except Exception as e:
+                    print(f'Error processing agent message {i}: {e}')
+                    continue
+        except Exception as e:
+            print(f'Error checking for agent messages: {e}')
+
+        page.wait_for_timeout(5000)
+
+    print('❌ Did not find agent response with README line count within time limit')
+    page.screenshot(path='test-results/conv_09_agent_response.png')
+    print('Screenshot saved: conv_09_agent_response.png')
+    page.screenshot(path='test-results/conv_10_final_state.png')
+    print('Screenshot saved: conv_10_final_state.png')
+    raise AssertionError(
+        'Agent response did not include README line count within time limit'
+    )
--- a/tests/e2e/test_e2e_workflow.py
+++ b/tests/e2e/test_e2e_workflow.py
--- a/tests/e2e/test_settings.py
+++ b/tests/e2e/test_settings.py
@@ -0,0 +1,290 @@
+"""
+E2E: Settings configuration test (GitHub token)
+
+This test navigates to OpenHands, configures the LLM API key if prompted,
+then ensures the GitHub token is set in Settings → Integrations and that the
+home screen shows the repository selector.
+"""
+
+import os
+
+from playwright.sync_api import Page, expect
+
+
+def test_github_token_configuration(page: Page):
+    """
+    Test the GitHub token configuration flow:
+    1. Navigate to OpenHands
+    2. Configure LLM API key if needed
+    3. Check if GitHub token is already configured
+    4. If not, navigate to settings and configure it
+    5. Verify the token is saved and repository selection is available
+    """
+    # Create test-results directory if it doesn't exist
+    os.makedirs('test-results', exist_ok=True)
+
+    # Navigate to the OpenHands application
+    print('Step 1: Navigating to OpenHands application...')
+    page.goto('http://localhost:12000')
+    page.wait_for_load_state('networkidle', timeout=30000)
+
+    # Take initial screenshot
+    page.screenshot(path='test-results/token_01_initial_load.png')
+    print('Screenshot saved: token_01_initial_load.png')
+
+    # Step 1.5: Handle any initial modals that might appear (LLM API key configuration)
+    try:
+        # Check for AI Provider Configuration modal
+        config_modal = page.locator('text=AI Provider Configuration')
+        if config_modal.is_visible(timeout=5000):
+            print('AI Provider Configuration modal detected')
+
+            # Fill in the LLM API key if available
+            llm_api_key_input = page.locator('[data-testid="llm-api-key-input"]')
+            if llm_api_key_input.is_visible(timeout=3000):
+                llm_api_key = os.getenv('LLM_API_KEY', 'test-key')
+                llm_api_key_input.fill(llm_api_key)
+                print(f'Filled LLM API key (length: {len(llm_api_key)})')
+
+            # Click the Save button
+            save_button = page.locator('button:has-text("Save")')
+            if save_button.is_visible(timeout=3000):
+                save_button.click()
+                page.wait_for_timeout(2000)
+                print('Saved LLM API key configuration')
+
+        # Check for Privacy Preferences modal
+        privacy_modal = page.locator('text=Your Privacy Preferences')
+        if privacy_modal.is_visible(timeout=5000):
+            print('Privacy Preferences modal detected')
+            confirm_button = page.locator('button:has-text("Confirm Preferences")')
+            if confirm_button.is_visible(timeout=3000):
+                confirm_button.click()
+                page.wait_for_timeout(2000)
+                print('Confirmed privacy preferences')
+    except Exception as e:
+        print(f'Error handling initial modals: {e}')
+        page.screenshot(path='test-results/token_01_5_modal_error.png')
+        print('Screenshot saved: token_01_5_modal_error.png')
+
+    # Step 2: Check if GitHub token is already configured or needs to be set
+    print('Step 2: Checking if GitHub token is configured...')
+
+    try:
+        # First, check if we're already on the home screen with repository selection
+        # This means the GitHub token is already configured in ~/.openhands/settings.json
+        connect_to_provider = page.locator('text=Connect to a Repository')
+
+        if connect_to_provider.is_visible(timeout=3000):
+            print('Found "Connect to a Repository" section')
+
+            # Check if we need to configure a provider (GitHub token)
+            navigate_to_settings_button = page.locator(
+                '[data-testid="navigate-to-settings-button"]'
+            )
+
+            if navigate_to_settings_button.is_visible(timeout=3000):
+                print('GitHub token not configured. Need to navigate to settings...')
+
+                # Click the Settings button to navigate to the settings page
+                navigate_to_settings_button.click()
+                page.wait_for_load_state('networkidle', timeout=10000)
+                page.wait_for_timeout(3000)  # Wait for navigation to complete
+
+                # We should now be on the /settings/integrations page
+                print('Navigated to settings page, looking for GitHub token input...')
+
+                # Check if we're on the settings page with the integrations tab
+                settings_screen = page.locator('[data-testid="settings-screen"]')
+                if settings_screen.is_visible(timeout=5000):
+                    print('Settings screen is visible')
+
+                    # Make sure we're on the Integrations tab
+                    integrations_tab = page.locator('text=Integrations')
+                    if integrations_tab.is_visible(timeout=3000):
+                        # Check if we need to click the tab
+                        if not page.url.endswith('/settings/integrations'):
+                            print('Clicking Integrations tab...')
+                            integrations_tab.click()
+                            page.wait_for_load_state('networkidle')
+                            page.wait_for_timeout(2000)
+
+                    # Now look for the GitHub token input
+                    github_token_input = page.locator(
+                        '[data-testid="github-token-input"]'
+                    )
+                    if github_token_input.is_visible(timeout=5000):
+                        print('Found GitHub token input field')
+
+                        # Fill in the GitHub token from environment variable
+                        github_token = os.getenv('GITHUB_TOKEN', '')
+                        if github_token:
+                            # Clear the field first, then fill it
+                            github_token_input.clear()
+                            github_token_input.fill(github_token)
+                            print(
+                                f'Filled GitHub token from environment variable (length: {len(github_token)})'
+                            )
+
+                            # Verify the token was filled
+                            filled_value = github_token_input.input_value()
+                            if filled_value:
+                                print(
+                                    f'Token field now contains value of length: {len(filled_value)}'
+                                )
+                            else:
+                                print(
+                                    'WARNING: Token field appears to be empty after filling'
+                                )
+
+                            # Look for the Save Changes button and ensure it's enabled
+                            save_button = page.locator('[data-testid="submit-button"]')
+                            if save_button.is_visible(timeout=3000):
+                                # Check if button is enabled
+                                is_disabled = save_button.is_disabled()
+                                print(
+                                    f'Save Changes button found, disabled: {is_disabled}'
+                                )
+
+                                if not is_disabled:
+                                    print('Clicking Save Changes button...')
+                                    save_button.click()
+
+                                    # Wait for the save operation to complete
+                                    try:
+                                        # Wait for the button to show "Saving..." (if it does)
+                                        page.wait_for_timeout(1000)
+
+                                        # Wait for the save to complete - button should be disabled again
+                                        page.wait_for_function(
+                                            'document.querySelector(\'[data-testid="submit-button"]\').disabled === true',
+                                            timeout=10000,
+                                        )
+                                        print(
+                                            'Save operation completed - form is now clean'
+                                        )
+                                    except Exception:
+                                        print(
+                                            'Save operation completed (timeout waiting for form clean state)'
+                                        )
+
+                                    # Navigate back to home page after successful save
+                                    print('Navigating back to home page...')
+                                    page.goto('http://localhost:12000')
+                                    page.wait_for_load_state('networkidle')
+                                    page.wait_for_timeout(
+                                        5000
+                                    )  # Wait longer for providers to be updated
+                                else:
+                                    print(
+                                        'Save Changes button is disabled - form may be invalid'
+                                    )
+                            else:
+                                print('Save Changes button not found')
+                        else:
+                            print('No GitHub token found in environment variables')
+                    else:
+                        print('GitHub token input field not found on settings page')
+                        # Take a screenshot to see what's on the page
+                        page.screenshot(path='test-results/token_02_settings_debug.png')
+                        print('Debug screenshot saved: token_02_settings_debug.png')
+                else:
+                    print('Settings screen not found')
+            else:
+                # Branch 2: GitHub token is already configured, repository selection is available
+                print(
+                    'GitHub token is already configured, repository selection is available'
+                )
+
+                # Check if we need to update the token by going to settings manually
+                settings_button = page.locator('button:has-text("Settings")')
+                if settings_button.is_visible(timeout=3000):
+                    print(
+                        'Settings button found, clicking to navigate to settings page...'
+                    )
+                    settings_button.click()
+                    page.wait_for_load_state('networkidle', timeout=10000)
+                    page.wait_for_timeout(3000)  # Wait for navigation to complete
+
+                    # Navigate to the Integrations tab
+                    integrations_tab = page.locator('text=Integrations')
+                    if integrations_tab.is_visible(timeout=3000):
+                        print('Clicking Integrations tab...')
+                        integrations_tab.click()
+                        page.wait_for_load_state('networkidle')
+                        page.wait_for_timeout(2000)
+
+                        # Now look for the GitHub token input
+                        github_token_input = page.locator(
+                            '[data-testid="github-token-input"]'
+                        )
+                        if github_token_input.is_visible(timeout=5000):
+                            print('Found GitHub token input field')
+
+                            # Fill in the GitHub token from environment variable
+                            github_token = os.getenv('GITHUB_TOKEN', '')
+                            if github_token:
+                                # Clear the field first, then fill it
+                                github_token_input.clear()
+                                github_token_input.fill(github_token)
+                                print(
+                                    f'Filled GitHub token from environment variable (length: {len(github_token)})'
+                                )
+
+                                # Look for the Save Changes button and ensure it's enabled
+                                save_button = page.locator(
+                                    '[data-testid="submit-button"]'
+                                )
+                                if (
+                                    save_button.is_visible(timeout=3000)
+                                    and not save_button.is_disabled()
+                                ):
+                                    print('Clicking Save Changes button...')
+                                    save_button.click()
+                                    page.wait_for_timeout(3000)
+
+                                # Navigate back to home page
+                                print('Navigating back to home page...')
+                                page.goto('http://localhost:12000')
+                                page.wait_for_load_state('networkidle')
+                                page.wait_for_timeout(3000)
+                        else:
+                            print(
+                                'GitHub token input field not found, going back to home page'
+                            )
+                            page.goto('http://localhost:12000')
+                            page.wait_for_load_state('networkidle')
+                    else:
+                        print('Integrations tab not found, going back to home page')
+                        page.goto('http://localhost:12000')
+                        page.wait_for_load_state('networkidle')
+                else:
+                    print('Settings button not found, continuing with existing token')
+        else:
+            print('Could not find "Connect to a Repository" section')
+
+        page.screenshot(path='test-results/token_03_after_settings.png')
+        print('Screenshot saved: token_03_after_settings.png')
+
+    except Exception as e:
+        print(f'Error checking GitHub token configuration: {e}')
+        page.screenshot(path='test-results/token_04_error.png')
+        print('Screenshot saved: token_04_error.png')
+
+    # Step 3: Verify we're back on the home screen with repository selection available
+    print('Step 3: Verifying repository selection is available...')
+
+    # Wait for the home screen to load
+    home_screen = page.locator('[data-testid="home-screen"]')
+    expect(home_screen).to_be_visible(timeout=15000)
+    print('Home screen is visible')
+
+    # Look for the repository dropdown/selector
+    repo_dropdown = page.locator('[data-testid="repo-dropdown"]')
+    expect(repo_dropdown).to_be_visible(timeout=15000)
+    print('Repository dropdown is visible')
+
+    # Success - we've verified the GitHub token configuration
+    print('GitHub token configuration verified successfully')
+    page.screenshot(path='test-results/token_05_success.png')
+    print('Screenshot saved: token_05_success.png')
--- a/tests/runtime/conftest.py
+++ b/tests/runtime/conftest.py
@@ -16,7 +16,6 @@ from openhands.runtime.impl.docker.docker_runtime import DockerRuntime
 from openhands.runtime.impl.local.local_runtime import LocalRuntime
 from openhands.runtime.impl.remote.remote_runtime import RemoteRuntime
 from openhands.runtime.plugins import AgentSkillsRequirement, JupyterRequirement
-from openhands.runtime.vscode.vscode_runtime import VsCodeRuntime
 from openhands.storage import get_file_store
 from openhands.utils.async_utils import call_async_from_sync

@@ -131,8 +130,6 @@ def get_runtime_classes() -> list[type[Runtime]]:
        return [RemoteRuntime]
    elif runtime.lower() == 'cli':
        return [CLIRuntime]
-    elif runtime.lower() == 'vscode':
-        return [VsCodeRuntime]
    else:
        raise ValueError(f'Invalid runtime: {runtime}')

--- a/tests/unit/runtime/test_vscode_runtime.py
+++ b/tests/unit/runtime/test_vscode_runtime.py
@@ -1,423 +0,0 @@
-# Unit tests for VsCodeRuntime
-
-from unittest.mock import AsyncMock, Mock, patch
-
-import pytest
-
-from openhands.core.config import OpenHandsConfig
-from openhands.events.action import CmdRunAction, FileReadAction
-from openhands.events.observation import (
-    CmdOutputObservation,
-    ErrorObservation,
-    FileReadObservation,
-)
-from openhands.events.stream import EventStream
-from openhands.runtime.vscode.vscode_runtime import VsCodeRuntime
-
-
-class TestVsCodeRuntimeConstructor:
-    """Test VsCodeRuntime constructor and initialization."""
-
-    def test_constructor_no_dependencies(self):
-        """Test that VsCodeRuntime can be constructed without sio_server/socket_connection_id."""
-        config = OpenHandsConfig()
-        event_stream = Mock(spec=EventStream)
-
-        # Should not raise any exceptions
-        runtime = VsCodeRuntime(config=config, event_stream=event_stream)
-
-        assert runtime.config is not None
-        assert runtime.sid == 'default'
-        assert runtime.plugins == []
-        assert runtime.env_vars == {}
-        assert runtime.sio_server is None
-        assert runtime.socket_connection_id is None
-        assert runtime._running_actions == {}
-        assert runtime._server_url == 'http://localhost:3000'
-
-    def test_constructor_with_optional_params(self):
-        """Test constructor with optional parameters."""
-        config = OpenHandsConfig()
-        event_stream = Mock(spec=EventStream)
-
-        runtime = VsCodeRuntime(
-            config=config, event_stream=event_stream, sid='test_sid', plugins=[]
-        )
-
-        assert runtime.config is not None
-        assert runtime.event_stream is not None
-        assert runtime.sid == 'test_sid'
-
-
-class TestVsCodeRuntimeDiscovery:
-    """Test VSCode instance discovery system."""
-
-    @pytest.fixture
-    def runtime(self):
-        config = OpenHandsConfig()
-        event_stream = Mock(spec=EventStream)
-        return VsCodeRuntime(config=config, event_stream=event_stream)
-
-    @pytest.mark.asyncio
-    async def test_discover_vscode_instances_success(self, runtime):
-        """Test successful discovery of VSCode instances."""
-        mock_response_data = [
-            {
-                'id': 'vscode-1',
-                'name': 'VSCode Instance 1',
-                'port': 3001,
-                'status': 'active',
-                'workspace': '/path/to/workspace1',
-            },
-            {
-                'id': 'vscode-2',
-                'name': 'VSCode Instance 2',
-                'port': 3002,
-                'status': 'active',
-                'workspace': '/path/to/workspace2',
-            },
-        ]
-
-        with patch('aiohttp.ClientSession.get') as mock_get:
-            mock_response = AsyncMock()
-            mock_response.status = 200
-            mock_response.json = AsyncMock(return_value=mock_response_data)
-            mock_get.return_value.__aenter__.return_value = mock_response
-
-            instances = await runtime._get_available_vscode_instances()
-
-            assert len(instances) == 2
-            assert instances[0]['id'] == 'vscode-1'
-            assert instances[1]['id'] == 'vscode-2'
-
-    @pytest.mark.asyncio
-    async def test_discover_vscode_instances_server_error(self, runtime):
-        """Test discovery when server returns error."""
-        with patch('aiohttp.ClientSession.get') as mock_get:
-            mock_response = AsyncMock()
-            mock_response.status = 500
-            mock_get.return_value.__aenter__.return_value = mock_response
-
-            instances = await runtime._get_available_vscode_instances()
-
-            assert instances == []
-
-    @pytest.mark.asyncio
-    async def test_discover_vscode_instances_connection_error(self, runtime):
-        """Test discovery when connection fails."""
-        with patch('aiohttp.ClientSession.get') as mock_get:
-            mock_get.side_effect = Exception('Connection failed')
-
-            instances = await runtime._get_available_vscode_instances()
-
-            assert instances == []
-
-    @pytest.mark.asyncio
-    async def test_discovery_multiple_calls(self, runtime):
-        """Test that multiple discovery calls work correctly."""
-        mock_response_data = [{'id': 'vscode-1', 'port': 3001}]
-
-        with patch('aiohttp.ClientSession.get') as mock_get:
-            mock_response = AsyncMock()
-            mock_response.status = 200
-            mock_response.json = AsyncMock(return_value=mock_response_data)
-            mock_get.return_value.__aenter__.return_value = mock_response
-
-            # First call should make HTTP request
-            instances1 = await runtime._get_available_vscode_instances()
-            assert mock_get.call_count == 1
-            assert len(instances1) == 1
-
-            # Second call should make another HTTP request (no caching)
-            instances2 = await runtime._get_available_vscode_instances()
-            assert mock_get.call_count == 2  # Additional call made
-            assert instances1 == instances2
-
-
-class TestVsCodeRuntimeConnection:
-    """Test VSCode connection management."""
-
-    @pytest.fixture
-    def runtime(self):
-        config = OpenHandsConfig()
-        event_stream = Mock(spec=EventStream)
-        return VsCodeRuntime(config=config, event_stream=event_stream)
-
-    @pytest.mark.asyncio
-    async def test_validate_connection_success(self, runtime):
-        """Test successful connection validation."""
-        connection_id = 'vscode-1'
-
-        with patch('aiohttp.ClientSession.get') as mock_get:
-            mock_response = AsyncMock()
-            mock_response.status = 200
-            mock_response.json = AsyncMock(return_value={'status': 'active'})
-            mock_get.return_value.__aenter__.return_value = mock_response
-
-            is_valid = await runtime._validate_vscode_connection(connection_id)
-
-            assert is_valid is True
-
-    @pytest.mark.asyncio
-    async def test_validate_connection_failure(self, runtime):
-        """Test connection validation failure."""
-        connection_id = 'vscode-1'
-
-        with patch('aiohttp.ClientSession.get') as mock_get:
-            mock_get.side_effect = Exception('Connection failed')
-
-            is_valid = await runtime._validate_vscode_connection(connection_id)
-
-            assert is_valid is False
-
-    @pytest.mark.asyncio
-    async def test_discover_and_connect_success(self, runtime):
-        """Test successful connection establishment."""
-        mock_instances = [
-            {
-                'id': 'vscode-1',
-                'port': 3001,
-                'status': 'active',
-                'connection_id': 'conn-1',
-            },
-            {
-                'id': 'vscode-2',
-                'port': 3002,
-                'status': 'active',
-                'connection_id': 'conn-2',
-            },
-        ]
-
-        with (
-            patch.object(
-                runtime, '_get_available_vscode_instances', return_value=mock_instances
-            ),
-            patch('openhands.server.shared.sio') as mock_sio,
-        ):
-            runtime.sio_server = mock_sio
-            result = await runtime._discover_and_connect()
-
-            assert result is True
-
-    @pytest.mark.asyncio
-    async def test_discover_and_connect_no_sio_server(self, runtime):
-        """Test connection when sio_server import fails."""
-        with patch(
-            'openhands.server.shared.sio', side_effect=ImportError('Module not found')
-        ):
-            result = await runtime._discover_and_connect()
-
-            assert result is False
-
-    @pytest.mark.asyncio
-    async def test_discover_and_connect_no_instances(self, runtime):
-        """Test connection when no instances are discovered."""
-        with (
-            patch.object(runtime, '_get_available_vscode_instances', return_value=[]),
-            patch('openhands.server.shared.sio') as mock_sio,
-        ):
-            runtime.sio_server = mock_sio
-            result = await runtime._discover_and_connect()
-
-            assert result is False
-
-
-class TestVsCodeRuntimeActions:
-    """Test action execution in VsCodeRuntime."""
-
-    # FIXME: Action tests are currently skipped due to complex async/sync boundary issues.
-    # The run_action() method is synchronous but calls async methods internally (_send_action_to_vscode).
-    # This creates complex async mocking requirements for HTTP calls and Socket.IO operations,
-    # causing tests to hang due to event loop conflicts. Need to properly mock all async operations
-    # and handle the sync/async boundary correctly.
-
-    @pytest.fixture
-    def runtime(self):
-        config = OpenHandsConfig()
-        event_stream = Mock(spec=EventStream)
-        runtime = VsCodeRuntime(config=config, event_stream=event_stream)
-        runtime._current_connection = {'id': 'vscode-1', 'port': 3001}
-        return runtime
-
-    @pytest.mark.skip(
-        reason='FIXME: Async/sync boundary mocking issues causing tests to hang'
-    )
-    def test_run_action_cmd_success(self, runtime):
-        """Test successful command execution."""
-        action = CmdRunAction(command="echo 'hello'")
-
-        # Mock the connection setup
-        runtime.socket_connection_id = 'test-connection'
-
-        with (
-            patch('aiohttp.ClientSession.post') as mock_post,
-            patch.object(
-                runtime,
-                '_validate_vscode_connection',
-                new_callable=AsyncMock,
-                return_value=True,
-            ),
-        ):
-            mock_response = AsyncMock()
-            mock_response.status = 200
-            mock_response.json = AsyncMock(
-                return_value={'exit_code': 0, 'output': 'hello\n'}
-            )
-            mock_post.return_value.__aenter__.return_value = mock_response
-
-            observation = runtime.run_action(action)
-
-            assert isinstance(observation, CmdOutputObservation)
-            assert observation.exit_code == 0
-            assert observation.content == 'hello\n'
-
-    @pytest.mark.skip(
-        reason='FIXME: Async/sync boundary mocking issues causing tests to hang'
-    )
-    def test_run_action_file_read_success(self, runtime):
-        """Test successful file read."""
-        action = FileReadAction(path='/test/file.txt')
-
-        # Mock the connection setup
-        runtime.socket_connection_id = 'test-connection'
-
-        with patch('aiohttp.ClientSession.post') as mock_post:
-            mock_response = AsyncMock()
-            mock_response.status = 200
-            mock_response.json = AsyncMock(
-                return_value={'content': 'file content here'}
-            )
-            mock_post.return_value.__aenter__.return_value = mock_response
-
-            observation = runtime.run_action(action)
-
-            assert isinstance(observation, FileReadObservation)
-            assert observation.content == 'file content here'
-
-    @pytest.mark.skip(
-        reason='FIXME: Async/sync boundary mocking issues causing tests to hang'
-    )
-    def test_run_action_connection_error(self, runtime):
-        """Test action execution when connection fails."""
-        action = CmdRunAction(command="echo 'hello'")
-
-        # No connection setup - should trigger discovery and fail
-        with patch.object(runtime, '_get_available_vscode_instances', return_value=[]):
-            observation = runtime.run_action(action)
-
-            assert isinstance(observation, ErrorObservation)
-            assert 'No VSCode instances' in observation.content
-
-    @pytest.mark.skip(
-        reason='FIXME: Async/sync boundary mocking issues causing tests to hang'
-    )
-    def test_run_action_with_valid_connection(self, runtime):
-        """Test action execution with a valid connection."""
-        action = CmdRunAction(command="echo 'hello'")
-
-        # Set up a valid connection
-        runtime.socket_connection_id = 'test-connection'
-
-        with patch('aiohttp.ClientSession.post') as mock_post:
-            mock_response = AsyncMock()
-            mock_response.status = 200
-            mock_response.json = AsyncMock(
-                return_value={'exit_code': 0, 'output': 'hello\n'}
-            )
-            mock_post.return_value.__aenter__.return_value = mock_response
-
-            observation = runtime.run_action(action)
-
-            assert isinstance(observation, CmdOutputObservation)
-            assert observation.exit_code == 0
-            assert observation.content == 'hello\n'
-
-
-class TestVsCodeRuntimeErrorHandling:
-    """Test error handling and recovery in VsCodeRuntime."""
-
-    @pytest.fixture
-    def runtime(self):
-        config = OpenHandsConfig()
-        event_stream = Mock(spec=EventStream)
-        return VsCodeRuntime(config=config, event_stream=event_stream)
-
-    def test_comprehensive_error_messages(self, runtime):
-        """Test that error messages are comprehensive and helpful."""
-        action = CmdRunAction(command='test')
-
-        with patch.object(runtime, '_discover_and_connect') as mock_discover:
-            mock_discover.return_value = False  # Connection failed
-
-            observation = runtime.run_action(action)
-
-            assert isinstance(observation, ErrorObservation)
-            assert 'No VSCode instances' in observation.content
-
-    def test_recovery_logic(self, runtime):
-        """Test recovery logic when connections fail."""
-        # Set up initial connection
-        runtime._current_connection = {'id': 'vscode-1', 'port': 3001}
-        runtime.socket_connection_id = 'vscode-1'
-
-        action = CmdRunAction(command='test')
-
-        # Mock connection validation to fail first, then succeed
-        with (
-            patch.object(runtime, '_validate_vscode_connection') as mock_validate,
-            patch.object(runtime, '_discover_and_connect') as mock_discover,
-        ):
-            # First validation fails (connection lost)
-            mock_validate.return_value = False
-            # Discovery succeeds with new connection
-            mock_discover.return_value = True
-            # Mock Socket.IO server directly
-            runtime.sio_server = Mock()
-
-            # This should trigger recovery
-            runtime.run_action(action)
-
-            # Should have attempted discovery (may be called multiple times during recovery)
-            assert mock_discover.call_count >= 1
-
-
-class TestVsCodeRuntimeIntegration:
-    """Integration tests for VsCodeRuntime components."""
-
-    @pytest.fixture
-    def runtime(self):
-        config = OpenHandsConfig()
-        event_stream = Mock(spec=EventStream)
-        return VsCodeRuntime(config=config, event_stream=event_stream)
-
-    def test_full_workflow_success(self, runtime):
-        """Test complete workflow from discovery to action execution."""
-        mock_instances = [
-            {
-                'id': 'vscode-1',
-                'port': 3001,
-                'status': 'active',
-                'connection_id': 'vscode-1',
-            }
-        ]
-        action = CmdRunAction(command='pwd')
-
-        with patch('aiohttp.ClientSession.get') as mock_get:
-            # Mock discovery - return proper format with 'instances' key
-            mock_discovery_response = AsyncMock()
-            mock_discovery_response.status = 200
-            mock_discovery_response.json = AsyncMock(return_value=mock_instances)
-
-            # Mock Socket.IO server directly
-            runtime.sio_server = Mock()
-
-            # Set up mock responses
-            mock_get.return_value.__aenter__.return_value = mock_discovery_response
-
-            # Execute action - should trigger discovery workflow
-            runtime.run_action(action)
-
-            # Should have attempted discovery
-            mock_get.assert_called()
-            # Should have set socket connection ID
-            assert runtime.socket_connection_id == 'vscode-1'
--- a/tests/unit/server/test_vscode_routes.py
+++ b/tests/unit/server/test_vscode_routes.py
@@ -1,622 +0,0 @@
-"""Unit tests for VSCode server routes
-
-Tests the VSCode integration API endpoints that implement the Lazy Connection Pattern.
-Covers registration, discovery, heartbeat, and management functionality.
-"""
-
-from unittest.mock import patch
-
-import pytest
-from fastapi import FastAPI
-from fastapi import status as http_status
-from fastapi.testclient import TestClient
-
-from openhands.server.routes.vscode import VSCodeInstance, _vscode_registry
-from openhands.server.routes.vscode import app as vscode_router
-
-
-@pytest.fixture
-def client():
-    """Create a test client for the VSCode routes."""
-    # Create a FastAPI app and include the VSCode router
-    test_app = FastAPI()
-    test_app.include_router(vscode_router)
-    return TestClient(test_app)
-
-
-@pytest.fixture
-def clean_registry():
-    """Clean the VSCode registry before and after each test."""
-    _vscode_registry.clear()
-    yield
-    _vscode_registry.clear()
-
-
-@pytest.fixture
-def sample_registration_data():
-    """Sample data for VSCode registration requests."""
-    return {
-        'workspace_path': '/home/user/project',
-        'workspace_name': 'test-project',
-        'vscode_version': '1.85.0',
-        'extension_version': '0.1.0',
-        'capabilities': ['file_operations', 'terminal_access'],
-    }
-
-
-@pytest.fixture
-def mock_time():
-    """Mock time.time() to return predictable values."""
-    with patch('time.time', return_value=1234567890.0):
-        yield 1234567890.0
-
-
-class TestVsCodeRegistration:
-    """Test VSCode instance registration endpoint."""
-
-    def test_register_vscode_instance_success(
-        self, client, clean_registry, sample_registration_data, mock_time
-    ):
-        """Test successful VSCode instance registration."""
-        response = client.post('/api/vscode/register', json=sample_registration_data)
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-
-        # Check response structure
-        assert 'connection_id' in data
-        assert 'message' in data
-        assert (
-            data['message']
-            == "Successfully registered VSCode instance for workspace 'test-project'"
-        )
-
-        # Verify connection_id is a valid UUID format
-        connection_id = data['connection_id']
-        assert len(connection_id) == 36  # UUID length
-        assert connection_id.count('-') == 4  # UUID format
-
-        # Verify instance was stored in registry
-        assert connection_id in _vscode_registry
-        instance = _vscode_registry[connection_id]
-        assert instance.workspace_path == sample_registration_data['workspace_path']
-        assert instance.workspace_name == sample_registration_data['workspace_name']
-        assert instance.vscode_version == sample_registration_data['vscode_version']
-        assert (
-            instance.extension_version == sample_registration_data['extension_version']
-        )
-        assert instance.capabilities == sample_registration_data['capabilities']
-        assert instance.status == 'active'
-        assert instance.registered_at == mock_time
-        assert instance.last_heartbeat == mock_time
-
-    def test_register_vscode_instance_minimal_data(
-        self, client, clean_registry, mock_time
-    ):
-        """Test registration with minimal required data."""
-        minimal_data = {
-            'workspace_path': '/home/user/minimal',
-            'workspace_name': 'minimal-project',
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-            # capabilities is optional and should default to empty list
-        }
-
-        response = client.post('/api/vscode/register', json=minimal_data)
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-        connection_id = data['connection_id']
-
-        # Verify instance was stored with default capabilities
-        instance = _vscode_registry[connection_id]
-        assert instance.capabilities == []
-
-    def test_register_vscode_instance_missing_required_fields(
-        self, client, clean_registry
-    ):
-        """Test registration with missing required fields."""
-        incomplete_data = {
-            'workspace_path': '/home/user/project',
-            # Missing workspace_name, vscode_version, extension_version
-        }
-
-        response = client.post('/api/vscode/register', json=incomplete_data)
-
-        assert response.status_code == http_status.HTTP_422_UNPROCESSABLE_ENTITY
-        # Verify no instance was stored
-        assert len(_vscode_registry) == 0
-
-    def test_register_vscode_instance_invalid_json(self, client, clean_registry):
-        """Test registration with invalid JSON data."""
-        response = client.post('/api/vscode/register', data='invalid json')
-
-        assert response.status_code == http_status.HTTP_422_UNPROCESSABLE_ENTITY
-        # Verify no instance was stored
-        assert len(_vscode_registry) == 0
-
-    def test_register_vscode_instance_empty_capabilities(
-        self, client, clean_registry, mock_time
-    ):
-        """Test registration with explicitly empty capabilities."""
-        data_with_empty_capabilities = {
-            'workspace_path': '/home/user/project',
-            'workspace_name': 'test-project',
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-            'capabilities': [],
-        }
-
-        response = client.post(
-            '/api/vscode/register', json=data_with_empty_capabilities
-        )
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-        connection_id = data['connection_id']
-
-        # Verify instance was stored with empty capabilities
-        instance = _vscode_registry[connection_id]
-        assert instance.capabilities == []
-
-
-class TestVsCodeDiscovery:
-    """Test VSCode instance discovery endpoint."""
-
-    def test_get_vscode_instances_empty_registry(self, client, clean_registry):
-        """Test discovery when no instances are registered."""
-        response = client.get('/api/vscode/instances')
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-        assert data == []
-
-    def test_get_vscode_instances_single_instance(
-        self, client, clean_registry, mock_time
-    ):
-        """Test discovery with a single registered instance."""
-        # Register an instance first
-        registration_data = {
-            'workspace_path': '/home/user/project',
-            'workspace_name': 'test-project',
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-            'capabilities': ['file_operations'],
-        }
-
-        reg_response = client.post('/api/vscode/register', json=registration_data)
-        connection_id = reg_response.json()['connection_id']
-
-        # Now test discovery
-        response = client.get('/api/vscode/instances')
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-        assert len(data) == 1
-
-        instance_info = data[0]
-        assert instance_info['connection_id'] == connection_id
-        assert instance_info['workspace_name'] == 'test-project'
-        assert instance_info['workspace_path'] == '/home/user/project'
-        assert instance_info['status'] == 'active'
-        assert instance_info['registered_at'] == mock_time
-        assert instance_info['last_heartbeat'] == mock_time
-
-    def test_get_vscode_instances_multiple_instances(
-        self, client, clean_registry, mock_time
-    ):
-        """Test discovery with multiple registered instances."""
-        # Register multiple instances
-        instances_data = [
-            {
-                'workspace_path': '/home/user/project1',
-                'workspace_name': 'project-1',
-                'vscode_version': '1.85.0',
-                'extension_version': '0.1.0',
-                'capabilities': ['file_operations'],
-            },
-            {
-                'workspace_path': '/home/user/project2',
-                'workspace_name': 'project-2',
-                'vscode_version': '1.86.0',
-                'extension_version': '0.2.0',
-                'capabilities': ['terminal_access'],
-            },
-        ]
-
-        connection_ids = []
-        for instance_data in instances_data:
-            reg_response = client.post('/api/vscode/register', json=instance_data)
-            connection_ids.append(reg_response.json()['connection_id'])
-
-        # Test discovery
-        response = client.get('/api/vscode/instances')
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-        assert len(data) == 2
-
-        # Verify both instances are returned
-        returned_ids = [instance['connection_id'] for instance in data]
-        assert set(returned_ids) == set(connection_ids)
-
-        # Verify instance details
-        for instance_info in data:
-            if instance_info['workspace_name'] == 'project-1':
-                assert instance_info['workspace_path'] == '/home/user/project1'
-            elif instance_info['workspace_name'] == 'project-2':
-                assert instance_info['workspace_path'] == '/home/user/project2'
-
-    def test_get_vscode_instances_stale_cleanup(self, client, clean_registry):
-        """Test that stale instances are cleaned up during discovery."""
-        current_time = 1234567890.0
-        stale_time = current_time - (
-            6 * 60
-        )  # 6 minutes ago (stale threshold is 5 minutes)
-
-        # Manually add a stale instance to registry
-        stale_connection_id = 'stale-instance-id'
-        _vscode_registry[stale_connection_id] = VSCodeInstance(
-            connection_id=stale_connection_id,
-            workspace_path='/home/user/stale',
-            workspace_name='stale-project',
-            vscode_version='1.85.0',
-            extension_version='0.1.0',
-            capabilities=[],
-            registered_at=stale_time,
-            last_heartbeat=stale_time,
-            status='active',
-        )
-
-        # Add a fresh instance
-        with patch('time.time', return_value=current_time):
-            registration_data = {
-                'workspace_path': '/home/user/fresh',
-                'workspace_name': 'fresh-project',
-                'vscode_version': '1.85.0',
-                'extension_version': '0.1.0',
-            }
-            reg_response = client.post('/api/vscode/register', json=registration_data)
-            fresh_connection_id = reg_response.json()['connection_id']
-
-        # Verify both instances are in registry before discovery
-        assert len(_vscode_registry) == 2
-        assert stale_connection_id in _vscode_registry
-        assert fresh_connection_id in _vscode_registry
-
-        # Test discovery - should clean up stale instance
-        with patch('time.time', return_value=current_time):
-            response = client.get('/api/vscode/instances')
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-
-        # Only fresh instance should be returned
-        assert len(data) == 1
-        assert data[0]['connection_id'] == fresh_connection_id
-        assert data[0]['workspace_name'] == 'fresh-project'
-
-        # Verify stale instance was removed from registry
-        assert len(_vscode_registry) == 1
-        assert stale_connection_id not in _vscode_registry
-        assert fresh_connection_id in _vscode_registry
-
-
-class TestVsCodeInstanceManagement:
-    """Test VSCode instance management endpoints."""
-
-    def test_heartbeat_success(self, client, clean_registry, mock_time):
-        """Test successful heartbeat update."""
-        # Register an instance first
-        registration_data = {
-            'workspace_path': '/home/user/project',
-            'workspace_name': 'test-project',
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-        }
-
-        reg_response = client.post('/api/vscode/register', json=registration_data)
-        connection_id = reg_response.json()['connection_id']
-
-        # Update heartbeat with a later time
-        later_time = mock_time + 60  # 1 minute later
-        with patch('time.time', return_value=later_time):
-            response = client.post(f'/api/vscode/heartbeat/{connection_id}')
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-        assert data['message'] == 'Heartbeat updated'
-
-        # Verify heartbeat was updated in registry
-        instance = _vscode_registry[connection_id]
-        assert instance.last_heartbeat == later_time
-        assert instance.status == 'active'
-
-    def test_heartbeat_nonexistent_instance(self, client, clean_registry):
-        """Test heartbeat for non-existent instance."""
-        fake_connection_id = 'non-existent-id'
-
-        response = client.post(f'/api/vscode/heartbeat/{fake_connection_id}')
-
-        assert response.status_code == http_status.HTTP_404_NOT_FOUND
-        data = response.json()
-        assert 'not found' in data['detail'].lower()
-
-    def test_unregister_success(self, client, clean_registry, mock_time):
-        """Test successful instance unregistration."""
-        # Register an instance first
-        registration_data = {
-            'workspace_path': '/home/user/project',
-            'workspace_name': 'test-project',
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-        }
-
-        reg_response = client.post('/api/vscode/register', json=registration_data)
-        connection_id = reg_response.json()['connection_id']
-
-        # Verify instance exists
-        assert connection_id in _vscode_registry
-
-        # Unregister the instance
-        response = client.delete(f'/api/vscode/unregister/{connection_id}')
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-        assert connection_id in data['message']
-        assert 'Successfully unregistered' in data['message']
-
-        # Verify instance was removed from registry
-        assert connection_id not in _vscode_registry
-
-    def test_unregister_nonexistent_instance(self, client, clean_registry):
-        """Test unregistration of non-existent instance."""
-        fake_connection_id = 'non-existent-id'
-
-        response = client.delete(f'/api/vscode/unregister/{fake_connection_id}')
-
-        assert response.status_code == http_status.HTTP_404_NOT_FOUND
-        data = response.json()
-        assert 'not found' in data['detail'].lower()
-
-    def test_get_instance_success(self, client, clean_registry, mock_time):
-        """Test getting information about a specific instance."""
-        # Register an instance first
-        registration_data = {
-            'workspace_path': '/home/user/project',
-            'workspace_name': 'test-project',
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-            'capabilities': ['file_operations', 'terminal_access'],
-        }
-
-        reg_response = client.post('/api/vscode/register', json=registration_data)
-        connection_id = reg_response.json()['connection_id']
-
-        # Get instance information
-        response = client.get(f'/api/vscode/instance/{connection_id}')
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-
-        # Verify instance information
-        assert data['connection_id'] == connection_id
-        assert data['workspace_name'] == 'test-project'
-        assert data['workspace_path'] == '/home/user/project'
-        assert data['status'] == 'active'
-        assert data['registered_at'] == mock_time
-        assert data['last_heartbeat'] == mock_time
-
-    def test_get_instance_nonexistent(self, client, clean_registry):
-        """Test getting information about non-existent instance."""
-        fake_connection_id = 'non-existent-id'
-
-        response = client.get(f'/api/vscode/instance/{fake_connection_id}')
-
-        assert response.status_code == http_status.HTTP_404_NOT_FOUND
-        data = response.json()
-        assert 'not found' in data['detail'].lower()
-
-    def test_get_registry_stats_empty(self, client, clean_registry):
-        """Test registry stats with empty registry."""
-        response = client.get('/api/vscode/registry/stats')
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-
-        assert data['total_instances'] == 0
-        assert data['status_counts'] == {}
-        assert data['recent_activity'] == 0
-        assert data['registry_size'] == 0
-
-    def test_get_registry_stats_with_instances(self, client, clean_registry, mock_time):
-        """Test registry stats with multiple instances."""
-        current_time = mock_time
-
-        # Register multiple instances with different statuses
-        instances_data = [
-            {
-                'workspace_path': '/home/user/project1',
-                'workspace_name': 'project-1',
-                'vscode_version': '1.85.0',
-                'extension_version': '0.1.0',
-            },
-            {
-                'workspace_path': '/home/user/project2',
-                'workspace_name': 'project-2',
-                'vscode_version': '1.86.0',
-                'extension_version': '0.2.0',
-            },
-        ]
-
-        connection_ids = []
-        for instance_data in instances_data:
-            reg_response = client.post('/api/vscode/register', json=instance_data)
-            connection_ids.append(reg_response.json()['connection_id'])
-
-        # Manually set one instance to idle status
-        _vscode_registry[connection_ids[1]].status = 'idle'
-
-        # Add an old instance (no recent activity)
-        old_time = current_time - (10 * 60)  # 10 minutes ago
-        old_connection_id = 'old-instance-id'
-        _vscode_registry[old_connection_id] = VSCodeInstance(
-            connection_id=old_connection_id,
-            workspace_path='/home/user/old',
-            workspace_name='old-project',
-            vscode_version='1.84.0',
-            extension_version='0.0.1',
-            capabilities=[],
-            registered_at=old_time,
-            last_heartbeat=old_time,
-            status='active',
-        )
-
-        # Get registry stats
-        with patch('time.time', return_value=current_time):
-            response = client.get('/api/vscode/registry/stats')
-
-        assert response.status_code == http_status.HTTP_200_OK
-        data = response.json()
-
-        assert data['total_instances'] == 3
-        assert data['registry_size'] == 3
-        assert data['status_counts']['active'] == 2
-        assert data['status_counts']['idle'] == 1
-        assert data['recent_activity'] == 2  # Only the 2 recent instances
-
-
-class TestVsCodeErrorHandling:
-    """Test error handling scenarios for VSCode routes."""
-
-    def test_registration_server_error_simulation(self, client, clean_registry):
-        """Test registration endpoint error handling."""
-        # Simulate server error by patching uuid.uuid4 to raise exception
-        with patch(
-            'openhands.server.routes.vscode.uuid.uuid4',
-            side_effect=Exception('UUID generation failed'),
-        ):
-            registration_data = {
-                'workspace_path': '/home/user/project',
-                'workspace_name': 'test-project',
-                'vscode_version': '1.85.0',
-                'extension_version': '0.1.0',
-            }
-
-            response = client.post('/api/vscode/register', json=registration_data)
-
-            assert response.status_code == http_status.HTTP_500_INTERNAL_SERVER_ERROR
-            data = response.json()
-            assert 'Registration failed' in data['detail']
-            assert 'UUID generation failed' in data['detail']
-
-            # Verify no instance was stored
-            assert len(_vscode_registry) == 0
-
-    def test_invalid_connection_id_format(self, client, clean_registry):
-        """Test endpoints with invalid connection ID formats."""
-        invalid_connection_id = 'invalid-id-format'
-
-        # Test heartbeat with invalid ID
-        response = client.post(f'/api/vscode/heartbeat/{invalid_connection_id}')
-        assert response.status_code == http_status.HTTP_404_NOT_FOUND
-
-        # Test unregister with invalid ID
-        response = client.delete(f'/api/vscode/unregister/{invalid_connection_id}')
-        assert response.status_code == http_status.HTTP_404_NOT_FOUND
-
-        # Test get instance with invalid ID
-        response = client.get(f'/api/vscode/instance/{invalid_connection_id}')
-        assert response.status_code == http_status.HTTP_404_NOT_FOUND
-
-    def test_malformed_registration_data(self, client, clean_registry):
-        """Test registration with various malformed data."""
-        # Test with non-string workspace_path
-        malformed_data = {
-            'workspace_path': 123,  # Should be string
-            'workspace_name': 'test-project',
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-        }
-
-        response = client.post('/api/vscode/register', json=malformed_data)
-        assert response.status_code == http_status.HTTP_422_UNPROCESSABLE_ENTITY
-
-        # Test with non-list capabilities
-        malformed_data = {
-            'workspace_path': '/home/user/project',
-            'workspace_name': 'test-project',
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-            'capabilities': 'not-a-list',  # Should be list
-        }
-
-        response = client.post('/api/vscode/register', json=malformed_data)
-        assert response.status_code == http_status.HTTP_422_UNPROCESSABLE_ENTITY
-
-    def test_empty_string_fields(self, client, clean_registry):
-        """Test registration with empty string fields."""
-        empty_data = {
-            'workspace_path': '',  # Empty string - should fail validation
-            'workspace_name': '',  # Empty string - should fail validation
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-        }
-
-        response = client.post('/api/vscode/register', json=empty_data)
-        # Should fail validation due to min_length=1 constraint
-        assert response.status_code == http_status.HTTP_422_UNPROCESSABLE_ENTITY
-
-        # Verify error details mention the validation failures
-        data = response.json()
-        assert 'detail' in data
-        # Should have validation errors for both empty fields
-        errors = data['detail']
-        assert len(errors) >= 2  # At least workspace_path and workspace_name errors
-
-    def test_extremely_long_field_values(self, client, clean_registry):
-        """Test registration with extremely long field values."""
-        long_string = 'x' * 10000  # Very long string
-
-        long_data = {
-            'workspace_path': long_string,
-            'workspace_name': long_string,
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-        }
-
-        # This should still work but might be handled differently in production
-        response = client.post('/api/vscode/register', json=long_data)
-        # For now, we expect it to work, but in production you might want validation
-        assert response.status_code in [
-            http_status.HTTP_200_OK,
-            http_status.HTTP_422_UNPROCESSABLE_ENTITY,
-        ]
-
-    def test_concurrent_registration_cleanup(self, client, clean_registry, mock_time):
-        """Test behavior when registry is modified during operations."""
-        # Register an instance
-        registration_data = {
-            'workspace_path': '/home/user/project',
-            'workspace_name': 'test-project',
-            'vscode_version': '1.85.0',
-            'extension_version': '0.1.0',
-        }
-
-        reg_response = client.post('/api/vscode/register', json=registration_data)
-        connection_id = reg_response.json()['connection_id']
-
-        # Manually remove the instance from registry (simulating concurrent modification)
-        del _vscode_registry[connection_id]
-
-        # Try to access the removed instance
-        response = client.get(f'/api/vscode/instance/{connection_id}')
-        assert response.status_code == http_status.HTTP_404_NOT_FOUND
-
-        # Try to update heartbeat for removed instance
-        response = client.post(f'/api/vscode/heartbeat/{connection_id}')
-        assert response.status_code == http_status.HTTP_404_NOT_FOUND
-
-
-if __name__ == '__main__':
-    pytest.main([__file__])
--- a/vscode.md
+++ b/vscode.md
@@ -1,142 +0,0 @@
-# VSCode Integration Approaches
-
-OpenHands can integrate with VSCode in three different ways, each serving different use cases:
-
-## 1. VSCode Integration (Launcher) ✅ **Completed**
-**Purpose**: Launch OpenHands from VSCode with context.
-
-**How it works**:
- VSCode extension provides context menu commands and Command Palette entries
- User can start OpenHands with current file content, selected text, or new conversation
- Extension launches OpenHands in terminal with appropriate context
- Auto-installs when user runs OpenHands CLI in VSCode/Windsurf
-
-**Use cases**:
- Quick OpenHands launch with file/selection context
- Seamless workflow from editing to AI assistance
- No need to manually copy-paste file contents
-
-## 2. VSCode Runtime (Executor) ⭐ **Current Focus**
-**Purpose**: Use VSCode as the execution environment for OpenHands actions.
-
-**How it works**:
- OpenHands AgentController sends actions to VSCode Runtime (Python)
- VSCode Runtime forwards actions to VSCode Extension via Socket.IO
- VSCode Extension executes actions using VSCode API (file ops, terminal, etc.)
- VSCode Extension sends observations back via Socket.IO
- VSCode Runtime returns observations to AgentController
-
-**Architecture**:
-```
-AgentController → VSCodeRuntime → Socket.IO Server → VSCode Extension → VSCode API
-                                     ↑                    ↓
-                                Socket.IO ← Observations ←
-```
-
-**Connection Flow**:
-1. User starts OpenHands with `--runtime vscode`
-2. OpenHands backend creates `VsCodeRuntime` instance (Python)
-3. `VsCodeRuntime` connects to OpenHands Socket.IO server
-4. VSCode extension connects to the same Socket.IO server (triggered by runtime activation)
-5. Actions flow: Backend → Socket.IO → VSCode Extension → VSCode API
-6. Observations flow: VSCode API → VSCode Extension → Socket.IO → Backend
-
-**Use cases**:
- Leverage VSCode's file system access and workspace management
- Use VSCode's integrated terminal and debugging capabilities
- Access VSCode's language services and extensions
- Work within user's existing VSCode setup and configuration
-
-## 3. VSCode Tab (Frontend)
-**Purpose**: Display OpenHands UI as a tab within VSCode.
-
-**How it works**:
- VSCode extension creates a webview panel
- Panel displays the OpenHands web interface
- Standard Socket.IO communication with OpenHands backend (running anywhere)
- Just another frontend client, like the web UI
-
-**Use cases**:
- View OpenHands interface without leaving VSCode
- Alternative to browser-based UI
- Integrated development environment experience
-
---
-
-## Extension Architecture Recommendation
-
-### ✅ **Combine Tasks 1, 2, and 3 in One Extension**
-
-**Rationale**:
- **Complementary workflows**: User launches OpenHands (Task 1) → OpenHands executes in VSCode (Task 2) → User views UI in VSCode tab (Task 3)
- **Shared infrastructure**: All three use Socket.IO communication and VSCode workspace utilities
- **Better user experience**: Single extension to install and configure
- **Natural user journey**: Complete VSCode ↔ OpenHands integration suite
-
-**Architecture**:
-```typescript
-extension.ts
-├── commands/           // Task 1: Context menu commands
-├── runtime/           // Task 2: Action execution handler
-├── webview/           // Task 3: OpenHands UI tab
-├── services/
-│   ├── socketio.ts    // Shared Socket.IO client/server
-│   └── workspace.ts   // Shared VSCode utilities
-└── types/             // Shared OpenHands types
-```
-
-**Activation patterns**:
- **Task 1**: On-demand (when user triggers commands)
- **Task 2**: Always listening (when OpenHands uses VSCode runtime)
- **Task 3**: On-demand (when user opens OpenHands tab)
-
-**User stories**:
-1. *"Launch OpenHands with my current file context"* → Task 1
-2. *"Have OpenHands execute actions in my VSCode"* → Task 2
-3. *"View OpenHands UI without leaving VSCode"* → Task 3
-
-**Implementation strategy**:
- Rebase `vscode-runtime` branch on top of `vscode-integration` branch
- Expand existing extension with runtime capabilities (Task 2)
- Add webview panel for OpenHands UI (Task 3)
- Share Socket.IO service across all three tasks
-
---
-
-## Socket.IO Infrastructure
-
-OpenHands has existing Socket.IO infrastructure that all approaches leverage:
-
- **Server**: `openhands/server/shared.py` creates `socketio.AsyncServer`
- **Event Handlers**: `openhands/server/listen_socket.py` handles client connections
- **Event Flow**: Clients connect, send `oh_user_action` events, receive `oh_event` emissions
- **Consistency**: VSCode integrations use the same protocol as the web frontend
-
-## Current Implementation Status
-
-### ✅ **Task 1 - VSCode Integration (Completed)**
- Beautiful OpenHands submenu in context menu
- Smart dual naming strategy (short names in menu, full names in Command Palette)
- Auto-installation when running OpenHands CLI in VSCode/Windsurf
- Successfully tested and pushed to `vscode-integration` branch
-
-### 🔧 **Task 2 - VSCode Runtime (In Progress)**
- VSCode Runtime implementation has been integrated with Task 1 extension
- Runtime action handler supports file operations (read, write, edit) and terminal commands
- Socket.IO communication established between OpenHands backend and VSCode extension
- VSCode extension can execute OpenHands actions within the VSCode environment
- Connection management with lazy initialization and error handling
- **Current work**: Refining functionality and ensuring robust operation
-
-### 📋 **Task 3 - VSCode Tab (Planned)**
- Will be added to the combined extension
- Webview panel to display OpenHands UI
- Socket.IO client to connect to OpenHands backend
-
-## Next Steps
-
-1. ✅ **Rebase and combine**: Completed - `vscode-runtime` branch contains integrated functionality
-2. 🔧 **Refine Task 2**: Currently working on making VSCode Runtime robust and reliable
-3. **Add Task 3**: Implement webview panel for OpenHands UI
-4. **Test integration**: Verify all three tasks work together seamlessly
-5. **Update documentation**: Document the complete integration suite
--- a/vscode_runtime_task.md
+++ b/vscode_runtime_task.md
@@ -1,114 +0,0 @@
-# VSCode Runtime Integration Task
-
-## What a VSCode Runtime Should Be Like
-
-A VSCode runtime should provide a bridge between OpenHands and a VSCode extension, allowing OpenHands agents to execute actions directly within the user's VSCode environment. Key characteristics:
-
-### Architecture
- **Socket.IO Communication**: Uses Socket.IO for real-time bidirectional communication between the OpenHands backend and VSCode extension
- **Extension-Based Execution**: Actions are executed by a VSCode extension running in the user's editor, not in a separate container
- **Direct File Access**: Works directly with files in the user's workspace without needing file copying or mounting
- **IDE Integration**: Leverages VSCode's built-in capabilities (terminal, file system, debugging, etc.)
-
-### Core Capabilities
- **Command Execution**: Run shell commands in VSCode's integrated terminal
- **File Operations**: Read, write, and edit files using VSCode's file system APIs
- **Browser Integration**: Open URLs in VSCode's built-in browser or external browser
- **Python/IPython**: Execute Python code in VSCode's Python environment
- **MCP Tool Support**: Call Model Context Protocol tools through the extension
-
-### Benefits
- **Native Experience**: Users see actions happening in their familiar VSCode environment
- **No Container Overhead**: Direct execution without Docker or sandboxing
- **Real-time Visibility**: Users can watch the agent work in real-time
- **Extension Ecosystem**: Can leverage VSCode's rich extension ecosystem
-
-## Current VSCode Runtime Implementation Analysis
-
-### What It Does Right
-
-1. **Proper Runtime Interface**:
-   - ✅ Inherits from `Runtime` base class
-   - ✅ Implements all required abstract methods (`connect`, `copy_from`, `copy_to`, `get_mcp_config`, `list_files`, etc.)
-   - ✅ Compatible with the standard runtime test framework
-
-2. **Socket.IO Architecture**:
-   - ✅ Uses async Socket.IO for communication
-   - ✅ Maintains action tracking with futures for async operations
-   - ✅ Proper event serialization/deserialization
-
-3. **Action Delegation**:
-   - ✅ All actions (run, read, write, edit, browse, etc.) are properly delegated to VSCode extension
-   - ✅ Consistent error handling when extension is not connected
-
-4. **Test Integration**:
-   - ✅ Successfully added to runtime test framework
-   - ✅ Can be instantiated and tested with `TEST_RUNTIME=vscode`
-   - ✅ Added to CI workflow for automated testing
-
-
-
-### Test Results
-
-The VSCode runtime successfully:
- ✅ Loads and initializes without errors
- ✅ Integrates with the runtime test framework
- ✅ Returns appropriate error messages when not connected to VSCode extension
- ✅ Handles action delegation correctly
-
-Expected test behavior:
-```
-ERROR: VsCodeRuntime is not properly configured with a connection. Cannot operate.
-```
-
-This is correct behavior when no VSCode extension is connected.
-
-## Implementation Locations
-
- **VSCode Extension**: `/openhands/integrations/vscode/` - TypeScript extension with Socket.IO connection and action handlers
- **VSCode Runtime**: `/openhands/runtime/vscode/` - Python runtime implementation that communicates with the extension
- **Server API Routes**: `/openhands/server/routes/vscode.py` - FastAPI endpoints for extension registration and discovery
-
-## Next Steps
-
-### For Full VSCode Integration:
-
-1. **VSCode Extension Development**:
-   - ✅ Create a VSCode extension that connects to the OpenHands Socket.IO server
-   - ✅ Implement action handlers for all runtime operations
-   - ⏳ Further refinement and testing of action handlers
-
-2. **Connection Management**:
-   - ✅ Add automatic connection discovery (server-side registry implemented)
-   - ⏳ Implement reconnection logic
-   - ⏳ Add connection status monitoring
-
-3. **Enhanced File Operations**:
-   - ⏳ Implement proper `list_files` through extension
-   - ⏳ Add workspace-aware file operations
-   - ⏳ Handle VSCode-specific file events
-
-4. **Testing Infrastructure**:
-   - ✅ Create mock VSCode extension for testing
-   - ⏳ Add integration tests with actual VSCode
-
-### For Current Testing:
-
-The VSCode runtime is now properly integrated into the test framework and will:
- Run in CI with `TEST_RUNTIME=vscode`
- Return appropriate errors when no extension is connected
- Validate the runtime interface implementation
-
-This provides a solid foundation for future VSCode extension development.
-
-
-
-## Current Status
-
-The VSCode runtime is now:
- ✅ Properly integrated into the OpenHands runtime system
- ✅ Compatible with the existing test framework
- ✅ Ready for CI testing
- ✅ Prepared for future VSCode extension development
-
-The implementation provides a solid foundation that correctly handles the case where no VSCode extension is connected, making it safe to include in automated testing.
Author	SHA1	Message	Date
Xingyao Wang	877a857e55	Merge branch 'main' into fix-timeout-message-tests	2025-08-15 15:40:45 -04:00
openhands	2a52902db8	Revert implementation changes - keep main branch implementation	2025-08-15 19:39:05 +00:00
openhands	02a5b7c307	Remove prompt changes - keep only timeout message fixes	2025-08-15 19:35:20 +00:00
openhands	4d4645068c	Fix timeout message format to match main branch - Updated TIMEOUT_MESSAGE_TEMPLATE in bash_constants.py to include specific key combinations ('C-c', 'C-z', 'C-d') - Modified bash.py to use TIMEOUT_MESSAGE_TEMPLATE instead of hardcoded message - Modified windows_bash.py to use TIMEOUT_MESSAGE_TEMPLATE instead of hardcoded message - Ensures consistent timeout message format across all bash implementations - Fixes failing runtime tests related to timeout error prompt changes	2025-08-15 19:24:03 +00:00
openhands	8e30ecca11	Revert unintended default system prompt change The change to set system_prompt_filename default to 'system_prompt_tech_philosophy.j2' was unintended. Reverting back to the original default 'system_prompt.j2' and updating the test accordingly. Co-authored-by: openhands <openhands@all-hands.dev>	2025-08-15 18:42:34 +00:00
openhands	9722d23f38	Fix test to match new default system prompt filename The default system_prompt_filename was changed from 'system_prompt.j2' to 'system_prompt_tech_philosophy.j2' in the AgentConfig, so the test needed to be updated to reflect this change. Co-authored-by: openhands <openhands@all-hands.dev>	2025-08-15 18:26:44 +00:00
Xingyao Wang	587b4c311a	runtime(bash): clarify guidance when previous command still running; recommend execute_bash timeout (issue #10350 ) (#10389 ) Co-authored-by: openhands <openhands@all-hands.dev>	2025-08-16 02:15:05 +08:00
Xingyao Wang	7a86402c9c	Add process management guidance to system prompt (#10083 ) Co-authored-by: openhands <openhands@all-hands.dev>	2025-08-16 02:09:20 +08:00
Insop	06d283dfa0	Temp fix for docker file and debug log (#10345 )	2025-08-15 15:34:46 +00:00
sp.wack	a6a4246e30	fix(frontend): Failing tests (#10369 )	2025-08-15 15:18:35 +00:00
Xingyao Wang	4830b9a67d	fix(llm): include gpt-5 to fn call model; set top p default value to None (#10363 )	2025-08-15 15:08:01 +00:00
Neeraj Panwar	d4489d62d7	fix(llm): set AWS credentials in `config.toml` (#10351 )	2025-08-15 22:16:50 +08:00
Ryan H. Tran	e41c020073	[CLI] Fix MCP toml formatting issue (#10312 ) Co-authored-by: openhands <openhands@all-hands.dev>	2025-08-15 13:56:46 +00:00
Ryan H. Tran	3f44c8436f	Fix swebench modal patch eval intermittent crash (#10353 )	2025-08-15 21:51:03 +08:00
Graham Neubig	b740944075	Split E2E settings and conversation tests; run settings first in workflow (#10359 ) Co-authored-by: openhands <openhands@all-hands.dev>	2025-08-15 09:19:27 -04:00
dependabot[bot]	5618a3eebb	chore(deps): bump the version-all group in /frontend with 9 updates (#10318 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-08-15 16:51:41 +04:00
Hiep Le	a1ffe5c936	fix(frontend): frontend UI keep flashing (#10352 )	2025-08-15 12:19:30 +04:00
Hiep Le	f8376a9702	fix(frontend): status message missing (#10349 )	2025-08-15 12:11:42 +07:00
Tim O'Farrell	985a634d60	Fix for issue where static system commands are truncated (#10292 ) Co-authored-by: openhands <openhands@all-hands.dev>	2025-08-15 04:16:50 +00:00
Xingyao Wang	9b78a5e200	update default prompt name	2025-08-14 13:49:50 -04:00
Xingyao Wang	1ce3723b60	rename and add file back	2025-08-14 13:48:44 -04:00
Xingyao Wang	95a32ae459	set default	2025-08-14 13:18:22 -04:00
Xingyao Wang	9be0acea9c	improve prompt	2025-08-14 13:15:01 -04:00
test	1a5965b951	Merge system prompt templates into experimental version - Combine system_prompt_interactive.j2 and system_prompt_roleplay.j2 into system_prompt_experimental.j2 - Use include directive to avoid code duplication and maintain DRY principle - Integrate interactive rules for handling vague instructions and clarification protocols - Incorporate Linus Torvalds technical philosophy with constructive communication style - Replace harsh language with professional, educational feedback approach - Maintain technical rigor while ensuring respectful user interactions Co-authored-by: openhands <openhands@all-hands.dev>	2025-08-14 17:03:53 +00:00
Xingyao Wang	f5cbb26770	minor tweak and reformat	2025-08-14 12:49:49 -04:00
Xingyao Wang	8caad14eb8	update prompt	2025-08-14 12:15:06 -04:00
Xingyao Wang	43e6ce631a	roleplay prompt	2025-08-14 00:11:38 -04:00