Merge branch 'main' into mh/rel0240

.github/pull_request_template.md

@@ -1,12 +1,11 @@
-- [ ] 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**
+
+- [ ] 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**
 
-**End-user friendly description of the problem this fixes or functionality that this introduces.**
 
 
 ---
-**Give a summary of what the PR does, explaining any non-trivial design decisions.**
-
-
----
-**Link of any specific issues this addresses.**
+**Link of any specific issues this addresses**

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

@@ -24,10 +24,6 @@ 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

@@ -41,10 +41,8 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.pull_request.head.sha }}
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3.6.0
+        uses: docker/setup-qemu-action@v3.4.0
         with:
           image: tonistiigi/binfmt:latest
       - name: Login to GHCR
@@ -56,22 +54,22 @@ jobs:
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
-      - name: Lowercase Repository Owner
-        run: |
-          echo REPO_OWNER=$(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 ${{ env.REPO_OWNER }} --push
+          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --push
       - name: Build app image
         if: "github.event.pull_request.head.repo.fork"
         run: |
-          ./containers/build.sh -i openhands -o ${{ env.REPO_OWNER }} --load
+          ./containers/build.sh -i openhands -o ${{ github.repository_owner }} --load
       - name: Get hash in App Image
         id: get_hash_in_app_image
         run: |
+          # Lowercase the repository owner
+          export REPO_OWNER=${{ github.repository_owner }}
+          REPO_OWNER=$(echo $REPO_OWNER | tr '[:upper:]' '[:lower:]')
           # Run the build script in the app image
-          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${{ env.REPO_OWNER }}/openhands:${{ env.RELEVANT_SHA }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
+          docker run -e SANDBOX_USER_ID=0 -v /var/run/docker.sock:/var/run/docker.sock ghcr.io/${REPO_OWNER}/openhands:${{ env.RELEVANT_SHA }} /bin/bash -c "mkdir -p containers/runtime; python3 openhands/runtime/utils/runtime_build.py --base_image ${{ env.BASE_IMAGE_FOR_HASH_EQUIVALENCE_TEST }} --build_folder containers/runtime --force_rebuild" 2>&1 | tee docker-outputs.txt
           # Get the hash from the build script
           hash_from_app_image=$(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
@@ -92,10 +90,8 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.pull_request.head.sha }}
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3.6.0
+        uses: docker/setup-qemu-action@v3.4.0
         with:
           image: tonistiigi/binfmt:latest
       - name: Login to GHCR
@@ -126,19 +122,16 @@ 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 ${{ env.REPO_OWNER }} --push -t ${{ matrix.base_image.tag }}
+          ./containers/build.sh -i runtime -o ${{ github.repository_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 ${{ matrix.base_image.image }} for fork
         if: github.event.pull_request.head.repo.fork
         uses: docker/build-push-action@v6
         with:
-          tags: ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image.tag }}
+          tags: ghcr.io/all-hands-ai/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
@@ -158,8 +151,6 @@ jobs:
         base_image: ['nikolaik']
     steps:
       - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.pull_request.head.sha }}
       - name: Cache Poetry dependencies
         uses: actions/cache@v4
         with:
@@ -242,9 +233,6 @@ jobs:
         run: pipx install poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies
-      - name: Lowercase Repository Owner
-        run: |
-          echo REPO_OWNER=$(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
@@ -253,7 +241,8 @@ jobs:
           # Install to be able to retry on failures for flaky tests
           poetry run pip install pytest-rerunfailures
 
-          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
+          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
+          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
 
           TEST_RUNTIME=docker \
           SANDBOX_USER_ID=$(id -u) \
@@ -307,9 +296,6 @@ jobs:
         run: pipx install poetry
       - name: Install Python dependencies using Poetry
         run: make install-python-dependencies
-      - name: Lowercase Repository Owner
-        run: |
-          echo REPO_OWNER=$(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
@@ -318,7 +304,8 @@ jobs:
           # Install to be able to retry on failures for flaky tests
           poetry run pip install pytest-rerunfailures
 
-          image_name=ghcr.io/${{ env.REPO_OWNER }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
+          image_name=ghcr.io/${{ github.repository_owner }}/runtime:${{ env.RELEVANT_SHA }}-${{ matrix.base_image }}
+          image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
 
           TEST_RUNTIME=docker \
           SANDBOX_USER_ID=$(id -u) \

.github/workflows/integration-runner.yml

@@ -40,11 +40,6 @@ 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

@@ -88,10 +88,12 @@ jobs:
         run: |
           python -m pip index versions openhands-ai > openhands_versions.txt
           OPENHANDS_VERSION=$(head -n 1 openhands_versions.txt | awk '{print $2}' | tr -d '()')
-
-          # Create a new requirements.txt locally within the workflow, ensuring no reference to the repo's file
-          echo "openhands-ai==${OPENHANDS_VERSION}" > /tmp/requirements.txt
-          cat /tmp/requirements.txt
+          # 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
 
       - name: Cache pip dependencies
         if: |
@@ -109,9 +111,9 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ${{ env.pythonLocation }}/lib/python3.12/site-packages/*
-          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('/tmp/requirements.txt') }}
+          key: ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
           restore-keys: |
-            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('/tmp/requirements.txt') }}
+            ${{ runner.os }}-pip-openhands-resolver-${{ hashFiles('requirements.txt') }}
 
       - name: Check required environment variables
         env:
@@ -223,14 +225,13 @@ jobs:
             } else {
               console.log("Installing from requirements.txt...");
               await exec.exec("python -m pip install --upgrade pip");
-              await exec.exec("pip install -r /tmp/requirements.txt");
+              await exec.exec("pip install -r 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 }}
@@ -267,7 +268,6 @@ 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

@@ -32,10 +32,6 @@ 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
@@ -48,7 +44,7 @@ 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_long_term_memory.py
+        run: poetry run pytest --forked -n auto --cov=openhands --cov-report=xml -svv ./tests/unit --ignore=tests/unit/test_memory.py
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v5
         env:

CITATION.cff

@@ -1,55 +0,0 @@
-cff-version: 1.2.0
-message: "If you use this software, please cite it using the following metadata."
-title: "OpenHands: An Open Platform for AI Software Developers as Generalist Agents"
-authors:
-  - family-names: Wang
-    given-names: Xingyao
-  - family-names: Li
-    given-names: Boxuan
-  - family-names: Song
-    given-names: Yufan
-  - family-names: Xu
-    given-names: Frank F.
-  - family-names: Tang
-    given-names: Xiangru
-  - family-names: Zhuge
-    given-names: Mingchen
-  - family-names: Pan
-    given-names: Jiayi
-  - family-names: Song
-    given-names: Yueqi
-  - family-names: Li
-    given-names: Bowen
-  - family-names: Singh
-    given-names: Jaskirat
-  - family-names: Tran
-    given-names: Hoang H.
-  - family-names: Li
-    given-names: Fuqiang
-  - family-names: Ma
-    given-names: Ren
-  - family-names: Zheng
-    given-names: Mingzhang
-  - family-names: Qian
-    given-names: Bill
-  - family-names: Shao
-    given-names: Yanjun
-  - family-names: Muennighoff
-    given-names: Niklas
-  - family-names: Zhang
-    given-names: Yizhe
-  - family-names: Hui
-    given-names: Binyuan
-  - family-names: Lin
-    given-names: Junyang
-  - family-names: Brennan
-    given-names: Robert
-  - family-names: Peng
-    given-names: Hao
-  - family-names: Ji
-    given-names: Heng
-  - family-names: Neubig
-    given-names: Graham
-year: 2024
-doi: "10.48550/arXiv.2407.16741"
-url: "https://arxiv.org/abs/2407.16741"

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:0.28-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.24-nikolaik`
 
 ## Develop inside Docker container
 

ISSUE_TRIAGE.md

@@ -2,13 +2,12 @@
 These are the procedures and guidelines on how issues are triaged in this repo by the maintainers.
 
 ## General
-* All issues must be tagged with **enhancement**, **bug** or **troubleshooting/help**.
-* Issues may be tagged with what it relates to (**agent quality**, **frontend**, **resolver**, etc.).
+* Most issues must be tagged with **enhancement** or **bug**.
+* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.).
 
 ## Severity
 * **Low**: Minor issues or affecting single user.
 * **Medium**: Affecting multiple users.
-* **High**: High visibility issues or affecting many users.
 * **Critical**: Affecting all users or potential security issues.
 
 ## Effort
@@ -19,14 +18,8 @@ These are the procedures and guidelines on how issues are triaged in this repo b
 
 ## Not Enough Information
 * User is asked to provide more information (logs, how to reproduce, etc.) when the issue is not clear.
-* If an issue is unclear and the author does not provide more information or respond to a request,
-the issue may be closed as **not planned** (Usually after a week).
+* If an issue is unclear and the author does not provide more information or respond to a request, the issue may be closed as **not planned** (Usually after a week).
 
 ## Multiple Requests/Fixes in One Issue
 * These issues will be narrowed down to one request/fix so the issue is more easily tracked and fixed.
 * Issues may be broken down into multiple issues if required.
-
-## Stale and Auto Closures
-* In order to keep a maintainable backlog, issues that have no activity within 30 days are automatically marked as **Stale**.
-* If issues marked as **Stale** continue to have no activity for 7 more days, they will automatically be closed as not planned.
-* Issues may be reopened by maintainers if deemed important.

Makefile

@@ -1,4 +1,4 @@
-SHELL=/usr/bin/env bash
+SHELL=/bin/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 22 ]; then \
+		if [ "$${NODE_VERSION_ARRAY[0]}" -ge 20 ]; then \
 			echo "$(BLUE)Node.js $$NODE_VERSION is already installed.$(RESET)"; \
 		else \
-			echo "$(RED)Node.js 22.x or later is required. Please install Node.js 22.x or later to continue.$(RESET)"; \
+			echo "$(RED)Node.js 20.x or later is required. Please install Node.js 20.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:0.28-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28
+    docker.all-hands.dev/all-hands-ai/openhands:0.24
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

build.sh

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

config.template.toml

@@ -17,12 +17,6 @@
 #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"
 
@@ -95,11 +89,6 @@ workspace_base = "./workspace"
 # List of allowed file extensions for uploads
 #file_uploads_allowed_extensions = [".*"]
 
-# Whether to enable the default LLM summarizing condenser when no condenser is specified in config
-# When true, a LLMSummarizingCondenserConfig will be used as the default condenser
-# When false, a NoOpCondenserConfig (no summarization) will be used
-#enable_default_condenser = true
-
 #################################### LLM #####################################
 # Configuration for LLM models (group name starts with 'llm')
 # use 'llm' for the default LLM config
@@ -245,10 +234,6 @@ 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
@@ -299,69 +284,6 @@ llm_config = 'gpt3'
 # The security analyzer to use (For Headless / CLI only -  In Web this is overridden by Session Init)
 #security_analyzer = ""
 
-#################################### Condenser #################################
-# Condensers control how conversation history is managed and compressed when
-# the context grows too large. Each agent uses one condenser configuration.
-##############################################################################
-[condenser]
-# The type of condenser to use. Available options:
-# - "noop": No condensing, keeps full history (default)
-# - "observation_masking": Keeps full event structure but masks older observations
-# - "recent": Keeps only recent events and discards older ones
-# - "llm": Uses an LLM to summarize conversation history
-# - "amortized": Intelligently forgets older events while preserving important context
-# - "llm_attention": Uses an LLM to prioritize most relevant context
-type = "noop"
-
-# Examples for each condenser type (uncomment and modify as needed):
-
-# 1. NoOp Condenser - No additional settings needed
-#type = "noop"
-
-# 2. Observation Masking Condenser
-#type = "observation_masking"
-# Number of most-recent events where observations will not be masked
-#attention_window = 100
-
-# 3. Recent Events Condenser
-#type = "recent"
-# Number of initial events to always keep (typically includes task description)
-#keep_first = 1
-# Maximum number of events to keep in history
-#max_events = 100
-
-# 4. LLM Summarizing Condenser
-#type = "llm"
-# Reference to an LLM config to use for summarization
-#llm_config = "condenser"
-# Number of initial events to always keep (typically includes task description)
-#keep_first = 1
-# Maximum size of history before triggering summarization
-#max_size = 100
-
-# 5. Amortized Forgetting Condenser
-#type = "amortized"
-# Number of initial events to always keep (typically includes task description)
-#keep_first = 1
-# Maximum size of history before triggering forgetting
-#max_size = 100
-
-# 6. LLM Attention Condenser
-#type = "llm_attention"
-# Reference to an LLM config to use for attention scoring
-#llm_config = "condenser"
-# Number of initial events to always keep (typically includes task description)
-#keep_first = 1
-# Maximum size of history before triggering attention mechanism
-#max_size = 100
-
-# Example of a custom LLM configuration for condensers that require an LLM
-# If not provided, it falls back to the default LLM
-#[llm.condenser]
-#model = "gpt-4o"
-#temperature = 0.1
-#max_tokens = 1024
-
 #################################### Eval ####################################
 # Configuration for the evaluation, please refer to the specific evaluation
 # plugin for the available options

containers/build.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/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:0.28-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.24-nikolaik}
       - SANDBOX_USER_ID=${SANDBOX_USER_ID:-1234}
       - WORKSPACE_MOUNT_PATH=${WORKSPACE_BASE:-$PWD/workspace}
     ports:

containers/dev/dev.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/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:0.28-nikolaik}
+      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik}
       #- SANDBOX_USER_ID=${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

@@ -46,11 +46,3 @@ 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

@@ -42,11 +42,10 @@ 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 ```base_container_image``` est défini sur le nom de votre image personnalisée précédente.
+> Assurez-vous que ```sandbox_base_container_image``` est défini sur le nom de votre image personnalisée précédente.
 
 ## Exécution
 
@@ -83,15 +82,14 @@ 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 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 sandbox_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"
-user_id="1001"
+sandbox_base_container_image="image_personnalisée"
+sandbox_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:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     python -m openhands.core.cli
 ```
 

docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/custom-sandbox-guide.md

@@ -44,13 +44,12 @@ 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 `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 `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 :
 
 ```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:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     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:0.28-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28
+    docker.all-hands.dev/all-hands-ai/openhands:0.24
 ```
 
 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:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

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

@@ -58,11 +58,10 @@ 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 `base_container_image` 的值, 您可以选择以下任意一项：
+对于 `sandbox_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）
 
@@ -84,15 +83,14 @@ 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 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 sandbox_user_id 字段为不同的值：
 
 ```
 [core]
 workspace_base="./workspace"
 run_as_openhands=true
-[sandbox]
-base_container_image="custom_image"
-user_id="1001"
+sandbox_base_container_image="custom_image"
+sandbox_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:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     python -m openhands.core.cli
 ```
 

docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/custom-sandbox-guide.md

@@ -42,13 +42,12 @@ 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 `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 `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：
 
 ```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:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     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:0.28-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28
+    docker.all-hands.dev/all-hands-ai/openhands:0.24
 ```
 
 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:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```

docs/modules/usage/architecture/runtime.md

@@ -54,13 +54,14 @@ 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:
 
+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.
@@ -77,15 +78,16 @@ 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

@@ -1,21 +0,0 @@
-# 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

@@ -1,39 +0,0 @@
-# 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

@@ -340,11 +340,6 @@ 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`
@@ -385,11 +380,6 @@ To use these with the docker command, pass in `-e SANDBOX_<option>`. Example: `-
   - Default: `false`
   - Description: Use host network
 
-- `runtime_binding_address`
-  - Type: `str`
-  - Default: `127.0.0.1`
-  - Description: The binding address for the runtime ports.  It specifies which network interface on the host machine Docker should bind the runtime ports to.
-
 ### Linting and Plugins
 - `enable_auto_lint`
   - 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:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     python -m openhands.core.cli
 ```
 

docs/modules/usage/how-to/custom-sandbox-guide.md

@@ -60,14 +60,13 @@ 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 `base_container_image` to the image you want to use.
+In the `config.toml` file within the OpenHands directory, set the `sandbox_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

@@ -1,6 +1,9 @@
 # GUI Mode
 
-OpenHands provides a Graphical User Interface (GUI) mode for interacting with the AI assistant.
+## 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.
 
 ## Installation and Setup
 
@@ -11,95 +14,104 @@ OpenHands provides a Graphical User Interface (GUI) mode for interacting with th
 
 ### Initial Setup
 
-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.
+1. Upon first launch, you'll see a settings modal.
+2. Select an `LLM Provider` and `LLM Model` from the dropdown menus.
 3. Enter the corresponding `API Key` for your chosen provider.
-4. Click `Save Changes` to apply the settings.
+4. Click "Save" 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:
 
-- **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)`.
+- **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)".
    - Required scopes:
      - `repo` (Full control of private repositories)
-  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>
+     - `workflow` (Update GitHub Action workflows)
+     - `read:org` (Read organization data)
 
-<details>
-  <summary>Organizational Token Policies</summary>
+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.
 
-  If you're working with organizational repositories, additional setup may be required:
+#### Organizational Token Policies
 
-  1. **Check Organization Requirements**:
+If you're working with organizational repositories, additional setup may be required:
+
+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>
 
-<details>
-  <summary>Troubleshooting</summary>
+#### OAuth Authentication (Online Mode)
 
-  Common issues and solutions:
+When using OpenHands in online mode, the GitHub OAuth flow:
 
-  - **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:
+1. Requests the following permissions:
    - Repository access (read/write)
    - Workflow management
    - Organization read access
 
-  To authenticate OpenHands:
-   - Click `Sign in with GitHub` when prompted.
+2. Authentication steps:
+   - 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.
-</details>
+
+#### 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.
 
 ### Advanced Settings
 
-1. Inside the Settings page, toggle `Advanced` options to access additional settings.
+1. 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 prompt in the input box.
+1. Type your question, request, or task description 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:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

docs/modules/usage/installation.mdx

@@ -6,14 +6,11 @@
 - 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.
@@ -26,7 +23,7 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
   Tested with Ubuntu 22.04.
   :::
 
-  **Docker Desktop**
+  ### Docker Desktop
 
   1. [Install Docker Desktop on Linux](https://docs.docker.com/desktop/setup/install/linux/).
 
@@ -34,13 +31,12 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 
 <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:
@@ -58,17 +54,17 @@ A system with a modern processor and a minimum of **4GB RAM** is recommended to
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.28
+    docker.all-hands.dev/all-hands-ai/openhands:0.24
 ```
 
 You'll find OpenHands running at http://localhost:3000!
@@ -80,22 +76,24 @@ 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 page. You **must** select an `LLM Provider` and `LLM Model` and enter a corresponding `API Key`.
+Upon launching OpenHands, you'll see a settings modal. 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 model does not exist in the list, you can toggle `Advanced` options and manually enter it with the correct prefix
+If the required `LLM 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.
 
-Now you're ready to [get started with OpenHands](./getting-started).
+<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>
 
 ## Versions
 
-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:$VERSION`, with `main`.
-This version is unstable and is recommended for testing or development purposes only.
+The command above pulls the most recent stable release of OpenHands. You have other options as well:
+- For a specific release, use `docker.all-hands.dev/all-hands-ai/openhands:$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.
 
 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).
+retry requests if it receives a Rate Limit Error (429 error code), API connection error, or other transient errors.
 
 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 4 times)
-- `LLM_RETRY_MIN_WAIT` (Default of 5 seconds)
-- `LLM_RETRY_MAX_WAIT` (Default of 30 seconds)
+- `LLM_NUM_RETRIES` (Default of 8)
+- `LLM_RETRY_MIN_WAIT` (Default of 15 seconds)
+- `LLM_RETRY_MAX_WAIT` (Default of 120 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 = 4
-retry_min_wait = 5
-retry_max_wait = 30
+num_retries = 8
+retry_min_wait = 15
+retry_max_wait = 120
 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:0.28-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik \
     -v /var/run/docker.sock:/var/run/docker.sock \
     # ...
 ```
@@ -84,36 +84,3 @@ docker run # ...
     -e MODAL_API_TOKEN_ID="your-id" \
     -e MODAL_API_TOKEN_SECRET="your-secret" \
 ```
-
-## Daytona Runtime
-
-Another option is using [Daytona](https://www.daytona.io/) as a runtime provider:
-
-### Step 1: Retrieve Your Daytona API Key
-1. Visit the [Daytona Dashboard](https://app.daytona.io/dashboard/keys).
-2. Click **"Create Key"**.
-3. Enter a name for your key and confirm the creation.
-4. Once the key is generated, copy it.
-
-### Step 2: Set Your API Key as an Environment Variable
-Run the following command in your terminal, replacing `<your-api-key>` with the actual key you copied:
-```bash
-export DAYTONA_API_KEY="<your-api-key>"
-```
-
-This step ensures that OpenHands can authenticate with the Daytona platform when it runs.
-
-### Step 3: Run OpenHands Locally Using Docker
-To start the latest version of OpenHands on your machine, execute the following command in your terminal:
-```bash
-bash -i <(curl -sL https://get.daytona.io/openhands)
-```
-
-#### What This Command Does:
-- Downloads the latest OpenHands release script.
-- Runs the script in an interactive Bash session.
-- Automatically pulls and runs the OpenHands container using Docker.
-
-Once executed, OpenHands should be running locally and ready for use.
-
-For more details and manual initialization, view the entire [README.md](https://github.com/All-Hands-AI/OpenHands/blob/main/openhands/runtime/impl/daytona/README.md)

docs/package-lock.json

@@ -17,14 +17,14 @@
         "prism-react-renderer": "^2.4.1",
         "react": "^19.0.0",
         "react-dom": "^19.0.0",
-        "react-icons": "^5.5.0",
+        "react-icons": "^5.4.0",
         "react-use": "^17.6.0"
       },
       "devDependencies": {
         "@docusaurus/module-type-aliases": "^3.5.1",
         "@docusaurus/tsconfig": "^3.7.0",
         "@docusaurus/types": "^3.5.1",
-        "typescript": "~5.8.2"
+        "typescript": "~5.7.3"
       },
       "engines": {
         "node": ">=18.0"
@@ -15680,9 +15680,9 @@
       }
     },
     "node_modules/react-icons": {
-      "version": "5.5.0",
-      "resolved": "https://registry.npmjs.org/react-icons/-/react-icons-5.5.0.tgz",
-      "integrity": "sha512-MEFcXdkP3dLo8uumGI5xN3lDFNsRtrjbOEKDLD7yv76v4wpnEq2Lt2qeHaQOr34I/wPN3s3+N08WkQ+CW37Xiw==",
+      "version": "5.4.0",
+      "resolved": "https://registry.npmjs.org/react-icons/-/react-icons-5.4.0.tgz",
+      "integrity": "sha512-7eltJxgVt7X64oHh6wSWNwwbKTCtMfK35hcjvJS0yxEAhPM8oUKdS3+kqaW1vicIltw+kR2unHaa12S9pPALoQ==",
       "license": "MIT",
       "peerDependencies": {
         "react": "*"
@@ -17638,9 +17638,9 @@
       }
     },
     "node_modules/typescript": {
-      "version": "5.8.2",
-      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.8.2.tgz",
-      "integrity": "sha512-aJn6wq13/afZp/jT9QZmwEjDqqvSGp1VT5GVg+f/t6/oVyrgXM6BY1h9BRh/O5p3PlUPAe+WuiEZOmb/49RqoQ==",
+      "version": "5.7.3",
+      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.7.3.tgz",
+      "integrity": "sha512-84MVSjMEHP+FQRPy3pX9sTVV/INIex71s9TL2Gm5FG/WG1SqXeKyZ0k7/blY/4FdOzI12CBy1vGc4og/eus0fw==",
       "license": "Apache-2.0",
       "bin": {
         "tsc": "bin/tsc",

docs/package.json

@@ -24,14 +24,14 @@
     "prism-react-renderer": "^2.4.1",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
-    "react-icons": "^5.5.0",
+    "react-icons": "^5.4.0",
     "react-use": "^17.6.0"
   },
   "devDependencies": {
     "@docusaurus/module-type-aliases": "^3.5.1",
     "@docusaurus/tsconfig": "^3.7.0",
     "@docusaurus/types": "^3.5.1",
-    "typescript": "~5.8.2"
+    "typescript": "~5.7.3"
   },
   "browserslist": {
     "production": [

docs/sidebars.ts

@@ -42,7 +42,7 @@ const sidebars: SidebarsConfig = {
               id: 'usage/prompting/microagents-public',
             },
           ],
-        },
+        }
       ],
     },
     {
@@ -66,26 +66,9 @@ const sidebars: SidebarsConfig = {
         },
         {
           type: 'doc',
-          label: 'Github Action',
+          label: 'Github Actions',
           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',
-            },
-          ],
-        },
       ],
     },
     {
@@ -202,7 +185,7 @@ const sidebars: SidebarsConfig = {
       type: 'doc',
       label: 'About',
       id: 'usage/about',
-    },
+    }
   ],
 };
 

docs/src/components/Demo/Demo.tsx

@@ -5,6 +5,9 @@ export function Demo() {
   const videoRef = React.useRef<HTMLVideoElement>(null);
 
   return (
+    <div
+      style={{ paddingBottom: "10px", paddingTop: "10px", textAlign: "center" }}
+    >
       <video
         playsInline
         autoPlay={true}
@@ -17,5 +20,6 @@ export function Demo() {
       >
         <source src="img/teaser.mp4" type="video/mp4"></source>
       </video>
+    </div>
   );
 }

docs/src/components/Demo/index.module.css

@@ -1,5 +1,6 @@
 .demo {
   width: 100%;
+  padding: 30px;
   max-width: 800px;
   text-align: center;
   border-radius: 40px;

docs/src/components/HomepageHeader/HomepageHeader.tsx

@@ -17,29 +17,6 @@ export function HomepageHeader() {
 
         <p className="header-subtitle">{siteConfig.tagline}</p>
 
-        <div style={{
-          textAlign: 'center',
-          fontSize: '1.2rem',
-          maxWidth: '800px',
-          margin: '0 auto',
-          padding: '0rem 0rem 1rem'
-        }}>
-        <p style={{ margin: '0' }}>
-          Use AI to tackle the toil in your backlog. Our agents have all the same tools as a human developer: they can modify code, run commands, browse the web,
-          call APIs, and yes-even copy code snippets from StackOverflow.
-          <br/>
-          <Link to="https://docs.all-hands.dev/modules/usage/installation"
-            style={{
-              textDecoration: 'underline',
-              display: 'inline-block',
-              marginTop: '0.5rem'
-            }}
-          >
-            Get started with OpenHands.
-          </Link>
-        </p>
-      </div>
-
         <div align="center" className="header-links">
           <a href="https://github.com/All-Hands-AI/OpenHands/graphs/contributors"><img src="https://img.shields.io/github/contributors/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Contributors" /></a>
           <a href="https://github.com/All-Hands-AI/OpenHands/stargazers"><img src="https://img.shields.io/github/stars/All-Hands-AI/OpenHands?style=for-the-badge&color=blue" alt="Stargazers" /></a>
@@ -50,9 +27,12 @@ export function HomepageHeader() {
           <a href="https://discord.gg/ESHStjSjD4"><img src="https://img.shields.io/badge/Discord-Join%20Us-purple?logo=discord&logoColor=white&style=for-the-badge" alt="Join our Discord community" /></a>
           <a href="https://github.com/All-Hands-AI/OpenHands/blob/main/CREDITS.md"><img src="https://img.shields.io/badge/Project-Credits-blue?style=for-the-badge&color=FFE165&logo=github&logoColor=white" alt="Credits" /></a>
           <br/>
+          <a href="https://docs.all-hands.dev/modules/usage/getting-started"><img src="https://img.shields.io/badge/Documentation-000?logo=googledocs&logoColor=FFE165&style=for-the-badge" alt="Check out the documentation" /></a>
           <a href="https://arxiv.org/abs/2407.16741"><img src="https://img.shields.io/badge/Paper%20on%20Arxiv-000?logoColor=FFE165&logo=arxiv&style=for-the-badge" alt="Paper on Arxiv" /></a>
           <a href="https://huggingface.co/spaces/OpenHands/evaluation"><img src="https://img.shields.io/badge/Benchmark%20score-000?logoColor=FFE165&logo=huggingface&style=for-the-badge" alt="Evaluation Benchmark Score" /></a>
         </div>
+
+        <Demo />
       </div>
     </div>
   );

docs/src/css/homepageHeader.css

@@ -1,14 +1,14 @@
 /* homepageHeader.css */
 
 .homepage-header {
-  padding: 1rem 0;
+  height: 800px;
 }
 
 .header-content {
   display: flex;
   flex-direction: column;
   align-items: center;
-  padding: 1rem;
+  padding: 2rem;
   font-weight: 300;
   width: 100%;
 }
@@ -25,7 +25,6 @@
 
 .header-subtitle {
   font-size: 1.5rem;
-  margin: 0.5rem 0;
 }
 
 .header-links {

docs/src/pages/index.tsx

@@ -2,7 +2,15 @@ import useDocusaurusContext from '@docusaurus/useDocusaurusContext';
 import Layout from '@theme/Layout';
 import { HomepageHeader } from '../components/HomepageHeader/HomepageHeader';
 import { translate } from '@docusaurus/Translate';
-import { Demo } from "../components/Demo/Demo";
+
+export function Header({ title, summary }): JSX.Element {
+  return (
+    <div>
+      <h1>{title}</h1>
+      <h2 style={{ fontSize: '3rem' }}>{summary}</h2>
+    </div>
+  );
+}
 
 export default function Home(): JSX.Element {
   const { siteConfig } = useDocusaurusContext();
@@ -15,20 +23,6 @@ export default function Home(): JSX.Element {
       })}
     >
       <HomepageHeader />
-
-      <div style={{ textAlign: 'center', padding: '1rem 0' }}>
-        <Demo />
-      </div>
-
-      <div style={{ textAlign: 'center', padding: '0.5rem 2rem 1.5rem' }}>
-        <h2>Most Popular Links</h2>
-        <ul style={{ listStyleType: 'none'}}>
-          <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

@@ -20,8 +20,6 @@ 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
@@ -42,8 +40,6 @@ 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

@@ -9,7 +9,6 @@ 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,
@@ -18,6 +17,7 @@ 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,
 )
@@ -60,14 +60,17 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='python:3.12-bookworm',
+            enable_auto_lint=False,
+            use_host_network=False,
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/EDA/scripts/run_infer.sh

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

evaluation/benchmarks/agent_bench/run_infer.py

@@ -17,7 +17,6 @@ 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,
@@ -26,6 +25,7 @@ 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,
 )
@@ -40,15 +40,21 @@ 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=sandbox_config,
+        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,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/agent_bench/scripts/run_infer.sh

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

evaluation/benchmarks/aider_bench/README.md

@@ -56,10 +56,9 @@ You can update the arguments in the script
 ./evaluation/benchmarks/aider_bench/scripts/run_infer.sh eval_gpt35_turbo HEAD CodeActAgent 100 1 "1,3,10"
 ```
 
-### Run Inference on `RemoteRuntime`
-
-This is in beta. Fill out [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply if you want to try this out!
+### Run Inference on `RemoteRuntime` (experimental)
 
+This is in limited beta. Contact Xingyao over slack if you want to try this out!
 
 ```bash
 ./evaluation/benchmarks/aider_bench/scripts/run_infer.sh [model_config] [git-version] [agent] [eval_limit] [eval-num-workers] [eval_ids]

evaluation/benchmarks/aider_bench/run_infer.py

@@ -16,7 +16,6 @@ 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,
@@ -25,6 +24,7 @@ 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,
@@ -47,14 +47,22 @@ 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=sandbox_config,
+        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,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -205,6 +213,7 @@ def process_instance(
 
     runtime: Runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)
+
     initialize_runtime(runtime, instance=instance)
 
     # Here's how you can run the agent (similar to the `main` function) and get the final task state

evaluation/benchmarks/aider_bench/scripts/run_infer.sh

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

evaluation/benchmarks/biocoder/run_infer.py

@@ -14,7 +14,6 @@ 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,
@@ -23,6 +22,7 @@ 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,
 )
@@ -57,15 +57,18 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image=BIOCODER_BENCH_CONTAINER_IMAGE,
+            enable_auto_lint=True,
+            use_host_network=False,
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/biocoder/scripts/run_infer.sh

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

evaluation/benchmarks/bird/run_infer.py

@@ -17,7 +17,6 @@ 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,
@@ -26,6 +25,7 @@ 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,
 )
@@ -71,15 +71,17 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='python:3.12-bookworm',
+            enable_auto_lint=True,
+            use_host_network=False,
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/bird/scripts/run_infer.sh

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

evaluation/benchmarks/browsing_delegation/run_infer.py

@@ -10,7 +10,6 @@ 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,
@@ -19,13 +18,13 @@ 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,
 )
 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
 
 # Only CodeActAgent can delegate to BrowsingAgent
 SUPPORTED_AGENT_CLS = {'CodeActAgent'}
@@ -37,14 +36,17 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='python:3.12-bookworm',
+            enable_auto_lint=False,
+            use_host_network=False,
+            remote_runtime_enable_retries=True,
+        ),
         workspace_base=None,
         workspace_mount_path=None,
     )
@@ -75,7 +77,6 @@ def process_instance(
     )
 
     runtime = create_runtime(config)
-    call_async_from_sync(runtime.connect)
 
     state: State | None = asyncio.run(
         run_controller(

evaluation/benchmarks/browsing_delegation/scripts/run_infer.sh

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

evaluation/benchmarks/commit0_bench/README.md

@@ -23,10 +23,10 @@ Make sure your Docker daemon is running, and you have ample disk space (at least
 When the `run_infer.sh` script is started, it will automatically pull the `lite` split in Commit0. For example, for instance ID `commit-0/minitorch`, it will try to pull our pre-build docker image `wentingzhao/minitorch` from DockerHub. This image will be used create an OpenHands runtime image where the agent will operate on.
 
 ```bash
-./evaluation/benchmarks/commit0/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
+./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
 
 # Example
-./evaluation/benchmarks/commit0/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 16 100 8 wentingzhao/commit0_combined test
+./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 16 100 8 wentingzhao/commit0_combined test
 ```
 
 where `model_config` is mandatory, and the rest are optional.
@@ -48,25 +48,26 @@ default, it is set to 1.
 - `dataset`, a huggingface dataset name. e.g. `wentingzhao/commit0_combined`, specifies which dataset to evaluate on.
 - `dataset_split`, split for the huggingface dataset. Notice only `test` is supported for Commit0.
 
+Note that the `USE_INSTANCE_IMAGE` environment variable is always set to `true` for Commit0.
+
 Let's say you'd like to run 10 instances using `llm.eval_sonnet` and CodeActAgent,
 
 then your command would be:
 
 ```bash
-./evaluation/benchmarks/commit0/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
+./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
 ```
 
-### Run Inference on `RemoteRuntime`
-
-This is in beta. Fill out [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply if you want to try this out!
+### Run Inference on `RemoteRuntime` (experimental)
 
+This is in limited beta. Contact Xingyao over slack if you want to try this out!
 
 ```bash
-./evaluation/benchmarks/commit0/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
+./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh [repo_split] [model_config] [git-version] [agent] [eval_limit] [max_iter] [num_workers] [dataset] [dataset_split]
 
 # Example - This runs evaluation on CodeActAgent for 10 instances on "wentingzhao/commit0_combined"'s test set, with max 30 iteration per instances, with 1 number of workers running in parallel
 ALLHANDS_API_KEY="YOUR-API-KEY" RUNTIME=remote SANDBOX_REMOTE_RUNTIME_API_URL="https://runtime.eval.all-hands.dev" EVAL_DOCKER_IMAGE_PREFIX="docker.io/wentingzhao" \
-./evaluation/benchmarks/commit0/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
+./evaluation/benchmarks/commit0_bench/scripts/run_infer.sh lite llm.eval_sonnet HEAD CodeActAgent 10 30 1 wentingzhao/commit0_combined test
 ```
 
 To clean-up all existing runtime you've already started, run:

evaluation/benchmarks/commit0_bench/run_infer.py

@@ -15,7 +15,6 @@ 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,
@@ -26,6 +25,7 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     AppConfig,
+    SandboxConfig,
     get_llm_config_arg,
     get_parser,
 )
@@ -39,6 +39,7 @@ 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'
+USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'false').lower() == 'true'
 RUN_WITH_BROWSING = os.environ.get('RUN_WITH_BROWSING', 'false').lower() == 'true'
 
 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
@@ -104,6 +105,9 @@ 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(
@@ -111,16 +115,28 @@ 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.'
     )
-
-    sandbox_config = get_default_sandbox_config_for_eval()
-    sandbox_config.base_container_image = base_container_image
+    # else:
+    #     raise
+    # base_container_image = SWE_BENCH_CONTAINER_IMAGE
+    # logger.info(f'Using swe-bench 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=sandbox_config,
+        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,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
@@ -301,16 +317,6 @@ def complete_runtime(
     pytest_exit_code = obs.content.strip()
     # logger.info(f'Pytest exit code: {pytest_exit_code}')
 
-    # Get test IDs from instance
-    repo_name = instance['repo'].split('/')[1]
-    repo_name = repo_name.replace('.', '-')
-    action = CmdRunAction(command=f'commit0 get-tests {repo_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'})
-    test_ids = obs.content.strip().split('\n')
-
     # Read the test report
     action = CmdRunAction(command='cat report.json')
     action.set_hard_timeout(600)
@@ -321,10 +327,18 @@ def complete_runtime(
         isinstance(obs, CmdOutputObservation),
         f'Failed to read test report: {str(obs)}',
     )
-    json_report = obs.content.strip()
+    # Get test IDs from instance
+    repo_name = instance['repo'].split('/')[1]
+    repo_name = repo_name.replace('.', '-')
+    action = CmdRunAction(command=f'commit0 get-tests {repo_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'})
+    test_ids = obs.content.strip().split('\n')
 
     try:
-        report = json.loads(json_report)
+        report = json.loads(obs.content)
         tests = {x['nodeid']: x['call'] for x in report['tests'] if 'call' in x}
 
         # Calculate test statistics

evaluation/benchmarks/commit0_bench/scripts/run_infer.sh

@@ -1,4 +1,4 @@
-#!/usr/bin/env bash
+#!/bin/bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"
@@ -30,6 +30,11 @@ if [ -z "$MAX_ITER" ]; then
   MAX_ITER=100
 fi
 
+if [ -z "$USE_INSTANCE_IMAGE" ]; then
+  echo "USE_INSTANCE_IMAGE not specified, use default true"
+  USE_INSTANCE_IMAGE=true
+fi
+
 if [ -z "$RUN_WITH_BROWSING" ]; then
   echo "RUN_WITH_BROWSING not specified, use default false"
   RUN_WITH_BROWSING=false
@@ -51,6 +56,8 @@ if [ -z "$SPLIT" ]; then
   SPLIT="test"
 fi
 
+export USE_INSTANCE_IMAGE=$USE_INSTANCE_IMAGE
+echo "USE_INSTANCE_IMAGE: $USE_INSTANCE_IMAGE"
 export RUN_WITH_BROWSING=$RUN_WITH_BROWSING
 echo "RUN_WITH_BROWSING: $RUN_WITH_BROWSING"
 
@@ -84,7 +91,7 @@ fi
 
 function run_eval() {
   local eval_note=$1
-  COMMAND="poetry run python evaluation/benchmarks/commit0/run_infer.py \
+  COMMAND="poetry run python evaluation/benchmarks/commit0_bench/run_infer.py \
     --agent-cls $AGENT \
     --llm-config $MODEL_CONFIG \
     --max-iterations $MAX_ITER \

evaluation/benchmarks/discoverybench/run_infer.py

@@ -16,7 +16,6 @@ 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,
@@ -26,6 +25,7 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     AppConfig,
+    SandboxConfig,
     get_llm_config_arg,
     parse_arguments,
 )
@@ -62,14 +62,17 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='python:3.12-bookworm',
+            enable_auto_lint=True,
+            use_host_network=False,
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/discoverybench/scripts/run_infer.sh

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

evaluation/benchmarks/gaia/run_infer.py

@@ -13,7 +13,6 @@ 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,
@@ -22,10 +21,10 @@ 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
@@ -48,25 +47,24 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='python:3.12-bookworm',
+            enable_auto_lint=True,
+            use_host_network=False,
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    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
+    agent_config = config.get_agent_config(metadata.agent_class)
+    agent_config.enable_prompt_extensions = False
     return config
 
 
@@ -240,10 +238,6 @@ 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)
@@ -262,7 +256,6 @@ 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 @@
-#!/usr/bin/env bash
+#!/bin/bash
 set -eo pipefail
 
 source "evaluation/utils/version_control.sh"
@@ -9,7 +9,6 @@ AGENT=$3
 EVAL_LIMIT=$4
 LEVELS=$5
 NUM_WORKERS=$6
-AGENT_CONFIG=$7
 
 if [ -z "$NUM_WORKERS" ]; then
   NUM_WORKERS=1
@@ -50,9 +49,5 @@ if [ -n "$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/ast_eval_hf.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 # This file is modified from https://github.com/ShishirPatil/gorilla/blob/main/eval/eval-scripts/ast_eval_hf.py
 
-import tree_sitter_python as tspython
 from tree_sitter import Language, Parser
 
 
@@ -40,9 +39,10 @@ def get_all_sub_trees(root_node):
 
 
 # Parse the program into AST trees
-def ast_parse(candidate):
-    LANGUAGE = Language(tspython.language())
-    parser = Parser(LANGUAGE)
+def ast_parse(candidate, lang='python'):
+    LANGUAGE = Language('evaluation/gorilla/my-languages.so', lang)
+    parser = Parser()
+    parser.set_language(LANGUAGE)
 
     candidate_tree = parser.parse(bytes(candidate, 'utf8')).root_node
     return candidate_tree

evaluation/benchmarks/gorilla/ast_eval_tf.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 # This file is modified from https://github.com/ShishirPatil/gorilla/blob/main/eval/eval-scripts/ast_eval_tf.py
 
-import tree_sitter_python as tspython
 from tree_sitter import Language, Parser
 
 
@@ -40,9 +39,10 @@ def get_all_sub_trees(root_node):
 
 
 # Parse the program into AST trees
-def ast_parse(candidate):
-    LANGUAGE = Language(tspython.language())
-    parser = Parser(LANGUAGE)
+def ast_parse(candidate, lang='python'):
+    LANGUAGE = Language('evaluation/gorilla/my-languages.so', lang)
+    parser = Parser()
+    parser.set_language(LANGUAGE)
 
     candidate_tree = parser.parse(bytes(candidate, 'utf8')).root_node
     return candidate_tree

evaluation/benchmarks/gorilla/ast_eval_th.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 # This file is modified from https://github.com/ShishirPatil/gorilla/blob/main/eval/eval-scripts/ast_eval_th.py
 
-import tree_sitter_python as tspython
 from tree_sitter import Language, Parser
 
 
@@ -40,9 +39,10 @@ def get_all_sub_trees(root_node):
 
 
 # Parse the program into AST trees
-def ast_parse(candidate):
-    LANGUAGE = Language(tspython.language())
-    parser = Parser(LANGUAGE)
+def ast_parse(candidate, lang='python'):
+    LANGUAGE = Language('evaluation/gorilla/my-languages.so', lang)
+    parser = Parser()
+    parser.set_language(LANGUAGE)
 
     candidate_tree = parser.parse(bytes(candidate, 'utf8')).root_node
     return candidate_tree

evaluation/benchmarks/gorilla/run_infer.py

@@ -11,7 +11,6 @@ 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,
@@ -20,6 +19,7 @@ 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,
 )
@@ -40,14 +40,17 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='python:3.12-bookworm',
+            enable_auto_lint=True,
+            use_host_network=False,
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/gorilla/scripts/run_infer.sh

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

evaluation/benchmarks/gorilla/utils.py

@@ -71,19 +71,19 @@ def fetch_data(url, filename):
 
 def get_data_for_hub(hub: str):
     if hub == 'hf':
-        question_data = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/refs/tags/v1.2/eval/eval-data/questions/huggingface/questions_huggingface_0_shot.jsonl'
-        api_dataset = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/refs/tags/v1.2/data/api/huggingface_api.jsonl'
-        apibench = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/refs/tags/v1.2/data/apibench/huggingface_eval.json'
+        question_data = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/main/eval/eval-data/questions/huggingface/questions_huggingface_0_shot.jsonl'
+        api_dataset = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/main/data/api/huggingface_api.jsonl'
+        apibench = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/main/data/apibench/huggingface_eval.json'
         ast_eval = ast_eval_hf
     elif hub == 'torch':
-        question_data = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/refs/tags/v1.2/eval/eval-data/questions/torchhub/questions_torchhub_0_shot.jsonl'
-        api_dataset = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/refs/tags/v1.2/data/api/torchhub_api.jsonl'
-        apibench = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/refs/tags/v1.2/data/apibench/torchhub_eval.json'
+        question_data = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/main/eval/eval-data/questions/torchhub/questions_torchhub_0_shot.jsonl'
+        api_dataset = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/main/data/api/torchhub_api.jsonl'
+        apibench = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/main/data/apibench/torchhub_eval.json'
         ast_eval = ast_eval_th
     elif hub == 'tf':
-        question_data = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/refs/tags/v1.2/eval/eval-data/questions/tensorflowhub/questions_tensorflowhub_0_shot.jsonl'
-        api_dataset = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/refs/tags/v1.2/data/api/tensorflowhub_api.jsonl'
-        apibench = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/refs/tags/v1.2/data/apibench/tensorflow_eval.json'
+        question_data = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/main/eval/eval-data/questions/tensorflowhub/questions_tensorflowhub_0_shot.jsonl'
+        api_dataset = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/main/data/api/tensorflowhub_api.jsonl'
+        apibench = 'https://raw.githubusercontent.com/ShishirPatil/gorilla/main/data/apibench/tensorflow_eval.json'
         ast_eval = ast_eval_tf
 
     question_data = fetch_data(question_data, 'question_data.jsonl')

evaluation/benchmarks/gpqa/run_infer.py

@@ -29,7 +29,6 @@ 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,
@@ -38,6 +37,7 @@ 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,
 )
@@ -61,14 +61,17 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='python:3.12-bookworm',
+            enable_auto_lint=True,
+            use_host_network=False,
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/gpqa/scripts/run_infer.sh

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

evaluation/benchmarks/humanevalfix/run_infer.py

@@ -22,7 +22,6 @@ 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,
@@ -31,6 +30,7 @@ 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,
 )
@@ -82,14 +82,17 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='python:3.12-bookworm',
+            enable_auto_lint=True,
+            use_host_network=False,
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/humanevalfix/scripts/run_infer.sh

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

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -9,7 +9,6 @@ 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,
@@ -18,6 +17,7 @@ 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,
 )
@@ -45,18 +45,18 @@ 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 = (
-        '$OH_INTERPRETER_PATH -m pip install scitools-pyke'
-    )
-
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='xingyaoww/od-eval-logic-reasoning:v1.0',
+            enable_auto_lint=True,
+            use_host_network=False,
+            runtime_extra_deps='$OH_INTERPRETER_PATH -m pip install scitools-pyke',
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/logic_reasoning/scripts/run_infer.sh

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

evaluation/benchmarks/miniwob/README.md

@@ -19,10 +19,9 @@ Access with browser the above MiniWoB URLs and see if they load correctly.
 ./evaluation/benchmarks/miniwob/scripts/run_infer.sh llm.claude-35-sonnet-eval
 ```
 
-### Run Inference on `RemoteRuntime`
-
-This is in beta. Fill out [this form](https://docs.google.com/forms/d/e/1FAIpQLSckVz_JFwg2_mOxNZjCtr7aoBFI2Mwdan3f75J_TrdMS1JV2g/viewform) to apply if you want to try this out!
+### Run Inference on `RemoteRuntime` (experimental)
 
+This is in limited beta. Contact Xingyao over slack if you want to try this out!
 
 ```bash
 ./evaluation/benchmarks/miniwob/scripts/run_infer.sh [model_config] [git-version] [agent] [note] [eval_limit] [num_workers]

evaluation/benchmarks/miniwob/run_infer.py

@@ -12,7 +12,6 @@ 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,
@@ -22,6 +21,7 @@ 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,
 )
@@ -55,14 +55,23 @@ 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=sandbox_config,
+        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,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/miniwob/scripts/run_infer.sh

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

evaluation/benchmarks/mint/run_infer.py

@@ -14,7 +14,6 @@ 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,
@@ -23,6 +22,7 @@ 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,
 )
@@ -103,18 +103,18 @@ 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'$OH_INTERPRETER_PATH -m pip install {" ".join(MINT_DEPENDENCIES)}'
-    )
-
     config = AppConfig(
         default_agent=metadata.agent_class,
         run_as_openhands=False,
         runtime='docker',
         max_iterations=metadata.max_iterations,
-        sandbox=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='xingyaoww/od-eval-mint:v1.0',
+            enable_auto_lint=True,
+            use_host_network=False,
+            runtime_extra_deps=f'$OH_INTERPRETER_PATH -m pip install {" ".join(MINT_DEPENDENCIES)}',
+            remote_runtime_enable_retries=True,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/mint/scripts/run_infer.sh

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

evaluation/benchmarks/ml_bench/run_infer.py

@@ -25,7 +25,6 @@ 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,
@@ -34,6 +33,7 @@ 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,
@@ -77,14 +77,16 @@ 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=sandbox_config,
+        sandbox=SandboxConfig(
+            base_container_image='public.ecr.aws/i5g0m1f6/ml-bench',
+            enable_auto_lint=True,
+            use_host_network=False,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,

evaluation/benchmarks/ml_bench/scripts/cleanup.sh

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

evaluation/benchmarks/ml_bench/scripts/run_analysis.sh

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

evaluation/benchmarks/ml_bench/scripts/run_infer.sh

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

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -11,7 +11,6 @@ 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,
@@ -21,6 +20,7 @@ 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,
 )
@@ -59,17 +59,22 @@ 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=sandbox_config,
+        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,
+        ),
         # do not mount workspace
         workspace_base=None,
         workspace_mount_path=None,