Rename Conversation to ServerConversation and AppConfig to OpenHandsConfig (#8754)

Co-authored-by: openhands <openhands@all-hands.dev>
2026-01-09 14:57:59 -05:00 · 2025-05-28 15:48:34 -04:00
parent c76809a766
commit 205f0234e8
111 changed files with 627 additions and 537 deletions
--- a/evaluation/benchmarks/EDA/run_infer.py
+++ b/evaluation/benchmarks/EDA/run_infer.py
@@ -17,7 +17,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -59,10 +59,10 @@ AGENT_CLS_TO_INST_SUFFIX = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/agent_bench/run_infer.py
+++ b/evaluation/benchmarks/agent_bench/run_infer.py
@@ -25,7 +25,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -39,11 +39,11 @@ from openhands.utils.async_utils import call_async_from_sync

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-slim'

-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime=os.environ.get('RUNTIME', 'docker'),
--- a/evaluation/benchmarks/aider_bench/run_infer.py
+++ b/evaluation/benchmarks/aider_bench/run_infer.py
@@ -24,7 +24,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    load_from_toml,
    parse_arguments,
@@ -46,10 +46,10 @@ SKIP_NUM = (

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.11-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime=os.environ.get('RUNTIME', 'docker'),
--- a/evaluation/benchmarks/biocoder/run_infer.py
+++ b/evaluation/benchmarks/biocoder/run_infer.py
@@ -22,7 +22,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -55,12 +55,12 @@ FILE_EXT_MAP = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    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(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/bird/run_infer.py
+++ b/evaluation/benchmarks/bird/run_infer.py
@@ -25,7 +25,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -70,11 +70,11 @@ AGENT_CLS_TO_INST_SUFFIX = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'

-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/browsing_delegation/run_infer.py
+++ b/evaluation/benchmarks/browsing_delegation/run_infer.py
@@ -18,7 +18,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -33,13 +33,13 @@ SUPPORTED_AGENT_CLS = {'CodeActAgent'}

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    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(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/commit0/run_infer.py
+++ b/evaluation/benchmarks/commit0/run_infer.py
@@ -25,7 +25,7 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
    AgentConfig,
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -101,7 +101,7 @@ def get_instance_docker_image(repo_name: str) -> str:
 def get_config(
    instance: pd.Series,
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    repo_name = instance['repo'].split('/')[1]
    base_container_image = get_instance_docker_image(repo_name)
    logger.info(
@@ -113,7 +113,7 @@ def get_config(
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = base_container_image

-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
--- a/evaluation/benchmarks/discoverybench/run_infer.py
+++ b/evaluation/benchmarks/discoverybench/run_infer.py
@@ -25,7 +25,7 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
    AgentConfig,
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -61,10 +61,10 @@ AGENT_CLS_TO_INST_SUFFIX = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/gaia/run_infer.py
+++ b/evaluation/benchmarks/gaia/run_infer.py
@@ -21,7 +21,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -47,10 +47,10 @@ AGENT_CLS_TO_INST_SUFFIX = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/gorilla/run_infer.py
+++ b/evaluation/benchmarks/gorilla/run_infer.py
@@ -19,7 +19,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -39,10 +39,10 @@ AGENT_CLS_TO_INST_SUFFIX = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/gpqa/run_infer.py
+++ b/evaluation/benchmarks/gpqa/run_infer.py
@@ -37,7 +37,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -60,10 +60,10 @@ ACTION_FORMAT = """

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/humanevalfix/run_infer.py
+++ b/evaluation/benchmarks/humanevalfix/run_infer.py
@@ -30,7 +30,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -81,10 +81,10 @@ AGENT_CLS_TO_INST_SUFFIX = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/lca_ci_build_repair/eval_infer.py
+++ b/evaluation/benchmarks/lca_ci_build_repair/eval_infer.py
@@ -19,10 +19,10 @@ from evaluation.utils.shared import (
    make_metadata,
 )
 from openhands.core.config import (
-    AppConfig,
    LLMConfig,
+    OpenHandsConfig,
    get_parser,
-    load_app_config,
+    load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
@@ -34,10 +34,10 @@ from openhands.utils.async_utils import call_async_from_sync

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
@@ -53,7 +53,7 @@ def get_config(
    return config


-config = load_app_config()
+config = load_openhands_config()


 def load_bench_config():
--- a/evaluation/benchmarks/lca_ci_build_repair/run_infer.py
+++ b/evaluation/benchmarks/lca_ci_build_repair/run_infer.py
@@ -29,10 +29,10 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
-    load_app_config,
+    load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -44,10 +44,10 @@ from openhands.utils.async_utils import call_async_from_sync

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
@@ -63,7 +63,7 @@ def get_config(
    return config


-config = load_app_config()
+config = load_openhands_config()


 def load_bench_config():
--- a/evaluation/benchmarks/logic_reasoning/run_infer.py
+++ b/evaluation/benchmarks/logic_reasoning/run_infer.py
@@ -17,7 +17,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -44,14 +44,14 @@ AGENT_CLS_TO_INST_SUFFIX = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    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(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/miniwob/run_infer.py
+++ b/evaluation/benchmarks/miniwob/run_infer.py
@@ -21,7 +21,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -54,10 +54,10 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 def get_config(
    metadata: EvalMetadata,
    env_id: str,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'xingyaoww/od-eval-miniwob:v1.0'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime=os.environ.get('RUNTIME', 'docker'),
--- a/evaluation/benchmarks/mint/run_infer.py
+++ b/evaluation/benchmarks/mint/run_infer.py
@@ -22,7 +22,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -102,14 +102,14 @@ def load_incontext_example(task_name: str, with_tool: bool = True):

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    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(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/ml_bench/run_analysis.py
+++ b/evaluation/benchmarks/ml_bench/run_analysis.py
@@ -4,11 +4,11 @@ import pprint

 import tqdm

-from openhands.core.config import get_llm_config_arg, get_parser, load_app_config
+from openhands.core.config import get_llm_config_arg, get_parser, load_openhands_config
 from openhands.core.logger import openhands_logger as logger
 from openhands.llm.llm import LLM

-config = load_app_config()
+config = load_openhands_config()


 def extract_test_results(res_file_path: str) -> tuple[list[str], list[str]]:
--- a/evaluation/benchmarks/ml_bench/run_infer.py
+++ b/evaluation/benchmarks/ml_bench/run_infer.py
@@ -33,10 +33,10 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
-    load_app_config,
+    load_openhands_config,
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
@@ -45,7 +45,7 @@ from openhands.events.observation import CmdOutputObservation
 from openhands.runtime.base import Runtime
 from openhands.utils.async_utils import call_async_from_sync

-config = load_app_config()
+config = load_openhands_config()

 AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
    'CodeActAgent': codeact_user_response,
@@ -76,10 +76,10 @@ ID2CONDA = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'public.ecr.aws/i5g0m1f6/ml-bench'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/multi_swe_bench/eval_infer.py
+++ b/evaluation/benchmarks/multi_swe_bench/eval_infer.py
@@ -28,8 +28,8 @@ from evaluation.utils.shared import (
    run_evaluation,
 )
 from openhands.core.config import (
-    AppConfig,
    LLMConfig,
+    OpenHandsConfig,
    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -73,7 +73,7 @@ def process_git_patch(patch):
    return patch


-def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
+def get_config(metadata: EvalMetadata, instance: pd.Series) -> OpenHandsConfig:
    # We use a different instance image for the each instance of swe-bench eval
    base_container_image = get_instance_docker_image(instance['instance_id'])
    logger.info(
@@ -87,7 +87,7 @@ def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
        dataset_name=metadata.dataset,
        instance_id=instance['instance_id'],
    )
-    config = AppConfig(
+    config = OpenHandsConfig(
        run_as_openhands=False,
        runtime=os.environ.get('RUNTIME', 'docker'),
        sandbox=sandbox_config,
--- a/evaluation/benchmarks/multi_swe_bench/run_infer.py
+++ b/evaluation/benchmarks/multi_swe_bench/run_infer.py
@@ -30,7 +30,7 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
    AgentConfig,
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -314,7 +314,7 @@ def get_instance_docker_image(instance: pd.Series):
 def get_config(
    instance: pd.Series,
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    SWE_BENCH_CONTAINER_IMAGE = 'ghcr.io/opendevin/eval-swe-bench:full-v1.2.1'
    if USE_INSTANCE_IMAGE:
        # We use a different instance image for the each instance of swe-bench eval
@@ -340,7 +340,7 @@ def get_config(
        instance_id=instance['instance_id'],
    )

-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
--- a/evaluation/benchmarks/scienceagentbench/run_infer.py
+++ b/evaluation/benchmarks/scienceagentbench/run_infer.py
@@ -20,7 +20,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -58,12 +58,12 @@ def format_task_dict(example, use_knowledge):
 def get_config(
    metadata: EvalMetadata,
    instance_id: str,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = (
        'docker.io/xingyaoww/openhands-eval-scienceagentbench'
    )
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime=os.environ.get('RUNTIME', 'docker'),
--- a/evaluation/benchmarks/swe_bench/eval_infer.py
+++ b/evaluation/benchmarks/swe_bench/eval_infer.py
@@ -24,8 +24,8 @@ from evaluation.utils.shared import (
    run_evaluation,
 )
 from openhands.core.config import (
-    AppConfig,
    LLMConfig,
+    OpenHandsConfig,
    get_parser,
 )
 from openhands.core.logger import openhands_logger as logger
@@ -69,7 +69,7 @@ def process_git_patch(patch):
    return patch


-def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
+def get_config(metadata: EvalMetadata, instance: pd.Series) -> OpenHandsConfig:
    # We use a different instance image for the each instance of swe-bench eval
    base_container_image = get_instance_docker_image(instance['instance_id'])
    logger.info(
@@ -83,7 +83,7 @@ def get_config(metadata: EvalMetadata, instance: pd.Series) -> AppConfig:
        dataset_name=metadata.dataset,
        instance_id=instance['instance_id'],
    )
-    config = AppConfig(
+    config = OpenHandsConfig(
        run_as_openhands=False,
        runtime=os.environ.get('RUNTIME', 'docker'),
        sandbox=sandbox_config,
--- a/evaluation/benchmarks/swe_bench/run_infer.py
+++ b/evaluation/benchmarks/swe_bench/run_infer.py
@@ -40,12 +40,12 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
    AgentConfig,
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
-from openhands.core.config.utils import get_condenser_config_arg
 from openhands.core.config.condenser_config import NoOpCondenserConfig
+from openhands.core.config.utils import get_condenser_config_arg
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
 from openhands.critic import AgentFinishedCritic
@@ -220,7 +220,7 @@ def get_instance_docker_image(
 def get_config(
    instance: pd.Series,
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    # We use a different instance image for the each instance of swe-bench eval
    use_swebench_official_image = 'swe-gym' not in metadata.dataset.lower()
    base_container_image = get_instance_docker_image(
@@ -244,7 +244,7 @@ def get_config(
        instance_id=instance['instance_id'],
    )

-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
@@ -721,15 +721,16 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
                # repos for the swe-bench instances:
                # ['astropy/astropy', 'django/django', 'matplotlib/matplotlib', 'mwaskom/seaborn', 'pallets/flask', 'psf/requests', 'pydata/xarray', 'pylint-dev/pylint', 'pytest-dev/pytest', 'scikit-learn/scikit-learn', 'sphinx-doc/sphinx', 'sympy/sympy']
                selected_repos = data['selected_repos']
-                if isinstance(selected_repos, str): selected_repos = [selected_repos]
+                if isinstance(selected_repos, str):
+                    selected_repos = [selected_repos]
                assert isinstance(selected_repos, list)
                logger.info(
                    f'Filtering {selected_repos} tasks from "selected_repos"...'
                )
-                subset = dataset[dataset["repo"].isin(selected_repos)]
+                subset = dataset[dataset['repo'].isin(selected_repos)]
                logger.info(f'Retained {subset.shape[0]} tasks after filtering')
                return subset
-                
+
    skip_ids = os.environ.get('SKIP_IDS', '').split(',')
    if len(skip_ids) > 0:
        logger.info(f'Filtering {len(skip_ids)} tasks from "SKIP_IDS"...')
@@ -806,7 +807,9 @@ if __name__ == '__main__':
    else:
        # If no specific condenser config is provided via env var, default to NoOpCondenser
        condenser_config = NoOpCondenserConfig()
-        logger.debug('No Condenser config provided via EVAL_CONDENSER, using NoOpCondenser.')
+        logger.debug(
+            'No Condenser config provided via EVAL_CONDENSER, using NoOpCondenser.'
+        )

    details = {'mode': args.mode}
    _agent_cls = openhands.agenthub.Agent.get_cls(args.agent_cls)
--- a/evaluation/benchmarks/swe_bench/run_localize.py
+++ b/evaluation/benchmarks/swe_bench/run_localize.py
@@ -30,7 +30,7 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
    AgentConfig,
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -58,7 +58,7 @@ def _get_swebench_workspace_dir_name(instance: pd.Series) -> str:


 def get_instruction(instance: pd.Series, metadata: EvalMetadata):
-    workspace_dir_name = _get_swebench_workspace_dir_name(instance)
+    _get_swebench_workspace_dir_name(instance)
    instruction = f"""
 Consider the following issue description:

@@ -168,7 +168,7 @@ def get_instance_docker_image(instance_id: str, official_image: bool = False) ->
 def get_config(
    instance: pd.Series,
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    # We use a different instance image for the each instance of swe-bench eval
    use_official_image = bool(
        'verified' in metadata.dataset.lower() or 'lite' in metadata.dataset.lower()
@@ -197,7 +197,7 @@ def get_config(
        'REPO_PATH': f'/workspace/{workspace_dir_name}/',
    }

-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
@@ -348,13 +348,13 @@ def initialize_runtime(

    # Check if an existing graph index file is available
    graph_index_file_path = os.path.join(
-        INDEX_BASE_DIR, 'graph_index_v2.3', f"{instance['instance_id']}.pkl"
+        INDEX_BASE_DIR, 'graph_index_v2.3', f'{instance["instance_id"]}.pkl'
    )
    if INDEX_BASE_DIR and os.path.exists(graph_index_file_path):
        logger.info(
-            f"Copying graph index from {graph_index_file_path} to /workspace/{workspace_dir_name}/_index_data/graph_index_v2.3"
+            f'Copying graph index from {graph_index_file_path} to /workspace/{workspace_dir_name}/_index_data/graph_index_v2.3'
        )
-    
+
        runtime.copy_to(
            graph_index_file_path,
            f'/workspace/{workspace_dir_name}/_index_data/graph_index_v2.3',
@@ -364,9 +364,13 @@ def initialize_runtime(
        )
        obs = runtime.run_action(action)

-        bm25_index_dir = os.path.join(INDEX_BASE_DIR, 'BM25_index', instance['instance_id'])
+        bm25_index_dir = os.path.join(
+            INDEX_BASE_DIR, 'BM25_index', instance['instance_id']
+        )
        runtime.copy_to(
-            bm25_index_dir, f'/workspace/{workspace_dir_name}/_index_data', recursive=True
+            bm25_index_dir,
+            f'/workspace/{workspace_dir_name}/_index_data',
+            recursive=True,
        )
        action = CmdRunAction(
            command=f'mv _index_data/{instance["instance_id"]} _index_data/bm25_index'
--- a/evaluation/benchmarks/testgeneval/eval_infer.py
+++ b/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 AppConfig, SandboxConfig, get_parser
+from openhands.core.config import OpenHandsConfig, SandboxConfig, get_parser
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime
 from openhands.events.action import CmdRunAction
@@ -52,13 +52,13 @@ DOCKER_IMAGE_PREFIX = os.environ.get('EVAL_DOCKER_IMAGE_PREFIX', 'docker.io/kdja
 logger.info(f'Using docker image prefix: {DOCKER_IMAGE_PREFIX}')


-def get_config(instance: pd.Series) -> AppConfig:
+def get_config(instance: pd.Series) -> OpenHandsConfig:
    base_container_image = get_instance_docker_image(instance['instance_id_swebench'])
    assert base_container_image, (
        f'Invalid container image for instance {instance["instance_id_swebench"]}.'
    )
    logger.info(f'Using instance container image: {base_container_image}.')
-    return AppConfig(
+    return OpenHandsConfig(
        run_as_openhands=False,
        runtime=os.environ.get('RUNTIME', 'eventstream'),
        sandbox=SandboxConfig(
--- a/evaluation/benchmarks/testgeneval/run_infer.py
+++ b/evaluation/benchmarks/testgeneval/run_infer.py
@@ -35,7 +35,7 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
    AgentConfig,
-    AppConfig,
+    OpenHandsConfig,
    SandboxConfig,
    get_llm_config_arg,
    get_parser,
@@ -117,7 +117,7 @@ def get_instance_docker_image(instance_id: str) -> str:
 def get_config(
    instance: pd.Series,
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    # We use a different instance image for the each instance of TestGenEval
    base_container_image = get_instance_docker_image(instance['instance_id_swebench'])
    logger.info(
@@ -126,7 +126,7 @@ def get_config(
        f'Submit an issue on https://github.com/All-Hands-AI/OpenHands if you run into any issues.'
    )

-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
--- a/evaluation/benchmarks/the_agent_company/run_infer.py
+++ b/evaluation/benchmarks/the_agent_company/run_infer.py
@@ -15,8 +15,8 @@ from browsing import pre_login
 from evaluation.utils.shared import get_default_sandbox_config_for_eval
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
    LLMConfig,
+    OpenHandsConfig,
    get_agent_config_arg,
    get_llm_config_arg,
    get_parser,
@@ -36,13 +36,13 @@ def get_config(
    mount_path_on_host: str,
    llm_config: LLMConfig,
    agent_config: AgentConfig | None,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = base_container_image
    sandbox_config.enable_auto_lint = True
    # If the web services are running on the host machine, this must be set to True
    sandbox_config.use_host_network = True
-    config = AppConfig(
+    config = OpenHandsConfig(
        run_as_openhands=False,
        max_budget_per_task=4,
        max_iterations=100,
@@ -126,7 +126,7 @@ def codeact_user_response(state: State) -> str:
 def run_solver(
    runtime: Runtime,
    task_name: str,
-    config: AppConfig,
+    config: OpenHandsConfig,
    dependencies: list[str],
    save_final_state: bool,
    state_dir: str,
@@ -274,7 +274,7 @@ if __name__ == '__main__':
        temp_dir = os.path.abspath(os.getenv('TMPDIR'))
    else:
        temp_dir = tempfile.mkdtemp()
-    config: AppConfig = get_config(
+    config: OpenHandsConfig = get_config(
        args.task_image_name, task_short_name, temp_dir, agent_llm_config, agent_config
    )
    runtime: Runtime = create_runtime(config)
--- a/evaluation/benchmarks/toolqa/run_infer.py
+++ b/evaluation/benchmarks/toolqa/run_infer.py
@@ -18,7 +18,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -40,10 +40,10 @@ AGENT_CLS_TO_INST_SUFFIX = {

 def get_config(
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.base_container_image = 'python:3.12-bookworm'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/visual_swe_bench/run_infer.py
+++ b/evaluation/benchmarks/visual_swe_bench/run_infer.py
@@ -30,7 +30,7 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
    AgentConfig,
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    get_parser,
 )
@@ -135,7 +135,7 @@ def get_instance_docker_image(instance_id: str, official_image: bool = False) ->
 def get_config(
    instance: pd.Series,
    metadata: EvalMetadata,
-) -> AppConfig:
+) -> OpenHandsConfig:
    # We use a different instance image for the each instance of swe-bench eval
    use_official_image = bool(
        'verified' in metadata.dataset.lower() or 'lite' in metadata.dataset.lower()
@@ -160,7 +160,7 @@ def get_config(
        instance_id=instance['instance_id'],
    )

-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        max_iterations=metadata.max_iterations,
--- a/evaluation/benchmarks/visualwebarena/run_infer.py
+++ b/evaluation/benchmarks/visualwebarena/run_infer.py
@@ -20,7 +20,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -48,7 +48,7 @@ AGENT_CLS_TO_FAKE_USER_RESPONSE_FN = {
 def get_config(
    metadata: EvalMetadata,
    env_id: str,
-) -> AppConfig:
+) -> OpenHandsConfig:
    base_url = os.environ.get('VISUALWEBARENA_BASE_URL', None)
    openai_api_key = os.environ.get('OPENAI_API_KEY', None)
    openai_base_url = os.environ.get('OPENAI_BASE_URL', None)
@@ -72,7 +72,7 @@ def get_config(
        'VWA_WIKIPEDIA': f'{base_url}:8888',
        'VWA_HOMEPAGE': f'{base_url}:4399',
    }
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/benchmarks/webarena/run_infer.py
+++ b/evaluation/benchmarks/webarena/run_infer.py
@@ -19,7 +19,7 @@ from evaluation.utils.shared import (
 )
 from openhands.controller.state.state import State
 from openhands.core.config import (
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -44,7 +44,7 @@ SUPPORTED_AGENT_CLS = {'BrowsingAgent'}
 def get_config(
    metadata: EvalMetadata,
    env_id: str,
-) -> AppConfig:
+) -> OpenHandsConfig:
    base_url = os.environ.get('WEBARENA_BASE_URL', None)
    openai_api_key = os.environ.get('OPENAI_API_KEY', None)
    assert base_url is not None, 'WEBARENA_BASE_URL must be set'
@@ -64,7 +64,7 @@ def get_config(
        'MAP': f'{base_url}:3000',
        'HOMEPAGE': f'{base_url}:4399',
    }
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime='docker',
--- a/evaluation/integration_tests/run_infer.py
+++ b/evaluation/integration_tests/run_infer.py
@@ -21,7 +21,7 @@ from evaluation.utils.shared import (
 from openhands.controller.state.state import State
 from openhands.core.config import (
    AgentConfig,
-    AppConfig,
+    OpenHandsConfig,
    get_llm_config_arg,
    parse_arguments,
 )
@@ -41,10 +41,10 @@ FAKE_RESPONSES = {
 def get_config(
    metadata: EvalMetadata,
    instance_id: str,
-) -> AppConfig:
+) -> OpenHandsConfig:
    sandbox_config = get_default_sandbox_config_for_eval()
    sandbox_config.platform = 'linux/amd64'
-    config = AppConfig(
+    config = OpenHandsConfig(
        default_agent=metadata.agent_class,
        run_as_openhands=False,
        runtime=os.environ.get('RUNTIME', 'docker'),
--- a/evaluation/regression/run_tests.py
+++ b/evaluation/regression/run_tests.py
@@ -2,9 +2,9 @@ import argparse

 import pytest

-from openhands.config import load_app_config
+from openhands.config import load_openhands_config

-config = load_app_config()
+config = load_openhands_config()

 if __name__ == '__main__':
    """Main entry point of the script.