docker related

system message update
update system message
2026-04-29 03:00:45 -04:00 · 2025-02-27 18:48:15 -05:00 · 2025-02-27 18:43:10 -05:00 · 2025-02-27 18:39:11 -05:00 · 2025-02-27 22:02:33 +00:00 · 2025-02-28 05:47:39 +08:00
192 changed files with 7016 additions and 3909 deletions
--- a/.github/workflows/ghcr-build.yml
+++ b/.github/workflows/ghcr-build.yml
@@ -54,22 +54,22 @@ jobs:
      - name: Set up Docker Buildx
        id: buildx
        uses: docker/setup-buildx-action@v3
+      - name: Lowercase Repository Owner
+        run: |
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
      - name: Build and push app image
        if: "!github.event.pull_request.head.repo.fork"
        run: |
-          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --push
+          ./containers/build.sh -i openhands -o ${{ env.REPO_OWNER }} --push
      - name: Build app image
        if: "github.event.pull_request.head.repo.fork"
        run: |
-          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --load
+          ./containers/build.sh -i openhands -o ${{ env.REPO_OWNER }} --load
      - name: Get hash in App Image
        id: get_hash_in_app_image
        run: |
-          # Lowercase the repository owner
-          export REPO_OWNER=${{ github.repository_owner }}
-          REPO_OWNER=$(echo $REPO_OWNER | tr '[:upper:]' '[:lower:]')
          # Run the build script in the app image
-          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${REPO_OWNER}/openhands:${{ env.RELEVANT_SHA }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
+          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${{ env.REPO_OWNER }}/openhands:${{ env.RELEVANT_SHA }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
          # Get the hash from the build script
          hash_from_app_image=$(cat docker-outputs.txt | grep "Hash for docker build directory" | awk -F "): " '{print $2}' | uniq | head -n1)
          echo "hash_from_app_image=$hash_from_app_image" >> $GITHUB_OUTPUT
@@ -122,16 +122,19 @@ jobs:
        run: make install-python-dependencies
      - name: Create source distribution and Dockerfile
        run: poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image.image }} --build_folder containers/runtime --force_rebuild
+      - name: Lowercase Repository Owner
+        run: |
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
      - name: Build and push runtime image ${{ matrix.base_image.image }}
        if: github.event.pull_request.head.repo.fork != true
        run: |
-          ./containers/build.sh -i runtime -o ${{ github.repository_owner }} --push -t ${{ matrix.base_image.tag }}
+          ./containers/build.sh -i runtime -o ${{ env.REPO_OWNER }} --push -t ${{ matrix.base_image.tag }}
      # Forked repos can't push to GHCR, so we need to upload the image as an artifact
      - name: Build runtime image ${{ matrix.base_image.image }} for fork
        if: github.event.pull_request.head.repo.fork
        uses: docker/build-push-action@v6
        with:
-          tags: ghcr.io/all-hands-ai/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
          outputs: type=docker,dest=/tmp/runtime-${{ matrix.base_image.tag }}.tar
          context: containers/runtime
      - name: Upload runtime image for fork
@@ -233,6 +236,9 @@ jobs:
        run: pipx install poetry
      - name: Install Python dependencies using Poetry
        run: make install-python-dependencies
+      - name: Lowercase Repository Owner
+        run: |
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
      - name: Run docker runtime tests
        run: |
          # We install pytest-xdist in order to run tests across CPUs
@@ -241,8 +247,7 @@ jobs:
          # Install to be able to retry on failures for flaky tests
          poetry run pip install pytest-rerunfailures

-          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
-          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
+          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}

          TEST_RUNTIME=docker \
          SANDBOX_USER_ID=$(id -u) \
@@ -296,6 +301,9 @@ jobs:
        run: pipx install poetry
      - name: Install Python dependencies using Poetry
        run: make install-python-dependencies
+      - name: Lowercase Repository Owner
+        run: |
+          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
      - name: Run runtime tests
        run: |
          # We install pytest-xdist in order to run tests across CPUs
@@ -304,8 +312,7 @@ jobs:
          # Install to be able to retry on failures for flaky tests
          poetry run pip install pytest-rerunfailures

-          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
-          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
+          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}

          TEST_RUNTIME=docker \
          SANDBOX_USER_ID=$(id -u) \
--- a/.github/workflows/integration-runner.yml
+++ b/.github/workflows/integration-runner.yml
@@ -40,6 +40,11 @@ jobs:
          python-version: ${{ matrix.python-version }}
          cache: "poetry"

+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22.x'
+
      - name: Comment on PR if 'integration-test' label is present
        if: github.event_name == 'pull_request' && github.event.label.name == 'integration-test'
        uses: KeisukeYamashita/create-comment@v1
--- a/Development.md
+++ b/Development.md
@@ -100,7 +100,7 @@ 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:0.26-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.27-nikolaik`

 ## Develop inside Docker container

--- a/README.md
+++ b/README.md
@@ -43,17 +43,17 @@ See the [Running OpenHands](https://docs.all-hands.dev/modules/usage/installatio
 system requirements and more information.

 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.26-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26
+    docker.all-hands.dev/all-hands-ai/openhands:0.27
 ```

 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!
--- a/containers/dev/compose.yml
+++ b/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:0.26-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.27-nikolaik}
      - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
      - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
    ports:
--- a/docker-compose.yml
+++ b/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:0.26-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik}
      #- SANDBOX_USER_ID=${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:
--- a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/custom_sandbox_guide.md
+++ b/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/custom_sandbox_guide.md
@@ -42,10 +42,11 @@ Créez un fichier ```config.toml``` dans le répertoire OpenHands et entrez ces
 [core]
 workspace_base="./workspace"
 run_as_openhands=true
-sandbox_base_container_image="image_personnalisée"
+[sandbox]
+base_container_image="image_personnalisée"
 ```

-> Assurez-vous que ```sandbox_base_container_image``` est défini sur le nom de votre image personnalisée précédente.
+> Assurez-vous que ```base_container_image``` est défini sur le nom de votre image personnalisée précédente.

 ## Exécution

@@ -82,14 +83,15 @@ dockerfile_content = (
 ## Dépannage / Erreurs

 ### Erreur: ```useradd: UID 1000 est non unique```
-Si vous voyez cette erreur dans la sortie de la console, il s'agit du fait que OpenHands essaie de créer le utilisateur openhands dans le sandbox avec un ID d'utilisateur de 1000, cependant cet ID d'utilisateur est déjà utilisé dans l'image (pour une raison inconnue). Pour résoudre ce problème, changez la valeur du champ sandbox_user_id dans le fichier config.toml en une valeur différente:
+Si vous voyez cette erreur dans la sortie de la console, il s'agit du fait que OpenHands essaie de créer le utilisateur openhands dans le sandbox avec un ID d'utilisateur de 1000, cependant cet ID d'utilisateur est déjà utilisé dans l'image (pour une raison inconnue). Pour résoudre ce problème, changez la valeur du champ user_id dans le fichier config.toml en une valeur différente:

 ```toml
 [core]
 workspace_base="./workspace"
 run_as_openhands=true
-sandbox_base_container_image="image_personnalisée"
-sandbox_user_id="1001"
+[sandbox]
+base_container_image="image_personnalisée"
+user_id="1001"
 ```

 ### Erreurs de port d'utilisation
--- a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md
+++ b/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:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
    python -m openhands.core.cli
 ```

--- a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/custom-sandbox-guide.md
+++ b/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/custom-sandbox-guide.md
@@ -44,12 +44,13 @@ Tout d'abord, assurez-vous de pouvoir exécuter OpenHands en suivant les instruc

 ### Spécifier l'Image de Base du Sandbox

-Dans le fichier `config.toml` dans le répertoire OpenHands, définissez `sandbox_base_container_image` sur l'image que vous souhaitez utiliser. Cela peut être une image que vous avez déjà extraite ou une que vous avez construite :
+Dans le fichier `config.toml` dans le répertoire OpenHands, définissez `base_container_image` sur l'image que vous souhaitez utiliser. Cela peut être une image que vous avez déjà extraite ou une que vous avez construite :

 ```bash
 [core]
 ...
-sandbox_base_container_image="custom-image"
+[sandbox]
+base_container_image="custom-image"
 ```

 ### Exécution
--- a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md
+++ b/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:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
    python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```
--- a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/installation.mdx
+++ b/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:0.26-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26
+    docker.all-hands.dev/all-hands-ai/openhands:0.27
 ```

 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).
--- a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/runtimes.md
+++ b/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:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
    -v /var/run/docker.sock:/var/run/docker.sock \
    # ...
 ```
--- a/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/custom_sandbox_guide.md
+++ b/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/custom_sandbox_guide.md
@@ -58,10 +58,11 @@ docker build -t custom_image .
 [core]
 workspace_base="./workspace"
 run_as_openhands=true
-sandbox_base_container_image="custom_image"
+[sandbox]
+base_container_image="custom_image"
 ```

-对于 `sandbox_base_container_image` 的值, 您可以选择以下任意一项：
+对于 `base_container_image` 的值, 您可以选择以下任意一项：
 1. 在上一步中您构建的自定义镜像的名称（例如，`“custom_image”`）
 2. 从 Docker Hub 拉取的镜像（例如，`“node:20”`，如果你需要一个预装 `Node.js` 的沙箱环境）

@@ -83,14 +84,15 @@ sandbox_base_container_image="custom_image"

 ### 错误：```useradd: UID 1000 is not unique```

-如果在控制台输出中看到此错误，说明 OpenHands 尝试在沙箱中以 UID 1000 创建 openhands 用户，但该 UID 已经被映像中的其他部分使用（不知何故）。要解决这个问题，请更改 config.toml 文件中的 sandbox_user_id 字段为不同的值：
+如果在控制台输出中看到此错误，说明 OpenHands 尝试在沙箱中以 UID 1000 创建 openhands 用户，但该 UID 已经被映像中的其他部分使用（不知何故）。要解决这个问题，请更改 config.toml 文件中的 user_id 字段为不同的值：

 ```
 [core]
 workspace_base="./workspace"
 run_as_openhands=true
-sandbox_base_container_image="custom_image"
-sandbox_user_id="1001"
+[sandbox]
+base_container_image="custom_image"
+user_id="1001"
 ```

 ### 端口使用错误
--- a/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md
+++ b/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:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
    python -m openhands.core.cli
 ```

--- a/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/custom-sandbox-guide.md
+++ b/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/custom-sandbox-guide.md
@@ -42,12 +42,13 @@ docker build -t custom-image .

 ### 指定基础沙箱镜像

-在 OpenHands 目录中的 `config.toml` 文件中，将 `sandbox_base_container_image` 设置为你要使用的镜像。这可以是你已经拉取的镜像或你构建的镜像：
+在 OpenHands 目录中的 `config.toml` 文件中，将 `base_container_image` 设置为你要使用的镜像。这可以是你已经拉取的镜像或你构建的镜像：

 ```bash
 [core]
 ...
-sandbox_base_container_image="custom-image"
+[sandbox]
+base_container_image="custom-image"
 ```

 ### 运行
--- a/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md
+++ b/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:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
    python -m openhands.core.main -t "write a bash script that prints hi" --no-auto-continue
 ```
--- a/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/installation.mdx
+++ b/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:0.26-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26
+    docker.all-hands.dev/all-hands-ai/openhands:0.27
 ```

 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)。
--- a/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/runtimes.md
+++ b/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:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
    -v /var/run/docker.sock:/var/run/docker.sock \
    # ...
 ```
--- a/docs/modules/usage/how-to/cli-mode.md
+++ b/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:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
    python -m openhands.core.cli
 ```

--- a/docs/modules/usage/how-to/custom-sandbox-guide.md
+++ b/docs/modules/usage/how-to/custom-sandbox-guide.md
@@ -60,13 +60,14 @@ First, ensure you can run OpenHands by following the instructions in [Developmen

 ### Specify the Base Sandbox Image

-In the `config.toml` file within the OpenHands directory, set the `sandbox_base_container_image` to the image you want to use.
+In the `config.toml` file within the OpenHands directory, set the `base_container_image` to the image you want to use.
 This can be an image you’ve already pulled or one you’ve built:

 ```bash
 [core]
 ...
-sandbox_base_container_image="custom-image"
+[sandbox]
+base_container_image="custom-image"
 ```

 ### Additional Configuration Options
--- a/docs/modules/usage/how-to/headless-mode.md
+++ b/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:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
    python -m openhands.core.main -t "write a bash script that prints hi"
 ```

--- a/docs/modules/usage/installation.mdx
+++ b/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:0.26-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik

 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-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:0.26
+    docker.all-hands.dev/all-hands-ai/openhands:0.27
 ```

 You'll find OpenHands running at http://localhost:3000!
--- a/docs/modules/usage/runtimes.md
+++ b/docs/modules/usage/runtimes.md
@@ -16,7 +16,7 @@ some flags being passed to `docker run` that make this possible:

 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.26-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.27-nikolaik \
    -v /var/run/docker.sock:/var/run/docker.sock \
    # ...
 ```
--- a/docs/package-lock.json
+++ b/docs/package-lock.json
@@ -17,7 +17,7 @@
        "prism-react-renderer": "^2.4.1",
        "react": "^19.0.0",
        "react-dom": "^19.0.0",
-        "react-icons": "^5.4.0",
+        "react-icons": "^5.5.0",
        "react-use": "^17.6.0"
      },
      "devDependencies": {
@@ -15680,9 +15680,9 @@
      }
    },
    "node_modules/react-icons": {
-      "version": "5.4.0",
-      "resolved": "https://registry.npmjs.org/react-icons/-/react-icons-5.4.0.tgz",
-      "integrity": "sha512-7eltJxgVt7X64oHh6wSWNwwbKTCtMfK35hcjvJS0yxEAhPM8oUKdS3+kqaW1vicIltw+kR2unHaa12S9pPALoQ==",
+      "version": "5.5.0",
+      "resolved": "https://registry.npmjs.org/react-icons/-/react-icons-5.5.0.tgz",
+      "integrity": "sha512-MEFcXdkP3dLo8uumGI5xN3lDFNsRtrjbOEKDLD7yv76v4wpnEq2Lt2qeHaQOr34I/wPN3s3+N08WkQ+CW37Xiw==",
      "license": "MIT",
      "peerDependencies": {
        "react": "*"
--- a/docs/package.json
+++ b/docs/package.json
@@ -24,7 +24,7 @@
    "prism-react-renderer": "^2.4.1",
    "react": "^19.0.0",
    "react-dom": "^19.0.0",
-    "react-icons": "^5.4.0",
+    "react-icons": "^5.5.0",
    "react-use": "^17.6.0"
  },
  "devDependencies": {
--- a/evaluation/benchmarks/EDA/run_infer.py
+++ b/evaluation/benchmarks/EDA/run_infer.py
@@ -24,7 +24,6 @@ from openhands.core.config import (
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import MessageAction
-from openhands.utils.async_utils import call_async_from_sync

 game = None

@@ -122,7 +121,6 @@ def process_instance(

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)

    state: State | None = asyncio.run(
        run_controller(
--- a/evaluation/benchmarks/agent_bench/run_infer.py
+++ b/evaluation/benchmarks/agent_bench/run_infer.py
@@ -34,7 +34,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import AgentFinishAction, CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync


 def get_config(
@@ -211,7 +210,6 @@ def process_instance(
    # =============================================

    runtime: Runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)

    initialize_runtime(runtime, instance=instance)

--- a/evaluation/benchmarks/aider_bench/run_infer.py
+++ b/evaluation/benchmarks/aider_bench/run_infer.py
@@ -34,7 +34,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 # Configure visibility of unit tests to the Agent.
 USE_UNIT_TESTS = os.environ.get('USE_UNIT_TESTS', 'false').lower() == 'true'
@@ -204,7 +203,6 @@ def process_instance(
    # =============================================

    runtime: Runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)

    initialize_runtime(runtime, instance=instance)

--- a/evaluation/benchmarks/biocoder/run_infer.py
+++ b/evaluation/benchmarks/biocoder/run_infer.py
@@ -31,7 +31,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
    'CodeActAgent': functools.partial(
@@ -275,7 +274,6 @@ def process_instance(
    instruction += AGENT_CLS_TO_INST_SUFFIX[metadata.agent_class]

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime, instance)

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
--- a/evaluation/benchmarks/bird/run_infer.py
+++ b/evaluation/benchmarks/bird/run_infer.py
@@ -34,7 +34,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync


 def codeact_user_response(state: State) -> str:
@@ -400,7 +399,6 @@ def process_instance(
    instruction += AGENT_CLS_TO_INST_SUFFIX[metadata.agent_class]

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime, instance)

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
--- a/evaluation/benchmarks/commit0_bench/run_infer.py
+++ b/evaluation/benchmarks/commit0_bench/run_infer.py
@@ -35,7 +35,6 @@ from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation, ErrorObservation
 from openhands.events.serialization.event import event_to_dict
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync
 from openhands.utils.shutdown_listener import sleep_if_should_continue

 USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
@@ -395,7 +394,6 @@ def process_instance(
        logger.info(f'Starting evaluation for instance {instance.instance_id}.')

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    try:
        initialize_runtime(runtime, instance)

--- a/evaluation/benchmarks/discoverybench/run_infer.py
+++ b/evaluation/benchmarks/discoverybench/run_infer.py
@@ -34,7 +34,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import AgentFinishAction, CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 EVALUATION_LLM = 'gpt-4-1106-preview'

@@ -282,7 +281,6 @@ def process_instance(

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime, instance.data_files)

    state: State | None = asyncio.run(
--- a/evaluation/benchmarks/gaia/run_infer.py
+++ b/evaluation/benchmarks/gaia/run_infer.py
@@ -31,7 +31,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import AgentFinishAction, CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 DATASET_CACHE_DIR = os.path.join(os.path.dirname(__file__), 'data')

@@ -149,7 +148,6 @@ def process_instance(
    logger.info(f'Instruction:\n{instruction}', extra={'msg_type': 'OBSERVATION'})

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime, instance)

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
--- a/evaluation/benchmarks/gorilla/run_infer.py
+++ b/evaluation/benchmarks/gorilla/run_infer.py
@@ -26,7 +26,6 @@ from openhands.core.config import (
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import MessageAction
-from openhands.utils.async_utils import call_async_from_sync

 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
    'CodeActAgent': codeact_user_response,
@@ -83,7 +82,6 @@ def process_instance(

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    state: State | None = asyncio.run(
        run_controller(
            config=config,
--- a/evaluation/benchmarks/gpqa/run_infer.py
+++ b/evaluation/benchmarks/gpqa/run_infer.py
@@ -49,7 +49,6 @@ from openhands.events.action import (
    MessageAction,
 )
 from openhands.events.observation import Observation
-from openhands.utils.async_utils import call_async_from_sync

 ACTION_FORMAT = """
 <<FINAL_ANSWER||
@@ -215,7 +214,6 @@ Ok now its time to start solving the question. Good luck!
 """

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    state: State | None = asyncio.run(
        run_controller(
            config=config,
--- a/evaluation/benchmarks/humanevalfix/run_infer.py
+++ b/evaluation/benchmarks/humanevalfix/run_infer.py
@@ -39,7 +39,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 IMPORT_HELPER = {
    'python': [
@@ -233,7 +232,6 @@ def process_instance(

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime, instance)
    state: State | None = asyncio.run(
        run_controller(
--- a/evaluation/benchmarks/logic_reasoning/run_infer.py
+++ b/evaluation/benchmarks/logic_reasoning/run_infer.py
@@ -31,7 +31,6 @@ from openhands.events.action import (
 )
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
    'CodeActAgent': codeact_user_response,
@@ -207,7 +206,6 @@ def process_instance(
    instruction += AGENT_CLS_TO_INST_SUFFIX[metadata.agent_class]

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime, instance)

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
--- a/evaluation/benchmarks/miniwob/run_infer.py
+++ b/evaluation/benchmarks/miniwob/run_infer.py
@@ -41,7 +41,6 @@ from openhands.runtime.browser.browser_env import (
    BROWSER_EVAL_GET_GOAL_ACTION,
    BROWSER_EVAL_GET_REWARDS_ACTION,
 )
-from openhands.utils.async_utils import call_async_from_sync

 SUPPORTED_AGENT_CLS = {'BrowsingAgent', 'CodeActAgent'}

@@ -146,7 +145,6 @@ def process_instance(
        logger.info(f'Starting evaluation for instance {env_id}.')

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    task_str, obs = initialize_runtime(runtime)

    task_str += (
--- a/evaluation/benchmarks/mint/run_infer.py
+++ b/evaluation/benchmarks/mint/run_infer.py
@@ -35,7 +35,6 @@ from openhands.events.action import (
 )
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync


 def codeact_user_response_mint(state: State, task: Task, task_config: dict[str, int]):
@@ -185,7 +184,6 @@ def process_instance(
    )

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime)

    state: State | None = asyncio.run(
--- a/evaluation/benchmarks/ml_bench/run_infer.py
+++ b/evaluation/benchmarks/ml_bench/run_infer.py
@@ -43,7 +43,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 config = load_app_config()

@@ -235,7 +234,6 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
    instruction += AGENT_CLS_TO_INST_SUFFIX[metadata.agent_class]

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime, instance)

    # Run the agent
--- a/evaluation/benchmarks/scienceagentbench/run_infer.py
+++ b/evaluation/benchmarks/scienceagentbench/run_infer.py
@@ -29,7 +29,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
    'CodeActAgent': codeact_user_response,
@@ -196,7 +195,6 @@ If the program uses some packages that are incompatible, please figure out alter
 """

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime, instance)

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
--- a/evaluation/benchmarks/swe_bench/eval_infer.py
+++ b/evaluation/benchmarks/swe_bench/eval_infer.py
@@ -11,7 +11,11 @@ from swebench.harness.run_evaluation import (
    APPLY_PATCH_FAIL,
    APPLY_PATCH_PASS,
 )
-from swebench.harness.test_spec import SWEbenchInstance, TestSpec, make_test_spec
+from swebench.harness.test_spec.test_spec import (
+    SWEbenchInstance,
+    TestSpec,
+    make_test_spec,
+)
 from swebench.harness.utils import load_swebench_dataset
 from tqdm import tqdm

--- a/evaluation/benchmarks/swe_bench/run_infer.py
+++ b/evaluation/benchmarks/swe_bench/run_infer.py
@@ -40,7 +40,6 @@ from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation, ErrorObservation
 from openhands.events.serialization.event import event_to_dict
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync
 from openhands.utils.shutdown_listener import sleep_if_should_continue

 USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
@@ -59,8 +58,6 @@ def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:

 def get_instruction(instance: pd.Series, metadata: EvalMetadata):
    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
-    # Prepare instruction
-
    # Instruction based on Anthropic's official trajectory
    # https://github.com/eschluntz/swe-bench-experiments/tree/main/evaluation/verified/20241022_tools_claude-3-5-sonnet-updated/trajs
    instruction = (
@@ -72,14 +69,20 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
        f'{instance.problem_statement}\n'
        '</issue_description>\n\n'
        'Can you help me implement the necessary changes to the repository so that the requirements specified in the <issue_description> are met?\n'
-        "I've already taken care of all changes to any of the test files described in the <pr_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!\n"
-        'Your task is to make the minimal changes to non-tests files in the /workspace directory to ensure the <pr_description> is satisfied.\n'
+        "I've already taken care of all changes to any of the test files described in the <issue_description>. This means you DON'T have to modify the testing logic or any of the tests in any way!\n"
+        "Also the development Python environment is already set up for you (i.e., all dependencies already installed), so you don't need to install other packages.\n"
+        'Your task is to make the minimal changes to non-test files in the /workspace directory to ensure the <issue_description> is satisfied.\n'
        'Follow these steps to resolve the issue:\n'
        '1. As a first step, it might be a good idea to explore the repo to familiarize yourself with its structure.\n'
        '2. Create a script to reproduce the error and execute it with `python <filename.py>` using the BashTool, to confirm the error\n'
        '3. Edit the sourcecode of the repo to resolve the issue\n'
        '4. Rerun your reproduce script and confirm that the error is fixed!\n'
-        '5. Think about edgecases and make sure your fix handles them as well\n'
+        '5. Think about edgecases, add comprehensive tests for them in your reproduce script, and run them to make sure your fix handles them as well\n'
+        f'6. Once you are done with the initial implementation, please carefully re-read the problem description and check the difference between the current code and the base commit {instance["base_commit"]}. Do you think that the issue has been completely and comprehensively solved? Write tests to check the correctness of the solution, specifically focusing on tests that may point out any remaining problems that are not yet solved. Run all of the tests in the repo and check if any of them fail, and if they do fix the code. Repeat this process of carefully reading the problem description and current implementation, testing, and fixing any problems until you are confident that the current implementation is correct. Find and run any tests in the repo that are related to:\n'
+        '   - The issue you are fixing\n'
+        '   - The files you modified\n'
+        '   - The functions you changed\n'
+        '   Make sure all these tests pass with your changes.\n'
        "Your thinking should be thorough and so it's fine if it's very long.\n"
    )

@@ -97,11 +100,19 @@ DOCKER_IMAGE_PREFIX = os.environ.get('EVAL_DOCKER_IMAGE_PREFIX', 'docker.io/xing
 logger.info(f'Using docker image prefix: {DOCKER_IMAGE_PREFIX}')


-def get_instance_docker_image(instance_id: str) -> str:
-    image_name = 'sweb.eval.x86_64.' + instance_id
-    image_name = image_name.replace(
-        '__', '_s_'
-    )  # to comply with docker image naming convention
+def get_instance_docker_image(instance_id: str, official_image: bool = False) -> str:
+    if official_image:
+        # Official SWE-Bench image
+        # swebench/sweb.eval.x86_64.django_1776_django-11333:v1
+        repo, name = instance_id.split('__')
+        image_name = f'sweb.eval.x86_64.{repo}_1776_{name}:latest'
+        logger.warning(f'Using official SWE-Bench image: {image_name}')
+    else:
+        # OpenHands version of the image
+        image_name = 'sweb.eval.x86_64.' + instance_id
+        image_name = image_name.replace(
+            '__', '_s_'
+        )  # to comply with docker image naming convention
    return (DOCKER_IMAGE_PREFIX.rstrip('/') + '/' + image_name).lower()


@@ -112,7 +123,12 @@ def get_config(
    SWE_BENCH_CONTAINER_IMAGE = 'ghcr.io/opendevin/eval-swe-bench:full-v1.2.1'
    if USE_INSTANCE_IMAGE:
        # We use a different instance image for the each instance of swe-bench eval
-        base_container_image = get_instance_docker_image(instance['instance_id'])
+        use_official_image = bool(
+            'verified' in metadata.dataset.lower() or 'lite' in metadata.dataset.lower()
+        )
+        base_container_image = get_instance_docker_image(
+            instance['instance_id'], use_official_image
+        )
        logger.info(
            f'Using instance container image: {base_container_image}. '
            f'Please make sure this image exists. '
@@ -422,7 +438,6 @@ def process_instance(
            f'This is the {runtime_failure_count + 1}th attempt for instance {instance.instance_id}, setting resource factor to {config.sandbox.remote_runtime_resource_factor}'
        )
    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)

    try:
        initialize_runtime(runtime, instance)
--- a/evaluation/benchmarks/swe_bench/scripts/docker/all-swebench-full-instance-images.txt
+++ b/evaluation/benchmarks/swe_bench/scripts/docker/all-swebench-full-instance-images.txt
--- a/evaluation/benchmarks/swe_bench/scripts/docker/all-swebench-lite-instance-images.txt
+++ b/evaluation/benchmarks/swe_bench/scripts/docker/all-swebench-lite-instance-images.txt
@@ -1,336 +1,300 @@
-sweb.base.x86_64:latest
-sweb.env.x86_64.088a7e628bda9770f9757b:latest
-sweb.env.x86_64.0d80c7dec81ee2f2f513e2:latest
-sweb.env.x86_64.0f99bce2750f3109957bec:latest
-sweb.env.x86_64.1b3b218535da0abf4469cb:latest
-sweb.env.x86_64.1c1a6945f732f9391228c5:latest
-sweb.env.x86_64.1f92e6d7cef88badc4f744:latest
-sweb.env.x86_64.27dd9791e13f5c857a09f9:latest
-sweb.env.x86_64.297af196949a2a635bce66:latest
-sweb.env.x86_64.2baaea72acc974f6c02079:latest
-sweb.env.x86_64.2e50125951bc69cddd7421:latest
-sweb.env.x86_64.2f217c8b4490bfa0e2ba14:latest
-sweb.env.x86_64.31244378a92e3bcce809ac:latest
-sweb.env.x86_64.428468730904ff6b4232aa:latest
-sweb.env.x86_64.5d1fda9d55d65d8a4e5bdb:latest
-sweb.env.x86_64.6b007979cf533f0f3016e8:latest
-sweb.env.x86_64.7037e8c448a4b8ebfe9b13:latest
-sweb.env.x86_64.71498c7426dbf05599642f:latest
-sweb.env.x86_64.756beac07713d7e8dc1129:latest
-sweb.env.x86_64.78278ae2cf880e395f1337:latest
-sweb.env.x86_64.8f1f7b974f0c57c7aeba39:latest
-sweb.env.x86_64.934a137824256b612e9dc5:latest
-sweb.env.x86_64.a0efca7a0fe6719dbf65c2:latest
-sweb.env.x86_64.a18371b03f944585b4f08c:latest
-sweb.env.x86_64.a33dddf55cdff5d8e23374:latest
-sweb.env.x86_64.aa92880033da20ca313928:latest
-sweb.env.x86_64.b649f0ff62fad147f7f073:latest
-sweb.env.x86_64.b7ce4be3b3c35f68c61248:latest
-sweb.env.x86_64.c70909fdac4897d1c685df:latest
-sweb.env.x86_64.c795f4b88616b8462021ed:latest
-sweb.env.x86_64.cc47cc71483942d0c3a15e:latest
-sweb.env.x86_64.dc5ff4c0e3fe8db5afc4da:latest
-sweb.env.x86_64.e3afd7f04b325a4de4982d:latest
-sweb.env.x86_64.e5bb89bf78258a7d14c34b:latest
-sweb.env.x86_64.e83e37f52c09532c62acfb:latest
-sweb.env.x86_64.efa6065ed5bf204410fd53:latest
-sweb.eval.x86_64.astropy_s_astropy-12907:latest
-sweb.eval.x86_64.astropy_s_astropy-14182:latest
-sweb.eval.x86_64.astropy_s_astropy-14365:latest
-sweb.eval.x86_64.astropy_s_astropy-14995:latest
-sweb.eval.x86_64.astropy_s_astropy-6938:latest
-sweb.eval.x86_64.astropy_s_astropy-7746:latest
-sweb.eval.x86_64.django_s_django-10914:latest
-sweb.eval.x86_64.django_s_django-10924:latest
-sweb.eval.x86_64.django_s_django-11001:latest
-sweb.eval.x86_64.django_s_django-11019:latest
-sweb.eval.x86_64.django_s_django-11039:latest
-sweb.eval.x86_64.django_s_django-11049:latest
-sweb.eval.x86_64.django_s_django-11099:latest
-sweb.eval.x86_64.django_s_django-11133:latest
-sweb.eval.x86_64.django_s_django-11179:latest
-sweb.eval.x86_64.django_s_django-11283:latest
-sweb.eval.x86_64.django_s_django-11422:latest
-sweb.eval.x86_64.django_s_django-11564:latest
-sweb.eval.x86_64.django_s_django-11583:latest
-sweb.eval.x86_64.django_s_django-11620:latest
-sweb.eval.x86_64.django_s_django-11630:latest
-sweb.eval.x86_64.django_s_django-11742:latest
-sweb.eval.x86_64.django_s_django-11797:latest
-sweb.eval.x86_64.django_s_django-11815:latest
-sweb.eval.x86_64.django_s_django-11848:latest
-sweb.eval.x86_64.django_s_django-11905:latest
-sweb.eval.x86_64.django_s_django-11910:latest
-sweb.eval.x86_64.django_s_django-11964:latest
-sweb.eval.x86_64.django_s_django-11999:latest
-sweb.eval.x86_64.django_s_django-12113:latest
-sweb.eval.x86_64.django_s_django-12125:latest
-sweb.eval.x86_64.django_s_django-12184:latest
-sweb.eval.x86_64.django_s_django-12284:latest
-sweb.eval.x86_64.django_s_django-12286:latest
-sweb.eval.x86_64.django_s_django-12308:latest
-sweb.eval.x86_64.django_s_django-12453:latest
-sweb.eval.x86_64.django_s_django-12470:latest
-sweb.eval.x86_64.django_s_django-12497:latest
-sweb.eval.x86_64.django_s_django-12589:latest
-sweb.eval.x86_64.django_s_django-12700:latest
-sweb.eval.x86_64.django_s_django-12708:latest
-sweb.eval.x86_64.django_s_django-12747:latest
-sweb.eval.x86_64.django_s_django-12856:latest
-sweb.eval.x86_64.django_s_django-12908:latest
-sweb.eval.x86_64.django_s_django-12915:latest
-sweb.eval.x86_64.django_s_django-12983:latest
-sweb.eval.x86_64.django_s_django-13028:latest
-sweb.eval.x86_64.django_s_django-13033:latest
-sweb.eval.x86_64.django_s_django-13158:latest
-sweb.eval.x86_64.django_s_django-13220:latest
-sweb.eval.x86_64.django_s_django-13230:latest
-sweb.eval.x86_64.django_s_django-13265:latest
-sweb.eval.x86_64.django_s_django-13315:latest
-sweb.eval.x86_64.django_s_django-13321:latest
-sweb.eval.x86_64.django_s_django-13401:latest
-sweb.eval.x86_64.django_s_django-13447:latest
-sweb.eval.x86_64.django_s_django-13448:latest
-sweb.eval.x86_64.django_s_django-13551:latest
-sweb.eval.x86_64.django_s_django-13590:latest
-sweb.eval.x86_64.django_s_django-13658:latest
-sweb.eval.x86_64.django_s_django-13660:latest
-sweb.eval.x86_64.django_s_django-13710:latest
-sweb.eval.x86_64.django_s_django-13757:latest
-sweb.eval.x86_64.django_s_django-13768:latest
-sweb.eval.x86_64.django_s_django-13925:latest
-sweb.eval.x86_64.django_s_django-13933:latest
-sweb.eval.x86_64.django_s_django-13964:latest
-sweb.eval.x86_64.django_s_django-14016:latest
-sweb.eval.x86_64.django_s_django-14017:latest
-sweb.eval.x86_64.django_s_django-14155:latest
-sweb.eval.x86_64.django_s_django-14238:latest
-sweb.eval.x86_64.django_s_django-14382:latest
-sweb.eval.x86_64.django_s_django-14411:latest
-sweb.eval.x86_64.django_s_django-14534:latest
-sweb.eval.x86_64.django_s_django-14580:latest
-sweb.eval.x86_64.django_s_django-14608:latest
-sweb.eval.x86_64.django_s_django-14667:latest
-sweb.eval.x86_64.django_s_django-14672:latest
-sweb.eval.x86_64.django_s_django-14730:latest
-sweb.eval.x86_64.django_s_django-14752:latest
-sweb.eval.x86_64.django_s_django-14787:latest
-sweb.eval.x86_64.django_s_django-14855:latest
-sweb.eval.x86_64.django_s_django-14915:latest
-sweb.eval.x86_64.django_s_django-14997:latest
-sweb.eval.x86_64.django_s_django-14999:latest
-sweb.eval.x86_64.django_s_django-15061:latest
-sweb.eval.x86_64.django_s_django-15202:latest
-sweb.eval.x86_64.django_s_django-15213:latest
-sweb.eval.x86_64.django_s_django-15252:latest
-sweb.eval.x86_64.django_s_django-15320:latest
-sweb.eval.x86_64.django_s_django-15347:latest
-sweb.eval.x86_64.django_s_django-15388:latest
-sweb.eval.x86_64.django_s_django-15400:latest
-sweb.eval.x86_64.django_s_django-15498:latest
-sweb.eval.x86_64.django_s_django-15695:latest
-sweb.eval.x86_64.django_s_django-15738:latest
-sweb.eval.x86_64.django_s_django-15781:latest
-sweb.eval.x86_64.django_s_django-15789:latest
-sweb.eval.x86_64.django_s_django-15790:latest
-sweb.eval.x86_64.django_s_django-15814:latest
-sweb.eval.x86_64.django_s_django-15819:latest
-sweb.eval.x86_64.django_s_django-15851:latest
-sweb.eval.x86_64.django_s_django-15902:latest
-sweb.eval.x86_64.django_s_django-15996:latest
-sweb.eval.x86_64.django_s_django-16041:latest
-sweb.eval.x86_64.django_s_django-16046:latest
-sweb.eval.x86_64.django_s_django-16139:latest
-sweb.eval.x86_64.django_s_django-16229:latest
-sweb.eval.x86_64.django_s_django-16255:latest
-sweb.eval.x86_64.django_s_django-16379:latest
-sweb.eval.x86_64.django_s_django-16400:latest
-sweb.eval.x86_64.django_s_django-16408:latest
-sweb.eval.x86_64.django_s_django-16527:latest
-sweb.eval.x86_64.django_s_django-16595:latest
-sweb.eval.x86_64.django_s_django-16816:latest
-sweb.eval.x86_64.django_s_django-16820:latest
-sweb.eval.x86_64.django_s_django-16873:latest
-sweb.eval.x86_64.django_s_django-16910:latest
-sweb.eval.x86_64.django_s_django-17051:latest
-sweb.eval.x86_64.django_s_django-17087:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-18869:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-22711:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-22835:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-23299:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-23314:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-23476:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-23562:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-23563:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-23913:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-23964:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-23987:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-24149:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-24265:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-24334:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-24970:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-25079:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-25311:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-25332:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-25433:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-25442:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-25498:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-26011:latest
-sweb.eval.x86_64.matplotlib_s_matplotlib-26020:latest
-sweb.eval.x86_64.mwaskom_s_seaborn-2848:latest
-sweb.eval.x86_64.mwaskom_s_seaborn-3010:latest
-sweb.eval.x86_64.mwaskom_s_seaborn-3190:latest
-sweb.eval.x86_64.mwaskom_s_seaborn-3407:latest
-sweb.eval.x86_64.pallets_s_flask-4045:latest
-sweb.eval.x86_64.pallets_s_flask-4992:latest
-sweb.eval.x86_64.pallets_s_flask-5063:latest
-sweb.eval.x86_64.psf_s_requests-1963:latest
-sweb.eval.x86_64.psf_s_requests-2148:latest
-sweb.eval.x86_64.psf_s_requests-2317:latest
-sweb.eval.x86_64.psf_s_requests-2674:latest
-sweb.eval.x86_64.psf_s_requests-3362:latest
-sweb.eval.x86_64.psf_s_requests-863:latest
-sweb.eval.x86_64.pydata_s_xarray-3364:latest
-sweb.eval.x86_64.pydata_s_xarray-4094:latest
-sweb.eval.x86_64.pydata_s_xarray-4248:latest
-sweb.eval.x86_64.pydata_s_xarray-4493:latest
-sweb.eval.x86_64.pydata_s_xarray-5131:latest
-sweb.eval.x86_64.pylint-dev_s_pylint-5859:latest
-sweb.eval.x86_64.pylint-dev_s_pylint-6506:latest
-sweb.eval.x86_64.pylint-dev_s_pylint-7080:latest
-sweb.eval.x86_64.pylint-dev_s_pylint-7114:latest
-sweb.eval.x86_64.pylint-dev_s_pylint-7228:latest
-sweb.eval.x86_64.pylint-dev_s_pylint-7993:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-11143:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-11148:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-5103:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-5221:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-5227:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-5413:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-5495:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-5692:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-6116:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-7168:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-7220:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-7373:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-7432:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-7490:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-8365:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-8906:latest
-sweb.eval.x86_64.pytest-dev_s_pytest-9359:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-10297:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-10508:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-10949:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-11040:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-11281:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-12471:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-13142:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-13241:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-13439:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-13496:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-13497:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-13584:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-13779:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-14087:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-14092:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-14894:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-14983:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-15512:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-15535:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-25500:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-25570:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-25638:latest
-sweb.eval.x86_64.scikit-learn_s_scikit-learn-25747:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-10325:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-10451:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-11445:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-7686:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-7738:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-7975:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8273:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8282:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8435:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8474:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8506:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8595:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8627:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8713:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8721:latest
-sweb.eval.x86_64.sphinx-doc_s_sphinx-8801:latest
-sweb.eval.x86_64.sympy_s_sympy-11400:latest
-sweb.eval.x86_64.sympy_s_sympy-11870:latest
-sweb.eval.x86_64.sympy_s_sympy-11897:latest
-sweb.eval.x86_64.sympy_s_sympy-12171:latest
-sweb.eval.x86_64.sympy_s_sympy-12236:latest
-sweb.eval.x86_64.sympy_s_sympy-12419:latest
-sweb.eval.x86_64.sympy_s_sympy-12454:latest
-sweb.eval.x86_64.sympy_s_sympy-12481:latest
-sweb.eval.x86_64.sympy_s_sympy-13031:latest
-sweb.eval.x86_64.sympy_s_sympy-13043:latest
-sweb.eval.x86_64.sympy_s_sympy-13146:latest
-sweb.eval.x86_64.sympy_s_sympy-13177:latest
-sweb.eval.x86_64.sympy_s_sympy-13437:latest
-sweb.eval.x86_64.sympy_s_sympy-13471:latest
-sweb.eval.x86_64.sympy_s_sympy-13480:latest
-sweb.eval.x86_64.sympy_s_sympy-13647:latest
-sweb.eval.x86_64.sympy_s_sympy-13773:latest
-sweb.eval.x86_64.sympy_s_sympy-13895:latest
-sweb.eval.x86_64.sympy_s_sympy-13915:latest
-sweb.eval.x86_64.sympy_s_sympy-13971:latest
-sweb.eval.x86_64.sympy_s_sympy-14024:latest
-sweb.eval.x86_64.sympy_s_sympy-14308:latest
-sweb.eval.x86_64.sympy_s_sympy-14317:latest
-sweb.eval.x86_64.sympy_s_sympy-14396:latest
-sweb.eval.x86_64.sympy_s_sympy-14774:latest
-sweb.eval.x86_64.sympy_s_sympy-14817:latest
-sweb.eval.x86_64.sympy_s_sympy-15011:latest
-sweb.eval.x86_64.sympy_s_sympy-15308:latest
-sweb.eval.x86_64.sympy_s_sympy-15345:latest
-sweb.eval.x86_64.sympy_s_sympy-15346:latest
-sweb.eval.x86_64.sympy_s_sympy-15609:latest
-sweb.eval.x86_64.sympy_s_sympy-15678:latest
-sweb.eval.x86_64.sympy_s_sympy-16106:latest
-sweb.eval.x86_64.sympy_s_sympy-16281:latest
-sweb.eval.x86_64.sympy_s_sympy-16503:latest
-sweb.eval.x86_64.sympy_s_sympy-16792:latest
-sweb.eval.x86_64.sympy_s_sympy-16988:latest
-sweb.eval.x86_64.sympy_s_sympy-17022:latest
-sweb.eval.x86_64.sympy_s_sympy-17139:latest
-sweb.eval.x86_64.sympy_s_sympy-17630:latest
-sweb.eval.x86_64.sympy_s_sympy-17655:latest
-sweb.eval.x86_64.sympy_s_sympy-18057:latest
-sweb.eval.x86_64.sympy_s_sympy-18087:latest
-sweb.eval.x86_64.sympy_s_sympy-18189:latest
-sweb.eval.x86_64.sympy_s_sympy-18199:latest
-sweb.eval.x86_64.sympy_s_sympy-18532:latest
-sweb.eval.x86_64.sympy_s_sympy-18621:latest
-sweb.eval.x86_64.sympy_s_sympy-18698:latest
-sweb.eval.x86_64.sympy_s_sympy-18835:latest
-sweb.eval.x86_64.sympy_s_sympy-19007:latest
-sweb.eval.x86_64.sympy_s_sympy-19254:latest
-sweb.eval.x86_64.sympy_s_sympy-19487:latest
-sweb.eval.x86_64.sympy_s_sympy-20049:latest
-sweb.eval.x86_64.sympy_s_sympy-20154:latest
-sweb.eval.x86_64.sympy_s_sympy-20212:latest
-sweb.eval.x86_64.sympy_s_sympy-20322:latest
-sweb.eval.x86_64.sympy_s_sympy-20442:latest
-sweb.eval.x86_64.sympy_s_sympy-20590:latest
-sweb.eval.x86_64.sympy_s_sympy-20639:latest
-sweb.eval.x86_64.sympy_s_sympy-21055:latest
-sweb.eval.x86_64.sympy_s_sympy-21171:latest
-sweb.eval.x86_64.sympy_s_sympy-21379:latest
-sweb.eval.x86_64.sympy_s_sympy-21612:latest
-sweb.eval.x86_64.sympy_s_sympy-21614:latest
-sweb.eval.x86_64.sympy_s_sympy-21627:latest
-sweb.eval.x86_64.sympy_s_sympy-21847:latest
-sweb.eval.x86_64.sympy_s_sympy-22005:latest
-sweb.eval.x86_64.sympy_s_sympy-22714:latest
-sweb.eval.x86_64.sympy_s_sympy-22840:latest
-sweb.eval.x86_64.sympy_s_sympy-23117:latest
-sweb.eval.x86_64.sympy_s_sympy-23191:latest
-sweb.eval.x86_64.sympy_s_sympy-23262:latest
-sweb.eval.x86_64.sympy_s_sympy-24066:latest
-sweb.eval.x86_64.sympy_s_sympy-24102:latest
-sweb.eval.x86_64.sympy_s_sympy-24152:latest
-sweb.eval.x86_64.sympy_s_sympy-24213:latest
-sweb.eval.x86_64.sympy_s_sympy-24909:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-12907:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14182:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14365:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14995:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-6938:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-7746:latest
+swebench/sweb.eval.x86_64.django_1776_django-10914:latest
+swebench/sweb.eval.x86_64.django_1776_django-10924:latest
+swebench/sweb.eval.x86_64.django_1776_django-11001:latest
+swebench/sweb.eval.x86_64.django_1776_django-11019:latest
+swebench/sweb.eval.x86_64.django_1776_django-11039:latest
+swebench/sweb.eval.x86_64.django_1776_django-11049:latest
+swebench/sweb.eval.x86_64.django_1776_django-11099:latest
+swebench/sweb.eval.x86_64.django_1776_django-11133:latest
+swebench/sweb.eval.x86_64.django_1776_django-11179:latest
+swebench/sweb.eval.x86_64.django_1776_django-11283:latest
+swebench/sweb.eval.x86_64.django_1776_django-11422:latest
+swebench/sweb.eval.x86_64.django_1776_django-11564:latest
+swebench/sweb.eval.x86_64.django_1776_django-11583:latest
+swebench/sweb.eval.x86_64.django_1776_django-11620:latest
+swebench/sweb.eval.x86_64.django_1776_django-11630:latest
+swebench/sweb.eval.x86_64.django_1776_django-11742:latest
+swebench/sweb.eval.x86_64.django_1776_django-11797:latest
+swebench/sweb.eval.x86_64.django_1776_django-11815:latest
+swebench/sweb.eval.x86_64.django_1776_django-11848:latest
+swebench/sweb.eval.x86_64.django_1776_django-11905:latest
+swebench/sweb.eval.x86_64.django_1776_django-11910:latest
+swebench/sweb.eval.x86_64.django_1776_django-11964:latest
+swebench/sweb.eval.x86_64.django_1776_django-11999:latest
+swebench/sweb.eval.x86_64.django_1776_django-12113:latest
+swebench/sweb.eval.x86_64.django_1776_django-12125:latest
+swebench/sweb.eval.x86_64.django_1776_django-12184:latest
+swebench/sweb.eval.x86_64.django_1776_django-12284:latest
+swebench/sweb.eval.x86_64.django_1776_django-12286:latest
+swebench/sweb.eval.x86_64.django_1776_django-12308:latest
+swebench/sweb.eval.x86_64.django_1776_django-12453:latest
+swebench/sweb.eval.x86_64.django_1776_django-12470:latest
+swebench/sweb.eval.x86_64.django_1776_django-12497:latest
+swebench/sweb.eval.x86_64.django_1776_django-12589:latest
+swebench/sweb.eval.x86_64.django_1776_django-12700:latest
+swebench/sweb.eval.x86_64.django_1776_django-12708:latest
+swebench/sweb.eval.x86_64.django_1776_django-12747:latest
+swebench/sweb.eval.x86_64.django_1776_django-12856:latest
+swebench/sweb.eval.x86_64.django_1776_django-12908:latest
+swebench/sweb.eval.x86_64.django_1776_django-12915:latest
+swebench/sweb.eval.x86_64.django_1776_django-12983:latest
+swebench/sweb.eval.x86_64.django_1776_django-13028:latest
+swebench/sweb.eval.x86_64.django_1776_django-13033:latest
+swebench/sweb.eval.x86_64.django_1776_django-13158:latest
+swebench/sweb.eval.x86_64.django_1776_django-13220:latest
+swebench/sweb.eval.x86_64.django_1776_django-13230:latest
+swebench/sweb.eval.x86_64.django_1776_django-13265:latest
+swebench/sweb.eval.x86_64.django_1776_django-13315:latest
+swebench/sweb.eval.x86_64.django_1776_django-13321:latest
+swebench/sweb.eval.x86_64.django_1776_django-13401:latest
+swebench/sweb.eval.x86_64.django_1776_django-13447:latest
+swebench/sweb.eval.x86_64.django_1776_django-13448:latest
+swebench/sweb.eval.x86_64.django_1776_django-13551:latest
+swebench/sweb.eval.x86_64.django_1776_django-13590:latest
+swebench/sweb.eval.x86_64.django_1776_django-13658:latest
+swebench/sweb.eval.x86_64.django_1776_django-13660:latest
+swebench/sweb.eval.x86_64.django_1776_django-13710:latest
+swebench/sweb.eval.x86_64.django_1776_django-13757:latest
+swebench/sweb.eval.x86_64.django_1776_django-13768:latest
+swebench/sweb.eval.x86_64.django_1776_django-13925:latest
+swebench/sweb.eval.x86_64.django_1776_django-13933:latest
+swebench/sweb.eval.x86_64.django_1776_django-13964:latest
+swebench/sweb.eval.x86_64.django_1776_django-14016:latest
+swebench/sweb.eval.x86_64.django_1776_django-14017:latest
+swebench/sweb.eval.x86_64.django_1776_django-14155:latest
+swebench/sweb.eval.x86_64.django_1776_django-14238:latest
+swebench/sweb.eval.x86_64.django_1776_django-14382:latest
+swebench/sweb.eval.x86_64.django_1776_django-14411:latest
+swebench/sweb.eval.x86_64.django_1776_django-14534:latest
+swebench/sweb.eval.x86_64.django_1776_django-14580:latest
+swebench/sweb.eval.x86_64.django_1776_django-14608:latest
+swebench/sweb.eval.x86_64.django_1776_django-14667:latest
+swebench/sweb.eval.x86_64.django_1776_django-14672:latest
+swebench/sweb.eval.x86_64.django_1776_django-14730:latest
+swebench/sweb.eval.x86_64.django_1776_django-14752:latest
+swebench/sweb.eval.x86_64.django_1776_django-14787:latest
+swebench/sweb.eval.x86_64.django_1776_django-14855:latest
+swebench/sweb.eval.x86_64.django_1776_django-14915:latest
+swebench/sweb.eval.x86_64.django_1776_django-14997:latest
+swebench/sweb.eval.x86_64.django_1776_django-14999:latest
+swebench/sweb.eval.x86_64.django_1776_django-15061:latest
+swebench/sweb.eval.x86_64.django_1776_django-15202:latest
+swebench/sweb.eval.x86_64.django_1776_django-15213:latest
+swebench/sweb.eval.x86_64.django_1776_django-15252:latest
+swebench/sweb.eval.x86_64.django_1776_django-15320:latest
+swebench/sweb.eval.x86_64.django_1776_django-15347:latest
+swebench/sweb.eval.x86_64.django_1776_django-15388:latest
+swebench/sweb.eval.x86_64.django_1776_django-15400:latest
+swebench/sweb.eval.x86_64.django_1776_django-15498:latest
+swebench/sweb.eval.x86_64.django_1776_django-15695:latest
+swebench/sweb.eval.x86_64.django_1776_django-15738:latest
+swebench/sweb.eval.x86_64.django_1776_django-15781:latest
+swebench/sweb.eval.x86_64.django_1776_django-15789:latest
+swebench/sweb.eval.x86_64.django_1776_django-15790:latest
+swebench/sweb.eval.x86_64.django_1776_django-15814:latest
+swebench/sweb.eval.x86_64.django_1776_django-15819:latest
+swebench/sweb.eval.x86_64.django_1776_django-15851:latest
+swebench/sweb.eval.x86_64.django_1776_django-15902:latest
+swebench/sweb.eval.x86_64.django_1776_django-15996:latest
+swebench/sweb.eval.x86_64.django_1776_django-16041:latest
+swebench/sweb.eval.x86_64.django_1776_django-16046:latest
+swebench/sweb.eval.x86_64.django_1776_django-16139:latest
+swebench/sweb.eval.x86_64.django_1776_django-16229:latest
+swebench/sweb.eval.x86_64.django_1776_django-16255:latest
+swebench/sweb.eval.x86_64.django_1776_django-16379:latest
+swebench/sweb.eval.x86_64.django_1776_django-16400:latest
+swebench/sweb.eval.x86_64.django_1776_django-16408:latest
+swebench/sweb.eval.x86_64.django_1776_django-16527:latest
+swebench/sweb.eval.x86_64.django_1776_django-16595:latest
+swebench/sweb.eval.x86_64.django_1776_django-16816:latest
+swebench/sweb.eval.x86_64.django_1776_django-16820:latest
+swebench/sweb.eval.x86_64.django_1776_django-16873:latest
+swebench/sweb.eval.x86_64.django_1776_django-16910:latest
+swebench/sweb.eval.x86_64.django_1776_django-17051:latest
+swebench/sweb.eval.x86_64.django_1776_django-17087:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-18869:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-22711:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-22835:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23299:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23314:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23476:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23562:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23563:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23913:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23964:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23987:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24149:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24265:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24334:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24970:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25079:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25311:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25332:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25433:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25442:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25498:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-26011:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-26020:latest
+swebench/sweb.eval.x86_64.mwaskom_1776_seaborn-2848:latest
+swebench/sweb.eval.x86_64.mwaskom_1776_seaborn-3010:latest
+swebench/sweb.eval.x86_64.mwaskom_1776_seaborn-3190:latest
+swebench/sweb.eval.x86_64.mwaskom_1776_seaborn-3407:latest
+swebench/sweb.eval.x86_64.pallets_1776_flask-4045:latest
+swebench/sweb.eval.x86_64.pallets_1776_flask-4992:latest
+swebench/sweb.eval.x86_64.pallets_1776_flask-5063:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-1963:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-2148:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-2317:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-2674:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-3362:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-863:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-3364:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4094:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4248:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4493:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-5131:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-5859:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-6506:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-7080:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-7114:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-7228:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-7993:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-11143:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-11148:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5103:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5221:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5227:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5413:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5495:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5692:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-6116:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7168:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7220:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7373:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7432:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7490:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-8365:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-8906:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-9359:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-10297:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-10508:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-10949:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-11040:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-11281:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-12471:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13142:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13241:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13439:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13496:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13497:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13584:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13779:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14087:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14092:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14894:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14983:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-15512:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-15535:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-25500:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-25570:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-25638:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-25747:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-10325:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-10451:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-11445:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7686:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7738:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7975:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8273:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8282:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8435:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8474:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8506:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8595:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8627:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8713:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8721:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8801:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-11400:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-11870:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-11897:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-12171:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-12236:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-12419:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-12454:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-12481:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13031:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13043:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13146:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13177:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13437:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13471:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13480:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13647:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13773:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13895:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13915:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13971:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14024:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14308:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14317:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14396:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14774:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14817:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15011:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15308:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15345:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15346:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15609:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15678:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16106:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16281:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16503:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16792:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16988:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-17022:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-17139:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-17630:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-17655:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18057:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18087:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18189:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18199:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18532:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18621:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18698:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18835:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-19007:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-19254:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-19487:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20049:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20154:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20212:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20322:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20442:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20590:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20639:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21055:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21171:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21379:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21612:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21614:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21627:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21847:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-22005:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-22714:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-22840:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-23117:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-23191:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-23262:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24066:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24102:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24152:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24213:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24909:latest
--- a/evaluation/benchmarks/swe_bench/scripts/docker/all-swebench-verified-instance-images.txt
+++ b/evaluation/benchmarks/swe_bench/scripts/docker/all-swebench-verified-instance-images.txt
@@ -0,0 +1,500 @@
+swebench/sweb.eval.x86_64.astropy_1776_astropy-12907:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-13033:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-13236:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-13398:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-13453:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-13579:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-13977:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14096:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14182:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14309:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14365:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14369:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14508:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14539:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14598:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-14995:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-7166:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-7336:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-7606:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-7671:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-8707:latest
+swebench/sweb.eval.x86_64.astropy_1776_astropy-8872:latest
+swebench/sweb.eval.x86_64.django_1776_django-10097:latest
+swebench/sweb.eval.x86_64.django_1776_django-10554:latest
+swebench/sweb.eval.x86_64.django_1776_django-10880:latest
+swebench/sweb.eval.x86_64.django_1776_django-10914:latest
+swebench/sweb.eval.x86_64.django_1776_django-10973:latest
+swebench/sweb.eval.x86_64.django_1776_django-10999:latest
+swebench/sweb.eval.x86_64.django_1776_django-11066:latest
+swebench/sweb.eval.x86_64.django_1776_django-11087:latest
+swebench/sweb.eval.x86_64.django_1776_django-11095:latest
+swebench/sweb.eval.x86_64.django_1776_django-11099:latest
+swebench/sweb.eval.x86_64.django_1776_django-11119:latest
+swebench/sweb.eval.x86_64.django_1776_django-11133:latest
+swebench/sweb.eval.x86_64.django_1776_django-11138:latest
+swebench/sweb.eval.x86_64.django_1776_django-11141:latest
+swebench/sweb.eval.x86_64.django_1776_django-11149:latest
+swebench/sweb.eval.x86_64.django_1776_django-11163:latest
+swebench/sweb.eval.x86_64.django_1776_django-11179:latest
+swebench/sweb.eval.x86_64.django_1776_django-11206:latest
+swebench/sweb.eval.x86_64.django_1776_django-11211:latest
+swebench/sweb.eval.x86_64.django_1776_django-11239:latest
+swebench/sweb.eval.x86_64.django_1776_django-11265:latest
+swebench/sweb.eval.x86_64.django_1776_django-11276:latest
+swebench/sweb.eval.x86_64.django_1776_django-11292:latest
+swebench/sweb.eval.x86_64.django_1776_django-11299:latest
+swebench/sweb.eval.x86_64.django_1776_django-11333:latest
+swebench/sweb.eval.x86_64.django_1776_django-11400:latest
+swebench/sweb.eval.x86_64.django_1776_django-11433:latest
+swebench/sweb.eval.x86_64.django_1776_django-11451:latest
+swebench/sweb.eval.x86_64.django_1776_django-11477:latest
+swebench/sweb.eval.x86_64.django_1776_django-11490:latest
+swebench/sweb.eval.x86_64.django_1776_django-11532:latest
+swebench/sweb.eval.x86_64.django_1776_django-11551:latest
+swebench/sweb.eval.x86_64.django_1776_django-11555:latest
+swebench/sweb.eval.x86_64.django_1776_django-11603:latest
+swebench/sweb.eval.x86_64.django_1776_django-11728:latest
+swebench/sweb.eval.x86_64.django_1776_django-11734:latest
+swebench/sweb.eval.x86_64.django_1776_django-11740:latest
+swebench/sweb.eval.x86_64.django_1776_django-11749:latest
+swebench/sweb.eval.x86_64.django_1776_django-11790:latest
+swebench/sweb.eval.x86_64.django_1776_django-11815:latest
+swebench/sweb.eval.x86_64.django_1776_django-11820:latest
+swebench/sweb.eval.x86_64.django_1776_django-11848:latest
+swebench/sweb.eval.x86_64.django_1776_django-11880:latest
+swebench/sweb.eval.x86_64.django_1776_django-11885:latest
+swebench/sweb.eval.x86_64.django_1776_django-11951:latest
+swebench/sweb.eval.x86_64.django_1776_django-11964:latest
+swebench/sweb.eval.x86_64.django_1776_django-11999:latest
+swebench/sweb.eval.x86_64.django_1776_django-12039:latest
+swebench/sweb.eval.x86_64.django_1776_django-12050:latest
+swebench/sweb.eval.x86_64.django_1776_django-12125:latest
+swebench/sweb.eval.x86_64.django_1776_django-12143:latest
+swebench/sweb.eval.x86_64.django_1776_django-12155:latest
+swebench/sweb.eval.x86_64.django_1776_django-12193:latest
+swebench/sweb.eval.x86_64.django_1776_django-12209:latest
+swebench/sweb.eval.x86_64.django_1776_django-12262:latest
+swebench/sweb.eval.x86_64.django_1776_django-12273:latest
+swebench/sweb.eval.x86_64.django_1776_django-12276:latest
+swebench/sweb.eval.x86_64.django_1776_django-12304:latest
+swebench/sweb.eval.x86_64.django_1776_django-12308:latest
+swebench/sweb.eval.x86_64.django_1776_django-12325:latest
+swebench/sweb.eval.x86_64.django_1776_django-12406:latest
+swebench/sweb.eval.x86_64.django_1776_django-12419:latest
+swebench/sweb.eval.x86_64.django_1776_django-12663:latest
+swebench/sweb.eval.x86_64.django_1776_django-12708:latest
+swebench/sweb.eval.x86_64.django_1776_django-12713:latest
+swebench/sweb.eval.x86_64.django_1776_django-12741:latest
+swebench/sweb.eval.x86_64.django_1776_django-12754:latest
+swebench/sweb.eval.x86_64.django_1776_django-12774:latest
+swebench/sweb.eval.x86_64.django_1776_django-12858:latest
+swebench/sweb.eval.x86_64.django_1776_django-12965:latest
+swebench/sweb.eval.x86_64.django_1776_django-13012:latest
+swebench/sweb.eval.x86_64.django_1776_django-13023:latest
+swebench/sweb.eval.x86_64.django_1776_django-13028:latest
+swebench/sweb.eval.x86_64.django_1776_django-13033:latest
+swebench/sweb.eval.x86_64.django_1776_django-13089:latest
+swebench/sweb.eval.x86_64.django_1776_django-13109:latest
+swebench/sweb.eval.x86_64.django_1776_django-13112:latest
+swebench/sweb.eval.x86_64.django_1776_django-13121:latest
+swebench/sweb.eval.x86_64.django_1776_django-13128:latest
+swebench/sweb.eval.x86_64.django_1776_django-13158:latest
+swebench/sweb.eval.x86_64.django_1776_django-13195:latest
+swebench/sweb.eval.x86_64.django_1776_django-13212:latest
+swebench/sweb.eval.x86_64.django_1776_django-13279:latest
+swebench/sweb.eval.x86_64.django_1776_django-13297:latest
+swebench/sweb.eval.x86_64.django_1776_django-13315:latest
+swebench/sweb.eval.x86_64.django_1776_django-13343:latest
+swebench/sweb.eval.x86_64.django_1776_django-13344:latest
+swebench/sweb.eval.x86_64.django_1776_django-13346:latest
+swebench/sweb.eval.x86_64.django_1776_django-13363:latest
+swebench/sweb.eval.x86_64.django_1776_django-13401:latest
+swebench/sweb.eval.x86_64.django_1776_django-13406:latest
+swebench/sweb.eval.x86_64.django_1776_django-13410:latest
+swebench/sweb.eval.x86_64.django_1776_django-13417:latest
+swebench/sweb.eval.x86_64.django_1776_django-13449:latest
+swebench/sweb.eval.x86_64.django_1776_django-13512:latest
+swebench/sweb.eval.x86_64.django_1776_django-13513:latest
+swebench/sweb.eval.x86_64.django_1776_django-13516:latest
+swebench/sweb.eval.x86_64.django_1776_django-13551:latest
+swebench/sweb.eval.x86_64.django_1776_django-13568:latest
+swebench/sweb.eval.x86_64.django_1776_django-13569:latest
+swebench/sweb.eval.x86_64.django_1776_django-13590:latest
+swebench/sweb.eval.x86_64.django_1776_django-13658:latest
+swebench/sweb.eval.x86_64.django_1776_django-13670:latest
+swebench/sweb.eval.x86_64.django_1776_django-13741:latest
+swebench/sweb.eval.x86_64.django_1776_django-13786:latest
+swebench/sweb.eval.x86_64.django_1776_django-13794:latest
+swebench/sweb.eval.x86_64.django_1776_django-13807:latest
+swebench/sweb.eval.x86_64.django_1776_django-13809:latest
+swebench/sweb.eval.x86_64.django_1776_django-13810:latest
+swebench/sweb.eval.x86_64.django_1776_django-13820:latest
+swebench/sweb.eval.x86_64.django_1776_django-13821:latest
+swebench/sweb.eval.x86_64.django_1776_django-13837:latest
+swebench/sweb.eval.x86_64.django_1776_django-13925:latest
+swebench/sweb.eval.x86_64.django_1776_django-13933:latest
+swebench/sweb.eval.x86_64.django_1776_django-13964:latest
+swebench/sweb.eval.x86_64.django_1776_django-14007:latest
+swebench/sweb.eval.x86_64.django_1776_django-14011:latest
+swebench/sweb.eval.x86_64.django_1776_django-14017:latest
+swebench/sweb.eval.x86_64.django_1776_django-14034:latest
+swebench/sweb.eval.x86_64.django_1776_django-14053:latest
+swebench/sweb.eval.x86_64.django_1776_django-14089:latest
+swebench/sweb.eval.x86_64.django_1776_django-14122:latest
+swebench/sweb.eval.x86_64.django_1776_django-14140:latest
+swebench/sweb.eval.x86_64.django_1776_django-14155:latest
+swebench/sweb.eval.x86_64.django_1776_django-14170:latest
+swebench/sweb.eval.x86_64.django_1776_django-14238:latest
+swebench/sweb.eval.x86_64.django_1776_django-14311:latest
+swebench/sweb.eval.x86_64.django_1776_django-14315:latest
+swebench/sweb.eval.x86_64.django_1776_django-14349:latest
+swebench/sweb.eval.x86_64.django_1776_django-14351:latest
+swebench/sweb.eval.x86_64.django_1776_django-14373:latest
+swebench/sweb.eval.x86_64.django_1776_django-14376:latest
+swebench/sweb.eval.x86_64.django_1776_django-14404:latest
+swebench/sweb.eval.x86_64.django_1776_django-14434:latest
+swebench/sweb.eval.x86_64.django_1776_django-14493:latest
+swebench/sweb.eval.x86_64.django_1776_django-14500:latest
+swebench/sweb.eval.x86_64.django_1776_django-14534:latest
+swebench/sweb.eval.x86_64.django_1776_django-14539:latest
+swebench/sweb.eval.x86_64.django_1776_django-14559:latest
+swebench/sweb.eval.x86_64.django_1776_django-14580:latest
+swebench/sweb.eval.x86_64.django_1776_django-14608:latest
+swebench/sweb.eval.x86_64.django_1776_django-14631:latest
+swebench/sweb.eval.x86_64.django_1776_django-14672:latest
+swebench/sweb.eval.x86_64.django_1776_django-14725:latest
+swebench/sweb.eval.x86_64.django_1776_django-14752:latest
+swebench/sweb.eval.x86_64.django_1776_django-14765:latest
+swebench/sweb.eval.x86_64.django_1776_django-14771:latest
+swebench/sweb.eval.x86_64.django_1776_django-14787:latest
+swebench/sweb.eval.x86_64.django_1776_django-14792:latest
+swebench/sweb.eval.x86_64.django_1776_django-14855:latest
+swebench/sweb.eval.x86_64.django_1776_django-14915:latest
+swebench/sweb.eval.x86_64.django_1776_django-14999:latest
+swebench/sweb.eval.x86_64.django_1776_django-15022:latest
+swebench/sweb.eval.x86_64.django_1776_django-15037:latest
+swebench/sweb.eval.x86_64.django_1776_django-15098:latest
+swebench/sweb.eval.x86_64.django_1776_django-15103:latest
+swebench/sweb.eval.x86_64.django_1776_django-15104:latest
+swebench/sweb.eval.x86_64.django_1776_django-15127:latest
+swebench/sweb.eval.x86_64.django_1776_django-15128:latest
+swebench/sweb.eval.x86_64.django_1776_django-15161:latest
+swebench/sweb.eval.x86_64.django_1776_django-15252:latest
+swebench/sweb.eval.x86_64.django_1776_django-15268:latest
+swebench/sweb.eval.x86_64.django_1776_django-15277:latest
+swebench/sweb.eval.x86_64.django_1776_django-15278:latest
+swebench/sweb.eval.x86_64.django_1776_django-15280:latest
+swebench/sweb.eval.x86_64.django_1776_django-15315:latest
+swebench/sweb.eval.x86_64.django_1776_django-15368:latest
+swebench/sweb.eval.x86_64.django_1776_django-15375:latest
+swebench/sweb.eval.x86_64.django_1776_django-15380:latest
+swebench/sweb.eval.x86_64.django_1776_django-15382:latest
+swebench/sweb.eval.x86_64.django_1776_django-15467:latest
+swebench/sweb.eval.x86_64.django_1776_django-15499:latest
+swebench/sweb.eval.x86_64.django_1776_django-15503:latest
+swebench/sweb.eval.x86_64.django_1776_django-15525:latest
+swebench/sweb.eval.x86_64.django_1776_django-15554:latest
+swebench/sweb.eval.x86_64.django_1776_django-15561:latest
+swebench/sweb.eval.x86_64.django_1776_django-15563:latest
+swebench/sweb.eval.x86_64.django_1776_django-15569:latest
+swebench/sweb.eval.x86_64.django_1776_django-15572:latest
+swebench/sweb.eval.x86_64.django_1776_django-15629:latest
+swebench/sweb.eval.x86_64.django_1776_django-15695:latest
+swebench/sweb.eval.x86_64.django_1776_django-15731:latest
+swebench/sweb.eval.x86_64.django_1776_django-15732:latest
+swebench/sweb.eval.x86_64.django_1776_django-15741:latest
+swebench/sweb.eval.x86_64.django_1776_django-15814:latest
+swebench/sweb.eval.x86_64.django_1776_django-15851:latest
+swebench/sweb.eval.x86_64.django_1776_django-15863:latest
+swebench/sweb.eval.x86_64.django_1776_django-15916:latest
+swebench/sweb.eval.x86_64.django_1776_django-15930:latest
+swebench/sweb.eval.x86_64.django_1776_django-15957:latest
+swebench/sweb.eval.x86_64.django_1776_django-15973:latest
+swebench/sweb.eval.x86_64.django_1776_django-15987:latest
+swebench/sweb.eval.x86_64.django_1776_django-16032:latest
+swebench/sweb.eval.x86_64.django_1776_django-16082:latest
+swebench/sweb.eval.x86_64.django_1776_django-16100:latest
+swebench/sweb.eval.x86_64.django_1776_django-16116:latest
+swebench/sweb.eval.x86_64.django_1776_django-16136:latest
+swebench/sweb.eval.x86_64.django_1776_django-16139:latest
+swebench/sweb.eval.x86_64.django_1776_django-16145:latest
+swebench/sweb.eval.x86_64.django_1776_django-16255:latest
+swebench/sweb.eval.x86_64.django_1776_django-16256:latest
+swebench/sweb.eval.x86_64.django_1776_django-16263:latest
+swebench/sweb.eval.x86_64.django_1776_django-16315:latest
+swebench/sweb.eval.x86_64.django_1776_django-16333:latest
+swebench/sweb.eval.x86_64.django_1776_django-16429:latest
+swebench/sweb.eval.x86_64.django_1776_django-16454:latest
+swebench/sweb.eval.x86_64.django_1776_django-16485:latest
+swebench/sweb.eval.x86_64.django_1776_django-16493:latest
+swebench/sweb.eval.x86_64.django_1776_django-16502:latest
+swebench/sweb.eval.x86_64.django_1776_django-16527:latest
+swebench/sweb.eval.x86_64.django_1776_django-16560:latest
+swebench/sweb.eval.x86_64.django_1776_django-16569:latest
+swebench/sweb.eval.x86_64.django_1776_django-16595:latest
+swebench/sweb.eval.x86_64.django_1776_django-16612:latest
+swebench/sweb.eval.x86_64.django_1776_django-16631:latest
+swebench/sweb.eval.x86_64.django_1776_django-16642:latest
+swebench/sweb.eval.x86_64.django_1776_django-16661:latest
+swebench/sweb.eval.x86_64.django_1776_django-16662:latest
+swebench/sweb.eval.x86_64.django_1776_django-16667:latest
+swebench/sweb.eval.x86_64.django_1776_django-16801:latest
+swebench/sweb.eval.x86_64.django_1776_django-16819:latest
+swebench/sweb.eval.x86_64.django_1776_django-16877:latest
+swebench/sweb.eval.x86_64.django_1776_django-16899:latest
+swebench/sweb.eval.x86_64.django_1776_django-16901:latest
+swebench/sweb.eval.x86_64.django_1776_django-16938:latest
+swebench/sweb.eval.x86_64.django_1776_django-16950:latest
+swebench/sweb.eval.x86_64.django_1776_django-17029:latest
+swebench/sweb.eval.x86_64.django_1776_django-17084:latest
+swebench/sweb.eval.x86_64.django_1776_django-17087:latest
+swebench/sweb.eval.x86_64.django_1776_django-7530:latest
+swebench/sweb.eval.x86_64.django_1776_django-9296:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-13989:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-14623:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-20488:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-20676:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-20826:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-20859:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-21568:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-22719:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-22865:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-22871:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23299:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23314:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23412:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-23476:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24026:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24149:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24177:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24570:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24627:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24637:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24870:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-24970:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25122:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25287:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25311:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25332:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25479:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25775:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-25960:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-26113:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-26208:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-26291:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-26342:latest
+swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-26466:latest
+swebench/sweb.eval.x86_64.mwaskom_1776_seaborn-3069:latest
+swebench/sweb.eval.x86_64.mwaskom_1776_seaborn-3187:latest
+swebench/sweb.eval.x86_64.pallets_1776_flask-5014:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-1142:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-1724:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-1766:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-1921:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-2317:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-2931:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-5414:latest
+swebench/sweb.eval.x86_64.psf_1776_requests-6028:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-2905:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-3095:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-3151:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-3305:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-3677:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-3993:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4075:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4094:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4356:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4629:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4687:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4695:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-4966:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-6461:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-6599:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-6721:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-6744:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-6938:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-6992:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-7229:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-7233:latest
+swebench/sweb.eval.x86_64.pydata_1776_xarray-7393:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-4551:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-4604:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-4661:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-4970:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-6386:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-6528:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-6903:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-7080:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-7277:latest
+swebench/sweb.eval.x86_64.pylint-dev_1776_pylint-8898:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-10051:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-10081:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-10356:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5262:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5631:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5787:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5809:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5840:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-6197:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-6202:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7205:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7236:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7324:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7432:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7490:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7521:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7571:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-7982:latest
+swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-8399:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-10297:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-10844:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-10908:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-11310:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-11578:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-12585:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-12682:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-12973:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13124:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13135:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13142:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13328:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13439:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13496:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13779:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14053:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14087:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14141:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14496:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14629:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14710:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14894:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-14983:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-15100:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-25102:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-25232:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-25747:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-25931:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-25973:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-26194:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-26323:latest
+swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-9288:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-10323:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-10435:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-10449:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-10466:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-10614:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-10673:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-11445:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-11510:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7440:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7454:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7462:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7590:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7748:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7757:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7889:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7910:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-7985:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8035:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8056:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8120:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8265:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8269:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8459:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8475:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8548:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8551:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8593:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8595:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8621:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8638:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8721:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9229:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9230:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9258:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9281:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9320:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9367:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9461:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9591:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9602:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9658:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9673:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9698:latest
+swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-9711:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-11618:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-12096:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-12419:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-12481:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-12489:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13031:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13091:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13372:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13480:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13551:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13615:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13647:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13757:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13798:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13852:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13877:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13878:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-13974:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14248:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14531:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14711:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-14976:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15017:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15345:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15349:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15599:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15809:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15875:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-15976:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16450:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16597:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16766:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16792:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-16886:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-17139:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-17318:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-17630:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-17655:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18189:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18199:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18211:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18698:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-18763:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-19040:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-19346:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-19495:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-19637:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-19783:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-19954:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20154:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20428:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20438:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20590:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20801:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-20916:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21379:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21596:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21612:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21847:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-21930:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-22080:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-22456:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-22714:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-22914:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-23262:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-23413:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-23534:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-23824:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-23950:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24066:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24213:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24443:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24539:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24562:latest
+swebench/sweb.eval.x86_64.sympy_1776_sympy-24661:latest
--- a/evaluation/benchmarks/swe_bench/scripts/docker/get_docker_image_names.py
+++ b/evaluation/benchmarks/swe_bench/scripts/docker/get_docker_image_names.py
@@ -0,0 +1,50 @@
+"""Get official docker image names for SWE-bench instances."""
+
+import argparse
+
+from datasets import load_dataset
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--dataset', type=str, default='princeton-nlp/SWE-bench')
+parser.add_argument('--split', type=str, default='test')
+parser.add_argument('--output', type=str, default='swebench_images.txt')
+args = parser.parse_args()
+
+SUPPORTED_DATASET = {
+    'princeton-nlp/SWE-bench_Multimodal',
+    'princeton-nlp/SWE-bench',
+    'princeton-nlp/SWE-bench_Lite',
+    'princeton-nlp/SWE-bench_Verified',
+}
+assert args.dataset in SUPPORTED_DATASET, f'Dataset {args.dataset} not supported'
+
+
+def swebench_instance_id_to_docker_image_name(instance_id: str) -> str:
+    # swebench/sweb.eval.x86_64.django_1776_django-11333:v1
+    repo, name = instance_id.split('__')
+    return f'swebench/sweb.eval.x86_64.{repo}_1776_{name}:latest'
+
+
+def swebench_multimodal_instance_id_to_docker_image_name(instance_id: str) -> str:
+    # swebench/sweb.mm.eval.x86_64.openlayers_1776_openlayers-12172
+    repo, name = instance_id.split('__')
+    return f'swebench/sweb.mm.eval.x86_64.{repo}_1776_{name}:latest'
+
+
+dataset = load_dataset(args.dataset, split=args.split)
+instance_ids = dataset['instance_id']
+
+print(f'Loading {len(instance_ids)} instances from {args.dataset} split {args.split}')
+with open(args.output, 'w') as f:
+    for instance_id in instance_ids:
+        if args.dataset in [
+            'princeton-nlp/SWE-bench',
+            'princeton-nlp/SWE-bench_Lite',
+            'princeton-nlp/SWE-bench_Verified',
+        ]:
+            f.write(swebench_instance_id_to_docker_image_name(instance_id) + '\n')
+        else:
+            f.write(
+                swebench_multimodal_instance_id_to_docker_image_name(instance_id) + '\n'
+            )
+print(f'Saved {len(instance_ids)} images to {args.output}')
--- a/evaluation/benchmarks/swe_bench/scripts/docker/pull_all_eval_docker.sh
+++ b/evaluation/benchmarks/swe_bench/scripts/docker/pull_all_eval_docker.sh
@@ -1,66 +1,36 @@
 #!/usr/bin/env bash
 set -e

-LEVEL=$1
-# three levels:
-# - base, keyword "sweb.base"
-# - env, keyword "sweb.env"
-# - instance, keyword "sweb.eval"
-SET=$2
-
-if [ -z "$LEVEL" ]; then
-    echo "Usage: $0 <cache_level> <set>"
-    echo "cache_level: base, env, or instance"
-    echo "set: lite, full"
+SET=$1
+# check set is in ["full", "lite", "verified"]
+if [ "$SET" != "full" ] && [ "$SET" != "lite" ] && [ "$SET" != "verified" ]; then
+    echo "Error: argument 1 must be one of: full, lite, verified"
    exit 1
 fi

-if [ -z "$SET" ]; then
-    echo "Usage: $0 <cache_level> <set>"
-    echo "cache_level: base, env, or instance"
-    echo "set: lite, full, default is lite"
-    SET="lite"
+input_file=evaluation/benchmarks/swe_bench/scripts/docker/all-swebench-${SET}-instance-images.txt
+echo "Downloading images based on ${input_file}"
+# Check if the file exists
+if [ ! -f "$input_file" ]; then
+    echo "Error: File '$input_file' not found"
+    exit 1
 fi

-# Check if namespace is provided via argument $3, otherwise default to 'xingyaoww'
-NAMESPACE=${3:-xingyaoww}
+# Get total number of images
+total_images=$(wc -l < "${input_file}")
+counter=0

-echo "Using namespace: $NAMESPACE"
+echo "Starting to pull ${total_images} images"

-if [ "$SET" == "lite" ]; then
-    IMAGE_FILE="$(dirname "$0")/all-swebench-lite-instance-images.txt"
-else
-    IMAGE_FILE="$(dirname "$0")/all-swebench-full-instance-images.txt"
-fi
+# Read the file line by line and pull each image
+while IFS= read -r image; do
+    # Skip empty lines or comments
+    if [ -n "$image" ] && [[ ! "$image" =~ ^[[:space:]]*# ]]; then
+        counter=$((counter + 1))
+        echo "[${counter}/${total_images}] Pulling ${image}"
+        docker pull "${image}"
+        sleep 2
+    fi
+done < "${input_file}"

-# Define a pattern based on the level
-case $LEVEL in
-    base)
-        PATTERN="sweb.base"
-        ;;
-    env)
-        PATTERN="sweb.base\|sweb.env"
-        ;;
-    instance)
-        PATTERN="sweb.base\|sweb.env\|sweb.eval"
-        ;;
-    *)
-        echo "Invalid cache level: $LEVEL"
-        echo "Valid levels are: base, env, instance"
-        exit 1
-        ;;
-esac
-
-echo "Pulling docker images for [$LEVEL] level"
-
-echo "Pattern: $PATTERN"
-echo "Image file: $IMAGE_FILE"
-
-# Read each line from the file, filter by pattern, and pull the docker image
-grep "$PATTERN" "$IMAGE_FILE" | while IFS= read -r image; do
-    echo "Pulling $NAMESPACE/$image into $image"
-    docker pull $NAMESPACE/$image
-    # replace _s_ to __ in the image name
-    renamed_image=$(echo "$image" | sed 's/_s_/__/g')
-    docker tag $NAMESPACE/$image $renamed_image
-done
+echo "Finished pulling all images"
--- a/evaluation/benchmarks/swe_bench/scripts/eval/compare_outputs.py
+++ b/evaluation/benchmarks/swe_bench/scripts/eval/compare_outputs.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 import argparse
 import os
+import subprocess

 import pandas as pd
 from termcolor import colored
@@ -35,6 +36,23 @@ if args.only_x_instances:
        f'After removing instances not in X={args.input_file_1}: Y={df2.shape[0]} instances'
    )

+
+# Add summarization step for each input file
+def summarize_file(file_path):
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    summarize_script = os.path.join(script_dir, 'summarize_outputs.py')
+
+    print(f'\nSummary for {file_path}:')
+    print('=' * 80)
+    subprocess.run(['python', summarize_script, file_path], check=True)
+    print('=' * 80)
+
+
+# Generate summaries
+summarize_file(args.input_file_1)
+summarize_file(args.input_file_2)
+
+
 # Get the intersection of the instance_ids
 df = pd.merge(df1, df2, on='instance_id', how='inner')

--- a/evaluation/benchmarks/swe_bench/scripts/eval/convert_oh_output_to_md.py
+++ b/evaluation/benchmarks/swe_bench/scripts/eval/convert_oh_output_to_md.py
@@ -248,6 +248,22 @@ def write_row_to_md_file(row, instance_id_to_test_result):

    completions = load_completions(instance_id)

+    # report file
+    global output_dir
+    report_file = os.path.join(output_dir, 'eval_outputs', instance_id, 'report.json')
+    if os.path.exists(report_file):
+        with open(report_file, 'r') as f:
+            report = json.load(f)
+    else:
+        report = None
+
+    test_output_file = os.path.join(
+        output_dir, 'eval_outputs', instance_id, 'test_output.txt'
+    )
+    if test_output is None and os.path.exists(test_output_file):
+        with open(test_output_file, 'r') as f:
+            test_output = f.read()
+
    with open(filepath, 'w') as f:
        f.write(f'# {instance_id} (resolved: {resolved})\n')

@@ -269,8 +285,14 @@ def write_row_to_md_file(row, instance_id_to_test_result):
        f.write('## Model Patch\n')
        f.write(f'{process_git_patch(model_patch)}\n')

+        if report is not None:
+            f.write('## Report\n')
+            f.write(json.dumps(report, indent=2))
+            f.write('\n')
+
        f.write('## Test Output\n')
        f.write(str(test_output))
+        f.write('\n')


 instance_id_to_test_result = {}
--- a/evaluation/benchmarks/swe_bench/scripts/eval/update_output_with_eval.py
+++ b/evaluation/benchmarks/swe_bench/scripts/eval/update_output_with_eval.py
@@ -44,7 +44,6 @@ if os.path.exists(swebench_official_report_json):
        f"- resolved instances: {report['resolved_instances']}\n"
        f"- unresolved instances: {report['unresolved_instances']}\n"
        f"- error instances: {report['error_instances']}\n"
-        f"- unstopped instances: {report['unstopped_instances']}\n"
    )

    output_md += '\n## Resolved Instances\n'
--- a/evaluation/benchmarks/the_agent_company/run_infer.py
+++ b/evaluation/benchmarks/the_agent_company/run_infer.py
@@ -28,7 +28,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import BrowserOutputObservation, CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync


 def get_config(
@@ -276,7 +275,6 @@ if __name__ == '__main__':
        args.task_image_name, task_short_name, temp_dir, agent_llm_config, agent_config
    )
    runtime: Runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)

    init_task_env(runtime, args.server_hostname, env_llm_config)

--- a/evaluation/benchmarks/toolqa/run_infer.py
+++ b/evaluation/benchmarks/toolqa/run_infer.py
@@ -27,7 +27,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import CmdRunAction, MessageAction
 from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
    'CodeActAgent': codeact_user_response,
@@ -105,7 +104,6 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
    logger.info(f'Instruction:\n{instruction}', extra={'msg_type': 'OBSERVATION'})

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    initialize_runtime(runtime)

    # Here's how you can run the agent (similar to the `main` function) and get the final task state
--- a/evaluation/benchmarks/visualwebarena/run_infer.py
+++ b/evaluation/benchmarks/visualwebarena/run_infer.py
@@ -37,7 +37,6 @@ from openhands.runtime.browser.browser_env import (
    BROWSER_EVAL_GET_GOAL_ACTION,
    BROWSER_EVAL_GET_REWARDS_ACTION,
 )
-from openhands.utils.async_utils import call_async_from_sync

 SUPPORTED_AGENT_CLS = {'VisualBrowsingAgent'}
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
@@ -160,7 +159,6 @@ def process_instance(
        logger.info(f'Starting evaluation for instance {env_id}.')

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    task_str, goal_image_urls = initialize_runtime(runtime)
    initial_user_action = MessageAction(content=task_str, image_urls=goal_image_urls)
    state: State | None = asyncio.run(
--- a/evaluation/benchmarks/webarena/run_infer.py
+++ b/evaluation/benchmarks/webarena/run_infer.py
@@ -36,7 +36,6 @@ from openhands.runtime.browser.browser_env import (
    BROWSER_EVAL_GET_GOAL_ACTION,
    BROWSER_EVAL_GET_REWARDS_ACTION,
 )
-from openhands.utils.async_utils import call_async_from_sync

 SUPPORTED_AGENT_CLS = {'BrowsingAgent'}

@@ -145,7 +144,6 @@ def process_instance(
        logger.info(f'Starting evaluation for instance {env_id}.')

    runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    task_str = initialize_runtime(runtime)

    state: State | None = asyncio.run(
--- a/evaluation/integration_tests/run_infer.py
+++ b/evaluation/integration_tests/run_infer.py
@@ -30,7 +30,6 @@ from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import MessageAction
 from openhands.events.serialization.event import event_to_dict
 from openhands.runtime.base import Runtime
-from openhands.utils.async_utils import call_async_from_sync

 FAKE_RESPONSES = {
    'CodeActAgent': fake_user_response,
@@ -109,7 +108,6 @@ def process_instance(
    # create sandbox and run the agent
    # =============================================
    runtime: Runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
    try:
        test_class.initialize_runtime(runtime)

--- a/evaluation/utils/shared.py
+++ b/evaluation/utils/shared.py
@@ -247,11 +247,21 @@ def prepare_dataset(
            f'Starting evaluation with skipping first {skip_num} instances ({len(dataset)} instances to run).'
        )
        if eval_n_limit and eval_n_limit > 0:
-            dataset = dataset.head(eval_n_limit)
-            logger.info(f'Limiting evaluation to {eval_n_limit} instances.')
+            # Use fixed random seed 42 for sampling without replacement
+            dataset = dataset.sample(
+                min(eval_n_limit, len(dataset)), random_state=42, replace=False
+            )
+            logger.info(
+                f'Randomly sampling {eval_n_limit} unique instances with random seed 42.'
+            )
    elif eval_n_limit and eval_n_limit > 0:
-        dataset = dataset.head(eval_n_limit)
-        logger.info(f'Limiting evaluation to first {eval_n_limit} instances.')
+        # Use fixed random seed 42 for sampling without replacement
+        dataset = dataset.sample(
+            min(eval_n_limit, len(dataset)), random_state=42, replace=False
+        )
+        logger.info(
+            f'Randomly sampling {eval_n_limit} unique instances with random seed 42.'
+        )

    new_dataset = [
        instance
--- a/frontend/tests/components/feedback-actions.test.tsx
+++ b/frontend/tests/components/feedback-actions.test.tsx
@@ -1,6 +1,7 @@
-import { render, screen, within } from "@testing-library/react";
+import { screen, within } from "@testing-library/react";
 import userEvent from "@testing-library/user-event";
 import { afterEach, describe, expect, it, vi } from "vitest";
+import { renderWithProviders } from "test-utils";
 import { TrajectoryActions } from "#/components/features/trajectory/trajectory-actions";

 describe("TrajectoryActions", () => {
@@ -14,7 +15,7 @@ describe("TrajectoryActions", () => {
  });

  it("should render correctly", () => {
-    render(
+    renderWithProviders(
      <TrajectoryActions
        onPositiveFeedback={onPositiveFeedback}
        onNegativeFeedback={onNegativeFeedback}
@@ -25,10 +26,11 @@ describe("TrajectoryActions", () => {
    const actions = screen.getByTestId("feedback-actions");
    within(actions).getByTestId("positive-feedback");
    within(actions).getByTestId("negative-feedback");
+    within(actions).getByTestId("export-trajectory");
  });

  it("should call onPositiveFeedback when positive feedback is clicked", async () => {
-    render(
+    renderWithProviders(
      <TrajectoryActions
        onPositiveFeedback={onPositiveFeedback}
        onNegativeFeedback={onNegativeFeedback}
@@ -43,7 +45,7 @@ describe("TrajectoryActions", () => {
  });

  it("should call onNegativeFeedback when negative feedback is clicked", async () => {
-    render(
+    renderWithProviders(
      <TrajectoryActions
        onPositiveFeedback={onPositiveFeedback}
        onNegativeFeedback={onNegativeFeedback}
@@ -58,7 +60,7 @@ describe("TrajectoryActions", () => {
  });

  it("should call onExportTrajectory when negative feedback is clicked", async () => {
-    render(
+    renderWithProviders(
      <TrajectoryActions
        onPositiveFeedback={onPositiveFeedback}
        onNegativeFeedback={onNegativeFeedback}
--- a/frontend/tests/components/file-operations.test.tsx
+++ b/frontend/tests/components/file-operations.test.tsx
@@ -2,6 +2,7 @@ import { render, screen } from "@testing-library/react";
 import { describe, it, expect } from "vitest";
 import { Messages } from "#/components/features/chat/messages";
 import type { Message } from "#/message";
+import { renderWithProviders } from "test-utils";

 describe("File Operations Messages", () => {
  it("should show success indicator for successful file read operation", () => {
@@ -16,7 +17,7 @@ describe("File Operations Messages", () => {
      },
    ];

-    render(<Messages messages={messages} isAwaitingUserConfirmation={false} />);
+    renderWithProviders(<Messages messages={messages} isAwaitingUserConfirmation={false} />);

    const statusIcon = screen.getByTestId("status-icon");
    expect(statusIcon).toBeInTheDocument();
@@ -35,7 +36,7 @@ describe("File Operations Messages", () => {
      },
    ];

-    render(<Messages messages={messages} isAwaitingUserConfirmation={false} />);
+    renderWithProviders(<Messages messages={messages} isAwaitingUserConfirmation={false} />);

    const statusIcon = screen.getByTestId("status-icon");
    expect(statusIcon).toBeInTheDocument();
@@ -54,7 +55,7 @@ describe("File Operations Messages", () => {
      },
    ];

-    render(<Messages messages={messages} isAwaitingUserConfirmation={false} />);
+    renderWithProviders(<Messages messages={messages} isAwaitingUserConfirmation={false} />);

    const statusIcon = screen.getByTestId("status-icon");
    expect(statusIcon).toBeInTheDocument();
@@ -73,7 +74,7 @@ describe("File Operations Messages", () => {
      },
    ];

-    render(<Messages messages={messages} isAwaitingUserConfirmation={false} />);
+    renderWithProviders(<Messages messages={messages} isAwaitingUserConfirmation={false} />);

    const statusIcon = screen.getByTestId("status-icon");
    expect(statusIcon).toBeInTheDocument();
--- a/frontend/tests/components/modals/settings/model-selector.test.tsx
+++ b/frontend/tests/components/modals/settings/model-selector.test.tsx
@@ -133,30 +133,4 @@ describe("ModelSelector", () => {
    expect(screen.getByLabelText("LLM Provider")).toHaveValue("Azure");
    expect(screen.getByLabelText("LLM Model")).toHaveValue("ada");
  });
-
-  it("should handle Mistral AI provider selection correctly", async () => {
-    const mistralModels = {
-      mistral: {
-        separator: "/",
-        models: ["mistral-tiny", "mistral-small", "mistral-medium"],
-      },
-    };
-
-    const user = userEvent.setup();
-    render(<ModelSelector models={mistralModels} />);
-
-    const providerSelector = screen.getByLabelText("LLM Provider");
-    await user.click(providerSelector);
-
-    // Select Mistral AI (display name)
-    const mistralOption = screen.getByText("Mistral AI");
-    await user.click(mistralOption);
-
-    // Verify model dropdown is enabled and shows correct models
-    const modelSelector = screen.getByLabelText("LLM Model");
-    expect(modelSelector).not.toBeDisabled();
-
-    await user.click(modelSelector);
-    expect(screen.getByText("mistral-tiny")).toBeInTheDocument();
-  });
 });
--- a/frontend/tests/components/modals/settings/brand-button.test.tsx
+++ b/frontend/tests/components/modals/settings/brand-button.test.tsx
@@ -36,4 +36,20 @@ describe("BrandButton", () => {

    expect(screen.getByText("Test Button")).toBeDisabled();
  });
+
+  it("should pass a start content", () => {
+    render(
+      <BrandButton
+        type="button"
+        variant="primary"
+        startContent={
+          <div data-testid="custom-start-content">Start Content</div>
+        }
+      >
+        Test Button
+      </BrandButton>,
+    );
+
+    screen.getByTestId("custom-start-content");
+  });
 });
--- a/frontend/package-lock.json
+++ b/frontend/package-lock.json
@@ -1,12 +1,12 @@
 {
  "name": "openhands-frontend",
-  "version": "0.26.0",
+  "version": "0.27.0",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "openhands-frontend",
-      "version": "0.26.0",
+      "version": "0.27.0",
      "dependencies": {
        "@heroui/react": "2.6.14",
        "@monaco-editor/react": "^4.7.0-rc.0",
--- a/frontend/package.json
+++ b/frontend/package.json
@@ -1,6 +1,6 @@
 {
  "name": "openhands-frontend",
-  "version": "0.26.0",
+  "version": "0.27.0",
  "private": true,
  "type": "module",
  "engines": {
--- a/frontend/src/assets/branding/github-logo.svg
+++ b/frontend/src/assets/branding/github-logo.svg
@@ -1,5 +1,5 @@
 <svg width="22" height="22" viewBox="0 0 22 22" fill="none" xmlns="http://www.w3.org/2000/svg">
  <path
    d="M15.359 21V17.319C15.3974 16.8654 15.3314 16.4095 15.1651 15.9814C14.9989 15.5534 14.7363 15.1631 14.3949 14.8364C17.6154 14.5035 21 13.3716 21 8.17826C20.9997 6.85027 20.4489 5.57321 19.4615 4.61139C19.9291 3.44954 19.896 2.16532 19.3692 1.02548C19.3692 1.02548 18.159 0.692576 15.359 2.43321C13.0082 1.84237 10.5302 1.84237 8.17949 2.43321C5.37949 0.692576 4.16923 1.02548 4.16923 1.02548C3.64244 2.16532 3.60938 3.44954 4.07692 4.61139C3.08218 5.58034 2.53079 6.86895 2.53846 8.2068C2.53846 13.3621 5.92308 14.494 9.14359 14.865C8.80615 15.1883 8.54591 15.574 8.3798 15.9968C8.2137 16.4196 8.14544 16.8701 8.17949 17.319V21M8.17949 18.1465C3.05128 19.5732 3.05128 15.7686 1 15.293L8.17949 18.1465Z"
-    stroke="white" stroke-linecap="round" stroke-linejoin="round" />
+    stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" />
 </svg>
--- a/frontend/src/assets/notification.mp3
+++ b/frontend/src/assets/notification.mp3
--- a/frontend/src/components/features/analytics/analytics-consent-form-modal.tsx
+++ b/frontend/src/components/features/analytics/analytics-consent-form-modal.tsx
@@ -1,4 +1,3 @@
-import { ModalButton } from "#/components/shared/buttons/modal-button";
 import {
  BaseModalTitle,
  BaseModalDescription,
@@ -7,6 +6,7 @@ import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
 import { ModalBody } from "#/components/shared/modals/modal-body";
 import { useCurrentSettings } from "#/context/settings-context";
 import { handleCaptureConsent } from "#/utils/handle-capture-consent";
+import { BrandButton } from "../settings/brand-button";

 interface AnalyticsConsentFormModalProps {
  onClose: () => void;
@@ -40,7 +40,7 @@ export function AnalyticsConsentFormModal({
        onSubmit={handleSubmit}
        className="flex flex-col gap-2"
      >
-        <ModalBody>
+        <ModalBody className="border border-tertiary">
          <BaseModalTitle title="Your Privacy Preferences" />
          <BaseModalDescription>
            We use tools to understand how our application is used to improve
@@ -53,12 +53,14 @@ export function AnalyticsConsentFormModal({
            Send anonymous usage data
          </label>

-          <ModalButton
+          <BrandButton
            testId="confirm-preferences"
            type="submit"
-            text="Confirm Preferences"
-            className="bg-primary text-white w-full hover:opacity-80"
-          />
+            variant="primary"
+            className="w-full"
+          >
+            Confirm Preferences
+          </BrandButton>
        </ModalBody>
      </form>
    </ModalBackdrop>
--- a/frontend/src/components/features/chat/chat-message.tsx
+++ b/frontend/src/components/features/chat/chat-message.tsx
@@ -47,7 +47,7 @@ export function ChatMessage({
      className={cn(
        "rounded-xl relative",
        "flex flex-col gap-2",
-        type === "user" && " max-w-[305px] p-4 bg-neutral-700 self-end",
+        type === "user" && " max-w-[305px] p-4 bg-tertiary self-end",
        type === "assistant" && "mt-6 max-w-full bg-tranparent",
      )}
    >
--- a/frontend/src/components/features/chat/chat-suggestions.tsx
+++ b/frontend/src/components/features/chat/chat-suggestions.tsx
@@ -13,7 +13,7 @@ export function ChatSuggestions({ onSuggestionsClick }: ChatSuggestionsProps) {

  return (
    <div className="flex flex-col gap-6 h-full px-4 items-center justify-center">
-      <div className="flex flex-col items-center p-4 bg-neutral-700 rounded-xl w-full">
+      <div className="flex flex-col items-center p-4 bg-tertiary rounded-xl w-full">
        <BuildIt width={45} height={54} />
        <span className="font-semibold text-[20px] leading-6 -tracking-[0.01em] gap-1">
          {t(I18nKey.LANDING$TITLE)}
--- a/frontend/src/components/features/chat/expandable-message.tsx
+++ b/frontend/src/components/features/chat/expandable-message.tsx
@@ -2,6 +2,7 @@ import { useState, useEffect } from "react";
 import { useTranslation } from "react-i18next";
 import Markdown from "react-markdown";
 import remarkGfm from "remark-gfm";
+import { Link } from "react-router";
 import { code } from "../markdown/code";
 import { ol, ul } from "../markdown/list";
 import ArrowUp from "#/icons/angle-up-solid.svg?react";
@@ -9,6 +10,8 @@ import ArrowDown from "#/icons/angle-down-solid.svg?react";
 import CheckCircle from "#/icons/check-circle-solid.svg?react";
 import XCircle from "#/icons/x-circle-solid.svg?react";
 import { cn } from "#/utils/utils";
+import { useConfig } from "#/hooks/query/use-config";
+import { BILLING_SETTINGS } from "#/utils/feature-flags";

 interface ExpandableMessageProps {
  id?: string;
@@ -23,6 +26,7 @@ export function ExpandableMessage({
  type,
  success,
 }: ExpandableMessageProps) {
+  const { data: config } = useConfig();
  const { t, i18n } = useTranslation();
  const [showDetails, setShowDetails] = useState(true);
  const [headline, setHeadline] = useState("");
@@ -38,6 +42,28 @@ export function ExpandableMessage({

  const statusIconClasses = "h-4 w-4 ml-2 inline";

+  if (
+    BILLING_SETTINGS() &&
+    config?.APP_MODE === "saas" &&
+    id === "STATUS$ERROR_LLM_OUT_OF_CREDITS"
+  ) {
+    return (
+      <div className="flex gap-2 items-center justify-start border-l-2 pl-2 my-2 py-2 border-danger">
+        <div className="text-sm w-full">
+          <div className="font-bold text-danger">
+            {t("STATUS$ERROR_LLM_OUT_OF_CREDITS")}
+          </div>
+          <Link
+            className="mt-2 mb-2 w-full h-10 rounded flex items-center justify-center gap-2 bg-primary text-[#0D0F11]"
+            to="/settings/billing"
+          >
+            {t("BILLING$CLICK_TO_TOP_UP")}
+          </Link>
+        </div>
+      </div>
+    );
+  }
+
  return (
    <div
      className={cn(
--- a/frontend/src/components/features/chat/interactive-chat-box.tsx
+++ b/frontend/src/components/features/chat/interactive-chat-box.tsx
@@ -59,7 +59,7 @@ export function InteractiveChatBox({
      <div
        className={cn(
          "flex items-end gap-1",
-          "bg-neutral-700 border border-neutral-600 rounded-lg px-2",
+          "bg-tertiary border border-neutral-600 rounded-lg px-2",
          "transition-colors duration-200",
          "hover:border-neutral-500 focus-within:border-neutral-500",
        )}
--- a/frontend/src/components/features/chat/typing-indicator.tsx
+++ b/frontend/src/components/features/chat/typing-indicator.tsx
@@ -1,6 +1,6 @@
 export function TypingIndicator() {
  return (
-    <div className="flex items-center space-x-1.5 bg-neutral-700 px-3 py-1.5 rounded-full">
+    <div className="flex items-center space-x-1.5 bg-tertiary px-3 py-1.5 rounded-full">
      <span
        className="w-1.5 h-1.5 bg-gray-400 rounded-full animate-[bounce_0.5s_infinite] translate-y-[-2px]"
        style={{ animationDelay: "0ms" }}
--- a/frontend/src/components/features/context-menu/context-menu.tsx
+++ b/frontend/src/components/features/context-menu/context-menu.tsx
@@ -18,7 +18,7 @@ export function ContextMenu({
    <ul
      data-testid={testId}
      ref={ref}
-      className={cn("bg-[#404040] rounded-md w-[140px]", className)}
+      className={cn("bg-tertiary rounded-md w-[140px]", className)}
    >
      {children}
    </ul>
--- a/frontend/src/components/features/controls/agent-status-bar.tsx
+++ b/frontend/src/components/features/controls/agent-status-bar.tsx
@@ -9,12 +9,21 @@ import {
  useWsClient,
  WsClientProviderStatus,
 } from "#/context/ws-client-provider";
+import { useNotification } from "#/hooks/useNotification";
+import { browserTab } from "#/utils/browser-tab";
+
+const notificationStates = [
+  AgentState.AWAITING_USER_INPUT,
+  AgentState.FINISHED,
+  AgentState.AWAITING_USER_CONFIRMATION,
+];

 export function AgentStatusBar() {
  const { t, i18n } = useTranslation();
  const { curAgentState } = useSelector((state: RootState) => state.agent);
  const { curStatusMessage } = useSelector((state: RootState) => state.status);
  const { status } = useWsClient();
+  const { notify } = useNotification();

  const [statusMessage, setStatusMessage] = React.useState<string>("");

@@ -45,13 +54,40 @@ export function AgentStatusBar() {
    updateStatusMessage();
  }, [curStatusMessage.id]);

+  // Handle window focus/blur
+  React.useEffect(() => {
+    if (typeof window === "undefined") return undefined;
+
+    const handleFocus = () => {
+      browserTab.stopNotification();
+    };
+
+    window.addEventListener("focus", handleFocus);
+    return () => {
+      window.removeEventListener("focus", handleFocus);
+      browserTab.stopNotification();
+    };
+  }, []);
+
  React.useEffect(() => {
    if (status === WsClientProviderStatus.DISCONNECTED) {
      setStatusMessage("Connecting...");
    } else {
      setStatusMessage(AGENT_STATUS_MAP[curAgentState].message);
+      if (notificationStates.includes(curAgentState)) {
+        const message = t(AGENT_STATUS_MAP[curAgentState].message);
+        notify(t(AGENT_STATUS_MAP[curAgentState].message), {
+          body: t(`Agent state changed to ${curAgentState}`),
+          playSound: true,
+        });
+
+        // Update browser tab if window exists and is not focused
+        if (typeof document !== "undefined" && !document.hasFocus()) {
+          browserTab.startNotification(message);
+        }
+      }
    }
-  }, [curAgentState]);
+  }, [curAgentState, notify, t]);

  return (
    <div className="flex flex-col items-center">
--- a/frontend/src/components/features/conversation-panel/confirm-delete-modal.tsx
+++ b/frontend/src/components/features/conversation-panel/confirm-delete-modal.tsx
@@ -1,10 +1,10 @@
-import { ModalButton } from "#/components/shared/buttons/modal-button";
 import {
  BaseModalDescription,
  BaseModalTitle,
 } from "#/components/shared/modals/confirmation-modals/base-modal";
 import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
 import { ModalBody } from "#/components/shared/modals/modal-body";
+import { BrandButton } from "../settings/brand-button";

 interface ConfirmDeleteModalProps {
  onConfirm: () => void;
@@ -17,7 +17,7 @@ export function ConfirmDeleteModal({
 }: ConfirmDeleteModalProps) {
  return (
    <ModalBackdrop>
-      <ModalBody className="items-start">
+      <ModalBody className="items-start border border-tertiary">
        <div className="flex flex-col gap-2">
          <BaseModalTitle title="Are you sure you want to delete this project?" />
          <BaseModalDescription description="All data associated with this project will be lost." />
@@ -26,16 +26,22 @@ export function ConfirmDeleteModal({
          className="flex flex-col gap-2 w-full"
          onClick={(event) => event.stopPropagation()}
        >
-          <ModalButton
+          <BrandButton
+            type="button"
+            variant="primary"
            onClick={onConfirm}
-            className="bg-danger font-bold"
-            text="Confirm"
-          />
-          <ModalButton
+            className="w-full"
+          >
+            Confirm
+          </BrandButton>
+          <BrandButton
+            type="button"
+            variant="secondary"
            onClick={onCancel}
-            className="bg-neutral-500 font-bold"
-            text="Cancel"
-          />
+            className="w-full"
+          >
+            Cancel
+          </BrandButton>
        </div>
      </ModalBody>
    </ModalBackdrop>
--- a/frontend/src/components/features/conversation-panel/conversation-card.tsx
+++ b/frontend/src/components/features/conversation-panel/conversation-card.tsx
@@ -101,9 +101,11 @@ export function ConversationCard({
          "h-auto w-fit rounded-xl border border-[#525252]",
      )}
    >
-      <div className="flex items-center justify-between">
-        <div className="flex items-center gap-2 w-full">
-          {isActive && <span className="w-2 h-2 bg-blue-500 rounded-full" />}
+      <div className="flex items-center justify-between w-full">
+        <div className="flex items-center gap-2 flex-1 min-w-0 overflow-hidden mr-2">
+          {isActive && (
+            <span className="w-2 h-2 bg-blue-500 rounded-full flex-shrink-0" />
+          )}
          {titleMode === "edit" && (
            <input
              ref={inputRef}
@@ -119,7 +121,8 @@ export function ConversationCard({
          {titleMode === "view" && (
            <p
              data-testid="conversation-card-title"
-              className="text-sm leading-6 font-semibold bg-transparent w-full"
+              className="text-sm leading-6 font-semibold bg-transparent truncate overflow-hidden"
+              title={title}
            >
              {title}
            </p>
--- a/frontend/src/components/features/conversation-panel/exit-conversation-modal.tsx
+++ b/frontend/src/components/features/conversation-panel/exit-conversation-modal.tsx
@@ -25,7 +25,7 @@ export function ExitConversationModal({
          <ModalButton
            text="Cancel"
            onClick={onClose}
-            className="bg-neutral-700 flex-1"
+            className="bg-tertiary flex-1"
          />
        </div>
      </ModalBody>
--- a/frontend/src/components/features/feedback/feedback-form.tsx
+++ b/frontend/src/components/features/feedback/feedback-form.tsx
@@ -4,7 +4,7 @@ import { useTranslation } from "react-i18next";
 import { I18nKey } from "#/i18n/declaration";
 import { Feedback } from "#/api/open-hands.types";
 import { useSubmitFeedback } from "#/hooks/mutation/use-submit-feedback";
-import { ModalButton } from "#/components/shared/buttons/modal-button";
+import { BrandButton } from "../settings/brand-button";

 const FEEDBACK_VERSION = "1.0";
 const VIEWER_PAGE = "https://www.all-hands.dev/share";
@@ -121,18 +121,23 @@ export function FeedbackForm({ onClose, polarity }: FeedbackFormProps) {
      </div>

      <div className="flex gap-2">
-        <ModalButton
-          disabled={isPending}
+        <BrandButton
          type="submit"
-          text={t(I18nKey.FEEDBACK$SHARE_LABEL)}
-          className="bg-[#4465DB] grow"
-        />
-        <ModalButton
-          disabled={isPending}
-          text={t(I18nKey.FEEDBACK$CANCEL_LABEL)}
+          variant="primary"
+          className="grow"
+          isDisabled={isPending}
+        >
+          {t(I18nKey.FEEDBACK$SHARE_LABEL)}
+        </BrandButton>
+        <BrandButton
+          type="button"
+          variant="secondary"
+          className="grow"
          onClick={onClose}
-          className="bg-[#737373] grow"
-        />
+          isDisabled={isPending}
+        >
+          {t(I18nKey.FEEDBACK$CANCEL_LABEL)}
+        </BrandButton>
      </div>
    </form>
  );
--- a/frontend/src/components/features/feedback/feedback-modal.tsx
+++ b/frontend/src/components/features/feedback/feedback-modal.tsx
@@ -21,7 +21,7 @@ export function FeedbackModal({

  return (
    <ModalBackdrop onClose={onClose}>
-      <ModalBody>
+      <ModalBody className="border border-tertiary">
        <BaseModalTitle title="Feedback" />
        <BaseModalDescription description="To help us improve, we collect feedback from your interactions to improve our prompts. By submitting this form, you consent to us collecting this data." />
        <FeedbackForm onClose={onClose} polarity={polarity} />
--- a/frontend/src/components/features/file-explorer/file-explorer.tsx
+++ b/frontend/src/components/features/file-explorer/file-explorer.tsx
@@ -10,7 +10,8 @@ import { useListFiles } from "#/hooks/query/use-list-files";
 import { cn } from "#/utils/utils";
 import { FileExplorerHeader } from "./file-explorer-header";
 import { useVSCodeUrl } from "#/hooks/query/use-vscode-url";
-import { OpenVSCodeButton } from "#/components/shared/buttons/open-vscode-button";
+import { BrandButton } from "../settings/brand-button";
+import VSCodeIcon from "#/assets/vscode-alt.svg?react";

 interface FileExplorerProps {
  isOpen: boolean;
@@ -77,10 +78,17 @@ export function FileExplorer({ isOpen, onToggle }: FileExplorerProps) {
            </div>
          )}
          {isOpen && (
-            <OpenVSCodeButton
-              onClick={handleOpenVSCode}
+            <BrandButton
+              testId="open-vscode-button"
+              type="button"
+              variant="secondary"
+              className="w-full text-content border-content"
              isDisabled={RUNTIME_INACTIVE_STATES.includes(curAgentState)}
-            />
+              onClick={handleOpenVSCode}
+              startContent={<VSCodeIcon width={20} height={20} />}
+            >
+              {t(I18nKey.VSCODE$OPEN)}
+            </BrandButton>
          )}
        </div>
      </div>
--- a/frontend/src/components/features/github/github-repositories-suggestion-box.tsx
+++ b/frontend/src/components/features/github/github-repositories-suggestion-box.tsx
@@ -3,14 +3,14 @@ import { useTranslation } from "react-i18next";
 import { useNavigate } from "react-router";
 import { I18nKey } from "#/i18n/declaration";
 import { SuggestionBox } from "#/components/features/suggestions/suggestion-box";
-import GitHubLogo from "#/assets/branding/github-logo.svg?react";
 import { GitHubRepositorySelector } from "./github-repo-selector";
-import { ModalButton } from "#/components/shared/buttons/modal-button";
 import { useAppRepositories } from "#/hooks/query/use-app-repositories";
 import { useSearchRepositories } from "#/hooks/query/use-search-repositories";
 import { useUserRepositories } from "#/hooks/query/use-user-repositories";
 import { sanitizeQuery } from "#/utils/sanitize-query";
 import { useDebounce } from "#/hooks/use-debounce";
+import { BrandButton } from "../settings/brand-button";
+import GitHubLogo from "#/assets/branding/github-logo.svg?react";

 interface GitHubRepositoriesSuggestionBoxProps {
  handleSubmit: () => void;
@@ -62,13 +62,16 @@ export function GitHubRepositoriesSuggestionBox({
            userRepositories={repositories}
          />
        ) : (
-          <ModalButton
+          <BrandButton
            testId="connect-to-github"
-            text={t(I18nKey.GITHUB$CONNECT)}
-            icon={<GitHubLogo width={20} height={20} />}
-            className="bg-[#791B80] w-full"
+            type="button"
+            variant="secondary"
+            className="w-full text-content border-content"
            onClick={handleConnectToGitHub}
-          />
+            startContent={<GitHubLogo width={20} height={20} />}
+          >
+            {t(I18nKey.GITHUB$CONNECT)}
+          </BrandButton>
        )
      }
    />
--- a/frontend/src/components/features/settings/brand-button.tsx
+++ b/frontend/src/components/features/settings/brand-button.tsx
@@ -7,6 +7,7 @@ interface BrandButtonProps {
  isDisabled?: boolean;
  className?: string;
  onClick?: () => void;
+  startContent?: React.ReactNode;
 }

 export function BrandButton({
@@ -17,6 +18,7 @@ export function BrandButton({
  isDisabled,
  className,
  onClick,
+  startContent,
 }: React.PropsWithChildren<BrandButtonProps>) {
  return (
    <button
@@ -30,9 +32,11 @@ export function BrandButton({
        "w-fit p-2 rounded disabled:opacity-30 disabled:cursor-not-allowed",
        variant === "primary" && "bg-primary text-[#0D0F11]",
        variant === "secondary" && "border border-primary text-primary",
+        startContent && "flex items-center justify-center gap-2",
        className,
      )}
    >
+      {startContent}
      {children}
    </button>
  );
--- a/frontend/src/components/features/suggestions/suggestion-item.tsx
+++ b/frontend/src/components/features/suggestions/suggestion-item.tsx
@@ -11,7 +11,7 @@ interface SuggestionItemProps {
 export function SuggestionItem({ suggestion, onClick }: SuggestionItemProps) {
  const { t } = useTranslation();
  return (
-    <li className="list-none border border-neutral-600 rounded-xl hover:bg-neutral-700 flex-1">
+    <li className="list-none border border-neutral-600 rounded-xl hover:bg-tertiary flex-1">
      <button
        type="button"
        data-testid="suggestion"
--- a/frontend/src/components/features/trajectory/trajectory-actions.tsx
+++ b/frontend/src/components/features/trajectory/trajectory-actions.tsx
@@ -1,3 +1,4 @@
+import { useTranslation } from "react-i18next";
 import ThumbsUpIcon from "#/icons/thumbs-up.svg?react";
 import ThumbDownIcon from "#/icons/thumbs-down.svg?react";
 import ExportIcon from "#/icons/export.svg?react";
@@ -14,22 +15,27 @@ export function TrajectoryActions({
  onNegativeFeedback,
  onExportTrajectory,
 }: TrajectoryActionsProps) {
+  const { t } = useTranslation();
+
  return (
    <div data-testid="feedback-actions" className="flex gap-1">
      <TrajectoryActionButton
        testId="positive-feedback"
        onClick={onPositiveFeedback}
        icon={<ThumbsUpIcon width={15} height={15} />}
+        tooltip={t("BUTTON$MARK_HELPFUL")}
      />
      <TrajectoryActionButton
        testId="negative-feedback"
        onClick={onNegativeFeedback}
        icon={<ThumbDownIcon width={15} height={15} />}
+        tooltip={t("BUTTON$MARK_NOT_HELPFUL")}
      />
      <TrajectoryActionButton
        testId="export-trajectory"
        onClick={onExportTrajectory}
        icon={<ExportIcon width={15} height={15} />}
+        tooltip={t("BUTTON$EXPORT_CONVERSATION")}
      />
    </div>
  );
--- a/frontend/src/components/features/waitlist/waitlist-modal.tsx
+++ b/frontend/src/components/features/waitlist/waitlist-modal.tsx
@@ -1,13 +1,13 @@
 import React from "react";
-import GitHubLogo from "#/assets/branding/github-logo.svg?react";
 import AllHandsLogo from "#/assets/branding/all-hands-logo.svg?react";
 import { JoinWaitlistAnchor } from "./join-waitlist-anchor";
 import { WaitlistMessage } from "./waitlist-message";
 import { ModalBackdrop } from "#/components/shared/modals/modal-backdrop";
-import { ModalButton } from "#/components/shared/buttons/modal-button";
 import { ModalBody } from "#/components/shared/modals/modal-body";
 import { TOSCheckbox } from "./tos-checkbox";
 import { handleCaptureConsent } from "#/utils/handle-capture-consent";
+import { BrandButton } from "../settings/brand-button";
+import GitHubLogo from "#/assets/branding/github-logo.svg?react";

 interface WaitlistModalProps {
  ghTokenIsSet: boolean;
@@ -29,20 +29,23 @@ export function WaitlistModal({

  return (
    <ModalBackdrop>
-      <ModalBody>
+      <ModalBody className="border border-tertiary">
        <AllHandsLogo width={68} height={46} />
        <WaitlistMessage content={ghTokenIsSet ? "waitlist" : "sign-in"} />

        <TOSCheckbox onChange={() => setIsTosAccepted((prev) => !prev)} />

        {!ghTokenIsSet && (
-          <ModalButton
-            disabled={!isTosAccepted}
-            text="Connect to GitHub"
-            icon={<GitHubLogo width={20} height={20} />}
-            className="bg-[#791B80] w-full"
+          <BrandButton
+            isDisabled={!isTosAccepted}
+            type="button"
+            variant="primary"
            onClick={handleGitHubAuth}
-          />
+            className="w-full"
+            startContent={<GitHubLogo width={20} height={20} />}
+          >
+            Connect to GitHub
+          </BrandButton>
        )}
        {ghTokenIsSet && <JoinWaitlistAnchor />}
      </ModalBody>
--- a/frontend/src/components/layout/nav-tab.tsx
+++ b/frontend/src/components/layout/nav-tab.tsx
@@ -15,18 +15,19 @@ export function NavTab({ to, label, icon, isBeta }: NavTabProps) {
      end
      key={to}
      to={to}
-      className={({ isActive }) =>
-        cn(
-          "px-2 border-b border-r border-neutral-600 bg-base flex-1",
-          "first-of-type:rounded-tl-xl last-of-type:rounded-tr-xl last-of-type:border-r-0",
-          "flex items-center gap-2",
-          isActive && "bg-base-secondary",
-        )
-      }
+      className={cn(
+        "px-2 border-b border-r border-neutral-600 bg-base-secondary flex-1",
+        "first-of-type:rounded-tl-xl last-of-type:rounded-tr-xl last-of-type:border-r-0",
+        "flex items-center gap-2",
+      )}
    >
-      {icon}
-      {label}
-      {isBeta && <BetaBadge />}
+      {({ isActive }) => (
+        <>
+          <div className={cn(isActive && "text-primary")}>{icon}</div>
+          {label}
+          {isBeta && <BetaBadge />}
+        </>
+      )}
    </NavLink>
  );
 }
--- a/frontend/src/components/shared/action-tooltip.tsx
+++ b/frontend/src/components/shared/action-tooltip.tsx
@@ -27,7 +27,7 @@ export function ActionTooltip({ type, onClick }: ActionTooltipProps) {
            ? t(I18nKey.ACTION$CONFIRM)
            : t(I18nKey.ACTION$REJECT)
        }
-        className="bg-neutral-700 rounded-full p-1 hover:bg-base-secondary"
+        className="bg-tertiary rounded-full p-1 hover:bg-base-secondary"
        onClick={onClick}
      >
        {type === "confirm" ? <ConfirmIcon /> : <RejectIcon />}
--- a/frontend/src/components/shared/buttons/editor-action-button.tsx
+++ b/frontend/src/components/shared/buttons/editor-action-button.tsx
@@ -19,7 +19,7 @@ export function EditorActionButton({
      disabled={disabled}
      className={cn(
        "text-sm py-0.5 rounded w-20",
-        "hover:bg-neutral-700 disabled:opacity-50 disabled:cursor-not-allowed",
+        "hover:bg-tertiary disabled:opacity-50 disabled:cursor-not-allowed",
        className,
      )}
    >
--- a/frontend/src/components/shared/buttons/open-vscode-button.tsx
+++ b/frontend/src/components/shared/buttons/open-vscode-button.tsx
@@ -1,35 +0,0 @@
-import { useTranslation } from "react-i18next";
-import { I18nKey } from "#/i18n/declaration";
-import { cn } from "#/utils/utils";
-import VSCodeIcon from "#/assets/vscode-alt.svg?react";
-
-interface OpenVSCodeButtonProps {
-  isDisabled: boolean;
-  onClick: () => void;
-}
-
-export function OpenVSCodeButton({
-  isDisabled,
-  onClick,
-}: OpenVSCodeButtonProps) {
-  const { t } = useTranslation();
-  const buttonText = t(I18nKey.VSCODE$OPEN);
-
-  return (
-    <button
-      type="button"
-      onClick={onClick}
-      disabled={isDisabled}
-      className={cn(
-        "mt-auto mb-2 w-full h-10 text-white rounded flex items-center justify-center gap-2 transition-colors",
-        isDisabled
-          ? "bg-neutral-600 cursor-not-allowed"
-          : "bg-[#4465DB] hover:bg-[#3451C7]",
-      )}
-      aria-label={buttonText}
-    >
-      <VSCodeIcon width={20} height={20} />
-      {buttonText}
-    </button>
-  );
-}
--- a/frontend/src/components/shared/buttons/trajectory-action-button.tsx
+++ b/frontend/src/components/shared/buttons/trajectory-action-button.tsx
@@ -1,15 +1,19 @@
+import { Tooltip } from "@heroui/react";
+
 interface TrajectoryActionButtonProps {
  testId?: string;
  onClick: () => void;
  icon: React.ReactNode;
+  tooltip?: string;
 }

 export function TrajectoryActionButton({
  testId,
  onClick,
  icon,
+  tooltip,
 }: TrajectoryActionButtonProps) {
-  return (
+  const button = (
    <button
      type="button"
      data-testid={testId}
@@ -19,4 +23,14 @@ export function TrajectoryActionButton({
      {icon}
    </button>
  );
+
+  if (tooltip) {
+    return (
+      <Tooltip content={tooltip} closeDelay={100}>
+        {button}
+      </Tooltip>
+    );
+  }
+
+  return button;
 }
--- a/frontend/src/components/shared/modals/base-modal/base-modal.tsx
+++ b/frontend/src/components/shared/modals/base-modal/base-modal.tsx
@@ -43,7 +43,7 @@ export function BaseModal({
      backdrop="blur"
      hideCloseButton
      size="sm"
-      className="bg-base rounded-lg"
+      className="bg-base-secondary rounded-lg"
    >
      <ModalContent className={contentClassName}>
        {(closeModal) => (
--- a/frontend/src/components/shared/modals/modal-body.tsx
+++ b/frontend/src/components/shared/modals/modal-body.tsx
@@ -12,7 +12,7 @@ export function ModalBody({ testID, children, className }: ModalBodyProps) {
    <div
      data-testid={testID}
      className={cn(
-        "bg-base flex flex-col gap-6 items-center w-[384px] p-6 rounded-xl",
+        "bg-base-secondary flex flex-col gap-6 items-center w-[384px] p-6 rounded-xl",
        className,
      )}
    >
--- a/frontend/src/components/shared/modals/security/invariant/invariant.tsx
+++ b/frontend/src/components/shared/modals/security/invariant/invariant.tsx
@@ -127,7 +127,7 @@ function SecurityInvariant() {
      <>
        <div className="flex justify-between items-center border-b border-neutral-600 mb-4 p-4">
          <h2 className="text-2xl">{t(I18nKey.INVARIANT$LOG_LABEL)}</h2>
-          <Button onPress={() => exportTraces()} className="bg-neutral-700">
+          <Button onPress={() => exportTraces()} className="bg-tertiary">
            {t(I18nKey.INVARIANT$EXPORT_TRACE_LABEL)}
          </Button>
        </div>
@@ -161,7 +161,7 @@ function SecurityInvariant() {
        <div className="flex justify-between items-center border-b border-neutral-600 mb-4 p-4">
          <h2 className="text-2xl">{t(I18nKey.INVARIANT$POLICY_LABEL)}</h2>
          <Button
-            className="bg-neutral-700"
+            className="bg-tertiary"
            onPress={() => updatePolicy({ policy })}
          >
            {t(I18nKey.INVARIANT$UPDATE_POLICY_LABEL)}
@@ -183,7 +183,7 @@ function SecurityInvariant() {
        <div className="flex justify-between items-center border-b border-neutral-600 mb-4 p-4">
          <h2 className="text-2xl">{t(I18nKey.INVARIANT$SETTINGS_LABEL)}</h2>
          <Button
-            className="bg-neutral-700"
+            className="bg-tertiary"
            onPress={() => updateRiskSeverity({ riskSeverity: selectedRisk })}
          >
            {t(I18nKey.INVARIANT$UPDATE_SETTINGS_LABEL)}
--- a/frontend/src/components/shared/modals/settings/model-selector.tsx
+++ b/frontend/src/components/shared/modals/settings/model-selector.tsx
@@ -6,7 +6,7 @@ import {
 import React from "react";
 import { useTranslation } from "react-i18next";
 import { I18nKey } from "#/i18n/declaration";
-import { mapProvider, MAP_PROVIDER } from "#/utils/map-provider";
+import { mapProvider } from "#/utils/map-provider";
 import { VERIFIED_MODELS, VERIFIED_PROVIDERS } from "#/utils/verified-models";
 import { extractModelAndProvider } from "#/utils/extract-model-and-provider";

@@ -39,16 +39,11 @@ export function ModelSelector({
  }, [currentModel]);

  const handleChangeProvider = (provider: string) => {
-    // Find the actual provider key from MAP_PROVIDER if a display name was provided
-    const providerKey = Object.entries(MAP_PROVIDER).find(
-      ([_, displayName]) => displayName === provider
-    )?.[0] || provider;
-
-    setSelectedProvider(providerKey);
+    setSelectedProvider(provider);
    setSelectedModel(null);

-    const separator = models[providerKey]?.separator || "";
-    setLitellmId(providerKey + separator);
+    const separator = models[provider]?.separator || "";
+    setLitellmId(provider + separator);
  };

  const handleChangeModel = (model: string) => {
--- a/frontend/src/components/shared/modals/settings/settings-modal.tsx
+++ b/frontend/src/components/shared/modals/settings/settings-modal.tsx
@@ -21,7 +21,7 @@ export function SettingsModal({ onClose, settings }: SettingsModalProps) {
    <ModalBackdrop>
      <div
        data-testid="ai-config-modal"
-        className="bg-base min-w-[384px] p-6 rounded-xl flex flex-col gap-2"
+        className="bg-base-secondary min-w-[384px] p-6 rounded-xl flex flex-col gap-2 border border-tertiary"
      >
        {aiConfigOptions.error && (
          <p className="text-danger text-xs">{aiConfigOptions.error.message}</p>
--- a/frontend/src/components/shared/task-form.tsx
+++ b/frontend/src/components/shared/task-form.tsx
@@ -70,7 +70,7 @@ export function TaskForm({ ref }: TaskFormProps) {
        <div
          className={cn(
            "border border-neutral-600 px-4 rounded-lg text-[17px] leading-5 w-full transition-colors duration-200",
-            inputIsFocused ? "bg-neutral-600" : "bg-neutral-700",
+            inputIsFocused ? "bg-neutral-600" : "bg-tertiary",
            "hover:border-neutral-500 focus-within:border-neutral-500",
          )}
        >
--- a/frontend/src/hooks/mutation/use-save-settings.ts
+++ b/frontend/src/hooks/mutation/use-save-settings.ts
@@ -20,6 +20,7 @@ const saveSettingsMutationFn = async (settings: Partial<PostSettings>) => {
    github_token: settings.github_token,
    unset_github_token: settings.unset_github_token,
    enable_default_condenser: settings.ENABLE_DEFAULT_CONDENSER,
+    enable_sound_notifications: settings.ENABLE_SOUND_NOTIFICATIONS,
    user_consents_to_analytics: settings.user_consents_to_analytics,
  };

--- a/frontend/src/hooks/query/use-settings.ts
+++ b/frontend/src/hooks/query/use-settings.ts
@@ -20,6 +20,7 @@ const getSettingsQueryFn = async () => {
    REMOTE_RUNTIME_RESOURCE_FACTOR: apiSettings.remote_runtime_resource_factor,
    GITHUB_TOKEN_IS_SET: apiSettings.github_token_is_set,
    ENABLE_DEFAULT_CONDENSER: apiSettings.enable_default_condenser,
+    ENABLE_SOUND_NOTIFICATIONS: apiSettings.enable_sound_notifications,
    USER_CONSENTS_TO_ANALYTICS: apiSettings.user_consents_to_analytics,
  };
 };
--- a/frontend/src/hooks/use-terminal.ts
+++ b/frontend/src/hooks/use-terminal.ts
@@ -40,7 +40,7 @@ export const useTerminal = ({
      fontFamily: "Menlo, Monaco, 'Courier New', monospace",
      fontSize: 14,
      theme: {
-        background: "#262626",
+        background: "#24272E",
      },
    });

--- a/frontend/src/hooks/useNotification.ts
+++ b/frontend/src/hooks/useNotification.ts
@@ -0,0 +1,56 @@
+import { useCallback, useRef } from "react";
+import notificationSound from "../assets/notification.mp3";
+import { useCurrentSettings } from "../context/settings-context";
+
+export const useNotification = () => {
+  const { settings } = useCurrentSettings();
+  const audioRef = useRef<HTMLAudioElement | undefined>(undefined);
+
+  // Initialize audio only in browser environment
+  if (typeof window !== "undefined" && !audioRef.current) {
+    audioRef.current = new Audio(notificationSound);
+    audioRef.current.volume = 0.5;
+  }
+
+  const notify = useCallback(
+    async (
+      title: string,
+      options?: NotificationOptions & { playSound?: boolean },
+    ): Promise<Notification | undefined> => {
+      if (typeof window === "undefined") return undefined;
+
+      // Only play sound if:
+      // 1. Explicitly requested via playSound option
+      // 2. Sound notifications are enabled in settings
+      // 3. Audio is available
+      // 4. Not a settings-related notification
+      if (
+        options?.playSound === true && // Must be explicitly true
+        settings?.ENABLE_SOUND_NOTIFICATIONS &&
+        audioRef.current &&
+        !title.includes("BUTTON$") // Don't play for button/settings actions
+      ) {
+        // Reset and play sound
+        audioRef.current.currentTime = 0;
+        audioRef.current.play().catch(() => {
+          // Ignore autoplay errors
+        });
+      }
+
+      if (Notification.permission === "default") {
+        await Notification.requestPermission();
+      }
+
+      if (Notification.permission === "granted") {
+        // Remove playSound from options before passing to Notification
+        const { playSound, ...notificationOptions } = options || {};
+        return new Notification(title, notificationOptions);
+      }
+
+      return undefined;
+    },
+    [settings?.ENABLE_SOUND_NOTIFICATIONS],
+  );
+
+  return { notify };
+};
--- a/frontend/src/i18n/declaration.ts
+++ b/frontend/src/i18n/declaration.ts
@@ -0,0 +1,316 @@
+// this file generate by script, don't modify it manually!!!
+export enum I18nKey {
+  APP$TITLE = "APP$TITLE",
+  BROWSER$TITLE = "BROWSER$TITLE",
+  BROWSER$EMPTY_MESSAGE = "BROWSER$EMPTY_MESSAGE",
+  SETTINGS$TITLE = "SETTINGS$TITLE",
+  PROJECT$START_NEW = "PROJECT$START_NEW",
+  PROJECT$NEW = "PROJECT$NEW",
+  ACCOUNT_SETTINGS$TITLE = "ACCOUNT_SETTINGS$TITLE",
+  WORKSPACE$TITLE = "WORKSPACE$TITLE",
+  WORKSPACE$TERMINAL_TAB_LABEL = "WORKSPACE$TERMINAL_TAB_LABEL",
+  TERMINAL$WAITING_FOR_CLIENT = "TERMINAL$WAITING_FOR_CLIENT",
+  CODE_EDITOR$FILE_SAVED_SUCCESSFULLY = "CODE_EDITOR$FILE_SAVED_SUCCESSFULLY",
+  CODE_EDITOR$SAVING_LABEL = "CODE_EDITOR$SAVING_LABEL",
+  CODE_EDITOR$SAVE_LABEL = "CODE_EDITOR$SAVE_LABEL",
+  CODE_EDITOR$OPTIONS = "CODE_EDITOR$OPTIONS",
+  CODE_EDITOR$FILE_SAVE_ERROR = "CODE_EDITOR$FILE_SAVE_ERROR",
+  CODE_EDITOR$EMPTY_MESSAGE = "CODE_EDITOR$EMPTY_MESSAGE",
+  FILE_SERVICE$SELECT_FILE_ERROR = "FILE_SERVICE$SELECT_FILE_ERROR",
+  FILE_SERVICE$UPLOAD_FILES_ERROR = "FILE_SERVICE$UPLOAD_FILES_ERROR",
+  FILE_SERVICE$LIST_FILES_ERROR = "FILE_SERVICE$LIST_FILES_ERROR",
+  FILE_SERVICE$SAVE_FILE_ERROR = "FILE_SERVICE$SAVE_FILE_ERROR",
+  SUGGESTIONS$INCREASE_TEST_COVERAGE = "SUGGESTIONS$INCREASE_TEST_COVERAGE",
+  SUGGESTIONS$AUTO_MERGE_PRS = "SUGGESTIONS$AUTO_MERGE_PRS",
+  SUGGESTIONS$FIX_README = "SUGGESTIONS$FIX_README",
+  SUGGESTIONS$CLEAN_DEPENDENCIES = "SUGGESTIONS$CLEAN_DEPENDENCIES",
+  FILE_SERVICE$INVALID_FILE_PATH = "FILE_SERVICE$INVALID_FILE_PATH",
+  WORKSPACE$PLANNER_TAB_LABEL = "WORKSPACE$PLANNER_TAB_LABEL",
+  WORKSPACE$JUPYTER_TAB_LABEL = "WORKSPACE$JUPYTER_TAB_LABEL",
+  WORKSPACE$CODE_EDITOR_TAB_LABEL = "WORKSPACE$CODE_EDITOR_TAB_LABEL",
+  WORKSPACE$BROWSER_TAB_LABEL = "WORKSPACE$BROWSER_TAB_LABEL",
+  VSCODE$OPEN = "VSCODE$OPEN",
+  INCREASE_TEST_COVERAGE = "INCREASE_TEST_COVERAGE",
+  AUTO_MERGE_PRS = "AUTO_MERGE_PRS",
+  FIX_README = "FIX_README",
+  CLEAN_DEPENDENCIES = "CLEAN_DEPENDENCIES",
+  CONFIGURATION$OPENHANDS_WORKSPACE_DIRECTORY_INPUT_LABEL = "CONFIGURATION$OPENHANDS_WORKSPACE_DIRECTORY_INPUT_LABEL",
+  LLM$PROVIDER = "LLM$PROVIDER",
+  LLM$SELECT_PROVIDER_PLACEHOLDER = "LLM$SELECT_PROVIDER_PLACEHOLDER",
+  API$KEY = "API$KEY",
+  API$DONT_KNOW_KEY = "API$DONT_KNOW_KEY",
+  BUTTON$SAVE = "BUTTON$SAVE",
+  BUTTON$CLOSE = "BUTTON$CLOSE",
+  BUTTON$RESET_TO_DEFAULTS = "BUTTON$RESET_TO_DEFAULTS",
+  MODAL$CONFIRM_RESET_TITLE = "MODAL$CONFIRM_RESET_TITLE",
+  MODAL$CONFIRM_RESET_MESSAGE = "MODAL$CONFIRM_RESET_MESSAGE",
+  MODAL$END_SESSION_TITLE = "MODAL$END_SESSION_TITLE",
+  MODAL$END_SESSION_MESSAGE = "MODAL$END_SESSION_MESSAGE",
+  BUTTON$END_SESSION = "BUTTON$END_SESSION",
+  BUTTON$CANCEL = "BUTTON$CANCEL",
+  LANGUAGE$LABEL = "LANGUAGE$LABEL",
+  GITHUB$TOKEN_LABEL = "GITHUB$TOKEN_LABEL",
+  GITHUB$TOKEN_OPTIONAL = "GITHUB$TOKEN_OPTIONAL",
+  GITHUB$GET_TOKEN = "GITHUB$GET_TOKEN",
+  COMMON$HERE = "COMMON$HERE",
+  ANALYTICS$ENABLE = "ANALYTICS$ENABLE",
+  GITHUB$TOKEN_INVALID = "GITHUB$TOKEN_INVALID",
+  BUTTON$DISCONNECT = "BUTTON$DISCONNECT",
+  GITHUB$CONFIGURE_REPOS = "GITHUB$CONFIGURE_REPOS",
+  COMMON$CLICK_FOR_INSTRUCTIONS = "COMMON$CLICK_FOR_INSTRUCTIONS",
+  LLM$SELECT_MODEL_PLACEHOLDER = "LLM$SELECT_MODEL_PLACEHOLDER",
+  LLM$MODEL = "LLM$MODEL",
+  CONFIGURATION$OPENHANDS_WORKSPACE_DIRECTORY_INPUT_PLACEHOLDER = "CONFIGURATION$OPENHANDS_WORKSPACE_DIRECTORY_INPUT_PLACEHOLDER",
+  CONFIGURATION$MODAL_TITLE = "CONFIGURATION$MODAL_TITLE",
+  CONFIGURATION$MODEL_SELECT_LABEL = "CONFIGURATION$MODEL_SELECT_LABEL",
+  CONFIGURATION$MODEL_SELECT_PLACEHOLDER = "CONFIGURATION$MODEL_SELECT_PLACEHOLDER",
+  CONFIGURATION$AGENT_SELECT_LABEL = "CONFIGURATION$AGENT_SELECT_LABEL",
+  CONFIGURATION$AGENT_SELECT_PLACEHOLDER = "CONFIGURATION$AGENT_SELECT_PLACEHOLDER",
+  CONFIGURATION$LANGUAGE_SELECT_LABEL = "CONFIGURATION$LANGUAGE_SELECT_LABEL",
+  CONFIGURATION$LANGUAGE_SELECT_PLACEHOLDER = "CONFIGURATION$LANGUAGE_SELECT_PLACEHOLDER",
+  CONFIGURATION$SECURITY_SELECT_LABEL = "CONFIGURATION$SECURITY_SELECT_LABEL",
+  CONFIGURATION$SECURITY_SELECT_PLACEHOLDER = "CONFIGURATION$SECURITY_SELECT_PLACEHOLDER",
+  CONFIGURATION$MODAL_CLOSE_BUTTON_LABEL = "CONFIGURATION$MODAL_CLOSE_BUTTON_LABEL",
+  CONFIGURATION$MODAL_SAVE_BUTTON_LABEL = "CONFIGURATION$MODAL_SAVE_BUTTON_LABEL",
+  CONFIGURATION$MODAL_RESET_BUTTON_LABEL = "CONFIGURATION$MODAL_RESET_BUTTON_LABEL",
+  STATUS$CONNECTED_TO_SERVER = "STATUS$CONNECTED_TO_SERVER",
+  PROJECT$NEW_PROJECT = "PROJECT$NEW_PROJECT",
+  BROWSER$SCREENSHOT = "BROWSER$SCREENSHOT",
+  TIME$MINUTES_AGO = "TIME$MINUTES_AGO",
+  TIME$HOURS_AGO = "TIME$HOURS_AGO",
+  TIME$DAYS_AGO = "TIME$DAYS_AGO",
+  SETTINGS_FORM$RUNTIME_SIZE_LABEL = "SETTINGS_FORM$RUNTIME_SIZE_LABEL",
+  CONFIGURATION$SETTINGS_NEED_UPDATE_MESSAGE = "CONFIGURATION$SETTINGS_NEED_UPDATE_MESSAGE",
+  CONFIGURATION$AGENT_LOADING = "CONFIGURATION$AGENT_LOADING",
+  CONFIGURATION$AGENT_RUNNING = "CONFIGURATION$AGENT_RUNNING",
+  CONFIGURATION$ERROR_FETCH_MODELS = "CONFIGURATION$ERROR_FETCH_MODELS",
+  CONFIGURATION$SETTINGS_NOT_FOUND = "CONFIGURATION$SETTINGS_NOT_FOUND",
+  CONNECT_TO_GITHUB_BY_TOKEN_MODAL$TERMS_OF_SERVICE = "CONNECT_TO_GITHUB_BY_TOKEN_MODAL$TERMS_OF_SERVICE",
+  SESSION$SERVER_CONNECTED_MESSAGE = "SESSION$SERVER_CONNECTED_MESSAGE",
+  SESSION$SESSION_HANDLING_ERROR_MESSAGE = "SESSION$SESSION_HANDLING_ERROR_MESSAGE",
+  SESSION$SESSION_CONNECTION_ERROR_MESSAGE = "SESSION$SESSION_CONNECTION_ERROR_MESSAGE",
+  SESSION$SOCKET_NOT_INITIALIZED_ERROR_MESSAGE = "SESSION$SOCKET_NOT_INITIALIZED_ERROR_MESSAGE",
+  EXPLORER$UPLOAD_ERROR_MESSAGE = "EXPLORER$UPLOAD_ERROR_MESSAGE",
+  EXPLORER$LABEL_DROP_FILES = "EXPLORER$LABEL_DROP_FILES",
+  EXPLORER$LABEL_WORKSPACE = "EXPLORER$LABEL_WORKSPACE",
+  EXPLORER$EMPTY_WORKSPACE_MESSAGE = "EXPLORER$EMPTY_WORKSPACE_MESSAGE",
+  EXPLORER$LOADING_WORKSPACE_MESSAGE = "EXPLORER$LOADING_WORKSPACE_MESSAGE",
+  EXPLORER$REFRESH_ERROR_MESSAGE = "EXPLORER$REFRESH_ERROR_MESSAGE",
+  EXPLORER$UPLOAD_SUCCESS_MESSAGE = "EXPLORER$UPLOAD_SUCCESS_MESSAGE",
+  EXPLORER$NO_FILES_UPLOADED_MESSAGE = "EXPLORER$NO_FILES_UPLOADED_MESSAGE",
+  EXPLORER$UPLOAD_PARTIAL_SUCCESS_MESSAGE = "EXPLORER$UPLOAD_PARTIAL_SUCCESS_MESSAGE",
+  EXPLORER$UPLOAD_UNEXPECTED_RESPONSE_MESSAGE = "EXPLORER$UPLOAD_UNEXPECTED_RESPONSE_MESSAGE",
+  EXPLORER$VSCODE_SWITCHING_MESSAGE = "EXPLORER$VSCODE_SWITCHING_MESSAGE",
+  EXPLORER$VSCODE_SWITCHING_ERROR_MESSAGE = "EXPLORER$VSCODE_SWITCHING_ERROR_MESSAGE",
+  LOAD_SESSION$MODAL_TITLE = "LOAD_SESSION$MODAL_TITLE",
+  LOAD_SESSION$MODAL_CONTENT = "LOAD_SESSION$MODAL_CONTENT",
+  LOAD_SESSION$RESUME_SESSION_MODAL_ACTION_LABEL = "LOAD_SESSION$RESUME_SESSION_MODAL_ACTION_LABEL",
+  LOAD_SESSION$START_NEW_SESSION_MODAL_ACTION_LABEL = "LOAD_SESSION$START_NEW_SESSION_MODAL_ACTION_LABEL",
+  FEEDBACK$MODAL_TITLE = "FEEDBACK$MODAL_TITLE",
+  FEEDBACK$MODAL_CONTENT = "FEEDBACK$MODAL_CONTENT",
+  FEEDBACK$EMAIL_LABEL = "FEEDBACK$EMAIL_LABEL",
+  FEEDBACK$CONTRIBUTE_LABEL = "FEEDBACK$CONTRIBUTE_LABEL",
+  FEEDBACK$SHARE_LABEL = "FEEDBACK$SHARE_LABEL",
+  FEEDBACK$CANCEL_LABEL = "FEEDBACK$CANCEL_LABEL",
+  FEEDBACK$EMAIL_PLACEHOLDER = "FEEDBACK$EMAIL_PLACEHOLDER",
+  FEEDBACK$PASSWORD_COPIED_MESSAGE = "FEEDBACK$PASSWORD_COPIED_MESSAGE",
+  FEEDBACK$GO_TO_FEEDBACK = "FEEDBACK$GO_TO_FEEDBACK",
+  FEEDBACK$PASSWORD = "FEEDBACK$PASSWORD",
+  FEEDBACK$INVALID_EMAIL_FORMAT = "FEEDBACK$INVALID_EMAIL_FORMAT",
+  FEEDBACK$FAILED_TO_SHARE = "FEEDBACK$FAILED_TO_SHARE",
+  FEEDBACK$COPY_LABEL = "FEEDBACK$COPY_LABEL",
+  FEEDBACK$SHARING_SETTINGS_LABEL = "FEEDBACK$SHARING_SETTINGS_LABEL",
+  SECURITY$UNKNOWN_ANALYZER_LABEL = "SECURITY$UNKNOWN_ANALYZER_LABEL",
+  INVARIANT$UPDATE_POLICY_LABEL = "INVARIANT$UPDATE_POLICY_LABEL",
+  INVARIANT$UPDATE_SETTINGS_LABEL = "INVARIANT$UPDATE_SETTINGS_LABEL",
+  INVARIANT$SETTINGS_LABEL = "INVARIANT$SETTINGS_LABEL",
+  INVARIANT$ASK_CONFIRMATION_RISK_SEVERITY_LABEL = "INVARIANT$ASK_CONFIRMATION_RISK_SEVERITY_LABEL",
+  INVARIANT$DONT_ASK_FOR_CONFIRMATION_LABEL = "INVARIANT$DONT_ASK_FOR_CONFIRMATION_LABEL",
+  INVARIANT$INVARIANT_ANALYZER_LABEL = "INVARIANT$INVARIANT_ANALYZER_LABEL",
+  INVARIANT$INVARIANT_ANALYZER_MESSAGE = "INVARIANT$INVARIANT_ANALYZER_MESSAGE",
+  INVARIANT$CLICK_TO_LEARN_MORE_LABEL = "INVARIANT$CLICK_TO_LEARN_MORE_LABEL",
+  INVARIANT$POLICY_LABEL = "INVARIANT$POLICY_LABEL",
+  INVARIANT$LOG_LABEL = "INVARIANT$LOG_LABEL",
+  INVARIANT$EXPORT_TRACE_LABEL = "INVARIANT$EXPORT_TRACE_LABEL",
+  INVARIANT$TRACE_EXPORTED_MESSAGE = "INVARIANT$TRACE_EXPORTED_MESSAGE",
+  INVARIANT$POLICY_UPDATED_MESSAGE = "INVARIANT$POLICY_UPDATED_MESSAGE",
+  INVARIANT$SETTINGS_UPDATED_MESSAGE = "INVARIANT$SETTINGS_UPDATED_MESSAGE",
+  CHAT_INTERFACE$INITIALIZING_AGENT_LOADING_MESSAGE = "CHAT_INTERFACE$INITIALIZING_AGENT_LOADING_MESSAGE",
+  CHAT_INTERFACE$AGENT_INIT_MESSAGE = "CHAT_INTERFACE$AGENT_INIT_MESSAGE",
+  CHAT_INTERFACE$AGENT_RUNNING_MESSAGE = "CHAT_INTERFACE$AGENT_RUNNING_MESSAGE",
+  CHAT_INTERFACE$AGENT_AWAITING_USER_INPUT_MESSAGE = "CHAT_INTERFACE$AGENT_AWAITING_USER_INPUT_MESSAGE",
+  CHAT_INTERFACE$AGENT_RATE_LIMITED_MESSAGE = "CHAT_INTERFACE$AGENT_RATE_LIMITED_MESSAGE",
+  CHAT_INTERFACE$AGENT_PAUSED_MESSAGE = "CHAT_INTERFACE$AGENT_PAUSED_MESSAGE",
+  LANDING$TITLE = "LANDING$TITLE",
+  LANDING$SUBTITLE = "LANDING$SUBTITLE",
+  LANDING$START_HELP = "LANDING$START_HELP",
+  LANDING$START_HELP_LINK = "LANDING$START_HELP_LINK",
+  SUGGESTIONS$HELLO_WORLD = "SUGGESTIONS$HELLO_WORLD",
+  SUGGESTIONS$TODO_APP = "SUGGESTIONS$TODO_APP",
+  SUGGESTIONS$HACKER_NEWS = "SUGGESTIONS$HACKER_NEWS",
+  LANDING$CHANGE_PROMPT = "LANDING$CHANGE_PROMPT",
+  GITHUB$CONNECT = "GITHUB$CONNECT",
+  GITHUB$NO_RESULTS = "GITHUB$NO_RESULTS",
+  GITHUB$ADD_MORE_REPOS = "GITHUB$ADD_MORE_REPOS",
+  GITHUB$YOUR_REPOS = "GITHUB$YOUR_REPOS",
+  GITHUB$PUBLIC_REPOS = "GITHUB$PUBLIC_REPOS",
+  DOWNLOAD$PREPARING = "DOWNLOAD$PREPARING",
+  DOWNLOAD$DOWNLOADING = "DOWNLOAD$DOWNLOADING",
+  DOWNLOAD$FOUND_FILES = "DOWNLOAD$FOUND_FILES",
+  DOWNLOAD$SCANNING = "DOWNLOAD$SCANNING",
+  DOWNLOAD$FILES_PROGRESS = "DOWNLOAD$FILES_PROGRESS",
+  DOWNLOAD$CANCEL = "DOWNLOAD$CANCEL",
+  ACTION$CONFIRM = "ACTION$CONFIRM",
+  ACTION$REJECT = "ACTION$REJECT",
+  BADGE$BETA = "BADGE$BETA",
+  AGENT$RESUME_TASK = "AGENT$RESUME_TASK",
+  AGENT$PAUSE_TASK = "AGENT$PAUSE_TASK",
+  TOS$ACCEPT = "TOS$ACCEPT",
+  TOS$TERMS = "TOS$TERMS",
+  USER$ACCOUNT_SETTINGS = "USER$ACCOUNT_SETTINGS",
+  JUPYTER$OUTPUT_LABEL = "JUPYTER$OUTPUT_LABEL",
+  BUTTON$STOP = "BUTTON$STOP",
+  LANDING$ATTACH_IMAGES = "LANDING$ATTACH_IMAGES",
+  LANDING$OPEN_REPO = "LANDING$OPEN_REPO",
+  LANDING$IMPORT_PROJECT = "LANDING$IMPORT_PROJECT",
+  LANDING$UPLOAD_ZIP = "LANDING$UPLOAD_ZIP",
+  LANDING$RECENT_CONVERSATION = "LANDING$RECENT_CONVERSATION",
+  LANDING$OR = "LANDING$OR",
+  SUGGESTIONS$TEST_COVERAGE = "SUGGESTIONS$TEST_COVERAGE",
+  SUGGESTIONS$AUTO_MERGE = "SUGGESTIONS$AUTO_MERGE",
+  CHAT_INTERFACE$AGENT_STOPPED_MESSAGE = "CHAT_INTERFACE$AGENT_STOPPED_MESSAGE",
+  CHAT_INTERFACE$AGENT_FINISHED_MESSAGE = "CHAT_INTERFACE$AGENT_FINISHED_MESSAGE",
+  CHAT_INTERFACE$AGENT_REJECTED_MESSAGE = "CHAT_INTERFACE$AGENT_REJECTED_MESSAGE",
+  CHAT_INTERFACE$AGENT_ERROR_MESSAGE = "CHAT_INTERFACE$AGENT_ERROR_MESSAGE",
+  CHAT_INTERFACE$AGENT_AWAITING_USER_CONFIRMATION_MESSAGE = "CHAT_INTERFACE$AGENT_AWAITING_USER_CONFIRMATION_MESSAGE",
+  CHAT_INTERFACE$AGENT_ACTION_USER_CONFIRMED_MESSAGE = "CHAT_INTERFACE$AGENT_ACTION_USER_CONFIRMED_MESSAGE",
+  CHAT_INTERFACE$AGENT_ACTION_USER_REJECTED_MESSAGE = "CHAT_INTERFACE$AGENT_ACTION_USER_REJECTED_MESSAGE",
+  CHAT_INTERFACE$INPUT_PLACEHOLDER = "CHAT_INTERFACE$INPUT_PLACEHOLDER",
+  CHAT_INTERFACE$INPUT_CONTINUE_MESSAGE = "CHAT_INTERFACE$INPUT_CONTINUE_MESSAGE",
+  CHAT_INTERFACE$USER_ASK_CONFIRMATION = "CHAT_INTERFACE$USER_ASK_CONFIRMATION",
+  CHAT_INTERFACE$USER_CONFIRMED = "CHAT_INTERFACE$USER_CONFIRMED",
+  CHAT_INTERFACE$USER_REJECTED = "CHAT_INTERFACE$USER_REJECTED",
+  CHAT_INTERFACE$INPUT_SEND_MESSAGE_BUTTON_CONTENT = "CHAT_INTERFACE$INPUT_SEND_MESSAGE_BUTTON_CONTENT",
+  CHAT_INTERFACE$CHAT_MESSAGE_COPIED = "CHAT_INTERFACE$CHAT_MESSAGE_COPIED",
+  CHAT_INTERFACE$CHAT_MESSAGE_COPY_FAILED = "CHAT_INTERFACE$CHAT_MESSAGE_COPY_FAILED",
+  CHAT_INTERFACE$TOOLTIP_COPY_MESSAGE = "CHAT_INTERFACE$TOOLTIP_COPY_MESSAGE",
+  CHAT_INTERFACE$TOOLTIP_SEND_MESSAGE = "CHAT_INTERFACE$TOOLTIP_SEND_MESSAGE",
+  CHAT_INTERFACE$TOOLTIP_UPLOAD_IMAGE = "CHAT_INTERFACE$TOOLTIP_UPLOAD_IMAGE",
+  CHAT_INTERFACE$INITIAL_MESSAGE = "CHAT_INTERFACE$INITIAL_MESSAGE",
+  CHAT_INTERFACE$ASSISTANT = "CHAT_INTERFACE$ASSISTANT",
+  CHAT_INTERFACE$TO_BOTTOM = "CHAT_INTERFACE$TO_BOTTOM",
+  CHAT_INTERFACE$MESSAGE_ARIA_LABEL = "CHAT_INTERFACE$MESSAGE_ARIA_LABEL",
+  CHAT_INTERFACE$CHAT_CONVERSATION = "CHAT_INTERFACE$CHAT_CONVERSATION",
+  CHAT_INTERFACE$UNKNOWN_SENDER = "CHAT_INTERFACE$UNKNOWN_SENDER",
+  SECURITY_ANALYZER$UNKNOWN_RISK = "SECURITY_ANALYZER$UNKNOWN_RISK",
+  SECURITY_ANALYZER$LOW_RISK = "SECURITY_ANALYZER$LOW_RISK",
+  SECURITY_ANALYZER$MEDIUM_RISK = "SECURITY_ANALYZER$MEDIUM_RISK",
+  SECURITY_ANALYZER$HIGH_RISK = "SECURITY_ANALYZER$HIGH_RISK",
+  SETTINGS$MODEL_TOOLTIP = "SETTINGS$MODEL_TOOLTIP",
+  SETTINGS$AGENT_TOOLTIP = "SETTINGS$AGENT_TOOLTIP",
+  SETTINGS$LANGUAGE_TOOLTIP = "SETTINGS$LANGUAGE_TOOLTIP",
+  SETTINGS$DISABLED_RUNNING = "SETTINGS$DISABLED_RUNNING",
+  SETTINGS$API_KEY_PLACEHOLDER = "SETTINGS$API_KEY_PLACEHOLDER",
+  SETTINGS$CONFIRMATION_MODE = "SETTINGS$CONFIRMATION_MODE",
+  SETTINGS$CONFIRMATION_MODE_TOOLTIP = "SETTINGS$CONFIRMATION_MODE_TOOLTIP",
+  SETTINGS$AGENT_SELECT_ENABLED = "SETTINGS$AGENT_SELECT_ENABLED",
+  SETTINGS$SECURITY_ANALYZER = "SETTINGS$SECURITY_ANALYZER",
+  PLANNER$EMPTY_MESSAGE = "PLANNER$EMPTY_MESSAGE",
+  FEEDBACK$PUBLIC_LABEL = "FEEDBACK$PUBLIC_LABEL",
+  FEEDBACK$PRIVATE_LABEL = "FEEDBACK$PRIVATE_LABEL",
+  STATUS$STARTING_RUNTIME = "STATUS$STARTING_RUNTIME",
+  STATUS$STARTING_CONTAINER = "STATUS$STARTING_CONTAINER",
+  STATUS$PREPARING_CONTAINER = "STATUS$PREPARING_CONTAINER",
+  STATUS$CONTAINER_STARTED = "STATUS$CONTAINER_STARTED",
+  ACCOUNT_SETTINGS_MODAL$DISCONNECT = "ACCOUNT_SETTINGS_MODAL$DISCONNECT",
+  ACCOUNT_SETTINGS_MODAL$SAVE = "ACCOUNT_SETTINGS_MODAL$SAVE",
+  ACCOUNT_SETTINGS_MODAL$CLOSE = "ACCOUNT_SETTINGS_MODAL$CLOSE",
+  ACCOUNT_SETTINGS_MODAL$GITHUB_TOKEN_INVALID = "ACCOUNT_SETTINGS_MODAL$GITHUB_TOKEN_INVALID",
+  CONNECT_TO_GITHUB_MODAL$GET_YOUR_TOKEN = "CONNECT_TO_GITHUB_MODAL$GET_YOUR_TOKEN",
+  CONNECT_TO_GITHUB_MODAL$HERE = "CONNECT_TO_GITHUB_MODAL$HERE",
+  CONNECT_TO_GITHUB_MODAL$CONNECT = "CONNECT_TO_GITHUB_MODAL$CONNECT",
+  CONNECT_TO_GITHUB_MODAL$CLOSE = "CONNECT_TO_GITHUB_MODAL$CLOSE",
+  CONNECT_TO_GITHUB_BY_TOKEN_MODAL$BY_CONNECTING_YOU_AGREE = "CONNECT_TO_GITHUB_BY_TOKEN_MODAL$BY_CONNECTING_YOU_AGREE",
+  CONNECT_TO_GITHUB_BY_TOKEN_MODAL$CONTINUE = "CONNECT_TO_GITHUB_BY_TOKEN_MODAL$CONTINUE",
+  LOADING_PROJECT$LOADING = "LOADING_PROJECT$LOADING",
+  CUSTOM_INPUT$OPTIONAL_LABEL = "CUSTOM_INPUT$OPTIONAL_LABEL",
+  SETTINGS_FORM$CUSTOM_MODEL_LABEL = "SETTINGS_FORM$CUSTOM_MODEL_LABEL",
+  SETTINGS_FORM$BASE_URL_LABEL = "SETTINGS_FORM$BASE_URL_LABEL",
+  SETTINGS_FORM$API_KEY_LABEL = "SETTINGS_FORM$API_KEY_LABEL",
+  SETTINGS_FORM$DONT_KNOW_API_KEY_LABEL = "SETTINGS_FORM$DONT_KNOW_API_KEY_LABEL",
+  SETTINGS_FORM$CLICK_HERE_FOR_INSTRUCTIONS_LABEL = "SETTINGS_FORM$CLICK_HERE_FOR_INSTRUCTIONS_LABEL",
+  SETTINGS_FORM$AGENT_LABEL = "SETTINGS_FORM$AGENT_LABEL",
+  SETTINGS_FORM$SECURITY_ANALYZER_LABEL = "SETTINGS_FORM$SECURITY_ANALYZER_LABEL",
+  SETTINGS_FORM$ENABLE_CONFIRMATION_MODE_LABEL = "SETTINGS_FORM$ENABLE_CONFIRMATION_MODE_LABEL",
+  SETTINGS_FORM$SAVE_LABEL = "SETTINGS_FORM$SAVE_LABEL",
+  SETTINGS_FORM$CLOSE_LABEL = "SETTINGS_FORM$CLOSE_LABEL",
+  SETTINGS_FORM$RESET_TO_DEFAULTS_LABEL = "SETTINGS_FORM$RESET_TO_DEFAULTS_LABEL",
+  SETTINGS_FORM$CANCEL_LABEL = "SETTINGS_FORM$CANCEL_LABEL",
+  SETTINGS_FORM$END_SESSION_LABEL = "SETTINGS_FORM$END_SESSION_LABEL",
+  SETTINGS_FORM$CHANGING_WORKSPACE_WARNING_MESSAGE = "SETTINGS_FORM$CHANGING_WORKSPACE_WARNING_MESSAGE",
+  SETTINGS_FORM$ARE_YOU_SURE_LABEL = "SETTINGS_FORM$ARE_YOU_SURE_LABEL",
+  SETTINGS_FORM$ALL_INFORMATION_WILL_BE_DELETED_MESSAGE = "SETTINGS_FORM$ALL_INFORMATION_WILL_BE_DELETED_MESSAGE",
+  PROJECT_MENU_DETAILS_PLACEHOLDER$NEW_PROJECT_LABEL = "PROJECT_MENU_DETAILS_PLACEHOLDER$NEW_PROJECT_LABEL",
+  PROJECT_MENU_DETAILS_PLACEHOLDER$CONNECT_TO_GITHUB = "PROJECT_MENU_DETAILS_PLACEHOLDER$CONNECT_TO_GITHUB",
+  PROJECT_MENU_DETAILS_PLACEHOLDER$CONNECTED = "PROJECT_MENU_DETAILS_PLACEHOLDER$CONNECTED",
+  PROJECT_MENU_DETAILS$AGO_LABEL = "PROJECT_MENU_DETAILS$AGO_LABEL",
+  STATUS$ERROR_LLM_AUTHENTICATION = "STATUS$ERROR_LLM_AUTHENTICATION",
+  STATUS$ERROR_LLM_SERVICE_UNAVAILABLE = "STATUS$ERROR_LLM_SERVICE_UNAVAILABLE",
+  STATUS$ERROR_LLM_INTERNAL_SERVER_ERROR = "STATUS$ERROR_LLM_INTERNAL_SERVER_ERROR",
+  STATUS$ERROR_RUNTIME_DISCONNECTED = "STATUS$ERROR_RUNTIME_DISCONNECTED",
+  STATUS$LLM_RETRY = "STATUS$LLM_RETRY",
+  AGENT_ERROR$BAD_ACTION = "AGENT_ERROR$BAD_ACTION",
+  AGENT_ERROR$ACTION_TIMEOUT = "AGENT_ERROR$ACTION_TIMEOUT",
+  PROJECT_MENU_CARD_CONTEXT_MENU$CONNECT_TO_GITHUB_LABEL = "PROJECT_MENU_CARD_CONTEXT_MENU$CONNECT_TO_GITHUB_LABEL",
+  PROJECT_MENU_CARD_CONTEXT_MENU$PUSH_TO_GITHUB_LABEL = "PROJECT_MENU_CARD_CONTEXT_MENU$PUSH_TO_GITHUB_LABEL",
+  PROJECT_MENU_CARD_CONTEXT_MENU$DOWNLOAD_FILES_LABEL = "PROJECT_MENU_CARD_CONTEXT_MENU$DOWNLOAD_FILES_LABEL",
+  PROJECT_MENU_CARD$OPEN = "PROJECT_MENU_CARD$OPEN",
+  ACTION_BUTTON$RESUME = "ACTION_BUTTON$RESUME",
+  ACTION_BUTTON$PAUSE = "ACTION_BUTTON$PAUSE",
+  BROWSER$SCREENSHOT_ALT = "BROWSER$SCREENSHOT_ALT",
+  ERROR_TOAST$CLOSE_BUTTON_LABEL = "ERROR_TOAST$CLOSE_BUTTON_LABEL",
+  FILE_EXPLORER$UPLOAD = "FILE_EXPLORER$UPLOAD",
+  FILE_EXPLORER$REFRESH_WORKSPACE = "FILE_EXPLORER$REFRESH_WORKSPACE",
+  FILE_EXPLORER$OPEN_WORKSPACE = "FILE_EXPLORER$OPEN_WORKSPACE",
+  FILE_EXPLORER$CLOSE_WORKSPACE = "FILE_EXPLORER$CLOSE_WORKSPACE",
+  ACTION_MESSAGE$RUN = "ACTION_MESSAGE$RUN",
+  ACTION_MESSAGE$RUN_IPYTHON = "ACTION_MESSAGE$RUN_IPYTHON",
+  ACTION_MESSAGE$READ = "ACTION_MESSAGE$READ",
+  ACTION_MESSAGE$EDIT = "ACTION_MESSAGE$EDIT",
+  ACTION_MESSAGE$WRITE = "ACTION_MESSAGE$WRITE",
+  ACTION_MESSAGE$BROWSE = "ACTION_MESSAGE$BROWSE",
+  OBSERVATION_MESSAGE$RUN = "OBSERVATION_MESSAGE$RUN",
+  OBSERVATION_MESSAGE$RUN_IPYTHON = "OBSERVATION_MESSAGE$RUN_IPYTHON",
+  OBSERVATION_MESSAGE$READ = "OBSERVATION_MESSAGE$READ",
+  OBSERVATION_MESSAGE$EDIT = "OBSERVATION_MESSAGE$EDIT",
+  OBSERVATION_MESSAGE$WRITE = "OBSERVATION_MESSAGE$WRITE",
+  OBSERVATION_MESSAGE$BROWSE = "OBSERVATION_MESSAGE$BROWSE",
+  EXPANDABLE_MESSAGE$SHOW_DETAILS = "EXPANDABLE_MESSAGE$SHOW_DETAILS",
+  EXPANDABLE_MESSAGE$HIDE_DETAILS = "EXPANDABLE_MESSAGE$HIDE_DETAILS",
+  AI_SETTINGS$TITLE = "AI_SETTINGS$TITLE",
+  SETTINGS$DESCRIPTION = "SETTINGS$DESCRIPTION",
+  SETTINGS$WARNING = "SETTINGS$WARNING",
+  SIDEBAR$SETTINGS = "SIDEBAR$SETTINGS",
+  SIDEBAR$DOCS = "SIDEBAR$DOCS",
+  SUGGESTIONS$ADD_DOCS = "SUGGESTIONS$ADD_DOCS",
+  SUGGESTIONS$ADD_DOCKERFILE = "SUGGESTIONS$ADD_DOCKERFILE",
+  STATUS$CONNECTED = "STATUS$CONNECTED",
+  BROWSER$NO_PAGE_LOADED = "BROWSER$NO_PAGE_LOADED",
+  USER$AVATAR_PLACEHOLDER = "USER$AVATAR_PLACEHOLDER",
+  ACCOUNT_SETTINGS$SETTINGS = "ACCOUNT_SETTINGS$SETTINGS",
+  ACCOUNT_SETTINGS$LOGOUT = "ACCOUNT_SETTINGS$LOGOUT",
+  SETTINGS_FORM$ADVANCED_OPTIONS_LABEL = "SETTINGS_FORM$ADVANCED_OPTIONS_LABEL",
+  CONVERSATION$NO_CONVERSATIONS = "CONVERSATION$NO_CONVERSATIONS",
+  LANDING$SELECT_REPO = "LANDING$SELECT_REPO",
+  BUTTON$SEND = "BUTTON$SEND",
+  STATUS$WAITING_FOR_CLIENT = "STATUS$WAITING_FOR_CLIENT",
+  SUGGESTIONS$WHAT_TO_BUILD = "SUGGESTIONS$WHAT_TO_BUILD",
+  SETTINGS_FORM$ENABLE_DEFAULT_CONDENSER_SWITCH_LABEL = "SETTINGS_FORM$ENABLE_DEFAULT_CONDENSER_SWITCH_LABEL",
+  BUTTON$ENABLE_SOUND = "BUTTON$ENABLE_SOUND",
+  BUTTON$DISABLE_SOUND = "BUTTON$DISABLE_SOUND",
+  BUTTON$MARK_HELPFUL = "BUTTON$MARK_HELPFUL",
+  BUTTON$MARK_NOT_HELPFUL = "BUTTON$MARK_NOT_HELPFUL",
+  NOTIFICATION$SOUND_ENABLED = "NOTIFICATION$SOUND_ENABLED",
+  NOTIFICATION$SOUND_DISABLED = "NOTIFICATION$SOUND_DISABLED",
+  BUTTON$EXPORT_CONVERSATION = "BUTTON$EXPORT_CONVERSATION",
+}
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Xingyao Wang	184e7db3c9	docker related	2025-02-27 18:48:15 -05:00
Xingyao Wang	ff623f17da	system message update	2025-02-27 18:43:10 -05:00
Xingyao Wang	a6c0545efc	update system message	2025-02-27 18:39:11 -05:00
Xingyao Wang	02bc7de36d	Add Memory Monitor VSCode Extension (#6951 ) Co-authored-by: openhands <openhands@all-hands.dev> Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>	2025-02-27 22:02:33 +00:00
Xingyao Wang	42332294a1	[agent] Add "thinking" tool only (#6977 )	2025-02-28 05:47:39 +08:00
Engel Nyst	6e3e9e397e	Re-add separators between user messages (#7004 )	2025-02-27 22:47:15 +01:00
dependabot[bot]	fb8de1f98c	chore(deps): bump the version-all group across 1 directory with 7 updates (#7005 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: openhands <openhands@all-hands.dev>	2025-02-27 22:44:48 +01:00
jaybutera	9e5f767571	add add_agent.md (#6891 ) Co-authored-by: smd <>	2025-02-27 20:51:09 +00:00
tofarr	ce30d63510	Page Refresh now restarts agent loop if status is STOPPED or ERROR (#6829 )	2025-02-27 12:34:16 -07:00
Xingyao Wang	616ff49787	feat: add sound and browser notifications for agent state changes (#6530 ) Co-authored-by: openhands <openhands@all-hands.dev> Co-authored-by: amanape <83104063+amanape@users.noreply.github.com>	2025-02-27 18:40:26 +00:00
mamoodi	0aa508c382	Release 0.27.0 (#6993 )	2025-02-27 13:40:05 -05:00
tofarr	f32f683f92	Refactor: Moving ConversationInfo to server module (#6981 )	2025-02-27 11:04:38 -07:00
zchn	fd5e1e0b0b	Fix image tag inconsistency in forked-PR workflows (#6998 )	2025-02-27 12:42:31 -05:00
sp.wack	f02d55ae8b	hotfix(frontend): Truncate long conversation card titles (#7001 )	2025-02-27 17:21:43 +00:00
tofarr	be73792230	Feat out of credits msg (#6969 ) Co-authored-by: openhands <openhands@all-hands.dev>	2025-02-27 16:02:31 +00:00
tofarr	f437d06e81	Fix for error cleaning stale (#6971 )	2025-02-27 08:04:37 -07:00
Engel Nyst	9e0fee1890	Refactor sandbox and security configurations (#6973 )	2025-02-27 14:38:51 +01:00
Xingyao Wang	33780f97d0	[eval] Upgrade SWE-Bench to use official image and latest harness (#6838 ) Co-authored-by: Robert Brennan <accounts@rbren.io> Co-authored-by: openhands <openhands@all-hands.dev> Co-authored-by: Engel Nyst <enyst@users.noreply.github.com> Co-authored-by: Graham Neubig <neubig@gmail.com>	2025-02-27 08:15:05 -05:00
dependabot[bot]	0137600988	chore(deps): bump react-icons from 5.4.0 to 5.5.0 in /docs in the version-all group (#6962 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-02-27 17:00:26 +04:00
Xingyao Wang	6b1a937024	[agent] System message update (#6787 ) Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>	2025-02-27 10:06:01 +08:00
Ray Myers	34febafae4	Add system event listeners for monitoring (#6929 )	2025-02-26 20:37:21 -05:00
Engel Nyst	8b234ae57c	Azure completion_tokens fix (take two) (#6975 )	2025-02-27 02:28:01 +01:00
dependabot[bot]	7ea418d020	chore(deps): bump the version-all group across 1 directory with 11 updates (#6966 ) Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: openhands <openhands@all-hands.dev>	2025-02-26 23:47:23 +00:00
Xingyao Wang	c4ba54122e	refactor: codeact tools into separate files (#6978 )	2025-02-26 22:57:14 +00:00
Engel Nyst	4b7cca9bdf	Refactor agent_config loading from toml (#6967 )	2025-02-26 22:06:10 +00:00
Engel Nyst	544e756f5f	Fix microagent matching to the user message, not previous enhancements (#6963 )	2025-02-26 20:46:24 +01:00
sp.wack	d5f7dde7c9	hotfix(frontend): Consistent buttons and their styles throughout the app (#6835 ) Co-authored-by: Robert Brennan <accounts@rbren.io>	2025-02-26 19:43:58 +00:00
Engel Nyst	4f98bce6df	Add selected_repo to command line (#6949 )	2025-02-26 20:42:59 +01:00
tofarr	b38039e626	Fix fd leak (#6950 )	2025-02-26 09:35:38 -07:00
Ray Myers	db1f5a8df2	Add ability to define custom runtime classes (#6955 ) Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>	2025-02-26 16:22:47 +01:00
Engel Nyst	f8045784b6	Refactor llm config from toml and clean up (#6923 )	2025-02-26 15:20:58 +01:00
Ryan H. Tran	34fa9ed4db	fix: `task_str` validation not required for trajectory replay (#6957 )	2025-02-26 14:17:03 +01:00
Rohit Malhotra	e49b9243af	[Feat]: Adding endpoint for suggested tasks Openhands could tackle (#6844 ) Co-authored-by: openhands <openhands@all-hands.dev>	2025-02-25 22:10:24 -05:00
Robert Brennan	ef62ccde36	Add pause_closed_runtimes config to pause instead of stop runtimes (#6885 ) Co-authored-by: openhands <openhands@all-hands.dev>	2025-02-25 13:43:51 -05:00