Merge branch 'OpenDevin:main' into kevin

.github/workflows/dummy-agent-test.yml

@@ -25,7 +25,7 @@ jobs:
       - name: Set up environment
         run: |
           curl -sSL https://install.python-poetry.org | python3 -
-          poetry install --without evaluation
+          poetry install --without evaluation,llama-index
           poetry run playwright install --with-deps chromium
           wget https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/1_Pooling/config.json -P /tmp/llama_index/models--BAAI--bge-small-en-v1.5/snapshots/5c38ec7c405ec4b44b94cc5a9bb96e735b38267a/1_Pooling/
       - name: Run tests

.github/workflows/review-pr.yml

@@ -50,7 +50,7 @@ jobs:
       run: |
         curl -sSL https://install.python-poetry.org | python3 -
         export PATH="/github/home/.local/bin:$PATH"
-        poetry install --without evaluation
+        poetry install --without evaluation,llama-index
         poetry run playwright install --with-deps chromium
 
     - name: Run OpenDevin

.github/workflows/run-unit-tests.yml

@@ -70,7 +70,7 @@ jobs:
           cache: "poetry"
 
       - name: Install Python dependencies using Poetry
-        run: poetry install
+        run: poetry install --without evaluation,llama-index
 
       - name: Install & Start Docker
         if: env.INSTALL_DOCKER == '1'
@@ -153,7 +153,7 @@ jobs:
           cache: "poetry"
 
       - name: Install Python dependencies using Poetry
-        run: poetry install --without evaluation
+        run: poetry install --without evaluation,llama-index
 
       - name: Build Environment
         run: make build

.github/workflows/solve-issue.yml

@@ -40,7 +40,7 @@ jobs:
       run: |
         curl -sSL https://install.python-poetry.org | python3 -
         export PATH="/github/home/.local/bin:$PATH"
-        poetry install --without evaluation
+        poetry install --without evaluation,llama-index
         poetry run playwright install --with-deps chromium
 
 

Makefile

@@ -141,7 +141,7 @@ install-python-dependencies:
 		export HNSWLIB_NO_NATIVE=1; \
 		poetry run pip install chroma-hnswlib; \
 	fi
-	@poetry install
+	@poetry install --without llama-index
 	@if [ -f "/etc/manjaro-release" ]; then \
 		echo "$(BLUE)Detected Manjaro Linux. Installing Playwright dependencies...$(RESET)"; \
 		poetry run pip install playwright; \

containers/app/Dockerfile

@@ -26,7 +26,7 @@ RUN apt-get update -y \
 
 COPY ./pyproject.toml ./poetry.lock ./
 RUN touch README.md
-RUN export POETRY_CACHE_DIR && poetry install --without evaluation --no-root && rm -rf $POETRY_CACHE_DIR
+RUN export POETRY_CACHE_DIR && poetry install --without evaluation,llama-index --no-root && rm -rf $POETRY_CACHE_DIR
 
 FROM python:3.12.3-slim AS runtime
 

docs/modules/usage/custom_sandbox_guide.md

@@ -4,22 +4,35 @@ sidebar_position: 6
 
 # 💿 How to Create and Use a Custom Docker Sandbox
 
-The default OpenDevin sandbox comes with a [minimal ubuntu configuration](https://github.com/OpenDevin/OpenDevin/blob/main/containers/sandbox/Dockerfile). 
+The default OpenDevin sandbox comes with a [minimal ubuntu configuration](https://github.com/OpenDevin/OpenDevin/blob/main/containers/sandbox/Dockerfile).
 
 Your use case may need additional software installed by default.
 
 There are two ways you can do so:
+
 1. Use an existing image from docker hub. For instance, if you want to have `nodejs` installed, you can do so by using the `node:20` image
 2. Creating your own custom docker image and using it
 
 If you want to take the first approach, you can skip the `Create Your Docker Image` section.
 
+For a more feature-rich environment, you might consider using pre-built images like **[nikolaik/python-nodejs](https://hub.docker.com/r/nikolaik/python-nodejs)**, which comes with both Python and Node.js pre-installed, along with many other useful tools and libraries, like:
+
+- Node.js: 22.x
+- npm: 10.x
+- yarn: stable
+- Python: latest
+- pip: latest
+- pipenv: latest
+- poetry: latest
+- uv: latest
+
 ## Setup
 
 Make sure you are able to run OpenDevin using the [Development.md](https://github.com/OpenDevin/OpenDevin/blob/main/Development.md) first.
 
 ## Create Your Docker Image
-To create a custom docker image, it must be debian/ubuntu based. 
+
+To create a custom docker image, it must be debian/ubuntu based.
 
 For example, if we want OpenDevin to have access to the `node` binary, we would use the following Dockerfile:
 
@@ -34,7 +47,7 @@ RUN apt-get update && apt-get install -y
 RUN apt-get install -y nodejs
 ```
 
-Next build your docker image with the name of your choice, for example `custom_image`. 
+Next build your docker image with the name of your choice, for example `custom_image`.
 
 To do this you can create a directory and put your file inside it with the name `Dockerfile`, and inside the directory run the following command:
 
@@ -50,7 +63,7 @@ This will produce a new image called ```custom_image``` that will be available i
 
 ## Specify your sandbox image in config.toml file
 
-OpenDevin configuration occurs via the top-level `config.toml` file. 
+OpenDevin configuration occurs via the top-level `config.toml` file.
 
 Create a `config.toml` file in the OpenDevin directory and enter these contents:
 
@@ -63,6 +76,7 @@ sandbox_container_image="custom_image"
 ```
 
 For `sandbox_container_image`, you can specify either:
+
 1. The name of your custom image that you built in the previous step (e.g., `”custom_image”`)
 2. A pre-existing image from Docker Hub (e.g., `”node:20”` if you want a sandbox with Node.js pre-installed)
 
@@ -79,7 +93,7 @@ Congratulations!
 
 The relevant code is defined in [ssh_box.py](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/ssh_box.py) and [image_agnostic_util.py](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py).
 
-In particular, ssh_box.py checks the config object for ```config.sandbox_container_image``` and then attempts to retrieve the image using [get_od_sandbox_image](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L72) which is defined in image_agnostic_util.py.
+In particular, `ssh_box.py` checks the config object for ```config.sandbox_container_image``` and then attempts to retrieve the image using [get_od_sandbox_image](https://github.com/OpenDevin/OpenDevin/blob/main/opendevin/runtime/docker/image_agnostic_util.py#L72) which is defined in image_agnostic_util.py.
 
 When first using a custom image, it will not be found and thus it will be built (on subsequent runs the built image will be found and returned).
 
@@ -109,6 +123,7 @@ dockerfile_content = (
 ## Troubleshooting / Errors
 
 ### Error: ```useradd: UID 1000 is not unique```
+
 If you see this error in the console output it is because OpenDevin is trying to create the opendevin user in the sandbox with a UID of 1000, however this UID is already being used in the image (for some reason). To fix this change the sandbox_user_id field in the config.toml file to a different value:
 
 ```toml
@@ -122,7 +137,7 @@ sandbox_user_id="1001"
 
 ### Port use errors
 
-If you see an error about a port being in use or unavailable, try deleting all running Docker Containers (run `docker ps` and `docker rm` relevant containers) and then re-running ```make run```
+If you see an error about a port being in use or unavailable, try deleting all running Docker Containers (run `docker ps` and `docker rm` relevant containers) and then re-running ```make run``` .
 
 ## Discuss
 

evaluation/miniwob/run_infer.py

@@ -33,7 +33,14 @@
 def get_sandbox():
     global docker_ssh_box
     if docker_ssh_box is None:
-        docker_ssh_box = DockerSSHBox()
+        docker_ssh_box = DockerSSHBox(
+            config=config.sandbox,
+            persist_sandbox=False,
+            workspace_mount_path=config.workspace_mount_path,
+            sandbox_workspace_dir=config.workspace_mount_path_in_sandbox,
+            cache_dir=config.cache_dir,
+            run_as_devin=config.run_as_devin,
+        )
     return docker_ssh_box
 
 

evaluation/swe_bench/run_infer.py

@@ -211,6 +211,7 @@ def process_instance(
     # You can omit this if you don't need to setup specialized sandbox
     workspace_dir_name = f'{instance.repo}__{instance.version}'.replace('/', '__')
     sandbox = SWEBenchSSHBox.get_box_for_instance(
+        config,
         instance,
         workspace_dir_name,
         workspace_mount_path=workspace_mount_path,

evaluation/swe_bench/swe_env_box.py

@@ -146,8 +146,8 @@ def volumes(self):
     @classmethod
     def get_box_for_instance(
         cls,
-        instance,
         config: AppConfig,
+        instance,
         workspace_dir_name=None,
         skip_workspace_mount: bool = True,
         workspace_mount_path: str | None = None,

frontend/src/components/modals/settings/SettingsForm.test.tsx

@@ -52,7 +52,7 @@ describe("SettingsForm", () => {
     expect(confirmationModeInput).toHaveAttribute("data-selected", "true");
   });
 
-  it("should display the existing values if it they are present", () => {
+  it("should display the existing values if they are present", () => {
     renderSettingsForm({
       LLM_MODEL: "model2",
       AGENT: "agent2",
@@ -119,17 +119,18 @@ describe("SettingsForm", () => {
     });
 
     it("should call the onAgentChange handler when the agent changes", async () => {
+      const user = userEvent.setup();
       renderSettingsForm();
 
+      // We need to enable the agent select
+      const agentSwitch = screen.getByTestId("enableagentselect");
+      await user.click(agentSwitch);
+
       const agentInput = screen.getByRole("combobox", { name: "agent" });
-      await act(async () => {
-        await userEvent.click(agentInput);
-      });
+      await user.click(agentInput);
 
       const agent3 = screen.getByText("agent3");
-      await act(async () => {
-        await userEvent.click(agent3);
-      });
+      await user.click(agent3);
 
       expect(onAgentChangeMock).toHaveBeenCalledWith("agent3");
     });

frontend/src/components/modals/settings/SettingsForm.tsx

@@ -33,17 +33,10 @@ function SettingsForm({
 }: SettingsFormProps) {
   const { t } = useTranslation();
   const { isOpen: isVisible, onOpenChange: onVisibleChange } = useDisclosure();
+  const [isAgentSelectEnabled, setIsAgentSelectEnabled] = React.useState(false);
 
   return (
     <>
-      <AutocompleteCombobox
-        ariaLabel="agent"
-        items={agents.map((agent) => ({ value: agent, label: agent }))}
-        defaultKey={settings.AGENT}
-        onChange={onAgentChange}
-        tooltip={t(I18nKey.SETTINGS$AGENT_TOOLTIP)}
-        disabled={disabled}
-      />
       <AutocompleteCombobox
         ariaLabel="model"
         items={models.map((model) => ({ value: model, label: model }))}
@@ -88,6 +81,23 @@ function SettingsForm({
         tooltip={t(I18nKey.SETTINGS$LANGUAGE_TOOLTIP)}
         disabled={disabled}
       />
+      <AutocompleteCombobox
+        ariaLabel="agent"
+        items={agents.map((agent) => ({ value: agent, label: agent }))}
+        defaultKey={settings.AGENT}
+        onChange={onAgentChange}
+        tooltip={t(I18nKey.SETTINGS$AGENT_TOOLTIP)}
+        disabled={disabled || !isAgentSelectEnabled}
+      />
+      <Switch
+        defaultSelected={false}
+        isSelected={isAgentSelectEnabled}
+        onValueChange={setIsAgentSelectEnabled}
+        aria-label="enableagentselect"
+        data-testid="enableagentselect"
+      >
+        {t(I18nKey.SETTINGS$AGENT_SELECT_ENABLED)}
+      </Switch>
       <Switch
         aria-label="confirmationmode"
         data-testid="confirmationmode"

frontend/src/components/modals/settings/SettingsModal.test.tsx

@@ -231,6 +231,10 @@ describe("SettingsModal", () => {
       ),
     );
 
+    // We need to enable the agent select first
+    const agentSwitch = screen.getByTestId("enableagentselect");
+    await user.click(agentSwitch);
+
     const resetButton = screen.getByRole("button", {
       name: /MODAL_RESET_BUTTON_LABEL/i,
     });

frontend/src/i18n/translation.json

@@ -721,6 +721,9 @@
     "de": "Wartet auf die Bestätigung des Benutzers, bevor der Code ausgeführt wird.",
     "zh-CN": "在执行代码之前等待用户确认。"
   },
+  "SETTINGS$AGENT_SELECT_ENABLED": {
+    "en": "Enable Agent Selection - Advanced Users"
+  },
   "BROWSER$EMPTY_MESSAGE": {
     "en": "No page loaded.",
     "zh-CN": "页面未加载",

opendevin/events/observation/__init__.py

@@ -6,7 +6,7 @@
 from .error import ErrorObservation
 from .files import FileReadObservation, FileWriteObservation
 from .observation import Observation
-from .reject import RejectObservation
+from .reject import UserRejectObservation
 from .success import SuccessObservation
 
 __all__ = [
@@ -21,5 +21,5 @@
     'AgentStateChangedObservation',
     'AgentDelegateObservation',
     'SuccessObservation',
-    'RejectObservation',
+    'UserRejectObservation',
 ]

opendevin/events/observation/reject.py

@@ -6,7 +6,7 @@
 
 
 @dataclass
-class RejectObservation(Observation):
+class UserRejectObservation(Observation):
     """This data class represents the result of a successful action."""
 
     observation: str = ObservationType.USER_REJECTED

opendevin/events/serialization/observation.py

@@ -9,7 +9,7 @@
 from opendevin.events.observation.error import ErrorObservation
 from opendevin.events.observation.files import FileReadObservation, FileWriteObservation
 from opendevin.events.observation.observation import Observation
-from opendevin.events.observation.reject import RejectObservation
+from opendevin.events.observation.reject import UserRejectObservation
 from opendevin.events.observation.success import SuccessObservation
 
 observations = (
@@ -23,7 +23,7 @@
     SuccessObservation,
     ErrorObservation,
     AgentStateChangedObservation,
-    RejectObservation,
+    UserRejectObservation,
 )
 
 OBSERVATION_TYPE_TO_CLASS = {