docker related

Co-authored-by: openhands <openhands@all-hands.dev>
Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

.github/pull_request_template.md

@@ -1,11 +1,12 @@
-**End-user friendly description of the problem this fixes or functionality that this introduces**
-
-- [ ] Include this change in the Release Notes. If checked, you must provide an **end-user friendly** description for your change below
-
----
-**Give a summary of what the PR does, explaining any non-trivial design decisions**
+- [ ] This change is worth documenting at https://docs.all-hands.dev/
+- [ ] Include this change in the Release Notes. If checked, you **must** provide an **end-user friendly** description for your change below
 
+**End-user friendly description of the problem this fixes or functionality that this introduces.**
 
 
 ---
-**Link of any specific issues this addresses**
+**Give a summary of what the PR does, explaining any non-trivial design decisions.**
+
+
+---
+**Link of any specific issues this addresses.**

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

@@ -24,6 +24,10 @@ jobs:
         uses: docker/setup-buildx-action@v3
       - name: Install tmux
         run: sudo apt-get update && sudo apt-get install -y tmux
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22.x'
       - name: Install poetry via pipx
         run: pipx install poetry
       - name: Set up Python

.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) \

.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

.github/workflows/openhands-resolver.yml

@@ -88,12 +88,10 @@ jobs:
         run: |
           python -m pip index versions openhands-ai > openhands_versions.txt
           OPENHANDS_VERSION=$(head -n 1 openhands_versions.txt | awk '{print $2}' | tr -d '()')
-          # Ensure requirements.txt ends with newline before appending
-          if [ -f requirements.txt ] && [ -s requirements.txt ]; then
-            sed -i -e '$a\' requirements.txt
-          fi
-          echo "openhands-ai==${OPENHANDS_VERSION}" >> requirements.txt
-          cat requirements.txt
+
+          # Create a new requirements.txt locally within the workflow, ensuring no reference to the repo's file
+          echo "openhands-ai==${OPENHANDS_VERSION}" > /tmp/requirements.txt
+          cat /tmp/requirements.txt
 
       - name: Cache pip dependencies
         if: |
@@ -111,9 +109,9 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ${{ env.pythonLocation }}/lib/python3.12/site-packages/*
-          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
+          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('/tmp/requirements.txt') }}
           restore-keys: |
-            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
+            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('/tmp/requirements.txt') }}
 
       - name: Check required environment variables
         env:
@@ -225,13 +223,14 @@ jobs:
             } else {
               console.log("Installing from requirements.txt...");
               await exec.exec("python -m pip install --upgrade pip");
-              await exec.exec("pip install -r requirements.txt");
+              await exec.exec("pip install -r /tmp/requirements.txt");
             }
 
       - name: Attempt to resolve issue
         env:
           GITHUB_TOKEN: ${{ secrets.PAT_TOKEN || github.token }}
           GITHUB_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
+          GIT_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
           LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
@@ -268,6 +267,7 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.PAT_TOKEN || github.token }}
           GITHUB_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
+          GIT_USERNAME: ${{ secrets.PAT_USERNAME || 'openhands-agent' }}
           LLM_MODEL: ${{ secrets.LLM_MODEL || inputs.LLM_MODEL }}
           LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
           LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}

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

@@ -32,6 +32,10 @@ jobs:
         uses: docker/setup-buildx-action@v3
       - name: Install tmux
         run: sudo apt-get update && sudo apt-get install -y tmux
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22.x'
       - name: Install poetry via pipx
         run: pipx install poetry
       - name: Set up Python
@@ -44,7 +48,7 @@ jobs:
       - name: Build Environment
         run: make build
       - name: Run Tests
-        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_memory.py
+        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_long_term_memory.py
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v5
         env:

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:0.23-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.27-nikolaik`
 
 ## Develop inside Docker container
 

FAQ.md

@@ -1,81 +0,0 @@
-# OpenHands FAQ
-
-## Table of Contents
-- [Docker Memory Management](#docker-memory-management)
-  - [Handling Out-of-Memory (OOM) Errors](#handling-out-of-memory-oom-errors)
-  - [Configuring Docker Memory Limits](#configuring-docker-memory-limits)
-  - [Best Practices](#best-practices)
-
-## Docker Memory Management
-
-### Handling Out-of-Memory (OOM) Errors
-
-#### Q: Why am I getting out-of-memory errors in my Docker container despite having sufficient host memory?
-
-A: This typically occurs when Docker containers don't have explicit memory limits set, or when the limits are set too low. By default, a container can use as much memory as the host's kernel scheduler allows. When running in Docker Desktop, containers are running inside a VM which has its own memory limits that may be lower than your host system's total memory.
-
-#### Q: How can I fix OOM errors in Docker Desktop?
-
-1. **Check Current Memory Settings**:
-   - Open Docker Desktop
-   - Go to Settings (gear icon)
-   - Navigate to "Resources"
-   - Check the "Memory" allocation
-
-2. **Increase Memory Limits**:
-   - Adjust the memory slider to allocate more memory to Docker
-   - Recommended: Start with at least 4GB for development workloads
-   - Click "Apply & Restart" to apply changes
-
-3. **Alternative Method (using docker-compose.yml)**:
-   ```yaml
-   services:
-     your_service:
-       mem_limit: 2g        # Hard memory limit
-       memswap_limit: 4g    # Total memory + swap limit
-   ```
-
-### Configuring Docker Memory Limits
-
-#### Q: What memory-related settings can I configure?
-
-Docker provides several options to control container memory usage:
-
-1. **Memory Limit** (`--memory` or `-m`):
-   ```bash
-   docker run -m 2g your_image    # Limits container to 2GB memory
-   ```
-
-2. **Memory + Swap** (`--memory-swap`):
-   ```bash
-   docker run -m 2g --memory-swap 4g your_image    # 2GB memory + 2GB swap
-   ```
-
-3. **Memory Reservation** (`--memory-reservation`):
-   ```bash
-   docker run --memory-reservation 1g your_image    # Soft limit of 1GB
-   ```
-
-### Best Practices
-
-1. **Always Set Memory Limits**:
-   - Explicitly set memory limits for production containers
-   - Monitor memory usage to set appropriate limits
-   - Consider both memory and swap limits
-
-2. **Performance Considerations**:
-   - Don't set memory limits too low to avoid frequent OOM kills
-   - Leave some headroom for memory spikes
-   - Consider using memory reservation for soft limits
-
-3. **Monitoring**:
-   - Use `docker stats` to monitor container memory usage
-   - Implement proper logging to catch OOM events
-   - Consider using container monitoring solutions
-
-4. **Resource Planning**:
-   - Calculate memory requirements during development
-   - Test with production-like workloads
-   - Account for peak memory usage
-
-For more detailed information about Docker memory management, refer to the [official Docker documentation on resource constraints](https://docs.docker.com/config/containers/resource_constraints/).

Makefile

@@ -1,4 +1,4 @@
-SHELL=/bin/bash
+SHELL=/usr/bin/env bash
 # Makefile for OpenHands project
 
 # Variables
@@ -81,10 +81,10 @@ check-nodejs:
 	@if command -v node > /dev/null; then \
 		NODE_VERSION=$(shell node --version | sed -E 's/v//g'); \
 		IFS='.' read -r -a NODE_VERSION_ARRAY <<< "$$NODE_VERSION"; \
-		if [ "$${NODE_VERSION_ARRAY[0]}" -ge 20 ]; then \
+		if [ "$${NODE_VERSION_ARRAY[0]}" -ge 22 ]; then \
 			echo "$(BLUE)Node.js $$NODE_VERSION is already installed.$(RESET)"; \
 		else \
-			echo "$(RED)Node.js 20.x or later is required. Please install Node.js 20.x or later to continue.$(RESET)"; \
+			echo "$(RED)Node.js 22.x or later is required. Please install Node.js 22.x or later to continue.$(RESET)"; \
 			exit 1; \
 		fi; \
 	else \

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:0.23-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:0.23-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:0.23
+    docker.all-hands.dev/all-hands-ai/openhands:0.27
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

build.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -e
 
 poetry build -v

config.template.toml

@@ -17,6 +17,12 @@
 #modal_api_token_id = ""
 #modal_api_token_secret = ""
 
+# API key for Daytona
+#daytona_api_key = ""
+
+# Daytona Target
+#daytona_target = ""
+
 # Base path for the workspace
 workspace_base = "./workspace"
 
@@ -234,6 +240,10 @@ codeact_enable_jupyter = true
 # List of microagents to disable
 #disabled_microagents = []
 
+# Whether history should be truncated to continue the session when hitting LLM context
+# length limit
+enable_history_truncation = true
+
 [agent.RepoExplorerAgent]
 # Example: use a cheaper model for RepoExplorerAgent to reduce cost, especially
 # useful when an agent doesn't demand high quality but uses a lot of tokens

containers/build.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 # Initialize variables with default values

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:0.23-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:

containers/dev/dev.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -o pipefail
 
 function get_docker() {

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:0.23-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:

docs/DOC_STYLE_GUIDE.md

@@ -46,3 +46,11 @@ docker run -it \
     -e THAT=that
     ...
 ```
+
+### Referring to UI Elements
+
+When referencing UI elements, use ``.
+
+Example:
+1. Toggle the `Advanced` option
+2. Enter your model in the `Custom Model` textbox.

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

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:0.23-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:0.23 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
     python -m openhands.core.cli
 ```
 

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

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:0.23-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:0.23 \
+    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
 ```

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:0.23-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:0.23-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:0.23
+    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).

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:0.23-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 \
     # ...
 ```

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

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:0.23-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:0.23 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
     python -m openhands.core.cli
 ```
 

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

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:0.23-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:0.23 \
+    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
 ```

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:0.23-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:0.23-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:0.23
+    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)。

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:0.23-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 \
     # ...
 ```

docs/modules/usage/architecture/runtime.md

@@ -54,14 +54,13 @@ graph TD
 6. Action Execution: The runtime client receives actions from the backend, executes them in the sandboxed environment, and sends back observations
 7. Observation Return: The action execution server sends execution results back to the OpenHands backend as observations
 
-
 The role of the client:
+
 - It acts as an intermediary between the OpenHands backend and the sandboxed environment
 - It executes various types of actions (shell commands, file operations, Python code, etc.) safely within the container
 - It manages the state of the sandboxed environment, including the current working directory and loaded plugins
 - It formats and returns observations to the backend, ensuring a consistent interface for processing results
 
-
 ## How OpenHands builds and maintains OH Runtime images
 
 OpenHands' approach to building and managing runtime images ensures efficiency, consistency, and flexibility in creating and maintaining Docker images for both production and development environments.
@@ -78,16 +77,15 @@ Tags may be in one of 2 formats:
 - **Source Tag**: `oh_v{openhands_version}_{16_digit_lock_hash}_{16_digit_source_hash}`
   (e.g.: `oh_v0.9.9_1234567890abcdef_1234567890abcdef`)
 
-
 #### Source Tag - Most Specific
 
 This is the first 16 digits of the MD5 of the directory hash for the source directory. This gives a hash
 for only the openhands source
 
-
 #### Lock Tag
 
 This hash is built from the first 16 digits of the MD5 of:
+
 - The name of the base image upon which the image was built (e.g.: `nikolaik/python-nodejs:python3.12-nodejs22`)
 - The content of the `pyproject.toml` included in the image.
 - The content of the `poetry.lock` included in the image.

docs/modules/usage/cloud/cloud-github-resolver.md

@@ -0,0 +1,21 @@
+# Cloud GitHub Resolver
+
+The GitHub Resolver automates code fixes and provides intelligent assistance for your repositories.
+
+## Setup
+
+The Cloud Github Resolver is available automatically when you
+[grant OpenHands Cloud repository access](./openhands-cloud.md#adding-repositories).
+
+## Usage
+
+### Issues
+
+On your repository, label an issue with `openhands`. OpenHands will attempt to fix the issue.
+
+### Pull Requests
+
+In order to get OpenHands to work on pull requests, use `@openhands` in top level or single inline comments to:
+     - Ask questions
+     - Request updates
+     - Get code explanations

docs/modules/usage/cloud/openhands-cloud.md

@@ -0,0 +1,39 @@
+# Openhands Cloud
+
+OpenHands Cloud is the cloud hosted version of OpenHands by All Hands AI.
+
+## Accessing OpenHands Cloud
+
+Currently, users are being admitted to access OpenHands Cloud in waves. To sign up,
+[join the waitlist](https://www.all-hands.dev/join-waitlist). Once you are approved, you will get an email with
+instructions on how to access it.
+
+## Getting Started
+
+After visiting OpenHands Cloud, you will be asked to connect with your GitHub account:
+1. After reading and accepting the terms of service, click `Connect to GitHub`.
+2. Review the permissions requested by OpenHands and then click `Authorize OpenHands by All Hands AI`.
+   - OpenHands will require some permissions from your GitHub account. To read more about these permissions,
+     you can click the `Learn more` link on the GitHub authorize page.
+
+## Adding Repositories
+
+You can grant OpenHands specific repository access:
+1. Under the `Select a GitHub project` dropdown, select `Add more repositories...`.
+2. Select the organization, then choose the specific repositories to grant OpenHands access to.
+   - Openhands requests short-lived tokens (8-hour expiry) with these permissions:
+     - Actions: Read and write
+     - Administration: Read-only
+     - Commit statuses: Read and write
+     - Contents: Read and write
+     - Issues: Read and write
+     - Metadata: Read-only
+     - Pull requests: Read and write
+     - Webhooks: Read and write
+     - Workflows: Read and write
+   - Repository access for a user is granted based on:
+     - Granted permission for the repository.
+     - User's GitHub permissions (owner/collaborator).
+
+You can manage repository access any time by following the above workflow or visiting the Settings page and selecting
+`Configure GitHub Repositories` under the `GitHub Settings` section.

docs/modules/usage/configuration-options.md

@@ -340,6 +340,11 @@ The agent configuration options are defined in the `[agent]` and `[agent.<agent_
   - Default: `false`
   - Description: Whether Jupyter is enabled in the action space
 
+- `enable_history_truncation`
+  - Type: `bool`
+  - Default: `true`
+  - Description: Whether history should be truncated to continue the session when hitting LLM context length limit
+
 ### Microagent Usage
 - `enable_prompt_extensions`
   - Type: `bool`

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:0.23-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:0.23 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
     python -m openhands.core.cli
 ```
 

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

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

@@ -1,9 +1,6 @@
 # GUI Mode
 
-## Introduction
-
-OpenHands provides a user-friendly Graphical User Interface (GUI) mode for interacting with the AI assistant.
-This mode offers an intuitive way to set up the environment, manage settings, and communicate with the AI.
+OpenHands provides a Graphical User Interface (GUI) mode for interacting with the AI assistant.
 
 ## Installation and Setup
 
@@ -14,104 +11,95 @@ This mode offers an intuitive way to set up the environment, manage settings, an
 
 ### Initial Setup
 
-1. Upon first launch, you'll see a settings modal.
-2. Select an `LLM Provider` and `LLM Model` from the dropdown menus.
+1. Upon first launch, you'll see a settings page.
+2. Select an `LLM Provider` and `LLM Model` from the dropdown menus. If the required model does not exist in the list,
+   toggle `Advanced` options and enter it with the correct prefix in the `Custom Model` text box.
 3. Enter the corresponding `API Key` for your chosen provider.
-4. Click "Save" to apply the settings.
+4. Click `Save Changes` to apply the settings.
 
 ### GitHub Token Setup
 
 OpenHands automatically exports a `GITHUB_TOKEN` to the shell environment if it is available. This can happen in two ways:
 
-- **Locally (OSS)**: The user directly inputs their GitHub token.
-- **Online (SaaS)**: The token is obtained through GitHub OAuth authentication.
-
-#### Setting Up a Local GitHub Token
-
-1. **Generate a Personal Access Token (PAT)**:
-   - Go to GitHub Settings > Developer Settings > Personal Access Tokens > Tokens (classic).
-   - Click "Generate new token (classic)".
+- **Local Installation**: The user directly inputs their GitHub token.
+<details>
+  <summary>Setting Up a GitHub Token</summary>
+  1. **Generate a Personal Access Token (PAT)**:
+   - On GitHub, go to Settings > Developer Settings > Personal Access Tokens > Tokens (classic).
+   - Click `Generate new token (classic)`.
    - Required scopes:
      - `repo` (Full control of private repositories)
-     - `workflow` (Update GitHub Action workflows)
-     - `read:org` (Read organization data)
+  2. **Enter Token in OpenHands**:
+   - Click the Settings button (gear icon).
+   - Navigate to the `GitHub Settings` section.
+   - Paste your token in the `GitHub Token` field.
+   - Click `Save Changes` to apply the changes.
+</details>
 
-2. **Enter Token in OpenHands**:
-   - Click the Settings button (gear icon) in the top right.
-   - Navigate to the "GitHub" section.
-   - Paste your token in the "GitHub Token" field.
-   - Click "Save" to apply the changes.
+<details>
+  <summary>Organizational Token Policies</summary>
 
-#### Organizational Token Policies
+  If you're working with organizational repositories, additional setup may be required:
 
-If you're working with organizational repositories, additional setup may be required:
-
-1. **Check Organization Requirements**:
+  1. **Check Organization Requirements**:
    - Organization admins may enforce specific token policies.
    - Some organizations require tokens to be created with SSO enabled.
    - Review your organization's [token policy settings](https://docs.github.com/en/organizations/managing-programmatic-access-to-your-organization/setting-a-personal-access-token-policy-for-your-organization).
-
-2. **Verify Organization Access**:
+  2. **Verify Organization Access**:
    - Go to your token settings on GitHub.
-   - Look for the organization under "Organization access".
-   - If required, click "Enable SSO" next to your organization.
+   - Look for the organization under `Organization access`.
+   - If required, click `Enable SSO` next to your organization.
    - Complete the SSO authorization process.
+</details>
 
-#### OAuth Authentication (Online Mode)
+<details>
+  <summary>Troubleshooting</summary>
 
-When using OpenHands in online mode, the GitHub OAuth flow:
+  Common issues and solutions:
 
-1. Requests the following permissions:
+  - **Token Not Recognized**:
+     - Ensure the token is properly saved in settings.
+     - Check that the token hasn't expired.
+     - Verify the token has the required scopes.
+     - Try regenerating the token.
+
+  - **Organization Access Denied**:
+     - Check if SSO is required but not enabled.
+     - Verify organization membership.
+     - Contact organization admin if token policies are blocking access.
+
+  - **Verifying Token Works**:
+     - The app will show a green checkmark if the token is valid.
+     - Try accessing a repository to confirm permissions.
+     - Check the browser console for any error messages.
+</details>
+
+- **OpenHands Cloud**: The token is obtained through GitHub OAuth authentication.
+
+<details>
+  <summary>OAuth Authentication</summary>
+
+  When using OpenHands Cloud, the GitHub OAuth flow requests the following permissions:
    - Repository access (read/write)
    - Workflow management
    - Organization read access
 
-2. Authentication steps:
-   - Click "Sign in with GitHub" when prompted.
+  To authenticate OpenHands:
+   - Click `Sign in with GitHub` when prompted.
    - Review the requested permissions.
    - Authorize OpenHands to access your GitHub account.
    - If using an organization, authorize organization access if prompted.
-
-#### Troubleshooting
-
-Common issues and solutions:
-
-- **Token Not Recognized**:
-   - Ensure the token is properly saved in settings.
-   - Check that the token hasn't expired.
-   - Verify the token has the required scopes.
-   - Try regenerating the token.
-
-- **Organization Access Denied**:
-   - Check if SSO is required but not enabled.
-   - Verify organization membership.
-   - Contact organization admin if token policies are blocking access.
-
-- **Verifying Token Works**:
-   - The app will show a green checkmark if the token is valid.
-   - Try accessing a repository to confirm permissions.
-   - Check the browser console for any error messages.
-   - Use the "Test Connection" button in settings if available.
+</details>
 
 ### Advanced Settings
 
-1. Toggle `Advanced Options` to access additional settings.
+1. Inside the Settings page, toggle `Advanced` options to access additional settings.
 2. Use the `Custom Model` text box to manually enter a model if it's not in the list.
 3. Specify a `Base URL` if required by your LLM provider.
 
-### Main Interface
-
-The main interface consists of several key components:
-
-- **Chat Window**: The central area where you can view the conversation history with the AI assistant.
-- **Input Box**: Located at the bottom of the screen, use this to type your messages or commands to the AI.
-- **Send Button**: Click this to send your message to the AI.
-- **Settings Button**: A gear icon that opens the settings modal, allowing you to adjust your configuration at any time.
-- **Workspace Panel**: Displays the files and folders in your workspace, allowing you to navigate and view files, or the agent's past commands or web browsing history.
-
 ### Interacting with the AI
 
-1. Type your question, request, or task description in the input box.
+1. Type your prompt in the input box.
 2. Click the send button or press Enter to submit your message.
 3. The AI will process your input and provide a response in the chat window.
 4. You can continue the conversation by asking follow-up questions or providing additional information.

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:0.23-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:0.23 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.27 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/modules/usage/installation.mdx

@@ -6,11 +6,14 @@
 - Linux
 - Windows with [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) and [Docker Desktop support](https://docs.docker.com/desktop/setup/install/windows-install/#system-requirements)
 
+A system with a modern processor and a minimum of **4GB RAM** is recommended to run OpenHands.
+
 ## Prerequisites
 
 <details>
   <summary>MacOS</summary>
-  ### Docker Desktop
+
+  **Docker Desktop**
 
   1. [Install Docker Desktop on Mac](https://docs.docker.com/desktop/setup/install/mac-install).
   2. Open Docker Desktop, go to `Settings > Advanced` and ensure `Allow the default Docker socket to be used` is enabled.
@@ -23,7 +26,7 @@
   Tested with Ubuntu 22.04.
   :::
 
-  ### Docker Desktop
+  **Docker Desktop**
 
   1. [Install Docker Desktop on Linux](https://docs.docker.com/desktop/setup/install/linux/).
 
@@ -31,12 +34,13 @@
 
 <details>
   <summary>Windows</summary>
-  ### WSL
+
+  **WSL**
 
   1. [Install WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
   2. Run `wsl --version` in powershell and confirm `Default Version: 2`.
 
-  ### Docker Desktop
+  **Docker Desktop**
 
   1. [Install Docker Desktop on Windows](https://docs.docker.com/desktop/setup/install/windows-install).
   2. Open Docker Desktop, go to `Settings` and confirm the following:
@@ -54,17 +58,17 @@
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.23-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:0.23-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:0.23
+    docker.all-hands.dev/all-hands-ai/openhands:0.27
 ```
 
 You'll find OpenHands running at http://localhost:3000!
@@ -76,24 +80,22 @@ or run it on tagged issues with [a github action](https://docs.all-hands.dev/mod
 
 ## Setup
 
-Upon launching OpenHands, you'll see a settings modal. You **must** select an `LLM Provider` and `LLM Model` and enter a corresponding `API Key`.
+Upon launching OpenHands, you'll see a Settings page. You **must** select an `LLM Provider` and `LLM Model` and enter a corresponding `API Key`.
 These can be changed at any time by selecting the `Settings` button (gear icon) in the UI.
 
-If the required `LLM Model` does not exist in the list, you can toggle `Advanced Options` and manually enter it with the correct prefix
+If the required model does not exist in the list, you can toggle `Advanced` options and manually enter it with the correct prefix
 in the `Custom Model` text box.
-The `Advanced Options` also allow you to specify a `Base URL` if required.
+The `Advanced` options also allow you to specify a `Base URL` if required.
 
-<div style={{ display: 'flex', justifyContent: 'center', gap: '20px' }}>
-  <img src="/img/settings-screenshot.png" alt="settings-modal" width="340" />
-  <img src="/img/settings-advanced.png" alt="settings-modal" width="335" />
-</div>
+Now you're ready to [get started with OpenHands](./getting-started).
 
 ## Versions
 
-The command above pulls the most recent stable release of OpenHands. You have other options as well:
-- For a specific release, use `docker.all-hands.dev/all-hands-ai/openhands:$VERSION`, replacing $VERSION with the version number.
-- We use semver, and release major, minor, and patch tags. So `0.9` will automatically point to the latest `0.9.x` release, and `0` will point to the latest `0.x.x` release.
-- For the most up-to-date development version, you can use `docker.all-hands.dev/all-hands-ai/openhands:main`. This version is unstable and is recommended for testing or development purposes only.
+The [docker command above](./installation#start-the-app) pulls the most recent stable release of OpenHands. You have other options as well:
+- For a specific release, replace $VERSION in `openhands:$VERSION` and `runtime:$VERSION`, with the version number.
+We use SemVer so `0.9` will automatically point to the latest `0.9.x` release, and `0` will point to the latest `0.x.x` release.
+- For the most up-to-date development version, replace $VERSION in `openhands:$VERSION` and `runtime:$VERSION`, with `main`.
+This version is unstable and is recommended for testing or development purposes only.
 
 You can choose the tag that best suits your needs based on stability requirements and desired features.
 

docs/modules/usage/llms/azure-llms.md

@@ -25,7 +25,7 @@ You will need your ChatGPT deployment name which can be found on the deployments
 <deployment-name> below.
 :::
 
-1. Enable `Advanced Options`
+1. Enable `Advanced` options
 2. Set the following:
    - `Custom Model` to azure/<deployment-name>
    - `Base URL` to your Azure API Base URL (e.g. `https://example-endpoint.openai.azure.com`)

docs/modules/usage/llms/google-llms.md

@@ -10,7 +10,7 @@ OpenHands uses LiteLLM to make calls to Google's chat models. You can find their
 When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
 - `LLM Provider` to `Gemini`
 - `LLM Model` to the model you will be using.
-If the model is not in the list, toggle `Advanced Options`, and enter it in `Custom Model` (e.g. gemini/<model-name> like `gemini/gemini-1.5-pro`).
+If the model is not in the list, toggle `Advanced` options, and enter it in `Custom Model` (e.g. gemini/<model-name> like `gemini/gemini-1.5-pro`).
 - `API Key` to your Gemini API key
 
 ## VertexAI - Google Cloud Platform Configs
@@ -27,4 +27,4 @@ VERTEXAI_LOCATION="<your-gcp-location>"
 Then set the following in the OpenHands UI through the Settings:
 - `LLM Provider` to `VertexAI`
 - `LLM Model` to the model you will be using.
-If the model is not in the list, toggle `Advanced Options`, and enter it in `Custom Model` (e.g. vertex_ai/&lt;model-name&gt;).
+If the model is not in the list, toggle `Advanced` options, and enter it in `Custom Model` (e.g. vertex_ai/&lt;model-name&gt;).

docs/modules/usage/llms/groq.md

@@ -8,7 +8,7 @@ When running OpenHands, you'll need to set the following in the OpenHands UI thr
 - `LLM Provider` to `Groq`
 - `LLM Model` to the model you will be using. [Visit here to see the list of
 models that Groq hosts](https://console.groq.com/docs/models). If the model is not in the list, toggle
-`Advanced Options`, and enter it in `Custom Model` (e.g. groq/<model-name> like `groq/llama3-70b-8192`).
+`Advanced` options, and enter it in `Custom Model` (e.g. groq/<model-name> like `groq/llama3-70b-8192`).
 - `API key` to your Groq API key. To find or create your Groq API Key, [see here](https://console.groq.com/keys).
 
 
@@ -17,7 +17,7 @@ models that Groq hosts](https://console.groq.com/docs/models). If the model is n
 
 The Groq endpoint for chat completion is [mostly OpenAI-compatible](https://console.groq.com/docs/openai). Therefore, you can access Groq models as you
 would access any OpenAI-compatible endpoint. In the OpenHands UI through the Settings:
-1. Enable `Advanced Options`
+1. Enable `Advanced` options
 2. Set the following:
    - `Custom Model` to the prefix `openai/` + the model you will be using (e.g. `openai/llama3-70b-8192`)
    - `Base URL` to `https://api.groq.com/openai/v1`

docs/modules/usage/llms/litellm-proxy.md

@@ -8,7 +8,7 @@ To use LiteLLM proxy with OpenHands, you need to:
 
 1. Set up a LiteLLM proxy server (see [LiteLLM documentation](https://docs.litellm.ai/docs/proxy/quick_start))
 2. When running OpenHands, you'll need to set the following in the OpenHands UI through the Settings:
-  * Enable `Advanced Options`
+  * Enable `Advanced` options
   * `Custom Model` to the prefix `litellm_proxy/` + the model you will be using (e.g. `litellm_proxy/anthropic.claude-3-5-sonnet-20241022-v2:0`)
   * `Base URL` to your LiteLLM proxy URL (e.g. `https://your-litellm-proxy.com`)
   * `API Key` to your LiteLLM proxy API key

docs/modules/usage/llms/llms.md

@@ -38,7 +38,7 @@ The following can be set in the OpenHands UI through the Settings:
 - `LLM Provider`
 - `LLM Model`
 - `API Key`
-- `Base URL` (through `Advanced Settings`)
+- `Base URL` (through `Advanced` settings)
 
 There are some settings that may be necessary for some LLMs/providers that cannot be set through the UI. Instead, these
 can be set through environment variables passed to the [docker run command](/modules/usage/installation#start-the-app)
@@ -63,22 +63,22 @@ We have a few guides for running OpenHands with specific model providers:
 ### API retries and rate limits
 
 LLM providers typically have rate limits, sometimes very low, and may require retries. OpenHands will automatically
-retry requests if it receives a Rate Limit Error (429 error code), API connection error, or other transient errors.
+retry requests if it receives a Rate Limit Error (429 error code).
 
 You can customize these options as you need for the provider you're using. Check their documentation, and set the
 following environment variables to control the number of retries and the time between retries:
 
-- `LLM_NUM_RETRIES` (Default of 8)
-- `LLM_RETRY_MIN_WAIT` (Default of 15 seconds)
-- `LLM_RETRY_MAX_WAIT` (Default of 120 seconds)
+- `LLM_NUM_RETRIES` (Default of 4 times)
+- `LLM_RETRY_MIN_WAIT` (Default of 5 seconds)
+- `LLM_RETRY_MAX_WAIT` (Default of 30 seconds)
 - `LLM_RETRY_MULTIPLIER` (Default of 2)
 
 If you are running OpenHands in development mode, you can also set these options in the `config.toml` file:
 
 ```toml
 [llm]
-num_retries = 8
-retry_min_wait = 15
-retry_max_wait = 120
+num_retries = 4
+retry_min_wait = 5
+retry_max_wait = 30
 retry_multiplier = 2
 ```

docs/modules/usage/llms/openai-llms.md

@@ -8,7 +8,7 @@ When running OpenHands, you'll need to set the following in the OpenHands UI thr
 * `LLM Provider` to `OpenAI`
 * `LLM Model` to the model you will be using.
 [Visit here to see a full list of OpenAI models that LiteLLM supports.](https://docs.litellm.ai/docs/providers/openai#openai-chat-completion-models)
-If the model is not in the list, toggle `Advanced Options`, and enter it in `Custom Model` (e.g. openai/<model-name> like `openai/gpt-4o`).
+If the model is not in the list, toggle `Advanced` options, and enter it in `Custom Model` (e.g. openai/<model-name> like `openai/gpt-4o`).
 * `API Key` to your OpenAI API key. To find or create your OpenAI Project API Key, [see here](https://platform.openai.com/api-keys).
 
 ## Using OpenAI-Compatible Endpoints
@@ -18,7 +18,7 @@ Just as for OpenAI Chat completions, we use LiteLLM for OpenAI-compatible endpoi
 ## Using an OpenAI Proxy
 
 If you're using an OpenAI proxy, in the OpenHands UI through the Settings:
-1. Enable `Advanced Options`
+1. Enable `Advanced` options
 2. Set the following:
    - `Custom Model` to openai/<model-name> (e.g. `openai/gpt-4o` or openai/<proxy-prefix>/<model-name>)
    - `Base URL` to the URL of your OpenAI proxy

docs/modules/usage/llms/openrouter.md

@@ -8,5 +8,5 @@ When running OpenHands, you'll need to set the following in the OpenHands UI thr
 * `LLM Provider` to `OpenRouter`
 * `LLM Model` to the model you will be using.
 [Visit here to see a full list of OpenRouter models](https://openrouter.ai/models).
-If the model is not in the list, toggle `Advanced Options`, and enter it in `Custom Model` (e.g. openrouter/<model-name> like `openrouter/anthropic/claude-3.5-sonnet`).
+If the model is not in the list, toggle `Advanced` options, and enter it in `Custom Model` (e.g. openrouter/<model-name> like `openrouter/anthropic/claude-3.5-sonnet`).
 * `API Key` to your OpenRouter API key.

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:0.23-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 \
     # ...
 ```

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": "*"

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": {

docs/sidebars.ts

@@ -42,7 +42,7 @@ const sidebars: SidebarsConfig = {
               id: 'usage/prompting/microagents-public',
             },
           ],
-        }
+        },
       ],
     },
     {
@@ -66,9 +66,26 @@ const sidebars: SidebarsConfig = {
         },
         {
           type: 'doc',
-          label: 'Github Actions',
+          label: 'Github Action',
           id: 'usage/how-to/github-action',
         },
+        {
+          type: 'category',
+          label: 'Cloud',
+          items: [
+            {
+              type: 'doc',
+              label: 'Openhands Cloud',
+              id: 'usage/cloud/openhands-cloud',
+            },
+
+            {
+              type: 'doc',
+              label: 'Cloud GitHub Resolver',
+              id: 'usage/cloud/cloud-github-resolver',
+            },
+          ],
+        },
       ],
     },
     {
@@ -185,7 +202,7 @@ const sidebars: SidebarsConfig = {
       type: 'doc',
       label: 'About',
       id: 'usage/about',
-    }
+    },
   ],
 };
 

docs/src/pages/index.tsx

@@ -23,6 +23,17 @@ export default function Home(): JSX.Element {
       })}
     >
       <HomepageHeader />
+      <div style={{ textAlign: 'center', padding: '2rem' }}>
+        <br />
+        <h2>Most Popular Links</h2>
+        <ul style={{ listStyleType: 'none'}}>
+          <li><a href="/modules/usage/Installation">How to Run OpenHands</a></li>
+          <li><a href="/modules/usage/prompting/microagents-repo">Customizing OpenHands to a repository</a></li>
+          <li><a href="/modules/usage/how-to/github-action">Integrating OpenHands with Github</a></li>
+          <li><a href="/modules/usage/llms#model-recommendations">Recommended models to use</a></li>
+          <li><a href="/modules/usage/runtimes#connecting-to-your-filesystem">Connecting OpenHands to your filesystem</a></li>
+        </ul>
+      </div>
     </Layout>
   );
 }

evaluation/README.md

@@ -20,6 +20,8 @@ To evaluate an agent, you can provide the agent's name to the `run_infer.py` pro
 ### Evaluating Different LLMs
 
 OpenHands in development mode uses `config.toml` to keep track of most configuration.
+**IMPORTANT: For evaluation, only the LLM section in `config.toml` will be used. Other configurations, such as `save_trajectory_path`, are not applied during evaluation.**
+
 Here's an example configuration file you can use to define and use multiple LLMs:
 
 ```toml
@@ -40,6 +42,8 @@ api_key = "XXX"
 temperature = 0.0
 ```
 
+For other configurations specific to evaluation, such as `save_trajectory_path`, these are typically set in the `get_config` function of the respective `run_infer.py` file for each benchmark.
+
 ## Supported Benchmarks
 
 The OpenHands evaluation harness supports a wide variety of benchmarks across [software engineering](#software-engineering), [web browsing](#web-browsing), [miscellaneous assistance](#misc-assistance), and [real-world](#real-world) tasks.

evaluation/benchmarks/EDA/run_infer.py

@@ -9,6 +9,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -17,14 +18,12 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
 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
 
@@ -60,17 +59,14 @@ AGENT_CLS_TO_INST_SUFFIX = {
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-bookworm',
-            enable_auto_lint=False,
-            use_host_network=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -125,7 +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(

evaluation/benchmarks/EDA/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/agent_bench/run_infer.py

@@ -17,6 +17,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -25,7 +26,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     parse_arguments,
 )
@@ -34,27 +34,20 @@ 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(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-slim'
+
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-slim',
-            enable_auto_lint=True,
-            use_host_network=False,
-            api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_runtime_alive=False,
-            remote_runtime_init_timeout=3600,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -217,7 +210,6 @@ def process_instance(
     # =============================================
 
     runtime: Runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
 
     initialize_runtime(runtime, instance=instance)
 

evaluation/benchmarks/agent_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/aider_bench/run_infer.py

@@ -16,6 +16,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -24,7 +25,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     load_from_toml,
     parse_arguments,
@@ -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'
@@ -47,22 +46,14 @@ SKIP_NUM = (
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.11-bookworm'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.11-bookworm',
-            enable_auto_lint=True,
-            use_host_network=False,
-            timeout=100,
-            api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_runtime_alive=False,
-            remote_runtime_init_timeout=1800,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -212,7 +203,6 @@ def process_instance(
     # =============================================
 
     runtime: Runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
 
     initialize_runtime(runtime, instance=instance)
 

evaluation/benchmarks/aider_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/biocoder/run_infer.py

@@ -14,6 +14,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     codeact_user_response,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -22,7 +23,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     parse_arguments,
 )
@@ -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(
@@ -57,18 +56,15 @@ def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
     BIOCODER_BENCH_CONTAINER_IMAGE = 'public.ecr.aws/i5g0m1f6/eval_biocoder:v1.0'
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = BIOCODER_BENCH_CONTAINER_IMAGE
 
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image=BIOCODER_BENCH_CONTAINER_IMAGE,
-            enable_auto_lint=True,
-            use_host_network=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -278,7 +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

evaluation/benchmarks/biocoder/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/bird/run_infer.py

@@ -17,6 +17,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -25,7 +26,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     parse_arguments,
 )
@@ -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:
@@ -71,17 +70,15 @@ AGENT_CLS_TO_INST_SUFFIX = {
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
+
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-bookworm',
-            enable_auto_lint=True,
-            use_host_network=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -402,7 +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

evaluation/benchmarks/bird/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/browsing_delegation/run_infer.py

@@ -10,6 +10,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -18,7 +19,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     parse_arguments,
 )
@@ -36,17 +36,14 @@ def get_config(
     assert (
         metadata.max_iterations == 1
     ), 'max_iterations must be 1 for browsing delegation evaluation.'
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-bookworm',
-            enable_auto_lint=False,
-            use_host_network=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         workspace_base=None,
         workspace_mount_path=None,
     )

evaluation/benchmarks/browsing_delegation/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/commit0_bench/run_infer.py

@@ -15,6 +15,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     assert_and_raise,
     codeact_user_response,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -25,7 +26,6 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
@@ -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'
@@ -105,9 +104,7 @@ def get_config(
     instance: pd.Series,
     metadata: EvalMetadata,
 ) -> AppConfig:
-    # COMMIT0_CONTAINER_IMAGE = 'wentingzhao/'
     assert USE_INSTANCE_IMAGE
-    # We use a different instance image for the each instance of commit0 eval
     repo_name = instance['repo'].split('/')[1]
     base_container_image = get_instance_docker_image(repo_name)
     logger.info(
@@ -115,28 +112,16 @@ def get_config(
         f'Please make sure this image exists. '
         f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
     )
-    # else:
-    #     raise
-    # base_container_image = SWE_BENCH_CONTAINER_IMAGE
-    # logger.info(f'Using swe-bench container image: {base_container_image}')
+
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = base_container_image
 
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         max_iterations=metadata.max_iterations,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox=SandboxConfig(
-            base_container_image=base_container_image,
-            enable_auto_lint=True,
-            use_host_network=False,
-            # large enough timeout, since some testcases take very long to run
-            timeout=300,
-            api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_runtime_alive=False,
-            remote_runtime_init_timeout=3600,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -409,7 +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)
 

evaluation/benchmarks/commit0_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/discoverybench/run_infer.py

@@ -16,6 +16,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     codeact_user_response,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -25,7 +26,6 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     parse_arguments,
 )
@@ -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'
 
@@ -62,17 +61,14 @@ AGENT_CLS_TO_INST_SUFFIX = {
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-bookworm',
-            enable_auto_lint=True,
-            use_host_network=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -285,7 +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(

evaluation/benchmarks/discoverybench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/gaia/run_infer.py

@@ -13,6 +13,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     codeact_user_response,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -21,16 +22,15 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
+from openhands.core.config.utils import get_agent_config_arg
 from openhands.core.logger import openhands_logger as logger
 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')
 
@@ -47,24 +47,25 @@ AGENT_CLS_TO_INST_SUFFIX = {
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-bookworm',
-            enable_auto_lint=True,
-            use_host_network=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.enable_prompt_extensions = False
+    if metadata.agent_config:
+        config.set_agent_config(metadata.agent_config, metadata.agent_class)
+    else:
+        logger.info('Agent config not provided, using default settings')
+        agent_config = config.get_agent_config(metadata.agent_class)
+        agent_config.enable_prompt_extensions = False
     return config
 
 
@@ -147,7 +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
@@ -238,6 +238,10 @@ if __name__ == '__main__':
     )
     args, _ = parser.parse_known_args()
 
+    agent_config = None
+    if args.agent_config:
+        agent_config = get_agent_config_arg(args.agent_config)
+
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
@@ -256,6 +260,7 @@ if __name__ == '__main__':
         eval_output_dir=args.eval_output_dir,
         data_split=args.data_split,
         details={'gaia-level': args.level},
+        agent_config=agent_config,
     )
 
     dataset = load_dataset('gaia-benchmark/GAIA', args.level)

evaluation/benchmarks/gaia/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"
@@ -9,6 +9,7 @@ AGENT=$3
 EVAL_LIMIT=$4
 LEVELS=$5
 NUM_WORKERS=$6
+AGENT_CONFIG=$7
 
 if [ -z "$NUM_WORKERS" ]; then
   NUM_WORKERS=1
@@ -49,5 +50,9 @@ if [ -n "$EVAL_LIMIT" ]; then
   COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
 fi
 
+if [ -n "$AGENT_CONFIG" ]; then
+  echo "AGENT_CONFIG: $AGENT_CONFIG"
+  COMMAND="$COMMAND --agent-config $AGENT_CONFIG"
+
 # Run the command
 eval $COMMAND

evaluation/benchmarks/gorilla/run_infer.py

@@ -11,6 +11,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     codeact_user_response,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -19,14 +20,12 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
 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,
@@ -40,17 +39,14 @@ AGENT_CLS_TO_INST_SUFFIX = {
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-bookworm',
-            enable_auto_lint=True,
-            use_host_network=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -86,7 +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,

evaluation/benchmarks/gorilla/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/gpqa/run_infer.py

@@ -29,6 +29,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -37,7 +38,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
@@ -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||
@@ -61,17 +60,14 @@ ACTION_FORMAT = """
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-bookworm',
-            enable_auto_lint=True,
-            use_host_network=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -218,7 +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,

evaluation/benchmarks/gpqa/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/humanevalfix/run_infer.py

@@ -22,6 +22,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     codeact_user_response,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -30,7 +31,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     parse_arguments,
 )
@@ -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': [
@@ -82,17 +81,14 @@ AGENT_CLS_TO_INST_SUFFIX = {
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'python:3.12-bookworm'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='python:3.12-bookworm',
-            enable_auto_lint=True,
-            use_host_network=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -236,7 +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(

evaluation/benchmarks/humanevalfix/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -9,6 +9,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     codeact_user_response,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -17,7 +18,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
@@ -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,
@@ -45,18 +44,18 @@ AGENT_CLS_TO_INST_SUFFIX = {
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'xingyaoww/od-eval-logic-reasoning:v1.0'
+    sandbox_config.runtime_extra_deps = (
+        '$OH_INTERPRETER_PATH -m pip install scitools-pyke'
+    )
+
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='xingyaoww/od-eval-logic-reasoning:v1.0',
-            enable_auto_lint=True,
-            use_host_network=False,
-            runtime_extra_deps='$OH_INTERPRETER_PATH -m pip install scitools-pyke',
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -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

evaluation/benchmarks/logic_reasoning/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/miniwob/run_infer.py

@@ -12,6 +12,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     codeact_user_response,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -21,7 +22,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     parse_arguments,
 )
@@ -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'}
 
@@ -55,23 +54,14 @@ def get_config(
     metadata: EvalMetadata,
     env_id: str,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'xingyaoww/od-eval-miniwob:v1.0'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='xingyaoww/od-eval-miniwob:v1.0',
-            enable_auto_lint=True,
-            use_host_network=False,
-            browsergym_eval_env=env_id,
-            api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            remote_runtime_init_timeout=1800,
-            keep_runtime_alive=False,
-            timeout=120,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -155,7 +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 += (

evaluation/benchmarks/miniwob/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/mint/run_infer.py

@@ -14,6 +14,7 @@ from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -22,7 +23,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
@@ -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]):
@@ -103,18 +102,18 @@ def load_incontext_example(task_name: str, with_tool: bool = True):
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'xingyaoww/od-eval-mint:v1.0'
+    sandbox_config.runtime_extra_deps = (
+        f'$OH_INTERPRETER_PATH -m pip install {" ".join(MINT_DEPENDENCIES)}'
+    )
+
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='xingyaoww/od-eval-mint:v1.0',
-            enable_auto_lint=True,
-            use_host_network=False,
-            runtime_extra_deps=f'$OH_INTERPRETER_PATH -m pip install {" ".join(MINT_DEPENDENCIES)}',
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -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(

evaluation/benchmarks/mint/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/ml_bench/run_infer.py

@@ -25,6 +25,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     codeact_user_response,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -33,7 +34,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
     load_app_config,
@@ -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()
 
@@ -77,16 +76,14 @@ ID2CONDA = {
 def get_config(
     metadata: EvalMetadata,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = 'public.ecr.aws/i5g0m1f6/ml-bench'
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='public.ecr.aws/i5g0m1f6/ml-bench',
-            enable_auto_lint=True,
-            use_host_network=False,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -237,7 +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

evaluation/benchmarks/ml_bench/scripts/cleanup.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 # Step 1: Stop all running containers
 echo "Stopping all running containers..."

evaluation/benchmarks/ml_bench/scripts/run_analysis.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 RESULT_FILE=$1
 MODEL_CONFIG=$2

evaluation/benchmarks/ml_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -11,6 +11,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     codeact_user_response,
     compatibility_for_eval_history_pairs,
+    get_default_sandbox_config_for_eval,
     make_metadata,
     prepare_dataset,
     reset_logger_for_multiprocessing,
@@ -20,7 +21,6 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
@@ -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,
@@ -59,22 +58,17 @@ def get_config(
     metadata: EvalMetadata,
     instance_id: str,
 ) -> AppConfig:
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = (
+        'docker.io/xingyaoww/openhands-eval-scienceagentbench'
+    )
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
         max_budget_per_task=4,
         max_iterations=metadata.max_iterations,
-        sandbox=SandboxConfig(
-            base_container_image='docker.io/xingyaoww/openhands-eval-scienceagentbench',
-            enable_auto_lint=True,
-            use_host_network=False,
-            timeout=300,
-            api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_runtime_alive=False,
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -201,7 +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

evaluation/benchmarks/scienceagentbench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -1,5 +1,6 @@
 import json
 import os
+import subprocess
 import tempfile
 import time
 from functools import partial
@@ -10,7 +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
 
@@ -21,13 +26,14 @@ from evaluation.benchmarks.swe_bench.run_infer import get_instance_docker_image
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,
+    get_default_sandbox_config_for_eval,
     prepare_dataset,
     reset_logger_for_multiprocessing,
     run_evaluation,
 )
 from openhands.core.config import (
     AppConfig,
-    SandboxConfig,
+    LLMConfig,
     get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -79,22 +85,16 @@ def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
         f'Please make sure this image exists. '
         f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
     )
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = base_container_image
+    sandbox_config.remote_runtime_resource_factor = get_instance_resource_factor(
+        dataset_name=metadata.dataset,
+        instance_id=instance['instance_id'],
+    )
     config = AppConfig(
         run_as_openhands=False,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox=SandboxConfig(
-            base_container_image=base_container_image,
-            use_host_network=False,
-            # large enough timeout, since some testcases take very long to run
-            timeout=600,
-            api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            remote_runtime_init_timeout=3600,
-            remote_runtime_resource_factor=get_instance_resource_factor(
-                dataset_name=metadata.dataset,
-                instance_id=instance['instance_id'],
-            ),
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -415,13 +415,17 @@ if __name__ == '__main__':
     else:
         # Initialize with a dummy metadata when file doesn't exist
         metadata = EvalMetadata(
-            agent_class="dummy_agent",  # Placeholder agent class
-            llm_config=LLMConfig(model="dummy_model"),  # Minimal LLM config
+            agent_class='dummy_agent',  # Placeholder agent class
+            llm_config=LLMConfig(model='dummy_model'),  # Minimal LLM config
             max_iterations=1,  # Minimal iterations
-            eval_output_dir=os.path.dirname(args.input_file),  # Use input file dir as output dir
+            eval_output_dir=os.path.dirname(
+                args.input_file
+            ),  # Use input file dir as output dir
             start_time=time.strftime('%Y-%m-%d %H:%M:%S'),  # Current time
-            git_commit=subprocess.check_output(['git', 'rev-parse', 'HEAD']).decode('utf-8').strip(),  # Current commit
-            dataset=args.dataset  # Dataset name from args
+            git_commit=subprocess.check_output(['git', 'rev-parse', 'HEAD'])
+            .decode('utf-8')
+            .strip(),  # Current commit
+            dataset=args.dataset,  # Dataset name from args
         )
 
     # The evaluation harness constrains the signature of `process_instance_func` but we need to

evaluation/benchmarks/swe_bench/resource/princeton-nlp__SWE-bench_Verified-test.json

@@ -1 +0,0 @@
-{"pydata__xarray-6721": 8, "pytest-dev__pytest-7236": 8, "matplotlib__matplotlib-24627": 4, "django__django-15561": 4, "django__django-15098": 4, "django__django-14771": 4, "sympy__sympy-21612": 4, "sympy__sympy-15345": 4, "psf__requests-5414": 4, "astropy__astropy-14508": 2, "django__django-11451": 2, "django__django-11477": 2, "django__django-10880": 2, "django__django-11163": 2, "django__django-11815": 2, "astropy__astropy-14369": 2, "django__django-10097": 2, "django__django-10554": 2, "django__django-12304": 2, "django__django-12325": 2, "django__django-11551": 2, "django__django-11734": 2, "django__django-13109": 2, "django__django-13089": 2, "django__django-13343": 2, "django__django-13363": 2, "django__django-13809": 2, "django__django-13810": 2, "django__django-13786": 2, "django__django-13807": 2, "django__django-14493": 2, "django__django-11820": 2, "django__django-11951": 2, "django__django-11964": 2, "astropy__astropy-14309": 2, "astropy__astropy-14365": 2, "astropy__astropy-12907": 2, "astropy__astropy-14182": 2, "django__django-15161": 2, "django__django-15128": 2, "django__django-14999": 2, "django__django-14915": 2, "django__django-14752": 2, "django__django-14765": 2, "django__django-14089": 2, "django__django-15252": 2, "django__django-15380": 2, "django__django-15382": 2, "django__django-15499": 2, "django__django-15467": 2, "django__django-15280": 2, "django__django-15315": 2, "django__django-15277": 2, "django__django-15268": 2, "django__django-15629": 2, "django__django-15695": 2, "django__django-15732": 2, "django__django-15863": 2, "django__django-16082": 2, "django__django-16145": 2, "django__django-16256": 2, "django__django-16429": 2, "django__django-16454": 2, "django__django-16493": 2, "matplotlib__matplotlib-13989": 2, "matplotlib__matplotlib-20488": 2, "django__django-15503": 2, "django__django-15525": 2, "django__django-15375": 2, "django__django-15278": 2, "matplotlib__matplotlib-21568": 2, "matplotlib__matplotlib-20859": 2, "matplotlib__matplotlib-20826": 2, "matplotlib__matplotlib-20676": 2, "matplotlib__matplotlib-23412": 2, "matplotlib__matplotlib-22719": 2, "matplotlib__matplotlib-23299": 2, "matplotlib__matplotlib-22865": 2, "matplotlib__matplotlib-24149": 2, "matplotlib__matplotlib-24177": 2, "matplotlib__matplotlib-24570": 2, "matplotlib__matplotlib-24637": 2, "matplotlib__matplotlib-24970": 2, "matplotlib__matplotlib-23476": 2, "matplotlib__matplotlib-24026": 2, "matplotlib__matplotlib-23314": 2, "matplotlib__matplotlib-25332": 2, "matplotlib__matplotlib-25311": 2, "matplotlib__matplotlib-25122": 2, "matplotlib__matplotlib-25479": 2, "matplotlib__matplotlib-26342": 2, "psf__requests-2317": 2, "matplotlib__matplotlib-25960": 2, "matplotlib__matplotlib-25775": 2, "pydata__xarray-4356": 2, "pydata__xarray-4075": 2, "pydata__xarray-6461": 2, "pydata__xarray-4687": 2, "pydata__xarray-6599": 2, "pylint-dev__pylint-4661": 2, "django__django-15554": 2, "django__django-15563": 2, "pytest-dev__pytest-5262": 2, "pytest-dev__pytest-10081": 2, "scikit-learn__scikit-learn-12973": 2, "scikit-learn__scikit-learn-13124": 2, "scikit-learn__scikit-learn-13779": 2, "scikit-learn__scikit-learn-14141": 2, "scikit-learn__scikit-learn-13439": 2, "scikit-learn__scikit-learn-13496": 2, "scikit-learn__scikit-learn-15100": 2, "scikit-learn__scikit-learn-25102": 2, "scikit-learn__scikit-learn-25232": 2, "scikit-learn__scikit-learn-25747": 2, "scikit-learn__scikit-learn-26323": 2, "scikit-learn__scikit-learn-9288": 2, "scikit-learn__scikit-learn-14496": 2, "scikit-learn__scikit-learn-14629": 2, "sphinx-doc__sphinx-8265": 2, "sphinx-doc__sphinx-8548": 2, "sphinx-doc__sphinx-8593": 2, "sphinx-doc__sphinx-8595": 2, "sphinx-doc__sphinx-8621": 2, "sphinx-doc__sphinx-8638": 2, "sphinx-doc__sphinx-9229": 2, "sphinx-doc__sphinx-9281": 2, "sphinx-doc__sphinx-9461": 2, "sphinx-doc__sphinx-9591": 2, "sphinx-doc__sphinx-9658": 2, "sphinx-doc__sphinx-9673": 2, "sympy__sympy-12096": 2, "sympy__sympy-12481": 2, "sphinx-doc__sphinx-10323": 2, "sphinx-doc__sphinx-7590": 2, "sympy__sympy-13877": 2, "sympy__sympy-12489": 2, "sympy__sympy-15809": 2, "sympy__sympy-14711": 2, "sympy__sympy-16597": 2, "sympy__sympy-16766": 2, "sympy__sympy-16792": 2, "sympy__sympy-15875": 2, "sympy__sympy-17655": 2, "sympy__sympy-18189": 2, "sympy__sympy-18763": 2, "sympy__sympy-19040": 2, "sympy__sympy-19495": 2, "sympy__sympy-19637": 2, "sympy__sympy-19783": 2, "sympy__sympy-17630": 2, "sympy__sympy-20428": 2, "sympy__sympy-20590": 2, "sympy__sympy-20801": 2, "sympy__sympy-21379": 2, "sympy__sympy-21847": 2, "sympy__sympy-22456": 2, "sympy__sympy-22714": 2, "sympy__sympy-22914": 2, "sympy__sympy-23262": 2, "sympy__sympy-23413": 2, "sympy__sympy-23534": 2, "sympy__sympy-24066": 2, "sympy__sympy-24213": 2, "sympy__sympy-24443": 2, "sympy__sympy-24562": 2, "sympy__sympy-24661": 2}

evaluation/benchmarks/swe_bench/run_infer.py

@@ -18,6 +18,7 @@ from evaluation.utils.shared import (
     EvalOutput,
     assert_and_raise,
     codeact_user_response,
+    get_default_sandbox_config_for_eval,
     get_metrics,
     is_fatal_evaluation_error,
     make_metadata,
@@ -30,7 +31,6 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     AppConfig,
-    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
@@ -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. '
@@ -122,30 +138,23 @@ def get_config(
         base_container_image = SWE_BENCH_CONTAINER_IMAGE
         logger.info(f'Using swe-bench container image: {base_container_image}')
 
+    sandbox_config = get_default_sandbox_config_for_eval()
+    sandbox_config.base_container_image = base_container_image
+    sandbox_config.enable_auto_lint = True
+    sandbox_config.use_host_network = False
+    # Add platform to the sandbox config to solve issue 4401
+    sandbox_config.platform = 'linux/amd64'
+    sandbox_config.remote_runtime_resource_factor = get_instance_resource_factor(
+        dataset_name=metadata.dataset,
+        instance_id=instance['instance_id'],
+    )
+
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         max_iterations=metadata.max_iterations,
         runtime=os.environ.get('RUNTIME', 'docker'),
-        sandbox=SandboxConfig(
-            base_container_image=base_container_image,
-            enable_auto_lint=True,
-            use_host_network=False,
-            # large enough timeout, since some testcases take very long to run
-            timeout=300,
-            # Add platform to the sandbox config to solve issue 4401
-            platform='linux/amd64',
-            api_key=os.environ.get('ALLHANDS_API_KEY', None),
-            remote_runtime_api_url=os.environ.get('SANDBOX_REMOTE_RUNTIME_API_URL'),
-            keep_runtime_alive=False,
-            remote_runtime_init_timeout=3600,
-            remote_runtime_api_timeout=120,
-            remote_runtime_resource_factor=get_instance_resource_factor(
-                dataset_name=metadata.dataset,
-                instance_id=instance['instance_id'],
-            ),
-            remote_runtime_enable_retries=True,
-        ),
+        sandbox=sandbox_config,
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -331,6 +340,22 @@ def complete_runtime(
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+    if obs.exit_code == -1:
+        # The previous command is still running
+        # We need to kill previous command
+        logger.info('The previous command is still running, trying to kill it...')
+        action = CmdRunAction(command='C-c')
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
+        # Then run the command again
+        action = CmdRunAction(command=f'cd /workspace/{workspace_dir_name}')
+        action.set_hard_timeout(600)
+        logger.info(action, extra={'msg_type': 'ACTION'})
+        obs = runtime.run_action(action)
+        logger.info(obs, extra={'msg_type': 'OBSERVATION'})
+
     assert_and_raise(
         isinstance(obs, CmdOutputObservation) and obs.exit_code == 0,
         f'Failed to cd to /workspace/{workspace_dir_name}: {str(obs)}',
@@ -413,7 +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)

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

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

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}')

evaluation/benchmarks/swe_bench/scripts/docker/pull_all_eval_docker.sh

@@ -1,66 +1,36 @@
-#!/bin/bash
+#!/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"

evaluation/benchmarks/swe_bench/scripts/docker/push_eval_docker.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 # This is ONLY used for pushing docker images created by https://github.com/princeton-nlp/SWE-bench/blob/main/docs/20240627_docker/README.md
 

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')
 

evaluation/benchmarks/swe_bench/scripts/eval/convert_oh_folder_to_swebench_submission.sh

@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 
 FOLDER_PATH=$1
 NEW_FOLDER_PATH=${FOLDER_PATH}.swebench_submission