[chore] Run full agent pre-commit (All-Hands-AI#8235)

Author: enyst

docs/modules/usage/mcp.md

@@ -20,7 +20,7 @@ MCP configuration is defined in the `[mcp]` section of your `config.toml` file.
 sse_servers = [
     # Basic SSE server with just a URL
     "http://example.com:8080/mcp",
-    
+
     # SSE server with API key authentication
     {url="https://secure-example.com/mcp", api_key="your-api-key"}
 ]
@@ -29,7 +29,7 @@ sse_servers = [
 stdio_servers = [
     # Basic stdio server
     {name="fetch", command="uvx", args=["mcp-server-fetch"]},
-    
+
     # Stdio server with environment variables
     {
         name="data-processor",

docs/package.json

@@ -55,4 +55,4 @@
     "node": ">=18.0"
   },
   "packageManager": "[email protected]"
-}
+}

evaluation/benchmarks/multi_swe_bench/run_infer.py

@@ -36,13 +36,12 @@
 )
 from openhands.core.logger import openhands_logger as logger
 from openhands.core.main import create_runtime, run_controller
-from openhands.events.action import CmdRunAction, MessageAction, FileReadAction
+from openhands.events.action import CmdRunAction, FileReadAction, MessageAction
 from openhands.events.observation import CmdOutputObservation, ErrorObservation
 from openhands.events.serialization.event import event_to_dict
 from openhands.runtime.base import Runtime
 from openhands.utils.async_utils import call_async_from_sync
 from openhands.utils.shutdown_listener import sleep_if_should_continue
-import pdb
 
 USE_HINT_TEXT = os.environ.get('USE_HINT_TEXT', 'false').lower() == 'true'
 USE_INSTANCE_IMAGE = os.environ.get('USE_INSTANCE_IMAGE', 'true').lower() == 'true'
@@ -51,7 +50,7 @@
 # TODO: migrate all swe-bench docker to ghcr.io/openhands
 # TODO: 适应所有的语言
 DOCKER_IMAGE_PREFIX = os.environ.get('EVAL_DOCKER_IMAGE_PREFIX', '')
-LANGUAGE =os.environ.get('LANGUAGE', 'python')
+LANGUAGE = os.environ.get('LANGUAGE', 'python')
 logger.info(f'Using docker image prefix: {DOCKER_IMAGE_PREFIX}')
 
 
@@ -71,7 +70,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
     # Instruction based on Anthropic's official trajectory
     # https://github.com/eschluntz/swe-bench-experiments/tree/main/evaluation/verified/20241022_tools_claude-3-5-sonnet-updated/trajs
     instructions = {
-        "python":(
+        'python': (
             '<uploaded_files>\n'
             f'/workspace/{workspace_dir_name}\n'
             '</uploaded_files>\n'
@@ -96,7 +95,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             '   Make sure all these tests pass with your changes.\n'
             "Your thinking should be thorough and so it's fine if it's very long.\n"
         ),
-        "java": (
+        'java': (
             '<uploaded_files>\n'
             f'/workspace/{workspace_dir_name}\n'
             '</uploaded_files>\n'
@@ -121,7 +120,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             "   Make sure all these tests pass with your changes.\n"
             "Your thinking should be thorough and so it's fine if it's very long.\n"
         ),
-        "go": (
+        'go': (
             '<uploaded_files>\n'
             f'/workspace/{workspace_dir_name}\n'
             '</uploaded_files>\n'
@@ -146,7 +145,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             '   Make sure all these tests pass with your changes.\n'
             "Your thinking should be thorough and so it's fine if it's very long.\n"
         ),
-        "c": (
+        'c': (
             '<uploaded_files>\n'
             f'/workspace/{workspace_dir_name}\n'
             '</uploaded_files>\n'
@@ -171,7 +170,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             '   Make sure all these tests pass with your changes.\n'
             "Your thinking should be thorough and so it's fine if it's very long.\n"
         ),
-        "cpp": (
+        'cpp': (
             '<uploaded_files>\n'
             f'/workspace/{workspace_dir_name}\n'
             '</uploaded_files>\n'
@@ -196,7 +195,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             '   Make sure all these tests pass with your changes.\n'
             "Your thinking should be thorough and so it's fine if it's very long.\n"
         ),
-        "javascript": (
+        'javascript': (
             '<uploaded_files>\n'
             f'/workspace/{workspace_dir_name}\n'
             '</uploaded_files>\n'
@@ -221,7 +220,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             '   Make sure all these tests pass with your changes.\n'
             "Your thinking should be thorough and so it's fine if it's very long.\n"
         ),
-        "typescript":(
+        'typescript': (
             '<uploaded_files>\n'
             f'/workspace/{workspace_dir_name}\n'
             '</uploaded_files>\n'
@@ -246,7 +245,7 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             '   Make sure all these tests pass with your changes.\n'
             "Your thinking should be thorough and so it's fine if it's very long.\n"
         ),
-        "rust":(
+        'rust': (
             '<uploaded_files>\n'
             f'/workspace/{workspace_dir_name}\n'
             '</uploaded_files>\n'
@@ -270,11 +269,10 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
             '   - The functions you changed\n'
             '   Make sure all these tests pass with your changes.\n'
             "Your thinking should be thorough and so it's fine if it's very long.\n"
-        )
+        ),
     }
     instruction = instructions.get(LANGUAGE.lower())
 
-
     if instruction and RUN_WITH_BROWSING:
         instruction += (
             '<IMPORTANT!>\n'
@@ -284,7 +282,6 @@ def get_instruction(instance: pd.Series, metadata: EvalMetadata):
     return instruction
 
 
-
 # TODO: 适应所有的语言
 # def get_instance_docker_image(instance_id: str) -> str:
 #     image_name = 'sweb.eval.x86_64.' + instance_id
@@ -307,16 +304,15 @@ def get_instance_docker_image(instance: pd.Series):
         container_name = container_name.replace('/', '_m_')
         instance_id = instance.get('instance_id', '')
         tag_suffix = instance_id.split('-')[-1] if instance_id else ''
-        container_tag = f"pr-{tag_suffix}"
+        container_tag = f'pr-{tag_suffix}'
         # pdb.set_trace()
-        return f"mswebench/{container_name}:{container_tag}"
+        return f'mswebench/{container_name}:{container_tag}'
         # return "kong/insomnia:pr-8284"
         # return "'sweb.eval.x86_64.local_insomnia"
         # return "local_insomnia_why"
         # return "local/kong-insomnia:pr-8117"
 
 
-
 def get_config(
     instance: pd.Series,
     metadata: EvalMetadata,
@@ -569,7 +565,6 @@ def complete_runtime(
         f'Failed to git config --global core.pager "": {str(obs)}',
     )
 
-
     action = CmdRunAction(command='git add -A')
     action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
@@ -582,14 +577,14 @@ def complete_runtime(
 
     ##删除二进制文件
     action = CmdRunAction(
-        command=f'''
+        command="""
         for file in $(git status --porcelain | grep -E "^(M| M|\\?\\?|A| A)" | cut -c4-); do
             if [ -f "$file" ] && (file "$file" | grep -q "executable" || git check-attr binary "$file" | grep -q "binary: set"); then
                 git rm -f "$file" 2>/dev/null || rm -f "$file"
                 echo "Removed: $file"
             fi
         done
-        '''
+        """
     )
     action.set_hard_timeout(600)
     logger.info(action, extra={'msg_type': 'ACTION'})
@@ -626,14 +621,12 @@ def complete_runtime(
         else:
             assert_and_raise(False, f'Unexpected observation type: {str(obs)}')
 
-    action = FileReadAction(
-            path='patch.diff'
-        )
+    action = FileReadAction(path='patch.diff')
     action.set_hard_timeout(max(300 + 100 * n_retries, 600))
     logger.info(action, extra={'msg_type': 'ACTION'})
     obs = runtime.run_action(action)
     git_patch = obs.content
-    # pdb.set_trace() 
+    # pdb.set_trace()
 
     assert_and_raise(git_patch is not None, 'Failed to get git diff (None)')
 
@@ -714,20 +707,21 @@ def remove_binary_diffs(patch_text):
         is_binary_block = False
 
         for line in lines:
-            if line.startswith("diff --git "):
+            if line.startswith('diff --git '):
                 if block and not is_binary_block:
                     cleaned_lines.extend(block)
                 block = [line]
                 is_binary_block = False
-            elif "Binary files" in line:
+            elif 'Binary files' in line:
                 is_binary_block = True
                 block.append(line)
             else:
                 block.append(line)
 
         if block and not is_binary_block:
             cleaned_lines.extend(block)
-        return "\n".join(cleaned_lines)
+        return '\n'.join(cleaned_lines)
+
     git_patch = remove_binary_diffs(git_patch)
     test_result = {
         'git_patch': git_patch,
@@ -797,7 +791,7 @@ def filter_dataset(dataset: pd.DataFrame, filter_column: str) -> pd.DataFrame:
     # so we don't need to manage file uploading to OpenHands's repo
     # dataset = load_dataset(args.dataset, split=args.split)
     # dataset = load_dataset(args.dataset)
-    dataset = load_dataset("json", data_files = args.dataset)
+    dataset = load_dataset('json', data_files=args.dataset)
     dataset = dataset[args.split]
     swe_bench_tests = filter_dataset(dataset.to_pandas(), 'instance_id')
     logger.info(

evaluation/benchmarks/multi_swe_bench/scripts/data/data_change.py

@@ -3,7 +3,9 @@
 input_file = 'XXX.jsonl'
 output_file = 'YYY.jsonl'
 
-with open(input_file, 'r', encoding='utf-8') as fin, open(output_file, 'w', encoding='utf-8') as fout:
+with open(input_file, 'r', encoding='utf-8') as fin, open(
+    output_file, 'w', encoding='utf-8'
+) as fout:
     for line in fin:
         line = line.strip()
         if not line:
@@ -13,18 +15,22 @@
         item = data
 
         # 提取原始数据
-        org = item.get("org", "")
-        repo = item.get("repo", "")
-        number = str(item.get("number", ""))
+        org = item.get('org', '')
+        repo = item.get('repo', '')
+        number = str(item.get('number', ''))
 
         new_item = {}
-        new_item["repo"] = f"{org}/{repo}"
-        new_item["instance_id"] = f"{org}__{repo}-{number}"
-        new_item["problem_statement"] = item["resolved_issues"][0].get("title", "") + "\n" + item["resolved_issues"][0].get("body", "")
-        new_item["FAIL_TO_PASS"] = []
-        new_item["PASS_TO_PASS"] = []
-        new_item["base_commit"] = item['base'].get("sha","")
-        new_item["version"] = "0.1" # depends
+        new_item['repo'] = f'{org}/{repo}'
+        new_item['instance_id'] = f'{org}__{repo}-{number}'
+        new_item['problem_statement'] = (
+            item['resolved_issues'][0].get('title', '')
+            + '\n'
+            + item['resolved_issues'][0].get('body', '')
+        )
+        new_item['FAIL_TO_PASS'] = []
+        new_item['PASS_TO_PASS'] = []
+        new_item['base_commit'] = item['base'].get('sha', '')
+        new_item['version'] = '0.1'  # depends
 
         output_data = new_item
-        fout.write(json.dumps(output_data, ensure_ascii=False) + "\n")
+        fout.write(json.dumps(output_data, ensure_ascii=False) + '\n')

evaluation/benchmarks/multi_swe_bench/scripts/eval/convert.py

@@ -15,7 +15,7 @@ def main():
                     'org': groups.group(1),
                     'repo': groups.group(2),
                     'number': groups.group(3),
-                    'fix_patch': data['test_result']['git_patch']
+                    'fix_patch': data['test_result']['git_patch'],
                 }
                 fout.write(json.dumps(patch) + '\n')
 

frontend/__tests__/components/features/auth-modal.test.tsx

@@ -27,7 +27,7 @@ describe("AuthModal", () => {
 
   it("should render the GitHub and GitLab buttons", () => {
     render(<AuthModal githubAuthUrl="mock-url" appMode="saas" />);
-    
+
     const githubButton = screen.getByRole("button", { name: "GITHUB$CONNECT_TO_GITHUB" });
     const gitlabButton = screen.getByRole("button", { name: "GITLAB$CONNECT_TO_GITLAB" });
 

frontend/__tests__/routes/accept-tos.test.tsx

@@ -43,7 +43,7 @@ const createWrapper = () => {
       },
     },
   });
-  
+
   return ({ children }: { children: React.ReactNode }) => (
     <QueryClientProvider client={queryClient}>{children}</QueryClientProvider>
   );
@@ -61,7 +61,7 @@ describe("AcceptTOS", () => {
 
   it("should render a TOS checkbox that is unchecked by default", () => {
     render(<AcceptTOS />, { wrapper: createWrapper() });
-    
+
     const checkbox = screen.getByRole("checkbox");
     const continueButton = screen.getByRole("button", { name: "TOS$CONTINUE" });
 
@@ -72,7 +72,7 @@ describe("AcceptTOS", () => {
   it("should enable the continue button when the TOS checkbox is checked", async () => {
     const user = userEvent.setup();
     render(<AcceptTOS />, { wrapper: createWrapper() });
-    
+
     const checkbox = screen.getByRole("checkbox");
     const continueButton = screen.getByRole("button", { name: "TOS$CONTINUE" });
 
@@ -96,7 +96,7 @@ describe("AcceptTOS", () => {
 
     const user = userEvent.setup();
     render(<AcceptTOS />, { wrapper: createWrapper() });
-    
+
     const checkbox = screen.getByRole("checkbox");
     await user.click(checkbox);
 
@@ -121,7 +121,7 @@ describe("AcceptTOS", () => {
 
     const user = userEvent.setup();
     render(<AcceptTOS />, { wrapper: createWrapper() });
-    
+
     const checkbox = screen.getByRole("checkbox");
     await user.click(checkbox);
 
@@ -133,4 +133,4 @@ describe("AcceptTOS", () => {
 
     expect(window.location.href).toBe(externalUrl);
   });
-});
+});

openhands/integrations/github/github_service.py

@@ -390,7 +390,9 @@ async def get_suggested_tasks(self) -> list[SuggestedTask]:
         except Exception:
             return []
 
-    async def get_repository_details_from_repo_name(self, repository: str) -> Repository:
+    async def get_repository_details_from_repo_name(
+        self, repository: str
+    ) -> Repository:
         url = f'{self.BASE_URL}/repos/{repository}'
         repo, _ = await self._make_request(url)
 

openhands/integrations/gitlab/gitlab_service.py

@@ -382,9 +382,10 @@ async def get_suggested_tasks(self) -> list[SuggestedTask]:
         except Exception:
             return []
 
-
-    async def get_repository_details_from_repo_name(self, repository: str) -> Repository:
-        encoded_name = repository.replace("/", "%2F")
+    async def get_repository_details_from_repo_name(
+        self, repository: str
+    ) -> Repository:
+        encoded_name = repository.replace('/', '%2F')
 
         url = f'{self.BASE_URL}/projects/{encoded_name}'
         repo, _ = await self._make_request(url)
@@ -396,8 +397,6 @@ async def get_repository_details_from_repo_name(self, repository: str) -> Reposi
             git_provider=ProviderType.GITLAB,
             is_public=repo.get('visibility') == 'public',
         )
-        
-       
 
 
 gitlab_service_cls = os.environ.get(

openhands/integrations/templates/suggested_task/failing_checks_prompt.j2

@@ -3,4 +3,4 @@ Use the {{ apiName }} with the {{ tokenEnvVar }} environment variable to retriev
 Check out the branch from that {{ requestVerb }} and look at the diff versus the base branch of the {{ requestTypeShort }} to understand the {{ requestTypeShort }}'s intention.
 Then use the {{ apiName }} to look at the {{ ciSystem }} that are failing on the most recent commit. Try and reproduce the failure locally.
 Get things working locally, then push your changes. Sleep for 30 seconds at a time until the {{ ciProvider }} {{ ciSystem.lower() }} have run again.
-If they are still failing, repeat the process.
+If they are still failing, repeat the process.

openhands/integrations/templates/suggested_task/merge_conflict_prompt.j2

@@ -1,4 +1,4 @@
 You are working on {{ requestType }} #{{ issue_number }} in repository {{ repo }}. You need to fix the merge conflicts.
 Use the {{ apiName }} with the {{ tokenEnvVar }} environment variable to retrieve the {{ requestTypeShort }} details.
 Check out the branch from that {{ requestVerb }} and look at the diff versus the base branch of the {{ requestTypeShort }} to understand the {{ requestTypeShort }}'s intention.
-Then resolve the merge conflicts. If you aren't sure what the right solution is, look back through the commit history at the commits that introduced the conflict and resolve them accordingly.
+Then resolve the merge conflicts. If you aren't sure what the right solution is, look back through the commit history at the commits that introduced the conflict and resolve them accordingly.