release 0.35.1

.github/workflows/openhands-resolver.yml

@@ -24,7 +24,7 @@ on:
       LLM_MODEL:
         required: false
         type: string
-        default: "anthropic/claude-3-7-sonnet-20250219"
+        default: "anthropic/claude-3-5-sonnet-20241022"
       LLM_API_VERSION:
         required: false
         type: string

Development.md

@@ -118,7 +118,7 @@ poetry run pytest ./tests/unit/test_*.py
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
 setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.34-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.35-nikolaik`
 
 ## Develop inside Docker container
 

README.md

@@ -52,17 +52,17 @@ system requirements and more information.
 
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.35
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

containers/dev/compose.yml

@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.34-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.35-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docker-compose.yml

@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik}
       #- SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234} # enable this only if you want a specific non-root sandbox user but you will have to manually adjust permissions of openhands-state for this user
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -52,7 +52,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -61,7 +61,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.cli
 ```
 

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -46,7 +46,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -56,6 +56,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.35
 ```
 
 Vous pouvez également exécuter OpenHands en mode [headless scriptable](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), en tant que [CLI interactive](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), ou en utilisant l'[Action GitHub OpenHands](https://docs.all-hands.dev/modules/usage/how-to/github-action).

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -34,7 +34,7 @@ Docker で OpenHands を CLI モードで実行するには:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -44,7 +44,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.cli
 ```
 

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -31,7 +31,7 @@ DockerでOpenHandsをヘッドレスモードで実行するには:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -42,7 +42,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/i18n/ja/docusaurus-plugin-content-docs/current/usage/runtimes/docker.md

@@ -25,7 +25,7 @@ nikolaik の `SANDBOX_RUNTIME_CONTAINER_IMAGE` は、ランタイムサーバー
 
     ```bash
     docker run # ...
-        -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+        -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
         -e SANDBOX_USER_ID=$(id -u) \
         -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
         -v $WORKSPACE_BASE:/opt/workspace_base \
@@ -82,5 +82,5 @@ docker network create openhands-network
 # 分離されたネットワークで OpenHands を実行
 docker run # ... \
     --network openhands-network \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.35
 ```

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -35,7 +35,7 @@ Para executar o OpenHands no modo CLI com Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -45,7 +45,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.cli
 ```
 

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -32,7 +32,7 @@ Para executar o OpenHands no modo Headless com Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -43,7 +43,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.main -t "escreva um script bash que imprima oi"
 ```
 

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -58,17 +58,17 @@
 A maneira mais fácil de executar o OpenHands é no Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.35
 ```
 
 Você encontrará o OpenHands em execução em http://localhost:3000!

docs/i18n/pt-BR/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -13,7 +13,7 @@ Este é o Runtime padrão que é usado quando você inicia o OpenHands. Você po
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md

@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -59,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.cli
 ```
 

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md

@@ -47,7 +47,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -57,6 +57,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/installation.mdx

@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.35
 ```
 
 你也可以在可脚本化的[无头模式](https://docs.all-hands.dev/modules/usage/how-to/headless-mode)下运行 OpenHands，作为[交互式 CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode)，或使用 [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action)。

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/runtimes.md

@@ -11,7 +11,7 @@
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/modules/usage/how-to/cli-mode.md

@@ -35,7 +35,7 @@ To run OpenHands in CLI mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -45,7 +45,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.cli
 ```
 

docs/modules/usage/how-to/gitlab-runner.md

@@ -1 +0,0 @@
-# Using GitLab CI Runners

docs/modules/usage/how-to/headless-mode.md

@@ -32,7 +32,7 @@ To run OpenHands in Headless mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -43,7 +43,7 @@ docker run -it \
     -v ~/.openhands-state:/.openhands-state \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.35 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/modules/usage/installation.mdx

@@ -58,17 +58,17 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.34-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.35-nikolaik \
     -e LOG_ALL_EVENTS=true \
     -v /var/run/docker.sock:/var/run/docker.sock \
     -v ~/.openhands-state:/.openhands-state \
     -p 3000:3000 \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app \
-    docker.all-hands.dev/all-hands-ai/openhands:0.34
+    docker.all-hands.dev/all-hands-ai/openhands:0.35
 ```
 
 You'll find OpenHands running at http://localhost:3000!

frontend/__tests__/routes/app-settings.test.tsx

@@ -1,291 +0,0 @@
-import { render, screen, waitFor } from "@testing-library/react";
-import { afterEach, describe, expect, it, vi } from "vitest";
-import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
-import userEvent from "@testing-library/user-event";
-import AppSettingsScreen from "#/routes/app-settings";
-import OpenHands from "#/api/open-hands";
-import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
-import { AuthProvider } from "#/context/auth-context";
-import { AvailableLanguages } from "#/i18n";
-import * as CaptureConsent from "#/utils/handle-capture-consent";
-import * as ToastHandlers from "#/utils/custom-toast-handlers";
-
-const renderAppSettingsScreen = () =>
-  render(<AppSettingsScreen />, {
-    wrapper: ({ children }) => (
-      <QueryClientProvider client={new QueryClient()}>
-        <AuthProvider>{children}</AuthProvider>
-      </QueryClientProvider>
-    ),
-  });
-
-describe("Content", () => {
-  it("should render the screen", () => {
-    renderAppSettingsScreen();
-    screen.getByTestId("app-settings-screen");
-  });
-
-  it("should render the correct default values", async () => {
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      language: "no",
-      user_consents_to_analytics: true,
-      enable_sound_notifications: true,
-    });
-
-    renderAppSettingsScreen();
-
-    await waitFor(() => {
-      const language = screen.getByTestId("language-input");
-      const analytics = screen.getByTestId("enable-analytics-switch");
-      const sound = screen.getByTestId("enable-sound-notifications-switch");
-
-      expect(language).toHaveValue("Norsk");
-      expect(analytics).toBeChecked();
-      expect(sound).toBeChecked();
-    });
-  });
-
-  it("should render the language options", async () => {
-    renderAppSettingsScreen();
-
-    const language = await screen.findByTestId("language-input");
-    await userEvent.click(language);
-
-    AvailableLanguages.forEach((lang) => {
-      const option = screen.getByText(lang.label);
-      expect(option).toBeInTheDocument();
-    });
-  });
-});
-
-describe("Form submission", () => {
-  afterEach(() => {
-    vi.clearAllMocks();
-  });
-
-  it("should submit the form with the correct values", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
-
-    renderAppSettingsScreen();
-
-    const language = await screen.findByTestId("language-input");
-    const analytics = await screen.findByTestId("enable-analytics-switch");
-    const sound = await screen.findByTestId(
-      "enable-sound-notifications-switch",
-    );
-
-    expect(language).toHaveValue("English");
-    expect(analytics).not.toBeChecked();
-    expect(sound).not.toBeChecked();
-
-    // change language
-    await userEvent.click(language);
-    const norsk = screen.getByText("Norsk");
-    await userEvent.click(norsk);
-    expect(language).toHaveValue("Norsk");
-
-    // toggle options
-    await userEvent.click(analytics);
-    expect(analytics).toBeChecked();
-    await userEvent.click(sound);
-    expect(sound).toBeChecked();
-
-    // submit the form
-    const submit = await screen.findByTestId("submit-button");
-    await userEvent.click(submit);
-    expect(saveSettingsSpy).toHaveBeenCalledWith(
-      expect.objectContaining({
-        language: "no",
-        user_consents_to_analytics: true,
-        enable_sound_notifications: true,
-      }),
-    );
-  });
-
-  it("should only enable the submit button when there are changes", async () => {
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
-
-    renderAppSettingsScreen();
-
-    const submit = await screen.findByTestId("submit-button");
-    expect(submit).toBeDisabled();
-
-    // Language check
-    const language = await screen.findByTestId("language-input");
-    await userEvent.click(language);
-    const norsk = screen.getByText("Norsk");
-    await userEvent.click(norsk);
-    expect(submit).not.toBeDisabled();
-
-    await userEvent.click(language);
-    const english = screen.getByText("English");
-    await userEvent.click(english);
-    expect(submit).toBeDisabled();
-
-    // Analytics check
-    const analytics = await screen.findByTestId("enable-analytics-switch");
-    await userEvent.click(analytics);
-    expect(submit).not.toBeDisabled();
-
-    await userEvent.click(analytics);
-    expect(submit).toBeDisabled();
-
-    // Sound check
-    const sound = await screen.findByTestId(
-      "enable-sound-notifications-switch",
-    );
-    await userEvent.click(sound);
-    expect(submit).not.toBeDisabled();
-
-    await userEvent.click(sound);
-    expect(submit).toBeDisabled();
-  });
-
-  it("should call handleCaptureConsents with true when the analytics switch is toggled", async () => {
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
-
-    const handleCaptureConsentsSpy = vi.spyOn(
-      CaptureConsent,
-      "handleCaptureConsent",
-    );
-
-    renderAppSettingsScreen();
-
-    const analytics = await screen.findByTestId("enable-analytics-switch");
-    const submit = await screen.findByTestId("submit-button");
-
-    await userEvent.click(analytics);
-    await userEvent.click(submit);
-
-    await waitFor(() =>
-      expect(handleCaptureConsentsSpy).toHaveBeenCalledWith(true),
-    );
-  });
-
-  it("should call handleCaptureConsents with false when the analytics switch is toggled", async () => {
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      user_consents_to_analytics: true,
-    });
-
-    const handleCaptureConsentsSpy = vi.spyOn(
-      CaptureConsent,
-      "handleCaptureConsent",
-    );
-
-    renderAppSettingsScreen();
-
-    const analytics = await screen.findByTestId("enable-analytics-switch");
-    const submit = await screen.findByTestId("submit-button");
-
-    await userEvent.click(analytics);
-    await userEvent.click(submit);
-
-    await waitFor(() =>
-      expect(handleCaptureConsentsSpy).toHaveBeenCalledWith(false),
-    );
-  });
-
-  // flaky test
-  it.skip("should disable the button when submitting changes", async () => {
-    renderAppSettingsScreen();
-
-    const submit = await screen.findByTestId("submit-button");
-    expect(submit).toBeDisabled();
-
-    const sound = await screen.findByTestId(
-      "enable-sound-notifications-switch",
-    );
-    await userEvent.click(sound);
-    expect(submit).not.toBeDisabled();
-
-    // submit the form
-    await userEvent.click(submit);
-
-    expect(submit).toHaveTextContent("Saving...");
-    expect(submit).toBeDisabled();
-
-    await waitFor(() => expect(submit).toHaveTextContent("Save"));
-  });
-
-  it("should disable the button after submitting changes", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
-
-    renderAppSettingsScreen();
-
-    const submit = await screen.findByTestId("submit-button");
-    expect(submit).toBeDisabled();
-
-    const sound = await screen.findByTestId(
-      "enable-sound-notifications-switch",
-    );
-    await userEvent.click(sound);
-    expect(submit).not.toBeDisabled();
-
-    // submit the form
-    await userEvent.click(submit);
-    expect(saveSettingsSpy).toHaveBeenCalled();
-
-    await waitFor(() => expect(submit).toBeDisabled());
-  });
-});
-
-describe("Status toasts", () => {
-  it("should call displaySuccessToast when the settings are saved", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
-
-    const displaySuccessToastSpy = vi.spyOn(
-      ToastHandlers,
-      "displaySuccessToast",
-    );
-
-    renderAppSettingsScreen();
-
-    // Toggle setting to change
-    const sound = await screen.findByTestId(
-      "enable-sound-notifications-switch",
-    );
-    await userEvent.click(sound);
-
-    const submit = await screen.findByTestId("submit-button");
-    await userEvent.click(submit);
-
-    expect(saveSettingsSpy).toHaveBeenCalled();
-    await waitFor(() => expect(displaySuccessToastSpy).toHaveBeenCalled());
-  });
-
-  it("should call displayErrorToast when the settings fail to save", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
-
-    const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
-
-    saveSettingsSpy.mockRejectedValue(new Error("Failed to save settings"));
-
-    renderAppSettingsScreen();
-
-    // Toggle setting to change
-    const sound = await screen.findByTestId(
-      "enable-sound-notifications-switch",
-    );
-    await userEvent.click(sound);
-
-    const submit = await screen.findByTestId("submit-button");
-    await userEvent.click(submit);
-
-    expect(saveSettingsSpy).toHaveBeenCalled();
-    expect(displayErrorToastSpy).toHaveBeenCalled();
-  });
-});

frontend/__tests__/routes/git-settings.test.tsx

@@ -1,461 +0,0 @@
-import { render, screen, waitFor } from "@testing-library/react";
-import { createRoutesStub } from "react-router";
-import { beforeEach, describe, expect, it, vi } from "vitest";
-import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
-import userEvent from "@testing-library/user-event";
-import GitSettingsScreen from "#/routes/git-settings";
-import OpenHands from "#/api/open-hands";
-import { MOCK_DEFAULT_USER_SETTINGS } from "#/mocks/handlers";
-import { AuthProvider } from "#/context/auth-context";
-import { GetConfigResponse } from "#/api/open-hands.types";
-import * as ToastHandlers from "#/utils/custom-toast-handlers";
-
-const VALID_OSS_CONFIG: GetConfigResponse = {
-  APP_MODE: "oss",
-  GITHUB_CLIENT_ID: "123",
-  POSTHOG_CLIENT_KEY: "456",
-  FEATURE_FLAGS: {
-    ENABLE_BILLING: false,
-    HIDE_LLM_SETTINGS: false,
-  },
-};
-
-const VALID_SAAS_CONFIG: GetConfigResponse = {
-  APP_MODE: "saas",
-  GITHUB_CLIENT_ID: "123",
-  POSTHOG_CLIENT_KEY: "456",
-  FEATURE_FLAGS: {
-    ENABLE_BILLING: false,
-    HIDE_LLM_SETTINGS: false,
-  },
-};
-
-const queryClient = new QueryClient();
-
-const GitSettingsRouterStub = createRoutesStub([
-  {
-    Component: GitSettingsScreen,
-    path: "/settings/github",
-  },
-]);
-
-const renderGitSettingsScreen = () => {
-  const { rerender, ...rest } = render(
-    <GitSettingsRouterStub initialEntries={["/settings/github"]} />,
-    {
-      wrapper: ({ children }) => (
-        <QueryClientProvider client={queryClient}>
-          <AuthProvider>{children}</AuthProvider>
-        </QueryClientProvider>
-      ),
-    },
-  );
-
-  const rerenderGitSettingsScreen = () =>
-    rerender(
-      <QueryClientProvider client={queryClient}>
-        <AuthProvider>
-          <GitSettingsRouterStub initialEntries={["/settings/github"]} />
-        </AuthProvider>
-      </QueryClientProvider>,
-    );
-
-  return {
-    ...rest,
-    rerender: rerenderGitSettingsScreen,
-  };
-};
-
-beforeEach(() => {
-  // Since we don't recreate the query client on every test, we need to
-  // reset the query client before each test to avoid state leaks
-  // between tests.
-  queryClient.invalidateQueries();
-});
-
-describe("Content", () => {
-  it("should render", async () => {
-    renderGitSettingsScreen();
-    await screen.findByTestId("git-settings-screen");
-  });
-
-  it("should render the inputs if OSS mode", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-
-    const { rerender } = renderGitSettingsScreen();
-
-    await screen.findByTestId("github-token-input");
-    await screen.findByTestId("github-token-help-anchor");
-
-    await screen.findByTestId("gitlab-token-input");
-    await screen.findByTestId("gitlab-token-help-anchor");
-
-    getConfigSpy.mockResolvedValue(VALID_SAAS_CONFIG);
-    queryClient.invalidateQueries();
-    rerender();
-
-    await waitFor(() => {
-      expect(
-        screen.queryByTestId("github-token-input"),
-      ).not.toBeInTheDocument();
-      expect(
-        screen.queryByTestId("github-token-help-anchor"),
-      ).not.toBeInTheDocument();
-
-      expect(
-        screen.queryByTestId("gitlab-token-input"),
-      ).not.toBeInTheDocument();
-      expect(
-        screen.queryByTestId("gitlab-token-help-anchor"),
-      ).not.toBeInTheDocument();
-    });
-  });
-
-  it("should set '<hidden>' placeholder and indicator if the GitHub token is set", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      provider_tokens_set: {
-        github: false,
-        gitlab: false,
-      },
-    });
-
-    const { rerender } = renderGitSettingsScreen();
-
-    await waitFor(() => {
-      const githubInput = screen.getByTestId("github-token-input");
-      expect(githubInput).toHaveProperty("placeholder", "");
-      expect(
-        screen.queryByTestId("gh-set-token-indicator"),
-      ).not.toBeInTheDocument();
-
-      const gitlabInput = screen.getByTestId("gitlab-token-input");
-      expect(gitlabInput).toHaveProperty("placeholder", "");
-      expect(
-        screen.queryByTestId("gl-set-token-indicator"),
-      ).not.toBeInTheDocument();
-    });
-
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      provider_tokens_set: {
-        github: true,
-        gitlab: true,
-      },
-    });
-    queryClient.invalidateQueries();
-
-    rerender();
-
-    await waitFor(() => {
-      const githubInput = screen.getByTestId("github-token-input");
-      expect(githubInput).toHaveProperty("placeholder", "<hidden>");
-      expect(
-        screen.queryByTestId("gh-set-token-indicator"),
-      ).toBeInTheDocument();
-
-      const gitlabInput = screen.getByTestId("gitlab-token-input");
-      expect(gitlabInput).toHaveProperty("placeholder", "<hidden>");
-      expect(
-        screen.queryByTestId("gl-set-token-indicator"),
-      ).toBeInTheDocument();
-    });
-
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      provider_tokens_set: {
-        github: false,
-        gitlab: true,
-      },
-    });
-    queryClient.invalidateQueries();
-
-    rerender();
-
-    await waitFor(() => {
-      const githubInput = screen.getByTestId("github-token-input");
-      expect(githubInput).toHaveProperty("placeholder", "");
-      expect(
-        screen.queryByTestId("gh-set-token-indicator"),
-      ).not.toBeInTheDocument();
-
-      const gitlabInput = screen.getByTestId("gitlab-token-input");
-      expect(gitlabInput).toHaveProperty("placeholder", "<hidden>");
-      expect(
-        screen.queryByTestId("gl-set-token-indicator"),
-      ).toBeInTheDocument();
-    });
-  });
-
-  it("should render the 'Configure GitHub Repositories' button if SaaS mode and app slug exists", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-
-    const { rerender } = renderGitSettingsScreen();
-
-    let button = screen.queryByTestId("configure-github-repositories-button");
-    expect(button).not.toBeInTheDocument();
-
-    expect(screen.getByTestId("submit-button")).toBeInTheDocument();
-    expect(screen.getByTestId("disconnect-tokens-button")).toBeInTheDocument();
-
-    getConfigSpy.mockResolvedValue(VALID_SAAS_CONFIG);
-    queryClient.invalidateQueries();
-    rerender();
-
-    await waitFor(() => {
-      // wait until queries are resolved
-      expect(queryClient.isFetching()).toBe(0);
-      button = screen.queryByTestId("configure-github-repositories-button");
-      expect(button).not.toBeInTheDocument();
-    });
-
-    getConfigSpy.mockResolvedValue({
-      ...VALID_SAAS_CONFIG,
-      APP_SLUG: "test-slug",
-    });
-    queryClient.invalidateQueries();
-    rerender();
-
-    await waitFor(() => {
-      button = screen.getByTestId("configure-github-repositories-button");
-      expect(button).toBeInTheDocument();
-      expect(screen.queryByTestId("submit-button")).not.toBeInTheDocument();
-      expect(
-        screen.queryByTestId("disconnect-tokens-button"),
-      ).not.toBeInTheDocument();
-    });
-  });
-});
-
-describe("Form submission", () => {
-  it("should save the GitHub token", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-
-    renderGitSettingsScreen();
-
-    const githubInput = await screen.findByTestId("github-token-input");
-    const submit = await screen.findByTestId("submit-button");
-
-    await userEvent.type(githubInput, "test-token");
-    await userEvent.click(submit);
-
-    expect(saveSettingsSpy).toHaveBeenCalledWith(
-      expect.objectContaining({
-        provider_tokens: {
-          github: "test-token",
-          gitlab: "",
-        },
-      }),
-    );
-
-    const gitlabInput = await screen.findByTestId("gitlab-token-input");
-    await userEvent.type(gitlabInput, "test-token");
-    await userEvent.click(submit);
-
-    expect(saveSettingsSpy).toHaveBeenCalledWith(
-      expect.objectContaining({
-        provider_tokens: {
-          github: "",
-          gitlab: "test-token",
-        },
-      }),
-    );
-  });
-
-  it("should disable the button if there is no input", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-
-    renderGitSettingsScreen();
-
-    const submit = await screen.findByTestId("submit-button");
-    expect(submit).toBeDisabled();
-
-    const githubInput = await screen.findByTestId("github-token-input");
-    await userEvent.type(githubInput, "test-token");
-
-    expect(submit).not.toBeDisabled();
-
-    await userEvent.clear(githubInput);
-    expect(submit).toBeDisabled();
-
-    const gitlabInput = await screen.findByTestId("gitlab-token-input");
-    await userEvent.type(gitlabInput, "test-token");
-
-    expect(submit).not.toBeDisabled();
-
-    await userEvent.clear(gitlabInput);
-    expect(submit).toBeDisabled();
-  });
-
-  it("should enable a disconnect tokens button if there is at least one token set", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      provider_tokens_set: {
-        github: true,
-        gitlab: false,
-      },
-    });
-
-    renderGitSettingsScreen();
-    await screen.findByTestId("git-settings-screen");
-
-    let disconnectButton = await screen.findByTestId(
-      "disconnect-tokens-button",
-    );
-    await waitFor(() => expect(disconnectButton).not.toBeDisabled());
-
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      provider_tokens_set: {
-        github: false,
-        gitlab: false,
-      },
-    });
-    queryClient.invalidateQueries();
-
-    disconnectButton = await screen.findByTestId("disconnect-tokens-button");
-    await waitFor(() => expect(disconnectButton).toBeDisabled());
-  });
-
-  it("should call logout when pressing the disconnect tokens button", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    const logoutSpy = vi.spyOn(OpenHands, "logout");
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      provider_tokens_set: {
-        github: true,
-        gitlab: false,
-      },
-    });
-
-    renderGitSettingsScreen();
-
-    const disconnectButton = await screen.findByTestId(
-      "disconnect-tokens-button",
-    );
-    await waitFor(() => expect(disconnectButton).not.toBeDisabled());
-    await userEvent.click(disconnectButton);
-
-    expect(logoutSpy).toHaveBeenCalled();
-  });
-
-  // flaky test
-  it.skip("should disable the button when submitting changes", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-
-    renderGitSettingsScreen();
-
-    const submit = await screen.findByTestId("submit-button");
-    expect(submit).toBeDisabled();
-
-    const githubInput = await screen.findByTestId("github-token-input");
-    await userEvent.type(githubInput, "test-token");
-    expect(submit).not.toBeDisabled();
-
-    // submit the form
-    await userEvent.click(submit);
-    expect(saveSettingsSpy).toHaveBeenCalled();
-
-    expect(submit).toHaveTextContent("Saving...");
-    expect(submit).toBeDisabled();
-
-    await waitFor(() => expect(submit).toHaveTextContent("Save"));
-  });
-
-  it("should disable the button after submitting changes", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    getConfigSpy.mockResolvedValue(VALID_OSS_CONFIG);
-
-    renderGitSettingsScreen();
-    await screen.findByTestId("git-settings-screen");
-
-    const submit = await screen.findByTestId("submit-button");
-    expect(submit).toBeDisabled();
-
-    const githubInput = await screen.findByTestId("github-token-input");
-    await userEvent.type(githubInput, "test-token");
-    expect(submit).not.toBeDisabled();
-
-    // submit the form
-    await userEvent.click(submit);
-    expect(saveSettingsSpy).toHaveBeenCalled();
-    expect(submit).toBeDisabled();
-
-    const gitlabInput = await screen.findByTestId("gitlab-token-input");
-    await userEvent.type(gitlabInput, "test-token");
-    expect(gitlabInput).toHaveValue("test-token");
-    expect(submit).not.toBeDisabled();
-
-    // submit the form
-    await userEvent.click(submit);
-    expect(saveSettingsSpy).toHaveBeenCalled();
-
-    await waitFor(() => expect(submit).toBeDisabled());
-  });
-});
-
-describe("Status toasts", () => {
-  it("should call displaySuccessToast when the settings are saved", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
-
-    const displaySuccessToastSpy = vi.spyOn(
-      ToastHandlers,
-      "displaySuccessToast",
-    );
-
-    renderGitSettingsScreen();
-
-    // Toggle setting to change
-    const githubInput = await screen.findByTestId("github-token-input");
-    await userEvent.type(githubInput, "test-token");
-
-    const submit = await screen.findByTestId("submit-button");
-    await userEvent.click(submit);
-
-    expect(saveSettingsSpy).toHaveBeenCalled();
-    await waitFor(() => expect(displaySuccessToastSpy).toHaveBeenCalled());
-  });
-
-  it("should call displayErrorToast when the settings fail to save", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue(MOCK_DEFAULT_USER_SETTINGS);
-
-    const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
-
-    saveSettingsSpy.mockRejectedValue(new Error("Failed to save settings"));
-
-    renderGitSettingsScreen();
-
-    // Toggle setting to change
-    const gitlabInput = await screen.findByTestId("gitlab-token-input");
-    await userEvent.type(gitlabInput, "test-token");
-
-    const submit = await screen.findByTestId("submit-button");
-    await userEvent.click(submit);
-
-    expect(saveSettingsSpy).toHaveBeenCalled();
-    expect(displayErrorToastSpy).toHaveBeenCalled();
-  });
-});

frontend/__tests__/routes/home-screen.test.tsx

@@ -91,13 +91,6 @@ describe("HomeScreen", () => {
     screen.getByTestId("task-suggestions");
   });
 
-  it("should have responsive layout for mobile and desktop screens", async () => {
-    renderHomeScreen();
-    
-    const mainContainer = screen.getByTestId("home-screen").querySelector("main");
-    expect(mainContainer).toHaveClass("flex", "flex-col", "md:flex-row");
-  });
-
   it("should filter the suggested tasks based on the selected repository", async () => {
     const retrieveUserGitRepositoriesSpy = vi.spyOn(
       GitService,

frontend/__tests__/routes/llm-settings.test.tsx

@@ -1,674 +0,0 @@
-import { render, screen, waitFor, within } from "@testing-library/react";
-import userEvent from "@testing-library/user-event";
-import { beforeEach, describe, expect, it, vi } from "vitest";
-import { QueryClientProvider, QueryClient } from "@tanstack/react-query";
-import LlmSettingsScreen from "#/routes/llm-settings";
-import OpenHands from "#/api/open-hands";
-import {
-  MOCK_DEFAULT_USER_SETTINGS,
-  resetTestHandlersMockSettings,
-} from "#/mocks/handlers";
-import { AuthProvider } from "#/context/auth-context";
-import * as AdvancedSettingsUtlls from "#/utils/has-advanced-settings-set";
-import * as ToastHandlers from "#/utils/custom-toast-handlers";
-
-const renderLlmSettingsScreen = () =>
-  render(<LlmSettingsScreen />, {
-    wrapper: ({ children }) => (
-      <QueryClientProvider client={new QueryClient()}>
-        <AuthProvider>{children}</AuthProvider>
-      </QueryClientProvider>
-    ),
-  });
-
-beforeEach(() => {
-  vi.resetAllMocks();
-  resetTestHandlersMockSettings();
-});
-
-describe("Content", () => {
-  describe("Basic form", () => {
-    it("should render the basic form by default", async () => {
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      const basicFom = screen.getByTestId("llm-settings-form-basic");
-      within(basicFom).getByTestId("llm-provider-input");
-      within(basicFom).getByTestId("llm-model-input");
-      within(basicFom).getByTestId("llm-api-key-input");
-      within(basicFom).getByTestId("llm-api-key-help-anchor");
-    });
-
-    it("should render the default values if non exist", async () => {
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      const provider = screen.getByTestId("llm-provider-input");
-      const model = screen.getByTestId("llm-model-input");
-      const apiKey = screen.getByTestId("llm-api-key-input");
-
-      await waitFor(() => {
-        expect(provider).toHaveValue("Anthropic");
-        expect(model).toHaveValue("claude-3-5-sonnet-20241022");
-
-        expect(apiKey).toHaveValue("");
-        expect(apiKey).toHaveProperty("placeholder", "");
-      });
-    });
-
-    it("should render the existing settings values", async () => {
-      const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-      getSettingsSpy.mockResolvedValue({
-        ...MOCK_DEFAULT_USER_SETTINGS,
-        llm_model: "openai/gpt-4o",
-        llm_api_key_set: true,
-      });
-
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      const provider = screen.getByTestId("llm-provider-input");
-      const model = screen.getByTestId("llm-model-input");
-      const apiKey = screen.getByTestId("llm-api-key-input");
-
-      await waitFor(() => {
-        expect(provider).toHaveValue("OpenAI");
-        expect(model).toHaveValue("gpt-4o");
-
-        expect(apiKey).toHaveValue("");
-        expect(apiKey).toHaveProperty("placeholder", "<hidden>");
-        expect(screen.getByTestId("set-indicator")).toBeInTheDocument();
-      });
-    });
-  });
-
-  describe("Advanced form", () => {
-    it("should render the advanced form if the switch is toggled", async () => {
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-      const basicForm = screen.getByTestId("llm-settings-form-basic");
-
-      expect(
-        screen.queryByTestId("llm-settings-form-advanced"),
-      ).not.toBeInTheDocument();
-      expect(basicForm).toBeInTheDocument();
-
-      await userEvent.click(advancedSwitch);
-
-      expect(
-        screen.queryByTestId("llm-settings-form-advanced"),
-      ).toBeInTheDocument();
-      expect(basicForm).not.toBeInTheDocument();
-
-      const advancedForm = screen.getByTestId("llm-settings-form-advanced");
-      within(advancedForm).getByTestId("llm-custom-model-input");
-      within(advancedForm).getByTestId("base-url-input");
-      within(advancedForm).getByTestId("llm-api-key-input");
-      within(advancedForm).getByTestId("llm-api-key-help-anchor");
-      within(advancedForm).getByTestId("agent-input");
-      within(advancedForm).getByTestId("enable-confirmation-mode-switch");
-      within(advancedForm).getByTestId("enable-memory-condenser-switch");
-
-      await userEvent.click(advancedSwitch);
-      expect(
-        screen.queryByTestId("llm-settings-form-advanced"),
-      ).not.toBeInTheDocument();
-      expect(screen.getByTestId("llm-settings-form-basic")).toBeInTheDocument();
-    });
-
-    it("should render the default advanced settings", async () => {
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-      expect(advancedSwitch).not.toBeChecked();
-
-      await userEvent.click(advancedSwitch);
-
-      const model = screen.getByTestId("llm-custom-model-input");
-      const baseUrl = screen.getByTestId("base-url-input");
-      const apiKey = screen.getByTestId("llm-api-key-input");
-      const agent = screen.getByTestId("agent-input");
-      const confirmation = screen.getByTestId(
-        "enable-confirmation-mode-switch",
-      );
-      const condensor = screen.getByTestId("enable-memory-condenser-switch");
-
-      expect(model).toHaveValue("anthropic/claude-3-5-sonnet-20241022");
-      expect(baseUrl).toHaveValue("");
-      expect(apiKey).toHaveValue("");
-      expect(apiKey).toHaveProperty("placeholder", "");
-      expect(agent).toHaveValue("CodeActAgent");
-      expect(confirmation).not.toBeChecked();
-      expect(condensor).toBeChecked();
-
-      // check that security analyzer is present
-      expect(
-        screen.queryByTestId("security-analyzer-input"),
-      ).not.toBeInTheDocument();
-      await userEvent.click(confirmation);
-      screen.getByTestId("security-analyzer-input");
-    });
-
-    it("should render the advanced form if existings settings are advanced", async () => {
-      const hasAdvancedSettingsSetSpy = vi.spyOn(
-        AdvancedSettingsUtlls,
-        "hasAdvancedSettingsSet",
-      );
-      hasAdvancedSettingsSetSpy.mockReturnValue(true);
-
-      renderLlmSettingsScreen();
-
-      await waitFor(() => {
-        const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-        expect(advancedSwitch).toBeChecked();
-        screen.getByTestId("llm-settings-form-advanced");
-      });
-    });
-
-    it("should render existing advanced settings correctly", async () => {
-      const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-      getSettingsSpy.mockResolvedValue({
-        ...MOCK_DEFAULT_USER_SETTINGS,
-        llm_model: "openai/gpt-4o",
-        llm_base_url: "https://api.openai.com/v1/chat/completions",
-        llm_api_key_set: true,
-        agent: "CoActAgent",
-        confirmation_mode: true,
-        enable_default_condenser: false,
-        security_analyzer: "mock-invariant",
-      });
-
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      const model = screen.getByTestId("llm-custom-model-input");
-      const baseUrl = screen.getByTestId("base-url-input");
-      const apiKey = screen.getByTestId("llm-api-key-input");
-      const agent = screen.getByTestId("agent-input");
-      const confirmation = screen.getByTestId(
-        "enable-confirmation-mode-switch",
-      );
-      const condensor = screen.getByTestId("enable-memory-condenser-switch");
-      const securityAnalyzer = screen.getByTestId("security-analyzer-input");
-
-      await waitFor(() => {
-        expect(model).toHaveValue("openai/gpt-4o");
-        expect(baseUrl).toHaveValue(
-          "https://api.openai.com/v1/chat/completions",
-        );
-        expect(apiKey).toHaveValue("");
-        expect(apiKey).toHaveProperty("placeholder", "<hidden>");
-        expect(agent).toHaveValue("CoActAgent");
-        expect(confirmation).toBeChecked();
-        expect(condensor).not.toBeChecked();
-        expect(securityAnalyzer).toHaveValue("mock-invariant");
-      });
-    });
-  });
-
-  it.todo("should render an indicator if the llm api key is set");
-});
-
-describe("Form submission", () => {
-  it("should submit the basic form with the correct values", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-
-    renderLlmSettingsScreen();
-    await screen.findByTestId("llm-settings-screen");
-
-    const provider = screen.getByTestId("llm-provider-input");
-    const model = screen.getByTestId("llm-model-input");
-    const apiKey = screen.getByTestId("llm-api-key-input");
-
-    // select provider
-    await userEvent.click(provider);
-    const providerOption = screen.getByText("OpenAI");
-    await userEvent.click(providerOption);
-    expect(provider).toHaveValue("OpenAI");
-
-    // enter api key
-    await userEvent.type(apiKey, "test-api-key");
-
-    // select model
-    await userEvent.click(model);
-    const modelOption = screen.getByText("gpt-4o");
-    await userEvent.click(modelOption);
-    expect(model).toHaveValue("gpt-4o");
-
-    const submitButton = screen.getByTestId("submit-button");
-    await userEvent.click(submitButton);
-
-    expect(saveSettingsSpy).toHaveBeenCalledWith(
-      expect.objectContaining({
-        llm_model: "openai/gpt-4o",
-        llm_api_key: "test-api-key",
-      }),
-    );
-  });
-
-  it("should submit the advanced form with the correct values", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-
-    renderLlmSettingsScreen();
-    await screen.findByTestId("llm-settings-screen");
-
-    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-    await userEvent.click(advancedSwitch);
-
-    const model = screen.getByTestId("llm-custom-model-input");
-    const baseUrl = screen.getByTestId("base-url-input");
-    const apiKey = screen.getByTestId("llm-api-key-input");
-    const agent = screen.getByTestId("agent-input");
-    const confirmation = screen.getByTestId("enable-confirmation-mode-switch");
-    const condensor = screen.getByTestId("enable-memory-condenser-switch");
-
-    // enter custom model
-    await userEvent.clear(model);
-    await userEvent.type(model, "openai/gpt-4o");
-    expect(model).toHaveValue("openai/gpt-4o");
-
-    // enter base url
-    await userEvent.type(baseUrl, "https://api.openai.com/v1/chat/completions");
-    expect(baseUrl).toHaveValue("https://api.openai.com/v1/chat/completions");
-
-    // enter api key
-    await userEvent.type(apiKey, "test-api-key");
-
-    // toggle confirmation mode
-    await userEvent.click(confirmation);
-    expect(confirmation).toBeChecked();
-
-    // toggle memory condensor
-    await userEvent.click(condensor);
-    expect(condensor).not.toBeChecked();
-
-    // select agent
-    await userEvent.click(agent);
-    const agentOption = screen.getByText("CoActAgent");
-    await userEvent.click(agentOption);
-    expect(agent).toHaveValue("CoActAgent");
-
-    // select security analyzer
-    const securityAnalyzer = screen.getByTestId("security-analyzer-input");
-    await userEvent.click(securityAnalyzer);
-    const securityAnalyzerOption = screen.getByText("mock-invariant");
-    await userEvent.click(securityAnalyzerOption);
-
-    const submitButton = screen.getByTestId("submit-button");
-    await userEvent.click(submitButton);
-
-    expect(saveSettingsSpy).toHaveBeenCalledWith(
-      expect.objectContaining({
-        llm_model: "openai/gpt-4o",
-        llm_base_url: "https://api.openai.com/v1/chat/completions",
-        agent: "CoActAgent",
-        confirmation_mode: true,
-        enable_default_condenser: false,
-        security_analyzer: "mock-invariant",
-      }),
-    );
-  });
-
-  it("should disable the button if there are no changes in the basic form", async () => {
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      llm_model: "openai/gpt-4o",
-      llm_api_key_set: true,
-    });
-
-    renderLlmSettingsScreen();
-    await screen.findByTestId("llm-settings-screen");
-    screen.getByTestId("llm-settings-form-basic");
-
-    const submitButton = screen.getByTestId("submit-button");
-    expect(submitButton).toBeDisabled();
-
-    const model = screen.getByTestId("llm-model-input");
-    const apiKey = screen.getByTestId("llm-api-key-input");
-
-    // select model
-    await userEvent.click(model);
-    const modelOption = screen.getByText("gpt-4o-mini");
-    await userEvent.click(modelOption);
-    expect(model).toHaveValue("gpt-4o-mini");
-    expect(submitButton).not.toBeDisabled();
-
-    // reset model
-    await userEvent.click(model);
-    const modelOption2 = screen.getByText("gpt-4o");
-    await userEvent.click(modelOption2);
-    expect(model).toHaveValue("gpt-4o");
-    expect(submitButton).toBeDisabled();
-
-    // set api key
-    await userEvent.type(apiKey, "test-api-key");
-    expect(apiKey).toHaveValue("test-api-key");
-    expect(submitButton).not.toBeDisabled();
-
-    // reset api key
-    await userEvent.clear(apiKey);
-    expect(apiKey).toHaveValue("");
-    expect(submitButton).toBeDisabled();
-  });
-
-  it("should disable the button if there are no changes in the advanced form", async () => {
-    const getSettingsSpy = vi.spyOn(OpenHands, "getSettings");
-    getSettingsSpy.mockResolvedValue({
-      ...MOCK_DEFAULT_USER_SETTINGS,
-      llm_model: "openai/gpt-4o",
-      llm_base_url: "https://api.openai.com/v1/chat/completions",
-      llm_api_key_set: true,
-      confirmation_mode: true,
-    });
-
-    renderLlmSettingsScreen();
-    await screen.findByTestId("llm-settings-screen");
-    screen.getByTestId("llm-settings-form-advanced");
-
-    const submitButton = screen.getByTestId("submit-button");
-    expect(submitButton).toBeDisabled();
-
-    const model = screen.getByTestId("llm-custom-model-input");
-    const baseUrl = screen.getByTestId("base-url-input");
-    const apiKey = screen.getByTestId("llm-api-key-input");
-    const agent = screen.getByTestId("agent-input");
-    const confirmation = screen.getByTestId("enable-confirmation-mode-switch");
-    const condensor = screen.getByTestId("enable-memory-condenser-switch");
-
-    // enter custom model
-    await userEvent.type(model, "-mini");
-    expect(model).toHaveValue("openai/gpt-4o-mini");
-    expect(submitButton).not.toBeDisabled();
-
-    // reset model
-    await userEvent.clear(model);
-    expect(model).toHaveValue("");
-    expect(submitButton).toBeDisabled();
-
-    await userEvent.type(model, "openai/gpt-4o");
-    expect(model).toHaveValue("openai/gpt-4o");
-    expect(submitButton).toBeDisabled();
-
-    // enter base url
-    await userEvent.type(baseUrl, "/extra");
-    expect(baseUrl).toHaveValue(
-      "https://api.openai.com/v1/chat/completions/extra",
-    );
-    expect(submitButton).not.toBeDisabled();
-
-    await userEvent.clear(baseUrl);
-    expect(baseUrl).toHaveValue("");
-    expect(submitButton).not.toBeDisabled();
-
-    await userEvent.type(baseUrl, "https://api.openai.com/v1/chat/completions");
-    expect(baseUrl).toHaveValue("https://api.openai.com/v1/chat/completions");
-    expect(submitButton).toBeDisabled();
-
-    // set api key
-    await userEvent.type(apiKey, "test-api-key");
-    expect(apiKey).toHaveValue("test-api-key");
-    expect(submitButton).not.toBeDisabled();
-
-    // reset api key
-    await userEvent.clear(apiKey);
-    expect(apiKey).toHaveValue("");
-    expect(submitButton).toBeDisabled();
-
-    // set agent
-    await userEvent.clear(agent);
-    await userEvent.type(agent, "test-agent");
-    expect(agent).toHaveValue("test-agent");
-    expect(submitButton).not.toBeDisabled();
-
-    // reset agent
-    await userEvent.clear(agent);
-    expect(agent).toHaveValue("");
-    expect(submitButton).toBeDisabled();
-
-    await userEvent.type(agent, "CodeActAgent");
-    expect(agent).toHaveValue("CodeActAgent");
-    expect(submitButton).toBeDisabled();
-
-    // toggle confirmation mode
-    await userEvent.click(confirmation);
-    expect(confirmation).not.toBeChecked();
-    expect(submitButton).not.toBeDisabled();
-    await userEvent.click(confirmation);
-    expect(confirmation).toBeChecked();
-    expect(submitButton).toBeDisabled();
-
-    // toggle memory condensor
-    await userEvent.click(condensor);
-    expect(condensor).not.toBeChecked();
-    expect(submitButton).not.toBeDisabled();
-    await userEvent.click(condensor);
-    expect(condensor).toBeChecked();
-    expect(submitButton).toBeDisabled();
-
-    // select security analyzer
-    const securityAnalyzer = screen.getByTestId("security-analyzer-input");
-    await userEvent.click(securityAnalyzer);
-    const securityAnalyzerOption = screen.getByText("mock-invariant");
-    await userEvent.click(securityAnalyzerOption);
-    expect(securityAnalyzer).toHaveValue("mock-invariant");
-
-    expect(submitButton).not.toBeDisabled();
-
-    await userEvent.clear(securityAnalyzer);
-    expect(securityAnalyzer).toHaveValue("");
-    expect(submitButton).toBeDisabled();
-  });
-
-  it("should reset button state when switching between forms", async () => {
-    renderLlmSettingsScreen();
-    await screen.findByTestId("llm-settings-screen");
-
-    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-    const submitButton = screen.getByTestId("submit-button");
-
-    expect(submitButton).toBeDisabled();
-
-    // dirty the basic form
-    const apiKey = screen.getByTestId("llm-api-key-input");
-    await userEvent.type(apiKey, "test-api-key");
-    expect(submitButton).not.toBeDisabled();
-
-    await userEvent.click(advancedSwitch);
-    expect(submitButton).toBeDisabled();
-
-    // dirty the advanced form
-    const model = screen.getByTestId("llm-custom-model-input");
-    await userEvent.type(model, "openai/gpt-4o");
-    expect(submitButton).not.toBeDisabled();
-
-    await userEvent.click(advancedSwitch);
-    expect(submitButton).toBeDisabled();
-  });
-
-  // flaky test
-  it.skip("should disable the button when submitting changes", async () => {
-    const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-
-    renderLlmSettingsScreen();
-    await screen.findByTestId("llm-settings-screen");
-
-    const apiKey = screen.getByTestId("llm-api-key-input");
-    await userEvent.type(apiKey, "test-api-key");
-
-    const submitButton = screen.getByTestId("submit-button");
-    await userEvent.click(submitButton);
-
-    expect(saveSettingsSpy).toHaveBeenCalledWith(
-      expect.objectContaining({
-        llm_api_key: "test-api-key",
-      }),
-    );
-
-    expect(submitButton).toHaveTextContent("Saving...");
-    expect(submitButton).toBeDisabled();
-
-    await waitFor(() => {
-      expect(submitButton).toHaveTextContent("Save");
-      expect(submitButton).toBeDisabled();
-    });
-  });
-});
-
-describe("Status toasts", () => {
-  describe("Basic form", () => {
-    it("should call displaySuccessToast when the settings are saved", async () => {
-      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-
-      const displaySuccessToastSpy = vi.spyOn(
-        ToastHandlers,
-        "displaySuccessToast",
-      );
-
-      renderLlmSettingsScreen();
-
-      // Toggle setting to change
-      const apiKeyInput = await screen.findByTestId("llm-api-key-input");
-      await userEvent.type(apiKeyInput, "test-api-key");
-
-      const submit = await screen.findByTestId("submit-button");
-      await userEvent.click(submit);
-
-      expect(saveSettingsSpy).toHaveBeenCalled();
-      await waitFor(() => expect(displaySuccessToastSpy).toHaveBeenCalled());
-    });
-
-    it("should call displayErrorToast when the settings fail to save", async () => {
-      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-
-      const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
-
-      saveSettingsSpy.mockRejectedValue(new Error("Failed to save settings"));
-
-      renderLlmSettingsScreen();
-
-      // Toggle setting to change
-      const apiKeyInput = await screen.findByTestId("llm-api-key-input");
-      await userEvent.type(apiKeyInput, "test-api-key");
-
-      const submit = await screen.findByTestId("submit-button");
-      await userEvent.click(submit);
-
-      expect(saveSettingsSpy).toHaveBeenCalled();
-      expect(displayErrorToastSpy).toHaveBeenCalled();
-    });
-  });
-
-  describe("Advanced form", () => {
-    it("should call displaySuccessToast when the settings are saved", async () => {
-      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-
-      const displaySuccessToastSpy = vi.spyOn(
-        ToastHandlers,
-        "displaySuccessToast",
-      );
-
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-      await userEvent.click(advancedSwitch);
-      await screen.findByTestId("llm-settings-form-advanced");
-
-      // Toggle setting to change
-      const apiKeyInput = await screen.findByTestId("llm-api-key-input");
-      await userEvent.type(apiKeyInput, "test-api-key");
-
-      const submit = await screen.findByTestId("submit-button");
-      await userEvent.click(submit);
-
-      expect(saveSettingsSpy).toHaveBeenCalled();
-      await waitFor(() => expect(displaySuccessToastSpy).toHaveBeenCalled());
-    });
-
-    it("should call displayErrorToast when the settings fail to save", async () => {
-      const saveSettingsSpy = vi.spyOn(OpenHands, "saveSettings");
-
-      const displayErrorToastSpy = vi.spyOn(ToastHandlers, "displayErrorToast");
-
-      saveSettingsSpy.mockRejectedValue(new Error("Failed to save settings"));
-
-      renderLlmSettingsScreen();
-      await screen.findByTestId("llm-settings-screen");
-
-      const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-      await userEvent.click(advancedSwitch);
-      await screen.findByTestId("llm-settings-form-advanced");
-
-      // Toggle setting to change
-      const apiKeyInput = await screen.findByTestId("llm-api-key-input");
-      await userEvent.type(apiKeyInput, "test-api-key");
-
-      const submit = await screen.findByTestId("submit-button");
-      await userEvent.click(submit);
-
-      expect(saveSettingsSpy).toHaveBeenCalled();
-      expect(displayErrorToastSpy).toHaveBeenCalled();
-    });
-  });
-});
-
-describe("SaaS mode", () => {
-  it("should not render the runtime settings input in oss mode", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    // @ts-expect-error - only return mode
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "oss",
-    });
-
-    renderLlmSettingsScreen();
-    await screen.findByTestId("llm-settings-screen");
-
-    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-    await userEvent.click(advancedSwitch);
-    await screen.findByTestId("llm-settings-form-advanced");
-
-    const runtimeSettingsInput = screen.queryByTestId("runtime-settings-input");
-    expect(runtimeSettingsInput).not.toBeInTheDocument();
-  });
-
-  it("should render the runtime settings input in saas mode", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    // @ts-expect-error - only return mode
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "saas",
-    });
-
-    renderLlmSettingsScreen();
-    await screen.findByTestId("llm-settings-screen");
-
-    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-    await userEvent.click(advancedSwitch);
-    await screen.findByTestId("llm-settings-form-advanced");
-
-    const runtimeSettingsInput = screen.queryByTestId("runtime-settings-input");
-    expect(runtimeSettingsInput).toBeInTheDocument();
-  });
-
-  it("should always render the runtime settings input as disabled", async () => {
-    const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
-    // @ts-expect-error - only return mode
-    getConfigSpy.mockResolvedValue({
-      APP_MODE: "saas",
-    });
-
-    renderLlmSettingsScreen();
-    await screen.findByTestId("llm-settings-screen");
-
-    const advancedSwitch = screen.getByTestId("advanced-settings-switch");
-    await userEvent.click(advancedSwitch);
-    await screen.findByTestId("llm-settings-form-advanced");
-
-    const runtimeSettingsInput = screen.queryByTestId("runtime-settings-input");
-    expect(runtimeSettingsInput).toBeInTheDocument();
-    expect(runtimeSettingsInput).toBeDisabled();
-  });
-});

frontend/__tests__/routes/settings-with-payment.test.tsx

@@ -1,4 +1,4 @@
-import { screen, within } from "@testing-library/react";
+import { screen, waitFor, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
 import { createRoutesStub } from "react-router";
@@ -7,30 +7,6 @@ import OpenHands from "#/api/open-hands";
 import SettingsScreen from "#/routes/settings";
 import { PaymentForm } from "#/components/features/payment/payment-form";
 
-// Mock the i18next hook
-vi.mock("react-i18next", async () => {
-  const actual = await vi.importActual<typeof import("react-i18next")>("react-i18next");
-  return {
-    ...actual,
-    useTranslation: () => ({
-      t: (key: string) => {
-        const translations: Record<string, string> = {
-          "SETTINGS$NAV_GIT": "Git",
-          "SETTINGS$NAV_APPLICATION": "Application",
-          "SETTINGS$NAV_CREDITS": "Credits",
-          "SETTINGS$NAV_API_KEYS": "API Keys",
-          "SETTINGS$NAV_LLM": "LLM",
-          "SETTINGS$TITLE": "Settings"
-        };
-        return translations[key] || key;
-      },
-      i18n: {
-        changeLanguage: vi.fn(),
-      },
-    }),
-  };
-});
-
 describe("Settings Billing", () => {
   const getConfigSpy = vi.spyOn(OpenHands, "getConfig");
 
@@ -43,22 +19,18 @@ describe("Settings Billing", () => {
           Component: () => <PaymentForm />,
           path: "/settings/billing",
         },
-        {
-          Component: () => <div data-testid="git-settings-screen" />,
-          path: "/settings/git",
-        },
       ],
     },
   ]);
 
   const renderSettingsScreen = () =>
-    renderWithProviders(<RoutesStub initialEntries={["/settings/billing"]} />);
+    renderWithProviders(<RoutesStub initialEntries={["/settings"]} />);
 
   afterEach(() => {
     vi.clearAllMocks();
   });
 
-  it("should not render the credits tab if OSS mode", async () => {
+  it("should not render the navbar if OSS mode", async () => {
     getConfigSpy.mockResolvedValue({
       APP_MODE: "oss",
       GITHUB_CLIENT_ID: "123",
@@ -71,12 +43,15 @@ describe("Settings Billing", () => {
 
     renderSettingsScreen();
 
-    const navbar = await screen.findByTestId("settings-navbar");
-    const credits = within(navbar).queryByText("Credits");
-    expect(credits).not.toBeInTheDocument();
+    // Wait for the settings screen to be rendered
+    await screen.findByTestId("settings-screen");
+
+    // Then check that the navbar is not present
+    const navbar = screen.queryByTestId("settings-navbar");
+    expect(navbar).not.toBeInTheDocument();
   });
 
-  it("should render the credits tab if SaaS mode and billing is enabled", async () => {
+  it("should render the navbar if SaaS mode", async () => {
     getConfigSpy.mockResolvedValue({
       APP_MODE: "saas",
       GITHUB_CLIENT_ID: "123",
@@ -89,8 +64,11 @@ describe("Settings Billing", () => {
 
     renderSettingsScreen();
 
-    const navbar = await screen.findByTestId("settings-navbar");
-    within(navbar).getByText("Credits");
+    await waitFor(() => {
+      const navbar = screen.getByTestId("settings-navbar");
+      within(navbar).getByText("Account");
+      within(navbar).getByText("Credits");
+    });
   });
 
   it("should render the billing settings if clicking the credits item", async () => {
@@ -112,6 +90,6 @@ describe("Settings Billing", () => {
     await user.click(credits);
 
     const billingSection = await screen.findByTestId("billing-settings");
-    expect(billingSection).toBeInTheDocument();
+    within(billingSection).getByText("PAYMENT$MANAGE_CREDITS");
   });
 });

frontend/__tests__/utils/has-advanced-settings-set.test.ts

@@ -7,10 +7,6 @@ describe("hasAdvancedSettingsSet", () => {
     expect(hasAdvancedSettingsSet(DEFAULT_SETTINGS)).toBe(false);
   });
 
-  it("should return false if an empty object", () => {
-    expect(hasAdvancedSettingsSet({})).toBe(false);
-  });
-
   describe("should be true if", () => {
     test("LLM_BASE_URL is set", () => {
       expect(
@@ -30,6 +26,15 @@ describe("hasAdvancedSettingsSet", () => {
       ).toBe(true);
     });
 
+    test("REMOTE_RUNTIME_RESOURCE_FACTOR is not default value", () => {
+      expect(
+        hasAdvancedSettingsSet({
+          ...DEFAULT_SETTINGS,
+          REMOTE_RUNTIME_RESOURCE_FACTOR: 999,
+        }),
+      ).toBe(true);
+    });
+
     test("CONFIRMATION_MODE is true", () => {
       expect(
         hasAdvancedSettingsSet({

frontend/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "openhands-frontend",
-  "version": "0.34.0",
+  "version": "0.35.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "openhands-frontend",
-      "version": "0.34.0",
+      "version": "0.35.1",
       "dependencies": {
         "@heroui/react": "2.7.6",
         "@microlink/react-json-view": "^1.26.1",

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.34.0",
+  "version": "0.35.1",
   "private": true,
   "type": "module",
   "engines": {

frontend/scripts/check-unlocalized-strings.cjs

@@ -107,10 +107,6 @@ function isRawTranslationKey(str) {
 const EXCLUDED_TECHNICAL_STRINGS = [
   "openid email profile", // OAuth scope string - not user-facing
   "OPEN_ISSUE", // Task type identifier, not a UI string
-  "Merge Request", // Git provider specific terminology
-  "GitLab API", // Git provider specific terminology
-  "Pull Request", // Git provider specific terminology
-  "GitHub API", // Git provider specific terminology
 ];
 
 function isExcludedTechnicalString(str) {

frontend/src/components/features/diff-viewer/file-diff-viewer.tsx

@@ -1,4 +1,4 @@
-import { DiffEditor, Monaco } from "@monaco-editor/react";
+import { DiffEditor } from "@monaco-editor/react";
 import React from "react";
 import { editor as editor_t } from "monaco-editor";
 import { LuFileDiff, LuFileMinus, LuFilePlus } from "react-icons/lu";
@@ -88,29 +88,6 @@ export function FileDiffViewer({ path, type }: FileDiffViewerProps) {
     }
   }, []);
 
-  const beforeMount = (monaco: Monaco) => {
-    monaco.editor.defineTheme("custom-diff-theme", {
-      base: "vs-dark",
-      inherit: true,
-      rules: [
-        { token: "comment", foreground: "6a9955" },
-        { token: "keyword", foreground: "569cd6" },
-        { token: "string", foreground: "ce9178" },
-        { token: "number", foreground: "b5cea8" },
-      ],
-      colors: {
-        "diffEditor.insertedTextBackground": "#014b01AA", // Stronger green background
-        "diffEditor.removedTextBackground": "#750000AA", // Stronger red background
-        "diffEditor.insertedLineBackground": "#003f00AA", // Dark green for added lines
-        "diffEditor.removedLineBackground": "#5a0000AA", // Dark red for removed lines
-        "diffEditor.border": "#444444", // Border between diff editors
-
-        "editorUnnecessaryCode.border": "#00000000", // No border for unnecessary code
-        "editorUnnecessaryCode.opacity": "#00000077", // Slightly faded
-      },
-    });
-  };
-
   const handleEditorDidMount = (editor: editor_t.IStandaloneDiffEditor) => {
     diffEditorRef.current = editor;
     updateEditorHeight();
@@ -168,9 +145,8 @@ export function FileDiffViewer({ path, type }: FileDiffViewerProps) {
             language={getLanguageFromPath(filePath)}
             original={isAdded ? "" : diff.original}
             modified={isDeleted ? "" : diff.modified}
-            theme="custom-diff-theme"
+            theme="vs-dark"
             onMount={handleEditorDidMount}
-            beforeMount={beforeMount}
             options={{
               renderValidationDecorations: "off",
               readOnly: true,

frontend/src/components/features/settings/app-settings/app-settings-inputs-skeleton.tsx

@@ -1,15 +0,0 @@
-import { InputSkeleton } from "../input-skeleton";
-import { SwitchSkeleton } from "../switch-skeleton";
-
-export function AppSettingsInputsSkeleton() {
-  return (
-    <div
-      data-testid="app-settings-skeleton"
-      className="px-11 py-9 flex flex-col gap-6"
-    >
-      <InputSkeleton />
-      <SwitchSkeleton />
-      <SwitchSkeleton />
-    </div>
-  );
-}

frontend/src/components/features/settings/app-settings/language-input.tsx

@@ -1,34 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { AvailableLanguages } from "#/i18n";
-import { I18nKey } from "#/i18n/declaration";
-import { SettingsDropdownInput } from "../settings-dropdown-input";
-
-interface LanguageInputProps {
-  name: string;
-  onChange: (value: string) => void;
-  defaultKey: string;
-}
-
-export function LanguageInput({
-  defaultKey,
-  onChange,
-  name,
-}: LanguageInputProps) {
-  const { t } = useTranslation();
-
-  return (
-    <SettingsDropdownInput
-      testId={name}
-      name={name}
-      onInputChange={onChange}
-      label={t(I18nKey.SETTINGS$LANGUAGE)}
-      items={AvailableLanguages.map((l) => ({
-        key: l.value,
-        label: l.label,
-      }))}
-      defaultSelectedKey={defaultKey}
-      isClearable={false}
-      wrapperClassName="w-[680px]"
-    />
-  );
-}

frontend/src/components/features/settings/brand-button.tsx

@@ -2,7 +2,6 @@ import { cn } from "#/utils/utils";
 
 interface BrandButtonProps {
   testId?: string;
-  name?: string;
   variant: "primary" | "secondary" | "danger";
   type: React.ButtonHTMLAttributes<HTMLButtonElement>["type"];
   isDisabled?: boolean;
@@ -13,7 +12,6 @@ interface BrandButtonProps {
 
 export function BrandButton({
   testId,
-  name,
   children,
   variant,
   type,
@@ -24,7 +22,6 @@ export function BrandButton({
 }: React.PropsWithChildren<BrandButtonProps>) {
   return (
     <button
-      name={name}
       data-testid={testId}
       disabled={isDisabled}
       // The type is alreadt passed as a prop to the button component

frontend/src/components/features/settings/git-settings/configure-github-repositories-anchor.tsx

@@ -1,27 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-import { BrandButton } from "../brand-button";
-
-interface ConfigureGitHubRepositoriesAnchorProps {
-  slug: string;
-}
-
-export function ConfigureGitHubRepositoriesAnchor({
-  slug,
-}: ConfigureGitHubRepositoriesAnchorProps) {
-  const { t } = useTranslation();
-
-  return (
-    <a
-      data-testid="configure-github-repositories-button"
-      href={`https://github.com/apps/${slug}/installations/new`}
-      target="_blank"
-      rel="noreferrer noopener"
-      className="px-11 py-9"
-    >
-      <BrandButton type="button" variant="secondary">
-        {t(I18nKey.GITHUB$CONFIGURE_REPOS)}
-      </BrandButton>
-    </a>
-  );
-}

frontend/src/components/features/settings/git-settings/github-settings-inputs-skeleton.tsx

@@ -1,18 +0,0 @@
-import { InputSkeleton } from "../input-skeleton";
-import { SubtextSkeleton } from "../subtext-skeleton";
-
-export function GitSettingInputsSkeleton() {
-  return (
-    <div className="px-11 py-9 flex flex-col gap-12">
-      <div className="flex flex-col gap-6">
-        <InputSkeleton />
-        <SubtextSkeleton />
-      </div>
-
-      <div className="flex flex-col gap-6">
-        <InputSkeleton />
-        <SubtextSkeleton />
-      </div>
-    </div>
-  );
-}

frontend/src/components/features/settings/git-settings/github-token-help-anchor.tsx

@@ -1,30 +0,0 @@
-import { Trans } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-
-export function GitHubTokenHelpAnchor() {
-  return (
-    <p data-testid="github-token-help-anchor" className="text-xs">
-      <Trans
-        i18nKey={I18nKey.GITHUB$TOKEN_HELP_TEXT}
-        components={[
-          <a
-            key="github-token-help-anchor-link"
-            aria-label="GitHub token help link"
-            href="https://github.com/settings/tokens/new?description=openhands-app&scopes=repo,user,workflow"
-            target="_blank"
-            className="underline underline-offset-2"
-            rel="noopener noreferrer"
-          />,
-          <a
-            key="github-token-help-anchor-link-2"
-            aria-label="GitHub token see more link"
-            href="https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/creating-a-personal-access-token"
-            target="_blank"
-            className="underline underline-offset-2"
-            rel="noopener noreferrer"
-          />,
-        ]}
-      />
-    </p>
-  );
-}

frontend/src/components/features/settings/git-settings/github-token-input.tsx

@@ -1,43 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-import { SettingsInput } from "../settings-input";
-import { GitHubTokenHelpAnchor } from "./github-token-help-anchor";
-import { KeyStatusIcon } from "../key-status-icon";
-
-interface GitHubTokenInputProps {
-  onChange: (value: string) => void;
-  isGitHubTokenSet: boolean;
-  name: string;
-}
-
-export function GitHubTokenInput({
-  onChange,
-  isGitHubTokenSet,
-  name,
-}: GitHubTokenInputProps) {
-  const { t } = useTranslation();
-
-  return (
-    <div className="flex flex-col gap-6">
-      <SettingsInput
-        testId={name}
-        name={name}
-        onChange={onChange}
-        label={t(I18nKey.GITHUB$TOKEN_LABEL)}
-        type="password"
-        className="w-[680px]"
-        placeholder={isGitHubTokenSet ? "<hidden>" : ""}
-        startContent={
-          isGitHubTokenSet && (
-            <KeyStatusIcon
-              testId="gh-set-token-indicator"
-              isSet={isGitHubTokenSet}
-            />
-          )
-        }
-      />
-
-      <GitHubTokenHelpAnchor />
-    </div>
-  );
-}

frontend/src/components/features/settings/git-settings/gitlab-token-help-anchor.tsx

@@ -1,30 +0,0 @@
-import { Trans } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-
-export function GitLabTokenHelpAnchor() {
-  return (
-    <p data-testid="gitlab-token-help-anchor" className="text-xs">
-      <Trans
-        i18nKey={I18nKey.GITLAB$TOKEN_HELP_TEXT}
-        components={[
-          <a
-            key="gitlab-token-help-anchor-link"
-            aria-label="Gitlab token help link"
-            href="https://gitlab.com/-/user_settings/personal_access_tokens?name=openhands-app&scopes=api,read_user,read_repository,write_repository"
-            target="_blank"
-            className="underline underline-offset-2"
-            rel="noopener noreferrer"
-          />,
-          <a
-            key="gitlab-token-help-anchor-link-2"
-            aria-label="GitLab token see more link"
-            href="https://docs.gitlab.com/user/profile/personal_access_tokens/"
-            target="_blank"
-            className="underline underline-offset-2"
-            rel="noopener noreferrer"
-          />,
-        ]}
-      />
-    </p>
-  );
-}

frontend/src/components/features/settings/git-settings/gitlab-token-input.tsx

@@ -1,43 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-import { SettingsInput } from "../settings-input";
-import { GitLabTokenHelpAnchor } from "./gitlab-token-help-anchor";
-import { KeyStatusIcon } from "../key-status-icon";
-
-interface GitLabTokenInputProps {
-  onChange: (value: string) => void;
-  isGitLabTokenSet: boolean;
-  name: string;
-}
-
-export function GitLabTokenInput({
-  onChange,
-  isGitLabTokenSet,
-  name,
-}: GitLabTokenInputProps) {
-  const { t } = useTranslation();
-
-  return (
-    <div className="flex flex-col gap-6">
-      <SettingsInput
-        testId={name}
-        name={name}
-        onChange={onChange}
-        label={t(I18nKey.GITLAB$TOKEN_LABEL)}
-        type="password"
-        className="w-[680px]"
-        placeholder={isGitLabTokenSet ? "<hidden>" : ""}
-        startContent={
-          isGitLabTokenSet && (
-            <KeyStatusIcon
-              testId="gl-set-token-indicator"
-              isSet={isGitLabTokenSet}
-            />
-          )
-        }
-      />
-
-      <GitLabTokenHelpAnchor />
-    </div>
-  );
-}

frontend/src/components/features/settings/input-skeleton.tsx

@@ -1,8 +0,0 @@
-export function InputSkeleton() {
-  return (
-    <div className="flex flex-col gap-2.5">
-      <div className="w-[70px] h-[20px] skeleton" />
-      <div className="w-[680px] h-[40px] skeleton" />
-    </div>
-  );
-}

frontend/src/components/features/settings/key-status-icon.tsx

@@ -2,13 +2,12 @@ import SuccessIcon from "#/icons/success.svg?react";
 import { cn } from "#/utils/utils";
 
 interface KeyStatusIconProps {
-  testId?: string;
   isSet: boolean;
 }
 
-export function KeyStatusIcon({ testId, isSet }: KeyStatusIconProps) {
+export function KeyStatusIcon({ isSet }: KeyStatusIconProps) {
   return (
-    <span data-testid={testId || (isSet ? "set-indicator" : "unset-indicator")}>
+    <span data-testid={isSet ? "set-indicator" : "unset-indicator"}>
       <SuccessIcon className={cn(isSet ? "text-success" : "text-danger")} />
     </span>
   );

frontend/src/components/features/settings/llm-settings/llm-settings-inputs-skeleton.tsx

@@ -1,21 +0,0 @@
-import { InputSkeleton } from "../input-skeleton";
-import { SubtextSkeleton } from "../subtext-skeleton";
-import { SwitchSkeleton } from "../switch-skeleton";
-
-export function LlmSettingsInputsSkeleton() {
-  return (
-    <div
-      data-testid="app-settings-skeleton"
-      className="px-11 py-9 flex flex-col gap-6"
-    >
-      <SwitchSkeleton />
-      <InputSkeleton />
-      <InputSkeleton />
-      <InputSkeleton />
-      <SubtextSkeleton />
-      <SwitchSkeleton />
-      <SwitchSkeleton />
-      <InputSkeleton />
-    </div>
-  );
-}

frontend/src/components/features/settings/llm-settings/reset-settings-modal.tsx

@@ -1,41 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
-import { I18nKey } from "#/i18n/declaration";
-import { BrandButton } from "../brand-button";
-
-interface ResetSettingsModalProps {
-  onReset: () => void;
-}
-
-export function ResetSettingsModal({ onReset }: ResetSettingsModalProps) {
-  const { t } = useTranslation();
-
-  return (
-    <ModalBackdrop>
-      <div className="bg-base-secondary p-4 rounded-xl flex flex-col gap-4 border border-tertiary">
-        <p>{t(I18nKey.SETTINGS$RESET_CONFIRMATION)}</p>
-        <div className="w-full flex gap-2" data-testid="reset-settings-modal">
-          <BrandButton
-            testId="confirm-button"
-            type="submit"
-            name="reset-settings"
-            variant="primary"
-            className="grow"
-          >
-            Reset
-          </BrandButton>
-
-          <BrandButton
-            testId="cancel-button"
-            type="button"
-            variant="secondary"
-            className="grow"
-            onClick={onReset}
-          >
-            Cancel
-          </BrandButton>
-        </div>
-      </div>
-    </ModalBackdrop>
-  );
-}

frontend/src/components/features/settings/settings-switch.tsx

@@ -6,7 +6,6 @@ interface SettingsSwitchProps {
   name?: string;
   onToggle?: (value: boolean) => void;
   defaultIsToggled?: boolean;
-  isToggled?: boolean;
   isBeta?: boolean;
 }
 
@@ -16,7 +15,6 @@ export function SettingsSwitch({
   name,
   onToggle,
   defaultIsToggled,
-  isToggled: controlledIsToggled,
   isBeta,
 }: React.PropsWithChildren<SettingsSwitchProps>) {
   const [isToggled, setIsToggled] = React.useState(defaultIsToggled ?? false);
@@ -27,18 +25,17 @@ export function SettingsSwitch({
   };
 
   return (
-    <label className="flex items-center gap-2 w-fit cursor-pointer">
+    <label className="flex items-center gap-2 w-fit">
       <input
         hidden
         data-testid={testId}
         name={name}
         type="checkbox"
         onChange={(e) => handleToggle(e.target.checked)}
-        checked={controlledIsToggled ?? isToggled}
         defaultChecked={defaultIsToggled}
       />
 
-      <StyledSwitchComponent isToggled={controlledIsToggled ?? isToggled} />
+      <StyledSwitchComponent isToggled={isToggled} />
 
       <div className="flex items-center gap-1">
         <span className="text-sm">{children}</span>

frontend/src/components/features/settings/subtext-skeleton.tsx

@@ -1,3 +0,0 @@
-export function SubtextSkeleton() {
-  return <div className="w-[250px] h-[20px] skeleton" />;
-}

frontend/src/components/features/settings/switch-skeleton.tsx

@@ -1,8 +0,0 @@
-export function SwitchSkeleton() {
-  return (
-    <div className="flex items-center gap-2">
-      <div className="w-[48px] h-[24px] skeleton-round" />
-      <div className="w-[100px] h-[20px] skeleton" />
-    </div>
-  );
-}

frontend/src/components/shared/modals/settings/model-selector.tsx

@@ -14,14 +14,12 @@ interface ModelSelectorProps {
   isDisabled?: boolean;
   models: Record<string, { separator: string; models: string[] }>;
   currentModel?: string;
-  onChange?: (model: string | null) => void;
 }
 
 export function ModelSelector({
   isDisabled,
   models,
   currentModel,
-  onChange,
 }: ModelSelectorProps) {
   const [, setLitellmId] = React.useState<string | null>(null);
   const [selectedProvider, setSelectedProvider] = React.useState<string | null>(
@@ -57,7 +55,6 @@ export function ModelSelector({
     }
     setLitellmId(fullModel);
     setSelectedModel(model);
-    onChange?.(fullModel);
   };
 
   const clear = () => {

frontend/src/hooks/query/use-settings.ts

@@ -4,9 +4,8 @@ import posthog from "posthog-js";
 import OpenHands from "#/api/open-hands";
 import { useAuth } from "#/context/auth-context";
 import { DEFAULT_SETTINGS } from "#/services/settings";
-import { Settings } from "#/types/settings";
 
-const getSettingsQueryFn = async (): Promise<Settings> => {
+const getSettingsQueryFn = async () => {
   const apiSettings = await OpenHands.getSettings();
 
   return {

frontend/src/i18n/declaration.ts

@@ -26,17 +26,6 @@ export enum I18nKey {
   ANALYTICS$DESCRIPTION = "ANALYTICS$DESCRIPTION",
   ANALYTICS$SEND_ANONYMOUS_DATA = "ANALYTICS$SEND_ANONYMOUS_DATA",
   ANALYTICS$CONFIRM_PREFERENCES = "ANALYTICS$CONFIRM_PREFERENCES",
-  SETTINGS$SAVING = "SETTINGS$SAVING",
-  SETTINGS$SAVE_CHANGES = "SETTINGS$SAVE_CHANGES",
-  SETTINGS$NAV_GIT = "SETTINGS$NAV_GIT",
-  SETTINGS$NAV_APPLICATION = "SETTINGS$NAV_APPLICATION",
-  SETTINGS$NAV_CREDITS = "SETTINGS$NAV_CREDITS",
-  SETTINGS$NAV_API_KEYS = "SETTINGS$NAV_API_KEYS",
-  SETTINGS$NAV_LLM = "SETTINGS$NAV_LLM",
-  GIT$MERGE_REQUEST = "GIT$MERGE_REQUEST",
-  GIT$GITLAB_API = "GIT$GITLAB_API",
-  GIT$PULL_REQUEST = "GIT$PULL_REQUEST",
-  GIT$GITHUB_API = "GIT$GITHUB_API",
   BUTTON$COPY = "BUTTON$COPY",
   BUTTON$COPIED = "BUTTON$COPIED",
   APP$TITLE = "APP$TITLE",
@@ -106,9 +95,6 @@ export enum I18nKey {
   GITHUB$TOKEN_LABEL = "GITHUB$TOKEN_LABEL",
   GITHUB$TOKEN_OPTIONAL = "GITHUB$TOKEN_OPTIONAL",
   GITHUB$GET_TOKEN = "GITHUB$GET_TOKEN",
-  GITHUB$TOKEN_HELP_TEXT = "GITHUB$TOKEN_HELP_TEXT",
-  GITHUB$TOKEN_LINK_TEXT = "GITHUB$TOKEN_LINK_TEXT",
-  GITHUB$INSTRUCTIONS_LINK_TEXT = "GITHUB$INSTRUCTIONS_LINK_TEXT",
   COMMON$HERE = "COMMON$HERE",
   ANALYTICS$ENABLE = "ANALYTICS$ENABLE",
   GITHUB$TOKEN_INVALID = "GITHUB$TOKEN_INVALID",
@@ -451,9 +437,6 @@ export enum I18nKey {
   MODEL_SELECTOR$OTHERS = "MODEL_SELECTOR$OTHERS",
   GITLAB$TOKEN_LABEL = "GITLAB$TOKEN_LABEL",
   GITLAB$GET_TOKEN = "GITLAB$GET_TOKEN",
-  GITLAB$TOKEN_HELP_TEXT = "GITLAB$TOKEN_HELP_TEXT",
-  GITLAB$TOKEN_LINK_TEXT = "GITLAB$TOKEN_LINK_TEXT",
-  GITLAB$INSTRUCTIONS_LINK_TEXT = "GITLAB$INSTRUCTIONS_LINK_TEXT",
   GITLAB$OR_SEE = "GITLAB$OR_SEE",
   COMMON$DOCUMENTATION = "COMMON$DOCUMENTATION",
   DIFF_VIEWER$LOADING = "DIFF_VIEWER$LOADING",

frontend/src/i18n/translation.json

@@ -389,171 +389,6 @@
         "tr": "Tercihleri Onayla",
         "de": "Einstellungen bestätigen"
     },
-    "SETTINGS$SAVING": {
-        "en": "Saving...",
-        "ja": "保存中...",
-        "zh-CN": "保存中...",
-        "zh-TW": "儲存中...",
-        "ko-KR": "저장 중...",
-        "no": "Lagrer...",
-        "it": "Salvataggio in corso...",
-        "pt": "Salvando...",
-        "es": "Guardando...",
-        "ar": "جار الحفظ...",
-        "fr": "Enregistrement en cours...",
-        "tr": "Kayıt yapılıyor...",
-        "de": "Speichern..."
-    },
-    "SETTINGS$SAVE_CHANGES": {
-        "en": "Save Changes",
-        "ja": "変更を保存",
-        "zh-CN": "保存更改",
-        "zh-TW": "儲存變更",
-        "ko-KR": "변경 사항 저장",
-        "no": "Lagre endringer",
-        "it": "Salva modifiche",
-        "pt": "Salvar alterações",
-        "es": "Guardar cambios",
-        "ar": "حفظ التغييرات",
-        "fr": "Enregistrer les modifications",
-        "tr": "Değişiklikleri Kaydet",
-        "de": "Änderungen speichern"
-    },
-    "SETTINGS$NAV_GIT": {
-        "en": "Git",
-        "ja": "Git",
-        "zh-CN": "Git",
-        "zh-TW": "Git",
-        "ko-KR": "Git",
-        "no": "Git",
-        "it": "Git",
-        "pt": "Git",
-        "es": "Git",
-        "ar": "Git",
-        "fr": "Git",
-        "tr": "Git",
-        "de": "Git"
-    },
-    "SETTINGS$NAV_APPLICATION": {
-        "en": "Application",
-        "ja": "アプリケーション",
-        "zh-CN": "应用程序",
-        "zh-TW": "應用程式",
-        "ko-KR": "애플리케이션",
-        "no": "Applikasjon",
-        "it": "Applicazione",
-        "pt": "Aplicação",
-        "es": "Aplicación",
-        "ar": "التطبيق",
-        "fr": "Application",
-        "tr": "Uygulama",
-        "de": "Anwendung"
-    },
-    "SETTINGS$NAV_CREDITS": {
-        "en": "Credits",
-        "ja": "クレジット",
-        "zh-CN": "积分",
-        "zh-TW": "點數",
-        "ko-KR": "크레딧",
-        "no": "Kreditter",
-        "it": "Crediti",
-        "pt": "Créditos",
-        "es": "Créditos",
-        "ar": "الرصيد",
-        "fr": "Crédits",
-        "tr": "Krediler",
-        "de": "Guthaben"
-    },
-    "SETTINGS$NAV_API_KEYS": {
-        "en": "API Keys",
-        "ja": "APIキー",
-        "zh-CN": "API密钥",
-        "zh-TW": "API金鑰",
-        "ko-KR": "API 키",
-        "no": "API-nøkler",
-        "it": "Chiavi API",
-        "pt": "Chaves de API",
-        "es": "Claves API",
-        "ar": "مفاتيح API",
-        "fr": "Clés API",
-        "tr": "API Anahtarları",
-        "de": "API-Schlüssel"
-    },
-    "SETTINGS$NAV_LLM": {
-        "en": "LLM",
-        "ja": "LLM",
-        "zh-CN": "LLM",
-        "zh-TW": "LLM",
-        "ko-KR": "LLM",
-        "no": "LLM",
-        "it": "LLM",
-        "pt": "LLM",
-        "es": "LLM",
-        "ar": "LLM",
-        "fr": "LLM",
-        "tr": "LLM",
-        "de": "LLM"
-    },
-    "GIT$MERGE_REQUEST": {
-        "en": "Merge Request",
-        "ja": "マージリクエスト",
-        "zh-CN": "合并请求",
-        "zh-TW": "合併請求",
-        "ko-KR": "머지 요청",
-        "no": "Fletteforespørsel",
-        "it": "Richiesta di fusione",
-        "pt": "Solicitação de mesclagem",
-        "es": "Solicitud de fusión",
-        "ar": "طلب الدمج",
-        "fr": "Demande de fusion",
-        "tr": "Birleştirme İsteği",
-        "de": "Merge-Anfrage"
-    },
-    "GIT$GITLAB_API": {
-        "en": "GitLab API",
-        "ja": "GitLab API",
-        "zh-CN": "GitLab API",
-        "zh-TW": "GitLab API",
-        "ko-KR": "GitLab API",
-        "no": "GitLab API",
-        "it": "API GitLab",
-        "pt": "API do GitLab",
-        "es": "API de GitLab",
-        "ar": "واجهة برمجة تطبيقات GitLab",
-        "fr": "API GitLab",
-        "tr": "GitLab API",
-        "de": "GitLab API"
-    },
-    "GIT$PULL_REQUEST": {
-        "en": "Pull Request",
-        "ja": "プルリクエスト",
-        "zh-CN": "拉取请求",
-        "zh-TW": "拉取請求",
-        "ko-KR": "풀 리퀘스트",
-        "no": "Trekkforespørsel",
-        "it": "Richiesta di pull",
-        "pt": "Solicitação de pull",
-        "es": "Solicitud de extracción",
-        "ar": "طلب السحب",
-        "fr": "Demande de tirage",
-        "tr": "Çekme İsteği",
-        "de": "Pull Request"
-    },
-    "GIT$GITHUB_API": {
-        "en": "GitHub API",
-        "ja": "GitHub API",
-        "zh-CN": "GitHub API",
-        "zh-TW": "GitHub API",
-        "ko-KR": "GitHub API",
-        "no": "GitHub API",
-        "it": "API GitHub",
-        "pt": "API do GitHub",
-        "es": "API de GitHub",
-        "ar": "واجهة برمجة تطبيقات GitHub",
-        "fr": "API GitHub",
-        "tr": "GitHub API",
-        "de": "GitHub API"
-    },
     "BUTTON$COPY": {
         "en": "Copy to clipboard",
         "ja": "クリップボードにコピー",
@@ -1599,51 +1434,6 @@
         "tr": "Jetonunuzu alın",
         "de": "Token abrufen"
     },
-    "GITHUB$TOKEN_HELP_TEXT": {
-        "en": "Get your <0>GitHub token</0> or <1>click here for instructions</1>",
-        "ja": "<0>GitHubトークン</0>を取得するか、<1>手順についてはここをクリック</1>",
-        "zh-CN": "获取您的<0>GitHub令牌</0>或<1>点击此处获取说明</1>",
-        "zh-TW": "取得您的<0>GitHub權杖</0>或<1>點擊此處獲取說明</1>",
-        "ko-KR": "<0>GitHub 토큰</0>을 받거나 <1>지침을 보려면 여기를 클릭</1>",
-        "no": "Få din <0>GitHub-token</0> eller <1>klikk her for instruksjoner</1>",
-        "it": "Ottieni il tuo <0>token GitHub</0> o <1>clicca qui per istruzioni</1>",
-        "pt": "Obtenha seu <0>token GitHub</0> ou <1>clique aqui para instruções</1>",
-        "es": "Obtenga su <0>token de GitHub</0> o <1>haga clic aquí para obtener instrucciones</1>",
-        "ar": "احصل على <0>رمز GitHub</0> الخاص بك أو <1>انقر هنا للحصول على تعليمات</1>",
-        "fr": "Obtenez votre <0>jeton GitHub</0> ou <1>cliquez ici pour les instructions</1>",
-        "tr": "<0>GitHub jetonu</0> alın veya <1>talimatlar için buraya tıklayın</1>",
-        "de": "Holen Sie sich Ihren <0>GitHub-Token</0> oder <1>klicken Sie hier für Anweisungen</1>"
-    },
-    "GITHUB$TOKEN_LINK_TEXT": {
-        "en": "GitHub token",
-        "ja": "GitHubトークン",
-        "zh-CN": "GitHub令牌",
-        "zh-TW": "GitHub權杖",
-        "ko-KR": "GitHub 토큰",
-        "no": "GitHub-token",
-        "it": "token GitHub",
-        "pt": "token GitHub",
-        "es": "token de GitHub",
-        "ar": "رمز GitHub",
-        "fr": "jeton GitHub",
-        "tr": "GitHub jetonu",
-        "de": "GitHub-Token"
-    },
-    "GITHUB$INSTRUCTIONS_LINK_TEXT": {
-        "en": "click here for instructions",
-        "ja": "手順についてはここをクリック",
-        "zh-CN": "点击此处获取说明",
-        "zh-TW": "點擊此處獲取說明",
-        "ko-KR": "지침을 보려면 여기를 클릭",
-        "no": "klikk her for instruksjoner",
-        "it": "clicca qui per istruzioni",
-        "pt": "clique aqui para instruções",
-        "es": "haga clic aquí para obtener instrucciones",
-        "ar": "انقر هنا للحصول على تعليمات",
-        "fr": "cliquez ici pour les instructions",
-        "tr": "talimatlar için buraya tıklayın",
-        "de": "klicken Sie hier für Anweisungen"
-    },
     "COMMON$HERE": {
         "en": "here",
         "ja": "こちら",
@@ -6484,51 +6274,6 @@
         "tr": "Üzerinde bir jeton oluştur",
         "de": "Token generieren auf"
     },
-    "GITLAB$TOKEN_HELP_TEXT": {
-        "en": "Get your <0>GitLab token</0> or <1>click here for instructions</1>",
-        "ja": "<0>GitLabトークン</0>を取得するか、<1>手順についてはここをクリック</1>",
-        "zh-CN": "获取您的<0>GitLab令牌</0>或<1>点击此处获取说明</1>",
-        "zh-TW": "取得您的<0>GitLab權杖</0>或<1>點擊此處獲取說明</1>",
-        "ko-KR": "<0>GitLab 토큰</0>을 받거나 <1>지침을 보려면 여기를 클릭</1>",
-        "no": "Få din <0>GitLab-token</0> eller <1>klikk her for instruksjoner</1>",
-        "it": "Ottieni il tuo <0>token GitLab</0> o <1>clicca qui per istruzioni</1>",
-        "pt": "Obtenha seu <0>token GitLab</0> ou <1>clique aqui para instruções</1>",
-        "es": "Obtenga su <0>token de GitLab</0> o <1>haga clic aquí para obtener instrucciones</1>",
-        "ar": "احصل على <0>رمز GitLab</0> الخاص بك أو <1>انقر هنا للحصول على تعليمات</1>",
-        "fr": "Obtenez votre <0>jeton GitLab</0> ou <1>cliquez ici pour les instructions</1>",
-        "tr": "<0>GitLab jetonu</0> alın veya <1>talimatlar için buraya tıklayın</1>",
-        "de": "Holen Sie sich Ihren <0>GitLab-Token</0> oder <1>klicken Sie hier für Anweisungen</1>"
-    },
-    "GITLAB$TOKEN_LINK_TEXT": {
-        "en": "GitLab token",
-        "ja": "GitLabトークン",
-        "zh-CN": "GitLab令牌",
-        "zh-TW": "GitLab權杖",
-        "ko-KR": "GitLab 토큰",
-        "no": "GitLab-token",
-        "it": "token GitLab",
-        "pt": "token GitLab",
-        "es": "token de GitLab",
-        "ar": "رمز GitLab",
-        "fr": "jeton GitLab",
-        "tr": "GitLab jetonu",
-        "de": "GitLab-Token"
-    },
-    "GITLAB$INSTRUCTIONS_LINK_TEXT": {
-        "en": "click here for instructions",
-        "ja": "手順についてはここをクリック",
-        "zh-CN": "点击此处获取说明",
-        "zh-TW": "點擊此處獲取說明",
-        "ko-KR": "지침을 보려면 여기를 클릭",
-        "no": "klikk her for instruksjoner",
-        "it": "clicca qui per istruzioni",
-        "pt": "clique aqui para instruções",
-        "es": "haga clic aquí para obtener instrucciones",
-        "ar": "انقر هنا للحصول على تعليمات",
-        "fr": "cliquez ici pour les instructions",
-        "tr": "talimatlar için buraya tıklayın",
-        "de": "klicken Sie hier für Anweisungen"
-    },
     "GITLAB$OR_SEE": {
         "en": "or see the",
         "ja": "または参照",

frontend/src/mocks/handlers.ts

@@ -35,15 +35,6 @@ const MOCK_USER_PREFERENCES: {
   settings: null,
 };
 
-/**
- * Set the user settings to the default settings
- *
- * Useful for resetting the settings in tests
- */
-export const resetTestHandlersMockSettings = () => {
-  MOCK_USER_PREFERENCES.settings = MOCK_DEFAULT_USER_SETTINGS;
-};
-
 const conversations: Conversation[] = [
   {
     conversation_id: "1",
@@ -89,7 +80,6 @@ const openHandsHandlers = [
     HttpResponse.json([
       "gpt-3.5-turbo",
       "gpt-4o",
-      "gpt-4o-mini",
       "anthropic/claude-3.5",
       "anthropic/claude-3-5-sonnet-20241022",
     ]),
@@ -183,7 +173,6 @@ export const handlers = [
     return HttpResponse.json(settings);
   }),
   http.post("/api/settings", async ({ request }) => {
-    await delay();
     const body = await request.json();
 
     if (body) {

frontend/src/routes.ts

@@ -9,9 +9,7 @@ export default [
   layout("routes/root-layout.tsx", [
     index("routes/home.tsx"),
     route("settings", "routes/settings.tsx", [
-      index("routes/llm-settings.tsx"),
-      route("git", "routes/git-settings.tsx"),
-      route("app", "routes/app-settings.tsx"),
+      index("routes/account-settings.tsx"),
       route("billing", "routes/billing.tsx"),
       route("api-keys", "routes/api-keys.tsx"),
     ]),

frontend/src/routes/account-settings.tsx

@@ -0,0 +1,531 @@
+import React from "react";
+import { Link } from "react-router";
+import { useTranslation } from "react-i18next";
+import { I18nKey } from "#/i18n/declaration";
+import { BrandButton } from "#/components/features/settings/brand-button";
+import { HelpLink } from "#/components/features/settings/help-link";
+import { KeyStatusIcon } from "#/components/features/settings/key-status-icon";
+import { SettingsDropdownInput } from "#/components/features/settings/settings-dropdown-input";
+import { SettingsInput } from "#/components/features/settings/settings-input";
+import { SettingsSwitch } from "#/components/features/settings/settings-switch";
+import { LoadingSpinner } from "#/components/shared/loading-spinner";
+import { ModelSelector } from "#/components/shared/modals/settings/model-selector";
+import { useSaveSettings } from "#/hooks/mutation/use-save-settings";
+import { useAIConfigOptions } from "#/hooks/query/use-ai-config-options";
+import { useConfig } from "#/hooks/query/use-config";
+import { useSettings } from "#/hooks/query/use-settings";
+import { useAppLogout } from "#/hooks/use-app-logout";
+import { AvailableLanguages } from "#/i18n";
+import { DEFAULT_SETTINGS } from "#/services/settings";
+import { handleCaptureConsent } from "#/utils/handle-capture-consent";
+import { hasAdvancedSettingsSet } from "#/utils/has-advanced-settings-set";
+import { isCustomModel } from "#/utils/is-custom-model";
+import { organizeModelsAndProviders } from "#/utils/organize-models-and-providers";
+import { retrieveAxiosErrorMessage } from "#/utils/retrieve-axios-error-message";
+import {
+  displayErrorToast,
+  displaySuccessToast,
+} from "#/utils/custom-toast-handlers";
+import { ProviderOptions } from "#/types/settings";
+import { useAuth } from "#/context/auth-context";
+
+// Define REMOTE_RUNTIME_OPTIONS for testing
+const REMOTE_RUNTIME_OPTIONS = [
+  { key: "1", label: "Standard" },
+  { key: "2", label: "Enhanced" },
+  { key: "4", label: "Premium" },
+];
+
+function AccountSettings() {
+  const { t } = useTranslation();
+  const {
+    data: settings,
+    isFetching: isFetchingSettings,
+    isFetched,
+    isSuccess: isSuccessfulSettings,
+  } = useSettings();
+  const { data: config } = useConfig();
+  const {
+    data: resources,
+    isFetching: isFetchingResources,
+    isSuccess: isSuccessfulResources,
+  } = useAIConfigOptions();
+  const { mutate: saveSettings } = useSaveSettings();
+  const { handleLogout } = useAppLogout();
+  const { providerTokensSet, providersAreSet } = useAuth();
+
+  const isFetching = isFetchingSettings || isFetchingResources;
+  const isSuccess = isSuccessfulSettings && isSuccessfulResources;
+
+  const isSaas = config?.APP_MODE === "saas";
+  const shouldHandleSpecialSaasCase =
+    config?.FEATURE_FLAGS.HIDE_LLM_SETTINGS && isSaas;
+
+  const determineWhetherToToggleAdvancedSettings = () => {
+    if (shouldHandleSpecialSaasCase) return true;
+
+    if (isSuccess) {
+      return (
+        isCustomModel(resources.models, settings.LLM_MODEL) ||
+        hasAdvancedSettingsSet({
+          ...settings,
+        })
+      );
+    }
+
+    return false;
+  };
+
+  const hasAppSlug = !!config?.APP_SLUG;
+  const isGitHubTokenSet =
+    providerTokensSet.includes(ProviderOptions.github) || false;
+  const isGitLabTokenSet =
+    providerTokensSet.includes(ProviderOptions.gitlab) || false;
+  const isLLMKeySet = settings?.LLM_API_KEY_SET;
+  const isAnalyticsEnabled = settings?.USER_CONSENTS_TO_ANALYTICS;
+  const isAdvancedSettingsSet = determineWhetherToToggleAdvancedSettings();
+
+  const modelsAndProviders = organizeModelsAndProviders(
+    resources?.models || [],
+  );
+
+  const [llmConfigMode, setLlmConfigMode] = React.useState<
+    "basic" | "advanced"
+  >(isAdvancedSettingsSet ? "advanced" : "basic");
+  const [confirmationModeIsEnabled, setConfirmationModeIsEnabled] =
+    React.useState(!!settings?.SECURITY_ANALYZER);
+
+  const formRef = React.useRef<HTMLFormElement>(null);
+
+  const onSubmit = async (formData: FormData) => {
+    const languageLabel = formData.get("language-input")?.toString();
+    const languageValue = AvailableLanguages.find(
+      ({ label }) => label === languageLabel,
+    )?.value;
+
+    const llmProvider = formData.get("llm-provider-input")?.toString();
+    const llmModel = formData.get("llm-model-input")?.toString();
+    const fullLlmModel = `${llmProvider}/${llmModel}`.toLowerCase();
+    const customLlmModel = formData.get("llm-custom-model-input")?.toString();
+
+    const rawRemoteRuntimeResourceFactor = formData
+      .get("runtime-settings-input")
+      ?.toString();
+    const remoteRuntimeResourceFactor = REMOTE_RUNTIME_OPTIONS.find(
+      ({ label }) => label === rawRemoteRuntimeResourceFactor,
+    )?.key;
+
+    const userConsentsToAnalytics =
+      formData.get("enable-analytics-switch")?.toString() === "on";
+    const enableMemoryCondenser =
+      formData.get("enable-memory-condenser-switch")?.toString() === "on";
+    const enableSoundNotifications =
+      formData.get("enable-sound-notifications-switch")?.toString() === "on";
+    const llmBaseUrl = formData.get("base-url-input")?.toString().trim() || "";
+    const inputApiKey = formData.get("llm-api-key-input")?.toString() || "";
+    const llmApiKey =
+      inputApiKey === "" && isLLMKeySet
+        ? undefined // don't update if it's already set and input is empty
+        : inputApiKey; // otherwise use the input value
+
+    const githubToken = formData.get("github-token-input")?.toString();
+    const gitlabToken = formData.get("gitlab-token-input")?.toString();
+    // we don't want the user to be able to modify these settings in SaaS
+    const finalLlmModel = shouldHandleSpecialSaasCase
+      ? undefined
+      : customLlmModel || fullLlmModel;
+    const finalLlmBaseUrl = shouldHandleSpecialSaasCase
+      ? undefined
+      : llmBaseUrl;
+    const finalLlmApiKey = shouldHandleSpecialSaasCase ? undefined : llmApiKey;
+
+    const newSettings = {
+      provider_tokens:
+        githubToken || gitlabToken
+          ? {
+              github: githubToken || "",
+              gitlab: gitlabToken || "",
+            }
+          : undefined,
+      LANGUAGE: languageValue,
+      user_consents_to_analytics: userConsentsToAnalytics,
+      ENABLE_DEFAULT_CONDENSER: enableMemoryCondenser,
+      ENABLE_SOUND_NOTIFICATIONS: enableSoundNotifications,
+      LLM_MODEL: finalLlmModel,
+      LLM_BASE_URL: finalLlmBaseUrl,
+      llm_api_key: finalLlmApiKey,
+      AGENT: formData.get("agent-input")?.toString(),
+      SECURITY_ANALYZER:
+        formData.get("security-analyzer-input")?.toString() || "",
+      REMOTE_RUNTIME_RESOURCE_FACTOR:
+        remoteRuntimeResourceFactor !== null
+          ? Number(remoteRuntimeResourceFactor)
+          : DEFAULT_SETTINGS.REMOTE_RUNTIME_RESOURCE_FACTOR,
+      CONFIRMATION_MODE: confirmationModeIsEnabled,
+    };
+
+    saveSettings(newSettings, {
+      onSuccess: () => {
+        handleCaptureConsent(userConsentsToAnalytics);
+        displaySuccessToast(t(I18nKey.SETTINGS$SAVED));
+        setLlmConfigMode(isAdvancedSettingsSet ? "advanced" : "basic");
+      },
+      onError: (error) => {
+        const errorMessage = retrieveAxiosErrorMessage(error);
+        displayErrorToast(errorMessage || t(I18nKey.ERROR$GENERIC));
+      },
+    });
+  };
+
+  React.useEffect(() => {
+    // If settings is still loading by the time the state is set, it will always
+    // default to basic settings. This is a workaround to ensure the correct
+    // settings are displayed.
+    setLlmConfigMode(isAdvancedSettingsSet ? "advanced" : "basic");
+  }, [isAdvancedSettingsSet]);
+
+  if (isFetched && !settings) {
+    return <div>Failed to fetch settings. Please try reloading.</div>;
+  }
+
+  const onToggleAdvancedMode = (isToggled: boolean) => {
+    setLlmConfigMode(isToggled ? "advanced" : "basic");
+    if (!isToggled) {
+      // reset advanced state
+      setConfirmationModeIsEnabled(!!settings?.SECURITY_ANALYZER);
+    }
+  };
+
+  if (isFetching || !settings) {
+    return (
+      <div className="flex grow p-4">
+        <LoadingSpinner size="large" />
+      </div>
+    );
+  }
+
+  return (
+    <>
+      <form
+        data-testid="account-settings-form"
+        ref={formRef}
+        action={onSubmit}
+        className="flex flex-col grow overflow-auto"
+      >
+        <div className="flex flex-col gap-12 px-11 py-9">
+          {!shouldHandleSpecialSaasCase && (
+            <section
+              data-testid="llm-settings-section"
+              className="flex flex-col gap-6"
+            >
+              <div className="flex items-center gap-7">
+                <h2 className="text-[28px] leading-8 tracking-[-0.02em] font-bold">
+                  {t(I18nKey.SETTINGS$LLM_SETTINGS)}
+                </h2>
+                {!shouldHandleSpecialSaasCase && (
+                  <SettingsSwitch
+                    testId="advanced-settings-switch"
+                    defaultIsToggled={isAdvancedSettingsSet}
+                    onToggle={onToggleAdvancedMode}
+                  >
+                    {t(I18nKey.SETTINGS$ADVANCED)}
+                  </SettingsSwitch>
+                )}
+              </div>
+
+              {llmConfigMode === "basic" && !shouldHandleSpecialSaasCase && (
+                <ModelSelector
+                  models={modelsAndProviders}
+                  currentModel={settings.LLM_MODEL}
+                />
+              )}
+
+              {llmConfigMode === "advanced" && !shouldHandleSpecialSaasCase && (
+                <SettingsInput
+                  testId="llm-custom-model-input"
+                  name="llm-custom-model-input"
+                  label={t(I18nKey.SETTINGS$CUSTOM_MODEL)}
+                  defaultValue={settings.LLM_MODEL}
+                  placeholder="anthropic/claude-3-5-sonnet-20241022"
+                  type="text"
+                  className="w-[680px]"
+                />
+              )}
+              {llmConfigMode === "advanced" && !shouldHandleSpecialSaasCase && (
+                <SettingsInput
+                  testId="base-url-input"
+                  name="base-url-input"
+                  label={t(I18nKey.SETTINGS$BASE_URL)}
+                  defaultValue={settings.LLM_BASE_URL}
+                  placeholder="https://api.openai.com"
+                  type="text"
+                  className="w-[680px]"
+                />
+              )}
+
+              {!shouldHandleSpecialSaasCase && (
+                <SettingsInput
+                  testId="llm-api-key-input"
+                  name="llm-api-key-input"
+                  label={t(I18nKey.SETTINGS_FORM$API_KEY)}
+                  type="password"
+                  className="w-[680px]"
+                  placeholder={isLLMKeySet ? "<hidden>" : ""}
+                  startContent={
+                    isLLMKeySet && <KeyStatusIcon isSet={isLLMKeySet} />
+                  }
+                />
+              )}
+
+              {!shouldHandleSpecialSaasCase && (
+                <HelpLink
+                  testId="llm-api-key-help-anchor"
+                  text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
+                  linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
+                  href="https://docs.all-hands.dev/modules/usage/installation#getting-an-api-key"
+                />
+              )}
+
+              {llmConfigMode === "advanced" && (
+                <SettingsDropdownInput
+                  testId="agent-input"
+                  name="agent-input"
+                  label={t(I18nKey.SETTINGS$AGENT)}
+                  items={
+                    resources?.agents.map((agent) => ({
+                      key: agent,
+                      label: agent,
+                    })) || []
+                  }
+                  wrapperClassName="w-[680px]"
+                  defaultSelectedKey={settings.AGENT}
+                  isClearable={false}
+                />
+              )}
+
+              {isSaas && llmConfigMode === "advanced" && (
+                <SettingsDropdownInput
+                  testId="runtime-settings-input"
+                  name="runtime-settings-input"
+                  label={
+                    <>
+                      {t(I18nKey.SETTINGS$RUNTIME_SETTINGS)}
+                      <a href="mailto:contact@all-hands.dev">
+                        {t(I18nKey.SETTINGS$GET_IN_TOUCH)}
+                      </a>
+                      )
+                    </>
+                  }
+                  items={REMOTE_RUNTIME_OPTIONS}
+                  defaultSelectedKey={settings.REMOTE_RUNTIME_RESOURCE_FACTOR?.toString()}
+                  isDisabled
+                  isClearable={false}
+                />
+              )}
+
+              {llmConfigMode === "advanced" && (
+                <SettingsSwitch
+                  testId="enable-confirmation-mode-switch"
+                  onToggle={setConfirmationModeIsEnabled}
+                  defaultIsToggled={!!settings.CONFIRMATION_MODE}
+                  isBeta
+                >
+                  {t(I18nKey.SETTINGS$CONFIRMATION_MODE)}
+                </SettingsSwitch>
+              )}
+
+              {llmConfigMode === "advanced" && (
+                <SettingsSwitch
+                  testId="enable-memory-condenser-switch"
+                  name="enable-memory-condenser-switch"
+                  defaultIsToggled={!!settings.ENABLE_DEFAULT_CONDENSER}
+                >
+                  {t(I18nKey.SETTINGS$ENABLE_MEMORY_CONDENSATION)}
+                </SettingsSwitch>
+              )}
+
+              {llmConfigMode === "advanced" && confirmationModeIsEnabled && (
+                <div>
+                  <SettingsDropdownInput
+                    testId="security-analyzer-input"
+                    name="security-analyzer-input"
+                    label={t(I18nKey.SETTINGS$SECURITY_ANALYZER)}
+                    items={
+                      resources?.securityAnalyzers.map((analyzer) => ({
+                        key: analyzer,
+                        label: analyzer,
+                      })) || []
+                    }
+                    defaultSelectedKey={settings.SECURITY_ANALYZER}
+                    isClearable
+                    showOptionalTag
+                  />
+                </div>
+              )}
+            </section>
+          )}
+
+          <section className="flex flex-col gap-6">
+            <h2 className="text-[28px] leading-8 tracking-[-0.02em] font-bold">
+              {t(I18nKey.SETTINGS$GIT_SETTINGS)}
+            </h2>
+            {isSaas && hasAppSlug && (
+              <Link
+                to={`https://github.com/apps/${config.APP_SLUG}/installations/new`}
+                target="_blank"
+                rel="noreferrer noopener"
+              >
+                <BrandButton type="button" variant="secondary">
+                  {t(I18nKey.GITHUB$CONFIGURE_REPOS)}
+                </BrandButton>
+              </Link>
+            )}
+            {!isSaas && (
+              <>
+                <SettingsInput
+                  testId="github-token-input"
+                  name="github-token-input"
+                  label={t(I18nKey.GITHUB$TOKEN_LABEL)}
+                  type="password"
+                  className="w-[680px]"
+                  startContent={
+                    isGitHubTokenSet && (
+                      <KeyStatusIcon isSet={!!isGitHubTokenSet} />
+                    )
+                  }
+                  placeholder={isGitHubTokenSet ? "<hidden>" : ""}
+                />
+                <p data-testid="github-token-help-anchor" className="text-xs">
+                  {" "}
+                  {t(I18nKey.GITHUB$GET_TOKEN)}{" "}
+                  <b>
+                    {" "}
+                    <a
+                      href="https://github.com/settings/tokens/new?description=openhands-app&scopes=repo,user,workflow"
+                      target="_blank"
+                      className="underline underline-offset-2"
+                      rel="noopener noreferrer"
+                    >
+                      GitHub
+                    </a>{" "}
+                  </b>
+                  {t(I18nKey.COMMON$HERE)}{" "}
+                  <b>
+                    <a
+                      href="https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/creating-a-personal-access-token"
+                      target="_blank"
+                      className="underline underline-offset-2"
+                      rel="noopener noreferrer"
+                    >
+                      {t(I18nKey.COMMON$CLICK_FOR_INSTRUCTIONS)}
+                    </a>
+                  </b>
+                  .
+                </p>
+
+                <SettingsInput
+                  testId="gitlab-token-input"
+                  name="gitlab-token-input"
+                  label={t(I18nKey.GITLAB$TOKEN_LABEL)}
+                  type="password"
+                  className="w-[680px]"
+                  startContent={
+                    isGitLabTokenSet && (
+                      <KeyStatusIcon isSet={!!isGitLabTokenSet} />
+                    )
+                  }
+                  placeholder={isGitHubTokenSet ? "<hidden>" : ""}
+                />
+
+                <p data-testid="gitlab-token-help-anchor" className="text-xs">
+                  {" "}
+                  {t(I18nKey.GITLAB$GET_TOKEN)}{" "}
+                  <b>
+                    {" "}
+                    <a
+                      href="https://gitlab.com/-/user_settings/personal_access_tokens?name=openhands-app&scopes=api,read_user,read_repository,write_repository"
+                      target="_blank"
+                      className="underline underline-offset-2"
+                      rel="noopener noreferrer"
+                    >
+                      GitLab
+                    </a>{" "}
+                  </b>
+                  {t(I18nKey.GITLAB$OR_SEE)}{" "}
+                  <b>
+                    <a
+                      href="https://docs.gitlab.com/user/profile/personal_access_tokens/"
+                      target="_blank"
+                      className="underline underline-offset-2"
+                      rel="noopener noreferrer"
+                    >
+                      {t(I18nKey.COMMON$DOCUMENTATION)}
+                    </a>
+                  </b>
+                  .
+                </p>
+                <BrandButton
+                  type="button"
+                  variant="secondary"
+                  onClick={handleLogout}
+                  isDisabled={!providersAreSet}
+                >
+                  Disconnect Tokens
+                </BrandButton>
+              </>
+            )}
+          </section>
+
+          <section className="flex flex-col gap-6">
+            <h2 className="text-[28px] leading-8 tracking-[-0.02em] font-bold">
+              {t(I18nKey.ACCOUNT_SETTINGS$ADDITIONAL_SETTINGS)}
+            </h2>
+
+            <SettingsDropdownInput
+              testId="language-input"
+              name="language-input"
+              label={t(I18nKey.SETTINGS$LANGUAGE)}
+              items={AvailableLanguages.map((language) => ({
+                key: language.value,
+                label: language.label,
+              }))}
+              defaultSelectedKey={settings.LANGUAGE}
+              wrapperClassName="w-[680px]"
+              isClearable={false}
+            />
+
+            <SettingsSwitch
+              testId="enable-analytics-switch"
+              name="enable-analytics-switch"
+              defaultIsToggled={!!isAnalyticsEnabled}
+            >
+              {t(I18nKey.ANALYTICS$ENABLE)}
+            </SettingsSwitch>
+
+            <SettingsSwitch
+              testId="enable-sound-notifications-switch"
+              name="enable-sound-notifications-switch"
+              defaultIsToggled={!!settings.ENABLE_SOUND_NOTIFICATIONS}
+            >
+              {t(I18nKey.SETTINGS$SOUND_NOTIFICATIONS)}
+            </SettingsSwitch>
+          </section>
+        </div>
+      </form>
+
+      <footer className="flex gap-6 p-6 justify-end border-t border-t-tertiary">
+        <BrandButton
+          type="button"
+          variant="primary"
+          onClick={() => {
+            formRef.current?.requestSubmit();
+          }}
+        >
+          {t(I18nKey.BUTTON$SAVE)}
+        </BrandButton>
+      </footer>
+    </>
+  );
+}
+
+export default AccountSettings;

frontend/src/routes/api-keys.tsx

@@ -3,7 +3,7 @@ import { ApiKeysManager } from "#/components/features/settings/api-keys-manager"
 
 function ApiKeysScreen() {
   return (
-    <div className="flex flex-col grow overflow-auto p-9">
+    <div className="flex flex-col grow overflow-auto p-11">
       <ApiKeysManager />
     </div>
   );

frontend/src/routes/app-settings.tsx

@@ -1,150 +0,0 @@
-import React from "react";
-import { useTranslation } from "react-i18next";
-import { useSaveSettings } from "#/hooks/mutation/use-save-settings";
-import { useSettings } from "#/hooks/query/use-settings";
-import { AvailableLanguages } from "#/i18n";
-import { DEFAULT_SETTINGS } from "#/services/settings";
-import { BrandButton } from "#/components/features/settings/brand-button";
-import { SettingsSwitch } from "#/components/features/settings/settings-switch";
-import { I18nKey } from "#/i18n/declaration";
-import { LanguageInput } from "#/components/features/settings/app-settings/language-input";
-import { handleCaptureConsent } from "#/utils/handle-capture-consent";
-import {
-  displayErrorToast,
-  displaySuccessToast,
-} from "#/utils/custom-toast-handlers";
-import { retrieveAxiosErrorMessage } from "#/utils/retrieve-axios-error-message";
-import { AppSettingsInputsSkeleton } from "#/components/features/settings/app-settings/app-settings-inputs-skeleton";
-
-function AppSettingsScreen() {
-  const { t } = useTranslation();
-
-  const { mutate: saveSettings, isPending } = useSaveSettings();
-  const { data: settings, isLoading } = useSettings();
-
-  const [languageInputHasChanged, setLanguageInputHasChanged] =
-    React.useState(false);
-  const [analyticsSwitchHasChanged, setAnalyticsSwitchHasChanged] =
-    React.useState(false);
-  const [
-    soundNotificationsSwitchHasChanged,
-    setSoundNotificationsSwitchHasChanged,
-  ] = React.useState(false);
-
-  const formAction = (formData: FormData) => {
-    const languageLabel = formData.get("language-input")?.toString();
-    const languageValue = AvailableLanguages.find(
-      ({ label }) => label === languageLabel,
-    )?.value;
-    const language = languageValue || DEFAULT_SETTINGS.LANGUAGE;
-
-    const enableAnalytics =
-      formData.get("enable-analytics-switch")?.toString() === "on";
-    const enableSoundNotifications =
-      formData.get("enable-sound-notifications-switch")?.toString() === "on";
-
-    saveSettings(
-      {
-        LANGUAGE: language,
-        user_consents_to_analytics: enableAnalytics,
-        ENABLE_SOUND_NOTIFICATIONS: enableSoundNotifications,
-      },
-      {
-        onSuccess: () => {
-          handleCaptureConsent(enableAnalytics);
-          displaySuccessToast(t(I18nKey.SETTINGS$SAVED));
-        },
-        onError: (error) => {
-          const errorMessage = retrieveAxiosErrorMessage(error);
-          displayErrorToast(errorMessage || t(I18nKey.ERROR$GENERIC));
-        },
-        onSettled: () => {
-          setLanguageInputHasChanged(false);
-          setAnalyticsSwitchHasChanged(false);
-          setSoundNotificationsSwitchHasChanged(false);
-        },
-      },
-    );
-  };
-
-  const checkIfLanguageInputHasChanged = (value: string) => {
-    const selectedLanguage = AvailableLanguages.find(
-      ({ label: langValue }) => langValue === value,
-    )?.label;
-    const currentLanguage = AvailableLanguages.find(
-      ({ value: langValue }) => langValue === settings?.LANGUAGE,
-    )?.label;
-
-    setLanguageInputHasChanged(selectedLanguage !== currentLanguage);
-  };
-
-  const checkIfAnalyticsSwitchHasChanged = (checked: boolean) => {
-    const currentAnalytics = !!settings?.USER_CONSENTS_TO_ANALYTICS;
-    setAnalyticsSwitchHasChanged(checked !== currentAnalytics);
-  };
-
-  const checkIfSoundNotificationsSwitchHasChanged = (checked: boolean) => {
-    const currentSoundNotifications = !!settings?.ENABLE_SOUND_NOTIFICATIONS;
-    setSoundNotificationsSwitchHasChanged(
-      checked !== currentSoundNotifications,
-    );
-  };
-
-  const formIsClean =
-    !languageInputHasChanged &&
-    !analyticsSwitchHasChanged &&
-    !soundNotificationsSwitchHasChanged;
-
-  const shouldBeLoading = !settings || isLoading || isPending;
-
-  return (
-    <form
-      data-testid="app-settings-screen"
-      action={formAction}
-      className="flex flex-col h-full justify-between"
-    >
-      {shouldBeLoading && <AppSettingsInputsSkeleton />}
-      {!shouldBeLoading && (
-        <div className="p-9 flex flex-col gap-6">
-          <LanguageInput
-            name="language-input"
-            defaultKey={settings.LANGUAGE}
-            onChange={checkIfLanguageInputHasChanged}
-          />
-
-          <SettingsSwitch
-            testId="enable-analytics-switch"
-            name="enable-analytics-switch"
-            defaultIsToggled={!!settings.USER_CONSENTS_TO_ANALYTICS}
-            onToggle={checkIfAnalyticsSwitchHasChanged}
-          >
-            {t(I18nKey.ANALYTICS$ENABLE)}
-          </SettingsSwitch>
-
-          <SettingsSwitch
-            testId="enable-sound-notifications-switch"
-            name="enable-sound-notifications-switch"
-            defaultIsToggled={!!settings.ENABLE_SOUND_NOTIFICATIONS}
-            onToggle={checkIfSoundNotificationsSwitchHasChanged}
-          >
-            {t(I18nKey.SETTINGS$SOUND_NOTIFICATIONS)}
-          </SettingsSwitch>
-        </div>
-      )}
-
-      <div className="flex gap-6 p-6 justify-end border-t border-t-tertiary">
-        <BrandButton
-          testId="submit-button"
-          variant="primary"
-          type="submit"
-          isDisabled={isPending || formIsClean}
-        >
-          {!isPending && t("SETTINGS$SAVE_CHANGES")}
-          {isPending && t("SETTINGS$SAVING")}
-        </BrandButton>
-      </div>
-    </form>
-  );
-}
-
-export default AppSettingsScreen;

frontend/src/routes/git-settings.tsx

@@ -1,134 +0,0 @@
-import React from "react";
-import { useTranslation } from "react-i18next";
-import { useSaveSettings } from "#/hooks/mutation/use-save-settings";
-import { useConfig } from "#/hooks/query/use-config";
-import { useSettings } from "#/hooks/query/use-settings";
-import { BrandButton } from "#/components/features/settings/brand-button";
-import { useLogout } from "#/hooks/mutation/use-logout";
-import { GitHubTokenInput } from "#/components/features/settings/git-settings/github-token-input";
-import { GitLabTokenInput } from "#/components/features/settings/git-settings/gitlab-token-input";
-import { ConfigureGitHubRepositoriesAnchor } from "#/components/features/settings/git-settings/configure-github-repositories-anchor";
-import { I18nKey } from "#/i18n/declaration";
-import {
-  displayErrorToast,
-  displaySuccessToast,
-} from "#/utils/custom-toast-handlers";
-import { retrieveAxiosErrorMessage } from "#/utils/retrieve-axios-error-message";
-import { GitSettingInputsSkeleton } from "#/components/features/settings/git-settings/github-settings-inputs-skeleton";
-
-function GitSettingsScreen() {
-  const { t } = useTranslation();
-
-  const { mutate: saveSettings, isPending } = useSaveSettings();
-  const { mutate: disconnectGitTokens } = useLogout();
-
-  const { data: settings, isLoading } = useSettings();
-  const { data: config } = useConfig();
-
-  const [githubTokenInputHasValue, setGithubTokenInputHasValue] =
-    React.useState(false);
-  const [gitlabTokenInputHasValue, setGitlabTokenInputHasValue] =
-    React.useState(false);
-
-  const isSaas = config?.APP_MODE === "saas";
-  const isGitHubTokenSet = !!settings?.PROVIDER_TOKENS_SET.github;
-  const isGitLabTokenSet = !!settings?.PROVIDER_TOKENS_SET.gitlab;
-
-  const formAction = async (formData: FormData) => {
-    const disconnectButtonClicked =
-      formData.get("disconnect-tokens-button") !== null;
-
-    if (disconnectButtonClicked) {
-      disconnectGitTokens();
-      return;
-    }
-
-    const githubToken = formData.get("github-token-input")?.toString() || "";
-    const gitlabToken = formData.get("gitlab-token-input")?.toString() || "";
-
-    saveSettings(
-      {
-        provider_tokens: {
-          github: githubToken,
-          gitlab: gitlabToken,
-        },
-      },
-      {
-        onSuccess: () => {
-          displaySuccessToast(t(I18nKey.SETTINGS$SAVED));
-        },
-        onError: (error) => {
-          const errorMessage = retrieveAxiosErrorMessage(error);
-          displayErrorToast(errorMessage || t(I18nKey.ERROR$GENERIC));
-        },
-        onSettled: () => {
-          setGithubTokenInputHasValue(false);
-          setGitlabTokenInputHasValue(false);
-        },
-      },
-    );
-  };
-
-  const formIsClean = !githubTokenInputHasValue && !gitlabTokenInputHasValue;
-  const shouldRenderExternalConfigureButtons = isSaas && config.APP_SLUG;
-
-  return (
-    <form
-      data-testid="git-settings-screen"
-      action={formAction}
-      className="flex flex-col h-full justify-between"
-    >
-      {isLoading && <GitSettingInputsSkeleton />}
-
-      {shouldRenderExternalConfigureButtons && !isLoading && (
-        <ConfigureGitHubRepositoriesAnchor slug={config.APP_SLUG!} />
-      )}
-
-      {!isSaas && !isLoading && (
-        <div className="p-9 flex flex-col gap-12">
-          <GitHubTokenInput
-            name="github-token-input"
-            isGitHubTokenSet={isGitHubTokenSet}
-            onChange={(value) => {
-              setGithubTokenInputHasValue(!!value);
-            }}
-          />
-
-          <GitLabTokenInput
-            name="gitlab-token-input"
-            isGitLabTokenSet={isGitLabTokenSet}
-            onChange={(value) => {
-              setGitlabTokenInputHasValue(!!value);
-            }}
-          />
-        </div>
-      )}
-
-      {!shouldRenderExternalConfigureButtons && (
-        <div className="flex gap-6 p-6 justify-end border-t border-t-tertiary">
-          <BrandButton
-            testId="disconnect-tokens-button"
-            name="disconnect-tokens-button"
-            type="submit"
-            variant="secondary"
-            isDisabled={!isGitHubTokenSet && !isGitLabTokenSet}
-          >
-            Disconnect Tokens
-          </BrandButton>
-
-          <BrandButton
-            testId="submit-button"
-            type="submit"
-            variant="primary"
-            isDisabled={isPending || formIsClean}
-          >
-            {!isPending && t("SETTINGS$SAVE_CHANGES")}
-            {isPending && t("SETTINGS$SAVING")}
-          </BrandButton>
-        </div>
-      )}
-    </form>
-  );
-}
-
-export default GitSettingsScreen;

frontend/src/routes/home.tsx

@@ -22,7 +22,7 @@ function HomeScreen() {
 
       <hr className="border-[#717888]" />
 
-      <main className="flex flex-col md:flex-row justify-between gap-4">
+      <main className="flex justify-between gap-4">
         <RepoConnector
           onRepoSelection={(title) => setSelectedRepoTitle(title)}
         />

frontend/src/routes/llm-settings.tsx

@@ -1,430 +0,0 @@
-import React from "react";
-import { useTranslation } from "react-i18next";
-import { AxiosError } from "axios";
-import { ModelSelector } from "#/components/shared/modals/settings/model-selector";
-import { organizeModelsAndProviders } from "#/utils/organize-models-and-providers";
-import { useAIConfigOptions } from "#/hooks/query/use-ai-config-options";
-import { useSettings } from "#/hooks/query/use-settings";
-import { hasAdvancedSettingsSet } from "#/utils/has-advanced-settings-set";
-import { useSaveSettings } from "#/hooks/mutation/use-save-settings";
-import { SettingsSwitch } from "#/components/features/settings/settings-switch";
-import { I18nKey } from "#/i18n/declaration";
-import { SettingsInput } from "#/components/features/settings/settings-input";
-import { HelpLink } from "#/components/features/settings/help-link";
-import { BrandButton } from "#/components/features/settings/brand-button";
-import {
-  displayErrorToast,
-  displaySuccessToast,
-} from "#/utils/custom-toast-handlers";
-import { retrieveAxiosErrorMessage } from "#/utils/retrieve-axios-error-message";
-import { SettingsDropdownInput } from "#/components/features/settings/settings-dropdown-input";
-import { useConfig } from "#/hooks/query/use-config";
-import { isCustomModel } from "#/utils/is-custom-model";
-import { LlmSettingsInputsSkeleton } from "#/components/features/settings/llm-settings/llm-settings-inputs-skeleton";
-import { KeyStatusIcon } from "#/components/features/settings/key-status-icon";
-
-function LlmSettingsScreen() {
-  const { t } = useTranslation();
-
-  const { mutate: saveSettings, isPending } = useSaveSettings();
-
-  const { data: resources } = useAIConfigOptions();
-  const { data: settings, isLoading, isFetching } = useSettings();
-  const { data: config } = useConfig();
-
-  const [view, setView] = React.useState<"basic" | "advanced">("basic");
-  const [securityAnalyzerInputIsVisible, setSecurityAnalyzerInputIsVisible] =
-    React.useState(false);
-
-  const [dirtyInputs, setDirtyInputs] = React.useState({
-    model: false,
-    apiKey: false,
-    baseUrl: false,
-    agent: false,
-    confirmationMode: false,
-    enableDefaultCondenser: false,
-    securityAnalyzer: false,
-  });
-
-  const modelsAndProviders = organizeModelsAndProviders(
-    resources?.models || [],
-  );
-
-  React.useEffect(() => {
-    const determineWhetherToToggleAdvancedSettings = () => {
-      if (resources && settings) {
-        return (
-          isCustomModel(resources.models, settings.LLM_MODEL) ||
-          hasAdvancedSettingsSet({
-            ...settings,
-          })
-        );
-      }
-
-      return false;
-    };
-
-    const userSettingsIsAdvanced = determineWhetherToToggleAdvancedSettings();
-    if (settings) setSecurityAnalyzerInputIsVisible(settings.CONFIRMATION_MODE);
-
-    if (userSettingsIsAdvanced) setView("advanced");
-    else setView("basic");
-  }, [settings, resources]);
-
-  const handleSuccessfulMutation = () => {
-    displaySuccessToast(t(I18nKey.SETTINGS$SAVED));
-    setDirtyInputs({
-      model: false,
-      apiKey: false,
-      baseUrl: false,
-      agent: false,
-      confirmationMode: false,
-      enableDefaultCondenser: false,
-      securityAnalyzer: false,
-    });
-  };
-
-  const handleErrorMutation = (error: AxiosError) => {
-    const errorMessage = retrieveAxiosErrorMessage(error);
-    displayErrorToast(errorMessage || t(I18nKey.ERROR$GENERIC));
-  };
-
-  const basicFormAction = (formData: FormData) => {
-    const provider = formData.get("llm-provider-input")?.toString();
-    const model = formData.get("llm-model-input")?.toString();
-    const apiKey = formData.get("llm-api-key-input")?.toString();
-
-    const fullLlmModel =
-      provider && model && `${provider}/${model}`.toLowerCase();
-
-    saveSettings(
-      {
-        LLM_MODEL: fullLlmModel,
-        llm_api_key: apiKey || null,
-      },
-      {
-        onSuccess: handleSuccessfulMutation,
-        onError: handleErrorMutation,
-      },
-    );
-  };
-
-  const advancedFormAction = (formData: FormData) => {
-    const model = formData.get("llm-custom-model-input")?.toString();
-    const baseUrl = formData.get("base-url-input")?.toString();
-    const apiKey = formData.get("llm-api-key-input")?.toString();
-    const agent = formData.get("agent-input")?.toString();
-    const confirmationMode =
-      formData.get("enable-confirmation-mode-switch")?.toString() === "on";
-    const enableDefaultCondenser =
-      formData.get("enable-memory-condenser-switch")?.toString() === "on";
-    const securityAnalyzer = formData
-      .get("security-analyzer-input")
-      ?.toString();
-
-    saveSettings(
-      {
-        LLM_MODEL: model,
-        LLM_BASE_URL: baseUrl,
-        llm_api_key: apiKey,
-        AGENT: agent,
-        CONFIRMATION_MODE: confirmationMode,
-        ENABLE_DEFAULT_CONDENSER: enableDefaultCondenser,
-        SECURITY_ANALYZER: confirmationMode ? securityAnalyzer : undefined,
-      },
-      {
-        onSuccess: handleSuccessfulMutation,
-        onError: handleErrorMutation,
-      },
-    );
-  };
-
-  const formAction = (formData: FormData) => {
-    if (view === "basic") basicFormAction(formData);
-    else advancedFormAction(formData);
-  };
-
-  const handleToggleAdvancedSettings = (isToggled: boolean) => {
-    setSecurityAnalyzerInputIsVisible(!!settings?.CONFIRMATION_MODE);
-    setView(isToggled ? "advanced" : "basic");
-    setDirtyInputs({
-      model: false,
-      apiKey: false,
-      baseUrl: false,
-      agent: false,
-      confirmationMode: false,
-      enableDefaultCondenser: false,
-      securityAnalyzer: false,
-    });
-  };
-
-  const handleModelIsDirty = (model: string | null) => {
-    // openai providers are special case; see ModelSelector
-    // component for details
-    const modelIsDirty = model !== settings?.LLM_MODEL.replace("openai/", "");
-    setDirtyInputs((prev) => ({
-      ...prev,
-      model: modelIsDirty,
-    }));
-  };
-
-  const handleApiKeyIsDirty = (apiKey: string) => {
-    const apiKeyIsDirty = apiKey !== "";
-    setDirtyInputs((prev) => ({
-      ...prev,
-      apiKey: apiKeyIsDirty,
-    }));
-  };
-
-  const handleCustomModelIsDirty = (model: string) => {
-    const modelIsDirty = model !== settings?.LLM_MODEL && model !== "";
-    setDirtyInputs((prev) => ({
-      ...prev,
-      model: modelIsDirty,
-    }));
-  };
-
-  const handleBaseUrlIsDirty = (baseUrl: string) => {
-    const baseUrlIsDirty = baseUrl !== settings?.LLM_BASE_URL;
-    setDirtyInputs((prev) => ({
-      ...prev,
-      baseUrl: baseUrlIsDirty,
-    }));
-  };
-
-  const handleAgentIsDirty = (agent: string) => {
-    const agentIsDirty = agent !== settings?.AGENT && agent !== "";
-    setDirtyInputs((prev) => ({
-      ...prev,
-      agent: agentIsDirty,
-    }));
-  };
-
-  const handleConfirmationModeIsDirty = (isToggled: boolean) => {
-    setSecurityAnalyzerInputIsVisible(isToggled);
-    const confirmationModeIsDirty = isToggled !== settings?.CONFIRMATION_MODE;
-    setDirtyInputs((prev) => ({
-      ...prev,
-      confirmationMode: confirmationModeIsDirty,
-    }));
-  };
-
-  const handleEnableDefaultCondenserIsDirty = (isToggled: boolean) => {
-    const enableDefaultCondenserIsDirty =
-      isToggled !== settings?.ENABLE_DEFAULT_CONDENSER;
-    setDirtyInputs((prev) => ({
-      ...prev,
-      enableDefaultCondenser: enableDefaultCondenserIsDirty,
-    }));
-  };
-
-  const handleSecurityAnalyzerIsDirty = (securityAnalyzer: string) => {
-    const securityAnalyzerIsDirty =
-      securityAnalyzer !== settings?.SECURITY_ANALYZER;
-    setDirtyInputs((prev) => ({
-      ...prev,
-      securityAnalyzer: securityAnalyzerIsDirty,
-    }));
-  };
-
-  const formIsDirty = Object.values(dirtyInputs).some((isDirty) => isDirty);
-
-  if (!settings || isFetching) return <LlmSettingsInputsSkeleton />;
-
-  return (
-    <div data-testid="llm-settings-screen" className="h-full">
-      <form
-        action={formAction}
-        className="flex flex-col h-full justify-between"
-      >
-        <div className="p-9 flex flex-col gap-6">
-          <SettingsSwitch
-            testId="advanced-settings-switch"
-            defaultIsToggled={view === "advanced"}
-            onToggle={handleToggleAdvancedSettings}
-            isToggled={view === "advanced"}
-          >
-            {t(I18nKey.SETTINGS$ADVANCED)}
-          </SettingsSwitch>
-
-          {view === "basic" && (
-            <div
-              data-testid="llm-settings-form-basic"
-              className="flex flex-col gap-6"
-            >
-              {!isLoading && !isFetching && (
-                <ModelSelector
-                  models={modelsAndProviders}
-                  currentModel={
-                    settings.LLM_MODEL || "anthropic/claude-3-5-sonnet-20241022"
-                  }
-                  onChange={handleModelIsDirty}
-                />
-              )}
-
-              <SettingsInput
-                testId="llm-api-key-input"
-                name="llm-api-key-input"
-                label={t(I18nKey.SETTINGS_FORM$API_KEY)}
-                type="password"
-                className="w-[680px]"
-                placeholder={settings.LLM_API_KEY_SET ? "<hidden>" : ""}
-                onChange={handleApiKeyIsDirty}
-                startContent={
-                  settings.LLM_API_KEY_SET && (
-                    <KeyStatusIcon isSet={settings.LLM_API_KEY_SET} />
-                  )
-                }
-              />
-
-              <HelpLink
-                testId="llm-api-key-help-anchor"
-                text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
-                linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
-                href="https://docs.all-hands.dev/modules/usage/installation#getting-an-api-key"
-              />
-            </div>
-          )}
-
-          {view === "advanced" && (
-            <div
-              data-testid="llm-settings-form-advanced"
-              className="flex flex-col gap-6"
-            >
-              <SettingsInput
-                testId="llm-custom-model-input"
-                name="llm-custom-model-input"
-                label={t(I18nKey.SETTINGS$CUSTOM_MODEL)}
-                defaultValue={
-                  settings.LLM_MODEL || "anthropic/claude-3-5-sonnet-20241022"
-                }
-                placeholder="anthropic/claude-3-5-sonnet-20241022"
-                type="text"
-                className="w-[680px]"
-                onChange={handleCustomModelIsDirty}
-              />
-
-              <SettingsInput
-                testId="base-url-input"
-                name="base-url-input"
-                label={t(I18nKey.SETTINGS$BASE_URL)}
-                defaultValue={settings.LLM_BASE_URL}
-                placeholder="https://api.openai.com"
-                type="text"
-                className="w-[680px]"
-                onChange={handleBaseUrlIsDirty}
-              />
-
-              <SettingsInput
-                testId="llm-api-key-input"
-                name="llm-api-key-input"
-                label={t(I18nKey.SETTINGS_FORM$API_KEY)}
-                type="password"
-                className="w-[680px]"
-                placeholder={settings.LLM_API_KEY_SET ? "<hidden>" : ""}
-                onChange={handleApiKeyIsDirty}
-                startContent={
-                  settings.LLM_API_KEY_SET && (
-                    <KeyStatusIcon isSet={settings.LLM_API_KEY_SET} />
-                  )
-                }
-              />
-              <HelpLink
-                testId="llm-api-key-help-anchor"
-                text={t(I18nKey.SETTINGS$DONT_KNOW_API_KEY)}
-                linkText={t(I18nKey.SETTINGS$CLICK_FOR_INSTRUCTIONS)}
-                href="https://docs.all-hands.dev/modules/usage/installation#getting-an-api-key"
-              />
-
-              <SettingsDropdownInput
-                testId="agent-input"
-                name="agent-input"
-                label={t(I18nKey.SETTINGS$AGENT)}
-                items={
-                  resources?.agents.map((agent) => ({
-                    key: agent,
-                    label: agent,
-                  })) || []
-                }
-                defaultSelectedKey={settings.AGENT}
-                isClearable={false}
-                onInputChange={handleAgentIsDirty}
-                wrapperClassName="w-[680px]"
-              />
-
-              {config?.APP_MODE === "saas" && (
-                <SettingsDropdownInput
-                  testId="runtime-settings-input"
-                  name="runtime-settings-input"
-                  label={
-                    <>
-                      {t(I18nKey.SETTINGS$RUNTIME_SETTINGS)}
-                      <a href="mailto:contact@all-hands.dev">
-                        {t(I18nKey.SETTINGS$GET_IN_TOUCH)}
-                      </a>
-                      )
-                    </>
-                  }
-                  items={[]}
-                  isDisabled
-                />
-              )}
-
-              <SettingsSwitch
-                testId="enable-memory-condenser-switch"
-                name="enable-memory-condenser-switch"
-                defaultIsToggled={settings.ENABLE_DEFAULT_CONDENSER}
-                onToggle={handleEnableDefaultCondenserIsDirty}
-              >
-                {t(I18nKey.SETTINGS$ENABLE_MEMORY_CONDENSATION)}
-              </SettingsSwitch>
-
-              <SettingsSwitch
-                testId="enable-confirmation-mode-switch"
-                name="enable-confirmation-mode-switch"
-                onToggle={handleConfirmationModeIsDirty}
-                defaultIsToggled={settings.CONFIRMATION_MODE}
-                isBeta
-              >
-                {t(I18nKey.SETTINGS$CONFIRMATION_MODE)}
-              </SettingsSwitch>
-
-              {securityAnalyzerInputIsVisible && (
-                <SettingsDropdownInput
-                  testId="security-analyzer-input"
-                  name="security-analyzer-input"
-                  label={t(I18nKey.SETTINGS$SECURITY_ANALYZER)}
-                  items={
-                    resources?.securityAnalyzers.map((analyzer) => ({
-                      key: analyzer,
-                      label: analyzer,
-                    })) || []
-                  }
-                  defaultSelectedKey={settings.SECURITY_ANALYZER}
-                  isClearable
-                  showOptionalTag
-                  onInputChange={handleSecurityAnalyzerIsDirty}
-                  wrapperClassName="w-[680px]"
-                />
-              )}
-            </div>
-          )}
-        </div>
-
-        <div className="flex gap-6 p-6 justify-end border-t border-t-tertiary">
-          <BrandButton
-            testId="submit-button"
-            type="submit"
-            variant="primary"
-            isDisabled={!formIsDirty || isPending}
-          >
-            {!isPending && t("SETTINGS$SAVE_CHANGES")}
-            {isPending && t("SETTINGS$SAVING")}
-          </BrandButton>
-        </div>
-      </form>
-    </div>
-  );
-}
-
-export default LlmSettingsScreen;

frontend/src/routes/settings.tsx

@@ -1,6 +1,5 @@
-import { NavLink, Outlet, useLocation, useNavigate } from "react-router";
+import { NavLink, Outlet } from "react-router";
 import { useTranslation } from "react-i18next";
-import React from "react";
 import SettingsIcon from "#/icons/settings.svg?react";
 import { cn } from "#/utils/utils";
 import { useConfig } from "#/hooks/query/use-config";
@@ -8,44 +7,9 @@ import { I18nKey } from "#/i18n/declaration";
 
 function SettingsScreen() {
   const { t } = useTranslation();
-  const navigate = useNavigate();
-  const { pathname } = useLocation();
   const { data: config } = useConfig();
-
   const isSaas = config?.APP_MODE === "saas";
 
-  const saasNavItems = [
-    { to: "/settings/git", text: t("SETTINGS$NAV_GIT") },
-    { to: "/settings/app", text: t("SETTINGS$NAV_APPLICATION") },
-    { to: "/settings/billing", text: t("SETTINGS$NAV_CREDITS") },
-    { to: "/settings/api-keys", text: t("SETTINGS$NAV_API_KEYS") },
-  ];
-
-  const ossNavItems = [
-    { to: "/settings", text: t("SETTINGS$NAV_LLM") },
-    { to: "/settings/git", text: t("SETTINGS$NAV_GIT") },
-    { to: "/settings/app", text: t("SETTINGS$NAV_APPLICATION") },
-  ];
-
-  React.useEffect(() => {
-    if (isSaas) {
-      if (pathname === "/settings") {
-        navigate("/settings/git");
-      }
-    } else {
-      const noEnteringPaths = [
-        "/settings/billing",
-        "/settings/credits",
-        "/settings/api-keys",
-      ];
-      if (noEnteringPaths.includes(pathname)) {
-        navigate("/settings");
-      }
-    }
-  }, [isSaas, pathname]);
-
-  const navItems = isSaas ? saasNavItems : ossNavItems;
-
   return (
     <main
       data-testid="settings-screen"
@@ -56,26 +20,32 @@ function SettingsScreen() {
         <h1 className="text-sm leading-6">{t(I18nKey.SETTINGS$TITLE)}</h1>
       </header>
 
-      <nav
-        data-testid="settings-navbar"
-        className="flex items-end gap-12 px-9 border-b border-tertiary"
-      >
-        {navItems.map(({ to, text }) => (
-          <NavLink
-            end
-            key={to}
-            to={to}
-            className={({ isActive }) =>
-              cn(
-                "border-b-2 border-transparent py-2.5",
-                isActive && "border-primary",
-              )
-            }
-          >
-            <ul className="text-[#F9FBFE] text-sm">{text}</ul>
-          </NavLink>
-        ))}
-      </nav>
+      {isSaas && (
+        <nav
+          data-testid="settings-navbar"
+          className="flex items-end gap-12 px-11 border-b border-tertiary"
+        >
+          {[
+            { to: "/settings", text: "Account" },
+            { to: "/settings/billing", text: "Credits" },
+            { to: "/settings/api-keys", text: "API Keys" },
+          ].map(({ to, text }) => (
+            <NavLink
+              end
+              key={to}
+              to={to}
+              className={({ isActive }) =>
+                cn(
+                  "border-b-2 border-transparent py-2.5",
+                  isActive && "border-primary",
+                )
+              }
+            >
+              <ul className="text-[#F9FBFE] text-sm">{text}</ul>
+            </NavLink>
+          ))}
+        </nav>
+      )}
 
       <div className="flex flex-col grow overflow-auto">
         <Outlet />

frontend/src/tailwind.css

@@ -6,14 +6,10 @@
   @apply bg-tertiary border border-neutral-600 rounded;
 }
 
-.skeleton {
-  @apply bg-gray-400 rounded-md animate-pulse;
-}
-
-.skeleton-round {
-  @apply bg-gray-400 rounded-full animate-pulse;
-}
-
 .heading {
   @apply text-[28px] leading-8 -tracking-[0.02em] font-bold text-content-2;
 }
+
+.skeleton {
+  @apply bg-gray-400 rounded-md animate-pulse;
+}

frontend/src/utils/has-advanced-settings-set.ts

@@ -2,8 +2,9 @@ import { DEFAULT_SETTINGS } from "#/services/settings";
 import { Settings } from "#/types/settings";
 
 export const hasAdvancedSettingsSet = (settings: Partial<Settings>): boolean =>
-  Object.keys(settings).length > 0 &&
-  (!!settings.LLM_BASE_URL ||
-    settings.AGENT !== DEFAULT_SETTINGS.AGENT ||
-    settings.CONFIRMATION_MODE ||
-    !!settings.SECURITY_ANALYZER);
+  !!settings.LLM_BASE_URL ||
+  settings.AGENT !== DEFAULT_SETTINGS.AGENT ||
+  settings.REMOTE_RUNTIME_RESOURCE_FACTOR !==
+    DEFAULT_SETTINGS.REMOTE_RUNTIME_RESOURCE_FACTOR ||
+  settings.CONFIRMATION_MODE ||
+  !!settings.SECURITY_ANALYZER;

openhands/agenthub/codeact_agent/codeact_agent.py

@@ -20,7 +20,10 @@ from openhands.controller.state.state import State
 from openhands.core.config import AgentConfig
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.message import Message
-from openhands.events.action import Action, AgentFinishAction, MessageAction
+from openhands.events.action import (
+    Action,
+    AgentFinishAction,
+)
 from openhands.events.event import Event
 from openhands.llm.llm import LLM
 from openhands.memory.condenser import Condenser
@@ -170,8 +173,7 @@ class CodeActAgent(Agent):
             f'Processing {len(condensed_history)} events from a total of {len(state.history)} events'
         )
 
-        initial_user_message = self._get_initial_user_message(state.history)
-        messages = self._get_messages(condensed_history, initial_user_message)
+        messages = self._get_messages(condensed_history)
         params: dict = {
             'messages': self.llm.format_messages_for_llm(messages),
         }
@@ -214,29 +216,7 @@ class CodeActAgent(Agent):
             self.pending_actions.append(action)
         return self.pending_actions.popleft()
 
-    def _get_initial_user_message(self, history: list[Event]) -> MessageAction:
-        """Finds the initial user message action from the full history."""
-        initial_user_message: MessageAction | None = None
-        for event in history:
-            if isinstance(event, MessageAction) and event.source == 'user':
-                initial_user_message = event
-                break
-
-        if initial_user_message is None:
-            # This should not happen in a valid conversation
-            logger.error(
-                f'CRITICAL: Could not find the initial user MessageAction in the full {len(history)} events history.'
-            )
-            # Depending on desired robustness, could raise error or create a dummy action
-            # and log the error
-            raise ValueError(
-                'Initial user message not found in history. Please report this issue.'
-            )
-        return initial_user_message
-
-    def _get_messages(
-        self, events: list[Event], initial_user_message: MessageAction
-    ) -> list[Message]:
+    def _get_messages(self, events: list[Event]) -> list[Message]:
         """Constructs the message history for the LLM conversation.
 
         This method builds a structured conversation history by processing events from the state
@@ -273,7 +253,6 @@ class CodeActAgent(Agent):
         # Use ConversationMemory to process events (including SystemMessageAction)
         messages = self.conversation_memory.process_events(
             condensed_history=events,
-            initial_user_action=initial_user_message,
             max_message_chars=self.llm.config.max_message_chars,
             vision_is_active=self.llm.vision_is_active(),
         )

openhands/controller/agent_controller.py

@@ -190,7 +190,7 @@ class AgentController:
         logger.debug(f'System message got from agent: {system_message}')
         if system_message:
             self.event_stream.add_event(system_message, EventSource.AGENT)
-            logger.info(f'System message added to event stream: {system_message}')
+            logger.debug(f'System message added to event stream: {system_message}')
 
     async def close(self, set_stop_state: bool = True) -> None:
         """Closes the agent controller, canceling any ongoing tasks and unsubscribing from the event stream.
@@ -1020,7 +1020,7 @@ class AgentController:
             self.state.start_id = 0
 
             self.log(
-                'info',
+                'debug',
                 f'AgentController {self.id} - created new state. start_id: {self.state.start_id}',
             )
         else:
@@ -1030,7 +1030,7 @@ class AgentController:
                 self.state.start_id = 0
 
             self.log(
-                'info',
+                'debug',
                 f'AgentController {self.id} initializing history from event {self.state.start_id}',
             )
 
@@ -1143,169 +1143,70 @@ class AgentController:
 
     def _handle_long_context_error(self) -> None:
         # When context window is exceeded, keep roughly half of agent interactions
-        kept_events = self._apply_conversation_window()
-        kept_event_ids = {e.id for e in kept_events}
-
-        self.log(
-            'info',
-            f'Context window exceeded. Keeping events with IDs: {kept_event_ids}',
-        )
-
-        # The events to forget are those that are not in the kept set
+        kept_event_ids = {
+            e.id for e in self._apply_conversation_window(self.state.history)
+        }
         forgotten_event_ids = {e.id for e in self.state.history} - kept_event_ids
 
-        if len(kept_event_ids) == 0:
-            self.log(
-                'warning',
-                'No events kept after applying conversation window. This should not happen.',
-            )
-
-        # verify that the first event id in kept_event_ids is the same as the start_id
-        if len(kept_event_ids) > 0 and self.state.history[0].id not in kept_event_ids:
-            self.log(
-                'warning',
-                f'First event after applying conversation window was not kept: {self.state.history[0].id} not in {kept_event_ids}',
-            )
+        # Save the ID of the first event in our truncated history for future reloading
+        if self.state.history:
+            self.state.start_id = self.state.history[0].id
 
         # Add an error event to trigger another step by the agent
         self.event_stream.add_event(
             CondensationAction(
-                forgotten_events_start_id=min(forgotten_event_ids)
-                if forgotten_event_ids
-                else 0,
-                forgotten_events_end_id=max(forgotten_event_ids)
-                if forgotten_event_ids
-                else 0,
+                forgotten_events_start_id=min(forgotten_event_ids),
+                forgotten_events_end_id=max(forgotten_event_ids),
             ),
             EventSource.AGENT,
         )
 
-    def _apply_conversation_window(self) -> list[Event]:
+    def _apply_conversation_window(self, events: list[Event]) -> list[Event]:
         """Cuts history roughly in half when context window is exceeded.
 
-        It preserves action-observation pairs and ensures that the system message,
-        the first user message, and its associated recall observation are always included
-        at the beginning of the context window.
+        It preserves action-observation pairs and ensures that the first user message is always included.
 
         The algorithm:
-        1. Identify essential initial events: System Message, First User Message, Recall Observation.
-        2. Determine the slice of recent events to potentially keep.
-        3. Validate the start of the recent slice for dangling observations.
-        4. Combine essential events and validated recent events, ensuring essentials come first.
+        1. Cut history in half
+        2. Check first event in new history:
+           - If Observation: find and include its Action
+           - If MessageAction: ensure its related Action-Observation pair isn't split
+        3. Always include the first user message
 
         Args:
             events: List of events to filter
 
         Returns:
-            Filtered list of events keeping newest half while preserving pairs and essential initial events.
+            Filtered list of events keeping newest half while preserving pairs
         """
-        if not self.state.history:
-            return []
+        if not events:
+            return events
 
-        history = self.state.history
-
-        # 1. Identify essential initial events
-        system_message: SystemMessageAction | None = None
-        first_user_msg: MessageAction | None = None
-        recall_action: RecallAction | None = None
-        recall_observation: Observation | None = None
-
-        # Find System Message (should be the first event, if it exists)
-        system_message = next(
-            (e for e in history if isinstance(e, SystemMessageAction)), None
-        )
-        assert (
-            system_message is None
-            or isinstance(system_message, SystemMessageAction)
-            and system_message.id == history[0].id
+        # Find first user message - we'll need to ensure it's included
+        first_user_msg = next(
+            (
+                e
+                for e in events
+                if isinstance(e, MessageAction) and e.source == EventSource.USER
+            ),
+            None,
         )
 
-        # Find First User Message, which MUST exist
-        first_user_msg = self._first_user_message()
-        if first_user_msg is None:
-            raise RuntimeError('No first user message found in the event stream.')
+        # cut in half
+        mid_point = max(1, len(events) // 2)
+        kept_events = events[mid_point:]
+        if len(kept_events) > 0 and isinstance(kept_events[0], Observation):
+            kept_events = kept_events[1:]
 
-        first_user_msg_index = -1
-        for i, event in enumerate(history):
-            if isinstance(event, MessageAction) and event.source == EventSource.USER:
-                first_user_msg = event
-                first_user_msg_index = i
-                break
+        # Ensure first user message is included
+        if first_user_msg and first_user_msg not in kept_events:
+            kept_events = [first_user_msg] + kept_events
 
-        # Find Recall Action and Observation related to the First User Message
-        if first_user_msg is not None and first_user_msg_index != -1:
-            # Look for RecallAction after the first user message
-            for i in range(first_user_msg_index + 1, len(history)):
-                event = history[i]
-                if (
-                    isinstance(event, RecallAction)
-                    and event.query == first_user_msg.content
-                ):
-                    # Found RecallAction, now look for its Observation
-                    recall_action = event
-                    for j in range(i + 1, len(history)):
-                        obs_event = history[j]
-                        # Check for Observation caused by this RecallAction
-                        if (
-                            isinstance(obs_event, Observation)
-                            and obs_event.cause == recall_action.id
-                        ):
-                            recall_observation = obs_event
-                            break  # Found the observation, stop inner loop
-                    break  # Found the recall action (and maybe obs), stop outer loop
-
-        essential_events: list[Event] = []
-        if system_message:
-            essential_events.append(system_message)
+        # start_id points to first user message
         if first_user_msg:
-            essential_events.append(first_user_msg)
-        # Also keep the RecallAction that triggered the essential RecallObservation
-        if recall_action:
-            essential_events.append(recall_action)
-        if recall_observation:
-            essential_events.append(recall_observation)
+            self.state.start_id = first_user_msg.id
 
-        # 2. Determine the slice of recent events to potentially keep
-        num_non_essential_events = len(history) - len(essential_events)
-        # Keep roughly half of the non-essential events, minimum 1
-        num_recent_to_keep = max(1, num_non_essential_events // 2)
-
-        # Calculate the starting index for the recent slice
-        slice_start_index = len(history) - num_recent_to_keep
-        slice_start_index = max(0, slice_start_index)  # Ensure index is not negative
-        recent_events_slice = history[slice_start_index:]
-
-        # 3. Validate the start of the recent slice for dangling observations
-        # IMPORTANT: Most observations in history are tool call results, which cannot be without their action, or we get an LLM API error
-        first_valid_event_index = 0
-        for i, event in enumerate(recent_events_slice):
-            if isinstance(event, Observation):
-                first_valid_event_index += 1
-            else:
-                break
-        # If all events in the slice are dangling observations, we need to keep at least one
-        if first_valid_event_index == len(recent_events_slice):
-            self.log(
-                'warning',
-                'All recent events are dangling observations, which we truncate. This means the agent has only the essential first events. This should not happen.',
-            )
-
-        # Adjust the recent_events_slice if dangling observations were found at the start
-        if first_valid_event_index < len(recent_events_slice):
-            validated_recent_events = recent_events_slice[first_valid_event_index:]
-            if first_valid_event_index > 0:
-                self.log(
-                    'debug',
-                    f'Removed {first_valid_event_index} dangling observation(s) from the start of recent event slice.',
-                )
-        else:
-            validated_recent_events = []
-
-        # 4. Combine essential events and validated recent events
-        events_to_keep: list[Event] = essential_events + validated_recent_events
-        self.log('debug', f'History truncated. Kept {len(events_to_keep)} events.')
-
-        return events_to_keep
+        return kept_events
 
     def _is_stuck(self) -> bool:
         """Checks if the agent or its delegate is stuck in a loop.

openhands/core/cli.py

@@ -14,14 +14,12 @@ from openhands.core.cli_commands import (
 )
 from openhands.core.cli_tui import (
     UsageMetrics,
-    display_agent_running_message,
     display_banner,
     display_event,
     display_initial_user_prompt,
     display_initialization_animation,
     display_runtime_initialization_message,
     display_welcome_message,
-    process_agent_pause,
     read_confirmation_input,
     read_prompt_input,
 )
@@ -101,7 +99,6 @@ async def run_session(
 
     sid = str(uuid4())
     is_loaded = asyncio.Event()
-    is_paused = asyncio.Event()
 
     # Show runtime initialization message
     display_runtime_initialization_message(config.runtime)
@@ -127,12 +124,10 @@ async def run_session(
 
     usage_metrics = UsageMetrics()
 
-    async def prompt_for_next_task(agent_state: str):
+    async def prompt_for_next_task():
         nonlocal reload_microagents, new_session_requested
         while True:
-            next_message = await read_prompt_input(
-                agent_state, multiline=config.cli_multiline_input
-            )
+            next_message = await read_prompt_input(config.cli_multiline_input)
 
             if not next_message.strip():
                 continue
@@ -155,23 +150,14 @@ async def run_session(
                 return
 
     async def on_event_async(event: Event) -> None:
-        nonlocal reload_microagents, is_paused
+        nonlocal reload_microagents
         display_event(event, config)
         update_usage_metrics(event, usage_metrics)
 
-        # Pause the agent if the pause event is set (if Ctrl-P is pressed)
-        if is_paused.is_set():
-            event_stream.add_event(
-                ChangeAgentStateAction(AgentState.PAUSED),
-                EventSource.USER,
-            )
-            is_paused.clear()
-
         if isinstance(event, AgentStateChangedObservation):
             if event.agent_state in [
                 AgentState.AWAITING_USER_INPUT,
                 AgentState.FINISHED,
-                AgentState.PAUSED,
             ]:
                 # Reload microagents after initialization of repo.md
                 if reload_microagents:
@@ -180,28 +166,20 @@ async def run_session(
                     )
                     memory.load_user_workspace_microagents(microagents)
                     reload_microagents = False
-                await prompt_for_next_task(event.agent_state)
+                await prompt_for_next_task()
 
             if event.agent_state == AgentState.AWAITING_USER_CONFIRMATION:
-                # Only display the confirmation prompt if the agent is not paused
-                if not is_paused.is_set():
-                    user_confirmed = await read_confirmation_input()
-                    if user_confirmed:
-                        event_stream.add_event(
-                            ChangeAgentStateAction(AgentState.USER_CONFIRMED),
-                            EventSource.USER,
-                        )
-                    else:
-                        event_stream.add_event(
-                            ChangeAgentStateAction(AgentState.USER_REJECTED),
-                            EventSource.USER,
-                        )
-
-            if event.agent_state == AgentState.RUNNING:
-                # Enable pause/resume functionality only if the confirmation mode is disabled
-                if not config.security.confirmation_mode:
-                    display_agent_running_message()
-                    loop.create_task(process_agent_pause(is_paused))
+                user_confirmed = await read_confirmation_input()
+                if user_confirmed:
+                    event_stream.add_event(
+                        ChangeAgentStateAction(AgentState.USER_CONFIRMED),
+                        EventSource.USER,
+                    )
+                else:
+                    event_stream.add_event(
+                        ChangeAgentStateAction(AgentState.USER_REJECTED),
+                        EventSource.USER,
+                    )
 
     def on_event(event: Event) -> None:
         loop.create_task(on_event_async(event))
@@ -234,7 +212,7 @@ async def run_session(
     clear()
 
     # Show OpenHands banner and session ID
-    display_banner(session_id=sid)
+    display_banner(session_id=sid, is_loaded=is_loaded)
 
     # Show OpenHands welcome
     display_welcome_message()
@@ -247,7 +225,7 @@ async def run_session(
         )
     else:
         # Otherwise prompt for the user's first message right away
-        asyncio.create_task(prompt_for_next_task(''))
+        asyncio.create_task(prompt_for_next_task())
 
     await run_agent_until_done(
         controller, runtime, memory, [AgentState.STOPPED, AgentState.ERROR]

openhands/core/cli_commands.py

@@ -70,8 +70,6 @@ async def handle_commands(
         )
     elif command == '/settings':
         await handle_settings_command(config, settings_store)
-    elif command == '/resume':
-        close_repl, new_session_requested = await handle_resume_command(event_stream)
     else:
         close_repl = True
         action = MessageAction(content=command)
@@ -185,28 +183,6 @@ async def handle_settings_command(
         await modify_llm_settings_advanced(config, settings_store)
 
 
-# FIXME: Currently there's an issue with the actual 'resume' behavior.
-# Setting the agent state to RUNNING will currently freeze the agent without continuing with the rest of the task.
-# This is a workaround to handle the resume command for the time being. Replace user message with the state change event once the issue is fixed.
-async def handle_resume_command(
-    event_stream: EventStream,
-) -> tuple[bool, bool]:
-    close_repl = True
-    new_session_requested = False
-
-    event_stream.add_event(
-        MessageAction(content='continue'),
-        EventSource.USER,
-    )
-
-    # event_stream.add_event(
-    #     ChangeAgentStateAction(AgentState.RUNNING),
-    #     EventSource.ENVIRONMENT,
-    # )
-
-    return close_repl, new_session_requested
-
-
 async def init_repository(current_dir: str) -> bool:
     repo_file_path = Path(current_dir) / '.openhands' / 'microagents' / 'repo.md'
     init_repo = False

openhands/core/cli_tui.py

@@ -10,9 +10,7 @@ from prompt_toolkit import PromptSession, print_formatted_text
 from prompt_toolkit.application import Application
 from prompt_toolkit.completion import Completer, Completion
 from prompt_toolkit.formatted_text import HTML, FormattedText, StyleAndTextTuples
-from prompt_toolkit.input import create_input
 from prompt_toolkit.key_binding import KeyBindings
-from prompt_toolkit.keys import Keys
 from prompt_toolkit.layout.containers import HSplit, Window
 from prompt_toolkit.layout.controls import FormattedTextControl
 from prompt_toolkit.layout.layout import Layout
@@ -24,7 +22,6 @@ from prompt_toolkit.widgets import Frame, TextArea
 
 from openhands import __version__
 from openhands.core.config import AppConfig
-from openhands.core.schema import AgentState
 from openhands.events import EventSource
 from openhands.events.action import (
     Action,
@@ -35,7 +32,6 @@ from openhands.events.action import (
 )
 from openhands.events.event import Event
 from openhands.events.observation import (
-    AgentStateChangedObservation,
     CmdOutputObservation,
     FileEditObservation,
     FileReadObservation,
@@ -60,7 +56,6 @@ COMMANDS = {
     '/status': 'Display session details and usage metrics',
     '/new': 'Create a new session',
     '/settings': 'Display and modify current settings',
-    '/resume': 'Resume the agent',
 }
 
 
@@ -119,7 +114,7 @@ def display_initialization_animation(text, is_loaded: asyncio.Event):
     sys.stdout.flush()
 
 
-def display_banner(session_id: str):
+def display_banner(session_id: str, is_loaded: asyncio.Event):
     print_formatted_text(
         HTML(r"""<gold>
      ___                    _   _                 _
@@ -134,8 +129,11 @@ def display_banner(session_id: str):
 
     print_formatted_text(HTML(f'<grey>OpenHands CLI v{__version__}</grey>'))
 
+    banner_text = (
+        'Initialized session' if is_loaded.is_set() else 'Initializing session'
+    )
     print_formatted_text('')
-    print_formatted_text(HTML(f'<grey>Initialized session {session_id}</grey>'))
+    print_formatted_text(HTML(f'<grey>{banner_text} {session_id}</grey>'))
     print_formatted_text('')
 
 
@@ -179,8 +177,6 @@ def display_event(event: Event, config: AppConfig) -> None:
         display_file_edit(event)
     if isinstance(event, FileReadObservation):
         display_file_read(event)
-    if isinstance(event, AgentStateChangedObservation):
-        display_agent_paused_message(event.agent_state)
 
 
 def display_message(message: str):
@@ -393,58 +389,77 @@ def display_status(usage_metrics: UsageMetrics, session_id: str):
     display_usage_metrics(usage_metrics)
 
 
-def display_agent_running_message():
-    print_formatted_text('')
-    print_formatted_text(
-        HTML('<gold>Agent running...</gold> <grey>(Ctrl-P to pause)</grey>')
-    )
-
-
-def display_agent_paused_message(agent_state: str):
-    if agent_state != AgentState.PAUSED:
-        return
-    print_formatted_text('')
-    print_formatted_text(
-        HTML('<gold>Agent paused</gold> <grey>(type /resume to resume)</grey>')
-    )
-
-
 # Common input functions
 class CommandCompleter(Completer):
     """Custom completer for commands."""
 
-    def __init__(self, agent_state: str):
-        super().__init__()
-        self.agent_state = agent_state
-
     def get_completions(self, document, complete_event):
-        text = document.text_before_cursor.lstrip()
+        text = document.text
+
+        # Only show completions if the user has typed '/'
         if text.startswith('/'):
-            available_commands = dict(COMMANDS)
-            if self.agent_state != AgentState.PAUSED:
-                available_commands.pop('/resume', None)
-
-            for command, description in available_commands.items():
-                if command.startswith(text):
+            # If just '/' is typed, show all commands
+            if text == '/':
+                for command, description in COMMANDS.items():
                     yield Completion(
-                        command,
-                        start_position=-len(text),
-                        display_meta=description,
-                        style='bg:ansidarkgray fg:ansiwhite',
+                        command[1:],  # Remove the leading '/' as it's already typed
+                        start_position=0,
+                        display=f'{command} - {description}',
                     )
+            # Otherwise show matching commands
+            else:
+                for command, description in COMMANDS.items():
+                    if command.startswith(text):
+                        yield Completion(
+                            command[len(text) :],  # Complete the remaining part
+                            start_position=0,
+                            display=f'{command} - {description}',
+                        )
 
 
-def create_prompt_session():
-    return PromptSession(style=DEFAULT_STYLE)
+prompt_session = PromptSession(style=DEFAULT_STYLE)
+
+# RPrompt animation related variables
+SPINNER_FRAMES = [
+    '[ ■□□□ ]',
+    '[ □■□□ ]',
+    '[ □□■□ ]',
+    '[ □□□■ ]',
+    '[ □□■□ ]',
+    '[ □■□□ ]',
+]
+ANIMATION_INTERVAL = 0.2  # seconds
+
+current_frame_index = 0
+last_update_time = time.monotonic()
 
 
-async def read_prompt_input(agent_state: str, multiline=False):
+# RPrompt function for the user confirmation
+def get_rprompt() -> FormattedText:
+    """
+    Returns the current animation frame for the rprompt.
+    This function is called by prompt_toolkit during rendering.
+    """
+    global current_frame_index, last_update_time
+
+    # Only update the frame if enough time has passed
+    # This prevents excessive recalculation during rendering
+    now = time.monotonic()
+    if now - last_update_time > ANIMATION_INTERVAL:
+        current_frame_index = (current_frame_index + 1) % len(SPINNER_FRAMES)
+        last_update_time = now
+
+    # Return the frame wrapped in FormattedText
+    return FormattedText(
+        [
+            ('', ' '),  # Add a space before the spinner
+            (COLOR_GOLD, SPINNER_FRAMES[current_frame_index]),
+        ]
+    )
+
+
+async def read_prompt_input(multiline=False):
     try:
-        prompt_session = create_prompt_session()
-        prompt_session.completer = (
-            CommandCompleter(agent_state) if not multiline else None
-        )
-
         if multiline:
             kb = KeyBindings()
 
@@ -455,54 +470,38 @@ async def read_prompt_input(agent_state: str, multiline=False):
             with patch_stdout():
                 print_formatted_text('')
                 message = await prompt_session.prompt_async(
-                    HTML(
-                        '<gold>Enter your message and press Ctrl-D to finish:</gold>\n'
-                    ),
+                    'Enter your message and press Ctrl+D to finish:\n',
                     multiline=True,
                     key_bindings=kb,
                 )
         else:
             with patch_stdout():
                 print_formatted_text('')
+                prompt_session.completer = CommandCompleter()
                 message = await prompt_session.prompt_async(
-                    HTML('<gold>> </gold>'),
+                    '> ',
                 )
-        return message if message is not None else ''
+        return message
     except (KeyboardInterrupt, EOFError):
         return '/exit'
 
 
-async def read_confirmation_input() -> bool:
+async def read_confirmation_input():
     try:
-        prompt_session = create_prompt_session()
-
         with patch_stdout():
-            print_formatted_text('')
-            confirmation: str = await prompt_session.prompt_async(
-                HTML('<gold>Proceed with action? (y)es/(n)o > </gold>'),
+            prompt_session.completer = None
+            confirmation = await prompt_session.prompt_async(
+                'Proceed with action? (y)es/(n)o > ',
+                rprompt=get_rprompt,
+                refresh_interval=ANIMATION_INTERVAL / 2,
             )
-
-            confirmation = '' if confirmation is None else confirmation.strip().lower()
+            prompt_session.rprompt = None
+            confirmation = confirmation.strip().lower()
             return confirmation in ['y', 'yes']
     except (KeyboardInterrupt, EOFError):
         return False
 
 
-async def process_agent_pause(done: asyncio.Event) -> None:
-    input = create_input()
-
-    def keys_ready():
-        for key_press in input.read_keys():
-            if key_press.key == Keys.ControlP:
-                print_formatted_text('')
-                print_formatted_text(HTML('<gold>Pausing the agent...</gold>'))
-                done.set()
-
-    with input.raw_mode():
-        with input.attach(keys_ready):
-            await done.wait()
-
-
 def cli_confirm(
     question: str = 'Are you sure?', choices: list[str] | None = None
 ) -> int:

openhands/memory/conversation_memory.py

@@ -54,7 +54,6 @@ class ConversationMemory:
     def process_events(
         self,
         condensed_history: list[Event],
-        initial_user_action: MessageAction,
         max_message_chars: int | None = None,
         vision_is_active: bool = False,
     ) -> list[Message]:
@@ -67,14 +66,12 @@ class ConversationMemory:
             max_message_chars: The maximum number of characters in the content of an event included
                 in the prompt to the LLM. Larger observations are truncated.
             vision_is_active: Whether vision is active in the LLM. If True, image URLs will be included.
-            initial_user_action: The initial user message action, if available. Used to ensure the conversation starts correctly.
         """
 
         events = condensed_history
 
-        # Ensure the event list starts with SystemMessageAction, then MessageAction(source='user')
+        # Ensure the system message exists (handles legacy cases)
         self._ensure_system_message(events)
-        self._ensure_initial_user_message(events, initial_user_action)
 
         # log visual browsing status
         logger.debug(f'Visual browsing: {self.agent_config.enable_som_visual_browsing}')
@@ -702,43 +699,6 @@ class ConversationMemory:
                 system_message = SystemMessageAction(content=system_prompt)
                 # Insert the system message directly at the beginning of the events list
                 events.insert(0, system_message)
-                logger.info(
+                logger.debug(
                     '[ConversationMemory] Added SystemMessageAction for backward compatibility'
                 )
-
-    def _ensure_initial_user_message(
-        self, events: list[Event], initial_user_action: MessageAction
-    ) -> None:
-        """Checks if the second event is a user MessageAction and inserts the provided one if needed."""
-        if (
-            not events
-        ):  # Should have system message from previous step, but safety check
-            logger.error('Cannot ensure initial user message: event list is empty.')
-            # Or raise? Let's log for now, _ensure_system_message should handle this.
-            return
-
-        # We expect events[0] to be SystemMessageAction after _ensure_system_message
-        if len(events) == 1:
-            # Only system message exists
-            logger.info(
-                'Initial user message action was missing. Inserting the initial user message.'
-            )
-            events.insert(1, initial_user_action)
-        elif not isinstance(events[1], MessageAction) or events[1].source != 'user':
-            # The second event exists but is not the correct initial user message action.
-            # We will insert the correct one provided.
-            logger.info(
-                'Second event was not the initial user message action. Inserting correct one at index 1.'
-            )
-
-            # Insert the user message event at index 1. This will be the second message as LLM APIs expect
-            # but something was wrong with the history, so log all we can.
-            events.insert(1, initial_user_action)
-
-        # Else: events[1] is already a user MessageAction.
-        # Check if it matches the one provided (if any discrepancy, log warning but proceed).
-        elif events[1] != initial_user_action:
-            logger.debug(
-                'The user MessageAction at index 1 does not match the provided initial_user_action. '
-                'Proceeding with the one found in condensed history.'
-            )

openhands/memory/view.py

@@ -4,7 +4,6 @@ from typing import overload
 
 from pydantic import BaseModel
 
-from openhands.core.logger import openhands_logger as logger
 from openhands.events.action.agent import CondensationAction
 from openhands.events.event import Event
 from openhands.events.observation.agent import AgentCondensationObservation
@@ -66,8 +65,6 @@ class View(BaseModel):
                     break
 
         if summary is not None and summary_offset is not None:
-            logger.info(f'Inserting summary at offset {summary_offset}')
-
             kept_events.insert(
                 summary_offset, AgentCondensationObservation(content=summary)
             )

openhands/resolver/README.md

@@ -1,141 +1,191 @@
-# OpenHands GitHub & GitLab Issue Resolver 🙌
+# OpenHands Github & Gitlab Issue Resolver 🙌
 
-Need help resolving GitHub or GitLab issues? Let an AI agent help you out!
+Need help resolving a GitHub issue but don't have the time to do it yourself? Let an AI agent help you out!
 
-This tool uses [OpenHands](https://github.com/all-hands-ai/openhands) AI agents to automatically resolve issues in your repositories. It's designed to handle one issue at a time with high quality.
+This tool allows you to use open-source AI agents based on [OpenHands](https://github.com/all-hands-ai/openhands)
+to attempt to resolve GitHub issues automatically. While it can handle multiple issues, it's primarily designed
+to help you resolve one issue at a time with high quality.
 
-## 1. Setting Up for GitHub (Action Workflow)
+Getting started is simple - just follow the instructions below.
 
-### Prerequisites
+## Using the GitHub Actions Workflow
 
-- [Create a personal access token](https://github.com/settings/tokens?type=beta) with read/write scope for
+This repository includes a GitHub Actions workflow that can automatically attempt to fix individual issues labeled with 'fix-me'.
+Follow these steps to use this workflow in your own repository:
 
-  - "contents"
-  - "issues"
-  - "pull requests"
-  - "workflows"
+1. [Create a personal access token](https://github.com/settings/tokens?type=beta) with read/write scope for "contents", "issues", "pull requests", and "workflows"
 
-- Create an LLM API key (e,g [Claude API](https://www.anthropic.com/api))
+   Note: If you're working with an organizational repository, you may need to configure the organization's personal access token policy first. See [Setting a personal access token policy for your organization](https://docs.github.com/en/organizations/managing-programmatic-access-to-your-organization/setting-a-personal-access-token-policy-for-your-organization) for details.
 
-### Installation
+2. Create an API key for the [Claude API](https://www.anthropic.com/api) (recommended) or another supported LLM service
 
-1. Copy `examples/openhands-resolver.yml` to your repository's `.github/workflows/` directory
+3. Copy `examples/openhands-resolver.yml` to your repository's `.github/workflows/` directory
 
-2. Configure repository permissions:
+4. Configure repository permissions:
+    - Go to `Settings -> Actions -> General -> Workflow permissions`
+    - Select "Read and write permissions"
+    - Enable "Allow Github Actions to create and approve pull requests"
 
-   - Go to `Settings -> Actions -> General -> Workflow permissions`
-   - Select **Read and write permissions**
-   - Enable **Allow Github Actions to create and approve pull requests**
-
-   > If "Read and write permissions" is greyed out:
-   >
-   > - Check organization settings first
-   > - Otherwise, permissions might need to be set in [Enterprise policy settings](https://docs.github.com/en/enterprise-cloud@latest/admin/enforcing-policies/enforcing-policies-for-your-enterprise/enforcing-policies-for-github-actions-in-your-enterprise#enforcing-a-policy-for-workflow-permissions-in-your-enterprise)
-
-3. Set up [GitHub secrets](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions):
+    Note: If the "Read and write permissions" option is greyed out:
+    - First check if permissions need to be set at the organization level
+    - If still greyed out at the organization level, permissions need to be set in the [Enterprise policy settings](https://docs.github.com/en/enterprise-cloud@latest/admin/enforcing-policies/enforcing-policies-for-your-enterprise/enforcing-policies-for-github-actions-in-your-enterprise#enforcing-a-policy-for-workflow-permissions-in-your-enterprise)
 
+5. Set up [GitHub secrets](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions):
    - Required:
-     - `LLM_API_KEY`: Your LLM API key
+    - `LLM_API_KEY`: Your LLM API key
    - Optional:
      - `PAT_USERNAME`: GitHub username for the personal access token
      - `PAT_TOKEN`: The personal access token
      - `LLM_BASE_URL`: Base URL for LLM API (only if using a proxy)
-     - [See how to customize more configurations](https://docs.all-hands.dev/modules/usage/how-to/github-action#custom-configurations)
 
-## 2. Setting up GitLab (CI Runner)
+   Note: You can set these secrets at the organization level to use across multiple repositories.
 
-### Prerequisites
+6. Set up any [custom configurations required](https://docs.all-hands.dev/modules/usage/how-to/github-action#custom-configurations)
 
-Create a GitLab Personal Access Token with API, read/write access
+7. Usage:
+   There are two ways to trigger the OpenHands agent:
 
-### Installation
+   a. Using the 'fix-me' label:
+      - Add the 'fix-me' label to any issue you want the AI to resolve
+      - The agent will consider all comments in the issue thread when resolving
+      - The workflow will:
+        1. Attempt to resolve the issue using OpenHands
+        2. Create a draft PR if successful, or push a branch if unsuccessful
+        3. Comment on the issue with the results
+        4. Remove the 'fix-me' label once processed
 
-## 3. Triggering OpenHands Agent
+   b. Using `@openhands-agent` mention:
+      - Create a new comment containing `@openhands-agent` in any issue
+      - The agent will only consider the comment where it's mentioned
+      - The workflow will:
+        1. Attempt to resolve the issue based on the specific comment
+        2. Create a draft PR if successful, or push a branch if unsuccessful
+        3. Comment on the issue with the results
 
-You can trigger OpenHands in two shared ways (works for both GitHub and GitLab):
+Need help? Feel free to [open an issue](https://github.com/all-hands-ai/openhands/issues) or email us at [contact@all-hands.dev](mailto:contact@all-hands.dev).
 
-Using the 'fix-me' label:
+## Manual Installation
 
-- Add the 'fix-me' label to any issue you want the AI to resolve
-- The agent will consider all comments in the issue thread when resolving
+If you prefer to run the resolver programmatically instead of using GitHub Actions, follow these steps:
 
-Using `@openhands-agent` in an issue/pr comment:
-
-- Create a new comment containing `@openhands-agent`
-- The agent will only consider the comment + comment thread where it's mentioned
-
-## 4. Running Locally
-
-### Installation
+1. Install the package:
 
 ```bash
 pip install openhands-ai
 ```
 
-### Setup
+2. Create a GitHub or GitLab access token:
+   - Create a GitHub acces token
+      - Visit [GitHub's token settings](https://github.com/settings/personal-access-tokens/new)
+      - Create a fine-grained token with these scopes:
+      - "Content"
+      - "Pull requests"
+      - "Issues"
+      - "Workflows"
+      - If you don't have push access to the target repo, you can fork it first
 
-Create a GitHub or GitLab access token with appropriate permissions
+   - Create a GitLab acces token
+      - Visit [GitLab's token settings](https://gitlab.com/-/user_settings/personal_access_tokens)
+      - Create a fine-grained token with these scopes:
+      - 'api'
+      - 'read_api'
+      - 'read_user'
+      - 'read_repository'
+      - 'write_repository'
 
-Set up environment variables:
+3. Set up environment variables:
 
 ```bash
-# GitHub credentials
-export GITHUB_TOKEN="your-github-token"
-export GIT_USERNAME="your-github-username"
 
-# GitLab credentials (if using GitLab)
+# GitHub credentials
+
+export GITHUB_TOKEN="your-github-token"
+export GIT_USERNAME="your-github-username"  # Optional, defaults to token owner
+
+# GitLab credentials if you're using GitLab repo
+
 export GITLAB_TOKEN="your-gitlab-token"
-export GIT_USERNAME="your-gitlab-username"
+export GIT_USERNAME="your-gitlab-username"  # Optional, defaults to token owner
 
 # LLM configuration
-export LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"
+
+export LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"  # Recommended
 export LLM_API_KEY="your-llm-api-key"
-export LLM_BASE_URL="your-api-url"  # Optional
+export LLM_BASE_URL="your-api-url"  # Optional, for API proxies
 ```
 
-### Resolving Issues
+Note: OpenHands works best with powerful models like Anthropic's Claude or OpenAI's GPT-4. While other models are supported, they may not perform as well for complex issue resolution.
 
-Resolve a single issue:
+## Resolving Issues
+
+The resolver can automatically attempt to fix a single issue in your repository using the following command:
 
 ```bash
 python -m openhands.resolver.resolve_issue --selected-repo [OWNER]/[REPO] --issue-number [NUMBER]
 ```
 
-### Responding to PR Comments
+For instance, if you want to resolve issue #100 in this repo, you would run:
 
-Respond to comments on pull requests:
+```bash
+python -m openhands.resolver.resolve_issue --selected-repo all-hands-ai/openhands --issue-number 100
+```
+
+The output will be written to the `output/` directory.
+
+If you've installed the package from source using poetry, you can use:
+
+```bash
+poetry run python openhands/resolver/resolve_issue.py --selected-repo all-hands-ai/openhands --issue-number 100
+```
+
+## Responding to PR Comments
+
+The resolver can also respond to comments on pull requests using:
 
 ```bash
 python -m openhands.resolver.send_pull_request --issue-number PR_NUMBER --issue-type pr
 ```
 
-### Visualizing Results
+This functionality is available both through the GitHub Actions workflow and when running the resolver locally.
 
-View successful PRs:
+## Visualizing successful PRs
+
+To find successful PRs, you can run the following command:
 
 ```bash
 grep '"success":true' output/output.jsonl | sed 's/.*\("number":[0-9]*\).*/\1/g'
 ```
 
-Visualize specific PR:
+Then you can go through and visualize the ones you'd like.
 
 ```bash
 python -m openhands.resolver.visualize_resolver_output --issue-number ISSUE_NUMBER --vis-method json
 ```
 
-### Uploading PRs
+## Uploading PRs
 
-Upload your changes in one of three ways:
+If you find any PRs that were successful, you can upload them.
+There are three ways you can upload:
+
+1. `branch` - upload a branch without creating a PR
+2. `draft` - create a draft PR
+3. `ready` - create a non-draft PR that's ready for review
 
 ```bash
-python -m openhands.resolver.send_pull_request --issue-number ISSUE_NUMBER --username YOUR_GITHUB_OR_GITLAB_USERNAME --pr-type [branch|draft|ready]
+python -m openhands.resolver.send_pull_request --issue-number ISSUE_NUMBER --username YOUR_GITHUB_OR_GITLAB_USERNAME --pr-type draft
 ```
 
-## Custom Instructions
+If you want to upload to a fork, you can do so by specifying the `fork-owner`:
 
-Add repository-specific instructions by creating a file at `.openhands/microagents/repo.md` in your repository. For more information about repository microagents, see [Repository Instructions](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents#2-repository-instructions-private).
+```bash
+python -m openhands.resolver.send_pull_request --issue-number ISSUE_NUMBER --username YOUR_GITHUB_OR_GITLAB_USERNAME --pr-type draft --fork-owner YOUR_GITHUB_OR_GITLAB_USERNAME
+```
+
+## Providing Custom Instructions
+
+You can customize how the AI agent approaches issue resolution by adding a repository microagent file at `.openhands/microagents/repo.md` in your repository. This file's contents will be automatically loaded in the prompt when working with your repository. For more information about repository microagents, see [Repository Instructions](https://github.com/All-Hands-AI/OpenHands/tree/main/microagents#2-repository-instructions-private).
 
 ## Troubleshooting
 
-If you have any issues, please open an issue on this github repo, we're happy to help!
+If you have any issues, please open an issue on this github or gitlab repo, we're happy to help!
 Alternatively, you can [email us](mailto:contact@all-hands.dev) or join the OpenHands Slack workspace (see [the README](/README.md) for an invite link).

poetry.lock

@@ -496,18 +496,18 @@ files = [
 
 [[package]]
 name = "boto3"
-version = "1.38.3"
+version = "1.38.2"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "boto3-1.38.3-py3-none-any.whl", hash = "sha256:9218f86e2164e1bddb75d435bbde4fa651aa58687213d7e3e1b50f7eb8868f66"},
-    {file = "boto3-1.38.3.tar.gz", hash = "sha256:655d51abcd68a40a33c52dbaa2ca73fc63c746b894e2ae22ed8ddc1912ddd93f"},
+    {file = "boto3-1.38.2-py3-none-any.whl", hash = "sha256:ef3237b169cd906a44a32c03b3229833d923c9e9733355b329ded2151f91ec0b"},
+    {file = "boto3-1.38.2.tar.gz", hash = "sha256:53c8d44b231251fa9421dd13d968236d59fe2cf0421e077afedbf3821653fb3b"},
 ]
 
 [package.dependencies]
-botocore = ">=1.38.3,<1.39.0"
+botocore = ">=1.38.2,<1.39.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.12.0,<0.13.0"
 
@@ -516,14 +516,14 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
 
 [[package]]
 name = "boto3-stubs"
-version = "1.38.3"
-description = "Type annotations for boto3 1.38.3 generated with mypy-boto3-builder 8.10.1"
+version = "1.38.2"
+description = "Type annotations for boto3 1.38.2 generated with mypy-boto3-builder 8.10.1"
 optional = false
 python-versions = ">=3.8"
 groups = ["evaluation"]
 files = [
-    {file = "boto3_stubs-1.38.3-py3-none-any.whl", hash = "sha256:93a2c38987dd0ee19a661e8fd9a77fb4b4a30e56f63115701c307bfc55e2695c"},
-    {file = "boto3_stubs-1.38.3.tar.gz", hash = "sha256:e406626de8daf537984678355ad0e32d838865c4ea3d223268964d4e6fb44534"},
+    {file = "boto3_stubs-1.38.2-py3-none-any.whl", hash = "sha256:e18f2dc194c4b8a29f61275ba039689d063c4775a78560e35a5ce820ec257fb5"},
+    {file = "boto3_stubs-1.38.2.tar.gz", hash = "sha256:405cd777d41530cf8ed009d20b04daef1f7d4bd2fd9fd3636ac86eccdb55159c"},
 ]
 
 [package.dependencies]
@@ -579,7 +579,7 @@ bedrock-data-automation-runtime = ["mypy-boto3-bedrock-data-automation-runtime (
 bedrock-runtime = ["mypy-boto3-bedrock-runtime (>=1.38.0,<1.39.0)"]
 billing = ["mypy-boto3-billing (>=1.38.0,<1.39.0)"]
 billingconductor = ["mypy-boto3-billingconductor (>=1.38.0,<1.39.0)"]
-boto3 = ["boto3 (==1.38.3)"]
+boto3 = ["boto3 (==1.38.2)"]
 braket = ["mypy-boto3-braket (>=1.38.0,<1.39.0)"]
 budgets = ["mypy-boto3-budgets (>=1.38.0,<1.39.0)"]
 ce = ["mypy-boto3-ce (>=1.38.0,<1.39.0)"]
@@ -943,14 +943,14 @@ xray = ["mypy-boto3-xray (>=1.38.0,<1.39.0)"]
 
 [[package]]
 name = "botocore"
-version = "1.38.3"
+version = "1.38.2"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "botocore-1.38.3-py3-none-any.whl", hash = "sha256:96f823240fe3704b99c17d1d1b2fd2d1679cf56d2a55b095f00255b76087cbf0"},
-    {file = "botocore-1.38.3.tar.gz", hash = "sha256:790f8f966201781f5fcf486d48b4492e9f734446bbf9d19ef8159d08be854243"},
+    {file = "botocore-1.38.2-py3-none-any.whl", hash = "sha256:5d9cffedb1c759a058b43793d16647ed44ec87072f98a1bd6cd673ac0ae6b81d"},
+    {file = "botocore-1.38.2.tar.gz", hash = "sha256:b688a9bd17211a1eaae3a6c965ba9f3973e5435efaaa4fa201f499d3467830e1"},
 ]
 
 [package.dependencies]
@@ -2663,7 +2663,7 @@ grpcio = {version = ">=1.49.1,<2.0dev", optional = true, markers = "python_versi
 grpcio-status = {version = ">=1.49.1,<2.0.dev0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""}
 proto-plus = [
     {version = ">=1.25.0,<2.0.0dev", markers = "python_version >= \"3.13\""},
-    {version = ">=1.22.3,<2.0.0dev", markers = "python_version < \"3.13\""},
+    {version = ">=1.22.3,<2.0.0dev"},
 ]
 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,<6.0.0.dev0"
 requests = ">=2.18.0,<3.0.0.dev0"
@@ -2878,7 +2878,7 @@ google-auth = ">=2.14.1,<2.24.0 || >2.24.0,<2.25.0 || >2.25.0,<3.0.0dev"
 grpc-google-iam-v1 = ">=0.14.0,<1.0.0dev"
 proto-plus = [
     {version = ">=1.25.0,<2.0.0dev", markers = "python_version >= \"3.13\""},
-    {version = ">=1.22.3,<2.0.0dev"},
+    {version = ">=1.22.3,<2.0.0dev", markers = "python_version < \"3.13\""},
 ]
 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"
 
@@ -3794,14 +3794,14 @@ files = [
 
 [[package]]
 name = "json-repair"
-version = "0.43.0"
+version = "0.42.0"
 description = "A package to repair broken json strings"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "json_repair-0.43.0-py3-none-any.whl", hash = "sha256:3f2b66819c9f5e29edd5dd4851223b72d10ed816b6423b3c92e424090c3ffc1d"},
-    {file = "json_repair-0.43.0.tar.gz", hash = "sha256:77cc6eda6f407ff5fe9544f962e42b332cca1e8c9f3f9f9dc660327028e0d651"},
+    {file = "json_repair-0.42.0-py3-none-any.whl", hash = "sha256:7b6805162053dfe65722e961bc51b5eecec0582ec8a8e0fd218d33e8de757daf"},
+    {file = "json_repair-0.42.0.tar.gz", hash = "sha256:1a901f706c5b6b4325f0f79b53b0d998c5b327070e98b530da71cc5a3eda8616"},
 ]
 
 [[package]]
@@ -4882,14 +4882,14 @@ files = [
 
 [[package]]
 name = "modal"
-version = "0.74.30"
+version = "0.74.23"
 description = "Python client library for Modal"
 optional = false
 python-versions = ">=3.9"
 groups = ["main", "evaluation"]
 files = [
-    {file = "modal-0.74.30-py3-none-any.whl", hash = "sha256:46006cb57309171fe36ee41528a7cc8c0e67c88afd9bf04a9900313c18925aa4"},
-    {file = "modal-0.74.30.tar.gz", hash = "sha256:14bd2ea0ebc9ab1ebce29ea76ddf12047f23599983725c5f82990ae97bea05c7"},
+    {file = "modal-0.74.23-py3-none-any.whl", hash = "sha256:96c397487ed5f499ad040b5edf5f378ada8e0676da17523a2d6fadb3f1d384e1"},
+    {file = "modal-0.74.23.tar.gz", hash = "sha256:3a042cdf482975b43341da0b33fa6a6adae06978ead69a086ca658a7dcb0cd6d"},
 ]
 
 [package.dependencies]
@@ -6343,67 +6343,54 @@ files = [
 
 [[package]]
 name = "pyarrow"
-version = "20.0.0"
+version = "19.0.1"
 description = "Python library for Apache Arrow"
 optional = false
 python-versions = ">=3.9"
 groups = ["evaluation"]
 files = [
-    {file = "pyarrow-20.0.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:c7dd06fd7d7b410ca5dc839cc9d485d2bc4ae5240851bcd45d85105cc90a47d7"},
-    {file = "pyarrow-20.0.0-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:d5382de8dc34c943249b01c19110783d0d64b207167c728461add1ecc2db88e4"},
-    {file = "pyarrow-20.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6415a0d0174487456ddc9beaead703d0ded5966129fa4fd3114d76b5d1c5ceae"},
-    {file = "pyarrow-20.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:15aa1b3b2587e74328a730457068dc6c89e6dcbf438d4369f572af9d320a25ee"},
-    {file = "pyarrow-20.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:5605919fbe67a7948c1f03b9f3727d82846c053cd2ce9303ace791855923fd20"},
-    {file = "pyarrow-20.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:a5704f29a74b81673d266e5ec1fe376f060627c2e42c5c7651288ed4b0db29e9"},
-    {file = "pyarrow-20.0.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:00138f79ee1b5aca81e2bdedb91e3739b987245e11fa3c826f9e57c5d102fb75"},
-    {file = "pyarrow-20.0.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:f2d67ac28f57a362f1a2c1e6fa98bfe2f03230f7e15927aecd067433b1e70ce8"},
-    {file = "pyarrow-20.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:4a8b029a07956b8d7bd742ffca25374dd3f634b35e46cc7a7c3fa4c75b297191"},
-    {file = "pyarrow-20.0.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:24ca380585444cb2a31324c546a9a56abbe87e26069189e14bdba19c86c049f0"},
-    {file = "pyarrow-20.0.0-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:95b330059ddfdc591a3225f2d272123be26c8fa76e8c9ee1a77aad507361cfdb"},
-    {file = "pyarrow-20.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5f0fb1041267e9968c6d0d2ce3ff92e3928b243e2b6d11eeb84d9ac547308232"},
-    {file = "pyarrow-20.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b8ff87cc837601532cc8242d2f7e09b4e02404de1b797aee747dd4ba4bd6313f"},
-    {file = "pyarrow-20.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:7a3a5dcf54286e6141d5114522cf31dd67a9e7c9133d150799f30ee302a7a1ab"},
-    {file = "pyarrow-20.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a6ad3e7758ecf559900261a4df985662df54fb7fdb55e8e3b3aa99b23d526b62"},
-    {file = "pyarrow-20.0.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6bb830757103a6cb300a04610e08d9636f0cd223d32f388418ea893a3e655f1c"},
-    {file = "pyarrow-20.0.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:96e37f0766ecb4514a899d9a3554fadda770fb57ddf42b63d80f14bc20aa7db3"},
-    {file = "pyarrow-20.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:3346babb516f4b6fd790da99b98bed9708e3f02e734c84971faccb20736848dc"},
-    {file = "pyarrow-20.0.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:75a51a5b0eef32727a247707d4755322cb970be7e935172b6a3a9f9ae98404ba"},
-    {file = "pyarrow-20.0.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:211d5e84cecc640c7a3ab900f930aaff5cd2702177e0d562d426fb7c4f737781"},
-    {file = "pyarrow-20.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ba3cf4182828be7a896cbd232aa8dd6a31bd1f9e32776cc3796c012855e1199"},
-    {file = "pyarrow-20.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c3a01f313ffe27ac4126f4c2e5ea0f36a5fc6ab51f8726cf41fee4b256680bd"},
-    {file = "pyarrow-20.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:a2791f69ad72addd33510fec7bb14ee06c2a448e06b649e264c094c5b5f7ce28"},
-    {file = "pyarrow-20.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:4250e28a22302ce8692d3a0e8ec9d9dde54ec00d237cff4dfa9c1fbf79e472a8"},
-    {file = "pyarrow-20.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:89e030dc58fc760e4010148e6ff164d2f44441490280ef1e97a542375e41058e"},
-    {file = "pyarrow-20.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:6102b4864d77102dbbb72965618e204e550135a940c2534711d5ffa787df2a5a"},
-    {file = "pyarrow-20.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:96d6a0a37d9c98be08f5ed6a10831d88d52cac7b13f5287f1e0f625a0de8062b"},
-    {file = "pyarrow-20.0.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:a15532e77b94c61efadde86d10957950392999503b3616b2ffcef7621a002893"},
-    {file = "pyarrow-20.0.0-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:dd43f58037443af715f34f1322c782ec463a3c8a94a85fdb2d987ceb5658e061"},
-    {file = "pyarrow-20.0.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:aa0d288143a8585806e3cc7c39566407aab646fb9ece164609dac1cfff45f6ae"},
-    {file = "pyarrow-20.0.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b6953f0114f8d6f3d905d98e987d0924dabce59c3cda380bdfaa25a6201563b4"},
-    {file = "pyarrow-20.0.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:991f85b48a8a5e839b2128590ce07611fae48a904cae6cab1f089c5955b57eb5"},
-    {file = "pyarrow-20.0.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:97c8dc984ed09cb07d618d57d8d4b67a5100a30c3818c2fb0b04599f0da2de7b"},
-    {file = "pyarrow-20.0.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:9b71daf534f4745818f96c214dbc1e6124d7daf059167330b610fc69b6f3d3e3"},
-    {file = "pyarrow-20.0.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:e8b88758f9303fa5a83d6c90e176714b2fd3852e776fc2d7e42a22dd6c2fb368"},
-    {file = "pyarrow-20.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:30b3051b7975801c1e1d387e17c588d8ab05ced9b1e14eec57915f79869b5031"},
-    {file = "pyarrow-20.0.0-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:ca151afa4f9b7bc45bcc791eb9a89e90a9eb2772767d0b1e5389609c7d03db63"},
-    {file = "pyarrow-20.0.0-cp313-cp313t-macosx_12_0_x86_64.whl", hash = "sha256:4680f01ecd86e0dd63e39eb5cd59ef9ff24a9d166db328679e36c108dc993d4c"},
-    {file = "pyarrow-20.0.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f4c8534e2ff059765647aa69b75d6543f9fef59e2cd4c6d18015192565d2b70"},
-    {file = "pyarrow-20.0.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3e1f8a47f4b4ae4c69c4d702cfbdfe4d41e18e5c7ef6f1bb1c50918c1e81c57b"},
-    {file = "pyarrow-20.0.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:a1f60dc14658efaa927f8214734f6a01a806d7690be4b3232ba526836d216122"},
-    {file = "pyarrow-20.0.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:204a846dca751428991346976b914d6d2a82ae5b8316a6ed99789ebf976551e6"},
-    {file = "pyarrow-20.0.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:f3b117b922af5e4c6b9a9115825726cac7d8b1421c37c2b5e24fbacc8930612c"},
-    {file = "pyarrow-20.0.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:e724a3fd23ae5b9c010e7be857f4405ed5e679db5c93e66204db1a69f733936a"},
-    {file = "pyarrow-20.0.0-cp313-cp313t-win_amd64.whl", hash = "sha256:82f1ee5133bd8f49d31be1299dc07f585136679666b502540db854968576faf9"},
-    {file = "pyarrow-20.0.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:1bcbe471ef3349be7714261dea28fe280db574f9d0f77eeccc195a2d161fd861"},
-    {file = "pyarrow-20.0.0-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:a18a14baef7d7ae49247e75641fd8bcbb39f44ed49a9fc4ec2f65d5031aa3b96"},
-    {file = "pyarrow-20.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb497649e505dc36542d0e68eca1a3c94ecbe9799cb67b578b55f2441a247fbc"},
-    {file = "pyarrow-20.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11529a2283cb1f6271d7c23e4a8f9f8b7fd173f7360776b668e509d712a02eec"},
-    {file = "pyarrow-20.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:6fc1499ed3b4b57ee4e090e1cea6eb3584793fe3d1b4297bbf53f09b434991a5"},
-    {file = "pyarrow-20.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:db53390eaf8a4dab4dbd6d93c85c5cf002db24902dbff0ca7d988beb5c9dd15b"},
-    {file = "pyarrow-20.0.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:851c6a8260ad387caf82d2bbf54759130534723e37083111d4ed481cb253cc0d"},
-    {file = "pyarrow-20.0.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:e22f80b97a271f0a7d9cd07394a7d348f80d3ac63ed7cc38b6d1b696ab3b2619"},
-    {file = "pyarrow-20.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:9965a050048ab02409fb7cbbefeedba04d3d67f2cc899eff505cc084345959ca"},
-    {file = "pyarrow-20.0.0.tar.gz", hash = "sha256:febc4a913592573c8d5805091a6c2b5064c8bd6e002131f01061797d91c783c1"},
+    {file = "pyarrow-19.0.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:fc28912a2dc924dddc2087679cc8b7263accc71b9ff025a1362b004711661a69"},
+    {file = "pyarrow-19.0.1-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:fca15aabbe9b8355800d923cc2e82c8ef514af321e18b437c3d782aa884eaeec"},
+    {file = "pyarrow-19.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ad76aef7f5f7e4a757fddcdcf010a8290958f09e3470ea458c80d26f4316ae89"},
+    {file = "pyarrow-19.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d03c9d6f2a3dffbd62671ca070f13fc527bb1867b4ec2b98c7eeed381d4f389a"},
+    {file = "pyarrow-19.0.1-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:65cf9feebab489b19cdfcfe4aa82f62147218558d8d3f0fc1e9dea0ab8e7905a"},
+    {file = "pyarrow-19.0.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:41f9706fbe505e0abc10e84bf3a906a1338905cbbcf1177b71486b03e6ea6608"},
+    {file = "pyarrow-19.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:c6cb2335a411b713fdf1e82a752162f72d4a7b5dbc588e32aa18383318b05866"},
+    {file = "pyarrow-19.0.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:cc55d71898ea30dc95900297d191377caba257612f384207fe9f8293b5850f90"},
+    {file = "pyarrow-19.0.1-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:7a544ec12de66769612b2d6988c36adc96fb9767ecc8ee0a4d270b10b1c51e00"},
+    {file = "pyarrow-19.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0148bb4fc158bfbc3d6dfe5001d93ebeed253793fff4435167f6ce1dc4bddeae"},
+    {file = "pyarrow-19.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f24faab6ed18f216a37870d8c5623f9c044566d75ec586ef884e13a02a9d62c5"},
+    {file = "pyarrow-19.0.1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:4982f8e2b7afd6dae8608d70ba5bd91699077323f812a0448d8b7abdff6cb5d3"},
+    {file = "pyarrow-19.0.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:49a3aecb62c1be1d822f8bf629226d4a96418228a42f5b40835c1f10d42e4db6"},
+    {file = "pyarrow-19.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:008a4009efdb4ea3d2e18f05cd31f9d43c388aad29c636112c2966605ba33466"},
+    {file = "pyarrow-19.0.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:80b2ad2b193e7d19e81008a96e313fbd53157945c7be9ac65f44f8937a55427b"},
+    {file = "pyarrow-19.0.1-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:ee8dec072569f43835932a3b10c55973593abc00936c202707a4ad06af7cb294"},
+    {file = "pyarrow-19.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4d5d1ec7ec5324b98887bdc006f4d2ce534e10e60f7ad995e7875ffa0ff9cb14"},
+    {file = "pyarrow-19.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3ad4c0eb4e2a9aeb990af6c09e6fa0b195c8c0e7b272ecc8d4d2b6574809d34"},
+    {file = "pyarrow-19.0.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:d383591f3dcbe545f6cc62daaef9c7cdfe0dff0fb9e1c8121101cabe9098cfa6"},
+    {file = "pyarrow-19.0.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:b4c4156a625f1e35d6c0b2132635a237708944eb41df5fbe7d50f20d20c17832"},
+    {file = "pyarrow-19.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:5bd1618ae5e5476b7654c7b55a6364ae87686d4724538c24185bbb2952679960"},
+    {file = "pyarrow-19.0.1-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:e45274b20e524ae5c39d7fc1ca2aa923aab494776d2d4b316b49ec7572ca324c"},
+    {file = "pyarrow-19.0.1-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:d9dedeaf19097a143ed6da37f04f4051aba353c95ef507764d344229b2b740ae"},
+    {file = "pyarrow-19.0.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ebfb5171bb5f4a52319344ebbbecc731af3f021e49318c74f33d520d31ae0c4"},
+    {file = "pyarrow-19.0.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f2a21d39fbdb948857f67eacb5bbaaf36802de044ec36fbef7a1c8f0dd3a4ab2"},
+    {file = "pyarrow-19.0.1-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:99bc1bec6d234359743b01e70d4310d0ab240c3d6b0da7e2a93663b0158616f6"},
+    {file = "pyarrow-19.0.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:1b93ef2c93e77c442c979b0d596af45e4665d8b96da598db145b0fec014b9136"},
+    {file = "pyarrow-19.0.1-cp313-cp313-win_amd64.whl", hash = "sha256:d9d46e06846a41ba906ab25302cf0fd522f81aa2a85a71021826f34639ad31ef"},
+    {file = "pyarrow-19.0.1-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:c0fe3dbbf054a00d1f162fda94ce236a899ca01123a798c561ba307ca38af5f0"},
+    {file = "pyarrow-19.0.1-cp313-cp313t-macosx_12_0_x86_64.whl", hash = "sha256:96606c3ba57944d128e8a8399da4812f56c7f61de8c647e3470b417f795d0ef9"},
+    {file = "pyarrow-19.0.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f04d49a6b64cf24719c080b3c2029a3a5b16417fd5fd7c4041f94233af732f3"},
+    {file = "pyarrow-19.0.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5a9137cf7e1640dce4c190551ee69d478f7121b5c6f323553b319cac936395f6"},
+    {file = "pyarrow-19.0.1-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:7c1bca1897c28013db5e4c83944a2ab53231f541b9e0c3f4791206d0c0de389a"},
+    {file = "pyarrow-19.0.1-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:58d9397b2e273ef76264b45531e9d552d8ec8a6688b7390b5be44c02a37aade8"},
+    {file = "pyarrow-19.0.1-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:b9766a47a9cb56fefe95cb27f535038b5a195707a08bf61b180e642324963b46"},
+    {file = "pyarrow-19.0.1-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:6c5941c1aac89a6c2f2b16cd64fe76bcdb94b2b1e99ca6459de4e6f07638d755"},
+    {file = "pyarrow-19.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd44d66093a239358d07c42a91eebf5015aa54fccba959db899f932218ac9cc8"},
+    {file = "pyarrow-19.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:335d170e050bcc7da867a1ed8ffb8b44c57aaa6e0843b156a501298657b1e972"},
+    {file = "pyarrow-19.0.1-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:1c7556165bd38cf0cd992df2636f8bcdd2d4b26916c6b7e646101aff3c16f76f"},
+    {file = "pyarrow-19.0.1-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:699799f9c80bebcf1da0983ba86d7f289c5a2a5c04b945e2f2bcf7e874a91911"},
+    {file = "pyarrow-19.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:8464c9fbe6d94a7fe1599e7e8965f350fd233532868232ab2596a71586c5a429"},
+    {file = "pyarrow-19.0.1.tar.gz", hash = "sha256:3bf266b485df66a400f282ac0b6d1b500b9d2ae73314a153dbe97d6d5cc8a99e"},
 ]
 
 [package.extras]
@@ -7990,14 +7977,14 @@ files = [
 
 [[package]]
 name = "runloop-api-client"
-version = "0.32.0"
+version = "0.31.0"
 description = "The official Python library for the runloop API"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "runloop_api_client-0.32.0-py3-none-any.whl", hash = "sha256:37f156f711b1aa4cef86c0f779cc27afa43ce3d3f6b1976d7f68667466317a6d"},
-    {file = "runloop_api_client-0.32.0.tar.gz", hash = "sha256:735a967d96b5c3e8a08b89072722adcbe2b10ed904268d3f45785b7cfd5420d1"},
+    {file = "runloop_api_client-0.31.0-py3-none-any.whl", hash = "sha256:1eb716a20b268e081bdbcf5b5d1df9ab6eb258a0b929130210a3b643048159c7"},
+    {file = "runloop_api_client-0.31.0.tar.gz", hash = "sha256:78992595fd34f98470aa73b8f5b92983414e4878218239e531a9371c5570a13d"},
 ]
 
 [package.dependencies]
@@ -10269,4 +10256,4 @@ testing = ["coverage[toml]", "zope.event", "zope.testing"]
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.12"
-content-hash = "d3f933e9abf6be481ec137e14f8f7ac502afd591a9ba74b315737fd894ca5cfe"
+content-hash = "ce44ae3718979f1878cbdd4e2f9595a6d73c2ffb0b9256e3ec163397a3916b25"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openhands-ai"
-version = "0.34.0"
+version = "0.35.1"
 description = "OpenHands: Code Less, Make More"
 authors = ["OpenHands"]
 license = "MIT"
@@ -58,7 +58,7 @@ protobuf = "^4.21.6,<5.0.0" # chromadb currently fails on 5.0+
 opentelemetry-api = "1.25.0"
 opentelemetry-exporter-otlp-proto-grpc = "1.25.0"
 modal = ">=0.66.26,<0.75.0"
-runloop-api-client = "0.32.0"
+runloop-api-client = "0.31.0"
 libtmux = ">=0.37,<0.40"
 pygithub = "^2.5.0"
 joblib = "*"
@@ -146,7 +146,7 @@ browsergym-webarena = "0.13.3"
 browsergym-miniwob = "0.13.3"
 browsergym-visualwebarena = "0.13.3"
 boto3-stubs = {extras = ["s3"], version = "^1.37.19"}
-pyarrow = "20.0.0" # transitive dependency, pinned here to avoid conflicts
+pyarrow = "19.0.1" # transitive dependency, pinned here to avoid conflicts
 datasets = "*"
 
 [tool.poetry-dynamic-versioning]

tests/unit/test_agent_controller.py

@@ -22,6 +22,7 @@ from openhands.events.observation import (
     ErrorObservation,
 )
 from openhands.events.observation.agent import RecallObservation
+from openhands.events.observation.commands import CmdOutputObservation
 from openhands.events.observation.empty import NullObservation
 from openhands.events.serialization import event_to_dict
 from openhands.llm import LLM
@@ -764,7 +765,7 @@ async def test_context_window_exceeded_error_handling(
 
     # We do that by playing the role of the recall module -- subscribe to the
     # event stream and respond to recall actions by inserting fake recall
-    # observations.
+    # obesrvations.
     def on_event_memory(event: Event):
         if isinstance(event, RecallAction):
             microagent_obs = RecallObservation(
@@ -806,19 +807,13 @@ async def test_context_window_exceeded_error_handling(
     # size (because we return a message action, which triggers a recall, which
     # triggers a recall response). But if the pre/post-views are on the turn
     # when we throw the context window exceeded error, we should see the
-    # post-step view compressed (or rather, a CondensationAction added).
+    # post-step view compressed.
     for index, (first_view, second_view) in enumerate(
         zip(step_state.views[:-1], step_state.views[1:])
     ):
         if index == error_after:
-            # Verify that the CondensationAction is present in the second view (after error)
-            # but not in the first view (before error)
-            assert not any(isinstance(e, CondensationAction) for e in first_view.events)
-            assert any(isinstance(e, CondensationAction) for e in second_view.events)
-            # The length might not strictly decrease due to CondensationAction being added
-            assert len(first_view) == len(second_view)
+            assert len(first_view) > len(second_view)
         else:
-            # Before the error, the view length should increase
             assert len(first_view) < len(second_view)
 
     # The final state's history should contain:
@@ -891,7 +886,7 @@ async def test_run_controller_with_context_window_exceeded_with_truncation(
         def step(self, state: State):
             # If the state has more than one message and we haven't errored yet,
             # throw the context window exceeded error
-            if len(state.history) > 5 and not self.has_errored:
+            if len(state.history) > 3 and not self.has_errored:
                 error = ContextWindowExceededError(
                     message='prompt is too long: 233885 tokens > 200000 maximum',
                     model='',
@@ -1472,6 +1467,126 @@ def test_agent_controller_should_step_with_null_observation_cause_zero(mock_agen
     ), 'should_step should return False for NullObservation with cause = 0'
 
 
+def test_apply_conversation_window_basic(mock_event_stream, mock_agent):
+    """Test that the _apply_conversation_window method correctly prunes a list of events."""
+    controller = AgentController(
+        agent=mock_agent,
+        event_stream=mock_event_stream,
+        max_iterations=10,
+        sid='test_apply_conversation_window_basic',
+        confirmation_mode=False,
+        headless_mode=True,
+    )
+
+    # Create a sequence of events with IDs
+    first_msg = MessageAction(content='Hello, start task', wait_for_response=False)
+    first_msg._source = EventSource.USER
+    first_msg._id = 1
+
+    # Add agent question
+    agent_msg = MessageAction(
+        content='What task would you like me to perform?', wait_for_response=True
+    )
+    agent_msg._source = EventSource.AGENT
+    agent_msg._id = 2
+
+    # Add user response
+    user_response = MessageAction(
+        content='Please list all files and show me current directory',
+        wait_for_response=False,
+    )
+    user_response._source = EventSource.USER
+    user_response._id = 3
+
+    cmd1 = CmdRunAction(command='ls')
+    cmd1._id = 4
+    obs1 = CmdOutputObservation(command='ls', content='file1.txt', command_id=4)
+    obs1._id = 5
+    obs1._cause = 4
+
+    cmd2 = CmdRunAction(command='pwd')
+    cmd2._id = 6
+    obs2 = CmdOutputObservation(command='pwd', content='/home', command_id=6)
+    obs2._id = 7
+    obs2._cause = 6
+
+    events = [first_msg, agent_msg, user_response, cmd1, obs1, cmd2, obs2]
+
+    # Apply truncation
+    truncated = controller._apply_conversation_window(events)
+
+    # Verify truncation occured
+    # Should keep first user message and roughly half of other events
+    assert (
+        3 <= len(truncated) < len(events)
+    )  # First message + at least one action-observation pair
+    assert truncated[0] == first_msg  # First message always preserved
+    assert controller.state.start_id == first_msg._id
+
+    # Verify pairs aren't split
+    for i, event in enumerate(truncated[1:]):
+        if isinstance(event, CmdOutputObservation):
+            assert any(e._id == event._cause for e in truncated[: i + 1])
+
+
+def test_history_restoration_after_truncation(mock_event_stream, mock_agent):
+    controller = AgentController(
+        agent=mock_agent,
+        event_stream=mock_event_stream,
+        max_iterations=10,
+        sid='test_truncation',
+        confirmation_mode=False,
+        headless_mode=True,
+    )
+
+    # Create events with IDs
+    first_msg = MessageAction(content='Start task', wait_for_response=False)
+    first_msg._source = EventSource.USER
+    first_msg._id = 1
+
+    events = [first_msg]
+    for i in range(5):
+        cmd = CmdRunAction(command=f'cmd{i}')
+        cmd._id = i + 2
+        obs = CmdOutputObservation(
+            command=f'cmd{i}', content=f'output{i}', command_id=cmd._id
+        )
+        obs._cause = cmd._id
+        events.extend([cmd, obs])
+
+    # Set up initial history
+    controller.state.history = events.copy()
+
+    # Force truncation
+    controller.state.history = controller._apply_conversation_window(
+        controller.state.history
+    )
+
+    # Save state
+    saved_start_id = controller.state.start_id
+    saved_history_len = len(controller.state.history)
+
+    # Set up mock event stream for new controller
+    mock_event_stream.get_events.return_value = controller.state.history
+
+    # Create new controller with saved state
+    new_controller = AgentController(
+        agent=mock_agent,
+        event_stream=mock_event_stream,
+        max_iterations=10,
+        sid='test_truncation',
+        confirmation_mode=False,
+        headless_mode=True,
+    )
+    new_controller.state.start_id = saved_start_id
+    new_controller.state.history = mock_event_stream.get_events()
+
+    # Verify restoration
+    assert len(new_controller.state.history) == saved_history_len
+    assert new_controller.state.history[0] == first_msg
+    assert new_controller.state.start_id == saved_start_id
+
+
 def test_system_message_in_event_stream(mock_agent, test_event_stream):
     """Test that SystemMessageAction is added to event stream in AgentController."""
     _ = AgentController(

tests/unit/test_agent_history.py

@@ -1,569 +0,0 @@
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from openhands.controller.agent import Agent
-from openhands.controller.agent_controller import AgentController
-from openhands.controller.state.state import State
-from openhands.core.config import AppConfig
-from openhands.events import EventSource
-from openhands.events.action import CmdRunAction, MessageAction, RecallAction
-from openhands.events.action.message import SystemMessageAction
-from openhands.events.event import RecallType
-from openhands.events.observation import (
-    CmdOutputObservation,
-    Observation,
-    RecallObservation,
-)
-from openhands.events.stream import EventStream
-from openhands.llm.llm import LLM
-from openhands.llm.metrics import Metrics
-from openhands.storage.memory import InMemoryFileStore
-
-
-# Helper function to create events with sequential IDs and causes
-def create_events(event_data):
-    events = []
-    # Import necessary types here to avoid repeated imports inside the loop
-    from openhands.events.action import CmdRunAction, RecallAction
-    from openhands.events.observation import CmdOutputObservation, RecallObservation
-
-    for i, data in enumerate(event_data):
-        event_type = data['type']
-        source = data.get('source', EventSource.AGENT)
-        kwargs = {}  # Arguments for the event constructor
-
-        # Determine arguments based on event type
-        if event_type == RecallAction:
-            kwargs['query'] = data.get('query', '')
-            kwargs['recall_type'] = data.get('recall_type', RecallType.KNOWLEDGE)
-        elif event_type == RecallObservation:
-            kwargs['content'] = data.get('content', '')
-            kwargs['recall_type'] = data.get('recall_type', RecallType.KNOWLEDGE)
-        elif event_type == CmdRunAction:
-            kwargs['command'] = data.get('command', '')
-        elif event_type == CmdOutputObservation:
-            # Required args for CmdOutputObservation
-            kwargs['content'] = data.get('content', '')
-            kwargs['command'] = data.get('command', '')
-            # Pass command_id via kwargs if present in data
-            if 'command_id' in data:
-                kwargs['command_id'] = data['command_id']
-            # Pass metadata if present
-            if 'metadata' in data:
-                kwargs['metadata'] = data['metadata']
-        else:  # Default for MessageAction, SystemMessageAction, etc.
-            kwargs['content'] = data.get('content', '')
-
-        # Instantiate the event
-        event = event_type(**kwargs)
-
-        # Assign internal attributes AFTER instantiation
-        event._id = i + 1  # Assign sequential IDs starting from 1
-        event._source = source
-        # Assign _cause using cause_id from data, AFTER event._id is set
-        if 'cause_id' in data:
-            event._cause = data['cause_id']
-        # If command_id was NOT passed via kwargs but cause_id exists,
-        # pass cause_id as command_id to __init__ via kwargs for legacy handling
-        # This needs to happen *before* instantiation if we want __init__ to handle it
-        # Let's adjust the logic slightly:
-        if event_type == CmdOutputObservation:
-            if 'command_id' not in kwargs and 'cause_id' in data:
-                kwargs['command_id'] = data['cause_id']  # Let __init__ handle this
-            # Re-instantiate if we added command_id
-            if 'command_id' in kwargs and event.command_id != kwargs['command_id']:
-                event = event_type(**kwargs)
-                event._id = i + 1
-                event._source = source
-
-        # Now assign _cause if it exists in data, after potential re-instantiation
-        if 'cause_id' in data:
-            event._cause = data['cause_id']
-
-        events.append(event)
-    return events
-
-
-@pytest.fixture
-def controller_fixture():
-    mock_agent = MagicMock(spec=Agent)
-    mock_agent.llm = MagicMock(spec=LLM)
-    mock_agent.llm.metrics = Metrics()
-    mock_agent.llm.config = AppConfig().get_llm_config()
-    mock_agent.config = AppConfig().get_agent_config('CodeActAgent')
-
-    mock_event_stream = MagicMock(spec=EventStream)
-    mock_event_stream.sid = 'test_sid'
-    mock_event_stream.file_store = InMemoryFileStore({})
-    # Ensure get_latest_event_id returns an integer
-    mock_event_stream.get_latest_event_id.return_value = -1
-
-    controller = AgentController(
-        agent=mock_agent,
-        event_stream=mock_event_stream,
-        max_iterations=10,
-        sid='test_sid',
-    )
-    controller.state = State(session_id='test_sid')
-
-    # Mock _first_user_message directly on the instance
-    mock_first_user_message = MagicMock(spec=MessageAction)
-    controller._first_user_message = MagicMock(return_value=mock_first_user_message)
-
-    return controller, mock_first_user_message
-
-
-# =============================================
-# Test Cases for _apply_conversation_window
-# =============================================
-
-
-def test_basic_truncation(controller_fixture):
-    controller, mock_first_user_message = controller_fixture
-
-    controller.state.history = create_events(
-        [
-            {'type': SystemMessageAction, 'content': 'System Prompt'},  # 1
-            {
-                'type': MessageAction,
-                'content': 'User Task 1',
-                'source': EventSource.USER,
-            },  # 2
-            {'type': RecallAction, 'query': 'User Task 1'},  # 3
-            {'type': RecallObservation, 'content': 'Recall result', 'cause_id': 3},  # 4
-            {'type': CmdRunAction, 'command': 'ls'},  # 5
-            {
-                'type': CmdOutputObservation,
-                'content': 'file1',
-                'command': 'ls',
-                'cause_id': 5,
-            },  # 6
-            {'type': CmdRunAction, 'command': 'pwd'},  # 7
-            {
-                'type': CmdOutputObservation,
-                'content': '/dir',
-                'command': 'pwd',
-                'cause_id': 7,
-            },  # 8
-            {'type': CmdRunAction, 'command': 'cat file1'},  # 9
-            {
-                'type': CmdOutputObservation,
-                'content': 'content',
-                'command': 'cat file1',
-                'cause_id': 9,
-            },  # 10
-        ]
-    )
-    mock_first_user_message.id = 2  # Set the ID of the mocked first user message
-
-    # Calculation (RecallAction now essential):
-    # History len = 10
-    # Essentials = [sys(1), user(2), recall_act(3), recall_obs(4)] (len=4)
-    # Non-essential count = 10 - 4 = 6
-    # num_recent_to_keep = max(1, 6 // 2) = 3
-    # slice_start_index = 10 - 3 = 7
-    # recent_events_slice = history[7:] = [obs2(8), cmd3(9), obs3(10)]
-    # Validation: remove leading obs2(8). validated_slice = [cmd3(9), obs3(10)]
-    # Final = essentials + validated_slice = [sys(1), user(2), recall_act(3), recall_obs(4), cmd3(9), obs3(10)]
-    # Expected IDs: [1, 2, 3, 4, 9, 10]. Length 6.
-    truncated_events = controller._apply_conversation_window()
-
-    assert len(truncated_events) == 6
-    expected_ids = [1, 2, 3, 4, 9, 10]
-    actual_ids = [e.id for e in truncated_events]
-    assert actual_ids == expected_ids
-    # Check no dangling observations at the start of the recent slice part
-    # The first event of the validated slice is cmd3(9)
-    assert not isinstance(truncated_events[4], Observation)  # Index adjusted
-
-
-def test_no_system_message(controller_fixture):
-    controller, mock_first_user_message = controller_fixture
-
-    controller.state.history = create_events(
-        [
-            {
-                'type': MessageAction,
-                'content': 'User Task 1',
-                'source': EventSource.USER,
-            },  # 1
-            {'type': RecallAction, 'query': 'User Task 1'},  # 2
-            {'type': RecallObservation, 'content': 'Recall result', 'cause_id': 2},  # 3
-            {'type': CmdRunAction, 'command': 'ls'},  # 4
-            {
-                'type': CmdOutputObservation,
-                'content': 'file1',
-                'command': 'ls',
-                'cause_id': 4,
-            },  # 5
-            {'type': CmdRunAction, 'command': 'pwd'},  # 6
-            {
-                'type': CmdOutputObservation,
-                'content': '/dir',
-                'command': 'pwd',
-                'cause_id': 6,
-            },  # 7
-            {'type': CmdRunAction, 'command': 'cat file1'},  # 8
-            {
-                'type': CmdOutputObservation,
-                'content': 'content',
-                'command': 'cat file1',
-                'cause_id': 8,
-            },  # 9
-        ]
-    )
-    mock_first_user_message.id = 1
-
-    # Calculation (RecallAction now essential):
-    # History len = 9
-    # Essentials = [user(1), recall_act(2), recall_obs(3)] (len=3)
-    # Non-essential count = 9 - 3 = 6
-    # num_recent_to_keep = max(1, 6 // 2) = 3
-    # slice_start_index = 9 - 3 = 6
-    # recent_events_slice = history[6:] = [obs2(7), cmd3(8), obs3(9)]
-    # Validation: remove leading obs2(7). validated_slice = [cmd3(8), obs3(9)]
-    # Final = essentials + validated_slice = [user(1), recall_act(2), recall_obs(3), cmd3(8), obs3(9)]
-    # Expected IDs: [1, 2, 3, 8, 9]. Length 5.
-    truncated_events = controller._apply_conversation_window()
-
-    assert len(truncated_events) == 5
-    expected_ids = [1, 2, 3, 8, 9]
-    actual_ids = [e.id for e in truncated_events]
-    assert actual_ids == expected_ids
-
-
-def test_no_recall_observation(controller_fixture):
-    controller, mock_first_user_message = controller_fixture
-
-    controller.state.history = create_events(
-        [
-            {'type': SystemMessageAction, 'content': 'System Prompt'},  # 1
-            {
-                'type': MessageAction,
-                'content': 'User Task 1',
-                'source': EventSource.USER,
-            },  # 2
-            {'type': RecallAction, 'query': 'User Task 1'},  # 3 (Recall Action exists)
-            # Recall Observation is missing
-            {'type': CmdRunAction, 'command': 'ls'},  # 4
-            {
-                'type': CmdOutputObservation,
-                'content': 'file1',
-                'command': 'ls',
-                'cause_id': 4,
-            },  # 5
-            {'type': CmdRunAction, 'command': 'pwd'},  # 6
-            {
-                'type': CmdOutputObservation,
-                'content': '/dir',
-                'command': 'pwd',
-                'cause_id': 6,
-            },  # 7
-            {'type': CmdRunAction, 'command': 'cat file1'},  # 8
-            {
-                'type': CmdOutputObservation,
-                'content': 'content',
-                'command': 'cat file1',
-                'cause_id': 8,
-            },  # 9
-        ]
-    )
-    mock_first_user_message.id = 2
-
-    # Calculation (RecallAction essential only if RecallObs exists):
-    # History len = 9
-    # Essentials = [sys(1), user(2)] (len=2) - RecallObs missing, so RecallAction not essential here
-    # Non-essential count = 9 - 2 = 7
-    # num_recent_to_keep = max(1, 7 // 2) = 3
-    # slice_start_index = 9 - 3 = 6
-    # recent_events_slice = history[6:] = [obs2(7), cmd3(8), obs3(9)]
-    # Validation: remove leading obs2(7). validated_slice = [cmd3(8), obs3(9)]
-    # Final = essentials + validated_slice = [sys(1), user(2), recall_action(3), cmd_cat(8), obs_cat(9)]
-    # Expected IDs: [1, 2, 3, 8, 9]. Length 5.
-    truncated_events = controller._apply_conversation_window()
-
-    assert len(truncated_events) == 5
-    expected_ids = [1, 2, 3, 8, 9]
-    actual_ids = [e.id for e in truncated_events]
-    assert actual_ids == expected_ids
-
-
-def test_short_history_no_truncation(controller_fixture):
-    controller, mock_first_user_message = controller_fixture
-
-    history = create_events(
-        [
-            {'type': SystemMessageAction, 'content': 'System Prompt'},  # 1
-            {
-                'type': MessageAction,
-                'content': 'User Task 1',
-                'source': EventSource.USER,
-            },  # 2
-            {'type': RecallAction, 'query': 'User Task 1'},  # 3
-            {'type': RecallObservation, 'content': 'Recall result', 'cause_id': 3},  # 4
-            {'type': CmdRunAction, 'command': 'ls'},  # 5
-            {
-                'type': CmdOutputObservation,
-                'content': 'file1',
-                'command': 'ls',
-                'cause_id': 5,
-            },  # 6
-        ]
-    )
-    controller.state.history = history
-    mock_first_user_message.id = 2
-
-    # Calculation (RecallAction now essential):
-    # History len = 6
-    # Essentials = [sys(1), user(2), recall_act(3), recall_obs(4)] (len=4)
-    # Non-essential count = 6 - 4 = 2
-    # num_recent_to_keep = max(1, 2 // 2) = 1
-    # slice_start_index = 6 - 1 = 5
-    # recent_events_slice = history[5:] = [obs1(6)]
-    # Validation: remove leading obs1(6). validated_slice = []
-    # Final = essentials + validated_slice = [sys(1), user(2), recall_act(3), recall_obs(4)]
-    # Expected IDs: [1, 2, 3, 4]. Length 4.
-    truncated_events = controller._apply_conversation_window()
-
-    assert len(truncated_events) == 4
-    expected_ids = [1, 2, 3, 4]
-    actual_ids = [e.id for e in truncated_events]
-    assert actual_ids == expected_ids
-
-
-def test_only_essential_events(controller_fixture):
-    controller, mock_first_user_message = controller_fixture
-
-    history = create_events(
-        [
-            {'type': SystemMessageAction, 'content': 'System Prompt'},  # 1
-            {
-                'type': MessageAction,
-                'content': 'User Task 1',
-                'source': EventSource.USER,
-            },  # 2
-            {'type': RecallAction, 'query': 'User Task 1'},  # 3
-            {'type': RecallObservation, 'content': 'Recall result', 'cause_id': 3},  # 4
-        ]
-    )
-    controller.state.history = history
-    mock_first_user_message.id = 2
-
-    # Calculation (RecallAction now essential):
-    # History len = 4
-    # Essentials = [sys(1), user(2), recall_act(3), recall_obs(4)] (len=4)
-    # Non-essential count = 4 - 4 = 0
-    # num_recent_to_keep = max(1, 0 // 2) = 1
-    # slice_start_index = 4 - 1 = 3
-    # recent_events_slice = history[3:] = [recall_obs(4)]
-    # Validation: remove leading recall_obs(4). validated_slice = []
-    # Final = essentials + validated_slice = [sys(1), user(2), recall_act(3), recall_obs(4)]
-    # Expected IDs: [1, 2, 3, 4]. Length 4.
-    truncated_events = controller._apply_conversation_window()
-
-    assert len(truncated_events) == 4
-    expected_ids = [1, 2, 3, 4]
-    actual_ids = [e.id for e in truncated_events]
-    assert actual_ids == expected_ids
-
-
-def test_dangling_observations_at_cut_point(controller_fixture):
-    controller, mock_first_user_message = controller_fixture
-
-    history_forced_dangle = create_events(
-        [
-            {'type': SystemMessageAction, 'content': 'System Prompt'},  # 1
-            {
-                'type': MessageAction,
-                'content': 'User Task 1',
-                'source': EventSource.USER,
-            },  # 2
-            {'type': RecallAction, 'query': 'User Task 1'},  # 3
-            {'type': RecallObservation, 'content': 'Recall result', 'cause_id': 3},  # 4
-            # --- Slice calculation should start here ---
-            {
-                'type': CmdOutputObservation,
-                'content': 'dangle1',
-                'command': 'cmd_unknown',
-            },  # 5 (Dangling)
-            {
-                'type': CmdOutputObservation,
-                'content': 'dangle2',
-                'command': 'cmd_unknown',
-            },  # 6 (Dangling)
-            {'type': CmdRunAction, 'command': 'cmd1'},  # 7
-            {
-                'type': CmdOutputObservation,
-                'content': 'obs1',
-                'command': 'cmd1',
-                'cause_id': 7,
-            },  # 8
-            {'type': CmdRunAction, 'command': 'cmd2'},  # 9
-            {
-                'type': CmdOutputObservation,
-                'content': 'obs2',
-                'command': 'cmd2',
-                'cause_id': 9,
-            },  # 10
-        ]
-    )  # 10 events total
-    controller.state.history = history_forced_dangle
-    mock_first_user_message.id = 2
-
-    # Calculation (RecallAction now essential):
-    # History len = 10
-    # Essentials = [sys(1), user(2), recall_act(3), recall_obs(4)] (len=4)
-    # Non-essential count = 10 - 4 = 6
-    # num_recent_to_keep = max(1, 6 // 2) = 3
-    # slice_start_index = 10 - 3 = 7
-    # recent_events_slice = history[7:] = [obs1(8), cmd2(9), obs2(10)]
-    # Validation: remove leading obs1(8). validated_slice = [cmd2(9), obs2(10)]
-    # Final = essentials + validated_slice = [sys(1), user(2), recall_act(3), recall_obs(4), cmd2(9), obs2(10)]
-    # Expected IDs: [1, 2, 3, 4, 9, 10]. Length 6.
-    truncated_events = controller._apply_conversation_window()
-
-    assert len(truncated_events) == 6
-    expected_ids = [1, 2, 3, 4, 9, 10]
-    actual_ids = [e.id for e in truncated_events]
-    assert actual_ids == expected_ids
-    # Verify dangling observations 5 and 6 were removed (implicitly by slice start and validation)
-
-
-def test_only_dangling_observations_in_recent_slice(controller_fixture):
-    controller, mock_first_user_message = controller_fixture
-
-    history = create_events(
-        [
-            {'type': SystemMessageAction, 'content': 'System Prompt'},  # 1
-            {
-                'type': MessageAction,
-                'content': 'User Task 1',
-                'source': EventSource.USER,
-            },  # 2
-            {'type': RecallAction, 'query': 'User Task 1'},  # 3
-            {'type': RecallObservation, 'content': 'Recall result', 'cause_id': 3},  # 4
-            # --- Slice calculation should start here ---
-            {
-                'type': CmdOutputObservation,
-                'content': 'dangle1',
-                'command': 'cmd_unknown',
-            },  # 5 (Dangling)
-            {
-                'type': CmdOutputObservation,
-                'content': 'dangle2',
-                'command': 'cmd_unknown',
-            },  # 6 (Dangling)
-        ]
-    )  # 6 events total
-    controller.state.history = history
-    mock_first_user_message.id = 2
-
-    # Calculation (RecallAction now essential):
-    # History len = 6
-    # Essentials = [sys(1), user(2), recall_act(3), recall_obs(4)] (len=4)
-    # Non-essential count = 6 - 4 = 2
-    # num_recent_to_keep = max(1, 2 // 2) = 1
-    # slice_start_index = 6 - 1 = 5
-    # recent_events_slice = history[5:] = [dangle2(6)]
-    # Validation: remove leading dangle2(6). validated_slice = [] (Corrected based on user feedback/bugfix)
-    # Final = essentials + validated_slice = [sys(1), user(2), recall_act(3), recall_obs(4)]
-    # Expected IDs: [1, 2, 3, 4]. Length 4.
-    with patch(
-        'openhands.controller.agent_controller.logger.warning'
-    ) as mock_log_warning:
-        truncated_events = controller._apply_conversation_window()
-
-        assert len(truncated_events) == 4
-        expected_ids = [1, 2, 3, 4]
-        actual_ids = [e.id for e in truncated_events]
-        assert actual_ids == expected_ids
-        # Verify dangling observations 5 and 6 were removed
-
-        # Check that the specific warning was logged exactly once
-        assert mock_log_warning.call_count == 1
-
-        # Check the essential parts of the arguments, allowing for variations like stacklevel
-        call_args, call_kwargs = mock_log_warning.call_args
-        expected_message_substring = 'All recent events are dangling observations, which we truncate. This means the agent has only the essential first events. This should not happen.'
-        assert expected_message_substring in call_args[0]
-        assert 'extra' in call_kwargs
-        assert call_kwargs['extra'].get('session_id') == 'test_sid'
-
-
-def test_empty_history(controller_fixture):
-    controller, _ = controller_fixture
-    controller.state.history = []
-
-    truncated_events = controller._apply_conversation_window()
-    assert truncated_events == []
-
-
-def test_multiple_user_messages(controller_fixture):
-    controller, mock_first_user_message = controller_fixture
-
-    history = create_events(
-        [
-            {'type': SystemMessageAction, 'content': 'System Prompt'},  # 1
-            {
-                'type': MessageAction,
-                'content': 'User Task 1',
-                'source': EventSource.USER,
-            },  # 2 (First)
-            {'type': RecallAction, 'query': 'User Task 1'},  # 3
-            {
-                'type': RecallObservation,
-                'content': 'Recall result 1',
-                'cause_id': 3,
-            },  # 4
-            {'type': CmdRunAction, 'command': 'cmd1'},  # 5
-            {
-                'type': CmdOutputObservation,
-                'content': 'obs1',
-                'command': 'cmd1',
-                'cause_id': 5,
-            },  # 6
-            {
-                'type': MessageAction,
-                'content': 'User Task 2',
-                'source': EventSource.USER,
-            },  # 7 (Second)
-            {'type': RecallAction, 'query': 'User Task 2'},  # 8
-            {
-                'type': RecallObservation,
-                'content': 'Recall result 2',
-                'cause_id': 8,
-            },  # 9
-            {'type': CmdRunAction, 'command': 'cmd2'},  # 10
-            {
-                'type': CmdOutputObservation,
-                'content': 'obs2',
-                'command': 'cmd2',
-                'cause_id': 10,
-            },  # 11
-        ]
-    )  # 11 events total
-    controller.state.history = history
-    mock_first_user_message.id = 2  # Explicitly set the first user message ID
-
-    # Calculation (RecallAction now essential):
-    # History len = 11
-    # Essentials = [sys(1), user1(2), recall_act1(3), recall_obs1(4)] (len=4)
-    # Non-essential count = 11 - 4 = 7
-    # num_recent_to_keep = max(1, 7 // 2) = 3
-    # slice_start_index = 11 - 3 = 8
-    # recent_events_slice = history[8:] = [recall_obs2(9), cmd2(10), obs2(11)]
-    # Validation: remove leading recall_obs2(9). validated_slice = [cmd2(10), obs2(11)]
-    # Final = essentials + validated_slice = [sys(1), user1(2), recall_act1(3), recall_obs1(4)] + [cmd2(10), obs2(11)]
-    # Expected IDs: [1, 2, 3, 4, 10, 11]. Length 6.
-    truncated_events = controller._apply_conversation_window()
-
-    assert len(truncated_events) == 6
-    expected_ids = [1, 2, 3, 4, 10, 11]
-    actual_ids = [e.id for e in truncated_events]
-    assert actual_ids == expected_ids
-
-    # Verify the second user message (ID 7) was NOT kept
-    assert not any(event.id == 7 for event in truncated_events)
-    # Verify the first user message (ID 2) is present
-    assert any(event.id == 2 for event in truncated_events)

tests/unit/test_agents.py

@@ -44,7 +44,6 @@ from openhands.events.observation.commands import (
 )
 from openhands.events.tool import ToolCallMetadata
 from openhands.llm.llm import LLM
-from openhands.memory.condenser import View
 
 
 @pytest.fixture(params=['CodeActAgent', 'ReadOnlyAgent'])
@@ -98,12 +97,6 @@ def test_reset(agent):
     action._source = EventSource.AGENT
     agent.pending_actions.append(action)
 
-    # Create a mock state with initial user message
-    mock_state = Mock(spec=State)
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
-    mock_state.history = [initial_user_message]
-
     # Reset
     agent.reset()
 
@@ -117,14 +110,8 @@ def test_step_with_pending_actions(agent):
     pending_action._source = EventSource.AGENT
     agent.pending_actions.append(pending_action)
 
-    # Create a mock state with initial user message
-    mock_state = Mock(spec=State)
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
-    mock_state.history = [initial_user_message]
-
     # Step should return the pending action
-    result = agent.step(mock_state)
+    result = agent.step(Mock())
     assert result == pending_action
     assert len(agent.pending_actions) == 0
 
@@ -273,11 +260,6 @@ def test_step_with_no_pending_actions(mock_state: State):
     mock_state.latest_user_message_llm_metrics = None
     mock_state.latest_user_message_tool_call_metadata = None
 
-    # Add initial user message to history
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
-    mock_state.history = [initial_user_message]
-
     action = agent.step(mock_state)
     assert isinstance(action, MessageAction)
     assert action.content == 'Task completed'
@@ -348,56 +330,42 @@ def test_mismatched_tool_call_events_and_auto_add_system_message(
     )
 
     action = CmdRunAction('foo')
-    action._source = EventSource.AGENT
+    action._source = 'agent'
     action.tool_call_metadata = tool_call_metadata
 
     observation = CmdOutputObservation(content='', command_id=0, command='foo')
     observation.tool_call_metadata = tool_call_metadata
 
-    # Add initial user message
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
-
     # When both events are provided, the agent should get three messages:
     # 1. The system message (added automatically for backward compatibility)
     # 2. The action message
     # 3. The observation message
-    mock_state.history = [initial_user_message, action, observation]
-    messages = agent._get_messages(mock_state.history, initial_user_message)
-    assert len(messages) == 4  # System + initial user + action + observation
+    mock_state.history = [action, observation]
+    messages = agent._get_messages(mock_state.history)
+    assert len(messages) == 3
     assert messages[0].role == 'system'  # First message should be the system message
-    assert (
-        messages[1].role == 'user'
-    )  # Second message should be the initial user message
-    assert messages[2].role == 'assistant'  # Third message should be the action
-    assert messages[3].role == 'tool'  # Fourth message should be the observation
+    assert messages[1].role == 'assistant'  # Second message should be the action
+    assert messages[2].role == 'tool'  # Third message should be the observation
 
     # The same should hold if the events are presented out-of-order
-    mock_state.history = [initial_user_message, observation, action]
-    messages = agent._get_messages(mock_state.history, initial_user_message)
-    assert len(messages) == 4
+    mock_state.history = [observation, action]
+    messages = agent._get_messages(mock_state.history)
+    assert len(messages) == 3
     assert messages[0].role == 'system'  # First message should be the system message
-    assert (
-        messages[1].role == 'user'
-    )  # Second message should be the initial user message
 
     # If only one of the two events is present, then we should just get the system message
     # plus any valid message from the event
-    mock_state.history = [initial_user_message, action]
-    messages = agent._get_messages(mock_state.history, initial_user_message)
+    mock_state.history = [action]
+    messages = agent._get_messages(mock_state.history)
     assert (
-        len(messages) == 2
-    )  # System + initial user message, action is waiting for its observation
+        len(messages) == 1
+    )  # Only system message, action is waiting for its observation
     assert messages[0].role == 'system'
-    assert messages[1].role == 'user'
 
-    mock_state.history = [initial_user_message, observation]
-    messages = agent._get_messages(mock_state.history, initial_user_message)
-    assert (
-        len(messages) == 2
-    )  # System + initial user message, observation has no matching action
+    mock_state.history = [observation]
+    messages = agent._get_messages(mock_state.history)
+    assert len(messages) == 1  # Only system message, observation has no matching action
     assert messages[0].role == 'system'
-    assert messages[1].role == 'user'
 
 
 def test_grep_tool():
@@ -502,19 +470,3 @@ def test_get_system_message():
     assert len(result.tools) > 0
     assert any(tool['function']['name'] == 'execute_bash' for tool in result.tools)
     assert result._source == EventSource.AGENT
-
-
-def test_step_raises_error_if_no_initial_user_message(
-    agent: CodeActAgent, mock_state: State
-):
-    """Tests that step raises ValueError if the initial user message is not found."""
-    # Ensure history does NOT contain a user MessageAction
-    assistant_message = MessageAction(content='Assistant message')
-    assistant_message._source = EventSource.AGENT
-    mock_state.history = [assistant_message]
-    # Mock the condenser to return the history as is
-    agent.condenser = Mock()
-    agent.condenser.condensed_history.return_value = View(events=mock_state.history)
-
-    with pytest.raises(ValueError, match='Initial user message not found'):
-        agent.step(mock_state)

tests/unit/test_cli_commands.py

@@ -8,7 +8,6 @@ from openhands.core.cli_commands import (
     handle_help_command,
     handle_init_command,
     handle_new_command,
-    handle_resume_command,
     handle_settings_command,
     handle_status_command,
 )
@@ -462,27 +461,3 @@ class TestHandleSettingsCommand:
         # Verify correct behavior
         mock_display_settings.assert_called_once_with(config)
         mock_cli_confirm.assert_called_once()
-
-
-class TestHandleResumeCommand:
-    @pytest.mark.asyncio
-    async def test_handle_resume_command(self):
-        """Test that handle_resume_command adds the 'continue' message to the event stream."""
-        # Create a mock event stream
-        event_stream = MagicMock(spec=EventStream)
-
-        # Call the function
-        close_repl, new_session_requested = await handle_resume_command(event_stream)
-
-        # Check that the event stream add_event was called with the correct message action
-        event_stream.add_event.assert_called_once()
-        args, kwargs = event_stream.add_event.call_args
-        message_action, source = args
-
-        assert isinstance(message_action, MessageAction)
-        assert message_action.content == 'continue'
-        assert source == EventSource.USER
-
-        # Check the return values
-        assert close_repl is True
-        assert new_session_requested is False

tests/unit/test_cli_pause_resume.py

@@ -1,325 +0,0 @@
-import asyncio
-from unittest.mock import MagicMock, call, patch
-
-import pytest
-from prompt_toolkit.formatted_text import HTML
-from prompt_toolkit.keys import Keys
-
-from openhands.core.cli_tui import process_agent_pause
-from openhands.core.schema import AgentState
-from openhands.events import EventSource
-from openhands.events.action import ChangeAgentStateAction
-from openhands.events.observation import AgentStateChangedObservation
-from openhands.events.stream import EventStream
-
-
-class TestProcessAgentPause:
-    @pytest.mark.asyncio
-    @patch('openhands.core.cli_tui.create_input')
-    @patch('openhands.core.cli_tui.print_formatted_text')
-    async def test_process_agent_pause_ctrl_p(self, mock_print, mock_create_input):
-        """Test that process_agent_pause sets the done event when Ctrl+P is pressed."""
-        # Create the done event
-        done = asyncio.Event()
-
-        # Set up the mock input
-        mock_input = MagicMock()
-        mock_create_input.return_value = mock_input
-
-        # Mock the context managers
-        mock_raw_mode = MagicMock()
-        mock_input.raw_mode.return_value = mock_raw_mode
-        mock_raw_mode.__enter__ = MagicMock()
-        mock_raw_mode.__exit__ = MagicMock()
-
-        mock_attach = MagicMock()
-        mock_input.attach.return_value = mock_attach
-        mock_attach.__enter__ = MagicMock()
-        mock_attach.__exit__ = MagicMock()
-
-        # Capture the keys_ready function
-        keys_ready_func = None
-
-        def fake_attach(callback):
-            nonlocal keys_ready_func
-            keys_ready_func = callback
-            return mock_attach
-
-        mock_input.attach.side_effect = fake_attach
-
-        # Create a task to run process_agent_pause
-        task = asyncio.create_task(process_agent_pause(done))
-
-        # Give it a moment to start and capture the callback
-        await asyncio.sleep(0.1)
-
-        # Make sure we captured the callback
-        assert keys_ready_func is not None
-
-        # Create a key press that simulates Ctrl+P
-        key_press = MagicMock()
-        key_press.key = Keys.ControlP
-        mock_input.read_keys.return_value = [key_press]
-
-        # Manually call the callback to simulate key press
-        keys_ready_func()
-
-        # Verify done was set
-        assert done.is_set()
-
-        # Verify print was called with the pause message
-        assert mock_print.call_count == 2
-        assert mock_print.call_args_list[0] == call('')
-
-        # Check that the second call contains the pause message HTML
-        second_call = mock_print.call_args_list[1][0][0]
-        assert isinstance(second_call, HTML)
-        assert 'Pausing the agent' in str(second_call)
-
-        # Cancel the task
-        task.cancel()
-        try:
-            await task
-        except asyncio.CancelledError:
-            pass
-
-
-class TestCliPauseResumeInRunSession:
-    @pytest.mark.asyncio
-    async def test_on_event_async_pause_processing(self):
-        """Test that on_event_async processes the pause event when is_paused is set."""
-        # Create a mock event
-        event = MagicMock()
-
-        # Create mock dependencies
-        event_stream = MagicMock()
-        is_paused = asyncio.Event()
-        reload_microagents = False
-        config = MagicMock()
-
-        # Patch the display_event function
-        with patch('openhands.core.cli.display_event') as mock_display_event, patch(
-            'openhands.core.cli.update_usage_metrics'
-        ) as mock_update_metrics:
-            # Create a closure to capture the current context
-            async def test_func():
-                # Set the pause event
-                is_paused.set()
-
-                # Create a context similar to run_session to call on_event_async
-                # We're creating a function that mimics the environment of on_event_async
-                async def on_event_async_test(event):
-                    nonlocal reload_microagents, is_paused
-                    mock_display_event(event, config)
-                    mock_update_metrics(event, usage_metrics=MagicMock())
-
-                    # Pause the agent if the pause event is set (through Ctrl-P)
-                    if is_paused.is_set():
-                        event_stream.add_event(
-                            ChangeAgentStateAction(AgentState.PAUSED),
-                            EventSource.USER,
-                        )
-                        is_paused.clear()
-
-                # Call our test function
-                await on_event_async_test(event)
-
-                # Check that the event_stream.add_event was called with the correct action
-                event_stream.add_event.assert_called_once()
-                args, kwargs = event_stream.add_event.call_args
-                action, source = args
-
-                assert isinstance(action, ChangeAgentStateAction)
-                assert action.agent_state == AgentState.PAUSED
-                assert source == EventSource.USER
-
-                # Check that is_paused was cleared
-                assert not is_paused.is_set()
-
-            # Run the test function
-            await test_func()
-
-
-class TestCliCommandsPauseResume:
-    @pytest.mark.asyncio
-    @patch('openhands.core.cli_commands.handle_resume_command')
-    async def test_handle_commands_resume(self, mock_handle_resume):
-        """Test that the handle_commands function properly calls handle_resume_command."""
-        # Import the handle_commands function
-        from openhands.core.cli_commands import handle_commands
-
-        # Set up mocks
-        event_stream = MagicMock(spec=EventStream)
-        usage_metrics = MagicMock()
-        sid = 'test-session-id'
-        config = MagicMock()
-        current_dir = '/test/dir'
-        settings_store = MagicMock()
-
-        # Set the return value for handle_resume_command
-        mock_handle_resume.return_value = (False, False)
-
-        # Call handle_commands with the resume command
-        close_repl, reload_microagents, new_session_requested = await handle_commands(
-            '/resume',
-            event_stream,
-            usage_metrics,
-            sid,
-            config,
-            current_dir,
-            settings_store,
-        )
-
-        # Check that handle_resume_command was called with the correct arguments
-        mock_handle_resume.assert_called_once_with(event_stream)
-
-        # Check the return values
-        assert close_repl is False
-        assert reload_microagents is False
-        assert new_session_requested is False
-
-
-class TestAgentStatePauseResume:
-    @pytest.mark.asyncio
-    @patch('openhands.core.cli.display_agent_running_message')
-    @patch('openhands.core.cli.process_agent_pause')
-    async def test_agent_running_enables_pause(
-        self, mock_process_agent_pause, mock_display_message
-    ):
-        """Test that when the agent is running, pause functionality is enabled."""
-        # Create mock dependencies
-        event = MagicMock()
-        # AgentStateChangedObservation requires a content parameter
-        event.observation = AgentStateChangedObservation(
-            agent_state=AgentState.RUNNING, content='Agent state changed to RUNNING'
-        )
-
-        # Create a context similar to run_session to call on_event_async
-        loop = MagicMock()
-        is_paused = asyncio.Event()
-        config = MagicMock()
-        config.security.confirmation_mode = False
-
-        # Create a closure to capture the current context
-        async def test_func():
-            # Call our simplified on_event_async
-            async def on_event_async_test(event):
-                if isinstance(event.observation, AgentStateChangedObservation):
-                    if event.observation.agent_state == AgentState.RUNNING:
-                        # Enable pause/resume functionality only if the confirmation mode is disabled
-                        if not config.security.confirmation_mode:
-                            mock_display_message()
-                            loop.create_task(mock_process_agent_pause(is_paused))
-
-            # Call the function
-            await on_event_async_test(event)
-
-            # Check that the message was displayed
-            mock_display_message.assert_called_once()
-
-            # Check that process_agent_pause was called with the right arguments
-            mock_process_agent_pause.assert_called_once_with(is_paused)
-
-            # Check that loop.create_task was called
-            loop.create_task.assert_called_once()
-
-        # Run the test function
-        await test_func()
-
-    @pytest.mark.asyncio
-    @patch('openhands.core.cli.display_event')
-    @patch('openhands.core.cli.update_usage_metrics')
-    async def test_pause_event_changes_agent_state(
-        self, mock_update_metrics, mock_display_event
-    ):
-        """Test that when is_paused is set, a PAUSED state change event is added to the stream."""
-        # Create mock dependencies
-        event = MagicMock()
-        event_stream = MagicMock()
-        is_paused = asyncio.Event()
-        config = MagicMock()
-        reload_microagents = False
-
-        # Set the pause event
-        is_paused.set()
-
-        # Create a closure to capture the current context
-        async def test_func():
-            # Create a context similar to run_session to call on_event_async
-            async def on_event_async_test(event):
-                nonlocal reload_microagents
-                mock_display_event(event, config)
-                mock_update_metrics(event, MagicMock())
-
-                # Pause the agent if the pause event is set (through Ctrl-P)
-                if is_paused.is_set():
-                    event_stream.add_event(
-                        ChangeAgentStateAction(AgentState.PAUSED),
-                        EventSource.USER,
-                    )
-                    is_paused.clear()
-
-            # Call the function
-            await on_event_async_test(event)
-
-            # Check that the event_stream.add_event was called with the correct action
-            event_stream.add_event.assert_called_once()
-            args, kwargs = event_stream.add_event.call_args
-            action, source = args
-
-            assert isinstance(action, ChangeAgentStateAction)
-            assert action.agent_state == AgentState.PAUSED
-            assert source == EventSource.USER
-
-            # Check that is_paused was cleared
-            assert not is_paused.is_set()
-
-        # Run the test
-        await test_func()
-
-    @pytest.mark.asyncio
-    async def test_paused_agent_awaits_input(self):
-        """Test that when the agent is paused, it awaits user input."""
-        # Create mock dependencies
-        event = MagicMock()
-        # AgentStateChangedObservation requires a content parameter
-        event.observation = AgentStateChangedObservation(
-            agent_state=AgentState.PAUSED, content='Agent state changed to PAUSED'
-        )
-        reload_microagents = False
-        memory = MagicMock()
-        runtime = MagicMock()
-        prompt_task = MagicMock()
-
-        # Create a closure to capture the current context
-        async def test_func():
-            # Create a simplified version of on_event_async
-            async def on_event_async_test(event):
-                nonlocal reload_microagents, prompt_task
-
-                if isinstance(event.observation, AgentStateChangedObservation):
-                    if event.observation.agent_state in [
-                        AgentState.AWAITING_USER_INPUT,
-                        AgentState.FINISHED,
-                        AgentState.PAUSED,
-                    ]:
-                        # Reload microagents after initialization of repo.md
-                        if reload_microagents:
-                            microagents = runtime.get_microagents_from_selected_repo(
-                                None
-                            )
-                            memory.load_user_workspace_microagents(microagents)
-                            reload_microagents = False
-
-                        # Since prompt_for_next_task is a nested function in cli.py,
-                        # we'll just check that we've reached this code path
-                        prompt_task = 'Prompt for next task would be called here'
-
-            # Call the function
-            await on_event_async_test(event)
-
-            # Check that we reached the code path where prompt_for_next_task would be called
-            assert prompt_task == 'Prompt for next task would be called here'
-
-        # Run the test
-        await test_func()

tests/unit/test_cli_tui.py

@@ -1,3 +1,4 @@
+import asyncio
 from unittest.mock import MagicMock, Mock, patch
 
 from openhands.core.cli_tui import (
@@ -51,9 +52,12 @@ class TestDisplayFunctions:
 
     @patch('openhands.core.cli_tui.print_formatted_text')
     def test_display_banner(self, mock_print):
+        # Create a mock loaded event
+        is_loaded = asyncio.Event()
+        is_loaded.set()
         session_id = 'test-session-id'
 
-        display_banner(session_id)
+        display_banner(session_id, is_loaded)
 
         # Verify banner calls
         assert mock_print.call_count >= 3

tests/unit/test_conversation_memory.py

@@ -100,7 +100,6 @@ def test_process_events_with_message_action(conversation_memory):
     # Process events
     messages = conversation_memory.process_events(
         condensed_history=[system_message, user_message, assistant_message],
-        initial_user_action=user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
@@ -109,178 +108,10 @@ def test_process_events_with_message_action(conversation_memory):
     assert len(messages) == 3
     assert messages[0].role == 'system'
     assert messages[0].content[0].text == 'System message'
-
-
-# Test cases for _ensure_system_message
-def test_ensure_system_message_adds_if_missing(conversation_memory):
-    """Test that _ensure_system_message adds a system message if none exists."""
-    user_message = MessageAction(content='User message')
-    user_message._source = EventSource.USER
-    events = [user_message]
-    conversation_memory._ensure_system_message(events)
-    assert len(events) == 2
-    assert isinstance(events[0], SystemMessageAction)
-    assert events[0].content == 'System message'  # From fixture
-    assert isinstance(events[1], MessageAction)  # Original event is still there
-
-
-def test_ensure_system_message_does_nothing_if_present(conversation_memory):
-    """Test that _ensure_system_message does nothing if a system message is already present."""
-    original_system_message = SystemMessageAction(content='Existing system message')
-    user_message = MessageAction(content='User message')
-    user_message._source = EventSource.USER
-    events = [
-        original_system_message,
-        user_message,
-    ]
-    original_events = list(events)  # Copy before modification
-    conversation_memory._ensure_system_message(events)
-    assert events == original_events  # List should be unchanged
-
-
-# Test cases for _ensure_initial_user_message
-@pytest.fixture
-def initial_user_action():
-    msg = MessageAction(content='Initial User Message')
-    msg._source = EventSource.USER
-    return msg
-
-
-def test_ensure_initial_user_message_adds_if_only_system(
-    conversation_memory, initial_user_action
-):
-    """Test adding the initial user message when only the system message exists."""
-    system_message = SystemMessageAction(content='System')
-    system_message._source = EventSource.AGENT
-    events = [system_message]
-    conversation_memory._ensure_initial_user_message(events, initial_user_action)
-    assert len(events) == 2
-    assert events[0] == system_message
-    assert events[1] == initial_user_action
-
-
-def test_ensure_initial_user_message_correct_already_present(
-    conversation_memory, initial_user_action
-):
-    """Test that nothing changes if the correct initial user message is at index 1."""
-    system_message = SystemMessageAction(content='System')
-    agent_message = MessageAction(content='Assistant')
-    agent_message._source = EventSource.USER
-    events = [
-        system_message,
-        initial_user_action,
-        agent_message,
-    ]
-    original_events = list(events)
-    conversation_memory._ensure_initial_user_message(events, initial_user_action)
-    assert events == original_events
-
-
-def test_ensure_initial_user_message_incorrect_at_index_1(
-    conversation_memory, initial_user_action
-):
-    """Test inserting the correct initial user message when an incorrect message is at index 1."""
-    system_message = SystemMessageAction(content='System')
-    incorrect_second_message = MessageAction(content='Assistant')
-    incorrect_second_message._source = EventSource.AGENT
-    events = [system_message, incorrect_second_message]
-    conversation_memory._ensure_initial_user_message(events, initial_user_action)
-    assert len(events) == 3
-    assert events[0] == system_message
-    assert events[1] == initial_user_action  # Correct one inserted
-    assert events[2] == incorrect_second_message  # Original second message shifted
-
-
-def test_ensure_initial_user_message_correct_present_later(
-    conversation_memory, initial_user_action
-):
-    """Test inserting the correct initial user message at index 1 even if it exists later."""
-    system_message = SystemMessageAction(content='System')
-    incorrect_second_message = MessageAction(content='Assistant')
-    incorrect_second_message._source = EventSource.AGENT
-    # Correct initial message is present, but later in the list
-    events = [system_message, incorrect_second_message]
-    conversation_memory._ensure_system_message(events)
-    conversation_memory._ensure_initial_user_message(events, initial_user_action)
-    assert len(events) == 3  # Should still insert at index 1, not remove the later one
-    assert events[0] == system_message
-    assert events[1] == initial_user_action  # Correct one inserted at index 1
-    assert events[2] == incorrect_second_message  # Original second message shifted
-    # The duplicate initial_user_action originally at index 2 is now at index 3 (implicitly tested by length and content)
-
-
-def test_ensure_initial_user_message_different_user_msg_at_index_1(
-    conversation_memory, initial_user_action
-):
-    """Test inserting the correct initial user message when a *different* user message is at index 1."""
-    system_message = SystemMessageAction(content='System')
-    different_user_message = MessageAction(content='Different User Message')
-    different_user_message._source = EventSource.USER
-    events = [system_message, different_user_message]
-    conversation_memory._ensure_initial_user_message(events, initial_user_action)
-    assert len(events) == 2
-    assert events[0] == system_message
-    assert events[1] == different_user_message  # Original second message remains
-
-
-def test_ensure_initial_user_message_different_user_msg_at_index_1_and_orphaned_obs(
-    conversation_memory, initial_user_action
-):
-    """
-    Test process_events when an incorrect user message is at index 1 AND
-    an orphaned observation (with tool_call_metadata but no matching action) exists.
-    Expect: System msg, CORRECT initial user msg, the incorrect user msg (shifted).
-            The orphaned observation should be filtered out.
-    """
-    system_message = SystemMessageAction(content='System')
-    different_user_message = MessageAction(content='Different User Message')
-    different_user_message._source = EventSource.USER
-
-    # Create an orphaned observation (no matching action/tool call request will exist)
-    # Use a dictionary that mimics ModelResponse structure to satisfy Pydantic
-    mock_response = {
-        'id': 'mock_response_id',
-        'choices': [{'message': {'content': None, 'tool_calls': []}}],
-        'created': 0,
-        'model': '',
-        'object': '',
-        'usage': {'completion_tokens': 0, 'prompt_tokens': 0, 'total_tokens': 0},
-    }
-    orphaned_obs = CmdOutputObservation(
-        command='orphan_cmd',
-        content='Orphaned output',
-        command_id=99,
-        exit_code=0,
-    )
-    orphaned_obs.tool_call_metadata = ToolCallMetadata(
-        tool_call_id='orphan_call_id',
-        function_name='execute_bash',
-        model_response=mock_response,
-        total_calls_in_response=1,
-    )
-
-    # Initial events list: system, wrong user message, orphaned observation
-    events = [system_message, different_user_message, orphaned_obs]
-
-    # Call the main process_events method
-    messages = conversation_memory.process_events(
-        condensed_history=events,
-        initial_user_action=initial_user_action,  # Provide the *correct* initial action
-        max_message_chars=None,
-        vision_is_active=False,
-    )
-
-    # Assertions on the final messages list
-    assert len(messages) == 2
-    # 1. System message should be first
-    assert messages[0].role == 'system'
-    assert messages[0].content[0].text == 'System'
-
-    # 2. The different user message should be left at index 1
     assert messages[1].role == 'user'
-    assert messages[1].content[0].text == different_user_message.content
-
-    # Implicitly assert that the orphaned_obs was filtered out by checking the length (2)
+    assert messages[1].content[0].text == 'Hello'
+    assert messages[2].role == 'assistant'
+    assert messages[2].content[0].text == 'Hi there'
 
 
 def test_process_events_with_cmd_output_observation(conversation_memory):
@@ -294,17 +125,14 @@ def test_process_events_with_cmd_output_observation(conversation_memory):
         ),
     )
 
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3  # System + initial user + result
-    result = messages[2]  # The actual result is now at index 2
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -320,17 +148,14 @@ def test_process_events_with_ipython_run_cell_observation(conversation_memory):
         content='IPython output\n![image](data:image/png;base64,ABC123)',
     )
 
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3  # System + initial user + result
-    result = messages[2]  # The actual result is now at index 2
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -347,17 +172,14 @@ def test_process_events_with_agent_delegate_observation(conversation_memory):
         content='Content', outputs={'content': 'Delegated agent output'}
     )
 
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3  # System + initial user + result
-    result = messages[2]  # The actual result is now at index 2
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -367,17 +189,14 @@ def test_process_events_with_agent_delegate_observation(conversation_memory):
 def test_process_events_with_error_observation(conversation_memory):
     obs = ErrorObservation('Error message')
 
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3  # System + initial user + result
-    result = messages[2]  # The actual result is now at index 2
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -388,13 +207,10 @@ def test_process_events_with_error_observation(conversation_memory):
 def test_process_events_with_unknown_observation(conversation_memory):
     # Create a mock that inherits from Event but not Action or Observation
     obs = Mock(spec=Event)
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
 
     with pytest.raises(ValueError, match='Unknown event type'):
         conversation_memory.process_events(
             condensed_history=[obs],
-            initial_user_action=initial_user_message,
             max_message_chars=None,
             vision_is_active=False,
         )
@@ -410,17 +226,14 @@ def test_process_events_with_file_edit_observation(conversation_memory):
         impl_source=FileEditSource.LLM_BASED_EDIT,
     )
 
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3  # System + initial user + result
-    result = messages[2]  # The actual result is now at index 2
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -434,21 +247,18 @@ def test_process_events_with_file_read_observation(conversation_memory):
         impl_source=FileReadSource.DEFAULT,
     )
 
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3  # System + initial user + result
-    result = messages[2]  # The actual result is now at index 2
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
-    assert result.content[0].text == '\n\nFile content'
+    assert result.content[0].text == 'File content'
 
 
 def test_process_events_with_browser_output_observation(conversation_memory):
@@ -460,17 +270,14 @@ def test_process_events_with_browser_output_observation(conversation_memory):
         error=False,
     )
 
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3  # System + initial user + result
-    result = messages[2]  # The actual result is now at index 2
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -480,17 +287,14 @@ def test_process_events_with_browser_output_observation(conversation_memory):
 def test_process_events_with_user_reject_observation(conversation_memory):
     obs = UserRejectObservation('Action rejected')
 
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3  # System + initial user + result
-    result = messages[2]  # The actual result is now at index 2
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -513,17 +317,14 @@ def test_process_events_with_empty_environment_info(conversation_memory):
         content='Retrieved environment info',
     )
 
-    initial_user_message = MessageAction(content='Initial user message')
-    initial_user_message._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[empty_obs],
-        initial_user_action=initial_user_message,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    # Should only contain system message and initial user message
-    assert len(messages) == 2
+    # Should only contain no messages except system message
+    assert len(messages) == 1
 
     # Verify that build_workspace_context was NOT called since all input values were empty
     conversation_memory.prompt_manager.build_workspace_context.assert_not_called()
@@ -547,20 +348,14 @@ def test_process_events_with_function_calling_observation(conversation_memory):
         model_response=mock_response,
         total_calls_in_response=1,
     )
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
     # No direct message when using function calling
-    assert (
-        len(messages) == 2
-    )  # should be no messages except system message and initial user message
+    assert len(messages) == 1  # should be no messages except system message
 
 
 def test_process_events_with_message_action_with_image(conversation_memory):
@@ -570,18 +365,14 @@ def test_process_events_with_message_action_with_image(conversation_memory):
     )
     action._source = EventSource.AGENT
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[action],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=True,
     )
 
-    assert len(messages) == 3
-    result = messages[2]
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'assistant'
     assert len(result.content) == 2
     assert isinstance(result.content[0], TextContent)
@@ -594,18 +385,14 @@ def test_process_events_with_user_cmd_action(conversation_memory):
     action = CmdRunAction(command='ls -l')
     action._source = EventSource.USER
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[action],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3
-    result = messages[2]
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -631,18 +418,14 @@ def test_process_events_with_agent_finish_action_with_tool_metadata(
         total_calls_in_response=1,
     )
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[action],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3
-    result = messages[2]
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'assistant'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -678,22 +461,18 @@ def test_process_events_with_environment_microagent_observation(conversation_mem
         content='Retrieved environment info',
     )
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3
-    result = messages[2]
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
-    assert result.content[0].text == '\n\nFormatted repository and runtime info'
+    assert result.content[0].text == 'Formatted repository and runtime info'
 
     # Verify the prompt_manager was called with the correct parameters
     conversation_memory.prompt_manager.build_workspace_context.assert_called_once()
@@ -737,18 +516,14 @@ def test_process_events_with_knowledge_microagent_microagent_observation(
         content='Retrieved knowledge from microagents',
     )
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
-    assert len(messages) == 3  # System + Initial User + Result
-    result = messages[2]  # Result is now at index 2
+    assert len(messages) == 2
+    result = messages[1]
     assert result.role == 'user'
     assert len(result.content) == 1
     assert isinstance(result.content[0], TextContent)
@@ -784,18 +559,14 @@ def test_process_events_with_microagent_observation_extensions_disabled(
         content='Retrieved environment info',
     )
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
     # When prompt extensions are disabled, the RecallObservation should be ignored
-    assert len(messages) == 2  # System + Initial User
+    assert len(messages) == 1  # should be no messages except system message
 
     # Verify the prompt_manager was not called
     conversation_memory.prompt_manager.build_workspace_context.assert_not_called()
@@ -810,18 +581,14 @@ def test_process_events_with_empty_microagent_knowledge(conversation_memory):
         content='Retrieved knowledge from microagents',
     )
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
     # The implementation returns an empty string and it doesn't creates a message
-    assert len(messages) == 2  # System + Initial User
+    assert len(messages) == 1  # should be no messages except system message
 
     # When there are no triggered agents, build_microagent_info is not called
     conversation_memory.prompt_manager.build_microagent_info.assert_not_called()
@@ -1026,23 +793,19 @@ def test_process_events_with_microagent_observation_deduplication(conversation_m
         content='Third retrieval',
     )
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs1, obs2, obs3],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
     # Verify that only the first occurrence of content for each agent is included
-    assert len(messages) == 3  # System + Initial User + Result
-    # Result is now at index 2
+    assert len(messages) == 2  # with system message
+
     # First microagent should include all agents since they appear here first
-    assert 'Image best practices v1' in messages[2].content[0].text
-    assert 'Git best practices v1' in messages[2].content[0].text
-    assert 'Python best practices v1' in messages[2].content[0].text
+    assert 'Image best practices v1' in messages[1].content[0].text
+    assert 'Git best practices v1' in messages[1].content[0].text
+    assert 'Python best practices v1' in messages[1].content[0].text
 
 
 def test_process_events_with_microagent_observation_deduplication_disabled_agents(
@@ -1079,22 +842,18 @@ def test_process_events_with_microagent_observation_deduplication_disabled_agent
         content='Second retrieval',
     )
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs1, obs2],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
     # Verify that disabled agents are filtered out and only the first occurrence of enabled agents is included
-    assert len(messages) == 3  # System + Initial User + Result
-    # Result is now at index 2
+    assert len(messages) == 2
+
     # First microagent should include enabled_agent but not disabled_agent
-    assert 'Disabled agent content' not in messages[2].content[0].text
-    assert 'Enabled agent content v1' in messages[2].content[0].text
+    assert 'Disabled agent content' not in messages[1].content[0].text
+    assert 'Enabled agent content v1' in messages[1].content[0].text
 
 
 def test_process_events_with_microagent_observation_deduplication_empty(
@@ -1107,22 +866,17 @@ def test_process_events_with_microagent_observation_deduplication_empty(
         content='Empty retrieval',
     )
 
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[obs],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
     # Verify that empty RecallObservations are handled gracefully
     assert (
-        len(messages) == 2  # System + Initial User
-    )  # an empty microagent is not added to Messages
+        len(messages) == 1
+    )  # an empty microagent is not added to Messages, only system message is found
     assert messages[0].role == 'system'
-    assert messages[1].role == 'user'  # Initial user message
 
 
 def test_has_agent_in_earlier_events(conversation_memory):
@@ -1334,183 +1088,13 @@ def test_system_message_in_events(conversation_memory):
     system_message._source = EventSource.AGENT
 
     # Process events with the system message in condensed_history
-    # Define initial user action
-    initial_user_action = MessageAction(content='Initial user message')
-    initial_user_action._source = EventSource.USER
     messages = conversation_memory.process_events(
         condensed_history=[system_message],
-        initial_user_action=initial_user_action,
         max_message_chars=None,
         vision_is_active=False,
     )
 
     # Check that the system message was processed correctly
-    assert len(messages) == 2  # System + Initial User
+    assert len(messages) == 1
     assert messages[0].role == 'system'
     assert messages[0].content[0].text == 'System message'
-    assert messages[1].role == 'user'  # Initial user message
-
-
-# Helper function to create mock tool call metadata
-def _create_mock_tool_call_metadata(
-    tool_call_id: str, function_name: str, response_id: str = 'mock_response_id'
-) -> ToolCallMetadata:
-    # Use a dictionary that mimics ModelResponse structure to satisfy Pydantic
-    mock_response = {
-        'id': response_id,
-        'choices': [
-            {
-                'message': {
-                    'role': 'assistant',
-                    'content': None,  # Content is None for tool calls
-                    'tool_calls': [
-                        {
-                            'id': tool_call_id,
-                            'type': 'function',
-                            'function': {
-                                'name': function_name,
-                                'arguments': '{}',
-                            },  # Args don't matter for this test
-                        }
-                    ],
-                }
-            }
-        ],
-        'created': 0,
-        'model': 'mock_model',
-        'object': 'chat.completion',
-        'usage': {'completion_tokens': 0, 'prompt_tokens': 0, 'total_tokens': 0},
-    }
-    return ToolCallMetadata(
-        tool_call_id=tool_call_id,
-        function_name=function_name,
-        model_response=mock_response,
-        total_calls_in_response=1,
-    )
-
-
-def test_process_events_partial_history(conversation_memory):
-    """
-    Tests process_events with full and partial histories to verify
-    _ensure_system_message, _ensure_initial_user_message, and tool call matching logic.
-    """
-    # --- Define Common Events ---
-    system_message = SystemMessageAction(content='System message')
-    system_message._source = EventSource.AGENT
-
-    user_message = MessageAction(
-        content='Initial user query'
-    )  # This is the crucial initial_user_action
-    user_message._source = EventSource.USER
-
-    recall_obs = RecallObservation(
-        recall_type=RecallType.WORKSPACE_CONTEXT,
-        repo_name='test-repo',
-        repo_directory='/path/to/repo',
-        content='Retrieved environment info',
-    )
-    recall_obs._source = EventSource.AGENT
-
-    cmd_action = CmdRunAction(command='ls', thought='Running ls')
-    cmd_action._source = EventSource.AGENT
-    cmd_action.tool_call_metadata = _create_mock_tool_call_metadata(
-        tool_call_id='call_ls_1', function_name='execute_bash', response_id='resp_ls_1'
-    )
-
-    cmd_obs = CmdOutputObservation(
-        command_id=1, command='ls', content='file1.txt\nfile2.py', exit_code=0
-    )
-    cmd_obs._source = EventSource.AGENT
-    cmd_obs.tool_call_metadata = _create_mock_tool_call_metadata(
-        tool_call_id='call_ls_1', function_name='execute_bash', response_id='resp_ls_1'
-    )
-
-    # --- Scenario 1: Full History ---
-    full_history: list[Event] = [
-        system_message,
-        user_message,  # Correct initial user message at index 1
-        recall_obs,
-        cmd_action,
-        cmd_obs,
-    ]
-    messages_full = conversation_memory.process_events(
-        condensed_history=list(full_history),  # Pass a copy
-        initial_user_action=user_message,  # Provide the initial action
-        max_message_chars=None,
-        vision_is_active=False,
-    )
-
-    # Expected: System, User, Recall (formatted), Assistant (tool call), Tool Response
-    assert len(messages_full) == 5
-    assert messages_full[0].role == 'system'
-    assert messages_full[0].content[0].text == 'System message'
-    assert messages_full[1].role == 'user'
-    assert messages_full[1].content[0].text == 'Initial user query'
-    assert messages_full[2].role == 'user'  # Recall obs becomes user message
-    assert (
-        'Formatted repository and runtime info' in messages_full[2].content[0].text
-    )  # From fixture mock
-    assert messages_full[3].role == 'assistant'
-    assert messages_full[3].tool_calls is not None
-    assert len(messages_full[3].tool_calls) == 1
-    assert messages_full[3].tool_calls[0].id == 'call_ls_1'
-    assert messages_full[4].role == 'tool'
-    assert messages_full[4].tool_call_id == 'call_ls_1'
-    assert 'file1.txt' in messages_full[4].content[0].text
-
-    # --- Scenario 2: Partial History (Action + Observation) ---
-    # Simulates processing only the last action/observation pair
-    partial_history_action_obs: list[Event] = [
-        cmd_action,
-        cmd_obs,
-    ]
-    messages_partial_action_obs = conversation_memory.process_events(
-        condensed_history=list(partial_history_action_obs),  # Pass a copy
-        initial_user_action=user_message,  # Provide the initial action
-        max_message_chars=None,
-        vision_is_active=False,
-    )
-
-    # Expected: System (added), Initial User (added), Assistant (tool call), Tool Response
-    assert len(messages_partial_action_obs) == 4
-    assert (
-        messages_partial_action_obs[0].role == 'system'
-    )  # Added by _ensure_system_message
-    assert messages_partial_action_obs[0].content[0].text == 'System message'
-    assert (
-        messages_partial_action_obs[1].role == 'user'
-    )  # Added by _ensure_initial_user_message
-    assert messages_partial_action_obs[1].content[0].text == 'Initial user query'
-    assert messages_partial_action_obs[2].role == 'assistant'
-    assert messages_partial_action_obs[2].tool_calls is not None
-    assert len(messages_partial_action_obs[2].tool_calls) == 1
-    assert messages_partial_action_obs[2].tool_calls[0].id == 'call_ls_1'
-    assert messages_partial_action_obs[3].role == 'tool'
-    assert messages_partial_action_obs[3].tool_call_id == 'call_ls_1'
-    assert 'file1.txt' in messages_partial_action_obs[3].content[0].text
-
-    # --- Scenario 3: Partial History (Observation Only) ---
-    # Simulates processing only the last observation
-    partial_history_obs_only: list[Event] = [
-        cmd_obs,
-    ]
-    messages_partial_obs_only = conversation_memory.process_events(
-        condensed_history=list(partial_history_obs_only),  # Pass a copy
-        initial_user_action=user_message,  # Provide the initial action
-        max_message_chars=None,
-        vision_is_active=False,
-    )
-
-    # Expected: System (added), Initial User (added).
-    # The CmdOutputObservation has tool_call_metadata, but there's no corresponding
-    # assistant message (from CmdRunAction) with the matching tool_call.id in the input history.
-    # Therefore, _filter_unmatched_tool_calls should remove the tool response message.
-    assert len(messages_partial_obs_only) == 2
-    assert (
-        messages_partial_obs_only[0].role == 'system'
-    )  # Added by _ensure_system_message
-    assert messages_partial_obs_only[0].content[0].text == 'System message'
-    assert (
-        messages_partial_obs_only[1].role == 'user'
-    )  # Added by _ensure_initial_user_message
-    assert messages_partial_obs_only[1].content[0].text == 'Initial user query'

tests/unit/test_prompt_caching.py

@@ -76,7 +76,7 @@ def test_get_messages(codeact_agent: CodeActAgent):
     history.append(message_action_5)
 
     codeact_agent.reset()
-    messages = codeact_agent._get_messages(history, message_action_1)
+    messages = codeact_agent._get_messages(history)
 
     assert (
         len(messages) == 6
@@ -106,19 +106,16 @@ def test_get_messages_prompt_caching(codeact_agent: CodeActAgent):
     history.append(system_message_action)
 
     # Add multiple user and agent messages
-    initial_user_message = None  # Keep track of the first user message
     for i in range(15):
         message_action_user = MessageAction(f'User message {i}')
         message_action_user._source = 'user'
-        if initial_user_message is None:
-            initial_user_message = message_action_user  # Store the first one
         history.append(message_action_user)
         message_action_agent = MessageAction(f'Agent message {i}')
         message_action_agent._source = 'agent'
         history.append(message_action_agent)
 
     codeact_agent.reset()
-    messages = codeact_agent._get_messages(history, initial_user_message)
+    messages = codeact_agent._get_messages(history)
 
     # Check that only the last two user messages have cache_prompt=True
     cached_user_messages = [