feat(cli): Use CLI to launch OpenHands UI server via Docker (#9783)

Co-authored-by: openhands <openhands@all-hands.dev>

evaluation/benchmarks/EDA/run_infer.py

@@ -18,8 +18,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -172,7 +172,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--answerer_model', '-a', default='gpt-3.5-turbo', help='answerer model'
     )

evaluation/benchmarks/commit0/run_infer.py

@@ -26,8 +26,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -525,7 +525,7 @@ def commit0_setup(dataset: pd.DataFrame, repo_split: str) -> pd.DataFrame:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/gaia/run_infer.py

@@ -31,8 +31,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
     load_from_toml,
 )
 from openhands.core.config.utils import get_agent_config_arg
@@ -294,7 +294,7 @@ Here is the task:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--level',
         type=str,

evaluation/benchmarks/gorilla/run_infer.py

@@ -20,8 +20,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -134,7 +134,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--hubs',
         type=str,

evaluation/benchmarks/gpqa/run_infer.py

@@ -38,8 +38,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -312,7 +312,7 @@ Ok now its time to start solving the question. Good luck!
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     # data split must be one of 'gpqa_main', 'gqpa_diamond', 'gpqa_experts', 'gpqa_extended'
     parser.add_argument(
         '--data-split',

evaluation/benchmarks/lca_ci_build_repair/eval_infer.py

@@ -21,7 +21,7 @@ from evaluation.utils.shared import (
 from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
-    get_parser,
+    get_evaluation_parser,
     load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -167,7 +167,7 @@ def process_predictions(predictions_path: str):
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '-s',
         '--eval-split',

evaluation/benchmarks/lca_ci_build_repair/run_infer.py

@@ -30,8 +30,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
     load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -358,7 +358,7 @@ Be thorough in your exploration, testing, and reasoning. It's fine if your think
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '-s',
         '--eval-split',

evaluation/benchmarks/logic_reasoning/run_infer.py

@@ -18,8 +18,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -267,7 +267,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/mint/run_infer.py

@@ -23,8 +23,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -229,7 +229,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
 
     SUBSETS = [
         # Eurus subset: https://arxiv.org/abs/2404.02078

evaluation/benchmarks/ml_bench/run_analysis.py

@@ -4,7 +4,11 @@ import pprint
 
 import tqdm
 
-from openhands.core.config import get_llm_config_arg, get_parser, load_openhands_config
+from openhands.core.config import (
+    get_evaluation_parser,
+    get_llm_config_arg,
+    load_openhands_config,
+)
 from openhands.core.logger import openhands_logger as logger
 from openhands.llm.llm import LLM
 
@@ -111,7 +115,7 @@ def classify_error(llm: LLM, failed_case: dict) -> str:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--json_file_path',
         type=str,

evaluation/benchmarks/ml_bench/run_infer.py

@@ -34,8 +34,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
     load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -273,7 +273,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '-s',
         '--eval-split',

evaluation/benchmarks/multi_swe_bench/eval_infer.py

@@ -30,7 +30,7 @@ from evaluation.utils.shared import (
 from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
-    get_parser,
+    get_evaluation_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
@@ -323,7 +323,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--input-file',
         type=str,

evaluation/benchmarks/multi_swe_bench/run_infer.py

@@ -32,8 +32,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -772,7 +772,7 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
 
 if __name__ == '__main__':
     # pdb.set_trace()
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/scienceagentbench/run_infer.py

@@ -21,8 +21,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -239,7 +239,7 @@ If the program uses some packages that are incompatible, please figure out alter
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--use-knowledge',
         type=str,

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -26,7 +26,7 @@ from evaluation.utils.shared import (
 from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
-    get_parser,
+    get_evaluation_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
@@ -353,7 +353,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--input-file',
         type=str,

evaluation/benchmarks/swe_bench/run_infer.py

@@ -43,8 +43,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.config.condenser_config import NoOpCondenserConfig
 from openhands.core.config.utils import get_condenser_config_arg
@@ -732,7 +732,7 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/swe_bench/run_infer_interact.py

@@ -28,8 +28,8 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.config.condenser_config import NoOpCondenserConfig
 from openhands.core.config.utils import get_condenser_config_arg
@@ -201,7 +201,7 @@ def process_instance(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/swe_bench/run_localize.py

@@ -31,8 +31,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -644,7 +644,7 @@ SWEGYM_EXCLUDE_IDS = [
 ]
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/testgeneval/eval_infer.py

@@ -41,7 +41,7 @@ from evaluation.utils.shared import (
     reset_logger_for_multiprocessing,
     run_evaluation,
 )
-from openhands.core.config import OpenHandsConfig, SandboxConfig, get_parser
+from openhands.core.config import OpenHandsConfig, SandboxConfig, get_evaluation_parser
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
 from openhands.events.action import CmdRunAction
@@ -484,7 +484,7 @@ def count_and_log_fields(evaluated_predictions, fields, key):
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--input-file', type=str, required=True, help='Path to input predictions file'
     )

evaluation/benchmarks/testgeneval/run_infer.py

@@ -37,8 +37,8 @@ from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
     SandboxConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -491,7 +491,7 @@ def prepare_dataset_pre(dataset: pd.DataFrame, filter_column: str) -> pd.DataFra
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/the_agent_company/run_infer.py

@@ -18,8 +18,8 @@ from openhands.core.config import (
     LLMConfig,
     OpenHandsConfig,
     get_agent_config_arg,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.config.agent_config import AgentConfig
 from openhands.core.logger import openhands_logger as logger
@@ -197,7 +197,7 @@ def run_evaluator(
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--task-image-name',
         type=str,

evaluation/benchmarks/toolqa/run_infer.py

@@ -19,8 +19,8 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -157,7 +157,7 @@ def process_instance(instance: Any, metadata: EvalMetadata, reset_logger: bool =
 
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,

evaluation/benchmarks/visual_swe_bench/run_infer.py

@@ -31,8 +31,8 @@ from openhands.controller.state.state import State
 from openhands.core.config import (
     AgentConfig,
     OpenHandsConfig,
+    get_evaluation_parser,
     get_llm_config_arg,
-    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -565,7 +565,7 @@ SWEGYM_EXCLUDE_IDS = [
 ]
 
 if __name__ == '__main__':
-    parser = get_parser()
+    parser = get_evaluation_parser()
     parser.add_argument(
         '--dataset',
         type=str,