A programming framework for agentic AI
This report summarizes scanner evidence for microsoft/autogen, a Python project with 61,342 GitHub stars. SynthScan examined 213,192 lines of code across 1519 source files, recording 3109 pattern matches distributed across 27 syntactic categories. The legacy adjusted pattern signal is 21.2 (Elevated pattern signal); it is not an authorship estimate.
Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.
Use each vector to guide manual verification of the underlying findings.
Can maintainers explain intent, assumptions, and trade-offs? 2100 finding(s).
Are imports declared and package/API names verified? 557 finding(s).
Are wrappers, guards, and repeated structures necessary? 1604 finding(s).
Which changes need focused human review? 3109 finding(s).
This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.
Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.
This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.
The scanner identified 3109 distinct pattern matches across 27 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.
Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/check_md_code_blocks.py | 17 | def extract_python_code_blocks(markdown_file_path: str) -> List[Tuple[str, int]]: | CODE |
| LOW | python/docs/src/generate_api_reference.py | 201 | def generate_toctree_from_rst_files(reference_dir: Path) -> Dict[str, List[str]]: | STRING |
| LOW | python/docs/src/generate_api_reference.py | 224 | def sort_modules_hierarchically(modules): | CODE |
| LOW | python/docs/src/_static/custom.js | 163 | function enhanceExpandableSections(item, parentLink, parentText, sectionTitle) { | CODE |
| LOW | python/samples/core_distributed-group-chat/_agents.py | 195 | async def publish_message_to_ui_and_backend( | CODE |
| LOW | …ples/core_streaming_handoffs_fastapi/tools_delegate.py | 8 | def transfer_to_issues_and_repairs() -> str: | CODE |
| LOW | …ask_centric_memory/eval_learning_from_demonstration.py | 30 | async def eval_learning_from_demonstration( | CODE |
| LOW | python/packages/agbench/benchmarks/process_logs.py | 144 | def get_number_of_chat_messages(chat_messages_dir): | CODE |
| LOW | python/packages/agbench/benchmarks/process_logs.py | 201 | def is_progress_not_being_made(instance_dir): | CODE |
| LOW | …/HumanEval/Templates/AgentChat/custom_code_executor.py | 24 | def _extract_markdown_code_blocks(self, markdown_text: str) -> List[CodeBlock]: | CODE |
| LOW | …ges/agbench/benchmarks/GAIA/Scripts/custom_tabulate.py | 16 | def in_house_normalize_answer(a): | CODE |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 115 | def team_specific_agentchat_event_logger_info(msg, *args, **kwargs): | CODE |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 124 | def team_specific_core_event_logger_info(msg, *args, **kwargs): | CODE |
| LOW | …hon/packages/agbench/src/agbench/remove_missing_cmd.py | 31 | def delete_folders_with_missing_results(runlogs_path: str, noconfirm: bool = False) -> None: | CODE |
| LOW | python/packages/agbench/src/agbench/run_cmd.py | 696 | def build_default_docker_image(docker_client: docker.DockerClient, image_tag: str) -> None: | STRING |
| LOW | …ackages/agbench/src/agbench/linter/coders/oai_coder.py | 15 | def remove_control_characters(text: str) -> str: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 312 | async def import_teams_from_directory( | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 88 | def _cleanup_existing_alembic(self) -> None: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 193 | def _generate_alembic_ini_content(self) -> str: | CODE |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 119 | async def register_auth_dependencies(app: FastAPI, auth_manager: AuthManager) -> None: | CODE |
| LOW | …ackages/autogen-studio/autogenstudio/web/routes/mcp.py | 186 | async def create_mcp_websocket_connection(request: CreateWebSocketConnectionRequest): | CODE |
| LOW | …ckages/autogen-studio/autogenstudio/gallery/builder.py | 57 | def _update_component_metadata( | CODE |
| LOW | …/packages/autogen-studio/autogenstudio/mcp/wsbridge.py | 137 | async def _handle_elicitation_response(self, message: Dict[str, Any]) -> None: | CODE |
| LOW | …packages/autogen-studio/autogenstudio/mcp/callbacks.py | 120 | def create_elicitation_callback( | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 523 | export function createComponentFromTemplate( | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 555 | export function getWorkbenchTemplatesForDropdown(): WorkbenchDropdownOption[] { | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 564 | export function createWorkbenchFromTemplate( | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 599 | export function createComponentFromTemplateById( | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 615 | export function getTeamTemplatesForDropdown(): ComponentDropdownOption[] { | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 626 | export function getAgentTemplatesForDropdown(): ComponentDropdownOption[] { | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 637 | export function getModelTemplatesForDropdown(): ComponentDropdownOption[] { | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 648 | export function getToolTemplatesForDropdown(): ComponentDropdownOption[] { | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 659 | export function getTerminationTemplatesForDropdown(): ComponentDropdownOption[] { | CODE |
| LOW | …o/frontend/src/components/types/component-templates.ts | 663 | export function createTerminationFromTemplate( | CODE |
| LOW | …autogen-studio/frontend/src/components/types/guards.ts | 191 | // export function isChatCompletionContextComponent( | COMMENT |
| LOW | …thon/packages/autogen-studio/tests/test_lite_studio.py | 59 | def test_init_with_team_object(sample_team_object: Dict[str, Union[str, List[Any]]]) -> None: | CODE |
| LOW | …thon/packages/autogen-studio/tests/test_lite_studio.py | 90 | def test_init_with_invalid_file() -> None: | CODE |
| LOW | …thon/packages/autogen-studio/tests/test_lite_studio.py | 170 | def test_stop_with_server_thread(sample_team_file: str) -> None: | CODE |
| LOW | …thon/packages/autogen-studio/tests/test_lite_studio.py | 200 | def test_start_twice_raises_error(mock_uvicorn: MagicMock, sample_team_file: str) -> None: | CODE |
| LOW | …thon/packages/autogen-studio/tests/test_lite_studio.py | 212 | def test_init_with_team_object_with_serialization_methods() -> None: | CODE |
| LOW | …thon/packages/autogen-studio/tests/test_lite_studio.py | 237 | def test_init_with_team_object_model_dump() -> None: | CODE |
| LOW | …thon/packages/autogen-studio/tests/test_lite_studio.py | 254 | def test_init_with_unsupported_team_object() -> None: | CODE |
| LOW | …thon/packages/autogen-studio/tests/test_lite_studio.py | 266 | def test_init_with_path_object(tmp_path: Path) -> None: | CODE |
| LOW | …thon/packages/autogen-studio/tests/test_lite_studio.py | 289 | def test_init_with_component_model() -> None: | CODE |
| LOW | python/packages/autogen-studio/tests/test_db_manager.py | 62 | def test_basic_entity_creation(self, test_db: DatabaseManager, sample_team: Team): | CODE |
| LOW | python/packages/autogen-studio/tests/test_db_manager.py | 170 | def test_initialize_database_scenarios(self, tmp_path, monkeypatch): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 58 | async def test_bridge_initialization(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 82 | async def test_on_initialized_event(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 95 | async def test_on_operation_result_event(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 109 | async def test_on_operation_error_event(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 123 | async def test_on_elicitation_request_event(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 160 | async def test_handle_operation_message_without_client(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 175 | async def test_handle_operation_message_with_client(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 198 | async def test_handle_unknown_message_type(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 213 | async def test_handle_elicitation_response_accept(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 240 | async def test_handle_elicitation_response_decline(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 262 | async def test_handle_elicitation_response_missing_request_id(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 278 | async def test_handle_elicitation_response_unknown_request_id(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 295 | async def test_message_loop_with_valid_json(self, bridge, mock_websocket): | CODE |
| LOW | …packages/autogen-studio/tests/mcp/test_mcp_wsbridge.py | 317 | async def test_message_loop_with_invalid_json(self, bridge, mock_websocket): | CODE |
| 1069 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | python/docs/redirects/redirects.py | 14 | # Create a new redirect page | COMMENT |
| MEDIUM | python/docs/redirects/redirects.py | 26 | # Create the path to the redirect page | COMMENT |
| MEDIUM | python/docs/redirects/redirects.py | 29 | # Create the directory if it doesn't exist | COMMENT |
| MEDIUM | python/docs/src/_extension/code_lint.py | 66 | # Create a temporary file to store the code block | COMMENT |
| MEDIUM | python/docs/src/_extension/gallery_directive.py | 115 | # Create the directive string for the grid | COMMENT |
| MEDIUM | python/samples/core_distributed-group-chat/_types.py | 71 | # Define the overall AppConfig model | COMMENT |
| MEDIUM | …/samples/core_streaming_handoffs_fastapi/agent_base.py | 82 | # Create the context for the delegate agent, including the function call and the result. | COMMENT |
| MEDIUM | python/samples/agentchat_fastapi/app_team.py | 52 | # Create the team. | COMMENT |
| MEDIUM | python/samples/agentchat_fastapi/app_agent.py | 46 | # Create the assistant agent. | COMMENT |
| MEDIUM | …on/samples/core_semantic_router/run_semantic_router.py | 85 | # Create the agents | COMMENT |
| MEDIUM | …on/samples/core_semantic_router/run_semantic_router.py | 92 | # Create the User Proxy Agent | COMMENT |
| MEDIUM | …on/samples/core_semantic_router/run_semantic_router.py | 104 | # Create the Semantic Router | COMMENT |
| MEDIUM | python/samples/agentchat_chess_game/main.py | 15 | # Create an agent that can use the model client. | COMMENT |
| MEDIUM | python/samples/core_streaming_response_fastapi/app.py | 70 | # Create a stream of messages to the model client. | COMMENT |
| MEDIUM | python/samples/task_centric_memory/eval_retrieval.py | 93 | # Create the necessary components. | COMMENT |
| MEDIUM | python/samples/task_centric_memory/eval_teachability.py | 93 | # Create the necessary components. | COMMENT |
| MEDIUM | …thon/samples/task_centric_memory/eval_self_teaching.py | 109 | # Create the necessary components. | COMMENT |
| MEDIUM⚡ | …mples/task_centric_memory/chat_with_teachable_agent.py | 9 | # Create a client | COMMENT |
| MEDIUM⚡ | …mples/task_centric_memory/chat_with_teachable_agent.py | 12 | # Create an instance of Task-Centric Memory, passing minimal parameters for this simple example | COMMENT |
| MEDIUM⚡ | …mples/task_centric_memory/chat_with_teachable_agent.py | 18 | # Create an AssistantAgent, and attach teachability as its memory | COMMENT |
| MEDIUM | …ask_centric_memory/eval_learning_from_demonstration.py | 91 | # Create the necessary components. | COMMENT |
| MEDIUM | python/samples/core_chess_game/main.py | 147 | # Create the board. | COMMENT |
| MEDIUM | python/samples/core_chainlit/app_team.py | 95 | # Create the assistant agent. | COMMENT |
| MEDIUM | python/samples/core_chainlit/app_team.py | 108 | # Create the critic agent. | COMMENT |
| MEDIUM⚡ | python/samples/core_chainlit/app_agent.py | 63 | # Create a runtime and save to chainlit session | COMMENT |
| MEDIUM⚡ | python/samples/core_chainlit/app_agent.py | 70 | # Create a queue for output stream data and save to chainlit session | COMMENT |
| MEDIUM⚡ | python/samples/core_chainlit/app_agent.py | 74 | # Create the assistant agent with the get_weather tool. | COMMENT |
| MEDIUM | python/samples/agentchat_chainlit/app_team.py | 21 | # Create the assistant agent. | COMMENT |
| MEDIUM | python/samples/agentchat_chainlit/app_team.py | 29 | # Create the critic agent. | COMMENT |
| MEDIUM | python/samples/agentchat_chainlit/app_agent.py | 38 | # Create the assistant agent with the get_weather tool. | COMMENT |
| MEDIUM⚡ | …thon/samples/agentchat_chainlit/app_team_user_proxy.py | 54 | # Create the assistant agent. | COMMENT |
| MEDIUM⚡ | …thon/samples/agentchat_chainlit/app_team_user_proxy.py | 62 | # Create the critic agent. | COMMENT |
| MEDIUM⚡ | …thon/samples/agentchat_chainlit/app_team_user_proxy.py | 71 | # Create the user proxy agent. | COMMENT |
| MEDIUM | …ges/agbench/benchmarks/HumanEval/Scripts/init_tasks.py | 67 | # Create a BytesIO object from the response content | COMMENT |
| MEDIUM | …ges/agbench/benchmarks/HumanEval/Scripts/init_tasks.py | 83 | # Create a task directory if it doesn't exist | COMMENT |
| MEDIUM | …ges/agbench/benchmarks/HumanEval/Scripts/init_tasks.py | 87 | # Create the jsonl file | COMMENT |
| MEDIUM | …ges/agbench/benchmarks/HumanEval/Scripts/init_tasks.py | 117 | # Create the various combinations of [models] x [templates] | COMMENT |
| MEDIUM | …h/benchmarks/HumanEval/Templates/AgentChat/scenario.py | 47 | # Define a team | COMMENT |
| MEDIUM | …packages/agbench/benchmarks/GAIA/Scripts/init_tasks.py | 117 | # Create the various combinations of [models] x [templates] | COMMENT |
| MEDIUM | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 56 | # Create a context variable to hold the current team's log file and the current team id. | COMMENT |
| MEDIUM | …enchmarks/GAIA/Templates/SelectorGroupChat/scenario.py | 83 | # Create the team | STRING |
| MEDIUM | python/packages/agbench/src/agbench/tabulate_cmd.py | 241 | # Create a per-trial summary dataframe | COMMENT |
| MEDIUM | python/packages/agbench/src/agbench/tabulate_cmd.py | 263 | # Create a dataframe | COMMENT |
| MEDIUM | python/packages/agbench/src/agbench/run_cmd.py | 135 | # Create a folder to store the results | COMMENT |
| MEDIUM | python/packages/agbench/src/agbench/run_cmd.py | 774 | # Create a folder to store the results | STRING |
| MEDIUM | python/packages/agbench/src/agbench/run_cmd.py | 825 | # Create a pool of worker processes | STRING |
| MEDIUM | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 277 | # Create a default session with this team | COMMENT |
| MEDIUM | …ckages/autogen-studio/autogenstudio/gallery/builder.py | 292 | # Create a complex termination combining multiple conditions | COMMENT |
| MEDIUM | …ckages/autogen-studio/autogenstudio/gallery/builder.py | 520 | # Create a static workbench with basic tools | COMMENT |
| MEDIUM | …ckages/autogen-studio/autogenstudio/gallery/builder.py | 528 | # Create an MCP workbench for fetching web content using mcp-server-fetch | COMMENT |
| MEDIUM | …ckages/autogen-studio/autogenstudio/gallery/builder.py | 542 | # Create an MCP workbench with StreamableHttpServerParams for HTTP-based MCP servers | COMMENT |
| MEDIUM | …ckages/autogen-studio/autogenstudio/gallery/builder.py | 558 | # Create an MCP workbench for filesystem operations | COMMENT |
| MEDIUM | …ckages/autogen-studio/autogenstudio/gallery/builder.py | 577 | # Create an MCP workbench for testing with everything server | COMMENT |
| MEDIUM | …ogen-studio/autogenstudio/gallery/tools/bing_search.py | 201 | # Create the Bing search tool | COMMENT |
| MEDIUM | …en-studio/autogenstudio/gallery/tools/google_search.py | 129 | # Create the enhanced Google search tool | COMMENT |
| MEDIUM | …n-studio/autogenstudio/gallery/tools/generate_image.py | 54 | # Create the image generation tool | COMMENT |
| MEDIUM | …en-studio/autogenstudio/gallery/tools/fetch_webpage.py | 75 | # Create the webpage fetching tool | COMMENT |
| MEDIUM | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 79 | # Create a score object | COMMENT |
| MEDIUM | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 109 | # Create the prompt | COMMENT |
| MEDIUM⚡ | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 216 | # # Create a model client | COMMENT |
| 232 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …ang_hello_python_agent/protos/agent_events_pb2_grpc.py | 4 | CODE | |
| LOW | python/samples/gitty/src/gitty/__init__.py | 1 | CODE | |
| LOW | …ges/agbench/benchmarks/HumanEval/Scripts/init_tasks.py | 6 | CODE | |
| LOW | …gbench/benchmarks/HumanEval/Scripts/custom_tabulate.py | 1 | CODE | |
| LOW | …/HumanEval/Templates/AgentChat/custom_code_executor.py | 1 | CODE | |
| LOW | …h/benchmarks/HumanEval/Templates/AgentChat/scenario.py | 2 | CODE | |
| LOW | …ges/agbench/benchmarks/GAIA/Scripts/custom_tabulate.py | 5 | CODE | |
| LOW | …ges/agbench/benchmarks/GAIA/Scripts/custom_tabulate.py | 6 | CODE | |
| LOW | …ges/agbench/benchmarks/GAIA/Scripts/custom_tabulate.py | 7 | CODE | |
| LOW | …ges/agbench/benchmarks/GAIA/Scripts/custom_tabulate.py | 8 | CODE | |
| LOW | …ges/agbench/benchmarks/GAIA/Scripts/custom_tabulate.py | 10 | CODE | |
| LOW | …ges/agbench/benchmarks/GAIA/Scripts/custom_tabulate.py | 11 | CODE | |
| LOW | …ench/benchmarks/GAIA/Templates/MagenticOne/scenario.py | 8 | CODE | |
| LOW | …ench/benchmarks/GAIA/Templates/MagenticOne/scenario.py | 10 | CODE | |
| LOW | …ench/benchmarks/GAIA/Templates/MagenticOne/scenario.py | 15 | CODE | |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 12 | CODE | |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 15 | CODE | |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 27 | CODE | |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 32 | CODE | |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 32 | CODE | |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 45 | CODE | |
| LOW | …enchmarks/GAIA/Templates/SelectorGroupChat/scenario.py | 11 | CODE | |
| LOW | …enchmarks/GAIA/Templates/SelectorGroupChat/scenario.py | 13 | CODE | |
| LOW | …enchmarks/GAIA/Templates/SelectorGroupChat/scenario.py | 19 | CODE | |
| LOW | …enchmarks/GAIA/Templates/SelectorGroupChat/scenario.py | 20 | CODE | |
| LOW | python/packages/agbench/src/agbench/__init__.py | 1 | CODE | |
| LOW | python/packages/agbench/src/agbench/linter/__init__.py | 2 | CODE | |
| LOW | python/packages/agbench/src/agbench/linter/__init__.py | 2 | CODE | |
| LOW | python/packages/agbench/src/agbench/linter/__init__.py | 2 | CODE | |
| LOW | python/packages/agbench/src/agbench/linter/__init__.py | 2 | CODE | |
| LOW | …thon/packages/autogen-studio/autogenstudio/__init__.py | 1 | CODE | |
| LOW | …thon/packages/autogen-studio/autogenstudio/__init__.py | 2 | CODE | |
| LOW | …thon/packages/autogen-studio/autogenstudio/__init__.py | 3 | CODE | |
| LOW | …thon/packages/autogen-studio/autogenstudio/__init__.py | 4 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/database/__init__.py | 1 | CODE | |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 2 | CODE | |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 8 | CODE | |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 14 | CODE | |
| LOW | …s/autogen-studio/autogenstudio/teammanager/__init__.py | 1 | CODE | |
| LOW | …packages/autogen-studio/autogenstudio/lite/__init__.py | 1 | CODE | |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 2 | CODE | |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 9 | CODE | |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 13 | CODE | |
| LOW | …ckages/autogen-studio/autogenstudio/web/auth/models.py | 1 | CODE | |
| LOW | …ckages/autogen-studio/autogenstudio/web/auth/models.py | 2 | CODE | |
| LOW | …ckages/autogen-studio/autogenstudio/web/auth/models.py | 4 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 1 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 2 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 2 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 2 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 2 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 3 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 4 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 5 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 6 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 6 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 7 | CODE | |
| LOW | …es/autogen-studio/autogenstudio/web/auth/authroutes.py | 4 | CODE | |
| LOW | …es/autogen-studio/autogenstudio/web/auth/authroutes.py | 5 | CODE | |
| LOW | …ges/autogen-studio/autogenstudio/web/auth/providers.py | 10 | CODE | |
| 431 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | python/packages/agbench/src/agbench/run_cmd.py | 683 | except APIError: | CODE |
| HIGH | …n/packages/autogen-studio/autogenstudio/lite/studio.py | 243 | except (subprocess.SubprocessError, FileNotFoundError): | CODE |
| HIGH | …ackages/autogen-studio/autogenstudio/web/routes/mcp.py | 171 | except Exception: | CODE |
| HIGH | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 190 | except (ValueError, IndexError): | CODE |
| HIGH | …/packages/autogen-core/src/autogen_core/_base_agent.py | 204 | except ValueError: | CODE |
| HIGH | python/packages/autogen-core/src/autogen_core/_queue.py | 130 | except ValueError: | CODE |
| HIGH | python/packages/autogen-core/src/autogen_core/_queue.py | 177 | except ValueError: | CODE |
| HIGH | …thon/packages/autogen-ext/tests/test_azure_ai_agent.py | 563 | except StopAsyncIteration: | CODE |
| HIGH | …thon/packages/autogen-ext/tests/test_worker_runtime.py | 432 | except asyncio.CancelledError: | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 1240 | except asyncio.CancelledError: | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 145 | except (asyncio.CancelledError, ValueError): | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 461 | except asyncio.TimeoutError: | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 1158 | except asyncio.TimeoutError: | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 475 | except asyncio.CancelledError: | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 497 | except asyncio.CancelledError: | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 608 | except asyncio.CancelledError: | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 800 | except asyncio.CancelledError: | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 1172 | except asyncio.CancelledError: | CODE |
| HIGH | …ode_executors/test_docker_commandline_code_executor.py | 393 | except asyncio.CancelledError: | CODE |
| HIGH | …on/packages/autogen-ext/examples/mcp_example_server.py | 53 | except ValueError: | CODE |
| HIGH | …t/experimental/task_centric_memory/utils/_functions.py | 93 | except Exception: | CODE |
| HIGH | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 351 | except Exception: | CODE |
| HIGH | …ckages/autogen-ext/src/autogen_ext/tools/mcp/_actor.py | 253 | except Exception: | CODE |
| HIGH | …kages/autogen-ext/src/autogen_ext/memory/mem0/_mem0.py | 332 | except (ValueError, TypeError): | CODE |
| HIGH | …kages/autogen-ext/src/autogen_ext/memory/mem0/_mem0.py | 339 | except (ValueError, TypeError): | CODE |
| HIGH | …kages/autogen-ext/src/autogen_ext/cache_store/redis.py | 119 | except (redis.RedisError, ConnectionError, UnicodeEncodeError, TypeError): | CODE |
| HIGH | …n-ext/src/autogen_ext/runtimes/grpc/_worker_runtime.py | 322 | except asyncio.CancelledError: | CODE |
| HIGH | …n-ext/src/autogen_ext/runtimes/grpc/_worker_runtime.py | 329 | except asyncio.CancelledError: | CODE |
| HIGH | …/src/autogen_ext/runtimes/grpc/_worker_runtime_host.py | 47 | except asyncio.CancelledError: | CODE |
| HIGH | …autogen_ext/agents/web_surfer/playwright_controller.py | 26 | except ImportError: | CODE |
| HIGH | …autogen_ext/agents/web_surfer/playwright_controller.py | 102 | except Exception: | CODE |
| HIGH | …autogen_ext/agents/web_surfer/playwright_controller.py | 128 | except Exception: | CODE |
| HIGH | …autogen_ext/agents/web_surfer/playwright_controller.py | 145 | except Exception: | CODE |
| HIGH | …autogen_ext/agents/web_surfer/playwright_controller.py | 163 | except Exception: | CODE |
| HIGH | …autogen_ext/agents/web_surfer/playwright_controller.py | 550 | except Exception: | CODE |
| HIGH | …autogen_ext/agents/web_surfer/playwright_controller.py | 385 | except TimeoutError: | CODE |
| HIGH | …autogen_ext/agents/web_surfer/playwright_controller.py | 397 | except TimeoutError: | CODE |
| HIGH | …utogen_ext/agents/web_surfer/_multimodal_web_surfer.py | 886 | except Exception: | CODE |
| HIGH | …utogen_ext/agents/web_surfer/_multimodal_web_surfer.py | 531 | except KeyError: | CODE |
| HIGH | …/src/autogen_ext/models/anthropic/_anthropic_client.py | 1015 | except json.JSONDecodeError: | CODE |
| HIGH | …autogen-ext/src/autogen_ext/code_executors/__init__.py | 64 | except Exception: | CODE |
| HIGH | …n_ext/code_executors/docker_jupyter/_jupyter_server.py | 392 | except docker.errors.NotFound: | CODE |
| HIGH | …gen_ext/code_executors/docker/_docker_code_executor.py | 534 | except NotFound: | CODE |
| HIGH | …gen_ext/code_executors/docker/_docker_code_executor.py | 372 | except (OSError, FileNotFoundError): | CODE |
| HIGH | …utogen-agentchat/tests/test_group_chat_pause_resume.py | 47 | except asyncio.CancelledError: | CODE |
| HIGH | …utogen-agentchat/tests/test_group_chat_pause_resume.py | 74 | except asyncio.CancelledError: | CODE |
| HIGH | …utogen_agentchat/teams/_group_chat/_base_group_chat.py | 101 | except TypeError: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …cs/src/user-guide/core-user-guide/framework/logging.md | 66 | except Exception: | CODE |
| LOW | …thon/samples/core_streaming_handoffs_fastapi/README.md | 132 | except Exception as e: | CODE |
| MEDIUM⚡ | python/samples/core_streaming_handoffs_fastapi/app.py | 239 | print(f"Error decoding JSON from {chat_history_file}. Starting with empty history.") | CODE |
| LOW⚡ | python/samples/core_streaming_handoffs_fastapi/app.py | 244 | except Exception as e: | CODE |
| MEDIUM⚡ | python/samples/core_streaming_handoffs_fastapi/app.py | 245 | print(f"Error loading chat history for {conversation_id}: {e}") | CODE |
| LOW | python/samples/agentchat_fastapi/app_team.py | 91 | except Exception as e: | CODE |
| LOW | python/samples/agentchat_fastapi/app_team.py | 142 | except Exception as e: | CODE |
| LOW | python/samples/agentchat_fastapi/app_team.py | 161 | except Exception as send_error: | CODE |
| LOW | python/samples/agentchat_fastapi/app_team.py | 167 | except Exception as e: | CODE |
| LOW | python/samples/agentchat_fastapi/app_team.py | 178 | except Exception: | CODE |
| MEDIUM | python/samples/agentchat_fastapi/app_team.py | 88 | def history() -> list[dict[str, Any]]: | CODE |
| LOW | python/samples/agentchat_fastapi/app_agent.py | 73 | except Exception as e: | CODE |
| LOW | python/samples/agentchat_fastapi/app_agent.py | 98 | except Exception as e: | CODE |
| MEDIUM | python/samples/agentchat_fastapi/app_agent.py | 70 | def history() -> list[dict[str, Any]]: | CODE |
| LOW | python/samples/gitty/src/gitty/_github.py | 27 | except Exception: | CODE |
| MEDIUM | python/samples/gitty/src/gitty/_github.py | 46 | print(f"Error fetching issue: {error_detail}") | CODE |
| MEDIUM | python/samples/gitty/src/gitty/_github.py | 51 | print("Error decoding gh cli output:", e) | CODE |
| MEDIUM | python/samples/gitty/src/gitty/_github.py | 67 | print("Error fetching issues:", result.stderr) | CODE |
| MEDIUM | python/samples/gitty/src/gitty/_github.py | 72 | print("Error decoding issues JSON:", e) | CODE |
| LOW | python/samples/gitty/src/gitty/_db.py | 48 | except Exception: | STRING |
| MEDIUM | python/samples/gitty/src/gitty/_db.py | 87 | print("Error fetching issues:", result.stderr) | STRING |
| MEDIUM | python/samples/gitty/src/gitty/_db.py | 92 | print("Error decoding issues JSON:", e) | STRING |
| LOW | python/samples/gitty/src/gitty/_db.py | 149 | except Exception: | STRING |
| LOW | python/samples/gitty/src/gitty/_gitty.py | 71 | except Exception as e: | CODE |
| LOW | python/samples/gitty/src/gitty/_gitty.py | 82 | except Exception as e: | CODE |
| MEDIUM | python/samples/gitty/src/gitty/_config.py | 24 | print("Error: not a git repository.") | CODE |
| MEDIUM | python/samples/gitty/src/gitty/__main__.py | 16 | print("Error: OPENAI_API_KEY environment variable is not set.") | CODE |
| MEDIUM | …thon/samples/core_streaming_response_fastapi/README.md | 93 | print(f"Error: {e}") | CODE |
| LOW | python/samples/core_streaming_response_fastapi/app.py | 79 | except Exception as e: | CODE |
| MEDIUM⚡ | python/samples/agentchat_graphrag/app.py | 38 | print("Error: OPENAI_API_KEY environment variable is not set!") | CODE |
| LOW | python/samples/core_chainlit/SimpleAssistantAgent.py | 105 | except Exception as e: | CODE |
| LOW | python/packages/agbench/benchmarks/process_logs.py | 49 | except Exception as e: | CODE |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 98 | except Exception: | CODE |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 358 | except Exception as e: | STRING |
| MEDIUM | …hon/packages/agbench/src/agbench/remove_missing_cmd.py | 97 | print(f"Error: '{runlogs_path}' is not a valid directory.") | CODE |
| MEDIUM | …hon/packages/agbench/src/agbench/remove_missing_cmd.py | 119 | print(f"Error: '{runlogs_path}' is not a valid directory.") | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 101 | except Exception as e: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 139 | except Exception as e: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 156 | except Exception as e: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 193 | except Exception as e: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 237 | except Exception as e: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 276 | except Exception as e: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 308 | except Exception as e: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 344 | except Exception as e: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 350 | except Exception as e: | CODE |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 372 | except Exception as e: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 68 | except Exception as e: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 136 | except Exception as e: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 256 | except Exception as e: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 308 | except Exception as e: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 413 | except Exception as e: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 433 | except Exception as e: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 474 | except Exception as e: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 555 | except Exception as e: | CODE |
| LOW | …utogen-studio/autogenstudio/teammanager/teammanager.py | 74 | except Exception as e: | CODE |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 44 | except Exception as e: | CODE |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 108 | except Exception as e: | CODE |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 170 | except Exception as e: | CODE |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 186 | except Exception as e: | CODE |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 200 | except Exception as e: | CODE |
| 154 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | CONTRIBUTING.md | 0 | this subscription matches on topics based on the type and maps to agents using the source of the topic as the agent key. | STRING |
| HIGH | …gen-core/src/autogen_core/_type_prefix_subscription.py | 0 | this subscription matches on topics based on the type and maps to agents using the source of the topic as the agent key. | STRING |
| HIGH | …es/autogen-core/src/autogen_core/_type_subscription.py | 0 | this subscription matches on topics based on the type and maps to agents using the source of the topic as the agent key. | STRING |
| HIGH | …ang_hello_python_agent/protos/agent_events_pb2_grpc.py | 0 | client and server classes corresponding to protobuf-defined services. | STRING |
| HIGH | …togen-core/tests/protos/serialization_test_pb2_grpc.py | 0 | client and server classes corresponding to protobuf-defined services. | STRING |
| HIGH | …utogen-ext/tests/protos/serialization_test_pb2_grpc.py | 0 | client and server classes corresponding to protobuf-defined services. | STRING |
| HIGH | …utogen_ext/runtimes/grpc/protos/cloudevent_pb2_grpc.py | 0 | client and server classes corresponding to protobuf-defined services. | STRING |
| HIGH | …ogen_ext/runtimes/grpc/protos/agent_worker_pb2_grpc.py | 0 | client and server classes corresponding to protobuf-defined services. | STRING |
| HIGH | …ang_hello_python_agent/protos/agent_events_pb2_grpc.py | 0 | client and server classes corresponding to protobuf-defined services. | STRING |
| HIGH | python/samples/task_centric_memory/eval_retrieval.py | 0 | runs the code example with the necessary components. | STRING |
| HIGH | python/samples/task_centric_memory/eval_teachability.py | 0 | runs the code example with the necessary components. | STRING |
| HIGH | …thon/samples/task_centric_memory/eval_self_teaching.py | 0 | runs the code example with the necessary components. | STRING |
| HIGH | …ask_centric_memory/eval_learning_from_demonstration.py | 0 | runs the code example with the necessary components. | STRING |
| HIGH | …ench/benchmarks/GAIA/Templates/MagenticOne/scenario.py | 0 | we have completed the following task: {prompt} the above messages contain the conversation that took place to complete t | STRING |
| HIGH | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 0 | we have completed the following task: {prompt} the above messages contain the conversation that took place to complete t | STRING |
| HIGH | …enchmarks/GAIA/Templates/SelectorGroupChat/scenario.py | 0 | we have completed the following task: {prompt} the above messages contain the conversation that took place to complete t | STRING |
| HIGH | …packages/autogen-ext/tests/memory/test_redis_memory.py | 0 | test updating model context with retrieved memories. | STRING |
| HIGH | python/packages/autogen-ext/tests/memory/test_mem0.py | 0 | test updating model context with retrieved memories. | STRING |
| HIGH | …ackages/autogen-ext/tests/memory/test_chroma_memory.py | 0 | test updating model context with retrieved memories. | STRING |
| HIGH | python/packages/autogen-ext/tests/memory/test_mem0.py | 0 | test serialization and deserialization of component. | STRING |
| HIGH | …ackages/autogen-ext/tests/memory/test_chroma_memory.py | 0 | test serialization and deserialization of component. | STRING |
| HIGH | …utogen-ext/tests/models/test_anthropic_model_client.py | 0 | test serialization and deserialization of component. | STRING |
| HIGH | …s/autogen-ext/tests/models/test_openai_model_client.py | 0 | test tool_choice parameter with a specific tool using mocks. | STRING |
| HIGH | …autogen-ext/tests/models/test_azure_ai_model_client.py | 0 | test tool_choice parameter with a specific tool using mocks. | STRING |
| HIGH | …utogen-ext/tests/models/test_anthropic_model_client.py | 0 | test tool_choice parameter with a specific tool using mocks. | STRING |
| HIGH | …s/autogen-ext/tests/models/test_openai_model_client.py | 0 | test tool_choice parameter with 'auto' setting using mocks. | STRING |
| HIGH | …autogen-ext/tests/models/test_azure_ai_model_client.py | 0 | test tool_choice parameter with 'auto' setting using mocks. | STRING |
| HIGH | …utogen-ext/tests/models/test_anthropic_model_client.py | 0 | test tool_choice parameter with 'auto' setting using mocks. | STRING |
| HIGH | …gen-ext/tests/task_centric_memory/test_teachability.py | 0 | tests memory using the components specified in the config file. by default, mode is "replay", which uses a pre-recorded | STRING |
| HIGH | …ask_centric_memory/test_learning_from_demonstration.py | 0 | tests memory using the components specified in the config file. by default, mode is "replay", which uses a pre-recorded | STRING |
| HIGH | …en-ext/tests/task_centric_memory/test_self_teaching.py | 0 | tests memory using the components specified in the config file. by default, mode is "replay", which uses a pre-recorded | STRING |
| HIGH | …ext/src/autogen_ext/agents/file_surfer/_file_surfer.py | 0 | ensure that the messages are compatible with the underlying client, by removing images if needed. | STRING |
| HIGH | …tchat/src/autogen_agentchat/agents/_assistant_agent.py | 0 | ensure that the messages are compatible with the underlying client, by removing images if needed. | STRING |
| HIGH | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 0 | ensure that the messages are compatible with the underlying client, by removing images if needed. | STRING |
| HIGH | …group_chat/_magentic_one/_magentic_one_orchestrator.py | 0 | ensure that the messages are compatible with the underlying client, by removing images if needed. | STRING |
| HIGH | …n-ext/src/autogen_ext/models/azure/_azure_ai_client.py | 0 | llms sometimes ask functions while ignoring their own format requirements, this function should be used to replace inval | STRING |
| HIGH | …n_ext/models/llama_cpp/_llama_cpp_completion_client.py | 0 | llms sometimes ask functions while ignoring their own format requirements, this function should be used to replace inval | STRING |
| HIGH | …en-ext/src/autogen_ext/models/ollama/_ollama_client.py | 0 | llms sometimes ask functions while ignoring their own format requirements, this function should be used to replace inval | STRING |
| HIGH | …en-ext/src/autogen_ext/models/openai/_openai_client.py | 0 | llms sometimes ask functions while ignoring their own format requirements, this function should be used to replace inval | STRING |
| HIGH | …n-ext/src/autogen_ext/models/azure/_azure_ai_client.py | 0 | ensure that configured names are valid, raises valueerror if not. for munging llm responses use _normalize_name to ensur | STRING |
| HIGH | …n_ext/models/llama_cpp/_llama_cpp_completion_client.py | 0 | ensure that configured names are valid, raises valueerror if not. for munging llm responses use _normalize_name to ensur | STRING |
| HIGH | …en-ext/src/autogen_ext/models/ollama/_ollama_client.py | 0 | ensure that configured names are valid, raises valueerror if not. for munging llm responses use _normalize_name to ensur | STRING |
| HIGH | …es/autogen-ext/src/autogen_ext/models/openai/_utils.py | 0 | ensure that configured names are valid, raises valueerror if not. for munging llm responses use _normalize_name to ensur | STRING |
| HIGH | …xt/src/autogen_ext/models/anthropic/config/__init__.py | 0 | what functionality the model supports, determined by default from model name but is overriden if value passed. | STRING |
| HIGH | …n-ext/src/autogen_ext/models/ollama/config/__init__.py | 0 | what functionality the model supports, determined by default from model name but is overriden if value passed. | STRING |
| HIGH | …n-ext/src/autogen_ext/models/openai/config/__init__.py | 0 | what functionality the model supports, determined by default from model name but is overriden if value passed. | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| CRITICAL | python/packages/agbench/src/agbench/run_cmd.py | 20 | from azure.core.exceptions import ClientAuthenticationError | CODE |
| CRITICAL | …ackages/agbench/src/agbench/linter/coders/oai_coder.py | 54 | completion = self.client.beta.chat.completions.parse( | CODE |
| CRITICAL | …ackages/agbench/src/agbench/linter/coders/oai_coder.py | 159 | completion = self.client.beta.chat.completions.parse( | STRING |
| CRITICAL | …end/src/components/views/teambuilder/builder/store.tsx | 387 | teamNode.data.component.config.participants.push( | CODE |
| CRITICAL | …end/src/components/views/teambuilder/builder/store.tsx | 461 | participants: node.data.component.config.participants.map( | CODE |
| CRITICAL | …end/src/components/views/teambuilder/builder/store.tsx | 538 | teamNode.data.component.config.participants.filter( | CODE |
| CRITICAL | …s/autogen-ext/tests/tools/azure/test_ai_search_tool.py | 20 | from azure.core.exceptions import HttpResponseError, ResourceNotFoundError | CODE |
| CRITICAL | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 25 | from azure.core.exceptions import HttpResponseError, ResourceNotFoundError | CODE |
| CRITICAL | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 345 | msgs: AsyncCursorPage[Message] = await self._client.beta.threads.messages.list( # type: ignore[reportDeprec | CODE |
| CRITICAL | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 419 | self._client.beta.threads.runs.create( # type: ignore[reportDeprecated] | CODE |
| CRITICAL | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 430 | self._client.beta.threads.runs.retrieve( # type: ignore[reportDeprecated] | CODE |
| CRITICAL | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 483 | self._client.beta.threads.runs.submit_tool_outputs( # type: ignore[reportDeprecated] | CODE |
| CRITICAL | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 500 | self._client.beta.threads.messages.list(thread_id=self._thread_id, order="desc", limit=1) # type: ignor | CODE |
| CRITICAL | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 538 | self._client.beta.threads.messages.create( # type: ignore[reportDeprecated] | CODE |
| CRITICAL | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 556 | self._client.beta.threads.messages.list(self._thread_id, after=after, order="asc", limit=100) # typ | CODE |
| CRITICAL | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 570 | self._client.beta.threads.messages.delete(message_id=msg_id, thread_id=self._thread_id) # type: ign | CODE |
| CRITICAL | …en-ext/src/autogen_ext/models/openai/_openai_client.py | 684 | self._client.beta.chat.completions.parse( | CODE |
| CRITICAL | …en-ext/src/autogen_ext/models/openai/_openai_client.py | 1118 | async with self._client.beta.chat.completions.stream( | CODE |
| CRITICAL | docs/dotnet/core/index.md | 89 | var autogenBackend = await Microsoft.AutoGen.RuntimeGateway.Grpc.Host.StartAsync(local: false, useGrpc: true).ConfigureA | CODE |
| CRITICAL | dotnet/samples/Hello/HelloAIAgents/Program.cs | 27 | var app = await Microsoft.AutoGen.Core.Grpc.AgentsApp.PublishMessageAsync("HelloAgents", new NewMessageReceived | CODE |
| CRITICAL | dotnet/samples/Hello/HelloAgentState/Program.cs | 12 | var app = await Microsoft.AutoGen.Core.Grpc.AgentsApp.PublishMessageAsync("HelloAgents", new NewMessageReceived | CODE |
| CRITICAL | dotnet/src/Microsoft.AutoGen/Core.Grpc/RpcExtensions.cs | 39 | var any = Google.Protobuf.WellKnownTypes.Any.Parser.ParseFrom(data); | CODE |
| CRITICAL | dotnet/src/Microsoft.AutoGen/AgentHost/Program.cs | 5 | var app = await Microsoft.AutoGen.RuntimeGateway.Grpc.Host.StartAsync(local: false, useGrpc: true).ConfigureAwait(false) | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …_streaming_handoffs_fastapi/model_config_template.yaml | 1 | # Use Open AI with key | COMMENT |
| LOW | …_streaming_handoffs_fastapi/model_config_template.yaml | 21 | # azure_ad_token_provider: | COMMENT |
| LOW | …n/samples/agentchat_fastapi/model_config_template.yaml | 1 | # Use Open AI with key | COMMENT |
| LOW | …n/samples/agentchat_fastapi/model_config_template.yaml | 21 | # azure_ad_token_provider: | COMMENT |
| LOW | …core_async_human_in_the_loop/model_config_template.yml | 1 | # Use Open AI with key | COMMENT |
| LOW | …core_async_human_in_the_loop/model_config_template.yml | 21 | # azure_ad_token_provider: | COMMENT |
| LOW | …amples/agentchat_chess_game/model_config_template.yaml | 1 | # Use Open AI with key | COMMENT |
| LOW | …amples/agentchat_chess_game/model_config_template.yaml | 21 | # azure_endpoint: https://{your-custom-endpoint}.openai.azure.com/ | COMMENT |
| LOW | …_streaming_response_fastapi/model_config_template.yaml | 1 | # Use Open AI with key | COMMENT |
| LOW | …_streaming_response_fastapi/model_config_template.yaml | 21 | # azure_ad_token_provider: | COMMENT |
| LOW | …/samples/agentchat_graphrag/model_config_template.yaml | 1 | # Use Open AI with key | COMMENT |
| LOW | …/samples/agentchat_graphrag/model_config_template.yaml | 21 | # azure_ad_token_provider: | COMMENT |
| LOW | …thon/samples/core_chess_game/model_config_template.yml | 1 | # Use Open AI with key | COMMENT |
| LOW | …thon/samples/core_chess_game/model_config_template.yml | 21 | # azure_ad_token_provider: | COMMENT |
| LOW | python/samples/core_chainlit/model_config_template.yaml | 1 | # Use Open AI with key | COMMENT |
| LOW | python/samples/core_chainlit/model_config_template.yaml | 21 | # azure_ad_token_provider: | COMMENT |
| LOW | …/samples/agentchat_chainlit/model_config_template.yaml | 1 | # Use Open AI with key | COMMENT |
| LOW | …/samples/agentchat_chainlit/model_config_template.yaml | 21 | # azure_ad_token_provider: | COMMENT |
| LOW | python/packages/agbench/benchmarks/HumanEval/ENV.yaml | 1 | # ENV.yaml | COMMENT |
| LOW | python/packages/agbench/benchmarks/HumanEval/ENV.yaml | 21 | # config: | COMMENT |
| LOW | …thon/packages/agbench/benchmarks/HumanEval/config.yaml | 1 | # config.yaml | COMMENT |
| LOW | …thon/packages/agbench/benchmarks/HumanEval/config.yaml | 21 | # config: | COMMENT |
| LOW | python/packages/agbench/benchmarks/GAIA/ENV.yaml | 1 | # ENV.yaml | COMMENT |
| LOW | python/packages/agbench/benchmarks/GAIA/ENV.yaml | 21 | # config: | COMMENT |
| LOW | python/packages/agbench/benchmarks/GAIA/config.yaml | 1 | # config.yaml | COMMENT |
| LOW | python/packages/agbench/benchmarks/GAIA/config.yaml | 21 | # config: | COMMENT |
| LOW | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 221 | # api_key="your-api-key" | COMMENT |
| LOW | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 241 | # ), | COMMENT |
| LOW | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 261 | # "messages": [{"content": "The capital of France is Paris.", "source": "model"}] | COMMENT |
| LOW | python/packages/autogen-studio/frontend/tsconfig.json | 21 | // "jsxImportSource": "", /* Specify module specifier used to import the JSX factory func | COMMENT |
| LOW | python/packages/autogen-studio/frontend/tsconfig.json | 41 | // "checkJs": true, /* Enable error reporting in type-checked JavaScript files. */ | COMMENT |
| LOW | python/packages/autogen-studio/frontend/tsconfig.json | 61 | // "newLine": "crlf", /* Set the newline character for emitting files. */ | COMMENT |
| LOW | python/packages/autogen-studio/frontend/tsconfig.json | 81 | // "strictBindCallApply": true, /* Check that the arguments for `bind`, `call`, and `apply` met | COMMENT |
| LOW | …dio/frontend/src/components/views/settings/manager.tsx | 81 | // ), | COMMENT |
| LOW | …/frontend/src/components/views/settings/view/panel.tsx | 41 | // setLoading(true); | COMMENT |
| LOW | …-studio/frontend/src/components/views/gallery/types.ts | 1 | import { Gallery } from "../../types/datamodel"; | COMMENT |
| LOW | …teambuilder/builder/component-editor/fields/fields.tsx | 161 | } | COMMENT |
| LOW | …utogen-studio/frontend/src/components/views/mcp/api.ts | 601 | // ) { | COMMENT |
| LOW | …thon/packages/autogen-ext/tests/test_worker_runtime.py | 681 | assert agent.num_calls == 4 | COMMENT |
| LOW | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 181 | with pytest.raises(ValueError, match="uri is required for read_resource"): | COMMENT |
| LOW | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 201 | # # Give it a brief moment to queue the command | COMMENT |
| LOW | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 221 | # actor._command_queue = original_queue # type: ignore[reportPrivateUsage] | COMMENT |
| LOW | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 241 | # actor._actor_task = MagicMock() # type: ignore[reportPrivateUsage] | COMMENT |
| LOW | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 341 | mock_context = MagicMock(spec=RequestContext) | COMMENT |
| LOW | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 361 | # } | COMMENT |
| LOW | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 381 | # assert result.code == mcp_types.INVALID_PARAMS | COMMENT |
| LOW | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 921 | COMMENT | |
| LOW | …utogen-ext/tests/models/test_llama_cpp_model_client.py | 121 | COMMENT | |
| LOW | …utogen-ext/tests/models/test_llama_cpp_model_client.py | 221 | # repo_id="unsloth/phi-4-GGUF", filename="phi-4-Q2_K_L.gguf", n_gpu_layers=-1, seed=1337, n_ctx=5000 | COMMENT |
| LOW | …utogen-ext/tests/models/test_llama_cpp_model_client.py | 241 | # if not ((hasattr(torch.backends, "mps") and torch.backends.mps.is_available()) or torch.cuda.is_available()): | COMMENT |
| LOW | …utogen-ext/tests/models/test_llama_cpp_model_client.py | 261 | # reflect_on_tool_use=True, # Reflect on tool results | COMMENT |
| LOW | …n-ext/src/autogen_ext/runtimes/grpc/_worker_runtime.py | 201 | COMMENT | |
| LOW | …gen_ext/runtimes/grpc/_worker_runtime_host_servicer.py | 361 | # context: grpc.aio.ServicerContext[agent_worker_pb2.AgentId, agent_worker_pb2.SaveStateResponse], | COMMENT |
| LOW | …gen-ext/src/autogen_ext/agents/openai/_openai_agent.py | 341 | # { | COMMENT |
| LOW | .devcontainer/docker-compose.yml | 21 | # - SYS_PTRACE | COMMENT |
| LOW | dotnet/dotnet-install.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | …ests/Infrastructure/DistributedApplicationExtension.cs | 201 | /// <summary> | COMMENT |
| LOW | …ests/Infrastructure/DistributedApplicationExtension.cs | 241 | #pragma warning restore ASPIREHOSTINGPYTHON001 | COMMENT |
| LOW | …en.RuntimeGateway.Grpc.Tests/Helpers/AgentsMetadata.cs | 1 | // Copyright (c) Microsoft Corporation. All rights reserved. | COMMENT |
| LOW | …teway.Grpc.Tests/Helpers/Grpc/TestAsyncStreamReader.cs | 1 | #pragma warning disable IDE0073 | COMMENT |
| 132 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | …ogen-studio/autogenstudio/gallery/tools/bing_search.py | 24 | Perform a Bing search using the Bing Web Search API. Args: query: Search query string num_resu | STRING |
| HIGH | …en-studio/autogenstudio/gallery/tools/fetch_webpage.py | 14 | Fetch a webpage and convert it to markdown format. Args: url: The URL of the webpage to fetch inclu | STRING |
| HIGH | …ore/src/autogen_core/_single_threaded_agent_runtime.py | 289 | Create OpenTelemetry attributes for the given agent and message. Args: sender_agent (Agent, optiona | STRING |
| HIGH | …ackages/autogen-core/src/autogen_core/_subscription.py | 50 | Map a topic_id to an agent. Should only be called if `is_match` returns True for the given topic_id. Args: | STRING |
| HIGH | …kages/autogen-core/src/autogen_core/_function_utils.py | 221 | Get a JSON schema for a function as defined by the OpenAI API Args: f: The function to get the JSON schema | STRING |
| HIGH | python/packages/autogen-core/src/autogen_core/_agent.py | 34 | Message handler for the agent. This should only be called by the runtime, not by other agents. Args: | STRING |
| HIGH | …ges/autogen-core/src/autogen_core/_component_config.py | 208 | Load a component from a model. Intended to be used with the return type of :py:meth:`autogen_core.ComponentConfig.dump_c | STRING |
| HIGH | …ckages/autogen-core/src/autogen_core/_agent_runtime.py | 31 | Send a message to an agent and get a response. Args: message (Any): The message to send. | STRING |
| HIGH | …ckages/autogen-core/src/autogen_core/_agent_runtime.py | 189 | Try to get the underlying agent instance by name and namespace. This is generally discouraged (hence the long name), but | STRING |
| HIGH | …utogen-core/src/autogen_core/tool_agent/_tool_agent.py | 64 | Handles a `FunctionCall` message by executing the requested tool with the provided arguments. Args: | STRING |
| HIGH | …togen-core/src/autogen_core/utils/_json_to_pydantic.py | 378 | Convert a JSON Schema dictionary to a fully-typed Pydantic model. This function handles schema translation and | STRING |
| HIGH | …s/autogen-core/src/autogen_core/code_executor/_base.py | 57 | Execute code blocks and return the result. This method should be implemented by the code executor. Arg | STRING |
| HIGH | …kages/autogen-ext/examples/mcp_session_host_example.py | 48 | Load a ChatCompletionClient from a JSON or YAML config file. Args: config_path: Path to the JSON or YAML co | STRING |
| HIGH | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 359 | Process credential to ensure it's the correct type for async SearchClient. Converts dictionary credentials with | STRING |
| HIGH | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 418 | Execute a search against the Azure AI Search index. Args: args: Search query text or SearchQuery ob | STRING |
| HIGH | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 896 | Create a tool for pure vector/similarity search. This factory method creates an AzureAISearchTool optimized for | STRING |
| HIGH | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 1028 | Create a tool that combines vector and text search capabilities. This factory method creates an AzureAISearchTo | STRING |
| HIGH | …ackages/autogen-ext/src/autogen_ext/tools/mcp/_base.py | 58 | Run the MCP tool with the provided arguments. Args: args (BaseModel): The arguments to pas | STRING |
| HIGH | …ackages/autogen-ext/src/autogen_ext/tools/mcp/_base.py | 133 | Create an instance of McpToolAdapter from server parameters and tool name. Args: server_pa | STRING |
| HIGH | …ages/autogen-ext/src/autogen_ext/tools/mcp/_factory.py | 14 | Creates a list of MCP tool adapters that can be used with AutoGen agents. .. warning:: Only connect to tru | STRING |
| HIGH | …es/autogen-ext/src/autogen_ext/tools/mcp/_workbench.py | 48 | A workbench that wraps an MCP server and provides an interface to list and call tools provided by the server. . | STRING |
| HIGH | …togen-ext/src/autogen_ext/tools/mcp/_host/_sampling.py | 28 | Convert MCP content types to AutoGen content types. Handles text and image content conversion, with vision model va | STRING |
| HIGH | …togen-ext/src/autogen_ext/tools/mcp/_host/_sampling.py | 59 | Convert MCP sampling messages to AutoGen LLM messages. Args: message: MCP sampling message with role and co | STRING |
| HIGH | …s/autogen-ext/src/autogen_ext/tools/http/_http_tool.py | 197 | Execute the HTTP tool with the given arguments. Args: args: The validated input arguments | STRING |
| HIGH | …en-ext/src/autogen_ext/agents/azure/_azure_ai_agent.py | 543 | Execute a tool call requested by the Azure AI agent. Args: tool_call (FunctionCall): The f | STRING |
| HIGH | …en-ext/src/autogen_ext/agents/azure/_azure_ai_agent.py | 572 | Upload files to the Azure AI Assistant API. This method handles uploading one or more files to be used | STRING |
| HIGH | …en-ext/src/autogen_ext/agents/azure/_azure_ai_agent.py | 627 | Process incoming messages and return a response from the Azure AI agent. This method is the primary en | STRING |
| HIGH | …en-ext/src/autogen_ext/agents/azure/_azure_ai_agent.py | 658 | Process incoming messages and yield streaming responses from the Azure AI agent. This method handles t | STRING |
| HIGH | …en_ext/models/replay/_replay_chat_completion_client.py | 33 | A mock chat completion client that replays predefined responses using an index-based approach. This class simu | STRING |
| HIGH | …es/autogen-agentchat/src/autogen_agentchat/messages.py | 269 | :meta private: A component that creates structured chat messages from Pydantic models or JSON schemas. This co | STRING |
| HIGH | …tchat/src/autogen_agentchat/agents/_assistant_agent.py | 91 | An agent that provides assistance with tool use. The :meth:`on_messages` returns a :class:`~autogen_agentchat.base.R | STRING |
| HIGH | …en_agentchat/teams/_group_chat/_selector_group_chat.py | 363 | A group chat team that have participants takes turn to publish a message to all, using a ChatCompletion model to sel | STRING |
| HIGH | …agentchat/teams/_group_chat/_round_robin_group_chat.py | 97 | A team that runs a group chat with participants taking turns in a round-robin fashion to publish a message to all. | STRING |
| HIGH | …/_group_chat/_magentic_one/_magentic_one_group_chat.py | 37 | A team that runs a group chat with participants managed by the MagenticOneOrchestrator. The orchestrator handles th | STRING |
| HIGH | …n_agentchat/teams/_group_chat/_graph/_graph_builder.py | 120 | Add a directed edge from source to target, optionally with a condition. Args: source: Source node ( | STRING |
| HIGH | …ntchat/teams/_group_chat/_graph/_digraph_group_chat.py | 552 | A team that runs a group chat following a Directed Graph execution pattern. .. warning:: This is an experi | STRING |
| HIGH | …n-agentchat/src/autogen_agentchat/base/_termination.py | 60 | Check if the conversation should be terminated based on the messages received since the last time the condition | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/check_md_code_blocks.py | 17 | CODE | |
| LOW | python/check_md_code_blocks.py | 38 | CODE | |
| LOW | python/docs/src/generate_api_reference.py | 48 | CODE | |
| LOW | python/docs/src/generate_api_reference.py | 65 | CODE | |
| LOW | python/docs/src/generate_api_reference.py | 145 | CODE | |
| LOW | python/docs/src/conf.py | 186 | CODE | |
| LOW | python/docs/src/_extension/code_lint.py | 52 | CODE | |
| LOW | …/samples/core_streaming_handoffs_fastapi/agent_base.py | 48 | CODE | |
| LOW | python/samples/core_streaming_handoffs_fastapi/app.py | 194 | CODE | |
| LOW | python/samples/agentchat_fastapi/app_team.py | 96 | CODE | |
| LOW | python/samples/gitty/src/gitty/__main__.py | 42 | CODE | |
| LOW | python/samples/core_chainlit/app_team.py | 160 | CODE | |
| LOW | python/samples/agentchat_chainlit/app_team.py | 68 | CODE | |
| LOW | …thon/samples/agentchat_chainlit/app_team_user_proxy.py | 108 | CODE | |
| LOW | python/packages/agbench/benchmarks/process_logs.py | 84 | CODE | |
| LOW | …ges/agbench/benchmarks/GAIA/Scripts/custom_tabulate.py | 36 | CODE | |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 154 | CODE | |
| LOW | …h/benchmarks/GAIA/Templates/ParallelAgents/scenario.py | 70 | CODE | |
| LOW | …enchmarks/GAIA/Templates/SelectorGroupChat/scenario.py | 25 | CODE | |
| LOW | …enchmarks/GAIA/Templates/SelectorGroupChat/scenario.py | 144 | CODE | |
| LOW | …hon/packages/agbench/src/agbench/remove_missing_cmd.py | 31 | CODE | |
| LOW | python/packages/agbench/src/agbench/tabulate_cmd.py | 68 | CODE | |
| LOW | python/packages/agbench/src/agbench/run_cmd.py | 59 | CODE | |
| LOW | python/packages/agbench/src/agbench/run_cmd.py | 181 | CODE | |
| LOW | python/packages/agbench/src/agbench/run_cmd.py | 269 | CODE | |
| LOW | python/packages/agbench/src/agbench/run_cmd.py | 342 | CODE | |
| LOW | python/packages/agbench/src/agbench/run_cmd.py | 869 | CODE | |
| LOW | python/packages/agbench/src/agbench/run_cmd.py | 353 | CODE | |
| LOW | python/packages/agbench/src/agbench/run_cmd.py | 364 | CODE | |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 108 | CODE | |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 165 | CODE | |
| LOW | …es/autogen-studio/autogenstudio/database/db_manager.py | 245 | CODE | |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 47 | CODE | |
| LOW | …utogen-studio/autogenstudio/teammanager/teammanager.py | 109 | CODE | |
| LOW | …utogen-studio/autogenstudio/teammanager/teammanager.py | 154 | CODE | |
| LOW | …n/packages/autogen-studio/autogenstudio/lite/studio.py | 52 | CODE | |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 261 | CODE | |
| LOW | …ckages/autogen-studio/autogenstudio/web/auth/wsauth.py | 17 | CODE | |
| LOW | …kages/autogen-studio/autogenstudio/web/auth/manager.py | 28 | CODE | |
| LOW | …es/autogen-studio/autogenstudio/web/auth/middleware.py | 88 | CODE | |
| LOW | …utogen-studio/autogenstudio/web/managers/connection.py | 85 | CODE | |
| LOW | …utogen-studio/autogenstudio/web/managers/connection.py | 282 | CODE | |
| LOW | …utogen-studio/autogenstudio/web/managers/connection.py | 344 | CODE | |
| LOW | …es/autogen-studio/autogenstudio/web/routes/sessions.py | 66 | CODE | |
| LOW | …packages/autogen-studio/autogenstudio/web/routes/ws.py | 21 | CODE | |
| LOW | …ackages/autogen-studio/autogenstudio/web/routes/mcp.py | 134 | CODE | |
| LOW | …ogen-studio/autogenstudio/gallery/tools/bing_search.py | 13 | CODE | |
| LOW | …en-studio/autogenstudio/gallery/tools/google_search.py | 12 | CODE | |
| LOW | …togen-studio/autogenstudio/gallery/tools/calculator.py | 4 | CODE | |
| LOW | …n/packages/autogen-studio/autogenstudio/utils/utils.py | 10 | CODE | |
| LOW | …on/packages/autogen-studio/autogenstudio/mcp/client.py | 63 | CODE | |
| LOW | …/packages/autogen-studio/autogenstudio/mcp/wsbridge.py | 137 | CODE | |
| LOW | …hon/packages/autogen-studio/autogenstudio/mcp/utils.py | 42 | CODE | |
| LOW | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 174 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 120 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 202 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 520 | CODE | |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 697 | CODE | |
| LOW | …/packages/autogen-studio/autogenstudio/eval/runners.py | 157 | CODE | |
| LOW | …-studio/autogenstudio/validation/validation_service.py | 114 | CODE | |
| 118 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | …s/autogen-ext/tests/models/test_openai_model_client.py | 495 | # Step 1: Mock the Image class with only the 'image' attribute | COMMENT |
| LOW⚡ | …ask_centric_memory/sessions/self_teaching/session.json | 262 | "content": "### Step 1: Understanding the User Message\n\nThe user presents a classic logic puzzle often referred | CODE |
| LOW⚡ | …ask_centric_memory/sessions/self_teaching/session.json | 286 | "### Step 1: Understanding the User Message\n\nThe user presents a classic logic puzzle often referred to as t | CODE |
| LOW | …ask_centric_memory/sessions/self_teaching/session.json | 704 | "content": "### Step 1: Understanding the User Message\n\nThe user has presented a classic liar puzzle. The scenar | CODE |
| LOW | …ask_centric_memory/sessions/self_teaching/session.json | 728 | "### Step 1: Understanding the User Message\n\nThe user has presented a classic liar puzzle. The scenario invo | CODE |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 217 | # Step 1: First code generation | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 224 | # Step 2: First code execution | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 231 | # Step 3: Retry generation with proposed correction | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 239 | # Step 4: Second retry code generation | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 246 | # Step 5: Second retry code execution | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 253 | # Step 6: Final response | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 549 | # Step 1: Add new user/handoff messages to the model context | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 555 | # Step 2: Run inference with the model context | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 579 | # Step 4: Add the assistant message to the model context (including thought if present) | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 588 | # Step 5: Extract the code blocks from inferred text | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 592 | # Step 6: Exit the loop if no code blocks found | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 602 | # Step 7: Yield a CodeGenerationEvent | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 612 | # Step 8: Execute the extracted code blocks | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 615 | # Step 9: Update model context with the code execution result | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 623 | # Step 10: Yield a CodeExecutionEvent | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 630 | # Step 11: If exit code is non-zero and retries are available then | COMMENT |
| LOW | …n.RuntimeGateway.Grpc.Tests/GrpcGatewayServiceTests.cs | 61 | // Step 4: Verify that the agent receives the control message | COMMENT |
| LOW⚡ | dotnet/website/tutorial/Image-chat-with-agent.md | 16 | ## Step 1: Install AutoGen | COMMENT |
| LOW⚡ | dotnet/website/tutorial/Image-chat-with-agent.md | 24 | ## Step 2: Add Using Statements | COMMENT |
| LOW⚡ | dotnet/website/tutorial/Image-chat-with-agent.md | 28 | ## Step 3: Create an @AutoGen.OpenAI.OpenAIChatAgent | COMMENT |
| LOW⚡ | dotnet/website/tutorial/Image-chat-with-agent.md | 32 | ## Step 4: Prepare Image Message | COMMENT |
| LOW⚡ | dotnet/website/tutorial/Image-chat-with-agent.md | 42 | ## Step 5: Generate Response | COMMENT |
| LOW | …utorial/Use-AutoGen.Net-agent-as-model-in-AG-Studio.md | 36 | ## Step 3: Start the web app | COMMENT |
| LOW | …utorial/Use-AutoGen.Net-agent-as-model-in-AG-Studio.md | 48 | ## Step 4: In another terminal, start autogen-studio | COMMENT |
| LOW | …utorial/Use-AutoGen.Net-agent-as-model-in-AG-Studio.md | 54 | ## Step 5: Navigate to AutoGen Studio UI and add hello world agent as openai Model | COMMENT |
| LOW | …utorial/Use-AutoGen.Net-agent-as-model-in-AG-Studio.md | 70 | ## Step 6: Create a hello world agent that uses the hello world model | COMMENT |
| LOW⚡ | dotnet/website/tutorial/Chat-with-an-agent.md | 16 | ## Step 1: Install AutoGen | COMMENT |
| LOW⚡ | dotnet/website/tutorial/Chat-with-an-agent.md | 24 | ## Step 2: add Using Statements | COMMENT |
| LOW⚡ | dotnet/website/tutorial/Chat-with-an-agent.md | 28 | ## Step 3: Create an @AutoGen.OpenAI.OpenAIChatAgent | COMMENT |
| LOW⚡ | dotnet/website/tutorial/Chat-with-an-agent.md | 36 | ## Step 4: Generate Response | COMMENT |
| LOW⚡ | …site/articles/AutoGen.Gemini/Image-chat-with-gemini.md | 9 | ### Step 1: Install AutoGen.Gemini | COMMENT |
| LOW⚡ | …site/articles/AutoGen.Gemini/Image-chat-with-gemini.md | 17 | ### Step 2: Add using statement | COMMENT |
| LOW⚡ | …site/articles/AutoGen.Gemini/Image-chat-with-gemini.md | 20 | ### Step 3: Create a Gemini agent | COMMENT |
| LOW⚡ | …site/articles/AutoGen.Gemini/Image-chat-with-gemini.md | 24 | ### Step 4: Send image to Gemini | COMMENT |
| LOW⚡ | …ite/articles/AutoGen.Gemini/Chat-with-google-gemini.md | 13 | ### Step 1: Install AutoGen.Gemini | COMMENT |
| LOW⚡ | …ite/articles/AutoGen.Gemini/Chat-with-google-gemini.md | 21 | ### Step 2: Add using statement | COMMENT |
| LOW⚡ | …ite/articles/AutoGen.Gemini/Chat-with-google-gemini.md | 25 | ### Step 3: Create a Gemini agent | COMMENT |
| LOW⚡ | …ite/articles/AutoGen.Gemini/Chat-with-google-gemini.md | 29 | ### Step 4: Chat with Gemini | COMMENT |
| LOW⚡ | …ite/articles/AutoGen.Gemini/Chat-with-vertex-gemini.md | 13 | ### Step 1: Install AutoGen.Gemini | COMMENT |
| LOW⚡ | …ite/articles/AutoGen.Gemini/Chat-with-vertex-gemini.md | 21 | ### Step 2: Add using statement | COMMENT |
| LOW⚡ | …ite/articles/AutoGen.Gemini/Chat-with-vertex-gemini.md | 25 | ### Step 3: Create a Gemini agent | COMMENT |
| LOW⚡ | …ite/articles/AutoGen.Gemini/Chat-with-vertex-gemini.md | 30 | ### Step 4: Chat with Gemini | COMMENT |
| LOW | …e/articles/AutoGen.Gemini/Function-call-with-gemini.md | 9 | ### Step 1: Install AutoGen.Gemini and AutoGen.SourceGenerator | COMMENT |
| LOW⚡ | …e/articles/AutoGen.Gemini/Function-call-with-gemini.md | 20 | ### Step 2: Add using statement | COMMENT |
| LOW⚡ | …e/articles/AutoGen.Gemini/Function-call-with-gemini.md | 23 | ### Step 3: Create `MovieFunction` | COMMENT |
| LOW⚡ | …e/articles/AutoGen.Gemini/Function-call-with-gemini.md | 27 | ### Step 4: Create a Gemini agent | COMMENT |
| LOW⚡ | …e/articles/AutoGen.Gemini/Function-call-with-gemini.md | 31 | ### Step 5: Single turn function call | COMMENT |
| LOW⚡ | …e/articles/AutoGen.Gemini/Function-call-with-gemini.md | 35 | ### Step 6: Multi-turn function call | COMMENT |
| LOW⚡ | ….SemanticKernel/SemanticKernelChatAgent-simple-chat.md | 8 | ### Step 1: add using statement | COMMENT |
| LOW⚡ | ….SemanticKernel/SemanticKernelChatAgent-simple-chat.md | 11 | ### Step 2: create kernel | COMMENT |
| LOW⚡ | ….SemanticKernel/SemanticKernelChatAgent-simple-chat.md | 14 | ### Step 3: create ChatCompletionAgent | COMMENT |
| LOW⚡ | ….SemanticKernel/SemanticKernelChatAgent-simple-chat.md | 17 | ### Step 4: create @AutoGen.SemanticKernel.SemanticKernelChatCompletionAgent | COMMENT |
| LOW⚡ | ….SemanticKernel/SemanticKernelChatAgent-simple-chat.md | 21 | ### Step 5: chat with @AutoGen.SemanticKernel.SemanticKernelChatCompletionAgent | COMMENT |
| LOW⚡ | …en.SemanticKernel/Use-kernel-plugin-in-other-agents.md | 8 | ### Step 1: add using statement | COMMENT |
| LOW⚡ | …en.SemanticKernel/Use-kernel-plugin-in-other-agents.md | 11 | ### Step 2: create plugin | COMMENT |
| 9 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | …autogen-ext/tests/tools/azure/test_ai_search_config.py | 14 | # ===================================== | COMMENT |
| MEDIUM⚡ | …autogen-ext/tests/tools/azure/test_ai_search_config.py | 16 | # ===================================== | COMMENT |
| MEDIUM⚡ | …autogen-ext/tests/tools/azure/test_ai_search_config.py | 93 | # ===================================== | COMMENT |
| MEDIUM⚡ | …autogen-ext/tests/tools/azure/test_ai_search_config.py | 95 | # ===================================== | COMMENT |
| MEDIUM⚡ | …autogen-ext/tests/tools/azure/test_ai_search_config.py | 173 | # ===================================== | COMMENT |
| MEDIUM⚡ | …autogen-ext/tests/tools/azure/test_ai_search_config.py | 175 | # ===================================== | COMMENT |
| MEDIUM⚡ | …autogen-ext/tests/tools/azure/test_ai_search_config.py | 217 | # ===================================== | COMMENT |
| MEDIUM⚡ | …autogen-ext/tests/tools/azure/test_ai_search_config.py | 219 | # ===================================== | COMMENT |
| MEDIUM | …es/autogen-ext/tests/memory/test_text_canvas_memory.py | 13 | # ── Fixtures ───────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM⚡ | …es/autogen-ext/tests/memory/test_text_canvas_memory.py | 39 | # ── Tests ──────────────────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM⚡ | …ackages/autogen-ext/tests/memory/test_chroma_memory.py | 277 | # ============================================================================ | COMMENT |
| MEDIUM⚡ | …ackages/autogen-ext/tests/memory/test_chroma_memory.py | 279 | # ============================================================================ | COMMENT |
| MEDIUM⚡ | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 39 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 41 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 49 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 51 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 61 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 63 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 95 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 97 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 181 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …ogen-ext/src/autogen_ext/memory/canvas/_text_canvas.py | 183 | # ---------------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …utogen_ext/agents/web_surfer/_multimodal_web_surfer.py | 606 | # =================================================== | COMMENT |
| MEDIUM | …/src/autogen_agentchat/agents/_message_filter_agent.py | 10 | # ------------------------------ | COMMENT |
| MEDIUM | …/src/autogen_agentchat/agents/_message_filter_agent.py | 12 | # ------------------------------ | COMMENT |
| MEDIUM⚡ | …/src/autogen_agentchat/agents/_message_filter_agent.py | 25 | # ------------------------------ | COMMENT |
| MEDIUM⚡ | …/src/autogen_agentchat/agents/_message_filter_agent.py | 27 | # ------------------------------ | COMMENT |
| MEDIUM⚡ | …/src/autogen_agentchat/agents/_message_filter_agent.py | 36 | # ------------------------------ | COMMENT |
| MEDIUM⚡ | …/src/autogen_agentchat/agents/_message_filter_agent.py | 38 | # ------------------------------ | COMMENT |
| MEDIUM | …/Microsoft.AutoGen/AgentChat/Abstractions/ChatAgent.cs | 52 | # ================================================ | COMMENT |
| MEDIUM | …/Microsoft.AutoGen/AgentChat/Abstractions/ChatAgent.cs | 63 | # ================================================ | COMMENT |
| MEDIUM | …/Microsoft.AutoGen/AgentChat/Abstractions/ChatAgent.cs | 77 | # ================================================ | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/run_task_in_pkgs_if_exist.py | 44 | # Check if there is an include too | COMMENT |
| LOW | python/docs/redirects/redirects.py | 44 | # Read file | COMMENT |
| LOW | python/docs/src/generate_api_reference.py | 55 | # Check if this package is in our documented packages list | COMMENT |
| LOW | python/docs/src/conf.py | 207 | # Print the output for visibility | COMMENT |
| LOW⚡ | python/samples/core_streaming_handoffs_fastapi/app.py | 229 | if content: # Check if file is not empty | CODE |
| LOW | python/samples/agentchat_chess_game/main.py | 86 | # Check if the response is a valid UC move. | COMMENT |
| LOW | python/samples/agentchat_chess_game/main.py | 92 | # Check if the move is legal. | COMMENT |
| LOW⚡ | python/samples/agentchat_chess_game/main.py | 113 | # Check if the game is over. | COMMENT |
| LOW⚡ | python/samples/agentchat_graphrag/app.py | 35 | # Check if OPENAI_API_KEY is set | COMMENT |
| LOW | python/packages/agbench/benchmarks/process_logs.py | 156 | # Check if the agent stalled | COMMENT |
| LOW | …ges/agbench/benchmarks/HumanEval/Scripts/init_tasks.py | 70 | # Read the file, line by line, populating a list of parsed JSON objects | COMMENT |
| LOW | python/packages/agbench/src/agbench/run_cmd.py | 660 | # Check if we need to terminate | STRING |
| LOW | …n/packages/autogen-studio/autogenstudio/lite/studio.py | 177 | # Check if already running | COMMENT |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 94 | # Check if auth is explicitly disabled via environment variable | COMMENT |
| LOW | …hon/packages/autogen-studio/autogenstudio/web/serve.py | 18 | # Check if team_file_path is set | COMMENT |
| LOW | …kages/autogen-studio/autogenstudio/web/auth/manager.py | 63 | # Check if path should be excluded from auth | COMMENT |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 319 | # Check if run is already active | COMMENT |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 503 | # Check if run is active | COMMENT |
| LOW | …dio/autogenstudio/validation/component_test_service.py | 58 | # Check if we got a valid response | COMMENT |
| LOW | …hon/packages/autogen-studio/tests/test_team_manager.py | 91 | # Check if at least one team has expected label | COMMENT |
| LOW | python/packages/autogen-core/tests/test_runtime.py | 192 | # Check if logger has the exception. | COMMENT |
| LOW | …autogen-core/src/autogen_core/_runtime_impl_helpers.py | 43 | # Check if the subscription already exists | COMMENT |
| LOW | …autogen-core/src/autogen_core/_runtime_impl_helpers.py | 51 | # Check if the subscription exists | COMMENT |
| LOW | …togen-core/src/autogen_core/tools/_static_workbench.py | 101 | # Check if the name is an override name and map it back to the original | COMMENT |
| LOW | …/autogen-core/src/autogen_core/tools/_function_tool.py | 78 | # Output the result as a formatted string. | STRING |
| LOW | …hon/packages/autogen-ext/tests/tools/test_mcp_tools.py | 629 | # Check if GITHUB_TOKEN is set. | COMMENT |
| LOW | …utogen-ext/tests/tools/graphrag/test_graphrag_tools.py | 192 | # Check if the log contains the expected message | COMMENT |
| LOW | …utogen-ext/tests/tools/graphrag/test_graphrag_tools.py | 256 | # Check if the log contains the expected message | COMMENT |
| LOW | …s/autogen-ext/tests/models/test_openai_model_client.py | 2152 | # Check if the model is running locally. | COMMENT |
| LOW | …ext/tests/models/test_ollama_chat_completion_client.py | 480 | # Check if the model is running locally. | COMMENT |
| LOW | …ts/code_executors/test_docker_jupyter_code_executor.py | 123 | # Check if the file was created | STRING |
| LOW | …ode_executors/test_docker_commandline_code_executor.py | 149 | # Check if the file was not created | STRING |
| LOW⚡ | …tests/code_executors/test_commandline_code_executor.py | 203 | # Check if the file is not created. | STRING |
| LOW | …tests/code_executors/test_commandline_code_executor.py | 305 | # Check if the expected venv has been used | STRING |
| LOW | …tests/code_executors/test_commandline_code_executor.py | 361 | # Check if the expected venv has been used | STRING |
| LOW | …/experimental/task_centric_memory/memory_controller.py | 175 | # Check if the response is correct. | COMMENT |
| LOW | …/experimental/task_centric_memory/utils/page_logger.py | 411 | # Check if it's a method by looking for 'self' or 'cls' in f_locals | COMMENT |
| LOW | …es/autogen-ext/src/autogen_ext/tools/mcp/_workbench.py | 332 | # Check if the name is an override name and map it back to the original | COMMENT |
| LOW | …kages/autogen-ext/src/autogen_ext/memory/mem0/_mem0.py | 250 | # Check if operation is cancelled | COMMENT |
| LOW | …kages/autogen-ext/src/autogen_ext/memory/mem0/_mem0.py | 290 | # Check if operation is cancelled | COMMENT |
| LOW | …togen_ext/agents/file_surfer/_markdown_file_browser.py | 82 | # Check if the path is within the base path | COMMENT |
| LOW | …en-ext/src/autogen_ext/agents/azure/_azure_ai_agent.py | 1027 | # Check if file_search is enabled in tools | COMMENT |
| LOW | …utogen_ext/agents/web_surfer/_multimodal_web_surfer.py | 654 | # Check if the argument starts with a known protocol | COMMENT |
| LOW | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 631 | # Check if file_search is enabled in tools | COMMENT |
| LOW | …/models/semantic_kernel/_sk_chat_completion_adapter.py | 311 | # Check if it's a function-call style message | COMMENT |
| LOW | …/models/semantic_kernel/_sk_chat_completion_adapter.py | 668 | # Check if the model signaled tool_calls finished | COMMENT |
| LOW⚡ | …/src/autogen_ext/models/anthropic/_anthropic_client.py | 530 | # Check if thinking is specified in extra_create_args (priority) | COMMENT |
| LOW⚡ | …/src/autogen_ext/models/anthropic/_anthropic_client.py | 533 | # Check if thinking is specified in base create_args | COMMENT |
| LOW | …/src/autogen_ext/models/anthropic/_anthropic_client.py | 356 | # Check if the tool has a valid name | COMMENT |
| LOW | …/src/autogen_ext/models/anthropic/_anthropic_client.py | 704 | # Check if the response includes tool uses | COMMENT |
| LOW | …/src/autogen_ext/models/anthropic/_anthropic_client.py | 844 | # Check if any message is a tool result | COMMENT |
| LOW | …n_ext/models/llama_cpp/_llama_cpp_completion_client.py | 108 | # Check if all tools have valid names. | COMMENT |
| LOW | …en-ext/src/autogen_ext/models/ollama/_ollama_client.py | 345 | # Check if all tools have valid names. | COMMENT |
| LOW | …en-ext/src/autogen_ext/models/openai/_openai_client.py | 268 | # Check if all tools have valid names. | COMMENT |
| LOW | …xt/src/autogen_ext/models/openai/_message_transform.py | 203 | # Check if name should be included in message | COMMENT |
| LOW | …/autogen-ext/src/autogen_ext/code_executors/_common.py | 163 | # Check if pwsh is available, otherwise fall back to powershell | COMMENT |
| LOW | …gen_ext/code_executors/docker/_docker_code_executor.py | 344 | # Check if there is a filename comment | COMMENT |
| LOW | …gen_ext/code_executors/docker/_docker_code_executor.py | 517 | # Check if the image exists | COMMENT |
| LOW | …gen_ext/code_executors/docker/_docker_code_executor.py | 530 | # Check if a container with the same name already exists and remove it | COMMENT |
| LOW | …gen_ext/code_executors/docker/_docker_code_executor.py | 562 | # Check if the container is running | COMMENT |
| 29 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/check_md_code_blocks.py | 13 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/docs/src/_extension/code_lint.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/docs/src/_extension/gallery_directive.py | 22 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/samples/agentchat_fastapi/app_team.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | python/samples/gitty/src/gitty/__init__.py | 3 | __all__ = ["main"] | CODE |
| LOW | python/samples/gitty/src/gitty/_db.py | 29 | def update_issue(db_path: str, number: int, title: str, updatedAt: str, content: str) -> None: | STRING |
| LOW | python/samples/gitty/src/gitty/_db.py | 43 | def update_chroma(gitty_dir: str, db_path: str) -> None: | STRING |
| LOW | python/packages/agbench/src/agbench/linter/__init__.py | 4 | __all__ = ["Code", "Document", "CodedDocument", "BaseQualitativeCoder"] | CODE |
| LOW | …thon/packages/autogen-studio/autogenstudio/__init__.py | 6 | __all__ = ["DatabaseManager", "Team", "TeamManager", "__version__"] | CODE |
| LOW | …ages/autogen-studio/autogenstudio/database/__init__.py | 3 | __all__ = [ | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 72 | def _update_configuration(self) -> None: | CODE |
| LOW | …utogen-studio/autogenstudio/database/schema_manager.py | 260 | def _update_env_py(self, env_path: Path) -> None: | CODE |
| LOW | …s/autogen-studio/autogenstudio/teammanager/__init__.py | 3 | __all__ = ["TeamManager"] | CODE |
| LOW | …utogen-studio/autogenstudio/teammanager/teammanager.py | 21 | logger = logging.getLogger(__name__) | CODE |
| LOW | …packages/autogen-studio/autogenstudio/lite/__init__.py | 3 | __all__ = ["LiteStudio"] | CODE |
| LOW | …thon/packages/autogen-studio/autogenstudio/web/deps.py | 18 | logger = logging.getLogger(__name__) | CODE |
| LOW | …ages/autogen-studio/autogenstudio/web/auth/__init__.py | 9 | __all__ = [ | CODE |
| LOW | …utogen-studio/autogenstudio/web/managers/connection.py | 39 | logger = logging.getLogger(__name__) | CODE |
| LOW | …utogen-studio/autogenstudio/web/managers/connection.py | 424 | async def _update_run_status(self, run_id: int, status: RunStatus, error: Optional[str] = None) -> None: | CODE |
| LOW | …kages/autogen-studio/autogenstudio/gallery/__init__.py | 3 | __all__ = ["GalleryBuilder", "create_default_gallery"] | CODE |
| LOW | …autogen-studio/autogenstudio/gallery/tools/__init__.py | 7 | __all__ = [ | CODE |
| LOW | …/packages/autogen-studio/autogenstudio/mcp/wsbridge.py | 92 | def set_mcp_client(self, mcp_client: MCPClient) -> None: | CODE |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 568 | async def _update_run_status(self, run_id: str, status: EvalRunStatus) -> None: | CODE |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 592 | async def _update_run_result(self, run_id: str, run_result: EvalRunResult) -> None: | CODE |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 616 | async def _update_score_result(self, run_id: str, score_result: EvalScore) -> None: | CODE |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 640 | async def _update_run_completed(self, run_id: str, start_time: datetime, end_time: datetime) -> None: | CODE |
| LOW | …ages/autogen-studio/autogenstudio/eval/orchestrator.py | 669 | async def _update_run_error(self, run_id: str, error_message: str) -> None: | CODE |
| LOW | …ges/autogen-studio/autogenstudio/datamodel/__init__.py | 16 | __all__ = [ | CODE |
| LOW | …ackages/autogen-core/src/autogen_core/_intervention.py | 6 | __all__ = [ | CODE |
| LOW | …hon/packages/autogen-core/src/autogen_core/__init__.py | 87 | __all__ = [ | CODE |
| LOW | …n/packages/autogen-core/src/autogen_core/exceptions.py | 1 | __all__ = ["CantHandleException", "UndeliverableException", "MessageDroppedException", "NotAccessibleError"] | CODE |
| LOW | …ckages/autogen-core/src/autogen_core/tools/__init__.py | 15 | __all__ = [ | CODE |
| LOW | …kages/autogen-core/src/autogen_core/memory/__init__.py | 4 | __all__ = [ | CODE |
| LOW | …s/autogen-core/src/autogen_core/_telemetry/__init__.py | 15 | __all__ = [ | CODE |
| LOW | …s/autogen-core/src/autogen_core/tool_agent/__init__.py | 10 | __all__ = [ | CODE |
| LOW | …utogen-core/src/autogen_core/tool_agent/_tool_agent.py | 9 | __all__ = [ | CODE |
| LOW | …utogen-core/src/autogen_core/model_context/__init__.py | 9 | __all__ = [ | CODE |
| LOW | …ckages/autogen-core/src/autogen_core/utils/__init__.py | 4 | __all__ = ["schema_to_pydantic_model", "extract_json_from_str"] | CODE |
| LOW | …kages/autogen-core/src/autogen_core/models/__init__.py | 22 | __all__ = [ | CODE |
| LOW | …utogen-core/src/autogen_core/code_executor/__init__.py | 11 | __all__ = [ | CODE |
| LOW | …packages/autogen-ext/tests/mcp_server_comprehensive.py | 26 | logger = logging.getLogger(__name__) | CODE |
| LOW⚡ | …ts/agents/test_openai_agent_builtin_tool_validation.py | 19 | def set_dummy_openai_key(monkeypatch: MonkeyPatch) -> None: | CODE |
| LOW | …kages/autogen-ext/examples/mcp_session_host_example.py | 43 | logger = logging.getLogger(__name__) | CODE |
| LOW | …on/packages/autogen-ext/src/autogen_ext/ui/__init__.py | 7 | __all__ = ["RichConsole"] | CODE |
| LOW | …togen_ext/experimental/task_centric_memory/__init__.py | 4 | __all__ = ["MemoryController", "MemoryControllerConfig", "MemoryBankConfig"] | CODE |
| LOW | …ext/experimental/task_centric_memory/utils/__init__.py | 7 | __all__ = [ | CODE |
| LOW | …utogen-ext/src/autogen_ext/tools/langchain/__init__.py | 3 | __all__ = ["LangChainToolAdapter"] | CODE |
| LOW | …es/autogen-ext/src/autogen_ext/tools/azure/__init__.py | 11 | __all__ = [ | CODE |
| LOW | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 44 | logger = logging.getLogger(__name__) | CODE |
| LOW | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 74 | __all__ = [ | CODE |
| LOW | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 84 | logger = logging.getLogger(__name__) | CODE |
| LOW | …ges/autogen-ext/src/autogen_ext/tools/azure/_config.py | 23 | logger = logging.getLogger(__name__) | CODE |
| LOW | …autogen-ext/src/autogen_ext/tools/graphrag/__init__.py | 12 | __all__ = [ | CODE |
| LOW | …ages/autogen-ext/src/autogen_ext/tools/mcp/__init__.py | 23 | __all__ = [ | CODE |
| LOW | …ckages/autogen-ext/src/autogen_ext/tools/mcp/_actor.py | 18 | logger = logging.getLogger(__name__) | CODE |
| LOW | …utogen-ext/src/autogen_ext/tools/mcp/_host/__init__.py | 6 | __all__ = [ | CODE |
| LOW | …ges/autogen-ext/src/autogen_ext/tools/http/__init__.py | 3 | __all__ = ["HttpTool"] | CODE |
| LOW | …-ext/src/autogen_ext/tools/semantic_kernel/__init__.py | 3 | __all__ = [ | CODE |
| LOW | …n-ext/src/autogen_ext/tools/code_execution/__init__.py | 3 | __all__ = ["CodeExecutionInput", "CodeExecutionResult", "PythonCodeExecutionTool"] | CODE |
| LOW | …utogen-ext/src/autogen_ext/memory/chromadb/__init__.py | 12 | __all__ = [ | CODE |
| 51 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | …on/docs/src/user-guide/autogenstudio-user-guide/faq.md | 44 | api_key="your-api-key", # Optional if ANTHROPIC_API_KEY is set in environment | CODE |
| HIGH | …on/docs/src/user-guide/autogenstudio-user-guide/faq.md | 104 | "api_key": "your-api-key" | CODE |
| HIGH | python/samples/gitty/src/gitty/__main__.py | 18 | print(" export OPENAI_API_KEY='your-api-key'") | CODE |
| HIGH | python/samples/agentchat_graphrag/README.md | 43 | export OPENAI_API_KEY='your-api-key-here' | CODE |
| HIGH⚡ | python/samples/agentchat_graphrag/app.py | 39 | print("Please run: export OPENAI_API_KEY='your-api-key-here'") | CODE |
| HIGH | …ckages/autogen-studio/autogenstudio/gallery/builder.py | 546 | headers={"Authorization": "Bearer your-api-key", "Content-Type": "application/json"}, | CODE |
| HIGH⚡ | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 221 | # api_key="your-api-key" | COMMENT |
| HIGH | …ckages/autogen-studio/autogenstudio/datamodel/types.py | 108 | model="gpt-4o-mini", api_key="your-api-key" | CODE |
| HIGH | …tend/src/components/views/gallery/default_gallery.json | 1158 | "Authorization": "Bearer your-api-key", | CODE |
| HIGH | …kages/autogen-ext/examples/mcp_session_host_example.py | 179 | "api_key": "your-api-key" | CODE |
| HIGH | …packages/autogen-ext/src/autogen_ext/tools/mcp/_sse.py | 63 | headers={"Authorization": "Bearer your-api-key", "Content-Type": "application/json"}, | STRING |
| HIGH | …ogen-ext/src/autogen_ext/tools/mcp/_streamable_http.py | 64 | headers={"Authorization": "Bearer your-api-key", "Content-Type": "application/json"}, | STRING |
| HIGH⚡ | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 145 | client = AsyncOpenAI(api_key="your-api-key", base_url="your-base-url") | STRING |
| HIGH | …/src/autogen_ext/models/anthropic/_anthropic_client.py | 1211 | api_key="your-api-key", # Optional if ANTHROPIC_API_KEY is set in environment | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | …s/autogen-ext/tests/models/test_openai_model_client.py | 495 | # Step 1: Mock the Image class with only the 'image' attribute | COMMENT |
| LOW⚡ | …ask_centric_memory/sessions/self_teaching/session.json | 262 | "content": "### Step 1: Understanding the User Message\n\nThe user presents a classic logic puzzle often referred | CODE |
| LOW⚡ | …ask_centric_memory/sessions/self_teaching/session.json | 286 | "### Step 1: Understanding the User Message\n\nThe user presents a classic logic puzzle often referred to as t | CODE |
| LOW | …ask_centric_memory/sessions/self_teaching/session.json | 704 | "content": "### Step 1: Understanding the User Message\n\nThe user has presented a classic liar puzzle. The scenar | CODE |
| LOW | …ask_centric_memory/sessions/self_teaching/session.json | 728 | "### Step 1: Understanding the User Message\n\nThe user has presented a classic liar puzzle. The scenario invo | CODE |
| LOW | …en-ext/src/autogen_ext/models/openai/_openai_client.py | 1015 | # Because the usage chunk is not guaranteed to be the last chunk, we need to check if it is available. | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 217 | # Step 1: First code generation | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 224 | # Step 2: First code execution | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 231 | # Step 3: Retry generation with proposed correction | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 239 | # Step 4: Second retry code generation | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 246 | # Step 5: Second retry code execution | COMMENT |
| LOW⚡ | …es/autogen-agentchat/tests/test_code_executor_agent.py | 253 | # Step 6: Final response | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 549 | # Step 1: Add new user/handoff messages to the model context | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 555 | # Step 2: Run inference with the model context | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 573 | # Step 3: [NEW] If the model produced a hidden "thought," yield it as an event | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 579 | # Step 4: Add the assistant message to the model context (including thought if present) | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 588 | # Step 5: Extract the code blocks from inferred text | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 592 | # Step 6: Exit the loop if no code blocks found | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 602 | # Step 7: Yield a CodeGenerationEvent | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 612 | # Step 8: Execute the extracted code blocks | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 615 | # Step 9: Update model context with the code execution result | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 623 | # Step 10: Yield a CodeExecutionEvent | COMMENT |
| LOW⚡ | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 630 | # Step 11: If exit code is non-zero and retries are available then | COMMENT |
| LOW | …n.RuntimeGateway.Grpc.Tests/GrpcGatewayServiceTests.cs | 61 | // Step 4: Verify that the agent receives the control message | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/docs/src/_extension/gallery_directive.py | 126 | # Sphinx Design outputs a container too, so just use that | COMMENT |
| LOW | python/samples/core_chainlit/SimpleAssistantAgent.py | 178 | # Message handler for Group chat message. It just add the message to the agent message history. | COMMENT |
| MEDIUM | …/HumanEval/Templates/AgentChat/custom_code_executor.py | 35 | # If python, wrap the extracted code in a unit testing harness | COMMENT |
| MEDIUM | …ckages/autogen-studio/autogenstudio/gallery/builder.py | 578 | # Note: This requires npx to be installed and provides comprehensive MCP testing tools | COMMENT |
| LOW | python/packages/autogen-core/tests/test_workbench.py | 40 | # For the regular run method, just return the final result | COMMENT |
| MEDIUM | …hon/packages/autogen-ext/tests/tools/test_mcp_actor.py | 51 | """Get the expected number of tools by importing and examining the comprehensive server.""" | STRING |
| MEDIUM | …packages/autogen-ext/tests/memory/test_redis_memory.py | 505 | # test that we can utilize the optional query arguments top_k and distance_threshold | STRING |
| LOW | …task_centric_memory/sessions/teachability/session.json | 439 | "content": "As a contribution to autogen, can I create a new autogen package for a copilot extension agent that | CODE |
| MEDIUM | …task_centric_memory/sessions/teachability/session.json | 446 | "content": "### Understanding of the User Message\n\nYou have developed a copilot extension agent using the Autoge | CODE |
| MEDIUM | …task_centric_memory/sessions/teachability/session.json | 470 | "### Understanding of the User Message\n\nYou have developed a copilot extension agent using the Autogen frame | CODE |
| MEDIUM⚡ | …ask_centric_memory/sessions/self_teaching/session.json | 262 | "content": "### Step 1: Understanding the User Message\n\nThe user presents a classic logic puzzle often referred | CODE |
| MEDIUM⚡ | …ask_centric_memory/sessions/self_teaching/session.json | 286 | "### Step 1: Understanding the User Message\n\nThe user presents a classic logic puzzle often referred to as t | CODE |
| LOW | …ckages/autogen-ext/src/autogen_ext/ui/_rich_console.py | 185 | # We don't want to print UserInputRequestedEvent messages, we just use them to signal the user input event. | COMMENT |
| LOW | …es/autogen-ext/src/autogen_ext/tools/mcp/_workbench.py | 355 | # For now we just use text representation. | COMMENT |
| MEDIUM | …togen_ext/agents/file_surfer/_markdown_file_browser.py | 251 | # Not robust to TOCTOU issues. | COMMENT |
| MEDIUM | …ckages/autogen-agentchat/tests/test_assistant_agent.py | 3010 | """Test suite for comprehensive workbench testing.""" | STRING |
| LOW | …autogen-agentchat/src/autogen_agentchat/ui/_console.py | 167 | # We don't want to print UserInputRequestedEvent messages, we just use them to signal the user input event. | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH⚡ | python/samples/agentchat_chess_game/main.py | 112 | board.push(chess.Move.from_uci(ai_move)) | CODE |
| HIGH⚡ | python/samples/agentchat_chess_game/main.py | 122 | board.push(chess.Move.from_uci(user_move)) | CODE |
| HIGH | python/samples/core_chess_game/main.py | 124 | board.push(new_move) | CODE |
| HIGH | …hon/packages/autogen-ext/tests/tools/test_mcp_tools.py | 279 | == '[{"type": "text", "text": "this is a sample text", "annotations": {"audience": ["user", "assistant"], "prior | CODE |
| HIGH | …/experimental/task_centric_memory/utils/page_logger.py | 426 | self.page_stack.push(page) | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 147 | def my_function(arg: str = "default") -> MyResult: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 242 | def my_function() -> str: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 252 | def my_function() -> Annotated[str, "The return type"]: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 262 | def my_function() -> "str": | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 272 | def my_function(arg: str) -> None: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 283 | def my_function(arg: str, arg2: int) -> None: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 294 | def my_function(arg: "str") -> None: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 304 | def my_function(arg: Annotated[str, "An arg"]) -> None: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 314 | def my_function() -> str: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 394 | def my_function() -> str: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 404 | def my_function() -> MyResult: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 415 | def my_function(arg: str) -> MyResult: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 426 | def my_function(arg: str) -> str: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 436 | def my_function(arg: str) -> MyResult: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 453 | def my_function(arg: str) -> MyResultCustomDump: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 463 | def my_function(arg: int) -> int: | CODE |
| LOW⚡ | python/packages/autogen-core/tests/test_tools.py | 473 | def my_function() -> List[int]: | CODE |
| LOW | python/packages/autogen-core/tests/test_tools.py | 74 | def my_function(arg: str, other: Annotated[int, "int arg"], nonrequired: int = 5) -> MyResult: | CODE |
| LOW | python/packages/autogen-core/tests/test_tools.py | 129 | def my_function(arg: str = "default") -> MyResult: | CODE |
| LOW | python/packages/autogen-core/tests/test_tools.py | 326 | def my_function(my_arg: Annotated[str, "test description"]) -> str: | CODE |
| LOW | python/packages/autogen-core/tests/test_tools.py | 344 | def my_function() -> Annotated[str, "test description"]: | CODE |
| LOW | python/packages/autogen-core/tests/test_tools.py | 356 | def my_function() -> str: | CODE |
| LOW | python/packages/autogen-core/tests/test_tools.py | 369 | def my_function() -> None: | CODE |
| LOW | python/packages/autogen-core/tests/test_tools.py | 381 | def my_function() -> MyResult: | CODE |
| LOW | …s/autogen-ext/tests/models/test_openai_model_client.py | 508 | def my_function(arg: str, other: Annotated[int, "int arg"], nonrequired: int = 5) -> MyResult: | CODE |
| LOW | …n_agentchat/teams/_group_chat/_chat_agent_container.py | 86 | async def handle_request(self, message: GroupChatRequestPublish, ctx: MessageContext) -> None: | CODE |
| LOW | …/packages/magentic-one-cli/src/magentic_one_cli/_m1.py | 109 | async def run_task(task: str, hil_mode: bool, use_rich_console: bool) -> None: | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | …allTemplateTests.TestFunctionCallTemplate.approved.txt | 3 | // This code was generated by a tool. | COMMENT |
| HIGH | …toGen.SourceGenerator/Template/FunctionCallTemplate.cs | 3 | // This code was generated by a tool. | COMMENT |
| HIGH | …toGen.SourceGenerator/Template/FunctionCallTemplate.cs | 31 | // This code was generated by a tool. | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/packages/autogen-studio/autogenstudio/cli.py | 26 | CODE | |
| LOW | …ges/autogen-studio/autogenstudio/web/routes/gallery.py | 71 | CODE | |
| LOW | …ogen-studio/autogenstudio/gallery/tools/bing_search.py | 13 | CODE | |
| LOW | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 237 | CODE | |
| LOW | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 761 | CODE | |
| LOW | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 876 | CODE | |
| LOW | …/autogen-ext/src/autogen_ext/tools/azure/_ai_search.py | 1005 | CODE | |
| LOW | …ogen_ext/runtimes/grpc/protos/agent_worker_pb2_grpc.py | 153 | CODE | |
| LOW | …ogen_ext/runtimes/grpc/protos/agent_worker_pb2_grpc.py | 180 | CODE | |
| LOW | …ogen_ext/runtimes/grpc/protos/agent_worker_pb2_grpc.py | 207 | CODE | |
| LOW | …ogen_ext/runtimes/grpc/protos/agent_worker_pb2_grpc.py | 234 | CODE | |
| LOW | …ogen_ext/runtimes/grpc/protos/agent_worker_pb2_grpc.py | 261 | CODE | |
| LOW | …ogen_ext/runtimes/grpc/protos/agent_worker_pb2_grpc.py | 288 | CODE | |
| LOW | …en-ext/src/autogen_ext/agents/azure/_azure_ai_agent.py | 288 | CODE | |
| LOW | …utogen_ext/agents/web_surfer/_multimodal_web_surfer.py | 209 | CODE | |
| LOW | …c/autogen_ext/agents/openai/_openai_assistant_agent.py | 235 | CODE | |
| LOW | …en-ext/src/autogen_ext/models/openai/_openai_client.py | 185 | CODE | |
| LOW | …n_ext/code_executors/docker_jupyter/_jupyter_server.py | 292 | CODE | |
| LOW | …gen_ext/code_executors/docker/_docker_code_executor.py | 158 | CODE | |
| LOW | …tchat/src/autogen_agentchat/agents/_assistant_agent.py | 724 | CODE | |
| LOW | …t/src/autogen_agentchat/agents/_code_executor_agent.py | 428 | CODE | |
| LOW | …en_agentchat/teams/_group_chat/_selector_group_chat.py | 597 | CODE | |
| LOW | …/_group_chat/_magentic_one/_magentic_one_group_chat.py | 109 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | …src/user-guide/agentchat-user-guide/migration-guide.md | 371 | ## RAG Agent | COMMENT |
| MEDIUM | …cs/src/user-guide/agentchat-user-guide/magentic-one.md | 10 | [Magentic-One](https://aka.ms/magentic-one-blog) is a generalist multi-agent system for solving open-ended web and file- | CODE |
| MEDIUM | python/samples/core_chess_game/main.py | 255 | # orchestration. | COMMENT |
| MEDIUM | python/packages/autogen-magentic-one/README.md | 8 | [Magentic-One](https://aka.ms/magentic-one-blog) is a generalist multi-agent system for solving open-ended web and file- | CODE |
| MEDIUM | …utogen_ext/agents/web_surfer/_multimodal_web_surfer.py | 899 | # Grow the buffer (which is added to the prompt) until we overflow the context window or run out of lines | COMMENT |
| MEDIUM | …en-ext/src/autogen_ext/models/anthropic/_model_info.py | 128 | # Model token limits (context window size) | COMMENT |
| MEDIUM | docs/dotnet/core/index.md | 105 | The [Hello.AppHost project](https://github.com/microsoft/autogen/blob/50d7587a4649504af3bb79ab928b2a3882a1a394/dotnet/sa | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …src/user-guide/agentchat-user-guide/migration-guide.md | 151 | api_key="placeholder", | CODE |
| LOW | …ackages/autogen-studio/tests/mcp/test_mcp_callbacks.py | 196 | result = ElicitResult(action="accept", content={"name": "John Doe"}) | CODE |
| LOW | …ackages/autogen-studio/tests/mcp/test_mcp_callbacks.py | 208 | assert result.content == {"name": "John Doe"} | CODE |
| LOW | …n/packages/autogen-core/tests/test_json_to_pydantic.py | 116 | "address": {"street": "123 Main St", "city": "Metropolis", "zipcode": "12345"}, | CODE |
| LOW | …n/packages/autogen-core/tests/test_json_to_pydantic.py | 198 | "address": {"street": "123 Main St", "city": "Metropolis"}, | CODE |
| LOW | …togen-core/src/autogen_core/utils/_json_to_pydantic.py | 556 | "address": {"street": "123 Main St", "city": "Wonderland", "zipcode": "12345"}, | STRING |
| LOW⚡ | …ts/agents/test_openai_agent_builtin_tool_validation.py | 23 | monkeypatch.setenv("OPENAI_API_KEY", "sk-test-dummy-key") | CODE |
| LOW⚡ | …ts/agents/test_openai_agent_builtin_tool_validation.py | 27 | os.getenv("OPENAI_API_KEY", "") in ("", "sk-test-dummy-key"), | CODE |
| LOW⚡ | …s/autogen-ext/tests/models/test_openai_model_client.py | 3344 | api_key="fake_key", | CODE |
| LOW⚡ | …s/autogen-ext/tests/models/test_openai_model_client.py | 3352 | api_key="fake_key", | CODE |
| LOW⚡ | …s/autogen-ext/tests/models/test_openai_model_client.py | 3361 | api_key="fake_key", | CODE |
| LOW | …s/autogen-ext/tests/models/test_openai_model_client.py | 2164 | api_key="placeholder", | CODE |
| LOW | …s/autogen-ext/tests/models/test_openai_model_client.py | 2639 | dummy_client = OpenAIChatCompletionClient(model="claude-3-5-haiku-20241022", api_key="dummy-key") | CODE |
| LOW | …s/autogen-ext/tests/models/test_openai_model_client.py | 3281 | api_key="fake_key", | CODE |
| LOW | …s/autogen-ext/tests/models/test_openai_model_client.py | 3292 | api_key="fake_key", | CODE |
| LOW | …s/autogen-ext/tests/models/test_openai_model_client.py | 3304 | "api_key": "fake_key", | CODE |
| LOW | …s/autogen-ext/tests/models/test_openai_model_client.py | 3321 | "api_key": "fake_key", | CODE |
| LOW | …s/autogen-ext/tests/models/test_openai_model_client.py | 3375 | "api_key": "fake_key", | CODE |
| LOW⚡ | …utogen-ext/tests/models/test_anthropic_model_client.py | 832 | dummy_client = AnthropicChatCompletionClient(model="claude-3-5-haiku-20241022", api_key="dummy-key") | CODE |
| LOW | …utogen-ext/tests/models/test_anthropic_model_client.py | 1116 | api_key="fake-key", | CODE |
| LOW | …utogen-ext/tests/models/test_anthropic_model_client.py | 1141 | api_key="fake-key", | CODE |
| LOW | …en-ext/src/autogen_ext/models/openai/_openai_client.py | 1296 | api_key="placeholder", | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | …frontend/src/components/views/deploy/guides/python.tsx | 60 | description="Here's a simple example of using the TeamManager class from AutoGen Studio in your python code." | CODE |
| MEDIUM | …task_centric_memory/sessions/teachability/session.json | 47 | "content": "1. **Understanding the User Message:**\n The user is inquiring about the possibility of creating a n | CODE |
| MEDIUM | …task_centric_memory/sessions/teachability/session.json | 71 | "1. **Understanding the User Message:**\n The user is inquiring about the possibility of creating a new pack | CODE |
| MEDIUM | …es/autogen-ext/src/autogen_ext/tools/mcp/_workbench.py | 97 | Here is a simple example of how to use the workbench with a `mcp-server-fetch` server: | STRING |
| MEDIUM | …/models/semantic_kernel/_sk_chat_completion_adapter.py | 313 | # If there's a 'thought' field, you can add that as plain assistant text | COMMENT |
| LOW | …en-ext/src/autogen_ext/models/openai/_openai_client.py | 1216 | # JSON response, make sure to instruct the model to return JSON. | STRING |
| LOW | …en-ext/src/autogen_ext/models/openai/_openai_client.py | 1557 | # JSON response, make sure to instruct the model to return JSON. | STRING |
| MEDIUM | …s/AgentChat/AutoGen.Basic.Sample/Example08_LMStudio.cs | 35 | // Of course! To calculate the 100th number in the Fibonacci sequence using C#, you can use the following code:` | COMMENT |
| MEDIUM | .github/workflows/codeql.yml | 58 | # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | …frontend/src/components/views/deploy/guides/python.tsx | 51 | print(config.model_dump_json())`} | CODE |
| HIGH | …frontend/src/components/views/deploy/guides/python.tsx | 72 | print(result)`} | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | python/samples/agentchat_fastapi/app_team.py | 184 | # Example usage | COMMENT |
| LOW | python/samples/agentchat_fastapi/app_agent.py | 107 | # Example usage | COMMENT |
| LOW⚡ | …n/packages/autogen-studio/autogenstudio/eval/judges.py | 214 | # # Usage example | COMMENT |
| LOW | …src/Microsoft.AutoGen/Contracts/KVStringParseHelper.cs | 34 | /// Example usage: | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | …thon/packages/autogen-ext/tests/test_azure_ai_agent.py | 177 | CODE | |
| MEDIUM | …n_ext/models/llama_cpp/_llama_cpp_completion_client.py | 427 | CODE |