Merge branch 'main' into kevin

SmartManoj · Feb 14, 2025 · b69139f · b69139f
2 parents b5cf7fb + f5fccab
commit b69139f
Show file tree

Hide file tree

Showing 60 changed files with 6,994 additions and 1,469 deletions.
diff --git a/.github/workflows/openhands-resolver.yml b/.github/workflows/openhands-resolver.yml
@@ -231,7 +231,7 @@ jobs:
       - 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 +267,7 @@ jobs:
         if: always() # Create PR or branch even if the previous steps fail
         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 }}

diff --git a/Development.md b/Development.md
@@ -100,7 +100,7 @@ poetry run pytest ./tests/unit/test_*.py
 To reduce build time (e.g., if no changes were made to the client-runtime component), you can use an existing Docker container image by
 setting the SANDBOX_RUNTIME_CONTAINER_IMAGE environment variable to the desired Docker image.
 
-Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.23-nikolaik`
+Example: `export SANDBOX_RUNTIME_CONTAINER_IMAGE=ghcr.io/all-hands-ai/runtime:0.24-nikolaik`
 
 ## Develop inside Docker container
 

diff --git a/README.md b/README.md
@@ -144,17 +144,17 @@ See the [Running OpenHands](https://docs.all-hands.dev/modules/usage/installatio
 system requirements and more information.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.23-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.23
+    docker.all-hands.dev/all-hands-ai/openhands:0.24
 ```
 
 You'll find OpenHands running at [http://localhost:3000](http://localhost:3000)!

diff --git a/containers/dev/compose.yml b/containers/dev/compose.yml
@@ -11,7 +11,7 @@ services:
       - BACKEND_HOST=${BACKEND_HOST:-"0.0.0.0"}
       - SANDBOX_API_HOSTNAME=host.docker.internal
       #
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-ghcr.io/all-hands-ai/runtime:0.23-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:

diff --git a/docker-compose.yml b/docker-compose.yml
@@ -7,7 +7,7 @@ services:
     image: openhands:latest
     container_name: openhands-app-${DATE:-}
     environment:
-      - SANDBOX_RUNTIME_CONTAINER_IMAGE=${SANDBOX_RUNTIME_CONTAINER_IMAGE:-docker.all-hands.dev/all-hands-ai/runtime:0.23-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:

diff --git a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md b/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md
@@ -52,7 +52,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-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:0.23 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     python -m openhands.core.cli
 ```
 

diff --git a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md b/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md
@@ -46,7 +46,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-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:0.23 \
+    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
 ```
diff --git a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/installation.mdx b/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/installation.mdx
@@ -13,16 +13,16 @@
 La façon la plus simple d'exécuter OpenHands est avec Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.23-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:0.23-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:0.23
+    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).

diff --git a/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/runtimes.md b/docs/i18n/fr/docusaurus-plugin-content-docs/current/usage/runtimes.md
@@ -13,7 +13,7 @@ C'est le Runtime par défaut qui est utilisé lorsque vous démarrez OpenHands.
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-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 \
     # ...
 ```

diff --git a/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md b/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/cli-mode.md
@@ -50,7 +50,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-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:0.23 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     python -m openhands.core.cli
 ```
 

diff --git a/...8n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md b/...8n/zh-Hans/docusaurus-plugin-content-docs/current/usage/how-to/headless-mode.md
@@ -47,7 +47,7 @@ LLM_API_KEY="sk_test_12345"
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.23 \
+    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
 ```
diff --git a/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/installation.mdx b/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/installation.mdx
@@ -11,16 +11,16 @@
 在 Docker 中运行 OpenHands 是最简单的方式。
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.23-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:0.23-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:0.23
+    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)。

diff --git a/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/runtimes.md b/docs/i18n/zh-Hans/docusaurus-plugin-content-docs/current/usage/runtimes.md
@@ -11,7 +11,7 @@
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-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 \
     # ...
 ```

diff --git a/docs/modules/usage/how-to/cli-mode.md b/docs/modules/usage/how-to/cli-mode.md
@@ -35,7 +35,7 @@ To run OpenHands in CLI mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-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:0.23 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     python -m openhands.core.cli
 ```
 

diff --git a/docs/modules/usage/how-to/headless-mode.md b/docs/modules/usage/how-to/headless-mode.md
@@ -32,7 +32,7 @@ To run OpenHands in Headless mode with Docker:
 ```bash
 docker run -it \
     --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-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:0.23 \
+    docker.all-hands.dev/all-hands-ai/openhands:0.24 \
     python -m openhands.core.main -t "write a bash script that prints hi"
 ```
 

diff --git a/docs/modules/usage/installation.mdx b/docs/modules/usage/installation.mdx
@@ -54,17 +54,17 @@
 The easiest way to run OpenHands is in Docker.
 
 ```bash
-docker pull docker.all-hands.dev/all-hands-ai/runtime:0.23-nikolaik
+docker pull docker.all-hands.dev/all-hands-ai/runtime:0.24-nikolaik
 
 docker run -it --rm --pull=always \
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-nikolaik \
+    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.24-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:0.23
+    docker.all-hands.dev/all-hands-ai/openhands:0.24
 ```
 
 You'll find OpenHands running at http://localhost:3000!

diff --git a/docs/modules/usage/runtimes.md b/docs/modules/usage/runtimes.md
@@ -16,7 +16,7 @@ some flags being passed to `docker run` that make this possible:
 
 ```
 docker run # ...
-    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.23-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 \
     # ...
 ```

diff --git a/evaluation/benchmarks/gaia/run_infer.py b/evaluation/benchmarks/gaia/run_infer.py
@@ -25,6 +25,7 @@
     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
@@ -63,8 +64,12 @@ def get_config(
         workspace_mount_path=None,
     )
     config.set_llm_config(metadata.llm_config)
-    agent_config = config.get_agent_config(metadata.agent_class)
-    agent_config.enable_prompt_extensions = False
+    if metadata.agent_config:
+        config.set_agent_config(metadata.agent_config, metadata.agent_class)
+    else:
+        logger.info('Agent config not provided, using default settings')
+        agent_config = config.get_agent_config(metadata.agent_class)
+        agent_config.enable_prompt_extensions = False
     return config
 
 
@@ -238,6 +243,10 @@ def process_instance(
     )
     args, _ = parser.parse_known_args()
 
+    agent_config = None
+    if args.agent_config:
+        agent_config = get_agent_config_arg(args.agent_config)
+
     llm_config = None
     if args.llm_config:
         llm_config = get_llm_config_arg(args.llm_config)
@@ -256,6 +265,7 @@ def process_instance(
         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)

diff --git a/evaluation/benchmarks/gaia/scripts/run_infer.sh b/evaluation/benchmarks/gaia/scripts/run_infer.sh
@@ -9,6 +9,7 @@ AGENT=$3
 EVAL_LIMIT=$4
 LEVELS=$5
 NUM_WORKERS=$6
+AGENT_CONFIG=$7
 
 if [ -z "$NUM_WORKERS" ]; then
   NUM_WORKERS=1
@@ -49,5 +50,9 @@ if [ -n "$EVAL_LIMIT" ]; then
   COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
 fi
 
+if [ -n "$AGENT_CONFIG" ]; then
+  echo "AGENT_CONFIG: $AGENT_CONFIG"
+  COMMAND="$COMMAND --agent-config $AGENT_CONFIG"
+
 # Run the command
 eval $COMMAND
diff --git a/evaluation/benchmarks/the_agent_company/run_infer.py b/evaluation/benchmarks/the_agent_company/run_infer.py
@@ -18,9 +18,11 @@
     AppConfig,
     LLMConfig,
     SandboxConfig,
+    get_agent_config_arg,
     get_llm_config_arg,
     get_parser,
 )
+from openhands.core.config.agent_config import AgentConfig
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
 from openhands.events.action import CmdRunAction, MessageAction
@@ -34,6 +36,7 @@ def get_config(
     task_short_name: str,
     mount_path_on_host: str,
     llm_config: LLMConfig,
+    agent_config: AgentConfig,
 ) -> AppConfig:
     config = AppConfig(
         run_as_openhands=False,
@@ -58,6 +61,14 @@ def get_config(
         workspace_mount_path_in_sandbox='/outputs',
     )
     config.set_llm_config(llm_config)
+    if agent_config:
+        config.set_agent_config(agent_config)
+    else:
+        logger.info('Agent config not provided, using default settings')
+        agent_config = AgentConfig(
+            enable_prompt_extensions=False,
+        )
+        config.set_agent_config(agent_config)
     return config
 
 
@@ -215,6 +226,10 @@ def run_evaluator(
     )
     args, _ = parser.parse_known_args()
 
+    agent_config: AgentConfig | None = None
+    if args.agent_config:
+        agent_config = get_agent_config_arg(args.agent_config)
+
     agent_llm_config: LLMConfig | None = None
     if args.agent_llm_config:
         agent_llm_config = get_llm_config_arg(args.agent_llm_config)
@@ -255,7 +270,7 @@ def run_evaluator(
     else:
         temp_dir = tempfile.mkdtemp()
     config: AppConfig = get_config(
-        args.task_image_name, task_short_name, temp_dir, agent_llm_config
+        args.task_image_name, task_short_name, temp_dir, agent_llm_config, agent_config
     )
     runtime: Runtime = create_runtime(config)
     call_async_from_sync(runtime.connect)