Merge branch 'All-Hands-AI:main' into main

ISSUE_TRIAGE.md

@@ -2,12 +2,13 @@
 These are the procedures and guidelines on how issues are triaged in this repo by the maintainers.
 
 ## General
-* Most issues must be tagged with **enhancement** or **bug**.
-* Issues may be tagged with what it relates to (**backend**, **frontend**, **agent quality**, etc.).
+* 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.).
 
 ## 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
@@ -18,8 +19,14 @@ 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.

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -288,7 +288,7 @@ def process_instance(
                                     'model_patch': model_patch,
                                     'instance_id': instance_id,
                                 },
-                                log_path=test_output_path,
+                                test_log_path=test_output_path,
                                 include_tests_status=True,
                             )
                             report = _report[instance_id]

openhands/runtime/builder/docker.py

@@ -19,19 +19,25 @@ def __init__(self, docker_client: docker.DockerClient):
 
         version_info = self.docker_client.version()
         server_version = version_info.get('Version', '').replace('-', '.')
-        if tuple(map(int, server_version.split('.')[:2])) < (18, 9):
+        self.is_podman = version_info.get('Components')[0].get('Name').startswith('Podman')
+        if tuple(map(int, server_version.split('.')[:2])) < (18, 9) and not self.is_podman:
             raise AgentRuntimeBuildError(
                 'Docker server version must be >= 18.09 to use BuildKit'
             )
 
+        if self.is_podman and tuple(map(int, server_version.split('.')[:2])) < (4, 9):
+            raise AgentRuntimeBuildError(
+                'Podman server version must be >= 4.9.0'
+            )
+
         self.rolling_logger = RollingLogger(max_lines=10)
 
     @staticmethod
-    def check_buildx():
+    def check_buildx(is_podman: bool = False):
         """Check if Docker Buildx is available"""
         try:
             result = subprocess.run(
-                ['docker', 'buildx', 'version'], capture_output=True, text=True
+                ['docker' if not is_podman else 'podman', 'buildx', 'version'], capture_output=True, text=True
             )
             return result.returncode == 0
         except FileNotFoundError:
@@ -68,12 +74,18 @@ def build(
         self.docker_client = docker.from_env()
         version_info = self.docker_client.version()
         server_version = version_info.get('Version', '').split('+')[0].replace('-', '.')
-        if tuple(map(int, server_version.split('.'))) < (18, 9):
+        self.is_podman = version_info.get('Components')[0].get('Name').startswith('Podman')
+        if tuple(map(int, server_version.split('.'))) < (18, 9) and not self.is_podman:
             raise AgentRuntimeBuildError(
                 'Docker server version must be >= 18.09 to use BuildKit'
             )
 
-        if not DockerRuntimeBuilder.check_buildx():
+        if self.is_podman and tuple(map(int, server_version.split('.'))) < (4, 9):
+            raise AgentRuntimeBuildError(
+                'Podman server version must be >= 4.9.0'
+            )
+
+        if not DockerRuntimeBuilder.check_buildx(self.is_podman):
             # when running openhands in a container, there might not be a "docker"
             # binary available, in which case we need to download docker binary.
             # since the official openhands app image is built from debian, we use
@@ -110,7 +122,7 @@ def build(
         target_image_tag = tags[1].split(':')[1] if len(tags) > 1 else None
 
         buildx_cmd = [
-            'docker',
+            'docker' if not self.is_podman else 'podman',
             'buildx',
             'build',
             '--progress=plain',
@@ -139,7 +151,7 @@ def build(
         buildx_cmd.append(path)  # must be last!
 
         self.rolling_logger.start(
-            '================ DOCKER BUILD STARTED ================'
+            f'================ {buildx_cmd[0].upper()} BUILD STARTED ================'
         )
 
         try:

openhands/runtime/impl/daytona/README.md

@@ -2,22 +2,54 @@
 
 [Daytona](https://www.daytona.io/) is a platform that provides a secure and elastic infrastructure for running AI-generated code. It provides all the necessary features for an AI Agent to interact with a codebase. It provides a Daytona SDK with official Python and TypeScript interfaces for interacting with Daytona, enabling you to programmatically manage development environments and execute code.
 
+## Quick start
+
+Get your Daytona API key from https://app.daytona.io/dashboard/keys and export it:
+
+```bash
+export DAYTONA_API_KEY="<your-api-key>"
+```
+
+Use the following command to run the latest OpenHands release locally using Docker:
+
+```bash
+bash -i <(curl -sL https://get.daytona.io/openhands)
+```
+
+
 ## Getting started
 
 1. Sign in at https://app.daytona.io/
 
 1. Generate and copy your API key
 
-1. Set the following environment variables before running the OpenHands app on your local machine or via a `docker run` command:
+1. Set the `OPENHANDS_VERSION` environment variable to the latest release's version seen in the main README.md file; as well as the `DAYTONA_API_KEY`
 
 ```bash
-    RUNTIME="daytona"
-    DAYTONA_API_KEY="<your-api-key>"
+export OPENHANDS_VERSION=<OPENHANDS_RELEASE>  # e.g. 0.27
+export DAYTONA_API_KEY=<your_api_key>
 ```
-Optionally, if you don't want your sandboxes to default to the US region, set:
+
+1. Run the following `docker` command:
+
+```bash
+docker run -it --rm --pull=always \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:${OPENHANDS_VERSION}-nikolaik \
+    -e LOG_ALL_EVENTS=true \
+    -e RUNTIME=daytona \
+    -e DAYTONA_API_KEY=${DAYTONA_API_KEY} \
+    -v ~/.openhands-state:/.openhands-state \
+    -p 3000:3000 \
+    --name openhands-app \
+    docker.all-hands.dev/all-hands-ai/openhands:${OPENHANDS_VERSION}
+```
+> **Tip:** If you don't want your sandboxes to default to the US region, you can set the `DAYTONA_TARGET` environment variable to `eu`
+
+Alternatively, if you want to run the OpenHands app on your local machine using `make run` without Docker, set the following environment variables first:
 
 ```bash
-    DAYTONA_TARGET="eu"
+export RUNTIME="daytona"
+export DAYTONA_API_KEY="<your-api-key>"
 ```
 
 ## Documentation

tests/unit/test_docker_runtime.py

@@ -21,7 +21,10 @@ def mock_docker_client():
         mock_client.return_value.containers.get.return_value = container_mock
         mock_client.return_value.containers.run.return_value = container_mock
         # Mock version info for BuildKit check
-        mock_client.return_value.version.return_value = {'Version': '20.10.0'}
+        mock_client.return_value.version.return_value = {
+            'Version': '20.10.0',
+            'Components': [{'Name': 'Engine', 'Version': '20.10.0'}],
+        }  # Ensure version is >= 18.09
         yield mock_client.return_value
 
 

tests/unit/test_runtime_build.py

@@ -40,7 +40,8 @@ def temp_dir(tmp_path_factory: TempPathFactory) -> str:
 def mock_docker_client():
     mock_client = MagicMock(spec=docker.DockerClient)
     mock_client.version.return_value = {
-        'Version': '19.03'
+        'Version': '20.10.0',
+        'Components': [{'Name': 'Engine', 'Version': '20.10.0'}],
     }  # Ensure version is >= 18.09
     return mock_client
 
@@ -612,15 +613,21 @@ def test_build_image_from_repo(docker_runtime_builder, tmp_path):
 
 def test_image_exists_local(docker_runtime_builder):
     mock_client = MagicMock()
-    mock_client.version().get.return_value = '18.9'
+    mock_client.version.return_value = {
+        'Version': '20.10.0',
+        'Components': [{'Name': 'Engine', 'Version': '20.10.0'}],
+    }  # Ensure version is >= 18.09
     builder = DockerRuntimeBuilder(mock_client)
     image_name = 'existing-local:image'  # The mock pretends this exists by default
     assert builder.image_exists(image_name)
 
 
 def test_image_exists_not_found():
     mock_client = MagicMock()
-    mock_client.version().get.return_value = '18.9'
+    mock_client.version.return_value = {
+        'Version': '20.10.0',
+        'Components': [{'Name': 'Engine', 'Version': '20.10.0'}],
+    }  # Ensure version is >= 18.09
     mock_client.images.get.side_effect = docker.errors.ImageNotFound(
         "He doesn't like you!"
     )