Merge remote-tracking branch 'upstream/main'

.github/workflows/ghcr-build.yml

@@ -399,3 +399,49 @@ jobs:
         run: |
           echo "Some runtime tests failed or were cancelled"
           exit 1
+  update_pr_description:
+    name: Update PR Description
+    if: github.event_name == 'pull_request' && !github.event.pull_request.head.repo.fork
+    needs: [ghcr_build_runtime]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Get short SHA
+        id: short_sha
+        run: echo "SHORT_SHA=$(echo ${{ github.event.pull_request.head.sha }} | cut -c1-7)" >> $GITHUB_OUTPUT
+
+      - name: Update PR Description
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+          REPO: ${{ github.repository }}
+          SHORT_SHA: ${{ steps.short_sha.outputs.SHORT_SHA }}
+        run: |
+          echo "updating PR description"
+          DOCKER_RUN_COMMAND="docker run -it --rm \
+            -p 3000:3000 \
+            -v /var/run/docker.sock:/var/run/docker.sock \
+            --add-host host.docker.internal:host-gateway \
+            -e SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:$SHORT_SHA-nikolaik \
+            --name openhands-app-$SHORT_SHA \
+            ghcr.io/all-hands-ai/runtime:$SHORT_SHA"
+
+          PR_BODY=$(gh pr view $PR_NUMBER --json body --jq .body)
+
+          if echo "$PR_BODY" | grep -q "To run this PR locally, use the following command:"; then
+            UPDATED_PR_BODY=$(echo "${PR_BODY}" | sed -E "s|docker run -it --rm.*|$DOCKER_RUN_COMMAND|")
+          else
+            UPDATED_PR_BODY="${PR_BODY}
+
+          ---
+
+          To run this PR locally, use the following command:
+          \`\`\`
+          $DOCKER_RUN_COMMAND
+          \`\`\`"
+          fi
+
+          echo "updated body: $UPDATED_PR_BODY"
+          gh pr edit $PR_NUMBER --body "$UPDATED_PR_BODY"

README.md

@@ -33,28 +33,26 @@ Learn more at [docs.all-hands.dev](https://docs.all-hands.dev), or jump to the [
 
 ## ⚡ Quick Start
 
-The easiest way to run OpenHands is in Docker. You can change `WORKSPACE_BASE` below to
-point OpenHands to existing code that you'd like to modify.
-
+The easiest way to run OpenHands is in Docker.
 See the [Installation](https://docs.all-hands.dev/modules/usage/installation) guide for
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.11-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.11-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik \
     -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:0.11
+    docker.all-hands.dev/all-hands-ai/openhands:0.12
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
 
-You'll need a model provider and API key.
-[Anthropic's Claude 3.5 Sonnet (`anthropic/claude-3-5-sonnet-20241022`)](https://www.anthropic.com/api)
+Finally, you'll need a model provider and API key.
+[Anthropic's Claude 3.5 Sonnet](https://www.anthropic.com/api) (`anthropic/claude-3-5-sonnet-20241022`)
 works best, but you have [many options](https://docs.all-hands.dev/modules/usage/llms).
 
 ---

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

@@ -50,6 +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:0.12-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -58,7 +59,7 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.11 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.12 \
     python -m openhands.core.cli
 ```
 
@@ -107,4 +108,3 @@ Expected Output:
 ```bash
 🤖 An error occurred. Please try again.
 ```
-

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

@@ -44,6 +44,7 @@ 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:0.12-nikolaik \
     -e SANDBOX_USER_ID=$(id -u) \
     -e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
     -e LLM_API_KEY=$LLM_API_KEY \
@@ -52,7 +53,6 @@ docker run -it \
     -v /var/run/docker.sock:/var/run/docker.sock \
     --add-host host.docker.internal:host-gateway \
     --name openhands-app-$(date +%Y%m%d%H%M%S) \
-    docker.all-hands.dev/all-hands-ai/openhands:0.11 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.12 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
-

docs/modules/usage/installation.mdx

@@ -11,15 +11,15 @@
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.11-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.11-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.12-nikolaik \
     -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:0.11
+    docker.all-hands.dev/all-hands-ai/openhands:0.12
 ```
 
 You can also run OpenHands in a scriptable [headless mode](https://docs.all-hands.dev/modules/usage/how-to/headless-mode), as an [interactive CLI](https://docs.all-hands.dev/modules/usage/how-to/cli-mode), or using the [OpenHands GitHub Action](https://docs.all-hands.dev/modules/usage/how-to/github-action).

evaluation/swe_bench/eval_infer.py

@@ -239,7 +239,7 @@ def process_instance(
                         # Create a directory structure that matches the expected format
                         # NOTE: this is a hack to make the eval report format consistent
                         # with the original SWE-Bench eval script
-                        log_dir = os.path.join(temp_dir, 'logs', instance_id)
+                        log_dir = os.path.join(temp_dir, 'logs', instance_id.lower())
                         os.makedirs(log_dir, exist_ok=True)
                         test_output_path = os.path.join(log_dir, 'test_output.txt')
                         with open(test_output_path, 'w') as f:

evaluation/swe_bench/run_infer.py

@@ -101,7 +101,7 @@ def get_instance_docker_image(instance_id: str) -> str:
     image_name = image_name.replace(
         '__', '_s_'
     )  # to comply with docker image naming convention
-    return DOCKER_IMAGE_PREFIX.rstrip('/') + '/' + image_name
+    return (DOCKER_IMAGE_PREFIX.rstrip('/') + '/' + image_name).lower()
 
 
 def get_config(

frontend/__tests__/components/feedback-form.test.tsx

@@ -5,15 +5,14 @@ import { FeedbackForm } from "#/components/feedback-form";
 
 describe("FeedbackForm", () => {
   const user = userEvent.setup();
-  const onSubmitMock = vi.fn();
   const onCloseMock = vi.fn();
 
   afterEach(() => {
     vi.clearAllMocks();
   });
 
   it("should render correctly", () => {
-    render(<FeedbackForm onSubmit={onSubmitMock} onClose={onCloseMock} />);
+    render(<FeedbackForm polarity="positive" onClose={onCloseMock} />);
 
     screen.getByLabelText("Email");
     screen.getByLabelText("Private");
@@ -24,7 +23,7 @@ describe("FeedbackForm", () => {
   });
 
   it("should switch between private and public permissions", async () => {
-    render(<FeedbackForm onSubmit={onSubmitMock} onClose={onCloseMock} />);
+    render(<FeedbackForm polarity="positive" onClose={onCloseMock} />);
     const privateRadio = screen.getByLabelText("Private");
     const publicRadio = screen.getByLabelText("Public");
 
@@ -40,69 +39,11 @@ describe("FeedbackForm", () => {
     expect(publicRadio).not.toBeChecked();
   });
 
-  it("should call onSubmit when the form is submitted", async () => {
-    render(<FeedbackForm onSubmit={onSubmitMock} onClose={onCloseMock} />);
-    const email = screen.getByLabelText("Email");
-
-    await user.type(email, "[email protected]");
-    await user.click(screen.getByRole("button", { name: "Submit" }));
-
-    expect(onSubmitMock).toHaveBeenCalledWith("private", "[email protected]"); // private is the default value
-  });
-
-  it("should not call onSubmit when the email is invalid", async () => {
-    render(<FeedbackForm onSubmit={onSubmitMock} onClose={onCloseMock} />);
-    const email = screen.getByLabelText("Email");
-    const submitButton = screen.getByRole("button", { name: "Submit" });
-
-    await user.click(submitButton);
-
-    expect(onSubmitMock).not.toHaveBeenCalled();
-
-    await user.type(email, "test");
-    await user.click(submitButton);
-
-    expect(onSubmitMock).not.toHaveBeenCalled();
-  });
-
-  it("should submit public permissions when the public radio is checked", async () => {
-    render(<FeedbackForm onSubmit={onSubmitMock} onClose={onCloseMock} />);
-    const email = screen.getByLabelText("Email");
-    const publicRadio = screen.getByLabelText("Public");
-
-    await user.type(email, "[email protected]");
-    await user.click(publicRadio);
-    await user.click(screen.getByRole("button", { name: "Submit" }));
-
-    expect(onSubmitMock).toHaveBeenCalledWith("public", "[email protected]");
-  });
-
   it("should call onClose when the close button is clicked", async () => {
-    render(<FeedbackForm onSubmit={onSubmitMock} onClose={onCloseMock} />);
+    render(<FeedbackForm polarity="positive" onClose={onCloseMock} />);
     await user.click(screen.getByRole("button", { name: "Cancel" }));
 
-    expect(onSubmitMock).not.toHaveBeenCalled();
     expect(onCloseMock).toHaveBeenCalled();
   });
 
-  it("should disable the buttons if isSubmitting is true", () => {
-    const { rerender } = render(
-      <FeedbackForm onSubmit={onSubmitMock} onClose={onCloseMock} />,
-    );
-    const submitButton = screen.getByRole("button", { name: "Submit" });
-    const cancelButton = screen.getByRole("button", { name: "Cancel" });
-
-    expect(submitButton).not.toBeDisabled();
-    expect(cancelButton).not.toBeDisabled();
-
-    rerender(
-      <FeedbackForm
-        onSubmit={onSubmitMock}
-        onClose={onCloseMock}
-        isSubmitting
-      />,
-    );
-    expect(submitButton).toBeDisabled();
-    expect(cancelButton).toBeDisabled();
-  });
 });

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openhands-frontend",
-  "version": "0.11.0",
+  "version": "0.12.0",
   "private": true,
   "type": "module",
   "engines": {

frontend/src/api/open-hands.types.ts

@@ -31,7 +31,7 @@ export interface Feedback {
   version: string;
   email: string;
   token: string;
-  feedback: "positive" | "negative";
+  polarity: "positive" | "negative";
   permissions: "public" | "private";
   trajectory: unknown[];
 }