github/OpenHands
1
0
Fork 0
mirror of https://github.com/OpenHands/OpenHands.git synced 2025-12-26 05:48:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore(lint): Apply comprehensive linting and formatting fixes (#10287)

Browse Source 
Co-authored-by: openhands <openhands@all-hands.dev>
This commit is contained in:
Xingyao Wang 2025-08-13 15:13:19 -04:00 committed by GitHub
parent e39bf80239
commit c2f46200c0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
164 changed files with 526 additions and 1023 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
build_vscode.py
View File

@ -93,8 +93,7 @@ def build_vscode_extension():
def build(setup_kwargs):
"""
This function is called by Poetry during the build process.
"""This function is called by Poetry during the build process.
`setup_kwargs` is a dictionary that will be passed to `setuptools.setup()`.
"""
print('--- Running custom Poetry build script (build_vscode.py) ---')

1
evaluation/benchmarks/commit0/run_infer.py
View File

@ -506,7 +506,6 @@ def commit0_setup(dataset: pd.DataFrame, repo_split: str) -> pd.DataFrame:
Returns:
Filtered dataset based on split type
"""
filtered_dataset = pd.concat(
[
dataset[dataset['repo'].str.split('/').str[1] == repo]

15
evaluation/benchmarks/discoverybench/run_infer.py
View File

@ -89,8 +89,7 @@ def get_config(
def get_dv_query_for_real(
datasets, question, domain_knowledge=None, workflow_tags=None
):
"""
Prepare a structured query for the agent to execute on the specified datasets.
"""Prepare a structured query for the agent to execute on the specified datasets.
This function constructs a query by compiling metadata from the provided datasets, along with any relevant domain knowledge and workflow tags.
@ -104,7 +103,6 @@ def get_dv_query_for_real(
query_to_dv: Query to be run on the dataset
dataset_meta: Metadata of the dataset
"""
dataset_meta = ''
for dataset_metadata in datasets:
dataset_meta += 'Dataset name: ' + dataset_metadata['name']
@ -140,8 +138,7 @@ def get_dv_query_for_real(
def initialize_runtime(runtime: Runtime, data_files: list[str]):
"""
Initialize the runtime for the agent.
"""Initialize the runtime for the agent.
This function is called before the runtime is used to run the agent.
"""
@ -231,8 +228,7 @@ def process_instance(
metadata: EvalMetadata,
reset_logger: bool = True,
):
"""
Process and evaluate a single instance of the dataset.
"""Process and evaluate a single instance of the dataset.
This function executes the OpenHands agent
for a specific instance of the dataset. It retrieves
@ -247,7 +243,6 @@ def process_instance(
Returns:
output: EvalOutput object
"""
config = get_config(metadata)
# Setup the logger properly, so you can run
@ -356,8 +351,7 @@ def list_csv_files(list_of_datasets):
def create_dataset(repo_location: str, split: str = 'test'):
"""
Create a dataset from the discoverybench repository
"""Create a dataset from the discoverybench repository
by walking through the repository and extracting metadata
from the metadata_{}.json files
@ -368,7 +362,6 @@ def create_dataset(repo_location: str, split: str = 'test'):
Returns:
df: DataFrame containing the dataset instances
"""
data_dict = {}
data_location = os.path.join(repo_location, 'discoverybench', 'real', split)

3
evaluation/benchmarks/multi_swe_bench/eval_infer.py
View File

@ -105,8 +105,7 @@ def process_instance(
log_dir: str | None = None,
runtime_failure_count: int = 0,
) -> EvalOutput:
"""
Evaluate agent performance on a SWE-bench problem instance.
"""Evaluate agent performance on a SWE-bench problem instance.
Note that this signature differs from the expected input to `run_evaluation`. Use
`functools.partial` to provide optional arguments before passing to the evaluation harness.

10
evaluation/benchmarks/swe_bench/binary_patch_utils.py
View File

@ -1,11 +1,8 @@
"""
Utilities for handling binary files and patch generation in SWE-bench evaluation.
"""
"""Utilities for handling binary files and patch generation in SWE-bench evaluation."""
def remove_binary_diffs(patch_text):
"""
Remove binary file diffs from a git patch.
"""Remove binary file diffs from a git patch.
Args:
patch_text (str): The git patch text
@ -36,8 +33,7 @@ def remove_binary_diffs(patch_text):
def remove_binary_files_from_git():
"""
Generate a bash command to remove binary files from git staging.
"""Generate a bash command to remove binary files from git staging.
Returns:
str: A bash command that removes binary files from git staging

3
evaluation/benchmarks/swe_bench/eval_infer.py
View File

@ -111,8 +111,7 @@ def process_instance(
runtime_failure_count: int = 0,
conditional_imports: ConditionalImports | None = None,
) -> EvalOutput:
"""
Evaluate agent performance on a SWE-bench problem instance.
"""Evaluate agent performance on a SWE-bench problem instance.
Note that this signature differs from the expected input to `run_evaluation`. Use
`functools.partial` to provide optional arguments before passing to the evaluation harness.

36
evaluation/benchmarks/swe_bench/loc_eval/loc_evaluator.py
View File

@ -16,8 +16,7 @@ from openhands.core.logger import openhands_logger as logger
class LocEvaluator:
def __init__(self, args):
"""
Localization evaluation.
"""Localization evaluation.
Args:
args: all main arguments
@ -76,8 +75,7 @@ class LocEvaluator:
self.task_resolved = False
def _init_dir(self, directory_path):
"""
Check if a directory exists and create it if it doesn't.
"""Check if a directory exists and create it if it doesn't.
Args:
directory_path (str): Path to the directory to check/create
@ -207,8 +205,7 @@ class LocEvaluator:
self._compute_avg_over_all()
def _write_to_json(self, data, file_name):
"""
Writes the current object data to a JSON file.
"""Writes the current object data to a JSON file.
Returns:
bool: True if writing was successful, False otherwise.
@ -225,8 +222,7 @@ class LocEvaluator:
return False
def read_from_json(self, file_path):
"""
Reads data from a JSON file and loads it into the current object.
"""Reads data from a JSON file and loads it into the current object.
Returns:
dict: The loaded JSON data, or an empty dict if the file doesn't exist
@ -253,8 +249,7 @@ class LocEvaluator:
return {}
def read_from_jsonl(self, file_path):
"""
Reads data from a JSON file and loads it into the current object.
"""Reads data from a JSON file and loads it into the current object.
Returns:
dict: The loaded JSON data, or an empty dict if the file doesn't exist
@ -294,8 +289,7 @@ class LocEvaluator:
history_idx += 1
def _parse_string_to_dict(self, dict_string) -> dict:
"""
Convert a string representation of a dictionary to an actual dictionary.
"""Convert a string representation of a dictionary to an actual dictionary.
Args:
dict_string (str): String representation of a dictionary
@ -328,8 +322,7 @@ class LocEvaluator:
return None
def _parse_value_from_args(self, argument_str: str, key: str) -> str:
"""
Parse a specific key's value from argument string.
"""Parse a specific key's value from argument string.
Args:
argument_str (str): The argument string containing key-value pairs
@ -407,8 +400,7 @@ class LocEvaluator:
return ''
def _parse_path_from_args(self, argument_str: str) -> str:
"""
Parse path from argument string.
"""Parse path from argument string.
Args:
argument_str (str): The argument string containing path information
@ -419,8 +411,7 @@ class LocEvaluator:
return self._parse_value_from_args(argument_str, 'path')
def _parse_func_names_from_str(self, code_patch) -> list:
"""
Parse function names from the new_str code patch.
"""Parse function names from the new_str code patch.
Args:
code_patch: Either a string (argument string) or already extracted new_str code
@ -801,8 +792,7 @@ class LocEvaluator:
def swe_data_loader(args):
"""
Loading SWE-Bench data.
"""Loading SWE-Bench data.
Args:
args: Main arguments.
@ -834,8 +824,7 @@ def swe_data_loader(args):
def infer_data_loader(args):
"""
Load instance IDs.
"""Load instance IDs.
Args:
args: Main arguments.
@ -868,8 +857,7 @@ def infer_data_loader(args):
def infer_cost_calculator(args):
"""
Calculate total and average costs from metric JSON files with detailed output.
"""Calculate total and average costs from metric JSON files with detailed output.
Args:
args: Main arguments.

63
evaluation/benchmarks/swe_bench/loc_eval/loc_utils.py
View File

@ -28,8 +28,7 @@ class LocalizationInfo:
hunks_per_file: dict[str, int] # File -> number of hunks
def to_dict(self) -> dict[str, Any]:
"""
Convert LocalizationInfo to a dictionary for JSON serialization.
"""Convert LocalizationInfo to a dictionary for JSON serialization.
Returns:
Dictionary representation of the localization information
@ -58,8 +57,7 @@ class LocalizationInfo:
@classmethod
def from_dict(cls, data: dict[str, Any]) -> 'LocalizationInfo':
"""
Create LocalizationInfo from a dictionary (for loading from JSON).
"""Create LocalizationInfo from a dictionary (for loading from JSON).
Args:
data: Dictionary containing localization information
@ -91,8 +89,7 @@ class LocalizationInfo:
class LocMeta:
"""
SWE-Bench dataset loader and ground-truth localization parser.
"""SWE-Bench dataset loader and ground-truth localization parser.
This class handles loading SWE-Bench datasets and extracting ground-truth
localization information from patches for code localization evaluation.
@ -104,8 +101,7 @@ class LocMeta:
dataset_name: str = 'princeton-nlp/SWE-bench_Verified',
split: str = 'test',
):
"""
Initialize LocMeta with a SWE-Bench dataset.
"""Initialize LocMeta with a SWE-Bench dataset.
Args:
dataset_name: HuggingFace dataset name (e.g., "princeton-nlp/SWE-bench_Verified")
@ -124,8 +120,7 @@ class LocMeta:
self._init_swe_dataset()
def _init_swe_dataset(self) -> None:
"""
Load and initialize the SWE-Bench dataset from HuggingFace.
"""Load and initialize the SWE-Bench dataset from HuggingFace.
Converts to pandas DataFrame for easy manipulation.
"""
try:
@ -150,8 +145,7 @@ class LocMeta:
raise
def get_instance_by_id(self, instance_id: str) -> pd.Series:
"""
Retrieve a specific instance by its ID.
"""Retrieve a specific instance by its ID.
Args:
instance_id: The instance identifier
@ -169,8 +163,7 @@ class LocMeta:
return self.df.iloc[idx]
def parse_instance_loc(self, instance: Union[pd.Series, str]) -> LocalizationInfo:
"""
Parse ground-truth localization information from a SWE-Bench instance.
"""Parse ground-truth localization information from a SWE-Bench instance.
Args:
instance: Either a pandas Series with instance data or an instance_id string
@ -218,8 +211,7 @@ class LocMeta:
def _parse_file_patch_lines(
self, file_patch: str
) -> tuple[list[tuple[int, int]], int, int]:
"""
Parse line ranges and count changes from a single file patch.
"""Parse line ranges and count changes from a single file patch.
Args:
file_patch: Patch content for a single file
@ -253,8 +245,7 @@ class LocMeta:
def _parse_code_structures_from_patch(
self, file_patch: str, file_path: str
) -> tuple[list[str], list[str]]:
"""
Extract function and class names from patch context (fallback method).
"""Extract function and class names from patch context (fallback method).
Args:
file_patch: Patch content for a single file
@ -311,8 +302,7 @@ class LocMeta:
def _parse_patch_localization(
self, patch_content: str, instance_id: str
) -> LocalizationInfo:
"""
Parse localization information from a git patch (improved method).
"""Parse localization information from a git patch (improved method).
Args:
patch_content: The git patch content
@ -390,8 +380,7 @@ class LocMeta:
def _extract_code_structures_from_patch(
self, file_patch: str, file_path: str
) -> tuple[list[str], list[str]]:
"""
Extract function and class names from patch context and content.
"""Extract function and class names from patch context and content.
Args:
file_patch: Patch content for a single file
@ -519,8 +508,7 @@ class LocMeta:
def _parse_patch_localization_with_runtime(
self, patch_content: str, instance_id: str, runtime: Runtime
) -> LocalizationInfo:
"""
Parse localization information from a git patch using OpenHands runtime.
"""Parse localization information from a git patch using OpenHands runtime.
This is the superior method when runtime is available.
Args:
@ -596,8 +584,7 @@ class LocMeta:
def parse_instance_loc_with_runtime(
self, instance: Union[pd.Series, str], runtime: Runtime = None
) -> LocalizationInfo:
"""
Parse ground-truth localization information using OpenHands runtime.
"""Parse ground-truth localization information using OpenHands runtime.
Args:
instance: Either a pandas Series with instance data or an instance_id string
@ -634,8 +621,7 @@ class LocMeta:
def _analyze_source_code_with_runtime(
self, runtime: Runtime, file_path: str, affected_lines: list[int]
) -> tuple[list[str], list[str], dict[int, str], dict[int, str]]:
"""
Analyze source code using OpenHands runtime to find functions and classes.
"""Analyze source code using OpenHands runtime to find functions and classes.
Args:
runtime: OpenHands runtime object
@ -695,8 +681,7 @@ class LocMeta:
def _parse_cython_content_with_line_mapping(
self, content: str, affected_lines: list[int]
) -> tuple[list[str], list[str], dict[int, str], dict[int, str]]:
"""
Parse Cython content to extract functions and classes with line mapping.
"""Parse Cython content to extract functions and classes with line mapping.
Since Cython files can't be parsed with Python's AST, we use regex-based parsing.
Args:
@ -828,8 +813,7 @@ class LocMeta:
def _parse_python_content_with_line_mapping(
self, content: str, affected_lines: list[int]
) -> tuple[list[str], list[str], dict[int, str], dict[int, str]]:
"""
Parse Python content to extract functions and classes with accurate line mapping.
"""Parse Python content to extract functions and classes with accurate line mapping.
Args:
content: Python source code content
@ -914,8 +898,7 @@ class LocMeta:
def _parse_python_content(
self, content: str, affected_lines: list[int]
) -> tuple[list[str], list[str], dict[int, str], dict[int, str]]:
"""
Parse Python content to extract functions and classes.
"""Parse Python content to extract functions and classes.
Args:
content: Python source code content
@ -989,8 +972,7 @@ class LocMeta:
return [], [], {}, {}
def _split_patch_by_files(self, patch_content: str) -> dict[str, str]:
"""
Split a multi-file patch into individual file patches.
"""Split a multi-file patch into individual file patches.
Args:
patch_content: Complete patch content
@ -1049,8 +1031,7 @@ class LocMeta:
def _empty_localization_info(
self, instance_id: str = 'unknown'
) -> LocalizationInfo:
"""
Return an empty LocalizationInfo object.
"""Return an empty LocalizationInfo object.
Args:
instance_id: Instance identifier
@ -1072,8 +1053,7 @@ class LocMeta:
)
def get_dataset_statistics(self) -> dict[str, Any]:
"""
Get statistics about the loaded dataset.
"""Get statistics about the loaded dataset.
Returns:
Dictionary containing dataset statistics
@ -1095,8 +1075,7 @@ class LocMeta:
return stats
def get_instances_by_repo(self, repo_name: str) -> pd.DataFrame:
"""
Get all instances for a specific repository.
"""Get all instances for a specific repository.
Args:
repo_name: Repository name (e.g., "django/django")

3
evaluation/benchmarks/swe_bench/scripts/eval/verify_costs.py
View File

@ -6,8 +6,7 @@ from openhands.core.logger import openhands_logger as logger
def verify_instance_costs(row: pd.Series) -> float:
"""
Verifies that the accumulated_cost matches the sum of individual costs in metrics.
"""Verifies that the accumulated_cost matches the sum of individual costs in metrics.
Also checks for duplicate consecutive costs which might indicate buggy counting.
If the consecutive costs are identical, the file is affected by this bug:
https://github.com/All-Hands-AI/OpenHands/issues/5383

8
evaluation/benchmarks/testgeneval/compute_readability.py
View File

@ -181,9 +181,7 @@ def distinct_methods_stats(tree, num_lines):
def loops_stats(tree, num_lines):
"""
Calculate the average number of loops.
"""
"""Calculate the average number of loops."""
total_loops = 0
def traverse(node):
@ -199,9 +197,7 @@ def loops_stats(tree, num_lines):
def branches_stats(tree, num_lines):
"""
Calculate the average number of branches (conditional statements).
"""
"""Calculate the average number of branches (conditional statements)."""
total_branches = 0
def traverse(node):

9
evaluation/benchmarks/testgeneval/eval_infer.py
View File

@ -192,8 +192,7 @@ def run_mutation_testing(
def grade_test_output(
test_suite: str, instance: pd.Series, test_output: str, test_spec: TestSpec, runtime
):
"""
Two-pass test grading with short-circuiting:
"""Two-pass test grading with short-circuiting:
1. Run all tests to identify passing/failing tests
2. If no failing tests, evaluate coverage immediately
3. Otherwise, run only passing tests for coverage analysis
@ -280,8 +279,7 @@ def process_instance(
reset_logger: bool = True,
log_dir: str | None = None,
) -> EvalOutput:
"""
Evaluate agent performance on a TestGenEval problem instance.
"""Evaluate agent performance on a TestGenEval problem instance.
Note that this signature differs from the expected input to `run_evaluation`. Use
`functools.partial` to provide optional arguments before passing to the evaluation harness.
@ -453,8 +451,7 @@ def process_instance(
def count_and_log_fields(evaluated_predictions, fields, key):
"""
Count and log the sum of specified fields in the evaluated predictions,
"""Count and log the sum of specified fields in the evaluated predictions,
ignoring fields with a value of -1. If all values for a field are -1,
return -1.

21
evaluation/benchmarks/testgeneval/log_parsers.py
View File

@ -4,8 +4,7 @@ from evaluation.benchmarks.testgeneval.constants import TestStatus
def parse_log_pytest(log: str) -> dict[str, str]:
"""
Parser for test logs generated with PyTest framework
"""Parser for test logs generated with PyTest framework
Args:
log (str): log content
@ -26,8 +25,7 @@ def parse_log_pytest(log: str) -> dict[str, str]:
def parse_log_pytest_options(log: str) -> dict[str, str]:
"""
Parser for test logs generated with PyTest framework with options
"""Parser for test logs generated with PyTest framework with options
Args:
log (str): log content
@ -61,8 +59,7 @@ def parse_log_pytest_options(log: str) -> dict[str, str]:
def parse_log_django(log: str) -> dict[str, str]:
"""
Parser for test logs generated with Django tester framework
"""Parser for test logs generated with Django tester framework
Args:
log (str): log content
@ -141,8 +138,7 @@ def parse_log_django(log: str) -> dict[str, str]:
def parse_log_pytest_v2(log: str) -> dict[str, str]:
"""
Parser for test logs generated with PyTest framework (Later Version)
"""Parser for test logs generated with PyTest framework (Later Version)
Args:
log (str): log content
@ -170,8 +166,7 @@ def parse_log_pytest_v2(log: str) -> dict[str, str]:
def parse_log_seaborn(log: str) -> dict[str, str]:
"""
Parser for test logs generated with seaborn testing framework
"""Parser for test logs generated with seaborn testing framework
Args:
log (str): log content
@ -196,8 +191,7 @@ def parse_log_seaborn(log: str) -> dict[str, str]:
def parse_log_sympy(log: str) -> dict[str, str]:
"""
Parser for test logs generated with Sympy framework
"""Parser for test logs generated with Sympy framework
Args:
log (str): log content
@ -229,8 +223,7 @@ def parse_log_sympy(log: str) -> dict[str, str]:
def parse_log_matplotlib(log: str) -> dict[str, str]:
"""
Parser for test logs generated with PyTest framework
"""Parser for test logs generated with PyTest framework
Args:
log (str): log content

45
evaluation/benchmarks/testgeneval/metrics.py
View File

@ -12,8 +12,7 @@ if sys.getrecursionlimit() < 10_000:
def bleu(gold: list[str], pred: list[str]) -> float:
"""
Calculate BLEU score, using smoothing method 2 with auto reweighting, in the range of 0~100.
"""Calculate BLEU score, using smoothing method 2 with auto reweighting, in the range of 0~100.
:param gold: list of gold tokens
:param pred: list of predicted tokens
@ -30,8 +29,7 @@ def bleu(gold: list[str], pred: list[str]) -> float:
def batch_bleu(golds: list[list[str]], preds: list[list[str]]) -> list[float]:
"""
Calculate BLEU score for a batch of sentences.
"""Calculate BLEU score for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@ -43,8 +41,7 @@ def batch_bleu(golds: list[list[str]], preds: list[list[str]]) -> list[float]:
def corpus_bleu(golds: list[list[str]], preds: list[list[str]]) -> float:
"""
Calculate corpus-level BLEU score for a batch of sentences.
"""Calculate corpus-level BLEU score for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@ -63,8 +60,7 @@ def corpus_bleu(golds: list[list[str]], preds: list[list[str]]) -> float:
def edit_sim(
gold: Union[str, list[str]], pred: Union[str, list[str]], sep: str = ' '
) -> float:
"""
Calculate char-level edit similarity, in the range of 0~100.
"""Calculate char-level edit similarity, in the range of 0~100.
:param gold: gold sentence or list of gold tokens
:param pred: predicted sentence or list of predicted tokens
@ -85,8 +81,7 @@ def batch_edit_sim(
preds: list[Union[str, list[str]]],
sep: str = ' ',
) -> list[float]:
"""
Calculate char-level edit similarity for a batch of sentences.
"""Calculate char-level edit similarity for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@ -102,8 +97,7 @@ T = TypeVar('T')
def exact_match(gold: T, pred: T) -> float:
"""
Calculate exact match accuracy, in the range of {0, 100}.
"""Calculate exact match accuracy, in the range of {0, 100}.
:param gold: gold sentence or list of gold tokens
:param pred: predicted sentence or list of predicted tokens
@ -115,8 +109,7 @@ def exact_match(gold: T, pred: T) -> float:
def batch_exact_match(golds: list[T], preds: list[T]) -> list[float]:
"""
Calculate exact match accuracy for a batch of sentences.
"""Calculate exact match accuracy for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@ -130,8 +123,7 @@ def batch_exact_match(golds: list[T], preds: list[T]) -> list[float]:
def rouge_l(
gold: Union[str, list[str]], pred: Union[str, list[str]], sep: str = ' '
) -> dict[str, float]:
"""
Calculate ROUGE-L F1, precision, and recall scores, in the range of 0~100.
"""Calculate ROUGE-L F1, precision, and recall scores, in the range of 0~100.
:param gold: gold sentence or list of gold tokens
:param pred: predicted sentence or list of predicted tokens
@ -156,8 +148,7 @@ def batch_rouge_l(
preds: list[Union[str, list[str]]],
sep: str = ' ',
) -> dict[str, list[float]]:
"""
Calculate ROUGE-L F1, precision, and recall scores for a batch of sentences.
"""Calculate ROUGE-L F1, precision, and recall scores for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@ -175,8 +166,7 @@ def accuracy(
pred: list[str],
ignore: Optional[Sequence[str]] = None,
) -> float:
"""
Calculate token-level accuracy, in the range of 0~100.
"""Calculate token-level accuracy, in the range of 0~100.
If gold and pred are not the same length, the longer one would be truncated.
:param gold: list of gold tokens
@ -210,8 +200,7 @@ def batch_accuracy(
preds: list[list[str]],
ignore: Optional[Sequence[str]] = None,
) -> list[float]:
"""
Calculate token-level accuracy for a batch of sentences.
"""Calculate token-level accuracy for a batch of sentences.
:param golds: list of gold sentences
:param preds: list of predicted sentences
@ -226,8 +215,7 @@ def batch_accuracy(
def first_match_to_topk(
first_match_list: list[int], k_values: list[int]
) -> dict[int, list[float]]:
"""
Calculate top-k accuracy with the first match ranks (1-indexed).
"""Calculate top-k accuracy with the first match ranks (1-indexed).
:param first_match: first match ranks (1-indexed)
:param k_values: k values to consider
@ -237,8 +225,7 @@ def first_match_to_topk(
def pass_at_k(n: int, c: int, k: int) -> float:
"""
Sample pass@k metric according to the Codex paper, but in the scale of 0~100.
"""Sample pass@k metric according to the Codex paper, but in the scale of 0~100.
:param n: total number of samples
:param c: number of correct samples
:param k: k in pass@$k$
@ -251,8 +238,7 @@ def pass_at_k(n: int, c: int, k: int) -> float:
def self_bleu(samples: list[list[str]]) -> float:
"""
Calculate self-BLEU among the samples.
"""Calculate self-BLEU among the samples.
:param samples: the chosen m samples
:return: self-BLEU
"""
@ -274,8 +260,7 @@ def self_bleu(samples: list[list[str]]) -> float:
def self_edit_distance(samples: list[Union[str, list[str]]], sep=' ') -> float:
"""
Calculate self-edit-distance among the samples.
"""Calculate self-edit-distance among the samples.
:param samples: the chosen m samples
:param sep: the separator between tokens
:return: self-edit-distance

6
evaluation/benchmarks/testgeneval/report_utils.py
View File

@ -30,8 +30,7 @@ def check_mutation(mutation_output):
def count_methods(code_str):
"""
Counts the number of methods/functions in a given string of code.
"""Counts the number of methods/functions in a given string of code.
Args:
code_str (str): A string containing code.
@ -46,8 +45,7 @@ def count_methods(code_str):
def get_lines_of_code(code_str):
"""
Extracts lines of code from a given string.
"""Extracts lines of code from a given string.
Args:
code_str (str): A string containing code.

6
evaluation/benchmarks/testgeneval/scripts/eval/build_outputs_ablation.py
View File

@ -7,8 +7,7 @@ import traceback
def insert_line_in_string(input_string, new_str, insert_line):
"""
Inserts a new line into a string at the specified line number.
"""Inserts a new line into a string at the specified line number.
:param input_string: The original string.
:param new_str: The string to insert.
@ -29,8 +28,7 @@ def insert_line_in_string(input_string, new_str, insert_line):
def print_string_diff(original, modified):
"""
Prints the differences between two strings line by line.
"""Prints the differences between two strings line by line.
:param original: The original string.
:param modified: The modified string.

10
evaluation/benchmarks/testgeneval/test_filter.py
View File

@ -37,8 +37,7 @@ def extract_preamble_classes_and_functions(code):
current_position = 0
def extract_class_body(code: str, start_index: int) -> tuple[str, int]:
"""
Extracts the body of a class from the given code starting from the specified index.
"""Extracts the body of a class from the given code starting from the specified index.
Returns the class body and the end index of the class body.
"""
if not code or start_index < 0 or start_index >= len(code):
@ -168,8 +167,8 @@ def extract_preamble_classes_and_functions(code):
def filter_passing_tests(
test_content: str, test_output: str, repo: str
) -> tuple[str, list[str], list[str]]:
"""
Filter tests based on their execution results.
"""Filter tests based on their execution results.
Returns:
Tuple containing:
- Modified test content with only passing tests
@ -246,8 +245,7 @@ def filter_passing_tests(
def filter_tests(
test_content: str, test_output: str, repo: str
) -> tuple[str, list[str], list[str]]:
"""
Filter tests using AST parsing to remove failing test functions from the test file.
"""Filter tests using AST parsing to remove failing test functions from the test file.
Non-test functions (e.g. setup or helper methods) and classes (even if all test methods are failing)
are preserved.

14
evaluation/benchmarks/testgeneval/test_spec.py
View File

@ -20,9 +20,7 @@ DIFF_MODIFIED_FILE_REGEX = r'--- a/(.*)'
@dataclass
class TestSpec:
"""
A dataclass that represents a test specification for a single instance of SWE-bench.
"""
"""A dataclass that represents a test specification for a single instance of SWE-bench."""
instance_id: str
id: str
@ -86,10 +84,7 @@ def make_test_setup(specs, env_name, repo_directory, includes_tox=False):
def make_test_script_list(test_cmd, specs, env_name, repo_directory):
"""
Runs the tests.
"""
"""Runs the tests."""
includes_tox = 'tox' in test_cmd
eval_commands = make_test_setup(specs, env_name, repo_directory, includes_tox)
eval_commands += [
@ -104,10 +99,7 @@ def make_test_script_list(test_cmd, specs, env_name, repo_directory):
def make_mutation_script_list(specs, env_name, repo_directory, mutation_timeout):
"""
Runs the tests.
"""
"""Runs the tests."""
eval_commands = make_test_setup(specs, env_name, repo_directory)
eval_commands += [
'cosmic-ray init mutation.toml mutation.sqlite',

7
evaluation/benchmarks/testgeneval/utils.py
View File

@ -11,8 +11,7 @@ from evaluation.benchmarks.testgeneval.constants import (
def get_test_directives(instance: TestGenEvalInstance) -> list:
"""
Get test directives from the test_patch of a task instance
"""Get test directives from the test_patch of a task instance
Args:
instance (dict): task instance
@ -43,9 +42,7 @@ def get_test_directives(instance: TestGenEvalInstance) -> list:
def load_testgeneval_dataset(
name='kjain14/testgeneval', split='test', ids=None
) -> list[TestGenEvalInstance]:
"""
Load SWE-bench dataset from Hugging Face Datasets or local .json/.jsonl file
"""
"""Load SWE-bench dataset from Hugging Face Datasets or local .json/.jsonl file"""
# check that all instance IDs are in the dataset
if ids:
ids = set(ids)

10
evaluation/benchmarks/the_agent_company/browsing.py
View File

@ -24,9 +24,7 @@ class ActionType(Enum):
@dataclass
class Selector:
"""
Represents either a direct anchor ID or a descriptive selector
"""
"""Represents either a direct anchor ID or a descriptive selector"""
value: str
is_anchor: bool = False
@ -149,8 +147,7 @@ def find_matching_anchor(content: str, selector: str) -> str | None:
def resolve_action(action: BrowserAction, content: str) -> BrowserAction:
"""
Resolve any descriptive selectors in the action to anchor IDs based on the content.
"""Resolve any descriptive selectors in the action to anchor IDs based on the content.
Returns a new action with resolved selectors.
"""
if isinstance(action, (InputAction, ClickAction)):
@ -174,8 +171,7 @@ def pre_login(
save_screenshots=True,
screenshots_dir='screenshots',
):
"""
Logs in to all the websites that are needed for the evaluation.
"""Logs in to all the websites that are needed for the evaluation.
Once logged in, the sessions would be cached in the browser, so OpenHands
agent doesn't need to log in to these websites again.
"""

3
evaluation/benchmarks/the_agent_company/run_infer.py
View File

@ -68,8 +68,7 @@ def get_config(
def load_dependencies(runtime: Runtime) -> list[str]:
"""
Every task has a dependencies.yml file, which lists all the services that the
"""Every task has a dependencies.yml file, which lists all the services that the
task depends on. This function loads the file and returns all dependent service names.
"""
command = 'cat /utils/dependencies.yml'

23
evaluation/benchmarks/the_agent_company/scripts/summarise_results.py
View File

@ -11,9 +11,7 @@ import sys
def calculate_cost(model: str, prompt_tokens: int, completion_tokens: int) -> float:
"""
Calculate the cost of the model call.
"""
"""Calculate the cost of the model call."""
if 'claude-3-5-sonnet' in model.lower():
# https://www.anthropic.com/pricing#anthropic-api, accessed 12/11/2024
return 0.000003 * prompt_tokens + 0.000015 * completion_tokens
@ -60,8 +58,7 @@ def calculate_cost(model: str, prompt_tokens: int, completion_tokens: int) -> fl
def analyze_eval_json_file(filepath: str) -> tuple[int, int]:
"""
Analyze a single eval JSON file and extract the total and result from final_score.
"""Analyze a single eval JSON file and extract the total and result from final_score.
Args:
filepath: Path to the JSON file
@ -84,8 +81,7 @@ def analyze_eval_json_file(filepath: str) -> tuple[int, int]:
def analyze_traj_json_file(filepath: str) -> tuple[int, float]:
"""
Analyze a single trajectory JSON file and extract the steps and tokens
"""Analyze a single trajectory JSON file and extract the steps and tokens
for each step. Then estimate the cost based on the tokens and the model type.
Note: this is assuming there's no prompt caching at all.
"""
@ -115,8 +111,7 @@ def analyze_traj_json_file(filepath: str) -> tuple[int, float]:
def analyze_folder(
folder_path: str,
) -> tuple[dict[str, tuple[int, int]], dict[str, tuple[int, float]]]:
"""
Analyze all eval_*.json & traj_*.json files in the specified folder.
"""Analyze all eval_*.json & traj_*.json files in the specified folder.
Args:
folder_path: Path to the folder containing JSON files
@ -148,9 +143,7 @@ def analyze_folder(
def get_task_nature_category(task_name: str) -> str:
"""
Get the nature category of the task.
"""
"""Get the nature category of the task."""
task_nature = task_name.split('-')[0]
if task_nature.lower() in ['sde', 'pm', 'ds', 'admin', 'hr', 'finance']:
return task_nature
@ -159,8 +152,7 @@ def get_task_nature_category(task_name: str) -> str:
def calculate_score(total: int, result: int) -> float:
"""
Calculate the score as a number between 0 and 1.
"""Calculate the score as a number between 0 and 1.
Formula: score = (result / total) * 0.5 + (result // total) * 0.5
Explanation:
@ -178,8 +170,7 @@ def calculate_score(total: int, result: int) -> float:
def is_perfect_completion(total: int, result: int) -> bool:
"""
Check if the task achieved perfect completion.
"""Check if the task achieved perfect completion.
Args:
total: Total possible points

7
evaluation/benchmarks/versicode/inference_utils/api_code_migration.py
View File

@ -1,6 +1,4 @@
"""
GPT performs line level generation prediction and truncates overly long tokens
"""
"""GPT performs line level generation prediction and truncates overly long tokens"""
import json
import os
@ -56,8 +54,7 @@ def predict(content, model_name):
def bulid_prompt(description, old_version, old_code, new_version) -> str:
"""
build prompt
"""Build prompt
:param version:
:param description:
:param masked_code:

7
evaluation/benchmarks/versicode/inference_utils/api_test_block_completion.py
View File

@ -1,6 +1,4 @@
"""
GPT performs line level generation prediction and truncates overly long tokens
"""
"""GPT performs line level generation prediction and truncates overly long tokens"""
import json
import os
@ -56,8 +54,7 @@ def predict(content, model_name):
def bulid_prompt(version, description) -> str:
"""
build prompt
"""Build prompt
:param version:
:param description:
:param masked_code:

7
evaluation/benchmarks/versicode/inference_utils/test_block.py
View File

@ -1,6 +1,4 @@
"""
block completion
"""
"""block completion"""
import copy
import gc
@ -79,8 +77,7 @@ def run_inference(model_name, origin_data_list):
def bulid_prompt(version, description) -> str:
"""
build prompt
"""Build prompt
:param version:
:param description:
:param masked_code:

7
evaluation/benchmarks/versicode/inference_utils/test_migration.py
View File

@ -1,6 +1,4 @@
"""
code migration
"""
"""code migration"""
import copy
import gc
@ -81,8 +79,7 @@ def run_inference(model_name, origin_data_list):
def bulid_prompt(description, old_version, old_code, new_version) -> str:
"""
build prompt
"""Build prompt
:param version:
:param description:
:param masked_code:

27
evaluation/benchmarks/versicode/metric/compute_ism_pm_score.py
View File

@ -1,5 +1,4 @@
"""
评测block的预测能力
"""评测block的预测能力
1、判断是否包含正确的函数名
2、判断是否合法
3、计算ISM，和PM
@ -22,8 +21,7 @@ def is_code_valid(code):
def longest_common_prefix_between_lists_with_elements(list1, list2):
"""
计算两个字符串列表中元素的最长前缀匹配长度
"""计算两个字符串列表中元素的最长前缀匹配长度
:param list1:
:param list2:
:return:
@ -46,8 +44,7 @@ def longest_common_prefix_between_lists_with_elements(list1, list2):
def get_token(ans_code: str, output_code: str):
"""
对代码进行词法分析，分解成标识符，返回两个标识符列表
"""对代码进行词法分析，分解成标识符，返回两个标识符列表
:param ans_code:
:param output_code:
:return:
@ -94,8 +91,7 @@ def get_token(ans_code: str, output_code: str):
def get_token_per_line(code: str):
"""
对每一行代码进行词法分析，记录每一行的标识符
"""对每一行代码进行词法分析，记录每一行的标识符
:param code: 代码字符串
:return: 每一行的标识符列表组成的列表
"""
@ -117,8 +113,7 @@ def get_token_per_line(code: str):
def get_ISM(answer_code: str, model_output_list: list, answer_name: str) -> list:
"""
计算ISM，返回一个有序的得分列表
"""计算ISM，返回一个有序的得分列表
:return:
"""
score_list = []
@ -157,8 +152,7 @@ def get_ISM(answer_code: str, model_output_list: list, answer_name: str) -> list
def get_ISM_without_verification(
answer_code: str, model_output_list: list, answer_name: str
) -> list:
"""
计算ISM，返回一个有序的得分列表
"""计算ISM，返回一个有序的得分列表
:return:
"""
score_list = []
@ -190,8 +184,7 @@ def get_ISM_without_verification(
def longest_common_prefix_with_lengths(list1, list2):
"""
计算两个二维列表中每个子列表的最长前缀匹配长度，并记录拥有最长前缀匹配长度的两个子列表的长度
"""计算两个二维列表中每个子列表的最长前缀匹配长度，并记录拥有最长前缀匹配长度的两个子列表的长度
:param list1: 第一个二维列表
:param list2: 第二个二维列表
:return: 最长前缀匹配长度以及拥有最长前缀匹配长度的两个子列表的长度
@ -216,8 +209,7 @@ def longest_common_prefix_with_lengths(list1, list2):
def get_PM(answer_code: str, model_output_list: list, answer_name: str) -> list:
"""
计算PM，返回一个有序的得分列表
"""计算PM，返回一个有序的得分列表
:return:
"""
score_list = []
@ -254,8 +246,7 @@ def get_PM(answer_code: str, model_output_list: list, answer_name: str) -> list:
def get_score(score_list: list, k):
"""
计算score@n,k
"""计算score@n,k
:param score_list:
:param k:
:return:

17
evaluation/benchmarks/versicode/metric/compute_migration_cdc_score.py
View File

@ -1,6 +1,4 @@
"""
Calculate the cdc score for migration
"""
"""Calculate the cdc score for migration"""
import json
import math
@ -11,8 +9,7 @@ import re
def is_correct_parameter_count(function_name, correct_code, test_code):
"""
判断参数数量是否一致
"""判断参数数量是否一致
:param function_name:
:param correct_code:
:param test_code:
@ -43,8 +40,7 @@ def is_correct_parameter_count(function_name, correct_code, test_code):
def check_keyword_parameters(function_name, correct_code, test_code):
"""
判断关键词参数赋值是否正确使用
"""判断关键词参数赋值是否正确使用
:param function_name:
:param correct_code:
:param test_code:
@ -82,8 +78,7 @@ def check_keyword_parameters(function_name, correct_code, test_code):
def with_correct(answer_code: str, model_output: str) -> bool:
"""
当answer是with结构时，判断模型生成的是不是with结构
"""当answer是with结构时，判断模型生成的是不是with结构
:param answer_code:
:param model_output:
:return:
@ -105,9 +100,7 @@ def compute_block_score_k(
core_line_in_core_block,
core_line_in_output_clear,
):
"""
cdc需要满足五个条件，em只需要满足第一个条件
"""
"""cdc需要满足五个条件，em只需要满足第一个条件"""
c = 0
n = len(model_output)
for index, code in enumerate(model_output):

13
evaluation/benchmarks/versicode/metric/compute_versicode_cdc_score.py
View File

@ -1,6 +1,4 @@
"""
Calculate the cdc score for line and block
"""
"""Calculate the cdc score for line and block"""
import json
import math
@ -19,8 +17,7 @@ def is_code_valid(code):
def is_correct_parameter_count(function_name, correct_code, test_code):
"""
判断参数数量是否一致
"""判断参数数量是否一致
:param function_name:
:param correct_code:
:param test_code:
@ -51,8 +48,7 @@ def is_correct_parameter_count(function_name, correct_code, test_code):
def check_keyword_parameters(function_name, correct_code, test_code):
"""
判断关键词参数赋值是否正确使用
"""判断关键词参数赋值是否正确使用
:param function_name:
:param correct_code:
:param test_code:
@ -90,8 +86,7 @@ def check_keyword_parameters(function_name, correct_code, test_code):
def with_correct(answer_code: str, model_output: str) -> bool:
"""
当answer是with结构时，判断模型生成的是不是with结构
"""当answer是with结构时，判断模型生成的是不是with结构
:param answer_code:
:param model_output:
:return:

13
evaluation/benchmarks/versicode/metric/compute_versicode_em_score.py
View File

@ -1,6 +1,4 @@
"""
Calculate the cdc score for line and block
"""
"""Calculate the cdc score for line and block"""
import json
import math
@ -19,8 +17,7 @@ def is_code_valid(code):
def is_correct_parameter_count(function_name, correct_code, test_code):
"""
判断参数数量是否一致
"""判断参数数量是否一致
:param function_name:
:param correct_code:
:param test_code:
@ -51,8 +48,7 @@ def is_correct_parameter_count(function_name, correct_code, test_code):
def check_keyword_parameters(function_name, correct_code, test_code):
"""
判断关键词参数赋值是否正确使用
"""判断关键词参数赋值是否正确使用
:param function_name:
:param correct_code:
:param test_code:
@ -90,8 +86,7 @@ def check_keyword_parameters(function_name, correct_code, test_code):
def with_correct(answer_code: str, model_output: str) -> bool:
"""
当answer是with结构时，判断模型生成的是不是with结构
"""当answer是with结构时，判断模型生成的是不是with结构
:param answer_code:
:param model_output:
:return:

4
evaluation/benchmarks/versicode/output_processing/choose_core_line_from_block_versicode.py
View File

@ -1,6 +1,4 @@
"""
Find the line of code generated by the model using the block in the version code
"""
"""Find the line of code generated by the model using the block in the version code"""
import json
import os

4
evaluation/benchmarks/versicode/output_processing/choose_core_line_from_migration_versicode.py
View File

@ -1,6 +1,4 @@
"""
Find the line of code generated by the model using the block in the version code
"""
"""Find the line of code generated by the model using the block in the version code"""
import json
import os

4
evaluation/benchmarks/versicode/output_processing/clear_ans.py
View File

@ -1,6 +1,4 @@
"""
Clear the<start>and<end>generated by the model in inference
"""
"""Clear the<start>and<end>generated by the model in inference"""
import json

3
evaluation/utils/shared.py
View File

@ -622,8 +622,7 @@ def compatibility_for_eval_history_pairs(
def is_fatal_evaluation_error(error: str | None) -> bool:
"""
The AgentController class overrides last error for certain exceptions
"""The AgentController class overrides last error for certain exceptions
We want to ensure those exeption do not overlap with fatal exceptions defined here
This is because we do a comparisino against the stringified error
"""

3
openhands/agenthub/codeact_agent/tools/prompt.py
View File

@ -3,8 +3,7 @@ import sys
def refine_prompt(prompt: str):
"""
Refines the prompt based on the platform.
"""Refines the prompt based on the platform.
On Windows systems, replaces 'bash' with 'powershell' and 'execute_bash' with 'execute_powershell'
to ensure commands work correctly on the Windows platform.

4
openhands/agenthub/readonly_agent/readonly_agent.py
View File

@ -1,6 +1,4 @@
"""
ReadOnlyAgent - A specialized version of CodeActAgent that only uses read-only tools.
"""
"""ReadOnlyAgent - A specialized version of CodeActAgent that only uses read-only tools."""
import os
from typing import TYPE_CHECKING

1
openhands/cli/suppress_warnings.py
View File

@ -5,7 +5,6 @@ import warnings
def suppress_cli_warnings():
"""Suppress common warnings that appear during CLI usage."""
# Suppress pydub warning about ffmpeg/avconv
warnings.filterwarnings(
'ignore',

9
openhands/cli/tui.py
View File

@ -239,8 +239,7 @@ def display_mcp_errors() -> None:
# Prompt output display functions
def display_thought_if_new(thought: str, is_agent_message: bool = False) -> None:
"""
Display a thought only if it hasn't been displayed recently.
"""Display a thought only if it hasn't been displayed recently.
Args:
thought: The thought to display
@ -301,8 +300,7 @@ def display_event(event: Event, config: OpenHandsConfig) -> None:
def display_message(message: str, is_agent_message: bool = False) -> None:
"""
Display a message in the terminal with markdown rendering.
"""Display a message in the terminal with markdown rendering.
Args:
message: The message to display
@ -338,8 +336,7 @@ def display_message(message: str, is_agent_message: bool = False) -> None:
def convert_markdown_to_html(text: str) -> str:
"""
Convert markdown to HTML for prompt_toolkit's HTML renderer using the markdown library.
"""Convert markdown to HTML for prompt_toolkit's HTML renderer using the markdown library.
Args:
text: Markdown text to convert

18
openhands/cli/vscode_extension.py
View File

@ -56,8 +56,7 @@ def download_latest_vsix_from_github() -> str | None:
def attempt_vscode_extension_install():
"""
Checks if running in a supported editor and attempts to install the OpenHands companion extension.
"""Checks if running in a supported editor and attempts to install the OpenHands companion extension.
This is a best-effort, one-time attempt.
"""
# 1. Check if we are in a supported editor environment
@ -132,8 +131,7 @@ def attempt_vscode_extension_install():
def _mark_installation_successful(flag_file: pathlib.Path, editor_name: str) -> None:
"""
Mark the extension installation as successful by creating the flag file.
"""Mark the extension installation as successful by creating the flag file.
Args:
flag_file: Path to the flag file to create
@ -147,8 +145,7 @@ def _mark_installation_successful(flag_file: pathlib.Path, editor_name: str) ->
def _is_extension_installed(editor_command: str, extension_id: str) -> bool:
"""
Check if the OpenHands extension is already installed.
"""Check if the OpenHands extension is already installed.
Args:
editor_command: The command to run the editor (e.g., 'code', 'windsurf')
@ -174,8 +171,7 @@ def _is_extension_installed(editor_command: str, extension_id: str) -> bool:
def _attempt_github_install(editor_command: str, editor_name: str) -> bool:
"""
Attempt to install the extension from GitHub Releases.
"""Attempt to install the extension from GitHub Releases.
Downloads the latest VSIX file from GitHub releases and attempts to install it.
Ensures proper cleanup of temporary files.
@ -227,8 +223,7 @@ def _attempt_github_install(editor_command: str, editor_name: str) -> bool:
def _attempt_bundled_install(editor_command: str, editor_name: str) -> bool:
"""
Attempt to install the extension from the bundled VSIX file.
"""Attempt to install the extension from the bundled VSIX file.
Uses the VSIX file packaged with the OpenHands installation.
@ -280,8 +275,7 @@ def _attempt_bundled_install(editor_command: str, editor_name: str) -> bool:
def _attempt_marketplace_install(
editor_command: str, editor_name: str, extension_id: str
) -> bool:
"""
Attempt to install the extension from the marketplace.
"""Attempt to install the extension from the marketplace.
This method is currently unused as the OpenHands extension is not yet published
to the VS Code/Windsurf marketplace. It's kept here for future use when the

3
openhands/controller/agent.py
View File

@ -55,8 +55,7 @@ class Agent(ABC):
return self._prompt_manager
def get_system_message(self) -> 'SystemMessageAction | None':
"""
Returns a SystemMessageAction containing the system message and tools.
"""Returns a SystemMessageAction containing the system message and tools.
This will be added to the event stream as the first message.
Returns:

1
openhands/controller/agent_controller.py
View File

@ -142,7 +142,6 @@ class AgentController:
status_callback: Optional callback function to handle status updates.
replay_events: A list of logs to replay.
"""
self.id = sid or event_stream.sid
self.user_id = user_id
self.file_store = file_store

3
openhands/controller/replay.py
View File

@ -57,8 +57,7 @@ class ReplayManager:
)
def should_replay(self) -> bool:
"""
Whether the controller is in trajectory replay mode, and the replay
"""Whether the controller is in trajectory replay mode, and the replay
hasn't finished. Note: after the replay is finished, the user and
the agent could continue to message/act.

8
openhands/controller/state/state.py
View File

@ -46,8 +46,7 @@ class TrafficControlState(str, Enum):
@dataclass
class State:
"""
Represents the running state of an agent in the OpenHands system, saving data of its operation and memory.
"""Represents the running state of an agent in the OpenHands system, saving data of its operation and memory.
- Multi-agent/delegate state:
- store the task (conversation between the agent and the user)
@ -143,10 +142,7 @@ class State:
def restore_from_session(
sid: str, file_store: FileStore, user_id: str | None = None
) -> 'State':
"""
Restores the state from the previously saved session.
"""
"""Restores the state from the previously saved session."""
state: State
try:
encoded = file_store.read(

18
openhands/controller/state/state_tracker.py
View File

@ -242,41 +242,33 @@ class StateTracker:
self.state.budget_flag.increase_limit(headless_mode)
def get_metrics_snapshot(self):
"""
Deep copy of metrics
"""Deep copy of metrics
This serves as a snapshot for the parent's metrics at the time a delegate is created
It will be stored and used to compute local metrics for the delegate
(since delegates now accumulate metrics from where its parent left off)
"""
return self.state.metrics.copy()
def save_state(self):
"""
Save's current state to persistent store
"""
"""Save's current state to persistent store"""
if self.sid and self.file_store:
self.state.save_to_session(self.sid, self.file_store, self.user_id)
def run_control_flags(self):
"""
Performs one step of the control flags
"""
"""Performs one step of the control flags"""
self.state.iteration_flag.step()
if self.state.budget_flag:
self.state.budget_flag.step()
def sync_budget_flag_with_metrics(self):
"""
Ensures that budget flag is up to date with accumulated costs from llm completions
"""Ensures that budget flag is up to date with accumulated costs from llm completions
Budget flag will monitor for when budget is exceeded
"""
if self.state.budget_flag:
self.state.budget_flag.current_value = self.state.metrics.accumulated_cost
def merge_metrics(self, metrics: Metrics):
"""
Merges metrics with the state metrics
"""Merges metrics with the state metrics
NOTE: this should be refactored in the future. We should have services (draft llm, title autocomplete, condenser, etc)
use their own LLMs, but the metrics object should be shared. This way we have one source of truth for accumulated costs from

3
openhands/core/config/kubernetes_config.py
View File

@ -66,8 +66,7 @@ class KubernetesConfig(BaseModel):
@classmethod
def from_toml_section(cls, data: dict) -> dict[str, 'KubernetesConfig']:
"""
Create a mapping of KubernetesConfig instances from a toml dictionary representing the [kubernetes] section.
"""Create a mapping of KubernetesConfig instances from a toml dictionary representing the [kubernetes] section.
The configuration is built from all keys in data.

4
openhands/core/config/llm_config.py
View File

@ -97,8 +97,7 @@ class LLMConfig(BaseModel):
@classmethod
def from_toml_section(cls, data: dict) -> dict[str, LLMConfig]:
"""
Create a mapping of LLMConfig instances from a toml dictionary representing the [llm] section.
"""Create a mapping of LLMConfig instances from a toml dictionary representing the [llm] section.
The default configuration is built from all non-dict keys in data.
Then, each key with a dict value (e.g. [llm.random_name]) is treated as a custom LLM configuration,
@ -117,7 +116,6 @@ class LLMConfig(BaseModel):
dict[str, LLMConfig]: A mapping where the key "llm" corresponds to the default configuration
and additional keys represent custom configurations.
"""
# Initialize the result mapping
llm_mapping: dict[str, LLMConfig] = {}

1
openhands/core/config/mcp_config.py
View File

@ -345,7 +345,6 @@ class OpenHandsMCPConfig:
Returns:
tuple[MCPSHTTPServerConfig | None, list[MCPStdioServerConfig]]: A tuple containing the default SHTTP server configuration (or None) and a list of MCP stdio server configurations
"""
stdio_servers = []
search_engine_stdio_server = OpenHandsMCPConfig.add_search_engine(config)
if search_engine_stdio_server:

3
openhands/core/config/sandbox_config.py
View File

@ -93,8 +93,7 @@ class SandboxConfig(BaseModel):
@classmethod
def from_toml_section(cls, data: dict) -> dict[str, 'SandboxConfig']:
"""
Create a mapping of SandboxConfig instances from a toml dictionary representing the [sandbox] section.
"""Create a mapping of SandboxConfig instances from a toml dictionary representing the [sandbox] section.
The configuration is built from all keys in data.

4
openhands/core/config/security_config.py
View File

@ -16,15 +16,13 @@ class SecurityConfig(BaseModel):
@classmethod
def from_toml_section(cls, data: dict) -> dict[str, 'SecurityConfig']:
"""
Create a mapping of SecurityConfig instances from a toml dictionary representing the [security] section.
"""Create a mapping of SecurityConfig instances from a toml dictionary representing the [security] section.
The configuration is built from all keys in data.
Returns:
dict[str, SecurityConfig]: A mapping where the key "security" corresponds to the [security] configuration
"""
# Initialize the result mapping
security_mapping: dict[str, SecurityConfig] = {}

8
openhands/core/logger.py
View File

@ -322,10 +322,7 @@ def json_log_handler(
level: int = logging.INFO,
_out: TextIO = sys.stdout,
) -> logging.Handler:
"""
Configure logger instance for structured logging as json lines.
"""
"""Configure logger instance for structured logging as json lines."""
handler = logging.StreamHandler(_out)
handler.setLevel(level)
handler.setFormatter(json_formatter())
@ -496,8 +493,7 @@ class OpenHandsLoggerAdapter(logging.LoggerAdapter):
def process(
self, msg: str, kwargs: MutableMapping[str, Any]
) -> tuple[str, MutableMapping[str, Any]]:
"""
If 'extra' is supplied in kwargs, merge it with the adapters 'extra' dict
"""If 'extra' is supplied in kwargs, merge it with the adapters 'extra' dict
Starting in Python 3.13, LoggerAdapter's merge_extra option will do this.
"""
if 'extra' in kwargs and isinstance(kwargs['extra'], dict):

3
openhands/core/loop.py
View File

@ -14,8 +14,7 @@ async def run_agent_until_done(
memory: Memory,
end_states: list[AgentState],
) -> None:
"""
run_agent_until_done takes a controller and a runtime, and will run
"""run_agent_until_done takes a controller and a runtime, and will run
the agent until it reaches a terminal state.
Note that runtime must be connected before being passed in here.
"""

3
openhands/core/main.py
View File

@ -257,8 +257,7 @@ def auto_continue_response(
def load_replay_log(trajectory_path: str) -> tuple[list[Event] | None, Action]:
"""
Load trajectory from given path, serialize it to a list of events, and return
"""Load trajectory from given path, serialize it to a list of events, and return
two things:
1) A list of events except the first action
2) First action (user message, a.k.a. initial task)

6
openhands/core/message_utils.py
View File

@ -3,8 +3,7 @@ from openhands.llm.metrics import Metrics, TokenUsage
def get_token_usage_for_event(event: Event, metrics: Metrics) -> TokenUsage | None:
"""
Returns at most one token usage record for either:
"""Returns at most one token usage record for either:
- `tool_call_metadata.model_response.id`, if possible
- otherwise event.response_id, if set
@ -34,8 +33,7 @@ def get_token_usage_for_event(event: Event, metrics: Metrics) -> TokenUsage | No
def get_token_usage_for_event_id(
events: list[Event], event_id: int, metrics: Metrics
) -> TokenUsage | None:
"""
Starting from the event with .id == event_id and moving backwards in `events`,
"""Starting from the event with .id == event_id and moving backwards in `events`,
find the first TokenUsage record (if any) associated either with:
- tool_call_metadata.model_response.id, or
- event.response_id

6
openhands/core/setup.py
View File

@ -94,8 +94,7 @@ def create_runtime(
def get_provider_tokens():
"""
Retrieve provider tokens from environment variables and return them as a dictionary.
"""Retrieve provider tokens from environment variables and return them as a dictionary.
Returns:
A dictionary mapping ProviderType to ProviderToken if tokens are found, otherwise None.
@ -126,8 +125,7 @@ def initialize_repository_for_runtime(
immutable_provider_tokens: PROVIDER_TOKEN_TYPE | None = None,
selected_repository: str | None = None,
) -> str | None:
"""
Initialize the repository for the runtime by cloning or initializing it,
"""Initialize the repository for the runtime by cloning or initializing it,
running setup scripts, and setting up git hooks if present.
Args:

12
openhands/critic/base.py
View File

@ -6,25 +6,19 @@ from openhands.events import Event
class CriticResult(BaseModel):
"""
A critic result is a score and a message.
"""
"""A critic result is a score and a message."""
score: float
message: str
@property
def success(self) -> bool:
"""
Whether the agent is successful.
"""
"""Whether the agent is successful."""
return self.score >= 0.5
class BaseCritic(abc.ABC):
"""
A critic is a function that takes in a list of events, optional git patch, and returns a score about the quality of those events.
"""
"""A critic is a function that takes in a list of events, optional git patch, and returns a score about the quality of those events."""
@abc.abstractmethod
def evaluate(

3
openhands/events/action/message.py
View File

@ -42,8 +42,7 @@ class MessageAction(Action):
@dataclass
class SystemMessageAction(Action):
"""
Action that represents a system message for an agent, including the system prompt
"""Action that represents a system message for an agent, including the system prompt
and available tools. This should be the first message in the event stream.
"""

8
openhands/events/event_store.py
View File

@ -42,9 +42,7 @@ _DUMMY_PAGE = _CachePage(None, 1, -1)
@dataclass
class EventStore(EventStoreABC):
"""
A stored list of events backing a conversation
"""
"""A stored list of events backing a conversation"""
sid: str
file_store: FileStore
@ -92,8 +90,7 @@ class EventStore(EventStoreABC):
filter: EventFilter | None = None,
limit: int | None = None,
) -> Iterable[Event]:
"""
Retrieve events from the event stream, optionally filtering out events of a given type
"""Retrieve events from the event stream, optionally filtering out events of a given type
and events marked as hidden.
Args:
@ -105,7 +102,6 @@ class EventStore(EventStoreABC):
Yields:
Events from the stream that match the criteria.
"""
if end_id is None:
end_id = self.cur_id
else:

7
openhands/events/event_store_abc.py
View File

@ -9,9 +9,7 @@ from openhands.events.event_filter import EventFilter
class EventStoreABC:
"""
A stored list of events backing a conversation
"""
"""A stored list of events backing a conversation"""
sid: str
user_id: str | None
@ -25,8 +23,7 @@ class EventStoreABC:
filter: EventFilter | None = None,
limit: int | None = None,
) -> Iterable[Event]:
"""
Retrieve events from the event stream, optionally excluding events using a filter
"""Retrieve events from the event stream, optionally excluding events using a filter
Args:
start_id: The ID of the first event to retrieve. Defaults to 0.

4
openhands/events/nested_event_store.py
View File

@ -13,9 +13,7 @@ from openhands.events.serialization.event import event_from_dict
@dataclass
class NestedEventStore(EventStoreABC):
"""
A stored list of events backing a conversation
"""
"""A stored list of events backing a conversation"""
base_url: str
sid: str

3
openhands/events/observation/agent.py
View File

@ -46,8 +46,7 @@ class AgentThinkObservation(Observation):
@dataclass
class MicroagentKnowledge:
"""
Represents knowledge from a triggered microagent.
"""Represents knowledge from a triggered microagent.
Attributes:
name: The name of the microagent that was triggered

1
openhands/events/observation/commands.py
View File

@ -146,7 +146,6 @@ class CmdOutputObservation(Observation):
Returns:
Original content if not too large, or truncated content otherwise
"""
if len(content) <= max_size:
return content

3
openhands/events/utils.py
View File

@ -12,7 +12,8 @@ from openhands.events.observation import (
def get_pairs_from_events(events: list[Event]) -> list[tuple[Action, Observation]]:
"""Return the history as a list of tuples (action, observation).
This function is a compatibility function for evals reading and visualization working with old histories."""
This function is a compatibility function for evals reading and visualization working with old histories.
"""
tuples: list[tuple[Action, Observation]] = []
action_map: dict[int, Action] = {}
observation_map: dict[int, Observation] = {}

7
openhands/integrations/bitbucket/bitbucket_service.py
View File

@ -191,8 +191,7 @@ class BitBucketService(BaseGitService, GitService, InstallationsService):
def _parse_repository(
self, repo: dict, link_header: str | None = None
) -> Repository:
"""
Parse a Bitbucket API repository response into a Repository object.
"""Parse a Bitbucket API repository response into a Repository object.
Args:
repo: Repository data from Bitbucket API
@ -201,7 +200,6 @@ class BitBucketService(BaseGitService, GitService, InstallationsService):
Returns:
Repository object
"""
repo_id = repo.get('uuid', '')
workspace_slug = repo.get('workspace', {}).get('slug', '')
@ -292,8 +290,7 @@ class BitBucketService(BaseGitService, GitService, InstallationsService):
async def _fetch_paginated_data(
self, url: str, params: dict, max_items: int
) -> list[dict]:
"""
Fetch data with pagination support for Bitbucket API.
"""Fetch data with pagination support for Bitbucket API.
Args:
url: The API endpoint URL

10
openhands/integrations/github/github_service.py
View File

@ -186,8 +186,7 @@ class GitHubService(BaseGitService, GitService, InstallationsService):
async def _fetch_paginated_repos(
self, url: str, params: dict, max_repos: int, extract_key: str | None = None
) -> list[dict]:
"""
Fetch repositories with pagination support.
"""Fetch repositories with pagination support.
Args:
url: The API endpoint URL
@ -228,8 +227,7 @@ class GitHubService(BaseGitService, GitService, InstallationsService):
def _parse_repository(
self, repo: dict, link_header: str | None = None
) -> Repository:
"""
Parse a GitHub API repository response into a Repository object.
"""Parse a GitHub API repository response into a Repository object.
Args:
repo: Repository data from GitHub API
@ -550,8 +548,7 @@ class GitHubService(BaseGitService, GitService, InstallationsService):
draft: bool = True,
labels: list[str] | None = None,
) -> str:
"""
Creates a PR using user credentials
"""Creates a PR using user credentials
Args:
repo_name: The full name of the repository (owner/repo)
@ -566,7 +563,6 @@ class GitHubService(BaseGitService, GitService, InstallationsService):
- PR URL when successful
- Error message when unsuccessful
"""
url = f'{self.BASE_URL}/repos/{repo_name}/pulls'
# Set default body if none provided

17
openhands/integrations/gitlab/gitlab_service.py
View File

@ -71,9 +71,7 @@ class GitLabService(BaseGitService, GitService):
return ProviderType.GITLAB.value
async def _get_gitlab_headers(self) -> dict[str, Any]:
"""
Retrieve the GitLab Token to construct the headers
"""
"""Retrieve the GitLab Token to construct the headers"""
if not self.token:
latest_token = await self.get_latest_token()
if latest_token:
@ -173,8 +171,7 @@ class GitLabService(BaseGitService, GitService):
async def execute_graphql_query(
self, query: str, variables: dict[str, Any] | None = None
) -> Any:
"""
Execute a GraphQL query against the GitLab GraphQL API
"""Execute a GraphQL query against the GitLab GraphQL API
Args:
query: The GraphQL query string
@ -244,8 +241,7 @@ class GitLabService(BaseGitService, GitService):
def _parse_repository(
self, repo: dict, link_header: str | None = None
) -> Repository:
"""
Parse a GitLab API project response into a Repository object.
"""Parse a GitLab API project response into a Repository object.
Args:
repo: Project data from GitLab API
@ -269,8 +265,7 @@ class GitLabService(BaseGitService, GitService):
)
def _parse_gitlab_url(self, url: str) -> str | None:
"""
Parse a GitLab URL to extract the repository path.
"""Parse a GitLab URL to extract the repository path.
Expected format: https://{domain}/{group}/{possibly_subgroup}/{repo}
Returns the full path from group onwards (e.g., 'group/subgroup/repo' or 'group/repo')
@ -588,8 +583,7 @@ class GitLabService(BaseGitService, GitService):
description: str | None = None,
labels: list[str] | None = None,
) -> str:
"""
Creates a merge request in GitLab
"""Creates a merge request in GitLab
Args:
id: The ID or URL-encoded path of the project
@ -603,7 +597,6 @@ class GitLabService(BaseGitService, GitService):
- MR URL when successful
- Error message when unsuccessful
"""
# Convert string ID to URL-encoded path if needed
project_id = str(id).replace('/', '%2F') if isinstance(id, str) else id
url = f'{self.BASE_URL}/projects/{project_id}/merge_requests'

30
openhands/integrations/provider.py
View File

@ -191,10 +191,7 @@ class ProviderHandler:
per_page: int | None,
installation_id: str | None,
) -> list[Repository]:
"""
Get repositories from providers
"""
"""Get repositories from providers"""
"""
Get repositories from providers
"""
@ -226,9 +223,7 @@ class ProviderHandler:
return all_repos
async def get_suggested_tasks(self) -> list[SuggestedTask]:
"""
Get suggested tasks from providers
"""
"""Get suggested tasks from providers"""
tasks: list[SuggestedTask] = []
for provider in self.provider_tokens:
try:
@ -303,8 +298,7 @@ class ProviderHandler:
event_stream: EventStream,
env_vars: dict[ProviderType, SecretStr] | None = None,
) -> None:
"""
This ensures that the latest provider tokens are masked from the event stream
"""This ensures that the latest provider tokens are masked from the event stream
It is called when the provider tokens are first initialized in the runtime or when tokens are re-exported with the latest working ones
Args:
@ -320,8 +314,7 @@ class ProviderHandler:
def expose_env_vars(
self, env_secrets: dict[ProviderType, SecretStr]
) -> dict[str, str]:
"""
Return string values instead of typed values for environment secrets
"""Return string values instead of typed values for environment secrets
Called just before exporting secrets to runtime, or setting secrets in the event stream
"""
exposed_envs = {}
@ -353,8 +346,7 @@ class ProviderHandler:
providers: list[ProviderType] | None = None,
get_latest: bool = False,
) -> dict[ProviderType, SecretStr] | dict[str, str]:
"""
Retrieves the provider tokens from ProviderHandler object
"""Retrieves the provider tokens from ProviderHandler object
This is used when initializing/exporting new provider tokens in the runtime
Args:
@ -362,7 +354,6 @@ class ProviderHandler:
providers: Return provider tokens for the list passed in, otherwise return all available providers
get_latest: Get the latest working token for the providers if True, otherwise get the existing ones
"""
if not self.provider_tokens:
return {}
@ -393,11 +384,9 @@ class ProviderHandler:
def check_cmd_action_for_provider_token_ref(
cls, event: Action
) -> list[ProviderType]:
"""
Detect if agent run action is using a provider token (e.g $GITHUB_TOKEN)
"""Detect if agent run action is using a provider token (e.g $GITHUB_TOKEN)
Returns a list of providers which are called by the agent
"""
if not isinstance(event, CmdRunAction):
return []
@ -410,9 +399,7 @@ class ProviderHandler:
@classmethod
def get_provider_env_key(cls, provider: ProviderType) -> str:
"""
Map ProviderType value to the environment variable name in the runtime
"""
"""Map ProviderType value to the environment variable name in the runtime"""
return f'{provider.value}_token'.lower()
async def verify_repo_provider(
@ -443,8 +430,7 @@ class ProviderHandler:
async def get_branches(
self, repository: str, specified_provider: ProviderType | None = None
) -> list[Branch]:
"""
Get branches for a repository
"""Get branches for a repository
Args:
repository: The repository name

3
openhands/integrations/utils.py
View File

@ -10,8 +10,7 @@ from openhands.integrations.provider import ProviderType
async def validate_provider_token(
token: SecretStr, base_domain: str | None = None
) -> ProviderType | None:
"""
Determine whether a token is for GitHub, GitLab, or Bitbucket by attempting to get user info
"""Determine whether a token is for GitHub, GitLab, or Bitbucket by attempting to get user info
from the services.
Args:

5
openhands/io/io.py
View File

@ -24,10 +24,7 @@ def read_task_from_file(file_path: str) -> str:
def read_task(args: argparse.Namespace, cli_multiline_input: bool) -> str:
"""
Read the task from the CLI args, file, or stdin.
"""
"""Read the task from the CLI args, file, or stdin."""
# Determine the task
task_str = ''
if args.file:

1
openhands/llm/llm.py
View File

@ -703,6 +703,7 @@ class LLM(RetryMixin, DebugMixin):
Args:
messages (list): A list of messages, either as a list of dicts or as a list of Message objects.
Returns:
int: The number of tokens.
"""

1
openhands/llm/metrics.py
View File

@ -150,7 +150,6 @@ class Metrics:
response_id: str,
) -> None:
"""Add a single usage record."""
# Token each turn for calculating context usage.
per_turn_token = prompt_tokens + completion_tokens

3
openhands/llm/retry_mixin.py
View File

@ -16,8 +16,7 @@ class RetryMixin:
"""Mixin class for retry logic."""
def retry_decorator(self, **kwargs: Any) -> Callable:
"""
Create a LLM retry decorator with customizable parameters. This is used for 429 errors, and a few other exceptions in LLM classes.
"""Create a LLM retry decorator with customizable parameters. This is used for 429 errors, and a few other exceptions in LLM classes.
Args:
**kwargs: Keyword arguments to override default retry behavior.

4
openhands/mcp/client.py
View File

@ -21,9 +21,7 @@ from openhands.mcp.tool import MCPClientTool
class MCPClient(BaseModel):
"""
A collection of tools that connects to an MCP server and manages available tools through the Model Context Protocol.
"""
"""A collection of tools that connects to an MCP server and manages available tools through the Model Context Protocol."""
model_config = ConfigDict(arbitrary_types_allowed=True)

3
openhands/mcp/tool.py
View File

@ -3,8 +3,7 @@ from pydantic import ConfigDict
class MCPClientTool(Tool):
"""
Represents a tool proxy that can be called on the MCP server from the client side.
"""Represents a tool proxy that can be called on the MCP server from the client side.
This version doesn't store a session reference, as sessions are created on-demand
by the MCPClient for each operation.

13
openhands/mcp/utils.py
View File

@ -26,8 +26,7 @@ from openhands.runtime.impl.cli.cli_runtime import CLIRuntime
def convert_mcp_clients_to_tools(mcp_clients: list[MCPClient] | None) -> list[dict]:
"""
Converts a list of MCPClient instances to ChatCompletionToolParam format
"""Converts a list of MCPClient instances to ChatCompletionToolParam format
that can be used by CodeActAgent.
Args:
@ -152,8 +151,7 @@ async def create_mcp_clients(
async def fetch_mcp_tools_from_config(
mcp_config: MCPConfig, conversation_id: str | None = None, use_stdio: bool = False
) -> list[dict]:
"""
Retrieves the list of MCP tools from the MCP clients.
"""Retrieves the list of MCP tools from the MCP clients.
Args:
mcp_config: The MCP configuration
@ -206,8 +204,7 @@ async def fetch_mcp_tools_from_config(
async def call_tool_mcp(mcp_clients: list[MCPClient], action: MCPAction) -> Observation:
"""
Call a tool on an MCP server and return the observation.
"""Call a tool on an MCP server and return the observation.
Args:
mcp_clients: The list of MCP clients to execute the action on
@ -270,9 +267,7 @@ async def call_tool_mcp(mcp_clients: list[MCPClient], action: MCPAction) -> Obse
async def add_mcp_tools_to_agent(
agent: 'Agent', runtime: Runtime, memory: 'Memory'
) -> MCPConfig:
"""
Add MCP tools to an agent.
"""
"""Add MCP tools to an agent."""
import sys
# Skip MCP tools on Windows

1
openhands/memory/conversation_memory.py
View File

@ -87,7 +87,6 @@ class ConversationMemory:
vision_is_active: Whether vision is active in the LLM. If True, image URLs will be included.
initial_user_action: The initial user message action, if available. Used to ensure the conversation starts correctly.
"""
events = condensed_history
# Ensure the event list starts with SystemMessageAction, then MessageAction(source='user')

21
openhands/memory/memory.py
View File

@ -39,8 +39,7 @@ USER_MICROAGENTS_DIR = Path.home() / '.openhands' / 'microagents'
class Memory:
"""
Memory is a component that listens to the EventStream for information retrieval actions
"""Memory is a component that listens to the EventStream for information retrieval actions
(a RecallAction) and publishes observations with the content (such as RecallObservation).
"""
@ -145,7 +144,6 @@ class Memory:
This method collects information from all available repo microagents and concatenates their contents.
Multiple repo microagents are supported, and their contents will be concatenated with newlines between them.
"""
# Create WORKSPACE_CONTEXT info:
# - repository_info
# - runtime_info
@ -211,7 +209,6 @@ class Memory:
event: RecallAction,
) -> RecallObservation | None:
"""When a microagent action triggers microagents, create a RecallObservation with structured data."""
# Find any matched microagents based on the query
microagent_knowledge = self._find_microagent_knowledge(event.query)
@ -257,8 +254,7 @@ class Memory:
def load_user_workspace_microagents(
self, user_microagents: list[BaseMicroagent]
) -> None:
"""
This method loads microagents from a user's cloned repo or workspace directory.
"""This method loads microagents from a user's cloned repo or workspace directory.
This is typically called from agent_session or setup once the workspace is cloned.
"""
@ -272,9 +268,7 @@ class Memory:
self.repo_microagents[user_microagent.name] = user_microagent
def _load_global_microagents(self) -> None:
"""
Loads microagents from the global microagents_dir
"""
"""Loads microagents from the global microagents_dir"""
repo_agents, knowledge_agents = load_microagents_from_dir(
GLOBAL_MICROAGENTS_DIR
)
@ -284,8 +278,7 @@ class Memory:
self.repo_microagents[name] = agent_repo
def _load_user_microagents(self) -> None:
"""
Loads microagents from the user's home directory (~/.openhands/microagents/)
"""Loads microagents from the user's home directory (~/.openhands/microagents/)
Creates the directory if it doesn't exist.
"""
try:
@ -307,8 +300,7 @@ class Memory:
)
def get_microagent_mcp_tools(self) -> list[MCPConfig]:
"""
Get MCP tools from all repo microagents (always active)
"""Get MCP tools from all repo microagents (always active)
Returns:
A list of MCP tools configurations from microagents
@ -365,8 +357,7 @@ class Memory:
def set_conversation_instructions(
self, conversation_instructions: str | None
) -> None:
"""
Set contextual information for conversation
"""Set contextual information for conversation
This is information the agent may require
"""
self.conversation_instructions = ConversationInstructions(

1
openhands/resolver/interfaces/github.py
View File

@ -92,7 +92,6 @@ class GithubIssueHandler(IssueHandlerInterface):
Returns:
List of Github issues.
"""
if not issue_numbers:
raise ValueError('Unspecified issue number')

1
openhands/resolver/interfaces/gitlab.py
View File

@ -86,7 +86,6 @@ class GitlabIssueHandler(IssueHandlerInterface):
Returns:
List of Gitlab issues.
"""
if not issue_numbers:
raise ValueError('Unspecified issue number')

2
openhands/resolver/issue_resolver.py
View File

@ -70,7 +70,6 @@ class IssueResolver:
comment_id: Optional ID of a specific comment to focus on.
base_domain: The base domain for the git server.
"""
parts = args.selected_repo.rsplit('/', 1)
if len(parts) < 2:
raise ValueError('Invalid repository format. Expected owner/repo')
@ -540,7 +539,6 @@ class IssueResolver:
Args:
reset_logger: Whether to reset the logger for multiprocessing.
"""
issue = self.extract_issue()
if self.comment_id is not None:

3
openhands/resolver/utils.py
View File

@ -16,8 +16,7 @@ from openhands.integrations.utils import validate_provider_token
async def identify_token(token: str, base_domain: str | None) -> ProviderType:
"""
Identifies whether a token belongs to GitHub, GitLab, or Bitbucket.
"""Identifies whether a token belongs to GitHub, GitLab, or Bitbucket.
Parameters:
token (str): The personal access token to check.
base_domain (str): Custom base domain for provider (e.g GitHub Enterprise)

3
openhands/runtime/__init__.py
View File

@ -88,8 +88,7 @@ _ALL_RUNTIME_CLASSES = {**_DEFAULT_RUNTIME_CLASSES, **_THIRD_PARTY_RUNTIME_CLASS
def get_runtime_cls(name: str) -> type[Runtime]:
"""
If name is one of the predefined runtime names (e.g. 'docker'), return its class.
"""If name is one of the predefined runtime names (e.g. 'docker'), return its class.
Otherwise attempt to resolve name as subclass of Runtime and return it.
Raise on invalid selections.
"""

3
openhands/runtime/action_execution_server.py
View File

@ -1,5 +1,4 @@
"""
This is the main file for the runtime client.
"""This is the main file for the runtime client.
It is responsible for executing actions received from OpenHands backend and producing observations.
NOTE: this will be executed inside the docker sandbox.

18
openhands/runtime/base.py
View File

@ -196,8 +196,7 @@ class Runtime(FileEditRuntimeMixin):
self.add_env_vars(self.config.sandbox.runtime_startup_env_vars)
def close(self) -> None:
"""
This should only be called by conversation manager or closing the session.
"""This should only be called by conversation manager or closing the session.
If called for instance by error handling, it could prevent recovery.
"""
pass
@ -300,9 +299,7 @@ class Runtime(FileEditRuntimeMixin):
asyncio.get_event_loop().run_until_complete(self._handle_action(event))
async def _export_latest_git_provider_tokens(self, event: Action) -> None:
"""
Refresh runtime provider tokens when agent attemps to run action with provider token
"""
"""Refresh runtime provider tokens when agent attemps to run action with provider token"""
if not self.user_id:
return
@ -1001,9 +998,7 @@ fi
def _execute_shell_fn_git_handler(
self, command: str, cwd: str | None
) -> CommandResult:
"""
This function is used by the GitHandler to execute shell commands.
"""
"""This function is used by the GitHandler to execute shell commands."""
obs = self.run(CmdRunAction(command=command, is_static=True, cwd=cwd))
exit_code = 0
content = ''
@ -1019,9 +1014,7 @@ fi
return CommandResult(content=content, exit_code=exit_code)
def _create_file_fn_git_handler(self, path: str, content: str) -> int:
"""
This function is used by the GitHandler to execute shell commands.
"""
"""This function is used by the GitHandler to execute shell commands."""
obs = self.write(FileWriteAction(path=path, content=content))
if isinstance(obs, ErrorObservation):
return -1
@ -1043,8 +1036,7 @@ fi
def subscribe_to_shell_stream(
self, callback: Callable[[str], None] | None = None
) -> bool:
"""
Subscribe to shell command output stream.
"""Subscribe to shell command output stream.
This method is meant to be overridden by runtime implementations
that want to stream shell command output to external consumers.

4
openhands/runtime/file_viewer_server.py
View File

@ -1,5 +1,4 @@
"""
A tiny, isolated server that provides only the /view endpoint from the action execution server.
"""A tiny, isolated server that provides only the /view endpoint from the action execution server.
This server has no authentication and only listens to localhost traffic.
"""
@ -83,7 +82,6 @@ def start_file_viewer_server(port: int) -> tuple[str, threading.Thread]:
Returns:
Tuple[str, threading.Thread]: The server URL and the thread object.
"""
# Save the server URL to a file
server_url = f'http://localhost:{port}'
port_path = '/tmp/oh-server-url'

4
openhands/runtime/impl/__init__.py
View File

@ -1,6 +1,4 @@
"""
Runtime implementations for OpenHands.
"""
"""Runtime implementations for OpenHands."""
from openhands.runtime.impl.action_execution.action_execution_client import (
ActionExecutionClient,

1
openhands/runtime/impl/action_execution/action_execution_client.py
View File

@ -138,7 +138,6 @@ class ActionExecutionClient(Runtime):
If path is None, list files in the sandbox's initial working directory (e.g., /workspace).
"""
try:
data = {}
if path is not None:

4
openhands/runtime/impl/cli/__init__.py
View File

@ -1,6 +1,4 @@
"""
CLI Runtime implementation for OpenHands.
"""
"""CLI Runtime implementation for OpenHands."""
from openhands.runtime.impl.cli.cli_runtime import CLIRuntime

23
openhands/runtime/impl/cli/cli_runtime.py
View File

@ -1,5 +1,4 @@
"""
This runtime runs commands locally using subprocess and performs file operations using Python's standard library.
"""This runtime runs commands locally using subprocess and performs file operations using Python's standard library.
It does not implement browser functionality.
"""
@ -88,8 +87,7 @@ After installing .NET SDK, restart your terminal and try again.
class CLIRuntime(Runtime):
"""
A runtime implementation that runs commands locally using subprocess and performs
"""A runtime implementation that runs commands locally using subprocess and performs
file operations using Python's standard library. It does not implement browser functionality.
Args:
@ -191,8 +189,7 @@ class CLIRuntime(Runtime):
logger.info(f'CLIRuntime initialized with workspace at {self._workspace_path}')
def add_env_vars(self, env_vars: dict[str, Any]) -> None:
"""
Adds environment variables to the current runtime environment.
"""Adds environment variables to the current runtime environment.
For CLIRuntime, this means updating os.environ for the current process,
so that subsequent commands inherit these variables.
This overrides the BaseRuntime behavior which tries to run shell commands
@ -218,8 +215,7 @@ class CLIRuntime(Runtime):
# during initialization before self._runtime_initialized is True.
def _safe_terminate_process(self, process_obj, signal_to_send=signal.SIGTERM):
"""
Safely attempts to terminate/kill a process group or a single process.
"""Safely attempts to terminate/kill a process group or a single process.
Args:
process_obj: the subprocess.Popen object started with start_new_session=True
@ -292,8 +288,8 @@ class CLIRuntime(Runtime):
def _execute_powershell_command(
self, command: str, timeout: float
) -> CmdOutputObservation | ErrorObservation:
"""
Execute a command using PowerShell session on Windows.
"""Execute a command using PowerShell session on Windows.
Args:
command: The command to execute
timeout: Timeout in seconds for the command
@ -326,8 +322,8 @@ class CLIRuntime(Runtime):
def _execute_shell_command(
self, command: str, timeout: float
) -> CmdOutputObservation:
"""
Execute a shell command and stream its output to a callback function.
"""Execute a shell command and stream its output to a callback function.
Args:
command: The shell command to execute
timeout: Timeout in seconds for the command
@ -965,8 +961,7 @@ class CLIRuntime(Runtime):
def subscribe_to_shell_stream(
self, callback: Callable[[str], None] | None = None
) -> bool:
"""
Subscribe to shell command output stream.
"""Subscribe to shell command output stream.
Args:
callback: A function that will be called with each line of output from shell commands.

5
openhands/runtime/impl/kubernetes/kubernetes_runtime.py
View File

@ -58,8 +58,7 @@ POD_LABEL = 'openhands-runtime'
class KubernetesRuntime(ActionExecutionClient):
"""
A Kubernetes runtime for OpenHands that works with Kind.
"""A Kubernetes runtime for OpenHands that works with Kind.
This runtime creates pods in a Kubernetes cluster to run the agent code.
It uses the Kubernetes Python client to create and manage the pods.
@ -411,7 +410,6 @@ class KubernetesRuntime(ActionExecutionClient):
def _get_vscode_service_manifest(self):
"""Create a service manifest for the VSCode server."""
vscode_service_spec = V1ServiceSpec(
selector={'app': POD_LABEL, 'session': self.sid},
type='ClusterIP',
@ -567,7 +565,6 @@ class KubernetesRuntime(ActionExecutionClient):
def _get_vscode_ingress_manifest(self):
"""Create an ingress manifest for the VSCode server."""
tls = []
if self._k8s_config.ingress_tls_secret:
runtime_tls = V1IngressTLS(

4
openhands/runtime/mcp/proxy/__init__.py
View File

@ -1,6 +1,4 @@
"""
MCP Proxy module for OpenHands.
"""
"""MCP Proxy module for OpenHands."""
from openhands.runtime.mcp.proxy.manager import MCPProxyManager

19
openhands/runtime/mcp/proxy/manager.py
View File

@ -1,5 +1,4 @@
"""
MCP Proxy Manager for OpenHands.
"""MCP Proxy Manager for OpenHands.
This module provides a manager class for handling FastMCP proxy instances,
including initialization, configuration, and mounting to FastAPI applications.
@ -20,8 +19,7 @@ fastmcp_logger = fastmcp_get_logger('fastmcp')
class MCPProxyManager:
"""
Manager for FastMCP proxy instances.
"""Manager for FastMCP proxy instances.
This class encapsulates all the functionality related to creating, configuring,
and managing FastMCP proxy instances, including mounting them to FastAPI applications.
@ -33,8 +31,7 @@ class MCPProxyManager:
api_key: Optional[str] = None,
logger_level: Optional[int] = None,
):
"""
Initialize the MCP Proxy Manager.
"""Initialize the MCP Proxy Manager.
Args:
name: Name of the proxy server
@ -55,9 +52,7 @@ class MCPProxyManager:
fastmcp_logger.setLevel(logger_level)
def initialize(self) -> None:
"""
Initialize the FastMCP proxy with the current configuration.
"""
"""Initialize the FastMCP proxy with the current configuration."""
if len(self.config['mcpServers']) == 0:
logger.info(
'No MCP servers configured for FastMCP Proxy, skipping initialization.'
@ -76,8 +71,7 @@ class MCPProxyManager:
async def mount_to_app(
self, app: FastAPI, allow_origins: Optional[list[str]] = None
) -> None:
"""
Mount the SSE server app to a FastAPI application.
"""Mount the SSE server app to a FastAPI application.
Args:
app: FastAPI application to mount to
@ -128,8 +122,7 @@ class MCPProxyManager:
stdio_servers: list[MCPStdioServerConfig],
allow_origins: Optional[list[str]] = None,
) -> None:
"""
Update the tools configuration and remount the proxy to the app.
"""Update the tools configuration and remount the proxy to the app.
This is a convenience method that combines updating the tools,
shutting down the existing proxy, initializing a new one, and

3
openhands/runtime/plugins/vscode/__init__.py
View File

@ -95,8 +95,7 @@ class VSCodePlugin(Plugin):
)
def _setup_vscode_settings(self) -> None:
"""
Set up VSCode settings by creating the .vscode directory in the workspace
"""Set up VSCode settings by creating the .vscode directory in the workspace
and copying the settings.json file there.
"""
# Get the path to the settings.json file in the plugin directory

4
openhands/runtime/utils/bash.py
View File

@ -79,8 +79,7 @@ def split_bash_commands(commands: str) -> list[str]:
def escape_bash_special_chars(command: str) -> str:
r"""
Escapes characters that have different interpretations in bash vs python.
r"""Escapes characters that have different interpretations in bash vs python.
Specifically handles escape sequences like \;, \|, \&, etc.
"""
if command.strip() == '':
@ -446,6 +445,7 @@ class BashSession:
ps1_matches: List of regex matches for PS1 prompts
get_content_before_last_match: when there's only one PS1 match, whether to get
the content before the last PS1 prompt (True) or after the last PS1 prompt (False)
Returns:
Combined string of all outputs between matches
"""

7
openhands/runtime/utils/file_viewer.py
View File

@ -1,6 +1,4 @@
"""
Utility module for generating file viewer HTML content.
"""
"""Utility module for generating file viewer HTML content."""
import base64
import mimetypes
@ -8,8 +6,7 @@ import os
def generate_file_viewer_html(file_path: str) -> str:
"""
Generate HTML content for viewing different file types.
"""Generate HTML content for viewing different file types.
Args:
file_path: The absolute path to the file

3
openhands/runtime/utils/git_changes.py
View File

@ -1,6 +1,5 @@
#!/usr/bin/env python3
"""
Get git changes in the current working directory relative to the remote origin if possible.
"""Get git changes in the current working directory relative to the remote origin if possible.
NOTE: Since this is run as a script, there should be no imports from project files!
"""

3
openhands/runtime/utils/git_diff.py
View File

@ -1,6 +1,5 @@
#!/usr/bin/env python3
"""
Get git diff in a single git file for the closest git repo in the file system
"""Get git diff in a single git file for the closest git repo in the file system
NOTE: Since this is run as a script, there should be no imports from project files!
"""

16
openhands/runtime/utils/git_handler.py
View File

@ -14,8 +14,7 @@ GIT_DIFF_CMD = (
@dataclass
class CommandResult:
"""
Represents the result of a shell command execution.
"""Represents the result of a shell command execution.
Attributes:
content (str): The output content of the command.
@ -27,9 +26,7 @@ class CommandResult:
class GitHandler:
"""
A handler for executing Git-related operations via shell commands.
"""
"""A handler for executing Git-related operations via shell commands."""
def __init__(
self,
@ -43,8 +40,7 @@ class GitHandler:
self.git_diff_cmd = GIT_DIFF_CMD
def set_cwd(self, cwd: str) -> None:
"""
Sets the current working directory for Git operations.
"""Sets the current working directory for Git operations.
Args:
cwd (str): The directory path.
@ -60,8 +56,7 @@ class GitHandler:
return script_file
def get_git_changes(self) -> list[dict[str, str]] | None:
"""
Retrieves the list of changed files in Git repositories.
"""Retrieves the list of changed files in Git repositories.
Examines each direct subdirectory of the workspace directory looking for git repositories
and returns the changes for each of these directories.
Optimized to use a single git command per repository for maximum performance.
@ -100,8 +95,7 @@ class GitHandler:
return self.get_git_changes()
def get_git_diff(self, file_path: str) -> dict[str, str]:
"""
Retrieves the original and modified content of a file in the repository.
"""Retrieves the original and modified content of a file in the repository.
Args:
file_path (str): Path to the file.

16
openhands/runtime/utils/windows_bash.py
View File

@ -1,5 +1,4 @@
"""
This module provides a Windows-specific implementation for running commands
"""This module provides a Windows-specific implementation for running commands
in a PowerShell session using the pythonnet library to interact with the .NET
PowerShell SDK directly. This aims to provide a more robust and integrated
way to manage PowerShell processes compared to using temporary script files.
@ -95,8 +94,7 @@ except Exception as e:
class WindowsPowershellSession:
"""
Manages a persistent PowerShell session using the .NET SDK via pythonnet.
"""Manages a persistent PowerShell session using the .NET SDK via pythonnet.
Allows executing commands within a single runspace, preserving state
(variables, current directory) between calls.
@ -110,8 +108,7 @@ class WindowsPowershellSession:
no_change_timeout_seconds: int = 30,
max_memory_mb: int | None = None,
):
"""
Initializes the PowerShell session.
"""Initializes the PowerShell session.
Args:
work_dir: The starting working directory for the session.
@ -388,9 +385,7 @@ class WindowsPowershellSession:
def _check_active_job(
self, timeout_seconds: int
) -> CmdOutputObservation | ErrorObservation:
"""
Checks the active job for new output and status, waiting up to timeout_seconds.
"""
"""Checks the active job for new output and status, waiting up to timeout_seconds."""
with self._job_lock:
if not self.active_job:
return ErrorObservation(
@ -649,8 +644,7 @@ class WindowsPowershellSession:
return self._cwd
def execute(self, action: CmdRunAction) -> CmdOutputObservation | ErrorObservation:
"""
Executes a command, potentially as a PowerShell background job for long-running tasks.
"""Executes a command, potentially as a PowerShell background job for long-running tasks.
Aligned with bash.py behavior regarding command execution and messages.
Args:

7
openhands/runtime/utils/windows_exceptions.py
View File

@ -1,11 +1,8 @@
"""
Custom exceptions for Windows-specific runtime issues.
"""
"""Custom exceptions for Windows-specific runtime issues."""
class DotNetMissingError(Exception):
"""
Exception raised when .NET SDK or CoreCLR is missing or cannot be loaded.
"""Exception raised when .NET SDK or CoreCLR is missing or cannot be loaded.
This is used to provide a cleaner error message to users without a full stack trace.
"""

4
openhands/server/data_models/agent_loop_info.py
View File

@ -7,9 +7,7 @@ from openhands.storage.data_models.conversation_status import ConversationStatus
@dataclass
class AgentLoopInfo:
"""
Information about an agent loop - the URL on which to locate it and the event store
"""
"""Information about an agent loop - the URL on which to locate it and the event store"""
conversation_id: str
url: str | None

3
openhands/server/data_models/conversation_info.py
View File

@ -9,8 +9,7 @@ from openhands.storage.data_models.conversation_status import ConversationStatus
@dataclass
class ConversationInfo:
"""
Information about a conversation. This combines conversation metadata with
"""Information about a conversation. This combines conversation metadata with
information on whether a conversation is currently running
"""

Some files were not shown because too many files have changed in this diff Show More