🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
This report presents the forensic synthetic code analysis of camel-ai/camel, a Python project with 17,383 GitHub stars. SynthScan v2.0 examined 321,851 lines of code across 1389 source files, recording 7036 pattern matches distributed across 25 syntactic categories. The overall adjusted score of 28.1 places this repository in the Moderate AI signal band.
The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).
This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.
Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.
This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.
The scanner identified 7036 distinct pattern matches across 25 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. 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 diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | test/test_all_exports.py | 16 | def test_all_exports_from_camel(): | CODE |
| LOW | test/conftest.py | 50 | def pytest_collection_modifyitems(config: Config, items: List[Item]) -> None: | CODE |
| LOW | test/test_generators.py | 22 | def test_system_message_generator(): | CODE |
| LOW | test/test_generators.py | 63 | def test_task_prompt_generator(): | CODE |
| LOW | test/terminators/test_response_terminator.py | 39 | def test_response_words_termination(mode): | CODE |
| LOW | test/terminators/test_token_limit_terminator.py | 20 | def test_token_limit_termination(num_tokens): | CODE |
| LOW | test/data_collectors/test_sharegpt_collector.py | 60 | def test_sharegpt_llm_converter(): | CODE |
| LOW | test/data_collectors/test_alpaca_collector.py | 55 | def test_alpaca_llm_converter(): | CODE |
| LOW⚡ | test/bots/test_discord_app.py | 32 | def test_init_with_token_from_env(self, mock_discord_client): | CODE |
| LOW⚡ | test/bots/test_discord_app.py | 40 | def test_init_with_provided_token(self, mock_discord_client): | CODE |
| LOW⚡ | test/bots/test_discord_app.py | 47 | def test_init_raises_value_error_without_token(self, mock_discord_client): | CODE |
| LOW | test/bots/test_discord_app.py | 66 | async def test_on_message_ignore_own_message(self, mock_discord_client): | CODE |
| LOW | test/bots/test_discord_app.py | 76 | async def test_on_message_respond_in_allowed_channel( | CODE |
| LOW | test/bots/test_discord_app.py | 93 | async def test_on_message_ignore_non_mentioned_message( | CODE |
| LOW | test/bots/test_discord_app.py | 107 | async def test_on_message_ignore_outside_channel( | CODE |
| LOW | test/bots/test_slack_app.py | 43 | def test_init_without_token_raises_error(self, mock_async_app): | CODE |
| LOW | test/bots/test_telegram_bot.py | 26 | def test_init_token_provided_uses_provided_token(self): | CODE |
| LOW | test/integration_test/test_minimal_dependency.py | 33 | def test_minimum_deps_module_importable(module_path): | CODE |
| LOW | test/integration_test/test_minimal_dependency.py | 59 | def test_example_runs_or_skips(example_path): | STRING |
| LOW | test/interpreters/test_subprocess_interpreter.py | 88 | def test_run_unsupported_code_type(subprocess_interpreter): | STRING |
| LOW | test/interpreters/test_subprocess_interpreter.py | 120 | def test_r_code_type_variants(subprocess_interpreter): | STRING |
| LOW | test/interpreters/test_subprocess_interpreter.py | 150 | def test_execute_command_require_confirm(subprocess_interpreter, monkeypatch): | STRING |
| LOW | test/interpreters/test_interpreters_decorators.py | 38 | def test_docker_interpreter_missing_dependency(): | CODE |
| LOW⚡ | test/interpreters/test_interpreters_decorators.py | 54 | def test_jupyter_kernel_interpreter_missing_dependency(): | CODE |
| LOW⚡ | test/interpreters/test_interpreters_decorators.py | 62 | def test_jupyter_kernel_interpreter_missing_ipykernel(): | CODE |
| LOW⚡ | test/interpreters/test_interpreters_decorators.py | 70 | def test_microsandbox_interpreter_missing_dependency(): | CODE |
| LOW | test/interpreters/test_python_interpreter.py | 289 | def test_augassign_operations(interpreter: InternalPythonInterpreter): | CODE |
| LOW | test/interpreters/test_python_interpreter.py | 395 | def test_unsafe_mode_complex_operations(unsafe_interpreter): | STRING |
| LOW | test/interpreters/test_python_interpreter.py | 423 | def not_allow_builtins_interpreter(): | STRING |
| LOW | test/interpreters/test_docker_interpreter.py | 130 | def test_r_code_type_variants(docker_interpreter: DockerInterpreter): | STRING |
| LOW | test/interpreters/test_docker_interpreter.py | 141 | def test_run_unsupported_code_type(docker_interpreter: DockerInterpreter): | STRING |
| LOW | test/interpreters/test_microsandbox_interpreter.py | 59 | def test_supported_code_types(): | CODE |
| LOW | test/interpreters/test_microsandbox_interpreter.py | 74 | def test_unsupported_language(interpreter): | CODE |
| LOW | test/retrievers/test_hybrid_retriever.py | 52 | def test_sort_rrf_scores_integration(mock_hybrid_retriever): | CODE |
| LOW | test/retrievers/test_auto_retriever.py | 45 | def test__initialize_vector_storage(auto_retriever): | CODE |
| LOW | test/retrievers/test_auto_retriever.py | 51 | def test_run_vector_retriever(auto_retriever): | CODE |
| LOW | test/retrievers/test_auto_retriever.py | 66 | def test_run_vector_retriever_with_element_input(auto_retriever): | CODE |
| LOW⚡ | test/retrievers/test_vector_retriever.py | 47 | def mock_unstructured_modules(): | CODE |
| LOW⚡ | test/retrievers/test_vector_retriever.py | 53 | def test_initialization_with_custom_embedding( | CODE |
| LOW⚡ | test/retrievers/test_vector_retriever.py | 60 | def test_initialization_with_default_embedding(): | CODE |
| LOW | test/retrievers/test_bm25_retriever.py | 23 | def mock_unstructured_modules(): | CODE |
| LOW | test/retrievers/test_bm25_retriever.py | 77 | def test_query_without_initialization(): | CODE |
| LOW | test/retrievers/test_retrievers_decorators.py | 44 | def test_auto_retriever_missing_dependency(): | CODE |
| LOW | test/retrievers/test_retrievers_decorators.py | 86 | def test_cohere_rerank_retriever_missing_dependency(): | CODE |
| LOW | test/retrievers/test_retrievers_decorators.py | 101 | def test_hybrid_retrieval_missing_dependency(): | CODE |
| LOW | test/retrievers/test_retrievers_decorators.py | 112 | def test_jina_rerank_retriever_missing_dependency(): | CODE |
| LOW | test/retrievers/test_retrievers_decorators.py | 123 | def test_vector_retriever_missing_dependency(): | CODE |
| LOW | test/retrievers/test_retrievers_decorators.py | 136 | def test_cohere_rerank_retriever_api_keys(): | CODE |
| LOW | test/retrievers/test_retrievers_decorators.py | 149 | def test_jina_rerank_retriever_api_keys(): | CODE |
| LOW⚡ | test/retrievers/test_jina_rerank_retriever.py | 29 | def test_initialization_with_custom_model(): | CODE |
| LOW⚡ | test/retrievers/test_jina_rerank_retriever.py | 35 | def test_initialization_without_api_key(): | CODE |
| LOW⚡ | test/retrievers/test_jina_rerank_retriever.py | 43 | def test_initialization_with_explicit_api_key(): | CODE |
| LOW | test/retrievers/test_jina_rerank_retriever.py | 129 | def test_query_with_content_key(mock_post, jina_rerank): | CODE |
| LOW | test/storages/test_storages_decorators.py | 41 | def test_redis_storage_missing_dependency(): | CODE |
| LOW | test/storages/test_storages_decorators.py | 74 | def test_azure_blob_storage_missing_dependency(): | CODE |
| LOW | test/storages/test_storages_decorators.py | 85 | def test_google_cloud_storage_missing_dependency(): | CODE |
| LOW | test/storages/vector_storages/test_tidb.py | 39 | def test_multiple_remote_clients(mock_tidb_storage): | CODE |
| LOW | test/storages/vector_storages/test_surreal.py | 105 | def test_distance_to_similarity( | CODE |
| LOW | test/storages/vector_storages/test_oceanbase.py | 109 | def test_oceanbase_storage_initialization(mock_ob_client): | CODE |
| LOW | test/storages/vector_storages/test_oceanbase.py | 154 | def test_oceanbase_storage_operations(mock_ob_client): | CODE |
| 2123 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | test/interpreters/test_interpreters_decorators.py | 0 | patch is_module_available to return false for a specific module. | STRING |
| HIGH | test/retrievers/test_retrievers_decorators.py | 0 | patch is_module_available to return false for a specific module. | STRING |
| HIGH | test/storages/test_storages_decorators.py | 0 | patch is_module_available to return false for a specific module. | STRING |
| HIGH | test/embeddings/test_embeddings_decorators.py | 0 | patch is_module_available to return false for a specific module. | STRING |
| HIGH | test/loaders/test_loaders_decorators.py | 0 | patch is_module_available to return false for a specific module. | STRING |
| HIGH | test/interpreters/test_jupyterkernel_interpreter.py | 0 | def add(a, b): return a + b def multiply(a, b): return a * b def subtract(a, b): return a - b def main(): a = 10 b = 20 | STRING |
| HIGH | test/interpreters/test_docker_interpreter.py | 0 | def add(a, b): return a + b def multiply(a, b): return a * b def subtract(a, b): return a - b def main(): a = 10 b = 20 | STRING |
| HIGH | examples/interpreters/ipython_interpreter_example.py | 0 | def add(a, b): return a + b def multiply(a, b): return a * b def subtract(a, b): return a - b def main(): a = 10 b = 20 | STRING |
| HIGH | test/retrievers/test_retrievers_decorators.py | 0 | test that the following decorators are correctly applied to camel.loaders: @api_keys_required - should raise valueerror | STRING |
| HIGH | test/storages/test_storages_decorators.py | 0 | test that the following decorators are correctly applied to camel.loaders: @api_keys_required - should raise valueerror | STRING |
| HIGH | test/loaders/test_loaders_decorators.py | 0 | test that the following decorators are correctly applied to camel.loaders: @api_keys_required - should raise valueerror | STRING |
| HIGH | test/toolkits/test_web_deploy_toolkit.py | 0 | test that get_tools returns the correct function tools. | STRING |
| HIGH | test/toolkits/test_sql_toolkit.py | 0 | test that get_tools returns the correct function tools. | STRING |
| HIGH | test/toolkits/test_file_toolkit.py | 0 | test that get_tools returns the correct function tools. | STRING |
| HIGH | test/models/test_moonshot_model.py | 0 | test that interleaved_thinking configuration is properly set. | STRING |
| HIGH | test/models/test_volcano_model.py | 0 | test that interleaved_thinking configuration is properly set. | STRING |
| HIGH | test/models/test_zhipuai_model.py | 0 | test that interleaved_thinking configuration is properly set. | STRING |
| HIGH | test/models/test_moonshot_model.py | 0 | test that interleaved_thinking is disabled by default. | STRING |
| HIGH | test/models/test_volcano_model.py | 0 | test that interleaved_thinking is disabled by default. | STRING |
| HIGH | test/models/test_zhipuai_model.py | 0 | test that interleaved_thinking is disabled by default. | STRING |
| HIGH | test/models/test_moonshot_model.py | 0 | test reasoning_content injection into assistant messages. | STRING |
| HIGH | test/models/test_volcano_model.py | 0 | test reasoning_content injection into assistant messages. | STRING |
| HIGH | test/models/test_zhipuai_model.py | 0 | test reasoning_content injection into assistant messages. | STRING |
| HIGH | test/models/test_moonshot_model.py | 0 | test that reasoning_content is not injected when disabled. | STRING |
| HIGH | test/models/test_volcano_model.py | 0 | test that reasoning_content is not injected when disabled. | STRING |
| HIGH | test/models/test_zhipuai_model.py | 0 | test that reasoning_content is not injected when disabled. | STRING |
| HIGH | test/models/test_moonshot_model.py | 0 | test extraction of reasoning_content from response. | STRING |
| HIGH | test/models/test_volcano_model.py | 0 | test extraction of reasoning_content from response. | STRING |
| HIGH | test/models/test_zhipuai_model.py | 0 | test extraction of reasoning_content from response. | STRING |
| HIGH | test/models/test_moonshot_model.py | 0 | test extraction returns none when no reasoning_content. | STRING |
| HIGH | test/models/test_volcano_model.py | 0 | test extraction returns none when no reasoning_content. | STRING |
| HIGH | test/models/test_zhipuai_model.py | 0 | test extraction returns none when no reasoning_content. | STRING |
| HIGH | camel/storages/vectordb_storages/milvus.py | 0 | searches for similar vectors in the storage based on the provided query. args: query (vectordbquery): the query object c | STRING |
| HIGH | camel/storages/vectordb_storages/tidb.py | 0 | searches for similar vectors in the storage based on the provided query. args: query (vectordbquery): the query object c | STRING |
| HIGH | camel/storages/vectordb_storages/weaviate.py | 0 | searches for similar vectors in the storage based on the provided query. args: query (vectordbquery): the query object c | STRING |
| HIGH | camel/storages/vectordb_storages/base.py | 0 | searches for similar vectors in the storage based on the provided query. args: query (vectordbquery): the query object c | STRING |
| HIGH | camel/storages/vectordb_storages/qdrant.py | 0 | provides access to the underlying vector database client. | STRING |
| HIGH | camel/storages/vectordb_storages/weaviate.py | 0 | provides access to the underlying vector database client. | STRING |
| HIGH | camel/storages/vectordb_storages/base.py | 0 | provides access to the underlying vector database client. | STRING |
| HIGH | camel/storages/vectordb_storages/tidb.py | 0 | deletes a list of vectors identified by their ids from the storage. args: ids (list[str]): list of unique identifiers fo | STRING |
| HIGH | camel/storages/vectordb_storages/weaviate.py | 0 | deletes a list of vectors identified by their ids from the storage. args: ids (list[str]): list of unique identifiers fo | STRING |
| HIGH | camel/storages/vectordb_storages/oceanbase.py | 0 | deletes a list of vectors identified by their ids from the storage. args: ids (list[str]): list of unique identifiers fo | STRING |
| HIGH | camel/storages/vectordb_storages/base.py | 0 | deletes a list of vectors identified by their ids from the storage. args: ids (list[str]): list of unique identifiers fo | STRING |
| HIGH | camel/storages/vectordb_storages/weaviate.py | 0 | returns status of the vector database. returns: vectordbstatus: the vector database status. | STRING |
| HIGH | camel/storages/vectordb_storages/oceanbase.py | 0 | returns status of the vector database. returns: vectordbstatus: the vector database status. | STRING |
| HIGH | camel/storages/vectordb_storages/base.py | 0 | returns status of the vector database. returns: vectordbstatus: the vector database status. | STRING |
| HIGH | camel/storages/key_value_storages/mem0_cloud.py | 0 | saves a batch of records to the key-value storage system. args: records (list[dict[str, any]]): a list of dictionaries, | STRING |
| HIGH | camel/storages/key_value_storages/json.py | 0 | saves a batch of records to the key-value storage system. args: records (list[dict[str, any]]): a list of dictionaries, | STRING |
| HIGH | camel/storages/key_value_storages/base.py | 0 | saves a batch of records to the key-value storage system. args: records (list[dict[str, any]]): a list of dictionaries, | STRING |
| HIGH | camel/storages/key_value_storages/in_memory.py | 0 | saves a batch of records to the key-value storage system. args: records (list[dict[str, any]]): a list of dictionaries, | STRING |
| HIGH | camel/storages/key_value_storages/mem0_cloud.py | 0 | loads all stored records from the key-value storage system. returns: list[dict[str, any]]: a list of dictionaries, where | STRING |
| HIGH | camel/storages/key_value_storages/redis.py | 0 | loads all stored records from the key-value storage system. returns: list[dict[str, any]]: a list of dictionaries, where | STRING |
| HIGH | camel/storages/key_value_storages/json.py | 0 | loads all stored records from the key-value storage system. returns: list[dict[str, any]]: a list of dictionaries, where | STRING |
| HIGH | camel/storages/key_value_storages/base.py | 0 | loads all stored records from the key-value storage system. returns: list[dict[str, any]]: a list of dictionaries, where | STRING |
| HIGH | camel/storages/key_value_storages/in_memory.py | 0 | loads all stored records from the key-value storage system. returns: list[dict[str, any]]: a list of dictionaries, where | STRING |
| HIGH | camel/storages/key_value_storages/redis.py | 0 | removes all records from the key-value storage system. | STRING |
| HIGH | camel/storages/key_value_storages/json.py | 0 | removes all records from the key-value storage system. | STRING |
| HIGH | camel/storages/key_value_storages/base.py | 0 | removes all records from the key-value storage system. | STRING |
| HIGH | camel/storages/key_value_storages/in_memory.py | 0 | removes all records from the key-value storage system. | STRING |
| HIGH | camel/embeddings/openai_embedding.py | 0 | generates embeddings for the given texts. args: objs (list[t]): the objects for which to generate the embeddings. **kwar | STRING |
| 217 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | test/test_all_exports.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/conftest.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/test_generators.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/test_human.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/terminators/test_response_terminator.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/terminators/test_token_limit_terminator.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/data_collectors/test_sharegpt_collector.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/data_collectors/test_alpaca_collector.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/bots/test_discord_app.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/bots/test_slack_app.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/bots/test_telegram_bot.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/integration_test/test_minimal_dependency.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/interpreters/test_subprocess_interpreter.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/interpreters/test_interpreters_decorators.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/interpreters/test_python_interpreter.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/interpreters/test_jupyterkernel_interpreter.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/interpreters/test_docker_interpreter.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/interpreters/test_microsandbox_interpreter.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/retrievers/test_hybrid_retriever.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/retrievers/test_auto_retriever.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/retrievers/test_cohere_rerank_retriever.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/retrievers/test_vector_retriever.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/retrievers/test_bm25_retriever.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/retrievers/test_retrievers_decorators.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/retrievers/test_jina_rerank_retriever.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/test_storages_decorators.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/vector_storages/test_tidb.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/vector_storages/test_surreal.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/vector_storages/test_oceanbase.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/vector_storages/test_all_vectordbs.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/vector_storages/test_milvus.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/vector_storages/test_qdrant.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/vector_storages/test_pgvector.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/vector_storages/test_weaviate.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/vector_storages/test_faiss.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/key_value_storages/test_redis.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | …storages/key_value_storages/test_key_value_storages.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/key_value_storages/test_mem0_cloud.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/graph_storages/test_graph_element.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/graph_storages/test_nebula_graph.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/graph_storages/test_neo4j_graph.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/object_storages/test_azure_blob.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/object_storages/test_google_cloud.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/storages/object_storages/test_amazon_s3.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/tasks/test_task.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/messages/test_message_base.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/messages/test_func_message.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/messages/test_chat_message.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/embeddings/test_azure_embedding.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/embeddings/test_vlm_embeddings.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/embeddings/test_mistral_embedding.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/embeddings/test_jina_embedding.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/embeddings/test_embeddings_decorators.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/embeddings/test_openai_compatible_embedding.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/embeddings/test_openai_embedding.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/embeddings/test_gemini_embedding.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/embeddings/test_open_source_embeddings.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/environments/test_multi_step_env.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/environments/test_tictactoe_env.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| LOW | test/environments/test_single_step_env.py | 1 | # ========= Copyright 2023-2026 @ CAMEL-AI.org. All Rights Reserved. ========= | COMMENT |
| 1088 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | camel/generators.py | 130 | Generates a list of system messages from a list of dictionaries. Args: meta_dicts (List[Dict[str, s | STRING |
| HIGH | camel/data_collectors/alpaca_collector.py | 109 | Convert collected data using an LLM schema converter. Args: converter (Optional[OpenAISchemaConvert | STRING |
| HIGH | camel/data_collectors/sharegpt_collector.py | 156 | Convert collected data using an LLM schema converter. Args: converter (Optional[OpenAISchemaConvert | STRING |
| HIGH | camel/bots/discord/discord_app.py | 143 | Exchange the authorization code for an access token. Args: code (str): The authorization code recei | STRING |
| HIGH | camel/societies/workforce/workforce.py | 1652 | Unified task analysis for both failures and quality evaluation. This method consolidates the logic for analyzin | STRING |
| HIGH | camel/societies/workforce/workforce.py | 3038 | Add a worker node to the workforce that uses a single agent. Can be called when workforce is paused to dynamical | STRING |
| HIGH | camel/societies/workforce/workforce.py | 3104 | Add a worker node to the workforce that uses `RolePlaying` system. Can be called when workforce is paused to dyn | STRING |
| HIGH | camel/societies/workforce/workforce.py | 3173 | Add a workforce node to the workforce. Can be called when workforce is paused to dynamically add workers. | STRING |
| HIGH | camel/societies/workforce/utils.py | 445 | Add a task to the pipeline with support for chaining. Args: content (str): The content/description | STRING |
| HIGH | camel/societies/workforce/utils.py | 517 | Add multiple parallel tasks that can execute simultaneously. Args: task_contents (List[str]): List | STRING |
| HIGH | camel/societies/workforce/utils.py | 578 | Add a synchronization task that waits for multiple tasks. Args: content (str): Content of the synch | STRING |
| HIGH | camel/interpreters/ipython_interpreter.py | 126 | Executes the given code in the Jupyter kernel. Args: code (str): The code string to execute. | STRING |
| HIGH | camel/interpreters/docker_interpreter.py | 216 | Executes the given code in the container attached to the interpreter, and captures the stdout and stderr streams | STRING |
| HIGH | camel/interpreters/docker_interpreter.py | 295 | Executes a command in the Docker container and returns its output. Args: command (str): The command | STRING |
| HIGH | camel/interpreters/e2b_interpreter.py | 115 | Executes the given code in the e2b sandbox. Args: code (str): The code string to execute. | STRING |
| HIGH | camel/interpreters/microsandbox_interpreter.py | 128 | Executes the given code in the microsandbox. Args: code (str): The code string to execute. | STRING |
| HIGH | camel/interpreters/microsandbox_interpreter.py | 161 | Asynchronously executes code in microsandbox. Args: code (str): The code to execute. co | STRING |
| HIGH | camel/interpreters/microsandbox_interpreter.py | 336 | Execute a shell command in the microsandbox. This method is designed for package management and system | STRING |
| HIGH | camel/interpreters/microsandbox_interpreter.py | 365 | Asynchronously executes a shell command in microsandbox. Args: command (str): The shell command to | STRING |
| HIGH | camel/interpreters/internal_python_interpreter.py | 157 | Executes the given code with specified code type in the interpreter. This method takes a string of code | STRING |
| HIGH | camel/interpreters/subprocess_interpreter.py | 274 | Generates a temporary file with the given code, executes it, and deletes the file afterward. Args: | STRING |
| HIGH | camel/interpreters/subprocess_interpreter.py | 439 | Executes a shell command in a subprocess and captures its output. Args: command (str): The shell co | STRING |
| HIGH | camel/interpreters/base.py | 23 | Executes the given code based on its type. Args: code (str): The code to be executed. c | STRING |
| HIGH | camel/retrievers/hybrid_retrival.py | 69 | Sorts and combines results from vector and BM25 retrievers using Reciprocal Rank Fusion (RRF). Args: | STRING |
| HIGH | camel/retrievers/jina_rerank_retriever.py | 87 | Queries and compiles results using the Jina AI re-ranking model. Args: query (str): Query string fo | STRING |
| HIGH | camel/retrievers/bm25_retriever.py | 92 | Executes a query and compiles the results. Args: query (str): Query string for information retrieve | STRING |
| HIGH | camel/retrievers/vector_retriever.py | 205 | Executes a query in vector storage and compiles the retrieved results into a dictionary. Args: | STRING |
| HIGH | camel/retrievers/auto_retriever.py | 179 | Executes the automatic vector retriever process using vector storage. Args: query (str): Qu | STRING |
| HIGH | camel/storages/vectordb_storages/qdrant.py | 331 | Deletes points from the collection based on either IDs or payload filters. Args: ids (Optio | STRING |
| HIGH | camel/storages/vectordb_storages/faiss.py | 413 | Deletes vectors from the index based on either IDs or payload filters. Args: ids (Optional[ | STRING |
| HIGH | camel/storages/vectordb_storages/chroma.py | 39 | An implementation of the `BaseVectorStorage` for interacting with ChromaDB, a vector database for embeddings. Ch | STRING |
| HIGH | camel/storages/vectordb_storages/chroma.py | 531 | Searches for similar vectors in ChromaDB based on the provided query. Args: query (VectorDB | STRING |
| HIGH | camel/storages/vectordb_storages/oceanbase.py | 296 | Searches for similar vectors in the storage based on the provided query. Args: query (Vecto | STRING |
| HIGH | camel/storages/graph_storages/nebula_graph.py | 139 | Execute a query on the graph store. Args: query (str): The Cypher-like query to be executed. | STRING |
| HIGH | camel/storages/graph_storages/nebula_graph.py | 618 | Validates the format of a time label string. Args: time_label (str): The time label string to valid | STRING |
| HIGH | camel/storages/graph_storages/neo4j_graph.py | 215 | Executes a Neo4j Cypher declarative query in a database. Args: query (str): The Cypher query to be | STRING |
| HIGH | camel/messages/conversion/alpaca.py | 55 | Creates an AlpacaItem from a formatted string. Args: text: String in either of these formats: | STRING |
| HIGH | camel/types/mcp_registries.py | 56 | Set the default OS based on the current platform if not provided. Args: values (Dict): The values d | STRING |
| HIGH | camel/embeddings/vlm_embedding.py | 108 | Generates embeddings for the given images or texts. Args: objs (List[Image.Image|str]): The list of | STRING |
| HIGH | camel/embeddings/together_embedding.py | 75 | Generates embeddings for the given texts. Args: objs (list[str]): The texts for which to generate t | STRING |
| HIGH | camel/embeddings/jina_embedding.py | 95 | Generates embeddings for the given texts or images. Args: objs (list[Union[str, Image.Image]]): The | STRING |
| HIGH | camel/environments/single_step.py | 144 | Resets the environment and starts a new episode. This method samples a new batch of data points from the datase | STRING |
| HIGH | camel/environments/single_step.py | 274 | Execute one interaction step in the environment using the proposed solution. This method processes the | STRING |
| HIGH | camel/environments/single_step.py | 454 | Normalize the user-provided action(s) into a validated list of `Action` objects. This method handles fl | STRING |
| HIGH | camel/environments/multi_step.py | 138 | Take a step in the environment using the given action. This method updates the environment state based on the L | STRING |
| HIGH | camel/datasets/few_shot_generator.py | 130 | Generates and validates `n` new datapoints through few-shot prompting, with a retry limit. Steps: | STRING |
| HIGH | camel/datasets/static_dataset.py | 103 | Convert input data from various formats into a list of :obj:`DataPoint` instances. Args: da | STRING |
| HIGH | camel/datasets/static_dataset.py | 203 | Retrieve a datapoint or a batch of datapoints by index or slice. Args: idx (Union[int, slice]): Ind | STRING |
| HIGH | camel/datasets/static_dataset.py | 273 | Convert a PyTorch dataset into a list of dictionaries. Args: data (Dataset): A PyTorch dataset. | STRING |
| HIGH | camel/datasets/static_dataset.py | 308 | Load and parse a dataset from a JSON file. Args: data (Path): Path to the JSON file. Retur | STRING |
| HIGH | camel/datasets/static_dataset.py | 344 | Load and parse a dataset from a JSONL file. Args: data (Path): Path to the JSONL file. Ret | STRING |
| HIGH | camel/datasets/static_dataset.py | 388 | Validate and convert a list of dictionaries into a dataset. Args: data (List[Dict[str, Any]]): A li | STRING |
| HIGH | camel/datasets/static_dataset.py | 459 | Save the dataset to the Hugging Face Hub using the project's HuggingFaceDatasetManager. Args: | STRING |
| HIGH | camel/datasets/base_generator.py | 211 | Saves the generated datapoints to a JSONL (JSON Lines) file. Each datapoint is stored as a separate JSON object | STRING |
| HIGH | camel/datasets/base_generator.py | 258 | Load and parse a dataset from a JSONL file. Args: file_path (Path): Path to the JSONL file. | STRING |
| HIGH | camel/datasets/base_generator.py | 299 | Get a datapoint by index without removing the datapoint from _data. Args: index (int): Index of the | STRING |
| HIGH | camel/runtimes/docker_runtime.py | 142 | Run a command inside this container. Similar to `docker exec`. Args: task (TaskConfig): The configu | STRING |
| HIGH | camel/verifiers/python_verifier.py | 469 | Compares two Python objects for equality with optional float tolerance. This method recursively compare | STRING |
| HIGH | camel/verifiers/base.py | 168 | Perform verification with full error handling. This method verifies the correctness of a generated solution by | STRING |
| HIGH | camel/verifiers/base.py | 286 | Abstract method for verification logic. Subclasses must implement this method to define how the solution | STRING |
| 109 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | test/retrievers/test_hybrid_retriever.py | 32 | # Create an instance of HybridRetriever | COMMENT |
| MEDIUM | test/retrievers/test_auto_retriever.py | 27 | # Define the path to the temporary storage | COMMENT |
| MEDIUM⚡ | test/retrievers/test_vector_retriever.py | 67 | # Create a VectorRetriever instance | COMMENT |
| MEDIUM | test/retrievers/test_bm25_retriever.py | 37 | # Create a mock chunk with metadata | COMMENT |
| MEDIUM | test/storages/vector_storages/test_oceanbase.py | 110 | # Create a mock factory that returns a new mock IndexParams with iterator | COMMENT |
| MEDIUM | test/storages/vector_storages/test_oceanbase.py | 155 | # Create a mock factory that returns a new mock IndexParams with iterator | COMMENT |
| MEDIUM | test/storages/vector_storages/test_oceanbase.py | 212 | # Create a mock factory that returns a new mock IndexParams with iterator | COMMENT |
| MEDIUM | test/storages/key_value_storages/test_mem0_cloud.py | 35 | # Create a mock for the Mem0 client | COMMENT |
| MEDIUM | test/storages/graph_storages/test_nebula_graph.py | 53 | # Initialize the NebulaGraph instance with the mocks | COMMENT |
| MEDIUM | test/storages/graph_storages/test_nebula_graph.py | 306 | # Create a GraphElement with nodes and optional source | COMMENT |
| MEDIUM | test/storages/graph_storages/test_nebula_graph.py | 331 | # Create a GraphElement with relationships and optional source | COMMENT |
| MEDIUM | test/storages/graph_storages/test_nebula_graph.py | 431 | # Create a GraphElement instance with nodes, relationships, and source | COMMENT |
| MEDIUM | test/embeddings/test_jina_embedding.py | 37 | # Initialize embedding instance | COMMENT |
| MEDIUM | test/embeddings/test_jina_embedding.py | 61 | # Create a dummy image | COMMENT |
| MEDIUM | test/embeddings/test_jina_embedding.py | 64 | # Initialize embedding instance with CLIP model | COMMENT |
| MEDIUM | test/embeddings/test_jina_embedding.py | 95 | # Initialize embedding instance with options | COMMENT |
| MEDIUM | test/embeddings/test_jina_embedding.py | 135 | # Initialize embedding instance | COMMENT |
| MEDIUM⚡ | test/embeddings/test_openai_compatible_embedding.py | 39 | # Initialize the OpenAICompatibleEmbedding object | COMMENT |
| MEDIUM | test/embeddings/test_openai_compatible_embedding.py | 74 | # Initialize the OpenAICompatibleEmbedding object | COMMENT |
| MEDIUM | test/embeddings/test_gemini_embedding.py | 39 | # Create the embedding instance and test embed_list | COMMENT |
| MEDIUM | test/embeddings/test_gemini_embedding.py | 72 | # Create the embedding instance with task type and test embed_list | COMMENT |
| MEDIUM⚡ | test/environments/test_multi_step_env.py | 65 | # Create a mock extractor | COMMENT |
| MEDIUM | test/environments/test_multi_step_env.py | 157 | # Create a new environment with max_steps=1 | COMMENT |
| MEDIUM | test/environments/test_single_step_env.py | 144 | # Define a sample dataset | COMMENT |
| MEDIUM | test/environments/test_single_step_env.py | 161 | # Create a mock verifier | COMMENT |
| MEDIUM | test/environments/test_single_step_env.py | 394 | # Create a mock verifier | COMMENT |
| MEDIUM | test/environments/test_single_step_env.py | 482 | # Define a valid dataset | COMMENT |
| MEDIUM | test/environments/test_single_step_env.py | 948 | # Define a simple dataset | COMMENT |
| MEDIUM | test/environments/test_single_step_env.py | 965 | # Create a mock verifier | COMMENT |
| MEDIUM | test/datasets/test_base_dataset.py | 1313 | # Create a real implementation of generate_new for testing | COMMENT |
| MEDIUM | test/datasets/test_base_dataset.py | 1330 | # Create a mock verifier | COMMENT |
| MEDIUM | test/datasets/test_base_dataset.py | 1381 | # Create a test data point that would be generated | COMMENT |
| MEDIUM | test/datasets/test_base_dataset.py | 1394 | # Create a real implementation of generate_new that simulates retries and | COMMENT |
| MEDIUM | test/datasets/test_base_dataset.py | 1417 | # Create a mock verifier | COMMENT |
| MEDIUM | test/workforce/test_workflow_memory.py | 67 | # Create a mock agent with conversation history | COMMENT |
| MEDIUM | test/workforce/test_workflow_memory.py | 889 | # Creating a file should create the directory | COMMENT |
| MEDIUM | test/workforce/test_workflow_memory.py | 1011 | # Create a test workflow file | COMMENT |
| MEDIUM | test/workforce/test_workflow_memory.py | 1339 | # Create a workforce with share_memory enabled | COMMENT |
| MEDIUM | test/workforce/test_workflow_memory.py | 1278 | # Create a side_effect function that returns properly | STRING |
| MEDIUM | test/workforce/test_workforce_single_agent.py | 32 | # Create a dummy agent - won't be used since we override _process_task | COMMENT |
| MEDIUM | test/workforce/test_workforce_single_agent.py | 101 | # Create a task to test with | COMMENT |
| MEDIUM | test/workforce/test_workforce_single_agent.py | 130 | # Create a task to test with | COMMENT |
| MEDIUM | test/agents/test_chat_agent.py | 2026 | # Create an async generator that wraps the chunks | COMMENT |
| MEDIUM | test/agents/test_chat_agent.py | 1812 | # Create an all blue PNG image: | STRING |
| MEDIUM | test/agents/test_chat_agent.py | 1915 | # Create an agent with a specific system message | STRING |
| MEDIUM | test/agents/test_chat_agent.py | 1930 | # Create a new memory instance | STRING |
| MEDIUM | test/agents/test_chat_agent.py | 2097 | # Define a simple test tool | STRING |
| MEDIUM | test/agents/test_repo_agent.py | 100 | # Create a mock that is recognized as a BaseModelBackend instance | COMMENT |
| MEDIUM | test/agents/test_repo_agent.py | 181 | # Create a more complete mock for the file content | COMMENT |
| MEDIUM⚡ | test/agents/test_repo_agent.py | 290 | # Create a proper ChatAgentResponse mock | COMMENT |
| MEDIUM | test/toolkits/test_note_taking_toolkit.py | 24 | # Create a toolkit with a temporary directory | COMMENT |
| MEDIUM⚡ | test/toolkits/test_note_taking_toolkit.py | 107 | # Create a note | COMMENT |
| MEDIUM⚡ | test/toolkits/test_note_taking_toolkit.py | 110 | # Create a new toolkit instance with the same directory | COMMENT |
| MEDIUM | test/toolkits/test_todo_toolkit.py | 169 | # Create a new instance pointing to the same directory | COMMENT |
| MEDIUM | test/toolkits/test_notion_toolkit.py | 132 | # Create a NotionToolkit instance | COMMENT |
| MEDIUM | test/toolkits/test_excel_toolkit.py | 269 | # Create a file first | COMMENT |
| MEDIUM | test/toolkits/test_microsoft_outlook_mail_toolkit.py | 114 | # Create a mock credentials object to avoid OAuth authentication | COMMENT |
| MEDIUM | test/toolkits/test_context_summarizer_toolkit.py | 44 | # Create a mock model backend that behaves like a real one | COMMENT |
| MEDIUM | test/toolkits/test_context_summarizer_toolkit.py | 61 | # Create a conversation about travel planning | COMMENT |
| MEDIUM | test/toolkits/test_context_summarizer_toolkit.py | 131 | # Create a mock summary agent | COMMENT |
| 257 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | test/workforce/test_workforce_pipeline.py | 30 | CODE | |
| LOW | test/workforce/test_workflow_memory.py | 29 | CODE | |
| LOW | test/toolkits/test_pyautogui_toolkit.py | 23 | CODE | |
| LOW | test/utils/test_stream_utils.py | 15 | CODE | |
| LOW | test/loaders/test_markitdown.py | 22 | CODE | |
| LOW | camel/__init__.py | 15 | CODE | |
| LOW | camel/__init__.py | 15 | CODE | |
| LOW | camel/__init__.py | 15 | CODE | |
| LOW | camel/terminators/__init__.py | 14 | CODE | |
| LOW | camel/terminators/__init__.py | 15 | CODE | |
| LOW | camel/terminators/__init__.py | 15 | CODE | |
| LOW | camel/terminators/__init__.py | 16 | CODE | |
| LOW | camel/data_collectors/__init__.py | 15 | CODE | |
| LOW | camel/data_collectors/__init__.py | 16 | CODE | |
| LOW | camel/data_collectors/__init__.py | 17 | CODE | |
| LOW | camel/bots/telegram_bot.py | 22 | CODE | |
| LOW | camel/bots/__init__.py | 14 | CODE | |
| LOW | camel/bots/__init__.py | 15 | CODE | |
| LOW | camel/bots/__init__.py | 15 | CODE | |
| LOW | camel/bots/__init__.py | 15 | CODE | |
| LOW | camel/bots/__init__.py | 15 | CODE | |
| LOW | camel/bots/__init__.py | 15 | CODE | |
| LOW | camel/bots/__init__.py | 22 | CODE | |
| LOW | camel/bots/__init__.py | 23 | CODE | |
| LOW | camel/bots/discord/discord_app.py | 29 | CODE | |
| LOW | camel/bots/discord/__init__.py | 14 | CODE | |
| LOW | camel/bots/discord/__init__.py | 15 | CODE | |
| LOW | camel/bots/discord/__init__.py | 16 | CODE | |
| LOW | camel/bots/discord/__init__.py | 16 | CODE | |
| LOW | camel/bots/slack/__init__.py | 14 | CODE | |
| LOW | camel/bots/slack/__init__.py | 14 | CODE | |
| LOW | camel/bots/slack/__init__.py | 14 | CODE | |
| LOW | camel/bots/slack/__init__.py | 14 | CODE | |
| LOW | camel/bots/slack/__init__.py | 14 | CODE | |
| LOW | camel/bots/slack/__init__.py | 21 | CODE | |
| LOW | camel/bots/slack/slack_app.py | 32 | CODE | |
| LOW | camel/bots/slack/slack_app.py | 33 | CODE | |
| LOW | camel/bots/slack/slack_app.py | 34 | CODE | |
| LOW | camel/societies/__init__.py | 14 | CODE | |
| LOW | camel/societies/__init__.py | 15 | CODE | |
| LOW | camel/societies/workforce/worker.py | 14 | CODE | |
| LOW | camel/societies/workforce/worker.py | 29 | CODE | |
| LOW | camel/societies/workforce/single_agent_worker.py | 14 | CODE | |
| LOW | camel/societies/workforce/single_agent_worker.py | 49 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 14 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 46 | CODE | |
| LOW | camel/societies/workforce/events.py | 14 | CODE | |
| LOW | camel/societies/workforce/role_playing_worker.py | 14 | CODE | |
| LOW | camel/societies/workforce/role_playing_worker.py | 35 | CODE | |
| LOW | camel/societies/workforce/__init__.py | 15 | CODE | |
| LOW | camel/societies/workforce/__init__.py | 16 | CODE | |
| LOW | camel/societies/workforce/__init__.py | 17 | CODE | |
| LOW | camel/societies/workforce/__init__.py | 17 | CODE | |
| LOW | camel/societies/workforce/__init__.py | 17 | CODE | |
| LOW | camel/societies/workforce/__init__.py | 18 | CODE | |
| LOW | camel/societies/workforce/__init__.py | 19 | CODE | |
| LOW | camel/societies/workforce/__init__.py | 19 | CODE | |
| LOW | camel/societies/workforce/workforce_callback.py | 14 | CODE | |
| LOW | camel/interpreters/__init__.py | 15 | CODE | |
| LOW | camel/interpreters/__init__.py | 16 | CODE | |
| 716 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | test/storages/graph_storages/test_neo4j_graph.py | 44 | except Exception as e: | CODE |
| LOW | test/storages/graph_storages/test_neo4j_graph.py | 129 | except Exception as e: | CODE |
| LOW | test/workforce/test_workflow_memory.py | 2239 | except Exception as e: | STRING |
| LOW | test/toolkits/test_agent_toolkit.py | 80 | except Exception: | CODE |
| LOW | test/toolkits/test_planning_worktree_toolkit.py | 238 | except Exception as exc: | CODE |
| LOW⚡ | test/toolkits/test_sql_toolkit.py | 65 | except Exception: | CODE |
| LOW⚡ | test/toolkits/test_sql_toolkit.py | 74 | except Exception: | CODE |
| LOW⚡ | test/toolkits/test_sql_toolkit.py | 78 | except Exception: | CODE |
| LOW⚡ | test/toolkits/test_sql_toolkit.py | 476 | except Exception: | CODE |
| LOW⚡ | test/toolkits/test_code_execution.py | 41 | except Exception: | CODE |
| LOW⚡ | test/toolkits/test_code_execution.py | 63 | except Exception as e: | CODE |
| LOW | test/models/test_sglang_model.py | 61 | except Exception as e: | CODE |
| MEDIUM | test/models/test_sglang_model.py | 62 | print(f"Error during cleanup: {e}") | CODE |
| LOW | camel/logger.py | 152 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/worker.py | 125 | except Exception: | CODE |
| LOW | camel/societies/workforce/worker.py | 141 | except Exception as e: | CODE |
| LOW | camel/societies/workforce/worker.py | 168 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/worker.py | 190 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/single_agent_worker.py | 498 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/single_agent_worker.py | 503 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/single_agent_worker.py | 610 | except Exception as e: | CODE |
| LOW⚡ | camel/societies/workforce/workforce.py | 2982 | except Exception as e: | CODE |
| LOW | camel/societies/workforce/workforce.py | 1459 | except Exception as e: | CODE |
| LOW | camel/societies/workforce/workforce.py | 3443 | except Exception as e: | CODE |
| LOW | camel/societies/workforce/workforce.py | 3733 | except Exception as exc: | CODE |
| LOW | camel/societies/workforce/workforce.py | 4482 | except Exception as e: | CODE |
| LOW⚡ | camel/societies/workforce/workforce.py | 2973 | except Exception as e: | STRING |
| LOW⚡ | camel/societies/workforce/workforce.py | 3658 | except Exception as e: | STRING |
| LOW⚡ | camel/societies/workforce/workforce.py | 3668 | except Exception as e: | STRING |
| LOW⚡ | camel/societies/workforce/workforce.py | 5233 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 1265 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 1393 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 1448 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 1820 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 2018 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 2152 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 2893 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 3544 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 3635 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 4167 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 4387 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 4818 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 4897 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 4982 | except Exception: | STRING |
| LOW | camel/societies/workforce/workforce.py | 5266 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 5358 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 5491 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 5689 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 5755 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 5771 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 6024 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 6053 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 6223 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workforce.py | 6299 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workflow_memory_manager.py | 1073 | except Exception as e: | CODE |
| LOW | camel/societies/workforce/workflow_memory_manager.py | 209 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workflow_memory_manager.py | 430 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workflow_memory_manager.py | 553 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workflow_memory_manager.py | 618 | except Exception as e: | STRING |
| LOW | camel/societies/workforce/workflow_memory_manager.py | 746 | except Exception as exc: | STRING |
| 939 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | test/toolkits/test_klavis_toolkit.py | 44 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_klavis_toolkit.py | 46 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_klavis_toolkit.py | 53 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_klavis_toolkit.py | 55 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_klavis_toolkit.py | 141 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_klavis_toolkit.py | 143 | # -------------------------- | COMMENT |
| MEDIUM | test/toolkits/test_klavis_toolkit.py | 274 | # -------------------------- | COMMENT |
| MEDIUM | test/toolkits/test_klavis_toolkit.py | 276 | # -------------------------- | COMMENT |
| MEDIUM | test/toolkits/test_lark_toolkit.py | 52 | # ============================================================================ | COMMENT |
| MEDIUM | test/toolkits/test_lark_toolkit.py | 54 | # ============================================================================ | COMMENT |
| MEDIUM | test/toolkits/test_lark_toolkit.py | 89 | # ============================================================================ | COMMENT |
| MEDIUM | test/toolkits/test_lark_toolkit.py | 91 | # ============================================================================ | COMMENT |
| MEDIUM | test/toolkits/test_planning_worktree_toolkit.py | 27 | # ── helpers ────────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | test/toolkits/test_planning_worktree_toolkit.py | 61 | # ── plan-mode tests ───────────────────────────────────────────────── | COMMENT |
| MEDIUM⚡ | test/toolkits/test_planning_worktree_toolkit.py | 89 | # ── worktree tests ─────────────────────────────────────────────────── | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 51 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 53 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 92 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 94 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 107 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 109 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 140 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 142 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 159 | # -------------------------- | COMMENT |
| MEDIUM⚡ | test/toolkits/test_image_analysis_toolkiy.py | 161 | # -------------------------- | COMMENT |
| MEDIUM | test/loaders/test_crawl4ai.py | 37 | # ------------------------ | COMMENT |
| MEDIUM | test/loaders/test_crawl4ai.py | 39 | # ------------------------ | COMMENT |
| MEDIUM⚡ | camel/societies/workforce/workforce.py | 794 | # ------------------------------------------------------------------ | STRING |
| MEDIUM⚡ | camel/societies/workforce/workforce.py | 796 | # ------------------------------------------------------------------ | STRING |
| MEDIUM | camel/societies/workforce/workforce.py | 557 | # ------------------------------------------------------------------ | STRING |
| MEDIUM | camel/societies/workforce/workforce.py | 559 | # ------------------------------------------------------------------ | STRING |
| MEDIUM⚡ | camel/toolkits/file_toolkit.py | 1163 | # ---------------------------------------------- | STRING |
| MEDIUM⚡ | camel/toolkits/file_toolkit.py | 1165 | # ---------------------------------------------- | STRING |
| MEDIUM⚡ | camel/toolkits/file_toolkit.py | 1240 | # ---------------------------------------------- | STRING |
| MEDIUM⚡ | camel/toolkits/file_toolkit.py | 1242 | # ---------------------------------------------- | STRING |
| MEDIUM | camel/toolkits/headless_browser_search_toolkit.py | 113 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | camel/toolkits/headless_browser_search_toolkit.py | 117 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | camel/toolkits/todo_toolkit.py | 88 | # ── persistence helpers ────────────────────────────────────────── | STRING |
| MEDIUM | camel/toolkits/todo_toolkit.py | 143 | # ── tool methods ───────────────────────────────────────────────── | COMMENT |
| MEDIUM | camel/toolkits/hybrid_browser_toolkit_py/actions.py | 59 | # ------------------------------------------------------------------ | STRING |
| MEDIUM | camel/toolkits/hybrid_browser_toolkit_py/actions.py | 61 | # ------------------------------------------------------------------ | STRING |
| MEDIUM⚡ | camel/toolkits/hybrid_browser_toolkit_py/actions.py | 127 | # ------------------------------------------------------------------ | STRING |
| MEDIUM⚡ | camel/toolkits/hybrid_browser_toolkit_py/actions.py | 129 | # ------------------------------------------------------------------ | STRING |
| MEDIUM⚡ | …/toolkits/hybrid_browser_toolkit_py/browser_session.py | 239 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | …/toolkits/hybrid_browser_toolkit_py/browser_session.py | 241 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | …/toolkits/hybrid_browser_toolkit_py/browser_session.py | 473 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | …/toolkits/hybrid_browser_toolkit_py/browser_session.py | 475 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | …/toolkits/hybrid_browser_toolkit_py/browser_session.py | 725 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | …/toolkits/hybrid_browser_toolkit_py/browser_session.py | 727 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | camel/toolkits/hybrid_browser_toolkit_py/snapshot.py | 47 | # --------------------------------------------------------------------- | STRING |
| MEDIUM | camel/toolkits/hybrid_browser_toolkit_py/snapshot.py | 49 | # --------------------------------------------------------------------- | STRING |
| MEDIUM⚡ | camel/toolkits/hybrid_browser_toolkit_py/snapshot.py | 133 | # ------------------------------------------------------------------ | STRING |
| MEDIUM⚡ | camel/toolkits/hybrid_browser_toolkit_py/snapshot.py | 135 | # ------------------------------------------------------------------ | STRING |
| MEDIUM | camel/toolkits/hybrid_browser_toolkit_py/snapshot.py | 251 | # ------------------------------------------------------------------ | STRING |
| MEDIUM | camel/toolkits/terminal_toolkit/runtime_utils.py | 38 | # ── Type Aliases ───────────────────────────────────────────────────── | STRING |
| MEDIUM | camel/toolkits/terminal_toolkit/runtime_utils.py | 53 | # ── Constants ──────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | camel/toolkits/terminal_toolkit/runtime_utils.py | 59 | # ── URL Templates ──────────────────────────────────────────────────── | COMMENT |
| MEDIUM | camel/toolkits/terminal_toolkit/runtime_utils.py | 72 | # ── Architecture & OS Mappings ─────────────────────────────────────── | COMMENT |
| MEDIUM | camel/toolkits/terminal_toolkit/runtime_utils.py | 84 | # ── Exceptions ─────────────────────────────────────────────────────── | COMMENT |
| MEDIUM | camel/toolkits/terminal_toolkit/runtime_utils.py | 99 | # ── Platform Detection ─────────────────────────────────────────────── | COMMENT |
| 62 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | test/conftest.py | 50 | CODE | |
| LOW | test/storages/vector_storages/test_oceanbase.py | 154 | CODE | |
| LOW | test/storages/vector_storages/test_oceanbase.py | 211 | CODE | |
| LOW | test/storages/vector_storages/test_oceanbase.py | 250 | CODE | |
| LOW | test/storages/vector_storages/test_oceanbase.py | 290 | CODE | |
| LOW | test/storages/vector_storages/test_oceanbase.py | 390 | CODE | |
| LOW | test/storages/vector_storages/test_oceanbase.py | 446 | CODE | |
| LOW | test/storages/vector_storages/test_oceanbase.py | 497 | CODE | |
| LOW | test/environments/test_tictactoe_env.py | 321 | CODE | |
| LOW | test/agents/test_chat_agent.py | 2068 | CODE | |
| LOW | test/toolkits/test_pyautogui_toolkit.py | 140 | CODE | |
| LOW | test/toolkits/test_pyautogui_toolkit.py | 216 | CODE | |
| LOW | test/models/test_openai_model.py | 222 | CODE | |
| LOW | test/memories/test_vector_db_memory.py | 147 | CODE | |
| LOW | camel/terminators/response_terminator.py | 61 | CODE | |
| LOW | camel/data_collectors/sharegpt_collector.py | 97 | CODE | |
| LOW | camel/societies/role_playing.py | 214 | CODE | |
| LOW | camel/societies/role_playing.py | 264 | CODE | |
| LOW | camel/societies/role_playing.py | 466 | CODE | |
| LOW | camel/societies/workforce/worker.py | 151 | CODE | |
| LOW | camel/societies/workforce/task_channel.py | 148 | CODE | |
| LOW | camel/societies/workforce/task_channel.py | 174 | CODE | |
| LOW | camel/societies/workforce/task_channel.py | 275 | CODE | |
| LOW | camel/societies/workforce/single_agent_worker.py | 349 | CODE | |
| LOW | camel/societies/workforce/workforce_logger.py | 401 | CODE | |
| LOW | camel/societies/workforce/workforce_logger.py | 550 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 1362 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 1645 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 1828 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 2903 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 2992 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 3561 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 4186 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 4397 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 4941 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 5282 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 5867 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 5925 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 6095 | CODE | |
| LOW | camel/societies/workforce/workflow_memory_manager.py | 121 | CODE | |
| LOW | camel/societies/workforce/workflow_memory_manager.py | 438 | CODE | |
| LOW | camel/societies/workforce/structured_output_handler.py | 158 | CODE | |
| LOW | camel/societies/workforce/structured_output_handler.py | 213 | CODE | |
| LOW | camel/societies/workforce/structured_output_handler.py | 281 | CODE | |
| LOW | camel/societies/workforce/structured_output_handler.py | 345 | CODE | |
| LOW | camel/societies/workforce/structured_output_handler.py | 462 | CODE | |
| LOW | camel/societies/workforce/utils.py | 734 | CODE | |
| LOW | camel/societies/workforce/utils.py | 301 | CODE | |
| LOW | camel/societies/workforce/utils.py | 764 | CODE | |
| LOW | camel/societies/workforce/utils.py | 766 | CODE | |
| LOW | camel/interpreters/ipython_interpreter.py | 84 | CODE | |
| LOW | camel/interpreters/docker_interpreter.py | 211 | CODE | |
| LOW | camel/interpreters/e2b_interpreter.py | 110 | CODE | |
| LOW | camel/interpreters/microsandbox_interpreter.py | 160 | CODE | |
| LOW | camel/interpreters/internal_python_interpreter.py | 296 | CODE | |
| LOW | camel/interpreters/internal_python_interpreter.py | 408 | CODE | |
| LOW | camel/interpreters/internal_python_interpreter.py | 498 | CODE | |
| LOW | camel/interpreters/internal_python_interpreter.py | 593 | CODE | |
| LOW | camel/interpreters/subprocess_interpreter.py | 88 | CODE | |
| LOW | camel/interpreters/subprocess_interpreter.py | 269 | CODE | |
| 303 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | test/bots/test_telegram_bot.py | 52 | # Check if the chat agent's methods are called appropriately | COMMENT |
| LOW | test/bots/test_telegram_bot.py | 56 | # Check if the bot replies with the correct message | COMMENT |
| LOW⚡ | test/embeddings/test_openai_compatible_embedding.py | 49 | # Check if the OpenAI client was called with the correct parameters | COMMENT |
| LOW⚡ | test/embeddings/test_openai_compatible_embedding.py | 54 | # Check if the result is as expected | COMMENT |
| LOW | test/datasets/test_self_instruct_generator.py | 181 | # Check if the agent was called with the correct prompt | COMMENT |
| LOW | test/datasets/test_self_instruct_generator.py | 209 | # Check if the agent was called with the correct prompt | COMMENT |
| LOW | test/workforce/test_workforce_pipeline.py | 286 | # Check if task 3 should be posted (PIPELINE mode continues) | COMMENT |
| LOW | test/workforce/test_workforce_pipeline.py | 333 | # Check if Task D should execute | COMMENT |
| LOW | test/agents/test_chat_agent.py | 1325 | # Check if the output language is set correctly | COMMENT |
| LOW | test/toolkits/test_klavis_toolkit.py | 292 | # Check if the function name matches the expected name | COMMENT |
| LOW | test/toolkits/test_bohrium_toolkit.py | 162 | # Check if result contains the expected job information | COMMENT |
| LOW⚡ | test/toolkits/test_pyautogui_toolkit.py | 44 | # Check if screen dimensions are properly set | COMMENT |
| LOW⚡ | test/toolkits/test_pyautogui_toolkit.py | 48 | # Check if safe boundaries are properly calculated | COMMENT |
| LOW⚡ | test/toolkits/test_pyautogui_toolkit.py | 55 | # Check if screen center is properly calculated | COMMENT |
| LOW⚡ | test/toolkits/test_pyautogui_toolkit.py | 58 | # Check if screenshots directory is properly set | COMMENT |
| LOW | test/toolkits/test_semantic_scholar_functions.py | 230 | # Check if JSON body includes the correct IDs | COMMENT |
| LOW | test/toolkits/test_search_functions.py | 425 | # Check if the result is as expected | COMMENT |
| LOW | test/toolkits/test_search_functions.py | 468 | # Check if the result matches the expected output | COMMENT |
| LOW | test/toolkits/test_search_functions.py | 798 | # Check if the result is as expected | COMMENT |
| LOW | test/toolkits/test_weather_function.py | 100 | # Set manager to return mock observation | COMMENT |
| LOW | test/toolkits/test_browser_toolkit.py | 81 | ) # Check if __init__ created it | CODE |
| LOW⚡ | test/toolkits/test_code_execution.py | 58 | # Check if the python executable exists | COMMENT |
| LOW⚡ | test/toolkits/test_code_execution.py | 101 | # Check if microsandbox server is running | COMMENT |
| LOW | test/toolkits/test_file_toolkit.py | 442 | # Read the file to verify content | COMMENT |
| LOW⚡ | test/utils/test_commons.py | 83 | # Check if the result is a dictionary | COMMENT |
| LOW⚡ | test/utils/test_commons.py | 97 | # Check if all expected keys are in the returned dictionary | COMMENT |
| LOW⚡ | test/utils/test_commons.py | 100 | # Check if all values are non-empty strings | COMMENT |
| LOW⚡ | test/prompts/test_prompt_base.py | 66 | # Check if the functions are wrapped correctly | COMMENT |
| LOW⚡ | licenses/update_license.py | 88 | # Check if directory exists | COMMENT |
| LOW⚡ | licenses/update_license.py | 91 | # Check if license template exists | COMMENT |
| LOW | camel/societies/workforce/task_channel.py | 263 | # Check if task ID exists before removing | COMMENT |
| LOW | camel/societies/workforce/single_agent_worker.py | 132 | # Check if we can create a new agent | COMMENT |
| LOW⚡ | camel/societies/workforce/workforce.py | 2478 | # Check if all provided IDs exist | COMMENT |
| LOW⚡ | camel/societies/workforce/workforce.py | 2488 | # Check if we have the same number of tasks | COMMENT |
| LOW | camel/societies/workforce/workforce.py | 574 | # Check if any metrics callback is provided | COMMENT |
| LOW | camel/societies/workforce/workforce.py | 4471 | # Check if task is already assigned to a worker | COMMENT |
| LOW | camel/societies/workforce/workforce.py | 4489 | # Check if all dependencies are in the completed state | COMMENT |
| LOW | camel/societies/workforce/workforce.py | 4547 | # Check if any failed dependencies can still be | COMMENT |
| LOW | camel/societies/workforce/workforce.py | 4556 | # Check if any failed dependency is still retryable | COMMENT |
| LOW⚡ | camel/societies/workforce/workforce.py | 5241 | # Check if there are any main pending tasks after filtering | STRING |
| LOW⚡ | camel/societies/workforce/workforce.py | 5243 | # Check if the first pending task needs decomposition | STRING |
| LOW | camel/societies/workforce/workforce.py | 2839 | # Check if we're already in an event loop | STRING |
| LOW | camel/societies/workforce/workforce.py | 3007 | # Check if we're in the same thread as the loop | STRING |
| LOW | camel/societies/workforce/workforce.py | 3809 | # Check if we should use structured handler | STRING |
| LOW | camel/societies/workforce/workforce.py | 4204 | # Check if we should use structured handler | STRING |
| LOW | camel/societies/workforce/workforce.py | 4716 | # Check if halt_on_max_retries is disabled in config | STRING |
| LOW | camel/societies/workforce/workforce.py | 4764 | # Check if no recovery strategies are enabled (empty list) | STRING |
| LOW | camel/societies/workforce/workforce.py | 4774 | # Check if only one strategy is enabled (skip LLM analysis) | STRING |
| LOW | camel/societies/workforce/workforce.py | 4922 | # Check if any pending tasks are now ready to execute | STRING |
| LOW | camel/societies/workforce/workforce.py | 5047 | # Check if all subtasks are completed and successful | STRING |
| LOW | camel/societies/workforce/workforce.py | 5097 | # Check if any pending tasks are now ready to execute | STRING |
| LOW | camel/societies/workforce/workforce.py | 5320 | # Check if we should decompose a main task | STRING |
| LOW | camel/societies/workforce/workforce.py | 5327 | # Check if the first pending task needs decomposition | STRING |
| LOW | camel/societies/workforce/workforce.py | 5430 | # Check if the "completed" task actually failed to provide | STRING |
| LOW | camel/interpreters/subprocess_interpreter.py | 172 | # Check if command is available | STRING |
| LOW | camel/interpreters/subprocess_interpreter.py | 188 | # Check if command is available | STRING |
| LOW | camel/retrievers/vector_retriever.py | 125 | # Check if the content is URL | STRING |
| LOW | camel/storages/vectordb_storages/faiss.py | 304 | # Check if the index needs training (for IVF indexes) | STRING |
| LOW | camel/storages/vectordb_storages/faiss.py | 461 | # Check if the index supports direct removal. | STRING |
| LOW | camel/storages/vectordb_storages/oceanbase.py | 417 | # Check if the id is stored in metadata | STRING |
| 177 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH⚡ | test/toolkits/test_terminal_toolkit.py | 296 | "cd sub && cd ..", | CODE |
| HIGH⚡ | test/toolkits/test_terminal_toolkit.py | 298 | "cd sub || cd ..", | CODE |
| HIGH⚡ | test/toolkits/test_terminal_toolkit.py | 299 | "false && cd sub; cd ..", | CODE |
| HIGH⚡ | test/toolkits/test_terminal_toolkit.py | 316 | "cd sub && ls", | CODE |
| HIGH⚡ | test/toolkits/test_terminal_toolkit.py | 317 | "cd sub && echo hello", | CODE |
| HIGH⚡ | test/toolkits/test_terminal_toolkit.py | 318 | "ls && cd sub", | CODE |
| HIGH⚡ | test/toolkits/test_terminal_toolkit.py | 336 | "pushd sub && pushd .", working_dir=str(temp_dir) | CODE |
| HIGH⚡ | test/toolkits/test_terminal_toolkit.py | 347 | "cd sub && pushd .", working_dir=str(temp_dir) | CODE |
| HIGH | test/loaders/test_jina_url_reader.py | 45 | FAILED_RESP = r'''{"data":null,"cause":{"name":"TimeoutError"},"code":422,"name":"AssertionFailureError","status":42206, | STRING |
| HIGH | camel/toolkits/browser_toolkit.py | 690 | if (el.innerText && el.innerText.includes(text)) {{ | CODE |
| HIGH | camel/toolkits/async_browser_toolkit.py | 813 | if (el.innerText && el.innerText.includes(text)) {{ | CODE |
| HIGH⚡ | camel/toolkits/headless_browser_search_toolkit.py | 131 | if (linkEl && titleEl) { | CODE |
| HIGH⚡ | camel/toolkits/headless_browser_search_toolkit.py | 133 | if (url && url.indexOf('google.com/search') === -1 && | CODE |
| HIGH⚡ | camel/toolkits/headless_browser_search_toolkit.py | 137 | results.push({ | CODE |
| HIGH | camel/toolkits/headless_browser_search_toolkit.py | 190 | if (title && url) { | CODE |
| HIGH | camel/toolkits/headless_browser_search_toolkit.py | 191 | results.push({ | CODE |
| HIGH | camel/toolkits/headless_browser_search_toolkit.py | 226 | if (!url || seen[url]) continue; | CODE |
| HIGH | camel/toolkits/headless_browser_search_toolkit.py | 240 | if (title && url) { | CODE |
| HIGH | camel/toolkits/headless_browser_search_toolkit.py | 241 | results.push({ | CODE |
| HIGH | camel/toolkits/hybrid_browser_toolkit_py/agent.py | 66 | \n \"ref\": null,\n \"summary\": \"Task was already completed. Summary | CODE |
| HIGH | camel/toolkits/hybrid_browser_toolkit_py/agent.py | 82 | - 'finish': {"type": "finish", "ref": null, "summary": "task completion | CODE |
| HIGH | …ts/hybrid_browser_toolkit_py/hybrid_browser_toolkit.py | 2047 | _logs.push(args.map(arg => { | CODE |
| HIGH | camel/toolkits/terminal_toolkit/utils.py | 57 | "For example, instead of 'cd subdir && cd ..', run 'cd subdir' " | CODE |
| HIGH | camel/models/moonshot_model.py | 186 | # All were null, use string as fallback | COMMENT |
| HIGH | camel/models/moonshot_model.py | 189 | "were null, falling back to 'string' " | CODE |
| HIGH | camel/models/moonshot_model.py | 213 | # All were null, return string type as fallback | COMMENT |
| HIGH | camel/models/moonshot_model.py | 215 | "All types in tool schema anyOf were null, " | CODE |
| HIGH | camel/personas/persona.py | 93 | # Output: '{"name": "Alice", "description": null, "text_to_persona_prompt": "...", "persona_to_persona_prompt": | STRING |
| HIGH | docs/mintlify/build_api_docs.py | 1352 | print(" cd docs/mintlify && npx mintlify dev") | CODE |
| HIGH | examples/toolkits/dynamic_dependency.py | 98 | if (!matrix1 || !matrix2 || matrix1.length === 0 || matrix2.length === 0) { | STRING |
| HIGH | examples/toolkits/dynamic_dependency.py | 113 | result.push(sum); | STRING |
| HIGH | examples/toolkits/mcp/mcp_search_toolkit.py | 40 | "external_url": null, | STRING |
| HIGH⚡ | examples/toolkits/mcp/mcp_search_toolkit.py | 56 | "package_registry": null, | STRING |
| HIGH⚡ | examples/toolkits/mcp/mcp_search_toolkit.py | 57 | "package_name": null, | STRING |
| HIGH⚡ | examples/toolkits/mcp/mcp_search_toolkit.py | 58 | "package_download_count": null, | STRING |
| HIGH⚡ | examples/toolkits/mcp/mcp_search_toolkit.py | 80 | "package_registry": null, | STRING |
| HIGH⚡ | examples/toolkits/mcp/mcp_search_toolkit.py | 81 | "package_name": null, | STRING |
| HIGH⚡ | examples/toolkits/mcp/mcp_search_toolkit.py | 82 | "package_download_count": null, | STRING |
| HIGH | examples/toolkits/mcp/mcp_search_toolkit.py | 108 | "external_url": null, | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | test/environments/test_multi_step_env.py | 34 | async def _update_state(self, action: Action) -> None: | CODE |
| LOW⚡ | test/environments/test_multi_step_env.py | 54 | async def _setup(self) -> None: | CODE |
| LOW | test/verifiers/test_base_verifier.py | 28 | async def _setup(self, **kwargs) -> None: | CODE |
| LOW | test/verifiers/test_base_verifier.py | 106 | async def _setup(self, **kwargs) -> None: | CODE |
| LOW | camel/__init__.py | 19 | __all__ = [ | CODE |
| LOW | camel/terminators/__init__.py | 18 | __all__ = [ | CODE |
| LOW | camel/data_collectors/__init__.py | 19 | __all__ = ["BaseDataCollector", "AlpacaDataCollector", "ShareGPTDataCollector"] | CODE |
| LOW | camel/bots/__init__.py | 25 | __all__ = [ | CODE |
| LOW | camel/bots/discord/__init__.py | 21 | __all__ = [ | CODE |
| LOW | camel/bots/slack/__init__.py | 23 | __all__ = [ | CODE |
| LOW | camel/bots/slack/slack_app.py | 37 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/societies/role_playing.py | 32 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/societies/__init__.py | 17 | __all__ = [ | CODE |
| LOW | camel/societies/workforce/worker.py | 31 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/societies/workforce/workforce.py | 1190 | def set_pipeline_tasks(self, tasks: List[Task]) -> None: | CODE |
| LOW⚡ | camel/societies/workforce/workforce.py | 3672 | def set_channel(self, channel: TaskChannel) -> None: | STRING |
| LOW | camel/societies/workforce/__init__.py | 21 | __all__ = [ | CODE |
| LOW | camel/interpreters/ipython_interpreter.py | 177 | def update_action_space(self, action_space: Dict[str, Any]) -> None: | STRING |
| LOW | camel/interpreters/docker_interpreter.py | 290 | def update_action_space(self, action_space: Dict[str, Any]) -> None: | CODE |
| LOW | camel/interpreters/e2b_interpreter.py | 227 | def update_action_space(self, action_space: Dict[str, Any]) -> None: | CODE |
| LOW | camel/interpreters/microsandbox_interpreter.py | 318 | def update_action_space(self, action_space: Dict[str, Any]) -> None: | CODE |
| LOW | camel/interpreters/__init__.py | 24 | __all__ = [ | CODE |
| LOW | camel/interpreters/internal_python_interpreter.py | 208 | def update_action_space(self, action_space: Dict[str, Any]) -> None: | STRING |
| LOW | camel/interpreters/subprocess_interpreter.py | 396 | def update_action_space(self, action_space: Dict[str, Any]) -> None: | CODE |
| LOW | camel/interpreters/base.py | 47 | def update_action_space(self, action_space: Dict[str, Any]) -> None: | CODE |
| LOW | camel/retrievers/__init__.py | 24 | __all__ = [ | CODE |
| LOW | camel/storages/__init__.py | 38 | __all__ = [ | CODE |
| LOW | camel/storages/vectordb_storages/milvus.py | 28 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/storages/vectordb_storages/qdrant.py | 33 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/storages/vectordb_storages/tidb.py | 33 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/storages/vectordb_storages/__init__.py | 32 | __all__ = [ | CODE |
| LOW | camel/storages/vectordb_storages/oceanbase.py | 32 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/storages/key_value_storages/mem0_cloud.py | 27 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/storages/key_value_storages/__init__.py | 21 | __all__ = [ | CODE |
| LOW | camel/storages/key_value_storages/redis.py | 26 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/storages/graph_storages/__init__.py | 20 | __all__ = [ | CODE |
| LOW | camel/storages/graph_storages/nebula_graph.py | 26 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/storages/graph_storages/neo4j_graph.py | 22 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/storages/object_storages/__init__.py | 18 | __all__ = [ | CODE |
| LOW | camel/parsers/__init__.py | 18 | __all__ = ["extract_tool_calls_from_text"] | CODE |
| LOW | camel/parsers/mcp_tool_call_parser.py | 45 | logger = logging.getLogger(__name__) | STRING |
| LOW | camel/tasks/__init__.py | 17 | __all__ = [ | CODE |
| LOW | camel/messages/__init__.py | 50 | __all__ = [ | CODE |
| LOW | camel/messages/conversion/__init__.py | 24 | __all__ = [ | CODE |
| LOW | camel/messages/conversion/sharegpt/__init__.py | 18 | __all__ = [ | CODE |
| LOW | camel/messages/conversion/sharegpt/hermes/__init__.py | 17 | __all__ = [ | CODE |
| LOW | camel/types/__init__.py | 57 | __all__ = [ | CODE |
| LOW | camel/types/openai_types.py | 38 | __all__ = [ | CODE |
| LOW | camel/types/unified_model_type.py | 22 | logger = logging.getLogger(__name__) | CODE |
| LOW | camel/types/agents/__init__.py | 16 | __all__ = ["ToolCallingRecord"] | CODE |
| LOW | camel/embeddings/__init__.py | 25 | __all__ = [ | CODE |
| LOW | camel/environments/rlcards_env.py | 102 | async def _setup(self) -> None: | STRING |
| LOW | camel/environments/rlcards_env.py | 163 | async def _update_state(self, action: Action) -> None: | STRING |
| LOW | camel/environments/__init__.py | 26 | __all__ = [ | CODE |
| LOW | camel/environments/multi_step.py | 75 | async def _setup(self) -> None: | STRING |
| LOW | camel/environments/multi_step.py | 214 | async def _update_state(self, action: Action) -> None: | STRING |
| LOW | camel/environments/tic_tac_toe.py | 245 | async def _update_state(self, action: Action) -> None: | STRING |
| LOW | camel/datasets/__init__.py | 20 | __all__ = [ | CODE |
| LOW | camel/datahubs/__init__.py | 19 | __all__ = [ | CODE |
| LOW | camel/responses/__init__.py | 16 | __all__ = [ | CODE |
| 67 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | camel/societies/role_playing.py | 92 | CODE | |
| LOW | camel/societies/workforce/workforce.py | 323 | CODE | |
| LOW | camel/retrievers/hybrid_retrival.py | 156 | CODE | |
| LOW | camel/storages/vectordb_storages/surreal.py | 62 | CODE | |
| LOW | camel/storages/vectordb_storages/weaviate.py | 140 | CODE | |
| LOW | camel/storages/vectordb_storages/chroma.py | 138 | CODE | |
| LOW | camel/datasets/static_dataset.py | 444 | CODE | |
| LOW | camel/datahubs/huggingface.py | 50 | CODE | |
| LOW | camel/verifiers/base.py | 46 | CODE | |
| LOW | camel/agents/repo_agent.py | 122 | CODE | |
| LOW | camel/agents/search_agent.py | 106 | CODE | |
| LOW | camel/agents/chat_agent.py | 473 | CODE | |
| LOW | camel/toolkits/openbb_toolkit.py | 217 | CODE | |
| LOW | camel/toolkits/aci_toolkit.py | 410 | CODE | |
| LOW | camel/toolkits/aci_toolkit.py | 442 | CODE | |
| LOW | camel/toolkits/mcp_toolkit.py | 333 | CODE | |
| LOW | camel/toolkits/mcp_toolkit.py | 601 | CODE | |
| LOW | camel/toolkits/mcp_toolkit.py | 673 | CODE | |
| LOW | camel/toolkits/browser_toolkit.py | 307 | CODE | |
| LOW | camel/toolkits/browser_toolkit.py | 815 | CODE | |
| LOW | camel/toolkits/imap_mail_toolkit.py | 73 | CODE | |
| LOW | camel/toolkits/video_analysis_toolkit.py | 124 | CODE | |
| LOW | camel/toolkits/mineru_toolkit.py | 43 | CODE | |
| LOW | camel/toolkits/image_generation_toolkit.py | 46 | CODE | |
| LOW | camel/toolkits/message_integration.py | 427 | CODE | |
| LOW | camel/toolkits/message_integration.py | 468 | CODE | |
| LOW | camel/toolkits/async_browser_toolkit.py | 332 | CODE | |
| LOW | camel/toolkits/async_browser_toolkit.py | 986 | CODE | |
| LOW | camel/toolkits/microsoft_outlook_mail_toolkit.py | 742 | CODE | |
| LOW | camel/toolkits/search_toolkit.py | 322 | CODE | |
| LOW | camel/toolkits/search_toolkit.py | 1405 | CODE | |
| LOW | camel/toolkits/search_toolkit.py | 1670 | CODE | |
| LOW | camel/toolkits/function_tool.py | 1114 | CODE | |
| LOW | camel/toolkits/wechat_official_toolkit.py | 232 | CODE | |
| LOW | camel/toolkits/wechat_official_toolkit.py | 260 | CODE | |
| LOW | camel/toolkits/wechat_official_toolkit.py | 357 | CODE | |
| LOW | camel/toolkits/bohrium_toolkit.py | 97 | CODE | |
| LOW | …/toolkits/hybrid_browser_toolkit_py/browser_session.py | 71 | CODE | |
| LOW | …/toolkits/hybrid_browser_toolkit_py/browser_session.py | 142 | CODE | |
| LOW | …ts/hybrid_browser_toolkit_py/hybrid_browser_toolkit.py | 88 | CODE | |
| LOW | camel/toolkits/terminal_toolkit/terminal_toolkit.py | 105 | CODE | |
| LOW | …ts/hybrid_browser_toolkit/hybrid_browser_toolkit_ts.py | 307 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 757 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 776 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 861 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 877 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 885 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 893 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 899 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 909 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 950 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 972 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 993 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 1009 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 1015 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 1021 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 1027 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 1033 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 1059 | CODE | |
| LOW | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 1069 | CODE | |
| 18 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| CRITICAL | test/models/test_azure_openai_model.py | 195 | model._client.chat.completions.create.assert_called_once() | CODE |
| CRITICAL | test/models/test_fish_audio_model.py | 54 | mock_file.return_value.__enter__.return_value.write.assert_called_once_with( | CODE |
| CRITICAL | test/loaders/test_apify.py | 51 | apify.client.actor.return_value.call.assert_called_once_with( | CODE |
| CRITICAL | test/loaders/test_apify.py | 123 | apify.client.datasets.return_value.list.assert_called_once_with( | CODE |
| CRITICAL | camel/storages/object_storages/azure_blob.py | 67 | from azure.core.exceptions import ClientAuthenticationError | CODE |
| CRITICAL | camel/schemas/openai_converter.py | 104 | response = self._client.beta.chat.completions.parse( | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | camel/storages/vectordb_storages/chroma.py | 133 | ... api_key="your-api-key" # optional | CODE |
| HIGH | camel/toolkits/mcp_toolkit.py | 316 | "X-API-Key": "YOUR_API_KEY" | CODE |
| HIGH | docs/mcp/camel_agents_as_an_mcp_clients.md | 49 | "COMPOSIO_API_KEY": "your-api-key-here" | CODE |
| HIGH | docs/key_modules/models.md | 368 | export OPENROUTER_API_KEY="your-api-key-here" | CODE |
| HIGH | docs/key_modules/datagen.md | 449 | api_key="your_api_key" | CODE |
| HIGH | examples/storages/chroma_vector_storage.py | 117 | CHROMA_API_KEY = "your-api-key" # Optional | CODE |
| HIGH | examples/agents/repo_agent.py | 132 | api_key="your_api_key", # Ensure you have appropriate credentials | STRING |
| HIGH⚡ | examples/models/nvidia_model_example.py | 61 | api_key = 'YOUR_API_KEY' | STRING |
| HIGH | examples/models/xai_model_example.py | 19 | export XAI_API_KEY="your_api_key" | STRING |
| HIGH | examples/models/claude_model_example.py | 27 | export ANTHROPIC_API_KEY="your-api-key-here" | STRING |
| HIGH | examples/models/amd_model_example.py | 70 | API_KEY = 'YOUR_API_KEY' | STRING |
| HIGH⚡ | examples/models/qwen_model_example.py | 145 | api_key='YOUR_API_KEY', | STRING |
| HIGH | examples/models/qwen_model_example.py | 255 | API_KEY = 'your_api_key' | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | test/services/test_agent_openapi_server.py | 119 | # Step 1: Init | STRING |
| LOW | test/services/test_agent_openapi_server.py | 132 | # Step 2: Async step with tool | STRING |
| LOW | camel/societies/workforce/workforce.py | 4401 | # Step 1: Identify and assign any new tasks in the pending queue | COMMENT |
| LOW | camel/societies/workforce/workforce.py | 4457 | # Step 2: Iterate through all pending tasks and post those that are | COMMENT |
| LOW | camel/societies/workforce/workforce.py | 4633 | # Step 3: Remove the posted tasks from the pending list | COMMENT |
| LOW | …ts/hybrid_browser_toolkit/hybrid_browser_toolkit_ts.py | 1798 | # Step 1: Setup copy interception with multiple captures | STRING |
| LOW | …lkits/hybrid_browser_toolkit/ts/src/browser-session.ts | 1210 | // Step 1: Try to find input elements within the clicked element | COMMENT |
| LOW | …lkits/hybrid_browser_toolkit/ts/src/browser-session.ts | 1237 | // Step 2: Look for new elements that appeared after the action | COMMENT |
| LOW | …ata_processing/summarisation_agent_with_mistral_ocr.md | 119 | ## Step 4: Obtain OCR output from Mistral | COMMENT |
| LOW | .camel/skills/skill-creator/SKILL.md | 215 | ### Step 1: Understanding the Skill with Concrete Examples | COMMENT |
| LOW | .camel/skills/skill-creator/SKILL.md | 232 | ### Step 2: Planning the Reusable Skill Contents | COMMENT |
| LOW | .camel/skills/skill-creator/SKILL.md | 256 | ### Step 3: Initializing the Skill | COMMENT |
| LOW | .camel/skills/skill-creator/SKILL.md | 281 | ### Step 4: Edit the Skill | COMMENT |
| LOW | .camel/skills/skill-creator/SKILL.md | 322 | ### Step 5: Packaging a Skill | COMMENT |
| LOW | .camel/skills/skill-creator/SKILL.md | 353 | ### Step 6: Iterate | COMMENT |
| LOW | examples/storages/nebular_graph.py | 24 | # Step 2: Initialize the NebulaGraph client | COMMENT |
| LOW⚡ | examples/models/ppio_model_example.py | 102 | ### Step 1: Set up the divisibility condition | STRING |
| LOW⚡ | examples/models/ppio_model_example.py | 108 | ### Step 2: Perform polynomial division or find a relationship | STRING |
| LOW | examples/models/ppio_model_example.py | 119 | ### Step 3: Find all divisors of 56 | STRING |
| LOW⚡ | examples/models/ppio_model_example.py | 130 | ### Step 4: Solve for $ b $ | STRING |
| LOW⚡ | examples/models/ppio_model_example.py | 140 | ### Step 5: Verify the solutions | STRING |
| LOW | examples/models/ppio_model_example.py | 152 | ### Step 6: Sum the valid bases | STRING |
| LOW⚡ | examples/services/agent_openapi_server.py | 341 | # Step 1: Create two agents | STRING |
| LOW⚡ | examples/services/agent_openapi_server.py | 352 | # Step 2: List current agents | STRING |
| LOW⚡ | examples/services/agent_openapi_server.py | 356 | # Step 3: Delete agent_1 | STRING |
| LOW⚡ | examples/services/agent_openapi_server.py | 360 | # Step 4: List agents again | STRING |
| LOW⚡ | examples/caches/semantic_cache_example.py | 53 | # Step 1: Initialize the embedding model | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 68 | # Step 2: Initialize vector storage (in-memory FAISS) | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 76 | # Step 3: Create the semantic cache | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 85 | # Step 4: Populate the cache with some responses | COMMENT |
| LOW | examples/caches/semantic_cache_example.py | 124 | # Step 5: Test cache lookups with similar queries | COMMENT |
| LOW | examples/caches/semantic_cache_example.py | 155 | # Step 6: Demonstrate deduplication (Replacement) | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 170 | # Step 7: Show cache statistics | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 178 | # Step 8: Demonstrate find_similar | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 188 | # Step 9: Demonstrate cache management | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | test/bots/test_discord_app.py | 24 | os.environ['DISCORD_BOT_TOKEN'] = 'fake_token' | CODE |
| LOW⚡ | test/bots/test_discord_app.py | 35 | self.assertEqual(app.token, 'fake_token') | CODE |
| LOW | test/bots/test_discord_app.py | 126 | app._client.start.assert_called_once_with('fake_token') | CODE |
| LOW | test/bots/test_discord_app.py | 135 | app._client.run.assert_called_once_with('fake_token') | CODE |
| LOW | test/bots/test_slack_app.py | 24 | os.environ["SLACK_TOKEN"] = "fake_token" | CODE |
| LOW | test/bots/test_telegram_bot.py | 24 | self.telegram_token = "123456789:fake_token" | CODE |
| LOW | test/datahubs/test_huggingface.py | 53 | manager = HuggingFaceDatasetManager(token="fake-token") | CODE |
| LOW | test/toolkits/test_dingtalk.py | 168 | {'userid': 'user1', 'name': 'John Doe'}, | CODE |
| LOW⚡ | test/toolkits/test_search_functions.py | 1174 | with patch.dict(os.environ, {'QUERIT_API_KEY': 'fake_key'}): | CODE |
| LOW⚡ | test/toolkits/test_search_functions.py | 1187 | with patch.dict(os.environ, {'QUERIT_API_KEY': 'fake_key'}): | CODE |
| LOW⚡ | test/toolkits/test_search_functions.py | 1370 | with patch.dict(os.environ, {'PERPLEXITY_API_KEY': 'fake_key'}): | CODE |
| LOW | test/toolkits/test_search_functions.py | 1209 | with patch.dict(os.environ, {'QUERIT_API_KEY': 'fake_key'}): | CODE |
| LOW⚡ | test/toolkits/test_dappier_function.py | 56 | author="John Doe", | CODE |
| LOW | test/toolkits/test_dappier_function.py | 93 | "author": "John Doe", | CODE |
| LOW | test/toolkits/test_linkedin_function.py | 26 | LinkedInToolkit, "_get_access_token", lambda self: "fake_token" | CODE |
| LOW⚡ | test/toolkits/test_imap_mail_toolkit.py | 91 | 'test@test.com', 'test_password' | CODE |
| LOW⚡ | test/toolkits/test_imap_mail_toolkit.py | 585 | username="test@test.com", | CODE |
| LOW⚡ | test/toolkits/test_imap_mail_toolkit.py | 601 | username="test@test.com", | CODE |
| LOW | test/toolkits/test_imap_mail_toolkit.py | 35 | 'EMAIL_USERNAME': 'test@test.com', | CODE |
| LOW | test/toolkits/test_imap_mail_toolkit.py | 62 | 'test@test.com', 'test_password' | CODE |
| LOW | test/toolkits/test_imap_mail_toolkit.py | 557 | username="test@test.com", | CODE |
| LOW | test/toolkits/test_imap_mail_toolkit.py | 629 | username="test@test.com", | CODE |
| LOW | test/toolkits/test_gmail_toolkit.py | 561 | 'emailAddress': 'user@example.com', | CODE |
| LOW | test/toolkits/test_gmail_toolkit.py | 570 | assert result['profile']['email_address'] == 'user@example.com' | CODE |
| LOW | test/toolkits/test_gmail_toolkit.py | 585 | 'names': [{'displayName': 'John Doe'}], | CODE |
| LOW | test/toolkits/test_gmail_toolkit.py | 611 | 'names': [{'displayName': 'John Doe'}], | CODE |
| LOW | test/models/test_aws_bedrock_converse_model.py | 35 | api_key="dummy_key", | CODE |
| LOW | test/models/test_aws_bedrock_model.py | 42 | api_key="dummy_key", | CODE |
| LOW | test/models/test_aws_bedrock_model.py | 68 | api_key="dummy_key", | STRING |
| LOW | test/loaders/test_mistral_reader.py | 52 | reader = MistralReader(api_key="dummy_key") | CODE |
| LOW⚡ | test/loaders/test_mistral_reader.py | 71 | reader = MistralReader(api_key="dummy_key") | CODE |
| LOW | test/loaders/test_mistral_reader.py | 99 | reader = MistralReader(api_key="dummy_key") | CODE |
| LOW | test/loaders/test_mistral_reader.py | 134 | reader = MistralReader(api_key="dummy_key") | CODE |
| LOW | test/loaders/test_mistral_reader.py | 162 | reader = MistralReader(api_key="dummy_key") | CODE |
| LOW | camel/toolkits/gmail_toolkit.py | 1201 | - Organization: 'Google' or 'Acme Corp' | CODE |
| LOW | …lkits/hybrid_browser_toolkit/ts/src/browser-session.ts | 1265 | const placeholder = await newElement.getAttribute('placeholder').catch(() => null); | CODE |
| LOW | …lkits/hybrid_browser_toolkit/ts/src/browser-session.ts | 1342 | const placeholder = await newElement.getAttribute('placeholder').catch(() => null); | CODE |
| LOW | camel/models/stub_model.py | 124 | ARBITRARY_STRING = "Lorem Ipsum" | STRING |
| LOW | camel/models/stub_model.py | 161 | ARBITRARY_STRING = "Lorem Ipsum" | STRING |
| LOW | docs/key_modules/browsertoolkit.md | 423 | await toolkit.browser_type(x=400, y=150, text="user@example.com") | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | README.zh.md | 238 | # CAMEL-AI is the first LLM (Large Language Model) multi-agent framework | COMMENT |
| MEDIUM | README.md | 88 | - [Multi-Agent Systems & Applications](#4-multi-agent-systems--applications) | CODE |
| MEDIUM | README.md | 283 | # CAMEL-AI is the first LLM (Large Language Model) multi-agent framework | COMMENT |
| MEDIUM⚡ | test/retrievers/test_vector_retriever.py | 52 | # Test initialization with a custom embedding model | COMMENT |
| MEDIUM⚡ | test/retrievers/test_vector_retriever.py | 59 | # Test initialization with default embedding model | COMMENT |
| MEDIUM⚡ | test/datagen/test_self_improving_cot_pipeline.py | 423 | # Create a mapping from problem text to expected reasoning trace | COMMENT |
| MEDIUM | camel/datasets/self_instruct_generator.py | 250 | # Build the prompt using the few-shot examples | STRING |
| MEDIUM | camel/datasets/self_instruct_generator.py | 286 | # Build few-shot example prompt | STRING |
| MEDIUM | camel/agents/chat_agent.py | 4179 | # This prevents single tool calls from exceeding context window | STRING |
| MEDIUM | camel/agents/chat_agent.py | 5054 | # context window | STRING |
| MEDIUM | camel/agents/chat_agent.py | 5221 | # context window | STRING |
| MEDIUM | camel/utils/constants.py | 33 | # Default top k value for RAG | COMMENT |
| MEDIUM | camel/utils/constants.py | 36 | # Default similarity threshold value for RAG | COMMENT |
| MEDIUM | camel/services/agent_openapi_server.py | 69 | # support future multi-agent and permission control | STRING |
| MEDIUM | docs/get_started/installation.md | 61 | pip install 'camel-ai[rag,web_tools,document_tools]' # Example: RAG system with web search and document process | CODE |
| MEDIUM⚡ | examples/caches/semantic_cache_example.py | 53 | # Step 1: Initialize the embedding model | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | test/utils/test_mcp_client.py | 558 | # Test with comprehensive config | COMMENT |
| MEDIUM | camel/societies/workforce/workforce.py | 6058 | r"""Get comprehensive information about the workforce. | STRING |
| LOW | camel/interpreters/internal_python_interpreter.py | 319 | # Constant -> just return the value | COMMENT |
| MEDIUM | camel/toolkits/openbb_toolkit.py | 500 | r"""Get IPO/SPO calendar with comprehensive filtering options. | STRING |
| MEDIUM | camel/toolkits/file_toolkit.py | 31 | r"""A comprehensive toolkit for file operations including reading, | CODE |
| MEDIUM | camel/toolkits/browser_toolkit_commons.py | 293 | # This is a simplified fix, more robust parsing might be needed | COMMENT |
| MEDIUM | camel/toolkits/weather_toolkit.py | 73 | r"""Fetch and return a comprehensive weather report for a given city | STRING |
| MEDIUM | camel/toolkits/microsoft_outlook_mail_toolkit.py | 227 | """A comprehensive toolkit for Microsoft Outlook Mail operations. | STRING |
| MEDIUM | camel/toolkits/sql_toolkit.py | 595 | r"""Get comprehensive information about table(s) in the database. | STRING |
| MEDIUM | camel/toolkits/gmail_toolkit.py | 39 | r"""A comprehensive toolkit for Gmail operations. | CODE |
| MEDIUM | camel/toolkits/message_agent_toolkit.py | 544 | r"""Get comprehensive status of the message toolkit. | STRING |
| MEDIUM | camel/toolkits/image_analysis_toolkit.py | 35 | r"""A toolkit for comprehensive image analysis and understanding. | CODE |
| MEDIUM | …ts/hybrid_browser_toolkit_py/hybrid_browser_toolkit.py | 1001 | # Create comprehensive output for logging | COMMENT |
| MEDIUM | …ts/hybrid_browser_toolkit_py/hybrid_browser_toolkit.py | 395 | r"""Log action details with comprehensive information.""" | CODE |
| LOW | camel/toolkits/hybrid_browser_toolkit_py/snapshot.py | 81 | # to the previous one we simply return it after the standard | STRING |
| MEDIUM | camel/toolkits/terminal_toolkit/terminal_toolkit.py | 490 | r"""A comprehensive command sanitizer for both local and | STRING |
| MEDIUM | camel/toolkits/terminal_toolkit/utils.py | 231 | r"""A comprehensive command sanitizer for both local and Docker backends. | STRING |
| MEDIUM | camel/toolkits/hybrid_browser_toolkit/ws_wrapper.py | 541 | """Log action details with comprehensive | STRING |
| MEDIUM | camel/utils/context_utils.py | 601 | r"""Collect comprehensive session information including identifiers, | STRING |
| LOW | camel/models/stub_model.py | 56 | # For stub models, just return a list of 0s with length proportional | STRING |
| MEDIUM | camel/personas/persona_hub.py | 182 | # Structured output (TODO: Use a more robust parser) | STRING |
| MEDIUM | examples/workforce/eigent.py | 1090 | "### Note-Taking: You have access to comprehensive note-taking tools " | STRING |
| MEDIUM⚡ | examples/toolkits/file_toolkit.py | 140 | Tool calls: [ToolCallingRecord(tool_name='write_to_file', args={'content': "# Basics of Machine Learning\n\nMachine Lear | STRING |
| MEDIUM | examples/toolkits/sql_toolkit.py | 376 | # Method 3: Get comprehensive info for a specific table | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | test/services/test_agent_openapi_server.py | 119 | # Step 1: Init | STRING |
| LOW | test/services/test_agent_openapi_server.py | 132 | # Step 2: Async step with tool | STRING |
| LOW | camel/societies/workforce/workforce.py | 4401 | # Step 1: Identify and assign any new tasks in the pending queue | COMMENT |
| LOW | camel/societies/workforce/workforce.py | 4457 | # Step 2: Iterate through all pending tasks and post those that are | COMMENT |
| LOW | camel/societies/workforce/workforce.py | 4633 | # Step 3: Remove the posted tasks from the pending list | COMMENT |
| LOW | …ts/hybrid_browser_toolkit/hybrid_browser_toolkit_ts.py | 1798 | # Step 1: Setup copy interception with multiple captures | STRING |
| LOW | …lkits/hybrid_browser_toolkit/ts/src/browser-session.ts | 1210 | // Step 1: Try to find input elements within the clicked element | COMMENT |
| LOW | …lkits/hybrid_browser_toolkit/ts/src/browser-session.ts | 1237 | // Step 2: Look for new elements that appeared after the action | COMMENT |
| LOW | examples/storages/nebular_graph.py | 24 | # Step 2: Initialize the NebulaGraph client | COMMENT |
| LOW⚡ | examples/models/ppio_model_example.py | 102 | ### Step 1: Set up the divisibility condition | STRING |
| LOW⚡ | examples/models/ppio_model_example.py | 108 | ### Step 2: Perform polynomial division or find a relationship | STRING |
| LOW | examples/models/ppio_model_example.py | 119 | ### Step 3: Find all divisors of 56 | STRING |
| LOW⚡ | examples/models/ppio_model_example.py | 130 | ### Step 4: Solve for $ b $ | STRING |
| LOW⚡ | examples/models/ppio_model_example.py | 140 | ### Step 5: Verify the solutions | STRING |
| LOW | examples/models/ppio_model_example.py | 152 | ### Step 6: Sum the valid bases | STRING |
| LOW⚡ | examples/services/agent_openapi_server.py | 341 | # Step 1: Create two agents | STRING |
| LOW⚡ | examples/services/agent_openapi_server.py | 352 | # Step 2: List current agents | STRING |
| LOW⚡ | examples/services/agent_openapi_server.py | 356 | # Step 3: Delete agent_1 | STRING |
| LOW⚡ | examples/services/agent_openapi_server.py | 360 | # Step 4: List agents again | STRING |
| LOW⚡ | examples/caches/semantic_cache_example.py | 53 | # Step 1: Initialize the embedding model | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 68 | # Step 2: Initialize vector storage (in-memory FAISS) | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 76 | # Step 3: Create the semantic cache | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 85 | # Step 4: Populate the cache with some responses | COMMENT |
| LOW | examples/caches/semantic_cache_example.py | 124 | # Step 5: Test cache lookups with similar queries | COMMENT |
| LOW | examples/caches/semantic_cache_example.py | 155 | # Step 6: Demonstrate deduplication (Replacement) | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 170 | # Step 7: Show cache statistics | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 178 | # Step 8: Demonstrate find_similar | COMMENT |
| LOW⚡ | examples/caches/semantic_cache_example.py | 188 | # Step 9: Demonstrate cache management | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | camel/toolkits/mcp_toolkit.py | 259 | # Don't forget to disconnect when done! | COMMENT |
| LOW | camel/toolkits/mcp_toolkit.py | 270 | # Don't forget to disconnect when done! | COMMENT |
| MEDIUM | examples/translation/translator.py | 155 | # Default to Arabic, you can change to any other language | COMMENT |
| MEDIUM | examples/runtimes/docker_runtime.py | 56 | # you can also use the runtime without the with statement | COMMENT |
| MEDIUM⚡ | examples/toolkits/file_toolkit.py | 140 | Tool calls: [ToolCallingRecord(tool_name='write_to_file', args={'content': "# Basics of Machine Learning\n\nMachine Lear | STRING |
| MEDIUM | examples/toolkits/context_summarizer_toolkit.py | 105 | enhanced by the seasonal beauty of cherry blossoms. Let me know if you need | STRING |
| MEDIUM | examples/toolkits/synthesize_function_execution.py | 90 | It seems that I'm unable to access the movie data at the moment due to a | CODE |
| LOW | examples/toolkits/google_calendar_toolkit.py | 15 | # To use GoogleCalendarToolkit make sure to set required environment variables: | COMMENT |
| MEDIUM | examples/models/nvidia_model_example.py | 44 | **Please note that this is a simplified example and should not be used for | STRING |
| MEDIUM | examples/benchmarks/apibank.py | 46 | # The following steps are only for demonstration purposes, | COMMENT |
| MEDIUM | examples/benchmarks/nexus.py | 33 | # Please note that the following step is only for demonstration purposes, | 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 |
|---|---|---|---|---|
| LOW | test/agents/test_repo_agent.py | 79 | self.decoded_content = b"def test_function():\n return 'test'" | CODE |
| LOW | test/agents/test_repo_agent.py | 89 | "text": "def test_function():\n return 'test'", | CODE |
| LOW | test/agents/test_repo_agent.py | 152 | content="def test_function():\n return 'test'", | CODE |
| LOW | test/agents/test_repo_agent.py | 170 | == "def test_function():\n return 'test'" | CODE |
| LOW | test/agents/test_repo_agent.py | 196 | content="def test_function():\n return 'test'", | CODE |
| LOW | test/agents/test_repo_agent.py | 224 | content="def test_function():\n return 'test'", | CODE |
| LOW | test/agents/test_repo_agent.py | 238 | assert "def test_function():" in agent.full_text | CODE |
| LOW | test/agents/test_repo_agent.py | 255 | content="def test_function():\n return 'test'", | CODE |
| LOW⚡ | test/agents/test_repo_agent.py | 279 | "text": "def test_function():\n return 'test'", | CODE |
| LOW⚡ | test/agents/test_repo_agent.py | 285 | return_value="def test_function():\n return 'test'" | CODE |
| LOW | test/agents/test_repo_agent.py | 303 | assert "def test_function():" in call_args.content | CODE |
| LOW⚡ | test/prompts/test_prompt_base.py | 25 | def my_function(): | CODE |
| LOW⚡ | test/prompts/test_prompt_base.py | 35 | def my_function(): | CODE |
| LOW | test/prompts/test_prompt_base.py | 52 | def my_function(self): | CODE |
| LOW | camel/bots/slack/slack_app.py | 166 | async def handle_request( | STRING |
| LOW | camel/utils/commons.py | 1023 | ... def my_function(): | CODE |
| LOW | camel/utils/commons.py | 1030 | ... def my_method(self): | CODE |
| LOW | examples/usecases/chat_with_github/demo_git_ingest.py | 77 | async def run_task(): | STRING |
| LOW | examples/usecases/airbnb_mcp/app.py | 100 | async def run_task(): | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | test/utils/test_mcp_client.py | 638 | CODE | |
| MEDIUM | test/utils/test_mcp_client.py | 663 | CODE | |
| MEDIUM | camel/agents/chat_agent.py | 5019 | CODE | |
| MEDIUM | camel/agents/chat_agent.py | 6031 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | examples/conversion.py | 44 | # Example usage | COMMENT |
| LOW | examples/tasks/multi_modal_task_generation.py | 83 | # Example usage | COMMENT |
| LOW | …example/.camel/skills/data-analyzer/scripts/analyze.py | 18 | # Example usage | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | examples/toolkits/mineru_toolkit.py | 56 | # TODO: implement this example with loader toolkit to get information from | COMMENT |